Update bundled pcre2 to 10.42

Closes GH-12109.

Author: nielsdos

NEWS

@@ -29,6 +29,9 @@ PHP                                                                        NEWS
   . Fixed persistent procedural ODBC connections not getting closed.
     (NattyNarwhal)
 
+- PCRE:
+  . Update bundled libpcre2 to 10.42. (nielsdos)
+
 - SPL:
   . Fixed bug GH-11972 (RecursiveCallbackFilterIterator regression in 8.1.18).
     (nielsdos)

ext/pcre/pcre2lib/pcre2.h

@@ -42,9 +42,9 @@ POSSIBILITY OF SUCH DAMAGE.
 /* The current PCRE version information. */
 
 #define PCRE2_MAJOR           10
-#define PCRE2_MINOR           40
+#define PCRE2_MINOR           42
 #define PCRE2_PRERELEASE      
-#define PCRE2_DATE            2022-04-14
+#define PCRE2_DATE            2022-12-12
 
 /* 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

ext/pcre/pcre2lib/pcre2_compile.c

@@ -1266,8 +1266,10 @@ PCRE2_SIZE* ref_count;
 
 if (code != NULL)
   {
+#ifdef SUPPORT_JIT
   if (code->executable_jit != NULL)
     PRIV(jit_free)(code->executable_jit, &code->memctl);
+#endif
 
   if ((code->flags & PCRE2_DEREF_TABLES) != 0)
     {
@@ -2687,7 +2689,7 @@ if ((options & PCRE2_EXTENDED_MORE) != 0) options |= PCRE2_EXTENDED;
 while (ptr < ptrend)
   {
   int prev_expect_cond_assert;
-  uint32_t min_repeat, max_repeat;
+  uint32_t min_repeat = 0, max_repeat = 0;
   uint32_t set, unset, *optset;
   uint32_t terminator;
   uint32_t prev_meta_quantifier;
@@ -8552,7 +8554,7 @@ do {
             op == OP_SCBRA || op == OP_SCBRAPOS)
      {
      int n = GET2(scode, 1+LINK_SIZE);
-     int new_map = bracket_map | ((n < 32)? (1u << n) : 1);
+     unsigned int new_map = bracket_map | ((n < 32)? (1u << n) : 1);
      if (!is_startline(scode, new_map, cb, atomcount, inassert)) return FALSE;
      }
 
@@ -10620,4 +10622,10 @@ re = NULL;
 goto EXIT;
 }
 
+/* These #undefs are here to enable unity builds with CMake. */
+
+#undef NLBLOCK /* Block containing newline information */
+#undef PSSTART /* Field containing processed string start */
+#undef PSEND   /* Field containing processed string end */
+
 /* End of pcre2_compile.c */

ext/pcre/pcre2lib/pcre2_context.c

@@ -7,7 +7,7 @@ and semantics are as close as possible to those of the Perl 5 language.
 
                        Written by Philip Hazel
      Original API code Copyright (c) 1997-2012 University of Cambridge
-          New API code Copyright (c) 2016-2018 University of Cambridge
+          New API code Copyright (c) 2016-2022 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without
@@ -443,8 +443,11 @@ mcontext->offset_limit = limit;
 return 0;
 }
 
-/* This function became obsolete at release 10.30. It is kept as a synonym for
-backwards compatibility. */
+/* These functions became obsolete at release 10.30. The first is kept as a
+synonym for backwards compatibility. The second now does nothing. Exclude both
+from coverage reports. */
+
+/* LCOV_EXCL_START */
 
 PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
 pcre2_set_recursion_limit(pcre2_match_context *mcontext, uint32_t limit)
@@ -464,6 +467,9 @@ pcre2_set_recursion_memory_management(pcre2_match_context *mcontext,
 return 0;
 }
 
+/* LCOV_EXCL_STOP */
+
+
 /* ------------ Convert context ------------ */
 
 PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION

ext/pcre/pcre2lib/pcre2_convert.c

@@ -7,7 +7,7 @@ and semantics are as close as possible to those of the Perl 5 language.
 
                        Written by Philip Hazel
      Original API code Copyright (c) 1997-2012 University of Cambridge
-          New API code Copyright (c) 2016-2018 University of Cambridge
+          New API code Copyright (c) 2016-2022 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without
@@ -65,9 +65,8 @@ POSSIBILITY OF SUCH DAMAGE.
 #define STR_QUERY_s STR_LEFT_PARENTHESIS STR_QUESTION_MARK STR_s STR_RIGHT_PARENTHESIS
 #define STR_STAR_NUL STR_LEFT_PARENTHESIS STR_ASTERISK STR_N STR_U STR_L STR_RIGHT_PARENTHESIS
 
-/* States for range and POSIX processing */
+/* States for POSIX processing */
 
-enum { RANGE_NOT_STARTED, RANGE_STARTING, RANGE_STARTED };
 enum { POSIX_START_REGEX, POSIX_ANCHORED, POSIX_NOT_BRACKET,
        POSIX_CLASS_NOT_STARTED, POSIX_CLASS_STARTING, POSIX_CLASS_STARTED };
 

ext/pcre/pcre2lib/pcre2_dfa_match.c

@@ -350,7 +350,7 @@ Returns:            the return from the callout
 */
 
 static int
-do_callout(PCRE2_SPTR code, PCRE2_SIZE *offsets, PCRE2_SPTR current_subject,
+do_callout_dfa(PCRE2_SPTR code, PCRE2_SIZE *offsets, PCRE2_SPTR current_subject,
   PCRE2_SPTR ptr, dfa_match_block *mb, PCRE2_SIZE extracode,
   PCRE2_SIZE *lengthptr)
 {
@@ -2799,7 +2799,7 @@ for (;;)
             || code[LINK_SIZE + 1] == OP_CALLOUT_STR)
           {
           PCRE2_SIZE callout_length;
-          rrc = do_callout(code, offsets, current_subject, ptr, mb,
+          rrc = do_callout_dfa(code, offsets, current_subject, ptr, mb,
             1 + LINK_SIZE, &callout_length);
           if (rrc < 0) return rrc;                 /* Abandon */
           if (rrc > 0) break;                      /* Fail this thread */
@@ -3196,7 +3196,7 @@ for (;;)
       case OP_CALLOUT_STR:
         {
         PCRE2_SIZE callout_length;
-        rrc = do_callout(code, offsets, current_subject, ptr, mb, 0,
+        rrc = do_callout_dfa(code, offsets, current_subject, ptr, mb, 0,
           &callout_length);
         if (rrc < 0) return rrc;   /* Abandon */
         if (rrc == 0)
@@ -4057,4 +4057,10 @@ while (rws->next != NULL)
 return rc;
 }
 
+/* These #undefs are here to enable unity builds with CMake. */
+
+#undef NLBLOCK /* Block containing newline information */
+#undef PSSTART /* Field containing processed string start */
+#undef PSEND   /* Field containing processed string end */
+
 /* End of pcre2_dfa_match.c */

ext/pcre/pcre2lib/pcre2_internal.h

@@ -220,18 +220,17 @@ not rely on this. */
 
 #define COMPILE_ERROR_BASE 100
 
-/* The initial frames vector for remembering backtracking points in
-pcre2_match() is allocated on the system stack, of this size (bytes). The size
-must be a multiple of sizeof(PCRE2_SPTR) in all environments, so making it a
-multiple of 8 is best. Typical frame sizes are a few hundred bytes (it depends
-on the number of capturing parentheses) so 20KiB handles quite a few frames. A
-larger vector on the heap is obtained for patterns that need more frames. The
-maximum size of this can be limited. */
+/* The initial frames vector for remembering pcre2_match() backtracking points
+is allocated on the heap, of this size (bytes) or ten times the frame size if
+larger, unless the heap limit is smaller. Typical frame sizes are a few hundred
+bytes (it depends on the number of capturing parentheses) so 20KiB handles
+quite a few frames. A larger vector on the heap is obtained for matches that
+need more frames, subject to the heap limit. */
 
 #define START_FRAMES_SIZE 20480
 
-/* Similarly, for DFA matching, an initial internal workspace vector is
-allocated on the stack. */
+/* For DFA matching, an initial internal workspace vector is allocated on the
+stack. The heap is used only if this turns out to be too small. */
 
 #define DFA_START_RWS_SIZE 30720
 

ext/pcre/pcre2lib/pcre2_intmodedep.h

@@ -7,7 +7,7 @@ and semantics are as close as possible to those of the Perl 5 language.
 
                        Written by Philip Hazel
      Original API code Copyright (c) 1997-2012 University of Cambridge
-          New API code Copyright (c) 2016-2018 University of Cambridge
+          New API code Copyright (c) 2016-2022 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without
@@ -649,19 +649,23 @@ the size varies from call to call. As the maximum number of capturing
 subpatterns is 65535 we must allow for 65536 strings to include the overall
 match. (See also the heapframe structure below.) */
 
+struct heapframe;  /* Forward reference */
+
 typedef struct pcre2_real_match_data {
-  pcre2_memctl     memctl;
-  const pcre2_real_code *code;    /* The pattern used for the match */
-  PCRE2_SPTR       subject;       /* The subject that was matched */
-  PCRE2_SPTR       mark;          /* Pointer to last mark */
-  PCRE2_SIZE       leftchar;      /* Offset to leftmost code unit */
-  PCRE2_SIZE       rightchar;     /* Offset to rightmost code unit */
-  PCRE2_SIZE       startchar;     /* Offset to starting code unit */
-  uint8_t          matchedby;     /* Type of match (normal, JIT, DFA) */
-  uint8_t          flags;         /* Various flags */
-  uint16_t         oveccount;     /* Number of pairs */
-  int              rc;            /* The return code from the match */
-  PCRE2_SIZE       ovector[131072]; /* Must be last in the structure */
+  pcre2_memctl     memctl;           /* Memory control fields */
+  const pcre2_real_code *code;       /* The pattern used for the match */
+  PCRE2_SPTR       subject;          /* The subject that was matched */
+  PCRE2_SPTR       mark;             /* Pointer to last mark */
+  struct heapframe *heapframes;      /* Backtracking frames heap memory */
+  PCRE2_SIZE       heapframes_size;  /* Malloc-ed size */
+  PCRE2_SIZE       leftchar;         /* Offset to leftmost code unit */
+  PCRE2_SIZE       rightchar;        /* Offset to rightmost code unit */
+  PCRE2_SIZE       startchar;        /* Offset to starting code unit */
+  uint8_t          matchedby;        /* Type of match (normal, JIT, DFA) */
+  uint8_t          flags;            /* Various flags */
+  uint16_t         oveccount;        /* Number of pairs */
+  int              rc;               /* The return code from the match */
+  PCRE2_SIZE       ovector[131072];  /* Must be last in the structure */
 } pcre2_real_match_data;
 
 
@@ -854,10 +858,6 @@ doing traditional NFA matching (pcre2_match() and friends). */
 
 typedef struct match_block {
   pcre2_memctl memctl;            /* For general use */
-  PCRE2_SIZE frame_vector_size;   /* Size of a backtracking frame */
-  heapframe *match_frames;        /* Points to vector of frames */
-  heapframe *match_frames_top;    /* Points after the end of the vector */
-  heapframe *stack_frames;        /* The original vector on the stack */
   PCRE2_SIZE heap_limit;          /* As it says */
   uint32_t match_limit;           /* As it says */
   uint32_t match_limit_depth;     /* As it says */