[SCM] WebKit Debian packaging branch, debian/experimental, updated. upstream/1.3.3-9427-gc2be6fc
mrobinson at webkit.org
mrobinson at webkit.org
Wed Dec 22 14:49:08 UTC 2010
The following commit has been merged in the debian/experimental branch:
commit 21863d62ba98e61fe2919eb0e611dceaa57e1178
Author: mrobinson at webkit.org <mrobinson at webkit.org@268f45cc-cd09-0410-ab3c-d52691b4dbfc>
Date: Thu Oct 21 08:08:12 2010 +0000
2010-10-21 Carlos Garcia Campos <cgarcia at igalia.com>
Reviewed by Martin Robinson.
[GTK] Replace encodings multi-dimensional array with calls to registrar method
https://bugs.webkit.org/show_bug.cgi?id=47990
* platform/text/gtk/TextCodecGtk.cpp:
(WebCore::isEncodingAvailable):
(WebCore::registerEncodingNameIfAvailable):
(WebCore::registerEncodingAliasIfAvailable):
(WebCore::registerCodecIfAvailable):
(WebCore::TextCodecGtk::registerBaseEncodingNames):
(WebCore::TextCodecGtk::registerBaseCodecs):
(WebCore::TextCodecGtk::registerExtendedEncodingNames):
(WebCore::TextCodecGtk::registerExtendedCodecs):
(WebCore::TextCodecGtk::createIConvDecoder):
(WebCore::TextCodecGtk::createIConvEncoder):
* platform/text/gtk/TextCodecGtk.h:
git-svn-id: http://svn.webkit.org/repository/webkit/trunk@70211 268f45cc-cd09-0410-ab3c-d52691b4dbfc
diff --git a/WebCore/ChangeLog b/WebCore/ChangeLog
index 83f63cc..1c7b397 100644
--- a/WebCore/ChangeLog
+++ b/WebCore/ChangeLog
@@ -1,3 +1,23 @@
+2010-10-21 Carlos Garcia Campos <cgarcia at igalia.com>
+
+ Reviewed by Martin Robinson.
+
+ [GTK] Replace encodings multi-dimensional array with calls to registrar method
+ https://bugs.webkit.org/show_bug.cgi?id=47990
+
+ * platform/text/gtk/TextCodecGtk.cpp:
+ (WebCore::isEncodingAvailable):
+ (WebCore::registerEncodingNameIfAvailable):
+ (WebCore::registerEncodingAliasIfAvailable):
+ (WebCore::registerCodecIfAvailable):
+ (WebCore::TextCodecGtk::registerBaseEncodingNames):
+ (WebCore::TextCodecGtk::registerBaseCodecs):
+ (WebCore::TextCodecGtk::registerExtendedEncodingNames):
+ (WebCore::TextCodecGtk::registerExtendedCodecs):
+ (WebCore::TextCodecGtk::createIConvDecoder):
+ (WebCore::TextCodecGtk::createIConvEncoder):
+ * platform/text/gtk/TextCodecGtk.h:
+
2010-10-20 Sheriff Bot <webkit.review.bot at gmail.com>
Unreviewed, rolling out r70040.
diff --git a/WebCore/platform/text/gtk/TextCodecGtk.cpp b/WebCore/platform/text/gtk/TextCodecGtk.cpp
index 4224c0c..4dadcf2 100644
--- a/WebCore/platform/text/gtk/TextCodecGtk.cpp
+++ b/WebCore/platform/text/gtk/TextCodecGtk.cpp
@@ -45,164 +45,12 @@ namespace WebCore {
// This can be achieved by specifying the UTF-16 codecs' endianness explicitly when initializing GLib.
#if (G_BYTE_ORDER == G_BIG_ENDIAN)
- const gchar* WebCore::TextCodecGtk::m_internalEncodingName = "UTF-16BE";
-#else
- const gchar* WebCore::TextCodecGtk::m_internalEncodingName = "UTF-16LE";
+static const gchar* internalEncodingName = "UTF-16BE";
+#else
+static const gchar* internalEncodingName = "UTF-16LE";
#endif
-// We're specifying the list of text codecs and their aliases here.
-// For each codec the first entry is the canonical name, remaining ones are used as aliases.
-// Each alias list must be terminated by a 0.
-
-// Unicode
-TextCodecGtk::codecAliasList TextCodecGtk::m_codecAliases_UTF_8 = { "UTF-8", 0 };
-
-// Western
-TextCodecGtk::codecAliasList TextCodecGtk::m_codecAliases_ISO_8859_1 = { "ISO-8859-1", "CP819", "IBM819", "ISO-IR-100", "ISO8859-1", "ISO_8859-1", "ISO_8859-1:1987", "L1", "LATIN1", "CSISOLATIN1", 0 };
-TextCodecGtk::codecAliasList TextCodecGtk::m_codecAliases_MACROMAN = { "MACROMAN", "MAC", "MACINTOSH", "CSMACINTOSH", 0 };
-
-// Japanese
-TextCodecGtk::codecAliasList TextCodecGtk::m_codecAliases_SHIFT_JIS = { "Shift_JIS", "MS_KANJI", "SHIFT-JIS", "SJIS", "CSSHIFTJIS", 0 };
- TextCodecGtk::codecAliasList TextCodecGtk::m_codecAliases_EUC_JP = { "EUC-JP", "EUC_JP", "EUCJP", "EXTENDED_UNIX_CODE_PACKED_FORMAT_FOR_JAPANESE", "CSEUCPKDFMTJAPANESE", 0 };
-TextCodecGtk::codecAliasList TextCodecGtk::m_codecAliases_ISO_2022_JP = { "ISO-2022-JP", 0 };
-
-// Traditional Chinese
-TextCodecGtk::codecAliasList TextCodecGtk::m_codecAliases_BIG5 = { "BIG5", "BIG-5", "BIG-FIVE", "BIG5", "BIGFIVE", "CN-BIG5", "CSBIG5", 0 };
-TextCodecGtk::codecAliasList TextCodecGtk::m_codecAliases_BIG5_HKSCS = { "BIG5-HKSCS", "BIG5-HKSCS:2004", "BIG5HKSCS", 0 };
-TextCodecGtk::codecAliasList TextCodecGtk::m_codecAliases_CP950 = { "CP950", 0 };
-
-// Korean
-TextCodecGtk::codecAliasList TextCodecGtk::m_codecAliases_ISO_2022_KR = { "ISO-2022-KR", "CSISO2022KR", 0 };
-TextCodecGtk::codecAliasList TextCodecGtk::m_codecAliases_CP949 = { "CP949", "UHC", 0 };
-TextCodecGtk::codecAliasList TextCodecGtk::m_codecAliases_EUC_KR = { "EUC-KR", "CSEUCKR", 0 };
-
-// Arabic
-TextCodecGtk::codecAliasList TextCodecGtk::m_codecAliases_ISO_8859_6 = { "ISO-8859-6", "ARABIC", "ASMO-708", "ECMA-114", "ISO-IR-127", "ISO8859-6", "ISO_8859-6", "ISO_8859-6:1987", "CSISOLATINARABIC", 0 };
-TextCodecGtk::codecAliasList TextCodecGtk::m_codecAliases_CP1256 = { "windows-1256", "CP1256", "MS-ARAB", 0 }; // rearranged, windows-1256 now declared the canonical name and put to lowercase to fix /fast/encoding/ahram-org-eg.html test case
-
-// Hebrew
-TextCodecGtk::codecAliasList TextCodecGtk::m_codecAliases_ISO_8859_8 = { "ISO-8859-8", "HEBREW", "ISO-8859-8", "ISO-IR-138", "ISO8859-8", "ISO_8859-8", "ISO_8859-8:1988", "CSISOLATINHEBREW", 0 };
-TextCodecGtk::codecAliasList TextCodecGtk::m_codecAliases_CP1255 = { "windows-1255", "CP1255", "MS-HEBR", 0 }; // rearranged, moved windows-1255 as canonical and lowercased, fixing /fast/encoding/meta-charset.html
-
-// Greek
-TextCodecGtk::codecAliasList TextCodecGtk::m_codecAliases_ISO_8859_7 = { "ISO-8859-7", "ECMA-118", "ELOT_928", "GREEK", "GREEK8", "ISO-IR-126", "ISO8859-7", "ISO_8859-7", "ISO_8859-7:1987", "ISO_8859-7:2003", "CSI", 0 };
-TextCodecGtk::codecAliasList TextCodecGtk::m_codecAliases_CP869 = { "CP869", "869", "CP-GR", "IBM869", "CSIBM869", 0 };
-TextCodecGtk::codecAliasList TextCodecGtk::m_codecAliases_WINDOWS_1253 = { "WINDOWS-1253", 0 };
-
-// Cyrillic
-TextCodecGtk::codecAliasList TextCodecGtk::m_codecAliases_ISO_8859_5 = { "ISO-8859-5", "CYRILLIC", "ISO-IR-144", "ISO8859-5", "ISO_8859-5", "ISO_8859-5:1988", "CSISOLATINCYRILLIC", 0 };
-TextCodecGtk::codecAliasList TextCodecGtk::m_codecAliases_KOI8_R = { "KOI8-R", "CSKOI8R", 0 };
-TextCodecGtk::codecAliasList TextCodecGtk::m_codecAliases_CP866 = { "CP866", "866", "IBM866", "CSIBM866", 0 };
-TextCodecGtk::codecAliasList TextCodecGtk::m_codecAliases_KOI8_U = { "KOI8-U", 0 };
-TextCodecGtk::codecAliasList TextCodecGtk::m_codecAliases_WINDOWS_1251 = { "windows-1251", "CP1251", 0 }; // CP1251 added to pass /fast/encoding/charset-cp1251.html
-TextCodecGtk::codecAliasList TextCodecGtk::m_codecAliases_MACCYRILLIC = { "mac-cyrillic", "MACCYRILLIC", "x-mac-cyrillic", 0 };
-
-// Thai
-TextCodecGtk::codecAliasList TextCodecGtk::m_codecAliases_CP874 = { "CP874", "WINDOWS-874", 0 };
-TextCodecGtk::codecAliasList TextCodecGtk::m_codecAliases_TIS_620 = { "TIS-620", 0 };
-
-// Simplified Chinese
-TextCodecGtk::codecAliasList TextCodecGtk::m_codecAliases_GBK = { "GBK", 0 };
-TextCodecGtk::codecAliasList TextCodecGtk::m_codecAliases_HZ = { "HZ", "HZ-GB-2312", 0 };
-TextCodecGtk::codecAliasList TextCodecGtk::m_codecAliases_GB18030 = { "GB18030", 0 };
-TextCodecGtk::codecAliasList TextCodecGtk::m_codecAliases_EUC_CN = { "EUC-CN", "EUCCN", "GB2312", "CN-GB", "CSGB2312", "EUC_CN", 0 };
-TextCodecGtk::codecAliasList TextCodecGtk::m_codecAliases_2312_80 = { "GB_2312-80", "CHINESE", "csISO58GB231280", "GB2312.1980-0", "ISO-IR-58" };
-
-// Central European
-TextCodecGtk::codecAliasList TextCodecGtk::m_codecAliases_ISO_8859_2 = { "ISO-8859-2", "ISO-IR-101", "ISO8859-2", "ISO_8859-2", "ISO_8859-2:1987", "L2", "LATIN2", "CSISOLATIN2", 0 };
-TextCodecGtk::codecAliasList TextCodecGtk::m_codecAliases_CP1250 = { "CP1250", "MS-EE", "WINDOWS-1250", 0 };
-TextCodecGtk::codecAliasList TextCodecGtk::m_codecAliases_MACCENTRALEUROPE = { "MAC-CENTRALEUROPE", 0 };
-
-// Vietnamese
-TextCodecGtk::codecAliasList TextCodecGtk::m_codecAliases_CP1258 = { "CP1258", "WINDOWS-1258", 0 };
-
-// Turkish
-TextCodecGtk::codecAliasList TextCodecGtk::m_codecAliases_CP1254 = { "CP1254", "MS-TURK", "WINDOWS-1254", 0 };
-TextCodecGtk::codecAliasList TextCodecGtk::m_codecAliases_ISO_8859_9 = { "ISO-8859-9", "ISO-IR-148", "ISO8859-9", "ISO_8859-9", "ISO_8859-9:1989", "L5", "LATIN5", "CSISOLATIN5", 0 };
-
-// Baltic
-TextCodecGtk::codecAliasList TextCodecGtk::m_codecAliases_CP1257 = { "CP1257", "WINBALTRIM", "WINDOWS-1257", 0 };
-TextCodecGtk::codecAliasList TextCodecGtk::m_codecAliases_ISO_8859_4 = { "ISO-8859-4", "ISO-IR-110", "ISO8859-4", "ISO_8859-4", "ISO_8859-4:1988", "L4", "LATIN4", "CSISOLATIN4", 0 };
-
-gconstpointer const TextCodecGtk::m_iconvBaseCodecList[] = {
- // Unicode
- &m_codecAliases_UTF_8,
-
- // Western
- &m_codecAliases_ISO_8859_1
-};
-
-gconstpointer const TextCodecGtk::m_iconvExtendedCodecList[] =
-{
- // Western
- &m_codecAliases_MACROMAN,
-
- // Japanese
- &m_codecAliases_SHIFT_JIS,
- &m_codecAliases_EUC_JP,
- &m_codecAliases_ISO_2022_JP,
-
- // Simplified Chinese
- &m_codecAliases_BIG5,
- &m_codecAliases_BIG5_HKSCS,
- &m_codecAliases_CP950,
-
- // Korean
- &m_codecAliases_ISO_2022_KR,
- &m_codecAliases_CP949,
- &m_codecAliases_EUC_KR,
-
- // Arabic
- &m_codecAliases_ISO_8859_6,
- &m_codecAliases_CP1256,
-
- // Hebrew
- &m_codecAliases_ISO_8859_8,
- &m_codecAliases_CP1255,
-
- // Greek
- &m_codecAliases_ISO_8859_7,
- &m_codecAliases_CP869,
- &m_codecAliases_WINDOWS_1253,
-
- // Cyrillic
- &m_codecAliases_ISO_8859_5,
- &m_codecAliases_KOI8_R,
- &m_codecAliases_CP866,
- &m_codecAliases_KOI8_U,
- &m_codecAliases_WINDOWS_1251,
- &m_codecAliases_MACCYRILLIC,
-
- // Thai
- &m_codecAliases_CP874,
- &m_codecAliases_TIS_620,
-
- // Traditional Chinese
- &m_codecAliases_GBK,
- &m_codecAliases_HZ,
- &m_codecAliases_GB18030,
- &m_codecAliases_EUC_CN,
- &m_codecAliases_2312_80,
-
- // Central European
- &m_codecAliases_ISO_8859_2,
- &m_codecAliases_CP1250,
- &m_codecAliases_MACCENTRALEUROPE,
-
- // Vietnamese
- &m_codecAliases_CP1258,
-
- // Turkish
- &m_codecAliases_CP1254,
- &m_codecAliases_ISO_8859_9,
-
- // Baltic
- &m_codecAliases_CP1257,
- &m_codecAliases_ISO_8859_4
-};
-
-
const size_t ConversionBufferSize = 16384;
@@ -211,17 +59,17 @@ static PassOwnPtr<TextCodec> newTextCodecGtk(const TextEncoding& encoding, const
return new TextCodecGtk(encoding);
}
-gboolean TextCodecGtk::isEncodingAvailable(const gchar* encName)
+static bool isEncodingAvailable(const gchar* encodingName)
{
GIConv tester;
// test decoding
- tester = g_iconv_open(m_internalEncodingName, encName);
+ tester = g_iconv_open(internalEncodingName, encodingName);
if (tester == reinterpret_cast<GIConv>(-1)) {
return false;
} else {
g_iconv_close(tester);
// test encoding
- tester = g_iconv_open(encName, m_internalEncodingName);
+ tester = g_iconv_open(encodingName, internalEncodingName);
if (tester == reinterpret_cast<GIConv>(-1)) {
return false;
} else {
@@ -231,81 +79,326 @@ gboolean TextCodecGtk::isEncodingAvailable(const gchar* encName)
}
}
-void TextCodecGtk::registerEncodingNames(EncodingNameRegistrar registrar, bool extended)
+static bool registerEncodingNameIfAvailable(EncodingNameRegistrar registrar, const char* canonicalName)
{
- const void* const* encodingList;
- unsigned int listLength = 0;
- if (extended) {
- encodingList = m_iconvExtendedCodecList;
- listLength = sizeof(m_iconvExtendedCodecList)/sizeof(gpointer);
- } else {
- encodingList = m_iconvBaseCodecList;
- listLength = sizeof(m_iconvBaseCodecList)/sizeof(gpointer);
- }
-
- for (unsigned int i = 0; i < listLength; ++i) {
- codecAliasList *codecAliases = static_cast<codecAliasList*>(encodingList[i]);
-
- // Our convention is, the first entry in codecAliases is the canonical name,
- // see above in the list of declarations.
- // Probe GLib for this one first. If it's not available, we skip the whole group of aliases.
-
- int codecCount = 0;
- const char *canonicalName;
- canonicalName = (*codecAliases)[codecCount];
-
- if (!isEncodingAvailable(canonicalName))
- continue;
+ if (isEncodingAvailable(canonicalName)) {
registrar(canonicalName, canonicalName);
-
- const char *currentAlias;
- while ((currentAlias = (*codecAliases)[++codecCount])) {
- if (isEncodingAvailable(currentAlias))
- registrar(currentAlias, canonicalName);
- }
-
+ return true;
}
+
+ return false;
}
-void TextCodecGtk::registerCodecs(TextCodecRegistrar registrar, bool extended)
+static void registerEncodingAliasIfAvailable(EncodingNameRegistrar registrar, const char* canonicalName, const char* aliasName)
{
- const void* const* encodingList;
- unsigned int listLength = 0;
- if (extended) {
- encodingList = m_iconvExtendedCodecList;
- listLength = sizeof(m_iconvExtendedCodecList)/sizeof(gpointer);
- } else {
- encodingList = m_iconvBaseCodecList;
- listLength = sizeof(m_iconvBaseCodecList)/sizeof(gpointer);
- }
+ if (isEncodingAvailable(aliasName))
+ registrar(aliasName, canonicalName);
+}
- for (unsigned int i = 0; i < listLength; ++i) {
- codecAliasList *codecAliases = static_cast<codecAliasList*>(encodingList[i]);
- // by convention, the first "alias" should be the canonical name, see the definition of the alias lists
- const gchar *codecName = (*codecAliases)[0];
- if (isEncodingAvailable(codecName))
- registrar(codecName, newTextCodecGtk, 0);
- }
+static void registerCodecIfAvailable(TextCodecRegistrar registrar, const char* codecName)
+{
+ if (isEncodingAvailable(codecName))
+ registrar(codecName, newTextCodecGtk, 0);
}
void TextCodecGtk::registerBaseEncodingNames(EncodingNameRegistrar registrar)
{
- registerEncodingNames(registrar, false);
+ // Unicode
+ registerEncodingNameIfAvailable(registrar, "UTF-8");
+
+ // Western
+ if (registerEncodingNameIfAvailable(registrar, "ISO-8859-1")) {
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-1", "CP819");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-1", "IBM819");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-1", "ISO-IR-100");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-1", "ISO8859-1");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-1", "ISO_8859-1");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-1", "ISO_8859-1:1987");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-1", "L1");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-1", "LATIN1");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-1", "CSISOLATIN1");
+ }
}
void TextCodecGtk::registerBaseCodecs(TextCodecRegistrar registrar)
{
- registerCodecs(registrar, false);
+ // Unicode
+ registerCodecIfAvailable(registrar, "UTF-8");
+
+ // Western
+ registerCodecIfAvailable(registrar, "ISO-8859-1");
}
void TextCodecGtk::registerExtendedEncodingNames(EncodingNameRegistrar registrar)
{
- registerEncodingNames(registrar, true);
+ // Western
+ if (registerEncodingNameIfAvailable(registrar, "MACROMAN")) {
+ registerEncodingAliasIfAvailable(registrar, "MACROMAN", "MAC");
+ registerEncodingAliasIfAvailable(registrar, "MACROMAN", "MACINTOSH");
+ registerEncodingAliasIfAvailable(registrar, "MACROMAN", "CSMACINTOSH");
+ }
+
+ // Japanese
+ if (registerEncodingNameIfAvailable(registrar, "Shift_JIS")) {
+ registerEncodingAliasIfAvailable(registrar, "Shift_JIS", "MS_KANJI");
+ registerEncodingAliasIfAvailable(registrar, "Shift_JIS", "SHIFT-JIS");
+ registerEncodingAliasIfAvailable(registrar, "Shift_JIS", "SJIS");
+ registerEncodingAliasIfAvailable(registrar, "Shift_JIS", "CSSHIFTJIS");
+ }
+ if (registerEncodingNameIfAvailable(registrar, "EUC-JP")) {
+ registerEncodingAliasIfAvailable(registrar, "EUC-JP", "EUC_JP");
+ registerEncodingAliasIfAvailable(registrar, "EUC-JP", "EUCJP");
+ registerEncodingAliasIfAvailable(registrar, "EUC-JP", "EXTENDED_UNIX_CODE_PACKED_FORMAT_FOR_JAPANESE");
+ registerEncodingAliasIfAvailable(registrar, "EUC-JP", "CSEUCPKDFMTJAPANESE");
+ }
+ registerEncodingNameIfAvailable(registrar, "ISO-2022-JP");
+
+ // Traditional Chinese
+ if (registerEncodingNameIfAvailable(registrar, "BIG5")) {
+ registerEncodingAliasIfAvailable(registrar, "BIG5", "BIG-5");
+ registerEncodingAliasIfAvailable(registrar, "BIG5", "BIG-FIVE");
+ registerEncodingAliasIfAvailable(registrar, "BIG5", "BIGFIVE");
+ registerEncodingAliasIfAvailable(registrar, "BIG5", "CN-BIG5");
+ registerEncodingAliasIfAvailable(registrar, "BIG5", "CSBIG5");
+ }
+ if (registerEncodingNameIfAvailable(registrar, "BIG5-HKSCS")) {
+ registerEncodingAliasIfAvailable(registrar, "BIG5-HKSCS", "BIG5-HKSCS:2004");
+ registerEncodingAliasIfAvailable(registrar, "BIG5-HKSCS", "BIG5HKSCS");
+ }
+ registerEncodingNameIfAvailable(registrar, "CP950");
+
+ // Korean
+ if (registerEncodingNameIfAvailable(registrar, "ISO-2022-KR"))
+ registerEncodingAliasIfAvailable(registrar, "ISO-2022-KR", "CSISO2022KR");
+ if (registerEncodingNameIfAvailable(registrar, "CP949"))
+ registerEncodingAliasIfAvailable(registrar, "CP949", "UHC");
+ if (registerEncodingNameIfAvailable(registrar, "EUC-KR"))
+ registerEncodingAliasIfAvailable(registrar, "EUC-KR", "CSEUCKR");
+
+ // Arabic
+ if (registerEncodingNameIfAvailable(registrar, "ISO-8859-6")) {
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-6", "ARABIC");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-6", "ASMO-708");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-6", "ECMA-114");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-6", "ISO-IR-127");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-6", "ISO8859-6");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-6", "ISO_8859-6");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-6", "ISO_8859-6:1987");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-6", "CSISOLATINARABIC");
+ }
+ // rearranged, windows-1256 now declared the canonical name and put to lowercase to fix /fast/encoding/ahram-org-eg.html test case
+ if (registerEncodingNameIfAvailable(registrar, "windows-1256")) {
+ registerEncodingAliasIfAvailable(registrar, "windows-1256", "CP1256");
+ registerEncodingAliasIfAvailable(registrar, "windows-1256", "MS-ARAB");
+ }
+
+ // Hebrew
+ if (registerEncodingNameIfAvailable(registrar, "ISO-8859-8")) {
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-8", "HEBREW");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-8", "ISO-8859-8");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-8", "ISO-IR-138");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-8", "ISO8859-8");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-8", "ISO_8859-8");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-8", "ISO_8859-8:1988");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-8", "CSISOLATINHEBREW");
+ }
+ // rearranged, moved windows-1255 as canonical and lowercased, fixing /fast/encoding/meta-charset.html
+ if (registerEncodingNameIfAvailable(registrar, "windows-1255")) {
+ registerEncodingAliasIfAvailable(registrar, "windows-1255", "CP1255");
+ registerEncodingAliasIfAvailable(registrar, "windows-1255", "MS-HEBR");
+ }
+
+ // Greek
+ if (registerEncodingNameIfAvailable(registrar, "ISO-8859-7")) {
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-7", "ECMA-118");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-7", "ELOT_928");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-7", "GREEK");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-7", "GREEK8");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-7", "ISO-IR-126");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-7", "ISO8859-7");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-7", "ISO_8859-7");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-7", "ISO_8859-7:1987");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-7", "ISO_8859-7:2003");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-7", "CSI");
+ }
+ if (registerEncodingNameIfAvailable(registrar, "CP869")) {
+ registerEncodingAliasIfAvailable(registrar, "CP869", "869");
+ registerEncodingAliasIfAvailable(registrar, "CP869", "CP-GR");
+ registerEncodingAliasIfAvailable(registrar, "CP869", "IBM869");
+ registerEncodingAliasIfAvailable(registrar, "CP869", "CSIBM869");
+ }
+ registerEncodingNameIfAvailable(registrar, "WINDOWS-1253");
+
+ // Cyrillic
+ if (registerEncodingNameIfAvailable(registrar, "ISO-8859-5")) {
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-5", "CYRILLIC");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-5", "ISO-IR-144");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-5", "ISO8859-5");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-5", "ISO_8859-5");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-5", "ISO_8859-5:1988");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-5", "CSISOLATINCYRILLIC");
+ }
+ if (registerEncodingNameIfAvailable(registrar, "KOI8-R"))
+ registerEncodingAliasIfAvailable(registrar, "KOI8-R", "CSKOI8R");
+ if (registerEncodingNameIfAvailable(registrar, "CP866")) {
+ registerEncodingAliasIfAvailable(registrar, "CP866", "866");
+ registerEncodingAliasIfAvailable(registrar, "CP866", "IBM866");
+ registerEncodingAliasIfAvailable(registrar, "CP866", "CSIBM866");
+ }
+ registerEncodingNameIfAvailable(registrar, "KOI8-U");
+ // CP1251 added to pass /fast/encoding/charset-cp1251.html
+ if (registerEncodingNameIfAvailable(registrar, "windows-1251"))
+ registerEncodingAliasIfAvailable(registrar, "windows-1251", "CP1251");
+ if (registerEncodingNameIfAvailable(registrar, "mac-cyrillic")) {
+ registerEncodingAliasIfAvailable(registrar, "mac-cyrillic", "MACCYRILLIC");
+ registerEncodingAliasIfAvailable(registrar, "mac-cyrillic", "x-mac-cyrillic");
+ }
+
+ // Thai
+ if (registerEncodingNameIfAvailable(registrar, "CP874"))
+ registerEncodingAliasIfAvailable(registrar, "CP874", "WINDOWS-874");
+ registerEncodingNameIfAvailable(registrar, "TIS-620");
+
+ // Simplified Chinese
+ registerEncodingNameIfAvailable(registrar, "GBK");
+ if (registerEncodingNameIfAvailable(registrar, "HZ"))
+ registerEncodingAliasIfAvailable(registrar, "HZ", "HZ-GB-2312");
+ registerEncodingNameIfAvailable(registrar, "GB18030");
+ if (registerEncodingNameIfAvailable(registrar, "EUC-CN")) {
+ registerEncodingAliasIfAvailable(registrar, "EUC-CN", "EUCCN");
+ registerEncodingAliasIfAvailable(registrar, "EUC-CN", "GB2312");
+ registerEncodingAliasIfAvailable(registrar, "EUC-CN", "CN-GB");
+ registerEncodingAliasIfAvailable(registrar, "EUC-CN", "CSGB2312");
+ registerEncodingAliasIfAvailable(registrar, "EUC-CN", "EUC_CN");
+ }
+ if (registerEncodingNameIfAvailable(registrar, "GB_2312-80")) {
+ registerEncodingAliasIfAvailable(registrar, "GB_2312-80", "CHINESE");
+ registerEncodingAliasIfAvailable(registrar, "GB_2312-80", "csISO58GB231280");
+ registerEncodingAliasIfAvailable(registrar, "GB_2312-80", "GB2312.1980-0");
+ registerEncodingAliasIfAvailable(registrar, "GB_2312-80", "ISO-IR-58");
+ }
+
+ // Central European
+ if (registerEncodingNameIfAvailable(registrar, "ISO-8859-2")) {
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-2", "ISO-IR-101");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-2", "ISO8859-2");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-2", "ISO_8859-2");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-2", "ISO_8859-2:1987");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-2", "L2");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-2", "LATIN2");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-2", "CSISOLATIN2");
+ }
+ if (registerEncodingNameIfAvailable(registrar, "CP1250")) {
+ registerEncodingAliasIfAvailable(registrar, "CP1250", "MS-EE");
+ registerEncodingAliasIfAvailable(registrar, "CP1250", "WINDOWS-1250");
+ }
+ registerEncodingNameIfAvailable(registrar, "MAC-CENTRALEUROPE");
+
+ // Vietnamese
+ if (registerEncodingNameIfAvailable(registrar, "CP1258"))
+ registerEncodingAliasIfAvailable(registrar, "CP1258", "WINDOWS-1258");
+
+ // Turkish
+ if (registerEncodingNameIfAvailable(registrar, "CP1254")) {
+ registerEncodingAliasIfAvailable(registrar, "CP1254", "MS-TURK");
+ registerEncodingAliasIfAvailable(registrar, "CP1254", "WINDOWS-1254");
+ }
+ if (registerEncodingNameIfAvailable(registrar, "ISO-8859-9")) {
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-9", "ISO-IR-148");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-9", "ISO8859-9");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-9", "ISO_8859-9");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-9", "ISO_8859-9:1989");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-9", "L5");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-9", "LATIN5");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-9", "CSISOLATIN5");
+ }
+
+ // Baltic
+ if (registerEncodingNameIfAvailable(registrar, "CP1257")) {
+ registerEncodingAliasIfAvailable(registrar, "CP1257", "WINBALTRIM");
+ registerEncodingAliasIfAvailable(registrar, "CP1257", "WINDOWS-1257");
+ }
+ if (registerEncodingNameIfAvailable(registrar, "ISO-8859-4")) {
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-4", "ISO-IR-110");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-4", "ISO8859-4");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-4", "ISO_8859-4");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-4", "ISO_8859-4:1988");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-4", "L4");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-4", "LATIN4");
+ registerEncodingAliasIfAvailable(registrar, "ISO-8859-4", "CSISOLATIN4");
+ }
}
void TextCodecGtk::registerExtendedCodecs(TextCodecRegistrar registrar)
{
- registerCodecs(registrar, true);
+ // Western
+ registerCodecIfAvailable(registrar, "MACROMAN");
+
+ // Japanese
+ registerCodecIfAvailable(registrar, "Shift_JIS");
+ registerCodecIfAvailable(registrar, "EUC-JP");
+ registerCodecIfAvailable(registrar, "ISO-2022-JP");
+
+ // Traditional Chinese
+ registerCodecIfAvailable(registrar, "BIG5");
+ registerCodecIfAvailable(registrar, "BIG5-HKSCS");
+ registerCodecIfAvailable(registrar, "CP950");
+
+ // Korean
+ registerCodecIfAvailable(registrar, "ISO-2022-KR");
+ registerCodecIfAvailable(registrar, "CP949");
+ registerCodecIfAvailable(registrar, "EUC-KR");
+
+ // Arabic
+ registerCodecIfAvailable(registrar, "ISO-8859-6");
+ // rearranged, windows-1256 now declared the canonical name and put to lowercase to fix /fast/encoding/ahram-org-eg.html test case
+ registerCodecIfAvailable(registrar, "windows-1256");
+
+ // Hebrew
+ registerCodecIfAvailable(registrar, "ISO-8859-8");
+ // rearranged, moved windows-1255 as canonical and lowercased, fixing /fast/encoding/meta-charset.html
+ registerCodecIfAvailable(registrar, "windows-1255");
+
+ // Greek
+ registerCodecIfAvailable(registrar, "ISO-8859-7");
+ registerCodecIfAvailable(registrar, "CP869");
+ registerCodecIfAvailable(registrar, "WINDOWS-1253");
+
+ // Cyrillic
+ registerCodecIfAvailable(registrar, "ISO-8859-5");
+ registerCodecIfAvailable(registrar, "KOI8-R");
+ registerCodecIfAvailable(registrar, "CP866");
+ registerCodecIfAvailable(registrar, "KOI8-U");
+ // CP1251 added to pass /fast/encoding/charset-cp1251.html
+ registerCodecIfAvailable(registrar, "windows-1251");
+ registerCodecIfAvailable(registrar, "mac-cyrillic");
+
+ // Thai
+ registerCodecIfAvailable(registrar, "CP874");
+ registerCodecIfAvailable(registrar, "TIS-620");
+
+ // Simplified Chinese
+ registerCodecIfAvailable(registrar, "GBK");
+ registerCodecIfAvailable(registrar, "HZ");
+ registerCodecIfAvailable(registrar, "GB18030");
+ registerCodecIfAvailable(registrar, "EUC-CN");
+ registerCodecIfAvailable(registrar, "GB_2312-80");
+
+ // Central European
+ registerCodecIfAvailable(registrar, "ISO-8859-2");
+ registerCodecIfAvailable(registrar, "CP1250");
+ registerCodecIfAvailable(registrar, "MAC-CENTRALEUROPE");
+
+ // Vietnamese
+ registerCodecIfAvailable(registrar, "CP1258");
+
+ // Turkish
+ registerCodecIfAvailable(registrar, "CP1254");
+ registerCodecIfAvailable(registrar, "ISO-8859-9");
+
+ // Baltic
+ registerCodecIfAvailable(registrar, "CP1257");
+ registerCodecIfAvailable(registrar, "ISO-8859-4");
}
TextCodecGtk::TextCodecGtk(const TextEncoding& encoding)
@@ -332,14 +425,14 @@ void TextCodecGtk::createIConvDecoder() const
{
ASSERT(m_iconvDecoder == reinterpret_cast<GIConv>(-1));
- m_iconvDecoder = g_iconv_open(m_internalEncodingName, m_encoding.name());
+ m_iconvDecoder = g_iconv_open(internalEncodingName, m_encoding.name());
}
void TextCodecGtk::createIConvEncoder() const
{
ASSERT(m_iconvDecoder == reinterpret_cast<GIConv>(-1));
- m_iconvEncoder = g_iconv_open(m_encoding.name(), m_internalEncodingName);
+ m_iconvEncoder = g_iconv_open(m_encoding.name(), internalEncodingName);
}
String TextCodecGtk::decode(const char* bytes, size_t length, bool flush, bool stopOnError, bool& sawError)
diff --git a/WebCore/platform/text/gtk/TextCodecGtk.h b/WebCore/platform/text/gtk/TextCodecGtk.h
index a8af752..65ddfb8 100644
--- a/WebCore/platform/text/gtk/TextCodecGtk.h
+++ b/WebCore/platform/text/gtk/TextCodecGtk.h
@@ -53,93 +53,11 @@ namespace WebCore {
void createIConvDecoder() const;
void createIConvEncoder() const;
- static void registerEncodingNames(EncodingNameRegistrar registrar, bool extended);
- static void registerCodecs(TextCodecRegistrar registrar, bool extended);
- static gboolean isEncodingAvailable(const gchar*);
-
TextEncoding m_encoding;
size_t m_numBufferedBytes;
unsigned char m_bufferedBytes[16]; // bigger than any single multi-byte character
mutable GIConv m_iconvDecoder;
mutable GIConv m_iconvEncoder;
-
- static const gchar* m_internalEncodingName;
-
- typedef const gchar* const codecAliasList[];
-
- // Unicode
- static codecAliasList m_codecAliases_UTF_8;
-
- // Western
- static codecAliasList m_codecAliases_ISO_8859_1;
- static codecAliasList m_codecAliases_MACROMAN;
-
- // Japanese
- static codecAliasList m_codecAliases_SHIFT_JIS;
- static codecAliasList m_codecAliases_EUC_JP;
- static codecAliasList m_codecAliases_ISO_2022_JP;
-
- // Traditional Chinese
- static codecAliasList m_codecAliases_BIG5;
- static codecAliasList m_codecAliases_BIG5_HKSCS;
- static codecAliasList m_codecAliases_CP950;
-
- // Korean
- static codecAliasList m_codecAliases_ISO_2022_KR;
- static codecAliasList m_codecAliases_CP949;
- static codecAliasList m_codecAliases_EUC_KR;
-
- // Arabic
- static codecAliasList m_codecAliases_ISO_8859_6;
- static codecAliasList m_codecAliases_CP1256;
-
- // Hebrew
- static codecAliasList m_codecAliases_ISO_8859_8;
- static codecAliasList m_codecAliases_CP1255;
-
- // Greek
- static codecAliasList m_codecAliases_ISO_8859_7;
- static codecAliasList m_codecAliases_CP869;
- static codecAliasList m_codecAliases_WINDOWS_1253;
-
- // Cyrillic
- static codecAliasList m_codecAliases_ISO_8859_5;
- static codecAliasList m_codecAliases_KOI8_R;
- static codecAliasList m_codecAliases_CP866;
- static codecAliasList m_codecAliases_KOI8_U;
- static codecAliasList m_codecAliases_WINDOWS_1251;
- static codecAliasList m_codecAliases_MACCYRILLIC;
-
- // Thai
- static codecAliasList m_codecAliases_CP874;
- static codecAliasList m_codecAliases_TIS_620;
-
- // Simplified Chinese
- static codecAliasList m_codecAliases_GBK;
- static codecAliasList m_codecAliases_HZ;
- static codecAliasList m_codecAliases_GB18030;
- static codecAliasList m_codecAliases_EUC_CN;
- static codecAliasList m_codecAliases_2312_80;
-
- // Central European
- static codecAliasList m_codecAliases_ISO_8859_2;
- static codecAliasList m_codecAliases_CP1250;
- static codecAliasList m_codecAliases_MACCENTRALEUROPE;
-
- // Vietnamese
- static codecAliasList m_codecAliases_CP1258;
-
- // Turkish
- static codecAliasList m_codecAliases_CP1254;
- static codecAliasList m_codecAliases_ISO_8859_9;
-
- // Baltic
- static codecAliasList m_codecAliases_CP1257;
- static codecAliasList m_codecAliases_ISO_8859_4;
-
- static gconstpointer const m_iconvBaseCodecList[];
- static gconstpointer const m_iconvExtendedCodecList[];
-
};
} // namespace WebCore
--
WebKit Debian packaging
More information about the Pkg-webkit-commits
mailing list