Diagnose conditional numerical reference to a non-existent subpattern.

git-svn-id: svn://vcs.exim.org/pcre/code/trunk@270 2f5784b3-3f2a-0410-8824-cb99058d5e15

7 files changed, 54 insertions, 60 deletions

diff --git a/ChangeLog b/ChangeLog
index 7e3fbf9..bb67f68 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -26,6 +26,12 @@ Version 7.5 12-Nov-07
 6.  The erroneous patterns (?+-a) and (?-+a) give different error messages;
     this is right because (?- can be followed by option settings as well as by 
     digits. I have, however, made the messages clearer.
+    
+7.  Patterns such as (?(1)a|b) (a pattern that contains fewer subpatterns
+    than the number used in the conditional) now cause a compile-time error.
+    This is actually not compatible with Perl, which accepts such patterns, but
+    treats the conditional as always being FALSE (as PCRE used to), but it
+    seems to me that giving a diagnostic is better.
 
 
 Version 7.4 21-Sep-07
diff --git a/pcre_compile.c b/pcre_compile.c
index 0d579db..21b1a8b 100644
--- a/pcre_compile.c
+++ b/pcre_compile.c
@@ -4248,16 +4248,13 @@ we set the flag only if there is a literal "\r" or "\n" in the class. */
             *errorcodeptr = ERR58;
             goto FAILED;
             }
-          if (refsign == '-')
+          recno = (refsign == '-')? 
+            cd->bracount - recno + 1 : recno +cd->bracount;
+          if (recno <= 0 || recno > cd->final_bracount)
             {
-            recno = cd->bracount - recno + 1;
-            if (recno <= 0)
-              {
-              *errorcodeptr = ERR15;
-              goto FAILED;
-              }
+            *errorcodeptr = ERR15;
+            goto FAILED;
             }
-          else recno += cd->bracount;
           PUT2(code, 2+LINK_SIZE, recno);
           break;
           }
@@ -4329,9 +4326,10 @@ we set the flag only if there is a literal "\r" or "\n" in the class. */
           skipbytes = 1;
           }
 
-        /* Check for the "name" actually being a subpattern number. */
+        /* Check for the "name" actually being a subpattern number. We are
+        in the second pass here, so final_bracount is set. */ 
 
-        else if (recno > 0)
+        else if (recno > 0 && recno <= cd->final_bracount)
           {
           PUT2(code, 2+LINK_SIZE, recno);
           }
@@ -5939,7 +5937,7 @@ to compile parts of the pattern into; the compiled code is discarded when it is
 no longer needed, so hopefully this workspace will never overflow, though there
 is a test for its doing so. */
 
-cd->bracount = 0;
+cd->bracount = cd->final_bracount = 0;
 cd->names_found = 0;
 cd->name_entry_size = 0;
 cd->name_table = NULL;
@@ -6016,6 +6014,7 @@ field. Reset the bracket count and the names_found field. Also reset the hwm
 field; this time it's used for remembering forward references to subpatterns.
 */
 
+cd->final_bracount = cd->bracount;  /* Save for checking forward references */
 cd->bracount = 0;
 cd->names_found = 0;
 cd->name_table = (uschar *)re + re->name_table_offset;
diff --git a/pcre_internal.h b/pcre_internal.h
index 7ffae2f..c72af6e 100644
--- a/pcre_internal.h
+++ b/pcre_internal.h
@@ -934,7 +934,8 @@ typedef struct compile_data {
   uschar *name_table;           /* The name/number table */
   int  names_found;             /* Number of entries so far */
   int  name_entry_size;         /* Size of each entry */
-  int  bracount;                /* Count of capturing parens */
+  int  bracount;                /* Count of capturing parens as we compile */
+  int  final_bracount;          /* Saved value after first pass */ 
   int  top_backref;             /* Maximum back reference */
   unsigned int backref_map;     /* Bitmap of low back refs */
   int  external_options;        /* External (initial) options */
diff --git a/testdata/testinput1 b/testdata/testinput1
index 79c98fa..c7f264a 100644
--- a/testdata/testinput1
+++ b/testdata/testinput1
@@ -3421,11 +3421,6 @@
 /((?m)^b)/
     a\nb\nc\n
 
-/(?(1)a|b)/
-
-/(?(1)b|a)/
-    a
-
 /(x)?(?(1)a|b)/
     *** Failers
     a
diff --git a/testdata/testinput2 b/testdata/testinput2
index 2a180e3..da3b01e 100644
--- a/testdata/testinput2
+++ b/testdata/testinput2
@@ -398,8 +398,6 @@
 
 /(?(1?)a|b)/
 
-/(?(1)a|b|c)/
-
 /[a[:xyz:/
 
 /(?<=x+)y/
@@ -568,15 +566,15 @@
 
 /ab\d+/I
 
-/a(?(1)b)/I
+/a(?(1)b)(.)/I
 
-/a(?(1)bag|big)/I
+/a(?(1)bag|big)(.)/I
 
-/a(?(1)bag|big)*/I
+/a(?(1)bag|big)*(.)/I
 
-/a(?(1)bag|big)+/I
+/a(?(1)bag|big)+(.)/I
 
-/a(?(1)b..|b..)/I
+/a(?(1)b..|b..)(.)/I
 
 /ab\d{0}e/I
 
@@ -977,13 +975,13 @@
 
 /()a/I
 
-/(?(1)ab|ac)/I
+/(?(1)ab|ac)(.)/I
 
-/(?(1)abz|acz)/I
+/(?(1)abz|acz)(.)/I
 
-/(?(1)abz)/I
+/(?(1)abz)(.)/I
 
-/(?(1)abz)123/I
+/(?(1)abz)(1)23/I
 
 /(a)+/I
 
@@ -2190,8 +2188,8 @@ a random value. /Ix
 
 /((?(-2)a))/BZ
 
-/^(?(+1)X|Y)/BZ
-    Y
+/^(?(+1)X|Y)(.)/BZ
+    Y!
 
 /(foo)\Kbar/
     foobar
diff --git a/testdata/testoutput1 b/testdata/testoutput1
index 4c0e680..83682f7 100644
--- a/testdata/testoutput1
+++ b/testdata/testoutput1
@@ -5551,12 +5551,6 @@ No match
  0: b
  1: b
 
-/(?(1)a|b)/
-
-/(?(1)b|a)/
-    a
- 0: a
-
 /(x)?(?(1)a|b)/
     *** Failers
 No match
diff --git a/testdata/testoutput2 b/testdata/testoutput2
index 85d931a..cb69551 100644
--- a/testdata/testoutput2
+++ b/testdata/testoutput2
@@ -963,9 +963,6 @@ Failed: unrecognized character after (? or (?- at offset 3
 /(?(1?)a|b)/
 Failed: malformed number or name after (?( at offset 4
 
-/(?(1)a|b|c)/
-Failed: conditional group contains more than two branches at offset 10
-
 /[a[:xyz:/
 Failed: missing terminating ] for character class at offset 8
 
@@ -1599,32 +1596,32 @@ No options
 First char = 'a'
 Need char = 'b'
 
-/a(?(1)b)/I
-Capturing subpattern count = 0
+/a(?(1)b)(.)/I
+Capturing subpattern count = 1
 No options
 First char = 'a'
 No need char
 
-/a(?(1)bag|big)/I
-Capturing subpattern count = 0
+/a(?(1)bag|big)(.)/I
+Capturing subpattern count = 1
 No options
 First char = 'a'
 Need char = 'g'
 
-/a(?(1)bag|big)*/I
-Capturing subpattern count = 0
+/a(?(1)bag|big)*(.)/I
+Capturing subpattern count = 1
 No options
 First char = 'a'
 No need char
 
-/a(?(1)bag|big)+/I
-Capturing subpattern count = 0
+/a(?(1)bag|big)+(.)/I
+Capturing subpattern count = 1
 No options
 First char = 'a'
 Need char = 'g'
 
-/a(?(1)b..|b..)/I
-Capturing subpattern count = 0
+/a(?(1)b..|b..)(.)/I
+Capturing subpattern count = 1
 No options
 First char = 'a'
 Need char = 'b'
@@ -3441,26 +3438,26 @@ No options
 No first char
 Need char = 'a'
 
-/(?(1)ab|ac)/I
-Capturing subpattern count = 0
+/(?(1)ab|ac)(.)/I
+Capturing subpattern count = 1
 No options
 First char = 'a'
 No need char
 
-/(?(1)abz|acz)/I
-Capturing subpattern count = 0
+/(?(1)abz|acz)(.)/I
+Capturing subpattern count = 1
 No options
 First char = 'a'
 Need char = 'z'
 
-/(?(1)abz)/I
-Capturing subpattern count = 0
+/(?(1)abz)(.)/I
+Capturing subpattern count = 1
 No options
 No first char
 No need char
 
-/(?(1)abz)123/I
-Capturing subpattern count = 0
+/(?(1)abz)(1)23/I
+Capturing subpattern count = 1
 No options
 No first char
 Need char = '3'
@@ -8308,7 +8305,7 @@ Failed: reference to non-existent subpattern at offset 6
 /((?(-2)a))/BZ
 Failed: reference to non-existent subpattern at offset 7
 
-/^(?(+1)X|Y)/BZ
+/^(?(+1)X|Y)(.)/BZ
 ------------------------------------------------------------------
         Bra
         ^
@@ -8318,11 +8315,15 @@ Failed: reference to non-existent subpattern at offset 7
         Alt
         Y
         Ket
+        CBra 1
+        Any
+        Ket
         Ket
         End
 ------------------------------------------------------------------
-    Y
- 0: Y
+    Y!
+ 0: Y!
+ 1: !
 
 /(foo)\Kbar/
     foobar