ext/pcre: Upgrade bundled PCRE2 to 10.49

Import PCRE2 10.49 and its pinned SLJIT sources, retaining PHP's
configuration and symbol prefixes. Update both build systems and the
reproducible importer, and cover the Unicode character-class regression
that prompted the 10.44 rollback.

Author: iliaal

.github/scripts/download-bundled/pcre2.sh

@@ -5,16 +5,20 @@ cd "$(dirname "$0")/../../.."
 tmp_dir=/tmp/php-src-download-bundled/pcre2
 rm -rf "$tmp_dir"
 
-revision=refs/tags/pcre2-10.44
+revision=refs/tags/pcre2-10.49
 
 git clone --depth 1 --recurse-submodules --revision="$revision" https://github.com/PCRE2Project/pcre2.git "$tmp_dir"
 
 rm -rf ext/pcre/pcre2lib
 cp -R "$tmp_dir"/src ext/pcre/pcre2lib
+cp -R "$tmp_dir"/deps/sljit/sljit_src ext/pcre/pcre2lib/sljit
+sed 's|"../deps/sljit/sljit_src/sljitLir.c"|"sljit/sljitLir.c"|' \
+    "$tmp_dir"/src/pcre2_jit_compile.c > ext/pcre/pcre2lib/pcre2_jit_compile.c
 
 cd ext/pcre/pcre2lib
 
 # remove unneeded files
+rm config-cmake.h.in
 rm config.h.generic
 rm pcre2.h.in
 rm pcre2_dftables.c
@@ -26,6 +30,9 @@ rm pcre2posix.c
 rm pcre2posix.h
 rm pcre2posix_test.c
 rm pcre2test.c
+rm pcre2test_inc.h
+rm pcre2_chartables.c.ebcdic-*
+rm libpcre2-*.sym.in
 
 # move renamed files
 mv pcre2.h.generic pcre2.h

NEWS

@@ -85,6 +85,9 @@ PHP                                                                        NEWS
   . Fixed bug GH-23986 (/proc/self paths resolve to the parent process after
     pcntl_fork()). (Lazizbek Ergashev)
 
+- PCRE:
+  . Upgraded bundled PCRE2 to 10.49. (Ilia Alshanetsky)
+
 - PDO:
   . Fixed PDO::setAttribute() installing a PDO::ATTR_STATEMENT_CLASS class
     whose constructor arguments it rejects. (Ilia Alshanetsky)

UPGRADING

@@ -119,6 +119,11 @@ PHP 8.6 UPGRADE NOTES
   . preg_grep() now returns false instead of a partial array when a PCRE
     execution error occurs (e.g. malformed UTF-8 input with the /u modifier).
     This is consistent with other preg_* functions.
+  . With the bundled PCRE2 library, case-insensitive matching of \p{Ll},
+    \p{Lu}, and \p{Lt} now matches any cased letter.
+  . A \x escape without a following hexadecimal digit or opening brace now
+    causes a compilation error. Use \x00 to match the NUL character.
+  . Unicode character properties in the bundled library now use Unicode 17.0.
 
 - PGSQL:
   . pg_fetch_object() now reports the ValueError for a non-empty
@@ -958,6 +963,9 @@ PHP 8.6 UPGRADE NOTES
 - Opcache:
   . JIT is now supported for ZTS builds on Apple Silicon.
 
+- PCRE:
+  . The bundled PCRE2 library has been upgraded to version 10.49.
+
 ========================================
 10. New Global Constants
 ========================================

ext/pcre/config.w32

@@ -2,7 +2,7 @@
 
 EXTENSION("pcre", "php_pcre.c", false /* never shared */,
 		"-Iext/pcre/pcre2lib");
-ADD_SOURCES("ext/pcre/pcre2lib", "pcre2_auto_possess.c pcre2_chartables.c pcre2_compile.c pcre2_config.c pcre2_context.c pcre2_chkdint.c pcre2_dfa_match.c pcre2_error.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_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 pcre2_find_bracket.c pcre2_convert.c pcre2_extuni.c pcre2_script_run.c", "pcre");
+ADD_SOURCES("ext/pcre/pcre2lib", "pcre2_auto_possess.c pcre2_chartables.c pcre2_compile.c pcre2_compile_cgroup.c pcre2_compile_class.c pcre2_config.c pcre2_context.c pcre2_chkdint.c pcre2_dfa_match.c pcre2_error.c pcre2_jit_compile.c pcre2_maketables.c pcre2_match.c pcre2_match_data.c pcre2_match_next.c pcre2_newline.c pcre2_ord2utf.c pcre2_pattern_info.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 pcre2_find_bracket.c pcre2_convert.c pcre2_extuni.c pcre2_script_run.c", "pcre");
 ADD_DEF_FILE("ext\\pcre\\php_pcre.def");
 
 AC_DEFINE('HAVE_BUNDLED_PCRE', 1, 'Define to 1 if PHP uses the bundled PCRE library.');

ext/pcre/config0.m4

@@ -67,6 +67,8 @@ else
     pcre2lib/pcre2_chartables.c
     pcre2lib/pcre2_chkdint.c
     pcre2lib/pcre2_compile.c
+    pcre2lib/pcre2_compile_cgroup.c
+    pcre2lib/pcre2_compile_class.c
     pcre2lib/pcre2_config.c
     pcre2lib/pcre2_context.c
     pcre2lib/pcre2_convert.c
@@ -78,6 +80,7 @@ else
     pcre2lib/pcre2_maketables.c
     pcre2lib/pcre2_match_data.c
     pcre2lib/pcre2_match.c
+    pcre2lib/pcre2_match_next.c
     pcre2lib/pcre2_newline.c
     pcre2lib/pcre2_ord2utf.c
     pcre2lib/pcre2_pattern_info.c

ext/pcre/pcre2lib/pcre2.h

@@ -42,40 +42,37 @@ POSSIBILITY OF SUCH DAMAGE.
 /* The current PCRE version information. */
 
 #define PCRE2_MAJOR           10
-#define PCRE2_MINOR           44
+#define PCRE2_MINOR           49
 #define PCRE2_PRERELEASE      
-#define PCRE2_DATE            2024-06-07
+#define PCRE2_DATE            2026-09-28
 
-/* When an application links to a PCRE DLL in Windows, the symbols that are
+/* When an application links to a PCRE2 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. */
+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. */
+By default, we use the standard "extern" declarations. */
 
 #ifndef PCRE2_EXP_DECL
-#  ifdef __cplusplus
+#  if defined(_WIN32) && !defined(PCRE2_STATIC)
+#    define PCRE2_EXP_DECL  extern __declspec(dllimport)
+#  elif defined __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
+a "calling convention" before exported function names. For example:
 
   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. */
+might be needed. In order to make this easy, all the exported functions have
+PCRE2_CALL_CONVENTION just before their names.
+
+PCRE2 normally uses the platform's standard calling convention, so this should
+not be set unless you know you need it. */
 
 #ifndef PCRE2_CALL_CONVENTION
 #define PCRE2_CALL_CONVENTION
@@ -143,6 +140,7 @@ D   is inspected during pcre2_dfa_match() execution
 #define PCRE2_EXTENDED_MORE       0x01000000u  /* C       */
 #define PCRE2_LITERAL             0x02000000u  /* C       */
 #define PCRE2_MATCH_INVALID_UTF   0x04000000u  /*   J M D */
+#define PCRE2_ALT_EXTENDED_CLASS  0x08000000u  /* C       */
 
 /* An additional compile options word is available in the compile context. */
 
@@ -159,13 +157,18 @@ D   is inspected during pcre2_dfa_match() execution
 #define PCRE2_EXTRA_ASCII_BSW                0x00000400u  /* C */
 #define PCRE2_EXTRA_ASCII_POSIX              0x00000800u  /* C */
 #define PCRE2_EXTRA_ASCII_DIGIT              0x00001000u  /* C */
+#define PCRE2_EXTRA_PYTHON_OCTAL             0x00002000u  /* C */
+#define PCRE2_EXTRA_NO_BS0                   0x00004000u  /* C */
+#define PCRE2_EXTRA_NEVER_CALLOUT            0x00008000u  /* C */
+#define PCRE2_EXTRA_TURKISH_CASING           0x00010000u  /* 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
+#define PCRE2_JIT_TEST_ALLOC      0x00000200u
 
 /* 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
@@ -318,9 +321,29 @@ pcre2_pattern_convert(). */
 #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
+#define PCRE2_ERROR_MISSING_OCTAL_DIGIT            198
 #define PCRE2_ERROR_BACKSLASH_K_IN_LOOKAROUND      199
-
+#define PCRE2_ERROR_MAX_VAR_LOOKBEHIND_EXCEEDED    200
+#define PCRE2_ERROR_PATTERN_COMPILED_SIZE_TOO_BIG  201
+#define PCRE2_ERROR_OVERSIZE_PYTHON_OCTAL          202
+#define PCRE2_ERROR_CALLOUT_CALLER_DISABLED        203
+#define PCRE2_ERROR_EXTRA_CASING_REQUIRES_UNICODE  204
+#define PCRE2_ERROR_TURKISH_CASING_REQUIRES_UTF    205
+#define PCRE2_ERROR_EXTRA_CASING_INCOMPATIBLE      206
+#define PCRE2_ERROR_ECLASS_NEST_TOO_DEEP           207
+#define PCRE2_ERROR_ECLASS_INVALID_OPERATOR        208
+#define PCRE2_ERROR_ECLASS_UNEXPECTED_OPERATOR     209
+#define PCRE2_ERROR_ECLASS_EXPECTED_OPERAND        210
+#define PCRE2_ERROR_ECLASS_MIXED_OPERATORS         211
+#define PCRE2_ERROR_ECLASS_HINT_SQUARE_BRACKET     212
+#define PCRE2_ERROR_PERL_ECLASS_UNEXPECTED_EXPR    213
+#define PCRE2_ERROR_PERL_ECLASS_EMPTY_EXPR         214
+#define PCRE2_ERROR_PERL_ECLASS_MISSING_CLOSE      215
+#define PCRE2_ERROR_PERL_ECLASS_UNEXPECTED_CHAR    216
+#define PCRE2_ERROR_EXPECTED_CAPTURE_GROUP         217
+#define PCRE2_ERROR_MISSING_OPENING_PARENTHESIS    218
+#define PCRE2_ERROR_MISSING_NUMBER_TERMINATOR      219
+#define PCRE2_ERROR_NULL_ERROROFFSET               220
 
 /* "Expected" matching error codes: no match and partial match. */
 
@@ -407,6 +430,15 @@ released, the numbers must not be changed. */
 #define PCRE2_ERROR_INTERNAL_DUPMATCH (-65)
 #define PCRE2_ERROR_DFA_UINVALID_UTF  (-66)
 #define PCRE2_ERROR_INVALIDOFFSET     (-67)
+#define PCRE2_ERROR_JIT_UNSUPPORTED   (-68)
+#define PCRE2_ERROR_REPLACECASE       (-69)
+#define PCRE2_ERROR_TOOLARGEREPLACE   (-70)
+#define PCRE2_ERROR_DIFFSUBSPATTERN   (-71)
+#define PCRE2_ERROR_DIFFSUBSSUBJECT   (-72)
+#define PCRE2_ERROR_DIFFSUBSOFFSET    (-73)
+#define PCRE2_ERROR_DIFFSUBSOPTIONS   (-74)
+#define PCRE2_ERROR_BAD_BACKSLASH_K   (-75)
+#define PCRE2_ERROR_PARTIALSUBS       (-76)
 
 
 /* Request types for pcre2_pattern_info() */
@@ -459,7 +491,32 @@ released, the numbers must not be changed. */
 #define PCRE2_CONFIG_NEVER_BACKSLASH_C      13
 #define PCRE2_CONFIG_COMPILED_WIDTHS        14
 #define PCRE2_CONFIG_TABLES_LENGTH          15
+#define PCRE2_CONFIG_EFFECTIVE_LINKSIZE     16
+
+/* Optimization directives for pcre2_set_optimize().
+For binary compatibility, only add to this list; do not renumber. */
+
+#define PCRE2_OPTIMIZATION_NONE    0
+#define PCRE2_OPTIMIZATION_FULL    1
+
+#define PCRE2_AUTO_POSSESS         64
+#define PCRE2_AUTO_POSSESS_OFF     65
+#define PCRE2_DOTSTAR_ANCHOR       66
+#define PCRE2_DOTSTAR_ANCHOR_OFF   67
+#define PCRE2_START_OPTIMIZE       68
+#define PCRE2_START_OPTIMIZE_OFF   69
 
+/* Types used in pcre2_set_substitute_case_callout().
+
+PCRE2_SUBSTITUTE_CASE_LOWER and PCRE2_SUBSTITUTE_CASE_UPPER are passed to the
+callout to indicate that the case of the entire callout input should be
+case-transformed. PCRE2_SUBSTITUTE_CASE_TITLE_FIRST is passed to indicate that
+only the first character or glyph should be transformed to Unicode titlecase,
+and the rest to lowercase. */
+
+#define PCRE2_SUBSTITUTE_CASE_LOWER        1
+#define PCRE2_SUBSTITUTE_CASE_UPPER        2
+#define PCRE2_SUBSTITUTE_CASE_TITLE_FIRST  3
 
 /* Types for code units in patterns and subject strings. */
 
@@ -613,7 +670,9 @@ 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 *);
+    int (*)(uint32_t, void *), void *); \
+PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
+  pcre2_set_optimize(pcre2_compile_context *, uint32_t);
 
 #define PCRE2_MATCH_CONTEXT_FUNCTIONS \
 PCRE2_EXP_DECL pcre2_match_context *PCRE2_CALL_CONVENTION \
@@ -628,6 +687,11 @@ PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
 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_substitute_case_callout(pcre2_match_context *, \
+    PCRE2_SIZE (*)(PCRE2_SPTR, PCRE2_SIZE, PCRE2_UCHAR *, PCRE2_SIZE, int, \
+                   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 \
@@ -687,14 +751,14 @@ PCRE2_EXP_DECL pcre2_match_data *PCRE2_CALL_CONVENTION \
 PCRE2_EXP_DECL pcre2_match_data *PCRE2_CALL_CONVENTION \
   pcre2_match_data_create_from_pattern(const pcre2_code *, \
     pcre2_general_context *); \
+PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
+  pcre2_match_data_free(pcre2_match_data *); \
 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 \
@@ -706,7 +770,9 @@ PCRE2_EXP_DECL uint32_t PCRE2_CALL_CONVENTION \
 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 *);
+  pcre2_get_startchar(pcre2_match_data *); \
+PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
+  pcre2_next_match(pcre2_match_data *, PCRE2_SIZE *, uint32_t *);
 
 
 /* Convenience functions for handling matched substrings. */
@@ -740,6 +806,7 @@ PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
 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 \
@@ -885,6 +952,7 @@ pcre2_compile are called by application code. */
 #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_next_match                      PCRE2_SUFFIX(pcre2_next_match_)
 #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_)
@@ -907,7 +975,9 @@ pcre2_compile are called by application code. */
 #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_optimize                    PCRE2_SUFFIX(pcre2_set_optimize_)
 #define pcre2_set_substitute_callout          PCRE2_SUFFIX(pcre2_set_substitute_callout_)
+#define pcre2_set_substitute_case_callout     PCRE2_SUFFIX(pcre2_set_substitute_case_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_)