Attachment 368432 Details for Bug 195535 – Patch

[patch] Patch

bug-195535-20190428091224.patch (text/plain), 67.00 KB, created by Darin Adler on 2019-04-28 09:12:31 PDT

(hide)

Description:

Filename:

MIME Type:

Creator: Darin Adler

Created: 2019-04-28 09:12:31 PDT

Size: 67.00 KB

patch

obsolete

>Subversion Revision: 244723
>diff --git a/Source/JavaScriptCore/ChangeLog b/Source/JavaScriptCore/ChangeLog
>index 28aeca460ca65580a9ae60e98de7e15fada6d41b..eb68fb4ee51640a8e8a92873a1b740988f535bc7 100644
>--- a/Source/JavaScriptCore/ChangeLog
>+++ b/Source/JavaScriptCore/ChangeLog
>@@ -1,3 +1,28 @@
>+2019-04-28  Darin Adler  <darin@apple.com>
>+
>+        WebKit has too much of its own UTF-8 code and should rely more on ICU's UTF-8 support
>+        https://bugs.webkit.org/show_bug.cgi?id=195535
>+
>+        Reviewed by NOBODY (OOPS!).
>+
>+        * API/JSClassRef.cpp: Removed uneeded include of UTF8Conversion.h.
>+
>+        * API/JSStringRef.cpp:
>+        (JSStringCreateWithUTF8CString): Updated for changes to convertUTF8ToUTF16.
>+        (JSStringGetUTF8CString): Removed unneeded "true" to get the strict version of
>+        convertUTF16ToUTF8, since that is the default. Also updated for changes to
>+        CompletionResult.
>+
>+        * runtime/JSGlobalObjectFunctions.cpp:
>+        (JSC::decode): Stop using UTF8SequenceLength, and instead use U8_COUNT_TRAIL_BYTES
>+        and U8_MAX_LENGTH. Instead of decodeUTF8Sequence, use U8_NEXT. Also use U_IS_BMP,
>+        U_IS_SUPPLEMENTARY, U16_LEAD, U16_TRAIL, and U_IS_SURROGATE instead of our own
>+        equivalents, since these macros from ICU are correct and efficient.
>+
>+        * wasm/WasmParser.h:
>+        (JSC::Wasm::Parser<SuccessType>::consumeUTF8String): Updated for changes to
>+        convertUTF8ToUTF16.
>+
> 2019-04-26  Keith Rollin  <krollin@apple.com>
> 
>         Enable new build rule for post-processing headers when using XCBuild
>diff --git a/Source/WTF/ChangeLog b/Source/WTF/ChangeLog
>index 475cdd28b74cf6c19251851e75de9c279aebd116..08a3b9831226520784b7718c809df76b14dacc95 100644
>--- a/Source/WTF/ChangeLog
>+++ b/Source/WTF/ChangeLog
>@@ -1,3 +1,71 @@
>+2019-04-28  Darin Adler  <darin@apple.com>
>+
>+        WebKit has too much of its own UTF-8 code and should rely more on ICU's UTF-8 support
>+        https://bugs.webkit.org/show_bug.cgi?id=195535
>+
>+        Reviewed by NOBODY (OOPS!).
>+
>+        * wtf/text/AtomicString.cpp:
>+        (WTF::AtomicString::fromUTF8Internal): Added code to compute string length when the
>+        end is nullptr; this behavior used to be implemented inside the
>+        calculateStringHashAndLengthFromUTF8MaskingTop8Bits function.
>+
>+        * wtf/text/AtomicStringImpl.cpp:
>+        (WTF::HashAndUTF8CharactersTranslator::translate): Updated for change to
>+        convertUTF8ToUTF16.
>+
>+        * wtf/text/AtomicStringImpl.h: Took the WTF_EXPORT_PRIVATE off of the
>+        AtomicStringImpl::addUTF8 function. This is used only inside a non-inlined function in
>+        the AtomicString class and its behavior changed subtly in this patch; it's helpful
>+        to document that it's not exported.
>+
>+        * wtf/text/StringImpl.cpp:
>+        (WTF::StringImpl::utf8Impl): Don't pass "true" for strictness to convertUTF16ToUTF8
>+        since strict is the default. Also updated for changes to ConversionResult.
>+        (WTF::StringImpl::utf8ForCharacters): Ditto.
>+        (WTF::StringImpl::tryGetUtf8ForRange const): Ditto.
>+
>+        * wtf/text/StringView.cpp: Removed uneeded include of UTF8Conversion.h.
>+
>+        * wtf/text/WTFString.cpp:
>+        (WTF::String::fromUTF8): Updated for change to convertUTF8ToUTF16.
>+
>+        * wtf/unicode/UTF8Conversion.cpp:
>+        (WTF::Unicode::inlineUTF8SequenceLengthNonASCII): Deleted.
>+        (WTF::Unicode::inlineUTF8SequenceLength): Deleted.
>+        (WTF::Unicode::UTF8SequenceLength): Deleted.
>+        (WTF::Unicode::decodeUTF8Sequence): Deleted.
>+        (WTF::Unicode::convertLatin1ToUTF8): Use U8_APPEND, enabling us to remove
>+        almost everything in the function. There is room for further simplification,
>+        since most callers have lengths rather than end pointers for the source buffer,
>+        all but two of the values of CompletionResult are unused, all but one caller
>+        supplies a buffer size known to be sufficient, so those don't need a return
>+        value at all, nor do they need to pass an end of buffer.
>+        (WTF::Unicode::convertUTF16ToUTF8): Use U_IS_LEAD, U_IS_TRAIL,
>+        U16_GET_SUPPLEMENTARY, U_IS_SURROGATE, and U8_APPEND. Also changed behavior
>+        for non-strict mode so that unpaired surrogates will be turned into the
>+        replacement character instead of invalid UTF-8 sequences, because U8_APPEND
>+        won't create an invalid UTF-8 sequence, and because we don't need to do that
>+        for any good reason at any call site.
>+        (WTF::Unicode::isLegalUTF8): Deleted.
>+        (WTF::Unicode::readUTF8Sequence): Deleted.
>+        (WTF::Unicode::convertUTF8ToUTF16): Use U8_NEXT instead of
>+        inlineUTF8SequenceLength, isLegalUTF8, and readUTF8Sequence. Use
>+        U16_APPEND instead of lots of code that does the same thing. There is
>+        room for further simplification since most callers don't need the "all ASCII"
>+        feature and could probably pass the arguments in a more natural way.
>+        (WTF::Unicode::calculateStringHashAndLengthFromUTF8MaskingTop8Bits):
>+        Use U8_NEXT instead of isLegalUTF8, readUTF8Sequence, and various
>+        error handling checks for things that are handled by U8_NEXT. Also removed
>+        support for passing nullptr for end to specify a null-terminated string.
>+        (WTF::Unicode::equalUTF16WithUTF8): Ditto.
>+
>+        * wtf/unicode/UTF8Conversion.h: Removed UTF8SequenceLength and
>+        decodeUTF8Sequence. Changed the ConversionResult to match WebKit coding
>+        style, with an eye toward perhaps removing it in the future. Changed
>+        the convertUTF8ToUTF16 return value to a boolean and removed the "strict"
>+        argument since no caller was passing false. Tweaked comments.
>+
> 2019-04-26  Don Olmstead  <don.olmstead@sony.com>
> 
>         Add WTF::findIgnoringASCIICaseWithoutLength to replace strcasestr
>diff --git a/Source/WebCore/ChangeLog b/Source/WebCore/ChangeLog
>index 0a8e4dc47de1be0c2adf1b8bb2c9fda576918b0e..a7d55876c5aa23ec4bdf5e8f92fb700bc7d4cd51 100644
>--- a/Source/WebCore/ChangeLog
>+++ b/Source/WebCore/ChangeLog
>@@ -1,3 +1,21 @@
>+2019-04-28  Darin Adler  <darin@apple.com>
>+
>+        WebKit has too much of its own UTF-8 code and should rely more on ICU's UTF-8 support
>+        https://bugs.webkit.org/show_bug.cgi?id=195535
>+
>+        Reviewed by NOBODY (OOPS!).
>+
>+        * platform/SharedBuffer.cpp:
>+        (WebCore::utf8Buffer): Removed unnecessary "strict" argument to convertUTF16ToUTF8 since
>+        that is the default behavior. Also updated for changes to CompletionResult.
>+
>+        * xml/XSLTProcessorLibxslt.cpp:
>+        (WebCore::writeToStringBuilder): Removed unnecessary use of StringBuffer for a temporary
>+        buffer for characters. Rewrote to use U8_NEXT and U16_APPEND directly.
>+
>+        * xml/parser/XMLDocumentParserLibxml2.cpp:
>+        (WebCore::convertUTF16EntityToUTF8): Updated for changes to CompletionResult.
>+
> 2019-04-27  Simon Fraser  <simon.fraser@apple.com>
> 
>         Move some Compositing logging to the Layers log channel
>diff --git a/Source/WebKit/ChangeLog b/Source/WebKit/ChangeLog
>index 3433e25307281486aca95a901ae873c894eb6e03..109eb51e1dd76eccffed45e39c6b5286260b7b6f 100644
>--- a/Source/WebKit/ChangeLog
>+++ b/Source/WebKit/ChangeLog
>@@ -1,3 +1,15 @@
>+2019-04-28  Darin Adler  <darin@apple.com>
>+
>+        WebKit has too much of its own UTF-8 code and should rely more on ICU's UTF-8 support
>+        https://bugs.webkit.org/show_bug.cgi?id=195535
>+
>+        Reviewed by NOBODY (OOPS!).
>+
>+        * Shared/API/APIString.h: Removed uneeded includes and also switched to #pragma once.
>+
>+        * Shared/API/c/WKString.cpp: Moved include of UTF8Conversion.h here.
>+        (WKStringGetUTF8CStringImpl): Updated for changes to CompletionResult.
>+
> 2019-04-27  Chris Dumez  <cdumez@apple.com>
> 
>         Improve safety of MachMessage class
>diff --git a/Source/JavaScriptCore/API/JSClassRef.cpp b/Source/JavaScriptCore/API/JSClassRef.cpp
>index 4cc97de40f3baca6973ca80be47dc907e9676496..d4583d8e16515d614a59c9acc383a3cc111f60ad 100644
>--- a/Source/JavaScriptCore/API/JSClassRef.cpp
>+++ b/Source/JavaScriptCore/API/JSClassRef.cpp
>@@ -35,10 +35,8 @@
> #include "ObjectPrototype.h"
> #include "JSCInlines.h"
> #include <wtf/text/StringHash.h>
>-#include <wtf/unicode/UTF8Conversion.h>
> 
> using namespace JSC;
>-using namespace WTF::Unicode;
> 
> const JSClassDefinition kJSClassDefinitionEmpty = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 };
> 
>diff --git a/Source/JavaScriptCore/API/JSStringRef.cpp b/Source/JavaScriptCore/API/JSStringRef.cpp
>index 04d1ca73d3eabfcc062d5f7628e16ae05965c6ec..c33be0dae284e0b6522ac3f85144691d6084a796 100644
>--- a/Source/JavaScriptCore/API/JSStringRef.cpp
>+++ b/Source/JavaScriptCore/API/JSStringRef.cpp
>@@ -49,7 +49,7 @@ JSStringRef JSStringCreateWithUTF8CString(const char* string)
>         UChar* p = buffer.data();
>         bool sourceIsAllASCII;
>         const LChar* stringStart = reinterpret_cast<const LChar*>(string);
>-        if (conversionOK == convertUTF8ToUTF16(&string, string + length, &p, p + length, &sourceIsAllASCII)) {
>+        if (convertUTF8ToUTF16(string, string + length, &p, p + length, &sourceIsAllASCII)) {
>             if (sourceIsAllASCII)
>                 return &OpaqueJSString::create(stringStart, length).leakRef();
>             return &OpaqueJSString::create(buffer.data(), p - buffer.data()).leakRef();
>@@ -108,11 +108,11 @@ size_t JSStringGetUTF8CString(JSStringRef string, char* buffer, size_t bufferSiz
>         result = convertLatin1ToUTF8(&source, source + string->length(), &destination, destination + bufferSize - 1);
>     } else {
>         const UChar* source = string->characters16();
>-        result = convertUTF16ToUTF8(&source, source + string->length(), &destination, destination + bufferSize - 1, true);
>+        result = convertUTF16ToUTF8(&source, source + string->length(), &destination, destination + bufferSize - 1);
>     }
> 
>     *destination++ = '\0';
>-    if (result != conversionOK && result != targetExhausted)
>+    if (result != ConversionOK && result != TargetExhausted)
>         return 0;
> 
>     return destination - buffer;
>diff --git a/Source/JavaScriptCore/runtime/JSGlobalObjectFunctions.cpp b/Source/JavaScriptCore/runtime/JSGlobalObjectFunctions.cpp
>index 8edf49f1c843a179221f68cf4201dcb00b8af88e..4c37285306798642418117be69a316b0fc15f29d 100644
>--- a/Source/JavaScriptCore/runtime/JSGlobalObjectFunctions.cpp
>+++ b/Source/JavaScriptCore/runtime/JSGlobalObjectFunctions.cpp
>@@ -58,12 +58,9 @@
> #include <wtf/MathExtras.h>
> #include <wtf/dtoa.h>
> #include <wtf/text/StringBuilder.h>
>-#include <wtf/unicode/UTF8Conversion.h>
> 
> namespace JSC {
> 
>-using namespace WTF::Unicode;
>-
> const ASCIILiteral ObjectProtoCalledOnNullOrUndefinedError { "Object.prototype.__proto__ called on null or undefined"_s };
> 
> template<unsigned charactersCount>
>@@ -184,10 +181,10 @@ static JSValue decode(ExecState* exec, const CharType* characters, int length, c
>             int charLen = 0;
>             if (k <= length - 3 && isASCIIHexDigit(p[1]) && isASCIIHexDigit(p[2])) {
>                 const char b0 = Lexer<CharType>::convertHex(p[1], p[2]);
>-                const int sequenceLen = UTF8SequenceLength(b0);
>-                if (sequenceLen && k <= length - sequenceLen * 3) {
>+                const int sequenceLen = 1 + U8_COUNT_TRAIL_BYTES(b0);
>+                if (k <= length - sequenceLen * 3) {
>                     charLen = sequenceLen * 3;
>-                    char sequence[5];
>+                    uint8_t sequence[U8_MAX_LENGTH];
>                     sequence[0] = b0;
>                     for (int i = 1; i < sequenceLen; ++i) {
>                         const CharType* q = p + i * 3;
>@@ -199,16 +196,20 @@ static JSValue decode(ExecState* exec, const CharType* characters, int length, c
>                         }
>                     }
>                     if (charLen != 0) {
>-                        sequence[sequenceLen] = 0;
>-                        const int character = decodeUTF8Sequence(sequence);
>-                        if (character < 0 || character >= 0x110000)
>+                        UChar32 character;
>+                        int32_t offset = 0;
>+                        U8_NEXT(sequence, offset, sequenceLen, character);
>+                        if (character < 0)
>                             charLen = 0;
>-                        else if (character >= 0x10000) {
>+                        else if (!U_IS_BMP(character)) {
>                             // Convert to surrogate pair.
>-                            builder.append(static_cast<UChar>(0xD800 | ((character - 0x10000) >> 10)));
>-                            u = static_cast<UChar>(0xDC00 | ((character - 0x10000) & 0x3FF));
>-                        } else
>+                            ASSERT(U_IS_SUPPLEMENTARY(character));
>+                            builder.append(U16_LEAD(character));
>+                            u = U16_TRAIL(character);
>+                        } else {
>+                            ASSERT(!U_IS_SURROGATE(character));
>                             u = static_cast<UChar>(character);
>+                        }
>                     }
>                 }
>             }
>diff --git a/Source/JavaScriptCore/wasm/WasmParser.h b/Source/JavaScriptCore/wasm/WasmParser.h
>index fc500c033ac18bb4807ecf7607eaef2aa31e27a8..a9744e68b37421c6fedb37930636d5b16e75937a 100644
>--- a/Source/JavaScriptCore/wasm/WasmParser.h
>+++ b/Source/JavaScriptCore/wasm/WasmParser.h
>@@ -162,7 +162,7 @@ ALWAYS_INLINE bool Parser<SuccessType>::consumeUTF8String(Name& result, size_t s
> 
>         UChar* bufferCurrent = bufferStart;
>         const char* stringCurrent = reinterpret_cast<const char*>(stringStart);
>-        if (WTF::Unicode::convertUTF8ToUTF16(&stringCurrent, reinterpret_cast<const char *>(stringStart + stringLength), &bufferCurrent, bufferCurrent + buffer.size()) != WTF::Unicode::conversionOK)
>+        if (!WTF::Unicode::convertUTF8ToUTF16(stringCurrent, reinterpret_cast<const char *>(stringStart + stringLength), &bufferCurrent, bufferCurrent + buffer.size()))
>             return false;
>     }
> 
>diff --git a/Source/WTF/wtf/text/AtomicString.cpp b/Source/WTF/wtf/text/AtomicString.cpp
>index fba7c9a774072869f58549d3a5117aea896d7bf7..ffdca7f9a76c0ca6df7c7a6d9c3912e7a57daad1 100644
>--- a/Source/WTF/wtf/text/AtomicString.cpp
>+++ b/Source/WTF/wtf/text/AtomicString.cpp
>@@ -113,19 +113,24 @@ AtomicString AtomicString::number(double number)
>     return numberToString(number, buffer);
> }
> 
>-AtomicString AtomicString::fromUTF8Internal(const char* charactersStart, const char* charactersEnd)
>+AtomicString AtomicString::fromUTF8Internal(const char* start, const char* end)
> {
>-    auto impl = AtomicStringImpl::addUTF8(charactersStart, charactersEnd);
>-    if (!impl)
>-        return nullAtom();
>-    return impl.get();
>+    ASSERT(start);
>+
>+    // Caller needs to handle empty string.
>+    ASSERT(!end || end > start);
>+    ASSERT(end || start[0]);
>+
>+    return AtomicStringImpl::addUTF8(start, end ? end : start + std::strlen(start));
> }
> 
> #ifndef NDEBUG
>+
> void AtomicString::show() const
> {
>     m_string.show();
> }
>+
> #endif
> 
> WTF_EXPORT_PRIVATE LazyNeverDestroyed<AtomicString> nullAtomData;
>diff --git a/Source/WTF/wtf/text/AtomicStringImpl.cpp b/Source/WTF/wtf/text/AtomicStringImpl.cpp
>index 14d82d2cc1cd066d7c44de37d9cab1fdbe9a7d91..601feb5fd33130bec46050236e2ec41d809c4fef 100644
>--- a/Source/WTF/wtf/text/AtomicStringImpl.cpp
>+++ b/Source/WTF/wtf/text/AtomicStringImpl.cpp
>@@ -219,7 +219,7 @@ struct HashAndUTF8CharactersTranslator {
> 
>         bool isAllASCII;
>         const char* source = buffer.characters;
>-        if (convertUTF8ToUTF16(&source, source + buffer.length, &target, target + buffer.utf16Length, &isAllASCII) != conversionOK)
>+        if (!convertUTF8ToUTF16(source, source + buffer.length, &target, target + buffer.utf16Length, &isAllASCII))
>             ASSERT_NOT_REACHED();
> 
>         if (isAllASCII)
>diff --git a/Source/WTF/wtf/text/AtomicStringImpl.h b/Source/WTF/wtf/text/AtomicStringImpl.h
>index d84623c9c8ffbb55c2541a9dabb83bde2402b055..36a04f4c4b8c8c1518b18796168289df8a384ff2 100644
>--- a/Source/WTF/wtf/text/AtomicStringImpl.h
>+++ b/Source/WTF/wtf/text/AtomicStringImpl.h
>@@ -56,7 +56,8 @@ public:
>     WTF_EXPORT_PRIVATE static Ref<AtomicStringImpl> addLiteral(const char* characters, unsigned length);
> 
>     // Returns null if the input data contains an invalid UTF-8 sequence.
>-    WTF_EXPORT_PRIVATE static RefPtr<AtomicStringImpl> addUTF8(const char* start, const char* end);
>+    static RefPtr<AtomicStringImpl> addUTF8(const char* start, const char* end);
>+
> #if USE(CF)
>     WTF_EXPORT_PRIVATE static RefPtr<AtomicStringImpl> add(CFStringRef);
> #endif
>diff --git a/Source/WTF/wtf/text/StringImpl.cpp b/Source/WTF/wtf/text/StringImpl.cpp
>index dd325ca0b3375faac065748afc4c6e5acfe070ec..7a9290aa4c5811a191e755a84d94361bbc2f2f72 100644
>--- a/Source/WTF/wtf/text/StringImpl.cpp
>+++ b/Source/WTF/wtf/text/StringImpl.cpp
>@@ -1756,11 +1756,11 @@ UTF8ConversionError StringImpl::utf8Impl(const UChar* characters, unsigned lengt
>         char* bufferEnd = buffer + bufferSize;
>         while (characters < charactersEnd) {
>             // Use strict conversion to detect unpaired surrogates.
>-            ConversionResult result = convertUTF16ToUTF8(&characters, charactersEnd, &buffer, bufferEnd, true);
>-            ASSERT(result != targetExhausted);
>+            ConversionResult result = convertUTF16ToUTF8(&characters, charactersEnd, &buffer, bufferEnd);
>+            ASSERT(result != TargetExhausted);
>             // Conversion fails when there is an unpaired surrogate.
>             // Put replacement character (U+FFFD) instead of the unpaired surrogate.
>-            if (result != conversionOK) {
>+            if (result != ConversionOK) {
>                 ASSERT((0xD800 <= *characters && *characters <= 0xDFFF));
>                 // There should be room left, since one UChar hasn't been converted.
>                 ASSERT((buffer + 3) <= bufferEnd);
>@@ -1772,16 +1772,16 @@ UTF8ConversionError StringImpl::utf8Impl(const UChar* characters, unsigned lengt
>         bool strict = mode == StrictConversion;
>         const UChar* originalCharacters = characters;
>         ConversionResult result = convertUTF16ToUTF8(&characters, characters + length, &buffer, buffer + bufferSize, strict);
>-        ASSERT(result != targetExhausted); // (length * 3) should be sufficient for any conversion
>+        ASSERT(result != TargetExhausted); // (length * 3) should be sufficient for any conversion
> 
>         // Only produced from strict conversion.
>-        if (result == sourceIllegal) {
>+        if (result == SourceIllegal) {
>             ASSERT(strict);
>             return UTF8ConversionError::IllegalSource;
>         }
> 
>         // Check for an unconverted high surrogate.
>-        if (result == sourceExhausted) {
>+        if (result == SourceExhausted) {
>             if (strict)
>                 return UTF8ConversionError::SourceExhausted;
>             // This should be one unpaired high surrogate. Treat it the same
>@@ -1810,7 +1810,7 @@ Expected<CString, UTF8ConversionError> StringImpl::utf8ForCharacters(const LChar
>     char* buffer = bufferVector.data();
>     const LChar* source = characters;
>     ConversionResult result = convertLatin1ToUTF8(&source, source + length, &buffer, buffer + bufferVector.size());
>-    ASSERT_UNUSED(result, result != targetExhausted); // (length * 3) should be sufficient for any conversion
>+    ASSERT_UNUSED(result, result != TargetExhausted); // (length * 3) should be sufficient for any conversion
>     return CString(bufferVector.data(), buffer - bufferVector.data());
> }
> 
>@@ -1856,7 +1856,7 @@ Expected<CString, UTF8ConversionError> StringImpl::tryGetUtf8ForRange(unsigned o
>         const LChar* characters = this->characters8() + offset;
> 
>         ConversionResult result = convertLatin1ToUTF8(&characters, characters + length, &buffer, buffer + bufferVector.size());
>-        ASSERT_UNUSED(result, result != targetExhausted); // (length * 3) should be sufficient for any conversion
>+        ASSERT_UNUSED(result, result != TargetExhausted); // (length * 3) should be sufficient for any conversion
>     } else {
>         UTF8ConversionError error = utf8Impl(this->characters16() + offset, length, buffer, bufferVector.size(), mode);
>         if (error != UTF8ConversionError::None)
>diff --git a/Source/WTF/wtf/text/StringView.cpp b/Source/WTF/wtf/text/StringView.cpp
>index ee16b9cd0122c4469ce23fc714bc660d4d86c61f..78b5e2f5ad3f8fb2f746d23ddf28d0caad811ea3 100644
>--- a/Source/WTF/wtf/text/StringView.cpp
>+++ b/Source/WTF/wtf/text/StringView.cpp
>@@ -35,12 +35,9 @@ SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
> #include <wtf/NeverDestroyed.h>
> #include <wtf/Optional.h>
> #include <wtf/text/TextBreakIterator.h>
>-#include <wtf/unicode/UTF8Conversion.h>
> 
> namespace WTF {
> 
>-using namespace Unicode;
>-
> bool StringView::containsIgnoringASCIICase(const StringView& matchString) const
> {
>     return findIgnoringASCIICase(matchString) != notFound;
>diff --git a/Source/WTF/wtf/text/WTFString.cpp b/Source/WTF/wtf/text/WTFString.cpp
>index dcd42cfb8f10d5a8574d152e0f2392de33d8780e..f5acba8374cba236f86eec5e7b7400b6bb6bb360 100644
>--- a/Source/WTF/wtf/text/WTFString.cpp
>+++ b/Source/WTF/wtf/text/WTFString.cpp
>@@ -859,7 +859,7 @@ String String::fromUTF8(const LChar* stringStart, size_t length)
>  
>     UChar* bufferCurrent = bufferStart;
>     const char* stringCurrent = reinterpret_cast<const char*>(stringStart);
>-    if (convertUTF8ToUTF16(&stringCurrent, reinterpret_cast<const char *>(stringStart + length), &bufferCurrent, bufferCurrent + buffer.size()) != conversionOK)
>+    if (!convertUTF8ToUTF16(stringCurrent, reinterpret_cast<const char *>(stringStart + length), &bufferCurrent, bufferCurrent + buffer.size()))
>         return String();
> 
>     unsigned utf16Length = bufferCurrent - bufferStart;
>diff --git a/Source/WTF/wtf/unicode/UTF8Conversion.cpp b/Source/WTF/wtf/unicode/UTF8Conversion.cpp
>index 6a4ee831573f2565ac6607804fac1f87006074e0..28dcf8925121f07af1940e111c9057519e8664fa 100644
>--- a/Source/WTF/wtf/unicode/UTF8Conversion.cpp
>+++ b/Source/WTF/wtf/unicode/UTF8Conversion.cpp
>@@ -34,425 +34,135 @@
> namespace WTF {
> namespace Unicode {
> 
>-inline int inlineUTF8SequenceLengthNonASCII(char b0)
>+ConversionResult convertLatin1ToUTF8(const LChar** sourceStart, const LChar* sourceEnd, char** targetStart, char* targetEnd)
> {
>-    if ((b0 & 0xC0) != 0xC0)
>-        return 0;
>-    if ((b0 & 0xE0) == 0xC0)
>-        return 2;
>-    if ((b0 & 0xF0) == 0xE0)
>-        return 3;
>-    if ((b0 & 0xF8) == 0xF0)
>-        return 4;
>-    return 0;
>-}
>-
>-inline int inlineUTF8SequenceLength(char b0)
>-{
>-    return isASCII(b0) ? 1 : inlineUTF8SequenceLengthNonASCII(b0);
>-}
>-
>-int UTF8SequenceLength(char b0)
>-{
>-    return isASCII(b0) ? 1 : inlineUTF8SequenceLengthNonASCII(b0);
>-}
>-
>-int decodeUTF8Sequence(const char* sequence)
>-{
>-    // Handle 0-byte sequences (never valid).
>-    const unsigned char b0 = sequence[0];
>-    const int length = inlineUTF8SequenceLength(b0);
>-    if (length == 0)
>-        return -1;
>-
>-    // Handle 1-byte sequences (plain ASCII).
>-    const unsigned char b1 = sequence[1];
>-    if (length == 1) {
>-        if (b1)
>-            return -1;
>-        return b0;
>-    }
>-
>-    // Handle 2-byte sequences.
>-    if ((b1 & 0xC0) != 0x80)
>-        return -1;
>-    const unsigned char b2 = sequence[2];
>-    if (length == 2) {
>-        if (b2)
>-            return -1;
>-        const int c = ((b0 & 0x1F) << 6) | (b1 & 0x3F);
>-        if (c < 0x80)
>-            return -1;
>-        return c;
>-    }
>-
>-    // Handle 3-byte sequences.
>-    if ((b2 & 0xC0) != 0x80)
>-        return -1;
>-    const unsigned char b3 = sequence[3];
>-    if (length == 3) {
>-        if (b3)
>-            return -1;
>-        const int c = ((b0 & 0xF) << 12) | ((b1 & 0x3F) << 6) | (b2 & 0x3F);
>-        if (c < 0x800)
>-            return -1;
>-        // UTF-16 surrogates should never appear in UTF-8 data.
>-        if (c >= 0xD800 && c <= 0xDFFF)
>-            return -1;
>-        return c;
>-    }
>-
>-    // Handle 4-byte sequences.
>-    if ((b3 & 0xC0) != 0x80)
>-        return -1;
>-    const unsigned char b4 = sequence[4];
>-    if (length == 4) {
>-        if (b4)
>-            return -1;
>-        const int c = ((b0 & 0x7) << 18) | ((b1 & 0x3F) << 12) | ((b2 & 0x3F) << 6) | (b3 & 0x3F);
>-        if (c < 0x10000 || c > 0x10FFFF)
>-            return -1;
>-        return c;
>-    }
>-
>-    return -1;
>-}
>-
>-// Once the bits are split out into bytes of UTF-8, this is a mask OR-ed
>-// into the first byte, depending on how many bytes follow.  There are
>-// as many entries in this table as there are UTF-8 sequence types.
>-// (I.e., one byte sequence, two byte... etc.). Remember that sequencs
>-// for *legal* UTF-8 will be 4 or fewer bytes total.
>-static const unsigned char firstByteMark[7] = { 0x00, 0x00, 0xC0, 0xE0, 0xF0, 0xF8, 0xFC };
>-
>-ConversionResult convertLatin1ToUTF8(
>-    const LChar** sourceStart, const LChar* sourceEnd, 
>-    char** targetStart, char* targetEnd)
>-{
>-    ConversionResult result = conversionOK;
>-    const LChar* source = *sourceStart;
>+    ConversionResult result = ConversionOK;
>+    const LChar* source;
>     char* target = *targetStart;
>-    while (source < sourceEnd) {
>-        UChar32 ch;
>-        unsigned short bytesToWrite = 0;
>-        const UChar32 byteMask = 0xBF;
>-        const UChar32 byteMark = 0x80; 
>-        const LChar* oldSource = source; // In case we have to back up because of target overflow.
>-        ch = static_cast<unsigned short>(*source++);
>-
>-        // Figure out how many bytes the result will require
>-        if (ch < (UChar32)0x80)
>-            bytesToWrite = 1;
>-        else
>-            bytesToWrite = 2;
>-
>-        target += bytesToWrite;
>-        if (target > targetEnd) {
>-            source = oldSource; // Back up source pointer!
>-            target -= bytesToWrite;
>-            result = targetExhausted;
>+    UBool sawError = false;
>+    unsigned i = 0;
>+    for (source = *sourceStart; source < sourceEnd; ++source) {
>+        U8_APPEND(reinterpret_cast<uint8_t*>(target), i, targetEnd - *targetStart, *source, sawError);
>+        if (sawError) {
>+            result = TargetExhausted;
>             break;
>         }
>-        switch (bytesToWrite) { // note: everything falls through.
>-        case 2:
>-            *--target = (char)((ch | byteMark) & byteMask);
>-            ch >>= 6;
>-            FALLTHROUGH;
>-        case 1:
>-            *--target =  (char)(ch | firstByteMark[bytesToWrite]);
>-        }
>-        target += bytesToWrite;
>     }
>     *sourceStart = source;
>-    *targetStart = target;
>+    *targetStart = target + i;
>     return result;
> }
> 
>-ConversionResult convertUTF16ToUTF8(
>-    const UChar** sourceStart, const UChar* sourceEnd, 
>-    char** targetStart, char* targetEnd, bool strict)
>+ConversionResult convertUTF16ToUTF8(const UChar** sourceStart, const UChar* sourceEnd, char** targetStart, char* targetEnd, bool strict)
> {
>-    ConversionResult result = conversionOK;
>+    ConversionResult result = ConversionOK;
>     const UChar* source = *sourceStart;
>     char* target = *targetStart;
>+    UBool sawError = false;
>+    unsigned i = 0;
>     while (source < sourceEnd) {
>         UChar32 ch;
>-        unsigned short bytesToWrite = 0;
>-        const UChar32 byteMask = 0xBF;
>-        const UChar32 byteMark = 0x80; 
>-        const UChar* oldSource = source; // In case we have to back up because of target overflow.
>-        ch = static_cast<unsigned short>(*source++);
>-        // If we have a surrogate pair, convert to UChar32 first.
>-        if (ch >= 0xD800 && ch <= 0xDBFF) {
>-            // If the 16 bits following the high surrogate are in the source buffer...
>-            if (source < sourceEnd) {
>-                UChar32 ch2 = static_cast<unsigned short>(*source);
>-                // If it's a low surrogate, convert to UChar32.
>-                if (ch2 >= 0xDC00 && ch2 <= 0xDFFF) {
>-                    ch = ((ch - 0xD800) << 10) + (ch2 - 0xDC00) + 0x0010000;
>-                    ++source;
>-                } else if (strict) { // it's an unpaired high surrogate
>-                    --source; // return to the illegal value itself
>-                    result = sourceIllegal;
>-                    break;
>-                }
>-            } else { // We don't have the 16 bits following the high surrogate.
>-                --source; // return to the high surrogate
>-                result = sourceExhausted;
>+        int j = 0;
>+        U16_NEXT(source, j, sourceEnd - source, ch);
>+        if (U_IS_SURROGATE(ch)) {
>+            if (source + j == sourceEnd && U_IS_SURROGATE_LEAD(ch)) {
>+                result = SourceExhausted;
>                 break;
>             }
>-        } else if (strict) {
>-            // UTF-16 surrogate values are illegal in UTF-32
>-            if (ch >= 0xDC00 && ch <= 0xDFFF) {
>-                --source; // return to the illegal value itself
>-                result = sourceIllegal;
>+            if (strict) {
>+                result = SourceIllegal;
>                 break;
>             }
>-        }
>-        // Figure out how many bytes the result will require
>-        if (ch < (UChar32)0x80) {
>-            bytesToWrite = 1;
>-        } else if (ch < (UChar32)0x800) {
>-            bytesToWrite = 2;
>-        } else if (ch < (UChar32)0x10000) {
>-            bytesToWrite = 3;
>-        } else if (ch < (UChar32)0x110000) {
>-            bytesToWrite = 4;
>-        } else {
>-            bytesToWrite = 3;
>             ch = replacementCharacter;
>         }
>+        if (ch >= 0x110000)
>+            ch = replacementCharacter;
> 
>-        target += bytesToWrite;
>-        if (target > targetEnd) {
>-            source = oldSource; // Back up source pointer!
>-            target -= bytesToWrite;
>-            result = targetExhausted;
>+        U8_APPEND(reinterpret_cast<uint8_t*>(target), i, targetEnd - target, ch, sawError);
>+        if (sawError) {
>+            result = TargetExhausted;
>             break;
>         }
>-        switch (bytesToWrite) { // note: everything falls through.
>-            case 4: *--target = (char)((ch | byteMark) & byteMask); ch >>= 6; FALLTHROUGH;
>-            case 3: *--target = (char)((ch | byteMark) & byteMask); ch >>= 6; FALLTHROUGH;
>-            case 2: *--target = (char)((ch | byteMark) & byteMask); ch >>= 6; FALLTHROUGH;
>-            case 1: *--target =  (char)(ch | firstByteMark[bytesToWrite]);
>-        }
>-        target += bytesToWrite;
>+
>+        source += j;
>     }
>     *sourceStart = source;
>-    *targetStart = target;
>+    *targetStart = target + i;
>     return result;
> }
> 
>-// This must be called with the length pre-determined by the first byte.
>-// If presented with a length > 4, this returns false.  The Unicode
>-// definition of UTF-8 goes up to 4-byte sequences.
>-static bool isLegalUTF8(const unsigned char* source, int length)
>+bool convertUTF8ToUTF16(const char* source, const char* sourceEnd, UChar** targetStart, UChar* targetEnd, bool* sourceAllASCII)
> {
>-    unsigned char a;
>-    const unsigned char* srcptr = source + length;
>-    switch (length) {
>-        default: return false;
>-        // Everything else falls through when "true"...
>-        case 4: if ((a = (*--srcptr)) < 0x80 || a > 0xBF) return false; FALLTHROUGH;
>-        case 3: if ((a = (*--srcptr)) < 0x80 || a > 0xBF) return false; FALLTHROUGH;
>-        case 2: if ((a = (*--srcptr)) > 0xBF) return false;
>-
>-        switch (*source) {
>-            // no fall-through in this inner switch
>-            case 0xE0: if (a < 0xA0) return false; break;
>-            case 0xED: if (a > 0x9F) return false; break;
>-            case 0xF0: if (a < 0x90) return false; break;
>-            case 0xF4: if (a > 0x8F) return false; break;
>-            default:   if (a < 0x80) return false;
>-        }
>-        FALLTHROUGH;
>-
>-        case 1: if (*source >= 0x80 && *source < 0xC2) return false;
>-    }
>-    if (*source > 0xF4)
>-        return false;
>-    return true;
>-}
>-
>-// Magic values subtracted from a buffer value during UTF8 conversion.
>-// This table contains as many values as there might be trailing bytes
>-// in a UTF-8 sequence.
>-static const UChar32 offsetsFromUTF8[6] = { 0x00000000UL, 0x00003080UL, 0x000E2080UL, 0x03C82080UL, static_cast<UChar32>(0xFA082080UL), static_cast<UChar32>(0x82082080UL) };
>-
>-static inline UChar32 readUTF8Sequence(const char*& sequence, unsigned length)
>-{
>-    UChar32 character = 0;
>-
>-    // The cases all fall through.
>-    switch (length) {
>-        case 6: character += static_cast<unsigned char>(*sequence++); character <<= 6; FALLTHROUGH;
>-        case 5: character += static_cast<unsigned char>(*sequence++); character <<= 6; FALLTHROUGH;
>-        case 4: character += static_cast<unsigned char>(*sequence++); character <<= 6; FALLTHROUGH;
>-        case 3: character += static_cast<unsigned char>(*sequence++); character <<= 6; FALLTHROUGH;
>-        case 2: character += static_cast<unsigned char>(*sequence++); character <<= 6; FALLTHROUGH;
>-        case 1: character += static_cast<unsigned char>(*sequence++);
>-    }
>-
>-    return character - offsetsFromUTF8[length - 1];
>-}
>-
>-ConversionResult convertUTF8ToUTF16(
>-    const char** sourceStart, const char* sourceEnd, 
>-    UChar** targetStart, UChar* targetEnd, bool* sourceAllASCII, bool strict)
>-{
>-    ConversionResult result = conversionOK;
>-    const char* source = *sourceStart;
>+    RELEASE_ASSERT(sourceEnd - source <= std::numeric_limits<int>::max());
>+    UBool error = false;
>     UChar* target = *targetStart;
>-    UChar orAllData = 0;
>-    while (source < sourceEnd) {
>-        int utf8SequenceLength = inlineUTF8SequenceLength(*source);
>-        if (sourceEnd - source < utf8SequenceLength)  {
>-            result = sourceExhausted;
>-            break;
>-        }
>-        // Do this check whether lenient or strict
>-        if (!isLegalUTF8(reinterpret_cast<const unsigned char*>(source), utf8SequenceLength)) {
>-            result = sourceIllegal;
>-            break;
>-        }
>-
>-        UChar32 character = readUTF8Sequence(source, utf8SequenceLength);
>-
>-        if (target >= targetEnd) {
>-            source -= utf8SequenceLength; // Back up source pointer!
>-            result = targetExhausted;
>-            break;
>-        }
>-
>-        if (U_IS_BMP(character)) {
>-            // UTF-16 surrogate values are illegal in UTF-32
>-            if (U_IS_SURROGATE(character)) {
>-                if (strict) {
>-                    source -= utf8SequenceLength; // return to the illegal value itself
>-                    result = sourceIllegal;
>-                    break;
>-                } else {
>-                    *target++ = replacementCharacter;
>-                    orAllData |= replacementCharacter;
>-                }
>-            } else {
>-                *target++ = character; // normal case
>-                orAllData |= character;
>-            }
>-        } else if (U_IS_SUPPLEMENTARY(character)) {
>-            // target is a character in range 0xFFFF - 0x10FFFF
>-            if (target + 1 >= targetEnd) {
>-                source -= utf8SequenceLength; // Back up source pointer!
>-                result = targetExhausted;
>-                break;
>-            }
>-            *target++ = U16_LEAD(character);
>-            *target++ = U16_TRAIL(character);
>-            orAllData = 0xffff;
>-        } else {
>-            if (strict) {
>-                source -= utf8SequenceLength; // return to the start
>-                result = sourceIllegal;
>-                break; // Bail out; shouldn't continue
>-            } else {
>-                *target++ = replacementCharacter;
>-                orAllData |= replacementCharacter;
>-            }
>-        }
>+    UChar32 orAllData = 0;
>+    unsigned targetOffset = 0;
>+    for (int sourceOffset = 0; sourceOffset < sourceEnd - source; ) {
>+        UChar32 character;
>+        U8_NEXT(reinterpret_cast<const uint8_t*>(source), sourceOffset, sourceEnd - source, character);
>+        if (character < 0)
>+            return false;
>+        U16_APPEND(target, targetOffset, targetEnd - target, character, error);
>+        if (error)
>+            return false;
>+        orAllData |= character;
>     }
>-    *sourceStart = source;
>-    *targetStart = target;
>-
>+    *targetStart = target + targetOffset;
>     if (sourceAllASCII)
>-        *sourceAllASCII = !(orAllData & ~0x7f);
>-
>-    return result;
>+        *sourceAllASCII = isASCII(orAllData);
>+    return true;
> }
> 
> unsigned calculateStringHashAndLengthFromUTF8MaskingTop8Bits(const char* data, const char* dataEnd, unsigned& dataLength, unsigned& utf16Length)
> {
>-    if (!data)
>-        return 0;
>-
>     StringHasher stringHasher;
>-    dataLength = 0;
>     utf16Length = 0;
> 
>-    while (data < dataEnd || (!dataEnd && *data)) {
>-        if (isASCII(*data)) {
>-            stringHasher.addCharacter(*data++);
>-            dataLength++;
>-            utf16Length++;
>-            continue;
>-        }
>-
>-        int utf8SequenceLength = inlineUTF8SequenceLengthNonASCII(*data);
>-        dataLength += utf8SequenceLength;
>-
>-        if (!dataEnd) {
>-            for (int i = 1; i < utf8SequenceLength; ++i) {
>-                if (!data[i])
>-                    return 0;
>-            }
>-        } else if (dataEnd - data < utf8SequenceLength)
>-            return 0;
>-
>-        if (!isLegalUTF8(reinterpret_cast<const unsigned char*>(data), utf8SequenceLength))
>+    int inputOffset = 0;
>+    int inputLength = dataEnd - data;
>+    while (inputOffset < inputLength) {
>+        UChar32 character;
>+        U8_NEXT(reinterpret_cast<const uint8_t*>(data), inputOffset, inputLength, character);
>+        if (character < 0)
>             return 0;
> 
>-        UChar32 character = readUTF8Sequence(data, utf8SequenceLength);
>-        ASSERT(!isASCII(character));
>-
>         if (U_IS_BMP(character)) {
>-            // UTF-16 surrogate values are illegal in UTF-32
>-            if (U_IS_SURROGATE(character))
>-                return 0;
>-            stringHasher.addCharacter(static_cast<UChar>(character)); // normal case
>+            ASSERT(!U_IS_SURROGATE(character));
>+            stringHasher.addCharacter(character);
>             utf16Length++;
>-        } else if (U_IS_SUPPLEMENTARY(character)) {
>-            stringHasher.addCharacters(static_cast<UChar>(U16_LEAD(character)),
>-                                       static_cast<UChar>(U16_TRAIL(character)));
>+        } else {
>+            ASSERT(U_IS_SUPPLEMENTARY(character));
>+            stringHasher.addCharacters(U16_LEAD(character), U16_TRAIL(character));
>             utf16Length += 2;
>-        } else
>-            return 0;
>+        }
>     }
> 
>+    dataLength = inputOffset;
>     return stringHasher.hashWithTop8BitsMasked();
> }
> 
> bool equalUTF16WithUTF8(const UChar* a, const char* b, const char* bEnd)
> {
>     while (b < bEnd) {
>-        if (isASCII(*a) || isASCII(*b)) {
>-            if (*a++ != *b++)
>-                return false;
>-            continue;
>-        }
>-
>-        int utf8SequenceLength = inlineUTF8SequenceLengthNonASCII(*b);
>-
>-        if (bEnd - b < utf8SequenceLength)
>-            return false;
>-
>-        if (!isLegalUTF8(reinterpret_cast<const unsigned char*>(b), utf8SequenceLength))
>+        int offset = 0;
>+        UChar32 character;
>+        U8_NEXT(reinterpret_cast<const uint8_t*>(b), offset, bEnd - b, character);
>+        if (character < 0)
>             return false;
>-
>-        UChar32 character = readUTF8Sequence(b, utf8SequenceLength);
>-        ASSERT(!isASCII(character));
>+        b += offset;
> 
>         if (U_IS_BMP(character)) {
>-            // UTF-16 surrogate values are illegal in UTF-32
>-            if (U_IS_SURROGATE(character))
>-                return false;
>+            ASSERT(!U_IS_SURROGATE(character));
>             if (*a++ != character)
>                 return false;
>-        } else if (U_IS_SUPPLEMENTARY(character)) {
>+        } else {
>+            ASSERT(U_IS_SUPPLEMENTARY(character));
>             if (*a++ != U16_LEAD(character))
>                 return false;
>             if (*a++ != U16_TRAIL(character))
>                 return false;
>-        } else
>-            return false;
>+        }
>     }
> 
>     return true;
>diff --git a/Source/WTF/wtf/unicode/UTF8Conversion.h b/Source/WTF/wtf/unicode/UTF8Conversion.h
>index 3764fe87f374a4899be4d8a3372dc41921d2e6ec..81820ff2a71f81d40c6408eeab2e0b2c87242227 100644
>--- a/Source/WTF/wtf/unicode/UTF8Conversion.h
>+++ b/Source/WTF/wtf/unicode/UTF8Conversion.h
>@@ -1,5 +1,5 @@
> /*
>- * Copyright (C) 2007 Apple Inc.  All rights reserved.
>+ * Copyright (C) 2007-2019 Apple Inc. All rights reserved.
>  *
>  * Redistribution and use in source and binary forms, with or without
>  * modification, are permitted provided that the following conditions
>@@ -31,54 +31,34 @@
> namespace WTF {
> namespace Unicode {
> 
>-    // Given a first byte, gives the length of the UTF-8 sequence it begins.
>-    // Returns 0 for bytes that are not legal starts of UTF-8 sequences.
>-    // Only allows sequences of up to 4 bytes, since that works for all Unicode characters (U-00000000 to U-0010FFFF).
>-    WTF_EXPORT_PRIVATE int UTF8SequenceLength(char);
>+enum ConversionResult {
>+    ConversionOK, // conversion successful
>+    SourceExhausted, // partial character in source, but hit end
>+    TargetExhausted, // insufficient room in target for conversion
>+    SourceIllegal // source sequence is illegal/malformed
>+};
> 
>-    // Takes a null-terminated C-style string with a UTF-8 sequence in it and converts it to a character.
>-    // Only allows Unicode characters (U-00000000 to U-0010FFFF).
>-    // Returns -1 if the sequence is not valid (including presence of extra bytes).
>-    WTF_EXPORT_PRIVATE int decodeUTF8Sequence(const char*);
>+// Conversion function are strict, except for convertUTF16ToUTF8, which takes
>+// "strict" argument. When strict, both irregular sequences and isolated surrogates
>+// will cause an error. When the convertUTF16ToUTF8 is used and strict is false,
>+// both irregular sequences and isolated surrogates are converted.
>+//
>+// All illegal sequences will cause an error. This includes sequences such as:
>+// <F4 90 80 80>, <C0 80>, or <A0> in UTF-8, and values above 0x10FFFF in UTF-32.
>+//
>+// When the convertUTF16ToUTF8 is used and strict is false, sequences that encode
>+// values over 0x10FFFF are converted to the replacement character; in other cases
>+// they constitute an error.
> 
>-    typedef enum {
>-            conversionOK,       // conversion successful
>-            sourceExhausted,    // partial character in source, but hit end
>-            targetExhausted,    // insuff. room in target for conversion
>-            sourceIllegal       // source sequence is illegal/malformed
>-    } ConversionResult;
>+WTF_EXPORT_PRIVATE bool convertUTF8ToUTF16(const char* sourceStart, const char* sourceEnd, UChar** targetStart, UChar* targetEnd, bool* isSourceAllASCII = nullptr);
>+WTF_EXPORT_PRIVATE ConversionResult convertLatin1ToUTF8(const LChar** sourceStart, const LChar* sourceEnd, char** targetStart, char* targetEnd);
>+WTF_EXPORT_PRIVATE ConversionResult convertUTF16ToUTF8(const UChar** sourceStart, const UChar* sourceEnd, char** targetStart, char* targetEnd, bool strict = true);
> 
>-    // These conversion functions take a "strict" argument. When this
>-    // flag is set to strict, both irregular sequences and isolated surrogates
>-    // will cause an error.  When the flag is set to lenient, both irregular
>-    // sequences and isolated surrogates are converted.
>-    // 
>-    // Whether the flag is strict or lenient, all illegal sequences will cause
>-    // an error return. This includes sequences such as: <F4 90 80 80>, <C0 80>,
>-    // or <A0> in UTF-8, and values above 0x10FFFF in UTF-32. Conformant code
>-    // must check for illegal sequences.
>-    // 
>-    // When the flag is set to lenient, characters over 0x10FFFF are converted
>-    // to the replacement character; otherwise (when the flag is set to strict)
>-    // they constitute an error.
>+WTF_EXPORT_PRIVATE unsigned calculateStringHashAndLengthFromUTF8MaskingTop8Bits(const char* data, const char* dataEnd, unsigned& dataLength, unsigned& utf16Length);
> 
>-    WTF_EXPORT_PRIVATE ConversionResult convertUTF8ToUTF16(
>-                    const char** sourceStart, const char* sourceEnd, 
>-                    UChar** targetStart, UChar* targetEnd, bool* isSourceAllASCII = 0, bool strict = true);
>-
>-    WTF_EXPORT_PRIVATE ConversionResult convertLatin1ToUTF8(
>-                    const LChar** sourceStart, const LChar* sourceEnd, 
>-                    char** targetStart, char* targetEnd);
>-
>-    WTF_EXPORT_PRIVATE ConversionResult convertUTF16ToUTF8(
>-                    const UChar** sourceStart, const UChar* sourceEnd, 
>-                    char** targetStart, char* targetEnd, bool strict = true);
>-
>-    WTF_EXPORT_PRIVATE unsigned calculateStringHashAndLengthFromUTF8MaskingTop8Bits(const char* data, const char* dataEnd, unsigned& dataLength, unsigned& utf16Length);
>-
>-    // The caller of these functions already knows that the lengths are the same, so we omit an end argument for UTF-16 and Latin-1.
>-    bool equalUTF16WithUTF8(const UChar* stringInUTF16, const char* stringInUTF8, const char* stringInUTF8End);
>-    bool equalLatin1WithUTF8(const LChar* stringInLatin1, const char* stringInUTF8, const char* stringInUTF8End);
>+// Callers of these functions must check that the lengths are the same; accordingly we omit an end argument for UTF-16 and Latin-1.
>+bool equalUTF16WithUTF8(const UChar* stringInUTF16, const char* stringInUTF8, const char* stringInUTF8End);
>+bool equalLatin1WithUTF8(const LChar* stringInLatin1, const char* stringInUTF8, const char* stringInUTF8End);
> 
> } // namespace Unicode
> } // namespace WTF
>diff --git a/Source/WebCore/platform/SharedBuffer.cpp b/Source/WebCore/platform/SharedBuffer.cpp
>index 63cfe462581dbbc2fda1fb63993945f8fe06029c..b5a4538e996c8bfc97c4f75dc0132c9e30992f8d 100644
>--- a/Source/WebCore/platform/SharedBuffer.cpp
>+++ b/Source/WebCore/platform/SharedBuffer.cpp
>@@ -341,9 +341,9 @@ RefPtr<SharedBuffer> utf8Buffer(const String& string)
>             result = WTF::Unicode::convertLatin1ToUTF8(&d, d + length, &p, p + buffer.size());
>         } else {
>             const UChar* d = string.characters16();
>-            result = WTF::Unicode::convertUTF16ToUTF8(&d, d + length, &p, p + buffer.size(), true);
>+            result = WTF::Unicode::convertUTF16ToUTF8(&d, d + length, &p, p + buffer.size());
>         }
>-        if (result != WTF::Unicode::conversionOK)
>+        if (result != WTF::Unicode::ConversionOK)
>             return nullptr;
>     }
> 
>diff --git a/Source/WebCore/xml/XSLTProcessorLibxslt.cpp b/Source/WebCore/xml/XSLTProcessorLibxslt.cpp
>index 95b1b6a51021282ab4660d7cd54e83f857657ffd..4243ca251df9c37454da49e0b755ba5e41df85f1 100644
>--- a/Source/WebCore/xml/XSLTProcessorLibxslt.cpp
>+++ b/Source/WebCore/xml/XSLTProcessorLibxslt.cpp
>@@ -48,8 +48,6 @@
> #include <libxslt/xslt.h>
> #include <libxslt/xsltutils.h>
> #include <wtf/Assertions.h>
>-#include <wtf/text/StringBuffer.h>
>-#include <wtf/unicode/UTF8Conversion.h>
> 
> #if OS(DARWIN) && !PLATFORM(GTK)
> #include "SoftLinkLibxslt.h"
>@@ -159,27 +157,37 @@ static inline void setXSLTLoadCallBack(xsltDocLoaderFunc func, XSLTProcessor* pr
>     globalCachedResourceLoader = cachedResourceLoader;
> }
> 
>-static int writeToStringBuilder(void* context, const char* buffer, int len)
>+static int writeToStringBuilder(void* context, const char* buffer, int length)
> {
>     StringBuilder& resultOutput = *static_cast<StringBuilder*>(context);
> 
>-    if (!len)
>-        return 0;
>-
>-    StringBuffer<UChar> stringBuffer(len);
>-    UChar* bufferUChar = stringBuffer.characters();
>-    UChar* bufferUCharEnd = bufferUChar + len;
>-
>-    const char* stringCurrent = buffer;
>-    WTF::Unicode::ConversionResult result = WTF::Unicode::convertUTF8ToUTF16(&stringCurrent, buffer + len, &bufferUChar, bufferUCharEnd);
>-    if (result != WTF::Unicode::conversionOK && result != WTF::Unicode::sourceExhausted) {
>-        ASSERT_NOT_REACHED();
>-        return -1;
>+    // FIXME: Should add an appendUTF8 function to StringBuilder and use that instead.
>+
>+    Vector<UChar> outputBuffer(length);
>+
>+    UBool error = false;
>+    int inputOffset = 0;
>+    int outputOffset = 0;
>+    while (inputOffset < length) {
>+        UChar32 character;
>+        int nextInputOffset = inputOffset;
>+        U8_NEXT(reinterpret_cast<const uint8_t*>(buffer), nextInputOffset, length, character);
>+        if (character < 0) {
>+            if (nextInputOffset == length)
>+                break;
>+            ASSERT_NOT_REACHED();
>+            return -1;
>+        }
>+        inputOffset = nextInputOffset;
>+        U16_APPEND(outputBuffer.data(), outputOffset, length, character, error);
>+        if (error) {
>+            ASSERT_NOT_REACHED();
>+            return -1;
>+        }
>     }
> 
>-    int utf16Length = bufferUChar - stringBuffer.characters();
>-    resultOutput.append(stringBuffer.characters(), utf16Length);
>-    return stringCurrent - buffer;
>+    resultOutput.append(outputBuffer.data(), outputOffset);
>+    return inputOffset;
> }
> 
> static bool saveResultToString(xmlDocPtr resultDoc, xsltStylesheetPtr sheet, String& resultString)
>diff --git a/Source/WebCore/xml/parser/XMLDocumentParserLibxml2.cpp b/Source/WebCore/xml/parser/XMLDocumentParserLibxml2.cpp
>index 761ab10e31d3c3138384c9028efd1dbaa3f87d93..9dc2cb0963836f0c4aaf8d19c3a13e3d68d81a1a 100644
>--- a/Source/WebCore/xml/parser/XMLDocumentParserLibxml2.cpp
>+++ b/Source/WebCore/xml/parser/XMLDocumentParserLibxml2.cpp
>@@ -1154,7 +1154,7 @@ static size_t convertUTF16EntityToUTF8(const UChar* utf16Entity, size_t numberOf
> {
>     const char* originalTarget = target;
>     auto conversionResult = WTF::Unicode::convertUTF16ToUTF8(&utf16Entity, utf16Entity + numberOfCodeUnits, &target, target + targetSize);
>-    if (conversionResult != WTF::Unicode::conversionOK)
>+    if (conversionResult != WTF::Unicode::ConversionOK)
>         return 0;
> 
>     // Even though we must pass the length, libxml expects the entity string to be null terminated.
>diff --git a/Source/WebKit/Shared/API/APIString.h b/Source/WebKit/Shared/API/APIString.h
>index 339a7fae3ca4a8b10067be149a0c15a70a257f58..99d1a3e3d369e5e0b91329f8294632bc96043789 100644
>--- a/Source/WebKit/Shared/API/APIString.h
>+++ b/Source/WebKit/Shared/API/APIString.h
>@@ -23,14 +23,10 @@
>  * THE POSSIBILITY OF SUCH DAMAGE.
>  */
> 
>-#ifndef APIString_h
>-#define APIString_h
>+#pragma once
> 
> #include "APIObject.h"
>-#include <wtf/Ref.h>
> #include <wtf/text/StringView.h>
>-#include <wtf/text/WTFString.h>
>-#include <wtf/unicode/UTF8Conversion.h>
> 
> namespace API {
> 
>@@ -75,5 +71,3 @@ private:
> };
> 
> } // namespace WebKit
>-
>-#endif // APIString_h
>diff --git a/Source/WebKit/Shared/API/c/WKString.cpp b/Source/WebKit/Shared/API/c/WKString.cpp
>index 02aa4cc0f0b6673e236a07a81c46fe39eab7feda..f7cec613a411c4af49a7d353e7c8726f528c25eb 100644
>--- a/Source/WebKit/Shared/API/c/WKString.cpp
>+++ b/Source/WebKit/Shared/API/c/WKString.cpp
>@@ -30,6 +30,7 @@
> #include "WKAPICast.h"
> #include <JavaScriptCore/InitializeThreading.h>
> #include <JavaScriptCore/OpaqueJSString.h>
>+#include <wtf/unicode/UTF8Conversion.h>
> 
> WKTypeID WKStringGetTypeID()
> {
>@@ -88,7 +89,7 @@ size_t WKStringGetUTF8CStringImpl(WKStringRef stringRef, char* buffer, size_t bu
>         result = WTF::Unicode::convertUTF16ToUTF8(&characters, characters + stringView.length(), &p, p + bufferSize - 1, strict);
>     }
> 
>-    if (result != WTF::Unicode::conversionOK && result != WTF::Unicode::targetExhausted)
>+    if (result != WTF::Unicode::ConversionOK && result != WTF::Unicode::TargetExhausted)
>         return 0;
> 
>     *p++ = '\0';
>diff --git a/LayoutTests/ChangeLog b/LayoutTests/ChangeLog
>index 52b7b788d46ddc52093166a779abaf47d92a7e4c..8676d4647b54628f4dabaea21a67837f331f9033 100644
>--- a/LayoutTests/ChangeLog
>+++ b/LayoutTests/ChangeLog
>@@ -1,3 +1,26 @@
>+2019-04-28  Darin Adler  <darin@apple.com>
>+
>+        WebKit has too much of its own UTF-8 code and should rely more on ICU's UTF-8 support
>+        https://bugs.webkit.org/show_bug.cgi?id=195535
>+
>+        Reviewed by NOBODY (OOPS!).
>+
>+        * css3/escape-dom-api-expected.txt:
>+        * fast/text/dangling-surrogates-expected.txt:
>+        * js/dom/webidl-type-mapping-expected.txt:
>+        * js/invalid-utf8-in-syntax-error-expected.txt:
>+        Updated expected results to have the Unicode replacement character in cases where the
>+        text contains unpaired surrogates. The tests are still doing the same operations, and
>+        still getting the same results, but the text output no longer includes illegal UTF-8.
>+
>+        * js/invalid-utf8-in-syntax-error.html: Added. Before adding this, the test was
>+        run, but unlike the rest of the tests in this directory, was only run as part of
>+        run-javascriptcore-tests. There are two reasons for adding this. One is to be
>+        consistent with the rest of the tests here and run a second time as part of the
>+        broader WebKit tests. The second is that we can now use "--reset-results" to generate
>+        new expected results, something that run-webkit-tests has but run-javascriptcore-tests
>+        does not have.
>+
> 2019-04-26  Youenn Fablet  <youenn@apple.com>
> 
>         Use normal loading path for ping loads
>diff --git a/LayoutTests/imported/w3c/ChangeLog b/LayoutTests/imported/w3c/ChangeLog
>index 3396ced2312272ad6a3d6151561c2ef12ad7caf2..6ebccda8be7d635146b634d9d8aaa086d9be910c 100644
>--- a/LayoutTests/imported/w3c/ChangeLog
>+++ b/LayoutTests/imported/w3c/ChangeLog
>@@ -1,3 +1,15 @@
>+2019-04-28  Darin Adler  <darin@apple.com>
>+
>+        WebKit has too much of its own UTF-8 code and should rely more on ICU's UTF-8 support
>+        https://bugs.webkit.org/show_bug.cgi?id=195535
>+
>+        Reviewed by NOBODY (OOPS!).
>+
>+        * web-platform-tests/encoding/textdecoder-utf16-surrogates-expected.txt:
>+        Updated expected results to have the Unicode replacement character in cases where the
>+        text contains unpaired surrogates. The tests are still doing the same operations, and
>+        still getting the same results, but the text output no longer includes illegal UTF-8.
>+
> 2019-04-26  Youenn Fablet  <youenn@apple.com>
> 
>         Use normal loading path for ping loads
>diff --git a/LayoutTests/css3/escape-dom-api-expected.txt b/LayoutTests/css3/escape-dom-api-expected.txt
>index c851c96ef745e0118673126ad8982a3104b8d2c1..f54fb3b77a927a05474f1e1374cb831ed1acb866 100644
>--- a/LayoutTests/css3/escape-dom-api-expected.txt
>+++ b/LayoutTests/css3/escape-dom-api-expected.txt
>@@ -4,14 +4,14 @@ On success, you will see a series of "PASS" messages, followed by "TEST COMPLETE
> 
> 
> PASS CSS.escape.length is 1
>-PASS CSS.escape('\0') is "Ã¯Â¿Â½"
>-PASS CSS.escape('a\0') is "aÃ¯Â¿Â½"
>-PASS CSS.escape('\0b') is "Ã¯Â¿Â½b"
>-PASS CSS.escape('a\0b') is "aÃ¯Â¿Â½b"
>-PASS CSS.escape('Ã¯Â¿Â½') is "Ã¯Â¿Â½"
>-PASS CSS.escape('aÃ¯Â¿Â½') is "aÃ¯Â¿Â½"
>-PASS CSS.escape('Ã¯Â¿Â½b') is "Ã¯Â¿Â½b"
>-PASS CSS.escape('aÃ¯Â¿Â½b') is "aÃ¯Â¿Â½b"
>+PASS CSS.escape('\0') is "ï¿½"
>+PASS CSS.escape('a\0') is "aï¿½"
>+PASS CSS.escape('\0b') is "ï¿½b"
>+PASS CSS.escape('a\0b') is "aï¿½b"
>+PASS CSS.escape('ï¿½') is "ï¿½"
>+PASS CSS.escape('aï¿½') is "aï¿½"
>+PASS CSS.escape('ï¿½b') is "ï¿½b"
>+PASS CSS.escape('aï¿½b') is "aï¿½b"
> PASS CSS.escape() threw exception TypeError: Not enough arguments.
> PASS CSS.escape(undefined) is "undefined"
> PASS CSS.escape(true) is "true"
>@@ -53,16 +53,16 @@ PASS CSS.escape('-') is "\\-"
> PASS CSS.escape('-a') is "-a"
> PASS CSS.escape('--') is "--"
> PASS CSS.escape('--a') is "--a"
>-PASS CSS.escape('ÃÂ-_ÃÂ©') is "ÃÂ-_ÃÂ©"
>-PASS CSS.escape('ÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂ') is "\\7f ÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂ"
>-PASS CSS.escape('ÃÂ ÃÂ¡ÃÂ¢') is "ÃÂ ÃÂ¡ÃÂ¢"
>+PASS CSS.escape('Â-_Â©') is "Â-_Â©"
>+PASS CSS.escape('ÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ') is "\\7f ÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ"
>+PASS CSS.escape('Â Â¡Â¢') is "Â Â¡Â¢"
> PASS CSS.escape('a0123456789b') is "a0123456789b"
> PASS CSS.escape('abcdefghijklmnopqrstuvwxyz') is "abcdefghijklmnopqrstuvwxyz"
> PASS CSS.escape('ABCDEFGHIJKLMNOPQRSTUVWXYZ') is "ABCDEFGHIJKLMNOPQRSTUVWXYZ"
> PASS CSS.escape(' !xy') is "\\ \\!xy"
>-PASS CSS.escape('Ã°ÂÂÂ') is "Ã°ÂÂÂ"
>-PASS CSS.escape('ÃÂ¼Â') is "\udf06"
>-PASS CSS.escape('ÃÂ Â´') is "\ud834"
>+PASS CSS.escape('ð') is "ð"
>+PASS CSS.escape('ï¿½') is "\udf06"
>+PASS CSS.escape('ï¿½') is "\ud834"
> PASS successfullyParsed is true
> 
> TEST COMPLETE
>diff --git a/LayoutTests/fast/text/dangling-surrogates-expected.txt b/LayoutTests/fast/text/dangling-surrogates-expected.txt
>index cd1fd817f3a9e5aa8ae0af3d3f5a0bf668d7b7e3..45a378e0e00df56092dbb33d98e859efe2efd590 100644
>--- a/LayoutTests/fast/text/dangling-surrogates-expected.txt
>+++ b/LayoutTests/fast/text/dangling-surrogates-expected.txt
>@@ -3,8 +3,8 @@ This tests verifies that the test tools can handle a dangling surrogate characte
> On success, you will see a series of "PASS" messages, followed by "TEST COMPLETE".
> 
> 
>-PASS danglingFirst is "ÃÂ Â"
>-PASS danglingSecond is "ÃÂ°Â"
>+PASS danglingFirst is "ï¿½"
>+PASS danglingSecond is "ï¿½"
> PASS successfullyParsed is true
> 
> TEST COMPLETE
>diff --git a/LayoutTests/imported/w3c/web-platform-tests/encoding/textdecoder-utf16-surrogates-expected.txt b/LayoutTests/imported/w3c/web-platform-tests/encoding/textdecoder-utf16-surrogates-expected.txt
>index b847acfbc257d470908f125323aa75caca5f3111..900fe37ded95dc67bb763c8916223a2ccbd50491 100644
>--- a/LayoutTests/imported/w3c/web-platform-tests/encoding/textdecoder-utf16-surrogates-expected.txt
>+++ b/LayoutTests/imported/w3c/web-platform-tests/encoding/textdecoder-utf16-surrogates-expected.txt
>@@ -1,21 +1,21 @@
> 
>-FAIL utf-16le - lone surrogate lead assert_equals: expected "\ufffd" but got "ÃÂ Â"
>+FAIL utf-16le - lone surrogate lead assert_equals: expected "\ufffd" but got "ï¿½"
> FAIL utf-16le - lone surrogate lead (fatal flag set) assert_throws: function "function () {
>             new TextDecoder(t.encoding, {fatal: true}).decode(new Uint8Array(t.input))
>         }" did not throw
>-FAIL utf-16le - lone surrogate trail assert_equals: expected "\ufffd" but got "ÃÂ°Â"
>+FAIL utf-16le - lone surrogate trail assert_equals: expected "\ufffd" but got "ï¿½"
> FAIL utf-16le - lone surrogate trail (fatal flag set) assert_throws: function "function () {
>             new TextDecoder(t.encoding, {fatal: true}).decode(new Uint8Array(t.input))
>         }" did not throw
>-FAIL utf-16le - unmatched surrogate lead assert_equals: expected "\ufffd\0" but got "ÃÂ Â\0"
>+FAIL utf-16le - unmatched surrogate lead assert_equals: expected "\ufffd\0" but got "ï¿½\0"
> FAIL utf-16le - unmatched surrogate lead (fatal flag set) assert_throws: function "function () {
>             new TextDecoder(t.encoding, {fatal: true}).decode(new Uint8Array(t.input))
>         }" did not throw
>-FAIL utf-16le - unmatched surrogate trail assert_equals: expected "\ufffd\0" but got "ÃÂ°Â\0"
>+FAIL utf-16le - unmatched surrogate trail assert_equals: expected "\ufffd\0" but got "ï¿½\0"
> FAIL utf-16le - unmatched surrogate trail (fatal flag set) assert_throws: function "function () {
>             new TextDecoder(t.encoding, {fatal: true}).decode(new Uint8Array(t.input))
>         }" did not throw
>-FAIL utf-16le - swapped surrogate pair assert_equals: expected "\ufffd\ufffd" but got "ÃÂ°ÂÃÂ Â"
>+FAIL utf-16le - swapped surrogate pair assert_equals: expected "\ufffd\ufffd" but got "ï¿½ï¿½"
> FAIL utf-16le - swapped surrogate pair (fatal flag set) assert_throws: function "function () {
>             new TextDecoder(t.encoding, {fatal: true}).decode(new Uint8Array(t.input))
>         }" did not throw
>diff --git a/LayoutTests/js/dom/webidl-type-mapping-expected.txt b/LayoutTests/js/dom/webidl-type-mapping-expected.txt
>index 75a4da60b81ecfbbc72f6cd504deb9e2a15321c6..7ec70f9b8bccb0bf4f8fe737af3f5ffcf8cc9962 100644
>--- a/LayoutTests/js/dom/webidl-type-mapping-expected.txt
>+++ b/LayoutTests/js/dom/webidl-type-mapping-expected.txt
>@@ -1009,48 +1009,48 @@ PASS converter.testEnforceRangeUnsignedShort = {valueOf:function(){throw new Err
> 
> converter.testUSVString = '!@#123ABCabc\x00\x80\xFF\r\n\t'
> converter.testString = '!@#123ABCabc\x00\x80\xFF\r\n\t'
>-PASS converter.testUSVString is "!@#123ABCabc\u0000ÃÂÃÂ¿\r\n\t"
>-PASS converter.testString is "!@#123ABCabc\u0000ÃÂÃÂ¿\r\n\t"
>+PASS converter.testUSVString is "!@#123ABCabc\u0000ÂÃ¿\r\n\t"
>+PASS converter.testString is "!@#123ABCabc\u0000ÂÃ¿\r\n\t"
> converter.testUSVString = '\u0100'
> converter.testString = '\u0100'
>-PASS converter.testUSVString is "ÃÂ"
>-PASS converter.testString is "ÃÂ"
>+PASS converter.testUSVString is "Ä"
>+PASS converter.testString is "Ä"
> PASS converter.testUSVString = {toString: function() { throw Error(); }} threw exception Error.
> PASS converter.testString = {toString: function() { throw Error(); }} threw exception Error.
>-PASS converter.testUSVString is "ÃÂ"
>-PASS converter.testString is "ÃÂ"
>+PASS converter.testUSVString is "Ä"
>+PASS converter.testString is "Ä"
> converter.testUSVString = "\ud800"
> converter.testString = "\ud800"
>-PASS converter.testUSVString is "Ã¯Â¿Â½"
>+PASS converter.testUSVString is "ï¿½"
> PASS converter.testString is "\ud800"
> converter.testUSVString = "\udc00"
> converter.testString = "\udc00"
>-PASS converter.testUSVString is "Ã¯Â¿Â½"
>+PASS converter.testUSVString is "ï¿½"
> PASS converter.testString is "\udc00"
> converter.testUSVString = "\ud800\u0000"
> converter.testString = "\ud800\u0000"
>-PASS converter.testUSVString is "Ã¯Â¿Â½\u0000"
>+PASS converter.testUSVString is "ï¿½\u0000"
> PASS converter.testString is "\ud800\u0000"
> converter.testUSVString = "\udc00\u0000"
> converter.testString = "\udc00\u0000"
>-PASS converter.testUSVString is "Ã¯Â¿Â½\u0000"
>+PASS converter.testUSVString is "ï¿½\u0000"
> PASS converter.testString is "\udc00\u0000"
> converter.testUSVString = "\udc00\ud800"
> converter.testString = "\udc00\ud800"
>-PASS converter.testUSVString is "Ã¯Â¿Â½Ã¯Â¿Â½"
>+PASS converter.testUSVString is "ï¿½ï¿½"
> PASS converter.testString is "\udc00\ud800"
>-converter.testUSVString = "Ã°ÂÂÂ"
>-converter.testString = "Ã°ÂÂÂ"
>-PASS converter.testUSVString is "Ã°ÂÂÂ"
>-PASS converter.testString is "Ã°ÂÂÂ"
>+converter.testUSVString = "ð"
>+converter.testString = "ð"
>+PASS converter.testUSVString is "ð"
>+PASS converter.testString is "ð"
> converter.testByteString = '!@#123ABCabc\x00\x80\xFF\r\n\t'
>-PASS converter.testByteString is "!@#123ABCabc\u0000ÃÂÃÂ¿\r\n\t"
>+PASS converter.testByteString is "!@#123ABCabc\u0000ÂÃ¿\r\n\t"
> converter.testByteString = '\u00FF'
>-PASS converter.testByteString is "ÃÂ¿"
>+PASS converter.testByteString is "Ã¿"
> PASS converter.testByteString = '\u0100' threw exception TypeError: Type error.
>-PASS converter.testByteString is "ÃÂ¿"
>+PASS converter.testByteString is "Ã¿"
> PASS converter.testByteString = {toString: function() { throw Error(); }} threw exception Error.
>-PASS converter.testByteString is "ÃÂ¿"
>+PASS converter.testByteString is "Ã¿"
> converter.testUSVString = true
> converter.testString = true
> converter.testByteString = true
>@@ -1180,37 +1180,37 @@ PASS converter.testNodeRecord().hasOwnProperty('key2') is true
> PASS 'key2' in converter.testNodeRecord() is true
> PASS converter.testNodeRecord()['key2'] is document.documentElement
> PASS converter.setTestNodeRecord({ key: 'hello' }) threw exception TypeError: Type error.
>-converter.setTestLongRecord({'ÃÂ Â': 1 })
>-PASS converter.testLongRecord()['ÃÂ Â'] is 1
>-converter.setTestNodeRecord({'ÃÂ Â': document })
>-PASS converter.testNodeRecord()['Ã¯Â¿Â½'] is document
>-converter.setTestLongRecord({'ÃÂ°Â': 1 })
>-PASS converter.testLongRecord()['ÃÂ°Â'] is 1
>-converter.setTestNodeRecord({'ÃÂ°Â': document })
>-PASS converter.testNodeRecord()['Ã¯Â¿Â½'] is document
>-converter.setTestLongRecord({'ÃÂ Â': 1 })
>-PASS converter.testLongRecord()['ÃÂ Â\0'] is 1
>-converter.setTestNodeRecord({'ÃÂ Â': document })
>-PASS converter.testNodeRecord()['Ã¯Â¿Â½\0'] is document
>-converter.setTestLongRecord({'ÃÂ°Â': 1 })
>-PASS converter.testLongRecord()['ÃÂ°Â\0'] is 1
>-converter.setTestNodeRecord({'ÃÂ°Â': document })
>-PASS converter.testNodeRecord()['Ã¯Â¿Â½\0'] is document
>-converter.setTestLongRecord({'ÃÂ°ÂÃÂ Â': 1 })
>-PASS converter.testLongRecord()['ÃÂ°ÂÃÂ Â'] is 1
>-converter.setTestNodeRecord({'ÃÂ°ÂÃÂ Â': document })
>-PASS converter.testNodeRecord()['Ã¯Â¿Â½Ã¯Â¿Â½'] is document
>-converter.setTestLongRecord({'Ã°ÂÂÂ': 1 })
>-PASS converter.testLongRecord()['Ã°ÂÂÂ'] is 1
>-converter.setTestNodeRecord({'Ã°ÂÂÂ': document })
>-PASS converter.testNodeRecord()['Ã°ÂÂÂ'] is document
>+converter.setTestLongRecord({'ï¿½': 1 })
>+PASS converter.testLongRecord()['ï¿½'] is 1
>+converter.setTestNodeRecord({'ï¿½': document })
>+PASS converter.testNodeRecord()['ï¿½'] is document
>+converter.setTestLongRecord({'ï¿½': 1 })
>+PASS converter.testLongRecord()['ï¿½'] is 1
>+converter.setTestNodeRecord({'ï¿½': document })
>+PASS converter.testNodeRecord()['ï¿½'] is document
>+converter.setTestLongRecord({'ï¿½': 1 })
>+PASS converter.testLongRecord()['ï¿½\0'] is 1
>+converter.setTestNodeRecord({'ï¿½': document })
>+PASS converter.testNodeRecord()['ï¿½\0'] is document
>+converter.setTestLongRecord({'ï¿½': 1 })
>+PASS converter.testLongRecord()['ï¿½\0'] is 1
>+converter.setTestNodeRecord({'ï¿½': document })
>+PASS converter.testNodeRecord()['ï¿½\0'] is document
>+converter.setTestLongRecord({'ï¿½ï¿½': 1 })
>+PASS converter.testLongRecord()['ï¿½ï¿½'] is 1
>+converter.setTestNodeRecord({'ï¿½ï¿½': document })
>+PASS converter.testNodeRecord()['ï¿½ï¿½'] is document
>+converter.setTestLongRecord({'ð': 1 })
>+PASS converter.testLongRecord()['ð'] is 1
>+converter.setTestNodeRecord({'ð': document })
>+PASS converter.testNodeRecord()['ð'] is document
> converter.setTestSequenceRecord({ key: ['value', 'other value'] })
> PASS converter.testSequenceRecord().hasOwnProperty('key') is true
> PASS 'key' in converter.testSequenceRecord() is true
> PASS converter.testSequenceRecord()['key'] is ['value', 'other value']
>-PASS converter.setTestSequenceRecord({ 'ÃÂ': ['value'] }) threw exception TypeError: Type error.
>-converter.setTestSequenceRecord({ 'ÃÂ¿': ['value'] })
>-PASS converter.testSequenceRecord()['ÃÂ¿'] is ['value']
>+PASS converter.setTestSequenceRecord({ 'Ä': ['value'] }) threw exception TypeError: Type error.
>+converter.setTestSequenceRecord({ 'Ã¿': ['value'] })
>+PASS converter.testSequenceRecord()['Ã¿'] is ['value']
> PASS converter.testImpureNaNUnrestrictedDouble is NaN
> PASS converter.testImpureNaN2UnrestrictedDouble is NaN
> PASS converter.testQuietNaNUnrestrictedDouble is NaN
>diff --git a/LayoutTests/js/invalid-utf8-in-syntax-error-expected.txt b/LayoutTests/js/invalid-utf8-in-syntax-error-expected.txt
>index 43dd9e463fbcaddb416ce73760acbe81cfb26a1b..32e1a7bf3cc443225996f479c1e16111cfb73876 100644
>--- a/LayoutTests/js/invalid-utf8-in-syntax-error-expected.txt
>+++ b/LayoutTests/js/invalid-utf8-in-syntax-error-expected.txt
>@@ -3,7 +3,7 @@ Ensures that we correctly propagate the error message for lexer errors containin
> On success, you will see a series of "PASS" messages, followed by "TEST COMPLETE".
> 
> 
>-PASS ({f("íº")}) threw exception SyntaxError: Unexpected string literal "ÃÂºÂ". Expected a parameter pattern or a ')' in parameter list..
>+PASS ({f("ï¿½")}) threw exception SyntaxError: Unexpected string literal "ï¿½". Expected a parameter pattern or a ')' in parameter list..
> PASS successfullyParsed is true
> 
> TEST COMPLETE
>diff --git a/LayoutTests/js/invalid-utf8-in-syntax-error.html b/LayoutTests/js/invalid-utf8-in-syntax-error.html
>new file mode 100644
>index 0000000000000000000000000000000000000000..8fb0a757bc0e3339dab604e670d8334c85d11290
>--- /dev/null
>+++ b/LayoutTests/js/invalid-utf8-in-syntax-error.html
>@@ -0,0 +1,10 @@
>+<!DOCTYPE HTML PUBLIC "-//IETF//DTD HTML//EN">
>+<html>
>+<head>
>+<script src="../resources/js-test-pre.js"></script>
>+</head>
>+<body>
>+<script src="script-tests/invalid-utf8-in-syntax-error.js"></script>
>+<script src="../resources/js-test-post.js"></script>
>+</body>
>+</html>

Actions: View | Formatted Diff | Diff

Attachments on bug 195535: 364198 | 364200 | 364203 | 364204 | 364208 | 367915 | 367917 | 367919 | 368432 | 368529