Improve error messages for (?+-a) and (?-+a).

git-svn-id: svn://vcs.exim.org/pcre/code/trunk@269 2f5784b3-3f2a-0410-8824-cb99058d5e15

6 files changed, 36 insertions, 12 deletions

diff --git a/ChangeLog b/ChangeLog
index 7ca7f72..7e3fbf9 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -22,6 +22,10 @@ Version 7.5 12-Nov-07
     first named subpattern) and a construct such as (?&a) would reference the 
     first named subpattern whose name started with "a" (in other words, the 
     length check was missing). 
+    
+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.
 
 
 Version 7.4 21-Sep-07
diff --git a/pcre_compile.c b/pcre_compile.c
index d160e1d..0d579db 100644
--- a/pcre_compile.c
+++ b/pcre_compile.c
@@ -241,7 +241,7 @@ static const char error_texts[] =
   /* 10 */
   "operand of unlimited repeat could match the empty string\0"  /** DEAD **/
   "internal error: unexpected repeat\0"
-  "unrecognized character after (?\0"
+  "unrecognized character after (? or (?-\0"
   "POSIX named classes are supported only within a class\0"
   "missing )\0"
   /* 15 */
@@ -301,7 +301,8 @@ static const char error_texts[] =
   /* 60 */
   "(*VERB) not recognized\0"
   "number is too big\0"
-  "subpattern name expected after (?&";
+  "subpattern name expected after (?&\0"
+  "digit expected after (?+";
 
 
 /* Table to identify digits and hex digits. This is used when compiling
@@ -4603,7 +4604,15 @@ we set the flag only if there is a literal "\r" or "\n" in the class. */
           {
           const uschar *called;
 
-          if ((refsign = *ptr) == '+') ptr++;
+          if ((refsign = *ptr) == '+') 
+            {
+            ptr++;
+            if ((digitab[*ptr] & ctype_digit) == 0)
+              {
+              *errorcodeptr = ERR63;
+              goto FAILED;
+              }    
+            } 
           else if (refsign == '-')
             {
             if ((digitab[ptr[1]] & ctype_digit) == 0)
diff --git a/pcre_internal.h b/pcre_internal.h
index ca8749a..7ffae2f 100644
--- a/pcre_internal.h
+++ b/pcre_internal.h
@@ -871,7 +871,7 @@ enum { ERR0,  ERR1,  ERR2,  ERR3,  ERR4,  ERR5,  ERR6,  ERR7,  ERR8,  ERR9,
        ERR30, ERR31, ERR32, ERR33, ERR34, ERR35, ERR36, ERR37, ERR38, ERR39,
        ERR40, ERR41, ERR42, ERR43, ERR44, ERR45, ERR46, ERR47, ERR48, ERR49,
        ERR50, ERR51, ERR52, ERR53, ERR54, ERR55, ERR56, ERR57, ERR58, ERR59,
-       ERR60, ERR61, ERR62 };
+       ERR60, ERR61, ERR62, ERR63 };
 
 /* The real format of the start of the pcre block; the index of names and the
 code vector run on as long as necessary after the end. We store an explicit
diff --git a/pcreposix.c b/pcreposix.c
index 545fbf9..1ddf6ae 100644
--- a/pcreposix.c
+++ b/pcreposix.c
@@ -125,7 +125,8 @@ static const int eint[] = {
   REG_BADPAT,  /* \g is not followed followed by an (optionally braced) non-zero number */
   REG_BADPAT,  /* (?+ or (?- must be followed by a non-zero number */
   REG_BADPAT,  /* number is too big */
-  REG_BADPAT   /* subpattern name expected after (?& */ 
+  REG_BADPAT,  /* subpattern name expected after (?& */ 
+  REG_BADPAT   /* digit expected after (?+ */ 
 };
 
 /* Table of texts corresponding to POSIX error codes */
diff --git a/testdata/testinput2 b/testdata/testinput2
index 572bcf3..2a180e3 100644
--- a/testdata/testinput2
+++ b/testdata/testinput2
@@ -2541,4 +2541,8 @@ a random value. /Ix
 
 /(?<a>)(?&aaaaaaaaaaaaaaaaaaaaaaa)/
 
+/(?+-a)/
+
+/(?-+a)/
+
 / End of testinput2 /
diff --git a/testdata/testoutput2 b/testdata/testoutput2
index 6648221..85d931a 100644
--- a/testdata/testoutput2
+++ b/testdata/testoutput2
@@ -109,7 +109,7 @@ Failed: missing ) at offset 4
 Failed: missing ) after comment at offset 7
 
 /(?z)abc/
-Failed: unrecognized character after (? at offset 2
+Failed: unrecognized character after (? or (?- at offset 2
 
 /.*b/I
 Capturing subpattern count = 0
@@ -310,7 +310,7 @@ No match
 No match
 
 /ab(?z)cd/
-Failed: unrecognized character after (? at offset 4
+Failed: unrecognized character after (? or (?- at offset 4
 
 /^abc|def/I
 Capturing subpattern count = 0
@@ -946,19 +946,19 @@ Failed: missing ) at offset 4
 Failed: unrecognized character after (?< at offset 3
 
 /a(?{)b/
-Failed: unrecognized character after (? at offset 3
+Failed: unrecognized character after (? or (?- at offset 3
 
 /a(?{{})b/
-Failed: unrecognized character after (? at offset 3
+Failed: unrecognized character after (? or (?- at offset 3
 
 /a(?{}})b/
-Failed: unrecognized character after (? at offset 3
+Failed: unrecognized character after (? or (?- at offset 3
 
 /a(?{"{"})b/
-Failed: unrecognized character after (? at offset 3
+Failed: unrecognized character after (? or (?- at offset 3
 
 /a(?{"{"}})b/
-Failed: unrecognized character after (? at offset 3
+Failed: unrecognized character after (? or (?- at offset 3
 
 /(?(1?)a|b)/
 Failed: malformed number or name after (?( at offset 4
@@ -9311,4 +9311,10 @@ Failed: reference to non-existent subpattern at offset 12
 /(?<a>)(?&aaaaaaaaaaaaaaaaaaaaaaa)/
 Failed: reference to non-existent subpattern at offset 32
 
+/(?+-a)/
+Failed: digit expected after (?+ at offset 3
+
+/(?-+a)/
+Failed: unrecognized character after (? or (?- at offset 3
+
 / End of testinput2 /