diff options
Diffstat (limited to 'JavaScriptCore/wtf/unicode/glib')
| -rw-r--r-- | JavaScriptCore/wtf/unicode/glib/UnicodeGLib.cpp | 117 | ||||
| -rw-r--r-- | JavaScriptCore/wtf/unicode/glib/UnicodeGLib.h | 2 | ||||
| -rw-r--r-- | JavaScriptCore/wtf/unicode/glib/UnicodeMacrosFromICU.h | 69 |
3 files changed, 48 insertions, 140 deletions
diff --git a/JavaScriptCore/wtf/unicode/glib/UnicodeGLib.cpp b/JavaScriptCore/wtf/unicode/glib/UnicodeGLib.cpp index e20c376..a01c3ee 100644 --- a/JavaScriptCore/wtf/unicode/glib/UnicodeGLib.cpp +++ b/JavaScriptCore/wtf/unicode/glib/UnicodeGLib.cpp @@ -1,6 +1,7 @@ /* * Copyright (C) 2008 Jürg Billeter <j@bitron.ch> * Copyright (C) 2008 Dominik Röttsches <dominik.roettsches@access-company.com> + * Copyright (C) 2010 Igalia S.L. * * This library is free software; you can redistribute it and/or * modify it under the terms of the GNU Library General Public @@ -22,6 +23,11 @@ #include "config.h" #include "UnicodeGLib.h" +#include <wtf/Vector.h> +#include <wtf/unicode/UTF8.h> + +#define UTF8_IS_SURROGATE(character) (character >= 0x10000 && character <= 0x10FFFF) + namespace WTF { namespace Unicode { @@ -43,100 +49,71 @@ UChar32 foldCase(UChar32 ch) return *ucs4Result; } -int foldCase(UChar* result, int resultLength, const UChar* src, int srcLength, bool* error) +static int getUTF16LengthFromUTF8(const gchar* utf8String, int length) { - *error = false; - GOwnPtr<GError> gerror; + int utf16Length = 0; + const gchar* inputString = utf8String; - 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)); + while ((utf8String + length - inputString > 0) && *inputString) { + gunichar character = g_utf8_get_char(inputString); - 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; + utf16Length += UTF8_IS_SURROGATE(character) ? 2 : 1; + inputString = g_utf8_next_char(inputString); } - if (utf16resultLength > resultLength) { - *error = true; - return utf16resultLength; - } - memcpy(result, utf16result.get(), utf16resultLength * sizeof(UChar)); - - return utf16resultLength; + return utf16Length; } -int toLower(UChar* result, int resultLength, const UChar* src, int srcLength, bool* error) +typedef gchar* (*UTF8CaseFunction)(const gchar*, gssize length); + +static int convertCase(UChar* result, int resultLength, const UChar* src, int srcLength, bool* error, UTF8CaseFunction caseFunction) { *error = false; - GOwnPtr<GError> gerror; - GOwnPtr<char> utf8src; - utf8src.set(g_utf16_to_utf8(src, srcLength, 0, 0, &gerror.outPtr())); - if (gerror) { + // Allocate a buffer big enough to hold all the characters. + Vector<char> buffer(srcLength * 3); + char* utf8Target = buffer.data(); + const UChar* utf16Source = src; + ConversionResult conversionResult = convertUTF16ToUTF8(&utf16Source, utf16Source + srcLength, &utf8Target, utf8Target + buffer.size(), true); + if (conversionResult != conversionOK) { *error = true; return -1; } + buffer.shrink(utf8Target - buffer.data()); - GOwnPtr<char> utf8result; - utf8result.set(g_utf8_strdown(utf8src.get(), -1)); + GOwnPtr<char> utf8Result(caseFunction(buffer.data(), buffer.size())); + long utf8ResultLength = strlen(utf8Result.get()); - long utf16resultLength = -1; - GOwnPtr<UChar> utf16result; - utf16result.set(g_utf8_to_utf16(utf8result.get(), -1, 0, &utf16resultLength, &gerror.outPtr())); - if (gerror) { + // Calculate the destination buffer size. + int realLength = getUTF16LengthFromUTF8(utf8Result.get(), utf8ResultLength); + if (realLength > resultLength) { *error = true; - return -1; + return realLength; } - if (utf16resultLength > resultLength) { + // Convert the result to UTF-16. + UChar* utf16Target = result; + const char* utf8Source = utf8Result.get(); + conversionResult = convertUTF8ToUTF16(&utf8Source, utf8Source + utf8ResultLength, &utf16Target, utf16Target + resultLength, true); + long utf16ResultLength = utf16Target - result; + if (conversionResult != conversionOK) *error = true; - return utf16resultLength; - } - memcpy(result, utf16result.get(), utf16resultLength * sizeof(UChar)); - return utf16resultLength; + return utf16ResultLength <= 0 ? -1 : utf16ResultLength; } - -int toUpper(UChar* result, int resultLength, const UChar* src, int srcLength, bool* error) +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_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; - } + return convertCase(result, resultLength, src, srcLength, error, g_utf8_casefold); +} - if (utf16resultLength > resultLength) { - *error = true; - return utf16resultLength; - } - memcpy(result, utf16result.get(), utf16resultLength * sizeof(UChar)); +int toLower(UChar* result, int resultLength, const UChar* src, int srcLength, bool* error) +{ + return convertCase(result, resultLength, src, srcLength, error, g_utf8_strdown); +} - return utf16resultLength; +int toUpper(UChar* result, int resultLength, const UChar* src, int srcLength, bool* error) +{ + return convertCase(result, resultLength, src, srcLength, error, g_utf8_strup); } Direction direction(UChar32 c) diff --git a/JavaScriptCore/wtf/unicode/glib/UnicodeGLib.h b/JavaScriptCore/wtf/unicode/glib/UnicodeGLib.h index d72e707..46b00ea 100644 --- a/JavaScriptCore/wtf/unicode/glib/UnicodeGLib.h +++ b/JavaScriptCore/wtf/unicode/glib/UnicodeGLib.h @@ -26,7 +26,7 @@ #define UnicodeGLib_h #include "UnicodeMacrosFromICU.h" -#include <wtf/gtk/GOwnPtr.h> +#include "GOwnPtr.h" #include <glib.h> #include <pango/pango.h> diff --git a/JavaScriptCore/wtf/unicode/glib/UnicodeMacrosFromICU.h b/JavaScriptCore/wtf/unicode/glib/UnicodeMacrosFromICU.h deleted file mode 100644 index 5d3eca6..0000000 --- a/JavaScriptCore/wtf/unicode/glib/UnicodeMacrosFromICU.h +++ /dev/null @@ -1,69 +0,0 @@ -/* - * 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 - |
