Changeset 27320 in webkit for trunk/JavaScriptCore/kjs/regexp_object.cpp

Timestamp:

Oct 31, 2007, 7:46:41 AM (18 years ago)

Author:

darin

Message:

Reviewed by Maciej.

• fix ​http://bugs.webkit.org/show_bug.cgi?id=15749 RegExp/RegExpObjectImp cause needless UString creation

Speeds things up 0.4% according to SunSpider.

• kjs/config.h: Define USE(PCRE16) instead of HAVE(PCREPOSIX), because this library doesn't use the real PCRE -- it uses its own PCRE that works on UTF-16.

• kjs/regexp.h: Removed a few unused functions. Changed the ifdef. Use Noncopyable. Change the return value of match.
• kjs/regexp.cpp: (KJS::RegExp::RegExp): Call pcre_compile2, for a slight speed boost. (KJS::RegExp::~RegExp): PCRE16 rather than PCREPOSIX. (KJS::RegExp::match): Change to return the position as an int and the ovector as a OwnArrayPtr<int> for efficiency and clearer storage management.

• kjs/regexp_object.h: Change performMatch and arrayOfMatches to no longer require a result string.
• kjs/regexp_object.cpp: (RegExpProtoFunc::callAsFunction): Update for new signature of performMatch. (RegExpObjectImp::performMatch): Change so it doesn't return a string. (RegExpObjectImp::arrayOfMatches): Simplify by unifying the handling of the main result with the backreferences; now it doesn't need to take a result parameter. (RegExpObjectImp::getBackref): Minor tweaks. (RegExpObjectImp::getLastParen): Ditto. (RegExpObjectImp::getLeftContext): Ditto. (RegExpObjectImp::getRightContext): Ditto. (RegExpObjectImp::getValueProperty): Change LastMatch case to call getBackref(0) so we don't need a separate getLastMatch function.

• kjs/string_object.cpp: (KJS::replace): Update to use new performMatch, including merging the matched string section with the other substrings. (KJS::StringProtoFunc::callAsFunction): Update functions to use the new performMatch and match. Also change to use OwnArrayPtr.

File:

• trunk/JavaScriptCore/kjs/regexp_object.cpp (modified) (7 diffs)

trunk/JavaScriptCore/kjs/regexp_object.cpp

@@ -1 +1 @@
 // -*- c-basic-offset: 2 -*-
 /*
- *  This file is part of the KDE libraries
  *  Copyright (C) 1999-2000 Harri Porten ([email protected])
  *  Copyright (C) 2003, 2007 Apple Inc. All Rights Reserved.
@@ -103 +102 @@
 
     int foundIndex;
-    UString match = regExpObj->performMatch(regExp, input, static_cast<int>(lastIndex), &foundIndex);
-    bool didMatch = !match.isNull();
+    int foundLength;
+    regExpObj->performMatch(regExp, input, static_cast<int>(lastIndex), foundIndex, foundLength);
 
     // Test
     if (id == Test)
-      return jsBoolean(didMatch);
+      return jsBoolean(foundIndex >= 0);
 
     // Exec
-    if (didMatch) {
-      if (globalFlag)
-        thisObj->put(exec, exec->propertyNames().lastIndex, jsNumber(foundIndex + match.size()), DontDelete | DontEnum);
-      return regExpObj->arrayOfMatches(exec, match);
-    } else {
+    if (foundIndex < 0) {
       if (globalFlag)
         thisObj->put(exec, exec->propertyNames().lastIndex, jsNumber(0), DontDelete | DontEnum);
       return jsNull();
     }
+    if (globalFlag)
+      thisObj->put(exec, exec->propertyNames().lastIndex, jsNumber(foundIndex + foundLength), DontDelete | DontEnum);
+    return regExpObj->arrayOfMatches(exec);
   }
   break;
@@ -258 +256 @@
   e.g., RegExp.lastMatch and RegExp.leftParen.
 */
-UString RegExpObjectImp::performMatch(RegExp* r, const UString& s, int startOffset, int *endOffset, int **ovector)
-{
-  int tmpOffset;
-  int *tmpOvector;
-  UString match = r->match(s, startOffset, &tmpOffset, &tmpOvector);
-
-  if (endOffset)
-    *endOffset = tmpOffset;
+void RegExpObjectImp::performMatch(RegExp* r, const UString& s, int startOffset, int& position, int& length, int** ovector)
+{
+  OwnArrayPtr<int> tmpOvector;
+  position = r->match(s, startOffset, &tmpOvector);
+
   if (ovector)
-    *ovector = tmpOvector;
+    *ovector = tmpOvector.get();
   
-  if (!match.isNull()) {
+  if (position != -1) {
     ASSERT(tmpOvector);
-    
+
+    length = tmpOvector[1] - tmpOvector[0];
+
     d->lastInput = s;
-    d->lastOvector.set(tmpOvector);
+    d->lastOvector.set(tmpOvector.release());
     d->lastNumSubPatterns = r->subPatterns();
   }
-  
-  return match;
-}
-
-JSObject *RegExpObjectImp::arrayOfMatches(ExecState *exec, const UString &result) const
-{
-  List list;
-  // The returned array contains 'result' as first item, followed by the list of matches
-  list.append(jsString(result));
-  if (d->lastOvector)
-    for (unsigned i = 1 ; i < d->lastNumSubPatterns + 1 ; ++i)
-    {
-      int start = d->lastOvector[2*i];
-      if (start == -1)
-        list.append(jsUndefined());
-      else {
-        UString substring = d->lastInput.substr(start, d->lastOvector[2*i+1] - start);
-        list.append(jsString(substring));
-      }
-    }
-  JSObject *arr = exec->lexicalInterpreter()->builtinArray()->construct(exec, list);
+}
+
+JSObject* RegExpObjectImp::arrayOfMatches(ExecState* exec) const
+{
+  unsigned lastNumSubpatterns = d->lastNumSubPatterns;
+  ArrayInstance* arr = new ArrayInstance(exec->lexicalInterpreter()->builtinArrayPrototype(), lastNumSubpatterns + 1);
+  for (unsigned i = 0; i <= lastNumSubpatterns; ++i) {
+    int start = d->lastOvector[2 * i];
+    if (start >= 0)
+      arr->put(exec, i, jsString(d->lastInput.substr(start, d->lastOvector[2 * i + 1] - start)));
+  }
   arr->put(exec, exec->propertyNames().index, jsNumber(d->lastOvector[0]));
   arr->put(exec, exec->propertyNames().input, jsString(d->lastInput));
@@ -302 +289 @@
 }
 
-JSValue *RegExpObjectImp::getBackref(unsigned i) const
-{
-  if (d->lastOvector && i < d->lastNumSubPatterns + 1) {
-    UString substring = d->lastInput.substr(d->lastOvector[2*i], d->lastOvector[2*i+1] - d->lastOvector[2*i] );
-    return jsString(substring);
-  } 
-
+JSValue* RegExpObjectImp::getBackref(unsigned i) const
+{
+  if (d->lastOvector && i <= d->lastNumSubPatterns)
+    return jsString(d->lastInput.substr(d->lastOvector[2 * i], d->lastOvector[2 * i + 1] - d->lastOvector[2 * i]));
   return jsString("");
 }
 
-JSValue *RegExpObjectImp::getLastMatch() const
-{
-  if (d->lastOvector) {
-    UString substring = d->lastInput.substr(d->lastOvector[0], d->lastOvector[1] - d->lastOvector[0]);
-    return jsString(substring);
-  }
-  
-  return jsString("");
-}
-
-JSValue *RegExpObjectImp::getLastParen() const
-{
-  int i = d->lastNumSubPatterns;
+JSValue* RegExpObjectImp::getLastParen() const
+{
+  unsigned i = d->lastNumSubPatterns;
   if (i > 0) {
     ASSERT(d->lastOvector);
-    UString substring = d->lastInput.substr(d->lastOvector[2*i], d->lastOvector[2*i+1] - d->lastOvector[2*i]);
-    return jsString(substring);
-  }
-    
+    return jsString(d->lastInput.substr(d->lastOvector[2 * i], d->lastOvector[2 * i + 1] - d->lastOvector[2 * i]));
+  }
   return jsString("");
 }
@@ -336 +308 @@
 JSValue *RegExpObjectImp::getLeftContext() const
 {
-  if (d->lastOvector) {
-    UString substring = d->lastInput.substr(0, d->lastOvector[0]);
-    return jsString(substring);
-  }
-  
+  if (d->lastOvector)
+    return jsString(d->lastInput.substr(0, d->lastOvector[0]));
   return jsString("");
 }
@@ -348 +317 @@
   if (d->lastOvector) {
     UString s = d->lastInput;
-    UString substring = s.substr(d->lastOvector[1], s.size() - d->lastOvector[1]);
-    return jsString(substring);
-  }
-  
+    return jsString(s.substr(d->lastOvector[1], s.size() - d->lastOvector[1]));
+  }
   return jsString("");
 }
@@ -386 +353 @@
       return jsBoolean(d->multiline);
     case LastMatch:
-      return getLastMatch();
+      return getBackref(0);
     case LastParen:
       return getLastParen();