feat: 添加regex模块

添加pcre2模块
添加regex模块(依赖pcre2)

CMakeLists.txt

@@ -15,6 +15,7 @@ ENDIF()
 
 IF(MSVC)
     SET(CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS TRUE)
+    SET(CMAKE_GNUtoMS TRUE)
     MESSAGE("Build with MSVC")
 ELSE()
     ADD_COMPILE_OPTIONS(-fPIC)  # 启用fPIC参数

include/aFun.h

@@ -11,6 +11,7 @@
 #include "run.h"
 #include "gc.h"
 #include "magic_func.h"
+#include "regex.h"
 
 // Init系列函数
 void aFunInit(void);

include/regex.h

@@ -0,0 +1,13 @@
+#ifndef AFUN_REGEX_H_PUBLIC
+#define AFUN_REGEX_H_PUBLIC
+
+#define REGEX_ERROR_SIZE (512)
+
+typedef struct af_Regex af_Regex;
+extern char regex_error[REGEX_ERROR_SIZE];
+
+af_Regex *makeRegex(char *pattern);
+void freeRegex(af_Regex *rg);
+int matchRegex(char *subject, af_Regex *rg);
+
+#endif //AFUN_REGEX_H_PUBLIC

src/CMakeLists.txt

@@ -5,8 +5,9 @@ ENDIF()
 
 ADD_SUBDIRECTORY(tool)
 ADD_SUBDIRECTORY(cjson)
+ADD_SUBDIRECTORY(regex)
 
-SET(libary af_tool af_json)
+SET(libary af_tool af_json  af_regex)
 
 ADD_SUBDIRECTORY(core)
 

src/regex/CMakeLists.txt

@@ -0,0 +1,22 @@
+CMAKE_MINIMUM_REQUIRED(VERSION 3.16)
+SET(CMAKE_C_STANDARD 11)
+
+PROJECT(af_regex LANGUAGES C)
+
+# 在msvc编译PCRE2时, 会遇到`extern char *sys_errlist[];`的相关代码引发错误
+# 使用HAVE_STRERROR不编译该部分代码
+# 该部分出错代码用于实现GNU的`strerror(int n)`函数
+
+
+SET(PCRE2_SHOW_REPORT OFF)
+SET(PCRE2_BUILD_TEST OFF)
+SET(BUILD_SHARED_LIBS ON)
+SET(CMAKE_INSTALL_LIBDIR  ${LIBRARY_OUTPUT_PATH})
+ADD_DEFINITIONS(-DHAVE_STRERROR=1)
+ADD_SUBDIRECTORY(pcre2)
+
+ADD_LIBRARY(af_regex regex.c)
+SET_TARGET_PROPERTIES(af_regex PROPERTIES OUTPUT_NAME "afRegex")
+TARGET_LINK_LIBRARIES(af_regex af_tool pcre2-8)
+
+INSTALL(TARGETS af_regex pcre2-8)

src/regex/__regex.h

@@ -0,0 +1,10 @@
+#ifndef AFUN_REGEX_H
+#define AFUN_REGEX_H
+#include "regex.h"
+
+struct af_Regex {
+    pcre2_code *re;  // 正则表达式
+    char *pattern;  // 正则表达式的字符串
+};
+
+#endif //AFUN_REGEX_H

src/regex/config.h

@@ -0,0 +1,58 @@
+/* config.h for CMake builds */
+
+/* #undef HAVE_ATTRIBUTE_UNINITIALIZED */
+/* #undef HAVE_DIRENT_H */
+/* #undef HAVE_INTTYPES_H */
+/* #undef HAVE_STDINT_H */
+/* #undef HAVE_STRERROR */
+/* #undef HAVE_SYS_STAT_H */
+/* #undef HAVE_SYS_TYPES_H */
+/* #undef HAVE_UNISTD_H */
+/* #undef HAVE_WINDOWS_H */
+
+/* #undef HAVE_BCOPY */
+/* #undef HAVE_MEMFD_CREATE */
+/* #undef HAVE_MEMMOVE */
+/* #undef HAVE_SECURE_GETENV */
+/* #undef HAVE_STRERROR */
+
+/* #undef PCRE2_STATIC */
+
+#define SUPPORT_PCRE2_8 1
+/* #undef SUPPORT_PCRE2_16 */
+/* #undef SUPPORT_PCRE2_32 */
+/* #undef PCRE2_DEBUG */
+/* #undef DISABLE_PERCENT_ZT */
+
+/* #undef SUPPORT_LIBBZ2 */
+/* #undef SUPPORT_LIBEDIT */
+/* #undef SUPPORT_LIBREADLINE */
+/* #undef SUPPORT_LIBZ */
+
+/* #undef SUPPORT_JIT */
+/* #undef SLJIT_PROT_EXECUTABLE_ALLOCATOR */
+#define SUPPORT_PCRE2GREP_JIT 1
+#define SUPPORT_PCRE2GREP_CALLOUT 1
+#define SUPPORT_PCRE2GREP_CALLOUT_FORK 1
+#define SUPPORT_UNICODE 1
+/* #undef SUPPORT_VALGRIND */
+
+/* #undef BSR_ANYCRLF */
+/* #undef EBCDIC */
+/* #undef EBCDIC_NL25 */
+/* #undef HEAP_MATCH_RECURSE */
+/* #undef NEVER_BACKSLASH_C */
+
+#define LINK_SIZE		2
+#define HEAP_LIMIT              20000000
+#define MATCH_LIMIT		10000000
+#define MATCH_LIMIT_DEPTH	MATCH_LIMIT
+#define NEWLINE_DEFAULT         2
+#define PARENS_NEST_LIMIT       250
+#define PCRE2GREP_BUFSIZE       20480
+#define PCRE2GREP_MAX_BUFSIZE   1048576
+
+#define MAX_NAME_SIZE	32
+#define MAX_NAME_COUNT	10000
+
+/* end config.h for CMake builds */

src/regex/pcre2.h

@@ -0,0 +1,991 @@
+/*************************************************
+*       Perl-Compatible Regular Expressions      *
+*************************************************/
+
+/* This is the public header file for the PCRE library, second API, to be
+#included by applications that call PCRE2 functions.
+
+           Copyright (c) 2016-2020 University of Cambridge
+
+-----------------------------------------------------------------------------
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+    * Redistributions of source code must retain the above copyright notice,
+      this list of conditions and the following disclaimer.
+
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in the
+      documentation and/or other materials provided with the distribution.
+
+    * Neither the name of the University of Cambridge nor the names of its
+      contributors may be used to endorse or promote products derived from
+      this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE.
+-----------------------------------------------------------------------------
+*/
+
+#ifndef PCRE2_H_IDEMPOTENT_GUARD
+#define PCRE2_H_IDEMPOTENT_GUARD
+
+/* The current PCRE version information. */
+
+#define PCRE2_MAJOR           10
+#define PCRE2_MINOR           37
+#define PCRE2_PRERELEASE      
+#define PCRE2_DATE            2021-05-26
+
+/* When an application links to a PCRE DLL in Windows, the symbols that are
+imported have to be identified as such. When building PCRE2, the appropriate
+export setting is defined in pcre2_internal.h, which includes this file. So we
+don't change existing definitions of PCRE2_EXP_DECL. */
+
+#if defined(_WIN32) && !defined(PCRE2_STATIC)
+#  ifndef PCRE2_EXP_DECL
+#    define PCRE2_EXP_DECL  extern __declspec(dllimport)
+#  endif
+#endif
+
+/* By default, we use the standard "extern" declarations. */
+
+#ifndef PCRE2_EXP_DECL
+#  ifdef __cplusplus
+#    define PCRE2_EXP_DECL  extern "C"
+#  else
+#    define PCRE2_EXP_DECL  extern
+#  endif
+#endif
+
+/* When compiling with the MSVC compiler, it is sometimes necessary to include
+a "calling convention" before exported function names. (This is secondhand
+information; I know nothing about MSVC myself). For example, something like
+
+  void __cdecl function(....)
+
+might be needed. In order so make this easy, all the exported functions have
+PCRE2_CALL_CONVENTION just before their names. It is rarely needed; if not
+set, we ensure here that it has no effect. */
+
+#ifndef PCRE2_CALL_CONVENTION
+#define PCRE2_CALL_CONVENTION
+#endif
+
+/* Have to include limits.h, stdlib.h, and inttypes.h to ensure that size_t and
+uint8_t, UCHAR_MAX, etc are defined. Some systems that do have inttypes.h do
+not have stdint.h, which is why we use inttypes.h, which according to the C
+standard is a superset of stdint.h. If none of these headers are available,
+the relevant values must be provided by some other means. */
+
+#include <limits.h>
+#include <stdlib.h>
+#include <inttypes.h>
+
+/* Allow for C++ users compiling this directly. */
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* The following option bits can be passed to pcre2_compile(), pcre2_match(),
+or pcre2_dfa_match(). PCRE2_NO_UTF_CHECK affects only the function to which it
+is passed. Put these bits at the most significant end of the options word so
+others can be added next to them */
+
+#define PCRE2_ANCHORED            0x80000000u
+#define PCRE2_NO_UTF_CHECK        0x40000000u
+#define PCRE2_ENDANCHORED         0x20000000u
+
+/* The following option bits can be passed only to pcre2_compile(). However,
+they may affect compilation, JIT compilation, and/or interpretive execution.
+The following tags indicate which:
+
+C   alters what is compiled by pcre2_compile()
+J   alters what is compiled by pcre2_jit_compile()
+M   is inspected during pcre2_match() execution
+D   is inspected during pcre2_dfa_match() execution
+*/
+
+#define PCRE2_ALLOW_EMPTY_CLASS   0x00000001u  /* C       */
+#define PCRE2_ALT_BSUX            0x00000002u  /* C       */
+#define PCRE2_AUTO_CALLOUT        0x00000004u  /* C       */
+#define PCRE2_CASELESS            0x00000008u  /* C       */
+#define PCRE2_DOLLAR_ENDONLY      0x00000010u  /*   J M D */
+#define PCRE2_DOTALL              0x00000020u  /* C       */
+#define PCRE2_DUPNAMES            0x00000040u  /* C       */
+#define PCRE2_EXTENDED            0x00000080u  /* C       */
+#define PCRE2_FIRSTLINE           0x00000100u  /*   J M D */
+#define PCRE2_MATCH_UNSET_BACKREF 0x00000200u  /* C J M   */
+#define PCRE2_MULTILINE           0x00000400u  /* C       */
+#define PCRE2_NEVER_UCP           0x00000800u  /* C       */
+#define PCRE2_NEVER_UTF           0x00001000u  /* C       */
+#define PCRE2_NO_AUTO_CAPTURE     0x00002000u  /* C       */
+#define PCRE2_NO_AUTO_POSSESS     0x00004000u  /* C       */
+#define PCRE2_NO_DOTSTAR_ANCHOR   0x00008000u  /* C       */
+#define PCRE2_NO_START_OPTIMIZE   0x00010000u  /*   J M D */
+#define PCRE2_UCP                 0x00020000u  /* C J M D */
+#define PCRE2_UNGREEDY            0x00040000u  /* C       */
+#define PCRE2_UTF                 0x00080000u  /* C J M D */
+#define PCRE2_NEVER_BACKSLASH_C   0x00100000u  /* C       */
+#define PCRE2_ALT_CIRCUMFLEX      0x00200000u  /*   J M D */
+#define PCRE2_ALT_VERBNAMES       0x00400000u  /* C       */
+#define PCRE2_USE_OFFSET_LIMIT    0x00800000u  /*   J M D */
+#define PCRE2_EXTENDED_MORE       0x01000000u  /* C       */
+#define PCRE2_LITERAL             0x02000000u  /* C       */
+#define PCRE2_MATCH_INVALID_UTF   0x04000000u  /*   J M D */
+
+/* An additional compile options word is available in the compile context. */
+
+#define PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES  0x00000001u  /* C */
+#define PCRE2_EXTRA_BAD_ESCAPE_IS_LITERAL    0x00000002u  /* C */
+#define PCRE2_EXTRA_MATCH_WORD               0x00000004u  /* C */
+#define PCRE2_EXTRA_MATCH_LINE               0x00000008u  /* C */
+#define PCRE2_EXTRA_ESCAPED_CR_IS_LF         0x00000010u  /* C */
+#define PCRE2_EXTRA_ALT_BSUX                 0x00000020u  /* C */
+
+/* These are for pcre2_jit_compile(). */
+
+#define PCRE2_JIT_COMPLETE        0x00000001u  /* For full matching */
+#define PCRE2_JIT_PARTIAL_SOFT    0x00000002u
+#define PCRE2_JIT_PARTIAL_HARD    0x00000004u
+#define PCRE2_JIT_INVALID_UTF     0x00000100u
+
+/* These are for pcre2_match(), pcre2_dfa_match(), pcre2_jit_match(), and
+pcre2_substitute(). Some are allowed only for one of the functions, and in
+these cases it is noted below. Note that PCRE2_ANCHORED, PCRE2_ENDANCHORED and
+PCRE2_NO_UTF_CHECK can also be passed to these functions (though
+pcre2_jit_match() ignores the latter since it bypasses all sanity checks). */
+
+#define PCRE2_NOTBOL                      0x00000001u
+#define PCRE2_NOTEOL                      0x00000002u
+#define PCRE2_NOTEMPTY                    0x00000004u  /* ) These two must be kept */
+#define PCRE2_NOTEMPTY_ATSTART            0x00000008u  /* ) adjacent to each other. */
+#define PCRE2_PARTIAL_SOFT                0x00000010u
+#define PCRE2_PARTIAL_HARD                0x00000020u
+#define PCRE2_DFA_RESTART                 0x00000040u  /* pcre2_dfa_match() only */
+#define PCRE2_DFA_SHORTEST                0x00000080u  /* pcre2_dfa_match() only */
+#define PCRE2_SUBSTITUTE_GLOBAL           0x00000100u  /* pcre2_substitute() only */
+#define PCRE2_SUBSTITUTE_EXTENDED         0x00000200u  /* pcre2_substitute() only */
+#define PCRE2_SUBSTITUTE_UNSET_EMPTY      0x00000400u  /* pcre2_substitute() only */
+#define PCRE2_SUBSTITUTE_UNKNOWN_UNSET    0x00000800u  /* pcre2_substitute() only */
+#define PCRE2_SUBSTITUTE_OVERFLOW_LENGTH  0x00001000u  /* pcre2_substitute() only */
+#define PCRE2_NO_JIT                      0x00002000u  /* Not for pcre2_dfa_match() */
+#define PCRE2_COPY_MATCHED_SUBJECT        0x00004000u
+#define PCRE2_SUBSTITUTE_LITERAL          0x00008000u  /* pcre2_substitute() only */
+#define PCRE2_SUBSTITUTE_MATCHED          0x00010000u  /* pcre2_substitute() only */
+#define PCRE2_SUBSTITUTE_REPLACEMENT_ONLY 0x00020000u  /* pcre2_substitute() only */
+
+/* Options for pcre2_pattern_convert(). */
+
+#define PCRE2_CONVERT_UTF                    0x00000001u
+#define PCRE2_CONVERT_NO_UTF_CHECK           0x00000002u
+#define PCRE2_CONVERT_POSIX_BASIC            0x00000004u
+#define PCRE2_CONVERT_POSIX_EXTENDED         0x00000008u
+#define PCRE2_CONVERT_GLOB                   0x00000010u
+#define PCRE2_CONVERT_GLOB_NO_WILD_SEPARATOR 0x00000030u
+#define PCRE2_CONVERT_GLOB_NO_STARSTAR       0x00000050u
+
+/* Newline and \R settings, for use in compile contexts. The newline values
+must be kept in step with values set in config.h and both sets must all be
+greater than zero. */
+
+#define PCRE2_NEWLINE_CR          1
+#define PCRE2_NEWLINE_LF          2
+#define PCRE2_NEWLINE_CRLF        3
+#define PCRE2_NEWLINE_ANY         4
+#define PCRE2_NEWLINE_ANYCRLF     5
+#define PCRE2_NEWLINE_NUL         6
+
+#define PCRE2_BSR_UNICODE         1
+#define PCRE2_BSR_ANYCRLF         2
+
+/* Error codes for pcre2_compile(). Some of these are also used by
+pcre2_pattern_convert(). */
+
+#define PCRE2_ERROR_END_BACKSLASH                  101
+#define PCRE2_ERROR_END_BACKSLASH_C                102
+#define PCRE2_ERROR_UNKNOWN_ESCAPE                 103
+#define PCRE2_ERROR_QUANTIFIER_OUT_OF_ORDER        104
+#define PCRE2_ERROR_QUANTIFIER_TOO_BIG             105
+#define PCRE2_ERROR_MISSING_SQUARE_BRACKET         106
+#define PCRE2_ERROR_ESCAPE_INVALID_IN_CLASS        107
+#define PCRE2_ERROR_CLASS_RANGE_ORDER              108
+#define PCRE2_ERROR_QUANTIFIER_INVALID             109
+#define PCRE2_ERROR_INTERNAL_UNEXPECTED_REPEAT     110
+#define PCRE2_ERROR_INVALID_AFTER_PARENS_QUERY     111
+#define PCRE2_ERROR_POSIX_CLASS_NOT_IN_CLASS       112
+#define PCRE2_ERROR_POSIX_NO_SUPPORT_COLLATING     113
+#define PCRE2_ERROR_MISSING_CLOSING_PARENTHESIS    114
+#define PCRE2_ERROR_BAD_SUBPATTERN_REFERENCE       115
+#define PCRE2_ERROR_NULL_PATTERN                   116
+#define PCRE2_ERROR_BAD_OPTIONS                    117
+#define PCRE2_ERROR_MISSING_COMMENT_CLOSING        118
+#define PCRE2_ERROR_PARENTHESES_NEST_TOO_DEEP      119
+#define PCRE2_ERROR_PATTERN_TOO_LARGE              120
+#define PCRE2_ERROR_HEAP_FAILED                    121
+#define PCRE2_ERROR_UNMATCHED_CLOSING_PARENTHESIS  122
+#define PCRE2_ERROR_INTERNAL_CODE_OVERFLOW         123
+#define PCRE2_ERROR_MISSING_CONDITION_CLOSING      124
+#define PCRE2_ERROR_LOOKBEHIND_NOT_FIXED_LENGTH    125
+#define PCRE2_ERROR_ZERO_RELATIVE_REFERENCE        126
+#define PCRE2_ERROR_TOO_MANY_CONDITION_BRANCHES    127
+#define PCRE2_ERROR_CONDITION_ASSERTION_EXPECTED   128
+#define PCRE2_ERROR_BAD_RELATIVE_REFERENCE         129
+#define PCRE2_ERROR_UNKNOWN_POSIX_CLASS            130
+#define PCRE2_ERROR_INTERNAL_STUDY_ERROR           131
+#define PCRE2_ERROR_UNICODE_NOT_SUPPORTED          132
+#define PCRE2_ERROR_PARENTHESES_STACK_CHECK        133
+#define PCRE2_ERROR_CODE_POINT_TOO_BIG             134
+#define PCRE2_ERROR_LOOKBEHIND_TOO_COMPLICATED     135
+#define PCRE2_ERROR_LOOKBEHIND_INVALID_BACKSLASH_C 136
+#define PCRE2_ERROR_UNSUPPORTED_ESCAPE_SEQUENCE    137
+#define PCRE2_ERROR_CALLOUT_NUMBER_TOO_BIG         138
+#define PCRE2_ERROR_MISSING_CALLOUT_CLOSING        139
+#define PCRE2_ERROR_ESCAPE_INVALID_IN_VERB         140
+#define PCRE2_ERROR_UNRECOGNIZED_AFTER_QUERY_P     141
+#define PCRE2_ERROR_MISSING_NAME_TERMINATOR        142
+#define PCRE2_ERROR_DUPLICATE_SUBPATTERN_NAME      143
+#define PCRE2_ERROR_INVALID_SUBPATTERN_NAME        144
+#define PCRE2_ERROR_UNICODE_PROPERTIES_UNAVAILABLE 145
+#define PCRE2_ERROR_MALFORMED_UNICODE_PROPERTY     146
+#define PCRE2_ERROR_UNKNOWN_UNICODE_PROPERTY       147
+#define PCRE2_ERROR_SUBPATTERN_NAME_TOO_LONG       148
+#define PCRE2_ERROR_TOO_MANY_NAMED_SUBPATTERNS     149
+#define PCRE2_ERROR_CLASS_INVALID_RANGE            150
+#define PCRE2_ERROR_OCTAL_BYTE_TOO_BIG             151
+#define PCRE2_ERROR_INTERNAL_OVERRAN_WORKSPACE     152
+#define PCRE2_ERROR_INTERNAL_MISSING_SUBPATTERN    153
+#define PCRE2_ERROR_DEFINE_TOO_MANY_BRANCHES       154
+#define PCRE2_ERROR_BACKSLASH_O_MISSING_BRACE      155
+#define PCRE2_ERROR_INTERNAL_UNKNOWN_NEWLINE       156
+#define PCRE2_ERROR_BACKSLASH_G_SYNTAX             157
+#define PCRE2_ERROR_PARENS_QUERY_R_MISSING_CLOSING 158
+/* Error 159 is obsolete and should now never occur */
+#define PCRE2_ERROR_VERB_ARGUMENT_NOT_ALLOWED      159
+#define PCRE2_ERROR_VERB_UNKNOWN                   160
+#define PCRE2_ERROR_SUBPATTERN_NUMBER_TOO_BIG      161
+#define PCRE2_ERROR_SUBPATTERN_NAME_EXPECTED       162
+#define PCRE2_ERROR_INTERNAL_PARSED_OVERFLOW       163
+#define PCRE2_ERROR_INVALID_OCTAL                  164
+#define PCRE2_ERROR_SUBPATTERN_NAMES_MISMATCH      165
+#define PCRE2_ERROR_MARK_MISSING_ARGUMENT          166
+#define PCRE2_ERROR_INVALID_HEXADECIMAL            167
+#define PCRE2_ERROR_BACKSLASH_C_SYNTAX             168
+#define PCRE2_ERROR_BACKSLASH_K_SYNTAX             169
+#define PCRE2_ERROR_INTERNAL_BAD_CODE_LOOKBEHINDS  170
+#define PCRE2_ERROR_BACKSLASH_N_IN_CLASS           171
+#define PCRE2_ERROR_CALLOUT_STRING_TOO_LONG        172
+#define PCRE2_ERROR_UNICODE_DISALLOWED_CODE_POINT  173
+#define PCRE2_ERROR_UTF_IS_DISABLED                174
+#define PCRE2_ERROR_UCP_IS_DISABLED                175
+#define PCRE2_ERROR_VERB_NAME_TOO_LONG             176
+#define PCRE2_ERROR_BACKSLASH_U_CODE_POINT_TOO_BIG 177
+#define PCRE2_ERROR_MISSING_OCTAL_OR_HEX_DIGITS    178
+#define PCRE2_ERROR_VERSION_CONDITION_SYNTAX       179
+#define PCRE2_ERROR_INTERNAL_BAD_CODE_AUTO_POSSESS 180
+#define PCRE2_ERROR_CALLOUT_NO_STRING_DELIMITER    181
+#define PCRE2_ERROR_CALLOUT_BAD_STRING_DELIMITER   182
+#define PCRE2_ERROR_BACKSLASH_C_CALLER_DISABLED    183
+#define PCRE2_ERROR_QUERY_BARJX_NEST_TOO_DEEP      184
+#define PCRE2_ERROR_BACKSLASH_C_LIBRARY_DISABLED   185
+#define PCRE2_ERROR_PATTERN_TOO_COMPLICATED        186
+#define PCRE2_ERROR_LOOKBEHIND_TOO_LONG            187
+#define PCRE2_ERROR_PATTERN_STRING_TOO_LONG        188
+#define PCRE2_ERROR_INTERNAL_BAD_CODE              189
+#define PCRE2_ERROR_INTERNAL_BAD_CODE_IN_SKIP      190
+#define PCRE2_ERROR_NO_SURROGATES_IN_UTF16         191
+#define PCRE2_ERROR_BAD_LITERAL_OPTIONS            192
+#define PCRE2_ERROR_SUPPORTED_ONLY_IN_UNICODE      193
+#define PCRE2_ERROR_INVALID_HYPHEN_IN_OPTIONS      194
+#define PCRE2_ERROR_ALPHA_ASSERTION_UNKNOWN        195
+#define PCRE2_ERROR_SCRIPT_RUN_NOT_AVAILABLE       196
+#define PCRE2_ERROR_TOO_MANY_CAPTURES              197
+#define PCRE2_ERROR_CONDITION_ATOMIC_ASSERTION_EXPECTED  198
+
+
+/* "Expected" matching error codes: no match and partial match. */
+
+#define PCRE2_ERROR_NOMATCH          (-1)
+#define PCRE2_ERROR_PARTIAL          (-2)
+
+/* Error codes for UTF-8 validity checks */
+
+#define PCRE2_ERROR_UTF8_ERR1        (-3)
+#define PCRE2_ERROR_UTF8_ERR2        (-4)
+#define PCRE2_ERROR_UTF8_ERR3        (-5)
+#define PCRE2_ERROR_UTF8_ERR4        (-6)
+#define PCRE2_ERROR_UTF8_ERR5        (-7)
+#define PCRE2_ERROR_UTF8_ERR6        (-8)
+#define PCRE2_ERROR_UTF8_ERR7        (-9)
+#define PCRE2_ERROR_UTF8_ERR8       (-10)
+#define PCRE2_ERROR_UTF8_ERR9       (-11)
+#define PCRE2_ERROR_UTF8_ERR10      (-12)
+#define PCRE2_ERROR_UTF8_ERR11      (-13)
+#define PCRE2_ERROR_UTF8_ERR12      (-14)
+#define PCRE2_ERROR_UTF8_ERR13      (-15)
+#define PCRE2_ERROR_UTF8_ERR14      (-16)
+#define PCRE2_ERROR_UTF8_ERR15      (-17)
+#define PCRE2_ERROR_UTF8_ERR16      (-18)
+#define PCRE2_ERROR_UTF8_ERR17      (-19)
+#define PCRE2_ERROR_UTF8_ERR18      (-20)
+#define PCRE2_ERROR_UTF8_ERR19      (-21)
+#define PCRE2_ERROR_UTF8_ERR20      (-22)
+#define PCRE2_ERROR_UTF8_ERR21      (-23)
+
+/* Error codes for UTF-16 validity checks */
+
+#define PCRE2_ERROR_UTF16_ERR1      (-24)
+#define PCRE2_ERROR_UTF16_ERR2      (-25)
+#define PCRE2_ERROR_UTF16_ERR3      (-26)
+
+/* Error codes for UTF-32 validity checks */
+
+#define PCRE2_ERROR_UTF32_ERR1      (-27)
+#define PCRE2_ERROR_UTF32_ERR2      (-28)
+
+/* Miscellaneous error codes for pcre2[_dfa]_match(), substring extraction
+functions, context functions, and serializing functions. They are in numerical
+order. Originally they were in alphabetical order too, but now that PCRE2 is
+released, the numbers must not be changed. */
+
+#define PCRE2_ERROR_BADDATA           (-29)
+#define PCRE2_ERROR_MIXEDTABLES       (-30)  /* Name was changed */
+#define PCRE2_ERROR_BADMAGIC          (-31)
+#define PCRE2_ERROR_BADMODE           (-32)
+#define PCRE2_ERROR_BADOFFSET         (-33)
+#define PCRE2_ERROR_BADOPTION         (-34)
+#define PCRE2_ERROR_BADREPLACEMENT    (-35)
+#define PCRE2_ERROR_BADUTFOFFSET      (-36)
+#define PCRE2_ERROR_CALLOUT           (-37)  /* Never used by PCRE2 itself */
+#define PCRE2_ERROR_DFA_BADRESTART    (-38)
+#define PCRE2_ERROR_DFA_RECURSE       (-39)
+#define PCRE2_ERROR_DFA_UCOND         (-40)
+#define PCRE2_ERROR_DFA_UFUNC         (-41)
+#define PCRE2_ERROR_DFA_UITEM         (-42)
+#define PCRE2_ERROR_DFA_WSSIZE        (-43)
+#define PCRE2_ERROR_INTERNAL          (-44)
+#define PCRE2_ERROR_JIT_BADOPTION     (-45)
+#define PCRE2_ERROR_JIT_STACKLIMIT    (-46)
+#define PCRE2_ERROR_MATCHLIMIT        (-47)
+#define PCRE2_ERROR_NOMEMORY          (-48)
+#define PCRE2_ERROR_NOSUBSTRING       (-49)
+#define PCRE2_ERROR_NOUNIQUESUBSTRING (-50)
+#define PCRE2_ERROR_NULL              (-51)
+#define PCRE2_ERROR_RECURSELOOP       (-52)
+#define PCRE2_ERROR_DEPTHLIMIT        (-53)
+#define PCRE2_ERROR_RECURSIONLIMIT    (-53)  /* Obsolete synonym */
+#define PCRE2_ERROR_UNAVAILABLE       (-54)
+#define PCRE2_ERROR_UNSET             (-55)
+#define PCRE2_ERROR_BADOFFSETLIMIT    (-56)
+#define PCRE2_ERROR_BADREPESCAPE      (-57)
+#define PCRE2_ERROR_REPMISSINGBRACE   (-58)
+#define PCRE2_ERROR_BADSUBSTITUTION   (-59)
+#define PCRE2_ERROR_BADSUBSPATTERN    (-60)
+#define PCRE2_ERROR_TOOMANYREPLACE    (-61)
+#define PCRE2_ERROR_BADSERIALIZEDDATA (-62)
+#define PCRE2_ERROR_HEAPLIMIT         (-63)
+#define PCRE2_ERROR_CONVERT_SYNTAX    (-64)
+#define PCRE2_ERROR_INTERNAL_DUPMATCH (-65)
+#define PCRE2_ERROR_DFA_UINVALID_UTF  (-66)
+
+
+/* Request types for pcre2_pattern_info() */
+
+#define PCRE2_INFO_ALLOPTIONS            0
+#define PCRE2_INFO_ARGOPTIONS            1
+#define PCRE2_INFO_BACKREFMAX            2
+#define PCRE2_INFO_BSR                   3
+#define PCRE2_INFO_CAPTURECOUNT          4
+#define PCRE2_INFO_FIRSTCODEUNIT         5
+#define PCRE2_INFO_FIRSTCODETYPE         6
+#define PCRE2_INFO_FIRSTBITMAP           7
+#define PCRE2_INFO_HASCRORLF             8
+#define PCRE2_INFO_JCHANGED              9
+#define PCRE2_INFO_JITSIZE              10
+#define PCRE2_INFO_LASTCODEUNIT         11
+#define PCRE2_INFO_LASTCODETYPE         12
+#define PCRE2_INFO_MATCHEMPTY           13
+#define PCRE2_INFO_MATCHLIMIT           14
+#define PCRE2_INFO_MAXLOOKBEHIND        15
+#define PCRE2_INFO_MINLENGTH            16
+#define PCRE2_INFO_NAMECOUNT            17
+#define PCRE2_INFO_NAMEENTRYSIZE        18
+#define PCRE2_INFO_NAMETABLE            19
+#define PCRE2_INFO_NEWLINE              20
+#define PCRE2_INFO_DEPTHLIMIT           21
+#define PCRE2_INFO_RECURSIONLIMIT       21  /* Obsolete synonym */
+#define PCRE2_INFO_SIZE                 22
+#define PCRE2_INFO_HASBACKSLASHC        23
+#define PCRE2_INFO_FRAMESIZE            24
+#define PCRE2_INFO_HEAPLIMIT            25
+#define PCRE2_INFO_EXTRAOPTIONS         26
+
+/* Request types for pcre2_config(). */
+
+#define PCRE2_CONFIG_BSR                     0
+#define PCRE2_CONFIG_JIT                     1
+#define PCRE2_CONFIG_JITTARGET               2
+#define PCRE2_CONFIG_LINKSIZE                3
+#define PCRE2_CONFIG_MATCHLIMIT              4
+#define PCRE2_CONFIG_NEWLINE                 5
+#define PCRE2_CONFIG_PARENSLIMIT             6
+#define PCRE2_CONFIG_DEPTHLIMIT              7
+#define PCRE2_CONFIG_RECURSIONLIMIT          7  /* Obsolete synonym */
+#define PCRE2_CONFIG_STACKRECURSE            8  /* Obsolete */
+#define PCRE2_CONFIG_UNICODE                 9
+#define PCRE2_CONFIG_UNICODE_VERSION        10
+#define PCRE2_CONFIG_VERSION                11
+#define PCRE2_CONFIG_HEAPLIMIT              12
+#define PCRE2_CONFIG_NEVER_BACKSLASH_C      13
+#define PCRE2_CONFIG_COMPILED_WIDTHS        14
+#define PCRE2_CONFIG_TABLES_LENGTH          15
+
+
+/* Types for code units in patterns and subject strings. */
+
+typedef uint8_t  PCRE2_UCHAR8;
+typedef uint16_t PCRE2_UCHAR16;
+typedef uint32_t PCRE2_UCHAR32;
+
+typedef const PCRE2_UCHAR8  *PCRE2_SPTR8;
+typedef const PCRE2_UCHAR16 *PCRE2_SPTR16;
+typedef const PCRE2_UCHAR32 *PCRE2_SPTR32;
+
+/* The PCRE2_SIZE type is used for all string lengths and offsets in PCRE2,
+including pattern offsets for errors and subject offsets after a match. We
+define special values to indicate zero-terminated strings and unset offsets in
+the offset vector (ovector). */
+
+#define PCRE2_SIZE            size_t
+#define PCRE2_SIZE_MAX        SIZE_MAX
+#define PCRE2_ZERO_TERMINATED (~(PCRE2_SIZE)0)
+#define PCRE2_UNSET           (~(PCRE2_SIZE)0)
+
+/* Generic types for opaque structures and JIT callback functions. These
+declarations are defined in a macro that is expanded for each width later. */
+
+#define PCRE2_TYPES_LIST \
+struct pcre2_real_general_context; \
+typedef struct pcre2_real_general_context pcre2_general_context; \
+\
+struct pcre2_real_compile_context; \
+typedef struct pcre2_real_compile_context pcre2_compile_context; \
+\
+struct pcre2_real_match_context; \
+typedef struct pcre2_real_match_context pcre2_match_context; \
+\
+struct pcre2_real_convert_context; \
+typedef struct pcre2_real_convert_context pcre2_convert_context; \
+\
+struct pcre2_real_code; \
+typedef struct pcre2_real_code pcre2_code; \
+\
+struct pcre2_real_match_data; \
+typedef struct pcre2_real_match_data pcre2_match_data; \
+\
+struct pcre2_real_jit_stack; \
+typedef struct pcre2_real_jit_stack pcre2_jit_stack; \
+\
+typedef pcre2_jit_stack *(*pcre2_jit_callback)(void *);
+
+
+/* The structures for passing out data via callout functions. We use structures
+so that new fields can be added on the end in future versions, without changing
+the API of the function, thereby allowing old clients to work without
+modification. Define the generic versions in a macro; the width-specific
+versions are generated from this macro below. */
+
+/* Flags for the callout_flags field. These are cleared after a callout. */
+
+#define PCRE2_CALLOUT_STARTMATCH    0x00000001u  /* Set for each bumpalong */
+#define PCRE2_CALLOUT_BACKTRACK     0x00000002u  /* Set after a backtrack */
+
+#define PCRE2_STRUCTURE_LIST \
+typedef struct pcre2_callout_block { \
+  uint32_t      version;           /* Identifies version of block */ \
+  /* ------------------------ Version 0 ------------------------------- */ \
+  uint32_t      callout_number;    /* Number compiled into pattern */ \
+  uint32_t      capture_top;       /* Max current capture */ \
+  uint32_t      capture_last;      /* Most recently closed capture */ \
+  PCRE2_SIZE   *offset_vector;     /* The offset vector */ \
+  PCRE2_SPTR    mark;              /* Pointer to current mark or NULL */ \
+  PCRE2_SPTR    subject;           /* The subject being matched */ \
+  PCRE2_SIZE    subject_length;    /* The length of the subject */ \
+  PCRE2_SIZE    start_match;       /* Offset to start of this match attempt */ \
+  PCRE2_SIZE    current_position;  /* Where we currently are in the subject */ \
+  PCRE2_SIZE    pattern_position;  /* Offset to next item in the pattern */ \
+  PCRE2_SIZE    next_item_length;  /* Length of next item in the pattern */ \
+  /* ------------------- Added for Version 1 -------------------------- */ \
+  PCRE2_SIZE    callout_string_offset; /* Offset to string within pattern */ \
+  PCRE2_SIZE    callout_string_length; /* Length of string compiled into pattern */ \
+  PCRE2_SPTR    callout_string;    /* String compiled into pattern */ \
+  /* ------------------- Added for Version 2 -------------------------- */ \
+  uint32_t      callout_flags;     /* See above for list */ \
+  /* ------------------------------------------------------------------ */ \
+} pcre2_callout_block; \
+\
+typedef struct pcre2_callout_enumerate_block { \
+  uint32_t      version;           /* Identifies version of block */ \
+  /* ------------------------ Version 0 ------------------------------- */ \
+  PCRE2_SIZE    pattern_position;  /* Offset to next item in the pattern */ \
+  PCRE2_SIZE    next_item_length;  /* Length of next item in the pattern */ \
+  uint32_t      callout_number;    /* Number compiled into pattern */ \
+  PCRE2_SIZE    callout_string_offset; /* Offset to string within pattern */ \
+  PCRE2_SIZE    callout_string_length; /* Length of string compiled into pattern */ \
+  PCRE2_SPTR    callout_string;    /* String compiled into pattern */ \
+  /* ------------------------------------------------------------------ */ \
+} pcre2_callout_enumerate_block; \
+\
+typedef struct pcre2_substitute_callout_block { \
+  uint32_t      version;           /* Identifies version of block */ \
+  /* ------------------------ Version 0 ------------------------------- */ \
+  PCRE2_SPTR    input;             /* Pointer to input subject string */ \
+  PCRE2_SPTR    output;            /* Pointer to output buffer */ \
+  PCRE2_SIZE    output_offsets[2]; /* Changed portion of the output */ \
+  PCRE2_SIZE   *ovector;           /* Pointer to current ovector */ \
+  uint32_t      oveccount;         /* Count of pairs set in ovector */ \
+  uint32_t      subscount;         /* Substitution number */ \
+  /* ------------------------------------------------------------------ */ \
+} pcre2_substitute_callout_block;
+
+
+/* List the generic forms of all other functions in macros, which will be
+expanded for each width below. Start with functions that give general
+information. */
+
+#define PCRE2_GENERAL_INFO_FUNCTIONS \
+PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION pcre2_config(uint32_t, void *);
+
+
+/* Functions for manipulating contexts. */
+
+#define PCRE2_GENERAL_CONTEXT_FUNCTIONS \
+PCRE2_EXP_DECL pcre2_general_context PCRE2_CALL_CONVENTION \
+  *pcre2_general_context_copy(pcre2_general_context *); \
+PCRE2_EXP_DECL pcre2_general_context PCRE2_CALL_CONVENTION \
+  *pcre2_general_context_create(void *(*)(PCRE2_SIZE, void *), \
+    void (*)(void *, void *), void *); \
+PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
+  pcre2_general_context_free(pcre2_general_context *);
+
+#define PCRE2_COMPILE_CONTEXT_FUNCTIONS \
+PCRE2_EXP_DECL pcre2_compile_context PCRE2_CALL_CONVENTION \
+  *pcre2_compile_context_copy(pcre2_compile_context *); \
+PCRE2_EXP_DECL pcre2_compile_context PCRE2_CALL_CONVENTION \
+  *pcre2_compile_context_create(pcre2_general_context *);\
+PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
+  pcre2_compile_context_free(pcre2_compile_context *); \
+PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
+  pcre2_set_bsr(pcre2_compile_context *, uint32_t); \
+PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
+  pcre2_set_character_tables(pcre2_compile_context *, const uint8_t *); \
+PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
+  pcre2_set_compile_extra_options(pcre2_compile_context *, uint32_t); \
+PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
+  pcre2_set_max_pattern_length(pcre2_compile_context *, PCRE2_SIZE); \
+PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
+  pcre2_set_newline(pcre2_compile_context *, uint32_t); \
+PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
+  pcre2_set_parens_nest_limit(pcre2_compile_context *, uint32_t); \
+PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
+  pcre2_set_compile_recursion_guard(pcre2_compile_context *, \
+    int (*)(uint32_t, void *), void *);
+
+#define PCRE2_MATCH_CONTEXT_FUNCTIONS \
+PCRE2_EXP_DECL pcre2_match_context PCRE2_CALL_CONVENTION \
+  *pcre2_match_context_copy(pcre2_match_context *); \
+PCRE2_EXP_DECL pcre2_match_context PCRE2_CALL_CONVENTION \
+  *pcre2_match_context_create(pcre2_general_context *); \
+PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
+  pcre2_match_context_free(pcre2_match_context *); \
+PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
+  pcre2_set_callout(pcre2_match_context *, \
+    int (*)(pcre2_callout_block *, void *), void *); \
+PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
+  pcre2_set_substitute_callout(pcre2_match_context *, \
+    int (*)(pcre2_substitute_callout_block *, void *), void *); \
+PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
+  pcre2_set_depth_limit(pcre2_match_context *, uint32_t); \
+PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
+  pcre2_set_heap_limit(pcre2_match_context *, uint32_t); \
+PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
+  pcre2_set_match_limit(pcre2_match_context *, uint32_t); \
+PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
+  pcre2_set_offset_limit(pcre2_match_context *, PCRE2_SIZE); \
+PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
+  pcre2_set_recursion_limit(pcre2_match_context *, uint32_t); \
+PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
+  pcre2_set_recursion_memory_management(pcre2_match_context *, \
+    void *(*)(PCRE2_SIZE, void *), void (*)(void *, void *), void *);
+
+#define PCRE2_CONVERT_CONTEXT_FUNCTIONS \
+PCRE2_EXP_DECL pcre2_convert_context PCRE2_CALL_CONVENTION \
+  *pcre2_convert_context_copy(pcre2_convert_context *); \
+PCRE2_EXP_DECL pcre2_convert_context PCRE2_CALL_CONVENTION \
+  *pcre2_convert_context_create(pcre2_general_context *); \
+PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
+  pcre2_convert_context_free(pcre2_convert_context *); \
+PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
+  pcre2_set_glob_escape(pcre2_convert_context *, uint32_t); \
+PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
+  pcre2_set_glob_separator(pcre2_convert_context *, uint32_t);
+
+
+/* Functions concerned with compiling a pattern to PCRE internal code. */
+
+#define PCRE2_COMPILE_FUNCTIONS \
+PCRE2_EXP_DECL pcre2_code PCRE2_CALL_CONVENTION \
+  *pcre2_compile(PCRE2_SPTR, PCRE2_SIZE, uint32_t, int *, PCRE2_SIZE *, \
+    pcre2_compile_context *); \
+PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
+  pcre2_code_free(pcre2_code *); \
+PCRE2_EXP_DECL pcre2_code PCRE2_CALL_CONVENTION \
+  *pcre2_code_copy(const pcre2_code *); \
+PCRE2_EXP_DECL pcre2_code PCRE2_CALL_CONVENTION \
+  *pcre2_code_copy_with_tables(const pcre2_code *);
+
+
+/* Functions that give information about a compiled pattern. */
+
+#define PCRE2_PATTERN_INFO_FUNCTIONS \
+PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
+  pcre2_pattern_info(const pcre2_code *, uint32_t, void *); \
+PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
+  pcre2_callout_enumerate(const pcre2_code *, \
+    int (*)(pcre2_callout_enumerate_block *, void *), void *);
+
+
+/* Functions for running a match and inspecting the result. */
+
+#define PCRE2_MATCH_FUNCTIONS \
+PCRE2_EXP_DECL pcre2_match_data PCRE2_CALL_CONVENTION \
+  *pcre2_match_data_create(uint32_t, pcre2_general_context *); \
+PCRE2_EXP_DECL pcre2_match_data PCRE2_CALL_CONVENTION \
+  *pcre2_match_data_create_from_pattern(const pcre2_code *, \
+    pcre2_general_context *); \
+PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
+  pcre2_dfa_match(const pcre2_code *, PCRE2_SPTR, PCRE2_SIZE, PCRE2_SIZE, \
+    uint32_t, pcre2_match_data *, pcre2_match_context *, int *, PCRE2_SIZE); \
+PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
+  pcre2_match(const pcre2_code *, PCRE2_SPTR, PCRE2_SIZE, PCRE2_SIZE, \
+    uint32_t, pcre2_match_data *, pcre2_match_context *); \
+PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
+  pcre2_match_data_free(pcre2_match_data *); \
+PCRE2_EXP_DECL PCRE2_SPTR PCRE2_CALL_CONVENTION \
+  pcre2_get_mark(pcre2_match_data *); \
+PCRE2_EXP_DECL PCRE2_SIZE PCRE2_CALL_CONVENTION \
+  pcre2_get_match_data_size(pcre2_match_data *); \
+PCRE2_EXP_DECL uint32_t PCRE2_CALL_CONVENTION \
+  pcre2_get_ovector_count(pcre2_match_data *); \
+PCRE2_EXP_DECL PCRE2_SIZE PCRE2_CALL_CONVENTION \
+  *pcre2_get_ovector_pointer(pcre2_match_data *); \
+PCRE2_EXP_DECL PCRE2_SIZE PCRE2_CALL_CONVENTION \
+  pcre2_get_startchar(pcre2_match_data *);
+
+
+/* Convenience functions for handling matched substrings. */
+
+#define PCRE2_SUBSTRING_FUNCTIONS \
+PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
+  pcre2_substring_copy_byname(pcre2_match_data *, PCRE2_SPTR, PCRE2_UCHAR *, \
+    PCRE2_SIZE *); \
+PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
+  pcre2_substring_copy_bynumber(pcre2_match_data *, uint32_t, PCRE2_UCHAR *, \
+    PCRE2_SIZE *); \
+PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
+  pcre2_substring_free(PCRE2_UCHAR *); \
+PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
+  pcre2_substring_get_byname(pcre2_match_data *, PCRE2_SPTR, PCRE2_UCHAR **, \
+    PCRE2_SIZE *); \
+PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
+  pcre2_substring_get_bynumber(pcre2_match_data *, uint32_t, PCRE2_UCHAR **, \
+    PCRE2_SIZE *); \
+PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
+  pcre2_substring_length_byname(pcre2_match_data *, PCRE2_SPTR, PCRE2_SIZE *); \
+PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
+  pcre2_substring_length_bynumber(pcre2_match_data *, uint32_t, PCRE2_SIZE *); \
+PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
+  pcre2_substring_nametable_scan(const pcre2_code *, PCRE2_SPTR, PCRE2_SPTR *, \
+    PCRE2_SPTR *); \
+PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
+  pcre2_substring_number_from_name(const pcre2_code *, PCRE2_SPTR); \
+PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
+  pcre2_substring_list_free(PCRE2_SPTR *); \
+PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
+  pcre2_substring_list_get(pcre2_match_data *, PCRE2_UCHAR ***, PCRE2_SIZE **);
+
+/* Functions for serializing / deserializing compiled patterns. */
+
+#define PCRE2_SERIALIZE_FUNCTIONS \
+PCRE2_EXP_DECL int32_t PCRE2_CALL_CONVENTION \
+  pcre2_serialize_encode(const pcre2_code **, int32_t, uint8_t **, \
+    PCRE2_SIZE *, pcre2_general_context *); \
+PCRE2_EXP_DECL int32_t PCRE2_CALL_CONVENTION \
+  pcre2_serialize_decode(pcre2_code **, int32_t, const uint8_t *, \
+    pcre2_general_context *); \
+PCRE2_EXP_DECL int32_t PCRE2_CALL_CONVENTION \
+  pcre2_serialize_get_number_of_codes(const uint8_t *); \
+PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
+  pcre2_serialize_free(uint8_t *);
+
+
+/* Convenience function for match + substitute. */
+
+#define PCRE2_SUBSTITUTE_FUNCTION \
+PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
+  pcre2_substitute(const pcre2_code *, PCRE2_SPTR, PCRE2_SIZE, PCRE2_SIZE, \
+    uint32_t, pcre2_match_data *, pcre2_match_context *, PCRE2_SPTR, \
+    PCRE2_SIZE, PCRE2_UCHAR *, PCRE2_SIZE *);
+
+
+/* Functions for converting pattern source strings. */
+
+#define PCRE2_CONVERT_FUNCTIONS \
+PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
+  pcre2_pattern_convert(PCRE2_SPTR, PCRE2_SIZE, uint32_t, PCRE2_UCHAR **, \
+    PCRE2_SIZE *, pcre2_convert_context *); \
+PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
+  pcre2_converted_pattern_free(PCRE2_UCHAR *);
+
+
+/* Functions for JIT processing */
+
+#define PCRE2_JIT_FUNCTIONS \
+PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
+  pcre2_jit_compile(pcre2_code *, uint32_t); \
+PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
+  pcre2_jit_match(const pcre2_code *, PCRE2_SPTR, PCRE2_SIZE, PCRE2_SIZE, \
+    uint32_t, pcre2_match_data *, pcre2_match_context *); \
+PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
+  pcre2_jit_free_unused_memory(pcre2_general_context *); \
+PCRE2_EXP_DECL pcre2_jit_stack PCRE2_CALL_CONVENTION \
+  *pcre2_jit_stack_create(PCRE2_SIZE, PCRE2_SIZE, pcre2_general_context *); \
+PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
+  pcre2_jit_stack_assign(pcre2_match_context *, pcre2_jit_callback, void *); \
+PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
+  pcre2_jit_stack_free(pcre2_jit_stack *);
+
+
+/* Other miscellaneous functions. */
+
+#define PCRE2_OTHER_FUNCTIONS \
+PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
+  pcre2_get_error_message(int, PCRE2_UCHAR *, PCRE2_SIZE); \
+PCRE2_EXP_DECL const uint8_t PCRE2_CALL_CONVENTION \
+  *pcre2_maketables(pcre2_general_context *); \
+PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
+  pcre2_maketables_free(pcre2_general_context *, const uint8_t *);
+
+/* Define macros that generate width-specific names from generic versions. The
+three-level macro scheme is necessary to get the macros expanded when we want
+them to be. First we get the width from PCRE2_LOCAL_WIDTH, which is used for
+generating three versions of everything below. After that, PCRE2_SUFFIX will be
+re-defined to use PCRE2_CODE_UNIT_WIDTH, for use when macros such as
+pcre2_compile are called by application code. */
+
+#define PCRE2_JOIN(a,b) a ## b
+#define PCRE2_GLUE(a,b) PCRE2_JOIN(a,b)
+#define PCRE2_SUFFIX(a) PCRE2_GLUE(a,PCRE2_LOCAL_WIDTH)
+
+
+/* Data types */
+
+#define PCRE2_UCHAR                 PCRE2_SUFFIX(PCRE2_UCHAR)
+#define PCRE2_SPTR                  PCRE2_SUFFIX(PCRE2_SPTR)
+
+#define pcre2_code                  PCRE2_SUFFIX(pcre2_code_)
+#define pcre2_jit_callback          PCRE2_SUFFIX(pcre2_jit_callback_)
+#define pcre2_jit_stack             PCRE2_SUFFIX(pcre2_jit_stack_)
+
+#define pcre2_real_code             PCRE2_SUFFIX(pcre2_real_code_)
+#define pcre2_real_general_context  PCRE2_SUFFIX(pcre2_real_general_context_)
+#define pcre2_real_compile_context  PCRE2_SUFFIX(pcre2_real_compile_context_)
+#define pcre2_real_convert_context  PCRE2_SUFFIX(pcre2_real_convert_context_)
+#define pcre2_real_match_context    PCRE2_SUFFIX(pcre2_real_match_context_)
+#define pcre2_real_jit_stack        PCRE2_SUFFIX(pcre2_real_jit_stack_)
+#define pcre2_real_match_data       PCRE2_SUFFIX(pcre2_real_match_data_)
+
+
+/* Data blocks */
+
+#define pcre2_callout_block            PCRE2_SUFFIX(pcre2_callout_block_)
+#define pcre2_callout_enumerate_block  PCRE2_SUFFIX(pcre2_callout_enumerate_block_)
+#define pcre2_substitute_callout_block PCRE2_SUFFIX(pcre2_substitute_callout_block_)
+#define pcre2_general_context          PCRE2_SUFFIX(pcre2_general_context_)
+#define pcre2_compile_context          PCRE2_SUFFIX(pcre2_compile_context_)
+#define pcre2_convert_context          PCRE2_SUFFIX(pcre2_convert_context_)
+#define pcre2_match_context            PCRE2_SUFFIX(pcre2_match_context_)
+#define pcre2_match_data               PCRE2_SUFFIX(pcre2_match_data_)
+
+
+/* Functions: the complete list in alphabetical order */
+
+#define pcre2_callout_enumerate               PCRE2_SUFFIX(pcre2_callout_enumerate_)
+#define pcre2_code_copy                       PCRE2_SUFFIX(pcre2_code_copy_)
+#define pcre2_code_copy_with_tables           PCRE2_SUFFIX(pcre2_code_copy_with_tables_)
+#define pcre2_code_free                       PCRE2_SUFFIX(pcre2_code_free_)
+#define pcre2_compile                         PCRE2_SUFFIX(pcre2_compile_)
+#define pcre2_compile_context_copy            PCRE2_SUFFIX(pcre2_compile_context_copy_)
+#define pcre2_compile_context_create          PCRE2_SUFFIX(pcre2_compile_context_create_)
+#define pcre2_compile_context_free            PCRE2_SUFFIX(pcre2_compile_context_free_)
+#define pcre2_config                          PCRE2_SUFFIX(pcre2_config_)
+#define pcre2_convert_context_copy            PCRE2_SUFFIX(pcre2_convert_context_copy_)
+#define pcre2_convert_context_create          PCRE2_SUFFIX(pcre2_convert_context_create_)
+#define pcre2_convert_context_free            PCRE2_SUFFIX(pcre2_convert_context_free_)
+#define pcre2_converted_pattern_free          PCRE2_SUFFIX(pcre2_converted_pattern_free_)
+#define pcre2_dfa_match                       PCRE2_SUFFIX(pcre2_dfa_match_)
+#define pcre2_general_context_copy            PCRE2_SUFFIX(pcre2_general_context_copy_)
+#define pcre2_general_context_create          PCRE2_SUFFIX(pcre2_general_context_create_)
+#define pcre2_general_context_free            PCRE2_SUFFIX(pcre2_general_context_free_)
+#define pcre2_get_error_message               PCRE2_SUFFIX(pcre2_get_error_message_)
+#define pcre2_get_mark                        PCRE2_SUFFIX(pcre2_get_mark_)
+#define pcre2_get_match_data_size             PCRE2_SUFFIX(pcre2_get_match_data_size_)
+#define pcre2_get_ovector_pointer             PCRE2_SUFFIX(pcre2_get_ovector_pointer_)
+#define pcre2_get_ovector_count               PCRE2_SUFFIX(pcre2_get_ovector_count_)
+#define pcre2_get_startchar                   PCRE2_SUFFIX(pcre2_get_startchar_)
+#define pcre2_jit_compile                     PCRE2_SUFFIX(pcre2_jit_compile_)
+#define pcre2_jit_match                       PCRE2_SUFFIX(pcre2_jit_match_)
+#define pcre2_jit_free_unused_memory          PCRE2_SUFFIX(pcre2_jit_free_unused_memory_)
+#define pcre2_jit_stack_assign                PCRE2_SUFFIX(pcre2_jit_stack_assign_)
+#define pcre2_jit_stack_create                PCRE2_SUFFIX(pcre2_jit_stack_create_)
+#define pcre2_jit_stack_free                  PCRE2_SUFFIX(pcre2_jit_stack_free_)
+#define pcre2_maketables                      PCRE2_SUFFIX(pcre2_maketables_)
+#define pcre2_maketables_free                 PCRE2_SUFFIX(pcre2_maketables_free_)
+#define pcre2_match                           PCRE2_SUFFIX(pcre2_match_)
+#define pcre2_match_context_copy              PCRE2_SUFFIX(pcre2_match_context_copy_)
+#define pcre2_match_context_create            PCRE2_SUFFIX(pcre2_match_context_create_)
+#define pcre2_match_context_free              PCRE2_SUFFIX(pcre2_match_context_free_)
+#define pcre2_match_data_create               PCRE2_SUFFIX(pcre2_match_data_create_)
+#define pcre2_match_data_create_from_pattern  PCRE2_SUFFIX(pcre2_match_data_create_from_pattern_)
+#define pcre2_match_data_free                 PCRE2_SUFFIX(pcre2_match_data_free_)
+#define pcre2_pattern_convert                 PCRE2_SUFFIX(pcre2_pattern_convert_)
+#define pcre2_pattern_info                    PCRE2_SUFFIX(pcre2_pattern_info_)
+#define pcre2_serialize_decode                PCRE2_SUFFIX(pcre2_serialize_decode_)
+#define pcre2_serialize_encode                PCRE2_SUFFIX(pcre2_serialize_encode_)
+#define pcre2_serialize_free                  PCRE2_SUFFIX(pcre2_serialize_free_)
+#define pcre2_serialize_get_number_of_codes   PCRE2_SUFFIX(pcre2_serialize_get_number_of_codes_)
+#define pcre2_set_bsr                         PCRE2_SUFFIX(pcre2_set_bsr_)
+#define pcre2_set_callout                     PCRE2_SUFFIX(pcre2_set_callout_)
+#define pcre2_set_character_tables            PCRE2_SUFFIX(pcre2_set_character_tables_)
+#define pcre2_set_compile_extra_options       PCRE2_SUFFIX(pcre2_set_compile_extra_options_)
+#define pcre2_set_compile_recursion_guard     PCRE2_SUFFIX(pcre2_set_compile_recursion_guard_)
+#define pcre2_set_depth_limit                 PCRE2_SUFFIX(pcre2_set_depth_limit_)
+#define pcre2_set_glob_escape                 PCRE2_SUFFIX(pcre2_set_glob_escape_)
+#define pcre2_set_glob_separator              PCRE2_SUFFIX(pcre2_set_glob_separator_)
+#define pcre2_set_heap_limit                  PCRE2_SUFFIX(pcre2_set_heap_limit_)
+#define pcre2_set_match_limit                 PCRE2_SUFFIX(pcre2_set_match_limit_)
+#define pcre2_set_max_pattern_length          PCRE2_SUFFIX(pcre2_set_max_pattern_length_)
+#define pcre2_set_newline                     PCRE2_SUFFIX(pcre2_set_newline_)
+#define pcre2_set_parens_nest_limit           PCRE2_SUFFIX(pcre2_set_parens_nest_limit_)
+#define pcre2_set_offset_limit                PCRE2_SUFFIX(pcre2_set_offset_limit_)
+#define pcre2_set_substitute_callout          PCRE2_SUFFIX(pcre2_set_substitute_callout_)
+#define pcre2_substitute                      PCRE2_SUFFIX(pcre2_substitute_)
+#define pcre2_substring_copy_byname           PCRE2_SUFFIX(pcre2_substring_copy_byname_)
+#define pcre2_substring_copy_bynumber         PCRE2_SUFFIX(pcre2_substring_copy_bynumber_)
+#define pcre2_substring_free                  PCRE2_SUFFIX(pcre2_substring_free_)
+#define pcre2_substring_get_byname            PCRE2_SUFFIX(pcre2_substring_get_byname_)
+#define pcre2_substring_get_bynumber          PCRE2_SUFFIX(pcre2_substring_get_bynumber_)
+#define pcre2_substring_length_byname         PCRE2_SUFFIX(pcre2_substring_length_byname_)
+#define pcre2_substring_length_bynumber       PCRE2_SUFFIX(pcre2_substring_length_bynumber_)
+#define pcre2_substring_list_get              PCRE2_SUFFIX(pcre2_substring_list_get_)
+#define pcre2_substring_list_free             PCRE2_SUFFIX(pcre2_substring_list_free_)
+#define pcre2_substring_nametable_scan        PCRE2_SUFFIX(pcre2_substring_nametable_scan_)
+#define pcre2_substring_number_from_name      PCRE2_SUFFIX(pcre2_substring_number_from_name_)
+
+/* Keep this old function name for backwards compatibility */
+#define pcre2_set_recursion_limit PCRE2_SUFFIX(pcre2_set_recursion_limit_)
+
+/* Keep this obsolete function for backwards compatibility: it is now a noop. */
+#define pcre2_set_recursion_memory_management PCRE2_SUFFIX(pcre2_set_recursion_memory_management_)
+
+/* Now generate all three sets of width-specific structures and function
+prototypes. */
+
+#define PCRE2_TYPES_STRUCTURES_AND_FUNCTIONS \
+PCRE2_TYPES_LIST \
+PCRE2_STRUCTURE_LIST \
+PCRE2_GENERAL_INFO_FUNCTIONS \
+PCRE2_GENERAL_CONTEXT_FUNCTIONS \
+PCRE2_COMPILE_CONTEXT_FUNCTIONS \
+PCRE2_CONVERT_CONTEXT_FUNCTIONS \
+PCRE2_CONVERT_FUNCTIONS \
+PCRE2_MATCH_CONTEXT_FUNCTIONS \
+PCRE2_COMPILE_FUNCTIONS \
+PCRE2_PATTERN_INFO_FUNCTIONS \
+PCRE2_MATCH_FUNCTIONS \
+PCRE2_SUBSTRING_FUNCTIONS \
+PCRE2_SERIALIZE_FUNCTIONS \
+PCRE2_SUBSTITUTE_FUNCTION \
+PCRE2_JIT_FUNCTIONS \
+PCRE2_OTHER_FUNCTIONS
+
+#define PCRE2_LOCAL_WIDTH 8
+PCRE2_TYPES_STRUCTURES_AND_FUNCTIONS
+#undef PCRE2_LOCAL_WIDTH
+
+#define PCRE2_LOCAL_WIDTH 16
+PCRE2_TYPES_STRUCTURES_AND_FUNCTIONS
+#undef PCRE2_LOCAL_WIDTH
+
+#define PCRE2_LOCAL_WIDTH 32
+PCRE2_TYPES_STRUCTURES_AND_FUNCTIONS
+#undef PCRE2_LOCAL_WIDTH
+
+/* Undefine the list macros; they are no longer needed. */
+
+#undef PCRE2_TYPES_LIST
+#undef PCRE2_STRUCTURE_LIST
+#undef PCRE2_GENERAL_INFO_FUNCTIONS
+#undef PCRE2_GENERAL_CONTEXT_FUNCTIONS
+#undef PCRE2_COMPILE_CONTEXT_FUNCTIONS
+#undef PCRE2_CONVERT_CONTEXT_FUNCTIONS
+#undef PCRE2_MATCH_CONTEXT_FUNCTIONS
+#undef PCRE2_COMPILE_FUNCTIONS
+#undef PCRE2_PATTERN_INFO_FUNCTIONS
+#undef PCRE2_MATCH_FUNCTIONS
+#undef PCRE2_SUBSTRING_FUNCTIONS
+#undef PCRE2_SERIALIZE_FUNCTIONS
+#undef PCRE2_SUBSTITUTE_FUNCTION
+#undef PCRE2_JIT_FUNCTIONS
+#undef PCRE2_OTHER_FUNCTIONS
+#undef PCRE2_TYPES_STRUCTURES_AND_FUNCTIONS
+
+/* PCRE2_CODE_UNIT_WIDTH must be defined. If it is 8, 16, or 32, redefine
+PCRE2_SUFFIX to use it. If it is 0, undefine the other macros and make
+PCRE2_SUFFIX a no-op. Otherwise, generate an error. */
+
+#undef PCRE2_SUFFIX
+#ifndef PCRE2_CODE_UNIT_WIDTH
+#error PCRE2_CODE_UNIT_WIDTH must be defined before including pcre2.h.
+#error Use 8, 16, or 32; or 0 for a multi-width application.
+#else  /* PCRE2_CODE_UNIT_WIDTH is defined */
+#if PCRE2_CODE_UNIT_WIDTH == 8 || \
+    PCRE2_CODE_UNIT_WIDTH == 16 || \
+    PCRE2_CODE_UNIT_WIDTH == 32
+#define PCRE2_SUFFIX(a) PCRE2_GLUE(a, PCRE2_CODE_UNIT_WIDTH)
+#elif PCRE2_CODE_UNIT_WIDTH == 0
+#undef PCRE2_JOIN
+#undef PCRE2_GLUE
+#define PCRE2_SUFFIX(a) a
+#else
+#error PCRE2_CODE_UNIT_WIDTH must be 0, 8, 16, or 32.
+#endif
+#endif  /* PCRE2_CODE_UNIT_WIDTH is defined */
+
+#ifdef __cplusplus
+}  /* extern "C" */
+#endif
+
+#endif  /* PCRE2_H_IDEMPOTENT_GUARD */
+
+/* End of pcre2.h */

src/regex/pcre2/.gitignore

@@ -0,0 +1,47 @@
+INSTALL
+Makefile.in
+aclocal.m4
+ar-lib
+compile
+config.guess
+config.sub
+configure
+depcomp
+install-sh
+ltmain.sh
+m4/
+missing
+test-driver
+
+Makefile
+config.log
+config.status
+libpcre2-*.pc
+libtool
+pcre2-config
+src/.deps
+src/config.h
+src/pcre2.h
+src/stamp-h1
+
+.libs
+*.o
+*.lo
+*.a
+*.la
+src/.dirstamp
+src/pcre2_chartables.c
+
+pcre2grep
+pcre2test
+pcre2_jit_test
+
+RunGrepTest.log
+RunGrepTest.trs
+RunTest.log
+RunTest.trs
+pcre2_jit_test.log
+pcre2_jit_test.trs
+test-suite.log
+
+*~

src/regex/pcre2/132html

@@ -0,0 +1,314 @@
+#! /usr/bin/perl -w
+
+# Script to turn PCRE2 man pages into HTML
+
+
+# Subroutine to handle font changes and other escapes
+
+sub do_line {
+my($s) = $_[0];
+
+$s =~ s/</&#60;/g;                   # Deal with < and >
+$s =~ s/>/&#62;/g;
+$s =~ s"\\fI(.*?)\\f[RP]"<i>$1</i>"g;
+$s =~ s"\\fB(.*?)\\f[RP]"<b>$1</b>"g;
+$s =~ s"\\e"\\"g;
+$s =~ s/(?<=Copyright )\(c\)/&copy;/g;
+$s;
+}
+
+# Subroutine to ensure not in a paragraph
+
+sub end_para {
+if ($inpara)
+  {
+  print TEMP "</PRE>\n" if ($inpre);
+  print TEMP "</P>\n";
+  }
+$inpara = $inpre = 0;
+$wrotetext = 0;
+}
+
+# Subroutine to start a new paragraph
+
+sub new_para {
+&end_para();
+print TEMP "<P>\n";
+$inpara = 1;
+}
+
+
+# Main program
+
+$innf = 0;
+$inpara = 0;
+$inpre = 0;
+$wrotetext = 0;
+$toc = 0;
+$ref = 1;
+
+while ($#ARGV >= 0 && $ARGV[0] =~ /^-/)
+  {
+  $toc = 1 if $ARGV[0] eq "-toc";
+  shift;
+  }
+
+# Initial output to STDOUT
+
+print <<End ;
+<html>
+<head>
+<title>$ARGV[0] specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>$ARGV[0] man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+End
+
+print "<ul>\n" if ($toc);
+
+open(TEMP, ">/tmp/$$") || die "Can't open /tmp/$$ for output\n";
+
+while (<STDIN>)
+  {
+  # Handle lines beginning with a dot
+
+  if (/^\./)
+    {
+    # Some of the PCRE2 man pages used to contain instances of .br. However,
+    # they should have all been removed because they cause trouble in some
+    # (other) automated systems that translate man pages to HTML. Complain if
+    # we find .br or .in (another macro that is deprecated).
+
+    if (/^\.br/ || /^\.in/)
+      {
+      print STDERR "\n*** Deprecated macro encountered - rewrite needed\n";
+      print STDERR "*** $_\n";
+      die "*** Processing abandoned\n";
+      }
+
+    # Instead of .br, relevent "literal" sections are enclosed in .nf/.fi.
+
+    elsif (/^\.nf/)
+      {
+      $innf = 1;
+      }
+
+    elsif (/^\.fi/)
+      {
+      $innf = 0;
+      }
+
+    # Handling .sp is subtle. If it is inside a literal section, do nothing if
+    # the next line is a non literal text line; similarly, if not inside a
+    # literal section, do nothing if a literal follows, unless we are inside
+    # a .nf/.fi section or about to enter one. The point being that the <pre>
+    # and </pre> that delimit literal sections will do the spacing. Always skip
+    # if no previous output.
+
+    elsif (/^\.sp/)
+      {
+      if ($wrotetext)
+        {
+        $_ = <STDIN>;
+        if ($inpre)
+          {
+          print TEMP "\n" if (/^[\s.]/);
+          }
+        else
+          {
+          print TEMP "<br>\n<br>\n" if ($innf || /^\.nf/ || !/^[\s.]/);
+          }
+        redo;    # Now process the lookahead line we just read
+        }
+      }
+    elsif (/^\.TP/ || /^\.PP/ || /^\.P/)
+      {
+      &new_para();
+      }
+    elsif (/^\.SH\s*("?)(.*)\1/)
+      {
+      # Ignore the NAME section
+      if ($2 =~ /^NAME\b/)
+        {
+        <STDIN>;
+        next;
+        }
+
+      &end_para();
+      my($title) = &do_line($2);
+      if ($toc)
+        {
+        printf("<li><a name=\"TOC%d\" href=\"#SEC%d\">$title</a>\n",
+          $ref, $ref);
+        printf TEMP ("<br><a name=\"SEC%d\" href=\"#TOC1\">$title</a><br>\n",
+          $ref);
+        $ref++;
+        }
+      else
+        {
+        print TEMP "<br><b>\n$title\n</b><br>\n";
+        }
+      }
+    elsif (/^\.SS\s*("?)(.*)\1/)
+      {
+      &end_para();
+      my($title) = &do_line($2);
+      print TEMP "<br><b>\n$title\n</b><br>\n";
+      }
+    elsif (/^\.B\s*(.*)/)
+      {
+      &new_para() if (!$inpara);
+      $_ = &do_line($1);
+      s/"(.*?)"/$1/g;
+      print TEMP "<b>$_</b>\n";
+      $wrotetext = 1;
+      }
+    elsif (/^\.I\s*(.*)/)
+      {
+      &new_para() if (!$inpara);
+      $_ = &do_line($1);
+      s/"(.*?)"/$1/g;
+      print TEMP "<i>$_</i>\n";
+      $wrotetext = 1;
+      }
+
+    # A comment that starts "HREF" takes the next line as a name that
+    # is turned into a hyperlink, using the text given, which might be
+    # in a special font. If it ends in () or (digits) or punctuation, they
+    # aren't part of the link.
+
+    elsif (/^\.\\"\s*HREF/)
+      {
+      $_=<STDIN>;
+      chomp;
+      $_ = &do_line($_);
+      $_ =~ s/\s+$//;
+      $_ =~ /^(?:<.>)?([^<(]+)(?:\(\))?(?:<\/.>)?(?:\(\d+\))?[.,;:]?$/;
+      print TEMP "<a href=\"$1.html\">$_</a>\n";
+      }
+
+    # A comment that starts "HTML" inserts literal HTML
+
+    elsif (/^\.\\"\s*HTML\s*(.*)/)
+      {
+      print TEMP $1;
+      }
+
+    # A comment that starts < inserts that HTML at the end of the
+    # *next* input line - so as not to get a newline between them.
+
+    elsif (/^\.\\"\s*(<.*>)/)
+      {
+      my($markup) = $1;
+      $_=<STDIN>;
+      chomp;
+      $_ = &do_line($_);
+      $_ =~ s/\s+$//;
+      print TEMP "$_$markup\n";
+      }
+
+    # A comment that starts JOIN joins the next two lines together, with one
+    # space between them. Then that line is processed. This is used in some
+    # displays where two lines are needed for the "man" version. JOINSH works
+    # the same, except that it assumes this is a shell command, so removes
+    # continuation backslashes.
+
+    elsif (/^\.\\"\s*JOIN(SH)?/)
+      {
+      my($one,$two);
+      $one = <STDIN>;
+      $two = <STDIN>;
+      $one =~ s/\s*\\e\s*$// if (defined($1));
+      chomp($one);
+      $two =~ s/^\s+//;
+      $_ = "$one $two";
+      redo;            # Process the joined lines
+      }
+
+    # .EX/.EE are used in the pcre2demo page to bracket the entire program,
+    # which is unmodified except for turning backslash into "\e".
+
+    elsif (/^\.EX\s*$/)
+      {
+      print TEMP "<PRE>\n";
+      while (<STDIN>)
+        {
+        last if /^\.EE\s*$/;
+        s/\\e/\\/g;
+        s/&/&amp;/g;
+        s/</&lt;/g;
+        s/>/&gt;/g;
+        print TEMP;
+        }
+      }
+
+    # Ignore anything not recognized
+
+    next;
+    }
+
+  # Line does not begin with a dot. Replace blank lines with new paragraphs
+
+  if (/^\s*$/)
+    {
+    &end_para() if ($wrotetext);
+    next;
+    }
+
+  # Convert fonts changes and output an ordinary line. Ensure that indented
+  # lines are marked as literal.
+
+  $_ = &do_line($_);
+  &new_para() if (!$inpara);
+
+  if (/^\s/)
+    {
+    if (!$inpre)
+      {
+      print TEMP "<pre>\n";
+      $inpre = 1;
+      }
+    }
+  elsif ($inpre)
+    {
+    print TEMP "</pre>\n";
+    $inpre = 0;
+    }
+
+  # Add <br> to the end of a non-literal line if we are within .nf/.fi
+
+  $_ .= "<br>\n" if (!$inpre && $innf);
+
+  print TEMP;
+  $wrotetext = 1;
+  }
+
+# The TOC, if present, will have been written - terminate it
+
+print "</ul>\n" if ($toc);
+
+# Copy the remainder to the standard output
+
+close(TEMP);
+open(TEMP, "/tmp/$$") || die "Can't open /tmp/$$ for input\n";
+
+print while (<TEMP>);
+
+print <<End ;
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+End
+
+close(TEMP);
+unlink("/tmp/$$");
+
+# End

src/regex/pcre2/AUTHORS

@@ -0,0 +1,36 @@
+THE MAIN PCRE2 LIBRARY CODE
+---------------------------
+
+Written by:       Philip Hazel
+Email local part: Philip.Hazel
+Email domain:     gmail.com
+
+University of Cambridge Computing Service,
+Cambridge, England.
+
+Copyright (c) 1997-2021 University of Cambridge
+All rights reserved
+
+
+PCRE2 JUST-IN-TIME COMPILATION SUPPORT
+--------------------------------------
+
+Written by:       Zoltan Herczeg
+Email local part: hzmester
+Emain domain:     freemail.hu
+
+Copyright(c) 2010-2021 Zoltan Herczeg
+All rights reserved.
+
+
+STACK-LESS JUST-IN-TIME COMPILER
+--------------------------------
+
+Written by:       Zoltan Herczeg
+Email local part: hzmester
+Emain domain:     freemail.hu
+
+Copyright(c) 2009-2021 Zoltan Herczeg
+All rights reserved.
+
+####

src/regex/pcre2/CMakeLists.txt

@@ -0,0 +1,1017 @@
+# CMakeLists.txt
+#
+# This file enables PCRE2 to be built with the CMake configuration and build
+# tool. Download CMake in source or binary form from http://www.cmake.org/
+# Converted to support PCRE2 from the original PCRE file, August 2014.
+#
+# Original listfile by Christian Ehrlicher <Ch.Ehrlicher@gmx.de>
+# Refined and expanded by Daniel Richard G. <skunk@iSKUNK.ORG>
+# 2007-09-14 mod by Sheri so 7.4 supported configuration options can be entered
+# 2007-09-19 Adjusted by PH to retain previous default settings
+# 2007-12-26 (a) On UNIX, use names libpcre instead of just pcre
+#            (b) Ensure pcretest and pcregrep link with the local library,
+#                not a previously-installed one.
+#            (c) Add PCRE_SUPPORT_LIBREADLINE, PCRE_SUPPORT_LIBZ, and
+#                PCRE_SUPPORT_LIBBZ2.
+# 2008-01-20 Brought up to date to include several new features by Christian
+#            Ehrlicher.
+# 2008-01-22 Sheri added options for backward compatibility of library names
+#            when building with minGW:
+#            if "ON", NON_STANDARD_LIB_PREFIX causes shared libraries to
+#            be built without "lib" as prefix. (The libraries will be named
+#            pcre.dll, pcreposix.dll and pcrecpp.dll).
+#            if "ON", NON_STANDARD_LIB_SUFFIX causes shared libraries to
+#            be built with suffix of "-0.dll". (The libraries will be named
+#            libpcre-0.dll, libpcreposix-0.dll and libpcrecpp-0.dll - same names
+#            built by default with Configure and Make.
+# 2008-01-23 PH removed the automatic build of pcredemo.
+# 2008-04-22 PH modified READLINE support so it finds NCURSES when needed.
+# 2008-07-03 PH updated for revised UCP property support (change of files)
+# 2009-03-23 PH applied Steven Van Ingelgem's patch to change the name
+#            CMAKE_BINARY_DIR to PROJECT_BINARY_DIR so that it works when PCRE
+#            is included within another project.
+# 2009-03-23 PH applied a modified version of Steven Van Ingelgem's patches to
+#            add options to stop the building of pcregrep and the tests, and
+#            to disable the final configuration report.
+# 2009-04-11 PH applied Christian Ehrlicher's patch to show compiler flags that
+#            are set by specifying a release type.
+# 2010-01-02 PH added test for stdint.h
+# 2010-03-02 PH added test for inttypes.h
+# 2011-08-01 PH added PCREGREP_BUFSIZE
+# 2011-08-22 PH added PCRE_SUPPORT_JIT
+# 2011-09-06 PH modified WIN32 ADD_TEST line as suggested by Sergey Cherepanov
+# 2011-09-06 PH added PCRE_SUPPORT_PCREGREP_JIT
+# 2011-10-04 Sheri added support for including coff data in windows shared libraries
+#            compiled with MINGW if pcre.rc and/or pcreposix.rc are placed in
+#            the source dir by the user prior to building
+# 2011-10-04 Sheri changed various add_test's to use exes' location built instead
+#            of DEBUG location only (likely only matters in MSVC)
+# 2011-10-04 Sheri added scripts to provide needed variables to RunTest and
+#            RunGrepTest (used for UNIX and Msys)
+# 2011-10-04 Sheri added scripts to provide needed variables and to execute
+#            RunTest.bat in Win32 (for effortless testing with "make test")
+# 2011-10-04 Sheri Increased minimum required cmake version
+# 2012-01-06 PH removed pcre_info.c and added pcre_string_utils.c
+# 2012-01-10 Zoltan Herczeg added libpcre16 support
+# 2012-01-13 Stephen Kelly added out of source build support
+# 2012-01-17 PH applied Stephen Kelly's patch to parse the version data out
+#            of the configure.ac file
+# 2012-02-26 PH added support for libedit
+# 2012-09-06 PH added support for PCRE_EBCDIC_NL25
+# 2012-09-08 ChPe added PCRE32 support
+# 2012-10-23 PH added support for VALGRIND and GCOV
+# 2012-12-08 PH added patch from Daniel Richard G to quash some MSVC warnings
+# 2013-07-01 PH realized that the "support" for GCOV was a total nonsense and
+#            so it has been removed.
+# 2013-10-08 PH got rid of the "source" command, which is a bash-ism (use ".")
+# 2013-11-05 PH added support for PARENS_NEST_LIMIT
+# 2014-08-29 PH converted the file for PCRE2 (which has no C++).
+# 2015-04-24 PH added support for PCRE2_DEBUG
+# 2015-07-16 PH updated for new pcre2_find_bracket source module
+# 2015-08-24 PH correct C_FLAGS setting (patch from Roy Ivy III)
+# 2015-10=16 PH added support for never-backslash-C
+# 2016-03-01 PH applied Chris Wilson's patch for MSVC static
+# 2016-06-24 PH applied Chris Wilson's second patch, putting the first under
+#            a new option instead of being unconditional.
+# 2016-10-05 PH fixed a typo (PCRE should be PCRE2) in above patch
+#            fix by David Gaussmann
+# 2016-10-07 PH added PCREGREP_MAX_BUFSIZE
+# 2017-03-11 PH turned HEAP_MATCH_RECURSE into a NO-OP for 10.30
+# 2017-04-08 PH added HEAP_LIMIT
+# 2017-06-15 ZH added SUPPORT_JIT_SEALLOC support
+# 2018-06-19 PH added checks for stdint.h and inttypes.h (later removed)
+# 2018-06-27 PH added Daniel's patch to increase the stack for MSVC
+# 2018-11-14 PH removed unnecessary checks for stdint.h and inttypes.h
+# 2018-11-16 PH added PCRE2GREP_SUPPORT_CALLOUT_FORK support and tidied
+# 2019-02-16 PH hacked to avoid CMP0026 policy issue (see comments below)
+# 2020-03-16 PH renamed dftables as pcre2_dftables (as elsewhere)
+# 2020-03-24 PH changed CMAKE_MODULE_PATH definition to add, not replace
+# 2020-04-08 Carlo added function check for secure_getenv, fixed strerror
+# 2020-04-16 enh added check for __attribute__((uninitialized))
+# 2020-04-25 PH applied patches from Uwe Korn to support pkg-config and
+#            library versioning.
+# 2020-04-25 Carlo added function check for mkostemp used in ProtExecAllocator
+# 2020-04-28 PH added function check for memfd_create based on Carlo's patch
+# 2020-05-25 PH added a check for Intel CET
+# 2020-12-03 PH altered the definition of pcre2test as suggested by Daniel
+
+PROJECT(PCRE2 C)
+
+# Increased minimum to 2.8.5 to support GNUInstallDirs.
+CMAKE_MINIMUM_REQUIRED(VERSION 2.8.5)
+
+# Set policy CMP0026 to avoid warnings for the use of LOCATION in
+# GET_TARGET_PROPERTY. This should no longer be required.
+# CMAKE_POLICY(SET CMP0026 OLD)
+
+# For FindReadline.cmake. This was changed to allow setting CMAKE_MODULE_PATH
+# on the command line.
+# SET(CMAKE_MODULE_PATH ${PROJECT_SOURCE_DIR}/cmake)
+
+LIST(APPEND CMAKE_MODULE_PATH ${PROJECT_SOURCE_DIR}/cmake)
+
+INCLUDE_DIRECTORIES(${PROJECT_SOURCE_DIR}/src)
+
+# external packages
+FIND_PACKAGE( BZip2 )
+FIND_PACKAGE( ZLIB )
+FIND_PACKAGE( Readline )
+FIND_PACKAGE( Editline )
+
+# Configuration checks
+
+INCLUDE(CheckCSourceCompiles)
+INCLUDE(CheckFunctionExists)
+INCLUDE(CheckSymbolExists)
+INCLUDE(CheckIncludeFile)
+INCLUDE(CheckTypeSize)
+INCLUDE(GNUInstallDirs) # for CMAKE_INSTALL_LIBDIR
+
+CHECK_INCLUDE_FILE(dirent.h     HAVE_DIRENT_H)
+CHECK_INCLUDE_FILE(stdint.h     HAVE_STDINT_H)
+CHECK_INCLUDE_FILE(inttypes.h   HAVE_INTTYPES_H)
+CHECK_INCLUDE_FILE(sys/stat.h   HAVE_SYS_STAT_H)
+CHECK_INCLUDE_FILE(sys/types.h  HAVE_SYS_TYPES_H)
+CHECK_INCLUDE_FILE(unistd.h     HAVE_UNISTD_H)
+CHECK_INCLUDE_FILE(windows.h    HAVE_WINDOWS_H)
+
+CHECK_SYMBOL_EXISTS(bcopy         "strings.h"  HAVE_BCOPY)
+CHECK_SYMBOL_EXISTS(memfd_create  "sys/mman.h" HAVE_MEMFD_CREATE)
+CHECK_SYMBOL_EXISTS(memmove       "string.h"   HAVE_MEMMOVE)
+CHECK_SYMBOL_EXISTS(secure_getenv "stdlib.h"   HAVE_SECURE_GETENV)
+CHECK_SYMBOL_EXISTS(strerror      "string.h"   HAVE_STRERROR)
+
+set(ORIG_CMAKE_REQUIRED_FLAGS ${CMAKE_REQUIRED_FLAGS})
+set(CMAKE_REQUIRED_FLAGS "${CMAKE_REQUIRED_FLAGS} -Werror")
+CHECK_C_SOURCE_COMPILES(
+  "int main() { char buf[128] __attribute__((uninitialized)); (void)buf; return 0; }"
+  HAVE_ATTRIBUTE_UNINITIALIZED
+)
+set(CMAKE_REQUIRED_FLAGS ${ORIG_CMAKE_REQUIRED_FLAGS})
+
+# Check whether Intel CET is enabled, and if so, adjust compiler flags. This
+# code was written by PH, trying to imitate the logic from the autotools
+# configuration.
+
+CHECK_C_SOURCE_COMPILES(
+  "#ifndef __CET__
+   #error CET is not enabled
+   #endif
+   int main() { return 0; }"
+  INTEL_CET_ENABLED
+)
+
+IF (INTEL_CET_ENABLED)
+  SET(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -mshstk")
+ENDIF(INTEL_CET_ENABLED)
+
+
+
+# User-configurable options
+#
+# Note: CMakeSetup displays these in alphabetical order, regardless of
+# the order we use here.
+
+SET(BUILD_SHARED_LIBS OFF CACHE BOOL
+    "Build shared libraries instead of static ones.")
+
+OPTION(PCRE2_BUILD_PCRE2_8 "Build 8 bit PCRE2 library" ON)
+
+OPTION(PCRE2_BUILD_PCRE2_16 "Build 16 bit PCRE2 library" OFF)
+
+OPTION(PCRE2_BUILD_PCRE2_32 "Build 32 bit PCRE2 library" OFF)
+
+OPTION(PCRE2_DEBUG "Include debugging code" OFF)
+
+OPTION(PCRE2_DISABLE_PERCENT_ZT "Disable the use of %zu and %td (rarely needed)" OFF)
+
+SET(PCRE2_EBCDIC OFF CACHE BOOL
+    "Use EBCDIC coding instead of ASCII. (This is rarely used outside of mainframe systems.)")
+
+SET(PCRE2_EBCDIC_NL25 OFF CACHE BOOL
+    "Use 0x25 as EBCDIC NL character instead of 0x15; implies EBCDIC.")
+
+SET(PCRE2_LINK_SIZE "2" CACHE STRING
+    "Internal link size (2, 3 or 4 allowed). See LINK_SIZE in config.h.in for details.")
+
+SET(PCRE2_PARENS_NEST_LIMIT "250" CACHE STRING
+    "Default nested parentheses limit. See PARENS_NEST_LIMIT in config.h.in for details.")
+
+SET(PCRE2_HEAP_LIMIT "20000000" CACHE STRING
+    "Default limit on heap memory (kibibytes). See HEAP_LIMIT in config.h.in for details.")
+
+SET(PCRE2_MATCH_LIMIT "10000000" CACHE STRING
+    "Default limit on internal looping. See MATCH_LIMIT in config.h.in for details.")
+
+SET(PCRE2_MATCH_LIMIT_DEPTH "MATCH_LIMIT" CACHE STRING
+    "Default limit on internal depth of search. See MATCH_LIMIT_DEPTH in config.h.in for details.")
+
+SET(PCRE2GREP_BUFSIZE "20480" CACHE STRING
+    "Buffer starting size parameter for pcre2grep. See PCRE2GREP_BUFSIZE in config.h.in for details.")
+
+SET(PCRE2GREP_MAX_BUFSIZE "1048576" CACHE STRING
+    "Buffer maximum size parameter for pcre2grep. See PCRE2GREP_MAX_BUFSIZE in config.h.in for details.")
+
+SET(PCRE2_NEWLINE "LF" CACHE STRING
+    "What to recognize as a newline (one of CR, LF, CRLF, ANY, ANYCRLF, NUL).")
+
+SET(PCRE2_HEAP_MATCH_RECURSE OFF CACHE BOOL
+    "Obsolete option: do not use")
+
+SET(PCRE2_SUPPORT_JIT OFF CACHE BOOL
+    "Enable support for Just-in-time compiling.")
+
+IF(${CMAKE_SYSTEM_NAME} MATCHES Linux|NetBSD)
+    SET(PCRE2_SUPPORT_JIT_SEALLOC OFF CACHE BOOL
+        "Enable SELinux compatible execmem allocator in JIT (experimental).")
+ELSE(${CMAKE_SYSTEM_NAME} MATCHES Linux|NetBSD)
+    SET(PCRE2_SUPPORT_JIT_SEALLOC IGNORE)
+ENDIF(${CMAKE_SYSTEM_NAME} MATCHES Linux|NetBSD)
+
+SET(PCRE2GREP_SUPPORT_JIT ON CACHE BOOL
+    "Enable use of Just-in-time compiling in pcre2grep.")
+
+SET(PCRE2GREP_SUPPORT_CALLOUT ON CACHE BOOL
+    "Enable callout string support in pcre2grep.")
+
+SET(PCRE2GREP_SUPPORT_CALLOUT_FORK ON CACHE BOOL
+    "Enable callout string fork support in pcre2grep.")
+
+SET(PCRE2_SUPPORT_UNICODE ON CACHE BOOL
+    "Enable support for Unicode and UTF-8/UTF-16/UTF-32 encoding.")
+
+SET(PCRE2_SUPPORT_BSR_ANYCRLF OFF CACHE BOOL
+    "ON=Backslash-R matches only LF CR and CRLF, OFF=Backslash-R matches all Unicode Linebreaks")
+
+SET(PCRE2_NEVER_BACKSLASH_C OFF CACHE BOOL
+    "If ON, backslash-C (upper case C) is locked out.")
+
+SET(PCRE2_SUPPORT_VALGRIND OFF CACHE BOOL
+    "Enable Valgrind support.")
+
+OPTION(PCRE2_SHOW_REPORT     "Show the final configuration report" ON)
+OPTION(PCRE2_BUILD_PCRE2GREP "Build pcre2grep" ON)
+OPTION(PCRE2_BUILD_TESTS     "Build the tests" ON)
+
+IF (MINGW)
+  OPTION(NON_STANDARD_LIB_PREFIX
+         "ON=Shared libraries built in mingw will be named pcre2.dll, etc., instead of libpcre2.dll, etc."
+         OFF)
+
+  OPTION(NON_STANDARD_LIB_SUFFIX
+         "ON=Shared libraries built in mingw will be named libpcre2-0.dll, etc., instead of libpcre2.dll, etc."
+         OFF)
+ENDIF(MINGW)
+
+IF(MSVC)
+  OPTION(PCRE2_STATIC_RUNTIME
+	"ON=Compile against the static runtime (/MT)."
+	OFF)
+  OPTION(INSTALL_MSVC_PDB
+         "ON=Install .pdb files built by MSVC, if generated"
+         OFF)
+ENDIF(MSVC)
+
+# bzip2 lib
+IF(BZIP2_FOUND)
+  OPTION (PCRE2_SUPPORT_LIBBZ2 "Enable support for linking pcre2grep with libbz2." ON)
+ENDIF(BZIP2_FOUND)
+IF(PCRE2_SUPPORT_LIBBZ2)
+  INCLUDE_DIRECTORIES(${BZIP2_INCLUDE_DIR})
+ENDIF(PCRE2_SUPPORT_LIBBZ2)
+
+# zlib
+IF(ZLIB_FOUND)
+  OPTION (PCRE2_SUPPORT_LIBZ "Enable support for linking pcre2grep with libz." ON)
+ENDIF(ZLIB_FOUND)
+IF(PCRE2_SUPPORT_LIBZ)
+  INCLUDE_DIRECTORIES(${ZLIB_INCLUDE_DIR})
+ENDIF(PCRE2_SUPPORT_LIBZ)
+
+# editline lib
+IF(EDITLINE_FOUND)
+  OPTION (PCRE2_SUPPORT_LIBEDIT  "Enable support for linking pcre2test with libedit." OFF)
+ENDIF(EDITLINE_FOUND)
+IF(PCRE2_SUPPORT_LIBEDIT)
+  INCLUDE_DIRECTORIES(${EDITLINE_INCLUDE_DIR})
+ENDIF(PCRE2_SUPPORT_LIBEDIT)
+
+# readline lib
+IF(READLINE_FOUND)
+  OPTION (PCRE2_SUPPORT_LIBREADLINE  "Enable support for linking pcre2test with libreadline." ON)
+ENDIF(READLINE_FOUND)
+IF(PCRE2_SUPPORT_LIBREADLINE)
+  INCLUDE_DIRECTORIES(${READLINE_INCLUDE_DIR})
+ENDIF(PCRE2_SUPPORT_LIBREADLINE)
+
+# Prepare build configuration
+
+IF(NOT BUILD_SHARED_LIBS)
+        SET(PCRE2_STATIC 1)
+ENDIF(NOT BUILD_SHARED_LIBS)
+
+IF(NOT PCRE2_BUILD_PCRE2_8 AND NOT PCRE2_BUILD_PCRE2_16 AND NOT PCRE2_BUILD_PCRE2_32)
+        MESSAGE(FATAL_ERROR "At least one of PCRE2_BUILD_PCRE2_8, PCRE2_BUILD_PCRE2_16 or PCRE2_BUILD_PCRE2_32 must be enabled")
+ENDIF(NOT PCRE2_BUILD_PCRE2_8 AND NOT PCRE2_BUILD_PCRE2_16 AND NOT PCRE2_BUILD_PCRE2_32)
+
+IF(PCRE2_BUILD_PCRE2_8)
+        SET(SUPPORT_PCRE2_8 1)
+ENDIF(PCRE2_BUILD_PCRE2_8)
+
+IF(PCRE2_BUILD_PCRE2_16)
+        SET(SUPPORT_PCRE2_16 1)
+ENDIF(PCRE2_BUILD_PCRE2_16)
+
+IF(PCRE2_BUILD_PCRE2_32)
+        SET(SUPPORT_PCRE2_32 1)
+ENDIF(PCRE2_BUILD_PCRE2_32)
+
+IF(PCRE2_BUILD_PCRE2GREP AND NOT PCRE2_BUILD_PCRE2_8)
+        MESSAGE(STATUS "** PCRE2_BUILD_PCRE2_8 must be enabled for the pcre2grep program")
+        SET(PCRE2_BUILD_PCRE2GREP OFF)
+ENDIF(PCRE2_BUILD_PCRE2GREP AND NOT PCRE2_BUILD_PCRE2_8)
+
+IF(PCRE2_SUPPORT_LIBREADLINE AND PCRE2_SUPPORT_LIBEDIT)
+        MESSAGE(FATAL_ERROR "Only one of libreadline or libeditline can be specified")
+ENDIF(PCRE2_SUPPORT_LIBREADLINE AND PCRE2_SUPPORT_LIBEDIT)
+
+IF(PCRE2_SUPPORT_BSR_ANYCRLF)
+        SET(BSR_ANYCRLF 1)
+ENDIF(PCRE2_SUPPORT_BSR_ANYCRLF)
+
+IF(PCRE2_NEVER_BACKSLASH_C)
+        SET(NEVER_BACKSLASH_C 1)
+ENDIF(PCRE2_NEVER_BACKSLASH_C)
+
+IF(PCRE2_SUPPORT_UNICODE)
+        SET(SUPPORT_UNICODE 1)
+ENDIF(PCRE2_SUPPORT_UNICODE)
+
+IF(PCRE2_SUPPORT_JIT)
+        SET(SUPPORT_JIT 1)
+ENDIF(PCRE2_SUPPORT_JIT)
+
+IF(PCRE2_SUPPORT_JIT_SEALLOC)
+        SET(CMAKE_REQUIRED_DEFINITIONS -D_GNU_SOURCE)
+	CHECK_SYMBOL_EXISTS(mkostemp stdlib.h REQUIRED)
+        UNSET(CMAKE_REQUIRED_DEFINITIONS)
+        IF(${REQUIRED})
+                IF(${CMAKE_SYSTEM_NAME} MATCHES Linux|NetBSD)
+                        ADD_DEFINITIONS(-D_GNU_SOURCE)
+                        SET(SLJIT_PROT_EXECUTABLE_ALLOCATOR 1)
+                ELSE(${CMAKE_SYSTEM_NAME} MATCHES Linux|NetBSD)
+                        MESSAGE(FATAL_ERROR "Your configuration is not supported")
+                ENDIF(${CMAKE_SYSTEM_NAME} MATCHES Linux|NetBSD)
+        ELSE(${REQUIRED})
+                SET(PCRE2_SUPPORT_JIT_SEALLOC OFF)
+        ENDIF(${REQUIRED})
+ENDIF(PCRE2_SUPPORT_JIT_SEALLOC)
+
+IF(PCRE2GREP_SUPPORT_JIT)
+        SET(SUPPORT_PCRE2GREP_JIT 1)
+ENDIF(PCRE2GREP_SUPPORT_JIT)
+
+IF(PCRE2GREP_SUPPORT_CALLOUT)
+        SET(SUPPORT_PCRE2GREP_CALLOUT 1)
+        IF(PCRE2GREP_SUPPORT_CALLOUT_FORK)
+                SET(SUPPORT_PCRE2GREP_CALLOUT_FORK 1)
+        ENDIF(PCRE2GREP_SUPPORT_CALLOUT_FORK)
+ENDIF(PCRE2GREP_SUPPORT_CALLOUT)
+
+IF(PCRE2_SUPPORT_VALGRIND)
+        SET(SUPPORT_VALGRIND 1)
+ENDIF(PCRE2_SUPPORT_VALGRIND)
+
+IF(PCRE2_DISABLE_PERCENT_ZT)
+        SET(DISABLE_PERCENT_ZT 1)
+ENDIF(PCRE2_DISABLE_PERCENT_ZT)
+
+# This next one used to reference ${READLINE_LIBRARY})
+# but I was advised to add the NCURSES test as well, along with
+# some modifications to cmake/FindReadline.cmake which should
+# make it possible to override the default if necessary. PH
+
+IF(PCRE2_SUPPORT_LIBREADLINE)
+        SET(SUPPORT_LIBREADLINE 1)
+        SET(PCRE2TEST_LIBS ${READLINE_LIBRARY} ${NCURSES_LIBRARY})
+ENDIF(PCRE2_SUPPORT_LIBREADLINE)
+
+# libedit is a plug-compatible alternative to libreadline
+
+IF(PCRE2_SUPPORT_LIBEDIT)
+        SET(SUPPORT_LIBEDIT 1)
+        SET(PCRE2TEST_LIBS ${EDITLINE_LIBRARY} ${NCURSES_LIBRARY})
+ENDIF(PCRE2_SUPPORT_LIBEDIT)
+
+IF(PCRE2_SUPPORT_LIBZ)
+        SET(SUPPORT_LIBZ 1)
+        SET(PCRE2GREP_LIBS ${PCRE2GREP_LIBS} ${ZLIB_LIBRARIES})
+ENDIF(PCRE2_SUPPORT_LIBZ)
+
+IF(PCRE2_SUPPORT_LIBBZ2)
+        SET(SUPPORT_LIBBZ2 1)
+        SET(PCRE2GREP_LIBS ${PCRE2GREP_LIBS} ${BZIP2_LIBRARIES})
+ENDIF(PCRE2_SUPPORT_LIBBZ2)
+
+SET(NEWLINE_DEFAULT "")
+
+IF(PCRE2_NEWLINE STREQUAL "CR")
+        SET(NEWLINE_DEFAULT "1")
+ENDIF(PCRE2_NEWLINE STREQUAL "CR")
+IF(PCRE2_NEWLINE STREQUAL "LF")
+        SET(NEWLINE_DEFAULT "2")
+ENDIF(PCRE2_NEWLINE STREQUAL "LF")
+IF(PCRE2_NEWLINE STREQUAL "CRLF")
+        SET(NEWLINE_DEFAULT "3")
+ENDIF(PCRE2_NEWLINE STREQUAL "CRLF")
+IF(PCRE2_NEWLINE STREQUAL "ANY")
+        SET(NEWLINE_DEFAULT "4")
+ENDIF(PCRE2_NEWLINE STREQUAL "ANY")
+IF(PCRE2_NEWLINE STREQUAL "ANYCRLF")
+        SET(NEWLINE_DEFAULT "5")
+ENDIF(PCRE2_NEWLINE STREQUAL "ANYCRLF")
+IF(PCRE2_NEWLINE STREQUAL "NUL")
+        SET(NEWLINE_DEFAULT "6")
+ENDIF(PCRE2_NEWLINE STREQUAL "NUL")
+
+IF(NEWLINE_DEFAULT STREQUAL "")
+        MESSAGE(FATAL_ERROR "The PCRE2_NEWLINE variable must be set to one of the following values: \"LF\", \"CR\", \"CRLF\", \"ANY\", \"ANYCRLF\".")
+ENDIF(NEWLINE_DEFAULT STREQUAL "")
+
+IF(PCRE2_EBCDIC)
+        SET(EBCDIC 1)
+ENDIF(PCRE2_EBCDIC)
+
+IF(PCRE2_EBCDIC_NL25)
+        SET(EBCDIC 1)
+        SET(EBCDIC_NL25 1)
+ENDIF(PCRE2_EBCDIC_NL25)
+
+# Output files
+
+CONFIGURE_FILE(config-cmake.h.in
+               ${PROJECT_BINARY_DIR}/config.h
+               @ONLY)
+
+# Parse version numbers and date out of configure.ac
+
+file(STRINGS ${PROJECT_SOURCE_DIR}/configure.ac
+  configure_lines
+  LIMIT_COUNT 50 # Read only the first 50 lines of the file
+)
+
+set(SEARCHED_VARIABLES "pcre2_major" "pcre2_minor" "pcre2_prerelease" "pcre2_date"
+  "libpcre2_posix_version" "libpcre2_8_version" "libpcre2_16_version" "libpcre2_32_version")
+foreach(configure_line ${configure_lines})
+    foreach(_substitution_variable ${SEARCHED_VARIABLES})
+        string(TOUPPER ${_substitution_variable} _substitution_variable_upper)
+        if (NOT ${_substitution_variable_upper})
+            string(REGEX MATCH "m4_define\\(${_substitution_variable}, *\\[(.*)\\]" MATCHED_STRING ${configure_line})
+            if (CMAKE_MATCH_1)
+                set(${_substitution_variable_upper} ${CMAKE_MATCH_1})
+            endif()
+        endif()
+    endforeach()
+endforeach()
+
+macro(PARSE_LIB_VERSION VARIABLE_PREFIX)
+  string(REPLACE ":" ";" ${VARIABLE_PREFIX}_VERSION_LIST ${${VARIABLE_PREFIX}_VERSION})
+  list(GET ${VARIABLE_PREFIX}_VERSION_LIST 0 ${VARIABLE_PREFIX}_VERSION_CURRENT)
+  list(GET ${VARIABLE_PREFIX}_VERSION_LIST 1 ${VARIABLE_PREFIX}_VERSION_REVISION)
+  list(GET ${VARIABLE_PREFIX}_VERSION_LIST 2 ${VARIABLE_PREFIX}_VERSION_AGE)
+
+  math(EXPR ${VARIABLE_PREFIX}_SOVERSION "${${VARIABLE_PREFIX}_VERSION_CURRENT} - ${${VARIABLE_PREFIX}_VERSION_AGE}")
+  math(EXPR ${VARIABLE_PREFIX}_MACHO_COMPATIBILITY_VERSION "${${VARIABLE_PREFIX}_VERSION_CURRENT} + 1")
+  math(EXPR ${VARIABLE_PREFIX}_MACHO_CURRENT_VERSION "${${VARIABLE_PREFIX}_VERSION_CURRENT} + 1")
+  set(${VARIABLE_PREFIX}_MACHO_CURRENT_VERSION "${${VARIABLE_PREFIX}_MACHO_CURRENT_VERSION}.${${VARIABLE_PREFIX}_VERSION_REVISION}}")
+  set(${VARIABLE_PREFIX}_VERSION "${${VARIABLE_PREFIX}_SOVERSION}.${${VARIABLE_PREFIX}_VERSION_AGE}.${${VARIABLE_PREFIX}_VERSION_REVISION}")
+endmacro()
+
+PARSE_LIB_VERSION(LIBPCRE2_POSIX)
+PARSE_LIB_VERSION(LIBPCRE2_8)
+PARSE_LIB_VERSION(LIBPCRE2_16)
+PARSE_LIB_VERSION(LIBPCRE2_32)
+
+CONFIGURE_FILE(src/pcre2.h.in
+               ${PROJECT_BINARY_DIR}/pcre2.h
+               @ONLY)
+
+# Make sure to not link debug libs
+# against release libs and vice versa
+IF(WIN32)
+  SET(CMAKE_DEBUG_POSTFIX "d")
+ENDIF(WIN32)
+
+# Generate pkg-config files
+
+SET(PACKAGE_VERSION "${PCRE2_MAJOR}.${PCRE2_MINOR}")
+SET(prefix ${CMAKE_INSTALL_PREFIX})
+
+SET(exec_prefix "\${prefix}")
+SET(libdir "\${exec_prefix}/${CMAKE_INSTALL_LIBDIR}")
+SET(includedir "\${prefix}/include")
+IF(WIN32 AND (CMAKE_BUILD_TYPE MATCHES Debug))
+  SET(LIB_POSTFIX ${CMAKE_DEBUG_POSTFIX})
+ENDIF()
+CONFIGURE_FILE(libpcre2-posix.pc.in libpcre2-posix.pc @ONLY)
+SET(pkg_config_files ${pkg_config_files} "${CMAKE_CURRENT_BINARY_DIR}/libpcre2-posix.pc")
+
+IF(PCRE2_BUILD_PCRE2_8)
+  CONFIGURE_FILE(libpcre2-8.pc.in libpcre2-8.pc @ONLY)
+  SET(pkg_config_files ${pkg_config_files} "${CMAKE_CURRENT_BINARY_DIR}/libpcre2-8.pc")
+  SET(enable_pcre2_8 "yes")
+ELSE()
+  SET(enable_pcre2_8 "no")
+ENDIF()
+
+IF(PCRE2_BUILD_PCRE2_16)
+  CONFIGURE_FILE(libpcre2-16.pc.in libpcre2-16.pc @ONLY)
+  SET(pkg_config_files ${pkg_config_files} "${CMAKE_CURRENT_BINARY_DIR}/libpcre2-16.pc")
+  SET(enable_pcre2_16 "yes")
+ELSE()
+  SET(enable_pcre2_16 "no")
+ENDIF()
+
+IF(PCRE2_BUILD_PCRE2_32)
+  CONFIGURE_FILE(libpcre2-32.pc.in libpcre2-32.pc @ONLY)
+  SET(pkg_config_files ${pkg_config_files} "${CMAKE_CURRENT_BINARY_DIR}/libpcre2-32.pc")
+  SET(enable_pcre2_32 "yes")
+ELSE()
+  SET(enable_pcre2_32 "no")
+ENDIF()
+
+CONFIGURE_FILE(pcre2-config.in pcre2-config @ONLY)
+
+# Character table generation
+
+OPTION(PCRE2_REBUILD_CHARTABLES "Rebuild char tables" OFF)
+IF(PCRE2_REBUILD_CHARTABLES)
+  ADD_EXECUTABLE(pcre2_dftables src/pcre2_dftables.c)
+  ADD_CUSTOM_COMMAND(
+    COMMENT "Generating character tables (pcre2_chartables.c) for current locale"
+    DEPENDS pcre2_dftables
+    COMMAND pcre2_dftables
+    ARGS        ${PROJECT_BINARY_DIR}/pcre2_chartables.c
+    OUTPUT      ${PROJECT_BINARY_DIR}/pcre2_chartables.c
+  )
+ELSE(PCRE2_REBUILD_CHARTABLES)
+  CONFIGURE_FILE(${PROJECT_SOURCE_DIR}/src/pcre2_chartables.c.dist
+                    ${PROJECT_BINARY_DIR}/pcre2_chartables.c
+                    COPYONLY)
+ENDIF(PCRE2_REBUILD_CHARTABLES)
+
+# Source code
+
+SET(PCRE2_HEADERS ${PROJECT_BINARY_DIR}/pcre2.h)
+
+SET(PCRE2_SOURCES
+  src/pcre2_auto_possess.c
+  ${PROJECT_BINARY_DIR}/pcre2_chartables.c
+  src/pcre2_compile.c
+  src/pcre2_config.c
+  src/pcre2_context.c
+  src/pcre2_convert.c
+  src/pcre2_dfa_match.c
+  src/pcre2_error.c
+  src/pcre2_extuni.c
+  src/pcre2_find_bracket.c
+  src/pcre2_jit_compile.c
+  src/pcre2_maketables.c
+  src/pcre2_match.c
+  src/pcre2_match_data.c
+  src/pcre2_newline.c
+  src/pcre2_ord2utf.c
+  src/pcre2_pattern_info.c
+  src/pcre2_script_run.c
+  src/pcre2_serialize.c
+  src/pcre2_string_utils.c
+  src/pcre2_study.c
+  src/pcre2_substitute.c
+  src/pcre2_substring.c
+  src/pcre2_tables.c
+  src/pcre2_ucd.c
+  src/pcre2_valid_utf.c
+  src/pcre2_xclass.c
+)
+
+SET(PCRE2POSIX_HEADERS src/pcre2posix.h)
+SET(PCRE2POSIX_SOURCES src/pcre2posix.c)
+
+IF(MINGW AND NOT PCRE2_STATIC)
+IF (EXISTS ${PROJECT_SOURCE_DIR}/pcre2.rc)
+ADD_CUSTOM_COMMAND(OUTPUT ${PROJECT_SOURCE_DIR}/pcre2.o
+PRE-LINK
+COMMAND windres ARGS pcre2.rc pcre2.o
+WORKING_DIRECTORY ${PROJECT_SOURCE_DIR}
+COMMENT Using pcre2 coff info in mingw build)
+SET(PCRE2_SOURCES
+  ${PCRE2_SOURCES} ${PROJECT_SOURCE_DIR}/pcre2.o
+)
+ENDIF(EXISTS ${PROJECT_SOURCE_DIR}/pcre2.rc)
+IF (EXISTS ${PROJECT_SOURCE_DIR}/pcre2posix.rc)
+ADD_CUSTOM_COMMAND(OUTPUT ${PROJECT_SOURCE_DIR}/pcre2posix.o
+PRE-LINK
+COMMAND windres ARGS pcre2posix.rc pcre2posix.o
+WORKING_DIRECTORY ${PROJECT_SOURCE_DIR}
+COMMENT Using pcre2posix coff info in mingw build)
+SET(PCRE2POSIX_SOURCES
+  ${PCRE2POSIX_SOURCES} ${PROJECT_SOURCE_DIR}/pcre2posix.o
+)
+ENDIF(EXISTS ${PROJECT_SOURCE_DIR}/pcre2posix.rc)
+ENDIF(MINGW AND NOT PCRE2_STATIC)
+
+IF(MSVC AND NOT PCRE2_STATIC)
+IF (EXISTS ${PROJECT_SOURCE_DIR}/pcre2.rc)
+SET(PCRE2_SOURCES
+  ${PCRE2_SOURCES} pcre2.rc)
+ENDIF(EXISTS ${PROJECT_SOURCE_DIR}/pcre2.rc)
+IF (EXISTS ${PROJECT_SOURCE_DIR}/pcre2posix.rc)
+SET(PCRE2POSIX_SOURCES
+  ${PCRE2POSIX_SOURCES} pcre2posix.rc)
+ENDIF (EXISTS ${PROJECT_SOURCE_DIR}/pcre2posix.rc)
+ENDIF(MSVC AND NOT PCRE2_STATIC)
+
+# Fix static compilation with MSVC: https://bugs.exim.org/show_bug.cgi?id=1681
+# This code was taken from the CMake wiki, not from WebM.
+
+IF(MSVC AND PCRE2_STATIC_RUNTIME)
+  MESSAGE(STATUS "** MSVC and PCRE2_STATIC_RUNTIME: modifying compiler flags to use static runtime library")
+  foreach(flag_var
+          CMAKE_C_FLAGS CMAKE_C_FLAGS_DEBUG CMAKE_C_FLAGS_RELEASE
+          CMAKE_C_FLAGS_MINSIZEREL CMAKE_C_FLAGS_RELWITHDEBINFO)
+    string(REGEX REPLACE "/MD" "/MT" ${flag_var} "${${flag_var}}")
+  endforeach()
+ENDIF(MSVC AND PCRE2_STATIC_RUNTIME)
+
+# Build setup
+
+ADD_DEFINITIONS(-DHAVE_CONFIG_H)
+
+IF(MSVC)
+  ADD_DEFINITIONS(-D_CRT_SECURE_NO_DEPRECATE -D_CRT_SECURE_NO_WARNINGS)
+ENDIF(MSVC)
+
+SET(CMAKE_INCLUDE_CURRENT_DIR 1)
+
+SET(targets)
+
+# 8-bit library
+
+IF(PCRE2_BUILD_PCRE2_8)
+ADD_LIBRARY(pcre2-8 ${PCRE2_HEADERS} ${PCRE2_SOURCES} ${PROJECT_BINARY_DIR}/config.h)
+SET_TARGET_PROPERTIES(pcre2-8 PROPERTIES
+  COMPILE_DEFINITIONS PCRE2_CODE_UNIT_WIDTH=8
+  MACHO_COMPATIBILITY_VERSION "${LIBPCRE2_8_MACHO_COMPATIBILITY_VERSION}"
+  MACHO_CURRENT_VERSION "${LIBPCRE2_8_MACHO_CURRENT_VERSION}"
+  VERSION ${LIBPCRE2_8_VERSION}
+  SOVERSION ${LIBPCRE2_8_SOVERSION})
+SET(targets ${targets} pcre2-8)
+ADD_LIBRARY(pcre2-posix ${PCRE2POSIX_HEADERS} ${PCRE2POSIX_SOURCES})
+SET_TARGET_PROPERTIES(pcre2-posix PROPERTIES
+  COMPILE_DEFINITIONS PCRE2_CODE_UNIT_WIDTH=8
+  MACHO_COMPATIBILITY_VERSION "${LIBPCRE2_POSIX_MACHO_COMPATIBILITY_VERSION}"
+  MACHO_CURRENT_VERSION "${LIBPCRE2_POSIX_MACHO_CURRENT_VERSION}"
+  VERSION ${LIBPCRE2_POSIX_VERSION}
+  SOVERSION ${LIBPCRE2_POSIX_SOVERSION})
+SET(targets ${targets} pcre2-posix)
+TARGET_LINK_LIBRARIES(pcre2-posix pcre2-8)
+
+IF(MINGW AND NOT PCRE2_STATIC)
+  IF(NON_STANDARD_LIB_PREFIX)
+    SET_TARGET_PROPERTIES(pcre2-8 pcre2-posix PROPERTIES PREFIX "")
+  ENDIF(NON_STANDARD_LIB_PREFIX)
+  IF(NON_STANDARD_LIB_SUFFIX)
+    SET_TARGET_PROPERTIES(pcre2-8 pcre2-posix PROPERTIES SUFFIX "-0.dll")
+  ENDIF(NON_STANDARD_LIB_SUFFIX)
+ENDIF(MINGW AND NOT PCRE2_STATIC)
+ENDIF(PCRE2_BUILD_PCRE2_8)
+
+# 16-bit library
+
+IF(PCRE2_BUILD_PCRE2_16)
+ADD_LIBRARY(pcre2-16 ${PCRE2_HEADERS} ${PCRE2_SOURCES} ${PROJECT_BINARY_DIR}/config.h)
+SET_TARGET_PROPERTIES(pcre2-16 PROPERTIES
+  COMPILE_DEFINITIONS PCRE2_CODE_UNIT_WIDTH=16
+  MACHO_COMPATIBILITY_VERSION "${LIBPCRE2_32_MACHO_COMPATIBILITY_VERSION}"
+  MACHO_CURRENT_VERSION "${LIBPCRE2_32_MACHO_CURRENT_VERSION}"
+  VERSION ${LIBPCRE2_16_VERSION}
+  SOVERSION ${LIBPCRE2_16_SOVERSION})
+SET(targets ${targets} pcre2-16)
+
+IF(MINGW AND NOT PCRE2_STATIC)
+  IF(NON_STANDARD_LIB_PREFIX)
+    SET_TARGET_PROPERTIES(pcre2-16 PROPERTIES PREFIX "")
+  ENDIF(NON_STANDARD_LIB_PREFIX)
+  IF(NON_STANDARD_LIB_SUFFIX)
+    SET_TARGET_PROPERTIES(pcre2-16 PROPERTIES SUFFIX "-0.dll")
+  ENDIF(NON_STANDARD_LIB_SUFFIX)
+ENDIF(MINGW AND NOT PCRE2_STATIC)
+ENDIF(PCRE2_BUILD_PCRE2_16)
+
+# 32-bit library
+
+IF(PCRE2_BUILD_PCRE2_32)
+ADD_LIBRARY(pcre2-32 ${PCRE2_HEADERS} ${PCRE2_SOURCES} ${PROJECT_BINARY_DIR}/config.h)
+SET_TARGET_PROPERTIES(pcre2-32 PROPERTIES
+  COMPILE_DEFINITIONS PCRE2_CODE_UNIT_WIDTH=32
+  MACHO_COMPATIBILITY_VERSION "${LIBPCRE2_32_MACHO_COMPATIBILITY_VERSION}"
+  MACHO_CURRENT_VERSION "${LIBPCRE2_32_MACHO_CURRENT_VERSION}"
+  VERSION ${LIBPCRE2_32_VERSION}
+  SOVERSION ${LIBPCRE2_32_SOVERSION})
+SET(targets ${targets} pcre2-32)
+
+IF(MINGW AND NOT PCRE2_STATIC)
+  IF(NON_STANDARD_LIB_PREFIX)
+    SET_TARGET_PROPERTIES(pcre2-32 PROPERTIES PREFIX "")
+  ENDIF(NON_STANDARD_LIB_PREFIX)
+  IF(NON_STANDARD_LIB_SUFFIX)
+    SET_TARGET_PROPERTIES(pcre2-32 PROPERTIES SUFFIX "-0.dll")
+  ENDIF(NON_STANDARD_LIB_SUFFIX)
+ENDIF(MINGW AND NOT PCRE2_STATIC)
+ENDIF(PCRE2_BUILD_PCRE2_32)
+
+# Executables
+
+IF(PCRE2_BUILD_PCRE2GREP)
+  ADD_EXECUTABLE(pcre2grep src/pcre2grep.c)
+  SET_PROPERTY(TARGET pcre2grep
+    PROPERTY COMPILE_DEFINITIONS PCRE2_CODE_UNIT_WIDTH=8)
+  SET(targets ${targets} pcre2grep)
+  TARGET_LINK_LIBRARIES(pcre2grep pcre2-posix ${PCRE2GREP_LIBS})
+ENDIF(PCRE2_BUILD_PCRE2GREP)
+
+# Testing
+
+IF(PCRE2_BUILD_TESTS)
+  ENABLE_TESTING()
+
+  SET(PCRE2TEST_SOURCES src/pcre2test.c)
+
+  IF(MSVC)
+    # This is needed to avoid a stack overflow error in the standard tests. The
+    # flag should be indicated with a forward-slash instead of a hyphen, but
+    # then CMake treats it as a file path.
+    SET(PCRE2TEST_LINKER_FLAGS -STACK:2500000)
+  ENDIF(MSVC)
+
+  ADD_EXECUTABLE(pcre2test ${PCRE2TEST_SOURCES})
+  SET(targets ${targets} pcre2test)
+  IF(PCRE2_BUILD_PCRE2_8)
+    LIST(APPEND PCRE2TEST_LIBS pcre2-posix pcre2-8)
+  ENDIF(PCRE2_BUILD_PCRE2_8)
+  IF(PCRE2_BUILD_PCRE2_16)
+    LIST(APPEND PCRE2TEST_LIBS pcre2-16)
+  ENDIF(PCRE2_BUILD_PCRE2_16)
+  IF(PCRE2_BUILD_PCRE2_32)
+    LIST(APPEND PCRE2TEST_LIBS pcre2-32)
+  ENDIF(PCRE2_BUILD_PCRE2_32)
+  TARGET_LINK_LIBRARIES(pcre2test ${PCRE2TEST_LIBS} ${PCRE2TEST_LINKER_FLAGS})
+
+  IF(PCRE2_SUPPORT_JIT)
+    ADD_EXECUTABLE(pcre2_jit_test src/pcre2_jit_test.c)
+    SET(targets ${targets} pcre2_jit_test)
+    SET(PCRE2_JIT_TEST_LIBS )
+    IF(PCRE2_BUILD_PCRE2_8)
+      LIST(APPEND PCRE2_JIT_TEST_LIBS pcre2-8)
+    ENDIF(PCRE2_BUILD_PCRE2_8)
+    IF(PCRE2_BUILD_PCRE2_16)
+      LIST(APPEND PCRE2_JIT_TEST_LIBS pcre2-16)
+    ENDIF(PCRE2_BUILD_PCRE2_16)
+    IF(PCRE2_BUILD_PCRE2_32)
+      LIST(APPEND PCRE2_JIT_TEST_LIBS pcre2-32)
+    ENDIF(PCRE2_BUILD_PCRE2_32)
+    TARGET_LINK_LIBRARIES(pcre2_jit_test ${PCRE2_JIT_TEST_LIBS})
+  ENDIF(PCRE2_SUPPORT_JIT)
+
+  # exes in Debug location tested by the RunTest and RunGrepTest shell scripts
+  # via "make test"
+
+  # The commented out code below provokes a warning about future removal
+  # of the facility, and requires policy CMP0026 to be set to "OLD". I have
+  # got fed-up with the warnings, but my plea for help on the mailing list
+  # produced no response. So, I've hacked. The new code below seems to work on
+  # Linux.
+
+#  IF(PCRE2_BUILD_PCRE2GREP)
+#    GET_TARGET_PROPERTY(PCRE2GREP_EXE pcre2grep DEBUG_LOCATION)
+#  ENDIF(PCRE2_BUILD_PCRE2GREP)
+#
+#  GET_TARGET_PROPERTY(PCRE2TEST_EXE pcre2test DEBUG_LOCATION)
+
+  IF(PCRE2_BUILD_PCRE2GREP)
+    SET(PCRE2GREP_EXE $<TARGET_FILE:pcre2grep>)
+  ENDIF(PCRE2_BUILD_PCRE2GREP)
+
+  SET(PCRE2TEST_EXE $<TARGET_FILE:pcre2test>)
+
+
+# =================================================
+  # Write out a CTest configuration file
+  #
+  FILE(WRITE ${PROJECT_BINARY_DIR}/CTestCustom.ctest
+  "# This is a generated file.
+MESSAGE(\"When testing is complete, review test output in the
+\\\"${PROJECT_BINARY_DIR}/Testing/Temporary\\\" folder.\")
+MESSAGE(\" \")
+")
+
+  FILE(WRITE ${PROJECT_BINARY_DIR}/pcre2_test.sh
+  "#! /bin/sh
+# This is a generated file.
+. ${PROJECT_SOURCE_DIR}/RunTest
+if test \"$?\" != \"0\"; then exit 1; fi
+# End
+")
+
+  IF(UNIX)
+    ADD_TEST(pcre2_test sh ${PROJECT_BINARY_DIR}/pcre2_test.sh)
+  ENDIF(UNIX)
+
+  IF(PCRE2_BUILD_PCRE2GREP)
+    FILE(WRITE ${PROJECT_BINARY_DIR}/pcre2_grep_test.sh
+    "#! /bin/sh
+# This is a generated file.
+. ${PROJECT_SOURCE_DIR}/RunGrepTest
+if test \"$?\" != \"0\"; then exit 1; fi
+# End
+")
+
+    IF(UNIX)
+      ADD_TEST(pcre2_grep_test sh ${PROJECT_BINARY_DIR}/pcre2_grep_test.sh)
+    ENDIF(UNIX)
+  ENDIF(PCRE2_BUILD_PCRE2GREP)
+
+  IF(WIN32)
+    # Provide environment for executing the bat file version of RunTest
+    FILE(TO_NATIVE_PATH ${PROJECT_SOURCE_DIR} winsrc)
+    FILE(TO_NATIVE_PATH ${PROJECT_BINARY_DIR} winbin)
+    FILE(TO_NATIVE_PATH ${PCRE2TEST_EXE} winexe)
+
+    FILE(WRITE ${PROJECT_BINARY_DIR}/pcre2_test.bat
+    "\@REM This is a generated file.
+\@echo off
+setlocal
+SET srcdir=\"${winsrc}\"
+# The next line was replaced by the following one after a user comment.
+# SET pcre2test=\"${winexe}\"
+SET pcre2test=\"${winbin}\\pcre2test.exe\"
+if not [%CMAKE_CONFIG_TYPE%]==[] SET pcre2test=\"${winbin}\\%CMAKE_CONFIG_TYPE%\\pcre2test.exe\"
+call %srcdir%\\RunTest.Bat
+if errorlevel 1 exit /b 1
+echo RunTest.bat tests successfully completed
+")
+
+  ADD_TEST(NAME pcre2_test_bat
+  COMMAND pcre2_test.bat)
+  SET_TESTS_PROPERTIES(pcre2_test_bat PROPERTIES
+  PASS_REGULAR_EXPRESSION "RunTest\\.bat tests successfully completed")
+
+    IF("$ENV{OSTYPE}" STREQUAL "msys")
+      # Both the sh and bat file versions of RunTest are run if make test is used
+      # in msys
+      ADD_TEST(pcre2_test_sh    sh.exe ${PROJECT_BINARY_DIR}/pcre2_test.sh)
+      IF(PCRE2_BUILD_PCRE2GREP)
+        ADD_TEST(pcre2_grep_test  sh.exe ${PROJECT_BINARY_DIR}/pcre2_grep_test.sh)
+      ENDIF(PCRE2_BUILD_PCRE2GREP)
+    ENDIF("$ENV{OSTYPE}" STREQUAL "msys")
+  ENDIF(WIN32)
+
+  # Changed to accommodate testing whichever location was just built
+
+  IF(PCRE2_SUPPORT_JIT)
+    ADD_TEST(pcre2_jit_test pcre2_jit_test)
+  ENDIF(PCRE2_SUPPORT_JIT)
+
+ENDIF(PCRE2_BUILD_TESTS)
+
+# Installation
+
+SET(CMAKE_INSTALL_ALWAYS 1)
+
+INSTALL(TARGETS ${targets}
+        RUNTIME DESTINATION bin
+        LIBRARY DESTINATION ${CMAKE_INSTALL_LIBDIR}
+        ARCHIVE DESTINATION ${CMAKE_INSTALL_LIBDIR})
+INSTALL(FILES ${pkg_config_files} DESTINATION ${CMAKE_INSTALL_LIBDIR}/pkgconfig)
+INSTALL(FILES "${CMAKE_CURRENT_BINARY_DIR}/pcre2-config"
+  DESTINATION bin
+  # Set 0755 permissions
+  PERMISSIONS OWNER_WRITE OWNER_READ OWNER_EXECUTE GROUP_READ GROUP_EXECUTE WORLD_READ WORLD_EXECUTE)
+
+INSTALL(FILES ${PCRE2_HEADERS} ${PCRE2POSIX_HEADERS} DESTINATION include)
+
+FILE(GLOB html ${PROJECT_SOURCE_DIR}/doc/html/*.html)
+FILE(GLOB man1 ${PROJECT_SOURCE_DIR}/doc/*.1)
+FILE(GLOB man3 ${PROJECT_SOURCE_DIR}/doc/*.3)
+
+FOREACH(man ${man3})
+        GET_FILENAME_COMPONENT(man_tmp ${man} NAME)
+        SET(man3_new ${man3} ${man})
+ENDFOREACH(man ${man3})
+SET(man3 ${man3_new})
+
+INSTALL(FILES ${man1} DESTINATION man/man1)
+INSTALL(FILES ${man3} DESTINATION man/man3)
+INSTALL(FILES ${html} DESTINATION share/doc/pcre2/html)
+
+IF(MSVC AND INSTALL_MSVC_PDB)
+    INSTALL(FILES ${PROJECT_BINARY_DIR}/pcre2.pdb
+                  ${PROJECT_BINARY_DIR}/pcre2posix.pdb
+            DESTINATION bin
+            CONFIGURATIONS RelWithDebInfo)
+    INSTALL(FILES ${PROJECT_BINARY_DIR}/pcre2d.pdb
+                  ${PROJECT_BINARY_DIR}/pcre2posixd.pdb
+            DESTINATION bin
+            CONFIGURATIONS Debug)
+ENDIF(MSVC AND INSTALL_MSVC_PDB)
+
+# Help, only for nice output
+IF(BUILD_SHARED_LIBS)
+  SET(BUILD_STATIC_LIBS OFF)
+ELSE(BUILD_SHARED_LIBS)
+  SET(BUILD_STATIC_LIBS ON)
+ENDIF(BUILD_SHARED_LIBS)
+
+IF(PCRE2_HEAP_MATCH_RECURSE)
+  MESSAGE(WARNING "HEAP_MATCH_RECURSE is obsolete and does nothing.")
+ENDIF(PCRE2_HEAP_MATCH_RECURSE)
+
+IF(PCRE2_SHOW_REPORT)
+  STRING(TOUPPER "${CMAKE_BUILD_TYPE}" buildtype)
+  IF (CMAKE_C_FLAGS)
+    SET(cfsp " ")
+  ENDIF(CMAKE_C_FLAGS)
+  MESSAGE(STATUS "")
+  MESSAGE(STATUS "")
+  MESSAGE(STATUS "PCRE2-${PCRE2_MAJOR}.${PCRE2_MINOR} configuration summary:")
+  MESSAGE(STATUS "")
+  MESSAGE(STATUS "  Install prefix .................. : ${CMAKE_INSTALL_PREFIX}")
+  MESSAGE(STATUS "  C compiler ...................... : ${CMAKE_C_COMPILER}")
+  MESSAGE(STATUS "  C compiler flags ................ : ${CMAKE_C_FLAGS}${cfsp}${CMAKE_C_FLAGS_${buildtype}}")
+  MESSAGE(STATUS "")
+  MESSAGE(STATUS "  Build 8 bit PCRE2 library ....... : ${PCRE2_BUILD_PCRE2_8}")
+  MESSAGE(STATUS "  Build 16 bit PCRE2 library ...... : ${PCRE2_BUILD_PCRE2_16}")
+  MESSAGE(STATUS "  Build 32 bit PCRE2 library ...... : ${PCRE2_BUILD_PCRE2_32}")
+  MESSAGE(STATUS "  Enable JIT compiling support .... : ${PCRE2_SUPPORT_JIT}")
+  MESSAGE(STATUS "  Use SELinux allocator in JIT .... : ${PCRE2_SUPPORT_JIT_SEALLOC}")
+  MESSAGE(STATUS "  Enable Unicode support .......... : ${PCRE2_SUPPORT_UNICODE}")
+  MESSAGE(STATUS "  Newline char/sequence ........... : ${PCRE2_NEWLINE}")
+  MESSAGE(STATUS "  \\R matches only ANYCRLF ......... : ${PCRE2_SUPPORT_BSR_ANYCRLF}")
+  MESSAGE(STATUS "  \\C is disabled .................. : ${PCRE2_NEVER_BACKSLASH_C}")
+  MESSAGE(STATUS "  EBCDIC coding ................... : ${PCRE2_EBCDIC}")
+  MESSAGE(STATUS "  EBCDIC coding with NL=0x25 ...... : ${PCRE2_EBCDIC_NL25}")
+  MESSAGE(STATUS "  Rebuild char tables ............. : ${PCRE2_REBUILD_CHARTABLES}")
+  MESSAGE(STATUS "  Internal link size .............. : ${PCRE2_LINK_SIZE}")
+  MESSAGE(STATUS "  Parentheses nest limit .......... : ${PCRE2_PARENS_NEST_LIMIT}")
+  MESSAGE(STATUS "  Heap limit ...................... : ${PCRE2_HEAP_LIMIT}")
+  MESSAGE(STATUS "  Match limit ..................... : ${PCRE2_MATCH_LIMIT}")
+  MESSAGE(STATUS "  Match depth limit ............... : ${PCRE2_MATCH_LIMIT_DEPTH}")
+  MESSAGE(STATUS "  Build shared libs ............... : ${BUILD_SHARED_LIBS}")
+  MESSAGE(STATUS "  Build static libs ............... : ${BUILD_STATIC_LIBS}")
+  MESSAGE(STATUS "  Build pcre2grep ................. : ${PCRE2_BUILD_PCRE2GREP}")
+  MESSAGE(STATUS "  Enable JIT in pcre2grep ......... : ${PCRE2GREP_SUPPORT_JIT}")
+  MESSAGE(STATUS "  Enable callouts in pcre2grep .... : ${PCRE2GREP_SUPPORT_CALLOUT}")
+  MESSAGE(STATUS "  Enable callout fork in pcre2grep. : ${PCRE2GREP_SUPPORT_CALLOUT_FORK}")
+  MESSAGE(STATUS "  Buffer size for pcre2grep ....... : ${PCRE2GREP_BUFSIZE}")
+  MESSAGE(STATUS "  Build tests (implies pcre2test .. : ${PCRE2_BUILD_TESTS}")
+  MESSAGE(STATUS "               and pcre2grep)")
+  IF(ZLIB_FOUND)
+    MESSAGE(STATUS "  Link pcre2grep with libz ........ : ${PCRE2_SUPPORT_LIBZ}")
+  ELSE(ZLIB_FOUND)
+    MESSAGE(STATUS "  Link pcre2grep with libz ........ : Library not found" )
+  ENDIF(ZLIB_FOUND)
+  IF(BZIP2_FOUND)
+    MESSAGE(STATUS "  Link pcre2grep with libbz2 ...... : ${PCRE2_SUPPORT_LIBBZ2}")
+  ELSE(BZIP2_FOUND)
+    MESSAGE(STATUS "  Link pcre2grep with libbz2 ...... : Library not found" )
+  ENDIF(BZIP2_FOUND)
+  IF(EDITLINE_FOUND)
+    MESSAGE(STATUS "  Link pcre2test with libeditline . : ${PCRE2_SUPPORT_LIBEDIT}")
+  ELSE(EDITLINE_FOUND)
+    MESSAGE(STATUS "  Link pcre2test with libeditline . : Library not found" )
+  ENDIF(EDITLINE_FOUND)
+  IF(READLINE_FOUND)
+    MESSAGE(STATUS "  Link pcre2test with libreadline . : ${PCRE2_SUPPORT_LIBREADLINE}")
+  ELSE(READLINE_FOUND)
+    MESSAGE(STATUS "  Link pcre2test with libreadline . : Library not found" )
+  ENDIF(READLINE_FOUND)
+  MESSAGE(STATUS "  Support Valgrind .................: ${PCRE2_SUPPORT_VALGRIND}")
+  IF(PCRE2_DISABLE_PERCENT_ZT)
+    MESSAGE(STATUS "  Use %zu and %td ..................: OFF" )
+  ELSE(PCRE2_DISABLE_PERCENT_ZT)
+    MESSAGE(STATUS "  Use %zu and %td ..................: AUTO" )
+  ENDIF(PCRE2_DISABLE_PERCENT_ZT)
+
+  IF(MINGW AND NOT PCRE2_STATIC)
+    MESSAGE(STATUS "  Non-standard dll names (prefix) . : ${NON_STANDARD_LIB_PREFIX}")
+    MESSAGE(STATUS "  Non-standard dll names (suffix) . : ${NON_STANDARD_LIB_SUFFIX}")
+  ENDIF(MINGW AND NOT PCRE2_STATIC)
+
+  IF(MSVC)
+    MESSAGE(STATUS "  Install MSVC .pdb files ..........: ${INSTALL_MSVC_PDB}")
+  ENDIF(MSVC)
+
+  MESSAGE(STATUS "")
+ENDIF(PCRE2_SHOW_REPORT)
+
+# end CMakeLists.txt

src/regex/pcre2/COPYING

@@ -0,0 +1,5 @@
+PCRE2 LICENCE
+
+Please see the file LICENCE in the PCRE2 distribution for licensing details.
+
+End

src/regex/pcre2/ChangeLog

@@ -0,0 +1,2487 @@
+Change Log for PCRE2
+--------------------
+
+
+Version 10.37 26-May-2021
+-------------------------
+
+1. Change RunGrepTest to use tr instead of sed when testing with binary
+zero bytes, because sed varies a lot from system to system and has problems
+with binary zeros. This is from Bugzilla #2681. Patch from Jeremie
+Courreges-Anglas via Nam Nguyen. This fixes RunGrepTest for OpenBSD. Later:
+it broke it for at least one version of Solaris, where tr can't handle binary
+zeros. However, that system had /usr/xpg4/bin/tr installed, which works OK, so
+RunGrepTest now checks for that command and uses it if found.
+
+2. Compiling with gcc 10.2's -fanalyzer option showed up a hypothetical problem
+with a NULL dereference. I don't think this case could ever occur in practice,
+but I have put in a check in order to get rid of the compiler error.
+
+3. An alternative patch for CMakeLists.txt because 10.36 #4 breaks CMake on
+Windows. Patch from email@cs-ware.de fixes bugzilla #2688.
+
+4. Two bugs related to over-large numbers have been fixed so the behaviour is
+now the same as Perl.
+
+  (a) A pattern such as /\214748364/ gave an overflow error instead of being
+  treated as the octal number \214 followed by literal digits.
+
+  (b) A sequence such as {65536 that has no terminating } so is not a
+  quantifier was nevertheless complaining that a quantifier number was too big.
+
+5. A run of autoconf suggested that configure.ac was out-of-date with respect
+to the lastest autoconf. Running autoupdate made some valid changes, some valid
+suggestions, and also some invalid changes, which were fixed by hand. Autoconf
+now runs clean and the resulting "configure" seems to work, so I hope nothing
+is broken. Later: the requirement for autoconf 2.70 broke some automatic test
+robots. It doesn't seem to be necessary: trying a reduction to 2.60.
+
+6. The pattern /a\K.(?0)*/ when matched against "abac" by the interpreter gave
+the answer "bac", whereas Perl and JIT both yield "c". This was because the
+effect of \K was not propagating back from the full pattern recursion. Other
+recursions such as /(a\K.(?1)*)/ did not have this problem.
+
+7. Restore single character repetition optimization in JIT. Currently fewer
+character repetitions are optimized than in 10.34.
+
+8. When the names of the functions in the POSIX wrapper were changed to
+pcre2_regcomp() etc. (see change 10.33 #4 below), functions with the original
+names were left in the library so that pre-compiled programs would still work.
+However, this has proved troublesome when programs link with several libraries,
+some of which use PCRE2 via the POSIX interface while others use a native POSIX
+library. For this reason, the POSIX function names are removed in this release.
+The macros in pcre2posix.h should ensure that re-compiling fixes any programs
+that haven't been compiled since before 10.33.
+
+
+Version 10.36 04-December-2020
+------------------------------
+
+1. Add CET_CFLAGS so that when Intel CET is enabled, pass -mshstk to
+compiler. This fixes https://bugs.exim.org/show_bug.cgi?id=2578. Patch for
+Makefile.am and configure.ac by H.J. Lu. Equivalent patch for CMakeLists.txt
+invented by PH.
+
+2. Fix inifinite loop when a single byte newline is searched in JIT when
+invalid utf8 mode is enabled.
+
+3. Updated CMakeLists.txt with patch from Wolfgang Stöggl (Bugzilla #2584):
+
+  - Include GNUInstallDirs and use ${CMAKE_INSTALL_LIBDIR} instead of hardcoded
+    lib. This allows differentiation between lib and lib64.
+    CMAKE_INSTALL_LIBDIR is used for installation of libraries and also for
+    pkgconfig file generation.
+
+  - Add the version of PCRE2 to the configuration summary like ./configure
+    does.
+
+  - Fix typo: MACTHED_STRING->MATCHED_STRING
+
+4. Updated CMakeLists.txt with another patch from Wolfgang Stöggl (Bugzilla
+#2588):
+
+  - Add escaped double quotes around include directory in CMakeLists.txt to
+    allow spaces in directory names.
+
+  - This fixes a cmake error, if the path of the pcre2 source contains a space.
+
+5. Updated CMakeLists.txt with a patch from B. Scott Michel: CMake's
+documentation suggests using CHECK_SYMBOL_EXISTS over CHECK_FUNCTION_EXIST.
+Moreover, these functions come from specific header files, which need to be
+specified (and, thankfully, are the same on both the Linux and WinXX
+platforms.)
+
+6. Added a (uint32_t) cast to prevent a compiler warning in pcre2_compile.c.
+
+7. Applied a patch from Wolfgang Stöggl (Bugzilla #2600) to fix postfix for
+debug Windows builds using CMake. This also updated configure so that it
+generates *.pc files and pcre2-config with the same content, as in the past.
+
+8. If a pattern ended with (?(VERSION=n.d where n is any number but d is just a
+single digit, the code unit beyond d was being read (i.e. there was a read
+buffer overflow). Fixes ClusterFuzz 23779.
+
+9. After the rework in r1235, certain character ranges were incorrectly
+handled by an optimization in JIT. Furthermore a wrong offset was used to
+read a value from a buffer which could lead to memory overread.
+
+10. Unnoticed for many years was the fact that delimiters other than / in the
+testinput1 and testinput4 files could cause incorrect behaviour when these
+files were processed by perltest.sh. There were several tests that used quotes
+as delimiters, and it was just luck that they didn't go wrong with perltest.sh.
+All the patterns in testinput1 and testinput4 now use / as their delimiter.
+This fixes Bugzilla #2641.
+
+11. Perl has started to give an error for \K within lookarounds (though there
+are cases where it doesn't). PCRE2 still allows this, so the tests that include
+this case have been moved from test 1 to test 2.
+
+12. Further to 10 above, pcre2test has been updated to detect and grumble if a
+delimiter other than / is used after #perltest.
+
+13. Fixed a bug with PCRE2_MATCH_INVALID_UTF in 8-bit mode when PCRE2_CASELESS
+was set and PCRE2_NO_START_OPTIMIZE was not set. The optimization for finding
+the start of a match was not resetting correctly after a failed match on the
+first valid fragment of the subject, possibly causing incorrect "no match"
+returns on subsequent fragments. For example, the pattern /A/ failed to match
+the subject \xe5A. Fixes Bugzilla #2642.
+
+14. Fixed a bug in character set matching when JIT is enabled and both unicode
+scripts and unicode classes are present at the same time.
+
+15. Added GNU grep's -m (aka --max-count) option to pcre2grep.
+
+16. Refactored substitution processing in pcre2grep strings, both for the -O
+option and when dealing with callouts. There is now a single function that
+handles $ expansion in all cases (instead of multiple copies of almost
+identical code). This means that the same escape sequences are available
+everywhere, which was not previously the case. At the same time, the escape
+sequences $x{...} and $o{...} have been introduced, to allow for characters
+whose code points are greater than 255 in Unicode mode.
+
+17. Applied the patch from Bugzilla #2628 to RunGrepTest. This does an explicit
+test for a version of sed that can handle binary zero, instead of assuming that
+any Linux version will work. Later: replaced $(...) by `...` because not all
+shells recognize the former.
+
+18. Fixed a word boundary check bug in JIT when partial matching is enabled.
+
+19. Fix ARM64 compilation warning in JIT. Patch by Carlo.
+
+20. A bug in the RunTest script meant that if the first part of test 2 failed,
+the failure was not reported.
+
+21. Test 2 was failing when run from a directory other than the source
+directory. This failure was previously missed in RunTest because of 20 above.
+Fixes added to both RunTest and RunTest.bat.
+
+22. Patch to CMakeLists.txt from Daniel to fix problem with testing under
+Windows.
+
+
+Version 10.35 09-May-2020
+---------------------------
+
+1. Use PCRE2_MATCH_EMPTY flag to detect empty matches in JIT.
+
+2. Fix ARMv5 JIT improper handling of labels right after a constant pool.
+
+3. A JIT bug is fixed which allowed to read the fields of the compiled
+pattern before its existence is checked.
+
+4. Back in the PCRE1 day, capturing groups that contained recursive back
+references to themselves were made atomic (version 8.01, change 18) because
+after the end a repeated group, the captured substrings had their values from
+the final repetition, not from an earlier repetition that might be the
+destination of a backtrack. This feature was documented, and was carried over
+into PCRE2. However, it has now been realized that the major refactoring that
+was done for 10.30 has made this atomicizing unnecessary, and it is confusing
+when users are unaware of it, making some patterns appear not to be working as
+expected. Capture values of recursive back references in repeated groups are
+now correctly backtracked, so this unnecessary restriction has been removed.
+
+5. Added PCRE2_SUBSTITUTE_LITERAL.
+
+6. Avoid some VS compiler warnings.
+
+7. Added PCRE2_SUBSTITUTE_MATCHED.
+
+8. Added (?* and (?<* as synonms for (*napla: and (*naplb: to match another
+regex engine. The Perl regex folks are aware of this usage and have made a note
+about it.
+
+9. When an assertion is repeated, PCRE2 used to limit the maximum repetition to
+1, believing that repeating an assertion is pointless. However, if a positive
+assertion contains capturing groups, repetition can be useful. In any case, an
+assertion could always be wrapped in a repeated group. The only restriction
+that is now imposed is that an unlimited maximum is changed to one more than
+the minimum.
+
+10. Fix *THEN verbs in lookahead assertions in JIT.
+
+11. Added PCRE2_SUBSTITUTE_REPLACEMENT_ONLY.
+
+12. The JIT stack should be freed when the low-level stack allocation fails.
+
+13. In pcre2grep, if the final line in a scanned file is output but does not
+end with a newline sequence, add a newline according to the --newline setting.
+
+14. (?(DEFINE)...) groups were not being handled correctly when checking for
+the fixed length of a lookbehind assertion. Such a group within a lookbehind
+should be skipped, as it does not contribute to the length of the group.
+Instead, the (DEFINE) group was being processed, and if at the end of the
+lookbehind, that end was not correctly recognized. Errors such as "lookbehind
+assertion is not fixed length" and also "internal error: bad code value in
+parsed_skip()" could result.
+
+15. Put a limit of 1000 on recursive calls in pcre2_study() when searching
+nested groups for starting code units, in order to avoid stack overflow issues.
+If the limit is reached, it just gives up trying for this optimization.
+
+16. The control verb chain list must always be restored when exiting from a
+recurse function in JIT.
+
+17. Fix a crash which occurs when the character type of an invalid UTF
+character is decoded in JIT.
+
+18. Changes in many areas of the code so that when Unicode is supported and
+PCRE2_UCP is set without PCRE2_UTF, Unicode character properties are used for
+upper/lower case computations on characters whose code points are greater than
+127.
+
+19. The function for checking UTF-16 validity was returning an incorrect offset
+for the start of the error when a high surrogate was not followed by a valid
+low surrogate. This caused incorrect behaviour, for example when
+PCRE2_MATCH_INVALID_UTF was set and a match started immediately following the
+invalid high surrogate, such as /aa/ matching "\x{d800}aa".
+
+20. If a DEFINE group immediately preceded a lookbehind assertion, the pattern
+could be mis-compiled and therefore not match correctly. This is the example
+that found this: /(?(DEFINE)(?<foo>bar))(?<![-a-z0-9])word/ which failed to
+match "word" because the "move back" value was set to zero.
+
+21. Following a request from a user, some extensions and tidies to the
+character tables handling have been done:
+
+  (a) The dftables auxiliary program is renamed pcre2_dftables, but it is still
+  not installed for public use.
+
+  (b) There is now a -b option for pcre2_dftables, which causes the tables to
+  be written in binary. There is also a -help option.
+
+  (c) PCRE2_CONFIG_TABLES_LENGTH is added to pcre2_config() so that an
+  application that wants to save tables in binary knows how long they are.
+
+22. Changed setting of CMAKE_MODULE_PATH in CMakeLists.txt from SET to
+LIST(APPEND...) to allow a setting from the command line to be included.
+
+23. Updated to Unicode 13.0.0.
+
+24. CMake build now checks for secure_getenv() and strerror(). Patch by Carlo.
+
+25. Avoid using [-1] as a suffix in pcre2test because it can provoke a compiler
+warning.
+
+26. Added tests for __attribute__((uninitialized)) to both the configure and
+CMake build files, and then applied this attribute to the variable called
+stack_frames_vector[] in pcre2_match(). When implemented, this disables
+automatic initialization (a facility in clang), which can take time on big
+variables.
+
+27. Updated CMakeLists.txt (patches by Uwe Korn) to add support for
+pcre2-config, the libpcre*.pc files, SOVERSION, VERSION and the
+MACHO_*_VERSIONS settings for CMake builds.
+
+28. Another patch to CMakeLists.txt to check for mkostemp (configure already
+does). Patch by Carlo Marcelo Arenas Belon.
+
+29. Check for the existence of memfd_create in both CMake and configure
+configurations. Patch by Carlo Marcelo Arenas Belon.
+
+30. Restrict the configuration setting for the SELinux compatible execmem
+allocator (change 10.30/44) to Linux and NetBSD.
+
+
+Version 10.34 21-November-2019
+------------------------------
+
+1. The maximum number of capturing subpatterns is 65535 (documented), but no
+check on this was ever implemented. This omission has been rectified; it fixes
+ClusterFuzz 14376.
+
+2. Improved the invalid utf32 support of the JIT compiler. Now it correctly
+detects invalid characters in the 0xd800-0xdfff range.
+
+3. Fix minor typo bug in JIT compile when \X is used in a non-UTF string.
+
+4. Add support for matching in invalid UTF strings to the pcre2_match()
+interpreter, and integrate with the existing JIT support via the new
+PCRE2_MATCH_INVALID_UTF compile-time option.
+
+5. Give more error detail for invalid UTF-8 when detected in pcre2grep.
+
+6. Add support for invalid UTF-8 to pcre2grep.
+
+7. Adjust the limit for "must have" code unit searching, in particular,
+increase it substantially for non-anchored patterns.
+
+8. Allow (*ACCEPT) to be quantified, because an ungreedy quantifier with a zero
+minimum is potentially useful.
+
+9. Some changes to the way the minimum subject length is handled:
+
+   * When PCRE2_NO_START_OPTIMIZE is set, no minimum length is computed;
+     pcre2test now omits this item instead of showing a value of zero.
+
+   * An incorrect minimum length could be calculated for a pattern that
+     contained (*ACCEPT) inside a qualified group whose minimum repetition was
+     zero, for example /A(?:(*ACCEPT))?B/, which incorrectly computed a minimum
+     of 2. The minimum length scan no longer happens for a pattern that
+     contains (*ACCEPT).
+
+   * When no minimum length is set by the normal scan, but a first and/or last
+     code unit is recorded, set the minimum to 1 or 2 as appropriate.
+
+   * When a pattern contains multiple groups with the same number, a back
+     reference cannot know which one to scan for a minimum length. This used to
+     cause the minimum length finder to give up with no result. Now it treats
+     such references as not adding to the minimum length (which it should have
+     done all along).
+
+   * Furthermore, the above action now happens only if the back reference is to
+     a group that exists more than once in a pattern instead of any back
+     reference in a pattern with duplicate numbers.
+
+10. A (*MARK) value inside a successful condition was not being returned by the
+interpretive matcher (it was returned by JIT). This bug has been mended.
+
+11. A bug in pcre2grep meant that -o without an argument (or -o0) didn't work
+if the pattern had more than 32 capturing parentheses. This is fixed. In
+addition (a) the default limit for groups requested by -o<n> has been raised to
+50, (b) the new --om-capture option changes the limit, (c) an error is raised
+if -o asks for a group that is above the limit.
+
+12. The quantifier {1} was always being ignored, but this is incorrect when it
+is made possessive and applied to an item in parentheses, because a
+parenthesized item may contain multiple branches or other backtracking points,
+for example /(a|ab){1}+c/ or /(a+){1}+a/.
+
+13. For partial matches, pcre2test was always showing the maximum lookbehind
+characters, flagged with "<", which is misleading when the lookbehind didn't
+actually look behind the start (because it was later in the pattern). Showing
+all consulted preceding characters for partial matches is now controlled by the
+existing "allusedtext" modifier and, as for complete matches, this facility is
+available only for non-JIT matching, because JIT does not maintain the first
+and last consulted characters.
+
+14. DFA matching (using pcre2_dfa_match()) was not recognising a partial match
+if the end of the subject was encountered in a lookahead (conditional or
+otherwise), an atomic group, or a recursion.
+
+15. Give error if pcre2test -t, -T, -tm or -TM is given an argument of zero.
+
+16. Check for integer overflow when computing lookbehind lengths. Fixes
+Clusterfuzz issue 15636.
+
+17. Implemented non-atomic positive lookaround assertions.
+
+18. If a lookbehind contained a lookahead that contained another lookbehind
+within it, the nested lookbehind was not correctly processed. For example, if
+/(?<=(?=(?<=a)))b/ was matched to "ab" it gave no match instead of matching
+"b".
+
+19. Implemented pcre2_get_match_data_size().
+
+20. Two alterations to partial matching:
+
+    (a) The definition of a partial match is slightly changed: if a pattern
+    contains any lookbehinds, an empty partial match may be given, because this
+    is another situation where adding characters to the current subject can
+    lead to a full match. Example: /c*+(?<=[bc])/ with subject "ab".
+
+    (b) Similarly, if a pattern could match an empty string, an empty partial
+    match may be given. Example: /(?![ab]).*/ with subject "ab". This case
+    applies only to PCRE2_PARTIAL_HARD.
+
+    (c) An empty string partial hard match can be returned for \z and \Z as it
+    is documented that they shouldn't match.
+
+21. A branch that started with (*ACCEPT) was not being recognized as one that
+could match an empty string.
+
+22. Corrected pcre2_set_character_tables() tables data type: was const unsigned
+char * instead of const uint8_t *, as generated by pcre2_maketables().
+
+23. Upgraded to Unicode 12.1.0.
+
+24. Add -jitfast command line option to pcre2test (to make all the jit options
+available directly).
+
+25. Make pcre2test -C show if libreadline or libedit is supported.
+
+26. If the length of one branch of a group exceeded 65535 (the maximum value
+that is remembered as a minimum length), the whole group's length was
+incorrectly recorded as 65535, leading to incorrect "no match" when start-up
+optimizations were in force.
+
+27. The "rightmost consulted character" value was not always correct; in
+particular, if a pattern ended with a negative lookahead, characters that were
+inspected in that lookahead were not included.
+
+28. Add the pcre2_maketables_free() function.
+
+29. The start-up optimization that looks for a unique initial matching
+code unit in the interpretive engines uses memchr() in 8-bit mode. When the
+search is caseless, it was doing so inefficiently, which ended up slowing down
+the match drastically when the subject was very long. The revised code (a)
+remembers if one case is not found, so it never repeats the search for that
+case after a bumpalong and (b) when one case has been found, it searches only
+up to that position for an earlier occurrence of the other case. This fix
+applies to both interpretive pcre2_match() and to pcre2_dfa_match().
+
+30. While scanning to find the minimum length of a group, if any branch has
+minimum length zero, there is no need to scan any subsequent branches (a small
+compile-time performance improvement).
+
+31. Installed a .gitignore file on a user's suggestion. When using the svn
+repository with git (through git svn) this helps keep it tidy.
+
+32. Add underflow check in JIT which may occur when the value of subject
+string pointer is close to 0.
+
+33. Arrange for classes such as [Aa] which contain just the two cases of the
+same character, to be treated as a single caseless character. This causes the
+first and required code unit optimizations to kick in where relevant.
+
+34. Improve the bitmap of starting bytes for positive classes that include wide
+characters, but no property types, in UTF-8 mode. Previously, on encountering
+such a class, the bits for all bytes greater than \xc4 were set, thus
+specifying any character with codepoint >= 0x100. Now the only bits that are
+set are for the relevant bytes that start the wide characters. This can give a
+noticeable performance improvement.
+
+35. If the bitmap of starting code units contains only 1 or 2 bits, replace it
+with a single starting code unit (1 bit) or a caseless single starting code
+unit if the two relevant characters are case-partners. This is particularly
+relevant to the 8-bit library, though it applies to all. It can give a
+performance boost for patterns such as [Ww]ord and (word|WORD). However, this
+optimization doesn't happen if there is a "required" code unit of the same
+value (because the search for a "required" code unit starts at the match start
+for non-unique first code unit patterns, but after a unique first code unit,
+and patterns such as a*a need the former action).
+
+36. Small patch to pcre2posix.c to set the erroroffset field to -1 immediately
+after a successful compile, instead of at the start of matching to avoid a
+sanitizer complaint (regexec is supposed to be thread safe).
+
+37. Add NEON vectorization to JIT to speed up matching of first character and
+pairs of characters on ARM64 CPUs.
+
+38. If a non-ASCII character was the first in a starting assertion in a
+caseless match, the "first code unit" optimization did not get the casing
+right, and the assertion failed to match a character in the other case if it
+did not start with the same code unit.
+
+39. Fixed the incorrect computation of jump sizes on x86 CPUs in JIT. A masking
+operation was incorrectly removed in r1136. Reported by Ralf Junker.
+
+
+Version 10.33 16-April-2019
+---------------------------
+
+1. Added "allvector" to pcre2test to make it easy to check the part of the
+ovector that shouldn't be changed, in particular after substitute and failed or
+partial matches.
+
+2. Fix subject buffer overread in JIT when UTF is disabled and \X or \R has
+a greater than 1 fixed quantifier. This issue was found by Yunho Kim.
+
+3. Added support for callouts from pcre2_substitute(). After 10.33-RC1, but
+prior to release, fixed a bug that caused a crash if pcre2_substitute() was
+called with a NULL match context.
+
+4. The POSIX functions are now all called pcre2_regcomp() etc., with wrapper
+functions that use the standard POSIX names. However, in pcre2posix.h the POSIX
+names are defined as macros. This should help avoid linking with the wrong
+library in some environments while still exporting the POSIX names for
+pre-existing programs that use them. (The Debian alternative names are also
+defined as macros, but not documented.)
+
+5. Fix an xclass matching issue in JIT.
+
+6. Implement PCRE2_EXTRA_ESCAPED_CR_IS_LF (see Bugzilla 2315).
+
+7. Implement the Perl 5.28 experimental alphabetic names for atomic groups and
+lookaround assertions, for example, (*pla:...) and (*atomic:...). These are
+characterized by a lower case letter following (* and to simplify coding for
+this, the character tables created by pcre2_maketables() were updated to add a
+new "is lower case letter" bit. At the same time, the now unused "is
+hexadecimal digit" bit was removed. The default tables in
+src/pcre2_chartables.c.dist are updated.
+
+8. Implement the new Perl "script run" features (*script_run:...) and
+(*atomic_script_run:...) aka (*sr:...) and (*asr:...).
+
+9. Fixed two typos in change 22 for 10.21, which added special handling for
+ranges such as a-z in EBCDIC environments. The original code probably never
+worked, though there were no bug reports.
+
+10. Implement PCRE2_COPY_MATCHED_SUBJECT for pcre2_match() (including JIT via
+pcre2_match()) and pcre2_dfa_match(), but *not* the pcre2_jit_match() fast
+path. Also, when a match fails, set the subject field in the match data to NULL
+for tidiness - none of the substring extractors should reference this after
+match failure.
+
+11. If a pattern started with a subroutine call that had a quantifier with a
+minimum of zero, an incorrect "match must start with this character" could be
+recorded. Example: /(?&xxx)*ABC(?<xxx>XYZ)/ would (incorrectly) expect 'A' to
+be the first character of a match.
+
+12. The heap limit checking code in pcre2_dfa_match() could suffer from
+overflow if the heap limit was set very large. This could cause incorrect "heap
+limit exceeded" errors.
+
+13. Add "kibibytes" to the heap limit output from pcre2test -C to make the
+units clear.
+
+14. Add a call to pcre2_jit_free_unused_memory() in pcre2grep, for tidiness.
+
+15. Updated the VMS-specific code in pcre2test on the advice of a VMS user.
+
+16. Removed the unnecessary inclusion of stdint.h (or inttypes.h) from
+pcre2_internal.h as it is now included by pcre2.h. Also, change 17 for 10.32
+below was unnecessarily complicated, as inttypes.h is a Standard C header,
+which is defined to be a superset of stdint.h. Instead of conditionally
+including stdint.h or inttypes.h, pcre2.h now unconditionally includes
+inttypes.h. This supports environments that do not have stdint.h but do have
+inttypes.h, which are known to exist. A note in the autotools documentation
+says (November 2018) that there are none known that are the other way round.
+
+17. Added --disable-percent-zt to "configure" (and equivalent to CMake) to
+forcibly disable the use of %zu and %td in formatting strings because there is
+at least one version of VMS that claims to be C99 but does not support these
+modifiers.
+
+18. Added --disable-pcre2grep-callout-fork, which restricts the callout support
+in pcre2grep to the inbuilt echo facility. This may be useful in environments
+that do not support fork().
+
+19. Fix two instances of <= 0 being applied to unsigned integers (the VMS
+compiler complains).
+
+20. Added "fork" support for VMS to pcre2grep, for running an external program
+via a string callout.
+
+21. Improve MAP_JIT flag usage on MacOS. Patch by Rich Siegel.
+
+22. If a pattern started with (*MARK), (*COMMIT), (*PRUNE), (*SKIP), or (*THEN)
+followed by ^ it was not recognized as anchored.
+
+23. The RunGrepTest script used to cut out the test of NUL characters for
+Solaris and MacOS as printf and sed can't handle them. It seems that the *BSD
+systems can't either. I've inverted the test so that only those OS that are
+known to work (currently only Linux) try to run this test.
+
+24. Some tests in RunGrepTest appended to testtrygrep from two different file
+descriptors instead of redirecting stderr to stdout. This worked on Linux, but
+it was reported not to on other systems, causing the tests to fail.
+
+25. In the RunTest script, make the test for stack setting use the same value
+for the stack as it needs for -bigstack.
+
+26. Insert a cast in pcre2_dfa_match.c to suppress a compiler warning.
+
+26. With PCRE2_EXTRA_BAD_ESCAPE_IS_LITERAL set, escape sequences such as \s
+which are valid in character classes, but not as the end of ranges, were being
+treated as literals. An example is [_-\s] (but not [\s-_] because that gave an
+error at the *start* of a range). Now an "invalid range" error is given
+independently of PCRE2_EXTRA_BAD_ESCAPE_IS_LITERAL.
+
+27. Related to 26 above, PCRE2_BAD_ESCAPE_IS_LITERAL was affecting known escape
+sequences such as \eX when they appeared invalidly in a character class. Now
+the option applies only to unrecognized or malformed escape sequences.
+
+28. Fix word boundary in JIT compiler. Patch by Mike Munday.
+
+29. The pcre2_dfa_match() function was incorrectly handling conditional version
+tests such as (?(VERSION>=0)...) when the version test was true. Incorrect
+processing or a crash could result.
+
+30. When PCRE2_UTF is set, allow non-ASCII letters and decimal digits in group
+names, as Perl does. There was a small bug in this new code, found by
+ClusterFuzz 12950, fixed before release.
+
+31. Implemented PCRE2_EXTRA_ALT_BSUX to support ECMAScript 6's \u{hhh}
+construct.
+
+32. Compile \p{Any} to be the same as . in DOTALL mode, so that it benefits
+from auto-anchoring if \p{Any}* starts a pattern.
+
+33. Compile invalid UTF check in JIT test when only pcre32 is enabled.
+
+34. For some time now, CMake has been warning about the setting of policy
+CMP0026 to "OLD" in CmakeLists.txt, and hinting that the feature might be
+removed in a future version. A request for CMake expertise on the list produced
+no result, so I have now hacked CMakeLists.txt along the lines of some changes
+I found on the Internet. The new code no longer needs the policy setting, and
+it appears to work fine on Linux.
+
+35. Setting --enable-jit=auto for an out-of-tree build failed because the
+source directory wasn't in the search path for AC_TRY_COMPILE always. Patch
+from Ross Burton.
+
+36. Disable SSE2 JIT optimizations in x86 CPUs when SSE2 is not available.
+Patch by Guillem Jover.
+
+37. Changed expressions such as 1<<10 to 1u<<10 in many places because compiler
+warnings were reported.
+
+38. Using the clang compiler with sanitizing options causes runtime complaints
+about truncation for statments such as x = ~x when x is an 8-bit value; it
+seems to compute ~x as a 32-bit value. Changing such statements to x = 255 ^ x
+gets rid of the warnings. There were also two missing casts in pcre2test.
+
+
+Version 10.32 10-September-2018
+-------------------------------
+
+1. When matching using the the REG_STARTEND feature of the POSIX API with a
+non-zero starting offset, unset capturing groups with lower numbers than a
+group that did capture something were not being correctly returned as "unset"
+(that is, with offset values of -1).
+
+2. When matching using the POSIX API, pcre2test used to omit listing unset
+groups altogether. Now it shows those that come before any actual captures as
+"<unset>", as happens for non-POSIX matching.
+
+3. Running "pcre2test -C" always stated "\R matches CR, LF, or CRLF only",
+whatever the build configuration was. It now correctly says "\R matches all
+Unicode newlines" in the default case when --enable-bsr-anycrlf has not been
+specified. Similarly, running "pcre2test -C bsr" never produced the result
+ANY.
+
+4. Matching the pattern /(*UTF)\C[^\v]+\x80/ against an 8-bit string containing
+multi-code-unit characters caused bad behaviour and possibly a crash. This
+issue was fixed for other kinds of repeat in release 10.20 by change 19, but
+repeating character classes were overlooked.
+
+5. pcre2grep now supports the inclusion of binary zeros in patterns that are
+read from files via the -f option.
+
+6. A small fix to pcre2grep to avoid compiler warnings for -Wformat-overflow=2.
+
+7. Added --enable-jit=auto support to configure.ac.
+
+8. Added some dummy variables to the heapframe structure in 16-bit and 32-bit
+modes for the benefit of m68k, where pointers can be 16-bit aligned. The
+dummies force 32-bit alignment and this ensures that the structure is a
+multiple of PCRE2_SIZE, a requirement that is tested at compile time. In other
+architectures, alignment requirements take care of this automatically.
+
+9. When returning an error from pcre2_pattern_convert(), ensure the error
+offset is set zero for early errors.
+
+10. A number of patches for Windows support from Daniel Richard G:
+
+  (a) List of error numbers in Runtest.bat corrected (it was not the same as in
+      Runtest).
+
+  (b) pcre2grep snprintf() workaround as used elsewhere in the tree.
+
+  (c) Support for non-C99 snprintf() that returns -1 in the overflow case.
+
+11. Minor tidy of pcre2_dfa_match() code.
+
+12. Refactored pcre2_dfa_match() so that the internal recursive calls no longer
+use the stack for local workspace and local ovectors. Instead, an initial block
+of stack is reserved, but if this is insufficient, heap memory is used. The
+heap limit parameter now applies to pcre2_dfa_match().
+
+13. If a "find limits" test of DFA matching in pcre2test resulted in too many
+matches for the ovector, no matches were displayed.
+
+14. Removed an occurrence of ctrl/Z from test 6 because Windows treats it as
+EOF. The test looks to have come from a fuzzer.
+
+15. If PCRE2 was built with a default match limit a lot greater than the
+default default of 10 000 000, some JIT tests of the match limit no longer
+failed. All such tests now set 10 000 000 as the upper limit.
+
+16. Another Windows related patch for pcregrep to ensure that WIN32 is
+undefined under Cygwin.
+
+17. Test for the presence of stdint.h and inttypes.h in configure and CMake and
+include whichever exists (stdint preferred) instead of unconditionally
+including stdint. This makes life easier for old and non-standard systems.
+
+18. Further changes to improve portability, especially to old and or non-
+standard systems:
+
+  (a) Put all printf arguments in RunGrepTest into single, not double, quotes,
+      and use \0 not \x00 for binary zero.
+
+  (b) Avoid the use of C++ (i.e. BCPL) // comments.
+
+  (c) Parameterize the use of %zu in pcre2test to make it like %td. For both of
+      these now, if using MSVC or a standard C before C99, %lu is used with a
+      cast if necessary.
+
+19. Applied a contributed patch to CMakeLists.txt to increase the stack size
+when linking pcre2test with MSVC. This gets rid of a stack overflow error in
+the standard set of tests.
+
+20. Output a warning in pcre2test when ignoring the "altglobal" modifier when
+it is given with the "replace" modifier.
+
+21. In both pcre2test and pcre2_substitute(), with global matching, a pattern
+that matched an empty string, but never at the starting match offset, was not
+handled in a Perl-compatible way. The pattern /(<?=\G.)/ is an example of such
+a pattern. Because \G is in a lookbehind assertion, there has to be a
+"bumpalong" before there can be a match. The automatic "advance by one
+character after an empty string match" rule is therefore inappropriate. A more
+complicated algorithm has now been implemented.
+
+22. When checking to see if a lookbehind is of fixed length, lookaheads were
+correctly ignored, but qualifiers on lookaheads were not being ignored, leading
+to an incorrect "lookbehind assertion is not fixed length" error.
+
+23. The VERSION condition test was reading fractional PCRE2 version numbers
+such as the 04 in 10.04 incorrectly and hence giving wrong results.
+
+24. Updated to Unicode version 11.0.0. As well as the usual addition of new
+scripts and characters, this involved re-jigging the grapheme break property
+algorithm because Unicode has changed the way emojis are handled.
+
+25. Fixed an obscure bug that struck when there were two atomic groups not
+separated by something with a backtracking point. There could be an incorrect
+backtrack into the first of the atomic groups. A complicated example is
+/(?>a(*:1))(?>b)(*SKIP:1)x|.*/ matched against "abc", where the *SKIP
+shouldn't find a MARK (because is in an atomic group), but it did.
+
+26. Upgraded the perltest.sh script: (1) #pattern lines can now be used to set
+a list of modifiers for all subsequent patterns - only those that the script
+recognizes are meaningful; (2) #subject lines can be used to set or unset a
+default "mark" modifier; (3) Unsupported #command lines give a warning when
+they are ignored; (4) Mark data is output only if the "mark" modifier is
+present.
+
+27. (*ACCEPT:ARG), (*FAIL:ARG), and (*COMMIT:ARG) are now supported.
+
+28. A (*MARK) name was not being passed back for positive assertions that were
+terminated by (*ACCEPT).
+
+29. Add support for \N{U+dddd}, but only in Unicode mode.
+
+30. Add support for (?^) for unsetting all imnsx options.
+
+31. The PCRE2_EXTENDED (/x) option only ever discarded space characters whose
+code point was less than 256 and that were recognized by the lookup table
+generated by pcre2_maketables(), which uses isspace() to identify white space.
+Now, when Unicode support is compiled, PCRE2_EXTENDED also discards U+0085,
+U+200E, U+200F, U+2028, and U+2029, which are additional characters defined by
+Unicode as "Pattern White Space". This makes PCRE2 compatible with Perl.
+
+32. In certain circumstances, option settings within patterns were not being
+correctly processed. For example, the pattern /((?i)A)(?m)B/ incorrectly
+matched "ab". (The (?m) setting lost the fact that (?i) should be reset at the
+end of its group during the parse process, but without another setting such as
+(?m) the compile phase got it right.) This bug was introduced by the
+refactoring in release 10.23.
+
+33. PCRE2 uses bcopy() if available when memmove() is not, and it used just to
+define memmove() as function call to bcopy(). This hasn't been tested for a
+long time because in pcre2test the result of memmove() was being used, whereas
+bcopy() doesn't return a result. This feature is now refactored always to call
+an emulation function when there is no memmove(). The emulation makes use of
+bcopy() when available.
+
+34. When serializing a pattern, set the memctl, executable_jit, and tables
+fields (that is, all the fields that contain pointers) to zeros so that the
+result of serializing is always the same. These fields are re-set when the
+pattern is deserialized.
+
+35. In a pattern such as /[^\x{100}-\x{ffff}]*[\x80-\xff]/ which has a repeated
+negative class with no characters less than 0x100 followed by a positive class
+with only characters less than 0x100, the first class was incorrectly being
+auto-possessified, causing incorrect match failures.
+
+36. Removed the character type bit ctype_meta, which dates from PCRE1 and is
+not used in PCRE2.
+
+37. Tidied up unnecessarily complicated macros used in the escapes table.
+
+38. Since 10.21, the new testoutput8-16-4 file has accidentally been omitted
+from distribution tarballs, owing to a typo in Makefile.am which had
+testoutput8-16-3 twice. Now fixed.
+
+39. If the only branch in a conditional subpattern was anchored, the whole
+subpattern was treated as anchored, when it should not have been, since the
+assumed empty second branch cannot be anchored. Demonstrated by test patterns
+such as /(?(1)^())b/ or /(?(?=^))b/.
+
+40. A repeated conditional subpattern that could match an empty string was
+always assumed to be unanchored. Now it it checked just like any other
+repeated conditional subpattern, and can be found to be anchored if the minimum
+quantifier is one or more. I can't see much use for a repeated anchored
+pattern, but the behaviour is now consistent.
+
+41. Minor addition to pcre2_jit_compile.c to avoid static analyzer complaint
+(for an event that could never occur but you had to have external information
+to know that).
+
+42. If before the first match in a file that was being searched by pcre2grep
+there was a line that was sufficiently long to cause the input buffer to be
+expanded, the variable holding the location of the end of the previous match
+was being adjusted incorrectly, and could cause an overflow warning from a code
+sanitizer. However, as the value is used only to print pending "after" lines
+when the next match is reached (and there are no such lines in this case) this
+bug could do no damage.
+
+
+Version 10.31 12-February-2018
+------------------------------
+
+1. Fix typo (missing ]) in VMS code in pcre2test.c.
+
+2. Replace the replicated code for matching extended Unicode grapheme sequences
+(which got a lot more complicated by change 10.30/49) by a single subroutine
+that is called by both pcre2_match() and pcre2_dfa_match().
+
+3. Add idempotent guard to pcre2_internal.h.
+
+4. Add new pcre2_config() options: PCRE2_CONFIG_NEVER_BACKSLASH_C and
+PCRE2_CONFIG_COMPILED_WIDTHS.
+
+5. Cut out \C tests in the JIT regression tests when NEVER_BACKSLASH_C is
+defined (e.g. by --enable-never-backslash-C).
+
+6. Defined public names for all the pcre2_compile() error numbers, and used
+the public names in pcre2_convert.c.
+
+7. Fixed a small memory leak in pcre2test (convert contexts).
+
+8. Added two casts to compile.c and one to match.c to avoid compiler warnings.
+
+9. Added code to pcre2grep when compiled under VMS to set the symbol
+PCRE2GREP_RC to the exit status, because VMS does not distinguish between
+exit(0) and exit(1).
+
+10. Added the -LM (list modifiers) option to pcre2test. Also made -C complain
+about a bad option only if the following argument item does not start with a
+hyphen.
+
+11. pcre2grep was truncating components of file names to 128 characters when
+processing files with the -r option, and also (some very odd code) truncating
+path names to 512 characters. There is now a check on the absolute length of
+full path file names, which may be up to 2047 characters long.
+
+12. When an assertion contained (*ACCEPT) it caused all open capturing groups
+to be closed (as for a non-assertion ACCEPT), which was wrong and could lead to
+misbehaviour for subsequent references to groups that started outside the
+assertion. ACCEPT in an assertion now closes only those groups that were
+started within that assertion. Fixes oss-fuzz issues 3852 and 3891.
+
+13. Multiline matching in pcre2grep was misbehaving if the pattern matched
+within a line, and then matched again at the end of the line and over into
+subsequent lines. Behaviour was different with and without colouring, and
+sometimes context lines were incorrectly printed and/or line endings were lost.
+All these issues should now be fixed.
+
+14. If --line-buffered was specified for pcre2grep when input was from a
+compressed file (.gz or .bz2) a segfault occurred. (Line buffering should be
+ignored for compressed files.)
+
+15. Although pcre2_jit_match checks whether the pattern is compiled
+in a given mode, it was also expected that at least one mode is available.
+This is fixed and pcre2_jit_match returns with PCRE2_ERROR_JIT_BADOPTION
+when the pattern is not optimized by JIT at all.
+
+16. The line number and related variables such as match counts in pcre2grep
+were all int variables, causing overflow when files with more than 2147483647
+lines were processed (assuming 32-bit ints). They have all been changed to
+unsigned long ints.
+
+17. If a backreference with a minimum repeat count of zero was first in a
+pattern, apart from assertions, an incorrect first matching character could be
+recorded. For example, for the pattern /(?=(a))\1?b/, "b" was incorrectly set
+as the first character of a match.
+
+18. Characters in a leading positive assertion are considered for recording a
+first character of a match when the rest of the pattern does not provide one.
+However, a character in a non-assertive group within a leading assertion such
+as in the pattern /(?=(a))\1?b/ caused this process to fail. This was an
+infelicity rather than an outright bug, because it did not affect the result of
+a match, just its speed. (In fact, in this case, the starting 'a' was
+subsequently picked up in the study.)
+
+19. A minor tidy in pcre2_match(): making all PCRE2_ERROR_ returns use "return"
+instead of "RRETURN" saves unwinding the backtracks in these cases (only one
+didn't).
+
+20. Allocate a single callout block on the stack at the start of pcre2_match()
+and set its never-changing fields once only. Do the same for pcre2_dfa_match().
+
+21. Save the extra compile options (set in the compile context) with the
+compiled pattern (they were not previously saved), add PCRE2_INFO_EXTRAOPTIONS
+to retrieve them, and update pcre2test to show them.
+
+22. Added PCRE2_CALLOUT_STARTMATCH and PCRE2_CALLOUT_BACKTRACK bits to a new
+field callout_flags in callout blocks. The bits are set by pcre2_match(), but
+not by JIT or pcre2_dfa_match(). Their settings are shown in pcre2test callouts
+if the callout_extra subject modifier is set. These bits are provided to help
+with tracking how a backtracking match is proceeding.
+
+23. Updated the pcre2demo.c demonstration program, which was missing the extra
+code for -g that handles the case when \K in an assertion causes the match to
+end at the original start point. Also arranged for it to detect when \K causes
+the end of a match to be before its start.
+
+24. Similar to 23 above, strange things (including loops) could happen in
+pcre2grep when \K was used in an assertion when --colour was used or in
+multiline mode. The "end at original start point" bug is fixed, and if the end
+point is found to be before the start point, they are swapped.
+
+25. When PCRE2_FIRSTLINE without PCRE2_NO_START_OPTIMIZE was used in non-JIT
+matching (both pcre2_match() and pcre2_dfa_match()) and the matched string
+started with the first code unit of a newline sequence, matching failed because
+it was not tried at the newline.
+
+26. Code for giving up a non-partial match after failing to find a starting
+code unit anywhere in the subject was missing when searching for one of a
+number of code units (the bitmap case) in both pcre2_match() and
+pcre2_dfa_match(). This was a missing optimization rather than a bug.
+
+27. Tidied up the ACROSSCHAR macro to be like FORWARDCHAR and BACKCHAR, using a
+pointer argument rather than a code unit value. This should not have affected
+the generated code.
+
+28. The JIT compiler has been updated.
+
+29. Avoid pointer overflow for unset captures in pcre2_substring_list_get().
+This could not actually cause a crash because it was always used in a memcpy()
+call with zero length.
+
+30. Some internal structures have a variable-length ovector[] as their last
+element. Their actual memory is obtained dynamically, giving an ovector of
+appropriate length. However, they are defined in the structure as
+ovector[NUMBER], where NUMBER is large so that array bound checkers don't
+grumble. The value of NUMBER was 10000, but a fuzzer exceeded 5000 capturing
+groups, making the ovector larger than this. The number has been increased to
+131072, which allows for the maximum number of captures (65535) plus the
+overall match. This fixes oss-fuzz issue 5415.
+
+31. Auto-possessification at the end of a capturing group was dependent on what
+follows the group (e.g. /(a+)b/ would auto-possessify the a+) but this caused
+incorrect behaviour when the group was called recursively from elsewhere in the
+pattern where something different might follow. This bug is an unforseen
+consequence of change #1 for 10.30 - the implementation of backtracking into
+recursions. Iterators at the ends of capturing groups are no longer considered
+for auto-possessification if the pattern contains any recursions. Fixes
+Bugzilla #2232.
+
+
+Version 10.30 14-August-2017
+----------------------------
+
+1. The main interpreter, pcre2_match(), has been refactored into a new version
+that does not use recursive function calls (and therefore the stack) for
+remembering backtracking positions. This makes --disable-stack-for-recursion a
+NOOP. The new implementation allows backtracking into recursive group calls in
+patterns, making it more compatible with Perl, and also fixes some other
+hard-to-do issues such as #1887 in Bugzilla. The code is also cleaner because
+the old code had a number of fudges to try to reduce stack usage. It seems to
+run no slower than the old code.
+
+A number of bugs in the refactored code were subsequently fixed during testing
+before release, but after the code was made available in the repository. These
+bugs were never in fully released code, but are noted here for the record.
+
+  (a) If a pattern had fewer capturing parentheses than the ovector supplied in
+      the match data block, a memory error (detectable by ASAN) occurred after
+      a match, because the external block was being set from non-existent
+      internal ovector fields. Fixes oss-fuzz issue 781.
+
+  (b) A pattern with very many capturing parentheses (when the internal frame
+      size was greater than the initial frame vector on the stack) caused a
+      crash. A vector on the heap is now set up at the start of matching if the
+      vector on the stack is not big enough to handle at least 10 frames.
+      Fixes oss-fuzz issue 783.
+
+  (c) Handling of (*VERB)s in recursions was wrong in some cases.
+
+  (d) Captures in negative assertions that were used as conditions were not
+      happening if the assertion matched via (*ACCEPT).
+
+  (e) Mark values were not being passed out of recursions.
+
+  (f) Refactor some code in do_callout() to avoid picky compiler warnings about
+      negative indices. Fixes oss-fuzz issue 1454.
+
+  (g) Similarly refactor the way the variable length ovector is addressed for
+      similar reasons. Fixes oss-fuzz issue 1465.
+
+2. Now that pcre2_match() no longer uses recursive function calls (see above),
+the "match limit recursion" value seems misnamed. It still exists, and limits
+the depth of tree that is searched. To avoid future confusion, it has been
+renamed as "depth limit" in all relevant places (--with-depth-limit,
+(*LIMIT_DEPTH), pcre2_set_depth_limit(), etc) but the old names are still
+available for backwards compatibility.
+
+3. Hardened pcre2test so as to reduce the number of bugs reported by fuzzers:
+
+  (a) Check for malloc failures when getting memory for the ovector (POSIX) or
+      the match data block (non-POSIX).
+
+4. In the 32-bit library in non-UTF mode, an attempt to find a Unicode property
+for a character with a code point greater than 0x10ffff (the Unicode maximum)
+caused a crash.
+
+5. If a lookbehind assertion that contained a back reference to a group
+appearing later in the pattern was compiled with the PCRE2_ANCHORED option,
+undefined actions (often a segmentation fault) could occur, depending on what
+other options were set. An example assertion is (?<!\1(abc)) where the
+reference \1 precedes the group (abc). This fixes oss-fuzz issue 865.
+
+6. Added the PCRE2_INFO_FRAMESIZE item to pcre2_pattern_info() and arranged for
+pcre2test to use it to output the frame size when the "framesize" modifier is
+given.
+
+7. Reworked the recursive pattern matching in the JIT compiler to follow the
+interpreter changes.
+
+8. When the zero_terminate modifier was specified on a pcre2test subject line
+for global matching, unpredictable things could happen. For example, in UTF-8
+mode, the pattern //g,zero_terminate read random memory when matched against an
+empty string with zero_terminate. This was a bug in pcre2test, not the library.
+
+9. Moved some Windows-specific code in pcre2grep (introduced in 10.23/13) out
+of the section that is compiled when Unix-style directory scanning is
+available, and into a new section that is always compiled for Windows.
+
+10. In pcre2test, explicitly close the file after an error during serialization
+or deserialization (the "load" or "save" commands).
+
+11. Fix memory leak in pcre2_serialize_decode() when the input is invalid.
+
+12. Fix potential NULL dereference in pcre2_callout_enumerate() if called with
+a NULL pattern pointer when Unicode support is available.
+
+13. When the 32-bit library was being tested by pcre2test, error messages that
+were longer than 64 code units could cause a buffer overflow. This was a bug in
+pcre2test.
+
+14. The alternative matching function, pcre2_dfa_match() misbehaved if it
+encountered a character class with a possessive repeat, for example [a-f]{3}+.
+
+15. The depth (formerly recursion) limit now applies to DFA matching (as
+of 10.23/36); pcre2test has been upgraded so that \=find_limits works with DFA
+matching to find the minimum value for this limit.
+
+16. Since 10.21, if pcre2_match() was called with a null context, default
+memory allocation functions were used instead of whatever was used when the
+pattern was compiled.
+
+17. Changes to the pcre2test "memory" modifier on a subject line. These apply
+only to pcre2_match():
+
+  (a) Warn if null_context is set on both pattern and subject, because the
+      memory details cannot then be shown.
+
+  (b) Remember (up to a certain number of) memory allocations and their
+      lengths, and list only the lengths, so as to be system-independent.
+      (In practice, the new interpreter never has more than 2 blocks allocated
+      simultaneously.)
+
+18. Make pcre2test detect an error return from pcre2_get_error_message(), give
+a message, and abandon the run (this would have detected #13 above).
+
+19. Implemented PCRE2_ENDANCHORED.
+
+20. Applied Jason Hood's patches (slightly modified) to pcre2grep, to implement
+the --output=text (-O) option and the inbuilt callout echo.
+
+21. Extend auto-anchoring etc. to ignore groups with a zero qualifier and
+single-branch conditions with a false condition (e.g. DEFINE) at the start of a
+branch. For example, /(?(DEFINE)...)^A/ and /(...){0}^B/ are now flagged as
+anchored.
+
+22. Added an explicit limit on the amount of heap used by pcre2_match(), set by
+pcre2_set_heap_limit() or (*LIMIT_HEAP=xxx). Upgraded pcre2test to show the
+heap limit along with other pattern information, and to find the minimum when
+the find_limits modifier is set.
+
+23. Write to the last 8 bytes of the pcre2_real_code structure when a compiled
+pattern is set up so as to initialize any padding the compiler might have
+included. This avoids valgrind warnings when a compiled pattern is copied, in
+particular when it is serialized.
+
+24. Remove a redundant line of code left in accidentally a long time ago.
+
+25. Remove a duplication typo in pcre2_tables.c
+
+26. Correct an incorrect cast in pcre2_valid_utf.c
+
+27. Update pcre2test, remove some unused code in pcre2_match(), and upgrade the
+tests to improve coverage.
+
+28. Some fixes/tidies as a result of looking at Coverity Scan output:
+
+    (a) Typo: ">" should be ">=" in opcode check in pcre2_auto_possess.c.
+    (b) Added some casts to avoid "suspicious implicit sign extension".
+    (c) Resource leaks in pcre2test in rare error cases.
+    (d) Avoid warning for never-use case OP_TABLE_LENGTH which is just a fudge
+        for checking at compile time that tables are the right size.
+    (e) Add missing "fall through" comment.
+
+29. Implemented PCRE2_EXTENDED_MORE and related /xx and (?xx) features.
+
+30. Implement (?n: for PCRE2_NO_AUTO_CAPTURE, because Perl now has this.
+
+31. If more than one of "push", "pushcopy", or "pushtablescopy" were set in
+pcre2test, a crash could occur.
+
+32. Make -bigstack in RunTest allocate a 64MiB stack (instead of 16MiB) so
+that all the tests can run with clang's sanitizing options.
+
+33. Implement extra compile options in the compile context and add the first
+one: PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES.
+
+34. Implement newline type PCRE2_NEWLINE_NUL.
+
+35. A lookbehind assertion that had a zero-length branch caused undefined
+behaviour when processed by pcre2_dfa_match(). This is oss-fuzz issue 1859.
+
+36. The match limit value now also applies to pcre2_dfa_match() as there are
+patterns that can use up a lot of resources without necessarily recursing very
+deeply. (Compare item 10.23/36.) This should fix oss-fuzz #1761.
+
+37. Implement PCRE2_EXTRA_BAD_ESCAPE_IS_LITERAL.
+
+38. Fix returned offsets from regexec() when REG_STARTEND is used with a
+starting offset greater than zero.
+
+39. Implement REG_PEND (GNU extension) for the POSIX wrapper.
+
+40. Implement the subject_literal modifier in pcre2test, and allow jitstack on
+pattern lines.
+
+41. Implement PCRE2_LITERAL and use it to support REG_NOSPEC.
+
+42. Implement PCRE2_EXTRA_MATCH_LINE and PCRE2_EXTRA_MATCH_WORD for the benefit
+of pcre2grep.
+
+43. Re-implement pcre2grep's -F, -w, and -x options using PCRE2_LITERAL,
+PCRE2_EXTRA_MATCH_WORD, and PCRE2_EXTRA_MATCH_LINE. This fixes two bugs:
+
+    (a) The -F option did not work for fixed strings containing \E.
+    (b) The -w option did not work for patterns with multiple branches.
+
+44. Added configuration options for the SELinux compatible execmem allocator in
+JIT.
+
+45. Increased the limit for searching for a "must be present" code unit in
+subjects from 1000 to 2000 for 8-bit searches, since they use memchr() and are
+much faster.
+
+46. Arrange for anchored patterns to record and use "first code unit" data,
+because this can give a fast "no match" without searching for a "required code
+unit". Previously only non-anchored patterns did this.
+
+47. Upgraded the Unicode tables from Unicode 8.0.0 to Unicode 10.0.0.
+
+48. Add the callout_no_where modifier to pcre2test.
+
+49. Update extended grapheme breaking rules to the latest set that are in
+Unicode Standard Annex #29.
+
+50. Added experimental foreign pattern conversion facilities
+(pcre2_pattern_convert() and friends).
+
+51. Change the macro FWRITE, used in pcre2grep, to FWRITE_IGNORE because FWRITE
+is defined in a system header in cygwin. Also modified some of the #ifdefs in
+pcre2grep related to Windows and Cygwin support.
+
+52. Change 3(g) for 10.23 was a bit too zealous. If a hyphen that follows a
+character class is the last character in the class, Perl does not give a
+warning. PCRE2 now also treats this as a literal.
+
+53. Related to 52, though PCRE2 was throwing an error for [[:digit:]-X] it was
+not doing so for [\d-X] (and similar escapes), as is documented.
+
+54. Fixed a MIPS issue in the JIT compiler reported by Joshua Kinard.
+
+55. Fixed a "maybe uninitialized" warning for class_uchardata in \p handling in
+pcre2_compile() which could never actually trigger (code should have been cut
+out when Unicode support is disabled).
+
+
+Version 10.23 14-February-2017
+------------------------------
+
+1. Extended pcre2test with the utf8_input modifier so that it is able to
+generate all possible 16-bit and 32-bit code unit values in non-UTF modes.
+
+2. In any wide-character mode (8-bit UTF or any 16-bit or 32-bit mode), without
+PCRE2_UCP set, a negative character type such as \D in a positive class should
+cause all characters greater than 255 to match, whatever else is in the class.
+There was a bug that caused this not to happen if a Unicode property item was
+added to such a class, for example [\D\P{Nd}] or [\W\pL].
+
+3. There has been a major re-factoring of the pcre2_compile.c file. Most syntax
+checking is now done in the pre-pass that identifies capturing groups. This has
+reduced the amount of duplication and made the code tidier. While doing this,
+some minor bugs and Perl incompatibilities were fixed, including:
+
+  (a) \Q\E in the middle of a quantifier such as A+\Q\E+ is now ignored instead
+      of giving an invalid quantifier error.
+
+  (b) {0} can now be used after a group in a lookbehind assertion; previously
+      this caused an "assertion is not fixed length" error.
+
+  (c) Perl always treats (?(DEFINE) as a "define" group, even if a group with
+      the name "DEFINE" exists. PCRE2 now does likewise.
+
+  (d) A recursion condition test such as (?(R2)...) must now refer to an
+      existing subpattern.
+
+  (e) A conditional recursion test such as (?(R)...) misbehaved if there was a
+      group whose name began with "R".
+
+  (f) When testing zero-terminated patterns under valgrind, the terminating
+      zero is now marked "no access". This catches bugs that would otherwise
+      show up only with non-zero-terminated patterns.
+
+  (g) A hyphen appearing immediately after a POSIX character class (for example
+      /[[:ascii:]-z]/) now generates an error. Perl does accept this as a
+      literal, but gives a warning, so it seems best to fail it in PCRE.
+
+  (h) An empty \Q\E sequence may appear after a callout that precedes an
+      assertion condition (it is, of course, ignored).
+
+One effect of the refactoring is that some error numbers and messages have
+changed, and the pattern offset given for compiling errors is not always the
+right-most character that has been read. In particular, for a variable-length
+lookbehind assertion it now points to the start of the assertion. Another
+change is that when a callout appears before a group, the "length of next
+pattern item" that is passed now just gives the length of the opening
+parenthesis item, not the length of the whole group. A length of zero is now
+given only for a callout at the end of the pattern. Automatic callouts are no
+longer inserted before and after explicit callouts in the pattern.
+
+A number of bugs in the refactored code were subsequently fixed during testing
+before release, but after the code was made available in the repository. Many
+of the bugs were discovered by fuzzing testing. Several of them were related to
+the change from assuming a zero-terminated pattern (which previously had
+required non-zero terminated strings to be copied). These bugs were never in
+fully released code, but are noted here for the record.
+
+  (a) An overall recursion such as (?0) inside a lookbehind assertion was not
+      being diagnosed as an error.
+
+  (b) In utf mode, the length of a *MARK (or other verb) name was being checked
+      in characters instead of code units, which could lead to bad code being
+      compiled, leading to unpredictable behaviour.
+
+  (c) In extended /x mode, characters whose code was greater than 255 caused
+      a lookup outside one of the global tables. A similar bug existed for wide
+      characters in *VERB names.
+
+  (d) The amount of memory needed for a compiled pattern was miscalculated if a
+      lookbehind contained more than one toplevel branch and the first branch
+      was of length zero.
+
+  (e) In UTF-8 or UTF-16 modes with PCRE2_EXTENDED (/x) set and a non-zero-
+      terminated pattern, if a # comment ran on to the end of the pattern, one
+      or more code units past the end were being read.
+
+  (f) An unterminated repeat at the end of a non-zero-terminated pattern (e.g.
+      "{2,2") could cause reading beyond the pattern.
+
+  (g) When reading a callout string, if the end delimiter was at the end of the
+      pattern one further code unit was read.
+
+  (h) An unterminated number after \g' could cause reading beyond the pattern.
+
+  (i) An insufficient memory size was being computed for compiling with
+      PCRE2_AUTO_CALLOUT.
+
+  (j) A conditional group with an assertion condition used more memory than was
+      allowed for it during parsing, so too many of them could therefore
+      overrun a buffer.
+
+  (k) If parsing a pattern exactly filled the buffer, the internal test for
+      overrun did not check when the final META_END item was added.
+
+  (l) If a lookbehind contained a subroutine call, and the called group
+      contained an option setting such as (?s), and the PCRE2_ANCHORED option
+      was set, unpredictable behaviour could occur. The underlying bug was
+      incorrect code and insufficient checking while searching for the end of
+      the called subroutine in the parsed pattern.
+
+  (m) Quantifiers following (*VERB)s were not being diagnosed as errors.
+
+  (n) The use of \Q...\E in a (*VERB) name when PCRE2_ALT_VERBNAMES and
+      PCRE2_AUTO_CALLOUT were both specified caused undetermined behaviour.
+
+  (o) If \Q was preceded by a quantified item, and the following \E was
+      followed by '?' or '+', and there was at least one literal character
+      between them, an internal error "unexpected repeat" occurred (example:
+      /.+\QX\E+/).
+
+  (p) A buffer overflow could occur while sorting the names in the group name
+      list (depending on the order in which the names were seen).
+
+  (q) A conditional group that started with a callout was not doing the right
+      check for a following assertion, leading to compiling bad code. Example:
+      /(?(C'XX))?!XX/
+
+  (r) If a character whose code point was greater than 0xffff appeared within
+      a lookbehind that was within another lookbehind, the calculation of the
+      lookbehind length went wrong and could provoke an internal error.
+
+  (t) The sequence \E- or \Q\E- after a POSIX class in a character class caused
+      an internal error. Now the hyphen is treated as a literal.
+
+4. Back references are now permitted in lookbehind assertions when there are
+no duplicated group numbers (that is, (?| has not been used), and, if the
+reference is by name, there is only one group of that name. The referenced
+group must, of course be of fixed length.
+
+5. pcre2test has been upgraded so that, when run under valgrind with valgrind
+support enabled, reading past the end of the pattern is detected, both when
+compiling and during callout processing.
+
+6. \g{+<number>} (e.g. \g{+2} ) is now supported. It is a "forward back
+reference" and can be useful in repetitions (compare \g{-<number>} ). Perl does
+not recognize this syntax.
+
+7. Automatic callouts are no longer generated before and after callouts in the
+pattern.
+
+8. When pcre2test was outputing information from a callout, the caret indicator
+for the current position in the subject line was incorrect if it was after an
+escape sequence for a character whose code point was greater than \x{ff}.
+
+9. Change 19 for 10.22 had a typo (PCRE_STATIC_RUNTIME should be
+PCRE2_STATIC_RUNTIME). Fix from David Gaussmann.
+
+10. Added --max-buffer-size to pcre2grep, to allow for automatic buffer
+expansion when long lines are encountered. Original patch by Dmitry
+Cherniachenko.
+
+11. If pcre2grep was compiled with JIT support, but the library was compiled
+without it (something that neither ./configure nor CMake allow, but it can be
+done by editing config.h), pcre2grep was giving a JIT error. Now it detects
+this situation and does not try to use JIT.
+
+12. Added some "const" qualifiers to variables in pcre2grep.
+
+13. Added Dmitry Cherniachenko's patch for colouring output in Windows
+(untested by me). Also, look for GREP_COLOUR or GREP_COLOR if the environment
+variables PCRE2GREP_COLOUR and PCRE2GREP_COLOR are not found.
+
+14. Add the -t (grand total) option to pcre2grep.
+
+15. A number of bugs have been mended relating to match start-up optimizations
+when the first thing in a pattern is a positive lookahead. These all applied
+only when PCRE2_NO_START_OPTIMIZE was *not* set:
+
+    (a) A pattern such as (?=.*X)X$ was incorrectly optimized as if it needed
+        both an initial 'X' and a following 'X'.
+    (b) Some patterns starting with an assertion that started with .* were
+        incorrectly optimized as having to match at the start of the subject or
+        after a newline. There are cases where this is not true, for example,
+        (?=.*[A-Z])(?=.{8,16})(?!.*[\s]) matches after the start in lines that
+        start with spaces. Starting .* in an assertion is no longer taken as an
+        indication of matching at the start (or after a newline).
+
+16. The "offset" modifier in pcre2test was not being ignored (as documented)
+when the POSIX API was in use.
+
+17. Added --enable-fuzz-support to "configure", causing an non-installed
+library containing a test function that can be called by fuzzers to be
+compiled. A non-installed  binary to run the test function locally, called
+pcre2fuzzcheck is also compiled.
+
+18. A pattern with PCRE2_DOTALL (/s) set but not PCRE2_NO_DOTSTAR_ANCHOR, and
+which started with .* inside a positive lookahead was incorrectly being
+compiled as implicitly anchored.
+
+19. Removed all instances of "register" declarations, as they are considered
+obsolete these days and in any case had become very haphazard.
+
+20. Add strerror() to pcre2test for failed file opening.
+
+21. Make pcre2test -C list valgrind support when it is enabled.
+
+22. Add the use_length modifier to pcre2test.
+
+23. Fix an off-by-one bug in pcre2test for the list of names for 'get' and
+'copy' modifiers.
+
+24. Add PCRE2_CALL_CONVENTION into the prototype declarations in pcre2.h as it
+is apparently needed there as well as in the function definitions. (Why did
+nobody ask for this in PCRE1?)
+
+25. Change the _PCRE2_H and _PCRE2_UCP_H guard macros in the header files to
+PCRE2_H_IDEMPOTENT_GUARD and PCRE2_UCP_H_IDEMPOTENT_GUARD to be more standard
+compliant and unique.
+
+26. pcre2-config --libs-posix was listing -lpcre2posix instead of
+-lpcre2-posix. Also, the CMake build process was building the library with the
+wrong name.
+
+27. In pcre2test, give some offset information for errors in hex patterns.
+This uses the C99 formatting sequence %td, except for MSVC which doesn't
+support it - %lu is used instead.
+
+28. Implemented pcre2_code_copy_with_tables(), and added pushtablescopy to
+pcre2test for testing it.
+
+29. Fix small memory leak in pcre2test.
+
+30. Fix out-of-bounds read for partial matching of /./ against an empty string
+when the newline type is CRLF.
+
+31. Fix a bug in pcre2test that caused a crash when a locale was set either in
+the current pattern or a previous one and a wide character was matched.
+
+32. The appearance of \p, \P, or \X in a substitution string when
+PCRE2_SUBSTITUTE_EXTENDED was set caused a segmentation fault (NULL
+dereference).
+
+33. If the starting offset was specified as greater than the subject length in
+a call to pcre2_substitute() an out-of-bounds memory reference could occur.
+
+34. When PCRE2 was compiled to use the heap instead of the stack for recursive
+calls to match(), a repeated minimizing caseless back reference, or a
+maximizing one where the two cases had different numbers of code units,
+followed by a caseful back reference, could lose the caselessness of the first
+repeated back reference (example: /(Z)(a)\2{1,2}?(?-i)\1X/i should match ZaAAZX
+but didn't).
+
+35. When a pattern is too complicated, PCRE2 gives up trying to find a minimum
+matching length and just records zero. Typically this happens when there are
+too many nested or recursive back references. If the limit was reached in
+certain recursive cases it failed to be triggered and an internal error could
+be the result.
+
+36. The pcre2_dfa_match() function now takes note of the recursion limit for
+the internal recursive calls that are used for lookrounds and recursions within
+the pattern.
+
+37. More refactoring has got rid of the internal could_be_empty_branch()
+function (around 400 lines of code, including comments) by keeping track of
+could-be-emptiness as the pattern is compiled instead of scanning compiled
+groups. (This would have been much harder before the refactoring of #3 above.)
+This lifts a restriction on the number of branches in a group (more than about
+1100 would give "pattern is too complicated").
+
+38. Add the "-ac" command line option to pcre2test as a synonym for "-pattern
+auto_callout".
+
+39. In a library with Unicode support, incorrect data was compiled for a
+pattern with PCRE2_UCP set without PCRE2_UTF if a class required all wide
+characters to match (for example, /[\s[:^ascii:]]/).
+
+40. The callout_error modifier has been added to pcre2test to make it possible
+to return PCRE2_ERROR_CALLOUT from a callout.
+
+41. A minor change to pcre2grep: colour reset is now "<esc>[0m" instead of
+"<esc>[00m".
+
+42. The limit in the auto-possessification code that was intended to catch
+overly-complicated patterns and not spend too much time auto-possessifying was
+being reset too often, resulting in very long compile times for some patterns.
+Now such patterns are no longer completely auto-possessified.
+
+43. Applied Jason Hood's revised patch for RunTest.bat.
+
+44. Added a new Windows script RunGrepTest.bat, courtesy of Jason Hood.
+
+45. Minor cosmetic fix to pcre2test: move a variable that is not used under
+Windows into the "not Windows" code.
+
+46. Applied Jason Hood's patches to upgrade pcre2grep under Windows and tidy
+some of the code:
+
+  * normalised the Windows condition by ensuring WIN32 is defined;
+  * enables the callout feature under Windows;
+  * adds globbing (Microsoft's implementation expands quoted args),
+    using a tweaked opendirectory;
+  * implements the is_*_tty functions for Windows;
+  * --color=always will write the ANSI sequences to file;
+  * add sequences 4 (underline works on Win10) and 5 (blink as bright
+    background, relatively standard on DOS/Win);
+  * remove the (char *) casts for the now-const strings;
+  * remove GREP_COLOUR (grep's command line allowed the 'u', but not
+    the environment), parsing GREP_COLORS instead;
+  * uses the current colour if not set, rather than black;
+  * add print_match for the undefined case;
+  * fixes a typo.
+
+In addition, colour settings containing anything other than digits and
+semicolon are ignored, and the colour controls are no longer output for empty
+strings.
+
+47. Detecting patterns that are too large inside the length-measuring loop
+saves processing ridiculously long patterns to their end.
+
+48. Ignore PCRE2_CASELESS when processing \h, \H, \v, and \V in classes as it
+just wastes time. In the UTF case it can also produce redundant entries in
+XCLASS lists caused by characters with multiple other cases and pairs of
+characters in the same "not-x" sublists.
+
+49. A pattern such as /(?=(a\K))/ can report the end of the match being before
+its start; pcre2test was not handling this correctly when using the POSIX
+interface (it was OK with the native interface).
+
+50. In pcre2grep, ignore all JIT compile errors. This means that pcre2grep will
+continue to work, falling back to interpretation if anything goes wrong with
+JIT.
+
+51. Applied patches from Christian Persch to configure.ac to make use of the
+AC_USE_SYSTEM_EXTENSIONS macro and to test for functions used by the JIT
+modules.
+
+52. Minor fixes to pcre2grep from Jason Hood:
+    * fixed some spacing;
+    * Windows doesn't usually use single quotes, so I've added a define
+      to use appropriate quotes [in an example];
+    * LC_ALL was displayed as "LCC_ALL";
+    * numbers 11, 12 & 13 should end in "th";
+    * use double quotes in usage message.
+
+53. When autopossessifying, skip empty branches without recursion, to reduce
+stack usage for the benefit of clang with -fsanitize-address, which uses huge
+stack frames. Example pattern: /X?(R||){3335}/. Fixes oss-fuzz issue 553.
+
+54. A pattern with very many explicit back references to a group that is a long
+way from the start of the pattern could take a long time to compile because
+searching for the referenced group in order to find the minimum length was
+being done repeatedly. Now up to 128 group minimum lengths are cached and the
+attempt to find a minimum length is abandoned if there is a back reference to a
+group whose number is greater than 128. (In that case, the pattern is so
+complicated that this optimization probably isn't worth it.) This fixes
+oss-fuzz issue 557.
+
+55. Issue 32 for 10.22 below was not correctly fixed. If pcre2grep in multiline
+mode with --only-matching matched several lines, it restarted scanning at the
+next line instead of moving on to the end of the matched string, which can be
+several lines after the start.
+
+56. Applied Jason Hood's new patch for RunGrepTest.bat that updates it in line
+with updates to the non-Windows version.
+
+
+
+Version 10.22 29-July-2016
+--------------------------
+
+1. Applied Jason Hood's patches to RunTest.bat and testdata/wintestoutput3
+to fix problems with running the tests under Windows.
+
+2. Implemented a facility for quoting literal characters within hexadecimal
+patterns in pcre2test, to make it easier to create patterns with just a few
+non-printing characters.
+
+3. Binary zeros are not supported in pcre2test input files. It now detects them
+and gives an error.
+
+4. Updated the valgrind parameters in RunTest: (a) changed smc-check=all to
+smc-check=all-non-file; (b) changed obj:* in the suppression file to obj:??? so
+that it matches only unknown objects.
+
+5. Updated the maintenance script maint/ManyConfigTests to make it easier to
+select individual groups of tests.
+
+6. When the POSIX wrapper function regcomp() is called, the REG_NOSUB option
+used to set PCRE2_NO_AUTO_CAPTURE when calling pcre2_compile(). However, this
+disables the use of back references (and subroutine calls), which are supported
+by other implementations of regcomp() with RE_NOSUB. Therefore, REG_NOSUB no
+longer causes PCRE2_NO_AUTO_CAPTURE to be set, though it still ignores nmatch
+and pmatch when regexec() is called.
+
+7. Because of 6 above, pcre2test has been modified with a new modifier called
+posix_nosub, to call regcomp() with REG_NOSUB. Previously the no_auto_capture
+modifier had this effect. That option is now ignored when the POSIX API is in
+use.
+
+8. Minor tidies to the pcre2demo.c sample program, including more comments
+about its 8-bit-ness.
+
+9. Detect unmatched closing parentheses and give the error in the pre-scan
+instead of later. Previously the pre-scan carried on and could give a
+misleading incorrect error message. For example, /(?J)(?'a'))(?'a')/ gave a
+message about invalid duplicate group names.
+
+10. It has happened that pcre2test was accidentally linked with another POSIX
+regex library instead of libpcre2-posix. In this situation, a call to regcomp()
+(in the other library) may succeed, returning zero, but of course putting its
+own data into the regex_t block. In one example the re_pcre2_code field was
+left as NULL, which made pcre2test think it had not got a compiled POSIX regex,
+so it treated the next line as another pattern line, resulting in a confusing
+error message. A check has been added to pcre2test to see if the data returned
+from a successful call of regcomp() are valid for PCRE2's regcomp(). If they
+are not, an error message is output and the pcre2test run is abandoned. The
+message points out the possibility of a mis-linking. Hopefully this will avoid
+some head-scratching the next time this happens.
+
+11. A pattern such as /(?<=((?C)0))/, which has a callout inside a lookbehind
+assertion, caused pcre2test to output a very large number of spaces when the
+callout was taken, making the program appearing to loop.
+
+12. A pattern that included (*ACCEPT) in the middle of a sufficiently deeply
+nested set of parentheses of sufficient size caused an overflow of the
+compiling workspace (which was diagnosed, but of course is not desirable).
+
+13. Detect missing closing parentheses during the pre-pass for group
+identification.
+
+14. Changed some integer variable types and put in a number of casts, following
+a report of compiler warnings from Visual Studio 2013 and a few tests with
+gcc's -Wconversion (which still throws up a lot).
+
+15. Implemented pcre2_code_copy(), and added pushcopy and #popcopy to pcre2test
+for testing it.
+
+16. Change 66 for 10.21 introduced the use of snprintf() in PCRE2's version of
+regerror(). When the error buffer is too small, my version of snprintf() puts a
+binary zero in the final byte. Bug #1801 seems to show that other versions do
+not do this, leading to bad output from pcre2test when it was checking for
+buffer overflow. It no longer assumes a binary zero at the end of a too-small
+regerror() buffer.
+
+17. Fixed typo ("&&" for "&") in pcre2_study(). Fortunately, this could not
+actually affect anything, by sheer luck.
+
+18. Two minor fixes for MSVC compilation: (a) removal of apparently incorrect
+"const" qualifiers in pcre2test and (b) defining snprintf as _snprintf for
+older MSVC compilers. This has been done both in src/pcre2_internal.h for most
+of the library, and also in src/pcre2posix.c, which no longer includes
+pcre2_internal.h (see 24 below).
+
+19. Applied Chris Wilson's patch (Bugzilla #1681) to CMakeLists.txt for MSVC
+static compilation. Subsequently applied Chris Wilson's second patch, putting
+the first patch under a new option instead of being unconditional when
+PCRE_STATIC is set.
+
+20. Updated pcre2grep to set stdout as binary when run under Windows, so as not
+to convert \r\n at the ends of reflected lines into \r\r\n. This required
+ensuring that other output that is written to stdout (e.g. file names) uses the
+appropriate line terminator: \r\n for Windows, \n otherwise.
+
+21. When a line is too long for pcre2grep's internal buffer, show the maximum
+length in the error message.
+
+22. Added support for string callouts to pcre2grep (Zoltan's patch with PH
+additions).
+
+23. RunTest.bat was missing a "set type" line for test 22.
+
+24. The pcre2posix.c file was including pcre2_internal.h, and using some
+"private" knowledge of the data structures. This is unnecessary; the code has
+been re-factored and no longer includes pcre2_internal.h.
+
+25. A racing condition is fixed in JIT reported by Mozilla.
+
+26. Minor code refactor to avoid "array subscript is below array bounds"
+compiler warning.
+
+27. Minor code refactor to avoid "left shift of negative number" warning.
+
+28. Add a bit more sanity checking to pcre2_serialize_decode() and document
+that it expects trusted data.
+
+29. Fix typo in pcre2_jit_test.c
+
+30. Due to an oversight, pcre2grep was not making use of JIT when available.
+This is now fixed.
+
+31. The RunGrepTest script is updated to use the valgrind suppressions file
+when testing with JIT under valgrind (compare 10.21/51 below). The suppressions
+file is updated so that is now the same as for PCRE1: it suppresses the
+Memcheck warnings Addr16 and Cond in unknown objects (that is, JIT-compiled
+code). Also changed smc-check=all to smc-check=all-non-file as was done for
+RunTest (see 4 above).
+
+32. Implemented the PCRE2_NO_JIT option for pcre2_match().
+
+33. Fix typo that gave a compiler error when JIT not supported.
+
+34. Fix comment describing the returns from find_fixedlength().
+
+35. Fix potential negative index in pcre2test.
+
+36. Calls to pcre2_get_error_message() with error numbers that are never
+returned by PCRE2 functions were returning empty strings. Now the error code
+PCRE2_ERROR_BADDATA is returned. A facility has been added to pcre2test to
+show the texts for given error numbers (i.e. to call pcre2_get_error_message()
+and display what it returns) and a few representative error codes are now
+checked in RunTest.
+
+37. Added "&& !defined(__INTEL_COMPILER)" to the test for __GNUC__ in
+pcre2_match.c, in anticipation that this is needed for the same reason it was
+recently added to pcrecpp.cc in PCRE1.
+
+38. Using -o with -M in pcre2grep could cause unnecessary repeated output when
+the match extended over a line boundary, as it tried to find more matches "on
+the same line" - but it was already over the end.
+
+39. Allow \C in lookbehinds and DFA matching in UTF-32 mode (by converting it
+to the same code as '.' when PCRE2_DOTALL is set).
+
+40. Fix two clang compiler warnings in pcre2test when only one code unit width
+is supported.
+
+41. Upgrade RunTest to automatically re-run test 2 with a large (64MiB) stack
+if it fails when running the interpreter with a 16MiB stack (and if changing
+the stack size via pcre2test is possible). This avoids having to manually set a
+large stack size when testing with clang.
+
+42. Fix register overwite in JIT when SSE2 acceleration is enabled.
+
+43. Detect integer overflow in pcre2test pattern and data repetition counts.
+
+44. In pcre2test, ignore "allcaptures" after DFA matching.
+
+45. Fix unaligned accesses on x86. Patch by Marc Mutz.
+
+46. Fix some more clang compiler warnings.
+
+
+Version 10.21 12-January-2016
+-----------------------------
+
+1. Improve matching speed of patterns starting with + or * in JIT.
+
+2. Use memchr() to find the first character in an unanchored match in 8-bit
+mode in the interpreter. This gives a significant speed improvement.
+
+3. Removed a redundant copy of the opcode_possessify table in the
+pcre2_auto_possessify.c source.
+
+4. Fix typos in dftables.c for z/OS.
+
+5. Change 36 for 10.20 broke the handling of [[:>:]] and [[:<:]] in that
+processing them could involve a buffer overflow if the following character was
+an opening parenthesis.
+
+6. Change 36 for 10.20 also introduced a bug in processing this pattern:
+/((?x)(*:0))#(?'/. Specifically: if a setting of (?x) was followed by a (*MARK)
+setting (which (*:0) is), then (?x) did not get unset at the end of its group
+during the scan for named groups, and hence the external # was incorrectly
+treated as a comment and the invalid (?' at the end of the pattern was not
+diagnosed. This caused a buffer overflow during the real compile. This bug was
+discovered by Karl Skomski with the LLVM fuzzer.
+
+7. Moved the pcre2_find_bracket() function from src/pcre2_compile.c into its
+own source module to avoid a circular dependency between src/pcre2_compile.c
+and src/pcre2_study.c
+
+8. A callout with a string argument containing an opening square bracket, for
+example /(?C$[$)(?<]/, was incorrectly processed and could provoke a buffer
+overflow. This bug was discovered by Karl Skomski with the LLVM fuzzer.
+
+9. The handling of callouts during the pre-pass for named group identification
+has been tightened up.
+
+10. The quantifier {1} can be ignored, whether greedy, non-greedy, or
+possessive. This is a very minor optimization.
+
+11. A possessively repeated conditional group that could match an empty string,
+for example, /(?(R))*+/, was incorrectly compiled.
+
+12. The Unicode tables have been updated to Unicode 8.0.0 (thanks to Christian
+Persch).
+
+13. An empty comment (?#) in a pattern was incorrectly processed and could
+provoke a buffer overflow. This bug was discovered by Karl Skomski with the
+LLVM fuzzer.
+
+14. Fix infinite recursion in the JIT compiler when certain patterns such as
+/(?:|a|){100}x/ are analysed.
+
+15. Some patterns with character classes involving [: and \\ were incorrectly
+compiled and could cause reading from uninitialized memory or an incorrect
+error diagnosis. Examples are: /[[:\\](?<[::]/ and /[[:\\](?'abc')[a:]. The
+first of these bugs was discovered by Karl Skomski with the LLVM fuzzer.
+
+16. Pathological patterns containing many nested occurrences of [: caused
+pcre2_compile() to run for a very long time. This bug was found by the LLVM
+fuzzer.
+
+17. A missing closing parenthesis for a callout with a string argument was not
+being diagnosed, possibly leading to a buffer overflow. This bug was found by
+the LLVM fuzzer.
+
+18. A conditional group with only one branch has an implicit empty alternative
+branch and must therefore be treated as potentially matching an empty string.
+
+19. If (?R was followed by - or + incorrect behaviour happened instead of a
+diagnostic. This bug was discovered by Karl Skomski with the LLVM fuzzer.
+
+20. Another bug that was introduced by change 36 for 10.20: conditional groups
+whose condition was an assertion preceded by an explicit callout with a string
+argument might be incorrectly processed, especially if the string contained \Q.
+This bug was discovered by Karl Skomski with the LLVM fuzzer.
+
+21. Compiling PCRE2 with the sanitize options of clang showed up a number of
+very pedantic coding infelicities and a buffer overflow while checking a UTF-8
+string if the final multi-byte UTF-8 character was truncated.
+
+22. For Perl compatibility in EBCDIC environments, ranges such as a-z in a
+class, where both values are literal letters in the same case, omit the
+non-letter EBCDIC code points within the range.
+
+23. Finding the minimum matching length of complex patterns with back
+references and/or recursions can take a long time. There is now a cut-off that
+gives up trying to find a minimum length when things get too complex.
+
+24. An optimization has been added that speeds up finding the minimum matching
+length for patterns containing repeated capturing groups or recursions.
+
+25. If a pattern contained a back reference to a group whose number was
+duplicated as a result of appearing in a (?|...) group, the computation of the
+minimum matching length gave a wrong result, which could cause incorrect "no
+match" errors. For such patterns, a minimum matching length cannot at present
+be computed.
+
+26. Added a check for integer overflow in conditions (?(<digits>) and
+(?(R<digits>). This omission was discovered by Karl Skomski with the LLVM
+fuzzer.
+
+27. Fixed an issue when \p{Any} inside an xclass did not read the current
+character.
+
+28. If pcre2grep was given the -q option with -c or -l, or when handling a
+binary file, it incorrectly wrote output to stdout.
+
+29. The JIT compiler did not restore the control verb head in case of *THEN
+control verbs. This issue was found by Karl Skomski with a custom LLVM fuzzer.
+
+30. The way recursive references such as (?3) are compiled has been re-written
+because the old way was the cause of many issues. Now, conversion of the group
+number into a pattern offset does not happen until the pattern has been
+completely compiled. This does mean that detection of all infinitely looping
+recursions is postponed till match time. In the past, some easy ones were
+detected at compile time. This re-writing was done in response to yet another
+bug found by the LLVM fuzzer.
+
+31. A test for a back reference to a non-existent group was missing for items
+such as \987. This caused incorrect code to be compiled. This issue was found
+by Karl Skomski with a custom LLVM fuzzer.
+
+32. Error messages for syntax errors following \g and \k were giving inaccurate
+offsets in the pattern.
+
+33. Improve the performance of starting single character repetitions in JIT.
+
+34. (*LIMIT_MATCH=) now gives an error instead of setting the value to 0.
+
+35. Error messages for syntax errors in *LIMIT_MATCH and *LIMIT_RECURSION now
+give the right offset instead of zero.
+
+36. The JIT compiler should not check repeats after a {0,1} repeat byte code.
+This issue was found by Karl Skomski with a custom LLVM fuzzer.
+
+37. The JIT compiler should restore the control chain for empty possessive
+repeats. This issue was found by Karl Skomski with a custom LLVM fuzzer.
+
+38. A bug which was introduced by the single character repetition optimization
+was fixed.
+
+39. Match limit check added to recursion. This issue was found by Karl Skomski
+with a custom LLVM fuzzer.
+
+40. Arrange for the UTF check in pcre2_match() and pcre2_dfa_match() to look
+only at the part of the subject that is relevant when the starting offset is
+non-zero.
+
+41. Improve first character match in JIT with SSE2 on x86.
+
+42. Fix two assertion fails in JIT. These issues were found by Karl Skomski
+with a custom LLVM fuzzer.
+
+43. Correct the setting of CMAKE_C_FLAGS in CMakeLists.txt (patch from Roy Ivy
+III).
+
+44. Fix bug in RunTest.bat for new test 14, and adjust the script for the added
+test (there are now 20 in total).
+
+45. Fixed a corner case of range optimization in JIT.
+
+46. Add the ${*MARK} facility to pcre2_substitute().
+
+47. Modifier lists in pcre2test were splitting at spaces without the required
+commas.
+
+48. Implemented PCRE2_ALT_VERBNAMES.
+
+49. Fixed two issues in JIT. These were found by Karl Skomski with a custom
+LLVM fuzzer.
+
+50. The pcre2test program has been extended by adding the #newline_default
+command. This has made it possible to run the standard tests when PCRE2 is
+compiled with either CR or CRLF as the default newline convention. As part of
+this work, the new command was added to several test files and the testing
+scripts were modified. The pcre2grep tests can now also be run when there is no
+LF in the default newline convention.
+
+51. The RunTest script has been modified so that, when JIT is used and valgrind
+is specified, a valgrind suppressions file is set up to ignore "Invalid read of
+size 16" errors because these are false positives when the hardware supports
+the SSE2 instruction set.
+
+52. It is now possible to have comment lines amid the subject strings in
+pcre2test (and perltest.sh) input.
+
+53. Implemented PCRE2_USE_OFFSET_LIMIT and pcre2_set_offset_limit().
+
+54. Add the null_context modifier to pcre2test so that calling pcre2_compile()
+and the matching functions with NULL contexts can be tested.
+
+55. Implemented PCRE2_SUBSTITUTE_EXTENDED.
+
+56. In a character class such as [\W\p{Any}] where both a negative-type escape
+("not a word character") and a property escape were present, the property
+escape was being ignored.
+
+57. Fixed integer overflow for patterns whose minimum matching length is very,
+very large.
+
+58. Implemented --never-backslash-C.
+
+59. Change 55 above introduced a bug by which certain patterns provoked the
+erroneous error "\ at end of pattern".
+
+60. The special sequences [[:<:]] and [[:>:]] gave rise to incorrect compiling
+errors or other strange effects if compiled in UCP mode. Found with libFuzzer
+and AddressSanitizer.
+
+61. Whitespace at the end of a pcre2test pattern line caused a spurious error
+message if there were only single-character modifiers. It should be ignored.
+
+62. The use of PCRE2_NO_AUTO_CAPTURE could cause incorrect compilation results
+or segmentation errors for some patterns. Found with libFuzzer and
+AddressSanitizer.
+
+63. Very long names in (*MARK) or (*THEN) etc. items could provoke a buffer
+overflow.
+
+64. Improve error message for overly-complicated patterns.
+
+65. Implemented an optional replication feature for patterns in pcre2test, to
+make it easier to test long repetitive patterns. The tests for 63 above are
+converted to use the new feature.
+
+66. In the POSIX wrapper, if regerror() was given too small a buffer, it could
+misbehave.
+
+67. In pcre2_substitute() in UTF mode, the UTF validity check on the
+replacement string was happening before the length setting when the replacement
+string was zero-terminated.
+
+68. In pcre2_substitute() in UTF mode, PCRE2_NO_UTF_CHECK can be set for the
+second and subsequent calls to pcre2_match().
+
+69. There was no check for integer overflow for a replacement group number in
+pcre2_substitute(). An added check for a number greater than the largest group
+number in the pattern means this is not now needed.
+
+70. The PCRE2-specific VERSION condition didn't work correctly if only one
+digit was given after the decimal point, or if more than two digits were given.
+It now works with one or two digits, and gives a compile time error if more are
+given.
+
+71. In pcre2_substitute() there was the possibility of reading one code unit
+beyond the end of the replacement string.
+
+72. The code for checking a subject's UTF-32 validity for a pattern with a
+lookbehind involved an out-of-bounds pointer, which could potentially cause
+trouble in some environments.
+
+73. The maximum lookbehind length was incorrectly calculated for patterns such
+as /(?<=(a)(?-1))x/ which have a recursion within a backreference.
+
+74. Give an error if a lookbehind assertion is longer than 65535 code units.
+
+75. Give an error in pcre2_substitute() if a match ends before it starts (as a
+result of the use of \K).
+
+76. Check the length of subpattern names and the names in (*MARK:xx) etc.
+dynamically to avoid the possibility of integer overflow.
+
+77. Implement pcre2_set_max_pattern_length() so that programs can restrict the
+size of patterns that they are prepared to handle.
+
+78. (*NO_AUTO_POSSESS) was not working.
+
+79. Adding group information caching improves the speed of compiling when
+checking whether a group has a fixed length and/or could match an empty string,
+especially when recursion or subroutine calls are involved. However, this
+cannot be used when (?| is present in the pattern because the same number may
+be used for groups of different sizes. To catch runaway patterns in this
+situation, counts have been introduced to the functions that scan for empty
+branches or compute fixed lengths.
+
+80. Allow for the possibility of the size of the nest_save structure not being
+a factor of the size of the compiling workspace (it currently is).
+
+81. Check for integer overflow in minimum length calculation and cap it at
+65535.
+
+82. Small optimizations in code for finding the minimum matching length.
+
+83. Lock out configuring for EBCDIC with non-8-bit libraries.
+
+84. Test for error code <= 0 in regerror().
+
+85. Check for too many replacements (more than INT_MAX) in pcre2_substitute().
+
+86. Avoid the possibility of computing with an out-of-bounds pointer (though
+not dereferencing it) while handling lookbehind assertions.
+
+87. Failure to get memory for the match data in regcomp() is now given as a
+regcomp() error instead of waiting for regexec() to pick it up.
+
+88. In pcre2_substitute(), ensure that CRLF is not split when it is a valid
+newline sequence.
+
+89. Paranoid check in regcomp() for bad error code from pcre2_compile().
+
+90. Run test 8 (internal offsets and code sizes) for link sizes 3 and 4 as well
+as for link size 2.
+
+91. Document that JIT has a limit on pattern size, and give more information
+about JIT compile failures in pcre2test.
+
+92. Implement PCRE2_INFO_HASBACKSLASHC.
+
+93. Re-arrange valgrind support code in pcre2test to avoid spurious reports
+with JIT (possibly caused by SSE2?).
+
+94. Support offset_limit in JIT.
+
+95. A sequence such as [[:punct:]b] that is, a POSIX character class followed
+by a single ASCII character in a class item, was incorrectly compiled in UCP
+mode. The POSIX class got lost, but only if the single character followed it.
+
+96. [:punct:] in UCP mode was matching some characters in the range 128-255
+that should not have been matched.
+
+97. If [:^ascii:] or [:^xdigit:] are present in a non-negated class, all
+characters with code points greater than 255 are in the class. When a Unicode
+property was also in the class (if PCRE2_UCP is set, escapes such as \w are
+turned into Unicode properties), wide characters were not correctly handled,
+and could fail to match.
+
+98. In pcre2test, make the "startoffset" modifier a synonym of "offset",
+because it sets the "startoffset" parameter for pcre2_match().
+
+99. If PCRE2_AUTO_CALLOUT was set on a pattern that had a (?# comment between
+an item and its qualifier (for example, A(?#comment)?B) pcre2_compile()
+misbehaved. This bug was found by the LLVM fuzzer.
+
+100. The error for an invalid UTF pattern string always gave the code unit
+offset as zero instead of where the invalidity was found.
+
+101. Further to 97 above, negated classes such as [^[:^ascii:]\d] were also not
+working correctly in UCP mode.
+
+102. Similar to 99 above, if an isolated \E was present between an item and its
+qualifier when PCRE2_AUTO_CALLOUT was set, pcre2_compile() misbehaved. This bug
+was found by the LLVM fuzzer.
+
+103. The POSIX wrapper function regexec() crashed if the option REG_STARTEND
+was set when the pmatch argument was NULL. It now returns REG_INVARG.
+
+104. Allow for up to 32-bit numbers in the ordin() function in pcre2grep.
+
+105. An empty \Q\E sequence between an item and its qualifier caused
+pcre2_compile() to misbehave when auto callouts were enabled. This bug
+was found by the LLVM fuzzer.
+
+106. If both PCRE2_ALT_VERBNAMES and PCRE2_EXTENDED were set, and a (*MARK) or
+other verb "name" ended with whitespace immediately before the closing
+parenthesis, pcre2_compile() misbehaved. Example: /(*:abc )/, but only when
+both those options were set.
+
+107. In a number of places pcre2_compile() was not handling NULL characters
+correctly, and pcre2test with the "bincode" modifier was not always correctly
+displaying fields containing NULLS:
+
+   (a) Within /x extended #-comments
+   (b) Within the "name" part of (*MARK) and other *verbs
+   (c) Within the text argument of a callout
+
+108. If a pattern that was compiled with PCRE2_EXTENDED started with white
+space or a #-type comment that was followed by (?-x), which turns off
+PCRE2_EXTENDED, and there was no subsequent (?x) to turn it on again,
+pcre2_compile() assumed that (?-x) applied to the whole pattern and
+consequently mis-compiled it. This bug was found by the LLVM fuzzer. The fix
+for this bug means that a setting of any of the (?imsxJU) options at the start
+of a pattern is no longer transferred to the options that are returned by
+PCRE2_INFO_ALLOPTIONS. In fact, this was an anachronism that should have
+changed when the effects of those options were all moved to compile time.
+
+109. An escaped closing parenthesis in the "name" part of a (*verb) when
+PCRE2_ALT_VERBNAMES was set caused pcre2_compile() to malfunction. This bug
+was found by the LLVM fuzzer.
+
+110. Implemented PCRE2_SUBSTITUTE_UNSET_EMPTY, and updated pcre2test to make it
+possible to test it.
+
+111. "Harden" pcre2test against ridiculously large values in modifiers and
+command line arguments.
+
+112. Implemented PCRE2_SUBSTITUTE_UNKNOWN_UNSET and PCRE2_SUBSTITUTE_OVERFLOW_
+LENGTH.
+
+113. Fix printing of *MARK names that contain binary zeroes in pcre2test.
+
+
+Version 10.20 30-June-2015
+--------------------------
+
+1. Callouts with string arguments have been added.
+
+2. Assertion code generator in JIT has been optimized.
+
+3. The invalid pattern (?(?C) has a missing assertion condition at the end. The
+pcre2_compile() function read past the end of the input before diagnosing an
+error. This bug was discovered by the LLVM fuzzer.
+
+4. Implemented pcre2_callout_enumerate().
+
+5. Fix JIT compilation of conditional blocks whose assertion is converted to
+(*FAIL). E.g: /(?(?!))/.
+
+6. The pattern /(?(?!)^)/ caused references to random memory. This bug was
+discovered by the LLVM fuzzer.
+
+7. The assertion (?!) is optimized to (*FAIL). This was not handled correctly
+when this assertion was used as a condition, for example (?(?!)a|b). In
+pcre2_match() it worked by luck; in pcre2_dfa_match() it gave an incorrect
+error about an unsupported item.
+
+8. For some types of pattern, for example /Z*(|d*){216}/, the auto-
+possessification code could take exponential time to complete. A recursion
+depth limit of 1000 has been imposed to limit the resources used by this
+optimization. This infelicity was discovered by the LLVM fuzzer.
+
+9. A pattern such as /(*UTF)[\S\V\H]/, which contains a negated special class
+such as \S in non-UCP mode, explicit wide characters (> 255) can be ignored
+because \S ensures they are all in the class. The code for doing this was
+interacting badly with the code for computing the amount of space needed to
+compile the pattern, leading to a buffer overflow. This bug was discovered by
+the LLVM fuzzer.
+
+10. A pattern such as /((?2)+)((?1))/ which has mutual recursion nested inside
+other kinds of group caused stack overflow at compile time. This bug was
+discovered by the LLVM fuzzer.
+
+11. A pattern such as /(?1)(?#?'){8}(a)/ which had a parenthesized comment
+between a subroutine call and its quantifier was incorrectly compiled, leading
+to buffer overflow or other errors. This bug was discovered by the LLVM fuzzer.
+
+12. The illegal pattern /(?(?<E>.*!.*)?)/ was not being diagnosed as missing an
+assertion after (?(. The code was failing to check the character after (?(?<
+for the ! or = that would indicate a lookbehind assertion. This bug was
+discovered by the LLVM fuzzer.
+
+13. A pattern such as /X((?2)()*+){2}+/ which has a possessive quantifier with
+a fixed maximum following a group that contains a subroutine reference was
+incorrectly compiled and could trigger buffer overflow. This bug was discovered
+by the LLVM fuzzer.
+
+14. Negative relative recursive references such as (?-7) to non-existent
+subpatterns were not being diagnosed and could lead to unpredictable behaviour.
+This bug was discovered by the LLVM fuzzer.
+
+15. The bug fixed in 14 was due to an integer variable that was unsigned when
+it should have been signed. Some other "int" variables, having been checked,
+have either been changed to uint32_t or commented as "must be signed".
+
+16. A mutual recursion within a lookbehind assertion such as (?<=((?2))((?1)))
+caused a stack overflow instead of the diagnosis of a non-fixed length
+lookbehind assertion. This bug was discovered by the LLVM fuzzer.
+
+17. The use of \K in a positive lookbehind assertion in a non-anchored pattern
+(e.g. /(?<=\Ka)/) could make pcre2grep loop.
+
+18. There was a similar problem to 17 in pcre2test for global matches, though
+the code there did catch the loop.
+
+19. If a greedy quantified \X was preceded by \C in UTF mode (e.g. \C\X*),
+and a subsequent item in the pattern caused a non-match, backtracking over the
+repeated \X did not stop, but carried on past the start of the subject, causing
+reference to random memory and/or a segfault. There were also some other cases
+where backtracking after \C could crash. This set of bugs was discovered by the
+LLVM fuzzer.
+
+20. The function for finding the minimum length of a matching string could take
+a very long time if mutual recursion was present many times in a pattern, for
+example, /((?2){73}(?2))((?1))/. A better mutual recursion detection method has
+been implemented. This infelicity was discovered by the LLVM fuzzer.
+
+21. Implemented PCRE2_NEVER_BACKSLASH_C.
+
+22. The feature for string replication in pcre2test could read from freed
+memory if the replication required a buffer to be extended, and it was not
+working properly in 16-bit and 32-bit modes. This issue was discovered by a
+fuzzer: see http://lcamtuf.coredump.cx/afl/.
+
+23. Added the PCRE2_ALT_CIRCUMFLEX option.
+
+24. Adjust the treatment of \8 and \9 to be the same as the current Perl
+behaviour.
+
+25. Static linking against the PCRE2 library using the pkg-config module was
+failing on missing pthread symbols.
+
+26. If a group that contained a recursive back reference also contained a
+forward reference subroutine call followed by a non-forward-reference
+subroutine call, for example /.((?2)(?R)\1)()/, pcre2_compile() failed to
+compile correct code, leading to undefined behaviour or an internally detected
+error. This bug was discovered by the LLVM fuzzer.
+
+27. Quantification of certain items (e.g. atomic back references) could cause
+incorrect code to be compiled when recursive forward references were involved.
+For example, in this pattern: /(?1)()((((((\1++))\x85)+)|))/. This bug was
+discovered by the LLVM fuzzer.
+
+28. A repeated conditional group whose condition was a reference by name caused
+a buffer overflow if there was more than one group with the given name. This
+bug was discovered by the LLVM fuzzer.
+
+29. A recursive back reference by name within a group that had the same name as
+another group caused a buffer overflow. For example: /(?J)(?'d'(?'d'\g{d}))/.
+This bug was discovered by the LLVM fuzzer.
+
+30. A forward reference by name to a group whose number is the same as the
+current group, for example in this pattern: /(?|(\k'Pm')|(?'Pm'))/, caused a
+buffer overflow at compile time. This bug was discovered by the LLVM fuzzer.
+
+31. Fix -fsanitize=undefined warnings for left shifts of 1 by 31 (it treats 1
+as an int; fixed by writing it as 1u).
+
+32. Fix pcre2grep compile when -std=c99 is used with gcc, though it still gives
+a warning for "fileno" unless -std=gnu99 us used.
+
+33. A lookbehind assertion within a set of mutually recursive subpatterns could
+provoke a buffer overflow. This bug was discovered by the LLVM fuzzer.
+
+34. Give an error for an empty subpattern name such as (?'').
+
+35. Make pcre2test give an error if a pattern that follows #forbud_utf contains
+\P, \p, or \X.
+
+36. The way named subpatterns are handled has been refactored. There is now a
+pre-pass over the regex which does nothing other than identify named
+subpatterns and count the total captures. This means that information about
+named patterns is known before the rest of the compile. In particular, it means
+that forward references can be checked as they are encountered. Previously, the
+code for handling forward references was contorted and led to several errors in
+computing the memory requirements for some patterns, leading to buffer
+overflows.
+
+37. There was no check for integer overflow in subroutine calls such as (?123).
+
+38. The table entry for \l in EBCDIC environments was incorrect, leading to its
+being treated as a literal 'l' instead of causing an error.
+
+39. If a non-capturing group containing a conditional group that could match
+an empty string was repeated, it was not identified as matching an empty string
+itself. For example: /^(?:(?(1)x|)+)+$()/.
+
+40. In an EBCDIC environment, pcretest was mishandling the escape sequences
+\a and \e in test subject lines.
+
+41. In an EBCDIC environment, \a in a pattern was converted to the ASCII
+instead of the EBCDIC value.
+
+42. The handling of \c in an EBCDIC environment has been revised so that it is
+now compatible with the specification in Perl's perlebcdic page.
+
+43. Single character repetition in JIT has been improved. 20-30% speedup
+was achieved on certain patterns.
+
+44. The EBCDIC character 0x41 is a non-breaking space, equivalent to 0xa0 in
+ASCII/Unicode. This has now been added to the list of characters that are
+recognized as white space in EBCDIC.
+
+45. When PCRE2 was compiled without Unicode support, the use of \p and \P gave
+an error (correctly) when used outside a class, but did not give an error
+within a class.
+
+46. \h within a class was incorrectly compiled in EBCDIC environments.
+
+47. JIT should return with error when the compiled pattern requires
+more stack space than the maximum.
+
+48. Fixed a memory leak in pcre2grep when a locale is set.
+
+
+Version 10.10 06-March-2015
+---------------------------
+
+1. When a pattern is compiled, it remembers the highest back reference so that
+when matching, if the ovector is too small, extra memory can be obtained to
+use instead. A conditional subpattern whose condition is a check on a capture
+having happened, such as, for example in the pattern /^(?:(a)|b)(?(1)A|B)/, is
+another kind of back reference, but it was not setting the highest
+backreference number. This mattered only if pcre2_match() was called with an
+ovector that was too small to hold the capture, and there was no other kind of
+back reference (a situation which is probably quite rare). The effect of the
+bug was that the condition was always treated as FALSE when the capture could
+not be consulted, leading to a incorrect behaviour by pcre2_match(). This bug
+has been fixed.
+
+2. Functions for serialization and deserialization of sets of compiled patterns
+have been added.
+
+3. The value that is returned by PCRE2_INFO_SIZE has been corrected to remove
+excess code units at the end of the data block that may occasionally occur if
+the code for calculating the size over-estimates. This change stops the
+serialization code copying uninitialized data, to which valgrind objects. The
+documentation of PCRE2_INFO_SIZE was incorrect in stating that the size did not
+include the general overhead. This has been corrected.
+
+4. All code units in every slot in the table of group names are now set, again
+in order to avoid accessing uninitialized data when serializing.
+
+5. The (*NO_JIT) feature is implemented.
+
+6. If a bug that caused pcre2_compile() to use more memory than allocated was
+triggered when using valgrind, the code in (3) above passed a stupidly large
+value to valgrind. This caused a crash instead of an "internal error" return.
+
+7. A reference to a duplicated named group (either a back reference or a test
+for being set in a conditional) that occurred in a part of the pattern where
+PCRE2_DUPNAMES was not set caused the amount of memory needed for the pattern
+to be incorrectly calculated, leading to overwriting.
+
+8. A mutually recursive set of back references such as (\2)(\1) caused a
+segfault at compile time (while trying to find the minimum matching length).
+The infinite loop is now broken (with the minimum length unset, that is, zero).
+
+9. If an assertion that was used as a condition was quantified with a minimum
+of zero, matching went wrong. In particular, if the whole group had unlimited
+repetition and could match an empty string, a segfault was likely. The pattern
+(?(?=0)?)+ is an example that caused this. Perl allows assertions to be
+quantified, but not if they are being used as conditions, so the above pattern
+is faulted by Perl. PCRE2 has now been changed so that it also rejects such
+patterns.
+
+10. The error message for an invalid quantifier has been changed from "nothing
+to repeat" to "quantifier does not follow a repeatable item".
+
+11. If a bad UTF string is compiled with NO_UTF_CHECK, it may succeed, but
+scanning the compiled pattern in subsequent auto-possessification can get out
+of step and lead to an unknown opcode. Previously this could have caused an
+infinite loop. Now it generates an "internal error" error. This is a tidyup,
+not a bug fix; passing bad UTF with NO_UTF_CHECK is documented as having an
+undefined outcome.
+
+12. A UTF pattern containing a "not" match of a non-ASCII character and a
+subroutine reference could loop at compile time. Example: /[^\xff]((?1))/.
+
+13. The locale test (RunTest 3) has been upgraded. It now checks that a locale
+that is found in the output of "locale -a" can actually be set by pcre2test
+before it is accepted. Previously, in an environment where a locale was listed
+but would not set (an example does exist), the test would "pass" without
+actually doing anything. Also the fr_CA locale has been added to the list of
+locales that can be used.
+
+14. Fixed a bug in pcre2_substitute(). If a replacement string ended in a
+capturing group number without parentheses, the last character was incorrectly
+literally included at the end of the replacement string.
+
+15. A possessive capturing group such as (a)*+ with a minimum repeat of zero
+failed to allow the zero-repeat case if pcre2_match() was called with an
+ovector too small to capture the group.
+
+16. Improved error message in pcre2test when setting the stack size (-S) fails.
+
+17. Fixed two bugs in CMakeLists.txt: (1) Some lines had got lost in the
+transfer from PCRE1, meaning that CMake configuration failed if "build tests"
+was selected. (2) The file src/pcre2_serialize.c had not been added to the list
+of PCRE2 sources, which caused a failure to build pcre2test.
+
+18. Fixed typo in pcre2_serialize.c (DECL instead of DEFN) that causes problems
+only on Windows.
+
+19. Use binary input when reading back saved serialized patterns in pcre2test.
+
+20. Added RunTest.bat for running the tests under Windows.
+
+21. "make distclean" was not removing config.h, a file that may be created for
+use with CMake.
+
+22. A pattern such as "((?2){0,1999}())?", which has a group containing a
+forward reference repeated a large (but limited) number of times within a
+repeated outer group that has a zero minimum quantifier, caused incorrect code
+to be compiled, leading to the error "internal error: previously-checked
+referenced subpattern not found" when an incorrect memory address was read.
+This bug was reported as "heap overflow", discovered by Kai Lu of Fortinet's
+FortiGuard Labs. (Added 24-March-2015: CVE-2015-2325 was given to this.)
+
+23. A pattern such as "((?+1)(\1))/" containing a forward reference subroutine
+call within a group that also contained a recursive back reference caused
+incorrect code to be compiled. This bug was reported as "heap overflow",
+discovered by Kai Lu of Fortinet's FortiGuard Labs. (Added 24-March-2015:
+CVE-2015-2326 was given to this.)
+
+24. Computing the size of the JIT read-only data in advance has been a source
+of various issues, and new ones are still appear unfortunately. To fix
+existing and future issues, size computation is eliminated from the code,
+and replaced by on-demand memory allocation.
+
+25. A pattern such as /(?i)[A-`]/, where characters in the other case are
+adjacent to the end of the range, and the range contained characters with more
+than one other case, caused incorrect behaviour when compiled in UTF mode. In
+that example, the range a-j was left out of the class.
+
+
+Version 10.00 05-January-2015
+-----------------------------
+
+Version 10.00 is the first release of PCRE2, a revised API for the PCRE
+library. Changes prior to 10.00 are logged in the ChangeLog file for the old
+API, up to item 20 for release 8.36.
+
+The code of the library was heavily revised as part of the new API
+implementation. Details of each and every modification were not individually
+logged. In addition to the API changes, the following changes were made. They
+are either new functionality, or bug fixes and other noticeable changes of
+behaviour that were implemented after the code had been forked.
+
+1. Including Unicode support at build time is now enabled by default, but it
+can optionally be disabled. It is not enabled by default at run time (no
+change).
+
+2. The test program, now called pcre2test, was re-specified and almost
+completely re-written. Its input is not compatible with input for pcretest.
+
+3. Patterns may start with (*NOTEMPTY) or (*NOTEMPTY_ATSTART) to set the
+PCRE2_NOTEMPTY or PCRE2_NOTEMPTY_ATSTART options for every subject line that is
+matched by that pattern.
+
+4. For the benefit of those who use PCRE2 via some other application, that is,
+not writing the function calls themselves, it is possible to check the PCRE2
+version by matching a pattern such as /(?(VERSION>=10)yes|no)/ against a
+string such as "yesno".
+
+5. There are case-equivalent Unicode characters whose encodings use different
+numbers of code units in UTF-8. U+023A and U+2C65 are one example. (It is
+theoretically possible for this to happen in UTF-16 too.) If a backreference to
+a group containing one of these characters was greedily repeated, and during
+the match a backtrack occurred, the subject might be backtracked by the wrong
+number of code units. For example, if /^(\x{23a})\1*(.)/ is matched caselessly
+(and in UTF-8 mode) against "\x{23a}\x{2c65}\x{2c65}\x{2c65}", group 2 should
+capture the final character, which is the three bytes E2, B1, and A5 in UTF-8.
+Incorrect backtracking meant that group 2 captured only the last two bytes.
+This bug has been fixed; the new code is slower, but it is used only when the
+strings matched by the repetition are not all the same length.
+
+6. A pattern such as /()a/ was not setting the "first character must be 'a'"
+information. This applied to any pattern with a group that matched no
+characters, for example: /(?:(?=.)|(?<!x))a/.
+
+7. When an (*ACCEPT) is triggered inside capturing parentheses, it arranges for
+those parentheses to be closed with whatever has been captured so far. However,
+it was failing to mark any other groups between the highest capture so far and
+the currrent group as "unset". Thus, the ovector for those groups contained
+whatever was previously there. An example is the pattern /(x)|((*ACCEPT))/ when
+matched against "abcd".
+
+8. The pcre2_substitute() function has been implemented.
+
+9. If an assertion used as a condition was quantified with a minimum of zero
+(an odd thing to do, but it happened), SIGSEGV or other misbehaviour could
+occur.
+
+10. The PCRE2_NO_DOTSTAR_ANCHOR option has been implemented.
+
+****

src/regex/pcre2/CheckMan

@@ -0,0 +1,78 @@
+#! /usr/bin/perl
+
+# A script to scan PCRE2's man pages to check for typos in the control
+# sequences. I use only a small set of the available repertoire, so it is 
+# straightforward to check that nothing else has slipped in by mistake. This
+# script should be called in the doc directory.
+
+$yield = 0;
+
+while (scalar(@ARGV) > 0)
+  {
+  $line = 0; 
+  $file = shift @ARGV;
+    
+  open (IN, $file) || die "Failed to open $file\n";
+  
+  while (<IN>)
+    {  
+    $count = 0;
+    $line++; 
+    if (/^\s*$/)
+      {
+      printf "Empty line $line of $file\n";
+      $yield = 1;  
+      }   
+    elsif (/^\./)
+      {
+      if (!/^\.\s*$|
+            ^\.B\s+\S| 
+            ^\.TH\s\S|
+            ^\.SH\s\S|
+            ^\.SS\s\S|
+            ^\.TP(?:\s?\d+)?\s*$|
+            ^\.SM\s*$|
+            ^\.br\s*$| 
+            ^\.rs\s*$| 
+            ^\.sp\s*$| 
+            ^\.nf\s*$| 
+            ^\.fi\s*$| 
+            ^\.P\s*$| 
+            ^\.PP\s*$| 
+            ^\.\\"(?:\ HREF)?\s*$|
+            ^\.\\"\sHTML\s<a\shref="[^"]+?">\s*$|
+            ^\.\\"\sHTML\s<a\sname="[^"]+?"><\/a>\s*$|
+            ^\.\\"\s<\/a>\s*$|
+            ^\.\\"\sJOINSH\s*$|
+            ^\.\\"\sJOIN\s*$/x  
+         )
+        {
+        printf "Bad control line $line of $file\n";
+        $yield = 1;
+        }
+      }
+    elsif (/\\[^ef]|\\f[^IBP]/)
+      {
+      printf "Bad backslash in line $line of $file\n";
+      $yield = 1;
+      }
+    while (/\\f[BI]/g)
+      {
+      $count++;
+      }
+    while (/\\fP/g)
+      {
+      $count--;
+      }
+    if ($count != 0)
+      {
+      printf "Mismatching formatting in line $line of $file\n";
+      $yield = 1;
+      }
+    }
+     
+  close(IN);   
+  }
+  
+exit $yield;
+# End  

src/regex/pcre2/CleanTxt

@@ -0,0 +1,113 @@
+#! /usr/bin/perl -w
+
+# Script to take the output of nroff -man and remove all the backspacing and
+# the page footers and the screen commands etc so that it is more usefully
+# readable online. In fact, in the latest nroff, intermediate footers don't
+# seem to be generated any more.
+
+$blankcount = 0;
+$lastwascut = 0;
+$firstheader = 1;
+
+# Input on STDIN; output to STDOUT.
+
+while (<STDIN>)
+  {
+  s/\x1b\[\d+m//g;   # Remove screen controls "ESC [ number m"
+  s/.\x8//g;         # Remove "char, backspace"
+
+  # Handle header lines. Retain only the first one we encounter, but remove
+  # the blank line that follows. Any others (e.g. at end of document) and the
+  # following blank line are dropped.
+
+  if (/^PCRE(\w*)\(([13])\)\s+PCRE\1\(\2\)$/)
+    {
+    if ($firstheader)
+      {
+      $firstheader = 0;
+      print;
+      $lastprinted = $_;
+      $lastwascut = 0;
+      }
+    $_=<STDIN>;       # Remove a blank that follows
+    next;
+    }
+
+  # Count runs of empty lines
+
+  if (/^\s*$/)
+    {
+    $blankcount++;
+    $lastwascut = 0;
+    next;
+    }
+
+  # If a chunk of lines has been cut out (page footer) and the next line
+  # has a different indentation, put back one blank line.
+
+  if ($lastwascut && $blankcount < 1 && defined($lastprinted))
+    {
+    ($a) = $lastprinted =~ /^(\s*)/;
+    ($b) = $_ =~ /^(\s*)/;
+    $blankcount++ if ($a ne $b);
+    }
+
+  # We get here only when we have a non-blank line in hand. If it was preceded
+  # by 3 or more blank lines, read the next 3 lines and see if they are blank.
+  # If so, remove all 7 lines, and remember that we have just done a cut.
+
+  if ($blankcount >= 3)
+    {
+    for ($i = 0; $i < 3; $i++)
+      {
+      $next[$i] = <STDIN>;
+      $next[$i] = "" if !defined $next[$i];
+      $next[$i] =~ s/\x1b\[\d+m//g;   # Remove screen controls "ESC [ number m"
+      $next[$i] =~ s/.\x8//g;         # Remove "char, backspace"
+      }
+
+    # Cut out chunks of the form <3 blanks><non-blank><3 blanks>
+
+    if ($next[0] =~ /^\s*$/ &&
+        $next[1] =~ /^\s*$/ &&
+        $next[2] =~ /^\s*$/)
+      {
+      $blankcount -= 3;
+      $lastwascut = 1;
+      }
+
+    # Otherwise output the saved blanks, the current, and the next three
+    # lines. Remember the last printed line.
+
+    else
+      {
+      for ($i = 0; $i < $blankcount; $i++) { print "\n"; }
+      print;
+      for ($i = 0; $i < 3; $i++)
+        {
+        $next[$i] =~ s/.\x8//g;
+        print $next[$i];
+        $lastprinted = $_;
+        }
+      $lastwascut = 0;
+      $blankcount = 0;
+      }
+    }
+
+  # This non-blank line is not preceded by 3 or more blank lines. Output
+  # any blanks there are, and the line. Remember it. Force two blank lines
+  # before headings.
+
+  else
+    {
+    $blankcount = 2 if /^\S/ && !/^Last updated/ && !/^Copyright/ &&
+      defined($lastprinted);
+    for ($i = 0; $i < $blankcount; $i++) { print "\n"; }
+    print;
+    $lastprinted = $_;
+    $lastwascut = 0;
+    $blankcount = 0;
+    }
+  }
+
+# End

src/regex/pcre2/Detrail

@@ -0,0 +1,35 @@
+#!/usr/bin/perl
+
+# This is a script for removing trailing whitespace from lines in files that
+# are listed on the command line.
+
+# This subroutine does the work for one file.
+
+sub detrail {
+my($file) = $_[0];
+my($changed) = 0;
+open(IN, "$file") || die "Can't open $file for input";
+@lines = <IN>;
+close(IN);
+foreach (@lines)
+  {
+  if (/\s+\n$/)
+    {
+    s/\s+\n$/\n/;
+    $changed = 1;
+    }
+  }
+if ($changed)
+  {
+  open(OUT, ">$file") || die "Can't open $file for output";
+  print OUT @lines;
+  close(OUT);
+  }
+}
+
+# This is the main program
+
+$, = "";   # Output field separator
+for ($i = 0; $i < @ARGV; $i++) { &detrail($ARGV[$i]); }
+
+# End

src/regex/pcre2/HACKING

@@ -0,0 +1,830 @@
+Technical Notes about PCRE2
+---------------------------
+
+These are very rough technical notes that record potentially useful information
+about PCRE2 internals. PCRE2 is a library based on the original PCRE library,
+but with a revised (and incompatible) API. To avoid confusion, the original
+library is referred to as PCRE1 below. For information about testing PCRE2, see
+the pcre2test documentation and the comment at the head of the RunTest file.
+
+PCRE1 releases were up to 8.3x when PCRE2 was developed, and later bug fix
+releases remain in the 8.xx series. PCRE2 releases started at 10.00 to avoid
+confusion with PCRE1.
+
+
+Historical note 1
+-----------------
+
+Many years ago I implemented some regular expression functions to an algorithm
+suggested by Martin Richards. The rather simple patterns were not Unix-like in
+form, and were quite restricted in what they could do by comparison with Perl.
+The interesting part about the algorithm was that the amount of space required
+to hold the compiled form of an expression was known in advance. The code to
+apply an expression did not operate by backtracking, as the original Henry
+Spencer code and current PCRE2 and Perl code does, but instead checked all
+possibilities simultaneously by keeping a list of current states and checking
+all of them as it advanced through the subject string. In the terminology of
+Jeffrey Friedl's book, it was a "DFA algorithm", though it was not a
+traditional Finite State Machine (FSM). When the pattern was all used up, all
+remaining states were possible matches, and the one matching the longest subset
+of the subject string was chosen. This did not necessarily maximize the
+individual wild portions of the pattern, as is expected in Unix and Perl-style
+regular expressions.
+
+
+Historical note 2
+-----------------
+
+By contrast, the code originally written by Henry Spencer (which was
+subsequently heavily modified for Perl) compiles the expression twice: once in
+a dummy mode in order to find out how much store will be needed, and then for
+real. (The Perl version probably doesn't do this any more; I'm talking about
+the original library.) The execution function operates by backtracking and
+maximizing (or, optionally, minimizing, in Perl) the amount of the subject that
+matches individual wild portions of the pattern. This is an "NFA algorithm" in
+Friedl's terminology.
+
+
+OK, here's the real stuff
+-------------------------
+
+For the set of functions that formed the original PCRE1 library in 1997 (which
+are unrelated to those mentioned above), I tried at first to invent an
+algorithm that used an amount of store bounded by a multiple of the number of
+characters in the pattern, to save on compiling time. However, because of the
+greater complexity in Perl regular expressions, I couldn't do this, even though
+the then current Perl 5.004 patterns were much simpler than those supported
+nowadays. In any case, a first pass through the pattern is helpful for other
+reasons.
+
+
+Support for 16-bit and 32-bit data strings
+-------------------------------------------
+
+The PCRE2 library can be compiled in any combination of 8-bit, 16-bit or 32-bit
+modes, creating up to three different libraries. In the description that
+follows, the word "short" is used for a 16-bit data quantity, and the phrase
+"code unit" is used for a quantity that is a byte in 8-bit mode, a short in
+16-bit mode and a 32-bit word in 32-bit mode. The names of PCRE2 functions are
+given in generic form, without the _8, _16, or _32 suffix.
+
+
+Computing the memory requirement: how it was
+--------------------------------------------
+
+Up to and including release 6.7, PCRE1 worked by running a very degenerate
+first pass to calculate a maximum memory requirement, and then a second pass to
+do the real compile - which might use a bit less than the predicted amount of
+memory. The idea was that this would turn out faster than the Henry Spencer
+code because the first pass is degenerate and the second pass can just store
+stuff straight into memory, which it knows is big enough.
+
+
+Computing the memory requirement: how it is
+-------------------------------------------
+
+By the time I was working on a potential 6.8 release, the degenerate first pass
+had become very complicated and hard to maintain. Indeed one of the early
+things I did for 6.8 was to fix Yet Another Bug in the memory computation. Then
+I had a flash of inspiration as to how I could run the real compile function in
+a "fake" mode that enables it to compute how much memory it would need, while
+in most cases only ever using a small amount of working memory, and without too
+many tests of the mode that might slow it down. So I refactored the compiling
+functions to work this way. This got rid of about 600 lines of source and made
+further maintenance and development easier. As this was such a major change, I
+never released 6.8, instead upping the number to 7.0 (other quite major changes
+were also present in the 7.0 release).
+
+A side effect of this work was that the previous limit of 200 on the nesting
+depth of parentheses was removed. However, there was a downside: compiling ran
+more slowly than before (30% or more, depending on the pattern) because it now
+did a full analysis of the pattern. My hope was that this would not be a big
+issue, and in the event, nobody has commented on it.
+
+At release 8.34, a limit on the nesting depth of parentheses was re-introduced
+(default 250, settable at build time) so as to put a limit on the amount of
+system stack used by the compile function, which uses recursive function calls
+for nested parenthesized groups. This is a safety feature for environments with
+small stacks where the patterns are provided by users.
+
+
+Yet another pattern scan
+------------------------
+
+History repeated itself for PCRE2 release 10.20. A number of bugs relating to
+named subpatterns had been discovered by fuzzers. Most of these were related to
+the handling of forward references when it was not known if the named group was
+unique. (References to non-unique names use a different opcode and more
+memory.) The use of duplicate group numbers (the (?| facility) also caused
+issues.
+
+To get around these problems I adopted a new approach by adding a third pass
+over the pattern (really a "pre-pass"), which did nothing other than identify
+all the named subpatterns and their corresponding group numbers. This means
+that the actual compile (both the memory-computing dummy run and the real
+compile) has full knowledge of group names and numbers throughout. Several
+dozen lines of messy code were eliminated, though the new pre-pass was not
+short. In particular, parsing and skipping over [] classes is complicated.
+
+While working on 10.22 I realized that I could simplify yet again by moving
+more of the parsing into the pre-pass, thus avoiding doing it in two places, so
+after 10.22 was released, the code underwent yet another big refactoring. This
+is how it is from 10.23 onwards:
+
+The function called parse_regex() scans the pattern characters, parsing them
+into literal data and meta characters. It converts escapes such as \x{123}
+into literals, handles \Q...\E, and skips over comments and non-significant
+white space. The result of the scanning is put into a vector of 32-bit unsigned
+integers. Values less than 0x80000000 are literal data. Higher values represent
+meta-characters. The top 16-bits of such values identify the meta-character,
+and these are given names such as META_CAPTURE. The lower 16-bits are available
+for data, for example, the capturing group number. The only situation in which
+literal data values greater than 0x7fffffff can appear is when the 32-bit
+library is running in non-UTF mode. This is handled by having a special
+meta-character that is followed by the 32-bit data value.
+
+The size of the parsed pattern vector, when auto-callouts are not enabled, is
+bounded by the length of the pattern (with one exception). The code is written
+so that each item in the pattern uses no more vector elements than the number
+of code units in the item itself. The exception is the aforementioned large
+32-bit number handling. For this reason, 32-bit non-UTF patterns are scanned in
+advance to check for such values. When auto-callouts are enabled, the generous
+assumption is made that there will be a callout for each pattern code unit
+(which of course is only actually true if all code units are literals) plus one
+at the end. There is a default parsed pattern vector on the system stack, but
+if this is not big enough, heap memory is used.
+
+As before, the actual compiling function is run twice, the first time to
+determine the amount of memory needed for the final compiled pattern. It
+now processes the parsed pattern vector, not the pattern itself, although some
+of the parsed items refer to strings in the pattern - for example, group
+names. As escapes and comments have already been processed, the code is a bit
+simpler than before.
+
+Most errors can be diagnosed during the parsing scan. For those that cannot
+(for example, "lookbehind assertion is not fixed length"), the parsed code
+contains offsets into the pattern so that the actual compiling code can
+report where errors are.
+
+
+The elements of the parsed pattern vector
+-----------------------------------------
+
+The word "offset" below means a code unit offset into the pattern. When
+PCRE2_SIZE (which is usually size_t) is no bigger than uint32_t, an offset is
+stored in a single parsed pattern element. Otherwise (typically on 64-bit
+systems) it occupies two elements. The following meta items occupy just one
+element, with no data:
+
+META_ACCEPT           (*ACCEPT)
+META_ASTERISK         *
+META_ASTERISK_PLUS    *+
+META_ASTERISK_QUERY   *?
+META_ATOMIC           (?> start of atomic group
+META_CIRCUMFLEX       ^ metacharacter
+META_CLASS            [ start of non-empty class
+META_CLASS_EMPTY      [] empty class - only with PCRE2_ALLOW_EMPTY_CLASS
+META_CLASS_EMPTY_NOT  [^] negative empty class - ditto
+META_CLASS_END        ] end of non-empty class
+META_CLASS_NOT        [^ start non-empty negative class
+META_COMMIT           (*COMMIT)
+META_COND_ASSERT      (?(?assertion)
+META_DOLLAR           $ metacharacter
+META_DOT              . metacharacter
+META_END              End of pattern (this value is 0x80000000)
+META_FAIL             (*FAIL)
+META_KET              ) closing parenthesis
+META_LOOKAHEAD        (?= start of lookahead
+META_LOOKAHEAD_NA     (*napla: start of non-atomic lookahead
+META_LOOKAHEADNOT     (?! start of negative lookahead
+META_NOCAPTURE        (?: no capture parens
+META_PLUS             +
+META_PLUS_PLUS        ++
+META_PLUS_QUERY       +?
+META_PRUNE            (*PRUNE) - no argument
+META_QUERY            ?
+META_QUERY_PLUS       ?+
+META_QUERY_QUERY      ??
+META_RANGE_ESCAPED    hyphen in class range with at least one escape
+META_RANGE_LITERAL    hyphen in class range defined literally
+META_SKIP             (*SKIP) - no argument
+META_THEN             (*THEN) - no argument
+
+The two RANGE values occur only in character classes. They are positioned
+between two literals that define the start and end of the range. In an EBCDIC
+evironment it is necessary to know whether either of the range values was
+specified as an escape. In an ASCII/Unicode environment the distinction is not
+relevant.
+
+The following have data in the lower 16 bits, and may be followed by other data
+elements:
+
+META_ALT              | alternation
+META_BACKREF          back reference
+META_CAPTURE          start of capturing group
+META_ESCAPE           non-literal escape sequence
+META_RECURSE          recursion call
+
+If the data for META_ALT is non-zero, it is inside a lookbehind, and the data
+is the length of its branch, for which OP_REVERSE must be generated.
+
+META_BACKREF, META_CAPTURE, and META_RECURSE have the capture group number as
+their data in the lower 16 bits of the element.
+
+META_BACKREF is followed by an offset if the back reference group number is 10
+or more. The offsets of the first ocurrences of references to groups whose
+numbers are less than 10 are put in cb->small_ref_offset[] (only the first
+occurrence is useful). On 64-bit systems this avoids using more than two parsed
+pattern elements for items such as \3. The offset is used when an error occurs
+because the reference is to a non-existent group.
+
+META_RECURSE is always followed by an offset, for use in error messages.
+
+META_ESCAPE has an ESC_xxx value as its data. For ESC_P and ESC_p, the next
+element contains the 16-bit type and data property values, packed together.
+ESC_g and ESC_k are used only for named references - numerical ones are turned
+into META_RECURSE or META_BACKREF as appropriate. ESC_g and ESC_k are followed
+by a length and an offset into the pattern to specify the name.
+
+The following have one data item that follows in the next vector element:
+
+META_BIGVALUE         Next is a literal >= META_END
+META_OPTIONS          (?i) and friends (data is new option bits)
+META_POSIX            POSIX class item (data identifies the class)
+META_POSIX_NEG        negative POSIX class item (ditto)
+
+The following are followed by a length element, then a number of character code
+values (which should match with the length):
+
+META_MARK             (*MARK:xxxx)
+META_COMMIT_ARG       )*COMMIT:xxxx)
+META_PRUNE_ARG        (*PRUNE:xxx)
+META_SKIP_ARG         (*SKIP:xxxx)
+META_THEN_ARG         (*THEN:xxxx)
+
+The following are followed by a length element, then an offset in the pattern
+that identifies the name:
+
+META_COND_NAME        (?(<name>) or (?('name') or (?(name)
+META_COND_RNAME       (?(R&name)
+META_COND_RNUMBER     (?(Rdigits)
+META_RECURSE_BYNAME   (?&name)
+META_BACKREF_BYNAME   \k'name'
+
+META_COND_RNUMBER is used for names that start with R and continue with digits,
+because this is an ambiguous case. It could be a back reference to a group with
+that name, or it could be a recursion test on a numbered group.
+
+This one is followed by an offset, for use in error messages, then a number:
+
+META_COND_NUMBER       (?([+-]digits)
+
+The following is followed just by an offset, for use in error messages:
+
+META_COND_DEFINE      (?(DEFINE)
+
+The following are also followed just by an offset, but also the lower 16 bits
+of the main word contain the length of the first branch of the lookbehind
+group; this is used when generating OP_REVERSE for that branch.
+
+META_LOOKBEHIND       (?<=      start of lookbehind
+META_LOOKBEHIND_NA    (*naplb:  start of non-atomic lookbehind
+META_LOOKBEHINDNOT    (?<!      start of negative lookbehind
+
+The following are followed by two elements, the minimum and maximum. Repeat
+values are limited to 65535 (MAX_REPEAT). A maximum value of "unlimited" is
+represented by UNLIMITED_REPEAT, which is bigger than MAX_REPEAT:
+
+META_MINMAX           {n,m}  repeat
+META_MINMAX_PLUS      {n,m}+ repeat
+META_MINMAX_QUERY     {n,m}? repeat
+
+This one is followed by three elements. The first is 0 for '>' and 1 for '>=';
+the next two are the major and minor numbers:
+
+META_COND_VERSION     (?(VERSION<op>x.y)
+
+Callouts are converted into one of two items:
+
+META_CALLOUT_NUMBER   (?C with numerical argument
+META_CALLOUT_STRING   (?C with string argument
+
+In both cases, the next two elements contain the offset and length of the next
+item in the pattern. Then there is either one callout number, or a length and
+an offset for the string argument. The length includes both delimiters.
+
+
+Traditional matching function
+-----------------------------
+
+The "traditional", and original, matching function is called pcre2_match(), and
+it implements an NFA algorithm, similar to the original Henry Spencer algorithm
+and the way that Perl works. This is not surprising, since it is intended to be
+as compatible with Perl as possible. This is the function most users of PCRE2
+will use most of the time. If PCRE2 is compiled with just-in-time (JIT)
+support, and studying a compiled pattern with JIT is successful, the JIT code
+is run instead of the normal pcre2_match() code, but the result is the same.
+
+
+Supplementary matching function
+-------------------------------
+
+There is also a supplementary matching function called pcre2_dfa_match(). This
+implements a DFA matching algorithm that searches simultaneously for all
+possible matches that start at one point in the subject string. (Going back to
+my roots: see Historical Note 1 above.) This function intreprets the same
+compiled pattern data as pcre2_match(); however, not all the facilities are
+available, and those that are do not always work in quite the same way. See the
+user documentation for details.
+
+The algorithm that is used for pcre2_dfa_match() is not a traditional FSM,
+because it may have a number of states active at one time. More work would be
+needed at compile time to produce a traditional FSM where only one state is
+ever active at once. I believe some other regex matchers work this way. JIT
+support is not available for this kind of matching.
+
+
+Changeable options
+------------------
+
+The /i, /m, or /s options (PCRE2_CASELESS, PCRE2_MULTILINE, PCRE2_DOTALL, and
+others) may be changed in the middle of patterns by items such as (?i). Their
+processing is handled entirely at compile time by generating different opcodes
+for the different settings. The runtime functions do not need to keep track of
+an option's state.
+
+PCRE2_DUPNAMES, PCRE2_EXTENDED, PCRE2_EXTENDED_MORE, and PCRE2_NO_AUTO_CAPTURE
+are tracked and processed during the parsing pre-pass. The others are handled
+from META_OPTIONS items during the main compile phase.
+
+
+Format of compiled patterns
+---------------------------
+
+The compiled form of a pattern is a vector of unsigned code units (bytes in
+8-bit mode, shorts in 16-bit mode, 32-bit words in 32-bit mode), containing
+items of variable length. The first code unit in an item contains an opcode,
+and the length of the item is either implicit in the opcode or contained in the
+data that follows it.
+
+In many cases listed below, LINK_SIZE data values are specified for offsets
+within the compiled pattern. LINK_SIZE always specifies a number of bytes. The
+default value for LINK_SIZE is 2, except for the 32-bit library, where it can
+only be 4. The 8-bit library can be compiled to used 3-byte or 4-byte values,
+and the 16-bit library can be compiled to use 4-byte values, though this
+impairs performance. Specifing a LINK_SIZE larger than 2 for these libraries is
+necessary only when patterns whose compiled length is greater than 65535 code
+units are going to be processed. When a LINK_SIZE value uses more than one code
+unit, the most significant unit is first.
+
+In this description, we assume the "normal" compilation options. Data values
+that are counts (e.g. quantifiers) are always two bytes long in 8-bit mode
+(most significant byte first), and one code unit in 16-bit and 32-bit modes.
+
+
+Opcodes with no following data
+------------------------------
+
+These items are all just one unit long:
+
+  OP_END                 end of pattern
+  OP_ANY                 match any one character other than newline
+  OP_ALLANY              match any one character, including newline
+  OP_ANYBYTE             match any single code unit, even in UTF-8/16 mode
+  OP_SOD                 match start of data: \A
+  OP_SOM,                start of match (subject + offset): \G
+  OP_SET_SOM,            set start of match (\K)
+  OP_CIRC                ^ (start of data)
+  OP_CIRCM               ^ multiline mode (start of data or after newline)
+  OP_NOT_WORD_BOUNDARY   \W
+  OP_WORD_BOUNDARY       \w
+  OP_NOT_DIGIT           \D
+  OP_DIGIT               \d
+  OP_NOT_HSPACE          \H
+  OP_HSPACE              \h
+  OP_NOT_WHITESPACE      \S
+  OP_WHITESPACE          \s
+  OP_NOT_VSPACE          \V
+  OP_VSPACE              \v
+  OP_NOT_WORDCHAR        \W
+  OP_WORDCHAR            \w
+  OP_EODN                match end of data or newline at end: \Z
+  OP_EOD                 match end of data: \z
+  OP_DOLL                $ (end of data, or before final newline)
+  OP_DOLLM               $ multiline mode (end of data or before newline)
+  OP_EXTUNI              match an extended Unicode grapheme cluster
+  OP_ANYNL               match any Unicode newline sequence
+
+  OP_ASSERT_ACCEPT       )
+  OP_ACCEPT              ) These are Perl 5.10's "backtracking control
+  OP_COMMIT              ) verbs". If OP_ACCEPT is inside capturing
+  OP_FAIL                ) parentheses, it may be preceded by one or more
+  OP_PRUNE               ) OP_CLOSE, each followed by a number that
+  OP_SKIP                ) indicates which parentheses must be closed.
+  OP_THEN                )
+
+OP_ASSERT_ACCEPT is used when (*ACCEPT) is encountered within an assertion.
+This ends the assertion, not the entire pattern match. The assertion (?!) is
+always optimized to OP_FAIL.
+
+OP_ALLANY is used for '.' when PCRE2_DOTALL is set. It is also used for \C in
+non-UTF modes and in UTF-32 mode (since one code unit still equals one
+character). Another use is for [^] when empty classes are permitted
+(PCRE2_ALLOW_EMPTY_CLASS is set).
+
+
+Backtracking control verbs
+--------------------------
+
+Verbs with no arguments generate opcodes with no following data (as listed
+in the section above). 
+
+(*MARK:NAME) generates OP_MARK followed by the mark name, preceded by a
+length in one code unit, and followed by a binary zero. The name length is
+limited by the size of the code unit.
+
+(*ACCEPT:NAME) and (*FAIL:NAME) are compiled as (*MARK:NAME)(*ACCEPT) and
+(*MARK:NAME)(*FAIL) respectively.
+
+For (*COMMIT:NAME), (*PRUNE:NAME), (*SKIP:NAME), and (*THEN:NAME), the opcodes
+OP_COMMIT_ARG, OP_PRUNE_ARG, OP_SKIP_ARG, and OP_THEN_ARG are used, with the
+name following in the same format as for OP_MARK.
+
+
+Matching literal characters
+---------------------------
+
+The OP_CHAR opcode is followed by a single character that is to be matched
+casefully. For caseless matching of characters that have at most two
+case-equivalent code points, OP_CHARI is used. In UTF-8 or UTF-16 modes, the
+character may be more than one code unit long. In UTF-32 mode, characters are
+always exactly one code unit long.
+
+If there is only one character in a character class, OP_CHAR or OP_CHARI is
+used for a positive class, and OP_NOT or OP_NOTI for a negative one (that is,
+for something like [^a]).
+
+Caseless matching (positive or negative) of characters that have more than two
+case-equivalent code points (which is possible only in UTF mode) is handled by
+compiling a Unicode property item (see below), with the pseudo-property
+PT_CLIST. The value of this property is an offset in a vector called
+"ucd_caseless_sets" which identifies the start of a short list of equivalent
+characters, terminated by the value NOTACHAR (0xffffffff).
+
+
+Repeating single characters
+---------------------------
+
+The common repeats (*, +, ?), when applied to a single character, use the
+following opcodes, which come in caseful and caseless versions:
+
+  Caseful         Caseless
+  OP_STAR         OP_STARI
+  OP_MINSTAR      OP_MINSTARI
+  OP_POSSTAR      OP_POSSTARI
+  OP_PLUS         OP_PLUSI
+  OP_MINPLUS      OP_MINPLUSI
+  OP_POSPLUS      OP_POSPLUSI
+  OP_QUERY        OP_QUERYI
+  OP_MINQUERY     OP_MINQUERYI
+  OP_POSQUERY     OP_POSQUERYI
+
+Each opcode is followed by the character that is to be repeated. In ASCII or
+UTF-32 modes, these are two-code-unit items; in UTF-8 or UTF-16 modes, the
+length is variable. Those with "MIN" in their names are the minimizing
+versions. Those with "POS" in their names are possessive versions. Other kinds
+of repeat make use of these opcodes:
+
+  Caseful         Caseless
+  OP_UPTO         OP_UPTOI
+  OP_MINUPTO      OP_MINUPTOI
+  OP_POSUPTO      OP_POSUPTOI
+  OP_EXACT        OP_EXACTI
+
+Each of these is followed by a count and then the repeated character. The count
+is two bytes long in 8-bit mode (most significant byte first), or one code unit
+in 16-bit and 32-bit modes.
+
+OP_UPTO matches from 0 to the given number. A repeat with a non-zero minimum
+and a fixed maximum is coded as an OP_EXACT followed by an OP_UPTO (or
+OP_MINUPTO or OPT_POSUPTO).
+
+Another set of matching repeating opcodes (called OP_NOTSTAR, OP_NOTSTARI,
+etc.) are used for repeated, negated, single-character classes such as [^a]*.
+The normal single-character opcodes (OP_STAR, etc.) are used for repeated
+positive single-character classes.
+
+
+Repeating character types
+-------------------------
+
+Repeats of things like \d are done exactly as for single characters, except
+that instead of a character, the opcode for the type (e.g. OP_DIGIT) is stored
+in the next code unit. The opcodes are:
+
+  OP_TYPESTAR
+  OP_TYPEMINSTAR
+  OP_TYPEPOSSTAR
+  OP_TYPEPLUS
+  OP_TYPEMINPLUS
+  OP_TYPEPOSPLUS
+  OP_TYPEQUERY
+  OP_TYPEMINQUERY
+  OP_TYPEPOSQUERY
+  OP_TYPEUPTO
+  OP_TYPEMINUPTO
+  OP_TYPEPOSUPTO
+  OP_TYPEEXACT
+
+
+Match by Unicode property
+-------------------------
+
+OP_PROP and OP_NOTPROP are used for positive and negative matches of a
+character by testing its Unicode property (the \p and \P escape sequences).
+Each is followed by two code units that encode the desired property as a type
+and a value. The types are a set of #defines of the form PT_xxx, and the values
+are enumerations of the form ucp_xx, defined in the pcre2_ucp.h source file.
+The value is relevant only for PT_GC (General Category), PT_PC (Particular
+Category), PT_SC (Script), and the pseudo-property PT_CLIST, which is used to
+identify a list of case-equivalent characters when there are three or more.
+
+Repeats of these items use the OP_TYPESTAR etc. set of opcodes, followed by
+three code units: OP_PROP or OP_NOTPROP, and then the desired property type and
+value.
+
+
+Character classes
+-----------------
+
+If there is only one character in a class, OP_CHAR or OP_CHARI is used for a
+positive class, and OP_NOT or OP_NOTI for a negative one (that is, for
+something like [^a]), except when caselessly matching a character that has more
+than two case-equivalent code points (which can happen only in UTF mode). In
+this case a Unicode property item is used, as described above in "Matching
+literal characters".
+
+A set of repeating opcodes (called OP_NOTSTAR etc.) are used for repeated,
+negated, single-character classes. The normal single-character opcodes
+(OP_STAR, etc.) are used for repeated positive single-character classes.
+
+When there is more than one character in a class, and all the code points are
+less than 256, OP_CLASS is used for a positive class, and OP_NCLASS for a
+negative one. In either case, the opcode is followed by a 32-byte (16-short,
+8-word) bit map containing a 1 bit for every character that is acceptable. The
+bits are counted from the least significant end of each unit. In caseless mode,
+bits for both cases are set.
+
+The reason for having both OP_CLASS and OP_NCLASS is so that, in UTF-8 and
+16-bit and 32-bit modes, subject characters with values greater than 255 can be
+handled correctly. For OP_CLASS they do not match, whereas for OP_NCLASS they
+do.
+
+For classes containing characters with values greater than 255 or that contain
+\p or \P, OP_XCLASS is used. It optionally uses a bit map if any acceptable
+code points are less than 256, followed by a list of pairs (for a range) and/or
+single characters and/or properties. In caseless mode, all equivalent
+characters are explicitly listed.
+
+OP_XCLASS is followed by a LINK_SIZE value containing the total length of the
+opcode and its data. This is followed by a code unit containing flag bits:
+XCL_NOT indicates that this is a negative class, and XCL_MAP indicates that a
+bit map is present. There follows the bit map, if XCL_MAP is set, and then a
+sequence of items coded as follows:
+
+  XCL_END      marks the end of the list
+  XCL_SINGLE   one character follows
+  XCL_RANGE    two characters follow
+  XCL_PROP     a Unicode property (type, value) follows
+  XCL_NOTPROP  a Unicode property (type, value) follows
+
+If a range starts with a code point less than 256 and ends with one greater
+than 255, it is split into two ranges, with characters less than 256 being
+indicated in the bit map, and the rest with XCL_RANGE.
+
+When XCL_NOT is set, the bit map, if present, contains bits for characters that
+are allowed (exactly as for OP_NCLASS), but the list of items that follow it
+specifies characters and properties that are not allowed.
+
+
+Back references
+---------------
+
+OP_REF (caseful) or OP_REFI (caseless) is followed by a count containing the
+reference number when the reference is to a unique capturing group (either by
+number or by name). When named groups are used, there may be more than one
+group with the same name. In this case, a reference to such a group by name
+generates OP_DNREF or OP_DNREFI. These are followed by two counts: the index
+(not the byte offset) in the group name table of the first entry for the
+required name, followed by the number of groups with the same name. The
+matching code can then search for the first one that is set.
+
+
+Repeating character classes and back references
+-----------------------------------------------
+
+Single-character classes are handled specially (see above). This section
+applies to other classes and also to back references. In both cases, the repeat
+information follows the base item. The matching code looks at the following
+opcode to see if it is one of these:
+
+  OP_CRSTAR
+  OP_CRMINSTAR
+  OP_CRPOSSTAR
+  OP_CRPLUS
+  OP_CRMINPLUS
+  OP_CRPOSPLUS
+  OP_CRQUERY
+  OP_CRMINQUERY
+  OP_CRPOSQUERY
+  OP_CRRANGE
+  OP_CRMINRANGE
+  OP_CRPOSRANGE
+
+All but the last three are single-code-unit items, with no data. The range
+opcodes are followed by the minimum and maximum repeat counts.
+
+
+Brackets and alternation
+------------------------
+
+A pair of non-capturing round brackets is wrapped round each expression at
+compile time, so alternation always happens in the context of brackets.
+
+[Note for North Americans: "bracket" to some English speakers, including
+myself, can be round, square, curly, or pointy. Hence this usage rather than
+"parentheses".]
+
+Non-capturing brackets use the opcode OP_BRA, capturing brackets use OP_CBRA. A
+bracket opcode is followed by a LINK_SIZE value which gives the offset to the
+next alternative OP_ALT or, if there aren't any branches, to the terminating
+opcode. Each OP_ALT is followed by a LINK_SIZE value giving the offset to the
+next one, or to the final opcode. For capturing brackets, the bracket number is
+a count that immediately follows the offset.
+
+There are several opcodes that mark the end of a subpattern group. OP_KET is
+used for subpatterns that do not repeat indefinitely, OP_KETRMIN and
+OP_KETRMAX are used for indefinite repetitions, minimally or maximally
+respectively, and OP_KETRPOS for possessive repetitions (see below for more 
+details). All four are followed by a LINK_SIZE value giving (as a positive
+number) the offset back to the matching bracket opcode.
+
+If a subpattern is quantified such that it is permitted to match zero times, it
+is preceded by one of OP_BRAZERO, OP_BRAMINZERO, or OP_SKIPZERO. These are
+single-unit opcodes that tell the matcher that skipping the following
+subpattern entirely is a valid match. In the case of the first two, not
+skipping the pattern is also valid (greedy and non-greedy). The third is used
+when a pattern has the quantifier {0,0}. It cannot be entirely discarded,
+because it may be called as a subroutine from elsewhere in the pattern.
+
+A subpattern with an indefinite maximum repetition is replicated in the
+compiled data its minimum number of times (or once with OP_BRAZERO if the
+minimum is zero), with the final copy terminating with OP_KETRMIN or OP_KETRMAX
+as appropriate.
+
+A subpattern with a bounded maximum repetition is replicated in a nested
+fashion up to the maximum number of times, with OP_BRAZERO or OP_BRAMINZERO
+before each replication after the minimum, so that, for example, (abc){2,5} is
+compiled as (abc)(abc)((abc)((abc)(abc)?)?)?, except that each bracketed group
+has the same number.
+
+When a repeated subpattern has an unbounded upper limit, it is checked to see
+whether it could match an empty string. If this is the case, the opcode in the
+final replication is changed to OP_SBRA or OP_SCBRA. This tells the matcher
+that it needs to check for matching an empty string when it hits OP_KETRMIN or
+OP_KETRMAX, and if so, to break the loop.
+
+
+Possessive brackets
+-------------------
+
+When a repeated group (capturing or non-capturing) is marked as possessive by
+the "+" notation, e.g. (abc)++, different opcodes are used. Their names all
+have POS on the end, e.g. OP_BRAPOS instead of OP_BRA and OP_SCBRAPOS instead
+of OP_SCBRA. The end of such a group is marked by OP_KETRPOS. If the minimum
+repetition is zero, the group is preceded by OP_BRAPOSZERO.
+
+
+Once-only (atomic) groups
+-------------------------
+
+These are just like other subpatterns, but they start with the opcode OP_ONCE.
+The check for matching an empty string in an unbounded repeat is handled
+entirely at runtime, so there is just this one opcode for atomic groups.
+
+
+Assertions
+----------
+
+Forward assertions are also just like other subpatterns, but starting with one
+of the opcodes OP_ASSERT, OP_ASSERT_NA (non-atomic assertion), or
+OP_ASSERT_NOT. Backward assertions use the opcodes OP_ASSERTBACK, 
+OP_ASSERTBACK_NA, and OP_ASSERTBACK_NOT, and the first opcode inside the
+assertion is OP_REVERSE, followed by a count of the number of characters to
+move back the pointer in the subject string. In ASCII or UTF-32 mode, the count
+is also the number of code units, but in UTF-8/16 mode each character may
+occupy more than one code unit. A separate count is present in each alternative
+of a lookbehind assertion, allowing each branch to have a different (but fixed)
+length.
+
+
+Conditional subpatterns
+-----------------------
+
+These are like other subpatterns, but they start with the opcode OP_COND, or
+OP_SCOND for one that might match an empty string in an unbounded repeat.
+
+If the condition is a back reference, this is stored at the start of the
+subpattern using the opcode OP_CREF followed by a count containing the
+reference number, provided that the reference is to a unique capturing group.
+If the reference was by name and there is more than one group with that name,
+OP_DNCREF is used instead. It is followed by two counts: the index in the group
+names table, and the number of groups with the same name. The allows the
+matcher to check if any group with the given name is set.
+
+If the condition is "in recursion" (coded as "(?(R)"), or "in recursion of
+group x" (coded as "(?(Rx)"), the group number is stored at the start of the
+subpattern using the opcode OP_RREF (with a value of RREF_ANY (0xffff) for "the
+whole pattern") or OP_DNRREF (with data as for OP_DNCREF).
+
+For a DEFINE condition, OP_FALSE is used (with no associated data). During
+compilation, however, a DEFINE condition is coded as OP_DEFINE so that, when
+the conditional group is complete, there can be a check to ensure that it
+contains only one top-level branch. Once this has happened, the opcode is
+changed to OP_FALSE, so the matcher never sees OP_DEFINE.
+
+There is a special PCRE2-specific condition of the form (VERSION[>]=x.y), which
+tests the PCRE2 version number. This compiles into one of the opcodes OP_TRUE
+or OP_FALSE.
+
+If a condition is not a back reference, recursion test, DEFINE, or VERSION, it
+must start with a parenthesized atomic assertion, whose opcode normally
+immediately follows OP_COND or OP_SCOND. However, if automatic callouts are
+enabled, a callout is inserted immediately before the assertion. It is also
+possible to insert a manual callout at this point. Only assertion conditions
+may have callouts preceding the condition.
+
+A condition that is the negative assertion (?!) is optimized to OP_FAIL in all
+parts of the pattern, so this is another opcode that may appear as a condition.
+It is treated the same as OP_FALSE.
+
+
+Recursion
+---------
+
+Recursion either matches the current pattern, or some subexpression. The opcode
+OP_RECURSE is followed by a LINK_SIZE value that is the offset to the starting
+bracket from the start of the whole pattern. OP_RECURSE is also used for
+"subroutine" calls, even though they are not strictly a recursion. Up till
+release 10.30 recursions were treated as atomic groups, making them
+incompatible with Perl (but PCRE had them well before Perl did). From 10.30,
+backtracking into recursions is supported.
+
+Repeated recursions used to be wrapped inside OP_ONCE brackets, which not only
+forced no backtracking, but also allowed repetition to be handled as for other
+bracketed groups. From 10.30 onwards, repeated recursions are duplicated for
+their minimum repetitions, and then wrapped in non-capturing brackets for the
+remainder. For example, (?1){3} is treated as (?1)(?1)(?1), and (?1){2,4} is
+treated as (?1)(?1)(?:(?1)){0,2}.
+
+
+Callouts
+--------
+
+A callout may have either a numerical argument or a string argument. These use
+OP_CALLOUT or OP_CALLOUT_STR, respectively. In each case these are followed by
+two LINK_SIZE values giving the offset in the pattern string to the start of
+the following item, and another count giving the length of this item. These
+values make it possible for pcre2test to output useful tracing information
+using callouts.
+
+In the case of a numeric callout, after these two values there is a single code
+unit containing the callout number, in the range 0-255, with 255 being used for
+callouts that are automatically inserted as a result of the PCRE2_AUTO_CALLOUT
+option. Thus, this opcode item is of fixed length:
+
+  [OP_CALLOUT] [PATTERN_OFFSET] [PATTERN_LENGTH] [NUMBER]
+
+For callouts with string arguments, OP_CALLOUT_STR has three more data items:
+a LINK_SIZE value giving the complete length of the entire opcode item, a
+LINK_SIZE item containing the offset within the pattern string to the start of
+the string argument, and the string itself, preceded by its starting delimiter
+and followed by a binary zero. When a callout function is called, a pointer to
+the actual string is passed, but the delimiter can be accessed as string[-1] if
+the application needs it. In the 8-bit library, the callout in /X(?C'abc')Y/ is
+compiled as the following bytes (decimal numbers represent binary values):
+
+  [OP_CALLOUT_STR]  [0] [10]  [0] [1]  [0] [14]  [0] [5] ['] [a] [b] [c] [0]
+                    --------  -------  --------  -------
+                       |         |        |         |
+                       ------- LINK_SIZE items ------
+
+Opcode table checking
+---------------------
+
+The last opcode that is defined in pcre2_internal.h is OP_TABLE_LENGTH. This is
+not a real opcode, but is used to check at compile time that tables indexed by
+opcode are the correct length, in order to catch updating errors.
+
+Philip Hazel
+12 July 2019

src/regex/pcre2/LICENCE

@@ -0,0 +1,94 @@
+PCRE2 LICENCE
+-------------
+
+PCRE2 is a library of functions to support regular expressions whose syntax
+and semantics are as close as possible to those of the Perl 5 language.
+
+Releases 10.00 and above of PCRE2 are distributed under the terms of the "BSD"
+licence, as specified below, with one exemption for certain binary
+redistributions. The documentation for PCRE2, supplied in the "doc" directory,
+is distributed under the same terms as the software itself. The data in the
+testdata directory is not copyrighted and is in the public domain.
+
+The basic library functions are written in C and are freestanding. Also
+included in the distribution is a just-in-time compiler that can be used to
+optimize pattern matching. This is an optional feature that can be omitted when
+the library is built.
+
+
+THE BASIC LIBRARY FUNCTIONS
+---------------------------
+
+Written by:       Philip Hazel
+Email local part: Philip.Hazel
+Email domain:     gmail.com
+
+University of Cambridge Computing Service,
+Cambridge, England.
+
+Copyright (c) 1997-2021 University of Cambridge
+All rights reserved.
+
+
+PCRE2 JUST-IN-TIME COMPILATION SUPPORT
+--------------------------------------
+
+Written by:       Zoltan Herczeg
+Email local part: hzmester
+Email domain:     freemail.hu
+
+Copyright(c) 2010-2021 Zoltan Herczeg
+All rights reserved.
+
+
+STACK-LESS JUST-IN-TIME COMPILER
+--------------------------------
+
+Written by:       Zoltan Herczeg
+Email local part: hzmester
+Email domain:     freemail.hu
+
+Copyright(c) 2009-2021 Zoltan Herczeg
+All rights reserved.
+
+
+THE "BSD" LICENCE
+-----------------
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+    * Redistributions of source code must retain the above copyright notices,
+      this list of conditions and the following disclaimer.
+
+    * Redistributions in binary form must reproduce the above copyright
+      notices, this list of conditions and the following disclaimer in the
+      documentation and/or other materials provided with the distribution.
+
+    * Neither the name of the University of Cambridge nor the names of any
+      contributors may be used to endorse or promote products derived from this
+      software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE.
+
+
+EXEMPTION FOR BINARY LIBRARY-LIKE PACKAGES
+------------------------------------------
+
+The second condition in the BSD licence (covering binary redistributions) does
+not apply all the way down a chain of software. If binary package A includes
+PCRE2, it must respect the condition, but if package B is software that
+includes package A, the condition is not imposed on package B unless it uses
+PCRE2 independently.
+
+End

src/regex/pcre2/Makefile.am

@@ -0,0 +1,868 @@
+## Process this file with automake to produce Makefile.in.
+
+AUTOMAKE_OPTIONS = subdir-objects
+ACLOCAL_AMFLAGS = -I m4
+
+## This seems to have become necessary for building in non-source directory.
+
+AM_CPPFLAGS="-I$(srcdir)/src"
+
+## Specify the documentation files that are distributed.
+
+dist_doc_DATA = \
+  AUTHORS \
+  COPYING \
+  ChangeLog \
+  LICENCE \
+  NEWS \
+  README \
+  doc/pcre2.txt \
+  doc/pcre2-config.txt \
+  doc/pcre2grep.txt \
+  doc/pcre2test.txt
+
+dist_html_DATA = \
+  doc/html/NON-AUTOTOOLS-BUILD.txt \
+  doc/html/README.txt \
+  doc/html/index.html \
+  doc/html/pcre2-config.html \
+  doc/html/pcre2.html \
+  doc/html/pcre2_callout_enumerate.html \
+  doc/html/pcre2_code_copy.html \
+  doc/html/pcre2_code_copy_with_tables.html \
+  doc/html/pcre2_code_free.html \
+  doc/html/pcre2_compile.html \
+  doc/html/pcre2_compile_context_copy.html \
+  doc/html/pcre2_compile_context_create.html \
+  doc/html/pcre2_compile_context_free.html \
+  doc/html/pcre2_config.html \
+  doc/html/pcre2_convert_context_copy.html \
+  doc/html/pcre2_convert_context_create.html \
+  doc/html/pcre2_convert_context_free.html \
+  doc/html/pcre2_converted_pattern_free.html \
+  doc/html/pcre2_dfa_match.html \
+  doc/html/pcre2_general_context_copy.html \
+  doc/html/pcre2_general_context_create.html \
+  doc/html/pcre2_general_context_free.html \
+  doc/html/pcre2_get_error_message.html \
+  doc/html/pcre2_get_mark.html \
+  doc/html/pcre2_get_match_data_size.html \
+  doc/html/pcre2_get_ovector_count.html \
+  doc/html/pcre2_get_ovector_pointer.html \
+  doc/html/pcre2_get_startchar.html \
+  doc/html/pcre2_jit_compile.html \
+  doc/html/pcre2_jit_free_unused_memory.html \
+  doc/html/pcre2_jit_match.html \
+  doc/html/pcre2_jit_stack_assign.html \
+  doc/html/pcre2_jit_stack_create.html \
+  doc/html/pcre2_jit_stack_free.html \
+  doc/html/pcre2_maketables.html \
+  doc/html/pcre2_maketables_free.html \
+  doc/html/pcre2_match.html \
+  doc/html/pcre2_match_context_copy.html \
+  doc/html/pcre2_match_context_create.html \
+  doc/html/pcre2_match_context_free.html \
+  doc/html/pcre2_match_data_create.html \
+  doc/html/pcre2_match_data_create_from_pattern.html \
+  doc/html/pcre2_match_data_free.html \
+  doc/html/pcre2_pattern_convert.html \
+  doc/html/pcre2_pattern_info.html \
+  doc/html/pcre2_serialize_decode.html \
+  doc/html/pcre2_serialize_encode.html \
+  doc/html/pcre2_serialize_free.html \
+  doc/html/pcre2_serialize_get_number_of_codes.html \
+  doc/html/pcre2_set_bsr.html \
+  doc/html/pcre2_set_callout.html \
+  doc/html/pcre2_set_character_tables.html \
+  doc/html/pcre2_set_compile_extra_options.html \
+  doc/html/pcre2_set_compile_recursion_guard.html \
+  doc/html/pcre2_set_depth_limit.html \
+  doc/html/pcre2_set_glob_escape.html \
+  doc/html/pcre2_set_glob_separator.html \
+  doc/html/pcre2_set_heap_limit.html \
+  doc/html/pcre2_set_match_limit.html \
+  doc/html/pcre2_set_max_pattern_length.html \
+  doc/html/pcre2_set_offset_limit.html \
+  doc/html/pcre2_set_newline.html \
+  doc/html/pcre2_set_parens_nest_limit.html \
+  doc/html/pcre2_set_recursion_limit.html \
+  doc/html/pcre2_set_recursion_memory_management.html \
+  doc/html/pcre2_set_substitute_callout.html \
+  doc/html/pcre2_substitute.html \
+  doc/html/pcre2_substring_copy_byname.html \
+  doc/html/pcre2_substring_copy_bynumber.html \
+  doc/html/pcre2_substring_free.html \
+  doc/html/pcre2_substring_get_byname.html \
+  doc/html/pcre2_substring_get_bynumber.html \
+  doc/html/pcre2_substring_length_byname.html \
+  doc/html/pcre2_substring_length_bynumber.html \
+  doc/html/pcre2_substring_list_free.html \
+  doc/html/pcre2_substring_list_get.html \
+  doc/html/pcre2_substring_nametable_scan.html \
+  doc/html/pcre2_substring_number_from_name.html \
+  doc/html/pcre2api.html \
+  doc/html/pcre2build.html \
+  doc/html/pcre2callout.html \
+  doc/html/pcre2compat.html \
+  doc/html/pcre2convert.html \
+  doc/html/pcre2demo.html \
+  doc/html/pcre2grep.html \
+  doc/html/pcre2jit.html \
+  doc/html/pcre2limits.html \
+  doc/html/pcre2matching.html \
+  doc/html/pcre2partial.html \
+  doc/html/pcre2pattern.html \
+  doc/html/pcre2perform.html \
+  doc/html/pcre2posix.html \
+  doc/html/pcre2sample.html \
+  doc/html/pcre2serialize.html \
+  doc/html/pcre2syntax.html \
+  doc/html/pcre2test.html \
+  doc/html/pcre2unicode.html
+
+dist_man_MANS = \
+  doc/pcre2-config.1 \
+  doc/pcre2.3 \
+  doc/pcre2_callout_enumerate.3 \
+  doc/pcre2_code_copy.3 \
+  doc/pcre2_code_copy_with_tables.3 \
+  doc/pcre2_code_free.3 \
+  doc/pcre2_compile.3 \
+  doc/pcre2_compile_context_copy.3 \
+  doc/pcre2_compile_context_create.3 \
+  doc/pcre2_compile_context_free.3 \
+  doc/pcre2_config.3 \
+  doc/pcre2_convert_context_copy.3 \
+  doc/pcre2_convert_context_create.3 \
+  doc/pcre2_convert_context_free.3 \
+  doc/pcre2_converted_pattern_free.3 \
+  doc/pcre2_dfa_match.3 \
+  doc/pcre2_general_context_copy.3 \
+  doc/pcre2_general_context_create.3 \
+  doc/pcre2_general_context_free.3 \
+  doc/pcre2_get_error_message.3 \
+  doc/pcre2_get_mark.3 \
+  doc/pcre2_get_match_data_size.3 \
+  doc/pcre2_get_ovector_count.3 \
+  doc/pcre2_get_ovector_pointer.3 \
+  doc/pcre2_get_startchar.3 \
+  doc/pcre2_jit_compile.3 \
+  doc/pcre2_jit_free_unused_memory.3 \
+  doc/pcre2_jit_match.3 \
+  doc/pcre2_jit_stack_assign.3 \
+  doc/pcre2_jit_stack_create.3 \
+  doc/pcre2_jit_stack_free.3 \
+  doc/pcre2_maketables.3 \
+  doc/pcre2_maketables_free.3 \
+  doc/pcre2_match.3 \
+  doc/pcre2_match_context_copy.3 \
+  doc/pcre2_match_context_create.3 \
+  doc/pcre2_match_context_free.3 \
+  doc/pcre2_match_data_create.3 \
+  doc/pcre2_match_data_create_from_pattern.3 \
+  doc/pcre2_match_data_free.3 \
+  doc/pcre2_pattern_convert.3 \
+  doc/pcre2_pattern_info.3 \
+  doc/pcre2_serialize_decode.3 \
+  doc/pcre2_serialize_encode.3 \
+  doc/pcre2_serialize_free.3 \
+  doc/pcre2_serialize_get_number_of_codes.3 \
+  doc/pcre2_set_bsr.3 \
+  doc/pcre2_set_callout.3 \
+  doc/pcre2_set_character_tables.3 \
+  doc/pcre2_set_compile_extra_options.3 \
+  doc/pcre2_set_compile_recursion_guard.3 \
+  doc/pcre2_set_depth_limit.3 \
+  doc/pcre2_set_glob_escape.3 \
+  doc/pcre2_set_glob_separator.3 \
+  doc/pcre2_set_heap_limit.3 \
+  doc/pcre2_set_match_limit.3 \
+  doc/pcre2_set_max_pattern_length.3 \
+  doc/pcre2_set_offset_limit.3 \
+  doc/pcre2_set_newline.3 \
+  doc/pcre2_set_parens_nest_limit.3 \
+  doc/pcre2_set_recursion_limit.3 \
+  doc/pcre2_set_recursion_memory_management.3 \
+  doc/pcre2_set_substitute_callout.3 \
+  doc/pcre2_substitute.3 \
+  doc/pcre2_substring_copy_byname.3 \
+  doc/pcre2_substring_copy_bynumber.3 \
+  doc/pcre2_substring_free.3 \
+  doc/pcre2_substring_get_byname.3 \
+  doc/pcre2_substring_get_bynumber.3 \
+  doc/pcre2_substring_length_byname.3 \
+  doc/pcre2_substring_length_bynumber.3 \
+  doc/pcre2_substring_list_free.3 \
+  doc/pcre2_substring_list_get.3 \
+  doc/pcre2_substring_nametable_scan.3 \
+  doc/pcre2_substring_number_from_name.3 \
+  doc/pcre2api.3 \
+  doc/pcre2build.3 \
+  doc/pcre2callout.3 \
+  doc/pcre2compat.3 \
+  doc/pcre2convert.3 \
+  doc/pcre2demo.3 \
+  doc/pcre2grep.1 \
+  doc/pcre2jit.3 \
+  doc/pcre2limits.3 \
+  doc/pcre2matching.3 \
+  doc/pcre2partial.3 \
+  doc/pcre2pattern.3 \
+  doc/pcre2perform.3 \
+  doc/pcre2posix.3 \
+  doc/pcre2sample.3 \
+  doc/pcre2serialize.3 \
+  doc/pcre2syntax.3 \
+  doc/pcre2test.1 \
+  doc/pcre2unicode.3
+
+# The Libtool libraries to install.  We'll add to this later.
+
+lib_LTLIBRARIES =
+
+# Unit tests you want to run when people type 'make check'.
+# TESTS is for binary unit tests, check_SCRIPTS for script-based tests
+
+TESTS =
+check_SCRIPTS =
+dist_noinst_SCRIPTS =
+
+# Some of the binaries we make are to be installed, and others are
+# (non-user-visible) helper programs needed to build the libraries.
+
+bin_PROGRAMS =
+noinst_PROGRAMS =
+
+# Additional files to delete on 'make clean', 'make distclean',
+# and 'make maintainer-clean'.
+
+CLEANFILES =
+DISTCLEANFILES = src/config.h.in~
+MAINTAINERCLEANFILES =
+
+# Additional files to bundle with the distribution, over and above what
+# the Autotools include by default.
+
+EXTRA_DIST =
+
+# These files contain additional m4 macros that are used by autoconf.
+
+EXTRA_DIST += \
+  m4/ax_pthread.m4 m4/pcre2_visibility.m4
+
+# These files contain maintenance information
+
+EXTRA_DIST += \
+  NON-AUTOTOOLS-BUILD \
+  HACKING
+
+# These files are used in the preparation of a release
+
+EXTRA_DIST += \
+  PrepareRelease \
+  CheckMan \
+  CleanTxt \
+  Detrail \
+  132html \
+  doc/index.html.src
+
+# These files are usable versions of pcre2.h and config.h that are distributed
+# for the benefit of people who are building PCRE2 manually, without the
+# Autotools support.
+
+EXTRA_DIST += \
+  src/pcre2.h.generic \
+  src/config.h.generic
+
+# The only difference between pcre2.h.in and pcre2.h is the setting of the PCRE
+# version number. Therefore, we can create the generic version just by copying.
+
+src/pcre2.h.generic: src/pcre2.h.in configure.ac
+	rm -f $@
+	cp -p src/pcre2.h $@
+
+# It is more complicated for config.h.generic. We need the version that results
+# from a default configuration so as to get all the default values for PCRE
+# configuration macros such as MATCH_LIMIT and NEWLINE. We can get this by
+# doing a configure in a temporary directory. However, some trickery is needed,
+# because the source directory may already be configured. If you just try
+# running configure in a new directory, it complains. For this reason, we move
+# config.status out of the way while doing the default configuration. The
+# resulting config.h is munged by perl to put #ifdefs round any #defines for
+# macros with values, and to #undef all boolean macros such as HAVE_xxx and
+# SUPPORT_xxx. We also get rid of any gcc-specific visibility settings. Make
+# sure that PCRE2_EXP_DEFN is unset (in case it has visibility settings).
+
+src/config.h.generic: configure.ac
+	rm -rf $@ _generic
+	mkdir _generic
+	cs=$(srcdir)/config.status; test ! -f $$cs || mv -f $$cs $$cs.aside
+	cd _generic && $(abs_top_srcdir)/configure || :
+	cs=$(srcdir)/config.status; test ! -f $$cs.aside || mv -f $$cs.aside $$cs
+	test -f _generic/src/config.h
+	perl -n \
+	  -e 'BEGIN{$$blank=0;}' \
+	  -e 'if(/PCRE2_EXP_DEFN/){print"/* #undef PCRE2_EXP_DEFN */\n";$$blank=0;next;}' \
+	  -e 'if(/to make a symbol visible/){next;}' \
+	  -e 'if(/__attribute__ \(\(visibility/){next;}' \
+	  -e 'if(/LT_OBJDIR/){print"/* This is ignored unless you are using libtool. */\n";}' \
+	  -e 'if(/^#define\s((?:HAVE|SUPPORT|STDC)_\w+)/){print"/* #undef $$1 */\n";$$blank=0;next;}' \
+	  -e 'if(/^#define\s(?!PACKAGE|VERSION)(\w+)/){print"#ifndef $$1\n$$_#endif\n";$$blank=0;next;}' \
+	  -e 'if(/^\s*$$/){print unless $$blank; $$blank=1;} else{print;$$blank=0;}' \
+	  _generic/src/config.h >$@
+	rm -rf _generic
+
+MAINTAINERCLEANFILES += src/pcre2.h.generic src/config.h.generic
+
+# These are the header files we'll install. We do not distribute pcre2.h
+# because it is generated from pcre2.h.in.
+
+nodist_include_HEADERS = src/pcre2.h
+include_HEADERS = src/pcre2posix.h
+
+# This is the "config" script.
+
+bin_SCRIPTS = pcre2-config
+
+## ---------------------------------------------------------------
+## The pcre2_dftables program is used to rebuild character tables before
+## compiling PCRE2, if --enable-rebuild-chartables is specified. It is not an
+## installed program. The default (when --enable-rebuild-chartables is not
+## specified) is to copy a distributed set of tables that are defined for ASCII
+## code. In this case, pcre2_dftables is not needed.
+
+if WITH_REBUILD_CHARTABLES
+noinst_PROGRAMS += pcre2_dftables
+pcre2_dftables_SOURCES = src/pcre2_dftables.c
+src/pcre2_chartables.c: pcre2_dftables$(EXEEXT)
+	rm -f $@
+	./pcre2_dftables$(EXEEXT) $@
+else
+src/pcre2_chartables.c: $(srcdir)/src/pcre2_chartables.c.dist
+	rm -f $@
+	$(LN_S) $(abs_srcdir)/src/pcre2_chartables.c.dist $(abs_builddir)/src/pcre2_chartables.c
+endif # WITH_REBUILD_CHARTABLES
+
+BUILT_SOURCES = src/pcre2_chartables.c
+NODIST_SOURCES = src/pcre2_chartables.c
+
+## Define the list of common sources, then arrange to build whichever of the
+## 8-, 16-, or 32-bit libraries are configured.
+
+COMMON_SOURCES = \
+  src/pcre2_auto_possess.c \
+  src/pcre2_compile.c \
+  src/pcre2_config.c \
+  src/pcre2_context.c \
+  src/pcre2_convert.c \
+  src/pcre2_dfa_match.c \
+  src/pcre2_error.c \
+  src/pcre2_extuni.c \
+  src/pcre2_find_bracket.c \
+  src/pcre2_internal.h \
+  src/pcre2_intmodedep.h \
+  src/pcre2_jit_compile.c \
+  src/pcre2_jit_neon_inc.h \
+  src/pcre2_jit_simd_inc.h \
+  src/pcre2_maketables.c \
+  src/pcre2_match.c \
+  src/pcre2_match_data.c \
+  src/pcre2_newline.c \
+  src/pcre2_ord2utf.c \
+  src/pcre2_pattern_info.c \
+  src/pcre2_script_run.c \
+  src/pcre2_serialize.c \
+  src/pcre2_string_utils.c \
+  src/pcre2_study.c \
+  src/pcre2_substitute.c \
+  src/pcre2_substring.c \
+  src/pcre2_tables.c \
+  src/pcre2_ucd.c \
+  src/pcre2_ucp.h \
+  src/pcre2_valid_utf.c \
+  src/pcre2_xclass.c
+
+if WITH_PCRE2_8
+lib_LTLIBRARIES += libpcre2-8.la
+libpcre2_8_la_SOURCES = \
+  $(COMMON_SOURCES)
+nodist_libpcre2_8_la_SOURCES = \
+  $(NODIST_SOURCES)
+libpcre2_8_la_CFLAGS = \
+  -DPCRE2_CODE_UNIT_WIDTH=8 \
+  $(VISIBILITY_CFLAGS) \
+  $(CET_CFLAGS) \
+  $(AM_CFLAGS)
+libpcre2_8_la_LIBADD =
+endif # WITH_PCRE2_8
+
+if WITH_PCRE2_16
+lib_LTLIBRARIES += libpcre2-16.la
+libpcre2_16_la_SOURCES = \
+  $(COMMON_SOURCES)
+nodist_libpcre2_16_la_SOURCES = \
+  $(NODIST_SOURCES)
+libpcre2_16_la_CFLAGS = \
+  -DPCRE2_CODE_UNIT_WIDTH=16 \
+  $(VISIBILITY_CFLAGS) \
+  $(CET_CFLAGS) \
+  $(AM_CFLAGS)
+libpcre2_16_la_LIBADD =
+endif # WITH_PCRE2_16
+
+if WITH_PCRE2_32
+lib_LTLIBRARIES += libpcre2-32.la
+libpcre2_32_la_SOURCES = \
+  $(COMMON_SOURCES)
+nodist_libpcre2_32_la_SOURCES = \
+  $(NODIST_SOURCES)
+libpcre2_32_la_CFLAGS = \
+  -DPCRE2_CODE_UNIT_WIDTH=32 \
+  $(VISIBILITY_CFLAGS) \
+  $(CET_CFLAGS) \
+  $(AM_CFLAGS)
+libpcre2_32_la_LIBADD =
+endif # WITH_PCRE2_32
+
+# The pcre2_chartables.c.dist file is the default version of
+# pcre2_chartables.c, used unless --enable-rebuild-chartables is specified.
+
+EXTRA_DIST += src/pcre2_chartables.c.dist
+CLEANFILES += src/pcre2_chartables.c
+
+# The JIT compiler lives in a separate directory, but its files are #included
+# when pcre2_jit_compile.c is processed, so they must be distributed.
+
+EXTRA_DIST += \
+  src/sljit/sljitConfig.h \
+  src/sljit/sljitConfigInternal.h \
+  src/sljit/sljitExecAllocator.c \
+  src/sljit/sljitLir.c \
+  src/sljit/sljitLir.h \
+  src/sljit/sljitNativeARM_32.c \
+  src/sljit/sljitNativeARM_64.c \
+  src/sljit/sljitNativeARM_T2_32.c \
+  src/sljit/sljitNativeMIPS_32.c \
+  src/sljit/sljitNativeMIPS_64.c \
+  src/sljit/sljitNativeMIPS_common.c \
+  src/sljit/sljitNativePPC_32.c \
+  src/sljit/sljitNativePPC_64.c \
+  src/sljit/sljitNativePPC_common.c \
+  src/sljit/sljitNativeS390X.c \
+  src/sljit/sljitNativeSPARC_32.c \
+  src/sljit/sljitNativeSPARC_common.c \
+  src/sljit/sljitNativeX86_32.c \
+  src/sljit/sljitNativeX86_64.c \
+  src/sljit/sljitNativeX86_common.c \
+  src/sljit/sljitProtExecAllocator.c \
+  src/sljit/sljitUtils.c \
+  src/sljit/sljitWXExecAllocator.c
+
+# Some of the JIT sources are also in separate files that are #included.
+
+EXTRA_DIST += \
+  src/pcre2_jit_match.c \
+  src/pcre2_jit_misc.c
+
+if WITH_PCRE2_8
+libpcre2_8_la_LDFLAGS = $(EXTRA_LIBPCRE2_8_LDFLAGS)
+endif # WITH_PCRE2_8
+if WITH_PCRE2_16
+libpcre2_16_la_LDFLAGS = $(EXTRA_LIBPCRE2_16_LDFLAGS)
+endif # WITH_PCRE2_16
+if WITH_PCRE2_32
+libpcre2_32_la_LDFLAGS = $(EXTRA_LIBPCRE2_32_LDFLAGS)
+endif # WITH_PCRE2_32
+
+if WITH_VALGRIND
+if WITH_PCRE2_8
+libpcre2_8_la_CFLAGS += $(VALGRIND_CFLAGS)
+endif # WITH_PCRE2_8
+if WITH_PCRE2_16
+libpcre2_16_la_CFLAGS += $(VALGRIND_CFLAGS)
+endif # WITH_PCRE2_16
+if WITH_PCRE2_32
+libpcre2_32_la_CFLAGS += $(VALGRIND_CFLAGS)
+endif # WITH_PCRE2_32
+endif # WITH_VALGRIND
+
+if WITH_GCOV
+if WITH_PCRE2_8
+libpcre2_8_la_CFLAGS += $(GCOV_CFLAGS)
+endif # WITH_PCRE2_8
+if WITH_PCRE2_16
+libpcre2_16_la_CFLAGS += $(GCOV_CFLAGS)
+endif # WITH_PCRE2_16
+if WITH_PCRE2_32
+libpcre2_32_la_CFLAGS += $(GCOV_CFLAGS)
+endif # WITH_PCRE2_32
+endif # WITH_GCOV
+
+## A version of the 8-bit library that has a POSIX API.
+
+if WITH_PCRE2_8
+lib_LTLIBRARIES += libpcre2-posix.la
+libpcre2_posix_la_SOURCES = src/pcre2posix.c
+libpcre2_posix_la_CFLAGS = \
+  -DPCRE2_CODE_UNIT_WIDTH=8 \
+  $(VISIBILITY_CFLAGS) $(AM_CFLAGS)
+libpcre2_posix_la_LDFLAGS = $(EXTRA_LIBPCRE2_POSIX_LDFLAGS)
+libpcre2_posix_la_LIBADD = libpcre2-8.la
+if WITH_GCOV
+libpcre2_posix_la_CFLAGS += $(GCOV_CFLAGS)
+endif # WITH_GCOV
+endif # WITH_PCRE2_8
+
+## Build pcre2grep and optional fuzzer stuff if the 8-bit library is enabled
+
+if WITH_PCRE2_8
+bin_PROGRAMS += pcre2grep
+pcre2grep_SOURCES = src/pcre2grep.c
+pcre2grep_CFLAGS = $(AM_CFLAGS)
+pcre2grep_LDADD = $(LIBZ) $(LIBBZ2)
+pcre2grep_LDADD += libpcre2-8.la
+if WITH_GCOV
+pcre2grep_CFLAGS += $(GCOV_CFLAGS)
+pcre2grep_LDADD += $(GCOV_LIBS)
+endif # WITH_GCOV
+
+## If fuzzer support is enabled, build a non-distributed library containing the
+## fuzzing function. Also build the standalone checking binary from the same
+## source but using -DSTANDALONE.
+
+if WITH_FUZZ_SUPPORT
+noinst_LIBRARIES = .libs/libpcre2-fuzzsupport.a
+_libs_libpcre2_fuzzsupport_a_SOURCES = src/pcre2_fuzzsupport.c
+_libs_libpcre2_fuzzsupport_a_CFLAGS = $(AM_CFLAGS)
+_libs_libpcre2_fuzzsupport_a_LIBADD =
+
+noinst_PROGRAMS += pcre2fuzzcheck
+pcre2fuzzcheck_SOURCES = src/pcre2_fuzzsupport.c
+pcre2fuzzcheck_CFLAGS = -DSTANDALONE $(AM_CFLAGS)
+pcre2fuzzcheck_LDADD = libpcre2-8.la
+if WITH_GCOV
+pcre2fuzzcheck_CFLAGS += $(GCOV_CFLAGS)
+pcre2fuzzcheck_LDADD += $(GCOV_LIBS)
+endif # WITH_GCOV
+endif # WITH FUZZ_SUPPORT
+endif # WITH_PCRE2_8
+
+## -------- Testing ----------
+
+## If JIT support is enabled, arrange for the JIT test program to run.
+
+if WITH_JIT
+TESTS += pcre2_jit_test
+noinst_PROGRAMS += pcre2_jit_test
+pcre2_jit_test_SOURCES = src/pcre2_jit_test.c
+pcre2_jit_test_CFLAGS = $(AM_CFLAGS)
+pcre2_jit_test_LDADD =
+if WITH_PCRE2_8
+pcre2_jit_test_LDADD += libpcre2-8.la
+endif # WITH_PCRE2_8
+if WITH_PCRE2_16
+pcre2_jit_test_LDADD += libpcre2-16.la
+endif # WITH_PCRE2_16
+if WITH_PCRE2_32
+pcre2_jit_test_LDADD += libpcre2-32.la
+endif # WITH_PCRE2_32
+if WITH_GCOV
+pcre2_jit_test_CFLAGS += $(GCOV_CFLAGS)
+pcre2_jit_test_LDADD += $(GCOV_LIBS)
+endif # WITH_GCOV
+endif # WITH_JIT
+
+# Build the general pcre2test program. The file src/pcre2_printint.c is
+# #included by pcre2test as many times as needed, at different code unit
+# widths.
+
+bin_PROGRAMS += pcre2test
+EXTRA_DIST += src/pcre2_printint.c
+pcre2test_SOURCES = src/pcre2test.c
+pcre2test_CFLAGS = $(AM_CFLAGS)
+pcre2test_LDADD = $(LIBREADLINE)
+
+if WITH_PCRE2_8
+pcre2test_LDADD += libpcre2-8.la libpcre2-posix.la
+endif # WITH_PCRE2_8
+
+if WITH_PCRE2_16
+pcre2test_LDADD += libpcre2-16.la
+endif # WITH_PCRE2_16
+
+if WITH_PCRE2_32
+pcre2test_LDADD += libpcre2-32.la
+endif # WITH_PCRE2_32
+
+if WITH_VALGRIND
+pcre2test_CFLAGS += $(VALGRIND_CFLAGS)
+endif # WITH_VALGRIND
+
+if WITH_GCOV
+pcre2test_CFLAGS += $(GCOV_CFLAGS)
+pcre2test_LDADD += $(GCOV_LIBS)
+endif # WITH_GCOV
+
+## The main library tests. Each test is a binary plus a script that runs that
+## binary in various ways. We install these test binaries in case folks find it
+## helpful. The two .bat files are for running the tests under Windows.
+
+TESTS += RunTest
+EXTRA_DIST += RunTest.bat
+dist_noinst_SCRIPTS += RunTest
+
+## When the 8-bit library is configured, pcre2grep will have been built.
+
+if WITH_PCRE2_8
+TESTS += RunGrepTest
+EXTRA_DIST += RunGrepTest.bat
+dist_noinst_SCRIPTS += RunGrepTest
+endif # WITH_PCRE2_8
+
+## Distribute all the test data files
+
+EXTRA_DIST += \
+  testdata/grepbinary \
+  testdata/grepfilelist \
+  testdata/grepinput \
+  testdata/grepinput3 \
+  testdata/grepinput8 \
+  testdata/grepinputM \
+  testdata/grepinputv \
+  testdata/grepinputx \
+  testdata/greplist \
+  testdata/grepoutput \
+  testdata/grepoutput8 \
+  testdata/grepoutputC \
+  testdata/grepoutputCN \
+  testdata/grepoutputN \
+  testdata/greppatN4 \
+  testdata/testbtables \
+  testdata/testinput1 \
+  testdata/testinput2 \
+  testdata/testinput3 \
+  testdata/testinput4 \
+  testdata/testinput5 \
+  testdata/testinput6 \
+  testdata/testinput7 \
+  testdata/testinput8 \
+  testdata/testinput9 \
+  testdata/testinput10 \
+  testdata/testinput11 \
+  testdata/testinput12 \
+  testdata/testinput13 \
+  testdata/testinput14 \
+  testdata/testinput15 \
+  testdata/testinput16 \
+  testdata/testinput17 \
+  testdata/testinput18 \
+  testdata/testinput19 \
+  testdata/testinput20 \
+  testdata/testinput21 \
+  testdata/testinput22 \
+  testdata/testinput23 \
+  testdata/testinput24 \
+  testdata/testinput25 \
+  testdata/testinputEBC \
+  testdata/testoutput1 \
+  testdata/testoutput2 \
+  testdata/testoutput3 \
+  testdata/testoutput3A \
+  testdata/testoutput3B \
+  testdata/testoutput4 \
+  testdata/testoutput5 \
+  testdata/testoutput6 \
+  testdata/testoutput7 \
+  testdata/testoutput8-16-2 \
+  testdata/testoutput8-16-3 \
+  testdata/testoutput8-16-4 \
+  testdata/testoutput8-32-2 \
+  testdata/testoutput8-32-3 \
+  testdata/testoutput8-32-4 \
+  testdata/testoutput8-8-2 \
+  testdata/testoutput8-8-3 \
+  testdata/testoutput8-8-4 \
+  testdata/testoutput9 \
+  testdata/testoutput10 \
+  testdata/testoutput11-16 \
+  testdata/testoutput11-32 \
+  testdata/testoutput12-16 \
+  testdata/testoutput12-32 \
+  testdata/testoutput13 \
+  testdata/testoutput14-16 \
+  testdata/testoutput14-32 \
+  testdata/testoutput14-8 \
+  testdata/testoutput15 \
+  testdata/testoutput16 \
+  testdata/testoutput17 \
+  testdata/testoutput18 \
+  testdata/testoutput19 \
+  testdata/testoutput20 \
+  testdata/testoutput21 \
+  testdata/testoutput22-16 \
+  testdata/testoutput22-32 \
+  testdata/testoutput22-8 \
+  testdata/testoutput23 \
+  testdata/testoutput24 \
+  testdata/testoutput25 \
+  testdata/testoutputEBC \
+  testdata/valgrind-jit.supp \
+  testdata/wintestinput3 \
+  testdata/wintestoutput3 \
+  perltest.sh
+
+# RunTest and RunGrepTest should clean up after themselves, but just in case
+# they don't, add their working files to CLEANFILES.
+
+CLEANFILES += \
+        testSinput \
+        test3input \
+        test3output \
+        test3outputA \
+        test3outputB \
+        testtry \
+        teststdout \
+	teststderr \
+        teststderrgrep \
+        testtemp1grep \
+        testtemp2grep \
+        testtrygrep \
+        testNinputgrep
+
+## ------------ End of testing -------------
+
+
+# PCRE2 demonstration program. Not built automatcally. The point is that the
+# users should build it themselves. So just distribute the source.
+
+EXTRA_DIST += src/pcre2demo.c
+
+
+# We have .pc files for pkg-config users.
+
+pkgconfigdir = $(libdir)/pkgconfig
+pkgconfig_DATA =
+
+if WITH_PCRE2_8
+pkgconfig_DATA += libpcre2-8.pc libpcre2-posix.pc
+endif
+
+if WITH_PCRE2_16
+pkgconfig_DATA += libpcre2-16.pc
+endif
+
+if WITH_PCRE2_32
+pkgconfig_DATA += libpcre2-32.pc
+endif
+
+
+# gcov/lcov code coverage reporting
+#
+# Coverage reporting targets:
+#
+# coverage: Create a coverage report from 'make check'
+# coverage-baseline: Capture baseline coverage information
+# coverage-reset: This zeros the coverage counters only
+# coverage-report: This creates the coverage report only
+# coverage-clean-report: This removes the generated coverage report
+#   without cleaning the coverage data itself
+# coverage-clean-data: This removes the captured coverage data without
+#   removing the coverage files created at compile time (*.gcno)
+# coverage-clean: This cleans all coverage data including the generated
+#   coverage report.
+
+if WITH_GCOV
+COVERAGE_TEST_NAME = $(PACKAGE)
+COVERAGE_NAME = $(PACKAGE)-$(VERSION)
+COVERAGE_OUTPUT_FILE = $(COVERAGE_NAME)-coverage.info
+COVERAGE_OUTPUT_DIR = $(COVERAGE_NAME)-coverage
+COVERAGE_LCOV_EXTRA_FLAGS =
+COVERAGE_GENHTML_EXTRA_FLAGS =
+
+coverage_quiet = $(coverage_quiet_$(V))
+coverage_quiet_ = $(coverage_quiet_$(AM_DEFAULT_VERBOSITY))
+coverage_quiet_0 = --quiet
+
+coverage-check: all
+	-$(MAKE) $(AM_MAKEFLAGS) -k check
+
+coverage-baseline:
+	$(LCOV) $(coverage_quiet) \
+		--directory $(top_builddir) \
+		--output-file "$(COVERAGE_OUTPUT_FILE)" \
+		--capture \
+		--initial
+
+coverage-report:
+	$(LCOV) $(coverage_quiet) \
+		--directory $(top_builddir) \
+		--capture \
+		--output-file "$(COVERAGE_OUTPUT_FILE).tmp" \
+		--test-name "$(COVERAGE_TEST_NAME)" \
+		--no-checksum \
+		--compat-libtool \
+		$(COVERAGE_LCOV_EXTRA_FLAGS)
+	$(LCOV) $(coverage_quiet) \
+		--directory $(top_builddir) \
+		--output-file "$(COVERAGE_OUTPUT_FILE)" \
+		--remove "$(COVERAGE_OUTPUT_FILE).tmp" \
+		"/tmp/*" \
+		"/usr/include/*" \
+		"$(includedir)/*"
+	-@rm -f "$(COVERAGE_OUTPUT_FILE).tmp"
+	LANG=C $(GENHTML) $(coverage_quiet) \
+		--prefix $(top_builddir) \
+		--output-directory "$(COVERAGE_OUTPUT_DIR)" \
+		--title "$(PACKAGE) $(VERSION) Code Coverage Report" \
+		--show-details "$(COVERAGE_OUTPUT_FILE)" \
+		--legend \
+		$(COVERAGE_GENHTML_EXTRA_FLAGS)
+	@echo "Code coverage report written to file://$(abs_builddir)/$(COVERAGE_OUTPUT_DIR)/index.html"
+
+coverage-reset:
+	-$(LCOV) $(coverage_quiet) --zerocounters --directory $(top_builddir)
+
+coverage-clean-report:
+	-rm -f "$(COVERAGE_OUTPUT_FILE)" "$(COVERAGE_OUTPUT_FILE).tmp"
+	-rm -rf "$(COVERAGE_OUTPUT_DIR)"
+
+coverage-clean-data:
+	-find $(top_builddir) -name "*.gcda" -delete
+
+coverage-clean: coverage-reset coverage-clean-report coverage-clean-data
+	-find $(top_builddir) -name "*.gcno" -delete
+
+coverage-distclean: coverage-clean
+
+coverage: coverage-reset coverage-baseline coverage-check coverage-report
+clean-local: coverage-clean
+distclean-local: coverage-distclean
+
+.PHONY: coverage coverage-baseline coverage-check coverage-report coverage-reset coverage-clean-report coverage-clean-data coverage-clean coverage-distclean
+
+# Without coverage support, still arrange for 'make distclean' to get rid of
+# any coverage files that may have been left from a different configuration.
+
+else
+
+coverage:
+	@echo "Configuring with --enable-coverage is required to generate code coverage report."
+
+DISTCLEANFILES += src/*.gcda src/*.gcno
+
+distclean-local:
+	rm -rf $(PACKAGE)-$(VERSION)-coverage*
+
+endif # WITH_GCOV
+
+## CMake support
+
+EXTRA_DIST += \
+  cmake/COPYING-CMAKE-SCRIPTS \
+  cmake/FindPackageHandleStandardArgs.cmake \
+  cmake/FindReadline.cmake \
+  cmake/FindEditline.cmake \
+  CMakeLists.txt \
+  config-cmake.h.in
+
+## end Makefile.am

src/regex/pcre2/NEWS

@@ -0,0 +1,355 @@
+News about PCRE2 releases
+-------------------------
+
+
+Version 10.37 26-May-2021
+-------------------------
+
+A few more bug fixes and tidies. The only change of real note is the removal of
+the actual POSIX names regcomp etc. from the POSIX wrapper library because
+these have caused issues for some applications (see 10.33 #2 below).
+
+
+Version 10.36 04-December-2020
+------------------------------
+
+Again, mainly bug fixes and tidies. The only enhancements are the addition of
+GNU grep's -m (aka --max-count) option to pcre2grep, and also unifying the
+handling of substitution strings for both -O and callouts in pcre2grep, with
+the addition of $x{...} and $o{...} to allow for characters whose code points
+are greater than 255 in Unicode mode.
+
+NOTE: there is an outstanding issue with JIT support for MacOS on arm64
+hardware. For details, please see Bugzilla issue #2618.
+
+
+Version 10.35 15-April-2020
+---------------------------
+
+Bugfixes, tidies, and a few new enhancements.
+
+1. Capturing groups that contain recursive backreferences to themselves are no
+longer automatically atomic, because the restriction is no longer necessary
+as a result of the 10.30 restructuring.
+
+2. Several new options for pcre2_substitute().
+
+3. When Unicode is supported and PCRE2_UCP is set without PCRE2_UTF, Unicode
+character properties are used for upper/lower case computations on characters
+whose code points are greater than 127.
+
+4. The character tables (for low-valued characters) can now more easily be
+saved and restored in binary.
+
+5. Updated to Unicode 13.0.0.
+
+
+Version 10.34 21-November-2019
+------------------------------
+
+Another release with a few enhancements as well as bugfixes and tidies. The
+main new features are:
+
+1. There is now some support for matching in invalid UTF strings.
+
+2. Non-atomic positive lookarounds are implemented in the pcre2_match()
+interpreter, but not in JIT.
+
+3. Added two new functions: pcre2_get_match_data_size() and
+pcre2_maketables_free().
+
+4. Upgraded to Unicode 12.1.0.
+
+
+Version 10.33 16-April-2019
+---------------------------
+
+Yet more bugfixes, tidies, and a few enhancements, summarized here (see
+ChangeLog for the full list):
+
+1. Callouts from pcre2_substitute() are now available.
+
+2. The POSIX functions are now all called pcre2_regcomp() etc., with wrapper
+functions that use the standard POSIX names. However, in pcre2posix.h the POSIX
+names are defined as macros. This should help avoid linking with the wrong
+library in some environments, while still exporting the POSIX names for
+pre-existing programs that use them.
+
+3. Some new options:
+
+   (a) PCRE2_EXTRA_ESCAPED_CR_IS_LF makes \r behave as \n.
+
+   (b) PCRE2_EXTRA_ALT_BSUX enables support for ECMAScript 6's \u{hh...}
+       construct.
+
+   (c) PCRE2_COPY_MATCHED_SUBJECT causes a copy of a matched subject to be
+       made, instead of just remembering a pointer.
+
+4. Some new Perl features:
+
+   (a) Perl 5.28's experimental alphabetic names for atomic groups and
+       lookaround assertions, for example, (*pla:...) and (*atomic:...).
+
+   (b) The new Perl "script run" features (*script_run:...) and
+       (*atomic_script_run:...) aka (*sr:...) and (*asr:...).
+
+   (c) When PCRE2_UTF is set, allow non-ASCII letters and decimal digits in
+       capture group names.
+
+5. --disable-percent-zt disables the use of %zu and %td in formatting strings
+in pcre2test. They were already automatically disabled for VC and older C
+compilers.
+
+6. Some changes related to callouts in pcre2grep:
+
+   (a) Support for running an external program under VMS has been added, in
+       addition to Windows and fork() support.
+
+   (b) --disable-pcre2grep-callout-fork restricts the callout support in
+       to the inbuilt echo facility.
+
+
+Version 10.32 10-September-2018
+-------------------------------
+
+This is another mainly bugfix and tidying release with a few minor
+enhancements. These are the main ones:
+
+1. pcre2grep now supports the inclusion of binary zeros in patterns that are
+read from files via the -f option.
+
+2. ./configure now supports --enable-jit=auto, which automatically enables JIT
+if the hardware supports it.
+
+3. In pcre2_dfa_match(), internal recursive calls no longer use the stack for
+local workspace and local ovectors. Instead, an initial block of stack is
+reserved, but if this is insufficient, heap memory is used. The heap limit
+parameter now applies to pcre2_dfa_match().
+
+4. Updated to Unicode version 11.0.0.
+
+5. (*ACCEPT:ARG), (*FAIL:ARG), and (*COMMIT:ARG) are now supported.
+
+6. Added support for \N{U+dddd}, but only in Unicode mode.
+
+7. Added support for (?^) to unset all imnsx options.
+
+
+Version 10.31 12-February-2018
+------------------------------
+
+This is mainly a bugfix and tidying release (see ChangeLog for full details).
+However, there are some minor enhancements.
+
+1. New pcre2_config() options: PCRE2_CONFIG_NEVER_BACKSLASH_C and
+PCRE2_CONFIG_COMPILED_WIDTHS.
+
+2. New pcre2_pattern_info() option PCRE2_INFO_EXTRAOPTIONS to retrieve the
+extra compile time options.
+
+3. There are now public names for all the pcre2_compile() error numbers.
+
+4. Added PCRE2_CALLOUT_STARTMATCH and PCRE2_CALLOUT_BACKTRACK bits to a new
+field callout_flags in callout blocks.
+
+
+Version 10.30 14-August-2017
+----------------------------
+
+The full list of changes that includes bugfixes and tidies is, as always, in
+ChangeLog. These are the most important new features:
+
+1. The main interpreter, pcre2_match(), has been refactored into a new version
+that does not use recursive function calls (and therefore the system stack) for
+remembering backtracking positions. This makes --disable-stack-for-recursion a
+NOOP. The new implementation allows backtracking into recursive group calls in
+patterns, making it more compatible with Perl, and also fixes some other
+previously hard-to-do issues. For patterns that have a lot of backtracking, the
+heap is now used, and there is an explicit limit on the amount, settable by
+pcre2_set_heap_limit() or (*LIMIT_HEAP=xxx). The "recursion limit" is retained,
+but is renamed as "depth limit" (though the old names remain for
+compatibility).
+
+There is also a change in the way callouts from pcre2_match() are handled. The
+offset_vector field in the callout block is no longer a pointer to the
+actual ovector that was passed to the matching function in the match data
+block. Instead it points to an internal ovector of a size large enough to hold
+all possible captured substrings in the pattern.
+
+2. The new option PCRE2_ENDANCHORED insists that a pattern match must end at
+the end of the subject.
+
+3. The new option PCRE2_EXTENDED_MORE implements Perl's /xx feature, and
+pcre2test is upgraded to support it. Setting within the pattern by (?xx) is
+also supported.
+
+4. (?n) can be used to set PCRE2_NO_AUTO_CAPTURE, because Perl now has this.
+
+5. Additional compile options in the compile context are now available, and the
+first two are: PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES and
+PCRE2_EXTRA_BAD_ESCAPE_IS_LITERAL.
+
+6. The newline type PCRE2_NEWLINE_NUL is now available.
+
+7. The match limit value now also applies to pcre2_dfa_match() as there are
+patterns that can use up a lot of resources without necessarily recursing very
+deeply.
+
+8. The option REG_PEND (a GNU extension) is now available for the POSIX
+wrapper. Also there is a new option PCRE2_LITERAL which is used to support
+REG_NOSPEC.
+
+9. PCRE2_EXTRA_MATCH_LINE and PCRE2_EXTRA_MATCH_WORD are implemented for the
+benefit of pcre2grep, and pcre2grep's -F, -w, and -x options are re-implemented
+using PCRE2_LITERAL, PCRE2_EXTRA_MATCH_WORD, and PCRE2_EXTRA_MATCH_LINE. This
+is tidier and also fixes some bugs.
+
+10. The Unicode tables are upgraded from Unicode 8.0.0 to Unicode 10.0.0.
+
+11. There are some experimental functions for converting foreign patterns
+(globs and POSIX patterns) into PCRE2 patterns.
+
+
+Version 10.23 14-February-2017
+------------------------------
+
+1. ChangeLog has the details of a lot of bug fixes and tidies.
+
+2. There has been a major re-factoring of the pcre2_compile.c file. Most syntax
+checking is now done in the pre-pass that identifies capturing groups. This has
+reduced the amount of duplication and made the code tidier. While doing this,
+some minor bugs and Perl incompatibilities were fixed (see ChangeLog for
+details.)
+
+3. Back references are now permitted in lookbehind assertions when there are
+no duplicated group numbers (that is, (?| has not been used), and, if the
+reference is by name, there is only one group of that name. The referenced
+group must, of course be of fixed length.
+
+4. \g{+<number>} (e.g. \g{+2} ) is now supported. It is a "forward back
+reference" and can be useful in repetitions (compare \g{-<number>} ). Perl does
+not recognize this syntax.
+
+5. pcre2grep now automatically expands its buffer up to a maximum set by
+--max-buffer-size.
+
+6. The -t option (grand total) has been added to pcre2grep.
+
+7. A new function called pcre2_code_copy_with_tables() exists to copy a
+compiled pattern along with a private copy of the character tables that is
+uses.
+
+8. A user supplied a number of patches to upgrade pcre2grep under Windows and
+tidy the code.
+
+9. Several updates have been made to pcre2test and test scripts (see
+ChangeLog).
+
+
+Version 10.22 29-July-2016
+--------------------------
+
+1. ChangeLog has the details of a number of bug fixes.
+
+2. The POSIX wrapper function regcomp() did not used to support back references
+and subroutine calls if called with the REG_NOSUB option. It now does.
+
+3. A new function, pcre2_code_copy(), is added, to make a copy of a compiled
+pattern.
+
+4. Support for string callouts is added to pcre2grep.
+
+5. Added the PCRE2_NO_JIT option to pcre2_match().
+
+6. The pcre2_get_error_message() function now returns with a negative error
+code if the error number it is given is unknown.
+
+7. Several updates have been made to pcre2test and test scripts (see
+ChangeLog).
+
+
+Version 10.21 12-January-2016
+-----------------------------
+
+1. Many bugs have been fixed. A large number of them were provoked only by very
+strange pattern input, and were discovered by fuzzers. Some others were
+discovered by code auditing. See ChangeLog for details.
+
+2. The Unicode tables have been updated to Unicode version 8.0.0.
+
+3. For Perl compatibility in EBCDIC environments, ranges such as a-z in a
+class, where both values are literal letters in the same case, omit the
+non-letter EBCDIC code points within the range.
+
+4. There have been a number of enhancements to the pcre2_substitute() function,
+giving more flexibility to replacement facilities. It is now also possible to
+cause the function to return the needed buffer size if the one given is too
+small.
+
+5. The PCRE2_ALT_VERBNAMES option causes the "name" parts of special verbs such
+as (*THEN:name) to be processed for backslashes and to take note of
+PCRE2_EXTENDED.
+
+6. PCRE2_INFO_HASBACKSLASHC makes it possible for a client to find out if a
+pattern uses \C, and --never-backslash-C makes it possible to compile a version
+PCRE2 in which the use of \C is always forbidden.
+
+7. A limit to the length of pattern that can be handled can now be set by
+calling pcre2_set_max_pattern_length().
+
+8. When matching an unanchored pattern, a match can be required to begin within
+a given number of code units after the start of the subject by calling
+pcre2_set_offset_limit().
+
+9. The pcre2test program has been extended to test new facilities, and it can
+now run the tests when LF on its own is not a valid newline sequence.
+
+10. The RunTest script has also been updated to enable more tests to be run.
+
+11. There have been some minor performance enhancements.
+
+
+Version 10.20 30-June-2015
+--------------------------
+
+1. Callouts with string arguments and the pcre2_callout_enumerate() function
+have been implemented.
+
+2. The PCRE2_NEVER_BACKSLASH_C option, which locks out the use of \C, is added.
+
+3. The PCRE2_ALT_CIRCUMFLEX option lets ^ match after a newline at the end of a
+subject in multiline mode.
+
+4. The way named subpatterns are handled has been refactored. The previous
+approach had several bugs.
+
+5. The handling of \c in EBCDIC environments has been changed to conform to the
+perlebcdic document. This is an incompatible change.
+
+6. Bugs have been mended, many of them discovered by fuzzers.
+
+
+Version 10.10 06-March-2015
+---------------------------
+
+1. Serialization and de-serialization functions have been added to the API,
+making it possible to save and restore sets of compiled patterns, though
+restoration must be done in the same environment that was used for compilation.
+
+2. The (*NO_JIT) feature has been added; this makes it possible for a pattern
+creator to specify that JIT is not to be used.
+
+3. A number of bugs have been fixed. In particular, bugs that caused building
+on Windows using CMake to fail have been mended.
+
+
+Version 10.00 05-January-2015
+-----------------------------
+
+Version 10.00 is the first release of PCRE2, a revised API for the PCRE
+library. Changes prior to 10.00 are logged in the ChangeLog file for the old
+API, up to item 20 for release 8.36. New programs are recommended to use the
+new library. Programs that use the original (PCRE1) API will need changing
+before linking with the new library.
+
+****

src/regex/pcre2/NON-AUTOTOOLS-BUILD

@@ -0,0 +1,410 @@
+Building PCRE2 without using autotools
+--------------------------------------
+
+This document contains the following sections:
+
+  General
+  Generic instructions for the PCRE2 C library
+  Stack size in Windows environments
+  Linking programs in Windows environments
+  Calling conventions in Windows environments
+  Comments about Win32 builds
+  Building PCRE2 on Windows with CMake
+  Building PCRE2 on Windows with Visual Studio
+  Testing with RunTest.bat
+  Building PCRE2 on native z/OS and z/VM
+
+
+GENERAL
+
+The basic PCRE2 library consists entirely of code written in Standard C, and so
+should compile successfully on any system that has a Standard C compiler and
+library.
+
+The PCRE2 distribution includes a "configure" file for use by the
+configure/make (autotools) build system, as found in many Unix-like
+environments. The README file contains information about the options for
+"configure".
+
+There is also support for CMake, which some users prefer, especially in Windows
+environments, though it can also be run in Unix-like environments. See the
+section entitled "Building PCRE2 on Windows with CMake" below.
+
+Versions of src/config.h and src/pcre2.h are distributed in the PCRE2 tarballs
+under the names src/config.h.generic and src/pcre2.h.generic. These are
+provided for those who build PCRE2 without using "configure" or CMake. If you
+use "configure" or CMake, the .generic versions are not used.
+
+
+GENERIC INSTRUCTIONS FOR THE PCRE2 C LIBRARY
+
+The following are generic instructions for building the PCRE2 C library "by
+hand". If you are going to use CMake, this section does not apply to you; you
+can skip ahead to the CMake section. Note that the settings concerned with
+8-bit, 16-bit, and 32-bit code units relate to the type of data string that
+PCRE2 processes. They are NOT referring to the underlying operating system bit
+width. You do not have to do anything special to compile in a 64-bit
+environment, for example.
+
+ (1) Copy or rename the file src/config.h.generic as src/config.h, and edit the
+     macro settings that it contains to whatever is appropriate for your
+     environment. In particular, you can alter the definition of the NEWLINE
+     macro to specify what character(s) you want to be interpreted as line
+     terminators by default.
+
+     When you subsequently compile any of the PCRE2 modules, you must specify
+     -DHAVE_CONFIG_H to your compiler so that src/config.h is included in the
+     sources.
+
+     An alternative approach is not to edit src/config.h, but to use -D on the
+     compiler command line to make any changes that you need to the
+     configuration options. In this case -DHAVE_CONFIG_H must not be set.
+
+     NOTE: There have been occasions when the way in which certain parameters
+     in src/config.h are used has changed between releases. (In the
+     configure/make world, this is handled automatically.) When upgrading to a
+     new release, you are strongly advised to review src/config.h.generic
+     before re-using what you had previously.
+
+     Note also that the src/config.h.generic file is created from a config.h
+     that was generated by Autotools, which automatically includes settings of
+     a number of macros that are not actually used by PCRE2 (for example,
+     HAVE_MEMORY_H).
+
+ (2) Copy or rename the file src/pcre2.h.generic as src/pcre2.h.
+
+ (3) EITHER:
+       Copy or rename file src/pcre2_chartables.c.dist as
+       src/pcre2_chartables.c.
+
+     OR:
+       Compile src/pcre2_dftables.c as a stand-alone program (using
+       -DHAVE_CONFIG_H if you have set up src/config.h), and then run it with
+       the single argument "src/pcre2_chartables.c". This generates a set of
+       standard character tables and writes them to that file. The tables are
+       generated using the default C locale for your system. If you want to use
+       a locale that is specified by LC_xxx environment variables, add the -L
+       option to the pcre2_dftables command. You must use this method if you
+       are building on a system that uses EBCDIC code.
+
+     The tables in src/pcre2_chartables.c are defaults. The caller of PCRE2 can
+     specify alternative tables at run time.
+
+ (4) For a library that supports 8-bit code units in the character strings that
+     it processes, compile the following source files from the src directory,
+     setting -DPCRE2_CODE_UNIT_WIDTH=8 as a compiler option. Also set
+     -DHAVE_CONFIG_H if you have set up src/config.h with your configuration,
+     or else use other -D settings to change the configuration as required.
+
+       pcre2_auto_possess.c
+       pcre2_chartables.c
+       pcre2_compile.c
+       pcre2_config.c
+       pcre2_context.c
+       pcre2_convert.c
+       pcre2_dfa_match.c
+       pcre2_error.c
+       pcre2_extuni.c
+       pcre2_find_bracket.c
+       pcre2_jit_compile.c
+       pcre2_maketables.c
+       pcre2_match.c
+       pcre2_match_data.c
+       pcre2_newline.c
+       pcre2_ord2utf.c
+       pcre2_pattern_info.c
+       pcre2_script_run.c
+       pcre2_serialize.c
+       pcre2_string_utils.c
+       pcre2_study.c
+       pcre2_substitute.c
+       pcre2_substring.c
+       pcre2_tables.c
+       pcre2_ucd.c
+       pcre2_valid_utf.c
+       pcre2_xclass.c
+
+     Make sure that you include -I. in the compiler command (or equivalent for
+     an unusual compiler) so that all included PCRE2 header files are first
+     sought in the src directory under the current directory. Otherwise you run
+     the risk of picking up a previously-installed file from somewhere else.
+
+     Note that you must compile pcre2_jit_compile.c, even if you have not
+     defined SUPPORT_JIT in src/config.h, because when JIT support is not
+     configured, dummy functions are compiled. When JIT support IS configured,
+     pcre2_jit_compile.c #includes other files from the sljit subdirectory,
+     all of whose names begin with "sljit". It also #includes
+     src/pcre2_jit_match.c and src/pcre2_jit_misc.c, so you should not compile
+     these yourself.
+
+     Note also that the pcre2_fuzzsupport.c file contains special code that is
+     useful to those who want to run fuzzing tests on the PCRE2 library. Unless
+     you are doing that, you can ignore it.
+
+ (5) Now link all the compiled code into an object library in whichever form
+     your system keeps such libraries. This is the basic PCRE2 C 8-bit library.
+     If your system has static and shared libraries, you may have to do this
+     once for each type.
+
+ (6) If you want to build a library that supports 16-bit or 32-bit code units,
+     (as well as, or instead of the 8-bit library) just supply 16 or 32 as the
+     value of -DPCRE2_CODE_UNIT_WIDTH when you are compiling.
+
+ (7) If you want to build the POSIX wrapper functions (which apply only to the
+     8-bit library), ensure that you have the src/pcre2posix.h file and then
+     compile src/pcre2posix.c. Link the result (on its own) as the pcre2posix
+     library.
+
+ (8) The pcre2test program can be linked with any combination of the 8-bit,
+     16-bit and 32-bit libraries (depending on what you selected in
+     src/config.h). Compile src/pcre2test.c; don't forget -DHAVE_CONFIG_H if
+     necessary, but do NOT define PCRE2_CODE_UNIT_WIDTH. Then link with the
+     appropriate library/ies. If you compiled an 8-bit library, pcre2test also
+     needs the pcre2posix wrapper library.
+
+ (9) Run pcre2test on the testinput files in the testdata directory, and check
+     that the output matches the corresponding testoutput files. There are
+     comments about what each test does in the section entitled "Testing PCRE2"
+     in the README file. If you compiled more than one of the 8-bit, 16-bit and
+     32-bit libraries, you need to run pcre2test with the -16 option to do
+     16-bit tests and with the -32 option to do 32-bit tests.
+
+     Some tests are relevant only when certain build-time options are selected.
+     For example, test 4 is for Unicode support, and will not run if you have
+     built PCRE2 without it. See the comments at the start of each testinput
+     file. If you have a suitable Unix-like shell, the RunTest script will run
+     the appropriate tests for you. The command "RunTest list" will output a
+     list of all the tests.
+
+     Note that the supplied files are in Unix format, with just LF characters
+     as line terminators. You may need to edit them to change this if your
+     system uses a different convention.
+
+(10) If you have built PCRE2 with SUPPORT_JIT, the JIT features can be tested
+     by running pcre2test with the -jit option. This is done automatically by
+     the RunTest script. You might also like to build and run the freestanding
+     JIT test program, src/pcre2_jit_test.c.
+
+(11) If you want to use the pcre2grep command, compile and link
+     src/pcre2grep.c; it uses only the basic 8-bit PCRE2 library (it does not
+     need the pcre2posix library). If you have built the PCRE2 library with JIT
+     support by defining SUPPORT_JIT in src/config.h, you can also define
+     SUPPORT_PCRE2GREP_JIT, which causes pcre2grep to make use of JIT (unless
+     it is run with --no-jit). If you define SUPPORT_PCRE2GREP_JIT without
+     defining SUPPORT_JIT, pcre2grep does not try to make use of JIT.
+
+
+STACK SIZE IN WINDOWS ENVIRONMENTS
+
+Prior to release 10.30 the default system stack size of 1MiB in some Windows
+environments caused issues with some tests. This should no longer be the case
+for 10.30 and later releases.
+
+
+LINKING PROGRAMS IN WINDOWS ENVIRONMENTS
+
+If you want to statically link a program against a PCRE2 library in the form of
+a non-dll .a file, you must define PCRE2_STATIC before including src/pcre2.h.
+
+
+CALLING CONVENTIONS IN WINDOWS ENVIRONMENTS
+
+It is possible to compile programs to use different calling conventions using
+MSVC. Search the web for "calling conventions" for more information. To make it
+easier to change the calling convention for the exported functions in the
+PCRE2 library, the macro PCRE2_CALL_CONVENTION is present in all the external
+definitions. It can be set externally when compiling (e.g. in CFLAGS). If it is
+not set, it defaults to empty; the default calling convention is then used
+(which is what is wanted most of the time).
+
+
+COMMENTS ABOUT WIN32 BUILDS (see also "BUILDING PCRE2 ON WINDOWS WITH CMAKE")
+
+There are two ways of building PCRE2 using the "configure, make, make install"
+paradigm on Windows systems: using MinGW or using Cygwin. These are not at all
+the same thing; they are completely different from each other. There is also
+support for building using CMake, which some users find a more straightforward
+way of building PCRE2 under Windows.
+
+The MinGW home page (http://www.mingw.org/) says this:
+
+  MinGW: A collection of freely available and freely distributable Windows
+  specific header files and import libraries combined with GNU toolsets that
+  allow one to produce native Windows programs that do not rely on any
+  3rd-party C runtime DLLs.
+
+The Cygwin home page (http://www.cygwin.com/) says this:
+
+  Cygwin is a Linux-like environment for Windows. It consists of two parts:
+
+  . A DLL (cygwin1.dll) which acts as a Linux API emulation layer providing
+    substantial Linux API functionality
+
+  . A collection of tools which provide Linux look and feel.
+
+On both MinGW and Cygwin, PCRE2 should build correctly using:
+
+  ./configure && make && make install
+
+This should create two libraries called libpcre2-8 and libpcre2-posix. These
+are independent libraries: when you link with libpcre2-posix you must also link
+with libpcre2-8, which contains the basic functions.
+
+Using Cygwin's compiler generates libraries and executables that depend on
+cygwin1.dll. If a library that is generated this way is distributed,
+cygwin1.dll has to be distributed as well. Since cygwin1.dll is under the GPL
+licence, this forces not only PCRE2 to be under the GPL, but also the entire
+application. A distributor who wants to keep their own code proprietary must
+purchase an appropriate Cygwin licence.
+
+MinGW has no such restrictions. The MinGW compiler generates a library or
+executable that can run standalone on Windows without any third party dll or
+licensing issues.
+
+But there is more complication:
+
+If a Cygwin user uses the -mno-cygwin Cygwin gcc flag, what that really does is
+to tell Cygwin's gcc to use the MinGW gcc. Cygwin's gcc is only acting as a
+front end to MinGW's gcc (if you install Cygwin's gcc, you get both Cygwin's
+gcc and MinGW's gcc). So, a user can:
+
+. Build native binaries by using MinGW or by getting Cygwin and using
+  -mno-cygwin.
+
+. Build binaries that depend on cygwin1.dll by using Cygwin with the normal
+  compiler flags.
+
+The test files that are supplied with PCRE2 are in UNIX format, with LF
+characters as line terminators. Unless your PCRE2 library uses a default
+newline option that includes LF as a valid newline, it may be necessary to
+change the line terminators in the test files to get some of the tests to work.
+
+
+BUILDING PCRE2 ON WINDOWS WITH CMAKE
+
+CMake is an alternative configuration facility that can be used instead of
+"configure". CMake creates project files (make files, solution files, etc.)
+tailored to numerous development environments, including Visual Studio,
+Borland, Msys, MinGW, NMake, and Unix. If possible, use short paths with no
+spaces in the names for your CMake installation and your PCRE2 source and build
+directories.
+
+The following instructions were contributed by a PCRE1 user, but they should
+also work for PCRE2. If they are not followed exactly, errors may occur. In the
+event that errors do occur, it is recommended that you delete the CMake cache
+before attempting to repeat the CMake build process. In the CMake GUI, the
+cache can be deleted by selecting "File > Delete Cache".
+
+1.  Install the latest CMake version available from http://www.cmake.org/, and
+    ensure that cmake\bin is on your path.
+
+2.  Unzip (retaining folder structure) the PCRE2 source tree into a source
+    directory such as C:\pcre2. You should ensure your local date and time
+    is not earlier than the file dates in your source dir if the release is
+    very new.
+
+3.  Create a new, empty build directory, preferably a subdirectory of the
+    source dir. For example, C:\pcre2\pcre2-xx\build.
+
+4.  Run cmake-gui from the Shell envirornment of your build tool, for example,
+    Msys for Msys/MinGW or Visual Studio Command Prompt for VC/VC++. Do not try
+    to start Cmake from the Windows Start menu, as this can lead to errors.
+
+5.  Enter C:\pcre2\pcre2-xx and C:\pcre2\pcre2-xx\build for the source and
+    build directories, respectively.
+
+6.  Hit the "Configure" button.
+
+7.  Select the particular IDE / build tool that you are using (Visual
+    Studio, MSYS makefiles, MinGW makefiles, etc.)
+
+8.  The GUI will then list several configuration options. This is where
+    you can disable Unicode support or select other PCRE2 optional features.
+
+9.  Hit "Configure" again. The adjacent "Generate" button should now be
+    active.
+
+10. Hit "Generate".
+
+11. The build directory should now contain a usable build system, be it a
+    solution file for Visual Studio, makefiles for MinGW, etc. Exit from
+    cmake-gui and use the generated build system with your compiler or IDE.
+    E.g., for MinGW you can run "make", or for Visual Studio, open the PCRE2
+    solution, select the desired configuration (Debug, or Release, etc.) and
+    build the ALL_BUILD project.
+
+12. If during configuration with cmake-gui you've elected to build the test
+    programs, you can execute them by building the test project. E.g., for
+    MinGW: "make test"; for Visual Studio build the RUN_TESTS project. The
+    most recent build configuration is targeted by the tests. A summary of
+    test results is presented. Complete test output is subsequently
+    available for review in Testing\Temporary under your build dir.
+
+
+BUILDING PCRE2 ON WINDOWS WITH VISUAL STUDIO
+
+The code currently cannot be compiled without a stdint.h header, which is
+available only in relatively recent versions of Visual Studio. However, this
+portable and permissively-licensed implementation of the header worked without
+issue:
+
+  http://www.azillionmonkeys.com/qed/pstdint.h
+
+Just rename it and drop it into the top level of the build tree.
+
+
+TESTING WITH RUNTEST.BAT
+
+If configured with CMake, building the test project ("make test" or building
+ALL_TESTS in Visual Studio) creates (and runs) pcre2_test.bat (and depending
+on your configuration options, possibly other test programs) in the build
+directory. The pcre2_test.bat script runs RunTest.bat with correct source and
+exe paths.
+
+For manual testing with RunTest.bat, provided the build dir is a subdirectory
+of the source directory: Open command shell window. Chdir to the location
+of your pcre2test.exe and pcre2grep.exe programs. Call RunTest.bat with
+"..\RunTest.Bat" or "..\..\RunTest.bat" as appropriate.
+
+To run only a particular test with RunTest.Bat provide a test number argument.
+
+Otherwise:
+
+1. Copy RunTest.bat into the directory where pcre2test.exe and pcre2grep.exe
+   have been created.
+
+2. Edit RunTest.bat to indentify the full or relative location of
+   the pcre2 source (wherein which the testdata folder resides), e.g.:
+
+   set srcdir=C:\pcre2\pcre2-10.00
+
+3. In a Windows command environment, chdir to the location of your bat and
+   exe programs.
+
+4. Run RunTest.bat. Test outputs will automatically be compared to expected
+   results, and discrepancies will be identified in the console output.
+
+To independently test the just-in-time compiler, run pcre2_jit_test.exe.
+
+
+BUILDING PCRE2 ON NATIVE Z/OS AND Z/VM
+
+z/OS and z/VM are operating systems for mainframe computers, produced by IBM.
+The character code used is EBCDIC, not ASCII or Unicode. In z/OS, UNIX APIs and
+applications can be supported through UNIX System Services, and in such an
+environment it should be possible to build PCRE2 in the same way as in other
+systems, with the EBCDIC related configuration settings, but it is not known if
+anybody has tried this.
+
+In native z/OS (without UNIX System Services) and in z/VM, special ports are
+required. For details, please see file 939 on this web site:
+
+  http://www.cbttape.org
+
+Everything in that location, source and executable, is in EBCDIC and native
+z/OS file formats. The port provides an API for LE languages such as COBOL and
+for the z/OS and z/VM versions of the Rexx languages.
+
+===========================
+Last Updated: 28 April 2021
+===========================

src/regex/pcre2/PrepareRelease

@@ -0,0 +1,236 @@
+#/bin/sh
+
+# Script to prepare the files for building a PCRE2 release. It does some
+# processing of the documentation, detrails files, and creates pcre2.h.generic
+# and config.h.generic (for use by builders who can't run ./configure).
+
+# You must run this script before runnning "make dist". If its first argument
+# is "doc", it stops after preparing the documentation. There are no other
+# arguments. The script makes use of the following files:
+
+# 132html     A Perl script that converts a .1 or .3 man page into HTML. It
+#             "knows" the relevant troff constructs that are used in the PCRE2
+#             man pages.
+
+# CheckMan    A Perl script that checks man pages for typos in the mark up.
+
+# CleanTxt    A Perl script that cleans up the output of "nroff -man" by
+#             removing backspaces and other redundant text so as to produce
+#             a readable .txt file.
+
+# Detrail     A Perl script that removes trailing spaces from files.
+
+# doc/index.html.src
+#             A file that is copied as index.html into the doc/html directory
+#             when the HTML documentation is built. It works like this so that
+#             doc/html can be deleted and re-created from scratch.
+
+# README & NON-AUTOTOOLS-BUILD
+#             These files are copied into the doc/html directory, with .txt
+#             extensions so that they can by hyperlinked from the HTML
+#             documentation, because some people just go to the HTML without
+#             looking for text files.
+
+
+# First, sort out the documentation. Remove pcre2demo.3 first because it won't
+# pass the markup check (it is created below, using markup that none of the
+# other pages use).
+
+cd doc
+echo Processing documentation
+
+/bin/rm -f pcre2demo.3
+
+# Check the remaining man pages
+
+perl ../CheckMan *.1 *.3
+if [ $? != 0 ] ; then exit 1; fi
+
+# Make Text form of the documentation. It needs some mangling to make it
+# tidy for online reading. Concatenate all the .3 stuff, but omit the
+# individual function pages.
+
+cat <<End >pcre2.txt
+-----------------------------------------------------------------------------
+This file contains a concatenation of the PCRE2 man pages, converted to plain
+text format for ease of searching with a text editor, or for use on systems
+that do not have a man page processor. The small individual files that give
+synopses of each function in the library have not been included. Neither has
+the pcre2demo program. There are separate text files for the pcre2grep and
+pcre2test commands.
+-----------------------------------------------------------------------------
+
+
+End
+
+echo "Making pcre2.txt"
+for file in pcre2 pcre2api pcre2build pcre2callout pcre2compat pcre2jit \
+            pcre2limits pcre2matching pcre2partial pcre2pattern pcre2perform \
+            pcre2posix pcre2sample pcre2serialize pcre2syntax \
+            pcre2unicode ; do
+  echo "  Processing $file.3"
+  nroff -c -man $file.3 >$file.rawtxt
+  perl ../CleanTxt <$file.rawtxt >>pcre2.txt
+  /bin/rm $file.rawtxt
+  echo "------------------------------------------------------------------------------" >>pcre2.txt
+  if [ "$file" != "pcre2sample" ] ; then
+    echo " " >>pcre2.txt
+    echo " " >>pcre2.txt
+  fi
+done
+
+# The three commands
+for file in pcre2test pcre2grep pcre2-config ; do
+  echo Making $file.txt
+  nroff -c -man $file.1 >$file.rawtxt
+  perl ../CleanTxt <$file.rawtxt >$file.txt
+  /bin/rm $file.rawtxt
+done
+
+
+# Make pcre2demo.3 from the pcre2demo.c source file
+
+echo "Making pcre2demo.3"
+perl <<"END" >pcre2demo.3
+  open(IN, "../src/pcre2demo.c") || die "Failed to open src/pcre2demo.c\n";
+  open(OUT, ">pcre2demo.3") || die "Failed to open pcre2demo.3\n";
+  print OUT ".\\\" Start example.\n" .
+            ".de EX\n" .
+            ".  nr mE \\\\n(.f\n" .
+            ".  nf\n" .
+            ".  nh\n" .
+            ".  ft CW\n" .
+            "..\n" .
+            ".\n" .
+            ".\n" .
+            ".\\\" End example.\n" .
+            ".de EE\n" .
+            ".  ft \\\\n(mE\n" .
+            ".  fi\n" .
+            ".  hy \\\\n(HY\n" .
+            "..\n" .
+            ".\n" .
+            ".EX\n" ;
+  while (<IN>)
+    {
+    s/\\/\\e/g;
+    print OUT;
+    }
+  print OUT ".EE\n";
+  close(IN);
+  close(OUT);
+END
+if [ $? != 0 ] ; then exit 1; fi
+
+
+# Make HTML form of the documentation.
+
+echo "Making HTML documentation"
+/bin/rm html/*
+cp index.html.src html/index.html
+cp ../README html/README.txt
+cp ../NON-AUTOTOOLS-BUILD html/NON-AUTOTOOLS-BUILD.txt
+
+for file in *.1 ; do
+  base=`basename $file .1`
+  echo "  Making $base.html"
+  perl ../132html -toc $base <$file >html/$base.html
+done
+
+# Exclude table of contents for function summaries. It seems that expr
+# forces an anchored regex. Also exclude them for small pages that have
+# only one section.
+
+for file in *.3 ; do
+  base=`basename $file .3`
+  toc=-toc
+  if [ `expr $base : '.*_'` -ne 0 ] ; then toc="" ; fi
+  if [ "$base" = "pcre2sample" ]  || \
+     [ "$base" = "pcre2compat" ]  || \
+     [ "$base" = "pcre2limits" ]  || \
+     [ "$base" = "pcre2unicode" ] ; then
+    toc=""
+  fi
+  echo "  Making $base.html"
+  perl ../132html $toc $base <$file >html/$base.html
+  if [ $? != 0 ] ; then exit 1; fi
+done
+
+# End of documentation processing; stop if only documentation required.
+
+cd ..
+echo Documentation done
+if [ "$1" = "doc" ] ; then exit; fi
+
+# These files are detrailed; do not detrail the test data because there may be
+# significant trailing spaces. Do not detrail RunTest.bat, because it has CRLF
+# line endings and the detrail script removes all trailing white space. The
+# configure files are also omitted from the detrailing.
+
+files="\
+  Makefile.am \
+  configure.ac \
+  README \
+  LICENCE \
+  COPYING \
+  AUTHORS \
+  NEWS \
+  NON-AUTOTOOLS-BUILD \
+  INSTALL \
+  132html \
+  CleanTxt \
+  Detrail \
+  ChangeLog \
+  CMakeLists.txt \
+  RunGrepTest \
+  RunTest \
+  pcre2-config.in \
+  perltest.sh \
+  libpcre2-8.pc.in \
+  libpcre2-16.pc.in \
+  libpcre2-32.pc.in \
+  libpcre2-posix.pc.in \
+  src/pcre2_dftables.c \
+  src/pcre2.h.in \
+  src/pcre2_auto_possess.c \
+  src/pcre2_compile.c \
+  src/pcre2_config.c \
+  src/pcre2_context.c \
+  src/pcre2_convert.c \
+  src/pcre2_dfa_match.c \
+  src/pcre2_error.c \
+  src/pcre2_extuni.c \
+  src/pcre2_find_bracket.c \
+  src/pcre2_internal.h \
+  src/pcre2_intmodedep.h \
+  src/pcre2_jit_compile.c \
+  src/pcre2_jit_match.c \
+  src/pcre2_jit_misc.c \
+  src/pcre2_jit_test.c \
+  src/pcre2_maketables.c \
+  src/pcre2_match.c \
+  src/pcre2_match_data.c \
+  src/pcre2_newline.c \
+  src/pcre2_ord2utf.c \
+  src/pcre2_pattern_info.c \
+  src/pcre2_printint.c \
+  src/pcre2_string_utils.c \
+  src/pcre2_study.c \
+  src/pcre2_substring.c \
+  src/pcre2_tables.c \
+  src/pcre2_ucd.c \
+  src/pcre2_ucp.h \
+  src/pcre2_valid_utf.c \
+  src/pcre2_xclass.c \
+  src/pcre2demo.c \
+  src/pcre2grep.c \
+  src/pcre2posix.c \
+  src/pcre2posix.h \
+  src/pcre2test.c"
+
+echo Detrailing
+perl ./Detrail $files doc/p* doc/html/*
+
+echo Done
+
+#End

src/regex/pcre2/README

@@ -0,0 +1,907 @@
+README file for PCRE2 (Perl-compatible regular expression library)
+------------------------------------------------------------------
+
+PCRE2 is a re-working of the original PCRE1 library to provide an entirely new
+API. Since its initial release in 2015, there has been further development of
+the code and it now differs from PCRE1 in more than just the API. There are new
+features, and the internals have been improved. The original PCRE1 library is
+now obsolete and should not be used in new projects. The latest release of
+PCRE2 is available in three alternative formats from:
+
+https://ftp.pcre.org/pub/pcre/pcre2-10.xx.tar.gz
+https://ftp.pcre.org/pub/pcre/pcre2-10.xx.tar.bz2
+https://ftp.pcre.org/pub/pcre/pcre2-10.xx.tar.zip
+
+There is a mailing list for discussion about the development of PCRE at
+pcre-dev@exim.org. You can access the archives and subscribe or manage your
+subscription here:
+
+   https://lists.exim.org/mailman/listinfo/pcre-dev
+
+Please read the NEWS file if you are upgrading from a previous release. The
+contents of this README file are:
+
+  The PCRE2 APIs
+  Documentation for PCRE2
+  Contributions by users of PCRE2
+  Building PCRE2 on non-Unix-like systems
+  Building PCRE2 without using autotools
+  Building PCRE2 using autotools
+  Retrieving configuration information
+  Shared libraries
+  Cross-compiling using autotools
+  Making new tarballs
+  Testing PCRE2
+  Character tables
+  File manifest
+
+
+The PCRE2 APIs
+--------------
+
+PCRE2 is written in C, and it has its own API. There are three sets of
+functions, one for the 8-bit library, which processes strings of bytes, one for
+the 16-bit library, which processes strings of 16-bit values, and one for the
+32-bit library, which processes strings of 32-bit values. Unlike PCRE1, there
+are no C++ wrappers.
+
+The distribution does contain a set of C wrapper functions for the 8-bit
+library that are based on the POSIX regular expression API (see the pcre2posix
+man page). These are built into a library called libpcre2-posix. Note that this
+just provides a POSIX calling interface to PCRE2; the regular expressions
+themselves still follow Perl syntax and semantics. The POSIX API is restricted,
+and does not give full access to all of PCRE2's facilities.
+
+The header file for the POSIX-style functions is called pcre2posix.h. The
+official POSIX name is regex.h, but I did not want to risk possible problems
+with existing files of that name by distributing it that way. To use PCRE2 with
+an existing program that uses the POSIX API, pcre2posix.h will have to be
+renamed or pointed at by a link (or the program modified, of course). See the
+pcre2posix documentation for more details.
+
+
+Documentation for PCRE2
+-----------------------
+
+If you install PCRE2 in the normal way on a Unix-like system, you will end up
+with a set of man pages whose names all start with "pcre2". The one that is
+just called "pcre2" lists all the others. In addition to these man pages, the
+PCRE2 documentation is supplied in two other forms:
+
+  1. There are files called doc/pcre2.txt, doc/pcre2grep.txt, and
+     doc/pcre2test.txt in the source distribution. The first of these is a
+     concatenation of the text forms of all the section 3 man pages except the
+     listing of pcre2demo.c and those that summarize individual functions. The
+     other two are the text forms of the section 1 man pages for the pcre2grep
+     and pcre2test commands. These text forms are provided for ease of scanning
+     with text editors or similar tools. They are installed in
+     <prefix>/share/doc/pcre2, where <prefix> is the installation prefix
+     (defaulting to /usr/local).
+
+  2. A set of files containing all the documentation in HTML form, hyperlinked
+     in various ways, and rooted in a file called index.html, is distributed in
+     doc/html and installed in <prefix>/share/doc/pcre2/html.
+
+
+Building PCRE2 on non-Unix-like systems
+---------------------------------------
+
+For a non-Unix-like system, please read the file NON-AUTOTOOLS-BUILD, though if
+your system supports the use of "configure" and "make" you may be able to build
+PCRE2 using autotools in the same way as for many Unix-like systems.
+
+PCRE2 can also be configured using CMake, which can be run in various ways
+(command line, GUI, etc). This creates Makefiles, solution files, etc. The file
+NON-AUTOTOOLS-BUILD has information about CMake.
+
+PCRE2 has been compiled on many different operating systems. It should be
+straightforward to build PCRE2 on any system that has a Standard C compiler and
+library, because it uses only Standard C functions.
+
+
+Building PCRE2 without using autotools
+--------------------------------------
+
+The use of autotools (in particular, libtool) is problematic in some
+environments, even some that are Unix or Unix-like. See the NON-AUTOTOOLS-BUILD
+file for ways of building PCRE2 without using autotools.
+
+
+Building PCRE2 using autotools
+------------------------------
+
+The following instructions assume the use of the widely used "configure; make;
+make install" (autotools) process.
+
+To build PCRE2 on system that supports autotools, first run the "configure"
+command from the PCRE2 distribution directory, with your current directory set
+to the directory where you want the files to be created. This command is a
+standard GNU "autoconf" configuration script, for which generic instructions
+are supplied in the file INSTALL.
+
+Most commonly, people build PCRE2 within its own distribution directory, and in
+this case, on many systems, just running "./configure" is sufficient. However,
+the usual methods of changing standard defaults are available. For example:
+
+CFLAGS='-O2 -Wall' ./configure --prefix=/opt/local
+
+This command specifies that the C compiler should be run with the flags '-O2
+-Wall' instead of the default, and that "make install" should install PCRE2
+under /opt/local instead of the default /usr/local.
+
+If you want to build in a different directory, just run "configure" with that
+directory as current. For example, suppose you have unpacked the PCRE2 source
+into /source/pcre2/pcre2-xxx, but you want to build it in
+/build/pcre2/pcre2-xxx:
+
+cd /build/pcre2/pcre2-xxx
+/source/pcre2/pcre2-xxx/configure
+
+PCRE2 is written in C and is normally compiled as a C library. However, it is
+possible to build it as a C++ library, though the provided building apparatus
+does not have any features to support this.
+
+There are some optional features that can be included or omitted from the PCRE2
+library. They are also documented in the pcre2build man page.
+
+. By default, both shared and static libraries are built. You can change this
+  by adding one of these options to the "configure" command:
+
+  --disable-shared
+  --disable-static
+
+  (See also "Shared libraries on Unix-like systems" below.)
+
+. By default, only the 8-bit library is built. If you add --enable-pcre2-16 to
+  the "configure" command, the 16-bit library is also built. If you add
+  --enable-pcre2-32 to the "configure" command, the 32-bit library is also
+  built. If you want only the 16-bit or 32-bit library, use --disable-pcre2-8
+  to disable building the 8-bit library.
+
+. If you want to include support for just-in-time (JIT) compiling, which can
+  give large performance improvements on certain platforms, add --enable-jit to
+  the "configure" command. This support is available only for certain hardware
+  architectures. If you try to enable it on an unsupported architecture, there
+  will be a compile time error. If in doubt, use --enable-jit=auto, which
+  enables JIT only if the current hardware is supported.
+
+. If you are enabling JIT under SELinux environment you may also want to add
+  --enable-jit-sealloc, which enables the use of an executable memory allocator
+  that is compatible with SELinux. Warning: this allocator is experimental!
+  It does not support fork() operation and may crash when no disk space is
+  available. This option has no effect if JIT is disabled.
+
+. If you do not want to make use of the default support for UTF-8 Unicode
+  character strings in the 8-bit library, UTF-16 Unicode character strings in
+  the 16-bit library, or UTF-32 Unicode character strings in the 32-bit
+  library, you can add --disable-unicode to the "configure" command. This
+  reduces the size of the libraries. It is not possible to configure one
+  library with Unicode support, and another without, in the same configuration.
+  It is also not possible to use --enable-ebcdic (see below) with Unicode
+  support, so if this option is set, you must also use --disable-unicode.
+
+  When Unicode support is available, the use of a UTF encoding still has to be
+  enabled by setting the PCRE2_UTF option at run time or starting a pattern
+  with (*UTF). When PCRE2 is compiled with Unicode support, its input can only
+  either be ASCII or UTF-8/16/32, even when running on EBCDIC platforms.
+
+  As well as supporting UTF strings, Unicode support includes support for the
+  \P, \p, and \X sequences that recognize Unicode character properties.
+  However, only the basic two-letter properties such as Lu are supported.
+  Escape sequences such as \d and \w in patterns do not by default make use of
+  Unicode properties, but can be made to do so by setting the PCRE2_UCP option
+  or starting a pattern with (*UCP).
+
+. You can build PCRE2 to recognize either CR or LF or the sequence CRLF, or any
+  of the preceding, or any of the Unicode newline sequences, or the NUL (zero)
+  character as indicating the end of a line. Whatever you specify at build time
+  is the default; the caller of PCRE2 can change the selection at run time. The
+  default newline indicator is a single LF character (the Unix standard). You
+  can specify the default newline indicator by adding --enable-newline-is-cr,
+  --enable-newline-is-lf, --enable-newline-is-crlf,
+  --enable-newline-is-anycrlf, --enable-newline-is-any, or
+  --enable-newline-is-nul to the "configure" command, respectively.
+
+. By default, the sequence \R in a pattern matches any Unicode line ending
+  sequence. This is independent of the option specifying what PCRE2 considers
+  to be the end of a line (see above). However, the caller of PCRE2 can
+  restrict \R to match only CR, LF, or CRLF. You can make this the default by
+  adding --enable-bsr-anycrlf to the "configure" command (bsr = "backslash R").
+
+. In a pattern, the escape sequence \C matches a single code unit, even in a
+  UTF mode. This can be dangerous because it breaks up multi-code-unit
+  characters. You can build PCRE2 with the use of \C permanently locked out by
+  adding --enable-never-backslash-C (note the upper case C) to the "configure"
+  command. When \C is allowed by the library, individual applications can lock
+  it out by calling pcre2_compile() with the PCRE2_NEVER_BACKSLASH_C option.
+
+. PCRE2 has a counter that limits the depth of nesting of parentheses in a
+  pattern. This limits the amount of system stack that a pattern uses when it
+  is compiled. The default is 250, but you can change it by setting, for
+  example,
+
+  --with-parens-nest-limit=500
+
+. PCRE2 has a counter that can be set to limit the amount of computing resource
+  it uses when matching a pattern. If the limit is exceeded during a match, the
+  match fails. The default is ten million. You can change the default by
+  setting, for example,
+
+  --with-match-limit=500000
+
+  on the "configure" command. This is just the default; individual calls to
+  pcre2_match() or pcre2_dfa_match() can supply their own value. There is more
+  discussion in the pcre2api man page (search for pcre2_set_match_limit).
+
+. There is a separate counter that limits the depth of nested backtracking
+  (pcre2_match()) or nested function calls (pcre2_dfa_match()) during a
+  matching process, which indirectly limits the amount of heap memory that is
+  used, and in the case of pcre2_dfa_match() the amount of stack as well. This
+  counter also has a default of ten million, which is essentially "unlimited".
+  You can change the default by setting, for example,
+
+  --with-match-limit-depth=5000
+
+  There is more discussion in the pcre2api man page (search for
+  pcre2_set_depth_limit).
+
+. You can also set an explicit limit on the amount of heap memory used by
+  the pcre2_match() and pcre2_dfa_match() interpreters:
+
+  --with-heap-limit=500
+
+  The units are kibibytes (units of 1024 bytes). This limit does not apply when
+  the JIT optimization (which has its own memory control features) is used.
+  There is more discussion on the pcre2api man page (search for
+  pcre2_set_heap_limit).
+
+. In the 8-bit library, the default maximum compiled pattern size is around
+  64 kibibytes. You can increase this by adding --with-link-size=3 to the
+  "configure" command. PCRE2 then uses three bytes instead of two for offsets
+  to different parts of the compiled pattern. In the 16-bit library,
+  --with-link-size=3 is the same as --with-link-size=4, which (in both
+  libraries) uses four-byte offsets. Increasing the internal link size reduces
+  performance in the 8-bit and 16-bit libraries. In the 32-bit library, the
+  link size setting is ignored, as 4-byte offsets are always used.
+
+. For speed, PCRE2 uses four tables for manipulating and identifying characters
+  whose code point values are less than 256. By default, it uses a set of
+  tables for ASCII encoding that is part of the distribution. If you specify
+
+  --enable-rebuild-chartables
+
+  a program called pcre2_dftables is compiled and run in the default C locale
+  when you obey "make". It builds a source file called pcre2_chartables.c. If
+  you do not specify this option, pcre2_chartables.c is created as a copy of
+  pcre2_chartables.c.dist. See "Character tables" below for further
+  information.
+
+. It is possible to compile PCRE2 for use on systems that use EBCDIC as their
+  character code (as opposed to ASCII/Unicode) by specifying
+
+  --enable-ebcdic --disable-unicode
+
+  This automatically implies --enable-rebuild-chartables (see above). However,
+  when PCRE2 is built this way, it always operates in EBCDIC. It cannot support
+  both EBCDIC and UTF-8/16/32. There is a second option, --enable-ebcdic-nl25,
+  which specifies that the code value for the EBCDIC NL character is 0x25
+  instead of the default 0x15.
+
+. If you specify --enable-debug, additional debugging code is included in the
+  build. This option is intended for use by the PCRE2 maintainers.
+
+. In environments where valgrind is installed, if you specify
+
+  --enable-valgrind
+
+  PCRE2 will use valgrind annotations to mark certain memory regions as
+  unaddressable. This allows it to detect invalid memory accesses, and is
+  mostly useful for debugging PCRE2 itself.
+
+. In environments where the gcc compiler is used and lcov is installed, if you
+  specify
+
+  --enable-coverage
+
+  the build process implements a code coverage report for the test suite. The
+  report is generated by running "make coverage". If ccache is installed on
+  your system, it must be disabled when building PCRE2 for coverage reporting.
+  You can do this by setting the environment variable CCACHE_DISABLE=1 before
+  running "make" to build PCRE2. There is more information about coverage
+  reporting in the "pcre2build" documentation.
+
+. When JIT support is enabled, pcre2grep automatically makes use of it, unless
+  you add --disable-pcre2grep-jit to the "configure" command.
+
+. There is support for calling external programs during matching in the
+  pcre2grep command, using PCRE2's callout facility with string arguments. This
+  support can be disabled by adding --disable-pcre2grep-callout to the
+  "configure" command. There are two kinds of callout: one that generates
+  output from inbuilt code, and another that calls an external program. The
+  latter has special support for Windows and VMS; otherwise it assumes the
+  existence of the fork() function. This facility can be disabled by adding
+  --disable-pcre2grep-callout-fork to the "configure" command.
+
+. The pcre2grep program currently supports only 8-bit data files, and so
+  requires the 8-bit PCRE2 library. It is possible to compile pcre2grep to use
+  libz and/or libbz2, in order to read .gz and .bz2 files (respectively), by
+  specifying one or both of
+
+  --enable-pcre2grep-libz
+  --enable-pcre2grep-libbz2
+
+  Of course, the relevant libraries must be installed on your system.
+
+. The default starting size (in bytes) of the internal buffer used by pcre2grep
+  can be set by, for example:
+
+  --with-pcre2grep-bufsize=51200
+
+  The value must be a plain integer. The default is 20480. The amount of memory
+  used by pcre2grep is actually three times this number, to allow for "before"
+  and "after" lines. If very long lines are encountered, the buffer is
+  automatically enlarged, up to a fixed maximum size.
+
+. The default maximum size of pcre2grep's internal buffer can be set by, for
+  example:
+
+  --with-pcre2grep-max-bufsize=2097152
+
+  The default is either 1048576 or the value of --with-pcre2grep-bufsize,
+  whichever is the larger.
+
+. It is possible to compile pcre2test so that it links with the libreadline
+  or libedit libraries, by specifying, respectively,
+
+  --enable-pcre2test-libreadline or --enable-pcre2test-libedit
+
+  If this is done, when pcre2test's input is from a terminal, it reads it using
+  the readline() function. This provides line-editing and history facilities.
+  Note that libreadline is GPL-licenced, so if you distribute a binary of
+  pcre2test linked in this way, there may be licensing issues. These can be
+  avoided by linking with libedit (which has a BSD licence) instead.
+
+  Enabling libreadline causes the -lreadline option to be added to the
+  pcre2test build. In many operating environments with a sytem-installed
+  readline library this is sufficient. However, in some environments (e.g. if
+  an unmodified distribution version of readline is in use), it may be
+  necessary to specify something like LIBS="-lncurses" as well. This is
+  because, to quote the readline INSTALL, "Readline uses the termcap functions,
+  but does not link with the termcap or curses library itself, allowing
+  applications which link with readline the to choose an appropriate library."
+  If you get error messages about missing functions tgetstr, tgetent, tputs,
+  tgetflag, or tgoto, this is the problem, and linking with the ncurses library
+  should fix it.
+
+. The C99 standard defines formatting modifiers z and t for size_t and
+  ptrdiff_t values, respectively. By default, PCRE2 uses these modifiers in
+  environments other than Microsoft Visual Studio when __STDC_VERSION__ is
+  defined and has a value greater than or equal to 199901L (indicating C99).
+  However, there is at least one environment that claims to be C99 but does not
+  support these modifiers. If --disable-percent-zt is specified, no use is made
+  of the z or t modifiers. Instead or %td or %zu, %lu is used, with a cast for
+  size_t values.
+
+. There is a special option called --enable-fuzz-support for use by people who
+  want to run fuzzing tests on PCRE2. At present this applies only to the 8-bit
+  library. If set, it causes an extra library called libpcre2-fuzzsupport.a to
+  be built, but not installed. This contains a single function called
+  LLVMFuzzerTestOneInput() whose arguments are a pointer to a string and the
+  length of the string. When called, this function tries to compile the string
+  as a pattern, and if that succeeds, to match it. This is done both with no
+  options and with some random options bits that are generated from the string.
+  Setting --enable-fuzz-support also causes a binary called pcre2fuzzcheck to
+  be created. This is normally run under valgrind or used when PCRE2 is
+  compiled with address sanitizing enabled. It calls the fuzzing function and
+  outputs information about it is doing. The input strings are specified by
+  arguments: if an argument starts with "=" the rest of it is a literal input
+  string. Otherwise, it is assumed to be a file name, and the contents of the
+  file are the test string.
+
+. Releases before 10.30 could be compiled with --disable-stack-for-recursion,
+  which caused pcre2_match() to use individual blocks on the heap for
+  backtracking instead of recursive function calls (which use the stack). This
+  is now obsolete since pcre2_match() was refactored always to use the heap (in
+  a much more efficient way than before). This option is retained for backwards
+  compatibility, but has no effect other than to output a warning.
+
+The "configure" script builds the following files for the basic C library:
+
+. Makefile             the makefile that builds the library
+. src/config.h         build-time configuration options for the library
+. src/pcre2.h          the public PCRE2 header file
+. pcre2-config          script that shows the building settings such as CFLAGS
+                         that were set for "configure"
+. libpcre2-8.pc        )
+. libpcre2-16.pc       ) data for the pkg-config command
+. libpcre2-32.pc       )
+. libpcre2-posix.pc    )
+. libtool              script that builds shared and/or static libraries
+
+Versions of config.h and pcre2.h are distributed in the src directory of PCRE2
+tarballs under the names config.h.generic and pcre2.h.generic. These are
+provided for those who have to build PCRE2 without using "configure" or CMake.
+If you use "configure" or CMake, the .generic versions are not used.
+
+The "configure" script also creates config.status, which is an executable
+script that can be run to recreate the configuration, and config.log, which
+contains compiler output from tests that "configure" runs.
+
+Once "configure" has run, you can run "make". This builds whichever of the
+libraries libpcre2-8, libpcre2-16 and libpcre2-32 are configured, and a test
+program called pcre2test. If you enabled JIT support with --enable-jit, another
+test program called pcre2_jit_test is built as well. If the 8-bit library is
+built, libpcre2-posix and the pcre2grep command are also built. Running
+"make" with the -j option may speed up compilation on multiprocessor systems.
+
+The command "make check" runs all the appropriate tests. Details of the PCRE2
+tests are given below in a separate section of this document. The -j option of
+"make" can also be used when running the tests.
+
+You can use "make install" to install PCRE2 into live directories on your
+system. The following are installed (file names are all relative to the
+<prefix> that is set when "configure" is run):
+
+  Commands (bin):
+    pcre2test
+    pcre2grep (if 8-bit support is enabled)
+    pcre2-config
+
+  Libraries (lib):
+    libpcre2-8      (if 8-bit support is enabled)
+    libpcre2-16     (if 16-bit support is enabled)
+    libpcre2-32     (if 32-bit support is enabled)
+    libpcre2-posix  (if 8-bit support is enabled)
+
+  Configuration information (lib/pkgconfig):
+    libpcre2-8.pc
+    libpcre2-16.pc
+    libpcre2-32.pc
+    libpcre2-posix.pc
+
+  Header files (include):
+    pcre2.h
+    pcre2posix.h
+
+  Man pages (share/man/man{1,3}):
+    pcre2grep.1
+    pcre2test.1
+    pcre2-config.1
+    pcre2.3
+    pcre2*.3 (lots more pages, all starting "pcre2")
+
+  HTML documentation (share/doc/pcre2/html):
+    index.html
+    *.html (lots more pages, hyperlinked from index.html)
+
+  Text file documentation (share/doc/pcre2):
+    AUTHORS
+    COPYING
+    ChangeLog
+    LICENCE
+    NEWS
+    README
+    pcre2.txt         (a concatenation of the man(3) pages)
+    pcre2test.txt     the pcre2test man page
+    pcre2grep.txt     the pcre2grep man page
+    pcre2-config.txt  the pcre2-config man page
+
+If you want to remove PCRE2 from your system, you can run "make uninstall".
+This removes all the files that "make install" installed. However, it does not
+remove any directories, because these are often shared with other programs.
+
+
+Retrieving configuration information
+------------------------------------
+
+Running "make install" installs the command pcre2-config, which can be used to
+recall information about the PCRE2 configuration and installation. For example:
+
+  pcre2-config --version
+
+prints the version number, and
+
+  pcre2-config --libs8
+
+outputs information about where the 8-bit library is installed. This command
+can be included in makefiles for programs that use PCRE2, saving the programmer
+from having to remember too many details. Run pcre2-config with no arguments to
+obtain a list of possible arguments.
+
+The pkg-config command is another system for saving and retrieving information
+about installed libraries. Instead of separate commands for each library, a
+single command is used. For example:
+
+  pkg-config --libs libpcre2-16
+
+The data is held in *.pc files that are installed in a directory called
+<prefix>/lib/pkgconfig.
+
+
+Shared libraries
+----------------
+
+The default distribution builds PCRE2 as shared libraries and static libraries,
+as long as the operating system supports shared libraries. Shared library
+support relies on the "libtool" script which is built as part of the
+"configure" process.
+
+The libtool script is used to compile and link both shared and static
+libraries. They are placed in a subdirectory called .libs when they are newly
+built. The programs pcre2test and pcre2grep are built to use these uninstalled
+libraries (by means of wrapper scripts in the case of shared libraries). When
+you use "make install" to install shared libraries, pcre2grep and pcre2test are
+automatically re-built to use the newly installed shared libraries before being
+installed themselves. However, the versions left in the build directory still
+use the uninstalled libraries.
+
+To build PCRE2 using static libraries only you must use --disable-shared when
+configuring it. For example:
+
+./configure --prefix=/usr/gnu --disable-shared
+
+Then run "make" in the usual way. Similarly, you can use --disable-static to
+build only shared libraries.
+
+
+Cross-compiling using autotools
+-------------------------------
+
+You can specify CC and CFLAGS in the normal way to the "configure" command, in
+order to cross-compile PCRE2 for some other host. However, you should NOT
+specify --enable-rebuild-chartables, because if you do, the pcre2_dftables.c
+source file is compiled and run on the local host, in order to generate the
+inbuilt character tables (the pcre2_chartables.c file). This will probably not
+work, because pcre2_dftables.c needs to be compiled with the local compiler,
+not the cross compiler.
+
+When --enable-rebuild-chartables is not specified, pcre2_chartables.c is
+created by making a copy of pcre2_chartables.c.dist, which is a default set of
+tables that assumes ASCII code. Cross-compiling with the default tables should
+not be a problem.
+
+If you need to modify the character tables when cross-compiling, you should
+move pcre2_chartables.c.dist out of the way, then compile pcre2_dftables.c by
+hand and run it on the local host to make a new version of
+pcre2_chartables.c.dist. See the pcre2build section "Creating character tables
+at build time" for more details.
+
+
+Making new tarballs
+-------------------
+
+The command "make dist" creates three PCRE2 tarballs, in tar.gz, tar.bz2, and
+zip formats. The command "make distcheck" does the same, but then does a trial
+build of the new distribution to ensure that it works.
+
+If you have modified any of the man page sources in the doc directory, you
+should first run the PrepareRelease script before making a distribution. This
+script creates the .txt and HTML forms of the documentation from the man pages.
+
+
+Testing PCRE2
+-------------
+
+To test the basic PCRE2 library on a Unix-like system, run the RunTest script.
+There is another script called RunGrepTest that tests the pcre2grep command.
+When JIT support is enabled, a third test program called pcre2_jit_test is
+built. Both the scripts and all the program tests are run if you obey "make
+check". For other environments, see the instructions in NON-AUTOTOOLS-BUILD.
+
+The RunTest script runs the pcre2test test program (which is documented in its
+own man page) on each of the relevant testinput files in the testdata
+directory, and compares the output with the contents of the corresponding
+testoutput files. RunTest uses a file called testtry to hold the main output
+from pcre2test. Other files whose names begin with "test" are used as working
+files in some tests.
+
+Some tests are relevant only when certain build-time options were selected. For
+example, the tests for UTF-8/16/32 features are run only when Unicode support
+is available. RunTest outputs a comment when it skips a test.
+
+Many (but not all) of the tests that are not skipped are run twice if JIT
+support is available. On the second run, JIT compilation is forced. This
+testing can be suppressed by putting "nojit" on the RunTest command line.
+
+The entire set of tests is run once for each of the 8-bit, 16-bit and 32-bit
+libraries that are enabled. If you want to run just one set of tests, call
+RunTest with either the -8, -16 or -32 option.
+
+If valgrind is installed, you can run the tests under it by putting "valgrind"
+on the RunTest command line. To run pcre2test on just one or more specific test
+files, give their numbers as arguments to RunTest, for example:
+
+  RunTest 2 7 11
+
+You can also specify ranges of tests such as 3-6 or 3- (meaning 3 to the
+end), or a number preceded by ~ to exclude a test. For example:
+
+  Runtest 3-15 ~10
+
+This runs tests 3 to 15, excluding test 10, and just ~13 runs all the tests
+except test 13. Whatever order the arguments are in, the tests are always run
+in numerical order.
+
+You can also call RunTest with the single argument "list" to cause it to output
+a list of tests.
+
+The test sequence starts with "test 0", which is a special test that has no
+input file, and whose output is not checked. This is because it will be
+different on different hardware and with different configurations. The test
+exists in order to exercise some of pcre2test's code that would not otherwise
+be run.
+
+Tests 1 and 2 can always be run, as they expect only plain text strings (not
+UTF) and make no use of Unicode properties. The first test file can be fed
+directly into the perltest.sh script to check that Perl gives the same results.
+The only difference you should see is in the first few lines, where the Perl
+version is given instead of the PCRE2 version. The second set of tests check
+auxiliary functions, error detection, and run-time flags that are specific to
+PCRE2. It also uses the debugging flags to check some of the internals of
+pcre2_compile().
+
+If you build PCRE2 with a locale setting that is not the standard C locale, the
+character tables may be different (see next paragraph). In some cases, this may
+cause failures in the second set of tests. For example, in a locale where the
+isprint() function yields TRUE for characters in the range 128-255, the use of
+[:isascii:] inside a character class defines a different set of characters, and
+this shows up in this test as a difference in the compiled code, which is being
+listed for checking. For example, where the comparison test output contains
+[\x00-\x7f] the test might contain [\x00-\xff], and similarly in some other
+cases. This is not a bug in PCRE2.
+
+Test 3 checks pcre2_maketables(), the facility for building a set of character
+tables for a specific locale and using them instead of the default tables. The
+script uses the "locale" command to check for the availability of the "fr_FR",
+"french", or "fr" locale, and uses the first one that it finds. If the "locale"
+command fails, or if its output doesn't include "fr_FR", "french", or "fr" in
+the list of available locales, the third test cannot be run, and a comment is
+output to say why. If running this test produces an error like this:
+
+  ** Failed to set locale "fr_FR"
+
+it means that the given locale is not available on your system, despite being
+listed by "locale". This does not mean that PCRE2 is broken. There are three
+alternative output files for the third test, because three different versions
+of the French locale have been encountered. The test passes if its output
+matches any one of them.
+
+Tests 4 and 5 check UTF and Unicode property support, test 4 being compatible
+with the perltest.sh script, and test 5 checking PCRE2-specific things.
+
+Tests 6 and 7 check the pcre2_dfa_match() alternative matching function, in
+non-UTF mode and UTF-mode with Unicode property support, respectively.
+
+Test 8 checks some internal offsets and code size features, but it is run only
+when Unicode support is enabled. The output is different in 8-bit, 16-bit, and
+32-bit modes and for different link sizes, so there are different output files
+for each mode and link size.
+
+Tests 9 and 10 are run only in 8-bit mode, and tests 11 and 12 are run only in
+16-bit and 32-bit modes. These are tests that generate different output in
+8-bit mode. Each pair are for general cases and Unicode support, respectively.
+
+Test 13 checks the handling of non-UTF characters greater than 255 by
+pcre2_dfa_match() in 16-bit and 32-bit modes.
+
+Test 14 contains some special UTF and UCP tests that give different output for
+different code unit widths.
+
+Test 15 contains a number of tests that must not be run with JIT. They check,
+among other non-JIT things, the match-limiting features of the intepretive
+matcher.
+
+Test 16 is run only when JIT support is not available. It checks that an
+attempt to use JIT has the expected behaviour.
+
+Test 17 is run only when JIT support is available. It checks JIT complete and
+partial modes, match-limiting under JIT, and other JIT-specific features.
+
+Tests 18 and 19 are run only in 8-bit mode. They check the POSIX interface to
+the 8-bit library, without and with Unicode support, respectively.
+
+Test 20 checks the serialization functions by writing a set of compiled
+patterns to a file, and then reloading and checking them.
+
+Tests 21 and 22 test \C support when the use of \C is not locked out, without
+and with UTF support, respectively. Test 23 tests \C when it is locked out.
+
+Tests 24 and 25 test the experimental pattern conversion functions, without and
+with UTF support, respectively.
+
+
+Character tables
+----------------
+
+For speed, PCRE2 uses four tables for manipulating and identifying characters
+whose code point values are less than 256. By default, a set of tables that is
+built into the library is used. The pcre2_maketables() function can be called
+by an application to create a new set of tables in the current locale. This are
+passed to PCRE2 by calling pcre2_set_character_tables() to put a pointer into a
+compile context.
+
+The source file called pcre2_chartables.c contains the default set of tables.
+By default, this is created as a copy of pcre2_chartables.c.dist, which
+contains tables for ASCII coding. However, if --enable-rebuild-chartables is
+specified for ./configure, a new version of pcre2_chartables.c is built by the
+program pcre2_dftables (compiled from pcre2_dftables.c), which uses the ANSI C
+character handling functions such as isalnum(), isalpha(), isupper(),
+islower(), etc. to build the table sources. This means that the default C
+locale that is set for your system will control the contents of these default
+tables. You can change the default tables by editing pcre2_chartables.c and
+then re-building PCRE2. If you do this, you should take care to ensure that the
+file does not get automatically re-generated. The best way to do this is to
+move pcre2_chartables.c.dist out of the way and replace it with your customized
+tables.
+
+When the pcre2_dftables program is run as a result of specifying
+--enable-rebuild-chartables, it uses the default C locale that is set on your
+system. It does not pay attention to the LC_xxx environment variables. In other
+words, it uses the system's default locale rather than whatever the compiling
+user happens to have set. If you really do want to build a source set of
+character tables in a locale that is specified by the LC_xxx variables, you can
+run the pcre2_dftables program by hand with the -L option. For example:
+
+  ./pcre2_dftables -L pcre2_chartables.c.special
+
+The second argument names the file where the source code for the tables is
+written. The first two 256-byte tables provide lower casing and case flipping
+functions, respectively. The next table consists of a number of 32-byte bit
+maps which identify certain character classes such as digits, "word"
+characters, white space, etc. These are used when building 32-byte bit maps
+that represent character classes for code points less than 256. The final
+256-byte table has bits indicating various character types, as follows:
+
+    1   white space character
+    2   letter
+    4   lower case letter
+    8   decimal digit
+   16   alphanumeric or '_'
+
+You can also specify -b (with or without -L) when running pcre2_dftables. This
+causes the tables to be written in binary instead of as source code. A set of
+binary tables can be loaded into memory by an application and passed to
+pcre2_compile() in the same way as tables created dynamically by calling
+pcre2_maketables(). The tables are just a string of bytes, independent of
+hardware characteristics such as endianness. This means they can be bundled
+with an application that runs in different environments, to ensure consistent
+behaviour.
+
+See also the pcre2build section "Creating character tables at build time".
+
+
+File manifest
+-------------
+
+The distribution should contain the files listed below.
+
+(A) Source files for the PCRE2 library functions and their headers are found in
+    the src directory:
+
+  src/pcre2_dftables.c     auxiliary program for building pcre2_chartables.c
+                           when --enable-rebuild-chartables is specified
+
+  src/pcre2_chartables.c.dist  a default set of character tables that assume
+                           ASCII coding; unless --enable-rebuild-chartables is
+                           specified, used by copying to pcre2_chartables.c
+
+  src/pcre2posix.c         )
+  src/pcre2_auto_possess.c )
+  src/pcre2_compile.c      )
+  src/pcre2_config.c       )
+  src/pcre2_context.c      )
+  src/pcre2_convert.c      )
+  src/pcre2_dfa_match.c    )
+  src/pcre2_error.c        )
+  src/pcre2_extuni.c       )
+  src/pcre2_find_bracket.c )
+  src/pcre2_jit_compile.c  )
+  src/pcre2_jit_match.c    ) sources for the functions in the library,
+  src/pcre2_jit_misc.c     )   and some internal functions that they use
+  src/pcre2_maketables.c   )
+  src/pcre2_match.c        )
+  src/pcre2_match_data.c   )
+  src/pcre2_newline.c      )
+  src/pcre2_ord2utf.c      )
+  src/pcre2_pattern_info.c )
+  src/pcre2_script_run.c   )
+  src/pcre2_serialize.c    )
+  src/pcre2_string_utils.c )
+  src/pcre2_study.c        )
+  src/pcre2_substitute.c   )
+  src/pcre2_substring.c    )
+  src/pcre2_tables.c       )
+  src/pcre2_ucd.c          )
+  src/pcre2_valid_utf.c    )
+  src/pcre2_xclass.c       )
+
+  src/pcre2_printint.c     debugging function that is used by pcre2test,
+  src/pcre2_fuzzsupport.c  function for (optional) fuzzing support
+
+  src/config.h.in          template for config.h, when built by "configure"
+  src/pcre2.h.in           template for pcre2.h when built by "configure"
+  src/pcre2posix.h         header for the external POSIX wrapper API
+  src/pcre2_internal.h     header for internal use
+  src/pcre2_intmodedep.h   a mode-specific internal header
+  src/pcre2_ucp.h          header for Unicode property handling
+
+  sljit/*                  source files for the JIT compiler
+
+(B) Source files for programs that use PCRE2:
+
+  src/pcre2demo.c          simple demonstration of coding calls to PCRE2
+  src/pcre2grep.c          source of a grep utility that uses PCRE2
+  src/pcre2test.c          comprehensive test program
+  src/pcre2_jit_test.c     JIT test program
+
+(C) Auxiliary files:
+
+  132html                  script to turn "man" pages into HTML
+  AUTHORS                  information about the author of PCRE2
+  ChangeLog                log of changes to the code
+  CleanTxt                 script to clean nroff output for txt man pages
+  Detrail                  script to remove trailing spaces
+  HACKING                  some notes about the internals of PCRE2
+  INSTALL                  generic installation instructions
+  LICENCE                  conditions for the use of PCRE2
+  COPYING                  the same, using GNU's standard name
+  Makefile.in              ) template for Unix Makefile, which is built by
+                           )   "configure"
+  Makefile.am              ) the automake input that was used to create
+                           )   Makefile.in
+  NEWS                     important changes in this release
+  NON-AUTOTOOLS-BUILD      notes on building PCRE2 without using autotools
+  PrepareRelease           script to make preparations for "make dist"
+  README                   this file
+  RunTest                  a Unix shell script for running tests
+  RunGrepTest              a Unix shell script for pcre2grep tests
+  aclocal.m4               m4 macros (generated by "aclocal")
+  config.guess             ) files used by libtool,
+  config.sub               )   used only when building a shared library
+  configure                a configuring shell script (built by autoconf)
+  configure.ac             ) the autoconf input that was used to build
+                           )   "configure" and config.h
+  depcomp                  ) script to find program dependencies, generated by
+                           )   automake
+  doc/*.3                  man page sources for PCRE2
+  doc/*.1                  man page sources for pcre2grep and pcre2test
+  doc/index.html.src       the base HTML page
+  doc/html/*               HTML documentation
+  doc/pcre2.txt            plain text version of the man pages
+  doc/pcre2test.txt        plain text documentation of test program
+  install-sh               a shell script for installing files
+  libpcre2-8.pc.in         template for libpcre2-8.pc for pkg-config
+  libpcre2-16.pc.in        template for libpcre2-16.pc for pkg-config
+  libpcre2-32.pc.in        template for libpcre2-32.pc for pkg-config
+  libpcre2-posix.pc.in     template for libpcre2-posix.pc for pkg-config
+  ltmain.sh                file used to build a libtool script
+  missing                  ) common stub for a few missing GNU programs while
+                           )   installing, generated by automake
+  mkinstalldirs            script for making install directories
+  perltest.sh              Script for running a Perl test program
+  pcre2-config.in          source of script which retains PCRE2 information
+  testdata/testinput*      test data for main library tests
+  testdata/testoutput*     expected test results
+  testdata/grep*           input and output for pcre2grep tests
+  testdata/*               other supporting test files
+
+(D) Auxiliary files for cmake support
+
+  cmake/COPYING-CMAKE-SCRIPTS
+  cmake/FindPackageHandleStandardArgs.cmake
+  cmake/FindEditline.cmake
+  cmake/FindReadline.cmake
+  CMakeLists.txt
+  config-cmake.h.in
+
+(E) Auxiliary files for building PCRE2 "by hand"
+
+  src/pcre2.h.generic     ) a version of the public PCRE2 header file
+                          )   for use in non-"configure" environments
+  src/config.h.generic    ) a version of config.h for use in non-"configure"
+                          )   environments
+
+Philip Hazel
+Email local part: Philip.Hazel
+Email domain: gmail.com
+Last updated: 28 April 2021

src/regex/pcre2/RunGrepTest

@@ -0,0 +1,821 @@
+#! /bin/sh
+
+# Run pcre2grep tests. The assumption is that the PCRE2 tests check the library
+# itself. What we are checking here is the file handling and options that are
+# supported by pcre2grep. This script must be run in the build directory.
+
+# CODING CONVENTIONS:
+# * Put printf arguments in single, not double quotes to avoid unwanted
+#     escaping.
+# * Use \0 for binary zero in printf, not \x0, for the benefit of older
+#     versions (and use octal for other special values).
+
+# Set the C locale, so that sort(1) behaves predictably.
+
+LC_ALL=C
+export LC_ALL
+
+# Remove any non-default colouring and aliases that the caller may have set.
+
+unset PCRE2GREP_COLOUR PCRE2GREP_COLOR PCREGREP_COLOUR PCREGREP_COLOR
+unset GREP_COLOR GREP_COLORS
+unset cp ls mv rm
+
+# Remember the current (build) directory, set the program to be tested, and
+# valgrind settings when requested.
+
+builddir=`pwd`
+pcre2grep=$builddir/pcre2grep
+pcre2test=$builddir/pcre2test
+
+if [ ! -x $pcre2grep ] ; then
+  echo "** $pcre2grep does not exist or is not executable."
+  exit 1
+fi
+
+if [ ! -x $pcre2test ] ; then
+  echo "** $pcre2test does not exist or is not executable."
+  exit 1
+fi
+
+valgrind=
+while [ $# -gt 0 ] ; do
+  case $1 in
+    valgrind) valgrind="valgrind -q --leak-check=no --smc-check=all-non-file";;
+    *) echo "RunGrepTest: Unknown argument $1"; exit 1;;
+  esac
+  shift
+done
+
+vjs=
+pcre2grep_version=`$pcre2grep -V`
+if [ "$valgrind" = "" ] ; then
+  echo "Testing $pcre2grep_version"
+else
+  echo "Testing $pcre2grep_version using valgrind"
+  $pcre2test -C jit >/dev/null
+  if [ $? -ne 0 ]; then
+    vjs="--suppressions=./testdata/valgrind-jit.supp"
+  fi
+fi
+
+# Set up a suitable "diff" command for comparison. Some systems have a diff
+# that lacks a -u option. Try to deal with this; better do the test for the -b
+# option as well.
+
+cf="diff"
+diff -b  /dev/null /dev/null 2>/dev/null && cf="diff -b"
+diff -u  /dev/null /dev/null 2>/dev/null && cf="diff -u"
+diff -ub /dev/null /dev/null 2>/dev/null && cf="diff -ub"
+
+# If this test is being run from "make check", $srcdir will be set. If not, set
+# it to the current or parent directory, whichever one contains the test data.
+# Subsequently, we run most of the pcre2grep tests in the source directory so
+# that the file names in the output are always the same.
+
+if [ -z "$srcdir" -o ! -d "$srcdir/testdata" ] ; then
+  if [ -d "./testdata" ] ; then
+    srcdir=.
+  elif [ -d "../testdata" ] ; then
+    srcdir=..
+  else
+    echo "Cannot find the testdata directory"
+    exit 1
+  fi
+fi
+
+# Check for the availability of UTF-8 support
+
+$pcre2test -C unicode >/dev/null
+utf8=$?
+
+# Check default newline convention. If it does not include LF, force LF.
+
+nl=`$pcre2test -C newline`
+if [ "$nl" != "LF" -a "$nl" != "ANY" -a "$nl" != "ANYCRLF" ]; then
+  pcre2grep="$pcre2grep -N LF"
+  echo "Default newline setting forced to LF"
+fi
+
+# ------ Function to run and check a special pcre2grep arguments test -------
+
+checkspecial()
+  {
+  $valgrind $pcre2grep $1 >>testtrygrep 2>&1
+  if [ $? -ne $2 ] ; then
+    echo "** pcre2grep $1 failed - check testtrygrep"
+    exit 1
+  fi
+  }
+
+# ------ Normal tests ------
+
+echo "Testing pcre2grep main features"
+
+echo "---------------------------- Test 1 ------------------------------" >testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep PATTERN ./testdata/grepinput) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 2 ------------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep '^PATTERN' ./testdata/grepinput) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 3 ------------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -in PATTERN ./testdata/grepinput) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 4 ------------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -ic PATTERN ./testdata/grepinput) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 5 ------------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -in PATTERN ./testdata/grepinput ./testdata/grepinputx) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 6 ------------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -inh PATTERN ./testdata/grepinput ./testdata/grepinputx) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 7 ------------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -il PATTERN ./testdata/grepinput ./testdata/grepinputx) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 8 ------------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -l PATTERN ./testdata/grepinput ./testdata/grepinputx) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 9 ------------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -q PATTERN ./testdata/grepinput ./testdata/grepinputx) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 10 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -q NEVER-PATTERN ./testdata/grepinput ./testdata/grepinputx) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 11 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -vn pattern ./testdata/grepinputx) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 12 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -ix pattern ./testdata/grepinputx) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 13 -----------------------------" >>testtrygrep
+echo seventeen >testtemp1grep
+(cd $srcdir; $valgrind $vjs $pcre2grep -f./testdata/greplist -f $builddir/testtemp1grep ./testdata/grepinputx) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 14 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -w pat ./testdata/grepinput ./testdata/grepinputx) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 15 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep 'abc^*' ./testdata/grepinput) >>testtrygrep 2>&1
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 16 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep abc ./testdata/grepinput ./testdata/nonexistfile) >>testtrygrep 2>&1
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 17 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -M 'the\noutput' ./testdata/grepinput) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 18 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -Mn '(the\noutput|dog\.\n--)' ./testdata/grepinput) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 19 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -Mix 'Pattern' ./testdata/grepinputx) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 20 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -Mixn 'complete pair\nof lines' ./testdata/grepinputx) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 21 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -nA3 'four' ./testdata/grepinputx) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 22 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -nB3 'four' ./testdata/grepinputx) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 23 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -C3 'four' ./testdata/grepinputx) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 24 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -A9 'four' ./testdata/grepinputx) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 25 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -nB9 'four' ./testdata/grepinputx) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 26 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -A9 -B9 'four' ./testdata/grepinputx) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 27 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -A10 'four' ./testdata/grepinputx) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 28 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -nB10 'four' ./testdata/grepinputx) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 29 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -C12 -B10 'four' ./testdata/grepinputx) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 30 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -inB3 'pattern' ./testdata/grepinput ./testdata/grepinputx) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 31 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -inA3 'pattern' ./testdata/grepinput ./testdata/grepinputx) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 32 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -L 'fox' ./testdata/grepinput ./testdata/grepinputx) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 33 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep 'fox' ./testdata/grepnonexist) >>testtrygrep 2>&1
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 34 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -s 'fox' ./testdata/grepnonexist) >>testtrygrep 2>&1
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 35 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -L -r --include=grepinputx --include grepinput8 --exclude-dir='^\.' 'fox' ./testdata | sort) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 36 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -L -r --include=grepinput --exclude 'grepinput$' --exclude=grepinput8 --exclude=grepinputM --exclude-dir='^\.' 'fox' ./testdata | sort) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 37 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep  '^(a+)*\d' ./testdata/grepinput) >>testtrygrep 2>teststderrgrep
+echo "RC=$?" >>testtrygrep
+echo "======== STDERR ========" >>testtrygrep
+cat teststderrgrep >>testtrygrep
+
+echo "---------------------------- Test 38 ------------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep '>\x00<' ./testdata/grepinput) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 39 ------------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -A1 'before the binary zero' ./testdata/grepinput) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 40 ------------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -B1 'after the binary zero' ./testdata/grepinput) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 41 ------------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -B1 -o '\w+ the binary zero' ./testdata/grepinput) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 42 ------------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -B1 -onH '\w+ the binary zero' ./testdata/grepinput) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 43 ------------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -on 'before|zero|after' ./testdata/grepinput) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 44 ------------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -on -e before -ezero -e after ./testdata/grepinput) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 45 ------------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -on -f ./testdata/greplist -e binary ./testdata/grepinput) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 46 ------------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -eabc -e '(unclosed' ./testdata/grepinput) >>testtrygrep 2>&1
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 47 ------------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -Fx "AB.VE
+elephant" ./testdata/grepinput) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 48 ------------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -F "AB.VE
+elephant" ./testdata/grepinput) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 49 ------------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -F -e DATA -e "AB.VE
+elephant" ./testdata/grepinput) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 50 ------------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep "^(abc|def|ghi|jkl)" ./testdata/grepinputx) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 51 ------------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -Mv "brown\sfox" ./testdata/grepinputv) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 52 ------------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep --colour=always jumps ./testdata/grepinputv) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 53 ------------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep --file-offsets 'before|zero|after' ./testdata/grepinput) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 54 ------------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep --line-offsets 'before|zero|after' ./testdata/grepinput) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 55 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -f./testdata/greplist --color=always ./testdata/grepinputx) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 56 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -c lazy ./testdata/grepinput*) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 57 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -c -l lazy ./testdata/grepinput*) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 58 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep --regex=PATTERN ./testdata/grepinput) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 59 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep --regexp=PATTERN ./testdata/grepinput) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 60 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep --regex PATTERN ./testdata/grepinput) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 61 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep --regexp PATTERN ./testdata/grepinput) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 62 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $pcre2grep --match-limit=1000 --no-jit -M 'This is a file(.|\R)*file.' ./testdata/grepinput) >>testtrygrep 2>&1
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 63 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $pcre2grep --recursion-limit=1000 --no-jit -M 'This is a file(.|\R)*file.' ./testdata/grepinput) >>testtrygrep 2>&1
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 64 ------------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -o1 '(?<=PAT)TERN (ap(pear)s)' ./testdata/grepinput) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 65 ------------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -o2 '(?<=PAT)TERN (ap(pear)s)' ./testdata/grepinput) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 66 ------------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -o3 '(?<=PAT)TERN (ap(pear)s)' ./testdata/grepinput) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 67 ------------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -o12 '(?<=PAT)TERN (ap(pear)s)' ./testdata/grepinput) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 68 ------------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep --only-matching=2 '(?<=PAT)TERN (ap(pear)s)' ./testdata/grepinput) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 69 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -vn --colour=always pattern ./testdata/grepinputx) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 70 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep --color=always -M "triple:\t.*\n\n" ./testdata/grepinput3) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep --color=always -M -n "triple:\t.*\n\n" ./testdata/grepinput3) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -M "triple:\t.*\n\n" ./testdata/grepinput3) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -M -n "triple:\t.*\n\n" ./testdata/grepinput3) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 71 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -o "^01|^02|^03" ./testdata/grepinput) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 72 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep --color=always "^01|^02|^03" ./testdata/grepinput) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 73 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -o --colour=always "^01|^02|^03" ./testdata/grepinput) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 74 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -o "^01|02|^03" ./testdata/grepinput) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 75 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep --color=always "^01|02|^03" ./testdata/grepinput) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 76 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -o --colour=always "^01|02|^03" ./testdata/grepinput) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 77 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -o "^01|^02|03" ./testdata/grepinput) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 78 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep --color=always "^01|^02|03" ./testdata/grepinput) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 79 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -o --colour=always "^01|^02|03" ./testdata/grepinput) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 80 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -o "\b01|\b02" ./testdata/grepinput) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 81 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep --color=always "\\b01|\\b02" ./testdata/grepinput) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 82 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -o --colour=always "\\b01|\\b02" ./testdata/grepinput) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 83 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep --buffer-size=10 --max-buffer-size=100 "^a" ./testdata/grepinput3) >>testtrygrep 2>&1
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 84 -----------------------------" >>testtrygrep
+echo testdata/grepinput3 >testtemp1grep
+(cd $srcdir; $valgrind $vjs $pcre2grep --file-list ./testdata/grepfilelist --file-list $builddir/testtemp1grep "fox|complete|t7") >>testtrygrep 2>&1
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 85 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep --file-list=./testdata/grepfilelist "dolor" ./testdata/grepinput3) >>testtrygrep 2>&1
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 86 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep "dog" ./testdata/grepbinary) >>testtrygrep 2>&1
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 87 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep "cat" ./testdata/grepbinary) >>testtrygrep 2>&1
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 88 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -v "cat" ./testdata/grepbinary) >>testtrygrep 2>&1
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 89 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -I "dog" ./testdata/grepbinary) >>testtrygrep 2>&1
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 90 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep --binary-files=without-match "dog" ./testdata/grepbinary) >>testtrygrep 2>&1
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 91 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -a "dog" ./testdata/grepbinary) >>testtrygrep 2>&1
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 92 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep --binary-files=text "dog" ./testdata/grepbinary) >>testtrygrep 2>&1
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 93 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep --text "dog" ./testdata/grepbinary) >>testtrygrep 2>&1
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 94 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -L -r --include=grepinputx --include grepinput8 'fox' ./testdata/grepinput* | sort) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 95 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep --file-list ./testdata/grepfilelist --exclude grepinputv "fox|complete") >>testtrygrep 2>&1
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 96 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -L -r --include-dir=testdata --exclude '^(?!grepinput)' --exclude=grepinputM 'fox' ./test* | sort) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 97 -----------------------------" >>testtrygrep
+echo "grepinput$" >testtemp1grep
+echo "grepinput8" >>testtemp1grep
+(cd $srcdir; $valgrind $vjs $pcre2grep -L -r --include=grepinput --exclude=grepinputM --exclude-from $builddir/testtemp1grep --exclude-dir='^\.' 'fox' ./testdata | sort) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 98 -----------------------------" >>testtrygrep
+echo "grepinput$" >testtemp1grep
+echo "grepinput8" >>testtemp1grep
+(cd $srcdir; $valgrind $vjs $pcre2grep -L -r --exclude=grepinput3 --exclude=grepinputM --include=grepinput --exclude-from $builddir/testtemp1grep --exclude-dir='^\.' 'fox' ./testdata | sort) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 99 -----------------------------" >>testtrygrep
+echo "grepinput$" >testtemp1grep
+echo "grepinput8" >testtemp2grep
+(cd $srcdir; $valgrind $vjs $pcre2grep -L -r --include grepinput --exclude=grepinputM --exclude-from $builddir/testtemp1grep --exclude-from=$builddir/testtemp2grep --exclude-dir='^\.' 'fox' ./testdata | sort) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 100 ------------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -Ho2 --only-matching=1 -o3 '(\w+) binary (\w+)(\.)?' ./testdata/grepinput) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 101 ------------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -o3 -Ho2 -o12 --only-matching=1 -o3 --colour=always --om-separator='|' '(\w+) binary (\w+)(\.)?' ./testdata/grepinput) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 102 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -n "^$" ./testdata/grepinput3) >>testtrygrep 2>&1
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 103 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep --only-matching "^$" ./testdata/grepinput3) >>testtrygrep 2>&1
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 104 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -n --only-matching "^$" ./testdata/grepinput3) >>testtrygrep 2>&1
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 105 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep --colour=always "ipsum|" ./testdata/grepinput3) >>testtrygrep 2>&1
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 106 -----------------------------" >>testtrygrep
+(cd $srcdir; echo "a" | $valgrind $vjs $pcre2grep -M "|a" ) >>testtrygrep 2>&1
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 107 -----------------------------" >>testtrygrep
+echo "a" >testtemp1grep
+echo "aaaaa" >>testtemp1grep
+(cd $srcdir; $valgrind $vjs $pcre2grep  --line-offsets '(?<=\Ka)' $builddir/testtemp1grep) >>testtrygrep 2>&1
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 108 ------------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -lq PATTERN ./testdata/grepinput ./testdata/grepinputx) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 109 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -cq lazy ./testdata/grepinput*) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 110 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep --om-separator / -Mo0 -o1 -o2 'match (\d+):\n (.)\n' testdata/grepinput) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 111 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep --line-offsets -M 'match (\d+):\n (.)\n' testdata/grepinput) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 112 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep --file-offsets -M 'match (\d+):\n (.)\n' testdata/grepinput) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 113 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep --total-count 'the' testdata/grepinput*) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 114 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -tc 'the' testdata/grepinput*) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 115 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -tlc 'the' testdata/grepinput*) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 116 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep --exclude=grepinputM -th 'the' testdata/grepinput*) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 117 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -tch 'the' testdata/grepinput*) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 118 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -tL 'the' testdata/grepinput*) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 119 -----------------------------" >>testtrygrep
+printf '123\n456\n789\n---abc\ndef\nxyz\n---\n' >testNinputgrep
+$valgrind $vjs $pcre2grep -Mo '(\n|[^-])*---' testNinputgrep >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 120 ------------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -HO '$0:$2$1$3' '(\w+) binary (\w+)(\.)?' ./testdata/grepinput) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 121 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -F '\E and (regex)' testdata/grepinputv) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 122 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -w 'cat|dog' testdata/grepinputv) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 123 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -w 'dog|cat' testdata/grepinputv) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 124 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -Mn --colour=always 'start[\s]+end' testdata/grepinputM) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -Mn --colour=always -A2 'start[\s]+end' testdata/grepinputM) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -Mn 'start[\s]+end' testdata/grepinputM) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -Mn -A2 'start[\s]+end' testdata/grepinputM) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 125 -----------------------------" >>testtrygrep
+printf 'abcd\n' >testNinputgrep
+$valgrind $vjs $pcre2grep --colour=always '(?<=\K.)' testNinputgrep >>testtrygrep
+echo "RC=$?" >>testtrygrep
+$valgrind $vjs $pcre2grep --colour=always '(?=.\K)' testNinputgrep >>testtrygrep
+echo "RC=$?" >>testtrygrep
+$valgrind $vjs $pcre2grep --colour=always '(?<=\K[ac])' testNinputgrep >>testtrygrep
+echo "RC=$?" >>testtrygrep
+$valgrind $vjs $pcre2grep --colour=always '(?=[ac]\K)' testNinputgrep >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 126 -----------------------------" >>testtrygrep
+printf 'Next line pattern has binary zero\nABC\0XYZ\n' >testtemp1grep
+printf 'ABC\0XYZ\nABCDEF\nDEFABC\n' >testtemp2grep
+$valgrind $vjs $pcre2grep -a -f testtemp1grep testtemp2grep >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 127 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -o --om-capture=0 'pattern()()()()' testdata/grepinput) >>testtrygrep
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 128 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -o1 --om-capture=0 'pattern()()()()' testdata/grepinput) >>testtrygrep 2>&1
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 129 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -m 2 'fox' testdata/grepinput) >>testtrygrep 2>&1
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 130 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -o -m2 'fox' testdata/grepinput) >>testtrygrep 2>&1
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 131 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -oc -m2 'fox' testdata/grepinput) >>testtrygrep 2>&1
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 132 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -m1 -A3 '^match'; echo '---'; head -1) <$srcdir/testdata/grepinput >>testtrygrep 2>&1
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 133 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -m1 -O '=$x{41}$x423$o{103}$o1045=' 'fox') <$srcdir/testdata/grepinputv >>testtrygrep 2>&1
+echo "RC=$?" >>testtrygrep
+
+# Now compare the results.
+
+$cf $srcdir/testdata/grepoutput testtrygrep
+if [ $? != 0 ] ; then exit 1; fi
+
+
+# These tests require UTF-8 support
+
+if [ $utf8 -ne 0 ] ; then
+  echo "Testing pcre2grep UTF-8 features"
+
+  echo "---------------------------- Test U1 ------------------------------" >testtrygrep
+  (cd $srcdir; $valgrind $vjs $pcre2grep -n -u --newline=any "^X" ./testdata/grepinput8) >>testtrygrep
+  echo "RC=$?" >>testtrygrep
+
+  echo "---------------------------- Test U2 ------------------------------" >>testtrygrep
+  (cd $srcdir; $valgrind $vjs $pcre2grep -n -u -C 3 --newline=any "Match" ./testdata/grepinput8) >>testtrygrep
+  echo "RC=$?" >>testtrygrep
+
+  echo "---------------------------- Test U3 ------------------------------" >>testtrygrep
+  (cd $srcdir; $valgrind $vjs $pcre2grep --line-offsets -u --newline=any '(?<=\K\x{17f})' ./testdata/grepinput8) >>testtrygrep
+  echo "RC=$?" >>testtrygrep
+
+  echo "---------------------------- Test U4 ------------------------------" >>testtrygrep
+  printf 'A\341\200\200\200CD\342\200\200Z\n' >testtemp1grep
+  (cd $srcdir; $valgrind $vjs $pcre2grep -u -o '....' $builddir/testtemp1grep) >>testtrygrep 2>&1
+  echo "RC=$?" >>testtrygrep
+
+  echo "---------------------------- Test U5 ------------------------------" >>testtrygrep
+  printf 'A\341\200\200\200CD\342\200\200Z\n' >testtemp1grep
+  (cd $srcdir; $valgrind $vjs $pcre2grep -U -o '....' $builddir/testtemp1grep) >>testtrygrep
+  echo "RC=$?" >>testtrygrep
+
+  echo "---------------------------- Test U6 -----------------------------" >>testtrygrep
+  (cd $srcdir; $valgrind $vjs $pcre2grep -u -m1 -O '=$x{1d3}$o{744}=' 'fox') <$srcdir/testdata/grepinputv >>testtrygrep 2>&1
+  echo "RC=$?" >>testtrygrep
+
+  $cf $srcdir/testdata/grepoutput8 testtrygrep
+  if [ $? != 0 ] ; then exit 1; fi
+
+else
+  echo "Skipping pcre2grep UTF-8 tests: no UTF-8 support in PCRE2 library"
+fi
+
+
+# We go to some contortions to try to ensure that the tests for the various
+# newline settings will work in environments where the normal newline sequence
+# is not \n. Do not use exported files, whose line endings might be changed.
+# Instead, create an input file using printf so that its contents are exactly
+# what we want. Note the messy fudge to get printf to write a string that
+# starts with a hyphen. These tests are run in the build directory.
+
+echo "Testing pcre2grep newline settings"
+printf 'abc\rdef\r\nghi\njkl' >testNinputgrep
+
+printf '%c--------------------------- Test N1 ------------------------------\r\n' - >testtrygrep
+$valgrind $vjs $pcre2grep -n -N CR "^(abc|def|ghi|jkl)" testNinputgrep >>testtrygrep
+
+printf '%c--------------------------- Test N2 ------------------------------\r\n' - >>testtrygrep
+$valgrind $vjs $pcre2grep -n --newline=crlf "^(abc|def|ghi|jkl)" testNinputgrep >>testtrygrep
+
+printf '%c--------------------------- Test N3 ------------------------------\r\n' - >>testtrygrep
+pattern=`printf 'def\rjkl'`
+$valgrind $vjs $pcre2grep -n --newline=cr -F "$pattern" testNinputgrep >>testtrygrep
+
+printf '%c--------------------------- Test N4 ------------------------------\r\n' - >>testtrygrep
+$valgrind $vjs $pcre2grep -n --newline=crlf -F -f $srcdir/testdata/greppatN4 testNinputgrep >>testtrygrep
+
+printf '%c--------------------------- Test N5 ------------------------------\r\n' - >>testtrygrep
+$valgrind $vjs $pcre2grep -n --newline=any "^(abc|def|ghi|jkl)" testNinputgrep >>testtrygrep
+
+printf '%c--------------------------- Test N6 ------------------------------\r\n' - >>testtrygrep
+$valgrind $vjs $pcre2grep -n --newline=anycrlf "^(abc|def|ghi|jkl)" testNinputgrep >>testtrygrep
+
+# This next test involves NUL characters. It seems impossible to handle them
+# easily in many operating systems. An earlier version of this script used sed
+# to translate NUL into the string ZERO, but this didn't work on Solaris (aka
+# SunOS), where the version of sed explicitly doesn't like them, and also MacOS
+# (Darwin), OpenBSD, FreeBSD, NetBSD, and some Linux distributions like Alpine,
+# even when using GNU sed. A user suggested using tr instead, which
+# necessitates translating to a single character (@). However, on (some
+# versions of?) Solaris, the normal "tr" cannot handle binary zeros, but if
+# /usr/xpg4/bin/tr is available, it can do so, so test for that.
+
+if [ -x /usr/xpg4/bin/tr ] ; then
+  tr=/usr/xpg4/bin/tr
+else
+  tr=tr
+fi
+
+printf '%c--------------------------- Test N7 ------------------------------\r\n' - >>testtrygrep
+printf 'abc\0def' >testNinputgrep
+$valgrind $vjs $pcre2grep -na --newline=nul "^(abc|def)" testNinputgrep | $tr '\000' '@' >>testtrygrep
+echo "" >>testtrygrep
+
+$cf $srcdir/testdata/grepoutputN testtrygrep
+if [ $? != 0 ] ; then exit 1; fi
+
+# If pcre2grep supports script callouts, run some tests on them. It is possible
+# to restrict these callouts to the non-fork case, either for security, or for
+# environments that do not support fork(). This is handled by comparing to a
+# different output.
+
+if $valgrind $vjs $pcre2grep --help | $valgrind $vjs $pcre2grep -q 'callout scripts in patterns are supported'; then
+  echo "Testing pcre2grep script callouts"
+  $valgrind $vjs $pcre2grep '(T)(..(.))(?C"/bin/echo|Arg1: [$1] [$2] [$3]|Arg2: $|${1}$| ($4) ($14) ($0)")()' $srcdir/testdata/grepinputv >testtrygrep
+  $valgrind $vjs $pcre2grep '(T)(..(.))()()()()()()()(..)(?C"/bin/echo|Arg1: [$11] [${11}]")' $srcdir/testdata/grepinputv >>testtrygrep
+  $valgrind $vjs $pcre2grep '(T)(?C"|$0:$1$n")' $srcdir/testdata/grepinputv >>testtrygrep
+  $valgrind $vjs $pcre2grep '(T)(?C"|$1$n")(*F)' $srcdir/testdata/grepinputv >>testtrygrep
+  $valgrind $vjs $pcre2grep -m1 '(T)(?C"|$0:$1:$x{41}$o{101}$n")' $srcdir/testdata/grepinputv >>testtrygrep
+
+  if $valgrind $vjs $pcre2grep --help | $valgrind $vjs $pcre2grep -q 'Non-fork callout scripts in patterns are supported'; then
+    $cf $srcdir/testdata/grepoutputCN testtrygrep
+  else
+    $cf $srcdir/testdata/grepoutputC testtrygrep
+  fi
+
+  if [ $? != 0 ] ; then exit 1; fi
+else
+  echo "Script callouts are not supported"
+fi
+
+# Finally, some tests to exercise code that is not tested above, just to be
+# sure that it runs OK. Doing this improves the coverage statistics. The output
+# is not checked.
+
+echo "Testing miscellaneous pcre2grep arguments (unchecked)"
+echo '' >testtrygrep
+checkspecial '-xxxxx' 2
+checkspecial '--help' 0
+checkspecial '--line-buffered --colour=auto abc /dev/null' 1
+
+# Clean up local working files
+rm -f testNinputgrep teststderrgrep testtrygrep testtemp1grep testtemp2grep
+
+exit 0
+
+# End

src/regex/pcre2/RunGrepTest.bat

@@ -0,0 +1,699 @@
+@echo off
+
+:: Run pcre2grep tests. The assumption is that the PCRE2 tests check the library
+:: itself. What we are checking here is the file handling and options that are
+:: supported by pcre2grep. This script must be run in the build directory.
+:: (jmh: I've only tested in the main directory, using my own builds.)
+
+setlocal enabledelayedexpansion
+
+:: Remove any non-default colouring that the caller may have set.
+
+set PCRE2GREP_COLOUR=
+set PCRE2GREP_COLOR=
+set PCREGREP_COLOUR=
+set PCREGREP_COLOR=
+set GREP_COLORS=
+set GREP_COLOR=
+
+:: Remember the current (build) directory and set the program to be tested.
+
+set builddir="%CD%"
+set pcre2grep=%builddir%\pcre2grep.exe
+set pcre2test=%builddir%\pcre2test.exe
+
+if NOT exist %pcre2grep% (
+  echo ** %pcre2grep% does not exist.
+  exit /b 1
+)
+
+if NOT exist %pcre2test% (
+  echo ** %pcre2test% does not exist.
+  exit /b 1
+)
+
+for /f "delims=" %%a in ('"%pcre2grep%" -V') do set pcre2grep_version=%%a
+echo Testing %pcre2grep_version%
+
+:: Set up a suitable "diff" command for comparison. Some systems have a diff
+:: that lacks a -u option. Try to deal with this; better do the test for the -b
+:: option as well. Use FC if there's no diff, taking care to ignore equality.
+
+set cf=
+set cfout=
+diff -b  nul nul 2>nul && set cf=diff -b
+diff -u  nul nul 2>nul && set cf=diff -u
+diff -ub nul nul 2>nul && set cf=diff -ub
+if NOT defined cf (
+  set cf=fc /n
+  set "cfout=>testcf || (type testcf & cmd /c exit /b 1)"
+)
+
+:: Set srcdir to the current or parent directory, whichever one contains the
+:: test data. Subsequently, we run most of the pcre2grep tests in the source
+:: directory so that the file names in the output are always the same.
+
+if NOT defined srcdir set srcdir=.
+if NOT exist %srcdir%\testdata\ (
+  if exist testdata\ (
+    set srcdir=.
+  ) else if exist ..\testdata\ (
+    set srcdir=..
+  ) else if exist ..\..\testdata\ (
+    set srcdir=..\..
+  ) else (
+    echo Cannot find the testdata directory
+    exit /b 1
+  )
+)
+
+:: Check for the availability of UTF-8 support
+
+%pcre2test% -C unicode >nul
+set utf8=%ERRORLEVEL%
+
+:: Check default newline convention. If it does not include LF, force LF.
+
+for /f %%a in ('"%pcre2test%" -C newline') do set nl=%%a
+if NOT "%nl%" == "LF" if NOT "%nl%" == "ANY" if NOT "%nl%" == "ANYCRLF" (
+  set pcre2grep=%pcre2grep% -N LF
+  echo Default newline setting forced to LF
+)
+
+:: Create a simple printf via cscript/JScript (an actual printf may translate
+:: LF to CRLF, which this one does not).
+
+echo WScript.StdOut.Write(WScript.Arguments(0).replace(/\\r/g, "\r").replace(/\\n/g, "\n")) >printf.js
+set printf=cscript //nologo printf.js
+
+:: ------ Normal tests ------
+
+echo Testing pcre2grep main features
+
+echo ---------------------------- Test 1 ------------------------------>testtrygrep
+(pushd %srcdir% & %pcre2grep% PATTERN ./testdata/grepinput & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 2 ------------------------------>>testtrygrep
+(pushd %srcdir% & %pcre2grep% "^PATTERN" ./testdata/grepinput & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 3 ------------------------------>>testtrygrep
+(pushd %srcdir% & %pcre2grep% -in PATTERN ./testdata/grepinput & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 4 ------------------------------>>testtrygrep
+(pushd %srcdir% & %pcre2grep% -ic PATTERN ./testdata/grepinput & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 5 ------------------------------>>testtrygrep
+(pushd %srcdir% & %pcre2grep% -in PATTERN ./testdata/grepinput ./testdata/grepinputx & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 6 ------------------------------>>testtrygrep
+(pushd %srcdir% & %pcre2grep% -inh PATTERN ./testdata/grepinput ./testdata/grepinputx & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 7 ------------------------------>>testtrygrep
+(pushd %srcdir% & %pcre2grep% -il PATTERN ./testdata/grepinput ./testdata/grepinputx & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 8 ------------------------------>>testtrygrep
+(pushd %srcdir% & %pcre2grep% -l PATTERN ./testdata/grepinput ./testdata/grepinputx & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 9 ------------------------------>>testtrygrep
+(pushd %srcdir% & %pcre2grep% -q PATTERN ./testdata/grepinput ./testdata/grepinputx & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 10 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% -q NEVER-PATTERN ./testdata/grepinput ./testdata/grepinputx & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 11 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% -vn pattern ./testdata/grepinputx & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 12 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% -ix pattern ./testdata/grepinputx & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 13 ----------------------------->>testtrygrep
+echo seventeen >testtemp1grep
+(pushd %srcdir% & %pcre2grep% -f./testdata/greplist -f %builddir%\testtemp1grep ./testdata/grepinputx & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 14 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% -w pat ./testdata/grepinput ./testdata/grepinputx & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 15 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% "abc^*" ./testdata/grepinput & popd) >>testtrygrep 2>&1
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 16 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% abc ./testdata/grepinput ./testdata/nonexistfile & popd) >>testtrygrep 2>&1
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 17 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% -M "the\noutput" ./testdata/grepinput & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 18 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% -Mn "(the\noutput|dog\.\n--)" ./testdata/grepinput & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 19 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% -Mix "Pattern" ./testdata/grepinputx & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 20 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% -Mixn "complete pair\nof lines" ./testdata/grepinputx & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 21 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% -nA3 "four" ./testdata/grepinputx & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 22 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% -nB3 "four" ./testdata/grepinputx & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 23 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% -C3 "four" ./testdata/grepinputx & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 24 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% -A9 "four" ./testdata/grepinputx & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 25 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% -nB9 "four" ./testdata/grepinputx & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 26 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% -A9 -B9 "four" ./testdata/grepinputx & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 27 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% -A10 "four" ./testdata/grepinputx & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 28 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% -nB10 "four" ./testdata/grepinputx & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 29 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% -C12 -B10 "four" ./testdata/grepinputx & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 30 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% -inB3 "pattern" ./testdata/grepinput ./testdata/grepinputx & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 31 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% -inA3 "pattern" ./testdata/grepinput ./testdata/grepinputx & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 32 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% -L "fox" ./testdata/grepinput ./testdata/grepinputx & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 33 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% "fox" ./testdata/grepnonexist & popd) >>testtrygrep 2>&1
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 34 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% -s "fox" ./testdata/grepnonexist & popd) >>testtrygrep 2>&1
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 35 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% -L -r --include=grepinputx --include grepinput8 --exclude-dir="^\." "fox" ./testdata | sort & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 36 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% -L -r --include=grepinput --exclude "grepinput$" --exclude=grepinput8 --exclude-dir="^\." "fox" ./testdata | sort & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 37 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep%  "^(a+)*\d" ./testdata/grepinput & popd) >>testtrygrep 2>teststderrgrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+echo ======== STDERR ========>>testtrygrep
+type teststderrgrep >>testtrygrep
+
+echo ---------------------------- Test 38 ------------------------------>>testtrygrep
+(pushd %srcdir% & %pcre2grep% ">\x00<" ./testdata/grepinput & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 39 ------------------------------>>testtrygrep
+(pushd %srcdir% & %pcre2grep% -A1 "before the binary zero" ./testdata/grepinput & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 40 ------------------------------>>testtrygrep
+(pushd %srcdir% & %pcre2grep% -B1 "after the binary zero" ./testdata/grepinput & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 41 ------------------------------>>testtrygrep
+(pushd %srcdir% & %pcre2grep% -B1 -o "\w+ the binary zero" ./testdata/grepinput & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 42 ------------------------------>>testtrygrep
+(pushd %srcdir% & %pcre2grep% -B1 -onH "\w+ the binary zero" ./testdata/grepinput & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 43 ------------------------------>>testtrygrep
+(pushd %srcdir% & %pcre2grep% -on "before|zero|after" ./testdata/grepinput & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 44 ------------------------------>>testtrygrep
+(pushd %srcdir% & %pcre2grep% -on -e before -ezero -e after ./testdata/grepinput & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 45 ------------------------------>>testtrygrep
+(pushd %srcdir% & %pcre2grep% -on -f ./testdata/greplist -e binary ./testdata/grepinput & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 46 ------------------------------>>testtrygrep
+(pushd %srcdir% & %pcre2grep% -eabc -e "(unclosed" ./testdata/grepinput & popd) >>testtrygrep 2>&1
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 47 ------------------------------>>testtrygrep
+(pushd %srcdir% & %pcre2grep% -Fx AB.VE^
+
+elephant ./testdata/grepinput & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 48 ------------------------------>>testtrygrep
+(pushd %srcdir% & %pcre2grep% -F AB.VE^
+
+elephant ./testdata/grepinput & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 49 ------------------------------>>testtrygrep
+(pushd %srcdir% & %pcre2grep% -F -e DATA -e AB.VE^
+
+elephant ./testdata/grepinput & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 50 ------------------------------>>testtrygrep
+(pushd %srcdir% & %pcre2grep% "^(abc|def|ghi|jkl)" ./testdata/grepinputx & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 51 ------------------------------>>testtrygrep
+(pushd %srcdir% & %pcre2grep% -Mv "brown\sfox" ./testdata/grepinputv & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 52 ------------------------------>>testtrygrep
+(pushd %srcdir% & %pcre2grep% --colour=always jumps ./testdata/grepinputv & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 53 ------------------------------>>testtrygrep
+(pushd %srcdir% & %pcre2grep% --file-offsets "before|zero|after" ./testdata/grepinput & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 54 ------------------------------>>testtrygrep
+(pushd %srcdir% & %pcre2grep% --line-offsets "before|zero|after" ./testdata/grepinput & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 55 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% -f./testdata/greplist --color=always ./testdata/grepinputx & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 56 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% -c lazy ./testdata/grepinput* & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 57 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% -c -l lazy ./testdata/grepinput* & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 58 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% --regex=PATTERN ./testdata/grepinput & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 59 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% --regexp=PATTERN ./testdata/grepinput & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 60 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% --regex PATTERN ./testdata/grepinput & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 61 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% --regexp PATTERN ./testdata/grepinput & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 62 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% --match-limit=1000 --no-jit -M "This is a file(.|\R)*file." ./testdata/grepinput & popd) >>testtrygrep 2>&1
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 63 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% --recursion-limit=1000 --no-jit -M "This is a file(.|\R)*file." ./testdata/grepinput & popd) >>testtrygrep 2>&1
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 64 ------------------------------>>testtrygrep
+(pushd %srcdir% & %pcre2grep% -o1 "(?<=PAT)TERN (ap(pear)s)" ./testdata/grepinput & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 65 ------------------------------>>testtrygrep
+(pushd %srcdir% & %pcre2grep% -o2 "(?<=PAT)TERN (ap(pear)s)" ./testdata/grepinput & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 66 ------------------------------>>testtrygrep
+(pushd %srcdir% & %pcre2grep% -o3 "(?<=PAT)TERN (ap(pear)s)" ./testdata/grepinput & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 67 ------------------------------>>testtrygrep
+(pushd %srcdir% & %pcre2grep% -o12 "(?<=PAT)TERN (ap(pear)s)" ./testdata/grepinput & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 68 ------------------------------>>testtrygrep
+(pushd %srcdir% & %pcre2grep% --only-matching=2 "(?<=PAT)TERN (ap(pear)s)" ./testdata/grepinput & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 69 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% -vn --colour=always pattern ./testdata/grepinputx & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 70 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% --color=always -M "triple:\t.*\n\n" ./testdata/grepinput3 & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 71 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% -o "^01|^02|^03" ./testdata/grepinput & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 72 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% --color=always "^01|^02|^03" ./testdata/grepinput & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 73 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% -o --colour=always "^01|^02|^03" ./testdata/grepinput & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 74 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% -o "^01|02|^03" ./testdata/grepinput & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 75 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% --color=always "^01|02|^03" ./testdata/grepinput & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 76 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% -o --colour=always "^01|02|^03" ./testdata/grepinput & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 77 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% -o "^01|^02|03" ./testdata/grepinput & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 78 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% --color=always "^01|^02|03" ./testdata/grepinput & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 79 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% -o --colour=always "^01|^02|03" ./testdata/grepinput & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 80 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% -o "\b01|\b02" ./testdata/grepinput & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 81 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% --color=always "\b01|\b02" ./testdata/grepinput & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 82 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% -o --colour=always "\b01|\b02" ./testdata/grepinput & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 83 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% --buffer-size=10 --max-buffer-size=100 "^a" ./testdata/grepinput3 & popd) >>testtrygrep 2>&1
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 84 ----------------------------->>testtrygrep
+echo testdata/grepinput3 >testtemp1grep
+(pushd %srcdir% & %pcre2grep% --file-list ./testdata/grepfilelist --file-list %builddir%\testtemp1grep "fox|complete|t7" & popd) >>testtrygrep 2>&1
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 85 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% --file-list=./testdata/grepfilelist "dolor" ./testdata/grepinput3 & popd) >>testtrygrep 2>&1
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 86 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% "dog" ./testdata/grepbinary & popd) >>testtrygrep 2>&1
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 87 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% "cat" ./testdata/grepbinary & popd) >>testtrygrep 2>&1
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 88 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% -v "cat" ./testdata/grepbinary & popd) >>testtrygrep 2>&1
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 89 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% -I "dog" ./testdata/grepbinary & popd) >>testtrygrep 2>&1
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 90 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% --binary-files=without-match "dog" ./testdata/grepbinary & popd) >>testtrygrep 2>&1
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 91 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% -a "dog" ./testdata/grepbinary & popd) >>testtrygrep 2>&1
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 92 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% --binary-files=text "dog" ./testdata/grepbinary & popd) >>testtrygrep 2>&1
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 93 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% --text "dog" ./testdata/grepbinary & popd) >>testtrygrep 2>&1
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 94 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% -L -r --include=grepinputx --include grepinput8 "fox" ./testdata/grepinput* | sort & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 95 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% --file-list ./testdata/grepfilelist --exclude grepinputv "fox|complete" & popd) >>testtrygrep 2>&1
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 96 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% -L -r --include-dir=testdata --exclude "^^(?^!grepinput)" "fox" ./test* | sort & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 97 ----------------------------->>testtrygrep
+echo grepinput$>testtemp1grep
+echo grepinput8>>testtemp1grep
+(pushd %srcdir% & %pcre2grep% -L -r --include=grepinput --exclude-from %builddir%\testtemp1grep --exclude-dir="^\." "fox" ./testdata | sort & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 98 ----------------------------->>testtrygrep
+echo grepinput$>testtemp1grep
+echo grepinput8>>testtemp1grep
+(pushd %srcdir% & %pcre2grep% -L -r --exclude=grepinput3 --include=grepinput --exclude-from %builddir%\testtemp1grep --exclude-dir="^\." "fox" ./testdata | sort & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 99 ----------------------------->>testtrygrep
+echo grepinput$>testtemp1grep
+echo grepinput8>testtemp2grep
+(pushd %srcdir% & %pcre2grep% -L -r --include grepinput --exclude-from %builddir%\testtemp1grep --exclude-from=%builddir%\testtemp2grep --exclude-dir="^\." "fox" ./testdata | sort & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 100 ------------------------------>>testtrygrep
+(pushd %srcdir% & %pcre2grep% -Ho2 --only-matching=1 -o3 "(\w+) binary (\w+)(\.)?" ./testdata/grepinput & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 101 ------------------------------>>testtrygrep
+(pushd %srcdir% & %pcre2grep% -o3 -Ho2 -o12 --only-matching=1 -o3 --colour=always --om-separator="|" "(\w+) binary (\w+)(\.)?" ./testdata/grepinput & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 102 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% -n "^$" ./testdata/grepinput3 & popd) >>testtrygrep 2>&1
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 103 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% --only-matching "^$" ./testdata/grepinput3 & popd) >>testtrygrep 2>&1
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 104 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% -n --only-matching "^$" ./testdata/grepinput3 & popd) >>testtrygrep 2>&1
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 105 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% --colour=always "ipsum|" ./testdata/grepinput3 & popd) >>testtrygrep 2>&1
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 106 ----------------------------->>testtrygrep
+(pushd %srcdir% & echo a| %pcre2grep% -M "|a" & popd) >>testtrygrep 2>&1
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 107 ----------------------------->>testtrygrep
+echo a>testtemp1grep
+echo aaaaa>>testtemp1grep
+(pushd %srcdir% & %pcre2grep%  --line-offsets "(?<=\Ka)" %builddir%\testtemp1grep & popd) >>testtrygrep 2>&1
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 108 ------------------------------>>testtrygrep
+(pushd %srcdir% & %pcre2grep% -lq PATTERN ./testdata/grepinput ./testdata/grepinputx & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 109 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% -cq lazy ./testdata/grepinput* & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 110 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% --om-separator / -Mo0 -o1 -o2 "match (\d+):\n (.)\n" testdata/grepinput & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 111 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% --line-offsets -M "match (\d+):\n (.)\n" testdata/grepinput & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 112 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% --file-offsets -M "match (\d+):\n (.)\n" testdata/grepinput & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 113 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% --total-count "the" testdata/grepinput* & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 114 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% -tc "the" testdata/grepinput* & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 115 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% -tlc "the" testdata/grepinput* & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 116 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% -th "the" testdata/grepinput* & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 117 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% -tch "the" testdata/grepinput* & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 118 ----------------------------->>testtrygrep
+(pushd %srcdir% & %pcre2grep% -tL "the" testdata/grepinput* & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 119 ----------------------------->>testtrygrep
+%printf% "123\n456\n789\n---abc\ndef\nxyz\n---\n" >testNinputgrep
+%pcre2grep% -Mo "(\n|[^-])*---" testNinputgrep >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+echo ---------------------------- Test 120 ------------------------------>>testtrygrep
+(pushd %srcdir% & %pcre2grep% -HO "$0:$2$1$3" "(\w+) binary (\w+)(\.)?" ./testdata/grepinput & popd) >>testtrygrep
+echo RC=^%ERRORLEVEL%>>testtrygrep
+
+:: Now compare the results.
+
+%cf% %srcdir%\testdata\grepoutput testtrygrep %cfout%
+if ERRORLEVEL 1 exit /b 1
+
+
+:: These tests require UTF-8 support
+
+if %utf8% neq 0 (
+  echo Testing pcre2grep UTF-8 features
+
+  echo ---------------------------- Test U1 ------------------------------>testtrygrep
+  (pushd %srcdir% & %pcre2grep% -n -u --newline=any "^X" ./testdata/grepinput8 & popd) >>testtrygrep
+  echo RC=^%ERRORLEVEL%>>testtrygrep
+
+  echo ---------------------------- Test U2 ------------------------------>>testtrygrep
+  (pushd %srcdir% & %pcre2grep% -n -u -C 3 --newline=any "Match" ./testdata/grepinput8 & popd) >>testtrygrep
+  echo RC=^%ERRORLEVEL%>>testtrygrep
+
+  echo ---------------------------- Test U3 ------------------------------>>testtrygrep
+  (pushd %srcdir% & %pcre2grep% --line-offsets -u --newline=any "(?<=\K\x{17f})" ./testdata/grepinput8 & popd) >>testtrygrep
+  echo RC=^%ERRORLEVEL%>>testtrygrep
+
+  %cf% %srcdir%\testdata\grepoutput8 testtrygrep %cfout%
+  if ERRORLEVEL 1 exit /b 1
+
+) else (
+  echo Skipping pcre2grep UTF-8 tests: no UTF-8 support in PCRE2 library
+)
+
+
+:: We go to some contortions to try to ensure that the tests for the various
+:: newline settings will work in environments where the normal newline sequence
+:: is not \n. Do not use exported files, whose line endings might be changed.
+:: Instead, create an input file so that its contents are exactly what we want.
+:: These tests are run in the build directory.
+
+echo Testing pcre2grep newline settings
+%printf% "abc\rdef\r\nghi\njkl" >testNinputgrep
+
+echo ---------------------------- Test N1 ------------------------------>testtrygrep
+%pcre2grep% -n -N CR "^(abc|def|ghi|jkl)" testNinputgrep >>testtrygrep
+
+echo ---------------------------- Test N2 ------------------------------>>testtrygrep
+%pcre2grep% -n --newline=crlf "^(abc|def|ghi|jkl)" testNinputgrep >>testtrygrep
+
+echo ---------------------------- Test N3 ------------------------------>>testtrygrep
+for /f %%a in ('%printf% "def\rjkl"') do set pattern=%%a
+%pcre2grep% -n --newline=cr -F "!pattern!" testNinputgrep >>testtrygrep
+
+echo ---------------------------- Test N4 ------------------------------>>testtrygrep
+%pcre2grep% -n --newline=crlf -F -f %srcdir%/testdata/greppatN4 testNinputgrep >>testtrygrep
+
+echo ---------------------------- Test N5 ------------------------------>>testtrygrep
+%pcre2grep% -n --newline=any "^(abc|def|ghi|jkl)" testNinputgrep >>testtrygrep
+
+echo ---------------------------- Test N6 ------------------------------>>testtrygrep
+%pcre2grep% -n --newline=anycrlf "^(abc|def|ghi|jkl)" testNinputgrep >>testtrygrep
+
+%cf% %srcdir%\testdata\grepoutputN testtrygrep %cfout%
+if ERRORLEVEL 1 exit /b 1
+
+:: If pcre2grep supports script callouts, run some tests on them.
+
+%pcre2grep% --help | %pcre2grep% -q "callout scripts in patterns are supported"
+if %ERRORLEVEL% equ 0 (
+  echo Testing pcre2grep script callouts
+  %pcre2grep% "(T)(..(.))(?C'cmd|/c echo|Arg1: [$1] [$2] [$3]|Arg2: ^$|${1}^$| ($4) ($14) ($0)')()" %srcdir%/testdata/grepinputv >testtrygrep
+  %pcre2grep% "(T)(..(.))()()()()()()()(..)(?C'cmd|/c echo|Arg1: [$11] [${11}]')" %srcdir%/testdata/grepinputv >>testtrygrep
+  %pcre2grep% "(T)(?C'|$0:$1$n')" %srcdir%/testdata/grepinputv >>testtrygrep
+  %pcre2grep% "(T)(?C'|$1$n')(*F)" %srcdir%/testdata/grepinputv >>testtrygrep
+  %pcre2grep% --help | %pcre2grep% -q "Non-script callout scripts in patterns are supported"
+  if %ERRORLEVEL% equ 0 (
+    %cf% %srcdir%\testdata\grepoutputCN testtrygrep %cfout%
+  ) else (
+    %cf% %srcdir%\testdata\grepoutputC testtrygrep %cfout%
+  )
+  if ERRORLEVEL 1 exit /b 1
+) else (
+  echo Script callouts are not supported
+)
+
+:: Finally, some tests to exercise code that is not tested above, just to be
+:: sure that it runs OK. Doing this improves the coverage statistics. The output
+:: is not checked.
+
+echo Testing miscellaneous pcre2grep arguments (unchecked)
+%printf% "" >testtrygrep
+call :checkspecial "-xxxxx" 2 || exit /b 1
+call :checkspecial "--help" 0 || exit /b 1
+call :checkspecial "--line-buffered --colour=auto abc nul" 1 || exit /b 1
+
+:: Clean up local working files
+del testcf printf.js testNinputgrep teststderrgrep testtrygrep testtemp1grep testtemp2grep
+
+exit /b 0
+
+:: ------ Function to run and check a special pcre2grep arguments test -------
+
+:checkspecial
+  %pcre2grep% %~1 >>testtrygrep 2>&1
+  if %ERRORLEVEL% neq %2 (
+    echo ** pcre2grep %~1 failed - check testtrygrep
+    exit /b 1
+  )
+  exit /b 0
+
+:: End

src/regex/pcre2/RunTest

@@ -0,0 +1,869 @@
+#! /bin/sh
+
+###############################################################################
+# Run the PCRE2 tests using the pcre2test program. The appropriate tests are
+# selected, depending on which build-time options were used.
+#
+# When JIT support is available, all appropriate tests are run with and without
+# JIT, unless "-nojit" is given on the command line. There are also two tests
+# for JIT-specific features, one to be run when JIT support is available
+# (unless "-nojit" is specified), and one when it is not.
+#
+# Whichever of the 8-, 16- and 32-bit libraries exist are tested. It is also
+# possible to select which to test by giving "-8", "-16" or "-32" on the
+# command line.
+#
+# As well as "-nojit", "-8", "-16", and "-32", arguments for this script are
+# individual test numbers, ranges of tests such as 3-6 or 3- (meaning 3 to the
+# end), or a number preceded by ~ to exclude a test. For example, "3-15 ~10"
+# runs tests 3 to 15, excluding test 10, and just "~10" runs all the tests
+# except test 10. Whatever order the arguments are in, the tests are always run
+# in numerical order.
+#
+# Inappropriate tests are automatically skipped (with a comment to say so). For
+# example, if JIT support is not compiled, test 16 is skipped, whereas if JIT
+# support is compiled, test 15 is skipped.
+#
+# Other arguments can be one of the words "-valgrind", "-valgrind-log", or
+# "-sim" followed by an argument to run cross-compiled executables under a
+# simulator, for example:
+#
+# RunTest 3 -sim "qemu-arm -s 8388608"
+#
+# For backwards compatibility, -nojit, -valgrind, -valgrind-log, and -sim may
+# be given without the leading "-" character.
+#
+# When PCRE2 is compiled by clang with -fsanitize arguments, some tests need
+# very much more stack than normal. In environments where the stack can be
+# set at runtime, -bigstack sets a gigantic stack.
+#
+# There are two special cases where only one argument is allowed:
+#
+# If the first and only argument is "ebcdic", the script runs the special
+# EBCDIC test that can be useful for checking certain EBCDIC features, even
+# when run in an ASCII environment. PCRE2 must be built with EBCDIC support for
+# this test to be run.
+#
+# If the script is obeyed as "RunTest list", a list of available tests is
+# output, but none of them are run.
+###############################################################################
+
+# Define test titles in variables so that they can be output as a list. Some
+# of them are modified (e.g. with -8 or -16) when used in the actual tests.
+
+title0="Test 0: Unchecked pcre2test argument tests (to improve coverage)"
+title1="Test 1: Main non-UTF, non-UCP functionality (compatible with Perl >= 5.10)"
+title2="Test 2: API, errors, internals and non-Perl stuff"
+title3="Test 3: Locale-specific features"
+title4A="Test 4: UTF"
+title4B=" and Unicode property support (compatible with Perl >= 5.10)"
+title5A="Test 5: API, internals, and non-Perl stuff for UTF"
+title5B=" and UCP support"
+title6="Test 6: DFA matching main non-UTF, non-UCP functionality"
+title7A="Test 7: DFA matching with UTF"
+title7B=" and Unicode property support"
+title8="Test 8: Internal offsets and code size tests"
+title9="Test 9: Specials for the basic 8-bit library"
+title10="Test 10: Specials for the 8-bit library with UTF-8 and UCP support"
+title11="Test 11: Specials for the basic 16-bit and 32-bit libraries"
+title12="Test 12: Specials for the 16-bit and 32-bit libraries UTF and UCP support"
+title13="Test 13: DFA specials for the basic 16-bit and 32-bit libraries"
+title14="Test 14: DFA specials for UTF and UCP support"
+title15="Test 15: Non-JIT limits and other non-JIT tests"
+title16="Test 16: JIT-specific features when JIT is not available"
+title17="Test 17: JIT-specific features when JIT is available"
+title18="Test 18: Tests of the POSIX interface, excluding UTF/UCP"
+title19="Test 19: Tests of the POSIX interface with UTF/UCP"
+title20="Test 20: Serialization and code copy tests"
+title21="Test 21: \C tests without UTF (supported for DFA matching)"
+title22="Test 22: \C tests with UTF (not supported for DFA matching)"
+title23="Test 23: \C disabled test"
+title24="Test 24: Non-UTF pattern conversion tests"
+title25="Test 25: UTF pattern conversion tests"
+maxtest=25
+
+if [ $# -eq 1 -a "$1" = "list" ]; then
+  echo $title0
+  echo $title1
+  echo $title2 "(not UTF or UCP)"
+  echo $title3
+  echo $title4A $title4B
+  echo $title5A $title5B
+  echo $title6
+  echo $title7A $title7B
+  echo $title8
+  echo $title9
+  echo $title10
+  echo $title11
+  echo $title12
+  echo $title13
+  echo $title14
+  echo $title15
+  echo $title16
+  echo $title17
+  echo $title18
+  echo $title19
+  echo $title20
+  echo $title21
+  echo $title22
+  echo $title23
+  echo $title24
+  echo $title25
+  exit 0
+fi
+
+# Set up a suitable "diff" command for comparison. Some systems
+# have a diff that lacks a -u option. Try to deal with this.
+
+cf="diff"
+diff -u /dev/null /dev/null 2>/dev/null && cf="diff -u"
+
+# Find the test data
+
+if [ -n "$srcdir" -a -d "$srcdir" ] ; then
+  testdata="$srcdir/testdata"
+elif [ -d "./testdata" ] ; then
+  testdata=./testdata
+elif [ -d "../testdata" ] ; then
+  testdata=../testdata
+else
+  echo "Cannot find the testdata directory"
+  exit 1
+fi
+
+
+# ------ Function to check results of a test -------
+
+# This function is called with three parameters:
+#
+#  $1 the value of $? after a call to pcre2test
+#  $2 the suffix of the output file to compare with
+#  $3 the $opt value (empty, -jit, or -dfa)
+#
+# Note: must define using name(), not "function name", for Solaris.
+
+checkresult()
+  {
+  if [ $1 -ne 0 ] ; then
+    echo "** pcre2test failed - check testtry"
+    exit 1
+  fi
+  case "$3" in
+    -jit) with=" with JIT";;
+    -dfa) with=" with DFA";;
+    *)    with="";;
+  esac
+  $cf $testdata/testoutput$2 testtry
+  if [ $? != 0 ] ; then
+    echo ""
+    echo "** Test $2 failed$with"
+    exit 1
+  fi
+  echo "  OK$with"
+  }
+
+
+# ------ Function to run and check a special pcre2test arguments test -------
+
+checkspecial()
+  {
+  $valgrind  $vjs ./pcre2test $1 >>testtry
+  if [ $? -ne 0 ] ; then
+    echo "** pcre2test $1 failed - check testtry"
+    exit 1
+  fi
+  }
+
+
+# ------ Special EBCDIC Test -------
+
+if [ $# -eq 1 -a "$1" = "ebcdic" ]; then
+  $valgrind ./pcre2test -C ebcdic >/dev/null
+  ebcdic=$?
+  if [ $ebcdic -ne 1 ] ; then
+    echo "Cannot run EBCDIC tests: EBCDIC support not compiled"
+    exit 1
+  fi
+  for opt in "" "-dfa"; do
+    ./pcre2test -q $opt $testdata/testinputEBC >testtry
+    checkresult $? EBC "$opt"
+  done
+exit 0
+fi
+
+
+# ------ Normal Tests ------
+
+# Default values
+
+arg8=
+arg16=
+arg32=
+nojit=
+bigstack=
+sim=
+skip=
+valgrind=
+vjs=
+
+# This is in case the caller has set aliases (as I do - PH)
+unset cp ls mv rm
+
+# Process options and select which tests to run; for those that are explicitly
+# requested, check that the necessary optional facilities are available.
+
+do0=no
+do1=no
+do2=no
+do3=no
+do4=no
+do5=no
+do6=no
+do7=no
+do8=no
+do9=no
+do10=no
+do11=no
+do12=no
+do13=no
+do14=no
+do15=no
+do16=no
+do17=no
+do18=no
+do19=no
+do20=no
+do21=no
+do22=no
+do23=no
+do24=no
+do25=no
+
+while [ $# -gt 0 ] ; do
+  case $1 in
+    0) do0=yes;;
+    1) do1=yes;;
+    2) do2=yes;;
+    3) do3=yes;;
+    4) do4=yes;;
+    5) do5=yes;;
+    6) do6=yes;;
+    7) do7=yes;;
+    8) do8=yes;;
+    9) do9=yes;;
+   10) do10=yes;;
+   11) do11=yes;;
+   12) do12=yes;;
+   13) do13=yes;;
+   14) do14=yes;;
+   15) do15=yes;;
+   16) do16=yes;;
+   17) do17=yes;;
+   18) do18=yes;;
+   19) do19=yes;;
+   20) do20=yes;;
+   21) do21=yes;;
+   22) do22=yes;;
+   23) do23=yes;;
+   24) do24=yes;;
+   25) do25=yes;;
+   -8) arg8=yes;;
+  -16) arg16=yes;;
+  -32) arg32=yes;;
+   bigstack|-bigstack) bigstack=yes;;
+   nojit|-nojit) nojit=yes;;
+   sim|-sim) shift; sim=$1;;
+   valgrind|-valgrind) valgrind="valgrind --tool=memcheck -q --smc-check=all-non-file";;
+   valgrind-log|-valgrind-log) valgrind="valgrind --tool=memcheck --num-callers=30 --leak-check=no --error-limit=no --smc-check=all-non-file --log-file=report.%p ";;
+   ~*)
+     if expr "$1" : '~[0-9][0-9]*$' >/dev/null; then
+       skip="$skip `expr "$1" : '~\([0-9]*\)*$'`"
+     else
+       echo "Unknown option or test selector '$1'"; exit 1
+     fi
+   ;;
+   *-*)
+     if expr "$1" : '[0-9][0-9]*-[0-9]*$' >/dev/null; then
+       tf=`expr "$1" : '\([0-9]*\)'`
+       tt=`expr "$1" : '.*-\([0-9]*\)'`
+       if [ "$tt" = "" ] ; then tt=$maxtest; fi
+       if expr \( "$tt" ">" "$maxtest" \) >/dev/null; then
+         echo "Invalid test range '$1'"; exit 1
+       fi
+       while expr "$tf" "<=" "$tt" >/dev/null; do
+         eval do${tf}=yes
+         tf=`expr $tf + 1`
+       done
+     else
+       echo "Invalid test range '$1'"; exit 1
+     fi
+   ;;
+   *) echo "Unknown option or test selector '$1'"; exit 1;;
+  esac
+  shift
+done
+
+# Find which optional facilities are available.
+
+$sim ./pcre2test -C linksize >/dev/null
+link_size=$?
+if [ $link_size -lt 2 ] ; then
+  echo "RunTest: Failed to find internal link size"
+  exit 1
+fi
+if [ $link_size -gt 4 ] ; then
+  echo "RunTest: Failed to find internal link size"
+  exit 1
+fi
+
+# If it is possible to set the system stack size and -bigstack was given,
+# set up a large stack.
+
+$sim ./pcre2test -S 64 /dev/null /dev/null
+if [ $? -eq 0 -a "$bigstack" != "" ] ; then
+  setstack="-S 64"
+else
+  setstack=""
+fi
+
+# All of 8-bit, 16-bit, and 32-bit character strings may be supported, but only
+# one need be.
+
+$sim ./pcre2test -C pcre2-8 >/dev/null
+support8=$?
+$sim ./pcre2test -C pcre2-16 >/dev/null
+support16=$?
+$sim ./pcre2test -C pcre2-32 >/dev/null
+support32=$?
+
+# \C may be disabled
+
+$sim ./pcre2test -C backslash-C >/dev/null
+supportBSC=$?
+
+# Initialize all bitsizes skipped
+
+test8=skip
+test16=skip
+test32=skip
+
+# If no bitsize arguments, select all that are available
+
+if [ "$arg8$arg16$arg32" = "" ] ; then
+  if [ $support8 -ne 0 ] ; then
+    test8=-8
+  fi
+  if [ $support16 -ne 0 ] ; then
+    test16=-16
+  fi
+  if [ $support32 -ne 0 ] ; then
+    test32=-32
+  fi
+
+# Otherwise, select requested bit sizes
+
+else
+  if [ "$arg8" = yes ] ; then
+    if [ $support8 -eq 0 ] ; then
+      echo "Cannot run 8-bit library tests: 8-bit library not compiled"
+      exit 1
+    fi
+    test8=-8
+  fi
+  if [ "$arg16" = yes ] ; then
+    if [ $support16 -eq 0 ] ; then
+      echo "Cannot run 16-bit library tests: 16-bit library not compiled"
+      exit 1
+    fi
+    test16=-16
+  fi
+  if [ "$arg32" = yes ] ; then
+    if [ $support32 -eq 0 ] ; then
+      echo "Cannot run 32-bit library tests: 32-bit library not compiled"
+      exit 1
+    fi
+    test32=-32
+  fi
+fi
+
+# UTF support is implied by Unicode support, and it always applies to all bit
+# sizes if both are supported; we can't have UTF-8 support without UTF-16 or
+# UTF-32 support.
+
+$sim ./pcre2test -C unicode >/dev/null
+utf=$?
+
+# When JIT is used with valgrind, we need to set up valgrind suppressions as
+# otherwise there are a lot of false positive valgrind reports when the
+# the hardware supports SSE2.
+
+jitopt=
+$sim ./pcre2test -C jit >/dev/null
+jit=$?
+if [ $jit -ne 0 -a "$nojit" != "yes" ] ; then
+  jitopt=-jit
+  if [ "$valgrind" != "" ] ; then
+    vjs="--suppressions=$testdata/valgrind-jit.supp"
+  fi
+fi
+
+# If no specific tests were requested, select all. Those that are not
+# relevant will be automatically skipped.
+
+if [ $do0  = no -a $do1  = no -a $do2  = no -a $do3  = no -a \
+     $do4  = no -a $do5  = no -a $do6  = no -a $do7  = no -a \
+     $do8  = no -a $do9  = no -a $do10 = no -a $do11 = no -a \
+     $do12 = no -a $do13 = no -a $do14 = no -a $do15 = no -a \
+     $do16 = no -a $do17 = no -a $do18 = no -a $do19 = no -a \
+     $do20 = no -a $do21 = no -a $do22 = no -a $do23 = no -a \
+     $do24 = no -a $do25 = no \
+   ]; then
+  do0=yes
+  do1=yes
+  do2=yes
+  do3=yes
+  do4=yes
+  do5=yes
+  do6=yes
+  do7=yes
+  do8=yes
+  do9=yes
+  do10=yes
+  do11=yes
+  do12=yes
+  do13=yes
+  do14=yes
+  do15=yes
+  do16=yes
+  do17=yes
+  do18=yes
+  do19=yes
+  do20=yes
+  do21=yes
+  do22=yes
+  do23=yes
+  do24=yes
+  do25=yes
+fi
+
+# Handle any explicit skips at this stage, so that an argument list may consist
+# only of explicit skips.
+
+for i in $skip; do eval do$i=no; done
+
+# Show which release and which test data
+
+echo ""
+echo PCRE2 C library tests using test data from $testdata
+$sim ./pcre2test /dev/null
+echo ""
+
+for bmode in "$test8" "$test16" "$test32"; do
+  case "$bmode" in
+    skip) continue;;
+    -16)  if [ "$test8$test32" != "skipskip" ] ; then echo ""; fi
+          bits=16; echo "---- Testing 16-bit library ----"; echo "";;
+    -32)  if [ "$test8$test16" != "skipskip" ] ; then echo ""; fi
+          bits=32; echo "---- Testing 32-bit library ----"; echo "";;
+    -8)   bits=8; echo "---- Testing 8-bit library ----"; echo "";;
+  esac
+
+  # Test 0 is a special test. Its output is not checked, because it will
+  # be different on different hardware and with different configurations.
+  # Running this test just exercises the code.
+
+  if [ $do0 = yes ] ; then
+    echo $title0
+    echo '/abc/jit,memory,framesize' >testSinput
+    echo '   abc' >>testSinput
+    echo '' >testtry
+    checkspecial '-C'
+    checkspecial '--help'
+    checkspecial '-S 1 -t 10 testSinput'
+    echo "  OK"
+  fi
+
+  # Primary non-UTF test, compatible with JIT and all versions of Perl >= 5.8
+
+  if [ $do1 = yes ] ; then
+    echo $title1
+    for opt in "" $jitopt; do
+      $sim $valgrind ${opt:+$vjs} ./pcre2test -q $setstack $bmode $opt $testdata/testinput1 testtry
+      checkresult $? 1 "$opt"
+    done
+  fi
+
+  # PCRE2 tests that are not Perl-compatible: API, errors, internals. We copy
+  # the testbtables file to the current directory for use by this test.
+
+  if [ $do2 = yes ] ; then
+    echo $title2 "(excluding UTF-$bits)"
+    cp $testdata/testbtables .
+    for opt in "" $jitopt; do
+      $sim $valgrind ${opt:+$vjs} ./pcre2test -q $setstack $bmode $opt $testdata/testinput2 testtry
+      saverc=$?
+      if [ $saverc = 0 ] ; then
+        $sim $valgrind ${opt:+$vjs} ./pcre2test -q $bmode $opt -error -70,-62,-2,-1,0,100,101,191,200 >>testtry
+        checkresult $? 2 "$opt"
+      else
+        checkresult $saverc 2 "$opt"
+      fi
+    done
+  fi
+
+  # Locale-specific tests, provided that either the "fr_FR", "fr_CA", "french"
+  # or "fr" locale is available. The first two are Unix-like standards; the
+  # last two are for Windows. Unfortunately, different versions of the French
+  # locale give different outputs for some items. This test passes if the
+  # output matches any one of the alternative output files.
+
+  if [ $do3 = yes ] ; then
+    locale=
+
+    # In some environments locales that are listed by the "locale -a"
+    # command do not seem to work with setlocale(). Therefore, we do
+    # a preliminary test to see if pcre2test can set one before going
+    # on to use it.
+
+    for loc in 'fr_FR' 'french' 'fr' 'fr_CA'; do
+      locale -a | grep "^$loc\$" >/dev/null
+      if [ $? -eq 0 ] ; then
+        echo "/a/locale=$loc" | \
+          $sim $valgrind ./pcre2test -q $bmode | \
+            grep "Failed to set locale" >/dev/null
+        if [ $? -ne 0 ] ; then
+          locale=$loc
+          if [ "$locale" = "fr_FR" ] ; then
+            infile=$testdata/testinput3
+            outfile=$testdata/testoutput3
+            outfile2=$testdata/testoutput3A
+            outfile3=$testdata/testoutput3B
+          else
+            infile=test3input
+            outfile=test3output
+            outfile2=test3outputA
+            outfile3=test3outputB
+            sed "s/fr_FR/$loc/" $testdata/testinput3 >test3input
+            sed "s/fr_FR/$loc/" $testdata/testoutput3 >test3output
+            sed "s/fr_FR/$loc/" $testdata/testoutput3A >test3outputA
+            sed "s/fr_FR/$loc/" $testdata/testoutput3B >test3outputB
+          fi
+          break
+        fi
+      fi
+    done
+
+    if [ "$locale" != "" ] ; then
+      echo $title3 "(using '$locale' locale)"
+      for opt in "" $jitopt; do
+        $sim $valgrind ${opt:+$vjs} ./pcre2test -q $setstack $bmode $opt $infile testtry
+        if [ $? = 0 ] ; then
+          case "$opt" in
+            -jit) with=" with JIT";;
+            *)    with="";;
+          esac
+          if $cf $outfile testtry >teststdout || \
+             $cf $outfile2 testtry >teststdout || \
+             $cf $outfile3 testtry >teststdout
+          then
+            echo "  OK$with"
+          else
+            echo "** Locale test did not run successfully$with. The output did not match"
+            echo "   $outfile, $outfile2 or $outfile3."
+            echo "   This may mean that there is a problem with the locale settings rather"
+            echo "   than a bug in PCRE2."
+            exit 1
+          fi
+        else exit 1
+        fi
+      done
+    else
+      echo "Cannot test locale-specific features - none of the 'fr_FR', 'fr_CA',"
+      echo "'fr' or 'french' locales can be set, or the \"locale\" command is"
+      echo "not available to check for them."
+      echo " "
+    fi
+  fi
+
+  # Tests for UTF and Unicode property support
+
+  if [ $do4 = yes ] ; then
+    echo ${title4A}-${bits}${title4B}
+    if [ $utf -eq 0 ] ; then
+      echo "  Skipped because UTF-$bits support is not available"
+    else
+      for opt in "" $jitopt; do
+        $sim $valgrind ${opt:+$vjs} ./pcre2test -q $setstack $bmode $opt $testdata/testinput4 testtry
+        checkresult $? 4 "$opt"
+      done
+    fi
+  fi
+
+  if [ $do5 = yes ] ; then
+    echo ${title5A}-${bits}$title5B
+    if [ $utf -eq 0 ] ; then
+      echo "  Skipped because UTF-$bits support is not available"
+    else
+      for opt in "" $jitopt; do
+        $sim $valgrind ${opt:+$vjs} ./pcre2test -q $setstack $bmode $opt $testdata/testinput5 testtry
+        checkresult $? 5 "$opt"
+      done
+    fi
+  fi
+
+  # Tests for DFA matching support
+
+  if [ $do6 = yes ] ; then
+    echo $title6
+    $sim $valgrind ./pcre2test -q $setstack $bmode $testdata/testinput6 testtry
+    checkresult $? 6 ""
+  fi
+
+  if [ $do7 = yes ] ; then
+    echo ${title7A}-${bits}$title7B
+    if [ $utf -eq 0 ] ; then
+      echo "  Skipped because UTF-$bits support is not available"
+    else
+      $sim $valgrind ./pcre2test -q $setstack $bmode $opt $testdata/testinput7 testtry
+      checkresult $? 7 ""
+    fi
+  fi
+
+  # Test of internal offsets and code sizes. This test is run only when there
+  # is UTF/UCP support. The actual tests are mostly the same as in some of the
+  # above, but in this test we inspect some offsets and sizes. This is a
+  # doublecheck for the maintainer, just in case something changes unexpectely.
+  # The output from this test is different in 8-bit, 16-bit, and 32-bit modes
+  # and for different link sizes, so there are different output files for each
+  # mode and link size.
+
+  if [ $do8 = yes ] ; then
+    echo $title8
+    if [ $utf -eq 0 ] ; then
+      echo "  Skipped because UTF-$bits support is not available"
+    else
+      $sim $valgrind ./pcre2test -q $setstack $bmode $testdata/testinput8 testtry
+      checkresult $? 8-$bits-$link_size ""
+    fi
+  fi
+
+  # Tests for 8-bit-specific features
+
+  if [ "$do9" = yes ] ; then
+    echo $title9
+    if [ "$bits" = "16" -o "$bits" = "32" ] ; then
+      echo "  Skipped when running 16/32-bit tests"
+    else
+      for opt in "" $jitopt; do
+        $sim $valgrind ${opt:+$vjs} ./pcre2test -q $setstack $bmode $opt $testdata/testinput9 testtry
+        checkresult $? 9 "$opt"
+      done
+    fi
+  fi
+
+  # Tests for UTF-8 and UCP 8-bit-specific features
+
+  if [ "$do10" = yes ] ; then
+    echo $title10
+    if [ "$bits" = "16" -o "$bits" = "32" ] ; then
+      echo "  Skipped when running 16/32-bit tests"
+    elif [ $utf -eq 0 ] ; then
+      echo "  Skipped because UTF-$bits support is not available"
+    else
+      for opt in "" $jitopt; do
+        $sim $valgrind ${opt:+$vjs} ./pcre2test -q $setstack $bmode $opt $testdata/testinput10 testtry
+        checkresult $? 10 "$opt"
+      done
+    fi
+  fi
+
+  # Tests for 16-bit and 32-bit features. Output is different for the two widths.
+
+  if [ $do11 = yes ] ; then
+    echo $title11
+    if [ "$bits" = "8" ] ; then
+      echo "  Skipped when running 8-bit tests"
+    else
+      for opt in "" $jitopt; do
+        $sim $valgrind ${opt:+$vjs} ./pcre2test -q $setstack $bmode $opt $testdata/testinput11 testtry
+        checkresult $? 11-$bits "$opt"
+      done
+    fi
+  fi
+
+  # Tests for 16-bit and 32-bit features with UTF-16/32 and UCP support. Output
+  # is different for the two widths.
+
+  if [ $do12 = yes ] ; then
+    echo $title12
+    if [ "$bits" = "8" ] ; then
+      echo "  Skipped when running 8-bit tests"
+    elif [ $utf -eq 0 ] ; then
+      echo "  Skipped because UTF-$bits support is not available"
+    else
+      for opt in "" $jitopt; do
+        $sim $valgrind ${opt:+$vjs} ./pcre2test -q $setstack $bmode $opt $testdata/testinput12 testtry
+        checkresult $? 12-$bits "$opt"
+      done
+    fi
+  fi
+
+  # Tests for 16/32-bit-specific features in DFA non-UTF modes
+
+  if [ $do13 = yes ] ; then
+    echo $title13
+    if [ "$bits" = "8" ] ; then
+      echo "  Skipped when running 8-bit tests"
+    else
+      $sim $valgrind ./pcre2test -q $setstack $bmode $testdata/testinput13 testtry
+      checkresult $? 13 ""
+    fi
+  fi
+
+  # Tests for DFA UTF and UCP features. Output is different for the different widths.
+
+  if [ $do14 = yes ] ; then
+    echo $title14
+    if [ $utf -eq 0 ] ; then
+      echo "  Skipped because UTF-$bits support is not available"
+    else
+      $sim $valgrind ./pcre2test -q $setstack $bmode $opt $testdata/testinput14 testtry
+      checkresult $? 14-$bits ""
+    fi
+  fi
+
+  # Test non-JIT match and recursion limits
+
+  if [ $do15 = yes ] ; then
+    echo $title15
+    $sim $valgrind ./pcre2test -q $setstack $bmode $testdata/testinput15 testtry
+    checkresult $? 15 ""
+  fi
+
+  # Test JIT-specific features when JIT is not available
+
+  if [ $do16 = yes ] ; then
+    echo $title16
+    if [ $jit -ne 0 ] ; then
+      echo "  Skipped because JIT is available"
+    else
+      $sim $valgrind ./pcre2test -q $setstack $bmode $testdata/testinput16 testtry
+      checkresult $? 16 ""
+    fi
+  fi
+
+  # Test JIT-specific features when JIT is available
+
+  if [ $do17 = yes ] ; then
+    echo $title17
+    if [ $jit -eq 0 -o "$nojit" = "yes" ] ; then
+      echo "  Skipped because JIT is not available or nojit was specified"
+    else
+      $sim $valgrind $vjs ./pcre2test -q $setstack $bmode $testdata/testinput17 testtry
+      checkresult $? 17 ""
+    fi
+  fi
+
+  # Tests for the POSIX interface without UTF/UCP (8-bit only)
+
+  if [ $do18 = yes ] ; then
+    echo $title18
+    if [ "$bits" = "16" -o "$bits" = "32" ] ; then
+      echo "  Skipped when running 16/32-bit tests"
+    else
+      $sim $valgrind ./pcre2test -q $setstack $bmode $testdata/testinput18 testtry
+      checkresult $? 18 ""
+    fi
+  fi
+
+  # Tests for the POSIX interface with UTF/UCP (8-bit only)
+
+  if [ $do19 = yes ] ; then
+    echo $title19
+    if [ "$bits" = "16" -o "$bits" = "32" ] ; then
+      echo "  Skipped when running 16/32-bit tests"
+    elif [ $utf -eq 0 ] ; then
+      echo "  Skipped because UTF-$bits support is not available"
+    else
+      $sim $valgrind ./pcre2test -q $setstack $bmode $testdata/testinput19 testtry
+      checkresult $? 19 ""
+    fi
+  fi
+
+  # Serialization tests
+
+  if [ $do20 = yes ] ; then
+    echo $title20
+    $sim $valgrind ./pcre2test -q $setstack $bmode $testdata/testinput20 testtry
+    checkresult $? 20 ""
+  fi
+
+  # \C tests without UTF - DFA matching is supported
+
+  if [ "$do21" = yes ] ; then
+    echo $title21
+    if [ $supportBSC -eq 0 ] ; then
+      echo "  Skipped because \C is disabled"
+    else
+      for opt in "" $jitopt -dfa; do
+        $sim $valgrind ${opt:+$vjs} ./pcre2test -q $setstack $bmode $opt $testdata/testinput21 testtry
+        checkresult $? 21 "$opt"
+      done
+    fi
+  fi
+
+  # \C tests with UTF - DFA matching is not supported for \C in UTF mode
+
+  if [ "$do22" = yes ] ; then
+    echo $title22
+    if [ $supportBSC -eq 0 ] ; then
+      echo "  Skipped because \C is disabled"
+    elif [ $utf -eq 0 ] ; then
+      echo "  Skipped because UTF-$bits support is not available"
+    else
+      for opt in "" $jitopt; do
+        $sim $valgrind ${opt:+$vjs} ./pcre2test -q $setstack $bmode $opt $testdata/testinput22 testtry
+        checkresult $? 22-$bits "$opt"
+      done
+    fi
+  fi
+
+  # Test when \C is disabled
+
+  if [ "$do23" = yes ] ; then
+    echo $title23
+    if [ $supportBSC -ne 0 ] ; then
+      echo "  Skipped because \C is not disabled"
+    else
+      $sim $valgrind ./pcre2test -q $setstack $bmode $testdata/testinput23 testtry
+      checkresult $? 23 ""
+    fi
+  fi
+
+  # Non-UTF pattern conversion tests
+
+  if [ "$do24" = yes ] ; then
+    echo $title24
+    $sim $valgrind ./pcre2test -q $setstack $bmode $testdata/testinput24 testtry
+    checkresult $? 24 ""
+  fi
+
+  # UTF pattern conversion tests
+
+  if [ "$do25" = yes ] ; then
+    echo $title25
+    if [ $utf -eq 0 ] ; then
+      echo "  Skipped because UTF-$bits support is not available"
+    else
+      $sim $valgrind ./pcre2test -q $setstack $bmode $testdata/testinput25 testtry
+      checkresult $? 25 ""
+    fi
+  fi
+
+# End of loop for 8/16/32-bit tests
+done
+
+# Clean up local working files
+rm -f testbtables testSinput test3input testsaved1 testsaved2 test3output test3outputA test3outputB teststdout teststderr testtry
+
+# End

src/regex/pcre2/RunTest.bat

@@ -0,0 +1,525 @@
+@echo off
+@rem
+@rem MS Windows batch file to run pcre2test on testfiles with the correct
+@rem options. This file must use CRLF linebreaks to function properly,
+@rem and requires both pcre2test and pcre2grep.
+@rem
+@rem ------------------------ HISTORY ----------------------------------
+@rem This file was originally contributed to PCRE1 by Ralf Junker, and touched
+@rem up by Daniel Richard G. Tests 10-12 added by Philip H.
+@rem Philip H also changed test 3 to use "wintest" files.
+@rem
+@rem Updated by Tom Fortmann to support explicit test numbers on the command
+@rem line. Added argument validation and added error reporting.
+@rem
+@rem Sheri Pierce added logic to skip feature dependent tests
+@rem tests 4 5 7 10 12 14 19 and 22 require Unicode support
+@rem 8 requires Unicode and link size 2
+@rem 16 requires absence of jit support
+@rem 17 requires presence of jit support
+@rem Sheri P also added override tests for study and jit testing
+@rem Zoltan Herczeg added libpcre16 support
+@rem Zoltan Herczeg added libpcre32 support
+@rem -------------------------------------------------------------------
+@rem
+@rem The file was converted for PCRE2 by PH, February 2015.
+@rem Updated for new test 14 (moving others up a number), August 2015.
+@rem Tidied and updated for new tests 21, 22, 23 by PH, October 2015.
+@rem PH added missing "set type" for test 22, April 2016.
+@rem PH added copy command for new testbtables file, November 2020
+
+
+setlocal enabledelayedexpansion
+if [%srcdir%]==[] (
+if exist testdata\ set srcdir=.)
+if [%srcdir%]==[] (
+if exist ..\testdata\ set srcdir=..)
+if [%srcdir%]==[] (
+if exist ..\..\testdata\ set srcdir=..\..)
+if NOT exist %srcdir%\testdata\ (
+Error: echo distribution testdata folder not found!
+call :conferror
+exit /b 1
+goto :eof
+)
+
+if [%pcre2test%]==[] set pcre2test=.\pcre2test.exe
+
+echo source dir is %srcdir%
+echo pcre2test=%pcre2test%
+
+if NOT exist %pcre2test% (
+echo Error: %pcre2test% not found!
+echo.
+call :conferror
+exit /b 1
+)
+
+%pcre2test% -C linksize >NUL
+set link_size=%ERRORLEVEL%
+%pcre2test% -C pcre2-8 >NUL
+set support8=%ERRORLEVEL%
+%pcre2test% -C pcre2-16 >NUL
+set support16=%ERRORLEVEL%
+%pcre2test% -C pcre2-32 >NUL
+set support32=%ERRORLEVEL%
+%pcre2test% -C unicode >NUL
+set unicode=%ERRORLEVEL%
+%pcre2test% -C jit >NUL
+set jit=%ERRORLEVEL%
+%pcre2test% -C backslash-C >NUL
+set supportBSC=%ERRORLEVEL%
+
+if %support8% EQU 1 (
+if not exist testout8 md testout8
+if not exist testoutjit8 md testoutjit8
+)
+
+if %support16% EQU 1 (
+if not exist testout16 md testout16
+if not exist testoutjit16 md testoutjit16
+)
+
+if %support16% EQU 1 (
+if not exist testout32 md testout32
+if not exist testoutjit32 md testoutjit32
+)
+
+set do1=no
+set do2=no
+set do3=no
+set do4=no
+set do5=no
+set do6=no
+set do7=no
+set do8=no
+set do9=no
+set do10=no
+set do11=no
+set do12=no
+set do13=no
+set do14=no
+set do15=no
+set do16=no
+set do17=no
+set do18=no
+set do19=no
+set do20=no
+set do21=no
+set do22=no
+set do23=no
+set all=yes
+
+for %%a in (%*) do (
+  set valid=no
+  for %%v in (1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23) do if %%v == %%a set valid=yes
+  if "!valid!" == "yes" (
+    set do%%a=yes
+    set all=no
+) else (
+    echo Invalid test number - %%a!
+        echo Usage %0 [ test_number ] ...
+        echo Where test_number is one or more optional test numbers 1 through 23, default is all tests.
+        exit /b 1
+)
+)
+set failed="no"
+
+if "%all%" == "yes" (
+  set do1=yes
+  set do2=yes
+  set do3=yes
+  set do4=yes
+  set do5=yes
+  set do6=yes
+  set do7=yes
+  set do8=yes
+  set do9=yes
+  set do10=yes
+  set do11=yes
+  set do12=yes
+  set do13=yes
+  set do14=yes
+  set do15=yes
+  set do16=yes
+  set do17=yes
+  set do18=yes
+  set do19=yes
+  set do20=yes
+  set do21=yes
+  set do22=yes
+  set do23=yes
+)
+
+@echo RunTest.bat's pcre2test output is written to newly created subfolders
+@echo named testout{8,16,32} and testoutjit{8,16,32}.
+@echo.
+
+set mode=
+set bits=8
+
+:nextMode
+if "%mode%" == "" (
+  if %support8% EQU 0 goto modeSkip
+  echo.
+  echo ---- Testing 8-bit library ----
+  echo.
+)
+if "%mode%" == "-16" (
+  if %support16% EQU 0 goto modeSkip
+  echo.
+  echo ---- Testing 16-bit library ----
+  echo.
+)
+if "%mode%" == "-32" (
+  if %support32% EQU 0 goto modeSkip
+  echo.
+  echo ---- Testing 32-bit library ----
+  echo.
+)
+if "%do1%" == "yes" call :do1
+if "%do2%" == "yes" call :do2
+if "%do3%" == "yes" call :do3
+if "%do4%" == "yes" call :do4
+if "%do5%" == "yes" call :do5
+if "%do6%" == "yes" call :do6
+if "%do7%" == "yes" call :do7
+if "%do8%" == "yes" call :do8
+if "%do9%" == "yes" call :do9
+if "%do10%" == "yes" call :do10
+if "%do11%" == "yes" call :do11
+if "%do12%" == "yes" call :do12
+if "%do13%" == "yes" call :do13
+if "%do14%" == "yes" call :do14
+if "%do15%" == "yes" call :do15
+if "%do16%" == "yes" call :do16
+if "%do17%" == "yes" call :do17
+if "%do18%" == "yes" call :do18
+if "%do19%" == "yes" call :do19
+if "%do20%" == "yes" call :do20
+if "%do21%" == "yes" call :do21
+if "%do22%" == "yes" call :do22
+if "%do23%" == "yes" call :do23
+:modeSkip
+if "%mode%" == "" (
+  set mode=-16
+  set bits=16
+  goto nextMode
+)
+if "%mode%" == "-16" (
+  set mode=-32
+  set bits=32
+  goto nextMode
+)
+
+@rem If mode is -32, testing is finished
+if %failed% == "yes" (
+echo In above output, one or more of the various tests failed!
+exit /b 1
+)
+echo All OK
+goto :eof
+
+:runsub
+@rem Function to execute pcre2test and compare the output
+@rem Arguments are as follows:
+@rem
+@rem       1 = test number
+@rem       2 = outputdir
+@rem       3 = test name use double quotes
+@rem   4 - 9 = pcre2test options
+
+if [%1] == [] (
+  echo Missing test number argument!
+  exit /b 1
+)
+
+if [%2] == [] (
+  echo Missing outputdir!
+  exit /b 1
+)
+
+if [%3] == [] (
+  echo Missing test name argument!
+  exit /b 1
+)
+
+if %1 == 8 (
+  set outnum=8-%bits%-%link_size%
+) else (
+  set outnum=%1
+)
+set testinput=testinput%1
+set testoutput=testoutput%outnum%
+if exist %srcdir%\testdata\win%testinput% (
+  set testinput=wintestinput%1
+  set testoutput=wintestoutput%outnum%
+)
+
+echo Test %1: %3
+%pcre2test% %mode% %4 %5 %6 %7 %8 %9 %srcdir%\testdata\%testinput% >%2%bits%\%testoutput%
+if errorlevel 1 (
+  echo.          failed executing command-line:
+  echo.            %pcre2test% %mode% %4 %5 %6 %7 %8 %9 %srcdir%\testdata\%testinput% ^>%2%bits%\%testoutput%
+  set failed="yes"
+  goto :eof
+) else if [%1]==[2] (
+  %pcre2test% %mode% %4 %5 %6 %7 %8 %9 -error -70,-62,-2,-1,0,100,101,191,200 >>%2%bits%\%testoutput%
+)
+
+set type=
+if [%1]==[11] (
+  set type=-%bits%
+)
+if [%1]==[12] (
+  set type=-%bits%
+)
+if [%1]==[14] (
+  set type=-%bits%
+)
+if [%1]==[22] (
+  set type=-%bits%
+)
+
+fc /n %srcdir%\testdata\%testoutput%%type% %2%bits%\%testoutput% >NUL
+
+if errorlevel 1 (
+  echo.          failed comparison: fc /n %srcdir%\testdata\%testoutput% %2%bits%\%testoutput%
+  if [%1]==[3] (
+    echo.
+    echo ** Test 3 failure usually means french locale is not
+    echo ** available on the system, rather than a bug or problem with PCRE2.
+    echo.
+    goto :eof
+)
+
+  set failed="yes"
+  goto :eof
+)
+
+echo.          Passed.
+goto :eof
+
+:do1
+call :runsub 1 testout "Main non-UTF, non-UCP functionality (Compatible with Perl >= 5.10)" -q
+if %jit% EQU 1 call :runsub 1 testoutjit "Test with JIT Override" -q -jit
+goto :eof
+
+:do2
+  copy /y %srcdir%\testdata\testbtables testbtables
 
+  call :runsub 2 testout "API, errors, internals, and non-Perl stuff" -q
+  if %jit% EQU 1 call :runsub 2 testoutjit "Test with JIT Override" -q -jit
+goto :eof
+
+:do3
+  call :runsub 3 testout "Locale-specific features" -q
+  if %jit% EQU 1 call :runsub 3 testoutjit "Test with JIT Override" -q -jit
+goto :eof
+
+:do4
+if %unicode% EQU 0 (
+  echo Test 4 Skipped due to absence of Unicode support.
+  goto :eof
+)
+  call :runsub 4 testout "UTF-%bits% and Unicode property support - (Compatible with Perl >= 5.10)" -q
+  if %jit% EQU 1 call :runsub 4 testoutjit "Test with JIT Override" -q -jit
+goto :eof
+
+:do5
+if %unicode% EQU 0 (
+  echo Test 5 Skipped due to absence of Unicode support.
+  goto :eof
+)
+  call :runsub 5 testout "API, internals, and non-Perl stuff for UTF-%bits% and UCP" -q
+  if %jit% EQU 1 call :runsub 5 testoutjit "Test with JIT Override" -q -jit
+goto :eof
+
+:do6
+  call :runsub 6 testout "DFA matching main non-UTF, non-UCP functionality" -q
+goto :eof
+
+:do7
+if %unicode% EQU 0 (
+  echo Test 7 Skipped due to absence of Unicode support.
+  goto :eof
+)
+  call :runsub 7 testout "DFA matching with UTF-%bits% and Unicode property support" -q
+  goto :eof
+
+:do8
+if NOT %link_size% EQU 2 (
+  echo Test 8 Skipped because link size is not 2.
+  goto :eof
+)
+if %unicode% EQU 0 (
+  echo Test 8 Skipped due to absence of Unicode support.
+  goto :eof
+)
+  call :runsub 8 testout "Internal offsets and code size tests" -q
+goto :eof
+
+:do9
+if NOT %bits% EQU 8 (
+  echo Test 9 Skipped when running 16/32-bit tests.
+  goto :eof
+)
+  call :runsub 9 testout "Specials for the basic 8-bit library" -q
+  if %jit% EQU 1 call :runsub 9 testoutjit "Test with JIT Override" -q -jit
+goto :eof
+
+:do10
+if NOT %bits% EQU 8 (
+  echo Test 10 Skipped when running 16/32-bit tests.
+  goto :eof
+)
+if %unicode% EQU 0 (
+  echo Test 10 Skipped due to absence of Unicode support.
+  goto :eof
+)
+  call :runsub 10 testout "Specials for the 8-bit library with Unicode support" -q
+  if %jit% EQU 1 call :runsub 10 testoutjit "Test with JIT Override" -q -jit
+goto :eof
+
+:do11
+if %bits% EQU 8 (
+  echo Test 11 Skipped when running 8-bit tests.
+  goto :eof
+)
+  call :runsub 11 testout "Specials for the basic 16/32-bit library" -q
+  if %jit% EQU 1 call :runsub 11 testoutjit "Test with JIT Override" -q -jit
+goto :eof
+
+:do12
+if %bits% EQU 8 (
+  echo Test 12 Skipped when running 8-bit tests.
+  goto :eof
+)
+if %unicode% EQU 0 (
+  echo Test 12 Skipped due to absence of Unicode support.
+  goto :eof
+)
+  call :runsub 12 testout "Specials for the 16/32-bit library with Unicode support" -q
+  if %jit% EQU 1 call :runsub 12 testoutjit "Test with JIT Override" -q -jit
+goto :eof
+
+:do13
+if %bits% EQU 8 (
+  echo Test 13 Skipped when running 8-bit tests.
+  goto :eof
+)
+  call :runsub 13 testout "DFA specials for the basic 16/32-bit library" -q
+goto :eof
+
+:do14
+if %unicode% EQU 0 (
+  echo Test 14 Skipped due to absence of Unicode support.
+  goto :eof
+)
+  call :runsub 14 testout "DFA specials for UTF and UCP support" -q
+  goto :eof
+
+:do15
+call :runsub 15 testout "Non-JIT limits and other non_JIT tests" -q
+goto :eof
+
+:do16
+if %jit% EQU 1 (
+  echo Test 16 Skipped due to presence of JIT support.
+  goto :eof
+)
+  call :runsub 16 testout "JIT-specific features when JIT is not available" -q
+goto :eof
+
+:do17
+if %jit% EQU 0 (
+  echo Test 17 Skipped due to absence of JIT support.
+  goto :eof
+)
+  call :runsub 17 testout "JIT-specific features when JIT is available" -q
+goto :eof
+
+:do18
+if %bits% EQU 16 (
+  echo Test 18 Skipped when running 16-bit tests.
+  goto :eof
+)
+if %bits% EQU 32 (
+  echo Test 18 Skipped when running 32-bit tests.
+  goto :eof
+)
+  call :runsub 18 testout "POSIX interface, excluding UTF-8 and UCP" -q
+goto :eof
+
+:do19
+if %bits% EQU 16 (
+  echo Test 19 Skipped when running 16-bit tests.
+  goto :eof
+)
+if %bits% EQU 32 (
+  echo Test 19 Skipped when running 32-bit tests.
+  goto :eof
+)
+if %unicode% EQU 0 (
+  echo Test 19 Skipped due to absence of Unicode support.
+  goto :eof
+)
+  call :runsub 19 testout "POSIX interface with UTF-8 and UCP" -q
+goto :eof
+
+:do20
+call :runsub 20 testout "Serialization tests" -q
+goto :eof
+
+:do21
+if %supportBSC% EQU 0 (
+  echo Test 21 Skipped due to absence of backslash-C support.
+  goto :eof
+)
+  call :runsub 21 testout "Backslash-C tests without UTF" -q
+  call :runsub 21 testout "Backslash-C tests without UTF (DFA)" -q -dfa
+  if %jit% EQU 1 call :runsub 21 testoutjit "Test with JIT Override" -q -jit
+goto :eof
+
+:do22
+if %supportBSC% EQU 0 (
+  echo Test 22 Skipped due to absence of backslash-C support.
+  goto :eof
+)
+if %unicode% EQU 0 (
+  echo Test 22 Skipped due to absence of Unicode support.
+  goto :eof
+)
+  call :runsub 22 testout "Backslash-C tests with UTF" -q
+  if %jit% EQU 1 call :runsub 22 testoutjit "Test with JIT Override" -q -jit
+goto :eof
+
+:do23
+if %supportBSC% EQU 1 (
+  echo Test 23 Skipped due to presence of backslash-C support.
+  goto :eof
+)
+  call :runsub 23 testout "Backslash-C disabled test" -q
+goto :eof
+
+:conferror
+@echo.
+@echo Either your build is incomplete or you have a configuration error.
+@echo.
+@echo If configured with cmake and executed via "make test" or the MSVC "RUN_TESTS"
+@echo project, pcre2_test.bat defines variables and automatically calls RunTest.bat.
+@echo For manual testing of all available features, after configuring with cmake
+@echo and building, you can run the built pcre2_test.bat. For best results with
+@echo cmake builds and tests avoid directories with full path names that include
+@echo spaces for source or build.
+@echo.
+@echo Otherwise, if the build dir is in a subdir of the source dir, testdata needed
+@echo for input and verification should be found automatically when (from the
+@echo location of the the built exes) you call RunTest.bat. By default RunTest.bat
+@echo runs all tests compatible with the linked pcre2 library but it can be given
+@echo a test number as an argument.
+@echo.
+@echo If the build dir is not under the source dir you can either copy your exes
+@echo to the source folder or copy RunTest.bat and the testdata folder to the
+@echo location of your built exes and then run RunTest.bat.
+@echo.
+goto :eof

src/regex/pcre2/autogen.sh

@@ -0,0 +1,45 @@
+#!/bin/sh
+
+# Running aclocal here first (as happened for a while) caused the macros that
+# libtoolize puts in the m4 directory to be newer than the aclocal.m4 file that
+# aclocal creates. This meant that the next "make" cause aclocal to be run
+# again. Moving aclocal to after libtoolize does not seem to cause any
+# problems, and it fixes this issue.
+
+# GNU libtool is named differently on some systems.  This code tries several
+# variants like glibtoolize (MacOSX) and libtoolize1x (FreeBSD)
+
+set +ex
+echo "Looking for a version of libtoolize (which can have different names)..."
+libtoolize=""
+for l in glibtoolize libtoolize15 libtoolize14 libtoolize ; do
+    $l --version > /dev/null 2>&1
+    if [ $? = 0 ]; then
+        libtoolize=$l
+        echo "Found $l" 
+        break
+    fi
+    echo "Did not find $l" 
+done
+
+if [ "x$libtoolize" = "x" ]; then
+    echo "Can't find libtoolize on your system"
+    exit 1
+fi
+
+set -ex
+$libtoolize -c -f
+rm -rf autom4te.cache Makefile.in aclocal.m4
+aclocal --force -I m4
+autoconf -f -W all,no-obsolete
+autoheader -f -W all
+
+# Added no-portability to suppress automake 1.12's warning about the use
+# of recursive variables.
+
+automake -a -c -f -W all,no-portability
+
+rm -rf autom4te.cache
+exit 0
+
+# end autogen.sh

src/regex/pcre2/cmake/COPYING-CMAKE-SCRIPTS

@@ -0,0 +1,22 @@
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions
+are met:
+
+1. Redistributions of source code must retain the copyright
+   notice, this list of conditions and the following disclaimer.
+2. Redistributions in binary form must reproduce the copyright
+   notice, this list of conditions and the following disclaimer in the
+   documentation and/or other materials provided with the distribution.
+3. The name of the author may not be used to endorse or promote products 
+   derived from this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
+IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
+OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
+IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
+INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
+NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
+THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

src/regex/pcre2/cmake/FindEditline.cmake

@@ -0,0 +1,17 @@
+# Modified from FindReadline.cmake (PH Feb 2012)
+
+if(EDITLINE_INCLUDE_DIR AND EDITLINE_LIBRARY AND NCURSES_LIBRARY)
+  set(EDITLINE_FOUND TRUE)
+else(EDITLINE_INCLUDE_DIR AND EDITLINE_LIBRARY AND NCURSES_LIBRARY)
+  FIND_PATH(EDITLINE_INCLUDE_DIR readline.h
+    /usr/include/editline
+    /usr/include/edit/readline  
+    /usr/include/readline
+  )
+  
+  FIND_LIBRARY(EDITLINE_LIBRARY NAMES edit)
+  include(FindPackageHandleStandardArgs)
+  FIND_PACKAGE_HANDLE_STANDARD_ARGS(Editline DEFAULT_MSG EDITLINE_INCLUDE_DIR EDITLINE_LIBRARY )
+
+  MARK_AS_ADVANCED(EDITLINE_INCLUDE_DIR EDITLINE_LIBRARY)
+endif(EDITLINE_INCLUDE_DIR AND EDITLINE_LIBRARY AND NCURSES_LIBRARY)

src/regex/pcre2/cmake/FindPackageHandleStandardArgs.cmake

@@ -0,0 +1,58 @@
+# FIND_PACKAGE_HANDLE_STANDARD_ARGS(NAME (DEFAULT_MSG|"Custom failure message") VAR1 ... )
+#    This macro is intended to be used in FindXXX.cmake modules files.
+#    It handles the REQUIRED and QUIET argument to FIND_PACKAGE() and
+#    it also sets the <UPPERCASED_NAME>_FOUND variable.
+#    The package is found if all variables listed are TRUE.
+#    Example:
+#
+#    FIND_PACKAGE_HANDLE_STANDARD_ARGS(LibXml2 DEFAULT_MSG LIBXML2_LIBRARIES LIBXML2_INCLUDE_DIR)
+#
+#    LibXml2 is considered to be found, if both LIBXML2_LIBRARIES and 
+#    LIBXML2_INCLUDE_DIR are valid. Then also LIBXML2_FOUND is set to TRUE.
+#    If it is not found and REQUIRED was used, it fails with FATAL_ERROR, 
+#    independent whether QUIET was used or not.
+#    If it is found, the location is reported using the VAR1 argument, so 
+#    here a message "Found LibXml2: /usr/lib/libxml2.so" will be printed out.
+#    If the second argument is DEFAULT_MSG, the message in the failure case will 
+#    be "Could NOT find LibXml2", if you don't like this message you can specify
+#    your own custom failure message there.
+
+MACRO(FIND_PACKAGE_HANDLE_STANDARD_ARGS _NAME _FAIL_MSG _VAR1 )
+
+  IF("${_FAIL_MSG}" STREQUAL "DEFAULT_MSG")
+    IF (${_NAME}_FIND_REQUIRED)
+      SET(_FAIL_MESSAGE "Could not find REQUIRED package ${_NAME}")
+    ELSE (${_NAME}_FIND_REQUIRED)
+      SET(_FAIL_MESSAGE "Could not find OPTIONAL package ${_NAME}")
+    ENDIF (${_NAME}_FIND_REQUIRED)
+  ELSE("${_FAIL_MSG}" STREQUAL "DEFAULT_MSG")
+    SET(_FAIL_MESSAGE "${_FAIL_MSG}")
+  ENDIF("${_FAIL_MSG}" STREQUAL "DEFAULT_MSG")
+
+  STRING(TOUPPER ${_NAME} _NAME_UPPER)
+
+  SET(${_NAME_UPPER}_FOUND TRUE)
+  IF(NOT ${_VAR1})
+    SET(${_NAME_UPPER}_FOUND FALSE)
+  ENDIF(NOT ${_VAR1})
+
+  FOREACH(_CURRENT_VAR ${ARGN})
+    IF(NOT ${_CURRENT_VAR})
+      SET(${_NAME_UPPER}_FOUND FALSE)
+    ENDIF(NOT ${_CURRENT_VAR})
+  ENDFOREACH(_CURRENT_VAR)
+
+  IF (${_NAME_UPPER}_FOUND)
+    IF (NOT ${_NAME}_FIND_QUIETLY)
+        MESSAGE(STATUS "Found ${_NAME}: ${${_VAR1}}")
+    ENDIF (NOT ${_NAME}_FIND_QUIETLY)
+  ELSE (${_NAME_UPPER}_FOUND)
+    IF (${_NAME}_FIND_REQUIRED)
+        MESSAGE(FATAL_ERROR "${_FAIL_MESSAGE}")
+    ELSE (${_NAME}_FIND_REQUIRED)
+      IF (NOT ${_NAME}_FIND_QUIETLY)
+        MESSAGE(STATUS "${_FAIL_MESSAGE}")
+      ENDIF (NOT ${_NAME}_FIND_QUIETLY)
+    ENDIF (${_NAME}_FIND_REQUIRED)
+  ENDIF (${_NAME_UPPER}_FOUND)
+ENDMACRO(FIND_PACKAGE_HANDLE_STANDARD_ARGS)

src/regex/pcre2/cmake/FindReadline.cmake

@@ -0,0 +1,29 @@
+# from http://websvn.kde.org/trunk/KDE/kdeedu/cmake/modules/FindReadline.cmake
+# http://websvn.kde.org/trunk/KDE/kdeedu/cmake/modules/COPYING-CMAKE-SCRIPTS
+# --> BSD licensed
+#
+# GNU Readline library finder
+if(READLINE_INCLUDE_DIR AND READLINE_LIBRARY AND NCURSES_LIBRARY)
+  set(READLINE_FOUND TRUE)
+else(READLINE_INCLUDE_DIR AND READLINE_LIBRARY AND NCURSES_LIBRARY)
+  FIND_PATH(READLINE_INCLUDE_DIR readline/readline.h
+    /usr/include/readline
+  )
+  
+# 2008-04-22 The next clause used to read like this:
+#
+#  FIND_LIBRARY(READLINE_LIBRARY NAMES readline)
+#        FIND_LIBRARY(NCURSES_LIBRARY NAMES ncurses )
+#        include(FindPackageHandleStandardArgs)
+#        FIND_PACKAGE_HANDLE_STANDARD_ARGS(Readline DEFAULT_MSG NCURSES_LIBRARY READLINE_INCLUDE_DIR READLINE_LIBRARY )
+#
+# I was advised to modify it such that it will find an ncurses library if
+# required, but not if one was explicitly given, that is, it allows the
+# default to be overridden. PH 
+
+  FIND_LIBRARY(READLINE_LIBRARY NAMES readline)
+        include(FindPackageHandleStandardArgs)
+        FIND_PACKAGE_HANDLE_STANDARD_ARGS(Readline DEFAULT_MSG READLINE_INCLUDE_DIR READLINE_LIBRARY )
+
+  MARK_AS_ADVANCED(READLINE_INCLUDE_DIR READLINE_LIBRARY)
+endif(READLINE_INCLUDE_DIR AND READLINE_LIBRARY AND NCURSES_LIBRARY)

src/regex/pcre2/config-cmake.h.in

@@ -0,0 +1,58 @@
+/* config.h for CMake builds */
+
+#cmakedefine HAVE_ATTRIBUTE_UNINITIALIZED 1
+#cmakedefine HAVE_DIRENT_H 1
+#cmakedefine HAVE_INTTYPES_H 1    
+#cmakedefine HAVE_STDINT_H 1                                                   
+#cmakedefine HAVE_STRERROR 1
+#cmakedefine HAVE_SYS_STAT_H 1
+#cmakedefine HAVE_SYS_TYPES_H 1
+#cmakedefine HAVE_UNISTD_H 1
+#cmakedefine HAVE_WINDOWS_H 1
+
+#cmakedefine HAVE_BCOPY 1
+#cmakedefine HAVE_MEMFD_CREATE 1
+#cmakedefine HAVE_MEMMOVE 1
+#cmakedefine HAVE_SECURE_GETENV 1
+#cmakedefine HAVE_STRERROR 1
+
+#cmakedefine PCRE2_STATIC 1
+
+#cmakedefine SUPPORT_PCRE2_8 1
+#cmakedefine SUPPORT_PCRE2_16 1
+#cmakedefine SUPPORT_PCRE2_32 1
+#cmakedefine PCRE2_DEBUG 1
+#cmakedefine DISABLE_PERCENT_ZT 1
+
+#cmakedefine SUPPORT_LIBBZ2 1
+#cmakedefine SUPPORT_LIBEDIT 1
+#cmakedefine SUPPORT_LIBREADLINE 1
+#cmakedefine SUPPORT_LIBZ 1
+
+#cmakedefine SUPPORT_JIT 1
+#cmakedefine SLJIT_PROT_EXECUTABLE_ALLOCATOR 1
+#cmakedefine SUPPORT_PCRE2GREP_JIT 1
+#cmakedefine SUPPORT_PCRE2GREP_CALLOUT 1
+#cmakedefine SUPPORT_PCRE2GREP_CALLOUT_FORK 1
+#cmakedefine SUPPORT_UNICODE 1
+#cmakedefine SUPPORT_VALGRIND 1
+
+#cmakedefine BSR_ANYCRLF 1
+#cmakedefine EBCDIC 1
+#cmakedefine EBCDIC_NL25 1
+#cmakedefine HEAP_MATCH_RECURSE 1
+#cmakedefine NEVER_BACKSLASH_C 1
+
+#define LINK_SIZE		@PCRE2_LINK_SIZE@
+#define HEAP_LIMIT              @PCRE2_HEAP_LIMIT@
+#define MATCH_LIMIT		@PCRE2_MATCH_LIMIT@
+#define MATCH_LIMIT_DEPTH	@PCRE2_MATCH_LIMIT_DEPTH@
+#define NEWLINE_DEFAULT         @NEWLINE_DEFAULT@
+#define PARENS_NEST_LIMIT       @PCRE2_PARENS_NEST_LIMIT@
+#define PCRE2GREP_BUFSIZE       @PCRE2GREP_BUFSIZE@
+#define PCRE2GREP_MAX_BUFSIZE   @PCRE2GREP_MAX_BUFSIZE@
+
+#define MAX_NAME_SIZE	32
+#define MAX_NAME_COUNT	10000
+
+/* end config.h for CMake builds */

src/regex/pcre2/configure.ac

@@ -0,0 +1,1115 @@
+dnl Process this file with autoconf to produce a configure script.
+
+dnl NOTE FOR MAINTAINERS: Do not use minor version numbers 08 or 09 because
+dnl the leading zeros may cause them to be treated as invalid octal constants
+dnl if a PCRE2 user writes code that uses PCRE2_MINOR as a number. There is now
+dnl a check further down that throws an error if 08 or 09 are used.
+
+dnl The PCRE2_PRERELEASE feature is for identifying release candidates. It might
+dnl be defined as -RC2, for example. For real releases, it should be empty.
+
+m4_define(pcre2_major, [10])
+m4_define(pcre2_minor, [37])
+m4_define(pcre2_prerelease, [])
+m4_define(pcre2_date, [2021-05-26])
+
+# Libtool shared library interface versions (current:revision:age)
+m4_define(libpcre2_8_version,     [10:2:10])
+m4_define(libpcre2_16_version,    [10:2:10])
+m4_define(libpcre2_32_version,    [10:2:10])
+m4_define(libpcre2_posix_version, [3:0:0])
+
+# NOTE: The CMakeLists.txt file searches for the above variables in the first
+# 50 lines of this file. Please update that if the variables above are moved.
+
+AC_PREREQ([2.60])
+AC_INIT([PCRE2],pcre2_major.pcre2_minor[]pcre2_prerelease,[],[pcre2])
+AC_CONFIG_SRCDIR([src/pcre2.h.in])
+AM_INIT_AUTOMAKE([dist-bzip2 dist-zip])
+m4_ifdef([AM_SILENT_RULES], [AM_SILENT_RULES([yes])])
+AC_CONFIG_HEADERS(src/config.h)
+
+# This was added at the suggestion of libtoolize (03-Jan-10)
+AC_CONFIG_MACRO_DIR([m4])
+
+# The default CFLAGS in Autoconf are "-g -O2" for gcc and just "-g" for any
+# other compiler. There doesn't seem to be a standard way of getting rid of the
+# -g (which I don't think is needed for a production library). This fudge seems
+# to achieve the necessary. First, we remember the externally set values of
+# CFLAGS. Then call the AC_PROG_CC macro to find the compiler - if CFLAGS is
+# not set, it will be set to Autoconf's defaults. Afterwards, if the original
+# values were not set, remove the -g from the Autoconf defaults.
+
+remember_set_CFLAGS="$CFLAGS"
+
+AC_PROG_CC
+AM_PROG_CC_C_O
+AC_USE_SYSTEM_EXTENSIONS
+
+if test "x$remember_set_CFLAGS" = "x"
+then
+  if test "$CFLAGS" = "-g -O2"
+  then
+    CFLAGS="-O2"
+  elif test "$CFLAGS" = "-g"
+  then
+    CFLAGS=""
+  fi
+fi
+
+# This is a new thing required to stop a warning from automake 1.12
+m4_ifdef([AM_PROG_AR], [AM_PROG_AR])
+
+# Check for a 64-bit integer type
+AC_TYPE_INT64_T
+
+AC_PROG_INSTALL
+LT_INIT([win32-dll])
+AC_PROG_LN_S
+
+# Check for GCC visibility feature
+
+PCRE2_VISIBILITY
+
+# Check for Clang __attribute__((uninitialized)) feature
+
+AC_MSG_CHECKING([for __attribute__((uninitialized))])
+AC_LANG_PUSH([C])
+tmp_CFLAGS=$CFLAGS
+CFLAGS="$CFLAGS -Werror"
+AC_COMPILE_IFELSE([AC_LANG_PROGRAM(,
+                   [[char buf[128] __attribute__((uninitialized));(void)buf]])],
+                   [pcre2_cc_cv_attribute_uninitialized=yes],
+                   [pcre2_cc_cv_attribute_uninitialized=no])
+AC_MSG_RESULT([$pcre2_cc_cv_attribute_uninitialized])
+if test "$pcre2_cc_cv_attribute_uninitialized" = yes; then
+  AC_DEFINE([HAVE_ATTRIBUTE_UNINITIALIZED], 1, [Define this if your compiler
+             supports __attribute__((uninitialized))])
+fi
+CFLAGS=$tmp_CFLAGS
+AC_LANG_POP([C])
+
+# Versioning
+
+PCRE2_MAJOR="pcre2_major"
+PCRE2_MINOR="pcre2_minor"
+PCRE2_PRERELEASE="pcre2_prerelease"
+PCRE2_DATE="pcre2_date"
+
+if test "$PCRE2_MINOR" = "08" -o "$PCRE2_MINOR" = "09"
+then
+  echo "***"
+  echo "*** Minor version number $PCRE2_MINOR must not be used. ***"
+  echo "*** Use only 00 to 07 or 10 onwards, to avoid octal issues. ***"
+  echo "***"
+  exit 1
+fi
+
+AC_SUBST(PCRE2_MAJOR)
+AC_SUBST(PCRE2_MINOR)
+AC_SUBST(PCRE2_PRERELEASE)
+AC_SUBST(PCRE2_DATE)
+
+# Set a more sensible default value for $(htmldir).
+if test "x$htmldir" = 'x${docdir}'
+then
+  htmldir='${docdir}/html'
+fi
+
+# Force an error for PCRE1 size options
+AC_ARG_ENABLE(pcre8,,,enable_pcre8=no)
+AC_ARG_ENABLE(pcre16,,,enable_pcre16=no)
+AC_ARG_ENABLE(pcre32,,,enable_pcre32=no)
+
+if test "$enable_pcre8$enable_pcre16$enable_pcre32" != "nonono"
+then
+  echo "** ERROR: Use --[[en|dis]]able-pcre2-[[8|16|32]], not --[[en|dis]]able-pcre[[8|16|32]]"
+  exit 1
+fi
+
+# Handle --disable-pcre2-8 (enabled by default)
+AC_ARG_ENABLE(pcre2-8,
+              AS_HELP_STRING([--disable-pcre2-8],
+                             [disable 8 bit character support]),
+              , enable_pcre2_8=unset)
+AC_SUBST(enable_pcre2_8)
+
+# Handle --enable-pcre2-16 (disabled by default)
+AC_ARG_ENABLE(pcre2-16,
+              AS_HELP_STRING([--enable-pcre2-16],
+                             [enable 16 bit character support]),
+              , enable_pcre2_16=unset)
+AC_SUBST(enable_pcre2_16)
+
+# Handle --enable-pcre2-32 (disabled by default)
+AC_ARG_ENABLE(pcre2-32,
+              AS_HELP_STRING([--enable-pcre2-32],
+                             [enable 32 bit character support]),
+              , enable_pcre2_32=unset)
+AC_SUBST(enable_pcre2_32)
+
+# Handle --enable-debug (disabled by default)
+AC_ARG_ENABLE(debug,
+              AS_HELP_STRING([--enable-debug],
+                             [enable debugging code]),
+              , enable_debug=no)
+
+# Handle --enable-jit (disabled by default)
+AC_ARG_ENABLE(jit,
+              AS_HELP_STRING([--enable-jit],
+                             [enable Just-In-Time compiling support]),
+              , enable_jit=no)
+
+# This code enables JIT if the hardware supports it.
+if test "$enable_jit" = "auto"; then
+  AC_LANG(C)
+  SAVE_CPPFLAGS=$CPPFLAGS
+  CPPFLAGS=-I$srcdir
+  AC_COMPILE_IFELSE([AC_LANG_SOURCE([[
+  #define SLJIT_CONFIG_AUTO 1
+  #include "src/sljit/sljitConfigInternal.h"
+  #if (defined SLJIT_CONFIG_UNSUPPORTED && SLJIT_CONFIG_UNSUPPORTED)
+  #error unsupported
+  #endif]])], enable_jit=yes, enable_jit=no)
+  CPPFLAGS=$SAVE_CPPFLAGS
+  echo checking for JIT support on this hardware... $enable_jit
+fi
+
+# Handle --enable-jit-sealloc (disabled by default and only experimental)
+case $host_os in
+  linux* | netbsd*)
+    AC_ARG_ENABLE(jit-sealloc,
+      AS_HELP_STRING([--enable-jit-sealloc],
+        [enable SELinux compatible execmem allocator in JIT (experimental)]),
+        ,enable_jit_sealloc=no)
+    ;;
+  *)
+    enable_jit_sealloc=unsupported
+    ;;
+esac
+
+# Handle --disable-pcre2grep-jit (enabled by default)
+AC_ARG_ENABLE(pcre2grep-jit,
+              AS_HELP_STRING([--disable-pcre2grep-jit],
+                             [disable JIT support in pcre2grep]),
+              , enable_pcre2grep_jit=yes)
+
+# Handle --disable-pcre2grep-callout (enabled by default)
+AC_ARG_ENABLE(pcre2grep-callout,
+              AS_HELP_STRING([--disable-pcre2grep-callout],
+                             [disable callout script support in pcre2grep]),
+              , enable_pcre2grep_callout=yes)
+
+# Handle --disable-pcre2grep-callout-fork (enabled by default)
+AC_ARG_ENABLE(pcre2grep-callout-fork,
+              AS_HELP_STRING([--disable-pcre2grep-callout-fork],
+                             [disable callout script fork support in pcre2grep]),
+              , enable_pcre2grep_callout_fork=yes)
+
+# Handle --enable-rebuild-chartables
+AC_ARG_ENABLE(rebuild-chartables,
+              AS_HELP_STRING([--enable-rebuild-chartables],
+                             [rebuild character tables in current locale]),
+              , enable_rebuild_chartables=no)
+
+# Handle --disable-unicode (enabled by default)
+AC_ARG_ENABLE(unicode,
+              AS_HELP_STRING([--disable-unicode],
+                             [disable Unicode support]),
+              , enable_unicode=unset)
+
+# Handle newline options
+ac_pcre2_newline=lf
+AC_ARG_ENABLE(newline-is-cr,
+              AS_HELP_STRING([--enable-newline-is-cr],
+                             [use CR as newline character]),
+              ac_pcre2_newline=cr)
+AC_ARG_ENABLE(newline-is-lf,
+              AS_HELP_STRING([--enable-newline-is-lf],
+                             [use LF as newline character (default)]),
+              ac_pcre2_newline=lf)
+AC_ARG_ENABLE(newline-is-crlf,
+              AS_HELP_STRING([--enable-newline-is-crlf],
+                             [use CRLF as newline sequence]),
+              ac_pcre2_newline=crlf)
+AC_ARG_ENABLE(newline-is-anycrlf,
+              AS_HELP_STRING([--enable-newline-is-anycrlf],
+                             [use CR, LF, or CRLF as newline sequence]),
+              ac_pcre2_newline=anycrlf)
+AC_ARG_ENABLE(newline-is-any,
+              AS_HELP_STRING([--enable-newline-is-any],
+                             [use any valid Unicode newline sequence]),
+              ac_pcre2_newline=any)
+AC_ARG_ENABLE(newline-is-nul,
+              AS_HELP_STRING([--enable-newline-is-nul],
+                             [use NUL (binary zero) as newline character]),
+              ac_pcre2_newline=nul)
+enable_newline="$ac_pcre2_newline"
+
+# Handle --enable-bsr-anycrlf
+AC_ARG_ENABLE(bsr-anycrlf,
+              AS_HELP_STRING([--enable-bsr-anycrlf],
+                             [\R matches only CR, LF, CRLF by default]),
+              , enable_bsr_anycrlf=no)
+
+# Handle --enable-never-backslash-C
+AC_ARG_ENABLE(never-backslash-C,
+              AS_HELP_STRING([--enable-never-backslash-C],
+                             [use of \C causes an error]),
+              , enable_never_backslash_C=no)
+
+# Handle --enable-ebcdic
+AC_ARG_ENABLE(ebcdic,
+              AS_HELP_STRING([--enable-ebcdic],
+                             [assume EBCDIC coding rather than ASCII; incompatible with --enable-utf; use only in (uncommon) EBCDIC environments; it implies --enable-rebuild-chartables]),
+              , enable_ebcdic=no)
+
+# Handle --enable-ebcdic-nl25
+AC_ARG_ENABLE(ebcdic-nl25,
+              AS_HELP_STRING([--enable-ebcdic-nl25],
+                             [set EBCDIC code for NL to 0x25 instead of 0x15; it implies --enable-ebcdic]),
+              , enable_ebcdic_nl25=no)
+
+# Handle --enable-pcre2grep-libz
+AC_ARG_ENABLE(pcre2grep-libz,
+              AS_HELP_STRING([--enable-pcre2grep-libz],
+                             [link pcre2grep with libz to handle .gz files]),
+              , enable_pcre2grep_libz=no)
+
+# Handle --enable-pcre2grep-libbz2
+AC_ARG_ENABLE(pcre2grep-libbz2,
+              AS_HELP_STRING([--enable-pcre2grep-libbz2],
+                             [link pcre2grep with libbz2 to handle .bz2 files]),
+              , enable_pcre2grep_libbz2=no)
+
+# Handle --with-pcre2grep-bufsize=N
+AC_ARG_WITH(pcre2grep-bufsize,
+              AS_HELP_STRING([--with-pcre2grep-bufsize=N],
+                             [pcre2grep initial buffer size (default=20480, minimum=8192)]),
+              , with_pcre2grep_bufsize=20480)
+
+# Handle --with-pcre2grep-max-bufsize=N
+AC_ARG_WITH(pcre2grep-max-bufsize,
+              AS_HELP_STRING([--with-pcre2grep-max-bufsize=N],
+                             [pcre2grep maximum buffer size (default=1048576, minimum=8192)]),
+              , with_pcre2grep_max_bufsize=1048576)
+
+# Handle --enable-pcre2test-libedit
+AC_ARG_ENABLE(pcre2test-libedit,
+              AS_HELP_STRING([--enable-pcre2test-libedit],
+                             [link pcre2test with libedit]),
+              , enable_pcre2test_libedit=no)
+
+# Handle --enable-pcre2test-libreadline
+AC_ARG_ENABLE(pcre2test-libreadline,
+              AS_HELP_STRING([--enable-pcre2test-libreadline],
+                             [link pcre2test with libreadline]),
+              , enable_pcre2test_libreadline=no)
+
+# Handle --with-link-size=N
+AC_ARG_WITH(link-size,
+            AS_HELP_STRING([--with-link-size=N],
+                           [internal link size (2, 3, or 4 allowed; default=2)]),
+            , with_link_size=2)
+
+# Handle --with-parens-nest-limit=N
+AC_ARG_WITH(parens-nest-limit,
+            AS_HELP_STRING([--with-parens-nest-limit=N],
+                           [nested parentheses limit (default=250)]),
+            , with_parens_nest_limit=250)
+
+# Handle --with-heap-limit
+AC_ARG_WITH(heap-limit,
+            AS_HELP_STRING([--with-heap-limit=N],
+                           [default limit on heap memory (kibibytes, default=20000000)]),
+            , with_heap_limit=20000000)
+
+# Handle --with-match-limit=N
+AC_ARG_WITH(match-limit,
+            AS_HELP_STRING([--with-match-limit=N],
+                           [default limit on internal looping (default=10000000)]),
+            , with_match_limit=10000000)
+
+# Handle --with-match-limit-depth=N
+# Recognize old synonym --with-match-limit-recursion
+#
+# Note: In config.h, the default is to define MATCH_LIMIT_DEPTH symbolically as
+# MATCH_LIMIT, which in turn is defined to be some numeric value (e.g.
+# 10000000). MATCH_LIMIT_DEPTH can otherwise be set to some different numeric
+# value (or even the same numeric value as MATCH_LIMIT, though no longer
+# defined in terms of the latter).
+#
+AC_ARG_WITH(match-limit-depth,
+            AS_HELP_STRING([--with-match-limit-depth=N],
+                           [default limit on match tree depth (default=MATCH_LIMIT)]),
+            , with_match_limit_depth=MATCH_LIMIT)
+
+AC_ARG_WITH(match-limit-recursion,,
+            , with_match_limit_recursion=UNSET)
+
+# Handle --enable-valgrind
+AC_ARG_ENABLE(valgrind,
+              AS_HELP_STRING([--enable-valgrind],
+                             [enable valgrind support]),
+              , enable_valgrind=no)
+
+# Enable code coverage reports using gcov
+AC_ARG_ENABLE(coverage,
+              AS_HELP_STRING([--enable-coverage],
+                             [enable code coverage reports using gcov]),
+              , enable_coverage=no)
+
+# Handle --enable-fuzz-support
+AC_ARG_ENABLE(fuzz_support,
+              AS_HELP_STRING([--enable-fuzz-support],
+                             [enable fuzzer support]),
+              , enable_fuzz_support=no)
+
+# Handle --disable-stack-for-recursion
+# This option became obsolete at release 10.30.
+AC_ARG_ENABLE(stack-for-recursion,,
+              , enable_stack_for_recursion=yes)
+
+# Original code
+# AC_ARG_ENABLE(stack-for-recursion,
+#               AS_HELP_STRING([--disable-stack-for-recursion],
+#                              [don't use stack recursion when matching]),
+#               , enable_stack_for_recursion=yes)
+
+# Handle --disable-percent_zt (set as "auto" by default)
+AC_ARG_ENABLE(percent-zt,
+              AS_HELP_STRING([--disable-percent-zt],
+                             [disable the use of z and t formatting modifiers]),
+              , enable_percent_zt=auto)
+
+# Set the default value for pcre2-8
+if test "x$enable_pcre2_8" = "xunset"
+then
+  enable_pcre2_8=yes
+fi
+
+# Set the default value for pcre2-16
+if test "x$enable_pcre2_16" = "xunset"
+then
+  enable_pcre2_16=no
+fi
+
+# Set the default value for pcre2-32
+if test "x$enable_pcre2_32" = "xunset"
+then
+  enable_pcre2_32=no
+fi
+
+# Make sure at least one library is selected
+if test "x$enable_pcre2_8$enable_pcre2_16$enable_pcre2_32" = "xnonono"
+then
+  AC_MSG_ERROR([At least one of the 8, 16 or 32 bit libraries must be enabled])
+fi
+
+# Unicode is enabled by default.
+if test "x$enable_unicode" = "xunset"
+then
+  enable_unicode=yes
+fi
+
+# Convert the newline identifier into the appropriate integer value. These must
+# agree with the PCRE2_NEWLINE_xxx values in pcre2.h.
+
+case "$enable_newline" in
+  cr)      ac_pcre2_newline_value=1 ;;
+  lf)      ac_pcre2_newline_value=2 ;;
+  crlf)    ac_pcre2_newline_value=3 ;;
+  any)     ac_pcre2_newline_value=4 ;;
+  anycrlf) ac_pcre2_newline_value=5 ;;
+  nul)     ac_pcre2_newline_value=6 ;;
+  *)
+  AC_MSG_ERROR([invalid argument "$enable_newline" to --enable-newline option])
+  ;;
+esac
+
+# --enable-ebcdic-nl25 implies --enable-ebcdic
+if test "x$enable_ebcdic_nl25" = "xyes"; then
+  enable_ebcdic=yes
+fi
+
+# Make sure that if enable_ebcdic is set, rebuild_chartables is also enabled.
+# Also check that UTF support is not requested, because PCRE2 cannot handle
+# EBCDIC and UTF in the same build. To do so it would need to use different
+# character constants depending on the mode. Also, EBCDIC cannot be used with
+# 16-bit and 32-bit libraries.
+#
+if test "x$enable_ebcdic" = "xyes"; then
+  enable_rebuild_chartables=yes
+  if test "x$enable_unicode" = "xyes"; then
+    AC_MSG_ERROR([support for EBCDIC and Unicode cannot be enabled at the same time])
+  fi
+  if test "x$enable_pcre2_16" = "xyes" -o "x$enable_pcre2_32" = "xyes"; then
+    AC_MSG_ERROR([EBCDIC support is available only for the 8-bit library])
+  fi
+fi
+
+# Check argument to --with-link-size
+case "$with_link_size" in
+  2|3|4) ;;
+  *)
+  AC_MSG_ERROR([invalid argument "$with_link_size" to --with-link-size option])
+  ;;
+esac
+
+AH_TOP([
+/* PCRE2 is written in Standard C, but there are a few non-standard things it
+can cope with, allowing it to run on SunOS4 and other "close to standard"
+systems.
+
+In environments that support the GNU autotools, config.h.in is converted into
+config.h by the "configure" script. In environments that use CMake,
+config-cmake.in is converted into config.h. If you are going to build PCRE2 "by
+hand" without using "configure" or CMake, you should copy the distributed
+config.h.generic to config.h, and edit the macro definitions to be the way you
+need them. You must then add -DHAVE_CONFIG_H to all of your compile commands,
+so that config.h is included at the start of every source.
+
+Alternatively, you can avoid editing by using -D on the compiler command line
+to set the macro values. In this case, you do not have to set -DHAVE_CONFIG_H,
+but if you do, default values will be taken from config.h for non-boolean
+macros that are not defined on the command line.
+
+Boolean macros such as HAVE_STDLIB_H and SUPPORT_PCRE2_8 should either be
+defined (conventionally to 1) for TRUE, and not defined at all for FALSE. All
+such macros are listed as a commented #undef in config.h.generic. Macros such
+as MATCH_LIMIT, whose actual value is relevant, have defaults defined, but are
+surrounded by #ifndef/#endif lines so that the value can be overridden by -D.
+
+PCRE2 uses memmove() if HAVE_MEMMOVE is defined; otherwise it uses bcopy() if
+HAVE_BCOPY is defined. If your system has neither bcopy() nor memmove(), make
+sure both macros are undefined; an emulation function will then be used. */])
+
+# Checks for header files.
+AC_CHECK_HEADERS(limits.h sys/types.h sys/stat.h dirent.h)
+AC_CHECK_HEADERS([windows.h], [HAVE_WINDOWS_H=1])
+AC_CHECK_HEADERS([sys/wait.h], [HAVE_SYS_WAIT_H=1])
+
+# Conditional compilation
+AM_CONDITIONAL(WITH_PCRE2_8, test "x$enable_pcre2_8" = "xyes")
+AM_CONDITIONAL(WITH_PCRE2_16, test "x$enable_pcre2_16" = "xyes")
+AM_CONDITIONAL(WITH_PCRE2_32, test "x$enable_pcre2_32" = "xyes")
+AM_CONDITIONAL(WITH_DEBUG, test "x$enable_debug" = "xyes")
+AM_CONDITIONAL(WITH_REBUILD_CHARTABLES, test "x$enable_rebuild_chartables" = "xyes")
+AM_CONDITIONAL(WITH_JIT, test "x$enable_jit" = "xyes")
+AM_CONDITIONAL(WITH_UNICODE, test "x$enable_unicode" = "xyes")
+AM_CONDITIONAL(WITH_VALGRIND, test "x$enable_valgrind" = "xyes")
+AM_CONDITIONAL(WITH_FUZZ_SUPPORT, test "x$enable_fuzz_support" = "xyes")
+
+if test "$enable_fuzz_support" = "yes" -a "$enable_pcre2_8" = "no"; then
+  echo "** ERROR: Fuzzer support requires the 8-bit library"
+  exit 1
+fi
+
+# Checks for typedefs, structures, and compiler characteristics.
+
+AC_C_CONST
+AC_TYPE_SIZE_T
+
+# Checks for library functions.
+
+AC_CHECK_FUNCS(bcopy memfd_create memmove mkostemp secure_getenv strerror)
+
+# Check for the availability of libz (aka zlib)
+
+AC_CHECK_HEADERS([zlib.h], [HAVE_ZLIB_H=1])
+AC_CHECK_LIB([z], [gzopen], [HAVE_LIBZ=1])
+
+# Check for the availability of libbz2. Originally we just used AC_CHECK_LIB,
+# as for libz. However, this had the following problem, diagnosed and fixed by
+# a user:
+#
+#   - libbz2 uses the Pascal calling convention (WINAPI) for the functions
+#     under Win32.
+#   - The standard autoconf AC_CHECK_LIB fails to include "bzlib.h",
+#     therefore missing the function definition.
+#   - The compiler thus generates a "C" signature for the test function.
+#   - The linker fails to find the "C" function.
+#   - PCRE2 fails to configure if asked to do so against libbz2.
+#
+# Solution:
+#
+#   - Replace the AC_CHECK_LIB test with a custom test.
+
+AC_CHECK_HEADERS([bzlib.h], [HAVE_BZLIB_H=1])
+# Original test
+# AC_CHECK_LIB([bz2], [BZ2_bzopen], [HAVE_LIBBZ2=1])
+#
+# Custom test follows
+
+AC_MSG_CHECKING([for libbz2])
+OLD_LIBS="$LIBS"
+LIBS="$LIBS -lbz2"
+AC_LINK_IFELSE([AC_LANG_PROGRAM([[
+#ifdef HAVE_BZLIB_H
+#include <bzlib.h>
+#endif]],
+[[return (int)BZ2_bzopen("conftest", "rb");]])],
+[AC_MSG_RESULT([yes]);HAVE_LIBBZ2=1; break;],
+AC_MSG_RESULT([no]))
+LIBS="$OLD_LIBS"
+
+# Check for the availabiity of libreadline
+
+if test "$enable_pcre2test_libreadline" = "yes"; then
+ AC_CHECK_HEADERS([readline/readline.h], [HAVE_READLINE_H=1])
+ AC_CHECK_HEADERS([readline/history.h], [HAVE_HISTORY_H=1])
+ AC_CHECK_LIB([readline], [readline], [LIBREADLINE="-lreadline"],
+   [unset ac_cv_lib_readline_readline;
+    AC_CHECK_LIB([readline], [readline], [LIBREADLINE="-ltinfo"],
+     [unset ac_cv_lib_readline_readline;
+      AC_CHECK_LIB([readline], [readline], [LIBREADLINE="-lcurses"],
+       [unset ac_cv_lib_readline_readline;
+        AC_CHECK_LIB([readline], [readline], [LIBREADLINE="-lncurses"],
+         [unset ac_cv_lib_readline_readline;
+	  AC_CHECK_LIB([readline], [readline], [LIBREADLINE="-lncursesw"],
+           [unset ac_cv_lib_readline_readline;
+	    AC_CHECK_LIB([readline], [readline], [LIBREADLINE="-ltermcap"],
+             [LIBREADLINE=""],
+             [-ltermcap])],
+           [-lncursesw])],
+         [-lncurses])],
+       [-lcurses])],
+     [-ltinfo])])
+ AC_SUBST(LIBREADLINE)
+ if test -n "$LIBREADLINE"; then
+   if test "$LIBREADLINE" != "-lreadline"; then
+     echo "-lreadline needs $LIBREADLINE"
+     LIBREADLINE="-lreadline $LIBREADLINE"
+   fi
+ fi
+fi
+
+
+# Check for the availability of libedit. Different distributions put its
+# headers in different places. Try to cover the most common ones.
+
+if test "$enable_pcre2test_libedit" = "yes"; then
+  AC_CHECK_HEADERS([editline/readline.h], [HAVE_EDITLINE_READLINE_H=1],
+    [AC_CHECK_HEADERS([edit/readline/readline.h], [HAVE_READLINE_READLINE_H=1],
+      [AC_CHECK_HEADERS([readline/readline.h], [HAVE_READLINE_READLINE_H=1])])])
+  AC_CHECK_LIB([edit], [readline], [LIBEDIT="-ledit"])
+fi
+
+PCRE2_STATIC_CFLAG=""
+if test "x$enable_shared" = "xno" ; then
+  AC_DEFINE([PCRE2_STATIC], [1], [
+    Define to any value if linking statically (TODO: make nice with Libtool)])
+  PCRE2_STATIC_CFLAG="-DPCRE2_STATIC"
+fi
+AC_SUBST(PCRE2_STATIC_CFLAG)
+
+# Here is where PCRE2-specific defines are handled
+
+if test "$enable_pcre2_8" = "yes"; then
+  AC_DEFINE([SUPPORT_PCRE2_8], [], [
+    Define to any value to enable the 8 bit PCRE2 library.])
+fi
+
+if test "$enable_pcre2_16" = "yes"; then
+  AC_DEFINE([SUPPORT_PCRE2_16], [], [
+    Define to any value to enable the 16 bit PCRE2 library.])
+fi
+
+if test "$enable_pcre2_32" = "yes"; then
+  AC_DEFINE([SUPPORT_PCRE2_32], [], [
+    Define to any value to enable the 32 bit PCRE2 library.])
+fi
+
+if test "$enable_debug" = "yes"; then
+  AC_DEFINE([PCRE2_DEBUG], [], [
+    Define to any value to include debugging code.])
+fi
+
+if test "$enable_percent_zt" = "no"; then
+  AC_DEFINE([DISABLE_PERCENT_ZT], [], [
+    Define to any value to disable the use of the z and t modifiers in
+    formatting settings such as %zu or %td (this is rarely needed).])
+else
+  enable_percent_zt=auto
+fi
+
+# Unless running under Windows, JIT support requires pthreads.
+
+if test "$enable_jit" = "yes"; then
+  if test "$HAVE_WINDOWS_H" != "1"; then
+    AX_PTHREAD([], [AC_MSG_ERROR([JIT support requires pthreads])])
+    CC="$PTHREAD_CC"
+    CFLAGS="$PTHREAD_CFLAGS $CFLAGS"
+    LIBS="$PTHREAD_LIBS $LIBS"
+  fi
+  AC_DEFINE([SUPPORT_JIT], [], [
+    Define to any value to enable support for Just-In-Time compiling.])
+else
+  enable_pcre2grep_jit="no"
+fi
+
+if test "$enable_jit_sealloc" = "yes"; then
+  AC_DEFINE([SLJIT_PROT_EXECUTABLE_ALLOCATOR], [1], [
+    Define to any non-zero number to enable support for SELinux
+    compatible executable memory allocator in JIT. Note that this
+    will have no effect unless SUPPORT_JIT is also defined.])
+fi
+
+if test "$enable_pcre2grep_jit" = "yes"; then
+  AC_DEFINE([SUPPORT_PCRE2GREP_JIT], [], [
+    Define to any value to enable JIT support in pcre2grep. Note that this will
+    have no effect unless SUPPORT_JIT is also defined.])
+fi
+
+if test "$enable_pcre2grep_callout" = "yes"; then
+  if test "$enable_pcre2grep_callout_fork" = "yes"; then
+    if test "$HAVE_WINDOWS_H" != "1"; then
+      if test "$HAVE_SYS_WAIT_H" != "1"; then
+        AC_MSG_ERROR([Callout script support needs sys/wait.h.])
+      fi
+    fi
+    AC_DEFINE([SUPPORT_PCRE2GREP_CALLOUT_FORK], [], [
+      Define to any value to enable fork support in pcre2grep callout scripts.
+      This will have no effect unless SUPPORT_PCRE2GREP_CALLOUT is also
+      defined.])
+  fi
+  AC_DEFINE([SUPPORT_PCRE2GREP_CALLOUT], [], [
+    Define to any value to enable callout script support in pcre2grep.])
+else
+  enable_pcre2grep_callout_fork="no"
+fi
+
+if test "$enable_unicode" = "yes"; then
+  AC_DEFINE([SUPPORT_UNICODE], [], [
+    Define to any value to enable support for Unicode and UTF encoding.
+    This will work even in an EBCDIC environment, but it is incompatible
+    with the EBCDIC macro. That is, PCRE2 can support *either* EBCDIC
+    code *or* ASCII/Unicode, but not both at once.])
+fi
+
+if test "$enable_pcre2grep_libz" = "yes"; then
+  AC_DEFINE([SUPPORT_LIBZ], [], [
+    Define to any value to allow pcre2grep to be linked with libz, so that it is
+    able to handle .gz files.])
+fi
+
+if test "$enable_pcre2grep_libbz2" = "yes"; then
+  AC_DEFINE([SUPPORT_LIBBZ2], [], [
+    Define to any value to allow pcre2grep to be linked with libbz2, so that it
+    is able to handle .bz2 files.])
+fi
+
+if test $with_pcre2grep_bufsize -lt 8192 ; then
+  AC_MSG_WARN([$with_pcre2grep_bufsize is too small for --with-pcre2grep-bufsize; using 8192])
+  with_pcre2grep_bufsize="8192"
+else
+  if test $? -gt 1 ; then
+  AC_MSG_ERROR([Bad value for --with-pcre2grep-bufsize])
+  fi
+fi
+
+if test $with_pcre2grep_max_bufsize -lt $with_pcre2grep_bufsize ; then
+  with_pcre2grep_max_bufsize="$with_pcre2grep_bufsize"
+else
+  if test $? -gt 1 ; then
+  AC_MSG_ERROR([Bad value for --with-pcre2grep-max-bufsize])
+  fi
+fi
+
+AC_DEFINE_UNQUOTED([PCRE2GREP_BUFSIZE], [$with_pcre2grep_bufsize], [
+  The value of PCRE2GREP_BUFSIZE is the starting size of the buffer used by
+  pcre2grep to hold parts of the file it is searching. The buffer will be
+  expanded up to PCRE2GREP_MAX_BUFSIZE if necessary, for files containing very
+  long lines. The actual amount of memory used by pcre2grep is three times this
+  number, because it allows for the buffering of "before" and "after" lines.])
+
+AC_DEFINE_UNQUOTED([PCRE2GREP_MAX_BUFSIZE], [$with_pcre2grep_max_bufsize], [
+  The value of PCRE2GREP_MAX_BUFSIZE specifies the maximum size of the buffer
+  used by pcre2grep to hold parts of the file it is searching. The actual
+  amount of memory used by pcre2grep is three times this number, because it
+  allows for the buffering of "before" and "after" lines.])
+
+if test "$enable_pcre2test_libedit" = "yes"; then
+  AC_DEFINE([SUPPORT_LIBEDIT], [], [
+    Define to any value to allow pcre2test to be linked with libedit.])
+  LIBREADLINE="$LIBEDIT"
+elif test "$enable_pcre2test_libreadline" = "yes"; then
+  AC_DEFINE([SUPPORT_LIBREADLINE], [], [
+    Define to any value to allow pcre2test to be linked with libreadline.])
+fi
+
+AC_DEFINE_UNQUOTED([NEWLINE_DEFAULT], [$ac_pcre2_newline_value], [
+  The value of NEWLINE_DEFAULT determines the default newline character
+  sequence. PCRE2 client programs can override this by selecting other values
+  at run time. The valid values are 1 (CR), 2 (LF), 3 (CRLF), 4 (ANY),
+  5 (ANYCRLF), and 6 (NUL).])
+
+if test "$enable_bsr_anycrlf" = "yes"; then
+  AC_DEFINE([BSR_ANYCRLF], [], [
+    By default, the \R escape sequence matches any Unicode line ending
+    character or sequence of characters. If BSR_ANYCRLF is defined (to any
+    value), this is changed so that backslash-R matches only CR, LF, or CRLF.
+    The build-time default can be overridden by the user of PCRE2 at runtime.])
+fi
+
+if test "$enable_never_backslash_C" = "yes"; then
+  AC_DEFINE([NEVER_BACKSLASH_C], [], [
+    Defining NEVER_BACKSLASH_C locks out the use of \C in all patterns.])
+fi
+
+AC_DEFINE_UNQUOTED([LINK_SIZE], [$with_link_size], [
+  The value of LINK_SIZE determines the number of bytes used to store
+  links as offsets within the compiled regex. The default is 2, which
+  allows for compiled patterns up to 65535 code units long. This covers the
+  vast majority of cases. However, PCRE2 can also be compiled to use 3 or 4
+  bytes instead. This allows for longer patterns in extreme cases.])
+
+AC_DEFINE_UNQUOTED([PARENS_NEST_LIMIT], [$with_parens_nest_limit], [
+  The value of PARENS_NEST_LIMIT specifies the maximum depth of nested
+  parentheses (of any kind) in a pattern. This limits the amount of system
+  stack that is used while compiling a pattern.])
+
+AC_DEFINE_UNQUOTED([MATCH_LIMIT], [$with_match_limit], [
+  The value of MATCH_LIMIT determines the default number of times the
+  pcre2_match() function can record a backtrack position during a single
+  matching attempt. The value is also used to limit a loop counter in
+  pcre2_dfa_match(). There is a runtime interface for setting a different
+  limit. The limit exists in order to catch runaway regular expressions that
+  take for ever to determine that they do not match. The default is set very
+  large so that it does not accidentally catch legitimate cases.])
+
+# --with-match-limit-recursion is an obsolete synonym for --with-match-limit-depth
+
+if test "$with_match_limit_recursion" != "UNSET"; then
+cat <<EOF
+
+WARNING: --with-match-limit-recursion is an obsolete option. Please use
+  --with-match-limit-depth in future. If both are set, --with-match-limit-depth
+  will be used. See also --with-heap-limit.
+
+EOF
+if test "$with_match_limit_depth" = "MATCH_LIMIT"; then
+  with_match_limit_depth=$with_match_limit_recursion
+fi
+fi
+
+AC_DEFINE_UNQUOTED([MATCH_LIMIT_DEPTH], [$with_match_limit_depth], [
+  The above limit applies to all backtracks, whether or not they are nested. In
+  some environments it is desirable to limit the nesting of backtracking (that
+  is, the depth of tree that is searched) more strictly, in order to restrict
+  the maximum amount of heap memory that is used. The value of
+  MATCH_LIMIT_DEPTH provides this facility. To have any useful effect, it must
+  be less than the value of MATCH_LIMIT. The default is to use the same value
+  as MATCH_LIMIT. There is a runtime method for setting a different limit. In
+  the case of pcre2_dfa_match(), this limit controls the depth of the internal
+  nested function calls that are used for pattern recursions, lookarounds, and
+  atomic groups.])
+
+AC_DEFINE_UNQUOTED([HEAP_LIMIT], [$with_heap_limit], [
+  This limits the amount of memory that may be used while matching
+  a pattern. It applies to both pcre2_match() and pcre2_dfa_match(). It does
+  not apply to JIT matching. The value is in kibibytes (units of 1024 bytes).])
+
+AC_DEFINE([MAX_NAME_SIZE], [32], [
+  This limit is parameterized just in case anybody ever wants to
+  change it. Care must be taken if it is increased, because it guards
+  against integer overflow caused by enormously large patterns.])
+
+AC_DEFINE([MAX_NAME_COUNT], [10000], [
+  This limit is parameterized just in case anybody ever wants to
+  change it. Care must be taken if it is increased, because it guards
+  against integer overflow caused by enormously large patterns.])
+
+AH_VERBATIM([PCRE2_EXP_DEFN], [
+/* If you are compiling for a system other than a Unix-like system or
+   Win32, and it needs some magic to be inserted before the definition
+   of a function that is exported by the library, define this macro to
+   contain the relevant magic. If you do not define this macro, a suitable
+    __declspec value is used for Windows systems; in other environments
+   "extern" is used for a C compiler and "extern C" for a C++ compiler.
+   This macro apears at the start of every exported function that is part
+   of the external API. It does not appear on functions that are "external"
+   in the C sense, but which are internal to the library. */
+#undef PCRE2_EXP_DEFN])
+
+if test "$enable_ebcdic" = "yes"; then
+  AC_DEFINE_UNQUOTED([EBCDIC], [], [
+    If you are compiling for a system that uses EBCDIC instead of ASCII
+    character codes, define this macro to any value. When EBCDIC is set, PCRE2
+    assumes that all input strings are in EBCDIC. If you do not define this
+    macro, PCRE2 will assume input strings are ASCII or UTF-8/16/32 Unicode. It
+    is not possible to build a version of PCRE2 that supports both EBCDIC and
+    UTF-8/16/32.])
+fi
+
+if test "$enable_ebcdic_nl25" = "yes"; then
+  AC_DEFINE_UNQUOTED([EBCDIC_NL25], [], [
+    In an EBCDIC environment, define this macro to any value to arrange for
+    the NL character to be 0x25 instead of the default 0x15. NL plays the role
+    that LF does in an ASCII/Unicode environment.])
+fi
+
+if test "$enable_valgrind" = "yes"; then
+  AC_DEFINE_UNQUOTED([SUPPORT_VALGRIND], [], [
+     Define to any value for valgrind support to find invalid memory reads.])
+fi
+
+# Platform specific issues
+NO_UNDEFINED=
+EXPORT_ALL_SYMBOLS=
+case $host_os in
+  cygwin* | mingw* )
+    if test X"$enable_shared" = Xyes; then
+      NO_UNDEFINED="-no-undefined"
+      EXPORT_ALL_SYMBOLS="-Wl,--export-all-symbols"
+    fi
+    ;;
+esac
+
+# The extra LDFLAGS for each particular library. The libpcre2*_version values
+# are m4 variables, assigned above.
+
+EXTRA_LIBPCRE2_8_LDFLAGS="$EXTRA_LIBPCRE2_8_LDFLAGS \
+  $NO_UNDEFINED -version-info libpcre2_8_version"
+
+EXTRA_LIBPCRE2_16_LDFLAGS="$EXTRA_LIBPCRE2_16_LDFLAGS \
+  $NO_UNDEFINED -version-info libpcre2_16_version"
+
+EXTRA_LIBPCRE2_32_LDFLAGS="$EXTRA_LIBPCRE2_32_LDFLAGS \
+  $NO_UNDEFINED -version-info libpcre2_32_version"
+
+EXTRA_LIBPCRE2_POSIX_LDFLAGS="$EXTRA_LIBPCRE2_POSIX_LDFLAGS \
+  $NO_UNDEFINED -version-info libpcre2_posix_version"
+
+AC_SUBST(EXTRA_LIBPCRE2_8_LDFLAGS)
+AC_SUBST(EXTRA_LIBPCRE2_16_LDFLAGS)
+AC_SUBST(EXTRA_LIBPCRE2_32_LDFLAGS)
+AC_SUBST(EXTRA_LIBPCRE2_POSIX_LDFLAGS)
+
+# When we run 'make distcheck', use these arguments. Turning off compiler
+# optimization makes it run faster.
+DISTCHECK_CONFIGURE_FLAGS="CFLAGS='' CXXFLAGS='' --enable-pcre2-16 --enable-pcre2-32 --enable-jit"
+AC_SUBST(DISTCHECK_CONFIGURE_FLAGS)
+
+# Check that, if --enable-pcre2grep-libz or --enable-pcre2grep-libbz2 is
+# specified, the relevant library is available.
+
+if test "$enable_pcre2grep_libz" = "yes"; then
+  if test "$HAVE_ZLIB_H" != "1"; then
+    echo "** Cannot --enable-pcre2grep-libz because zlib.h was not found"
+    exit 1
+  fi
+  if test "$HAVE_LIBZ" != "1"; then
+    echo "** Cannot --enable-pcre2grep-libz because libz was not found"
+    exit 1
+  fi
+  LIBZ="-lz"
+fi
+AC_SUBST(LIBZ)
+
+if test "$enable_pcre2grep_libbz2" = "yes"; then
+  if test "$HAVE_BZLIB_H" != "1"; then
+    echo "** Cannot --enable-pcre2grep-libbz2 because bzlib.h was not found"
+    exit 1
+  fi
+  if test "$HAVE_LIBBZ2" != "1"; then
+    echo "** Cannot --enable-pcre2grep-libbz2 because libbz2 was not found"
+    exit 1
+  fi
+  LIBBZ2="-lbz2"
+fi
+AC_SUBST(LIBBZ2)
+
+# Similarly for --enable-pcre2test-readline
+
+if test "$enable_pcre2test_libedit" = "yes"; then
+  if test "$enable_pcre2test_libreadline" = "yes"; then
+    echo "** Cannot use both --enable-pcre2test-libedit and --enable-pcre2test-readline"
+    exit 1
+  fi
+  if test "$HAVE_EDITLINE_READLINE_H" != "1" -a \
+          "$HAVE_READLINE_READLINE_H" != "1"; then
+    echo "** Cannot --enable-pcre2test-libedit because neither editline/readline.h"
+    echo "** nor readline/readline.h was found."
+    exit 1
+  fi
+  if test -z "$LIBEDIT"; then
+    echo "** Cannot --enable-pcre2test-libedit because libedit library was not found."
+    exit 1
+  fi
+fi
+
+if test "$enable_pcre2test_libreadline" = "yes"; then
+  if test "$HAVE_READLINE_H" != "1"; then
+    echo "** Cannot --enable-pcre2test-readline because readline/readline.h was not found."
+    exit 1
+  fi
+  if test "$HAVE_HISTORY_H" != "1"; then
+    echo "** Cannot --enable-pcre2test-readline because readline/history.h was not found."
+    exit 1
+  fi
+  if test -z "$LIBREADLINE"; then
+    echo "** Cannot --enable-pcre2test-readline because readline library was not found."
+    exit 1
+  fi
+fi
+
+# Handle valgrind support
+
+if test "$enable_valgrind" = "yes"; then
+  m4_ifdef([PKG_CHECK_MODULES],
+           [PKG_CHECK_MODULES([VALGRIND],[valgrind])],
+           [AC_MSG_ERROR([pkg-config not supported])])
+fi
+
+# Handle code coverage reporting support
+if test "$enable_coverage" = "yes"; then
+  if test "x$GCC" != "xyes"; then
+    AC_MSG_ERROR([Code coverage reports can only be generated when using GCC])
+  fi
+
+  # ccache is incompatible with gcov
+  AC_PATH_PROG([SHTOOL],[shtool],[false])
+  case `$SHTOOL path $CC` in
+    *ccache*) cc_ccache=yes;;
+    *) cc_ccache=no;;
+  esac
+
+  if test "$cc_ccache" = "yes"; then
+    if test -z "$CCACHE_DISABLE" -o "$CCACHE_DISABLE" != "1"; then
+      AC_MSG_ERROR([must export CCACHE_DISABLE=1 to disable ccache for code coverage])
+    fi
+  fi
+
+  AC_ARG_VAR([LCOV],[the ltp lcov program])
+  AC_PATH_PROG([LCOV],[lcov],[false])
+  if test "x$LCOV" = "xfalse"; then
+    AC_MSG_ERROR([lcov not found])
+  fi
+
+  AC_ARG_VAR([GENHTML],[the ltp genhtml program])
+  AC_PATH_PROG([GENHTML],[genhtml],[false])
+  if test "x$GENHTML" = "xfalse"; then
+    AC_MSG_ERROR([genhtml not found])
+  fi
+
+  # Set flags needed for gcov
+  GCOV_CFLAGS="-O0 -ggdb3 -fprofile-arcs -ftest-coverage"
+  GCOV_CXXFLAGS="-O0 -ggdb3 -fprofile-arcs -ftest-coverage"
+  GCOV_LIBS="-lgcov"
+  AC_SUBST([GCOV_CFLAGS])
+  AC_SUBST([GCOV_CXXFLAGS])
+  AC_SUBST([GCOV_LIBS])
+fi # enable_coverage
+
+AM_CONDITIONAL([WITH_GCOV],[test "x$enable_coverage" = "xyes"])
+
+AC_MSG_CHECKING([whether Intel CET is enabled])
+AC_LANG_PUSH([C])
+AC_COMPILE_IFELSE([AC_LANG_PROGRAM(,
+                   [[#ifndef __CET__
+# error CET is not enabled
+#endif]])],
+                   [pcre2_cc_cv_intel_cet_enabled=yes],
+                   [pcre2_cc_cv_intel_cet_enabled=no])
+AC_MSG_RESULT([$pcre2_cc_cv_intel_cet_enabled])
+if test "$pcre2_cc_cv_intel_cet_enabled" = yes; then
+  CET_CFLAGS="-mshstk"
+  AC_SUBST([CET_CFLAGS])
+fi
+AC_LANG_POP([C])
+
+# LIB_POSTFIX is used by CMakeLists.txt for Windows debug builds.
+# Pass empty LIB_POSTFIX to *.pc files and pcre2-config here.
+AC_SUBST(LIB_POSTFIX)
+
+# Produce these files, in addition to config.h.
+
+AC_CONFIG_FILES(
+	Makefile
+	libpcre2-8.pc
+	libpcre2-16.pc
+	libpcre2-32.pc
+	libpcre2-posix.pc
+	pcre2-config
+	src/pcre2.h
+)
+
+# Make the generated script files executable.
+AC_CONFIG_COMMANDS([script-chmod], [chmod a+x pcre2-config])
+
+# Make sure that pcre2_chartables.c is removed in case the method for
+# creating it was changed by reconfiguration.
+AC_CONFIG_COMMANDS([delete-old-chartables], [rm -f pcre2_chartables.c])
+
+AC_OUTPUT
+
+# --disable-stack-for-recursion is obsolete and has no effect.
+
+if test "$enable_stack_for_recursion" = "no"; then
+cat <<EOF
+
+WARNING: --disable-stack-for-recursion is obsolete and has no effect.
+EOF
+fi
+
+# Print out a nice little message after configure is run displaying the
+# chosen options.
+
+ebcdic_nl_code=n/a
+if test "$enable_ebcdic_nl25" = "yes"; then
+  ebcdic_nl_code=0x25
+elif test "$enable_ebcdic" = "yes"; then
+  ebcdic_nl_code=0x15
+fi
+
+cat <<EOF
+
+$PACKAGE-$VERSION configuration summary:
+
+    Install prefix ..................... : ${prefix}
+    C preprocessor ..................... : ${CPP}
+    C compiler ......................... : ${CC}
+    Linker ............................. : ${LD}
+    C preprocessor flags ............... : ${CPPFLAGS}
+    C compiler flags ................... : ${CFLAGS} ${VISIBILITY_CFLAGS}
+    Linker flags ....................... : ${LDFLAGS}
+    Extra libraries .................... : ${LIBS}
+
+    Build 8-bit pcre2 library .......... : ${enable_pcre2_8}
+    Build 16-bit pcre2 library ......... : ${enable_pcre2_16}
+    Build 32-bit pcre2 library ......... : ${enable_pcre2_32}
+    Include debugging code ............. : ${enable_debug}
+    Enable JIT compiling support ....... : ${enable_jit}
+    Use SELinux allocator in JIT ....... : ${enable_jit_sealloc}
+    Enable Unicode support ............. : ${enable_unicode}
+    Newline char/sequence .............. : ${enable_newline}
+    \R matches only ANYCRLF ............ : ${enable_bsr_anycrlf}
+    \C is disabled ..................... : ${enable_never_backslash_C}
+    EBCDIC coding ...................... : ${enable_ebcdic}
+    EBCDIC code for NL ................. : ${ebcdic_nl_code}
+    Rebuild char tables ................ : ${enable_rebuild_chartables}
+    Internal link size ................. : ${with_link_size}
+    Nested parentheses limit ........... : ${with_parens_nest_limit}
+    Heap limit ......................... : ${with_heap_limit} kibibytes
+    Match limit ........................ : ${with_match_limit}
+    Match depth limit .................. : ${with_match_limit_depth}
+    Build shared libs .................. : ${enable_shared}
+    Build static libs .................. : ${enable_static}
+    Use JIT in pcre2grep ............... : ${enable_pcre2grep_jit}
+    Enable callouts in pcre2grep ....... : ${enable_pcre2grep_callout}
+    Enable fork in pcre2grep callouts .. : ${enable_pcre2grep_callout_fork}
+    Initial buffer size for pcre2grep .. : ${with_pcre2grep_bufsize}
+    Maximum buffer size for pcre2grep .. : ${with_pcre2grep_max_bufsize}
+    Link pcre2grep with libz ........... : ${enable_pcre2grep_libz}
+    Link pcre2grep with libbz2 ......... : ${enable_pcre2grep_libbz2}
+    Link pcre2test with libedit ........ : ${enable_pcre2test_libedit}
+    Link pcre2test with libreadline .... : ${enable_pcre2test_libreadline}
+    Valgrind support ................... : ${enable_valgrind}
+    Code coverage ...................... : ${enable_coverage}
+    Fuzzer support ..................... : ${enable_fuzz_support}
+    Use %zu and %td .................... : ${enable_percent_zt}
+
+EOF
+
+dnl end configure.ac

src/regex/pcre2/doc/html/NON-AUTOTOOLS-BUILD.txt

@@ -0,0 +1,410 @@
+Building PCRE2 without using autotools
+--------------------------------------
+
+This document contains the following sections:
+
+  General
+  Generic instructions for the PCRE2 C library
+  Stack size in Windows environments
+  Linking programs in Windows environments
+  Calling conventions in Windows environments
+  Comments about Win32 builds
+  Building PCRE2 on Windows with CMake
+  Building PCRE2 on Windows with Visual Studio
+  Testing with RunTest.bat
+  Building PCRE2 on native z/OS and z/VM
+
+
+GENERAL
+
+The basic PCRE2 library consists entirely of code written in Standard C, and so
+should compile successfully on any system that has a Standard C compiler and
+library.
+
+The PCRE2 distribution includes a "configure" file for use by the
+configure/make (autotools) build system, as found in many Unix-like
+environments. The README file contains information about the options for
+"configure".
+
+There is also support for CMake, which some users prefer, especially in Windows
+environments, though it can also be run in Unix-like environments. See the
+section entitled "Building PCRE2 on Windows with CMake" below.
+
+Versions of src/config.h and src/pcre2.h are distributed in the PCRE2 tarballs
+under the names src/config.h.generic and src/pcre2.h.generic. These are
+provided for those who build PCRE2 without using "configure" or CMake. If you
+use "configure" or CMake, the .generic versions are not used.
+
+
+GENERIC INSTRUCTIONS FOR THE PCRE2 C LIBRARY
+
+The following are generic instructions for building the PCRE2 C library "by
+hand". If you are going to use CMake, this section does not apply to you; you
+can skip ahead to the CMake section. Note that the settings concerned with
+8-bit, 16-bit, and 32-bit code units relate to the type of data string that
+PCRE2 processes. They are NOT referring to the underlying operating system bit
+width. You do not have to do anything special to compile in a 64-bit
+environment, for example.
+
+ (1) Copy or rename the file src/config.h.generic as src/config.h, and edit the
+     macro settings that it contains to whatever is appropriate for your
+     environment. In particular, you can alter the definition of the NEWLINE
+     macro to specify what character(s) you want to be interpreted as line
+     terminators by default.
+
+     When you subsequently compile any of the PCRE2 modules, you must specify
+     -DHAVE_CONFIG_H to your compiler so that src/config.h is included in the
+     sources.
+
+     An alternative approach is not to edit src/config.h, but to use -D on the
+     compiler command line to make any changes that you need to the
+     configuration options. In this case -DHAVE_CONFIG_H must not be set.
+
+     NOTE: There have been occasions when the way in which certain parameters
+     in src/config.h are used has changed between releases. (In the
+     configure/make world, this is handled automatically.) When upgrading to a
+     new release, you are strongly advised to review src/config.h.generic
+     before re-using what you had previously.
+
+     Note also that the src/config.h.generic file is created from a config.h
+     that was generated by Autotools, which automatically includes settings of
+     a number of macros that are not actually used by PCRE2 (for example,
+     HAVE_MEMORY_H).
+
+ (2) Copy or rename the file src/pcre2.h.generic as src/pcre2.h.
+
+ (3) EITHER:
+       Copy or rename file src/pcre2_chartables.c.dist as
+       src/pcre2_chartables.c.
+
+     OR:
+       Compile src/pcre2_dftables.c as a stand-alone program (using
+       -DHAVE_CONFIG_H if you have set up src/config.h), and then run it with
+       the single argument "src/pcre2_chartables.c". This generates a set of
+       standard character tables and writes them to that file. The tables are
+       generated using the default C locale for your system. If you want to use
+       a locale that is specified by LC_xxx environment variables, add the -L
+       option to the pcre2_dftables command. You must use this method if you
+       are building on a system that uses EBCDIC code.
+
+     The tables in src/pcre2_chartables.c are defaults. The caller of PCRE2 can
+     specify alternative tables at run time.
+
+ (4) For a library that supports 8-bit code units in the character strings that
+     it processes, compile the following source files from the src directory,
+     setting -DPCRE2_CODE_UNIT_WIDTH=8 as a compiler option. Also set
+     -DHAVE_CONFIG_H if you have set up src/config.h with your configuration,
+     or else use other -D settings to change the configuration as required.
+
+       pcre2_auto_possess.c
+       pcre2_chartables.c
+       pcre2_compile.c
+       pcre2_config.c
+       pcre2_context.c
+       pcre2_convert.c
+       pcre2_dfa_match.c
+       pcre2_error.c
+       pcre2_extuni.c
+       pcre2_find_bracket.c
+       pcre2_jit_compile.c
+       pcre2_maketables.c
+       pcre2_match.c
+       pcre2_match_data.c
+       pcre2_newline.c
+       pcre2_ord2utf.c
+       pcre2_pattern_info.c
+       pcre2_script_run.c
+       pcre2_serialize.c
+       pcre2_string_utils.c
+       pcre2_study.c
+       pcre2_substitute.c
+       pcre2_substring.c
+       pcre2_tables.c
+       pcre2_ucd.c
+       pcre2_valid_utf.c
+       pcre2_xclass.c
+
+     Make sure that you include -I. in the compiler command (or equivalent for
+     an unusual compiler) so that all included PCRE2 header files are first
+     sought in the src directory under the current directory. Otherwise you run
+     the risk of picking up a previously-installed file from somewhere else.
+
+     Note that you must compile pcre2_jit_compile.c, even if you have not
+     defined SUPPORT_JIT in src/config.h, because when JIT support is not
+     configured, dummy functions are compiled. When JIT support IS configured,
+     pcre2_jit_compile.c #includes other files from the sljit subdirectory,
+     all of whose names begin with "sljit". It also #includes
+     src/pcre2_jit_match.c and src/pcre2_jit_misc.c, so you should not compile
+     these yourself.
+
+     Note also that the pcre2_fuzzsupport.c file contains special code that is
+     useful to those who want to run fuzzing tests on the PCRE2 library. Unless
+     you are doing that, you can ignore it.
+
+ (5) Now link all the compiled code into an object library in whichever form
+     your system keeps such libraries. This is the basic PCRE2 C 8-bit library.
+     If your system has static and shared libraries, you may have to do this
+     once for each type.
+
+ (6) If you want to build a library that supports 16-bit or 32-bit code units,
+     (as well as, or instead of the 8-bit library) just supply 16 or 32 as the
+     value of -DPCRE2_CODE_UNIT_WIDTH when you are compiling.
+
+ (7) If you want to build the POSIX wrapper functions (which apply only to the
+     8-bit library), ensure that you have the src/pcre2posix.h file and then
+     compile src/pcre2posix.c. Link the result (on its own) as the pcre2posix
+     library.
+
+ (8) The pcre2test program can be linked with any combination of the 8-bit,
+     16-bit and 32-bit libraries (depending on what you selected in
+     src/config.h). Compile src/pcre2test.c; don't forget -DHAVE_CONFIG_H if
+     necessary, but do NOT define PCRE2_CODE_UNIT_WIDTH. Then link with the
+     appropriate library/ies. If you compiled an 8-bit library, pcre2test also
+     needs the pcre2posix wrapper library.
+
+ (9) Run pcre2test on the testinput files in the testdata directory, and check
+     that the output matches the corresponding testoutput files. There are
+     comments about what each test does in the section entitled "Testing PCRE2"
+     in the README file. If you compiled more than one of the 8-bit, 16-bit and
+     32-bit libraries, you need to run pcre2test with the -16 option to do
+     16-bit tests and with the -32 option to do 32-bit tests.
+
+     Some tests are relevant only when certain build-time options are selected.
+     For example, test 4 is for Unicode support, and will not run if you have
+     built PCRE2 without it. See the comments at the start of each testinput
+     file. If you have a suitable Unix-like shell, the RunTest script will run
+     the appropriate tests for you. The command "RunTest list" will output a
+     list of all the tests.
+
+     Note that the supplied files are in Unix format, with just LF characters
+     as line terminators. You may need to edit them to change this if your
+     system uses a different convention.
+
+(10) If you have built PCRE2 with SUPPORT_JIT, the JIT features can be tested
+     by running pcre2test with the -jit option. This is done automatically by
+     the RunTest script. You might also like to build and run the freestanding
+     JIT test program, src/pcre2_jit_test.c.
+
+(11) If you want to use the pcre2grep command, compile and link
+     src/pcre2grep.c; it uses only the basic 8-bit PCRE2 library (it does not
+     need the pcre2posix library). If you have built the PCRE2 library with JIT
+     support by defining SUPPORT_JIT in src/config.h, you can also define
+     SUPPORT_PCRE2GREP_JIT, which causes pcre2grep to make use of JIT (unless
+     it is run with --no-jit). If you define SUPPORT_PCRE2GREP_JIT without
+     defining SUPPORT_JIT, pcre2grep does not try to make use of JIT.
+
+
+STACK SIZE IN WINDOWS ENVIRONMENTS
+
+Prior to release 10.30 the default system stack size of 1MiB in some Windows
+environments caused issues with some tests. This should no longer be the case
+for 10.30 and later releases.
+
+
+LINKING PROGRAMS IN WINDOWS ENVIRONMENTS
+
+If you want to statically link a program against a PCRE2 library in the form of
+a non-dll .a file, you must define PCRE2_STATIC before including src/pcre2.h.
+
+
+CALLING CONVENTIONS IN WINDOWS ENVIRONMENTS
+
+It is possible to compile programs to use different calling conventions using
+MSVC. Search the web for "calling conventions" for more information. To make it
+easier to change the calling convention for the exported functions in the
+PCRE2 library, the macro PCRE2_CALL_CONVENTION is present in all the external
+definitions. It can be set externally when compiling (e.g. in CFLAGS). If it is
+not set, it defaults to empty; the default calling convention is then used
+(which is what is wanted most of the time).
+
+
+COMMENTS ABOUT WIN32 BUILDS (see also "BUILDING PCRE2 ON WINDOWS WITH CMAKE")
+
+There are two ways of building PCRE2 using the "configure, make, make install"
+paradigm on Windows systems: using MinGW or using Cygwin. These are not at all
+the same thing; they are completely different from each other. There is also
+support for building using CMake, which some users find a more straightforward
+way of building PCRE2 under Windows.
+
+The MinGW home page (http://www.mingw.org/) says this:
+
+  MinGW: A collection of freely available and freely distributable Windows
+  specific header files and import libraries combined with GNU toolsets that
+  allow one to produce native Windows programs that do not rely on any
+  3rd-party C runtime DLLs.
+
+The Cygwin home page (http://www.cygwin.com/) says this:
+
+  Cygwin is a Linux-like environment for Windows. It consists of two parts:
+
+  . A DLL (cygwin1.dll) which acts as a Linux API emulation layer providing
+    substantial Linux API functionality
+
+  . A collection of tools which provide Linux look and feel.
+
+On both MinGW and Cygwin, PCRE2 should build correctly using:
+
+  ./configure && make && make install
+
+This should create two libraries called libpcre2-8 and libpcre2-posix. These
+are independent libraries: when you link with libpcre2-posix you must also link
+with libpcre2-8, which contains the basic functions.
+
+Using Cygwin's compiler generates libraries and executables that depend on
+cygwin1.dll. If a library that is generated this way is distributed,
+cygwin1.dll has to be distributed as well. Since cygwin1.dll is under the GPL
+licence, this forces not only PCRE2 to be under the GPL, but also the entire
+application. A distributor who wants to keep their own code proprietary must
+purchase an appropriate Cygwin licence.
+
+MinGW has no such restrictions. The MinGW compiler generates a library or
+executable that can run standalone on Windows without any third party dll or
+licensing issues.
+
+But there is more complication:
+
+If a Cygwin user uses the -mno-cygwin Cygwin gcc flag, what that really does is
+to tell Cygwin's gcc to use the MinGW gcc. Cygwin's gcc is only acting as a
+front end to MinGW's gcc (if you install Cygwin's gcc, you get both Cygwin's
+gcc and MinGW's gcc). So, a user can:
+
+. Build native binaries by using MinGW or by getting Cygwin and using
+  -mno-cygwin.
+
+. Build binaries that depend on cygwin1.dll by using Cygwin with the normal
+  compiler flags.
+
+The test files that are supplied with PCRE2 are in UNIX format, with LF
+characters as line terminators. Unless your PCRE2 library uses a default
+newline option that includes LF as a valid newline, it may be necessary to
+change the line terminators in the test files to get some of the tests to work.
+
+
+BUILDING PCRE2 ON WINDOWS WITH CMAKE
+
+CMake is an alternative configuration facility that can be used instead of
+"configure". CMake creates project files (make files, solution files, etc.)
+tailored to numerous development environments, including Visual Studio,
+Borland, Msys, MinGW, NMake, and Unix. If possible, use short paths with no
+spaces in the names for your CMake installation and your PCRE2 source and build
+directories.
+
+The following instructions were contributed by a PCRE1 user, but they should
+also work for PCRE2. If they are not followed exactly, errors may occur. In the
+event that errors do occur, it is recommended that you delete the CMake cache
+before attempting to repeat the CMake build process. In the CMake GUI, the
+cache can be deleted by selecting "File > Delete Cache".
+
+1.  Install the latest CMake version available from http://www.cmake.org/, and
+    ensure that cmake\bin is on your path.
+
+2.  Unzip (retaining folder structure) the PCRE2 source tree into a source
+    directory such as C:\pcre2. You should ensure your local date and time
+    is not earlier than the file dates in your source dir if the release is
+    very new.
+
+3.  Create a new, empty build directory, preferably a subdirectory of the
+    source dir. For example, C:\pcre2\pcre2-xx\build.
+
+4.  Run cmake-gui from the Shell envirornment of your build tool, for example,
+    Msys for Msys/MinGW or Visual Studio Command Prompt for VC/VC++. Do not try
+    to start Cmake from the Windows Start menu, as this can lead to errors.
+
+5.  Enter C:\pcre2\pcre2-xx and C:\pcre2\pcre2-xx\build for the source and
+    build directories, respectively.
+
+6.  Hit the "Configure" button.
+
+7.  Select the particular IDE / build tool that you are using (Visual
+    Studio, MSYS makefiles, MinGW makefiles, etc.)
+
+8.  The GUI will then list several configuration options. This is where
+    you can disable Unicode support or select other PCRE2 optional features.
+
+9.  Hit "Configure" again. The adjacent "Generate" button should now be
+    active.
+
+10. Hit "Generate".
+
+11. The build directory should now contain a usable build system, be it a
+    solution file for Visual Studio, makefiles for MinGW, etc. Exit from
+    cmake-gui and use the generated build system with your compiler or IDE.
+    E.g., for MinGW you can run "make", or for Visual Studio, open the PCRE2
+    solution, select the desired configuration (Debug, or Release, etc.) and
+    build the ALL_BUILD project.
+
+12. If during configuration with cmake-gui you've elected to build the test
+    programs, you can execute them by building the test project. E.g., for
+    MinGW: "make test"; for Visual Studio build the RUN_TESTS project. The
+    most recent build configuration is targeted by the tests. A summary of
+    test results is presented. Complete test output is subsequently
+    available for review in Testing\Temporary under your build dir.
+
+
+BUILDING PCRE2 ON WINDOWS WITH VISUAL STUDIO
+
+The code currently cannot be compiled without a stdint.h header, which is
+available only in relatively recent versions of Visual Studio. However, this
+portable and permissively-licensed implementation of the header worked without
+issue:
+
+  http://www.azillionmonkeys.com/qed/pstdint.h
+
+Just rename it and drop it into the top level of the build tree.
+
+
+TESTING WITH RUNTEST.BAT
+
+If configured with CMake, building the test project ("make test" or building
+ALL_TESTS in Visual Studio) creates (and runs) pcre2_test.bat (and depending
+on your configuration options, possibly other test programs) in the build
+directory. The pcre2_test.bat script runs RunTest.bat with correct source and
+exe paths.
+
+For manual testing with RunTest.bat, provided the build dir is a subdirectory
+of the source directory: Open command shell window. Chdir to the location
+of your pcre2test.exe and pcre2grep.exe programs. Call RunTest.bat with
+"..\RunTest.Bat" or "..\..\RunTest.bat" as appropriate.
+
+To run only a particular test with RunTest.Bat provide a test number argument.
+
+Otherwise:
+
+1. Copy RunTest.bat into the directory where pcre2test.exe and pcre2grep.exe
+   have been created.
+
+2. Edit RunTest.bat to indentify the full or relative location of
+   the pcre2 source (wherein which the testdata folder resides), e.g.:
+
+   set srcdir=C:\pcre2\pcre2-10.00
+
+3. In a Windows command environment, chdir to the location of your bat and
+   exe programs.
+
+4. Run RunTest.bat. Test outputs will automatically be compared to expected
+   results, and discrepancies will be identified in the console output.
+
+To independently test the just-in-time compiler, run pcre2_jit_test.exe.
+
+
+BUILDING PCRE2 ON NATIVE Z/OS AND Z/VM
+
+z/OS and z/VM are operating systems for mainframe computers, produced by IBM.
+The character code used is EBCDIC, not ASCII or Unicode. In z/OS, UNIX APIs and
+applications can be supported through UNIX System Services, and in such an
+environment it should be possible to build PCRE2 in the same way as in other
+systems, with the EBCDIC related configuration settings, but it is not known if
+anybody has tried this.
+
+In native z/OS (without UNIX System Services) and in z/VM, special ports are
+required. For details, please see file 939 on this web site:
+
+  http://www.cbttape.org
+
+Everything in that location, source and executable, is in EBCDIC and native
+z/OS file formats. The port provides an API for LE languages such as COBOL and
+for the z/OS and z/VM versions of the Rexx languages.
+
+===========================
+Last Updated: 28 April 2021
+===========================

src/regex/pcre2/doc/html/README.txt

@@ -0,0 +1,907 @@
+README file for PCRE2 (Perl-compatible regular expression library)
+------------------------------------------------------------------
+
+PCRE2 is a re-working of the original PCRE1 library to provide an entirely new
+API. Since its initial release in 2015, there has been further development of
+the code and it now differs from PCRE1 in more than just the API. There are new
+features, and the internals have been improved. The original PCRE1 library is
+now obsolete and should not be used in new projects. The latest release of
+PCRE2 is available in three alternative formats from:
+
+https://ftp.pcre.org/pub/pcre/pcre2-10.xx.tar.gz
+https://ftp.pcre.org/pub/pcre/pcre2-10.xx.tar.bz2
+https://ftp.pcre.org/pub/pcre/pcre2-10.xx.tar.zip
+
+There is a mailing list for discussion about the development of PCRE at
+pcre-dev@exim.org. You can access the archives and subscribe or manage your
+subscription here:
+
+   https://lists.exim.org/mailman/listinfo/pcre-dev
+
+Please read the NEWS file if you are upgrading from a previous release. The
+contents of this README file are:
+
+  The PCRE2 APIs
+  Documentation for PCRE2
+  Contributions by users of PCRE2
+  Building PCRE2 on non-Unix-like systems
+  Building PCRE2 without using autotools
+  Building PCRE2 using autotools
+  Retrieving configuration information
+  Shared libraries
+  Cross-compiling using autotools
+  Making new tarballs
+  Testing PCRE2
+  Character tables
+  File manifest
+
+
+The PCRE2 APIs
+--------------
+
+PCRE2 is written in C, and it has its own API. There are three sets of
+functions, one for the 8-bit library, which processes strings of bytes, one for
+the 16-bit library, which processes strings of 16-bit values, and one for the
+32-bit library, which processes strings of 32-bit values. Unlike PCRE1, there
+are no C++ wrappers.
+
+The distribution does contain a set of C wrapper functions for the 8-bit
+library that are based on the POSIX regular expression API (see the pcre2posix
+man page). These are built into a library called libpcre2-posix. Note that this
+just provides a POSIX calling interface to PCRE2; the regular expressions
+themselves still follow Perl syntax and semantics. The POSIX API is restricted,
+and does not give full access to all of PCRE2's facilities.
+
+The header file for the POSIX-style functions is called pcre2posix.h. The
+official POSIX name is regex.h, but I did not want to risk possible problems
+with existing files of that name by distributing it that way. To use PCRE2 with
+an existing program that uses the POSIX API, pcre2posix.h will have to be
+renamed or pointed at by a link (or the program modified, of course). See the
+pcre2posix documentation for more details.
+
+
+Documentation for PCRE2
+-----------------------
+
+If you install PCRE2 in the normal way on a Unix-like system, you will end up
+with a set of man pages whose names all start with "pcre2". The one that is
+just called "pcre2" lists all the others. In addition to these man pages, the
+PCRE2 documentation is supplied in two other forms:
+
+  1. There are files called doc/pcre2.txt, doc/pcre2grep.txt, and
+     doc/pcre2test.txt in the source distribution. The first of these is a
+     concatenation of the text forms of all the section 3 man pages except the
+     listing of pcre2demo.c and those that summarize individual functions. The
+     other two are the text forms of the section 1 man pages for the pcre2grep
+     and pcre2test commands. These text forms are provided for ease of scanning
+     with text editors or similar tools. They are installed in
+     <prefix>/share/doc/pcre2, where <prefix> is the installation prefix
+     (defaulting to /usr/local).
+
+  2. A set of files containing all the documentation in HTML form, hyperlinked
+     in various ways, and rooted in a file called index.html, is distributed in
+     doc/html and installed in <prefix>/share/doc/pcre2/html.
+
+
+Building PCRE2 on non-Unix-like systems
+---------------------------------------
+
+For a non-Unix-like system, please read the file NON-AUTOTOOLS-BUILD, though if
+your system supports the use of "configure" and "make" you may be able to build
+PCRE2 using autotools in the same way as for many Unix-like systems.
+
+PCRE2 can also be configured using CMake, which can be run in various ways
+(command line, GUI, etc). This creates Makefiles, solution files, etc. The file
+NON-AUTOTOOLS-BUILD has information about CMake.
+
+PCRE2 has been compiled on many different operating systems. It should be
+straightforward to build PCRE2 on any system that has a Standard C compiler and
+library, because it uses only Standard C functions.
+
+
+Building PCRE2 without using autotools
+--------------------------------------
+
+The use of autotools (in particular, libtool) is problematic in some
+environments, even some that are Unix or Unix-like. See the NON-AUTOTOOLS-BUILD
+file for ways of building PCRE2 without using autotools.
+
+
+Building PCRE2 using autotools
+------------------------------
+
+The following instructions assume the use of the widely used "configure; make;
+make install" (autotools) process.
+
+To build PCRE2 on system that supports autotools, first run the "configure"
+command from the PCRE2 distribution directory, with your current directory set
+to the directory where you want the files to be created. This command is a
+standard GNU "autoconf" configuration script, for which generic instructions
+are supplied in the file INSTALL.
+
+Most commonly, people build PCRE2 within its own distribution directory, and in
+this case, on many systems, just running "./configure" is sufficient. However,
+the usual methods of changing standard defaults are available. For example:
+
+CFLAGS='-O2 -Wall' ./configure --prefix=/opt/local
+
+This command specifies that the C compiler should be run with the flags '-O2
+-Wall' instead of the default, and that "make install" should install PCRE2
+under /opt/local instead of the default /usr/local.
+
+If you want to build in a different directory, just run "configure" with that
+directory as current. For example, suppose you have unpacked the PCRE2 source
+into /source/pcre2/pcre2-xxx, but you want to build it in
+/build/pcre2/pcre2-xxx:
+
+cd /build/pcre2/pcre2-xxx
+/source/pcre2/pcre2-xxx/configure
+
+PCRE2 is written in C and is normally compiled as a C library. However, it is
+possible to build it as a C++ library, though the provided building apparatus
+does not have any features to support this.
+
+There are some optional features that can be included or omitted from the PCRE2
+library. They are also documented in the pcre2build man page.
+
+. By default, both shared and static libraries are built. You can change this
+  by adding one of these options to the "configure" command:
+
+  --disable-shared
+  --disable-static
+
+  (See also "Shared libraries on Unix-like systems" below.)
+
+. By default, only the 8-bit library is built. If you add --enable-pcre2-16 to
+  the "configure" command, the 16-bit library is also built. If you add
+  --enable-pcre2-32 to the "configure" command, the 32-bit library is also
+  built. If you want only the 16-bit or 32-bit library, use --disable-pcre2-8
+  to disable building the 8-bit library.
+
+. If you want to include support for just-in-time (JIT) compiling, which can
+  give large performance improvements on certain platforms, add --enable-jit to
+  the "configure" command. This support is available only for certain hardware
+  architectures. If you try to enable it on an unsupported architecture, there
+  will be a compile time error. If in doubt, use --enable-jit=auto, which
+  enables JIT only if the current hardware is supported.
+
+. If you are enabling JIT under SELinux environment you may also want to add
+  --enable-jit-sealloc, which enables the use of an executable memory allocator
+  that is compatible with SELinux. Warning: this allocator is experimental!
+  It does not support fork() operation and may crash when no disk space is
+  available. This option has no effect if JIT is disabled.
+
+. If you do not want to make use of the default support for UTF-8 Unicode
+  character strings in the 8-bit library, UTF-16 Unicode character strings in
+  the 16-bit library, or UTF-32 Unicode character strings in the 32-bit
+  library, you can add --disable-unicode to the "configure" command. This
+  reduces the size of the libraries. It is not possible to configure one
+  library with Unicode support, and another without, in the same configuration.
+  It is also not possible to use --enable-ebcdic (see below) with Unicode
+  support, so if this option is set, you must also use --disable-unicode.
+
+  When Unicode support is available, the use of a UTF encoding still has to be
+  enabled by setting the PCRE2_UTF option at run time or starting a pattern
+  with (*UTF). When PCRE2 is compiled with Unicode support, its input can only
+  either be ASCII or UTF-8/16/32, even when running on EBCDIC platforms.
+
+  As well as supporting UTF strings, Unicode support includes support for the
+  \P, \p, and \X sequences that recognize Unicode character properties.
+  However, only the basic two-letter properties such as Lu are supported.
+  Escape sequences such as \d and \w in patterns do not by default make use of
+  Unicode properties, but can be made to do so by setting the PCRE2_UCP option
+  or starting a pattern with (*UCP).
+
+. You can build PCRE2 to recognize either CR or LF or the sequence CRLF, or any
+  of the preceding, or any of the Unicode newline sequences, or the NUL (zero)
+  character as indicating the end of a line. Whatever you specify at build time
+  is the default; the caller of PCRE2 can change the selection at run time. The
+  default newline indicator is a single LF character (the Unix standard). You
+  can specify the default newline indicator by adding --enable-newline-is-cr,
+  --enable-newline-is-lf, --enable-newline-is-crlf,
+  --enable-newline-is-anycrlf, --enable-newline-is-any, or
+  --enable-newline-is-nul to the "configure" command, respectively.
+
+. By default, the sequence \R in a pattern matches any Unicode line ending
+  sequence. This is independent of the option specifying what PCRE2 considers
+  to be the end of a line (see above). However, the caller of PCRE2 can
+  restrict \R to match only CR, LF, or CRLF. You can make this the default by
+  adding --enable-bsr-anycrlf to the "configure" command (bsr = "backslash R").
+
+. In a pattern, the escape sequence \C matches a single code unit, even in a
+  UTF mode. This can be dangerous because it breaks up multi-code-unit
+  characters. You can build PCRE2 with the use of \C permanently locked out by
+  adding --enable-never-backslash-C (note the upper case C) to the "configure"
+  command. When \C is allowed by the library, individual applications can lock
+  it out by calling pcre2_compile() with the PCRE2_NEVER_BACKSLASH_C option.
+
+. PCRE2 has a counter that limits the depth of nesting of parentheses in a
+  pattern. This limits the amount of system stack that a pattern uses when it
+  is compiled. The default is 250, but you can change it by setting, for
+  example,
+
+  --with-parens-nest-limit=500
+
+. PCRE2 has a counter that can be set to limit the amount of computing resource
+  it uses when matching a pattern. If the limit is exceeded during a match, the
+  match fails. The default is ten million. You can change the default by
+  setting, for example,
+
+  --with-match-limit=500000
+
+  on the "configure" command. This is just the default; individual calls to
+  pcre2_match() or pcre2_dfa_match() can supply their own value. There is more
+  discussion in the pcre2api man page (search for pcre2_set_match_limit).
+
+. There is a separate counter that limits the depth of nested backtracking
+  (pcre2_match()) or nested function calls (pcre2_dfa_match()) during a
+  matching process, which indirectly limits the amount of heap memory that is
+  used, and in the case of pcre2_dfa_match() the amount of stack as well. This
+  counter also has a default of ten million, which is essentially "unlimited".
+  You can change the default by setting, for example,
+
+  --with-match-limit-depth=5000
+
+  There is more discussion in the pcre2api man page (search for
+  pcre2_set_depth_limit).
+
+. You can also set an explicit limit on the amount of heap memory used by
+  the pcre2_match() and pcre2_dfa_match() interpreters:
+
+  --with-heap-limit=500
+
+  The units are kibibytes (units of 1024 bytes). This limit does not apply when
+  the JIT optimization (which has its own memory control features) is used.
+  There is more discussion on the pcre2api man page (search for
+  pcre2_set_heap_limit).
+
+. In the 8-bit library, the default maximum compiled pattern size is around
+  64 kibibytes. You can increase this by adding --with-link-size=3 to the
+  "configure" command. PCRE2 then uses three bytes instead of two for offsets
+  to different parts of the compiled pattern. In the 16-bit library,
+  --with-link-size=3 is the same as --with-link-size=4, which (in both
+  libraries) uses four-byte offsets. Increasing the internal link size reduces
+  performance in the 8-bit and 16-bit libraries. In the 32-bit library, the
+  link size setting is ignored, as 4-byte offsets are always used.
+
+. For speed, PCRE2 uses four tables for manipulating and identifying characters
+  whose code point values are less than 256. By default, it uses a set of
+  tables for ASCII encoding that is part of the distribution. If you specify
+
+  --enable-rebuild-chartables
+
+  a program called pcre2_dftables is compiled and run in the default C locale
+  when you obey "make". It builds a source file called pcre2_chartables.c. If
+  you do not specify this option, pcre2_chartables.c is created as a copy of
+  pcre2_chartables.c.dist. See "Character tables" below for further
+  information.
+
+. It is possible to compile PCRE2 for use on systems that use EBCDIC as their
+  character code (as opposed to ASCII/Unicode) by specifying
+
+  --enable-ebcdic --disable-unicode
+
+  This automatically implies --enable-rebuild-chartables (see above). However,
+  when PCRE2 is built this way, it always operates in EBCDIC. It cannot support
+  both EBCDIC and UTF-8/16/32. There is a second option, --enable-ebcdic-nl25,
+  which specifies that the code value for the EBCDIC NL character is 0x25
+  instead of the default 0x15.
+
+. If you specify --enable-debug, additional debugging code is included in the
+  build. This option is intended for use by the PCRE2 maintainers.
+
+. In environments where valgrind is installed, if you specify
+
+  --enable-valgrind
+
+  PCRE2 will use valgrind annotations to mark certain memory regions as
+  unaddressable. This allows it to detect invalid memory accesses, and is
+  mostly useful for debugging PCRE2 itself.
+
+. In environments where the gcc compiler is used and lcov is installed, if you
+  specify
+
+  --enable-coverage
+
+  the build process implements a code coverage report for the test suite. The
+  report is generated by running "make coverage". If ccache is installed on
+  your system, it must be disabled when building PCRE2 for coverage reporting.
+  You can do this by setting the environment variable CCACHE_DISABLE=1 before
+  running "make" to build PCRE2. There is more information about coverage
+  reporting in the "pcre2build" documentation.
+
+. When JIT support is enabled, pcre2grep automatically makes use of it, unless
+  you add --disable-pcre2grep-jit to the "configure" command.
+
+. There is support for calling external programs during matching in the
+  pcre2grep command, using PCRE2's callout facility with string arguments. This
+  support can be disabled by adding --disable-pcre2grep-callout to the
+  "configure" command. There are two kinds of callout: one that generates
+  output from inbuilt code, and another that calls an external program. The
+  latter has special support for Windows and VMS; otherwise it assumes the
+  existence of the fork() function. This facility can be disabled by adding
+  --disable-pcre2grep-callout-fork to the "configure" command.
+
+. The pcre2grep program currently supports only 8-bit data files, and so
+  requires the 8-bit PCRE2 library. It is possible to compile pcre2grep to use
+  libz and/or libbz2, in order to read .gz and .bz2 files (respectively), by
+  specifying one or both of
+
+  --enable-pcre2grep-libz
+  --enable-pcre2grep-libbz2
+
+  Of course, the relevant libraries must be installed on your system.
+
+. The default starting size (in bytes) of the internal buffer used by pcre2grep
+  can be set by, for example:
+
+  --with-pcre2grep-bufsize=51200
+
+  The value must be a plain integer. The default is 20480. The amount of memory
+  used by pcre2grep is actually three times this number, to allow for "before"
+  and "after" lines. If very long lines are encountered, the buffer is
+  automatically enlarged, up to a fixed maximum size.
+
+. The default maximum size of pcre2grep's internal buffer can be set by, for
+  example:
+
+  --with-pcre2grep-max-bufsize=2097152
+
+  The default is either 1048576 or the value of --with-pcre2grep-bufsize,
+  whichever is the larger.
+
+. It is possible to compile pcre2test so that it links with the libreadline
+  or libedit libraries, by specifying, respectively,
+
+  --enable-pcre2test-libreadline or --enable-pcre2test-libedit
+
+  If this is done, when pcre2test's input is from a terminal, it reads it using
+  the readline() function. This provides line-editing and history facilities.
+  Note that libreadline is GPL-licenced, so if you distribute a binary of
+  pcre2test linked in this way, there may be licensing issues. These can be
+  avoided by linking with libedit (which has a BSD licence) instead.
+
+  Enabling libreadline causes the -lreadline option to be added to the
+  pcre2test build. In many operating environments with a sytem-installed
+  readline library this is sufficient. However, in some environments (e.g. if
+  an unmodified distribution version of readline is in use), it may be
+  necessary to specify something like LIBS="-lncurses" as well. This is
+  because, to quote the readline INSTALL, "Readline uses the termcap functions,
+  but does not link with the termcap or curses library itself, allowing
+  applications which link with readline the to choose an appropriate library."
+  If you get error messages about missing functions tgetstr, tgetent, tputs,
+  tgetflag, or tgoto, this is the problem, and linking with the ncurses library
+  should fix it.
+
+. The C99 standard defines formatting modifiers z and t for size_t and
+  ptrdiff_t values, respectively. By default, PCRE2 uses these modifiers in
+  environments other than Microsoft Visual Studio when __STDC_VERSION__ is
+  defined and has a value greater than or equal to 199901L (indicating C99).
+  However, there is at least one environment that claims to be C99 but does not
+  support these modifiers. If --disable-percent-zt is specified, no use is made
+  of the z or t modifiers. Instead or %td or %zu, %lu is used, with a cast for
+  size_t values.
+
+. There is a special option called --enable-fuzz-support for use by people who
+  want to run fuzzing tests on PCRE2. At present this applies only to the 8-bit
+  library. If set, it causes an extra library called libpcre2-fuzzsupport.a to
+  be built, but not installed. This contains a single function called
+  LLVMFuzzerTestOneInput() whose arguments are a pointer to a string and the
+  length of the string. When called, this function tries to compile the string
+  as a pattern, and if that succeeds, to match it. This is done both with no
+  options and with some random options bits that are generated from the string.
+  Setting --enable-fuzz-support also causes a binary called pcre2fuzzcheck to
+  be created. This is normally run under valgrind or used when PCRE2 is
+  compiled with address sanitizing enabled. It calls the fuzzing function and
+  outputs information about it is doing. The input strings are specified by
+  arguments: if an argument starts with "=" the rest of it is a literal input
+  string. Otherwise, it is assumed to be a file name, and the contents of the
+  file are the test string.
+
+. Releases before 10.30 could be compiled with --disable-stack-for-recursion,
+  which caused pcre2_match() to use individual blocks on the heap for
+  backtracking instead of recursive function calls (which use the stack). This
+  is now obsolete since pcre2_match() was refactored always to use the heap (in
+  a much more efficient way than before). This option is retained for backwards
+  compatibility, but has no effect other than to output a warning.
+
+The "configure" script builds the following files for the basic C library:
+
+. Makefile             the makefile that builds the library
+. src/config.h         build-time configuration options for the library
+. src/pcre2.h          the public PCRE2 header file
+. pcre2-config          script that shows the building settings such as CFLAGS
+                         that were set for "configure"
+. libpcre2-8.pc        )
+. libpcre2-16.pc       ) data for the pkg-config command
+. libpcre2-32.pc       )
+. libpcre2-posix.pc    )
+. libtool              script that builds shared and/or static libraries
+
+Versions of config.h and pcre2.h are distributed in the src directory of PCRE2
+tarballs under the names config.h.generic and pcre2.h.generic. These are
+provided for those who have to build PCRE2 without using "configure" or CMake.
+If you use "configure" or CMake, the .generic versions are not used.
+
+The "configure" script also creates config.status, which is an executable
+script that can be run to recreate the configuration, and config.log, which
+contains compiler output from tests that "configure" runs.
+
+Once "configure" has run, you can run "make". This builds whichever of the
+libraries libpcre2-8, libpcre2-16 and libpcre2-32 are configured, and a test
+program called pcre2test. If you enabled JIT support with --enable-jit, another
+test program called pcre2_jit_test is built as well. If the 8-bit library is
+built, libpcre2-posix and the pcre2grep command are also built. Running
+"make" with the -j option may speed up compilation on multiprocessor systems.
+
+The command "make check" runs all the appropriate tests. Details of the PCRE2
+tests are given below in a separate section of this document. The -j option of
+"make" can also be used when running the tests.
+
+You can use "make install" to install PCRE2 into live directories on your
+system. The following are installed (file names are all relative to the
+<prefix> that is set when "configure" is run):
+
+  Commands (bin):
+    pcre2test
+    pcre2grep (if 8-bit support is enabled)
+    pcre2-config
+
+  Libraries (lib):
+    libpcre2-8      (if 8-bit support is enabled)
+    libpcre2-16     (if 16-bit support is enabled)
+    libpcre2-32     (if 32-bit support is enabled)
+    libpcre2-posix  (if 8-bit support is enabled)
+
+  Configuration information (lib/pkgconfig):
+    libpcre2-8.pc
+    libpcre2-16.pc
+    libpcre2-32.pc
+    libpcre2-posix.pc
+
+  Header files (include):
+    pcre2.h
+    pcre2posix.h
+
+  Man pages (share/man/man{1,3}):
+    pcre2grep.1
+    pcre2test.1
+    pcre2-config.1
+    pcre2.3
+    pcre2*.3 (lots more pages, all starting "pcre2")
+
+  HTML documentation (share/doc/pcre2/html):
+    index.html
+    *.html (lots more pages, hyperlinked from index.html)
+
+  Text file documentation (share/doc/pcre2):
+    AUTHORS
+    COPYING
+    ChangeLog
+    LICENCE
+    NEWS
+    README
+    pcre2.txt         (a concatenation of the man(3) pages)
+    pcre2test.txt     the pcre2test man page
+    pcre2grep.txt     the pcre2grep man page
+    pcre2-config.txt  the pcre2-config man page
+
+If you want to remove PCRE2 from your system, you can run "make uninstall".
+This removes all the files that "make install" installed. However, it does not
+remove any directories, because these are often shared with other programs.
+
+
+Retrieving configuration information
+------------------------------------
+
+Running "make install" installs the command pcre2-config, which can be used to
+recall information about the PCRE2 configuration and installation. For example:
+
+  pcre2-config --version
+
+prints the version number, and
+
+  pcre2-config --libs8
+
+outputs information about where the 8-bit library is installed. This command
+can be included in makefiles for programs that use PCRE2, saving the programmer
+from having to remember too many details. Run pcre2-config with no arguments to
+obtain a list of possible arguments.
+
+The pkg-config command is another system for saving and retrieving information
+about installed libraries. Instead of separate commands for each library, a
+single command is used. For example:
+
+  pkg-config --libs libpcre2-16
+
+The data is held in *.pc files that are installed in a directory called
+<prefix>/lib/pkgconfig.
+
+
+Shared libraries
+----------------
+
+The default distribution builds PCRE2 as shared libraries and static libraries,
+as long as the operating system supports shared libraries. Shared library
+support relies on the "libtool" script which is built as part of the
+"configure" process.
+
+The libtool script is used to compile and link both shared and static
+libraries. They are placed in a subdirectory called .libs when they are newly
+built. The programs pcre2test and pcre2grep are built to use these uninstalled
+libraries (by means of wrapper scripts in the case of shared libraries). When
+you use "make install" to install shared libraries, pcre2grep and pcre2test are
+automatically re-built to use the newly installed shared libraries before being
+installed themselves. However, the versions left in the build directory still
+use the uninstalled libraries.
+
+To build PCRE2 using static libraries only you must use --disable-shared when
+configuring it. For example:
+
+./configure --prefix=/usr/gnu --disable-shared
+
+Then run "make" in the usual way. Similarly, you can use --disable-static to
+build only shared libraries.
+
+
+Cross-compiling using autotools
+-------------------------------
+
+You can specify CC and CFLAGS in the normal way to the "configure" command, in
+order to cross-compile PCRE2 for some other host. However, you should NOT
+specify --enable-rebuild-chartables, because if you do, the pcre2_dftables.c
+source file is compiled and run on the local host, in order to generate the
+inbuilt character tables (the pcre2_chartables.c file). This will probably not
+work, because pcre2_dftables.c needs to be compiled with the local compiler,
+not the cross compiler.
+
+When --enable-rebuild-chartables is not specified, pcre2_chartables.c is
+created by making a copy of pcre2_chartables.c.dist, which is a default set of
+tables that assumes ASCII code. Cross-compiling with the default tables should
+not be a problem.
+
+If you need to modify the character tables when cross-compiling, you should
+move pcre2_chartables.c.dist out of the way, then compile pcre2_dftables.c by
+hand and run it on the local host to make a new version of
+pcre2_chartables.c.dist. See the pcre2build section "Creating character tables
+at build time" for more details.
+
+
+Making new tarballs
+-------------------
+
+The command "make dist" creates three PCRE2 tarballs, in tar.gz, tar.bz2, and
+zip formats. The command "make distcheck" does the same, but then does a trial
+build of the new distribution to ensure that it works.
+
+If you have modified any of the man page sources in the doc directory, you
+should first run the PrepareRelease script before making a distribution. This
+script creates the .txt and HTML forms of the documentation from the man pages.
+
+
+Testing PCRE2
+-------------
+
+To test the basic PCRE2 library on a Unix-like system, run the RunTest script.
+There is another script called RunGrepTest that tests the pcre2grep command.
+When JIT support is enabled, a third test program called pcre2_jit_test is
+built. Both the scripts and all the program tests are run if you obey "make
+check". For other environments, see the instructions in NON-AUTOTOOLS-BUILD.
+
+The RunTest script runs the pcre2test test program (which is documented in its
+own man page) on each of the relevant testinput files in the testdata
+directory, and compares the output with the contents of the corresponding
+testoutput files. RunTest uses a file called testtry to hold the main output
+from pcre2test. Other files whose names begin with "test" are used as working
+files in some tests.
+
+Some tests are relevant only when certain build-time options were selected. For
+example, the tests for UTF-8/16/32 features are run only when Unicode support
+is available. RunTest outputs a comment when it skips a test.
+
+Many (but not all) of the tests that are not skipped are run twice if JIT
+support is available. On the second run, JIT compilation is forced. This
+testing can be suppressed by putting "nojit" on the RunTest command line.
+
+The entire set of tests is run once for each of the 8-bit, 16-bit and 32-bit
+libraries that are enabled. If you want to run just one set of tests, call
+RunTest with either the -8, -16 or -32 option.
+
+If valgrind is installed, you can run the tests under it by putting "valgrind"
+on the RunTest command line. To run pcre2test on just one or more specific test
+files, give their numbers as arguments to RunTest, for example:
+
+  RunTest 2 7 11
+
+You can also specify ranges of tests such as 3-6 or 3- (meaning 3 to the
+end), or a number preceded by ~ to exclude a test. For example:
+
+  Runtest 3-15 ~10
+
+This runs tests 3 to 15, excluding test 10, and just ~13 runs all the tests
+except test 13. Whatever order the arguments are in, the tests are always run
+in numerical order.
+
+You can also call RunTest with the single argument "list" to cause it to output
+a list of tests.
+
+The test sequence starts with "test 0", which is a special test that has no
+input file, and whose output is not checked. This is because it will be
+different on different hardware and with different configurations. The test
+exists in order to exercise some of pcre2test's code that would not otherwise
+be run.
+
+Tests 1 and 2 can always be run, as they expect only plain text strings (not
+UTF) and make no use of Unicode properties. The first test file can be fed
+directly into the perltest.sh script to check that Perl gives the same results.
+The only difference you should see is in the first few lines, where the Perl
+version is given instead of the PCRE2 version. The second set of tests check
+auxiliary functions, error detection, and run-time flags that are specific to
+PCRE2. It also uses the debugging flags to check some of the internals of
+pcre2_compile().
+
+If you build PCRE2 with a locale setting that is not the standard C locale, the
+character tables may be different (see next paragraph). In some cases, this may
+cause failures in the second set of tests. For example, in a locale where the
+isprint() function yields TRUE for characters in the range 128-255, the use of
+[:isascii:] inside a character class defines a different set of characters, and
+this shows up in this test as a difference in the compiled code, which is being
+listed for checking. For example, where the comparison test output contains
+[\x00-\x7f] the test might contain [\x00-\xff], and similarly in some other
+cases. This is not a bug in PCRE2.
+
+Test 3 checks pcre2_maketables(), the facility for building a set of character
+tables for a specific locale and using them instead of the default tables. The
+script uses the "locale" command to check for the availability of the "fr_FR",
+"french", or "fr" locale, and uses the first one that it finds. If the "locale"
+command fails, or if its output doesn't include "fr_FR", "french", or "fr" in
+the list of available locales, the third test cannot be run, and a comment is
+output to say why. If running this test produces an error like this:
+
+  ** Failed to set locale "fr_FR"
+
+it means that the given locale is not available on your system, despite being
+listed by "locale". This does not mean that PCRE2 is broken. There are three
+alternative output files for the third test, because three different versions
+of the French locale have been encountered. The test passes if its output
+matches any one of them.
+
+Tests 4 and 5 check UTF and Unicode property support, test 4 being compatible
+with the perltest.sh script, and test 5 checking PCRE2-specific things.
+
+Tests 6 and 7 check the pcre2_dfa_match() alternative matching function, in
+non-UTF mode and UTF-mode with Unicode property support, respectively.
+
+Test 8 checks some internal offsets and code size features, but it is run only
+when Unicode support is enabled. The output is different in 8-bit, 16-bit, and
+32-bit modes and for different link sizes, so there are different output files
+for each mode and link size.
+
+Tests 9 and 10 are run only in 8-bit mode, and tests 11 and 12 are run only in
+16-bit and 32-bit modes. These are tests that generate different output in
+8-bit mode. Each pair are for general cases and Unicode support, respectively.
+
+Test 13 checks the handling of non-UTF characters greater than 255 by
+pcre2_dfa_match() in 16-bit and 32-bit modes.
+
+Test 14 contains some special UTF and UCP tests that give different output for
+different code unit widths.
+
+Test 15 contains a number of tests that must not be run with JIT. They check,
+among other non-JIT things, the match-limiting features of the intepretive
+matcher.
+
+Test 16 is run only when JIT support is not available. It checks that an
+attempt to use JIT has the expected behaviour.
+
+Test 17 is run only when JIT support is available. It checks JIT complete and
+partial modes, match-limiting under JIT, and other JIT-specific features.
+
+Tests 18 and 19 are run only in 8-bit mode. They check the POSIX interface to
+the 8-bit library, without and with Unicode support, respectively.
+
+Test 20 checks the serialization functions by writing a set of compiled
+patterns to a file, and then reloading and checking them.
+
+Tests 21 and 22 test \C support when the use of \C is not locked out, without
+and with UTF support, respectively. Test 23 tests \C when it is locked out.
+
+Tests 24 and 25 test the experimental pattern conversion functions, without and
+with UTF support, respectively.
+
+
+Character tables
+----------------
+
+For speed, PCRE2 uses four tables for manipulating and identifying characters
+whose code point values are less than 256. By default, a set of tables that is
+built into the library is used. The pcre2_maketables() function can be called
+by an application to create a new set of tables in the current locale. This are
+passed to PCRE2 by calling pcre2_set_character_tables() to put a pointer into a
+compile context.
+
+The source file called pcre2_chartables.c contains the default set of tables.
+By default, this is created as a copy of pcre2_chartables.c.dist, which
+contains tables for ASCII coding. However, if --enable-rebuild-chartables is
+specified for ./configure, a new version of pcre2_chartables.c is built by the
+program pcre2_dftables (compiled from pcre2_dftables.c), which uses the ANSI C
+character handling functions such as isalnum(), isalpha(), isupper(),
+islower(), etc. to build the table sources. This means that the default C
+locale that is set for your system will control the contents of these default
+tables. You can change the default tables by editing pcre2_chartables.c and
+then re-building PCRE2. If you do this, you should take care to ensure that the
+file does not get automatically re-generated. The best way to do this is to
+move pcre2_chartables.c.dist out of the way and replace it with your customized
+tables.
+
+When the pcre2_dftables program is run as a result of specifying
+--enable-rebuild-chartables, it uses the default C locale that is set on your
+system. It does not pay attention to the LC_xxx environment variables. In other
+words, it uses the system's default locale rather than whatever the compiling
+user happens to have set. If you really do want to build a source set of
+character tables in a locale that is specified by the LC_xxx variables, you can
+run the pcre2_dftables program by hand with the -L option. For example:
+
+  ./pcre2_dftables -L pcre2_chartables.c.special
+
+The second argument names the file where the source code for the tables is
+written. The first two 256-byte tables provide lower casing and case flipping
+functions, respectively. The next table consists of a number of 32-byte bit
+maps which identify certain character classes such as digits, "word"
+characters, white space, etc. These are used when building 32-byte bit maps
+that represent character classes for code points less than 256. The final
+256-byte table has bits indicating various character types, as follows:
+
+    1   white space character
+    2   letter
+    4   lower case letter
+    8   decimal digit
+   16   alphanumeric or '_'
+
+You can also specify -b (with or without -L) when running pcre2_dftables. This
+causes the tables to be written in binary instead of as source code. A set of
+binary tables can be loaded into memory by an application and passed to
+pcre2_compile() in the same way as tables created dynamically by calling
+pcre2_maketables(). The tables are just a string of bytes, independent of
+hardware characteristics such as endianness. This means they can be bundled
+with an application that runs in different environments, to ensure consistent
+behaviour.
+
+See also the pcre2build section "Creating character tables at build time".
+
+
+File manifest
+-------------
+
+The distribution should contain the files listed below.
+
+(A) Source files for the PCRE2 library functions and their headers are found in
+    the src directory:
+
+  src/pcre2_dftables.c     auxiliary program for building pcre2_chartables.c
+                           when --enable-rebuild-chartables is specified
+
+  src/pcre2_chartables.c.dist  a default set of character tables that assume
+                           ASCII coding; unless --enable-rebuild-chartables is
+                           specified, used by copying to pcre2_chartables.c
+
+  src/pcre2posix.c         )
+  src/pcre2_auto_possess.c )
+  src/pcre2_compile.c      )
+  src/pcre2_config.c       )
+  src/pcre2_context.c      )
+  src/pcre2_convert.c      )
+  src/pcre2_dfa_match.c    )
+  src/pcre2_error.c        )
+  src/pcre2_extuni.c       )
+  src/pcre2_find_bracket.c )
+  src/pcre2_jit_compile.c  )
+  src/pcre2_jit_match.c    ) sources for the functions in the library,
+  src/pcre2_jit_misc.c     )   and some internal functions that they use
+  src/pcre2_maketables.c   )
+  src/pcre2_match.c        )
+  src/pcre2_match_data.c   )
+  src/pcre2_newline.c      )
+  src/pcre2_ord2utf.c      )
+  src/pcre2_pattern_info.c )
+  src/pcre2_script_run.c   )
+  src/pcre2_serialize.c    )
+  src/pcre2_string_utils.c )
+  src/pcre2_study.c        )
+  src/pcre2_substitute.c   )
+  src/pcre2_substring.c    )
+  src/pcre2_tables.c       )
+  src/pcre2_ucd.c          )
+  src/pcre2_valid_utf.c    )
+  src/pcre2_xclass.c       )
+
+  src/pcre2_printint.c     debugging function that is used by pcre2test,
+  src/pcre2_fuzzsupport.c  function for (optional) fuzzing support
+
+  src/config.h.in          template for config.h, when built by "configure"
+  src/pcre2.h.in           template for pcre2.h when built by "configure"
+  src/pcre2posix.h         header for the external POSIX wrapper API
+  src/pcre2_internal.h     header for internal use
+  src/pcre2_intmodedep.h   a mode-specific internal header
+  src/pcre2_ucp.h          header for Unicode property handling
+
+  sljit/*                  source files for the JIT compiler
+
+(B) Source files for programs that use PCRE2:
+
+  src/pcre2demo.c          simple demonstration of coding calls to PCRE2
+  src/pcre2grep.c          source of a grep utility that uses PCRE2
+  src/pcre2test.c          comprehensive test program
+  src/pcre2_jit_test.c     JIT test program
+
+(C) Auxiliary files:
+
+  132html                  script to turn "man" pages into HTML
+  AUTHORS                  information about the author of PCRE2
+  ChangeLog                log of changes to the code
+  CleanTxt                 script to clean nroff output for txt man pages
+  Detrail                  script to remove trailing spaces
+  HACKING                  some notes about the internals of PCRE2
+  INSTALL                  generic installation instructions
+  LICENCE                  conditions for the use of PCRE2
+  COPYING                  the same, using GNU's standard name
+  Makefile.in              ) template for Unix Makefile, which is built by
+                           )   "configure"
+  Makefile.am              ) the automake input that was used to create
+                           )   Makefile.in
+  NEWS                     important changes in this release
+  NON-AUTOTOOLS-BUILD      notes on building PCRE2 without using autotools
+  PrepareRelease           script to make preparations for "make dist"
+  README                   this file
+  RunTest                  a Unix shell script for running tests
+  RunGrepTest              a Unix shell script for pcre2grep tests
+  aclocal.m4               m4 macros (generated by "aclocal")
+  config.guess             ) files used by libtool,
+  config.sub               )   used only when building a shared library
+  configure                a configuring shell script (built by autoconf)
+  configure.ac             ) the autoconf input that was used to build
+                           )   "configure" and config.h
+  depcomp                  ) script to find program dependencies, generated by
+                           )   automake
+  doc/*.3                  man page sources for PCRE2
+  doc/*.1                  man page sources for pcre2grep and pcre2test
+  doc/index.html.src       the base HTML page
+  doc/html/*               HTML documentation
+  doc/pcre2.txt            plain text version of the man pages
+  doc/pcre2test.txt        plain text documentation of test program
+  install-sh               a shell script for installing files
+  libpcre2-8.pc.in         template for libpcre2-8.pc for pkg-config
+  libpcre2-16.pc.in        template for libpcre2-16.pc for pkg-config
+  libpcre2-32.pc.in        template for libpcre2-32.pc for pkg-config
+  libpcre2-posix.pc.in     template for libpcre2-posix.pc for pkg-config
+  ltmain.sh                file used to build a libtool script
+  missing                  ) common stub for a few missing GNU programs while
+                           )   installing, generated by automake
+  mkinstalldirs            script for making install directories
+  perltest.sh              Script for running a Perl test program
+  pcre2-config.in          source of script which retains PCRE2 information
+  testdata/testinput*      test data for main library tests
+  testdata/testoutput*     expected test results
+  testdata/grep*           input and output for pcre2grep tests
+  testdata/*               other supporting test files
+
+(D) Auxiliary files for cmake support
+
+  cmake/COPYING-CMAKE-SCRIPTS
+  cmake/FindPackageHandleStandardArgs.cmake
+  cmake/FindEditline.cmake
+  cmake/FindReadline.cmake
+  CMakeLists.txt
+  config-cmake.h.in
+
+(E) Auxiliary files for building PCRE2 "by hand"
+
+  src/pcre2.h.generic     ) a version of the public PCRE2 header file
+                          )   for use in non-"configure" environments
+  src/config.h.generic    ) a version of config.h for use in non-"configure"
+                          )   environments
+
+Philip Hazel
+Email local part: Philip.Hazel
+Email domain: gmail.com
+Last updated: 28 April 2021

src/regex/pcre2/doc/html/index.html

@@ -0,0 +1,312 @@
+<html>
+<!-- This is a manually maintained file that is the root of the HTML version of
+     the PCRE2 documentation. When the HTML documents are built from the man
+     page versions, the entire doc/html directory is emptied, this file is then
+     copied into doc/html/index.html, and the remaining files therein are
+     created by the 132html script.
+-->
+<head>
+<title>PCRE2 specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>Perl-compatible Regular Expressions (revised API: PCRE2)</h1>
+<p>
+The HTML documentation for PCRE2 consists of a number of pages that are listed
+below in alphabetical order. If you are new to PCRE2, please read the first one
+first.
+</p>
+
+<table>
+<tr><td><a href="pcre2.html">pcre2</a></td>
+    <td>&nbsp;&nbsp;Introductory page</td></tr>
+
+<tr><td><a href="pcre2-config.html">pcre2-config</a></td>
+    <td>&nbsp;&nbsp;Information about the installation configuration</td></tr>
+
+<tr><td><a href="pcre2api.html">pcre2api</a></td>
+    <td>&nbsp;&nbsp;PCRE2's native API</td></tr>
+
+<tr><td><a href="pcre2build.html">pcre2build</a></td>
+    <td>&nbsp;&nbsp;Building PCRE2</td></tr>
+
+<tr><td><a href="pcre2callout.html">pcre2callout</a></td>
+    <td>&nbsp;&nbsp;The <i>callout</i> facility</td></tr>
+
+<tr><td><a href="pcre2compat.html">pcre2compat</a></td>
+    <td>&nbsp;&nbsp;Compability with Perl</td></tr>
+
+<tr><td><a href="pcre2convert.html">pcre2convert</a></td>
+    <td>&nbsp;&nbsp;Experimental foreign pattern conversion functions</td></tr>
+
+<tr><td><a href="pcre2demo.html">pcre2demo</a></td>
+    <td>&nbsp;&nbsp;A demonstration C program that uses the PCRE2 library</td></tr>
+
+<tr><td><a href="pcre2grep.html">pcre2grep</a></td>
+    <td>&nbsp;&nbsp;The <b>pcre2grep</b> command</td></tr>
+
+<tr><td><a href="pcre2jit.html">pcre2jit</a></td>
+    <td>&nbsp;&nbsp;Discussion of the just-in-time optimization support</td></tr>
+
+<tr><td><a href="pcre2limits.html">pcre2limits</a></td>
+    <td>&nbsp;&nbsp;Details of size and other limits</td></tr>
+
+<tr><td><a href="pcre2matching.html">pcre2matching</a></td>
+    <td>&nbsp;&nbsp;Discussion of the two matching algorithms</td></tr>
+
+<tr><td><a href="pcre2partial.html">pcre2partial</a></td>
+    <td>&nbsp;&nbsp;Using PCRE2 for partial matching</td></tr>
+
+<tr><td><a href="pcre2pattern.html">pcre2pattern</a></td>
+    <td>&nbsp;&nbsp;Specification of the regular expressions supported by PCRE2</td></tr>
+
+<tr><td><a href="pcre2perform.html">pcre2perform</a></td>
+    <td>&nbsp;&nbsp;Some comments on performance</td></tr>
+
+<tr><td><a href="pcre2posix.html">pcre2posix</a></td>
+    <td>&nbsp;&nbsp;The POSIX API to the PCRE2 8-bit library</td></tr>
+
+<tr><td><a href="pcre2sample.html">pcre2sample</a></td>
+    <td>&nbsp;&nbsp;Discussion of the pcre2demo program</td></tr>
+
+<tr><td><a href="pcre2serialize.html">pcre2serialize</a></td>
+    <td>&nbsp;&nbsp;Serializing functions for saving precompiled patterns</td></tr>
+
+<tr><td><a href="pcre2syntax.html">pcre2syntax</a></td>
+    <td>&nbsp;&nbsp;Syntax quick-reference summary</td></tr>
+
+<tr><td><a href="pcre2test.html">pcre2test</a></td>
+    <td>&nbsp;&nbsp;The <b>pcre2test</b> command for testing PCRE2</td></tr>
+
+<tr><td><a href="pcre2unicode.html">pcre2unicode</a></td>
+    <td>&nbsp;&nbsp;Discussion of Unicode and UTF-8/UTF-16/UTF-32 support</td></tr>
+</table>
+
+<p>
+There are also individual pages that summarize the interface for each function
+in the library.
+</p>
+
+<table>
+
+<tr><td><a href="pcre2_callout_enumerate.html">pcre2_callout_enumerate</a></td>
+    <td>&nbsp;&nbsp;Enumerate callouts in a compiled pattern</td></tr>
+
+<tr><td><a href="pcre2_code_copy.html">pcre2_code_copy</a></td>
+    <td>&nbsp;&nbsp;Copy a compiled pattern</td></tr>
+
+<tr><td><a href="pcre2_code_copy_with_tables.html">pcre2_code_copy_with_tables</a></td>
+    <td>&nbsp;&nbsp;Copy a compiled pattern and its character tables</td></tr>
+
+<tr><td><a href="pcre2_code_free.html">pcre2_code_free</a></td>
+    <td>&nbsp;&nbsp;Free a compiled pattern</td></tr>
+
+<tr><td><a href="pcre2_compile.html">pcre2_compile</a></td>
+    <td>&nbsp;&nbsp;Compile a regular expression pattern</td></tr>
+
+<tr><td><a href="pcre2_compile_context_copy.html">pcre2_compile_context_copy</a></td>
+    <td>&nbsp;&nbsp;Copy a compile context</td></tr>
+
+<tr><td><a href="pcre2_compile_context_create.html">pcre2_compile_context_create</a></td>
+    <td>&nbsp;&nbsp;Create a compile context</td></tr>
+
+<tr><td><a href="pcre2_compile_context_free.html">pcre2_compile_context_free</a></td>
+    <td>&nbsp;&nbsp;Free a compile context</td></tr>
+
+<tr><td><a href="pcre2_config.html">pcre2_config</a></td>
+    <td>&nbsp;&nbsp;Show build-time configuration options</td></tr>
+
+<tr><td><a href="pcre2_convert_context_copy.html">pcre2_convert_context_copy</a></td>
+    <td>&nbsp;&nbsp;Copy a convert context</td></tr>
+
+<tr><td><a href="pcre2_convert_context_create.html">pcre2_convert_context_create</a></td>
+    <td>&nbsp;&nbsp;Create a convert context</td></tr>
+
+<tr><td><a href="pcre2_convert_context_free.html">pcre2_convert_context_free</a></td>
+    <td>&nbsp;&nbsp;Free a convert context</td></tr>
+
+<tr><td><a href="pcre2_converted_pattern_free.html">pcre2_converted_pattern_free</a></td>
+    <td>&nbsp;&nbsp;Free converted foreign pattern</td></tr>
+
+<tr><td><a href="pcre2_dfa_match.html">pcre2_dfa_match</a></td>
+    <td>&nbsp;&nbsp;Match a compiled pattern to a subject string
+    (DFA algorithm; <i>not</i> Perl compatible)</td></tr>
+
+<tr><td><a href="pcre2_general_context_copy.html">pcre2_general_context_copy</a></td>
+    <td>&nbsp;&nbsp;Copy a general context</td></tr>
+
+<tr><td><a href="pcre2_general_context_create.html">pcre2_general_context_create</a></td>
+    <td>&nbsp;&nbsp;Create a general context</td></tr>
+
+<tr><td><a href="pcre2_general_context_free.html">pcre2_general_context_free</a></td>
+    <td>&nbsp;&nbsp;Free a general context</td></tr>
+
+<tr><td><a href="pcre2_get_error_message.html">pcre2_get_error_message</a></td>
+    <td>&nbsp;&nbsp;Get textual error message for error number</td></tr>
+
+<tr><td><a href="pcre2_get_mark.html">pcre2_get_mark</a></td>
+    <td>&nbsp;&nbsp;Get a (*MARK) name</td></tr>
+
+<tr><td><a href="pcre2_get_match_data_size.html">pcre2_get_match_data_size</a></td>
+    <td>&nbsp;&nbsp;Get the size of a match data block</td></tr>
+
+<tr><td><a href="pcre2_get_ovector_count.html">pcre2_get_ovector_count</a></td>
+    <td>&nbsp;&nbsp;Get the ovector count</td></tr>
+
+<tr><td><a href="pcre2_get_ovector_pointer.html">pcre2_get_ovector_pointer</a></td>
+    <td>&nbsp;&nbsp;Get a pointer to the ovector</td></tr>
+
+<tr><td><a href="pcre2_get_startchar.html">pcre2_get_startchar</a></td>
+    <td>&nbsp;&nbsp;Get the starting character offset</td></tr>
+
+<tr><td><a href="pcre2_jit_compile.html">pcre2_jit_compile</a></td>
+    <td>&nbsp;&nbsp;Process a compiled pattern with the JIT compiler</td></tr>
+
+<tr><td><a href="pcre2_jit_free_unused_memory.html">pcre2_jit_free_unused_memory</a></td>
+    <td>&nbsp;&nbsp;Free unused JIT memory</td></tr>
+
+<tr><td><a href="pcre2_jit_match.html">pcre2_jit_match</a></td>
+    <td>&nbsp;&nbsp;Fast path interface to JIT matching</td></tr>
+
+<tr><td><a href="pcre2_jit_stack_assign.html">pcre2_jit_stack_assign</a></td>
+    <td>&nbsp;&nbsp;Assign stack for JIT matching</td></tr>
+
+<tr><td><a href="pcre2_jit_stack_create.html">pcre2_jit_stack_create</a></td>
+    <td>&nbsp;&nbsp;Create a stack for JIT matching</td></tr>
+
+<tr><td><a href="pcre2_jit_stack_free.html">pcre2_jit_stack_free</a></td>
+    <td>&nbsp;&nbsp;Free a JIT matching stack</td></tr>
+
+<tr><td><a href="pcre2_maketables.html">pcre2_maketables</a></td>
+    <td>&nbsp;&nbsp;Build character tables in current locale</td></tr>
+
+<tr><td><a href="pcre2_maketables_free.html">pcre2_maketables_free</a></td>
+    <td>&nbsp;&nbsp;Free character tables</td></tr>
+
+<tr><td><a href="pcre2_match.html">pcre2_match</a></td>
+    <td>&nbsp;&nbsp;Match a compiled pattern to a subject string
+    (Perl compatible)</td></tr>
+
+<tr><td><a href="pcre2_match_context_copy.html">pcre2_match_context_copy</a></td>
+    <td>&nbsp;&nbsp;Copy a match context</td></tr>
+
+<tr><td><a href="pcre2_match_context_create.html">pcre2_match_context_create</a></td>
+    <td>&nbsp;&nbsp;Create a match context</td></tr>
+
+<tr><td><a href="pcre2_match_context_free.html">pcre2_match_context_free</a></td>
+    <td>&nbsp;&nbsp;Free a match context</td></tr>
+
+<tr><td><a href="pcre2_match_data_create.html">pcre2_match_data_create</a></td>
+    <td>&nbsp;&nbsp;Create a match data block</td></tr>
+
+<tr><td><a href="pcre2_match_data_create_from_pattern.html">pcre2_match_data_create_from_pattern</a></td>
+    <td>&nbsp;&nbsp;Create a match data block getting size from pattern</td></tr>
+
+<tr><td><a href="pcre2_match_data_free.html">pcre2_match_data_free</a></td>
+    <td>&nbsp;&nbsp;Free a match data block</td></tr>
+
+<tr><td><a href="pcre2_pattern_convert.html">pcre2_pattern_convert</a></td>
+    <td>&nbsp;&nbsp;Experimental foreign pattern converter</td></tr>
+
+<tr><td><a href="pcre2_pattern_info.html">pcre2_pattern_info</a></td>
+    <td>&nbsp;&nbsp;Extract information about a pattern</td></tr>
+
+<tr><td><a href="pcre2_serialize_decode.html">pcre2_serialize_decode</a></td>
+    <td>&nbsp;&nbsp;Decode serialized compiled patterns</td></tr>
+
+<tr><td><a href="pcre2_serialize_encode.html">pcre2_serialize_encode</a></td>
+    <td>&nbsp;&nbsp;Serialize compiled patterns for save/restore</td></tr>
+
+<tr><td><a href="pcre2_serialize_free.html">pcre2_serialize_free</a></td>
+    <td>&nbsp;&nbsp;Free serialized compiled patterns</td></tr>
+
+<tr><td><a href="pcre2_serialize_get_number_of_codes.html">pcre2_serialize_get_number_of_codes</a></td>
+    <td>&nbsp;&nbsp;Get number of serialized compiled patterns</td></tr>
+
+<tr><td><a href="pcre2_set_bsr.html">pcre2_set_bsr</a></td>
+    <td>&nbsp;&nbsp;Set \R convention</td></tr>
+
+<tr><td><a href="pcre2_set_callout.html">pcre2_set_callout</a></td>
+    <td>&nbsp;&nbsp;Set up a callout function</td></tr>
+
+<tr><td><a href="pcre2_set_character_tables.html">pcre2_set_character_tables</a></td>
+    <td>&nbsp;&nbsp;Set character tables</td></tr>
+
+<tr><td><a href="pcre2_set_compile_extra_options.html">pcre2_set_compile_extra_options</a></td>
+    <td>&nbsp;&nbsp;Set compile time extra options</td></tr>
+
+<tr><td><a href="pcre2_set_compile_recursion_guard.html">pcre2_set_compile_recursion_guard</a></td>
+    <td>&nbsp;&nbsp;Set up a compile recursion guard function</td></tr>
+
+<tr><td><a href="pcre2_set_depth_limit.html">pcre2_set_depth_limit</a></td>
+    <td>&nbsp;&nbsp;Set the match backtracking depth limit</td></tr>
+
+<tr><td><a href="pcre2_set_glob_escape.html">pcre2_set_glob_escape</a></td>
+    <td>&nbsp;&nbsp;Set glob escape character</td></tr>
+
+<tr><td><a href="pcre2_set_glob_separator.html">pcre2_set_glob_separator</a></td>
+    <td>&nbsp;&nbsp;Set glob separator character</td></tr>
+
+<tr><td><a href="pcre2_set_heap_limit.html">pcre2_set_heap_limit</a></td>
+    <td>&nbsp;&nbsp;Set the match backtracking heap limit</td></tr>
+
+<tr><td><a href="pcre2_set_match_limit.html">pcre2_set_match_limit</a></td>
+    <td>&nbsp;&nbsp;Set the match limit</td></tr>
+
+<tr><td><a href="pcre2_set_max_pattern_length.html">pcre2_set_max_pattern_length</a></td>
+    <td>&nbsp;&nbsp;Set the maximum length of pattern</td></tr>
+
+<tr><td><a href="pcre2_set_newline.html">pcre2_set_newline</a></td>
+    <td>&nbsp;&nbsp;Set the newline convention</td></tr>
+
+<tr><td><a href="pcre2_set_offset_limit.html">pcre2_set_offset_limit</a></td>
+    <td>&nbsp;&nbsp;Set the offset limit</td></tr>
+
+<tr><td><a href="pcre2_set_parens_nest_limit.html">pcre2_set_parens_nest_limit</a></td>
+    <td>&nbsp;&nbsp;Set the parentheses nesting limit</td></tr>
+
+<tr><td><a href="pcre2_set_recursion_limit.html">pcre2_set_recursion_limit</a></td>
+    <td>&nbsp;&nbsp;Obsolete: use pcre2_set_depth_limit</td></tr>
+
+<tr><td><a href="pcre2_set_recursion_memory_management.html">pcre2_set_recursion_memory_management</a></td>
+    <td>&nbsp;&nbsp;Obsolete function that (from 10.30 onwards) does nothing</td></tr>
+
+<tr><td><a href="pcre2_substitute.html">pcre2_substitute</a></td>
+    <td>&nbsp;&nbsp;Match a compiled pattern to a subject string and do
+    substitutions</td></tr>
+
+<tr><td><a href="pcre2_substring_copy_byname.html">pcre2_substring_copy_byname</a></td>
+    <td>&nbsp;&nbsp;Extract named substring into given buffer</td></tr>
+
+<tr><td><a href="pcre2_substring_copy_bynumber.html">pcre2_substring_copy_bynumber</a></td>
+    <td>&nbsp;&nbsp;Extract numbered substring into given buffer</td></tr>
+
+<tr><td><a href="pcre2_substring_free.html">pcre2_substring_free</a></td>
+    <td>&nbsp;&nbsp;Free extracted substring</td></tr>
+
+<tr><td><a href="pcre2_substring_get_byname.html">pcre2_substring_get_byname</a></td>
+    <td>&nbsp;&nbsp;Extract named substring into new memory</td></tr>
+
+<tr><td><a href="pcre2_substring_get_bynumber.html">pcre2_substring_get_bynumber</a></td>
+    <td>&nbsp;&nbsp;Extract numbered substring into new memory</td></tr>
+
+<tr><td><a href="pcre2_substring_length_byname.html">pcre2_substring_length_byname</a></td>
+    <td>&nbsp;&nbsp;Find length of named substring</td></tr>
+
+<tr><td><a href="pcre2_substring_length_bynumber.html">pcre2_substring_length_bynumber</a></td>
+    <td>&nbsp;&nbsp;Find length of numbered substring</td></tr>
+
+<tr><td><a href="pcre2_substring_list_free.html">pcre2_substring_list_free</a></td>
+    <td>&nbsp;&nbsp;Free list of extracted substrings</td></tr>
+
+<tr><td><a href="pcre2_substring_list_get.html">pcre2_substring_list_get</a></td>
+    <td>&nbsp;&nbsp;Extract all substrings into new memory</td></tr>
+
+<tr><td><a href="pcre2_substring_nametable_scan.html">pcre2_substring_nametable_scan</a></td>
+    <td>&nbsp;&nbsp;Find table entries for given string name</td></tr>
+
+<tr><td><a href="pcre2_substring_number_from_name.html">pcre2_substring_number_from_name</a></td>
+    <td>&nbsp;&nbsp;Convert captured string name to number</td></tr>
+</table>
+
+</html>
+

src/regex/pcre2/doc/html/pcre2-config.html

@@ -0,0 +1,102 @@
+<html>
+<head>
+<title>pcre2-config specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2-config man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<ul>
+<li><a name="TOC1" href="#SEC1">SYNOPSIS</a>
+<li><a name="TOC2" href="#SEC2">DESCRIPTION</a>
+<li><a name="TOC3" href="#SEC3">OPTIONS</a>
+<li><a name="TOC4" href="#SEC4">SEE ALSO</a>
+<li><a name="TOC5" href="#SEC5">AUTHOR</a>
+<li><a name="TOC6" href="#SEC6">REVISION</a>
+</ul>
+<br><a name="SEC1" href="#TOC1">SYNOPSIS</a><br>
+<P>
+<b>pcre2-config  [--prefix] [--exec-prefix] [--version]</b>
+<b>             [--libs8] [--libs16] [--libs32] [--libs-posix]</b>
+<b>             [--cflags] [--cflags-posix]</b>
+</P>
+<br><a name="SEC2" href="#TOC1">DESCRIPTION</a><br>
+<P>
+<b>pcre2-config</b> returns the configuration of the installed PCRE2 libraries
+and the options required to compile a program to use them. Some of the options
+apply only to the 8-bit, or 16-bit, or 32-bit libraries, respectively, and are
+not available for libraries that have not been built. If an unavailable option
+is encountered, the "usage" information is output.
+</P>
+<br><a name="SEC3" href="#TOC1">OPTIONS</a><br>
+<P>
+<b>--prefix</b>
+Writes the directory prefix used in the PCRE2 installation for architecture
+independent files (<i>/usr</i> on many systems, <i>/usr/local</i> on some
+systems) to the standard output.
+</P>
+<P>
+<b>--exec-prefix</b>
+Writes the directory prefix used in the PCRE2 installation for architecture
+dependent files (normally the same as <b>--prefix</b>) to the standard output.
+</P>
+<P>
+<b>--version</b>
+Writes the version number of the installed PCRE2 libraries to the standard
+output.
+</P>
+<P>
+<b>--libs8</b>
+Writes to the standard output the command line options required to link
+with the 8-bit PCRE2 library (<b>-lpcre2-8</b> on many systems).
+</P>
+<P>
+<b>--libs16</b>
+Writes to the standard output the command line options required to link
+with the 16-bit PCRE2 library (<b>-lpcre2-16</b> on many systems).
+</P>
+<P>
+<b>--libs32</b>
+Writes to the standard output the command line options required to link
+with the 32-bit PCRE2 library (<b>-lpcre2-32</b> on many systems).
+</P>
+<P>
+<b>--libs-posix</b>
+Writes to the standard output the command line options required to link with
+PCRE2's POSIX API wrapper library (<b>-lpcre2-posix</b> <b>-lpcre2-8</b> on many
+systems).
+</P>
+<P>
+<b>--cflags</b>
+Writes to the standard output the command line options required to compile
+files that use PCRE2 (this may include some <b>-I</b> options, but is blank on
+many systems).
+</P>
+<P>
+<b>--cflags-posix</b>
+Writes to the standard output the command line options required to compile
+files that use PCRE2's POSIX API wrapper library (this may include some
+<b>-I</b> options, but is blank on many systems).
+</P>
+<br><a name="SEC4" href="#TOC1">SEE ALSO</a><br>
+<P>
+<b>pcre2(3)</b>
+</P>
+<br><a name="SEC5" href="#TOC1">AUTHOR</a><br>
+<P>
+This manual page was originally written by Mark Baker for the Debian GNU/Linux
+system. It has been subsequently revised as a generic PCRE2 man page.
+</P>
+<br><a name="SEC6" href="#TOC1">REVISION</a><br>
+<P>
+Last updated: 28 September 2014
+<br>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2.html

@@ -0,0 +1,213 @@
+<html>
+<head>
+<title>pcre2 specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2 man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<ul>
+<li><a name="TOC1" href="#SEC1">INTRODUCTION</a>
+<li><a name="TOC2" href="#SEC2">SECURITY CONSIDERATIONS</a>
+<li><a name="TOC3" href="#SEC3">USER DOCUMENTATION</a>
+<li><a name="TOC4" href="#SEC4">AUTHOR</a>
+<li><a name="TOC5" href="#SEC5">REVISION</a>
+</ul>
+<br><a name="SEC1" href="#TOC1">INTRODUCTION</a><br>
+<P>
+PCRE2 is the name used for a revised API for the PCRE library, which is a set
+of functions, written in C, that implement regular expression pattern matching
+using the same syntax and semantics as Perl, with just a few differences. After
+nearly two decades, the limitations of the original API were making development
+increasingly difficult. The new API is more extensible, and it was simplified
+by abolishing the separate "study" optimizing function; in PCRE2, patterns are
+automatically optimized where possible. Since forking from PCRE1, the code has
+been extensively refactored and new features introduced.
+</P>
+<P>
+As well as Perl-style regular expression patterns, some features that appeared
+in Python and the original PCRE before they appeared in Perl are available
+using the Python syntax. There is also some support for one or two .NET and
+Oniguruma syntax items, and there are options for requesting some minor changes
+that give better ECMAScript (aka JavaScript) compatibility.
+</P>
+<P>
+The source code for PCRE2 can be compiled to support strings of 8-bit, 16-bit,
+or 32-bit code units, which means that up to three separate libraries may be
+installed, one for each code unit size. The size of code unit is not related to
+the bit size of the underlying hardware. In a 64-bit environment that also
+supports 32-bit applications, versions of PCRE2 that are compiled in both
+64-bit and 32-bit modes may be needed.
+</P>
+<P>
+The original work to extend PCRE to 16-bit and 32-bit code units was done by
+Zoltan Herczeg and Christian Persch, respectively. In all three cases, strings
+can be interpreted either as one character per code unit, or as UTF-encoded
+Unicode, with support for Unicode general category properties. Unicode support
+is optional at build time (but is the default). However, processing strings as
+UTF code units must be enabled explicitly at run time. The version of Unicode
+in use can be discovered by running
+<pre>
+  pcre2test -C
+</PRE>
+</P>
+<P>
+The three libraries contain identical sets of functions, with names ending in
+_8, _16, or _32, respectively (for example, <b>pcre2_compile_8()</b>). However,
+by defining PCRE2_CODE_UNIT_WIDTH to be 8, 16, or 32, a program that uses just
+one code unit width can be written using generic names such as
+<b>pcre2_compile()</b>, and the documentation is written assuming that this is
+the case.
+</P>
+<P>
+In addition to the Perl-compatible matching function, PCRE2 contains an
+alternative function that matches the same compiled patterns in a different
+way. In certain circumstances, the alternative function has some advantages.
+For a discussion of the two matching algorithms, see the
+<a href="pcre2matching.html"><b>pcre2matching</b></a>
+page.
+</P>
+<P>
+Details of exactly which Perl regular expression features are and are not
+supported by PCRE2 are given in separate documents. See the
+<a href="pcre2pattern.html"><b>pcre2pattern</b></a>
+and
+<a href="pcre2compat.html"><b>pcre2compat</b></a>
+pages. There is a syntax summary in the
+<a href="pcre2syntax.html"><b>pcre2syntax</b></a>
+page.
+</P>
+<P>
+Some features of PCRE2 can be included, excluded, or changed when the library
+is built. The
+<a href="pcre2_config.html"><b>pcre2_config()</b></a>
+function makes it possible for a client to discover which features are
+available. The features themselves are described in the
+<a href="pcre2build.html"><b>pcre2build</b></a>
+page. Documentation about building PCRE2 for various operating systems can be
+found in the
+<a href="README.txt"><b>README</b></a>
+and
+<a href="NON-AUTOTOOLS-BUILD.txt"><b>NON-AUTOTOOLS_BUILD</b></a>
+files in the source distribution.
+</P>
+<P>
+The libraries contains a number of undocumented internal functions and data
+tables that are used by more than one of the exported external functions, but
+which are not intended for use by external callers. Their names all begin with
+"_pcre2", which hopefully will not provoke any name clashes. In some
+environments, it is possible to control which external symbols are exported
+when a shared library is built, and in these cases the undocumented symbols are
+not exported.
+</P>
+<br><a name="SEC2" href="#TOC1">SECURITY CONSIDERATIONS</a><br>
+<P>
+If you are using PCRE2 in a non-UTF application that permits users to supply
+arbitrary patterns for compilation, you should be aware of a feature that
+allows users to turn on UTF support from within a pattern. For example, an
+8-bit pattern that begins with "(*UTF)" turns on UTF-8 mode, which interprets
+patterns and subjects as strings of UTF-8 code units instead of individual
+8-bit characters. This causes both the pattern and any data against which it is
+matched to be checked for UTF-8 validity. If the data string is very long, such
+a check might use sufficiently many resources as to cause your application to
+lose performance.
+</P>
+<P>
+One way of guarding against this possibility is to use the
+<b>pcre2_pattern_info()</b> function to check the compiled pattern's options for
+PCRE2_UTF. Alternatively, you can set the PCRE2_NEVER_UTF option when calling
+<b>pcre2_compile()</b>. This causes a compile time error if the pattern contains
+a UTF-setting sequence.
+</P>
+<P>
+The use of Unicode properties for character types such as \d can also be
+enabled from within the pattern, by specifying "(*UCP)". This feature can be
+disallowed by setting the PCRE2_NEVER_UCP option.
+</P>
+<P>
+If your application is one that supports UTF, be aware that validity checking
+can take time. If the same data string is to be matched many times, you can use
+the PCRE2_NO_UTF_CHECK option for the second and subsequent matches to avoid
+running redundant checks.
+</P>
+<P>
+The use of the \C escape sequence in a UTF-8 or UTF-16 pattern can lead to
+problems, because it may leave the current matching point in the middle of a
+multi-code-unit character. The PCRE2_NEVER_BACKSLASH_C option can be used by an
+application to lock out the use of \C, causing a compile-time error if it is
+encountered. It is also possible to build PCRE2 with the use of \C permanently
+disabled.
+</P>
+<P>
+Another way that performance can be hit is by running a pattern that has a very
+large search tree against a string that will never match. Nested unlimited
+repeats in a pattern are a common example. PCRE2 provides some protection
+against this: see the <b>pcre2_set_match_limit()</b> function in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page. There is a similar function called <b>pcre2_set_depth_limit()</b> that can
+be used to restrict the amount of memory that is used.
+</P>
+<br><a name="SEC3" href="#TOC1">USER DOCUMENTATION</a><br>
+<P>
+The user documentation for PCRE2 comprises a number of different sections. In
+the "man" format, each of these is a separate "man page". In the HTML format,
+each is a separate page, linked from the index page. In the plain text format,
+the descriptions of the <b>pcre2grep</b> and <b>pcre2test</b> programs are in
+files called <b>pcre2grep.txt</b> and <b>pcre2test.txt</b>, respectively. The
+remaining sections, except for the <b>pcre2demo</b> section (which is a program
+listing), and the short pages for individual functions, are concatenated in
+<b>pcre2.txt</b>, for ease of searching. The sections are as follows:
+<pre>
+  pcre2              this document
+  pcre2-config       show PCRE2 installation configuration information
+  pcre2api           details of PCRE2's native C API
+  pcre2build         building PCRE2
+  pcre2callout       details of the pattern callout feature
+  pcre2compat        discussion of Perl compatibility
+  pcre2convert       details of pattern conversion functions
+  pcre2demo          a demonstration C program that uses PCRE2
+  pcre2grep          description of the <b>pcre2grep</b> command (8-bit only)
+  pcre2jit           discussion of just-in-time optimization support
+  pcre2limits        details of size and other limits
+  pcre2matching      discussion of the two matching algorithms
+  pcre2partial       details of the partial matching facility
+  pcre2pattern       syntax and semantics of supported regular expression patterns
+  pcre2perform       discussion of performance issues
+  pcre2posix         the POSIX-compatible C API for the 8-bit library
+  pcre2sample        discussion of the pcre2demo program
+  pcre2serialize     details of pattern serialization
+  pcre2syntax        quick syntax reference
+  pcre2test          description of the <b>pcre2test</b> command
+  pcre2unicode       discussion of Unicode and UTF support
+</pre>
+In the "man" and HTML formats, there is also a short page for each C library
+function, listing its arguments and results.
+</P>
+<br><a name="SEC4" href="#TOC1">AUTHOR</a><br>
+<P>
+Philip Hazel
+<br>
+University Computing Service
+<br>
+Cambridge, England.
+<br>
+</P>
+<P>
+Putting an actual email address here is a spam magnet. If you want to email me,
+use my two initials, followed by the two digits 10, at the domain cam.ac.uk.
+</P>
+<br><a name="SEC5" href="#TOC1">REVISION</a><br>
+<P>
+Last updated: 28 April 2021
+<br>
+Copyright &copy; 1997-2021 University of Cambridge.
+<br>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_callout_enumerate.html

@@ -0,0 +1,63 @@
+<html>
+<head>
+<title>pcre2_callout_enumerate specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_callout_enumerate man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>int pcre2_callout_enumerate(const pcre2_code *<i>code</i>,</b>
+<b>  int (*<i>callback</i>)(pcre2_callout_enumerate_block *, void *),</b>
+<b>  void *<i>callout_data</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function scans a compiled regular expression and calls the <i>callback()</i>
+function for each callout within the pattern. The yield of the function is zero
+for success and non-zero otherwise. The arguments are:
+<pre>
+  <i>code</i>           Points to the compiled pattern
+  <i>callback</i>       The callback function
+  <i>callout_data</i>   User data that is passed to the callback
+</pre>
+The <i>callback()</i> function is passed a pointer to a data block containing
+the following fields (not necessarily in this order):
+<pre>
+  uint32_t   <i>version</i>                Block version number
+  uint32_t   <i>callout_number</i>         Number for numbered callouts
+  PCRE2_SIZE <i>pattern_position</i>       Offset to next item in pattern
+  PCRE2_SIZE <i>next_item_length</i>       Length of next item in pattern
+  PCRE2_SIZE <i>callout_string_offset</i>  Offset to string within pattern
+  PCRE2_SIZE <i>callout_string_length</i>  Length of callout string
+  PCRE2_SPTR <i>callout_string</i>         Points to callout string or is NULL
+</pre>
+The second argument passed to the <b>callback()</b> function is the callout data
+that was passed to <b>pcre2_callout_enumerate()</b>. The <b>callback()</b>
+function must return zero for success. Any other value causes the pattern scan
+to stop, with the value being passed back as the result of
+<b>pcre2_callout_enumerate()</b>.
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the POSIX API in the
+<a href="pcre2posix.html"><b>pcre2posix</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_code_copy.html

@@ -0,0 +1,43 @@
+<html>
+<head>
+<title>pcre2_code_copy specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_code_copy man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>pcre2_code *pcre2_code_copy(const pcre2_code *<i>code</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function makes a copy of the memory used for a compiled pattern, excluding
+any memory used by the JIT compiler. Without a subsequent call to
+<b>pcre2_jit_compile()</b>, the copy can be used only for non-JIT matching. The
+pointer to the character tables is copied, not the tables themselves (see
+<b>pcre2_code_copy_with_tables()</b>). The yield of the function is NULL if
+<i>code</i> is NULL or if sufficient memory cannot be obtained.
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the POSIX API in the
+<a href="pcre2posix.html"><b>pcre2posix</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_code_copy_with_tables.html

@@ -0,0 +1,44 @@
+<html>
+<head>
+<title>pcre2_code_copy_with_tables specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_code_copy_with_tables man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>pcre2_code *pcre2_code_copy_with_tables(const pcre2_code *<i>code</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function makes a copy of the memory used for a compiled pattern, excluding
+any memory used by the JIT compiler. Without a subsequent call to
+<b>pcre2_jit_compile()</b>, the copy can be used only for non-JIT matching.
+Unlike <b>pcre2_code_copy()</b>, a separate copy of the character tables is also
+made, with the new code pointing to it. This memory will be automatically freed
+when <b>pcre2_code_free()</b> is called. The yield of the function is NULL if
+<i>code</i> is NULL or if sufficient memory cannot be obtained.
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the POSIX API in the
+<a href="pcre2posix.html"><b>pcre2posix</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_code_free.html

@@ -0,0 +1,42 @@
+<html>
+<head>
+<title>pcre2_code_free specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_code_free man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>void pcre2_code_free(pcre2_code *<i>code</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+If <i>code</i> is NULL, this function does nothing. Otherwise, <i>code</i> must
+point to a compiled pattern. This function frees its memory, including any
+memory used by the JIT compiler. If the compiled pattern was created by a call
+to <b>pcre2_code_copy_with_tables()</b>, the memory for the character tables is
+also freed.
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the POSIX API in the
+<a href="pcre2posix.html"><b>pcre2posix</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_compile.html

@@ -0,0 +1,107 @@
+<html>
+<head>
+<title>pcre2_compile specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_compile man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>pcre2_code *pcre2_compile(PCRE2_SPTR <i>pattern</i>, PCRE2_SIZE <i>length</i>,</b>
+<b>  uint32_t <i>options</i>, int *<i>errorcode</i>, PCRE2_SIZE *<i>erroroffset,</i></b>
+<b>  pcre2_compile_context *<i>ccontext</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function compiles a regular expression pattern into an internal form. Its
+arguments are:
+<pre>
+  <i>pattern</i>       A string containing expression to be compiled
+  <i>length</i>        The length of the string or PCRE2_ZERO_TERMINATED
+  <i>options</i>       Option bits
+  <i>errorcode</i>     Where to put an error code
+  <i>erroffset</i>     Where to put an error offset
+  <i>ccontext</i>      Pointer to a compile context or NULL
+</pre>
+The length of the pattern and any error offset that is returned are in code
+units, not characters. A compile context is needed only if you want to provide
+custom memory allocation functions, or to provide an external function for
+system stack size checking, or to change one or more of these parameters:
+<pre>
+  What \R matches (Unicode newlines, or CR, LF, CRLF only);
+  PCRE2's character tables;
+  The newline character sequence;
+  The compile time nested parentheses limit;
+  The maximum pattern length (in code units) that is allowed.
+  The additional options bits (see pcre2_set_compile_extra_options())
+</pre>
+The option bits are:
+<pre>
+  PCRE2_ANCHORED           Force pattern anchoring
+  PCRE2_ALLOW_EMPTY_CLASS  Allow empty classes
+  PCRE2_ALT_BSUX           Alternative handling of \u, \U, and \x
+  PCRE2_ALT_CIRCUMFLEX     Alternative handling of ^ in multiline mode
+  PCRE2_ALT_VERBNAMES      Process backslashes in verb names
+  PCRE2_AUTO_CALLOUT       Compile automatic callouts
+  PCRE2_CASELESS           Do caseless matching
+  PCRE2_DOLLAR_ENDONLY     $ not to match newline at end
+  PCRE2_DOTALL             . matches anything including NL
+  PCRE2_DUPNAMES           Allow duplicate names for subpatterns
+  PCRE2_ENDANCHORED        Pattern can match only at end of subject
+  PCRE2_EXTENDED           Ignore white space and # comments
+  PCRE2_FIRSTLINE          Force matching to be before newline
+  PCRE2_LITERAL            Pattern characters are all literal
+  PCRE2_MATCH_INVALID_UTF  Enable support for matching invalid UTF
+  PCRE2_MATCH_UNSET_BACKREF  Match unset backreferences
+  PCRE2_MULTILINE          ^ and $ match newlines within data
+  PCRE2_NEVER_BACKSLASH_C  Lock out the use of \C in patterns
+  PCRE2_NEVER_UCP          Lock out PCRE2_UCP, e.g. via (*UCP)
+  PCRE2_NEVER_UTF          Lock out PCRE2_UTF, e.g. via (*UTF)
+  PCRE2_NO_AUTO_CAPTURE    Disable numbered capturing paren-
+                            theses (named ones available)
+  PCRE2_NO_AUTO_POSSESS    Disable auto-possessification
+  PCRE2_NO_DOTSTAR_ANCHOR  Disable automatic anchoring for .*
+  PCRE2_NO_START_OPTIMIZE  Disable match-time start optimizations
+  PCRE2_NO_UTF_CHECK       Do not check the pattern for UTF validity
+                             (only relevant if PCRE2_UTF is set)
+  PCRE2_UCP                Use Unicode properties for \d, \w, etc.
+  PCRE2_UNGREEDY           Invert greediness of quantifiers
+  PCRE2_USE_OFFSET_LIMIT   Enable offset limit for unanchored matching
+  PCRE2_UTF                Treat pattern and subjects as UTF strings
+</pre>
+PCRE2 must be built with Unicode support (the default) in order to use
+PCRE2_UTF, PCRE2_UCP and related options.
+</P>
+<P>
+Additional options may be set in the compile context via the
+<a href="pcre2_set_compile_extra_options.html"><b>pcre2_set_compile_extra_options</b></a>
+function.
+</P>
+<P>
+The yield of this function is a pointer to a private data structure that
+contains the compiled pattern, or NULL if an error was detected.
+</P>
+<P>
+There is a complete description of the PCRE2 native API, with more detail on
+each option, in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page, and a description of the POSIX API in the
+<a href="pcre2posix.html"><b>pcre2posix</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_compile_context_copy.html

@@ -0,0 +1,41 @@
+<html>
+<head>
+<title>pcre2_compile_context_copy specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_compile_context_copy man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>pcre2_compile_context *pcre2_compile_context_copy(</b>
+<b>  pcre2_compile_context *<i>ccontext</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function makes a new copy of a compile context, using the memory
+allocation function that was used for the original context. The result is NULL
+if the memory cannot be obtained.
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the POSIX API in the
+<a href="pcre2posix.html"><b>pcre2posix</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_compile_context_create.html

@@ -0,0 +1,42 @@
+<html>
+<head>
+<title>pcre2_compile_context_create specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_compile_context_create man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>pcre2_compile_context *pcre2_compile_context_create(</b>
+<b>  pcre2_general_context *<i>gcontext</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function creates and initializes a new compile context. If its argument is
+NULL, <b>malloc()</b> is used to get the necessary memory; otherwise the memory
+allocation function within the general context is used. The result is NULL if
+the memory could not be obtained.
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the POSIX API in the
+<a href="pcre2posix.html"><b>pcre2posix</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_compile_context_free.html

@@ -0,0 +1,41 @@
+<html>
+<head>
+<title>pcre2_compile_context_free specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_compile_context_free man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>void pcre2_compile_context_free(pcre2_compile_context *<i>ccontext</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function frees the memory occupied by a compile context, using the memory
+freeing function from the general context with which it was created, or
+<b>free()</b> if that was not set. If the argument is NULL, the function returns
+immediately without doing anything.
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the POSIX API in the
+<a href="pcre2posix.html"><b>pcre2posix</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_config.html

@@ -0,0 +1,84 @@
+<html>
+<head>
+<title>pcre2_config specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_config man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>int pcre2_config(uint32_t <i>what</i>, void *<i>where</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function makes it possible for a client program to find out which optional
+features are available in the version of the PCRE2 library it is using. The
+arguments are as follows:
+<pre>
+  <i>what</i>     A code specifying what information is required
+  <i>where</i>    Points to where to put the information
+</pre>
+If <i>where</i> is NULL, the function returns the amount of memory needed for
+the requested information. When the information is a string, the value is in
+code units; for other types of data it is in bytes.
+</P>
+<P>
+If <b>where</b> is not NULL, for PCRE2_CONFIG_JITTARGET,
+PCRE2_CONFIG_UNICODE_VERSION, and PCRE2_CONFIG_VERSION it must point to a
+buffer that is large enough to hold the string. For all other codes it must
+point to a uint32_t integer variable. The available codes are:
+<pre>
+  PCRE2_CONFIG_BSR             Indicates what \R matches by default:
+                                 PCRE2_BSR_UNICODE
+                                 PCRE2_BSR_ANYCRLF
+  PCRE2_CONFIG_COMPILED_WIDTHS Which of 8/16/32 support was compiled
+  PCRE2_CONFIG_DEPTHLIMIT      Default backtracking depth limit
+  PCRE2_CONFIG_HEAPLIMIT       Default heap memory limit
+  PCRE2_CONFIG_JIT             Availability of just-in-time compiler support (1=yes 0=no)
+  PCRE2_CONFIG_JITTARGET       Information (a string) about the target architecture for the JIT compiler
+  PCRE2_CONFIG_LINKSIZE        Configured internal link size (2, 3, 4)
+  PCRE2_CONFIG_MATCHLIMIT      Default internal resource limit
+  PCRE2_CONFIG_NEVER_BACKSLASH_C  Whether or not \C is disabled
+  PCRE2_CONFIG_NEWLINE         Code for the default newline sequence:
+                                 PCRE2_NEWLINE_CR
+                                 PCRE2_NEWLINE_LF
+                                 PCRE2_NEWLINE_CRLF
+                                 PCRE2_NEWLINE_ANY
+                                 PCRE2_NEWLINE_ANYCRLF
+                                 PCRE2_NEWLINE_NUL
+  PCRE2_CONFIG_PARENSLIMIT     Default parentheses nesting limit
+  PCRE2_CONFIG_RECURSIONLIMIT  Obsolete: use PCRE2_CONFIG_DEPTHLIMIT
+  PCRE2_CONFIG_STACKRECURSE    Obsolete: always returns 0
+  PCRE2_CONFIG_UNICODE         Availability of Unicode support (1=yes 0=no)
+  PCRE2_CONFIG_UNICODE_VERSION The Unicode version (a string)
+  PCRE2_CONFIG_VERSION         The PCRE2 version (a string)
+</pre>
+The function yields a non-negative value on success or the negative value
+PCRE2_ERROR_BADOPTION otherwise. This is also the result for the
+PCRE2_CONFIG_JITTARGET code if JIT support is not available. When a string is
+requested, the function returns the number of code units used, including the
+terminating zero.
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the POSIX API in the
+<a href="pcre2posix.html"><b>pcre2posix</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_convert_context_copy.html

@@ -0,0 +1,40 @@
+<html>
+<head>
+<title>pcre2_convert_context_copy specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_convert_context_copy man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>pcre2_convert_context *pcre2_convert_context_copy(</b>
+<b>  pcre2_convert_context *<i>cvcontext</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function is part of an experimental set of pattern conversion functions.
+It makes a new copy of a convert context, using the memory allocation function
+that was used for the original context. The result is NULL if the memory cannot
+be obtained.
+</P>
+<P>
+The pattern conversion functions are described in the
+<a href="pcre2convert.html"><b>pcre2convert</b></a>
+documentation.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_convert_context_create.html

@@ -0,0 +1,41 @@
+<html>
+<head>
+<title>pcre2_convert_context_create specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_convert_context_create man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>pcre2_convert_context *pcre2_convert_context_create(</b>
+<b>  pcre2_general_context *<i>gcontext</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function is part of an experimental set of pattern conversion functions.
+It creates and initializes a new convert context. If its argument is
+NULL, <b>malloc()</b> is used to get the necessary memory; otherwise the memory
+allocation function within the general context is used. The result is NULL if
+the memory could not be obtained.
+</P>
+<P>
+The pattern conversion functions are described in the
+<a href="pcre2convert.html"><b>pcre2convert</b></a>
+documentation.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_convert_context_free.html

@@ -0,0 +1,40 @@
+<html>
+<head>
+<title>pcre2_convert_context_free specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_convert_context_free man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>void pcre2_convert_context_free(pcre2_convert_context *<i>cvcontext</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function is part of an experimental set of pattern conversion functions.
+It frees the memory occupied by a convert context, using the memory
+freeing function from the general context with which it was created, or
+<b>free()</b> if that was not set. If the argument is NULL, the function returns
+immediately without doing anything.
+</P>
+<P>
+The pattern conversion functions are described in the
+<a href="pcre2convert.html"><b>pcre2convert</b></a>
+documentation.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_converted_pattern_free.html

@@ -0,0 +1,40 @@
+<html>
+<head>
+<title>pcre2_converted_pattern_free specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_converted_pattern_free man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>void pcre2_converted_pattern_free(PCRE2_UCHAR *<i>converted_pattern</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function is part of an experimental set of pattern conversion functions.
+It frees the memory occupied by a converted pattern that was obtained by
+calling <b>pcre2_pattern_convert()</b> with arguments that caused it to place
+the converted pattern into newly obtained heap memory. If the argument is NULL,
+the function returns immediately without doing anything.
+</P>
+<P>
+The pattern conversion functions are described in the
+<a href="pcre2convert.html"><b>pcre2convert</b></a>
+documentation.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_dfa_match.html

@@ -0,0 +1,80 @@
+<html>
+<head>
+<title>pcre2_dfa_match specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_dfa_match man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>int pcre2_dfa_match(const pcre2_code *<i>code</i>, PCRE2_SPTR <i>subject</i>,</b>
+<b>  PCRE2_SIZE <i>length</i>, PCRE2_SIZE <i>startoffset</i>,</b>
+<b>  uint32_t <i>options</i>, pcre2_match_data *<i>match_data</i>,</b>
+<b>  pcre2_match_context *<i>mcontext</i>,</b>
+<b>  int *<i>workspace</i>, PCRE2_SIZE <i>wscount</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function matches a compiled regular expression against a given subject
+string, using an alternative matching algorithm that scans the subject string
+just once (except when processing lookaround assertions). This function is
+<i>not</i> Perl-compatible (the Perl-compatible matching function is
+<b>pcre2_match()</b>). The arguments for this function are:
+<pre>
+  <i>code</i>         Points to the compiled pattern
+  <i>subject</i>      Points to the subject string
+  <i>length</i>       Length of the subject string
+  <i>startoffset</i>  Offset in the subject at which to start matching
+  <i>options</i>      Option bits
+  <i>match_data</i>   Points to a match data block, for results
+  <i>mcontext</i>     Points to a match context, or is NULL
+  <i>workspace</i>    Points to a vector of ints used as working space
+  <i>wscount</i>      Number of elements in the vector
+</pre>
+For <b>pcre2_dfa_match()</b>, a match context is needed only if you want to set
+up a callout function or specify the heap limit or the match or the recursion
+depth limits. The <i>length</i> and <i>startoffset</i> values are code units, not
+characters. The options are:
+<pre>
+  PCRE2_ANCHORED          Match only at the first position
+  PCRE2_COPY_MATCHED_SUBJECT
+                          On success, make a private subject copy
+  PCRE2_ENDANCHORED       Pattern can match only at end of subject
+  PCRE2_NOTBOL            Subject is not the beginning of a line
+  PCRE2_NOTEOL            Subject is not the end of a line
+  PCRE2_NOTEMPTY          An empty string is not a valid match
+  PCRE2_NOTEMPTY_ATSTART  An empty string at the start of the subject is not a valid match
+  PCRE2_NO_UTF_CHECK      Do not check the subject for UTF validity (only relevant if PCRE2_UTF
+                           was set at compile time)
+  PCRE2_PARTIAL_HARD      Return PCRE2_ERROR_PARTIAL for a partial match even if there is a full match
+  PCRE2_PARTIAL_SOFT      Return PCRE2_ERROR_PARTIAL for a partial match if no full matches are found
+  PCRE2_DFA_RESTART       Restart after a partial match
+  PCRE2_DFA_SHORTEST      Return only the shortest match
+</pre>
+There are restrictions on what may appear in a pattern when using this matching
+function. Details are given in the
+<a href="pcre2matching.html"><b>pcre2matching</b></a>
+documentation. For details of partial matching, see the
+<a href="pcre2partial.html"><b>pcre2partial</b></a>
+page. There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the POSIX API in the
+<a href="pcre2posix.html"><b>pcre2posix</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_general_context_copy.html

@@ -0,0 +1,42 @@
+<html>
+<head>
+<title>pcre2_general_context_copy specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_general_context_copy man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>pcre2_general_context *pcre2_general_context_copy(</b>
+<b>  pcre2_general_context *<i>gcontext</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function makes a new copy of a general context, using the memory
+allocation functions in the context, if set, to get the necessary memory.
+Otherwise <b>malloc()</b> is used. The result is NULL if the memory cannot be
+obtained.
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the POSIX API in the
+<a href="pcre2posix.html"><b>pcre2posix</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_general_context_create.html

@@ -0,0 +1,44 @@
+<html>
+<head>
+<title>pcre2_general_context_create specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_general_context_create man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>pcre2_general_context *pcre2_general_context_create(</b>
+<b>  void *(*<i>private_malloc</i>)(PCRE2_SIZE, void *),</b>
+<b>  void (*<i>private_free</i>)(void *, void *), void *<i>memory_data</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function creates and initializes a general context. The arguments define
+custom memory management functions and a data value that is passed to them when
+they are called. The <b>private_malloc()</b> function is used to get memory for
+the context. If either of the first two arguments is NULL, the system memory
+management function is used. The result is NULL if no memory could be obtained.
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the POSIX API in the
+<a href="pcre2posix.html"><b>pcre2posix</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_general_context_free.html

@@ -0,0 +1,40 @@
+<html>
+<head>
+<title>pcre2_general_context_free specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_general_context_free man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>void pcre2_general_context_free(pcre2_general_context *<i>gcontext</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function frees the memory occupied by a general context, using the memory
+freeing function within the context, if set.  If the argument is NULL, the
+function returns immediately without doing anything.
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the POSIX API in the
+<a href="pcre2posix.html"><b>pcre2posix</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_get_error_message.html

@@ -0,0 +1,51 @@
+<html>
+<head>
+<title>pcre2_get_error_message specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_get_error_message man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>int pcre2_get_error_message(int <i>errorcode</i>, PCRE2_UCHAR *<i>buffer</i>,</b>
+<b>  PCRE2_SIZE <i>bufflen</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function provides a textual error message for each PCRE2 error code.
+Compilation errors are positive numbers; UTF formatting errors and matching
+errors are negative numbers. The arguments are:
+<pre>
+  <i>errorcode</i>   an error code (positive or negative)
+  <i>buffer</i>      where to put the message
+  <i>bufflen</i>     the length of the buffer (code units)
+</pre>
+The function returns the length of the message in code units, excluding the
+trailing zero, or the negative error code PCRE2_ERROR_NOMEMORY if the buffer is
+too small. In this case, the returned message is truncated (but still with a
+trailing zero). If <i>errorcode</i> does not contain a recognized error code
+number, the negative value PCRE2_ERROR_BADDATA is returned.
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the POSIX API in the
+<a href="pcre2posix.html"><b>pcre2posix</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_get_mark.html

@@ -0,0 +1,47 @@
+<html>
+<head>
+<title>pcre2_get_mark specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_get_mark man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>PCRE2_SPTR pcre2_get_mark(pcre2_match_data *<i>match_data</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+After a call of <b>pcre2_match()</b> that was passed the match block that is
+this function's argument, this function returns a pointer to the last (*MARK),
+(*PRUNE), or (*THEN) name that was encountered during the matching process. The
+name is zero-terminated, and is within the compiled pattern. The length of the
+name is in the preceding code unit. If no name is available, NULL is returned.
+</P>
+<P>
+After a successful match, the name that is returned is the last one on the
+matching path. After a failed match or a partial match, the last encountered
+name is returned.
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the POSIX API in the
+<a href="pcre2posix.html"><b>pcre2posix</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_get_match_data_size.html

@@ -0,0 +1,39 @@
+<html>
+<head>
+<title>pcre2_get_match_data_size specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_get_match_data_size man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>PCRE2_SIZE pcre2_get_match_data_size(pcre2_match_data *<i>match_data</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function returns the size, in bytes, of the match data block that is its
+argument.
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the POSIX API in the
+<a href="pcre2posix.html"><b>pcre2posix</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_get_ovector_count.html

@@ -0,0 +1,39 @@
+<html>
+<head>
+<title>pcre2_get_ovector_count specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_get_ovector_count man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>uint32_t pcre2_get_ovector_count(pcre2_match_data *<i>match_data</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function returns the number of pairs of offsets in the ovector that forms
+part of the given match data block.
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the POSIX API in the
+<a href="pcre2posix.html"><b>pcre2posix</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_get_ovector_pointer.html

@@ -0,0 +1,40 @@
+<html>
+<head>
+<title>pcre2_get_ovector_pointer specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_get_ovector_pointer man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>PCRE2_SIZE *pcre2_get_ovector_pointer(pcre2_match_data *<i>match_data</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function returns a pointer to the vector of offsets that forms part of the
+given match data block. The number of pairs can be found by calling
+<b>pcre2_get_ovector_count()</b>.
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the POSIX API in the
+<a href="pcre2posix.html"><b>pcre2posix</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_get_startchar.html

@@ -0,0 +1,44 @@
+<html>
+<head>
+<title>pcre2_get_startchar specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_get_startchar man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>PCRE2_SIZE pcre2_get_startchar(pcre2_match_data *<i>match_data</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+After a successful call of <b>pcre2_match()</b> that was passed the match block
+that is this function's argument, this function returns the code unit offset of
+the character at which the successful match started. For a non-partial match,
+this can be different to the value of <i>ovector[0]</i> if the pattern contains
+the \K escape sequence. After a partial match, however, this value is always
+the same as <i>ovector[0]</i> because \K does not affect the result of a
+partial match.
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the POSIX API in the
+<a href="pcre2posix.html"><b>pcre2posix</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_jit_compile.html

@@ -0,0 +1,63 @@
+<html>
+<head>
+<title>pcre2_jit_compile specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_jit_compile man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>int pcre2_jit_compile(pcre2_code *<i>code</i>, uint32_t <i>options</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function requests JIT compilation, which, if the just-in-time compiler is
+available, further processes a compiled pattern into machine code that executes
+much faster than the <b>pcre2_match()</b> interpretive matching function. Full
+details are given in the
+<a href="pcre2jit.html"><b>pcre2jit</b></a>
+documentation.
+</P>
+<P>
+The first argument is a pointer that was returned by a successful call to
+<b>pcre2_compile()</b>, and the second must contain one or more of the following
+bits:
+<pre>
+  PCRE2_JIT_COMPLETE      compile code for full matching
+  PCRE2_JIT_PARTIAL_SOFT  compile code for soft partial matching
+  PCRE2_JIT_PARTIAL_HARD  compile code for hard partial matching
+</pre>
+There is also an obsolete option called PCRE2_JIT_INVALID_UTF, which has been
+superseded by the <b>pcre2_compile()</b> option PCRE2_MATCH_INVALID_UTF. The old
+option is deprecated and may be removed in the future.
+</P>
+<P>
+The yield of the function is 0 for success, or a negative error code otherwise.
+In particular, PCRE2_ERROR_JIT_BADOPTION is returned if JIT is not supported or
+if an unknown bit is set in <i>options</i>. The function can also return
+PCRE2_ERROR_NOMEMORY if JIT is unable to allocate executable memory for the
+compiler, even if it was because of a system security restriction.
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the POSIX API in the
+<a href="pcre2posix.html"><b>pcre2posix</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_jit_free_unused_memory.html

@@ -0,0 +1,43 @@
+<html>
+<head>
+<title>pcre2_jit_free_unused_memory specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_jit_free_unused_memory man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>void pcre2_jit_free_unused_memory(pcre2_general_context *<i>gcontext</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function frees unused JIT executable memory. The argument is a general
+context, for custom memory management, or NULL for standard memory management.
+JIT memory allocation retains some memory in order to improve future JIT
+compilation speed. In low memory conditions,
+<b>pcre2_jit_free_unused_memory()</b> can be used to cause this memory to be
+freed.
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the POSIX API in the
+<a href="pcre2posix.html"><b>pcre2posix</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_jit_match.html

@@ -0,0 +1,60 @@
+<html>
+<head>
+<title>pcre2_jit_match specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_jit_match man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>int pcre2_jit_match(const pcre2_code *<i>code</i>, PCRE2_SPTR <i>subject</i>,</b>
+<b>  PCRE2_SIZE <i>length</i>, PCRE2_SIZE <i>startoffset</i>,</b>
+<b>  uint32_t <i>options</i>, pcre2_match_data *<i>match_data</i>,</b>
+<b>  pcre2_match_context *<i>mcontext</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function matches a compiled regular expression that has been successfully
+processed by the JIT compiler against a given subject string, using a matching
+algorithm that is similar to Perl's. It is a "fast path" interface to JIT, and
+it bypasses some of the sanity checks that <b>pcre2_match()</b> applies.
+Its arguments are exactly the same as for
+<a href="pcre2_match.html"><b>pcre2_match()</b>,</a>
+except that the subject string must be specified with a length;
+PCRE2_ZERO_TERMINATED is not supported.
+</P>
+<P>
+The supported options are PCRE2_NOTBOL, PCRE2_NOTEOL, PCRE2_NOTEMPTY,
+PCRE2_NOTEMPTY_ATSTART, PCRE2_PARTIAL_HARD, and PCRE2_PARTIAL_SOFT. Unsupported
+options are ignored. The subject string is not checked for UTF validity.
+</P>
+<P>
+The return values are the same as for <b>pcre2_match()</b> plus
+PCRE2_ERROR_JIT_BADOPTION if a matching mode (partial or complete) is requested
+that was not compiled. For details of partial matching, see the
+<a href="pcre2partial.html"><b>pcre2partial</b></a>
+page.
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the JIT API in the
+<a href="pcre2jit.html"><b>pcre2jit</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_jit_stack_assign.html

@@ -0,0 +1,75 @@
+<html>
+<head>
+<title>pcre2_jit_stack_assign specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_jit_stack_assign man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>void pcre2_jit_stack_assign(pcre2_match_context *<i>mcontext</i>,</b>
+<b>  pcre2_jit_callback <i>callback_function</i>, void *<i>callback_data</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function provides control over the memory used by JIT as a run-time stack
+when <b>pcre2_match()</b> or <b>pcre2_jit_match()</b> is called with a pattern
+that has been successfully processed by the JIT compiler. The information that
+determines which stack is used is put into a match context that is subsequently
+passed to a matching function. The arguments of this function are:
+<pre>
+  mcontext       a pointer to a match context
+  callback       a callback function
+  callback_data  a JIT stack or a value to be passed to the callback
+</PRE>
+</P>
+<P>
+If <i>mcontext</i> is NULL, the function returns immediately, without doing
+anything.
+</P>
+<P>
+If <i>callback</i> is NULL and <i>callback_data</i> is NULL, an internal 32KiB
+block on the machine stack is used.
+</P>
+<P>
+If <i>callback</i> is NULL and <i>callback_data</i> is not NULL,
+<i>callback_data</i> must be a valid JIT stack, the result of calling
+<b>pcre2_jit_stack_create()</b>.
+</P>
+<P>
+If <i>callback</i> not NULL, it is called with <i>callback_data</i> as an
+argument at the start of matching, in order to set up a JIT stack. If the
+result is NULL, the internal 32KiB stack is used; otherwise the return value
+must be a valid JIT stack, the result of calling
+<b>pcre2_jit_stack_create()</b>.
+</P>
+<P>
+You may safely use the same JIT stack for multiple patterns, as long as they
+are all matched in the same thread. In a multithread application, each thread
+must use its own JIT stack. For more details, see the
+<a href="pcre2jit.html"><b>pcre2jit</b></a>
+page.
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the POSIX API in the
+<a href="pcre2posix.html"><b>pcre2posix</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_jit_stack_create.html

@@ -0,0 +1,49 @@
+<html>
+<head>
+<title>pcre2_jit_stack_create specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_jit_stack_create man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>pcre2_jit_stack *pcre2_jit_stack_create(PCRE2_SIZE <i>startsize</i>,</b>
+<b>  PCRE2_SIZE <i>maxsize</i>, pcre2_general_context *<i>gcontext</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function is used to create a stack for use by the code compiled by the JIT
+compiler. The first two arguments are a starting size for the stack, and a
+maximum size to which it is allowed to grow. The final argument is a general
+context, for memory allocation functions, or NULL for standard memory
+allocation. The result can be passed to the JIT run-time code by calling
+<b>pcre2_jit_stack_assign()</b> to associate the stack with a compiled pattern,
+which can then be processed by <b>pcre2_match()</b> or <b>pcre2_jit_match()</b>.
+A maximum stack size of 512KiB to 1MiB should be more than enough for any
+pattern. For more details, see the
+<a href="pcre2jit.html"><b>pcre2jit</b></a>
+page.
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the POSIX API in the
+<a href="pcre2posix.html"><b>pcre2posix</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_jit_stack_free.html

@@ -0,0 +1,43 @@
+<html>
+<head>
+<title>pcre2_jit_stack_free specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_jit_stack_free man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>void pcre2_jit_stack_free(pcre2_jit_stack *<i>jit_stack</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function is used to free a JIT stack that was created by
+<b>pcre2_jit_stack_create()</b> when it is no longer needed. If the argument is
+NULL, the function returns immediately without doing anything. For more
+details, see the
+<a href="pcre2jit.html"><b>pcre2jit</b></a>
+page.
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the POSIX API in the
+<a href="pcre2posix.html"><b>pcre2posix</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_maketables.html

@@ -0,0 +1,48 @@
+<html>
+<head>
+<title>pcre2_maketables specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_maketables man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>const uint8_t *pcre2_maketables(pcre2_general_context *<i>gcontext</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function builds a set of character tables for character code points that
+are less than 256. These can be passed to <b>pcre2_compile()</b> in a compile
+context in order to override the internal, built-in tables (which were either
+defaulted or made by <b>pcre2_maketables()</b> when PCRE2 was compiled). See the
+<a href="pcre2_set_character_tables.html"><b>pcre2_set_character_tables()</b></a>
+page. You might want to do this if you are using a non-standard locale.
+</P>
+<P>
+If the argument is NULL, <b>malloc()</b> is used to get memory for the tables.
+Otherwise it must point to a general context, which can supply pointers to a
+custom memory manager. The function yields a pointer to the tables.
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the POSIX API in the
+<a href="pcre2posix.html"><b>pcre2posix</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_maketables_free.html

@@ -0,0 +1,44 @@
+<html>
+<head>
+<title>pcre2_maketables_free specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_maketables_free man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>void pcre2_maketables_free(pcre2_general_context *<i>gcontext</i>,</b>
+<b>  const uint8_t *<i>tables</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function discards a set of character tables that were created by a call
+to
+<a href="pcre2_maketables.html"><b>pcre2_maketables()</b>.</a>
+</P>
+<P>
+The <i>gcontext</i> parameter should match what was used in that call to
+account for any custom allocators that might be in use; if it is NULL
+the system <b>free()</b> is used.
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_match.html

@@ -0,0 +1,85 @@
+<html>
+<head>
+<title>pcre2_match specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_match man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>int pcre2_match(const pcre2_code *<i>code</i>, PCRE2_SPTR <i>subject</i>,</b>
+<b>  PCRE2_SIZE <i>length</i>, PCRE2_SIZE <i>startoffset</i>,</b>
+<b>  uint32_t <i>options</i>, pcre2_match_data *<i>match_data</i>,</b>
+<b>  pcre2_match_context *<i>mcontext</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function matches a compiled regular expression against a given subject
+string, using a matching algorithm that is similar to Perl's. It returns
+offsets to what it has matched and to captured substrings via the
+<b>match_data</b> block, which can be processed by functions with names that
+start with <b>pcre2_get_ovector_...()</b> or <b>pcre2_substring_...()</b>. The
+return from <b>pcre2_match()</b> is one more than the highest numbered capturing
+pair that has been set (for example, 1 if there are no captures), zero if the
+vector of offsets is too small, or a negative error code for no match and other
+errors. The function arguments are:
+<pre>
+  <i>code</i>         Points to the compiled pattern
+  <i>subject</i>      Points to the subject string
+  <i>length</i>       Length of the subject string
+  <i>startoffset</i>  Offset in the subject at which to start matching
+  <i>options</i>      Option bits
+  <i>match_data</i>   Points to a match data block, for results
+  <i>mcontext</i>     Points to a match context, or is NULL
+</pre>
+A match context is needed only if you want to:
+<pre>
+  Set up a callout function
+  Set a matching offset limit
+  Change the heap memory limit
+  Change the backtracking match limit
+  Change the backtracking depth limit
+  Set custom memory management specifically for the match
+</pre>
+The <i>length</i> and <i>startoffset</i> values are code units, not characters.
+The length may be given as PCRE2_ZERO_TERMINATED for a subject that is
+terminated by a binary zero code unit. The options are:
+<pre>
+  PCRE2_ANCHORED          Match only at the first position
+  PCRE2_COPY_MATCHED_SUBJECT
+                          On success, make a private subject copy
+  PCRE2_ENDANCHORED       Pattern can match only at end of subject
+  PCRE2_NOTBOL            Subject string is not the beginning of a line
+  PCRE2_NOTEOL            Subject string is not the end of a line
+  PCRE2_NOTEMPTY          An empty string is not a valid match
+  PCRE2_NOTEMPTY_ATSTART  An empty string at the start of the subject is not a valid match
+  PCRE2_NO_JIT            Do not use JIT matching
+  PCRE2_NO_UTF_CHECK      Do not check the subject for UTF validity (only relevant if PCRE2_UTF
+                           was set at compile time)
+  PCRE2_PARTIAL_HARD      Return PCRE2_ERROR_PARTIAL for a partial match even if there is a full match
+  PCRE2_PARTIAL_SOFT      Return PCRE2_ERROR_PARTIAL for a partial match if no full matches are found
+</pre>
+For details of partial matching, see the
+<a href="pcre2partial.html"><b>pcre2partial</b></a>
+page. There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the POSIX API in the
+<a href="pcre2posix.html"><b>pcre2posix</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_match_context_copy.html

@@ -0,0 +1,41 @@
+<html>
+<head>
+<title>pcre2_match_context_copy specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_match_context_copy man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>pcre2_match_context *pcre2_match_context_copy(</b>
+<b>  pcre2_match_context *<i>mcontext</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function makes a new copy of a match context, using the memory
+allocation function that was used for the original context. The result is NULL
+if the memory cannot be obtained.
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the POSIX API in the
+<a href="pcre2posix.html"><b>pcre2posix</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_match_context_create.html

@@ -0,0 +1,42 @@
+<html>
+<head>
+<title>pcre2_match_context_create specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_match_context_create man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>pcre2_match_context *pcre2_match_context_create(</b>
+<b>  pcre2_general_context *<i>gcontext</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function creates and initializes a new match context. If its argument is
+NULL, <b>malloc()</b> is used to get the necessary memory; otherwise the memory
+allocation function within the general context is used. The result is NULL if
+the memory could not be obtained.
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the POSIX API in the
+<a href="pcre2posix.html"><b>pcre2posix</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_match_context_free.html

@@ -0,0 +1,41 @@
+<html>
+<head>
+<title>pcre2_match_context_free specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_match_context_free man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>void pcre2_match_context_free(pcre2_match_context *<i>mcontext</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function frees the memory occupied by a match context, using the memory
+freeing function from the general context with which it was created, or
+<b>free()</b> if that was not set. If the argument is NULL, the function returns
+immediately without doing anything.
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the POSIX API in the
+<a href="pcre2posix.html"><b>pcre2posix</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_match_data_create.html

@@ -0,0 +1,49 @@
+<html>
+<head>
+<title>pcre2_match_data_create specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_match_data_create man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>pcre2_match_data *pcre2_match_data_create(uint32_t <i>ovecsize</i>,</b>
+<b>  pcre2_general_context *<i>gcontext</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function creates a new match data block, which is used for holding the
+result of a match. The first argument specifies the number of pairs of offsets
+that are required. These form the "output vector" (ovector) within the match
+data block, and are used to identify the matched string and any captured
+substrings. There is always one pair of offsets; if <b>ovecsize</b> is zero, it
+is treated as one.
+</P>
+<P>
+The second argument points to a general context, for custom memory management,
+or is NULL for system memory management. The result of the function is NULL if
+the memory for the block could not be obtained.
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the POSIX API in the
+<a href="pcre2posix.html"><b>pcre2posix</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_match_data_create_from_pattern.html

@@ -0,0 +1,50 @@
+<html>
+<head>
+<title>pcre2_match_data_create_from_pattern specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_match_data_create_from_pattern man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>pcre2_match_data *pcre2_match_data_create_from_pattern(</b>
+<b>  const pcre2_code *<i>code</i>, pcre2_general_context *<i>gcontext</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function creates a new match data block, which is used for holding the
+result of a match. The first argument points to a compiled pattern. The number
+of capturing parentheses within the pattern is used to compute the number of
+pairs of offsets that are required in the match data block. These form the
+"output vector" (ovector) within the match data block, and are used to identify
+the matched string and any captured substrings.
+</P>
+<P>
+The second argument points to a general context, for custom memory management,
+or is NULL to use the same memory allocator as was used for the compiled
+pattern. The result of the function is NULL if the memory for the block could
+not be obtained.
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the POSIX API in the
+<a href="pcre2posix.html"><b>pcre2posix</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_match_data_free.html

@@ -0,0 +1,46 @@
+<html>
+<head>
+<title>pcre2_match_data_free specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_match_data_free man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>void pcre2_match_data_free(pcre2_match_data *<i>match_data</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+If <i>match_data</i> is NULL, this function does nothing. Otherwise,
+<i>match_data</i> must point to a match data block, which this function frees,
+using the memory freeing function from the general context or compiled pattern
+with which it was created, or <b>free()</b> if that was not set.
+</P>
+<P>
+If the PCRE2_COPY_MATCHED_SUBJECT was used for a successful match using this
+match data block, the copy of the subject that was remembered with the block is
+also freed.
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the POSIX API in the
+<a href="pcre2posix.html"><b>pcre2posix</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_pattern_convert.html

@@ -0,0 +1,70 @@
+<html>
+<head>
+<title>pcre2_pattern_convert specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_pattern_convert man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>int pcre2_pattern_convert(PCRE2_SPTR <i>pattern</i>, PCRE2_SIZE <i>length</i>,</b>
+<b>  uint32_t <i>options</i>, PCRE2_UCHAR **<i>buffer</i>,</b>
+<b>  PCRE2_SIZE *<i>blength</i>, pcre2_convert_context *<i>cvcontext</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function is part of an experimental set of pattern conversion functions.
+It converts a foreign pattern (for example, a glob) into a PCRE2 regular
+expression pattern. Its arguments are:
+<pre>
+  <i>pattern</i>     The foreign pattern
+  <i>length</i>      The length of the input pattern or PCRE2_ZERO_TERMINATED
+  <i>options</i>     Option bits
+  <i>buffer</i>      Pointer to pointer to output buffer, or NULL
+  <i>blength</i>     Pointer to output length field
+  <i>cvcontext</i>   Pointer to a convert context or NULL
+</pre>
+The length of the converted pattern (excluding the terminating zero) is
+returned via <i>blength</i>. If <i>buffer</i> is NULL, the function just returns
+the output length. If <i>buffer</i> points to a NULL pointer, heap memory is
+obtained for the converted pattern, using the allocator in the context if
+present (or else <b>malloc()</b>), and the field pointed to by <i>buffer</i> is
+updated. If <i>buffer</i> points to a non-NULL field, that must point to a
+buffer whose size is in the variable pointed to by <i>blength</i>. This value is
+updated.
+</P>
+<P>
+The option bits are:
+<pre>
+  PCRE2_CONVERT_UTF                     Input is UTF
+  PCRE2_CONVERT_NO_UTF_CHECK            Do not check UTF validity
+  PCRE2_CONVERT_POSIX_BASIC             Convert POSIX basic pattern
+  PCRE2_CONVERT_POSIX_EXTENDED          Convert POSIX extended pattern
+  PCRE2_CONVERT_GLOB                    ) Convert
+  PCRE2_CONVERT_GLOB_NO_WILD_SEPARATOR  )   various types
+  PCRE2_CONVERT_GLOB_NO_STARSTAR        )     of glob
+</pre>
+The return value from <b>pcre2_pattern_convert()</b> is zero on success or a
+non-zero PCRE2 error code.
+</P>
+<P>
+The pattern conversion functions are described in the
+<a href="pcre2convert.html"><b>pcre2convert</b></a>
+documentation.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_pattern_info.html

@@ -0,0 +1,109 @@
+<html>
+<head>
+<title>pcre2_pattern_info specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_pattern_info man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>int pcre2_pattern_info(const pcre2_code *<i>code</i>, uint32_t <i>what</i>,</b>
+<b>   void *<i>where</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function returns information about a compiled pattern. Its arguments are:
+<pre>
+  <i>code</i>     Pointer to a compiled regular expression pattern
+  <i>what</i>     What information is required
+  <i>where</i>    Where to put the information
+</pre>
+The recognized values for the <i>what</i> argument, and the information they
+request are as follows:
+<pre>
+  PCRE2_INFO_ALLOPTIONS      Final options after compiling
+  PCRE2_INFO_ARGOPTIONS      Options passed to <b>pcre2_compile()</b>
+  PCRE2_INFO_BACKREFMAX      Number of highest backreference
+  PCRE2_INFO_BSR             What \R matches:
+                               PCRE2_BSR_UNICODE: Unicode line endings
+                               PCRE2_BSR_ANYCRLF: CR, LF, or CRLF only
+  PCRE2_INFO_CAPTURECOUNT    Number of capturing subpatterns
+  PCRE2_INFO_DEPTHLIMIT      Backtracking depth limit if set, otherwise PCRE2_ERROR_UNSET
+  PCRE2_INFO_EXTRAOPTIONS    Extra options that were passed in the
+                               compile context
+  PCRE2_INFO_FIRSTBITMAP     Bitmap of first code units, or NULL
+  PCRE2_INFO_FIRSTCODETYPE   Type of start-of-match information
+                               0 nothing set
+                               1 first code unit is set
+                               2 start of string or after newline
+  PCRE2_INFO_FIRSTCODEUNIT   First code unit when type is 1
+  PCRE2_INFO_FRAMESIZE       Size of backtracking frame
+  PCRE2_INFO_HASBACKSLASHC   Return 1 if pattern contains \C
+  PCRE2_INFO_HASCRORLF       Return 1 if explicit CR or LF matches exist in the pattern
+  PCRE2_INFO_HEAPLIMIT       Heap memory limit if set, otherwise PCRE2_ERROR_UNSET
+  PCRE2_INFO_JCHANGED        Return 1 if (?J) or (?-J) was used
+  PCRE2_INFO_JITSIZE         Size of JIT compiled code, or 0
+  PCRE2_INFO_LASTCODETYPE    Type of must-be-present information
+                               0 nothing set
+                               1 code unit is set
+  PCRE2_INFO_LASTCODEUNIT    Last code unit when type is 1
+  PCRE2_INFO_MATCHEMPTY      1 if the pattern can match an empty string, 0 otherwise
+  PCRE2_INFO_MATCHLIMIT      Match limit if set, otherwise PCRE2_ERROR_UNSET
+  PCRE2_INFO_MAXLOOKBEHIND   Length (in characters) of the longest lookbehind assertion
+  PCRE2_INFO_MINLENGTH       Lower bound length of matching strings
+  PCRE2_INFO_NAMECOUNT       Number of named subpatterns
+  PCRE2_INFO_NAMEENTRYSIZE   Size of name table entries
+  PCRE2_INFO_NAMETABLE       Pointer to name table
+  PCRE2_CONFIG_NEWLINE       Code for the newline sequence:
+                               PCRE2_NEWLINE_CR
+                               PCRE2_NEWLINE_LF
+                               PCRE2_NEWLINE_CRLF
+                               PCRE2_NEWLINE_ANY
+                               PCRE2_NEWLINE_ANYCRLF
+                               PCRE2_NEWLINE_NUL
+  PCRE2_INFO_RECURSIONLIMIT  Obsolete synonym for PCRE2_INFO_DEPTHLIMIT
+  PCRE2_INFO_SIZE            Size of compiled pattern
+</pre>
+If <i>where</i> is NULL, the function returns the amount of memory needed for
+the requested information, in bytes. Otherwise, the <i>where</i> argument must
+point to an unsigned 32-bit integer (uint32_t variable), except for the
+following <i>what</i> values, when it must point to a variable of the type
+shown:
+<pre>
+  PCRE2_INFO_FIRSTBITMAP     const uint8_t *
+  PCRE2_INFO_JITSIZE         size_t
+  PCRE2_INFO_NAMETABLE       PCRE2_SPTR
+  PCRE2_INFO_SIZE            size_t
+</pre>
+The yield of the function is zero on success or:
+<pre>
+  PCRE2_ERROR_NULL           the argument <i>code</i> is NULL
+  PCRE2_ERROR_BADMAGIC       the "magic number" was not found
+  PCRE2_ERROR_BADOPTION      the value of <i>what</i> is invalid
+  PCRE2_ERROR_BADMODE        the pattern was compiled in the wrong mode
+  PCRE2_ERROR_UNSET          the requested information is not set
+</PRE>
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the POSIX API in the
+<a href="pcre2posix.html"><b>pcre2posix</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_serialize_decode.html

@@ -0,0 +1,65 @@
+<html>
+<head>
+<title>pcre2_serialize_decode specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_serialize_decode man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>int32_t pcre2_serialize_decode(pcre2_code **<i>codes</i>,</b>
+<b>  int32_t <i>number_of_codes</i>, const uint8_t *<i>bytes</i>,</b>
+<b>  pcre2_general_context *<i>gcontext</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function decodes a serialized set of compiled patterns back into a list of
+individual patterns. This is possible only on a host that is running the same
+version of PCRE2, with the same code unit width, and the host must also have
+the same endianness, pointer width and PCRE2_SIZE type. The arguments for
+<b>pcre2_serialize_decode()</b> are:
+<pre>
+  <i>codes</i>            pointer to a vector in which to build the list
+  <i>number_of_codes</i>  number of slots in the vector
+  <i>bytes</i>            the serialized byte stream
+  <i>gcontext</i>         pointer to a general context or NULL
+</pre>
+The <i>bytes</i> argument must point to a block of data that was originally
+created by <b>pcre2_serialize_encode()</b>, though it may have been saved on
+disc or elsewhere in the meantime. If there are more codes in the serialized
+data than slots in the list, only those compiled patterns that will fit are
+decoded. The yield of the function is the number of decoded patterns, or one of
+the following negative error codes:
+<pre>
+  PCRE2_ERROR_BADDATA   <i>number_of_codes</i> is zero or less
+  PCRE2_ERROR_BADMAGIC  mismatch of id bytes in <i>bytes</i>
+  PCRE2_ERROR_BADMODE   mismatch of variable unit size or PCRE version
+  PCRE2_ERROR_MEMORY    memory allocation failed
+  PCRE2_ERROR_NULL      <i>codes</i> or <i>bytes</i> is NULL
+</pre>
+PCRE2_ERROR_BADMAGIC may mean that the data is corrupt, or that it was compiled
+on a system with different endianness.
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the serialization functions in the
+<a href="pcre2serialize.html"><b>pcre2serialize</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_serialize_encode.html

@@ -0,0 +1,66 @@
+<html>
+<head>
+<title>pcre2_serialize_encode specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_serialize_encode man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>int32_t pcre2_serialize_encode(const pcre2_code **<i>codes</i>,</b>
+<b>  int32_t <i>number_of_codes</i>, uint8_t **<i>serialized_bytes</i>,</b>
+<b>  PCRE2_SIZE *<i>serialized_size</i>, pcre2_general_context *<i>gcontext</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function encodes a list of compiled patterns into a byte stream that can
+be saved on disc or elsewhere. Note that this is not an abstract format like
+Java or .NET. Conversion of the byte stream back into usable compiled patterns
+can only happen on a host that is running the same version of PCRE2, with the
+same code unit width, and the host must also have the same endianness, pointer
+width and PCRE2_SIZE type. The arguments for <b>pcre2_serialize_encode()</b>
+are:
+<pre>
+  <i>codes</i>             pointer to a vector containing the list
+  <i>number_of_codes</i>   number of slots in the vector
+  <i>serialized_bytes</i>  set to point to the serialized byte stream
+  <i>serialized_size</i>   set to the number of bytes in the byte stream
+  <i>gcontext</i>          pointer to a general context or NULL
+</pre>
+The context argument is used to obtain memory for the byte stream. When the
+serialized data is no longer needed, it must be freed by calling
+<b>pcre2_serialize_free()</b>. The yield of the function is the number of
+serialized patterns, or one of the following negative error codes:
+<pre>
+  PCRE2_ERROR_BADDATA      <i>number_of_codes</i> is zero or less
+  PCRE2_ERROR_BADMAGIC     mismatch of id bytes in one of the patterns
+  PCRE2_ERROR_MEMORY       memory allocation failed
+  PCRE2_ERROR_MIXEDTABLES  the patterns do not all use the same tables
+  PCRE2_ERROR_NULL         an argument other than <i>gcontext</i> is NULL
+</pre>
+PCRE2_ERROR_BADMAGIC means either that a pattern's code has been corrupted, or
+that a slot in the vector does not point to a compiled pattern.
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the serialization functions in the
+<a href="pcre2serialize.html"><b>pcre2serialize</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_serialize_free.html

@@ -0,0 +1,41 @@
+<html>
+<head>
+<title>pcre2_serialize_free specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_serialize_free man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>void pcre2_serialize_free(uint8_t *<i>bytes</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function frees the memory that was obtained by
+<b>pcre2_serialize_encode()</b> to hold a serialized byte stream. The argument
+must point to such a byte stream or be NULL, in which case the function returns
+without doing anything.
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the serialization functions in the
+<a href="pcre2serialize.html"><b>pcre2serialize</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_serialize_get_number_of_codes.html

@@ -0,0 +1,49 @@
+<html>
+<head>
+<title>pcre2_serialize_get_number_of_codes specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_serialize_get_number_of_codes man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>int32_t pcre2_serialize_get_number_of_codes(const uint8_t *<i>bytes</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+The <i>bytes</i> argument must point to a serialized byte stream that was
+originally created by <b>pcre2_serialize_encode()</b> (though it may have been
+saved on disc or elsewhere in the meantime). The function returns the number of
+serialized patterns in the byte stream, or one of the following negative error
+codes:
+<pre>
+  PCRE2_ERROR_BADMAGIC  mismatch of id bytes in <i>bytes</i>
+  PCRE2_ERROR_BADMODE   mismatch of variable unit size or PCRE version
+  PCRE2_ERROR_NULL      the argument is NULL
+</pre>
+PCRE2_ERROR_BADMAGIC may mean that the data is corrupt, or that it was compiled
+on a system with different endianness.
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the serialization functions in the
+<a href="pcre2serialize.html"><b>pcre2serialize</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_set_bsr.html

@@ -0,0 +1,42 @@
+<html>
+<head>
+<title>pcre2_set_bsr specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_set_bsr man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>int pcre2_set_bsr(pcre2_compile_context *<i>ccontext</i>,</b>
+<b>  uint32_t <i>value</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function sets the convention for processing \R within a compile context.
+The second argument must be one of PCRE2_BSR_ANYCRLF or PCRE2_BSR_UNICODE. The
+result is zero for success or PCRE2_ERROR_BADDATA if the second argument is
+invalid.
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the POSIX API in the
+<a href="pcre2posix.html"><b>pcre2posix</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_set_callout.html

@@ -0,0 +1,43 @@
+<html>
+<head>
+<title>pcre2_set_callout specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_set_callout man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>int pcre2_set_callout(pcre2_match_context *<i>mcontext</i>,</b>
+<b>  int (*<i>callout_function</i>)(pcre2_callout_block *),</b>
+<b>  void *<i>callout_data</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function sets the callout fields in a match context (the first argument).
+The second argument specifies a callout function, and the third argument is an
+opaque data item that is passed to it. The result of this function is always
+zero.
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the POSIX API in the
+<a href="pcre2posix.html"><b>pcre2posix</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_set_character_tables.html

@@ -0,0 +1,45 @@
+<html>
+<head>
+<title>pcre2_set_character_tables specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_set_character_tables man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>int pcre2_set_character_tables(pcre2_compile_context *<i>ccontext</i>,</b>
+<b>  const uint8_t *<i>tables</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function sets a pointer to custom character tables within a compile
+context. The second argument must point to a set of PCRE2 character tables or
+be NULL to request the default tables. The result is always zero. Character
+tables can be created by calling <b>pcre2_maketables()</b> or by running the
+<b>pcre2_dftables</b> maintenance command in binary mode (see the
+<a href="pcre2build.html"><b>pcre2build</b></a>
+documentation).
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the POSIX API in the
+<a href="pcre2posix.html"><b>pcre2posix</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_set_compile_extra_options.html

@@ -0,0 +1,47 @@
+<html>
+<head>
+<title>pcre2_set_compile_extra_options specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_set_compile_extra_options man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>int pcre2_set_compile_extra_options(pcre2_compile_context *<i>ccontext</i>,</b>
+<b>  uint32_t <i>extra_options</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function sets additional option bits for <b>pcre2_compile()</b> that are
+housed in a compile context. It completely replaces all the bits. The extra
+options are:
+<pre>
+  PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES  Allow \x{df800} to \x{dfff} in UTF-8 and UTF-32 modes
+  PCRE2_EXTRA_ALT_BSUX                 Extended alternate \u, \U, and \x handling
+  PCRE2_EXTRA_BAD_ESCAPE_IS_LITERAL    Treat all invalid escapes as a literal following character
+  PCRE2_EXTRA_ESCAPED_CR_IS_LF         Interpret \r as \n
+  PCRE2_EXTRA_MATCH_LINE               Pattern matches whole lines
+  PCRE2_EXTRA_MATCH_WORD               Pattern matches "words"
+</pre>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the POSIX API in the
+<a href="pcre2posix.html"><b>pcre2posix</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_set_compile_recursion_guard.html

@@ -0,0 +1,46 @@
+<html>
+<head>
+<title>pcre2_set_compile_recursion_guard specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_set_compile_recursion_guard man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>int pcre2_set_compile_recursion_guard(pcre2_compile_context *<i>ccontext</i>,</b>
+<b>  int (*<i>guard_function</i>)(uint32_t, void *), void *<i>user_data</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function defines, within a compile context, a function that is called
+whenever <b>pcre2_compile()</b> starts to compile a parenthesized part of a
+pattern. The first argument to the function gives the current depth of
+parenthesis nesting, and the second is user data that is supplied when the
+function is set up. The callout function should return zero if all is well, or
+non-zero to force an error. This feature is provided so that applications can
+check the available system stack space, in order to avoid running out. The
+result of <b>pcre2_set_compile_recursion_guard()</b> is always zero.
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the POSIX API in the
+<a href="pcre2posix.html"><b>pcre2posix</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_set_depth_limit.html

@@ -0,0 +1,40 @@
+<html>
+<head>
+<title>pcre2_set_depth_limit specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_set_depth_limit man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>int pcre2_set_depth_limit(pcre2_match_context *<i>mcontext</i>,</b>
+<b>  uint32_t <i>value</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function sets the backtracking depth limit field in a match context. The
+result is always zero.
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the POSIX API in the
+<a href="pcre2posix.html"><b>pcre2posix</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_set_glob_escape.html

@@ -0,0 +1,43 @@
+<html>
+<head>
+<title>pcre2_set_glob_escape specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_set_glob_escape man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>int pcre2_set_glob_escape(pcre2_convert_context *<i>cvcontext</i>,</b>
+<b>  uint32_t <i>escape_char</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function is part of an experimental set of pattern conversion functions.
+It sets the escape character that is used when converting globs. The second
+argument must either be zero (meaning there is no escape character) or a
+punctuation character whose code point is less than 256. The default is grave
+accent if running under Windows, otherwise backslash. The result of the
+function is zero for success or PCRE2_ERROR_BADDATA if the second argument is
+invalid.
+</P>
+<P>
+The pattern conversion functions are described in the
+<a href="pcre2convert.html"><b>pcre2convert</b></a>
+documentation.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_set_glob_separator.html

@@ -0,0 +1,42 @@
+<html>
+<head>
+<title>pcre2_set_glob_separator specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_set_glob_separator man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>int pcre2_set_glob_separator(pcre2_convert_context *<i>cvcontext</i>,</b>
+<b>  uint32_t <i>separator_char</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function is part of an experimental set of pattern conversion functions.
+It sets the component separator character that is used when converting globs.
+The second argument must be one of the characters forward slash, backslash, or
+dot. The default is backslash when running under Windows, otherwise forward
+slash. The result of the function is zero for success or PCRE2_ERROR_BADDATA if
+the second argument is invalid.
+</P>
+<P>
+The pattern conversion functions are described in the
+<a href="pcre2convert.html"><b>pcre2convert</b></a>
+documentation.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_set_heap_limit.html

@@ -0,0 +1,40 @@
+<html>
+<head>
+<title>pcre2_set_heap_limit specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_set_heap_limit man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>int pcre2_set_heap_limit(pcre2_match_context *<i>mcontext</i>,</b>
+<b>  uint32_t <i>value</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function sets the backtracking heap limit field in a match context. The
+result is always zero.
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the POSIX API in the
+<a href="pcre2posix.html"><b>pcre2posix</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_set_match_limit.html

@@ -0,0 +1,40 @@
+<html>
+<head>
+<title>pcre2_set_match_limit specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_set_match_limit man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>int pcre2_set_match_limit(pcre2_match_context *<i>mcontext</i>,</b>
+<b>  uint32_t <i>value</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function sets the match limit field in a match context. The result is
+always zero.
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the POSIX API in the
+<a href="pcre2posix.html"><b>pcre2posix</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_set_max_pattern_length.html

@@ -0,0 +1,43 @@
+<html>
+<head>
+<title>pcre2_set_max_pattern_length specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_set_max_pattern_length man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>int pcre2_set_max_pattern_length(pcre2_compile_context *<i>ccontext</i>,</b>
+<b>  PCRE2_SIZE <i>value</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function sets, in a compile context, the maximum text length (in code
+units) of the pattern that can be compiled. The result is always zero. If a
+longer pattern is passed to <b>pcre2_compile()</b> there is an immediate error
+return. The default is effectively unlimited, being the largest value a
+PCRE2_SIZE variable can hold.
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the POSIX API in the
+<a href="pcre2posix.html"><b>pcre2posix</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_set_newline.html

@@ -0,0 +1,51 @@
+<html>
+<head>
+<title>pcre2_set_newline specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_set_newline man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>int pcre2_set_newline(pcre2_compile_context *<i>ccontext</i>,</b>
+<b>  uint32_t <i>value</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function sets the newline convention within a compile context. This
+specifies which character(s) are recognized as newlines when compiling and
+matching patterns. The second argument must be one of:
+<pre>
+  PCRE2_NEWLINE_CR        Carriage return only
+  PCRE2_NEWLINE_LF        Linefeed only
+  PCRE2_NEWLINE_CRLF      CR followed by LF only
+  PCRE2_NEWLINE_ANYCRLF   Any of the above
+  PCRE2_NEWLINE_ANY       Any Unicode newline sequence
+  PCRE2_NEWLINE_NUL       The NUL character (binary zero)
+</pre>
+The result is zero for success or PCRE2_ERROR_BADDATA if the second argument is
+invalid.
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the POSIX API in the
+<a href="pcre2posix.html"><b>pcre2posix</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_set_offset_limit.html

@@ -0,0 +1,40 @@
+<html>
+<head>
+<title>pcre2_set_offset_limit specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_set_offset_limit man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>int pcre2_set_offset_limit(pcre2_match_context *<i>mcontext</i>,</b>
+<b>  PCRE2_SIZE <i>value</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function sets the offset limit field in a match context. The result is
+always zero.
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the POSIX API in the
+<a href="pcre2posix.html"><b>pcre2posix</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_set_parens_nest_limit.html

@@ -0,0 +1,40 @@
+<html>
+<head>
+<title>pcre2_set_parens_nest_limit specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_set_parens_nest_limit man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>int pcre2_set_parens_nest_limit(pcre2_compile_context *<i>ccontext</i>,</b>
+<b>  uint32_t <i>value</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function sets, in a compile context, the maximum depth of nested
+parentheses in a pattern. The result is always zero.
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the POSIX API in the
+<a href="pcre2posix.html"><b>pcre2posix</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_set_recursion_limit.html

@@ -0,0 +1,40 @@
+<html>
+<head>
+<title>pcre2_set_recursion_limit specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_set_recursion_limit man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>int pcre2_set_recursion_limit(pcre2_match_context *<i>mcontext</i>,</b>
+<b>  uint32_t <i>value</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+This function is obsolete and should not be used in new code. Use
+<b>pcre2_set_depth_limit()</b> instead.
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the POSIX API in the
+<a href="pcre2posix.html"><b>pcre2posix</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>

src/regex/pcre2/doc/html/pcre2_set_recursion_memory_management.html

@@ -0,0 +1,42 @@
+<html>
+<head>
+<title>pcre2_set_recursion_memory_management specification</title>
+</head>
+<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
+<h1>pcre2_set_recursion_memory_management man page</h1>
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>
+<p>
+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+<br>
+<br><b>
+SYNOPSIS
+</b><br>
+<P>
+<b>#include &#60;pcre2.h&#62;</b>
+</P>
+<P>
+<b>int pcre2_set_recursion_memory_management(</b>
+<b>  pcre2_match_context *<i>mcontext</i>,</b>
+<b>  void *(*<i>private_malloc</i>)(PCRE2_SIZE, void *),</b>
+<b>  void (*<i>private_free</i>)(void *, void *), void *<i>memory_data</i>);</b>
+</P>
+<br><b>
+DESCRIPTION
+</b><br>
+<P>
+From release 10.30 onwards, this function is obsolete and does nothing. The
+result is always zero.
+</P>
+<P>
+There is a complete description of the PCRE2 native API in the
+<a href="pcre2api.html"><b>pcre2api</b></a>
+page and a description of the POSIX API in the
+<a href="pcre2posix.html"><b>pcre2posix</b></a>
+page.
+<p>
+Return to the <a href="index.html">PCRE2 index page</a>.
+</p>