Update to PCRE2 10.35

We also backport the fix for bug #79846, and add a test case for the
related bug #79363.

Author: cmb69

NEWS

@@ -10,6 +10,9 @@ PHP                                                                        NEWS
   . Fixed bug #80083 (Optimizer pass 6 removes variables used for ibm_db2 data
     binding). (Nikita)
 
+- PCRE:
+  . Updated to PCRE 10.35. (cmb)
+
 01 Oct 2020, PHP 7.4.11
 
 - Core:

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) 2016-2019 University of Cambridge
+           Copyright (c) 2016-2020 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           34
+#define PCRE2_MINOR           35
 #define PCRE2_PRERELEASE      
-#define PCRE2_DATE            2019-11-21
+#define PCRE2_DATE            2020-05-09
 
 /* 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
@@ -181,6 +181,9 @@ pcre2_jit_match() ignores the latter since it bypasses all sanity checks). */
 #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(). */
 
@@ -445,6 +448,7 @@ released, the numbers must not be changed. */
 #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. */

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) 2016-2019 University of Cambridge
+          New API code Copyright (c) 2016-2020 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without
@@ -292,6 +292,7 @@ possessification, and if so, fills a list with its properties.
 Arguments:
   code        points to start of expression
   utf         TRUE if in UTF mode
+  ucp         TRUE if in UCP mode
   fcc         points to the case-flipping table
   list        points to output list
               list[0] will be filled with the opcode
@@ -304,7 +305,7 @@ Returns:      points to the start of the next opcode if *code is accepted
 */
 
 static PCRE2_SPTR
-get_chr_property_list(PCRE2_SPTR code, BOOL utf, const uint8_t *fcc,
+get_chr_property_list(PCRE2_SPTR code, BOOL utf, BOOL ucp, const uint8_t *fcc,
   uint32_t *list)
 {
 PCRE2_UCHAR c = *code;
@@ -316,7 +317,8 @@ uint32_t chr;
 uint32_t *clist_dest;
 const uint32_t *clist_src;
 #else
-(void)utf;    /* Suppress "unused parameter" compiler warning */
+(void)utf;    /* Suppress "unused parameter" compiler warnings */
+(void)ucp;
 #endif
 
 list[0] = c;
@@ -396,7 +398,7 @@ switch(c)
   list[2] = chr;
 
 #ifdef SUPPORT_UNICODE
-  if (chr < 128 || (chr < 256 && !utf))
+  if (chr < 128 || (chr < 256 && !utf && !ucp))
     list[3] = fcc[chr];
   else
     list[3] = UCD_OTHERCASE(chr);
@@ -503,6 +505,7 @@ which case the base cannot be possessified.
 Arguments:
   code        points to the byte code
   utf         TRUE in UTF mode
+  ucp         TRUE in UCP mode
   cb          compile data block
   base_list   the data list of the base opcode
   base_end    the end of the base opcode
@@ -512,7 +515,7 @@ Returns:      TRUE if the auto-possessification is possible
 */
 
 static BOOL
-compare_opcodes(PCRE2_SPTR code, BOOL utf, const compile_block *cb,
+compare_opcodes(PCRE2_SPTR code, BOOL utf, BOOL ucp, const compile_block *cb,
   const uint32_t *base_list, PCRE2_SPTR base_end, int *rec_limit)
 {
 PCRE2_UCHAR c;
@@ -651,7 +654,7 @@ for(;;)
 
     while (*next_code == OP_ALT)
       {
-      if (!compare_opcodes(code, utf, cb, base_list, base_end, rec_limit))
+      if (!compare_opcodes(code, utf, ucp, cb, base_list, base_end, rec_limit))
         return FALSE;
       code = next_code + 1 + LINK_SIZE;
       next_code += GET(next_code, 1);
@@ -672,7 +675,8 @@ for(;;)
     /* The bracket content will be checked by the OP_BRA/OP_CBRA case above. */
 
     next_code += 1 + LINK_SIZE;
-    if (!compare_opcodes(next_code, utf, cb, base_list, base_end, rec_limit))
+    if (!compare_opcodes(next_code, utf, ucp, cb, base_list, base_end,
+         rec_limit))
       return FALSE;
 
     code += PRIV(OP_lengths)[c];
@@ -688,7 +692,7 @@ for(;;)
   /* We now have the next appropriate opcode to compare with the base. Check
   for a supported opcode, and load its properties. */
 
-  code = get_chr_property_list(code, utf, cb->fcc, list);
+  code = get_chr_property_list(code, utf, ucp, cb->fcc, list);
   if (code == NULL) return FALSE;    /* Unsupported */
 
   /* If either opcode is a small character list, set pointers for comparing
@@ -1100,21 +1104,22 @@ leaving the remainder of the pattern unpossessified.
 
 Arguments:
   code        points to start of the byte code
-  utf         TRUE in UTF mode
   cb          compile data block
 
 Returns:      0 for success
               -1 if a non-existant opcode is encountered
 */
 
 int
-PRIV(auto_possessify)(PCRE2_UCHAR *code, BOOL utf, const compile_block *cb)
+PRIV(auto_possessify)(PCRE2_UCHAR *code, const compile_block *cb)
 {
 PCRE2_UCHAR c;
 PCRE2_SPTR end;
 PCRE2_UCHAR *repeat_opcode;
 uint32_t list[8];
 int rec_limit = 1000;  /* Was 10,000 but clang+ASAN uses a lot of stack. */
+BOOL utf = (cb->external_options & PCRE2_UTF) != 0;
+BOOL ucp = (cb->external_options & PCRE2_UCP) != 0;
 
 for (;;)
   {
@@ -1126,10 +1131,11 @@ for (;;)
     {
     c -= get_repeat_base(c) - OP_STAR;
     end = (c <= OP_MINUPTO) ?
-      get_chr_property_list(code, utf, cb->fcc, list) : NULL;
+      get_chr_property_list(code, utf, ucp, cb->fcc, list) : NULL;
     list[1] = c == OP_STAR || c == OP_PLUS || c == OP_QUERY || c == OP_UPTO;
 
-    if (end != NULL && compare_opcodes(end, utf, cb, list, end, &rec_limit))
+    if (end != NULL && compare_opcodes(end, utf, ucp, cb, list, end,
+        &rec_limit))
       {
       switch(c)
         {
@@ -1181,11 +1187,11 @@ for (;;)
     if (c >= OP_CRSTAR && c <= OP_CRMINRANGE)
       {
       /* end must not be NULL. */
-      end = get_chr_property_list(code, utf, cb->fcc, list);
+      end = get_chr_property_list(code, utf, ucp, cb->fcc, list);
 
       list[1] = (c & 1) == 0;
 
-      if (compare_opcodes(end, utf, cb, list, end, &rec_limit))
+      if (compare_opcodes(end, utf, ucp, cb, list, end, &rec_limit))
         {
         switch (c)
           {

ext/pcre/pcre2lib/pcre2_chartables.c

@@ -2,17 +2,21 @@
 *      Perl-Compatible Regular Expressions       *
 *************************************************/
 
-/* This file was automatically written by the dftables auxiliary
+/* This file was automatically written by the pcre2_dftables auxiliary
 program. It contains character tables that are used when no external
 tables are passed to PCRE2 by the application that calls it. The tables
 are used only for characters whose code values are less than 256. */
 
-/*The dftables program (which is distributed with PCRE2) can be used to
-build alternative versions of this file. This is necessary if you are
+/* This set of tables was written in the C locale. */
+
+/* The pcre2_ftables program (which is distributed with PCRE2) can be used
+to build alternative versions of this file. This is necessary if you are
 running in an EBCDIC environment, or if you want to default to a different
-encoding, for example ISO-8859-1. When dftables is run, it creates these
-tables in the current locale. This happens automatically if PCRE2 is
-configured with --enable-rebuild-chartables. */
+encoding, for example ISO-8859-1. When pcre2_dftables is run, it creates
+these tables in the "C" locale by default. This happens automatically if
+PCRE2 is configured with --enable-rebuild-chartables. However, you can run
+pcre2_dftables manually with the -L option to build tables using the LC_ALL
+locale. */
 
 /* The following #include is present because without it gcc 4.x may remove
 the array definition from the final binary if PCRE2 is built into a static
@@ -102,54 +106,54 @@ const uint8_t PRIV(default_tables)[] = {
 /* This table contains bit maps for various character classes. Each map is 32
 bytes long and the bits run from the least significant end of each byte. The
 classes that have their own maps are: space, xdigit, digit, upper, lower, word,
-graph print, punct, and cntrl. Other classes are built from combinations. */
+graph, print, punct, and cntrl. Other classes are built from combinations. */
 
-  0x00,0x3e,0x00,0x00,0x01,0x00,0x00,0x00,
+  0x00,0x3e,0x00,0x00,0x01,0x00,0x00,0x00,  /* space */
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
 
-  0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03,
+  0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03,  /* xdigit */
   0x7e,0x00,0x00,0x00,0x7e,0x00,0x00,0x00,
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
 
-  0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03,
+  0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03,  /* digit */
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
 
-  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,  /* upper */
   0xfe,0xff,0xff,0x07,0x00,0x00,0x00,0x00,
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
 
-  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,  /* lower */
   0x00,0x00,0x00,0x00,0xfe,0xff,0xff,0x07,
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
 
-  0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03,
+  0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03,  /* word */
   0xfe,0xff,0xff,0x87,0xfe,0xff,0xff,0x07,
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
 
-  0x00,0x00,0x00,0x00,0xfe,0xff,0xff,0xff,
+  0x00,0x00,0x00,0x00,0xfe,0xff,0xff,0xff,  /* graph */
   0xff,0xff,0xff,0xff,0xff,0xff,0xff,0x7f,
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
 
-  0x00,0x00,0x00,0x00,0xff,0xff,0xff,0xff,
+  0x00,0x00,0x00,0x00,0xff,0xff,0xff,0xff,  /* print */
   0xff,0xff,0xff,0xff,0xff,0xff,0xff,0x7f,
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
 
-  0x00,0x00,0x00,0x00,0xfe,0xff,0x00,0xfc,
+  0x00,0x00,0x00,0x00,0xfe,0xff,0x00,0xfc,  /* punct */
   0x01,0x00,0x00,0xf8,0x01,0x00,0x00,0x78,
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
 
-  0xff,0xff,0xff,0xff,0x00,0x00,0x00,0x00,
+  0xff,0xff,0xff,0xff,0x00,0x00,0x00,0x00,  /* cntrl */
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x80,
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,