Changeset 18483 in webkit for trunk/JavaScriptCore/pcre/pcre_compile.c

Timestamp:

Dec 29, 2006, 7:03:43 PM (18 years ago)

Author:

ddkilzer

Message:

2006-12-29 David Kilzer <​[email protected]>

Reviewed by Geoff.

Update embedded pcre library from version 6.1 to 6.2. From the pcre ChangeLog:

3. Added "b" to the 2nd argument of fopen() in dftables.c, for non-Unix-like operating environments where this matters.

5. Named capturing subpatterns were not being correctly counted when a pattern was compiled. This caused two problems: (a) If there were more than 100 such subpatterns, the calculation of the memory needed for the whole compiled pattern went wrong, leading to an overflow error. (b) Numerical back references of the form \12, where the number was greater than 9, were not recognized as back references, even though there were sufficient previous subpatterns.

• pcre/dftables.c: Item 3. (main):
• pcre/pcre.h: Updated version.
• pcre/pcre_compile.c: Item 5. (read_repeat_counts): (pcre_compile2):

File:

• trunk/JavaScriptCore/pcre/pcre_compile.c (modified) (7 diffs)

trunk/JavaScriptCore/pcre/pcre_compile.c

@@ -718 +718 @@
 int max = -1;
 
+/* Read the minimum value and do a paranoid check: a negative value indicates
+an integer overflow. */
+
 while ((DIGITAB(*p) & ctype_digit) != 0) min = min * 10 + *p++ - '0';
 if (min < 0 || min > 65535)
@@ -724 +727 @@
     return p;
   }
+
+/* Read the maximum value if there is one, and again do a paranoid on its size.
+Also, max must not be less than min. */
 
 if (*p == '}') max = min; else
@@ -3916 +3922 @@
 #endif
 BOOL inescq = FALSE;
+BOOL capturing;
 unsigned int brastackptr = 0;
 size_t size;
@@ -4480 +4487 @@
     branch_newextra = 0;
     bracket_length = 1 + LINK_SIZE;
+    capturing = FALSE;
 
     /* Handle special forms of bracket, which all start (? */
@@ -4572 +4580 @@
         case 'P':
         ptr += 3;
+
+        /* Handle the definition of a named subpattern */
+
         if (*ptr == '<')
           {
@@ -4584 +4595 @@
           name_count++;
           if (ptr - p > max_name_size) max_name_size = INT_CAST(ptr - p);
+          capturing = TRUE;   /* Named parentheses are always capturing */
           break;
           }
+
+        /* Handle back references and recursive calls to named subpatterns */
 
         if (*ptr == '=' || *ptr == '>')
@@ -4772 +4786 @@
           }
 
-        /* If options were terminated by ':' control comes here. Fall through
-        to handle the group below. */
+        /* If options were terminated by ':' control comes here. This is a
+        non-capturing group with an options change. There is nothing more that
+        needs to be done because "capturing" is already set FALSE by default;
+        we can just fall through. */
+
         }
       }
 
-    /* Extracting brackets must be counted so we can process escapes in a
-    Perlish way. If the number exceeds EXTRACT_BASIC_MAX we are going to
-    need an additional 3 bytes of store per extracting bracket. However, if
-    PCRE_NO_AUTO)CAPTURE is set, unadorned brackets become non-capturing, so we
-    must leave the count alone (it will aways be zero). */
-
-    else if ((options & PCRE_NO_AUTO_CAPTURE) == 0)
+    /* Ordinary parentheses, not followed by '?', are capturing unless
+    PCRE_NO_AUTO_CAPTURE is set. */
+
+    else capturing = (options & PCRE_NO_AUTO_CAPTURE) == 0;
+
+    /* Capturing brackets must be counted so we can process escapes in a
+    Perlish way. If the number exceeds EXTRACT_BASIC_MAX we are going to need
+    an additional 3 bytes of memory per capturing bracket. */
+
+    if (capturing)
       {
       bracount++;