Upgrade bundled pcre2 to 10.43

NEWS

@@ -84,6 +84,9 @@ PHP                                                                        NEWS
 - Output:
   . Clear output handler status flags during handler initialization. (haszi)
 
+- PCRE:
+  . Upgrade bundled pcre2lib to version 10.43. (nielsdos)
+
 - PDO:
   . Fixed setAttribute and getAttribute. (SakiTakamachi)
   . Implemented PDO driver-specific subclasses RFC. (danack, kocsismate)

UPGRADING

@@ -64,6 +64,13 @@ PHP 8.4 UPGRADE NOTES
     exclusively, without also specifying a JIT mode using opcache.jit. To enable
     JIT, set the opcache.jit config value accordingly.
 
+- PCRE:
+  . The bundled pcre2lib has been updated to version 10.43.
+    As a consequence, this means {,3} is now recognized as a quantifier instead
+    of as text. Furthermore, the meaning of some character classes in UCP mode
+    has changed. Consult https://github.com/PCRE2Project/pcre2/blob/master/NEWS
+    for a full changelog.
+
 - PDO_DBLIB:
   . setAttribute, DBLIB_ATTR_STRINGIFY_UNIQUEIDENTIFIER and DBLIB_ATTR_DATETIME_CONVERT
     have been changed to set value as a bool.
@@ -179,6 +186,12 @@ PHP 8.4 UPGRADE NOTES
 - Phar:
   . Added support for the unix timestamp extension for zip archives.
 
+- PCRE:
+  . The bundled pcre2lib has been updated to version 10.43.
+    As a consequence, LoongArch JIT support has been added, spaces
+    are now allowed between braces in Perl-compatible items, and
+    variable-length lookbehind assertions are now supported.
+
 - PDO:
   . Added support for driver-specific subclasses.
     RFC: https://wiki.php.net/rfc/pdo_driver_specific_subclasses

ext/pcre/config.w32

@@ -2,7 +2,7 @@
 
 EXTENSION("pcre", "php_pcre.c", false /* never shared */,
 		"-Iext/pcre/pcre2lib -DZEND_ENABLE_STATIC_TSRMLS_CACHE=1");
-ADD_SOURCES("ext/pcre/pcre2lib", "pcre2_auto_possess.c pcre2_chartables.c pcre2_compile.c pcre2_config.c pcre2_context.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_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_DEF_FILE("ext\\pcre\\php_pcre.def");
 
 AC_DEFINE('HAVE_BUNDLED_PCRE', 1, 'Using bundled PCRE library');

ext/pcre/config0.m4

@@ -60,7 +60,7 @@ else
   AC_MSG_CHECKING([for PCRE library to use])
   AC_MSG_RESULT([bundled])
   pcrelib_sources="pcre2lib/pcre2_auto_possess.c pcre2lib/pcre2_chartables.c pcre2lib/pcre2_compile.c \
-      pcre2lib/pcre2_config.c pcre2lib/pcre2_context.c pcre2lib/pcre2_dfa_match.c pcre2lib/pcre2_error.c \
+      pcre2lib/pcre2_config.c pcre2lib/pcre2_context.c pcre2lib/pcre2_chkdint.c pcre2lib/pcre2_dfa_match.c pcre2lib/pcre2_error.c \
   pcre2lib/pcre2_jit_compile.c pcre2lib/pcre2_maketables.c pcre2lib/pcre2_match.c pcre2lib/pcre2_match_data.c \
   pcre2lib/pcre2_newline.c pcre2lib/pcre2_ord2utf.c pcre2lib/pcre2_pattern_info.c pcre2lib/pcre2_serialize.c \
   pcre2lib/pcre2_string_utils.c pcre2lib/pcre2_study.c pcre2lib/pcre2_substitute.c  pcre2lib/pcre2_substring.c \

ext/pcre/pcre2lib/config.h

@@ -26,7 +26,7 @@
 
 /* Define to any value to enable support for Just-In-Time compiling. */
 #ifdef HAVE_PCRE_JIT_SUPPORT
-#define SUPPORT_JIT
+#define SUPPORT_JIT 1
 #endif
 
 /* This limits the amount of memory that pcre2_match() may use while matching
@@ -98,3 +98,13 @@
 #define LINK_SIZE 2
 #endif
 
+/* The value of MAX_VARLOOKBEHIND specifies the default maximum length, in
+  characters, for a variable-length lookbehind assertion. */
+#ifndef MAX_VARLOOKBEHIND
+#define MAX_VARLOOKBEHIND 255
+#endif
+
+/* to make a symbol visible */
+#ifndef PCRE2_EXPORT
+#define PCRE2_EXPORT
+#endif

ext/pcre/pcre2lib/pcre2.h

@@ -5,7 +5,7 @@
 /* This is the public header file for the PCRE library, second API, to be
 #included by applications that call PCRE2 functions.
 
-           Copyright (c) 2016-2021 University of Cambridge
+           Copyright (c) 2016-2024 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without
@@ -42,9 +42,9 @@ POSSIBILITY OF SUCH DAMAGE.
 /* The current PCRE version information. */
 
 #define PCRE2_MAJOR           10
-#define PCRE2_MINOR           42
+#define PCRE2_MINOR           43
 #define PCRE2_PRERELEASE      
-#define PCRE2_DATE            2022-12-12
+#define PCRE2_DATE            2024-02-16
 
 /* 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
@@ -153,6 +153,12 @@ D   is inspected during pcre2_dfa_match() execution
 #define PCRE2_EXTRA_ESCAPED_CR_IS_LF         0x00000010u  /* C */
 #define PCRE2_EXTRA_ALT_BSUX                 0x00000020u  /* C */
 #define PCRE2_EXTRA_ALLOW_LOOKAROUND_BSK     0x00000040u  /* C */
+#define PCRE2_EXTRA_CASELESS_RESTRICT        0x00000080u  /* C */
+#define PCRE2_EXTRA_ASCII_BSD                0x00000100u  /* C */
+#define PCRE2_EXTRA_ASCII_BSS                0x00000200u  /* C */
+#define PCRE2_EXTRA_ASCII_BSW                0x00000400u  /* C */
+#define PCRE2_EXTRA_ASCII_POSIX              0x00000800u  /* C */
+#define PCRE2_EXTRA_ASCII_DIGIT              0x00001000u  /* C */
 
 /* These are for pcre2_jit_compile(). */
 
@@ -180,11 +186,12 @@ pcre2_jit_match() ignores the latter since it bypasses all sanity checks). */
 #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_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 */
+#define PCRE2_DISABLE_RECURSELOOP_CHECK   0x00040000u  /* not for pcre2_dfa_match() or pcre2_jit_match() */
 
 /* Options for pcre2_pattern_convert(). */
 
@@ -399,6 +406,7 @@ released, the numbers must not be changed. */
 #define PCRE2_ERROR_CONVERT_SYNTAX    (-64)
 #define PCRE2_ERROR_INTERNAL_DUPMATCH (-65)
 #define PCRE2_ERROR_DFA_UINVALID_UTF  (-66)
+#define PCRE2_ERROR_INVALIDOFFSET     (-67)
 
 
 /* Request types for pcre2_pattern_info() */
@@ -572,19 +580,19 @@ 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 *), \
+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 *(*)(size_t, 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 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 \
@@ -595,6 +603,8 @@ 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_max_varlookbehind(pcre2_compile_context *, uint32_t); \
 PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
   pcre2_set_newline(pcre2_compile_context *, uint32_t); \
 PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
@@ -604,10 +614,10 @@ PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
     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 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 \
@@ -628,13 +638,13 @@ 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 *);
+    void *(*)(size_t, 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 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 \
@@ -646,15 +656,15 @@ PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
 /* 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_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 *);
+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. */
@@ -670,10 +680,10 @@ PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
 /* 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_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, \
@@ -687,10 +697,12 @@ 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 PCRE2_SIZE PCRE2_CALL_CONVENTION \
+  pcre2_get_match_data_heapframes_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_ovector_pointer(pcre2_match_data *); \
 PCRE2_EXP_DECL PCRE2_SIZE PCRE2_CALL_CONVENTION \
   pcre2_get_startchar(pcre2_match_data *);
 
@@ -722,7 +734,7 @@ PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
 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_substring_list_free(PCRE2_UCHAR **); \
 PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
   pcre2_substring_list_get(pcre2_match_data *, PCRE2_UCHAR ***, PCRE2_SIZE **);
 
@@ -770,8 +782,8 @@ PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
     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 pcre2_jit_stack *PCRE2_CALL_CONVENTION \
+  pcre2_jit_stack_create(size_t, size_t, 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 \
@@ -783,8 +795,8 @@ PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
 #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 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 *);
 
@@ -851,6 +863,7 @@ pcre2_compile are called by application code. */
 #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_heapframes_size  PCRE2_SUFFIX(pcre2_get_match_data_heapframes_size_)
 #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_)
@@ -886,6 +899,7 @@ pcre2_compile are called by application code. */
 #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_varlookbehind           PCRE2_SUFFIX(pcre2_set_max_varlookbehind_)
 #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_)

ext/pcre/pcre2lib/pcre2_auto_possess.c

@@ -560,6 +560,8 @@ matches to an empty string (also represented by a non-zero value). */
 
 for(;;)
   {
+  PCRE2_SPTR bracode;
+
   /* All operations move the code pointer forward.
   Therefore infinite recursions are not possible. */
 
@@ -617,7 +619,8 @@ for(;;)
     recursions. (This could be improved by keeping a list of group numbers that
     are called by recursion.) */
 
-    switch(*(code - GET(code, 1)))
+    bracode = code - GET(code, 1);
+    switch(*bracode)
       {
       case OP_CBRA:
       case OP_SCBRA:
@@ -636,16 +639,19 @@ for(;;)
       break;
 
       /* Atomic sub-patterns and assertions can always auto-possessify their
-      last iterator. However, if the group was entered as a result of checking
-      a previous iterator, this is not possible. */
+      last iterator except for variable length lookbehinds. However, if the
+      group was entered as a result of checking a previous iterator, this is
+      not possible. */
 
       case OP_ASSERT:
       case OP_ASSERT_NOT:
-      case OP_ASSERTBACK:
-      case OP_ASSERTBACK_NOT:
       case OP_ONCE:
       return !entered_a_group;
 
+      case OP_ASSERTBACK:
+      case OP_ASSERTBACK_NOT:
+      return (bracode[1+LINK_SIZE] == OP_VREVERSE)? FALSE : !entered_a_group;
+
       /* Non-atomic assertions - don't possessify last iterator. This needs
       more thought. */