Disallow \N in character classes, for Perl compatibility.

git-svn-id: svn://vcs.exim.org/pcre/code/trunk@758 2f5784b3-3f2a-0410-8824-cb99058d5e15

7 files changed, 30 insertions, 7 deletions

diff --git a/ChangeLog b/ChangeLog
index 1cc0d94..d9aed78 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -52,6 +52,9 @@ Version 8.21
     
 13. In non-UTF-8 mode, \C is now supported in lookbehinds and DFA matching.
 
+14. Perl does not support \N without a following name in a [] class; PCRE now
+    also gives an error.
+
 
 Version 8.20 21-Oct-2011
 ------------------------
diff --git a/doc/pcrepattern.3 b/doc/pcrepattern.3
index 18def50..100ae9e 100644
--- a/doc/pcrepattern.3
+++ b/doc/pcrepattern.3
@@ -328,12 +328,14 @@ Note that octal values of 100 or greater must not be introduced by a leading
 zero, because no more than three octal digits are ever read.
 .P
 All the sequences that define a single character value can be used both inside
-and outside character classes. In addition, inside a character class, the
-sequence \eb is interpreted as the backspace character (hex 08). The sequences
-\eB, \eN, \eR, and \eX are not special inside a character class. Like any other
-unrecognized escape sequences, they are treated as the literal characters "B",
-"N", "R", and "X" by default, but cause an error if the PCRE_EXTRA option is
-set. Outside a character class, these sequences have different meanings.
+and outside character classes. In addition, inside a character class, \eb is
+interpreted as the backspace character (hex 08).
+.P
+\eN is not allowed in a character class. \eB, \eR, and \eX are not special
+inside a character class. Like other unrecognized escape sequences, they are
+treated as the literal characters "B", "R", and "X" by default, but cause an
+error if the PCRE_EXTRA option is set. Outside a character class, these
+sequences have different meanings.
 .
 .
 .SS "Unsupported escape sequences"
diff --git a/pcre_compile.c b/pcre_compile.c
index 0252261..4a63e69 100644
--- a/pcre_compile.c
+++ b/pcre_compile.c
@@ -412,6 +412,7 @@ static const char error_texts[] =
   "\\k is not followed by a braced, angle-bracketed, or quoted name\0"
   /* 70 */
   "internal error: unknown opcode in find_fixedlength()\0"
+  "\\N is not supported in a class\0" 
   ;
 
 /* Table to identify digits and hex digits. This is used when compiling
@@ -3770,6 +3771,11 @@ for (;; ptr++)
         if (*errorcodeptr != 0) goto FAILED;
 
         if (-c == ESC_b) c = CHAR_BS;    /* \b is backspace in a class */
+        else if (-c == ESC_N)            /* \N is not supported in a class */
+          {
+          *errorcodeptr = ERR71;
+          goto FAILED;  
+          }   
         else if (-c == ESC_Q)            /* Handle start of quoted string */
           {
           if (ptr[1] == CHAR_BACKSLASH && ptr[2] == CHAR_E)
diff --git a/pcre_internal.h b/pcre_internal.h
index 0c5d676..3655349 100644
--- a/pcre_internal.h
+++ b/pcre_internal.h
@@ -1665,7 +1665,7 @@ enum { ERR0,  ERR1,  ERR2,  ERR3,  ERR4,  ERR5,  ERR6,  ERR7,  ERR8,  ERR9,
        ERR40, ERR41, ERR42, ERR43, ERR44, ERR45, ERR46, ERR47, ERR48, ERR49,
        ERR50, ERR51, ERR52, ERR53, ERR54, ERR55, ERR56, ERR57, ERR58, ERR59,
        ERR60, ERR61, ERR62, ERR63, ERR64, ERR65, ERR66, ERR67, ERR68, ERR69,
-       ERR70, ERRCOUNT };
+       ERR70, ERR71, ERRCOUNT };
 
 /* 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 648254b..b5f9d0e 100644
--- a/pcreposix.c
+++ b/pcreposix.c
@@ -155,6 +155,7 @@ static const int eint[] = {
   REG_BADPAT,  /* \k is not followed by a braced, angle-bracketed, or quoted name */
   /* 70 */
   REG_BADPAT,  /* internal error: unknown opcode in find_fixedlength() */ 
+  REG_BADPAT,  /* \N is not supported in a class */ 
 };
 
 /* Table of texts corresponding to POSIX error codes */
diff --git a/testdata/testinput2 b/testdata/testinput2
index b673fef..c7c5c16 100644
--- a/testdata/testinput2
+++ b/testdata/testinput2
@@ -4009,4 +4009,9 @@ AbcdCBefgBhiBqz
 
 /(?<=ab\Cde)X/8
 
+/a[\NB]c/
+    aNc
+    
+/a[B-\Nc]/ 
+
 /-- End of testinput2 --/
diff --git a/testdata/testoutput2 b/testdata/testoutput2
index 417225a..ba2f53c 100644
--- a/testdata/testoutput2
+++ b/testdata/testoutput2
@@ -12594,4 +12594,10 @@ No match
 /(?<=ab\Cde)X/8
 Failed: \C not allowed in lookbehind assertion at offset 10
 
+/a[\NB]c/
+Failed: \N is not supported in a class at offset 3
+
+/a[B-\Nc]/ 
+Failed: \N is not supported in a class at offset 5
+
 /-- End of testinput2 --/