Merge branch 'PHP-7.4'

* PHP-7.4:
  Upgrade bundled PCRE2 to 10.33

Author: weltling

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", "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 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

@@ -65,7 +65,7 @@ else
   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_extuni.c"
+  pcre2lib/pcre2_find_bracket.c pcre2lib/pcre2_convert.c pcre2lib/pcre2_extuni.c pcre2lib/pcre2_script_run.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

@@ -42,15 +42,9 @@ POSSIBILITY OF SUCH DAMAGE.
 /* The current PCRE version information. */
 
 #define PCRE2_MAJOR           10
-#define PCRE2_MINOR           32
+#define PCRE2_MINOR           33
 #define PCRE2_PRERELEASE      
-#define PCRE2_DATE            2018-09-10
-
-/* For the benefit of systems without stdint.h, an alternative is to use
-inttypes.h. The existence of these headers is checked by configure or CMake. */
-
-#define PCRE2_HAVE_STDINT_H   1
-#define PCRE2_HAVE_INTTYPES_H 1
+#define PCRE2_DATE            2019-04-16
 
 /* 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
@@ -87,18 +81,15 @@ set, we ensure here that it has no effect. */
 #define PCRE2_CALL_CONVENTION
 #endif
 
-/* Have to include limits.h, stdlib.h and stdint.h (or inttypes.h) to ensure
-that size_t and uint8_t, UCHAR_MAX, etc are defined. If the system has neither
-header, the relevant values must be provided by some other means. */
+/* Have to include limits.h, stdlib.h, and inttypes.h to ensure that size_t and
+uint8_t, UCHAR_MAX, etc are defined. Some systems that do have inttypes.h do
+not have stdint.h, which is why we use inttypes.h, which according to the C
+standard is a superset of stdint.h. If none of these headers are available,
+the relevant values must be provided by some other means. */
 
 #include <limits.h>
 #include <stdlib.h>
-
-#if PCRE2_HAVE_STDINT_H
-#include <stdint.h>
-#elif PCRE2_HAVE_INTTYPES_H
 #include <inttypes.h>
-#endif
 
 /* Allow for C++ users compiling this directly. */
 
@@ -158,43 +149,37 @@ D   is inspected during pcre2_dfa_match() execution
 #define PCRE2_EXTRA_BAD_ESCAPE_IS_LITERAL    0x00000002u  /* C */
 #define PCRE2_EXTRA_MATCH_WORD               0x00000004u  /* C */
 #define PCRE2_EXTRA_MATCH_LINE               0x00000008u  /* C */
+#define PCRE2_EXTRA_ESCAPED_CR_IS_LF         0x00000010u  /* C */
+#define PCRE2_EXTRA_ALT_BSUX                 0x00000020u  /* C */
 
 /* These are for pcre2_jit_compile(). */
 
 #define PCRE2_JIT_COMPLETE        0x00000001u  /* For full matching */
 #define PCRE2_JIT_PARTIAL_SOFT    0x00000002u
 #define PCRE2_JIT_PARTIAL_HARD    0x00000004u
-
-/* These are for pcre2_match(), pcre2_dfa_match(), and pcre2_jit_match(). Note
-that PCRE2_ANCHORED and PCRE2_NO_UTF_CHECK can also be passed to these
-functions (though pcre2_jit_match() ignores the latter since it bypasses all
-sanity checks). */
-
-#define PCRE2_NOTBOL              0x00000001u
-#define PCRE2_NOTEOL              0x00000002u
-#define PCRE2_NOTEMPTY            0x00000004u  /* ) These two must be kept */
-#define PCRE2_NOTEMPTY_ATSTART    0x00000008u  /* ) adjacent to each other. */
-#define PCRE2_PARTIAL_SOFT        0x00000010u
-#define PCRE2_PARTIAL_HARD        0x00000020u
-
-/* These are additional options for pcre2_dfa_match(). */
-
-#define PCRE2_DFA_RESTART         0x00000040u
-#define PCRE2_DFA_SHORTEST        0x00000080u
-
-/* These are additional options for pcre2_substitute(), which passes any others
-through to pcre2_match(). */
-
-#define PCRE2_SUBSTITUTE_GLOBAL           0x00000100u
-#define PCRE2_SUBSTITUTE_EXTENDED         0x00000200u
-#define PCRE2_SUBSTITUTE_UNSET_EMPTY      0x00000400u
-#define PCRE2_SUBSTITUTE_UNKNOWN_UNSET    0x00000800u
-#define PCRE2_SUBSTITUTE_OVERFLOW_LENGTH  0x00001000u
-
-/* A further option for pcre2_match(), not allowed for pcre2_dfa_match(),
-ignored for pcre2_jit_match(). */
-
-#define PCRE2_NO_JIT              0x00002000u
+#define PCRE2_JIT_INVALID_UTF     0x00000100u
+
+/* These are for pcre2_match(), pcre2_dfa_match(), pcre2_jit_match(), and
+pcre2_substitute(). Some are allowed only for one of the functions, and in
+these cases it is noted below. Note that PCRE2_ANCHORED, PCRE2_ENDANCHORED and
+PCRE2_NO_UTF_CHECK can also be passed to these functions (though
+pcre2_jit_match() ignores the latter since it bypasses all sanity checks). */
+
+#define PCRE2_NOTBOL                      0x00000001u
+#define PCRE2_NOTEOL                      0x00000002u
+#define PCRE2_NOTEMPTY                    0x00000004u  /* ) These two must be kept */
+#define PCRE2_NOTEMPTY_ATSTART            0x00000008u  /* ) adjacent to each other. */
+#define PCRE2_PARTIAL_SOFT                0x00000010u
+#define PCRE2_PARTIAL_HARD                0x00000020u
+#define PCRE2_DFA_RESTART                 0x00000040u  /* pcre2_dfa_match() only */
+#define PCRE2_DFA_SHORTEST                0x00000080u  /* pcre2_dfa_match() only */
+#define PCRE2_SUBSTITUTE_GLOBAL           0x00000100u  /* pcre2_substitute() only */
+#define PCRE2_SUBSTITUTE_EXTENDED         0x00000200u  /* pcre2_substitute() only */
+#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_COPY_MATCHED_SUBJECT        0x00004000u
 
 /* Options for pcre2_pattern_convert(). */
 
@@ -318,6 +303,8 @@ pcre2_pattern_convert(). */
 #define PCRE2_ERROR_BAD_LITERAL_OPTIONS            192
 #define PCRE2_ERROR_SUPPORTED_ONLY_IN_UNICODE      193
 #define PCRE2_ERROR_INVALID_HYPHEN_IN_OPTIONS      194
+#define PCRE2_ERROR_ALPHA_ASSERTION_UNKNOWN        195
+#define PCRE2_ERROR_SCRIPT_RUN_NOT_AVAILABLE       196
 
 
 /* "Expected" matching error codes: no match and partial match. */
@@ -504,10 +491,10 @@ typedef struct pcre2_real_jit_stack pcre2_jit_stack; \
 typedef pcre2_jit_stack *(*pcre2_jit_callback)(void *);
 
 
-/* The structure for passing out data via the pcre_callout_function. We use a
-structure so that new fields can be added on the end in future versions,
-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
+/* The structures for passing out data via callout functions. We use structures
+so that new fields can be added on the end in future versions, without changing
+the API of the function, thereby allowing old clients to work without
+modification. Define the generic versions 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. */
@@ -549,7 +536,19 @@ typedef struct pcre2_callout_enumerate_block { \
   PCRE2_SIZE    callout_string_length; /* Length of string compiled into pattern */ \
   PCRE2_SPTR    callout_string;    /* String compiled into pattern */ \
   /* ------------------------------------------------------------------ */ \
-} pcre2_callout_enumerate_block;
+} pcre2_callout_enumerate_block; \
+\
+typedef struct pcre2_substitute_callout_block { \
+  uint32_t      version;           /* Identifies version of block */ \
+  /* ------------------------ Version 0 ------------------------------- */ \
+  PCRE2_SPTR    input;             /* Pointer to input subject string */ \
+  PCRE2_SPTR    output;            /* Pointer to output buffer */ \
+  PCRE2_SIZE    output_offsets[2]; /* Changed portion of the output */ \
+  PCRE2_SIZE   *ovector;           /* Pointer to current ovector */ \
+  uint32_t      oveccount;         /* Count of pairs set in ovector */ \
+  uint32_t      subscount;         /* Substitution number */ \
+  /* ------------------------------------------------------------------ */ \
+} pcre2_substitute_callout_block;
 
 
 /* List the generic forms of all other functions in macros, which will be
@@ -604,6 +603,9 @@ PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
 PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
   pcre2_set_callout(pcre2_match_context *, \
     int (*)(pcre2_callout_block *, void *), void *); \
+PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
+  pcre2_set_substitute_callout(pcre2_match_context *, \
+    int (*)(pcre2_substitute_callout_block *, void *), void *); \
 PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
   pcre2_set_depth_limit(pcre2_match_context *, uint32_t); \
 PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
@@ -807,6 +809,7 @@ pcre2_compile are called by application code. */
 
 #define pcre2_callout_block            PCRE2_SUFFIX(pcre2_callout_block_)
 #define pcre2_callout_enumerate_block  PCRE2_SUFFIX(pcre2_callout_enumerate_block_)
+#define pcre2_substitute_callout_block PCRE2_SUFFIX(pcre2_substitute_callout_block_)
 #define pcre2_general_context          PCRE2_SUFFIX(pcre2_general_context_)
 #define pcre2_compile_context          PCRE2_SUFFIX(pcre2_compile_context_)
 #define pcre2_convert_context          PCRE2_SUFFIX(pcre2_convert_context_)
@@ -872,6 +875,7 @@ pcre2_compile are called by application code. */
 #define pcre2_set_newline                     PCRE2_SUFFIX(pcre2_set_newline_)
 #define pcre2_set_parens_nest_limit           PCRE2_SUFFIX(pcre2_set_parens_nest_limit_)
 #define pcre2_set_offset_limit                PCRE2_SUFFIX(pcre2_set_offset_limit_)
+#define pcre2_set_substitute_callout          PCRE2_SUFFIX(pcre2_set_substitute_callout_)
 #define pcre2_substitute                      PCRE2_SUFFIX(pcre2_substitute_)
 #define pcre2_substring_copy_byname           PCRE2_SUFFIX(pcre2_substring_copy_byname_)
 #define pcre2_substring_copy_bynumber         PCRE2_SUFFIX(pcre2_substring_copy_bynumber_)

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) 2016-2018 University of Cambridge
+          New API code Copyright (c) 2016-2019 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without
@@ -605,6 +605,15 @@ for(;;)
       if (cb->had_recurse) return FALSE;
       break;
 
+      /* A script run might have to backtrack if the iterated item can match
+      characters from more than one script. So give up unless repeating an
+      explicit character. */
+
+      case OP_SCRIPT_RUN:
+      if (base_list[0] != OP_CHAR && base_list[0] != OP_CHARI)
+        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. */
@@ -614,7 +623,6 @@ for(;;)
       case OP_ASSERTBACK:
       case OP_ASSERTBACK_NOT:
       case OP_ONCE:
-
       return !entered_a_group;
       }
 
@@ -1043,7 +1051,7 @@ for(;;)
       if (chr > 255) break;
       class_bitset = (uint8_t *)
         ((list_ptr == list ? code : base_end) - list_ptr[2]);
-      if ((class_bitset[chr >> 3] & (1 << (chr & 7))) != 0) return FALSE;
+      if ((class_bitset[chr >> 3] & (1u << (chr & 7))) != 0) return FALSE;
       break;
 
 #ifdef SUPPORT_WIDE_CHARS

ext/pcre/pcre2lib/pcre2_chartables.c

@@ -7,7 +7,14 @@ 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 dftables 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. */
+
+/* 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
 library and dead code stripping is activated. This leads to link errors.
 Pulling in the header ensures that the array gets flagged as "someone
@@ -92,11 +99,10 @@ 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,
@@ -151,28 +157,27 @@ print, punct, and cntrl. Other classes are built from combinations. */
 /* This table identifies various classes of character by individual bits:
   0x01   white space character
   0x02   letter
-  0x04   decimal digit
-  0x08   hexadecimal digit
+  0x04   lower case letter
+  0x08   decimal digit
   0x10   alphanumeric or '_'
-  0x80   regular expression metacharacter or binary zero
 */
 
-  0x80,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*   0-  7 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*   0-  7 */
   0x00,0x01,0x01,0x01,0x01,0x01,0x00,0x00, /*   8- 15 */
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  16- 23 */
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  24- 31 */
-  0x01,0x00,0x00,0x00,0x80,0x00,0x00,0x00, /*    - '  */
-  0x80,0x80,0x80,0x80,0x00,0x00,0x80,0x00, /*  ( - /  */
-  0x1c,0x1c,0x1c,0x1c,0x1c,0x1c,0x1c,0x1c, /*  0 - 7  */
-  0x1c,0x1c,0x00,0x00,0x00,0x00,0x00,0x80, /*  8 - ?  */
-  0x00,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /*  @ - G  */
+  0x01,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*    - '  */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  ( - /  */
+  0x18,0x18,0x18,0x18,0x18,0x18,0x18,0x18, /*  0 - 7  */
+  0x18,0x18,0x00,0x00,0x00,0x00,0x00,0x00, /*  8 - ?  */
+  0x00,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /*  @ - G  */
   0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /*  H - O  */
   0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /*  P - W  */
-  0x12,0x12,0x12,0x80,0x80,0x00,0x80,0x10, /*  X - _  */
-  0x00,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /*  ` - g  */
-  0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /*  h - o  */
-  0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /*  p - w  */
-  0x12,0x12,0x12,0x80,0x80,0x00,0x00,0x00, /*  x -127 */
+  0x12,0x12,0x12,0x00,0x00,0x00,0x00,0x10, /*  X - _  */
+  0x00,0x16,0x16,0x16,0x16,0x16,0x16,0x16, /*  ` - g  */
+  0x16,0x16,0x16,0x16,0x16,0x16,0x16,0x16, /*  h - o  */
+  0x16,0x16,0x16,0x16,0x16,0x16,0x16,0x16, /*  p - w  */
+  0x16,0x16,0x16,0x00,0x00,0x00,0x00,0x00, /*  x -127 */
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 128-135 */
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 136-143 */
   0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 144-151 */