--- code/trunk/pcre_compile.c	2007/08/15 11:34:14	213
+++ code/trunk/pcre_compile.c	2007/08/17 09:25:08	221
@@ -283,7 +283,7 @@
   "(*VERB) with an argument is not supported",
   /* 60 */
   "(*VERB) not recognized",
-  "number is too big" 
+  "number is too big"
 };
 
 
@@ -524,12 +524,12 @@
     c = 0;
     while ((digitab[ptr[1]] & ctype_digit) != 0)
       c = c * 10 + *(++ptr) - '0';
-      
+
     if (c < 0)
       {
       *errorcodeptr = ERR61;
       break;
-      }    
+      }
 
     if (c == 0 || (braced && *(++ptr) != '}'))
       {
@@ -574,8 +574,8 @@
       if (c < 0)
         {
         *errorcodeptr = ERR61;
-        break; 
-        }      
+        break;
+        }
       if (c < 10 || c <= bracount)
         {
         c = -(ESC_REF + c);
@@ -950,6 +950,7 @@
     {
     while (*(++ptr) != ']')
       {
+      if (*ptr == 0) return -1;
       if (*ptr == '\\')
         {
         if (*(++ptr) == 0) return -1;
@@ -1105,7 +1106,6 @@
   {
   int d;
   register int op = *cc;
-
   switch (op)
     {
     case OP_CBRA:
@@ -1194,6 +1194,7 @@
 
     case OP_TYPEEXACT:
     branchlength += GET2(cc,1);
+    if (cc[3] == OP_PROP || cc[3] == OP_NOTPROP) cc += 2;
     cc += 4;
     break;
 
@@ -1302,13 +1303,42 @@
     code += _pcre_OP_lengths[c];
     }
 
-  /* In UTF-8 mode, opcodes that are followed by a character may be followed by
-  a multi-byte character. The length in the table is a minimum, so we have to
-  arrange to skip the extra bytes. */
+  /* Otherwise, we can get the item's length from the table, except that for
+  repeated character types, we have to test for \p and \P, which have an extra
+  two bytes of parameters. */
 
   else
     {
+    switch(c)
+      {
+      case OP_TYPESTAR:
+      case OP_TYPEMINSTAR:
+      case OP_TYPEPLUS:
+      case OP_TYPEMINPLUS:
+      case OP_TYPEQUERY:
+      case OP_TYPEMINQUERY:
+      case OP_TYPEPOSSTAR:
+      case OP_TYPEPOSPLUS:
+      case OP_TYPEPOSQUERY:
+      if (code[1] == OP_PROP || code[1] == OP_NOTPROP) code += 2;
+      break;
+
+      case OP_TYPEUPTO:
+      case OP_TYPEMINUPTO:
+      case OP_TYPEEXACT:
+      case OP_TYPEPOSUPTO:
+      if (code[3] == OP_PROP || code[3] == OP_NOTPROP) code += 2;
+      break;
+      }
+
+    /* Add in the fixed length from the table */
+
     code += _pcre_OP_lengths[c];
+
+  /* In UTF-8 mode, opcodes that are followed by a character may be followed by
+  a multi-byte character. The length in the table is a minimum, so we have to
+  arrange to skip the extra bytes. */
+
 #ifdef SUPPORT_UTF8
     if (utf8) switch(c)
       {
@@ -1366,14 +1396,42 @@
 
   if (c == OP_XCLASS) code += GET(code, 1);
 
-  /* Otherwise, we get the item's length from the table. In UTF-8 mode, opcodes
-  that are followed by a character may be followed by a multi-byte character.
-  The length in the table is a minimum, so we have to arrange to skip the extra
-  bytes. */
+  /* Otherwise, we can get the item's length from the table, except that for
+  repeated character types, we have to test for \p and \P, which have an extra
+  two bytes of parameters. */
 
   else
     {
+    switch(c)
+      {
+      case OP_TYPESTAR:
+      case OP_TYPEMINSTAR:
+      case OP_TYPEPLUS:
+      case OP_TYPEMINPLUS:
+      case OP_TYPEQUERY:
+      case OP_TYPEMINQUERY:
+      case OP_TYPEPOSSTAR:
+      case OP_TYPEPOSPLUS:
+      case OP_TYPEPOSQUERY:
+      if (code[1] == OP_PROP || code[1] == OP_NOTPROP) code += 2;
+      break;
+
+      case OP_TYPEPOSUPTO:
+      case OP_TYPEUPTO:
+      case OP_TYPEMINUPTO:
+      case OP_TYPEEXACT:
+      if (code[3] == OP_PROP || code[3] == OP_NOTPROP) code += 2;
+      break;
+      }
+
+    /* Add in the fixed length from the table */
+
     code += _pcre_OP_lengths[c];
+
+    /* In UTF-8 mode, opcodes that are followed by a character may be followed
+    by a multi-byte character. The length in the table is a minimum, so we have
+    to arrange to skip the extra bytes. */
+
 #ifdef SUPPORT_UTF8
     if (utf8) switch(c)
       {
@@ -1469,11 +1527,15 @@
 
   switch (c)
     {
-    /* Check for quantifiers after a class */
+    /* Check for quantifiers after a class. XCLASS is used for classes that
+    cannot be represented just by a bit map. This includes negated single
+    high-valued characters. The length in _pcre_OP_lengths[] is zero; the
+    actual length is stored in the compiled code, so we must update "code"
+    here. */
 
 #ifdef SUPPORT_UTF8
     case OP_XCLASS:
-    ccode = code + GET(code, 1);
+    ccode = code += GET(code, 1);
     goto CHECK_CLASS_REPEAT;
 #endif
 
@@ -2666,6 +2728,7 @@
           else inescq = TRUE;
           continue;
           }
+        else if (-c == ESC_E) continue;  /* Ignore orphan \E */
 
         if (c < 0)
           {
@@ -4740,10 +4803,10 @@
       goto FAILED;
       }
 
-    /* In the pre-compile phase, update the length by the length of the nested
-    group, less the brackets at either end. Then reduce the compiled code to
-    just the brackets so that it doesn't use much memory if it is duplicated by
-    a quantifier. */
+    /* In the pre-compile phase, update the length by the length of the group,
+    less the brackets at either end. Then reduce the compiled code to just a
+    set of non-capturing brackets so that it doesn't use much memory if it is
+    duplicated by a quantifier.*/
 
     if (lengthptr != NULL)
       {
@@ -4753,15 +4816,16 @@
         goto FAILED;
         }
       *lengthptr += length_prevgroup - 2 - 2*LINK_SIZE;
-      code++;
+      *code++ = OP_BRA;
       PUTINC(code, 0, 1 + LINK_SIZE);
       *code++ = OP_KET;
       PUTINC(code, 0, 1 + LINK_SIZE);
+      break;    /* No need to waste time with special character handling */
       }
 
     /* Otherwise update the main code pointer to the end of the group. */
 
-    else code = tempcode;
+    code = tempcode;
 
     /* For a DEFINE group, required and first character settings are not
     relevant. */