pcre2lib: Pull PCRE2 10.37

Excerpt from the release news:

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 php#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 php#2618.

Signed-off-by: Anatol Belski <[email protected]>

Author: weltling

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           35
+#define PCRE2_MINOR           37
 #define PCRE2_PRERELEASE      
-#define PCRE2_DATE            2020-05-09
+#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

ext/pcre/pcre2lib/pcre2_auto_possess.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) 2016-2020 University of Cambridge
+          New API code Copyright (c) 2016-2021 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without
@@ -490,6 +490,7 @@ switch(c)
   list[2] = (uint32_t)(end - code);
   return end;
   }
+
 return NULL;    /* Opcode not accepted */
 }
 
@@ -1186,12 +1187,16 @@ for (;;)
     c = *repeat_opcode;
     if (c >= OP_CRSTAR && c <= OP_CRMINRANGE)
       {
-      /* end must not be NULL. */
-      end = get_chr_property_list(code, utf, ucp, cb->fcc, list);
+      /* The return from get_chr_property_list() will never be NULL when
+      *code (aka c) is one of the three class opcodes. However, gcc with
+      -fanalyzer notes that a NULL return is possible, and grumbles. Hence we
+      put in a check. */
 
+      end = get_chr_property_list(code, utf, ucp, cb->fcc, list);
       list[1] = (c & 1) == 0;
 
-      if (compare_opcodes(end, utf, ucp, cb, list, end, &rec_limit))
+      if (end != NULL &&
+          compare_opcodes(end, utf, ucp, cb, list, end, &rec_limit))
         {
         switch (c)
           {

ext/pcre/pcre2lib/pcre2_chartables.c

@@ -0,0 +1 @@
+/home/weltling/dws/src/pcre2-10.37/src/pcre2_chartables.c.dist

ext/pcre/pcre2lib/pcre2_chartables.c

@@ -1398,32 +1398,47 @@ static BOOL
 read_repeat_counts(PCRE2_SPTR *ptrptr, PCRE2_SPTR ptrend, uint32_t *minp,
   uint32_t *maxp, int *errorcodeptr)
 {
-PCRE2_SPTR p = *ptrptr;
+PCRE2_SPTR p;
 BOOL yield = FALSE;
+BOOL had_comma = FALSE;
 int32_t min = 0;
 int32_t max = REPEAT_UNLIMITED; /* This value is larger than MAX_REPEAT_COUNT */
 
-/* NB read_number() initializes the error code to zero. The only error is for a
-number that is too big. */
+/* Check the syntax */
 
+*errorcodeptr = 0;
+for (p = *ptrptr;; p++)
+  {
+  uint32_t c;
+  if (p >= ptrend) return FALSE;
+  c = *p;
+  if (IS_DIGIT(c)) continue;
+  if (c == CHAR_RIGHT_CURLY_BRACKET) break;
+  if (c == CHAR_COMMA)
+    {
+    if (had_comma) return FALSE;
+    had_comma = TRUE;
+    }
+  else return FALSE;
+  }
+
+/* The only error from read_number() is for a number that is too big. */
+
+p = *ptrptr;
 if (!read_number(&p, ptrend, -1, MAX_REPEAT_COUNT, ERR5, &min, errorcodeptr))
   goto EXIT;
 
-if (p >= ptrend) goto EXIT;
-
 if (*p == CHAR_RIGHT_CURLY_BRACKET)
   {
   p++;
   max = min;
   }
-
 else
   {
-  if (*p++ != CHAR_COMMA || p >= ptrend) goto EXIT;
-  if (*p != CHAR_RIGHT_CURLY_BRACKET)
+  if (*(++p) != CHAR_RIGHT_CURLY_BRACKET)
     {
     if (!read_number(&p, ptrend, -1, MAX_REPEAT_COUNT, ERR5, &max,
-        errorcodeptr) || p >= ptrend ||  *p != CHAR_RIGHT_CURLY_BRACKET)
+        errorcodeptr))
       goto EXIT;
     if (max < min)
       {
@@ -1438,11 +1453,10 @@ yield = TRUE;
 if (minp != NULL) *minp = (uint32_t)min;
 if (maxp != NULL) *maxp = (uint32_t)max;
 
-/* Update the pattern pointer on success, or after an error, but not when
-the result is "not a repeat quantifier". */
+/* Update the pattern pointer */
 
 EXIT:
-if (yield || *errorcodeptr != 0) *ptrptr = p;
+*ptrptr = p;
 return yield;
 }
 
@@ -1776,19 +1790,23 @@ else
       {
       oldptr = ptr;
       ptr--;   /* Back to the digit */
-      if (!read_number(&ptr, ptrend, -1, INT_MAX/10 - 1, ERR61, &s,
-          errorcodeptr))
-        break;
 
-      /* \1 to \9 are always back references. \8x and \9x are too; \1x to \7x
+      /* As we know we are at a digit, the only possible error from
+      read_number() is a number that is too large to be a group number. In this
+      case we fall through handle this as not a group reference. If we have
+      read a small enough number, check for a back reference.
+
+      \1 to \9 are always back references. \8x and \9x are too; \1x to \7x
       are octal escapes if there are not that many previous captures. */
 
-      if (s < 10 || oldptr[-1] >= CHAR_8 || s <= (int)cb->bracount)
+      if (read_number(&ptr, ptrend, -1, INT_MAX/10 - 1, 0, &s, errorcodeptr) &&
+          (s < 10 || oldptr[-1] >= CHAR_8 || s <= (int)cb->bracount))
         {
         if (s > (int)MAX_GROUP_NUMBER) *errorcodeptr = ERR61;
           else escape = -s;     /* Indicates a back reference */
         break;
         }
+
       ptr = oldptr;      /* Put the pointer back and fall through */
       }
 
@@ -2344,7 +2362,7 @@ if (ptr > *nameptr + MAX_NAME_SIZE)
   *errorcodeptr = ERR48;
   goto FAILED;
   }
-*namelenptr = ptr - *nameptr;
+*namelenptr = (uint32_t)(ptr - *nameptr);
 
 /* Subpattern names must not be empty, and their terminator is checked here.
 (What follows a verb or alpha assertion name is checked separately.) */
@@ -4331,6 +4349,7 @@ while (ptr < ptrend)
           {
           if (++ptr >= ptrend || !IS_DIGIT(*ptr)) goto BAD_VERSION_CONDITION;
           minor = (*ptr++ - CHAR_0) * 10;
+          if (ptr >= ptrend) goto BAD_VERSION_CONDITION;
           if (IS_DIGIT(*ptr)) minor += *ptr++ - CHAR_0;
           if (ptr >= ptrend || *ptr != CHAR_RIGHT_PARENTHESIS)
             goto BAD_VERSION_CONDITION;