Allow callout before assertion condition in a conditional group.

git-svn-id: svn://vcs.exim.org/pcre/code/trunk@1266 2f5784b3-3f2a-0410-8824-cb99058d5e15

6 files changed, 87 insertions, 19 deletions

diff --git a/ChangeLog b/ChangeLog
index 9ab8fd8..d935b5f 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -89,6 +89,10 @@ Version 8.33 xx-xxxx-201x
     there was a conditional group that depended on an assertion, if the 
     assertion was false, the callout that immediately followed the alternation 
     in the condition was skipped when pcre_exec() was used for matching.
+    
+23. Allow an explicit callout to be inserted before an assertion that is the
+    condition for a conditional group, for compatibility with automatic 
+    callouts, which always insert a callout at this point.
 
 
 Version 8.32 30-November-2012
diff --git a/doc/pcrecallout.3 b/doc/pcrecallout.3
index 946035d..19baf23 100644
--- a/doc/pcrecallout.3
+++ b/doc/pcrecallout.3
@@ -1,4 +1,4 @@
-.TH PCRECALLOUT 3 "13 January 2013" "PCRE 8.33"
+.TH PCRECALLOUT 3 "03 March 2013" "PCRE 8.33"
 .SH NAME
 PCRE - Perl-compatible regular expressions
 .SH SYNOPSIS
@@ -41,8 +41,17 @@ it is processed as if it were
 (?C255)A(?C255)((?C255)\ed{2}(?C255)|(?C255)-(?C255)-(?C255))(?C255)
 .sp
 Notice that there is a callout before and after each parenthesis and
-alternation bar. Automatic callouts can be used for tracking the progress of
-pattern matching. The
+alternation bar. If the pattern contains a conditional group whose condition is 
+an assertion, an automatic callout is inserted immediately before the 
+condition. Such a callout may also be inserted explicitly, for example:
+.sp
+  (?(?C9)(?=a)ab|de)
+.sp
+This applies only to assertion conditions (because they are themselves 
+independent groups).   
+.P
+Automatic callouts can be used for tracking the progress of pattern matching.
+The
 .\" HREF
 \fBpcretest\fP
 .\"
@@ -115,10 +124,10 @@ automatically generated callouts).
 .P
 The \fIoffset_vector\fP field is a pointer to the vector of offsets that was
 passed by the caller to the matching function. When \fBpcre_exec()\fP or
-\fBpcre[16|32]_exec()\fP is used, the contents can be inspected, in order to extract
-substrings that have been matched so far, in the same way as for extracting
-substrings after a match has completed. For the DFA matching functions, this
-field is not useful.
+\fBpcre[16|32]_exec()\fP is used, the contents can be inspected, in order to
+extract substrings that have been matched so far, in the same way as for
+extracting substrings after a match has completed. For the DFA matching
+functions, this field is not useful.
 .P
 The \fIsubject\fP and \fIsubject_length\fP fields contain copies of the values
 that were passed to the matching function.
@@ -171,11 +180,12 @@ help in distinguishing between different automatic callouts, which all have the
 same callout number. However, they are set for all callouts.
 .P
 The \fImark\fP field is present from version 2 of the callout structure. In
-callouts from \fBpcre_exec()\fP or \fBpcre[16|32]_exec()\fP it contains a pointer to
-the zero-terminated name of the most recently passed (*MARK), (*PRUNE), or
-(*THEN) item in the match, or NULL if no such items have been passed. Instances
-of (*PRUNE) or (*THEN) without a name do not obliterate a previous (*MARK). In
-callouts from the DFA matching functions this field always contains NULL.
+callouts from \fBpcre_exec()\fP or \fBpcre[16|32]_exec()\fP it contains a
+pointer to the zero-terminated name of the most recently passed (*MARK),
+(*PRUNE), or (*THEN) item in the match, or NULL if no such items have been
+passed. Instances of (*PRUNE) or (*THEN) without a name do not obliterate a
+previous (*MARK). In callouts from the DFA matching functions this field always
+contains NULL.
 .
 .
 .SH "RETURN VALUES"
@@ -207,6 +217,6 @@ Cambridge CB2 3QH, England.
 .rs
 .sp
 .nf
-Last updated: 13 January 2013
+Last updated: 03 March 2013
 Copyright (c) 1997-2013 University of Cambridge.
 .fi
diff --git a/doc/pcrepattern.3 b/doc/pcrepattern.3
index 9b3e471..73d256b 100644
--- a/doc/pcrepattern.3
+++ b/doc/pcrepattern.3
@@ -1,4 +1,4 @@
-.TH PCREPATTERN 3 "27 February 2013" "PCRE 8.33"
+.TH PCREPATTERN 3 "03 March 2013" "PCRE 8.33"
 .SH NAME
 PCRE - Perl-compatible regular expressions
 .SH "PCRE REGULAR EXPRESSION DETAILS"
@@ -2640,7 +2640,14 @@ For example, this pattern has two callout points:
 .sp
 If the PCRE_AUTO_CALLOUT flag is passed to a compiling function, callouts are
 automatically installed before each item in the pattern. They are all numbered
-255.
+255. If there is a conditional group in the pattern whose condition is an
+assertion, an additional callout is inserted just before the condition. An
+explicit callout may also be set at this position, as in this example:
+.sp
+  (?(?C9)(?=a)abc|def)
+.sp
+Note that this applies only to assertion conditions, not to other types of 
+condition.   
 .P
 During matching, when PCRE reaches a callout point, the external function is
 called. It is provided with the number of the callout, the position in the
@@ -2989,6 +2996,6 @@ Cambridge CB2 3QH, England.
 .rs
 .sp
 .nf
-Last updated: 27 February 2013
+Last updated: 03 March 2013
 Copyright (c) 1997-2013 University of Cambridge.
 .fi
diff --git a/pcre_compile.c b/pcre_compile.c
index 4fd1678..4f17ba1 100644
--- a/pcre_compile.c
+++ b/pcre_compile.c
@@ -5729,6 +5729,7 @@ for (;; ptr++)
         /* ------------------------------------------------------------ */
         case CHAR_LEFT_PARENTHESIS:
         bravalue = OP_COND;       /* Conditional group */
+        tempptr = ptr; 
 
         /* A condition can be an assertion, a number (referring to a numbered
         group), a name (referring to a named group), or 'R', referring to
@@ -5741,14 +5742,28 @@ for (;; ptr++)
         be the recursive thing or the name 'R' (and similarly for 'R' followed
         by digits), and (b) a number could be a name that consists of digits.
         In both cases, we look for a name first; if not found, we try the other
-        cases. */
+        cases.
+        
+        For compatibility with auto-callouts, we allow a callout to be 
+        specified before a condition that is an assertion. First, check for the 
+        syntax of a callout; if found, adjust the temporary pointer that is 
+        used to check for an assertion condition. That's all that is needed! */
+        
+        if (ptr[1] == CHAR_QUESTION_MARK && ptr[2] == CHAR_C)
+          {
+          for (i = 3;; i++) if (!IS_DIGIT(ptr[i])) break;
+          if (ptr[i] == CHAR_RIGHT_PARENTHESIS)
+            tempptr += i + 1; 
+          }    
 
         /* For conditions that are assertions, check the syntax, and then exit
         the switch. This will take control down to where bracketed groups,
         including assertions, are processed. */
 
-        if (ptr[1] == CHAR_QUESTION_MARK && (ptr[2] == CHAR_EQUALS_SIGN ||
-            ptr[2] == CHAR_EXCLAMATION_MARK || ptr[2] == CHAR_LESS_THAN_SIGN))
+        if (tempptr[1] == CHAR_QUESTION_MARK && 
+              (tempptr[2] == CHAR_EQUALS_SIGN ||
+               tempptr[2] == CHAR_EXCLAMATION_MARK || 
+               tempptr[2] == CHAR_LESS_THAN_SIGN))
           break;
 
         /* Most other conditions use OP_CREF (a couple change to OP_RREF
diff --git a/testdata/testinput2 b/testdata/testinput2
index f16444a..efb5741 100644
--- a/testdata/testinput2
+++ b/testdata/testinput2
@@ -3845,4 +3845,10 @@ settings of the anchored and startline bits. --/
     xxxx123a\P\P
     xxxx123a\P
 
+/^(?(?=a)aa|bb)/C
+    bb
+
+/(?C1)^(?C2)(?(?C99)(?=(?C3)a(?C4))(?C5)a(?C6)a(?C7)|(?C8)b(?C9)b(?C10))(?C11)/
+    bb
+
 /-- End of testinput2 --/
diff --git a/testdata/testoutput2 b/testdata/testoutput2
index cdb186e..aa38634 100644
--- a/testdata/testoutput2
+++ b/testdata/testoutput2
@@ -12616,4 +12616,30 @@ Partial match: 123a
     xxxx123a\P
 Partial match: 123a
 
+/^(?(?=a)aa|bb)/C
+    bb
+--->bb
+ +0 ^      ^
+ +1 ^      (?(?=a)aa|bb)
+ +3 ^      (?=a)
+ +6 ^      a
++11 ^      b
++12 ^^     b
++13 ^ ^    )
++14 ^ ^    
+ 0: bb
+
+/(?C1)^(?C2)(?(?C99)(?=(?C3)a(?C4))(?C5)a(?C6)a(?C7)|(?C8)b(?C9)b(?C10))(?C11)/
+    bb
+--->bb
+  1 ^      ^
+  2 ^      (?(?C99)(?=(?C3)a(?C4))(?C5)a(?C6)a(?C7)|(?C8)b(?C9)b(?C10))
+ 99 ^      (?=(?C3)a(?C4))
+  3 ^      a
+  8 ^      b
+  9 ^^     b
+ 10 ^ ^    )
+ 11 ^ ^    
+ 0: bb
+
 /-- End of testinput2 --/