Make back references to duplicated named subpatterns more like Perl.

git-svn-id: svn://vcs.exim.org/pcre/code/trunk@1361 2f5784b3-3f2a-0410-8824-cb99058d5e15

1 files changed, 52 insertions, 46 deletions

diff --git a/pcre_internal.h b/pcre_internal.h
index ec9fca6..fa3af98 100644
--- a/pcre_internal.h
+++ b/pcre_internal.h
@@ -2055,79 +2055,81 @@ enum {
                               class. This does both positive and negative. */
   OP_REF,            /* 109 Match a back reference, casefully */
   OP_REFI,           /* 110 Match a back reference, caselessly */
-  OP_RECURSE,        /* 111 Match a numbered subpattern (possibly recursive) */
-  OP_CALLOUT,        /* 112 Call out to external function if provided */
+  OP_DNREF,          /* 111 Match a duplicate name backref, casefully */ 
+  OP_DNREFI,         /* 112 Match a duplicate name backref, caselessly */ 
+  OP_RECURSE,        /* 113 Match a numbered subpattern (possibly recursive) */
+  OP_CALLOUT,        /* 114 Call out to external function if provided */
 
-  OP_ALT,            /* 113 Start of alternation */
-  OP_KET,            /* 114 End of group that doesn't have an unbounded repeat */
-  OP_KETRMAX,        /* 115 These two must remain together and in this */
-  OP_KETRMIN,        /* 116 order. They are for groups the repeat for ever. */
-  OP_KETRPOS,        /* 117 Possessive unlimited repeat. */
+  OP_ALT,            /* 115 Start of alternation */
+  OP_KET,            /* 116 End of group that doesn't have an unbounded repeat */
+  OP_KETRMAX,        /* 117 These two must remain together and in this */
+  OP_KETRMIN,        /* 118 order. They are for groups the repeat for ever. */
+  OP_KETRPOS,        /* 119 Possessive unlimited repeat. */
 
   /* The assertions must come before BRA, CBRA, ONCE, and COND, and the four
   asserts must remain in order. */
 
-  OP_REVERSE,        /* 118 Move pointer back - used in lookbehind assertions */
-  OP_ASSERT,         /* 119 Positive lookahead */
-  OP_ASSERT_NOT,     /* 120 Negative lookahead */
-  OP_ASSERTBACK,     /* 121 Positive lookbehind */
-  OP_ASSERTBACK_NOT, /* 122 Negative lookbehind */
+  OP_REVERSE,        /* 129 Move pointer back - used in lookbehind assertions */
+  OP_ASSERT,         /* 121 Positive lookahead */
+  OP_ASSERT_NOT,     /* 122 Negative lookahead */
+  OP_ASSERTBACK,     /* 123 Positive lookbehind */
+  OP_ASSERTBACK_NOT, /* 124 Negative lookbehind */
 
   /* ONCE, ONCE_NC, BRA, BRAPOS, CBRA, CBRAPOS, and COND must come immediately
   after the assertions, with ONCE first, as there's a test for >= ONCE for a
   subpattern that isn't an assertion. The POS versions must immediately follow
   the non-POS versions in each case. */
 
-  OP_ONCE,           /* 123 Atomic group, contains captures */
-  OP_ONCE_NC,        /* 124 Atomic group containing no captures */
-  OP_BRA,            /* 125 Start of non-capturing bracket */
-  OP_BRAPOS,         /* 126 Ditto, with unlimited, possessive repeat */
-  OP_CBRA,           /* 127 Start of capturing bracket */
-  OP_CBRAPOS,        /* 128 Ditto, with unlimited, possessive repeat */
-  OP_COND,           /* 129 Conditional group */
+  OP_ONCE,           /* 125 Atomic group, contains captures */
+  OP_ONCE_NC,        /* 126 Atomic group containing no captures */
+  OP_BRA,            /* 127 Start of non-capturing bracket */
+  OP_BRAPOS,         /* 128 Ditto, with unlimited, possessive repeat */
+  OP_CBRA,           /* 129 Start of capturing bracket */
+  OP_CBRAPOS,        /* 130 Ditto, with unlimited, possessive repeat */
+  OP_COND,           /* 131 Conditional group */
 
   /* These five must follow the previous five, in the same order. There's a
   check for >= SBRA to distinguish the two sets. */
 
-  OP_SBRA,           /* 130 Start of non-capturing bracket, check empty  */
-  OP_SBRAPOS,        /* 131 Ditto, with unlimited, possessive repeat */
-  OP_SCBRA,          /* 132 Start of capturing bracket, check empty */
-  OP_SCBRAPOS,       /* 133 Ditto, with unlimited, possessive repeat */
-  OP_SCOND,          /* 134 Conditional group, check empty */
+  OP_SBRA,           /* 132 Start of non-capturing bracket, check empty  */
+  OP_SBRAPOS,        /* 133 Ditto, with unlimited, possessive repeat */
+  OP_SCBRA,          /* 134 Start of capturing bracket, check empty */
+  OP_SCBRAPOS,       /* 135 Ditto, with unlimited, possessive repeat */
+  OP_SCOND,          /* 136 Conditional group, check empty */
 
   /* The next two pairs must (respectively) be kept together. */
 
-  OP_CREF,           /* 135 Used to hold a capture number as condition */
-  OP_NCREF,          /* 136 Same, but generated by a name reference*/
-  OP_RREF,           /* 137 Used to hold a recursion number as condition */
-  OP_NRREF,          /* 138 Same, but generated by a name reference*/
-  OP_DEF,            /* 139 The DEFINE condition */
+  OP_CREF,           /* 137 Used to hold a capture number as condition */
+  OP_NCREF,          /* 138 Same, but generated by a name reference*/
+  OP_RREF,           /* 139 Used to hold a recursion number as condition */
+  OP_NRREF,          /* 140 Same, but generated by a name reference*/
+  OP_DEF,            /* 141 The DEFINE condition */
 
-  OP_BRAZERO,        /* 140 These two must remain together and in this */
-  OP_BRAMINZERO,     /* 141 order. */
-  OP_BRAPOSZERO,     /* 142 */
+  OP_BRAZERO,        /* 142 These two must remain together and in this */
+  OP_BRAMINZERO,     /* 143 order. */
+  OP_BRAPOSZERO,     /* 144 */
 
   /* These are backtracking control verbs */
 
-  OP_MARK,           /* 143 always has an argument */
-  OP_PRUNE,          /* 144 */
-  OP_PRUNE_ARG,      /* 145 same, but with argument */
-  OP_SKIP,           /* 146 */
-  OP_SKIP_ARG,       /* 147 same, but with argument */
-  OP_THEN,           /* 148 */
-  OP_THEN_ARG,       /* 149 same, but with argument */
-  OP_COMMIT,         /* 150 */
+  OP_MARK,           /* 145 always has an argument */
+  OP_PRUNE,          /* 146 */
+  OP_PRUNE_ARG,      /* 147 same, but with argument */
+  OP_SKIP,           /* 148 */
+  OP_SKIP_ARG,       /* 149 same, but with argument */
+  OP_THEN,           /* 150 */
+  OP_THEN_ARG,       /* 151 same, but with argument */
+  OP_COMMIT,         /* 152 */
 
   /* These are forced failure and success verbs */
 
-  OP_FAIL,           /* 151 */
-  OP_ACCEPT,         /* 152 */
-  OP_ASSERT_ACCEPT,  /* 153 Used inside assertions */
-  OP_CLOSE,          /* 154 Used before OP_ACCEPT to close open captures */
+  OP_FAIL,           /* 153 */
+  OP_ACCEPT,         /* 154 */
+  OP_ASSERT_ACCEPT,  /* 155 Used inside assertions */
+  OP_CLOSE,          /* 156 Used before OP_ACCEPT to close open captures */
 
   /* This is used to skip a subpattern with a {0} quantifier */
 
-  OP_SKIPZERO,       /* 155 */
+  OP_SKIPZERO,       /* 157 */
 
   /* This is not an opcode, but is used to check that tables indexed by opcode
   are the correct length, in order to catch updating errors - there have been
@@ -2167,7 +2169,7 @@ some cases doesn't actually use these names at all). */
   "*", "*?", "+", "+?", "?", "??", "{", "{", "{",                 \
   "*+","++", "?+", "{",                                           \
   "*", "*?", "+", "+?", "?", "??", "{", "{",                      \
-  "class", "nclass", "xclass", "Ref", "Refi",                     \
+  "class", "nclass", "xclass", "Ref", "Refi", "DnRef", "DnRefi",  \
   "Recurse", "Callout",                                           \
   "Alt", "Ket", "KetRmax", "KetRmin", "KetRpos",                  \
   "Reverse", "Assert", "Assert not", "AssertB", "AssertB not",    \
@@ -2237,6 +2239,8 @@ in UTF-8 mode. The code that uses this table must know about such things. */
   0,                             /* XCLASS - variable length               */ \
   1+IMM2_SIZE,                   /* REF                                    */ \
   1+IMM2_SIZE,                   /* REFI                                   */ \
+  1+2*IMM2_SIZE,                 /* DNREF                                  */ \
+  1+2*IMM2_SIZE,                 /* DNREFI                                 */ \
   1+LINK_SIZE,                   /* RECURSE                                */ \
   2+2*LINK_SIZE,                 /* CALLOUT                                */ \
   1+LINK_SIZE,                   /* Alt                                    */ \
@@ -2441,6 +2445,7 @@ typedef struct compile_data {
   int  max_lookbehind;              /* Maximum lookbehind (characters) */
   int  top_backref;                 /* Maximum back reference */
   unsigned int backref_map;         /* Bitmap of low back refs */
+  unsigned int namedrefcount;       /* Number of backreferences by name */ 
   int  assert_depth;                /* Depth of nested assertions */
   pcre_uint32 external_options;     /* External (initial) options */
   pcre_uint32 external_flags;       /* External flag bits to be set */
@@ -2448,6 +2453,7 @@ typedef struct compile_data {
   BOOL had_accept;                  /* (*ACCEPT) encountered */
   BOOL had_pruneorskip;             /* (*PRUNE) or (*SKIP) encountered */
   BOOL check_lookbehind;            /* Lookbehinds need later checking */
+  BOOL dupnames;                    /* Duplicate names exist */
   int  nltype;                      /* Newline type */
   int  nllen;                       /* Newline string length */
   pcre_uchar nl[4];                 /* Newline string when fixed length */