Changeset 65305 in webkit for trunk/JavaScriptCore/runtime/UString.cpp

Timestamp:

Aug 13, 2010, 12:35:45 AM (15 years ago)

Author:

[email protected]

Message:

Unify UString::UTF8String() & String::utf8() methods,
remove UString::cost() & make atArrayIndex a free function.

Reviewed by Sam Weinig

JavaScriptCore:

• JavaScriptCore.exp:
• bytecode/CodeBlock.cpp:

(JSC::constantName):
(JSC::idName):
(JSC::CodeBlock::registerName):
(JSC::regexpName):
(JSC::printGlobalResolveInfo):
(JSC::printStructureStubInfo):
(JSC::CodeBlock::printStructure):
(JSC::CodeBlock::printStructures):

• jsc.cpp:

(functionPrint):
(functionDebug):
(runInteractive):
(fillBufferWithContentsOfFile):

• pcre/pcre_exec.cpp:

(Histogram::~Histogram):

• profiler/CallIdentifier.h:

(JSC::CallIdentifier::c_str):

• profiler/Profile.cpp:

(JSC::Profile::debugPrintDataSampleStyle):

• profiler/ProfileGenerator.cpp:

(JSC::ProfileGenerator::willExecute):
(JSC::ProfileGenerator::didExecute):

• profiler/ProfileNode.cpp:

(JSC::ProfileNode::debugPrintData):
(JSC::ProfileNode::debugPrintDataSampleStyle):

• runtime/Arguments.cpp:

(JSC::Arguments::getOwnPropertySlot):
(JSC::Arguments::getOwnPropertyDescriptor):
(JSC::Arguments::put):
(JSC::Arguments::deleteProperty):

• runtime/DateConversion.cpp:

(JSC::parseDate):

• runtime/Identifier.h:

(JSC::Identifier::toStrictUInt32):

• runtime/JSArray.cpp:

(JSC::JSArray::getOwnPropertySlot):
(JSC::JSArray::getOwnPropertyDescriptor):
(JSC::JSArray::put):
(JSC::JSArray::deleteProperty):

• runtime/JSArray.h:

(JSC::toArrayIndex):

• runtime/JSGlobalObjectFunctions.cpp:

(JSC::encode):
(JSC::parseInt):
(JSC::globalFuncJSCPrint):

• runtime/JSString.h:

(JSC::RopeBuilder::JSString):

• runtime/UString.cpp:

(JSC::UString::toDouble):
(JSC::putUTF8Triple):
(JSC::UString::utf8):

• runtime/UString.h:

(JSC::UString::~UString):
(JSC::UString::isNull):
(JSC::UString::isEmpty):
(JSC::UString::impl):

• wtf/text/WTFString.cpp:

(WTF::String::utf8):

• wtf/text/WTFString.h:

(WTF::String::~String):
(WTF::String::swap):
(WTF::String::isNull):
(WTF::String::isEmpty):
(WTF::String::impl):
(WTF::String::length):
(WTF::String::String):
(WTF::String::isHashTableDeletedValue):

WebCore:

• WebCore.xcodeproj/project.pbxproj:
• bindings/js/JSDOMWindowCustom.cpp:

(WebCore::JSDOMWindow::getOwnPropertySlot):
(WebCore::JSDOMWindow::getOwnPropertyDescriptor):

• bridge/NP_jsobject.cpp:

(_NPN_Enumerate):

• bridge/c/c_utility.cpp:

(JSC::Bindings::convertValueToNPVariant):

• bridge/jni/JNIBridge.cpp:

(JavaParameter::JavaParameter):
(JavaMethod::JavaMethod):
(JavaMethod::signature):
(JavaMethod::methodID):

• bridge/jni/JNIBridge.h:

(JSC::Bindings::JavaString::utf8):
(JSC::Bindings::JavaParameter::type):
(JSC::Bindings::JavaMethod::returnType):

• bridge/jni/jni_jsobject.mm:

(JavaJSObject::call):
(JavaJSObject::eval):
(JavaJSObject::getMember):
(JavaJSObject::setMember):
(JavaJSObject::removeMember):
(JavaJSObject::convertJObjectToValue):

• bridge/jni/jsc/JNIBridgeJSC.cpp:

(JavaField::JavaField):
(JavaField::valueFromInstance):
(JavaField::setValueToInstance):

• bridge/jni/jsc/JNIBridgeJSC.h:

(JSC::Bindings::JavaField::type):

• bridge/jni/jsc/JavaInstanceJSC.cpp:

(JavaInstance::invokeMethod):

• bridge/jni/jsc/JavaStringJSC.h:

(JSC::Bindings::JavaStringImpl::utf8):

• bridge/runtime_array.cpp:

(JSC::RuntimeArray::getOwnPropertySlot):
(JSC::RuntimeArray::getOwnPropertyDescriptor):
(JSC::RuntimeArray::put):

WebKit/mac:

• Plugins/Hosted/NetscapePluginInstanceProxy.mm:

(WebKit::NetscapePluginInstanceProxy::enumerate):

WebKit/wx:

• WebFrame.cpp:

(wxWebFrame::RunScript):

WebKit2:

• WebProcess/Plugins/JSNPObject.cpp:

(WebKit::npIdentifierFromIdentifier):

• WebProcess/Plugins/NPJSObject.cpp:

(WebKit::NPJSObject::enumerate):

• WebProcess/Plugins/NPRuntimeObjectMap.cpp:

(WebKit::NPRuntimeObjectMap::convertJSValueToNPVariant):

File:

• trunk/JavaScriptCore/runtime/UString.cpp (modified) (2 diffs)

trunk/JavaScriptCore/runtime/UString.cpp

@@ -258 +258 @@
     }
 
-    // FIXME: If tolerateTrailingJunk is true, then we want to tolerate junk 
-    // after the number, even if it contains invalid UTF-16 sequences. So we
-    // shouldn't use the UTF8String function, which returns null when it
-    // encounters invalid UTF-16. Further, we have no need to convert the
-    // non-ASCII characters to UTF-8, so the UTF8String does quite a bit of
-    // unnecessary work.
-
-    // FIXME: The space skipping code below skips only ASCII spaces, but callers
-    // need to skip all StrWhiteSpace. The isStrWhiteSpace function does the
-    // right thing but requires UChar, not char, for its argument.
-
     const UChar* data = this->characters();
     const UChar* end = data + size;
@@ -595 +584 @@
 }
 
-CString UString::UTF8String(bool strict) const
-{
-    // Allocate a buffer big enough to hold all the characters.
-    const unsigned len = length();
-    Vector<char, 1024> buffer(len * 3);
-
-    // Convert to runs of 8-bit characters.
-    char* p = buffer.data();
-    const UChar* d = reinterpret_cast<const UChar*>(&characters()[0]);
-    ConversionResult result = convertUTF16ToUTF8(&d, d + len, &p, p + buffer.size(), strict);
-    if (result != conversionOK)
+// Helper to write a three-byte UTF-8 code point to the buffer, caller must check room is available.
+static inline void putUTF8Triple(char*& buffer, UChar ch)
+{
+    ASSERT(ch >= 0x0800);
+    *buffer++ = static_cast<char>(((ch >> 12) & 0x0F) | 0xE0);
+    *buffer++ = static_cast<char>(((ch >> 6) & 0x3F) | 0x80);
+    *buffer++ = static_cast<char>((ch & 0x3F) | 0x80);
+}
+
+CString UString::utf8(bool strict) const
+{
+    unsigned length = this->length();
+    const UChar* characters = this->characters();
+
+    // Allocate a buffer big enough to hold all the characters
+    // (an individual UTF-16 UChar can only expand to 3 UTF-8 bytes).
+    // Optimization ideas, if we find this function is hot:
+    //  * We could speculatively create a CStringBuffer to contain 'length' 
+    //    characters, and resize if necessary (i.e. if the buffer contains
+    //    non-ascii characters). (Alternatively, scan the buffer first for
+    //    ascii characters, so we know this will be sufficient).
+    //  * We could allocate a CStringBuffer with an appropriate size to
+    //    have a good chance of being able to write the string into the
+    //    buffer without reallocing (say, 1.5 x length).
+    Vector<char, 1024> bufferVector(length * 3);
+
+    char* buffer = bufferVector.data();
+    ConversionResult result = convertUTF16ToUTF8(&characters, characters + length, &buffer, buffer + bufferVector.size(), strict);
+    ASSERT(result != targetExhausted); // (length * 3) should be sufficient for any conversion
+
+    // Only produced from strict conversion.
+    if (result == sourceIllegal)
         return CString();
 
-    return CString(buffer.data(), p - buffer.data());
+    // Check for an unconverted high surrogate.
+    if (result == sourceExhausted) {
+        if (strict)
+            return CString();
+        // This should be one unpaired high surrogate. Treat it the same
+        // was as an unpaired high surrogate would have been handled in
+        // the middle of a string with non-strict conversion - which is
+        // to say, simply encode it to UTF-8.
+        ASSERT((characters + 1) == (this->characters() + length));
+        ASSERT((*characters >= 0xD800) && (*characters <= 0xDBFF));
+        // There should be room left, since one UChar hasn't been converted.
+        ASSERT((buffer + 3) <= (buffer + bufferVector.size()));
+        putUTF8Triple(buffer, *characters);
+    }
+
+    return CString(bufferVector.data(), buffer - bufferVector.data());
 }