Fix extended *verb name ignored terminating whitespace bug.

git-svn-id: svn://vcs.exim.org/pcre2/code/trunk@454 6239d852-aaf2-0410-a92c-79f79f948069

4 files changed, 39 insertions, 8 deletions

diff --git a/ChangeLog b/ChangeLog
index 7c5b9c4..332b3c2 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -353,6 +353,11 @@ was set when the pmatch argument was NULL. It now returns REG_INVARG.
 pcre2_compile() to misbehave when auto callouts were enabled. This bug
 was found by the LLVM fuzzer.
 
+106. If both PCRE2_ALT_VERBNAMES and PCRE2_EXTENDED were set, and a (*MARK) or 
+other verb "name" ended with whitespace immediately before the closing 
+parenthesis, pcre2_compile() misbehaved. Example: /(*:abc )/, but only when 
+both those options were set.
+
 
 Version 10.20 30-June-2015
 --------------------------
diff --git a/src/pcre2_compile.c b/src/pcre2_compile.c
index 1699835..3e92436 100644
--- a/src/pcre2_compile.c
+++ b/src/pcre2_compile.c
@@ -3013,15 +3013,14 @@ for (; ptr < cb->end_pattern; ptr++)
     {
     if (x == CHAR_RIGHT_PARENTHESIS) break;
 
-    /* Skip over comments and whitespace in extended mode. Need a loop to
-    handle whitespace after a comment. */
+    /* Skip over comments and whitespace in extended mode. */
 
     if ((options & PCRE2_EXTENDED) != 0)
       {
-      for (;;)
-        {
-        while (MAX_255(x) && (cb->ctypes[x] & ctype_space) != 0) x = *(++ptr);
-        if (x != CHAR_NUMBER_SIGN) break;
+      PCRE2_SPTR wscptr = ptr; 
+      while (MAX_255(x) && (cb->ctypes[x] & ctype_space) != 0) x = *(++ptr);
+      if (x == CHAR_NUMBER_SIGN)
+        { 
         ptr++;
         while (*ptr != CHAR_NULL)
           {
@@ -3035,9 +3034,15 @@ for (; ptr < cb->end_pattern; ptr++)
           if (utf) FORWARDCHAR(ptr);
 #endif
           }
-        x = *ptr;     /* Either NULL or the char after a newline */
+        }   
+      
+      /* If we have skipped any characters, restart the loop. */
+       
+      if (ptr > wscptr)
+        {
+        ptr--;
+        continue;
         }
-      if (ptr >= cb->end_pattern) break;
       }
 
     /* Process escapes */
diff --git a/testdata/testinput2 b/testdata/testinput2
index 19240d2..eb6b9e4 100644
--- a/testdata/testinput2
+++ b/testdata/testinput2
@@ -4702,4 +4702,6 @@ a)"xI
 /()\Q\E*]/B,auto_callout
     a[bc]d
 
+/\x8a+f|;T?(*:;.'?`(\xeap ){![^()!y*''C*(?';]{1;(\x08)/B,alt_verbnames,dupnames,extended
+
 # End of testinput2 
diff --git a/testdata/testoutput2 b/testdata/testoutput2
index a3aced7..698c44d 100644
--- a/testdata/testoutput2
+++ b/testdata/testoutput2
@@ -14979,4 +14979,23 @@ Subject length lower bound = 0
  0: ]
  1: 
 
+/\x8a+f|;T?(*:;.'?`(\xeap ){![^()!y*''C*(?';]{1;(\x08)/B,alt_verbnames,dupnames,extended
+------------------------------------------------------------------
+        Bra
+        \x{8a}++
+        f
+        Alt
+        ;
+        T?
+        *MARK ;.'?`(\x{ea}p
+        {!
+        [\x00- "-&+-:<->@-BD-xz-\xff] (neg)
+        {1;
+        CBra 1
+        \x08
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+
 # End of testinput2