Support \k{name} and \g{name} a la Perl 5.10.

git-svn-id: svn://vcs.exim.org/pcre/code/trunk@171 2f5784b3-3f2a-0410-8824-cb99058d5e15

5 files changed, 71 insertions, 14 deletions

diff --git a/ChangeLog b/ChangeLog
index a0a8d9c..46689b0 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -36,13 +36,18 @@ Version 7.2 01-May-07
     (d) \K resets the start of the current match so that everything before
         is not part of it.  
         
+    (e) \k{name} is synonymous with \k<name> and \k'name' (.NET compatible).
+    
+    (f) \g{name} is another synonym - part of Perl 5.10's unification of
+        reference syntax.  
+        
  7. Added two new calls to pcre_fullinfo(): PCRE_INFO_OKPARTIAL and 
     PCRE_INFO_JCHANGED. 
     
  8. A pattern such as  (.*(.)?)*  caused pcre_exec() to fail by either not 
     terminating or by crashing. Diagnosed by Viktor Griph; it was in the code 
     for detecting groups that can match an empty string.
-
+    
 
 Version 7.1 24-Apr-07
 ---------------------
diff --git a/doc/pcrepattern.3 b/doc/pcrepattern.3
index c19e364..4d8b943 100644
--- a/doc/pcrepattern.3
+++ b/doc/pcrepattern.3
@@ -241,8 +241,8 @@ meanings
 .rs
 .sp
 The sequence \eg followed by a positive or negative number, optionally enclosed
-in braces, is an absolute or relative back reference. Back references are
-discussed
+in braces, is an absolute or relative back reference. A named back reference 
+can be coded as \eg{name}. Back references are discussed
 .\" HTML <a href="#backreferences">
 .\" </a>
 later,
@@ -1325,12 +1325,17 @@ back reference, the case of letters is relevant. For example,
 matches "rah rah" and "RAH RAH", but not "RAH rah", even though the original
 capturing subpattern is matched caselessly.
 .P
-Back references to named subpatterns use the Perl syntax \ek<name> or \ek'name'
-or the Python syntax (?P=name). We could rewrite the above example in either of
+There are several different ways of writing back references to named
+subpatterns. The .NET syntax \ek{name} and the Perl syntax \ek<name> or
+\ek'name' are supported, as is the Python syntax (?P=name). Perl 5.10's unified
+back reference syntax, in which \eg can be used for both numeric and named
+references, is also supported. We could rewrite the above example in any of
 the following ways:
 .sp
   (?<p1>(?i)rah)\es+\ek<p1>
+  (?'p1'(?i)rah)\es+\ek{p1}
   (?P<p1>(?i)rah)\es+(?P=p1)
+  (?<p1>(?i)rah)\es+\eg{p1}
 .sp
 A subpattern that is referenced by name may appear in the pattern before or
 after the reference.
diff --git a/pcre_compile.c b/pcre_compile.c
index c930193..3fd5432 100644
--- a/pcre_compile.c
+++ b/pcre_compile.c
@@ -242,7 +242,7 @@ static const char *error_texts[] = {
   /* 55 */
   "repeating a DEFINE group is not allowed",
   "inconsistent NEWLINE options",
-  "\\g is not followed by an (optionally braced) non-zero number",
+  "\\g is not followed by a braced name or an optionally braced non-zero number",
   "(?+ or (?- or (?(+ or (?(- must be followed by a non-zero number" 
 };
 
@@ -453,11 +453,22 @@ else
 
     /* \g must be followed by a number, either plain or braced. If positive, it
     is an absolute backreference. If negative, it is a relative backreference.
-    This is a Perl 5.10 feature. */
+    This is a Perl 5.10 feature. Perl 5.10 also supports \g{name} as a 
+    reference to a named group. This is part of Perl's movement towards a 
+    unified syntax for back references. As this is synonymous with \k{name}, we 
+    fudge it up by pretending it really was \k. */
 
     case 'g':
     if (ptr[1] == '{')
       {
+      const uschar *p;
+      for (p = ptr+2; *p != 0 && *p != '}'; p++)
+        if (*p != '-' && (digitab[*p] & ctype_digit) == 0) break;
+      if (*p != 0 && *p != '}') 
+        {
+        c = -ESC_k;
+        break;
+        }  
       braced = TRUE;
       ptr++;
       }
@@ -4470,12 +4481,13 @@ for (;; ptr++)
       zerofirstbyte = firstbyte;
       zeroreqbyte = reqbyte;
 
-      /* \k<name> or \k'name' is a back reference by name (Perl syntax) */
+      /* \k<name> or \k'name' is a back reference by name (Perl syntax).
+      We also support \k{name} (.NET syntax) */
 
-      if (-c == ESC_k && (ptr[1] == '<' || ptr[1] == '\''))
+      if (-c == ESC_k && (ptr[1] == '<' || ptr[1] == '\'' || ptr[1] == '{'))
         {
         is_recurse = FALSE;
-        terminator = (*(++ptr) == '<')? '>' : '\'';
+        terminator = (*(++ptr) == '<')? '>' : (*ptr == '\'')? '\'' : '}';
         goto NAMED_REF_OR_RECURSE;
         }
 
diff --git a/testdata/testinput2 b/testdata/testinput2
index 1faa2a9..8e152bc 100644
--- a/testdata/testinput2
+++ b/testdata/testinput2
@@ -2203,4 +2203,16 @@ a random value. /Ix
 /(foo\Kbar)baz/
     foobarbaz
 
+/(?<A>tom|bon)-\k{A}/
+    tom-tom
+    bon-bon 
+    ** Failers
+    tom-bon  
+
+/(?<A>tom|bon)-\g{A}/
+    tom-tom
+    bon-bon 
+    
+/\g{A/ 
+
 / End of testinput2 /
diff --git a/testdata/testoutput2 b/testdata/testoutput2
index 8cda6a2..c6982e9 100644
--- a/testdata/testoutput2
+++ b/testdata/testoutput2
@@ -8067,16 +8067,16 @@ No match
 Failed: reference to non-existent subpattern at offset 4
 
 /^(a)\g/
-Failed: \g is not followed by an (optionally braced) non-zero number at offset 4
+Failed: \g is not followed by a braced name or an optionally braced non-zero number at offset 4
 
 /^(a)\g{0}/
-Failed: \g is not followed by an (optionally braced) non-zero number at offset 4
+Failed: \g is not followed by a braced name or an optionally braced non-zero number at offset 4
 
 /^(a)\g{3/
-Failed: \g is not followed by an (optionally braced) non-zero number at offset 4
+Failed: \g is not followed by a braced name or an optionally braced non-zero number at offset 4
 
 /^(a)\g{4a}/
-Failed: \g is not followed by an (optionally braced) non-zero number at offset 4
+Failed: reference to non-existent subpattern at offset 9
 
 /^a.b/<lf>
     a\rb
@@ -8334,4 +8334,27 @@ Failed: reference to non-existent subpattern at offset 7
  0: barbaz
  1: foobar
 
+/(?<A>tom|bon)-\k{A}/
+    tom-tom
+ 0: tom-tom
+ 1: tom
+    bon-bon 
+ 0: bon-bon
+ 1: bon
+    ** Failers
+No match
+    tom-bon  
+No match
+
+/(?<A>tom|bon)-\g{A}/
+    tom-tom
+ 0: tom-tom
+ 1: tom
+    bon-bon 
+ 0: bon-bon
+ 1: bon
+    
+/\g{A/ 
+Failed: syntax error in subpattern name (missing terminator) at offset 4
+
 / End of testinput2 /