Changeset 31454 in webkit for trunk/JavaScriptCore/pcre

Timestamp:

Mar 31, 2008, 1:01:09 AM (17 years ago)

Author:

[email protected]

Message:

Reviewed by darin.

Make matching of regexps using ^{much faster
​http://bugs.webkit.org/show_bug.cgi?id=18086}

• pcre/pcre_compile.cpp: (compileBranch): (branchNeedsLineStart):
• pcre/pcre_exec.cpp: (match): (jsRegExpExecute):
• pcre/pcre_internal.h:

Location:

trunk/JavaScriptCore/pcre

Files:

• pcre_compile.cpp (modified) (2 diffs)
• pcre_exec.cpp (modified) (2 diffs)
• pcre_internal.h (modified) (1 diff)

trunk/JavaScriptCore/pcre/pcre_compile.cpp

@@ -637 +637 @@
             /* Handle single-character metacharacters. In multiline mode, ^ disables
              the setting of any following char as a first character. */
-                
+
             case '^':
                 if (options & MatchAcrossMultipleLinesOption) {
                     if (firstbyte == REQ_UNSET)
                         firstbyte = REQ_NONE;
-                }
+                    *code++ = OP_BOL;
+                } else
+                    *code++ = OP_CIRC;
                 previous = NULL;
-                *code++ = OP_CIRC;
                 break;
-                
+
             case '$':
                 previous = NULL;
-                *code++ = OP_DOLL;
+                if (options & MatchAcrossMultipleLinesOption)
+                  *code++ = OP_EOL;
+                else
+                  *code++ = OP_DOLL;
                 break;
-                
+
             /* There can never be a first char if '.' is first, whatever happens about
              repeats. The value of reqbyte doesn't change either. */
-                
+
             case '.':
                 if (firstbyte == REQ_UNSET)
@@ -1905 +1909 @@
 
     /* Explicit ^ */
-    return op == OP_CIRC;
+    return op == OP_CIRC || op == OP_BOL;
 }
 

trunk/JavaScriptCore/pcre/pcre_exec.cpp

@@ -653 +653 @@
                 RRETURN;
                 
-            /* Start of subject, or after internal newline if multiline. */
-                
+            /* Start of subject. */
+
             BEGIN_OPCODE(CIRC):
-                if (stack.currentFrame->args.subjectPtr != md.startSubject && (!md.multiline || !isNewline(stack.currentFrame->args.subjectPtr[-1])))
+                if (stack.currentFrame->args.subjectPtr != md.startSubject)
                     RRETURN_NO_MATCH;
                 stack.currentFrame->args.instructionPtr++;
                 NEXT_OPCODE;
-                
-            /* End of subject, or before internal newline if multiline. */
-                
+
+            /* After internal newline if multiline. */
+
+            BEGIN_OPCODE(BOL):
+                if (stack.currentFrame->args.subjectPtr != md.startSubject && !isNewline(stack.currentFrame->args.subjectPtr[-1]))
+                    RRETURN_NO_MATCH;
+                stack.currentFrame->args.instructionPtr++;
+                NEXT_OPCODE;
+
+            /* End of subject. */
+
             BEGIN_OPCODE(DOLL):
-                if (stack.currentFrame->args.subjectPtr < md.endSubject && (!md.multiline || !isNewline(*stack.currentFrame->args.subjectPtr)))
+                if (stack.currentFrame->args.subjectPtr < md.endSubject)
+                    RRETURN_NO_MATCH;
+                stack.currentFrame->args.instructionPtr++;
+                NEXT_OPCODE;
+
+            /* Before internal newline if multiline. */
+
+            BEGIN_OPCODE(EOL):
+                if (stack.currentFrame->args.subjectPtr < md.endSubject && !isNewline(*stack.currentFrame->args.subjectPtr))
                     RRETURN_NO_MATCH;
                 stack.currentFrame->args.instructionPtr++;
@@ -2055 +2071 @@
         DPRINTF((">>>> returning %d\n", returnCode));
         return returnCode;
-    } while (startMatch <= endSubject);
+    } while (!(re->options & IsAnchoredOption) && startMatch <= endSubject);
     
     if (using_temporary_offsets) {

trunk/JavaScriptCore/pcre/pcre_internal.h

@@ -232 +232 @@
     macro(CIRC) \
     macro(DOLL) \
+    macro(BOL) \
+    macro(EOL) \
     macro(CHAR) \
     macro(CHAR_IGNORING_CASE) \