Get WebKit r44544.

6 files changed, 540 insertions, 0 deletions

diff --git a/JavaScriptCore/wtf/unicode/Unicode.h b/JavaScriptCore/wtf/unicode/Unicode.h
index e6e8f23..f86a9b7 100644
--- a/JavaScriptCore/wtf/unicode/Unicode.h
+++ b/JavaScriptCore/wtf/unicode/Unicode.h
@@ -28,6 +28,8 @@
 #include "qt4/UnicodeQt4.h"
 #elif USE(ICU_UNICODE)
 #include <wtf/unicode/icu/UnicodeIcu.h>
+#elif USE(GLIB_UNICODE)
+#include <wtf/unicode/glib/UnicodeGLib.h>
 #else
 #error "Unknown Unicode implementation"
 #endif
diff --git a/JavaScriptCore/wtf/unicode/glib/UnicodeGLib.cpp b/JavaScriptCore/wtf/unicode/glib/UnicodeGLib.cpp
new file mode 100644
index 0000000..a779b36
--- /dev/null
+++ b/JavaScriptCore/wtf/unicode/glib/UnicodeGLib.cpp
@@ -0,0 +1,214 @@
+/*
+ *  Copyright (C) 2008 Jürg Billeter <j@bitron.ch>
+ *  Copyright (C) 2008 Dominik Röttsches <dominik.roettsches@access-company.com>
+ *
+ *  This library is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU Library General Public
+ *  License as published by the Free Software Foundation; either
+ *  version 2 of the License, or (at your option) any later version.
+ *
+ *  This library is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  Library General Public License for more details.
+ *
+ *  You should have received a copy of the GNU Library General Public License
+ *  along with this library; see the file COPYING.LIB.  If not, write to
+ *  the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
+ *  Boston, MA 02110-1301, USA.
+ *
+ */
+
+#include "UnicodeGLib.h"
+
+namespace WTF {
+namespace Unicode {
+
+UChar32 foldCase(UChar32 ch)
+{
+    GOwnPtr<GError> gerror;
+
+    GOwnPtr<char> utf8char;
+    utf8char.set(g_ucs4_to_utf8(reinterpret_cast<gunichar*>(&ch), 1, 0, 0, &gerror.outPtr()));
+    if (gerror)
+        return ch;
+
+    GOwnPtr<char> utf8caseFolded;
+    utf8caseFolded.set(g_utf8_casefold(utf8char.get(), -1));
+
+    GOwnPtr<gunichar> ucs4Result;
+    ucs4Result.set(g_utf8_to_ucs4_fast(utf8caseFolded.get(), -1, 0));
+
+    return *ucs4Result;
+}
+
+int foldCase(UChar* result, int resultLength, const UChar* src, int srcLength, bool* error)
+{
+    *error = false;
+    GOwnPtr<GError> gerror;
+
+    GOwnPtr<char> utf8src;
+    utf8src.set(g_utf16_to_utf8(src, srcLength, 0, 0, &gerror.outPtr()));
+    if (gerror) {
+        *error = true;
+        return -1;
+    }
+
+    GOwnPtr<char> utf8result;
+    utf8result.set(g_utf8_casefold(utf8src.get(), -1));
+
+    long utf16resultLength = -1;
+    GOwnPtr<UChar> utf16result;
+    utf16result.set(g_utf8_to_utf16(utf8result.get(), -1, 0, &utf16resultLength, &gerror.outPtr()));
+    if (gerror) {
+        *error = true;
+        return -1;
+    }
+
+    if (utf16resultLength > resultLength) {
+        *error = true;
+        return utf16resultLength;
+    }
+    memcpy(result, utf16result.get(), utf16resultLength * sizeof(UChar));
+
+    return utf16resultLength;
+}
+
+int toLower(UChar* result, int resultLength, const UChar* src, int srcLength, bool* error)
+{
+    *error = false;
+    GOwnPtr<GError> gerror;
+
+    GOwnPtr<char> utf8src;
+    utf8src.set(g_utf16_to_utf8(src, srcLength, 0, 0, &gerror.outPtr()));
+    if (gerror) {
+        *error = true;
+        return -1;
+    }
+
+    GOwnPtr<char> utf8result;
+    utf8result.set(g_utf8_strdown(utf8src.get(), -1));
+
+    long utf16resultLength = -1;
+    GOwnPtr<UChar> utf16result;
+    utf16result.set(g_utf8_to_utf16(utf8result.get(), -1, 0, &utf16resultLength, &gerror.outPtr()));
+    if (gerror) {
+        *error = true;
+        return -1;
+    }
+
+    if (utf16resultLength > resultLength) {
+        *error = true;
+        return utf16resultLength;
+    }
+    memcpy(result, utf16result.get(), utf16resultLength * sizeof(UChar));
+
+    return utf16resultLength;
+}
+
+int toUpper(UChar* result, int resultLength, const UChar* src, int srcLength, bool* error)
+{
+    *error = false;
+    GOwnPtr<GError> gerror;
+
+    GOwnPtr<char> utf8src;
+    utf8src.set(g_utf16_to_utf8(src, srcLength, 0, 0, &gerror.outPtr()));
+    if (gerror) {
+        *error = true;
+        return -1;
+    }
+
+    GOwnPtr<char> utf8result;
+    utf8result.set(g_utf8_strup(utf8src.get(), -1));
+
+    long utf16resultLength = -1;
+    GOwnPtr<UChar> utf16result;
+    utf16result.set(g_utf8_to_utf16(utf8result.get(), -1, 0, &utf16resultLength, &gerror.outPtr()));
+    if (gerror) {
+        *error = true;
+        return -1;
+    }
+
+    if (utf16resultLength > resultLength) {
+        *error = true;
+        return utf16resultLength;
+    }
+    memcpy(result, utf16result.get(), utf16resultLength * sizeof(UChar));
+
+    return utf16resultLength;
+}
+
+Direction direction(UChar32 c)
+{
+    PangoBidiType type = pango_bidi_type_for_unichar(c);
+    switch (type) {
+    case PANGO_BIDI_TYPE_L:
+        return LeftToRight;
+    case PANGO_BIDI_TYPE_R:
+        return RightToLeft;
+    case PANGO_BIDI_TYPE_AL:
+        return RightToLeftArabic;
+    case PANGO_BIDI_TYPE_LRE:
+        return LeftToRightEmbedding;
+    case PANGO_BIDI_TYPE_RLE:
+        return RightToLeftEmbedding;
+    case PANGO_BIDI_TYPE_LRO:
+        return LeftToRightOverride;
+    case PANGO_BIDI_TYPE_RLO:
+        return RightToLeftOverride;
+    case PANGO_BIDI_TYPE_PDF:
+        return PopDirectionalFormat;
+    case PANGO_BIDI_TYPE_EN:
+        return EuropeanNumber;
+    case PANGO_BIDI_TYPE_AN:
+        return ArabicNumber;
+    case PANGO_BIDI_TYPE_ES:
+        return EuropeanNumberSeparator;
+    case PANGO_BIDI_TYPE_ET:
+        return EuropeanNumberTerminator;
+    case PANGO_BIDI_TYPE_CS:
+        return CommonNumberSeparator;
+    case PANGO_BIDI_TYPE_NSM:
+        return NonSpacingMark;
+    case PANGO_BIDI_TYPE_BN:
+        return BoundaryNeutral;
+    case PANGO_BIDI_TYPE_B:
+        return BlockSeparator;
+    case PANGO_BIDI_TYPE_S:
+        return SegmentSeparator;
+    case PANGO_BIDI_TYPE_WS:
+        return WhiteSpaceNeutral;
+    default:
+        return OtherNeutral;
+    }
+}
+
+int umemcasecmp(const UChar* a, const UChar* b, int len)
+{
+    GOwnPtr<char> utf8a;
+    GOwnPtr<char> utf8b;
+
+    utf8a.set(g_utf16_to_utf8(a, len, 0, 0, 0));
+    utf8b.set(g_utf16_to_utf8(b, len, 0, 0, 0));
+
+    GOwnPtr<char> foldedA;
+    GOwnPtr<char> foldedB;
+
+    foldedA.set(g_utf8_casefold(utf8a.get(), -1));
+    foldedB.set(g_utf8_casefold(utf8b.get(), -1));
+
+    // FIXME: umemcasecmp needs to mimic u_memcasecmp of icu
+    // from the ICU docs:
+    // "Compare two strings case-insensitively using full case folding.
+    // his is equivalent to u_strcmp(u_strFoldCase(s1, n, options), u_strFoldCase(s2, n, options))."
+    //
+    // So it looks like we don't need the full g_utf8_collate here,
+    // but really a bitwise comparison of casefolded unicode chars (not utf-8 bytes).
+    // As there is no direct equivalent to this icu function in GLib, for now
+    // we'll use g_utf8_collate():
+
+    return g_utf8_collate(foldedA.get(), foldedB.get());
+}
+
+}
+}
diff --git a/JavaScriptCore/wtf/unicode/glib/UnicodeGLib.h b/JavaScriptCore/wtf/unicode/glib/UnicodeGLib.h
new file mode 100644
index 0000000..c03d3ec
--- /dev/null
+++ b/JavaScriptCore/wtf/unicode/glib/UnicodeGLib.h
@@ -0,0 +1,238 @@
+/*
+ *  Copyright (C) 2006 George Staikos <staikos@kde.org>
+ *  Copyright (C) 2006 Alexey Proskuryakov <ap@nypop.com>
+ *  Copyright (C) 2007 Apple Computer, Inc. All rights reserved.
+ *  Copyright (C) 2008 Jürg Billeter <j@bitron.ch>
+ *  Copyright (C) 2008 Dominik Röttsches <dominik.roettsches@access-company.com>
+ *
+ *  This library is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU Library General Public
+ *  License as published by the Free Software Foundation; either
+ *  version 2 of the License, or (at your option) any later version.
+ *
+ *  This library is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  Library General Public License for more details.
+ *
+ *  You should have received a copy of the GNU Library General Public License
+ *  along with this library; see the file COPYING.LIB.  If not, write to
+ *  the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
+ *  Boston, MA 02110-1301, USA.
+ *
+ */
+
+#ifndef UnicodeGLib_h
+#define UnicodeGLib_h
+
+#include "UnicodeMacrosFromICU.h"
+#include <wtf/GOwnPtr.h>
+
+#include <glib.h>
+#include <pango/pango.h>
+#include <stdint.h>
+#include <stdlib.h>
+#include <string.h>
+
+typedef uint16_t UChar;
+typedef int32_t UChar32;
+
+namespace WTF {
+namespace Unicode {
+
+enum Direction {
+    LeftToRight,
+    RightToLeft,
+    EuropeanNumber,
+    EuropeanNumberSeparator,
+    EuropeanNumberTerminator,
+    ArabicNumber,
+    CommonNumberSeparator,
+    BlockSeparator,
+    SegmentSeparator,
+    WhiteSpaceNeutral,
+    OtherNeutral,
+    LeftToRightEmbedding,
+    LeftToRightOverride,
+    RightToLeftArabic,
+    RightToLeftEmbedding,
+    RightToLeftOverride,
+    PopDirectionalFormat,
+    NonSpacingMark,
+    BoundaryNeutral
+};
+
+enum DecompositionType {
+    DecompositionNone,
+    DecompositionCanonical,
+    DecompositionCompat,
+    DecompositionCircle,
+    DecompositionFinal,
+    DecompositionFont,
+    DecompositionFraction,
+    DecompositionInitial,
+    DecompositionIsolated,
+    DecompositionMedial,
+    DecompositionNarrow,
+    DecompositionNoBreak,
+    DecompositionSmall,
+    DecompositionSquare,
+    DecompositionSub,
+    DecompositionSuper,
+    DecompositionVertical,
+    DecompositionWide,
+};
+
+enum CharCategory {
+    NoCategory =  0,
+    Other_NotAssigned = U_MASK(G_UNICODE_UNASSIGNED),
+    Letter_Uppercase = U_MASK(G_UNICODE_UPPERCASE_LETTER),
+    Letter_Lowercase = U_MASK(G_UNICODE_LOWERCASE_LETTER),
+    Letter_Titlecase = U_MASK(G_UNICODE_TITLECASE_LETTER),
+    Letter_Modifier = U_MASK(G_UNICODE_MODIFIER_LETTER),
+    Letter_Other = U_MASK(G_UNICODE_OTHER_LETTER),
+
+    Mark_NonSpacing = U_MASK(G_UNICODE_NON_SPACING_MARK),
+    Mark_Enclosing = U_MASK(G_UNICODE_ENCLOSING_MARK),
+    Mark_SpacingCombining = U_MASK(G_UNICODE_COMBINING_MARK),
+
+    Number_DecimalDigit = U_MASK(G_UNICODE_DECIMAL_NUMBER),
+    Number_Letter = U_MASK(G_UNICODE_LETTER_NUMBER),
+    Number_Other = U_MASK(G_UNICODE_OTHER_NUMBER),
+
+    Separator_Space = U_MASK(G_UNICODE_SPACE_SEPARATOR),
+    Separator_Line = U_MASK(G_UNICODE_LINE_SEPARATOR),
+    Separator_Paragraph = U_MASK(G_UNICODE_PARAGRAPH_SEPARATOR),
+
+    Other_Control = U_MASK(G_UNICODE_CONTROL),
+    Other_Format = U_MASK(G_UNICODE_FORMAT),
+    Other_PrivateUse = U_MASK(G_UNICODE_PRIVATE_USE),
+    Other_Surrogate = U_MASK(G_UNICODE_SURROGATE),
+
+    Punctuation_Dash = U_MASK(G_UNICODE_DASH_PUNCTUATION),
+    Punctuation_Open = U_MASK(G_UNICODE_OPEN_PUNCTUATION),
+    Punctuation_Close = U_MASK(G_UNICODE_CLOSE_PUNCTUATION),
+    Punctuation_Connector = U_MASK(G_UNICODE_CONNECT_PUNCTUATION),
+    Punctuation_Other = U_MASK(G_UNICODE_OTHER_PUNCTUATION),
+
+    Symbol_Math = U_MASK(G_UNICODE_MATH_SYMBOL),
+    Symbol_Currency = U_MASK(G_UNICODE_CURRENCY_SYMBOL),
+    Symbol_Modifier = U_MASK(G_UNICODE_MODIFIER_SYMBOL),
+    Symbol_Other = U_MASK(G_UNICODE_OTHER_SYMBOL),
+
+    Punctuation_InitialQuote = U_MASK(G_UNICODE_INITIAL_PUNCTUATION),
+    Punctuation_FinalQuote = U_MASK(G_UNICODE_FINAL_PUNCTUATION)
+};
+
+UChar32 foldCase(UChar32);
+
+int foldCase(UChar* result, int resultLength, const UChar* src, int srcLength, bool* error);
+
+int toLower(UChar* result, int resultLength, const UChar* src, int srcLength, bool* error);
+
+inline UChar32 toLower(UChar32 c)
+{
+    return g_unichar_tolower(c);
+}
+
+inline UChar32 toUpper(UChar32 c)
+{
+    return g_unichar_toupper(c);
+}
+
+int toUpper(UChar* result, int resultLength, const UChar* src, int srcLength, bool* error);
+
+inline UChar32 toTitleCase(UChar32 c)
+{
+    return g_unichar_totitle(c);
+}
+
+inline bool isArabicChar(UChar32 c)
+{
+    return c >= 0x0600 && c <= 0x06FF;
+}
+
+inline bool isFormatChar(UChar32 c)
+{
+    return g_unichar_type(c) == G_UNICODE_FORMAT;
+}
+
+inline bool isSeparatorSpace(UChar32 c)
+{
+    return g_unichar_type(c) == G_UNICODE_SPACE_SEPARATOR;
+}
+
+inline bool isPrintableChar(UChar32 c)
+{
+    return g_unichar_isprint(c);
+}
+
+inline bool isDigit(UChar32 c)
+{
+    return g_unichar_isdigit(c);
+}
+
+inline bool isPunct(UChar32 c)
+{
+    return g_unichar_ispunct(c);
+}
+
+inline bool hasLineBreakingPropertyComplexContext(UChar32 c)
+{
+    // FIXME
+    return false;
+}
+
+inline bool hasLineBreakingPropertyComplexContextOrIdeographic(UChar32 c)
+{
+    // FIXME
+    return false;
+}
+
+inline UChar32 mirroredChar(UChar32 c)
+{
+    gunichar mirror = 0;
+    g_unichar_get_mirror_char(c, &mirror);
+    return mirror;
+}
+
+inline CharCategory category(UChar32 c)
+{
+    if (c > 0xffff)
+        return NoCategory;
+
+    return (CharCategory) U_MASK(g_unichar_type(c));
+}
+
+Direction direction(UChar32);
+
+inline bool isLower(UChar32 c)
+{
+    return g_unichar_islower(c);
+}
+
+inline int digitValue(UChar32 c)
+{
+    return g_unichar_digit_value(c);
+}
+
+inline uint8_t combiningClass(UChar32 c)
+{
+    // FIXME
+    // return g_unichar_combining_class(c);
+    return 0;
+}
+
+inline DecompositionType decompositionType(UChar32 c)
+{
+    // FIXME
+    return DecompositionNone;
+}
+
+int umemcasecmp(const UChar*, const UChar*, int len);
+
+}
+}
+
+#endif
+
diff --git a/JavaScriptCore/wtf/unicode/glib/UnicodeMacrosFromICU.h b/JavaScriptCore/wtf/unicode/glib/UnicodeMacrosFromICU.h
new file mode 100644
index 0000000..5d3eca6
--- /dev/null
+++ b/JavaScriptCore/wtf/unicode/glib/UnicodeMacrosFromICU.h
@@ -0,0 +1,69 @@
+/*
+ *  Copyright (C) 2006 George Staikos <staikos@kde.org>
+ *  Copyright (C) 2006 Alexey Proskuryakov <ap@nypop.com>
+ *  Copyright (C) 2007 Apple Computer, Inc. All rights reserved.
+ *  Copyright (C) 2008 Jürg Billeter <j@bitron.ch>
+ *  Copyright (C) 2008 Dominik Röttsches <dominik.roettsches@access-company.com>
+ *
+ *  This library is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU Library General Public
+ *  License as published by the Free Software Foundation; either
+ *  version 2 of the License, or (at your option) any later version.
+ *
+ *  This library is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  Library General Public License for more details.
+ *
+ *  You should have received a copy of the GNU Library General Public License
+ *  along with this library; see the file COPYING.LIB.  If not, write to
+ *  the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
+ *  Boston, MA 02110-1301, USA.
+ *
+ */
+
+#ifndef UnicodeMacrosFromICU_h
+#define UnicodeMacrosFromICU_h
+
+// some defines from ICU
+
+#define U16_IS_LEAD(c) (((c)&0xfffffc00)==0xd800)
+#define U16_IS_TRAIL(c) (((c)&0xfffffc00)==0xdc00)
+#define U16_SURROGATE_OFFSET ((0xd800<<10UL)+0xdc00-0x10000)
+#define U16_GET_SUPPLEMENTARY(lead, trail) \
+    (((UChar32)(lead)<<10UL)+(UChar32)(trail)-U16_SURROGATE_OFFSET)
+
+#define U16_LEAD(supplementary) (UChar)(((supplementary)>>10)+0xd7c0)
+#define U16_TRAIL(supplementary) (UChar)(((supplementary)&0x3ff)|0xdc00)
+
+#define U_IS_SURROGATE(c) (((c)&0xfffff800)==0xd800)
+#define U16_IS_SINGLE(c) !U_IS_SURROGATE(c)
+#define U16_IS_SURROGATE(c) U_IS_SURROGATE(c)
+#define U16_IS_SURROGATE_LEAD(c) (((c)&0x400)==0)
+
+#define U16_PREV(s, start, i, c) { \
+    (c)=(s)[--(i)]; \
+    if(U16_IS_TRAIL(c)) { \
+        uint16_t __c2; \
+        if((i)>(start) && U16_IS_LEAD(__c2=(s)[(i)-1])) { \
+            --(i); \
+            (c)=U16_GET_SUPPLEMENTARY(__c2, (c)); \
+        } \
+    } \
+}
+
+#define U16_NEXT(s, i, length, c) { \
+    (c)=(s)[(i)++]; \
+    if(U16_IS_LEAD(c)) { \
+        uint16_t __c2; \
+        if((i)<(length) && U16_IS_TRAIL(__c2=(s)[(i)])) { \
+            ++(i); \
+            (c)=U16_GET_SUPPLEMENTARY((c), __c2); \
+        } \
+    } \
+}
+
+#define U_MASK(x) ((uint32_t)1<<(x))
+
+#endif
+
diff --git a/JavaScriptCore/wtf/unicode/icu/UnicodeIcu.h b/JavaScriptCore/wtf/unicode/icu/UnicodeIcu.h
index de5e082..35c6fbf 100644
--- a/JavaScriptCore/wtf/unicode/icu/UnicodeIcu.h
+++ b/JavaScriptCore/wtf/unicode/icu/UnicodeIcu.h
@@ -184,6 +184,12 @@ inline bool hasLineBreakingPropertyComplexContext(UChar32 c)
     return u_getIntPropertyValue(c, UCHAR_LINE_BREAK) == U_LB_COMPLEX_CONTEXT;
 }
 
+inline bool hasLineBreakingPropertyComplexContextOrIdeographic(UChar32 c)
+{
+    int32_t prop = u_getIntPropertyValue(c, UCHAR_LINE_BREAK);
+    return prop == U_LB_COMPLEX_CONTEXT || prop == U_LB_IDEOGRAPHIC;
+}
+
 inline UChar32 mirroredChar(UChar32 c)
 {
     return u_charMirror(c);
diff --git a/JavaScriptCore/wtf/unicode/qt4/UnicodeQt4.h b/JavaScriptCore/wtf/unicode/qt4/UnicodeQt4.h
index f65e292..1531694 100644
--- a/JavaScriptCore/wtf/unicode/qt4/UnicodeQt4.h
+++ b/JavaScriptCore/wtf/unicode/qt4/UnicodeQt4.h
@@ -92,6 +92,17 @@ typedef uint32_t UChar32;
     } \
 }
 
+#define U16_PREV(s, start, i, c) { \
+    (c)=(s)[--(i)]; \
+    if(U16_IS_TRAIL(c)) { \
+        uint16_t __c2; \
+        if((i)>(start) && U16_IS_LEAD(__c2=(s)[(i)-1])) { \
+            --(i); \
+            (c)=U16_GET_SUPPLEMENTARY(__c2, (c)); \
+        } \
+    } \
+}
+
 #define U_MASK(x) ((uint32_t)1<<(x))
 
 namespace WTF {