Upgrade bundled PCRE2 to 10.31

Author: weltling

ext/pcre/config.w32

@@ -3,7 +3,7 @@
 
 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 ", "pcre");
+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", "pcre");
 ADD_DEF_FILE("ext\\pcre\\php_pcre.def");
 
 AC_DEFINE('HAVE_BUNDLED_PCRE', 1, 'Using bundled PCRE library');

ext/pcre/config0.m4

@@ -68,7 +68,7 @@ PHP_ARG_WITH(pcre-jit,,[  --with-pcre-jit         Enable PCRE JIT functionality
 	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 \
 	pcre2lib/pcre2_tables.c pcre2lib/pcre2_ucd.c pcre2lib/pcre2_valid_utf.c pcre2lib/pcre2_xclass.c \
-	pcre2lib/pcre2_find_bracket.c pcre2lib/pcre2_convert.c"
+	pcre2lib/pcre2_find_bracket.c pcre2lib/pcre2_convert.c pcre2lib/pcre2_extuni.c"
     PHP_PCRE_CFLAGS="-DHAVE_CONFIG_H -I@ext_srcdir@/pcre2lib -DZEND_ENABLE_STATIC_TSRMLS_CACHE=1"
     PHP_NEW_EXTENSION(pcre, $pcrelib_sources php_pcre.c, no,,$PHP_PCRE_CFLAGS)
     PHP_ADD_BUILD_DIR($ext_builddir/pcre2lib)

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          30
-#define PCRE2_PRERELEASE
-#define PCRE2_DATE           2017-08-14
+#define PCRE2_MINOR          31
+#define PCRE2_PRERELEASE     
+#define PCRE2_DATE           2018-02-12
 
 /* 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
@@ -208,7 +208,104 @@ greater than zero. */
 #define PCRE2_BSR_UNICODE         1
 #define PCRE2_BSR_ANYCRLF         2
 
-/* Error codes: no match and partial match are "expected" errors. */
+/* Error codes for pcre2_compile(). Some of these are also used by
+pcre2_pattern_convert(). */
+
+#define PCRE2_ERROR_END_BACKSLASH                  101
+#define PCRE2_ERROR_END_BACKSLASH_C                102
+#define PCRE2_ERROR_UNKNOWN_ESCAPE                 103
+#define PCRE2_ERROR_QUANTIFIER_OUT_OF_ORDER        104
+#define PCRE2_ERROR_QUANTIFIER_TOO_BIG             105
+#define PCRE2_ERROR_MISSING_SQUARE_BRACKET         106
+#define PCRE2_ERROR_ESCAPE_INVALID_IN_CLASS        107
+#define PCRE2_ERROR_CLASS_RANGE_ORDER              108
+#define PCRE2_ERROR_QUANTIFIER_INVALID             109
+#define PCRE2_ERROR_INTERNAL_UNEXPECTED_REPEAT     110
+#define PCRE2_ERROR_INVALID_AFTER_PARENS_QUERY     111
+#define PCRE2_ERROR_POSIX_CLASS_NOT_IN_CLASS       112
+#define PCRE2_ERROR_POSIX_NO_SUPPORT_COLLATING     113
+#define PCRE2_ERROR_MISSING_CLOSING_PARENTHESIS    114
+#define PCRE2_ERROR_BAD_SUBPATTERN_REFERENCE       115
+#define PCRE2_ERROR_NULL_PATTERN                   116
+#define PCRE2_ERROR_BAD_OPTIONS                    117
+#define PCRE2_ERROR_MISSING_COMMENT_CLOSING        118
+#define PCRE2_ERROR_PARENTHESES_NEST_TOO_DEEP      119
+#define PCRE2_ERROR_PATTERN_TOO_LARGE              120
+#define PCRE2_ERROR_HEAP_FAILED                    121
+#define PCRE2_ERROR_UNMATCHED_CLOSING_PARENTHESIS  122
+#define PCRE2_ERROR_INTERNAL_CODE_OVERFLOW         123
+#define PCRE2_ERROR_MISSING_CONDITION_CLOSING      124
+#define PCRE2_ERROR_LOOKBEHIND_NOT_FIXED_LENGTH    125
+#define PCRE2_ERROR_ZERO_RELATIVE_REFERENCE        126
+#define PCRE2_ERROR_TOO_MANY_CONDITION_BRANCHES    127
+#define PCRE2_ERROR_CONDITION_ASSERTION_EXPECTED   128
+#define PCRE2_ERROR_BAD_RELATIVE_REFERENCE         129
+#define PCRE2_ERROR_UNKNOWN_POSIX_CLASS            130
+#define PCRE2_ERROR_INTERNAL_STUDY_ERROR           131
+#define PCRE2_ERROR_UNICODE_NOT_SUPPORTED          132
+#define PCRE2_ERROR_PARENTHESES_STACK_CHECK        133
+#define PCRE2_ERROR_CODE_POINT_TOO_BIG             134
+#define PCRE2_ERROR_LOOKBEHIND_TOO_COMPLICATED     135
+#define PCRE2_ERROR_LOOKBEHIND_INVALID_BACKSLASH_C 136
+#define PCRE2_ERROR_UNSUPPORTED_ESCAPE_SEQUENCE    137
+#define PCRE2_ERROR_CALLOUT_NUMBER_TOO_BIG         138
+#define PCRE2_ERROR_MISSING_CALLOUT_CLOSING        139
+#define PCRE2_ERROR_ESCAPE_INVALID_IN_VERB         140
+#define PCRE2_ERROR_UNRECOGNIZED_AFTER_QUERY_P     141
+#define PCRE2_ERROR_MISSING_NAME_TERMINATOR        142
+#define PCRE2_ERROR_DUPLICATE_SUBPATTERN_NAME      143
+#define PCRE2_ERROR_INVALID_SUBPATTERN_NAME        144
+#define PCRE2_ERROR_UNICODE_PROPERTIES_UNAVAILABLE 145
+#define PCRE2_ERROR_MALFORMED_UNICODE_PROPERTY     146
+#define PCRE2_ERROR_UNKNOWN_UNICODE_PROPERTY       147
+#define PCRE2_ERROR_SUBPATTERN_NAME_TOO_LONG       148
+#define PCRE2_ERROR_TOO_MANY_NAMED_SUBPATTERNS     149
+#define PCRE2_ERROR_CLASS_INVALID_RANGE            150
+#define PCRE2_ERROR_OCTAL_BYTE_TOO_BIG             151
+#define PCRE2_ERROR_INTERNAL_OVERRAN_WORKSPACE     152
+#define PCRE2_ERROR_INTERNAL_MISSING_SUBPATTERN    153
+#define PCRE2_ERROR_DEFINE_TOO_MANY_BRANCHES       154
+#define PCRE2_ERROR_BACKSLASH_O_MISSING_BRACE      155
+#define PCRE2_ERROR_INTERNAL_UNKNOWN_NEWLINE       156
+#define PCRE2_ERROR_BACKSLASH_G_SYNTAX             157
+#define PCRE2_ERROR_PARENS_QUERY_R_MISSING_CLOSING 158
+#define PCRE2_ERROR_VERB_ARGUMENT_NOT_ALLOWED      159
+#define PCRE2_ERROR_VERB_UNKNOWN                   160
+#define PCRE2_ERROR_SUBPATTERN_NUMBER_TOO_BIG      161
+#define PCRE2_ERROR_SUBPATTERN_NAME_EXPECTED       162
+#define PCRE2_ERROR_INTERNAL_PARSED_OVERFLOW       163
+#define PCRE2_ERROR_INVALID_OCTAL                  164
+#define PCRE2_ERROR_SUBPATTERN_NAMES_MISMATCH      165
+#define PCRE2_ERROR_MARK_MISSING_ARGUMENT          166
+#define PCRE2_ERROR_INVALID_HEXADECIMAL            167
+#define PCRE2_ERROR_BACKSLASH_C_SYNTAX             168
+#define PCRE2_ERROR_BACKSLASH_K_SYNTAX             169
+#define PCRE2_ERROR_INTERNAL_BAD_CODE_LOOKBEHINDS  170
+#define PCRE2_ERROR_BACKSLASH_N_IN_CLASS           171
+#define PCRE2_ERROR_CALLOUT_STRING_TOO_LONG        172
+#define PCRE2_ERROR_UNICODE_DISALLOWED_CODE_POINT  173
+#define PCRE2_ERROR_UTF_IS_DISABLED                174
+#define PCRE2_ERROR_UCP_IS_DISABLED                175
+#define PCRE2_ERROR_VERB_NAME_TOO_LONG             176
+#define PCRE2_ERROR_BACKSLASH_U_CODE_POINT_TOO_BIG 177
+#define PCRE2_ERROR_MISSING_OCTAL_OR_HEX_DIGITS    178
+#define PCRE2_ERROR_VERSION_CONDITION_SYNTAX       179
+#define PCRE2_ERROR_INTERNAL_BAD_CODE_AUTO_POSSESS 180
+#define PCRE2_ERROR_CALLOUT_NO_STRING_DELIMITER    181
+#define PCRE2_ERROR_CALLOUT_BAD_STRING_DELIMITER   182
+#define PCRE2_ERROR_BACKSLASH_C_CALLER_DISABLED    183
+#define PCRE2_ERROR_QUERY_BARJX_NEST_TOO_DEEP      184
+#define PCRE2_ERROR_BACKSLASH_C_LIBRARY_DISABLED   185
+#define PCRE2_ERROR_PATTERN_TOO_COMPLICATED        186
+#define PCRE2_ERROR_LOOKBEHIND_TOO_LONG            187
+#define PCRE2_ERROR_PATTERN_STRING_TOO_LONG        188
+#define PCRE2_ERROR_INTERNAL_BAD_CODE              189
+#define PCRE2_ERROR_INTERNAL_BAD_CODE_IN_SKIP      190
+#define PCRE2_ERROR_NO_SURROGATES_IN_UTF16         191
+#define PCRE2_ERROR_BAD_LITERAL_OPTIONS            192
+
+
+/* "Expected" matching error codes: no match and partial match. */
 
 #define PCRE2_ERROR_NOMATCH          (-1)
 #define PCRE2_ERROR_PARTIAL          (-2)
@@ -248,10 +345,10 @@ greater than zero. */
 #define PCRE2_ERROR_UTF32_ERR1      (-27)
 #define PCRE2_ERROR_UTF32_ERR2      (-28)
 
-/* Error codes for pcre2[_dfa]_match(), substring extraction functions, context
-functions, and serializing functions. They are in numerical order. Originally
-they were in alphabetical order too, but now that PCRE2 is released, the
-numbers must not be changed. */
+/* Miscellaneous error codes for pcre2[_dfa]_match(), substring extraction
+functions, context functions, and serializing functions. They are in numerical
+order. Originally they were in alphabetical order too, but now that PCRE2 is
+released, the numbers must not be changed. */
 
 #define PCRE2_ERROR_BADDATA           (-29)
 #define PCRE2_ERROR_MIXEDTABLES       (-30)  /* Name was changed */
@@ -321,6 +418,7 @@ numbers must not be changed. */
 #define PCRE2_INFO_HASBACKSLASHC        23
 #define PCRE2_INFO_FRAMESIZE            24
 #define PCRE2_INFO_HEAPLIMIT            25
+#define PCRE2_INFO_EXTRAOPTIONS         26
 
 /* Request types for pcre2_config(). */
 
@@ -338,6 +436,9 @@ numbers must not be changed. */
 #define PCRE2_CONFIG_UNICODE_VERSION        10
 #define PCRE2_CONFIG_VERSION                11
 #define PCRE2_CONFIG_HEAPLIMIT              12
+#define PCRE2_CONFIG_NEVER_BACKSLASH_C      13
+#define PCRE2_CONFIG_COMPILED_WIDTHS        14
+
 
 /* Types for code units in patterns and subject strings. */
 
@@ -393,6 +494,11 @@ without changing the API of the function, thereby allowing old clients to work
 without modification. Define the generic version in a macro; the width-specific
 versions are generated from this macro below. */
 
+/* Flags for the callout_flags field. These are cleared after a callout. */
+
+#define PCRE2_CALLOUT_STARTMATCH    0x00000001u  /* Set for each bumpalong */
+#define PCRE2_CALLOUT_BACKTRACK     0x00000002u  /* Set after a backtrack */
+
 #define PCRE2_STRUCTURE_LIST \
 typedef struct pcre2_callout_block { \
   uint32_t      version;           /* Identifies version of block */ \
@@ -412,6 +518,8 @@ typedef struct pcre2_callout_block { \
   PCRE2_SIZE    callout_string_offset; /* Offset to string within pattern */ \
   PCRE2_SIZE    callout_string_length; /* Length of string compiled into pattern */ \
   PCRE2_SPTR    callout_string;    /* String compiled into pattern */ \
+  /* ------------------- Added for Version 2 -------------------------- */ \
+  uint32_t      callout_flags;     /* See above for list */ \
   /* ------------------------------------------------------------------ */ \
 } pcre2_callout_block; \
 \

ext/pcre/pcre2lib/pcre2_auto_possess.c

@@ -558,47 +558,73 @@ for(;;)
     continue;
     }
 
+  /* At the end of a branch, skip to the end of the group. */
+
   if (c == OP_ALT)
     {
     do code += GET(code, 1); while (*code == OP_ALT);
     c = *code;
     }
 
+  /* Inspect the next opcode. */
+
   switch(c)
     {
-    case OP_END:
-    case OP_KETRPOS:
-    /* TRUE only in greedy case. The non-greedy case could be replaced by
-    an OP_EXACT, but it is probably not worth it. (And note that OP_EXACT
-    uses more memory, which we cannot get at this stage.) */
+    /* We can always possessify a greedy iterator at the end of the pattern,
+    which is reached after skipping over the final OP_KET. A non-greedy
+    iterator must never be possessified. */
 
+    case OP_END:
     return base_list[1] != 0;
 
+    /* When an iterator is at the end of certain kinds of group we can inspect
+    what follows the group by skipping over the closing ket. Note that this
+    does not apply to OP_KETRMAX or OP_KETRMIN because what follows any given
+    iteration is variable (could be another iteration or could be the next
+    item). As these two opcodes are not listed in the next switch, they will
+    end up as the next code to inspect, and return FALSE by virtue of being
+    unsupported. */
+
     case OP_KET:
-    /* If the bracket is capturing, and referenced by an OP_RECURSE, or
-    it is an atomic sub-pattern (assert, once, etc.) the non-greedy case
-    cannot be converted to a possessive form. */
+    case OP_KETRPOS:
+    /* The non-greedy case cannot be converted to a possessive form. */
 
     if (base_list[1] == 0) return FALSE;
 
+    /* If the bracket is capturing it might be referenced by an OP_RECURSE
+    so its last iterator can never be possessified if the pattern contains
+    recursions. (This could be improved by keeping a list of group numbers that
+    are called by recursion.) */
+
     switch(*(code - GET(code, 1)))
       {
+      case OP_CBRA:
+      case OP_SCBRA:
+      case OP_CBRAPOS:
+      case OP_SCBRAPOS:
+      if (cb->had_recurse) return FALSE;
+      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. */
+
       case OP_ASSERT:
       case OP_ASSERT_NOT:
       case OP_ASSERTBACK:
       case OP_ASSERTBACK_NOT:
       case OP_ONCE:
 
-      /* 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. */
-
       return !entered_a_group;
       }
 
+    /* Skip over the bracket and inspect what comes next. */
+
     code += PRIV(OP_lengths)[c];
     continue;
 
+    /* Handle cases where the next item is a group. */
+
     case OP_ONCE:
     case OP_BRA:
     case OP_CBRA:
@@ -637,11 +663,15 @@ for(;;)
     code += PRIV(OP_lengths)[c];
     continue;
 
+    /* The next opcode does not need special handling; fall through and use it
+    to see if the base can be possessified. */
+
     default:
     break;
     }
 
-  /* Check for a supported opcode, and load its properties. */
+  /* 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);
   if (code == NULL) return FALSE;    /* Unsupported */

ext/pcre/pcre2lib/pcre2_chartables.c

@@ -2,23 +2,17 @@
 *      Perl-Compatible Regular Expressions       *
 *************************************************/
 
-/* This file 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.
-
-This is a default version of the tables that assumes ASCII encoding. A program
-called dftables (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. If PCRE2 is configured with --enable-rebuild-chartables, this
-happens automatically.
-
-The following #includes are present because without them gcc 4.x may remove the
-array definition from the final binary if PCRE2 is built into a static library
-and dead code stripping is activated. This leads to link errors. Pulling in the
-header ensures that the array gets flagged as "someone outside this compilation
-unit might reference this" and so it will always be supplied to the linker. */
+/* This file was automatically written by the 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 following #includes are present because without them gcc 4.x may remove
+the array definition from the final binary if PCRE2 is built into a static
+library and dead code stripping is activated. This leads to link errors.
+Pulling in the header ensures that the array gets flagged as "someone
+outside this compilation unit might reference this" and so it will always
+be supplied to the linker. */
 
 #ifdef HAVE_CONFIG_H
 #include "config.h"
@@ -98,10 +92,11 @@ const uint8_t PRIV(default_tables)[] = {
   240,241,242,243,244,245,246,247,
   248,249,250,251,252,253,254,255,
 
-/* 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. */
+/* 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. */
 
   0x00,0x3e,0x00,0x00,0x01,0x00,0x00,0x00,
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,