textcodecicu.cpp

linux下开源浏览器WebKit的源码,市面上的很多商用浏览器都是移植自WebKit

/*
 * Copyright (C) 2004, 2006, 2007, 2008 Apple Inc. All rights reserved.
 * Copyright (C) 2006 Alexey Proskuryakov <[e-mail]>
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 *
 * THIS SOFTWARE IS PROVIDED BY APPLE COMPUTER, INC. ``AS IS'' AND ANY
 * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
 * PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL APPLE COMPUTER, INC. OR
 * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
 * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
 * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
 * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
 * OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. 
 */

#include "config.h"
#include "TextCodecICU.h"

#include "CharacterNames.h"
#include "CString.h"
#include "PlatformString.h"
#include "ThreadGlobalData.h"
#include <unicode/ucnv.h>
#include <unicode/ucnv_cb.h>
#include <wtf/Assertions.h>
#include <wtf/StringExtras.h>
#include <wtf/Threading.h>

using std::auto_ptr;
using std::min;

namespace WebCore {

const size_t ConversionBufferSize = 16384;

ICUConverterWrapper::~ICUConverterWrapper()
{
    if (converter)
        ucnv_close(converter);
}

static UConverter*& cachedConverterICU()
{
    return threadGlobalData().cachedConverterICU().converter;
}

static auto_ptr<TextCodec> newTextCodecICU(const TextEncoding& encoding, const void*)
{
    return auto_ptr<TextCodec>(new TextCodecICU(encoding));
}

void TextCodecICU::registerBaseEncodingNames(EncodingNameRegistrar registrar)
{
    registrar("UTF-8", "UTF-8");
}

void TextCodecICU::registerBaseCodecs(TextCodecRegistrar registrar)
{
    registrar("UTF-8", newTextCodecICU, 0);
}

// FIXME: Registering all the encodings we get from ucnv_getAvailableName
// includes encodings we don't want or need. For example, all
// the encodings with commas and version numbers.

void TextCodecICU::registerExtendedEncodingNames(EncodingNameRegistrar registrar)
{
    // We register Hebrew with logical ordering using a separate name.
    // Otherwise, this would share the same canonical name as the
    // visual ordering case, and then TextEncoding could not tell them
    // apart; ICU treats these names as synonyms.
    registrar("ISO-8859-8-I", "ISO-8859-8-I");

    int32_t numEncodings = ucnv_countAvailable();
    for (int32_t i = 0; i < numEncodings; ++i) {
        const char* name = ucnv_getAvailableName(i);
        UErrorCode error = U_ZERO_ERROR;
        // Try MIME before trying IANA to pick up commonly used names like
        // 'EUC-JP' instead of horrendeously long names like 
        // 'Extended_UNIX_Code_Packed_Format_for_Japanese'. 
        const char* standardName = ucnv_getStandardName(name, "MIME", &error);
        if (!U_SUCCESS(error) || !standardName) {
            error = U_ZERO_ERROR;
            // Try IANA to pick up 'windows-12xx' and other names
            // which are not preferred MIME names but are widely used. 
            standardName = ucnv_getStandardName(name, "IANA", &error);
            if (!U_SUCCESS(error) || !standardName)
                continue;
        }

        // 1. Treat GB2312 encoding as GBK (its more modern superset), to match other browsers.
        // 2. On the Web, GB2312 is encoded as EUC-CN or HZ, while ICU provides a native encoding
        //    for encoding GB_2312-80 and several others. So, we need to override this behavior, too.
        if (strcmp(standardName, "GB2312") == 0 || strcmp(standardName, "GB_2312-80") == 0)
            standardName = "GBK";
        // Similarly, EUC-KR encodings all map to an extended version.
        else if (strcmp(standardName, "KSC_5601") == 0 || strcmp(standardName, "EUC-KR") == 0 || strcmp(standardName, "cp1363") == 0)
            standardName = "windows-949";
        // And so on.
        else if (strcasecmp(standardName, "iso-8859-9") == 0) // This name is returned in different case by ICU 3.2 and 3.6.
            standardName = "windows-1254";
        else if (strcmp(standardName, "TIS-620") == 0)
            standardName = "windows-874";

        registrar(standardName, standardName);

        uint16_t numAliases = ucnv_countAliases(name, &error);
        ASSERT(U_SUCCESS(error));
        if (U_SUCCESS(error))
            for (uint16_t j = 0; j < numAliases; ++j) {
                error = U_ZERO_ERROR;
                const char* alias = ucnv_getAlias(name, j, &error);
                ASSERT(U_SUCCESS(error));
                if (U_SUCCESS(error) && alias != standardName)
                    registrar(alias, standardName);
            }
    }

    // Additional aliases.
    // These are present in modern versions of ICU, but not in ICU 3.2 (shipped with Mac OS X 10.4).
    registrar("macroman", "macintosh");
    registrar("maccyrillic", "x-mac-cyrillic");

    // Additional aliases that historically were present in the encoding
    // table in WebKit on Macintosh that don't seem to be present in ICU.
    // Perhaps we can prove these are not used on the web and remove them.
    // Or perhaps we can get them added to ICU.
    registrar("xmacroman", "macintosh");
    registrar("xmacukrainian", "x-mac-cyrillic");
    registrar("cnbig5", "Big5");
    registrar("xxbig5", "Big5");
    registrar("cngb", "GBK");
    registrar("csgb231280", "GBK");
    registrar("xeuccn", "GBK");
    registrar("xgbk", "GBK");
    registrar("csISO88598I", "ISO_8859-8-I");
    registrar("koi", "KOI8-R");
    registrar("logical", "ISO-8859-8-I");
    registrar("unicode11utf8", "UTF-8");
    registrar("unicode20utf8", "UTF-8");
    registrar("xunicode20utf8", "UTF-8");
    registrar("visual", "ISO-8859-8");
    registrar("winarabic", "windows-1256");
    registrar("winbaltic", "windows-1257");
    registrar("wincyrillic", "windows-1251");
    registrar("iso885911", "windows-874");
    registrar("dos874", "windows-874");
    registrar("wingreek", "windows-1253");
    registrar("winhebrew", "windows-1255");
    registrar("winlatin2", "windows-1250");
    registrar("winturkish", "windows-1254");
    registrar("winvietnamese", "windows-1258");
    registrar("xcp1250", "windows-1250");
    registrar("xcp1251", "windows-1251");
    registrar("xeuc", "EUC-JP");
    registrar("xwindows949", "windows-949");
    registrar("xuhc", "windows-949");

    // These aliases are present in modern versions of ICU, but use different codecs, and have no standard names.
    // They are not present in ICU 3.2.
    registrar("dos720", "cp864");
    registrar("jis7", "ISO-2022-JP");
}

void TextCodecICU::registerExtendedCodecs(TextCodecRegistrar registrar)
{
    // See comment above in registerEncodingNames.
    registrar("ISO-8859-8-I", newTextCodecICU, 0);

    int32_t numEncodings = ucnv_countAvailable();
    for (int32_t i = 0; i < numEncodings; ++i) {
        const char* name = ucnv_getAvailableName(i);
        UErrorCode error = U_ZERO_ERROR;
        const char* standardName = ucnv_getStandardName(name, "MIME", &error);
        if (!U_SUCCESS(error) || !standardName) {
            error = U_ZERO_ERROR;
            standardName = ucnv_getStandardName(name, "IANA", &error);
            if (!U_SUCCESS(error) || !standardName)
                continue;
        }
        registrar(standardName, newTextCodecICU, 0);
    }
}

TextCodecICU::TextCodecICU(const TextEncoding& encoding)
    : m_encoding(encoding)
    , m_numBufferedBytes(0)
    , m_converterICU(0)
    , m_needsGBKFallbacks(false)
{
}

TextCodecICU::~TextCodecICU()
{
    releaseICUConverter();
}

void TextCodecICU::releaseICUConverter() const
{
    if (m_converterICU) {
        UConverter*& cachedConverter = cachedConverterICU();
        if (cachedConverter)
            ucnv_close(cachedConverter);
        cachedConverter = m_converterICU;
        m_converterICU = 0;
    }
}

void TextCodecICU::createICUConverter() const
{
    ASSERT(!m_converterICU);

    const char* name = m_encoding.name();
    m_needsGBKFallbacks = name[0] == 'G' && name[1] == 'B' && name[2] == 'K' && !name[3];

    UErrorCode err;

    UConverter*& cachedConverter = cachedConverterICU();
    if (cachedConverter) {
        err = U_ZERO_ERROR;
        const char* cachedName = ucnv_getName(cachedConverter, &err);
        if (U_SUCCESS(err) && m_encoding == cachedName) {
            m_converterICU = cachedConverter;
            cachedConverter = 0;
            return;
        }