Diff
Modified: trunk/Source/WTF/ChangeLog (165791 => 165792)
--- trunk/Source/WTF/ChangeLog 2014-03-18 02:45:24 UTC (rev 165791)
+++ trunk/Source/WTF/ChangeLog 2014-03-18 03:00:06 UTC (rev 165792)
@@ -1,3 +1,36 @@
+2014-03-17 Darin Adler <[email protected]>
+
+ Remove most uses of deprecatedCharacter in WTF
+ https://bugs.webkit.org/show_bug.cgi?id=130317
+
+ Reviewed by Andreas Kling.
+
+ Re-landing after fixing the "80 instead of 0x80" typo in equalLatin1WithUTF8.
+
+ * wtf/text/AtomicString.cpp:
+ (WTF::HashAndUTF8CharactersTranslator::equal): Add an 8-bit code path to the
+ non-ASCII path.
+ (WTF::SubstringTranslator8::hash): Added.
+ (WTF::SubstringTranslator8::equal): Added.
+ (WTF::SubstringTranslator16::hash): Renamed class.
+ (WTF::SubstringTranslator16::equal): Ditto.
+ (WTF::AtomicString::add): Added an 8-bit code path to the substring case.
+
+ * wtf/text/Base64.cpp:
+ (WTF::base64Decode): Added an 8 bit code path.
+ (WTF::base64URLDecode): Ditto.
+
+ * wtf/text/StringImpl.cpp:
+ (WTF::StringImpl::find): Fixed a case that was incorrectly using characters16
+ without first using is8Bit. Need to return later to remove use of deprecatedCharacters.
+
+ * wtf/unicode/UTF8.cpp:
+ (WTF::Unicode::equalUTF16WithUTF8): Added a case for when the UTF-16 characters
+ are ASCII. Also removed the aEnd argument, since the caller only calls this when the
+ lengths are equal.
+ (WTF::Unicode::equalLatin1WithUTF8): Added.
+ * wtf/unicode/UTF8.h: Updated as described above.
+
2014-03-17 Commit Queue <[email protected]>
Unreviewed, rolling out r165721.
Modified: trunk/Source/WTF/wtf/text/AtomicString.cpp (165791 => 165792)
--- trunk/Source/WTF/wtf/text/AtomicString.cpp 2014-03-18 02:45:24 UTC (rev 165791)
+++ trunk/Source/WTF/wtf/text/AtomicString.cpp 2014-03-18 03:00:06 UTC (rev 165792)
@@ -187,9 +187,10 @@
// If buffer contains only ASCII characters UTF-8 and UTF16 length are the same.
if (buffer.utf16Length != buffer.length) {
- const UChar* stringCharacters = string->deprecatedCharacters();
+ if (string->is8Bit())
+ return equalLatin1WithUTF8(string->characters8(), buffer.characters, buffer.characters + buffer.length);
- return equalUTF16WithUTF8(stringCharacters, stringCharacters + string->length(), buffer.characters, buffer.characters + buffer.length);
+ return equalUTF16WithUTF8(string->characters16(), buffer.characters, buffer.characters + buffer.length);
}
if (string->is8Bit()) {
@@ -281,28 +282,42 @@
};
struct SubstringTranslator {
+ static void translate(StringImpl*& location, const SubstringLocation& buffer, unsigned hash)
+ {
+ location = &StringImpl::createSubstringSharingImpl(buffer.baseString, buffer.start, buffer.length).leakRef();
+ location->setHash(hash);
+ location->setIsAtomic(true);
+ }
+};
+
+struct SubstringTranslator8 : SubstringTranslator {
static unsigned hash(const SubstringLocation& buffer)
{
- return StringHasher::computeHashAndMaskTop8Bits(buffer.baseString->deprecatedCharacters() + buffer.start, buffer.length);
+ return StringHasher::computeHashAndMaskTop8Bits(buffer.baseString->characters8() + buffer.start, buffer.length);
}
static bool equal(StringImpl* const& string, const SubstringLocation& buffer)
{
- return WTF::equal(string, buffer.baseString->deprecatedCharacters() + buffer.start, buffer.length);
+ return WTF::equal(string, buffer.baseString->characters8() + buffer.start, buffer.length);
}
+};
- static void translate(StringImpl*& location, const SubstringLocation& buffer, unsigned hash)
+struct SubstringTranslator16 : SubstringTranslator {
+ static unsigned hash(const SubstringLocation& buffer)
{
- location = &StringImpl::createSubstringSharingImpl(buffer.baseString, buffer.start, buffer.length).leakRef();
- location->setHash(hash);
- location->setIsAtomic(true);
+ return StringHasher::computeHashAndMaskTop8Bits(buffer.baseString->characters16() + buffer.start, buffer.length);
}
+
+ static bool equal(StringImpl* const& string, const SubstringLocation& buffer)
+ {
+ return WTF::equal(string, buffer.baseString->characters16() + buffer.start, buffer.length);
+ }
};
PassRefPtr<StringImpl> AtomicString::add(StringImpl* baseString, unsigned start, unsigned length)
{
if (!baseString)
- return 0;
+ return nullptr;
if (!length || start >= baseString->length())
return StringImpl::empty();
@@ -315,7 +330,9 @@
}
SubstringLocation buffer = { baseString, start, length };
- return addToStringTable<SubstringLocation, SubstringTranslator>(buffer);
+ if (baseString->is8Bit())
+ return addToStringTable<SubstringLocation, SubstringTranslator8>(buffer);
+ return addToStringTable<SubstringLocation, SubstringTranslator16>(buffer);
}
typedef HashTranslatorCharBuffer<LChar> LCharBuffer;
Modified: trunk/Source/WTF/wtf/text/Base64.cpp (165791 => 165792)
--- trunk/Source/WTF/wtf/text/Base64.cpp 2014-03-18 02:45:24 UTC (rev 165791)
+++ trunk/Source/WTF/wtf/text/Base64.cpp 2014-03-18 03:00:06 UTC (rev 165792)
@@ -250,7 +250,10 @@
bool base64Decode(const String& in, SignedOrUnsignedCharVectorAdapter out, Base64DecodePolicy policy)
{
- return base64DecodeInternal<UChar>(in.deprecatedCharacters(), in.length(), out, policy, base64DecMap);
+ unsigned length = in.length();
+ if (!length || in.is8Bit())
+ return base64DecodeInternal(in.characters8(), length, out, policy, base64DecMap);
+ return base64DecodeInternal(in.characters16(), length, out, policy, base64DecMap);
}
bool base64Decode(const Vector<char>& in, SignedOrUnsignedCharVectorAdapter out, Base64DecodePolicy policy)
@@ -261,17 +264,20 @@
if (in.size() > UINT_MAX)
return false;
- return base64DecodeInternal<char>(in.data(), in.size(), out, policy, base64DecMap);
+ return base64DecodeInternal(reinterpret_cast<const LChar*>(in.data()), in.size(), out, policy, base64DecMap);
}
bool base64Decode(const char* data, unsigned len, SignedOrUnsignedCharVectorAdapter out, Base64DecodePolicy policy)
{
- return base64DecodeInternal<char>(data, len, out, policy, base64DecMap);
+ return base64DecodeInternal(reinterpret_cast<const LChar*>(data), len, out, policy, base64DecMap);
}
bool base64URLDecode(const String& in, SignedOrUnsignedCharVectorAdapter out)
{
- return base64DecodeInternal<UChar>(in.deprecatedCharacters(), in.length(), out, Base64FailOnInvalidCharacter, base64URLDecMap);
+ unsigned length = in.length();
+ if (!length || in.is8Bit())
+ return base64DecodeInternal(in.characters8(), length, out, Base64FailOnInvalidCharacter, base64URLDecMap);
+ return base64DecodeInternal(in.characters16(), length, out, Base64FailOnInvalidCharacter, base64URLDecMap);
}
bool base64URLDecode(const Vector<char>& in, SignedOrUnsignedCharVectorAdapter out)
@@ -282,12 +288,12 @@
if (in.size() > UINT_MAX)
return false;
- return base64DecodeInternal<char>(in.data(), in.size(), out, Base64FailOnInvalidCharacter, base64URLDecMap);
+ return base64DecodeInternal(reinterpret_cast<const LChar*>(in.data()), in.size(), out, Base64FailOnInvalidCharacter, base64URLDecMap);
}
bool base64URLDecode(const char* data, unsigned len, SignedOrUnsignedCharVectorAdapter out)
{
- return base64DecodeInternal<char>(data, len, out, Base64FailOnInvalidCharacter, base64URLDecMap);
+ return base64DecodeInternal(reinterpret_cast<const LChar*>(data), len, out, Base64FailOnInvalidCharacter, base64URLDecMap);
}
} // namespace WTF
Modified: trunk/Source/WTF/wtf/text/StringImpl.cpp (165791 => 165792)
--- trunk/Source/WTF/wtf/text/StringImpl.cpp 2014-03-18 02:45:24 UTC (rev 165791)
+++ trunk/Source/WTF/wtf/text/StringImpl.cpp 2014-03-18 03:00:06 UTC (rev 165792)
@@ -986,7 +986,7 @@
// Optimization 1: fast case for strings of length 1.
if (matchLength == 1)
- return WTF::find(characters16(), length(), *matchString, index);
+ return WTF::find(deprecatedCharacters(), length(), *matchString, index);
// Check index & matchLength are in range.
if (index > length())
Modified: trunk/Source/WTF/wtf/unicode/UTF8.cpp (165791 => 165792)
--- trunk/Source/WTF/wtf/unicode/UTF8.cpp 2014-03-18 02:45:24 UTC (rev 165791)
+++ trunk/Source/WTF/wtf/unicode/UTF8.cpp 2014-03-18 03:00:06 UTC (rev 165792)
@@ -1,5 +1,5 @@
/*
- * Copyright (C) 2007 Apple Inc. All rights reserved.
+ * Copyright (C) 2007, 2014 Apple Inc. All rights reserved.
* Copyright (C) 2010 Patrick Gansterer <[email protected]>
*
* Redistribution and use in source and binary forms, with or without
@@ -420,10 +420,10 @@
return stringHasher.hashWithTop8BitsMasked();
}
-bool equalUTF16WithUTF8(const UChar* a, const UChar* aEnd, const char* b, const char* bEnd)
+bool equalUTF16WithUTF8(const UChar* a, const char* b, const char* bEnd)
{
while (b < bEnd) {
- if (isASCII(*b)) {
+ if (isASCII(*a) || isASCII(*b)) {
if (*a++ != *b++)
return false;
continue;
@@ -435,7 +435,7 @@
return false;
if (!isLegalUTF8(reinterpret_cast<const unsigned char*>(b), utf8SequenceLength))
- return 0;
+ return false;
UChar32 character = readUTF8Sequence(b, utf8SequenceLength);
ASSERT(!isASCII(character));
@@ -455,8 +455,34 @@
return false;
}
- return a == aEnd;
+ return true;
}
+bool equalLatin1WithUTF8(const LChar* a, const char* b, const char* bEnd)
+{
+ while (b < bEnd) {
+ if (isASCII(*a) || isASCII(*b)) {
+ if (*a++ != *b++)
+ return false;
+ continue;
+ }
+
+ if (b + 1 == bEnd)
+ return false;
+
+ if ((b[0] & 0xE0) != 0xC0 || (b[1] & 0xC0) != 0x80)
+ return false;
+
+ LChar character = ((b[0] & 0x1F) << 6) | (b[1] & 0x3F);
+
+ b += 2;
+
+ if (*a++ != character)
+ return false;
+ }
+
+ return true;
+}
+
} // namespace Unicode
} // namespace WTF
Modified: trunk/Source/WTF/wtf/unicode/UTF8.h (165791 => 165792)
--- trunk/Source/WTF/wtf/unicode/UTF8.h 2014-03-18 02:45:24 UTC (rev 165791)
+++ trunk/Source/WTF/wtf/unicode/UTF8.h 2014-03-18 03:00:06 UTC (rev 165792)
@@ -77,7 +77,9 @@
WTF_EXPORT_PRIVATE unsigned calculateStringHashAndLengthFromUTF8MaskingTop8Bits(const char* data, const char* dataEnd, unsigned& dataLength, unsigned& utf16Length);
- WTF_EXPORT_PRIVATE bool equalUTF16WithUTF8(const UChar* a, const UChar* aEnd, const char* b, const char* bEnd);
+ // 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);
} // namespace Unicode
} // namespace WTF
