Diff
Modified: trunk/LayoutTests/ChangeLog (225026 => 225027)
--- trunk/LayoutTests/ChangeLog 2017-11-19 01:55:37 UTC (rev 225026)
+++ trunk/LayoutTests/ChangeLog 2017-11-19 03:42:49 UTC (rev 225027)
@@ -1,3 +1,16 @@
+2017-11-18 Maciej Stachowiak <m...@apple.com>
+
+ Remove TEC support and all TEC-only encodings except EUC-TW (which now uses ICU)
+ https://bugs.webkit.org/show_bug.cgi?id=179582
+
+ Reviewed by Darin Adler.
+
+ * fast/encoding/legacy-tec-encodings.html: Added. Verify that we
+ no longer support these encodings.
+ * fast/encoding/legacy-tec-encodings-expected.txt: Added.
+ * platform/mac/fast/encoding/xnextstep-decoding.html: Removed. We no longer support this encoding.
+ * platform/mac/fast/encoding/xnextstep-decoding-expected.txt: Removed.
+
2017-11-18 Simon Fraser <simon.fra...@apple.com>
Line of garbage pixels at the bottom of an feTurbulence sometimes
Added: trunk/LayoutTests/fast/encoding/legacy-tec-encodings-expected.txt (0 => 225027)
--- trunk/LayoutTests/fast/encoding/legacy-tec-encodings-expected.txt (rev 0)
+++ trunk/LayoutTests/fast/encoding/legacy-tec-encodings-expected.txt 2017-11-19 03:42:49 UTC (rev 225027)
@@ -0,0 +1,64 @@
+This test verifies that encodings that used to be supported by TEC on macOS are not supported.
+
+On success, you will see a series of "PASS" messages, followed by "TEST COMPLETE".
+
+
+The following encodings should not be supported
+PASS new TextDecoder("cp950").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("cp737").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("ibm737").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("ISO-2022-JP-3").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("JIS_C6226-1978").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("Shift_JIS_X0213-2000").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("ibm-942_P12A-1999").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("ibm-1399_P110-2003").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("JIS_X0212-1990").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("x-mac-arabic").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("x-mac-croatian").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("x-mac-hebrew").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("x-mac-icelandic").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("x-mac-romanian").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("x-mac-thai").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("johab").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("x-mac-dingbats").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("x-mac-symbol").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("JIS_X0208-1990").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("JIS_X0208-1983").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("csiso159jisx02121990").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("isoir159").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("x0212").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("jis_x0208-1983").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("csiso87jisx0208").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("isoir87").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("ibm-953_P100-2000").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("macos-518-10.2").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("macos-36_2-10.2").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("macos-1285-10.2").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("macos-37_5-10.2").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("macos-38_2-10.2").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("macos-21-10.5").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("windows-1361-2000").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("macos-34-10.2").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("macos-33-10.5").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("ibm-952_P110-1997").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("ibm-955_P110-1997").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("x-mac-chinesesimp").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("xmacsimpchinese").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("x-mac-chinesetrad").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("xmactradchinese").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("x-mac-japanese").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("x-mac-korean").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("x-mac-vt100").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("x-nextstep").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("x-mac-farsi").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("x-mac-roman-latin1").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("x-mac-devanagari").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("x-mac-gujarati").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("x-mac-gurmukhi").encoding threw exception RangeError: Bad value.
+PASS new TextDecoder("x-mac-tibetan").encoding threw exception RangeError: Bad value.
+The following encoding names are supported by WebKit cross-platform, but some may be removed at a later time.
+PASS new TextDecoder("EUC-TW").encoding is "euc-tw"
+PASS successfullyParsed is true
+
+TEST COMPLETE
+
Added: trunk/LayoutTests/fast/encoding/legacy-tec-encodings.html (0 => 225027)
--- trunk/LayoutTests/fast/encoding/legacy-tec-encodings.html (rev 0)
+++ trunk/LayoutTests/fast/encoding/legacy-tec-encodings.html 2017-11-19 03:42:49 UTC (rev 225027)
@@ -0,0 +1,39 @@
+<!DOCTYPE html>
+<html>
+<head>
+<meta charset="utf-8">
+<script src=""
+</head>
+<body>
+<script>
+description("This test verifies that encodings that used to be supported by TEC on macOS are not supported.");
+
+debug("The following encodings should not be supported");
+let tecLegacyEncodings = ['cp950', 'cp737', 'ibm737',
+'ISO-2022-JP-3', 'JIS_C6226-1978', 'Shift_JIS_X0213-2000', 'ibm-942_P12A-1999', 'ibm-1399_P110-2003',
+'JIS_X0212-1990', 'x-mac-arabic', 'x-mac-croatian', 'x-mac-hebrew', 'x-mac-icelandic', 'x-mac-romanian', 'x-mac-thai', 'johab', 'x-mac-dingbats', 'x-mac-symbol', 'JIS_X0208-1990', 'JIS_X0208-1983', 'csiso159jisx02121990', 'isoir159', 'x0212', 'jis_x0208-1983', 'csiso87jisx0208', 'isoir87',
+'ibm-953_P100-2000', 'macos-518-10.2', 'macos-36_2-10.2', 'macos-1285-10.2', 'macos-37_5-10.2', 'macos-38_2-10.2', 'macos-21-10.5', 'windows-1361-2000', 'macos-34-10.2', 'macos-33-10.5', 'ibm-952_P110-1997', 'ibm-955_P110-1997',
+'x-mac-chinesesimp', 'xmacsimpchinese', 'x-mac-chinesetrad', 'xmactradchinese', 'x-mac-japanese', 'x-mac-korean', 'x-mac-vt100', 'x-nextstep', 'x-mac-farsi', 'x-mac-roman-latin1', 'x-mac-devanagari', 'x-mac-gujarati', 'x-mac-gurmukhi', 'x-mac-tibetan',
+];
+
+for (let encoding of tecLegacyEncodings) {
+ let canonical_name_expr = 'new TextDecoder("' + encoding + '").encoding';
+ shouldThrow(canonical_name_expr);
+}
+
+debug("The following encoding names are supported by WebKit cross-platform, but some may be removed at a later time.");
+let validForNow = [
+ {encoding: 'euc-tw', aliases: ['EUC-TW']},
+];
+
+for (let encoding of validForNow) {
+ for (let alias of encoding.aliases) {
+ let canonical_name_expr = 'new TextDecoder("' + alias + '").encoding';
+ shouldBe(canonical_name_expr, '"' + encoding.encoding + '"');
+ }
+}
+
+
+</script>
+</body>
+</html>
Deleted: trunk/LayoutTests/platform/mac/fast/encoding/xnextstep-decoding-expected.txt (225026 => 225027)
--- trunk/LayoutTests/platform/mac/fast/encoding/xnextstep-decoding-expected.txt 2017-11-19 01:55:37 UTC (rev 225026)
+++ trunk/LayoutTests/platform/mac/fast/encoding/xnextstep-decoding-expected.txt 2017-11-19 03:42:49 UTC (rev 225027)
@@ -1,13 +0,0 @@
-This tests decoding characters in various character sets.
-
-On success, you will see a series of "PASS" messages, followed by "TEST COMPLETE".
-
-
-PASS decode('x-nextstep', '%E1') is 'U+00C6'
-
-The x-nextstep test is meant to ensure that we still support legacy encodings that are not part of ICU - it is expected that it fails in other browsers, which do not support this particular encoding. See http://bugs.webkit.org/show_bug.cgi?id=4195 for more details.
-
-PASS successfullyParsed is true
-
-TEST COMPLETE
-
Deleted: trunk/LayoutTests/platform/mac/fast/encoding/xnextstep-decoding.html (225026 => 225027)
--- trunk/LayoutTests/platform/mac/fast/encoding/xnextstep-decoding.html 2017-11-19 01:55:37 UTC (rev 225026)
+++ trunk/LayoutTests/platform/mac/fast/encoding/xnextstep-decoding.html 2017-11-19 03:42:49 UTC (rev 225027)
@@ -1,24 +0,0 @@
-<html>
-<head>
-<script src=""
-<script src=""
-</head>
-<body>
-<p id="description"></p>
-<div id="console"></div>
-<script>
-
-description("This tests decoding characters in various character sets.");
-
-testDecode('x-nextstep', '%E1', 'U+00C6');
-debug('');
-
-debug("The x-nextstep test is meant to ensure that we still support legacy encodings that are not part of ICU - it is expected that it fails in other browsers, which do not support this particular encoding. See <a href="" for more details.");
-
-debug('');
-
-
-</script>
-<script src=""
-</body>
-</html>
Modified: trunk/Source/WebCore/ChangeLog (225026 => 225027)
--- trunk/Source/WebCore/ChangeLog 2017-11-19 01:55:37 UTC (rev 225026)
+++ trunk/Source/WebCore/ChangeLog 2017-11-19 03:42:49 UTC (rev 225027)
@@ -1,3 +1,36 @@
+2017-11-18 Maciej Stachowiak <m...@apple.com>
+
+ Remove TEC support and all TEC-only encodings except EUC-TW (which now uses ICU)
+ https://bugs.webkit.org/show_bug.cgi?id=179582
+
+ Reviewed by Darin Adler.
+
+ Already covered by fast/encoding/legacy-tec-encodings.html
+
+ * platform/text/TextCodecICU.cpp: Add support for EUC-TW.
+
+ Remove all vestiges of TEC text codec and its related autogeneration scripts.
+
+ * DerivedSources.make:
+ * PlatformMac.cmake:
+ * SourcesMac.txt:
+ * WebCore.order:
+ * WebCore.xcodeproj/project.pbxproj:
+ * platform/ThreadGlobalData.cpp:
+ (WebCore::ThreadGlobalData::ThreadGlobalData): No more cached TEC decoder.
+ (WebCore::ThreadGlobalData::destroy): ditto
+ * platform/ThreadGlobalData.h:
+ (WebCore::ThreadGlobalData::ThreadGlobalData::cachedConverterTEC): Deleted.
+ * platform/text/TextEncodingRegistry.cpp:
+ (WebCore::extendTextCodecMaps): Don't add TEC decoders on MAc.
+ * platform/text/mac/CharsetData.h: Removed.
+ * platform/text/mac/TextCodecMac.cpp: Removed.
+ * platform/text/mac/TextCodecMac.h: Removed.
+ * platform/text/mac/character-sets.txt: Removed.
+ * platform/text/mac/ios-encodings.txt: Removed.
+ * platform/text/mac/mac-encodings.txt: Removed.
+ * platform/text/mac/make-charset-table.pl: Removed.
+
2017-11-18 Simon Fraser <simon.fra...@apple.com>
Mechanical cleanup of FE* files
Modified: trunk/Source/WebCore/DerivedSources.make (225026 => 225027)
--- trunk/Source/WebCore/DerivedSources.make 2017-11-19 01:55:37 UTC (rev 225026)
+++ trunk/Source/WebCore/DerivedSources.make 2017-11-19 03:42:49 UTC (rev 225027)
@@ -1531,26 +1531,3 @@
# ------------------------
-# Mac-specific rules
-
-ifeq ($(OS),MACOS)
-
-all : CharsetData.cpp
-
-# --------
-
-# character set name table
-
-ifeq ($(WTF_PLATFORM_IOS),1)
-ENCODINGS_FILENAME := ios-encodings.txt
-else
-ENCODINGS_FILENAME := mac-encodings.txt
-endif # WTF_PLATFORM_IOS
-
-CharsetData.cpp : platform/text/mac/make-charset-table.pl platform/text/mac/character-sets.txt platform/text/mac/$(ENCODINGS_FILENAME)
- $(PERL) $^ kTextEncoding > $@
-
-# --------
-
-endif # MACOS
-
Modified: trunk/Source/WebCore/PlatformMac.cmake (225026 => 225027)
--- trunk/Source/WebCore/PlatformMac.cmake 2017-11-19 01:55:37 UTC (rev 225026)
+++ trunk/Source/WebCore/PlatformMac.cmake 2017-11-19 03:42:49 UTC (rev 225027)
@@ -138,19 +138,6 @@
${WEBCORE_DIR}/Modules/plugins/QuickTimePluginReplacement.js
)
-#FIXME: Use ios-encodings.txt once we get CMake working for iOS.
-add_custom_command(
- OUTPUT ${DERIVED_SOURCES_WEBCORE_DIR}/CharsetData.cpp
- MAIN_DEPENDENCY ${WEBCORE_DIR}/platform/text/mac/make-charset-table.pl
- DEPENDS platform/text/mac/character-sets.txt
- DEPENDS platform/text/mac/mac-encodings.txt
- COMMAND ${PERL_EXECUTABLE} ${WEBCORE_DIR}/platform/text/mac/make-charset-table.pl ${WEBCORE_DIR}/platform/text/mac/character-sets.txt ${WEBCORE_DIR}/platform/text/mac/mac-encodings.txt kTextEncoding > ${DERIVED_SOURCES_WEBCORE_DIR}/CharsetData.cpp
- VERBATIM)
-
-list(APPEND WebCore_DERIVED_SOURCES
- ${DERIVED_SOURCES_WEBCORE_DIR}/CharsetData.cpp
-)
-
list(APPEND WebCore_SYSTEM_INCLUDE_DIRECTORIES
"${CMAKE_OSX_SYSROOT}/usr/include/libxslt"
"${CMAKE_OSX_SYSROOT}/usr/include/libxml2"
@@ -479,7 +466,6 @@
platform/text/mac/LocaleMac.mm
platform/text/mac/TextBoundaries.mm
- platform/text/mac/TextCodecMac.cpp
platform/text/mac/TextEncodingRegistryMac.mm
rendering/RenderThemeCocoa.mm
Modified: trunk/Source/WebCore/SourcesMac.txt (225026 => 225027)
--- trunk/Source/WebCore/SourcesMac.txt 2017-11-19 01:55:37 UTC (rev 225026)
+++ trunk/Source/WebCore/SourcesMac.txt 2017-11-19 03:42:49 UTC (rev 225027)
@@ -112,7 +112,6 @@
platform/network/mac/NetworkStateNotifierMac.cpp
-platform/text/mac/TextCodecMac.cpp
platform/text/mac/TextEncodingRegistryMac.mm
rendering/RenderThemeMac.mm
Modified: trunk/Source/WebCore/WebCore.order (225026 => 225027)
--- trunk/Source/WebCore/WebCore.order 2017-11-19 01:55:37 UTC (rev 225026)
+++ trunk/Source/WebCore/WebCore.order 2017-11-19 03:42:49 UTC (rev 225027)
@@ -16129,8 +16129,6 @@
__ZN7WebCore17HTMLButtonElement19defaultEventHandlerEPNS_5EventE
__ZN7WebCore12TextCodecICU21registerEncodingNamesEPFvPKcS2_E
__ZN7WebCore12TextCodecICU14registerCodecsEPFvPKcPFN3WTF10PassOwnPtrINS_9TextCodecEEERKNS_12TextEncodingEPKvESB_E
-__ZN7WebCore12TextCodecMac21registerEncodingNamesEPFvPKcS2_E
-__ZN7WebCore12TextCodecMac14registerCodecsEPFvPKcPFN3WTF10PassOwnPtrINS_9TextCodecEEERKNS_12TextEncodingEPKvESB_E
__ZN3WTF6VectorIPKcLm0ENS_15CrashOnOverflowEE14expandCapacityEmPKS2_
__ZN3WTF6VectorIPKcLm0ENS_15CrashOnOverflowEE15reserveCapacityEm
__ZN3WTF7HashMapIPKcN7WebCore16TextCodecFactoryENS_7PtrHashIS2_EENS_10HashTraitsIS2_EENS7_IS4_EEE6removeERKS2_
@@ -23707,7 +23705,6 @@
__ZTVN7WebCore4TextE
__ZTVN7WebCore12TextCodecICUE
__ZTVN7WebCore15TextCodecLatin1E
-__ZTVN7WebCore12TextCodecMacE
__ZTVN7WebCore20TextCodecUserDefinedE
__ZTVN7WebCore14TextCodecUTF16E
__ZTVN7WebCore13TextCodecUTF8E
Modified: trunk/Source/WebCore/WebCore.xcodeproj/project.pbxproj (225026 => 225027)
--- trunk/Source/WebCore/WebCore.xcodeproj/project.pbxproj 2017-11-19 01:55:37 UTC (rev 225026)
+++ trunk/Source/WebCore/WebCore.xcodeproj/project.pbxproj 2017-11-19 03:42:49 UTC (rev 225027)
@@ -1596,7 +1596,6 @@
538EC9321F99B9F7004D22A8 /* JSMallocStatistics.cpp in Sources */ = {isa = PBXBuildFile; fileRef = A7B4EA6814C9348400C8F5BF /* JSMallocStatistics.cpp */; };
538EC9331F99B9F7004D22A8 /* JSMockCDMFactory.h in Headers */ = {isa = PBXBuildFile; fileRef = CDF4B72E1E03CA4A00E235A2 /* JSMockCDMFactory.h */; };
538EC9341F99B9F7004D22A8 /* JSMockPageOverlay.h in Headers */ = {isa = PBXBuildFile; fileRef = 2D6F3E931C1F85550061DBD4 /* JSMockPageOverlay.h */; };
- 538EC93B1F99BE50004D22A8 /* CharsetData.cpp in Sources */ = {isa = PBXBuildFile; fileRef = 656581AC09D14EE6000E61D7 /* CharsetData.cpp */; };
538EC93E1F99BF5A004D22A8 /* JSQuickTimePluginReplacement.cpp in Sources */ = {isa = PBXBuildFile; fileRef = 077664FA183E6B5C00133B92 /* JSQuickTimePluginReplacement.cpp */; };
538F10A81F9022A4005102CE /* SoftLinkLibxslt.cpp in Sources */ = {isa = PBXBuildFile; fileRef = 538F10A31F900BDC005102CE /* SoftLinkLibxslt.cpp */; };
53B895AF19DC7ED9009CAA93 /* Microtasks.h in Headers */ = {isa = PBXBuildFile; fileRef = 53B895AD19DC7C37009CAA93 /* Microtasks.h */; settings = {ATTRIBUTES = (Private, ); }; };
@@ -3295,11 +3294,9 @@
B2A1F2AE0CEF0ABF00442F6A /* SVGGlyphElement.h in Headers */ = {isa = PBXBuildFile; fileRef = B2A1F2A50CEF0ABF00442F6A /* SVGGlyphElement.h */; };
B2A1F2B10CEF0ABF00442F6A /* SVGMissingGlyphElement.h in Headers */ = {isa = PBXBuildFile; fileRef = B2A1F2A80CEF0ABF00442F6A /* SVGMissingGlyphElement.h */; };
B2AFFC7E0D00A5C10030074D /* FontCustomPlatformData.h in Headers */ = {isa = PBXBuildFile; fileRef = B2AFFC760D00A5C10030074D /* FontCustomPlatformData.h */; };
- B2AFFC9A0D00A5DF0030074D /* TextCodecMac.h in Headers */ = {isa = PBXBuildFile; fileRef = B2AFFC8F0D00A5DF0030074D /* TextCodecMac.h */; };
B2B1F7170D00CAA8004AEA64 /* PointerEventsHitRules.h in Headers */ = {isa = PBXBuildFile; fileRef = B2B1F7150D00CAA8004AEA64 /* PointerEventsHitRules.h */; };
B2C3DA240D006C1D00EF6F26 /* BidiContext.h in Headers */ = {isa = PBXBuildFile; fileRef = B2C3D9F30D006C1D00EF6F26 /* BidiContext.h */; settings = {ATTRIBUTES = (Private, ); }; };
B2C3DA250D006C1D00EF6F26 /* BidiResolver.h in Headers */ = {isa = PBXBuildFile; fileRef = B2C3D9F40D006C1D00EF6F26 /* BidiResolver.h */; settings = {ATTRIBUTES = (Private, ); }; };
- B2C3DA2A0D006C1D00EF6F26 /* CharsetData.h in Headers */ = {isa = PBXBuildFile; fileRef = B2C3D9FA0D006C1D00EF6F26 /* CharsetData.h */; settings = {ATTRIBUTES = (Private, ); }; };
B2C3DA2F0D006C1D00EF6F26 /* SegmentedString.h in Headers */ = {isa = PBXBuildFile; fileRef = B2C3D9FF0D006C1D00EF6F26 /* SegmentedString.h */; settings = {ATTRIBUTES = (Private, ); }; };
B2C3DA340D006C1D00EF6F26 /* TextBoundaries.h in Headers */ = {isa = PBXBuildFile; fileRef = B2C3DA040D006C1D00EF6F26 /* TextBoundaries.h */; settings = {ATTRIBUTES = (Private, ); }; };
B2C3DA3A0D006C1D00EF6F26 /* TextCodec.h in Headers */ = {isa = PBXBuildFile; fileRef = B2C3DA0A0D006C1D00EF6F26 /* TextCodec.h */; settings = {ATTRIBUTES = (Private, ); }; };
@@ -5409,7 +5406,6 @@
0F4966A81DB40C4300A274BB /* JSDOMPointReadOnly.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; path = JSDOMPointReadOnly.cpp; sourceTree = "<group>"; };
0F4966A91DB40C4300A274BB /* JSDOMPointReadOnly.h */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.h; path = JSDOMPointReadOnly.h; sourceTree = "<group>"; };
0F4E57161313276200CF85AF /* RenderSVGAllInOne.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; path = RenderSVGAllInOne.cpp; sourceTree = "<group>"; };
- 0F54DCCC1880C6AB003EEDBB /* ios-encodings.txt */ = {isa = PBXFileReference; lastKnownFileType = text; path = "ios-encodings.txt"; sourceTree = "<group>"; };
0F54DCE31881051D003EEDBB /* TextAutoSizing.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; path = TextAutoSizing.cpp; sourceTree = "<group>"; };
0F54DCE41881051D003EEDBB /* TextAutoSizing.h */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.h; path = TextAutoSizing.h; sourceTree = "<group>"; };
0F54DD051881D5F5003EEDBB /* Touch.h */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.h; path = Touch.h; sourceTree = "<group>"; };
@@ -8395,7 +8391,6 @@
656580EF09D12B20000E61D7 /* CSSPropertyNames.h */ = {isa = PBXFileReference; fileEncoding = 30; lastKnownFileType = sourcecode.c.h; path = CSSPropertyNames.h; sourceTree = "<group>"; };
6565814709D13043000E61D7 /* CSSValueKeywords.gperf */ = {isa = PBXFileReference; fileEncoding = 30; lastKnownFileType = text; path = CSSValueKeywords.gperf; sourceTree = "<group>"; };
6565814809D13043000E61D7 /* CSSValueKeywords.h */ = {isa = PBXFileReference; fileEncoding = 30; lastKnownFileType = sourcecode.c.h; path = CSSValueKeywords.h; sourceTree = "<group>"; };
- 656581AC09D14EE6000E61D7 /* CharsetData.cpp */ = {isa = PBXFileReference; fileEncoding = 30; lastKnownFileType = sourcecode.cpp.cpp; path = CharsetData.cpp; sourceTree = "<group>"; };
656581AE09D14EE6000E61D7 /* UserAgentStyleSheets.h */ = {isa = PBXFileReference; fileEncoding = 30; lastKnownFileType = sourcecode.c.h; path = UserAgentStyleSheets.h; sourceTree = "<group>"; };
656581AF09D14EE6000E61D7 /* UserAgentStyleSheetsData.cpp */ = {isa = PBXFileReference; fileEncoding = 30; lastKnownFileType = sourcecode.cpp.cpp; path = UserAgentStyleSheetsData.cpp; sourceTree = "<group>"; };
656581E609D1508D000E61D7 /* SVGElementFactory.cpp */ = {isa = PBXFileReference; fileEncoding = 30; lastKnownFileType = sourcecode.cpp.cpp; path = SVGElementFactory.cpp; sourceTree = "<group>"; };
@@ -11786,18 +11781,12 @@
B2AFFC760D00A5C10030074D /* FontCustomPlatformData.h */ = {isa = PBXFileReference; fileEncoding = 30; lastKnownFileType = sourcecode.c.h; path = FontCustomPlatformData.h; sourceTree = "<group>"; };
B2AFFC780D00A5C10030074D /* FontCascadeCocoa.mm */ = {isa = PBXFileReference; fileEncoding = 30; lastKnownFileType = sourcecode.cpp.objcpp; path = FontCascadeCocoa.mm; sourceTree = "<group>"; };
B2AFFC7B0D00A5C10030074D /* GlyphPageMac.cpp */ = {isa = PBXFileReference; fileEncoding = 30; lastKnownFileType = sourcecode.cpp.cpp; path = GlyphPageMac.cpp; sourceTree = "<group>"; };
- B2AFFC850D00A5DF0030074D /* character-sets.txt */ = {isa = PBXFileReference; fileEncoding = 30; lastKnownFileType = text; path = "character-sets.txt"; sourceTree = "<group>"; };
- B2AFFC860D00A5DF0030074D /* mac-encodings.txt */ = {isa = PBXFileReference; fileEncoding = 30; lastKnownFileType = text; path = "mac-encodings.txt"; sourceTree = "<group>"; };
- B2AFFC870D00A5DF0030074D /* make-charset-table.pl */ = {isa = PBXFileReference; fileEncoding = 30; lastKnownFileType = text.script.perl; path = "make-charset-table.pl"; sourceTree = "<group>"; };
B2AFFC8C0D00A5DF0030074D /* TextBoundaries.mm */ = {isa = PBXFileReference; fileEncoding = 30; lastKnownFileType = sourcecode.cpp.objcpp; path = TextBoundaries.mm; sourceTree = "<group>"; };
- B2AFFC8E0D00A5DF0030074D /* TextCodecMac.cpp */ = {isa = PBXFileReference; fileEncoding = 30; lastKnownFileType = sourcecode.cpp.cpp; path = TextCodecMac.cpp; sourceTree = "<group>"; };
- B2AFFC8F0D00A5DF0030074D /* TextCodecMac.h */ = {isa = PBXFileReference; fileEncoding = 30; lastKnownFileType = sourcecode.c.h; path = TextCodecMac.h; sourceTree = "<group>"; };
B2B1F7140D00CAA8004AEA64 /* PointerEventsHitRules.cpp */ = {isa = PBXFileReference; fileEncoding = 30; lastKnownFileType = sourcecode.cpp.cpp; path = PointerEventsHitRules.cpp; sourceTree = "<group>"; };
B2B1F7150D00CAA8004AEA64 /* PointerEventsHitRules.h */ = {isa = PBXFileReference; fileEncoding = 30; lastKnownFileType = sourcecode.c.h; path = PointerEventsHitRules.h; sourceTree = "<group>"; };
B2C3D9F20D006C1D00EF6F26 /* BidiContext.cpp */ = {isa = PBXFileReference; fileEncoding = 30; lastKnownFileType = sourcecode.cpp.cpp; path = BidiContext.cpp; sourceTree = "<group>"; };
B2C3D9F30D006C1D00EF6F26 /* BidiContext.h */ = {isa = PBXFileReference; fileEncoding = 30; lastKnownFileType = sourcecode.c.h; path = BidiContext.h; sourceTree = "<group>"; };
B2C3D9F40D006C1D00EF6F26 /* BidiResolver.h */ = {isa = PBXFileReference; fileEncoding = 30; lastKnownFileType = sourcecode.c.h; path = BidiResolver.h; sourceTree = "<group>"; };
- B2C3D9FA0D006C1D00EF6F26 /* CharsetData.h */ = {isa = PBXFileReference; fileEncoding = 30; lastKnownFileType = sourcecode.c.h; path = CharsetData.h; sourceTree = "<group>"; };
B2C3D9FE0D006C1D00EF6F26 /* SegmentedString.cpp */ = {isa = PBXFileReference; fileEncoding = 30; lastKnownFileType = sourcecode.cpp.cpp; path = SegmentedString.cpp; sourceTree = "<group>"; };
B2C3D9FF0D006C1D00EF6F26 /* SegmentedString.h */ = {isa = PBXFileReference; fileEncoding = 30; lastKnownFileType = sourcecode.c.h; path = SegmentedString.h; sourceTree = "<group>"; };
B2C3DA040D006C1D00EF6F26 /* TextBoundaries.h */ = {isa = PBXFileReference; fileEncoding = 30; lastKnownFileType = sourcecode.c.h; path = TextBoundaries.h; sourceTree = "<group>"; };
@@ -18052,7 +18041,6 @@
538EC7EA1F96A95B004D22A8 /* unified-sources */,
9908B0F31BCACFFE00ED0F65 /* ByteLengthQueuingStrategyBuiltins.cpp */,
9908B0F51BCAD07D00ED0F65 /* ByteLengthQueuingStrategyBuiltins.h */,
- 656581AC09D14EE6000E61D7 /* CharsetData.cpp */,
E406F3FB1198307D009D59D6 /* ColorData.cpp */,
9908B0F61BCAD07D00ED0F65 /* CountQueuingStrategyBuiltins.cpp */,
9908B0F71BCAD07D00ED0F65 /* CountQueuingStrategyBuiltins.h */,
@@ -22854,16 +22842,9 @@
B2C3D9F90D006C1D00EF6F26 /* mac */ = {
isa = PBXGroup;
children = (
- B2AFFC850D00A5DF0030074D /* character-sets.txt */,
- B2C3D9FA0D006C1D00EF6F26 /* CharsetData.h */,
- 0F54DCCC1880C6AB003EEDBB /* ios-encodings.txt */,
F5973DDE15CFB2030027F804 /* LocaleMac.h */,
F5973DDF15CFB2030027F804 /* LocaleMac.mm */,
- B2AFFC860D00A5DF0030074D /* mac-encodings.txt */,
- B2AFFC870D00A5DF0030074D /* make-charset-table.pl */,
B2AFFC8C0D00A5DF0030074D /* TextBoundaries.mm */,
- B2AFFC8E0D00A5DF0030074D /* TextCodecMac.cpp */,
- B2AFFC8F0D00A5DF0030074D /* TextCodecMac.h */,
A1F55DC41F54D3F000EDB75F /* TextEncodingRegistryMac.mm */,
);
path = mac;
@@ -26241,7 +26222,6 @@
6550B6A0099DF0270090D781 /* CharacterData.h in Headers */,
C5592F781A92AA28001F8862 /* CharacterProperties.h in Headers */,
97B8FFD116AE7F960038388D /* CharacterReferenceParserInlines.h in Headers */,
- B2C3DA2A0D006C1D00EF6F26 /* CharsetData.h in Headers */,
F55B3DB21251F12D003EF269 /* CheckboxInputType.h in Headers */,
D619A308144E00BE004BC302 /* ChildListMutationScope.h in Headers */,
A81872200977D3C0005826D9 /* ChildNodeList.h in Headers */,
@@ -29426,7 +29406,6 @@
26E98A10130A9FCA008EB7B2 /* TextCodecASCIIFastPath.h in Headers */,
B2C3DA3C0D006C1D00EF6F26 /* TextCodecICU.h in Headers */,
B2C3DA3E0D006C1D00EF6F26 /* TextCodecLatin1.h in Headers */,
- B2AFFC9A0D00A5DF0030074D /* TextCodecMac.h in Headers */,
57EF5E601D20C83900171E60 /* TextCodecReplacement.h in Headers */,
B2C3DA400D006C1D00EF6F26 /* TextCodecUserDefined.h in Headers */,
B2C3DA420D006C1D00EF6F26 /* TextCodecUTF16.h in Headers */,
@@ -30233,7 +30212,6 @@
CDDE02ED18B3ED6D00CF7FF1 /* CDMSessionAVFoundationObjC.mm in Sources */,
CDDE02F018B5651300CF7FF1 /* CDMSessionAVStreamSession.mm in Sources */,
CDE5959D1BF2757100A1CBE8 /* CDMSessionMediaSourceAVFObjC.mm in Sources */,
- 538EC93B1F99BE50004D22A8 /* CharsetData.cpp in Sources */,
A14090FB1AA51E1D0091191A /* ContentFilterUnblockHandlerCocoa.mm in Sources */,
07AFF4231EFB144900B545B3 /* CoreAudioCaptureSourceIOS.mm in Sources */,
46C696CC1E7205FC00597937 /* CPUMonitor.cpp in Sources */,
Modified: trunk/Source/WebCore/platform/ThreadGlobalData.cpp (225026 => 225027)
--- trunk/Source/WebCore/platform/ThreadGlobalData.cpp 2017-11-19 01:55:37 UTC (rev 225026)
+++ trunk/Source/WebCore/platform/ThreadGlobalData.cpp 2017-11-19 03:42:49 UTC (rev 225027)
@@ -37,10 +37,6 @@
#include <wtf/Threading.h>
#include <wtf/text/StringImpl.h>
-#if PLATFORM(MAC)
-#include "TextCodecMac.h"
-#endif
-
namespace WebCore {
ThreadGlobalData::ThreadGlobalData()
@@ -52,9 +48,6 @@
, m_isMainThread(isMainThread())
#endif
, m_cachedConverterICU(std::make_unique<ICUConverterWrapper>())
-#if PLATFORM(MAC)
- , m_cachedConverterTEC(std::make_unique<TECConverterWrapper>())
-#endif
{
// This constructor will have been called on the main thread before being called on
// any other thread, and is only called once per thread - this makes this a convenient
@@ -67,10 +60,6 @@
void ThreadGlobalData::destroy()
{
-#if PLATFORM(MAC)
- m_cachedConverterTEC = nullptr;
-#endif
-
m_cachedConverterICU = nullptr;
m_eventNames = nullptr;
Modified: trunk/Source/WebCore/platform/ThreadGlobalData.h (225026 => 225027)
--- trunk/Source/WebCore/platform/ThreadGlobalData.h 2017-11-19 01:55:37 UTC (rev 225026)
+++ trunk/Source/WebCore/platform/ThreadGlobalData.h 2017-11-19 03:42:49 UTC (rev 225027)
@@ -38,7 +38,6 @@
struct CachedResourceRequestInitiators;
struct EventNames;
struct ICUConverterWrapper;
- struct TECConverterWrapper;
#if USE(WEB_THREAD)
class ThreadGlobalData : public ThreadSafeRefCounted<ThreadGlobalData> {
@@ -59,10 +58,6 @@
ICUConverterWrapper& cachedConverterICU() { return *m_cachedConverterICU; }
-#if PLATFORM(MAC)
- TECConverterWrapper& cachedConverterTEC() { return *m_cachedConverterTEC; }
-#endif
-
#if USE(WEB_THREAD)
void setWebCoreThreadData();
#endif
@@ -79,10 +74,6 @@
std::unique_ptr<ICUConverterWrapper> m_cachedConverterICU;
-#if PLATFORM(MAC)
- std::unique_ptr<TECConverterWrapper> m_cachedConverterTEC;
-#endif
-
WEBCORE_EXPORT friend ThreadGlobalData& threadGlobalData();
};
Modified: trunk/Source/WebCore/platform/text/TextCodecICU.cpp (225026 => 225027)
--- trunk/Source/WebCore/platform/text/TextCodecICU.cpp 2017-11-19 01:55:37 UTC (rev 225026)
+++ trunk/Source/WebCore/platform/text/TextCodecICU.cpp 2017-11-19 03:42:49 UTC (rev 225027)
@@ -154,6 +154,7 @@
DECLARE_ENCODING_NAME("x-mac-centraleurroman", x_mac_centraleurroman),
DECLARE_ENCODING_NAME("x-mac-turkish", x_mac_turkish),
DECLARE_ENCODING_NAME("Big5-HKSCS", Big5_HKSCS),
+ DECLARE_ENCODING_NAME_NO_ALIASES("EUC-TW"),
};
void TextCodecICU::registerEncodingNames(EncodingNameRegistrar registrar)
Modified: trunk/Source/WebCore/platform/text/TextEncodingRegistry.cpp (225026 => 225027)
--- trunk/Source/WebCore/platform/text/TextEncodingRegistry.cpp 2017-11-19 01:55:37 UTC (rev 225026)
+++ trunk/Source/WebCore/platform/text/TextEncodingRegistry.cpp 2017-11-19 03:42:49 UTC (rev 225027)
@@ -43,10 +43,6 @@
#include <wtf/StdLibExtras.h>
#include <wtf/StringExtras.h>
-#if PLATFORM(MAC)
-#include "TextCodecMac.h"
-#endif
-
#include <wtf/CurrentTime.h>
#include <wtf/text/CString.h>
@@ -267,11 +263,6 @@
TextCodecICU::registerEncodingNames(addToTextEncodingNameMap);
TextCodecICU::registerCodecs(addToTextCodecMap);
-#if PLATFORM(MAC)
- TextCodecMac::registerEncodingNames(addToTextEncodingNameMap);
- TextCodecMac::registerCodecs(addToTextCodecMap);
-#endif
-
pruneBlacklistedCodecs();
buildQuirksSets();
}
Deleted: trunk/Source/WebCore/platform/text/mac/CharsetData.h (225026 => 225027)
--- trunk/Source/WebCore/platform/text/mac/CharsetData.h 2017-11-19 01:55:37 UTC (rev 225026)
+++ trunk/Source/WebCore/platform/text/mac/CharsetData.h 2017-11-19 03:42:49 UTC (rev 225027)
@@ -1,41 +0,0 @@
-/*
- * Copyright (C) 2003, 2006 Apple Inc. All rights reserved.
- *
- * 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 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 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.
- */
-
-#if PLATFORM(IOS)
-typedef UInt32 TextEncoding;
-#endif
-
-namespace WebCore {
-
- #define kTextEncodingISOLatinThai kCFStringEncodingISOLatinThai
-
- struct CharsetEntry {
- const char* name;
- ::TextEncoding encoding;
- };
-
- extern const CharsetEntry CharsetTable[];
-
-}
Deleted: trunk/Source/WebCore/platform/text/mac/TextCodecMac.cpp (225026 => 225027)
--- trunk/Source/WebCore/platform/text/mac/TextCodecMac.cpp 2017-11-19 01:55:37 UTC (rev 225026)
+++ trunk/Source/WebCore/platform/text/mac/TextCodecMac.cpp 2017-11-19 03:42:49 UTC (rev 225027)
@@ -1,331 +0,0 @@
-/*
- * Copyright (C) 2004, 2006, 2008 Apple Inc. All rights reserved.
- * Copyright (C) 2006 Alexey Proskuryakov <a...@nypop.com>
- *
- * 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 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 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"
-
-#if !PLATFORM(IOS)
-
-#include "TextCodecMac.h"
-
-#include "CharsetData.h"
-#include "ThreadGlobalData.h"
-#include <wtf/Assertions.h>
-#include <wtf/RetainPtr.h>
-#include <wtf/Threading.h>
-#include <wtf/text/CString.h>
-#include <wtf/text/WTFString.h>
-#include <wtf/unicode/CharacterNames.h>
-
-namespace WebCore {
-
-// We need to keep this because ICU doesn't support some of the encodings that we need:
-// <http://bugs.webkit.org/show_bug.cgi?id=4195>.
-
-const size_t ConversionBufferSize = 16384;
-
-static TECConverterWrapper& cachedConverterTEC()
-{
- return threadGlobalData().cachedConverterTEC();
-}
-
-void TextCodecMac::registerEncodingNames(EncodingNameRegistrar registrar)
-{
- TECTextEncodingID lastEncoding = invalidEncoding;
- const char* lastName = 0;
-
- for (size_t i = 0; CharsetTable[i].name; ++i) {
- if (CharsetTable[i].encoding != lastEncoding) {
- lastEncoding = CharsetTable[i].encoding;
- lastName = CharsetTable[i].name;
- }
- registrar(CharsetTable[i].name, lastName);
- }
-}
-
-static std::unique_ptr<TextCodec> newTextCodecMac(const TextEncoding&, const void* additionalData)
-{
- return std::make_unique<TextCodecMac>(*static_cast<const TECTextEncodingID*>(additionalData));
-}
-
-void TextCodecMac::registerCodecs(TextCodecRegistrar registrar)
-{
- TECTextEncodingID lastEncoding = invalidEncoding;
-
- for (size_t i = 0; CharsetTable[i].name; ++i)
- if (CharsetTable[i].encoding != lastEncoding) {
- registrar(CharsetTable[i].name, newTextCodecMac, &CharsetTable[i].encoding);
- lastEncoding = CharsetTable[i].encoding;
- }
-}
-
-TextCodecMac::TextCodecMac(TECTextEncodingID encoding)
- : m_encoding(encoding)
- , m_numBufferedBytes(0)
- , m_converterTEC(0)
-{
-}
-
-TextCodecMac::~TextCodecMac()
-{
- releaseTECConverter();
-}
-
-void TextCodecMac::releaseTECConverter() const
-{
- if (m_converterTEC) {
- TECConverterWrapper& cachedConverter = cachedConverterTEC();
- if (cachedConverter.converter)
- TECDisposeConverter(cachedConverter.converter);
- cachedConverter.converter = m_converterTEC;
- cachedConverter.encoding = m_encoding;
- m_converterTEC = 0;
- }
-}
-
-OSStatus TextCodecMac::createTECConverter() const
-{
- TECConverterWrapper& cachedConverter = cachedConverterTEC();
-
- bool cachedEncodingEqual = cachedConverter.encoding == m_encoding;
- cachedConverter.encoding = invalidEncoding;
-
- if (cachedEncodingEqual && cachedConverter.converter) {
- m_converterTEC = cachedConverter.converter;
- cachedConverter.converter = 0;
-
- TECClearConverterContextInfo(m_converterTEC);
- } else {
- OSStatus status = TECCreateConverter(&m_converterTEC, m_encoding,
- CreateTextEncoding(kTextEncodingUnicodeDefault, kTextEncodingDefaultVariant, kUnicode16BitFormat));
- if (status)
- return status;
-
- TECSetBasicOptions(m_converterTEC, kUnicodeForceASCIIRangeMask);
- }
-
- return noErr;
-}
-
-OSStatus TextCodecMac::decode(const unsigned char* inputBuffer, int inputBufferLength, int& inputLength,
- void *outputBuffer, int outputBufferLength, int& outputLength)
-{
- OSStatus status;
- unsigned long bytesRead = 0;
- unsigned long bytesWritten = 0;
-
- if (m_numBufferedBytes != 0) {
- // Finish converting a partial character that's in our buffer.
-
- // First, fill the partial character buffer with as many bytes as are available.
- ASSERT_WITH_SECURITY_IMPLICATION(m_numBufferedBytes < sizeof(m_bufferedBytes));
- const int spaceInBuffer = sizeof(m_bufferedBytes) - m_numBufferedBytes;
- const int bytesToPutInBuffer = std::min(spaceInBuffer, inputBufferLength);
- ASSERT(bytesToPutInBuffer != 0);
- memcpy(m_bufferedBytes + m_numBufferedBytes, inputBuffer, bytesToPutInBuffer);
-
- // Now, do a conversion on the buffer.
- status = TECConvertText(m_converterTEC, m_bufferedBytes, m_numBufferedBytes + bytesToPutInBuffer, &bytesRead,
- reinterpret_cast<unsigned char*>(outputBuffer), outputBufferLength, &bytesWritten);
- ASSERT(bytesRead <= m_numBufferedBytes + bytesToPutInBuffer);
-
- if (status == kTECPartialCharErr && bytesRead == 0) {
- // Handle the case where the partial character was not converted.
- if (bytesToPutInBuffer >= spaceInBuffer) {
- LOG_ERROR("TECConvertText gave a kTECPartialCharErr but read none of the %zu bytes in the buffer", sizeof(m_bufferedBytes));
- m_numBufferedBytes = 0;
- status = kTECUnmappableElementErr; // should never happen, but use this error code
- } else {
- // Tell the caller we read all the source bytes and keep them in the buffer.
- m_numBufferedBytes += bytesToPutInBuffer;
- bytesRead = bytesToPutInBuffer;
- status = noErr;
- }
- } else {
- // We are done with the partial character buffer.
- // Also, we have read some of the bytes from the main buffer.
- if (bytesRead > m_numBufferedBytes) {
- bytesRead -= m_numBufferedBytes;
- } else {
- LOG_ERROR("TECConvertText accepted some bytes it previously rejected with kTECPartialCharErr");
- bytesRead = 0;
- }
- m_numBufferedBytes = 0;
- if (status == kTECPartialCharErr) {
- // While there may be a partial character problem in the small buffer,
- // we have to try again and not get confused and think there is a partial
- // character problem in the large buffer.
- status = noErr;
- }
- }
- } else {
- status = TECConvertText(m_converterTEC, inputBuffer, inputBufferLength, &bytesRead,
- static_cast<unsigned char*>(outputBuffer), outputBufferLength, &bytesWritten);
- ASSERT(static_cast<int>(bytesRead) <= inputBufferLength);
- }
-
- // Work around bug 3351093, where sometimes we get kTECBufferBelowMinimumSizeErr instead of kTECOutputBufferFullStatus.
- if (status == kTECBufferBelowMinimumSizeErr && bytesWritten != 0)
- status = kTECOutputBufferFullStatus;
-
- inputLength = bytesRead;
- outputLength = bytesWritten;
- return status;
-}
-
-String TextCodecMac::decode(const char* bytes, size_t length, bool flush, bool stopOnError, bool& sawError)
-{
- // Get a converter for the passed-in encoding.
- if (!m_converterTEC && createTECConverter() != noErr)
- return String();
-
- StringVector<UChar> result;
-
- const unsigned char* sourcePointer = reinterpret_cast<const unsigned char*>(bytes);
- int sourceLength = length;
- bool bufferWasFull = false;
- UniChar buffer[ConversionBufferSize];
-
- while ((sourceLength || bufferWasFull) && !sawError) {
- int bytesRead = 0;
- int bytesWritten = 0;
- OSStatus status = decode(sourcePointer, sourceLength, bytesRead, buffer, sizeof(buffer), bytesWritten);
- ASSERT(bytesRead <= sourceLength);
- sourcePointer += bytesRead;
- sourceLength -= bytesRead;
-
- switch (status) {
- case noErr:
- case kTECOutputBufferFullStatus:
- break;
- case kTextMalformedInputErr:
- case kTextUndefinedElementErr:
- // FIXME: Put FFFD character into the output string in this case?
- TECClearConverterContextInfo(m_converterTEC);
- if (stopOnError) {
- sawError = true;
- break;
- }
- if (sourceLength) {
- sourcePointer += 1;
- sourceLength -= 1;
- }
- break;
- case kTECPartialCharErr: {
- // Put the partial character into the buffer.
- ASSERT(m_numBufferedBytes == 0);
- const int bufferSize = sizeof(m_numBufferedBytes);
- if (sourceLength < bufferSize) {
- memcpy(m_bufferedBytes, sourcePointer, sourceLength);
- m_numBufferedBytes = sourceLength;
- } else {
- LOG_ERROR("TECConvertText gave a kTECPartialCharErr, but left %u bytes in the buffer", sourceLength);
- }
- sourceLength = 0;
- break;
- }
- default:
- sawError = true;
- return String();
- }
-
- ASSERT(!(bytesWritten % sizeof(UChar)));
- result.append(buffer, bytesWritten / sizeof(UChar));
-
- bufferWasFull = status == kTECOutputBufferFullStatus;
- }
-
- if (flush) {
- unsigned long bytesWritten = 0;
- TECFlushText(m_converterTEC, reinterpret_cast<unsigned char*>(buffer), sizeof(buffer), &bytesWritten);
- ASSERT(!(bytesWritten % sizeof(UChar)));
- result.append(buffer, bytesWritten / sizeof(UChar));
- }
-
- String resultString = String::adopt(WTFMove(result));
-
- // <rdar://problem/3225472>
- // Simplified Chinese pages use the code A3A0 to mean "full-width space".
- // But GB18030 decodes it to U+E5E5, which is correct in theory but not in practice.
- // To work around, just change all occurences of U+E5E5 to U+3000 (ideographic space).
- if (m_encoding == kCFStringEncodingGB_18030_2000)
- resultString.replace(0xE5E5, ideographicSpace);
-
- return resultString;
-}
-
-CString TextCodecMac::encode(const UChar* characters, size_t length, UnencodableHandling handling)
-{
- // FIXME: We should really use TEC here instead of CFString for consistency with the other direction.
-
- // FIXME: Since there's no "force ASCII range" mode in CFString, we change the backslash into a yen sign.
- // Encoding will change the yen sign back into a backslash.
- String copy(characters, length);
- copy.replace('\\', m_backslashAsCurrencySymbol);
- RetainPtr<CFStringRef> cfs = copy.createCFString();
-
- CFIndex startPos = 0;
- CFIndex charactersLeft = CFStringGetLength(cfs.get());
- Vector<char> result;
- size_t size = 0;
- UInt8 lossByte = handling == QuestionMarksForUnencodables ? '?' : 0;
- while (charactersLeft > 0) {
- CFRange range = CFRangeMake(startPos, charactersLeft);
- CFIndex bufferLength;
- CFStringGetBytes(cfs.get(), range, m_encoding, lossByte, false, NULL, 0x7FFFFFFF, &bufferLength);
-
- result.grow(size + bufferLength);
- unsigned char* buffer = reinterpret_cast<unsigned char*>(result.data() + size);
- CFIndex charactersConverted = CFStringGetBytes(cfs.get(), range, m_encoding, lossByte, false, buffer, bufferLength, &bufferLength);
- size += bufferLength;
-
- if (charactersConverted != charactersLeft) {
- unsigned badChar = CFStringGetCharacterAtIndex(cfs.get(), startPos + charactersConverted);
- ++charactersConverted;
- if ((badChar & 0xFC00) == 0xD800 && charactersConverted != charactersLeft) { // is high surrogate
- UniChar low = CFStringGetCharacterAtIndex(cfs.get(), startPos + charactersConverted);
- if ((low & 0xFC00) == 0xDC00) { // is low surrogate
- badChar <<= 10;
- badChar += low;
- badChar += 0x10000 - (0xD800 << 10) - 0xDC00;
- ++charactersConverted;
- }
- }
- UnencodableReplacementArray entity;
- int entityLength = getUnencodableReplacement(badChar, handling, entity);
- result.grow(size + entityLength);
- memcpy(result.data() + size, entity, entityLength);
- size += entityLength;
- }
-
- startPos += charactersConverted;
- charactersLeft -= charactersConverted;
- }
- return CString(result.data(), size);
-}
-
-} // namespace WebCore
-
-#endif // !PLATFORM(IOS)
Deleted: trunk/Source/WebCore/platform/text/mac/TextCodecMac.h (225026 => 225027)
--- trunk/Source/WebCore/platform/text/mac/TextCodecMac.h 2017-11-19 01:55:37 UTC (rev 225026)
+++ trunk/Source/WebCore/platform/text/mac/TextCodecMac.h 2017-11-19 03:42:49 UTC (rev 225027)
@@ -1,77 +0,0 @@
-/*
- * Copyright (C) 2004, 2006 Apple Inc. All rights reserved.
- * Copyright (C) 2006 Alexey Proskuryakov <a...@nypop.com>
- *
- * 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 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 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.
- */
-
-#ifndef TextCodecMac_h
-#define TextCodecMac_h
-
-#if !PLATFORM(IOS)
-
-#include "TextCodec.h"
-#include <CoreServices/CoreServices.h>
-
-namespace WebCore {
-
- typedef ::TextEncoding TECTextEncodingID;
- const TECTextEncodingID invalidEncoding = kCFStringEncodingInvalidId;
-
- class TextCodecMac : public TextCodec {
- public:
- static void registerEncodingNames(EncodingNameRegistrar);
- static void registerCodecs(TextCodecRegistrar);
-
- explicit TextCodecMac(TECTextEncodingID);
- virtual ~TextCodecMac();
-
- virtual String decode(const char*, size_t length, bool flush, bool stopOnError, bool& sawError);
- virtual CString encode(const UChar*, size_t length, UnencodableHandling);
-
- private:
- OSStatus decode(const unsigned char* inputBuffer, int inputBufferLength, int& inputLength,
- void* outputBuffer, int outputBufferLength, int& outputLength);
-
- OSStatus createTECConverter() const;
- void releaseTECConverter() const;
-
- TECTextEncodingID m_encoding;
- UChar m_backslashAsCurrencySymbol;
- unsigned m_numBufferedBytes;
- unsigned char m_bufferedBytes[16]; // bigger than any single multi-byte character
- mutable TECObjectRef m_converterTEC;
- };
-
- struct TECConverterWrapper {
- TECConverterWrapper() : converter(0), encoding(invalidEncoding) { }
- ~TECConverterWrapper() { if (converter) TECDisposeConverter(converter); }
-
- TECObjectRef converter;
- TECTextEncodingID encoding;
- };
-
-} // namespace WebCore
-
-#endif // !PLATFORM(IOS)
-
-#endif // TextCodecMac_h
Deleted: trunk/Source/WebCore/platform/text/mac/character-sets.txt (225026 => 225027)
--- trunk/Source/WebCore/platform/text/mac/character-sets.txt 2017-11-19 01:55:37 UTC (rev 225026)
+++ trunk/Source/WebCore/platform/text/mac/character-sets.txt 2017-11-19 03:42:49 UTC (rev 225027)
@@ -1,1868 +0,0 @@
-
-===================================================================
-CHARACTER SETS
-
-(last updated 28 January 2005)
-
-These are the official names for character sets that may be used in
-the Internet and may be referred to in Internet documentation. These
-names are expressed in ANSI_X3.4-1968 which is commonly called
-US-ASCII or simply ASCII. The character set most commonly use in the
-Internet and used especially in protocol standards is US-ASCII, this
-is strongly encouraged. The use of the name US-ASCII is also
-encouraged.
-
-The character set names may be up to 40 characters taken from the
-printable characters of US-ASCII. However, no distinction is made
-between use of upper and lower case letters.
-
-The MIBenum value is a unique value for use in MIBs to identify coded
-character sets.
-
-The value space for MIBenum values has been divided into three
-regions. The first region (3-999) consists of coded character sets
-that have been standardized by some standard setting organization.
-This region is intended for standards that do not have subset
-implementations. The second region (1000-1999) is for the Unicode and
-ISO/IEC 10646 coded character sets together with a specification of a
-(set of) sub-repertoires that may occur. The third region (>1999) is
-intended for vendor specific coded character sets.
-
- Assigned MIB enum Numbers
- -------------------------
- 0-2 Reserved
- 3-999 Set By Standards Organizations
- 1000-1999 Unicode / 10646
- 2000-2999 Vendor
-
-The aliases that start with "cs" have been added for use with the
-IANA-CHARSET-MIB as originally defined in RFC3808, and as currently
-maintained by IANA at http://www/iana.org/assignments/ianacharset-mib.
-Note that the ianacharset-mib needs to be kept in sync with this
-registry. These aliases that start with "cs" contain the standard
-numbers along with suggestive names in order to facilitate applications
-that want to display the names in user interfaces. The "cs" stands
-for character set and is provided for applications that need a lower
-case first letter but want to use mixed case thereafter that cannot
-contain any special characters, such as underbar ("_") and dash ("-").
-
-If the character set is from an ISO standard, its cs alias is the ISO
-standard number or name. If the character set is not from an ISO
-standard, but is registered with ISO (IPSJ/ITSCJ is the current ISO
-Registration Authority), the ISO Registry number is specified as
-ISOnnn followed by letters suggestive of the name or standards number
-of the code set. When a national or international standard is
-revised, the year of revision is added to the cs alias of the new
-character set entry in the IANA Registry in order to distinguish the
-revised character set from the original character set.
-
-
-Character Set Reference
-------------- ---------
-
-Name: ANSI_X3.4-1968 [RFC1345,KXS2]
-MIBenum: 3
-Source: ECMA registry
-Alias: iso-ir-6
-Alias: ANSI_X3.4-1986
-Alias: ISO_646.irv:1991
-Alias: ASCII
-Alias: ISO646-US
-Alias: US-ASCII (preferred MIME name)
-Alias: us
-Alias: IBM367
-Alias: cp367
-Alias: csASCII
-
-Name: ISO-10646-UTF-1
-MIBenum: 27
-Source: Universal Transfer Format (1), this is the multibyte
- encoding, that subsets ASCII-7. It does not have byte
- ordering issues.
-Alias: csISO10646UTF1
-
-Name: ISO_646.basic:1983 [RFC1345,KXS2]
-MIBenum: 28
-Source: ECMA registry
-Alias: ref
-Alias: csISO646basic1983
-
-Name: INVARIANT [RFC1345,KXS2]
-MIBenum: 29
-Alias: csINVARIANT
-
-Name: ISO_646.irv:1983 [RFC1345,KXS2]
-MIBenum: 30
-Source: ECMA registry
-Alias: iso-ir-2
-Alias: irv
-Alias: csISO2IntlRefVersion
-
-Name: BS_4730 [RFC1345,KXS2]
-MIBenum: 20
-Source: ECMA registry
-Alias: iso-ir-4
-Alias: ISO646-GB
-Alias: gb
-Alias: uk
-Alias: csISO4UnitedKingdom
-
-Name: NATS-SEFI [RFC1345,KXS2]
-MIBenum: 31
-Source: ECMA registry
-Alias: iso-ir-8-1
-Alias: csNATSSEFI
-
-Name: NATS-SEFI-ADD [RFC1345,KXS2]
-MIBenum: 32
-Source: ECMA registry
-Alias: iso-ir-8-2
-Alias: csNATSSEFIADD
-
-Name: NATS-DANO [RFC1345,KXS2]
-MIBenum: 33
-Source: ECMA registry
-Alias: iso-ir-9-1
-Alias: csNATSDANO
-
-Name: NATS-DANO-ADD [RFC1345,KXS2]
-MIBenum: 34
-Source: ECMA registry
-Alias: iso-ir-9-2
-Alias: csNATSDANOADD
-
-Name: SEN_850200_B [RFC1345,KXS2]
-MIBenum: 35
-Source: ECMA registry
-Alias: iso-ir-10
-Alias: FI
-Alias: ISO646-FI
-Alias: ISO646-SE
-Alias: se
-Alias: csISO10Swedish
-
-Name: SEN_850200_C [RFC1345,KXS2]
-MIBenum: 21
-Source: ECMA registry
-Alias: iso-ir-11
-Alias: ISO646-SE2
-Alias: se2
-Alias: csISO11SwedishForNames
-
-Name: KS_C_5601-1987 [RFC1345,KXS2]
-MIBenum: 36
-Source: ECMA registry
-Alias: iso-ir-149
-Alias: KS_C_5601-1989
-Alias: KSC_5601
-Alias: korean
-Alias: csKSC56011987
-
-Name: ISO-2022-KR (preferred MIME name) [RFC1557,Choi]
-MIBenum: 37
-Source: RFC-1557 (see also KS_C_5601-1987)
-Alias: csISO2022KR
-
-Name: EUC-KR (preferred MIME name) [RFC1557,Choi]
-MIBenum: 38
-Source: RFC-1557 (see also KS_C_5861-1992)
-Alias: csEUCKR
-
-Name: ISO-2022-JP (preferred MIME name) [RFC1468,Murai]
-MIBenum: 39
-Source: RFC-1468 (see also RFC-2237)
-Alias: csISO2022JP
-
-Name: ISO-2022-JP-2 (preferred MIME name) [RFC1554,Ohta]
-MIBenum: 40
-Source: RFC-1554
-Alias: csISO2022JP2
-
-Name: ISO-2022-CN [RFC1922]
-MIBenum: 104
-Source: RFC-1922
-
-Name: ISO-2022-CN-EXT [RFC1922]
-MIBenum: 105
-Source: RFC-1922
-
-Name: JIS_C6220-1969-jp [RFC1345,KXS2]
-MIBenum: 41
-Source: ECMA registry
-Alias: JIS_C6220-1969
-Alias: iso-ir-13
-Alias: katakana
-Alias: x0201-7
-Alias: csISO13JISC6220jp
-
-Name: JIS_C6220-1969-ro [RFC1345,KXS2]
-MIBenum: 42
-Source: ECMA registry
-Alias: iso-ir-14
-Alias: jp
-Alias: ISO646-JP
-Alias: csISO14JISC6220ro
-
-Name: IT [RFC1345,KXS2]
-MIBenum: 22
-Source: ECMA registry
-Alias: iso-ir-15
-Alias: ISO646-IT
-Alias: csISO15Italian
-
-Name: PT [RFC1345,KXS2]
-MIBenum: 43
-Source: ECMA registry
-Alias: iso-ir-16
-Alias: ISO646-PT
-Alias: csISO16Portuguese
-
-Name: ES [RFC1345,KXS2]
-MIBenum: 23
-Source: ECMA registry
-Alias: iso-ir-17
-Alias: ISO646-ES
-Alias: csISO17Spanish
-
-Name: greek7-old [RFC1345,KXS2]
-MIBenum: 44
-Source: ECMA registry
-Alias: iso-ir-18
-Alias: csISO18Greek7Old
-
-Name: latin-greek [RFC1345,KXS2]
-MIBenum: 45
-Source: ECMA registry
-Alias: iso-ir-19
-Alias: csISO19LatinGreek
-
-Name: DIN_66003 [RFC1345,KXS2]
-MIBenum: 24
-Source: ECMA registry
-Alias: iso-ir-21
-Alias: de
-Alias: ISO646-DE
-Alias: csISO21German
-
-Name: NF_Z_62-010_(1973) [RFC1345,KXS2]
-MIBenum: 46
-Source: ECMA registry
-Alias: iso-ir-25
-Alias: ISO646-FR1
-Alias: csISO25French
-
-Name: Latin-greek-1 [RFC1345,KXS2]
-MIBenum: 47
-Source: ECMA registry
-Alias: iso-ir-27
-Alias: csISO27LatinGreek1
-
-Name: ISO_5427 [RFC1345,KXS2]
-MIBenum: 48
-Source: ECMA registry
-Alias: iso-ir-37
-Alias: csISO5427Cyrillic
-
-Name: JIS_C6226-1978 [RFC1345,KXS2]
-MIBenum: 49
-Source: ECMA registry
-Alias: iso-ir-42
-Alias: csISO42JISC62261978
-
-Name: BS_viewdata [RFC1345,KXS2]
-MIBenum: 50
-Source: ECMA registry
-Alias: iso-ir-47
-Alias: csISO47BSViewdata
-
-Name: INIS [RFC1345,KXS2]
-MIBenum: 51
-Source: ECMA registry
-Alias: iso-ir-49
-Alias: csISO49INIS
-
-Name: INIS-8 [RFC1345,KXS2]
-MIBenum: 52
-Source: ECMA registry
-Alias: iso-ir-50
-Alias: csISO50INIS8
-
-Name: INIS-cyrillic [RFC1345,KXS2]
-MIBenum: 53
-Source: ECMA registry
-Alias: iso-ir-51
-Alias: csISO51INISCyrillic
-
-Name: ISO_5427:1981 [RFC1345,KXS2]
-MIBenum: 54
-Source: ECMA registry
-Alias: iso-ir-54
-Alias: ISO5427Cyrillic1981
-
-Name: ISO_5428:1980 [RFC1345,KXS2]
-MIBenum: 55
-Source: ECMA registry
-Alias: iso-ir-55
-Alias: csISO5428Greek
-
-Name: GB_1988-80 [RFC1345,KXS2]
-MIBenum: 56
-Source: ECMA registry
-Alias: iso-ir-57
-Alias: cn
-Alias: ISO646-CN
-Alias: csISO57GB1988
-
-Name: GB_2312-80 [RFC1345,KXS2]
-MIBenum: 57
-Source: ECMA registry
-Alias: iso-ir-58
-Alias: chinese
-Alias: csISO58GB231280
-
-Name: NS_4551-1 [RFC1345,KXS2]
-MIBenum: 25
-Source: ECMA registry
-Alias: iso-ir-60
-Alias: ISO646-NO
-Alias: no
-Alias: csISO60DanishNorwegian
-Alias: csISO60Norwegian1
-
-Name: NS_4551-2 [RFC1345,KXS2]
-MIBenum: 58
-Source: ECMA registry
-Alias: ISO646-NO2
-Alias: iso-ir-61
-Alias: no2
-Alias: csISO61Norwegian2
-
-Name: NF_Z_62-010 [RFC1345,KXS2]
-MIBenum: 26
-Source: ECMA registry
-Alias: iso-ir-69
-Alias: ISO646-FR
-Alias: fr
-Alias: csISO69French
-
-Name: videotex-suppl [RFC1345,KXS2]
-MIBenum: 59
-Source: ECMA registry
-Alias: iso-ir-70
-Alias: csISO70VideotexSupp1
-
-Name: PT2 [RFC1345,KXS2]
-MIBenum: 60
-Source: ECMA registry
-Alias: iso-ir-84
-Alias: ISO646-PT2
-Alias: csISO84Portuguese2
-
-Name: ES2 [RFC1345,KXS2]
-MIBenum: 61
-Source: ECMA registry
-Alias: iso-ir-85
-Alias: ISO646-ES2
-Alias: csISO85Spanish2
-
-Name: MSZ_7795.3 [RFC1345,KXS2]
-MIBenum: 62
-Source: ECMA registry
-Alias: iso-ir-86
-Alias: ISO646-HU
-Alias: hu
-Alias: csISO86Hungarian
-
-Name: JIS_C6226-1983 [RFC1345,KXS2]
-MIBenum: 63
-Source: ECMA registry
-Alias: iso-ir-87
-Alias: x0208
-Alias: JIS_X0208-1983
-Alias: csISO87JISX0208
-
-Name: greek7 [RFC1345,KXS2]
-MIBenum: 64
-Source: ECMA registry
-Alias: iso-ir-88
-Alias: csISO88Greek7
-
-Name: ASMO_449 [RFC1345,KXS2]
-MIBenum: 65
-Source: ECMA registry
-Alias: ISO_9036
-Alias: arabic7
-Alias: iso-ir-89
-Alias: csISO89ASMO449
-
-Name: iso-ir-90 [RFC1345,KXS2]
-MIBenum: 66
-Source: ECMA registry
-Alias: csISO90
-
-Name: JIS_C6229-1984-a [RFC1345,KXS2]
-MIBenum: 67
-Source: ECMA registry
-Alias: iso-ir-91
-Alias: jp-ocr-a
-Alias: csISO91JISC62291984a
-
-Name: JIS_C6229-1984-b [RFC1345,KXS2]
-MIBenum: 68
-Source: ECMA registry
-Alias: iso-ir-92
-Alias: ISO646-JP-OCR-B
-Alias: jp-ocr-b
-Alias: csISO92JISC62991984b
-
-Name: JIS_C6229-1984-b-add [RFC1345,KXS2]
-MIBenum: 69
-Source: ECMA registry
-Alias: iso-ir-93
-Alias: jp-ocr-b-add
-Alias: csISO93JIS62291984badd
-
-Name: JIS_C6229-1984-hand [RFC1345,KXS2]
-MIBenum: 70
-Source: ECMA registry
-Alias: iso-ir-94
-Alias: jp-ocr-hand
-Alias: csISO94JIS62291984hand
-
-Name: JIS_C6229-1984-hand-add [RFC1345,KXS2]
-MIBenum: 71
-Source: ECMA registry
-Alias: iso-ir-95
-Alias: jp-ocr-hand-add
-Alias: csISO95JIS62291984handadd
-
-Name: JIS_C6229-1984-kana [RFC1345,KXS2]
-MIBenum: 72
-Source: ECMA registry
-Alias: iso-ir-96
-Alias: csISO96JISC62291984kana
-
-Name: ISO_2033-1983 [RFC1345,KXS2]
-MIBenum: 73
-Source: ECMA registry
-Alias: iso-ir-98
-Alias: e13b
-Alias: csISO2033
-
-Name: ANSI_X3.110-1983 [RFC1345,KXS2]
-MIBenum: 74
-Source: ECMA registry
-Alias: iso-ir-99
-Alias: CSA_T500-1983
-Alias: NAPLPS
-Alias: csISO99NAPLPS
-
-Name: ISO_8859-1:1987 [RFC1345,KXS2]
-MIBenum: 4
-Source: ECMA registry
-Alias: iso-ir-100
-Alias: ISO_8859-1
-Alias: ISO-8859-1 (preferred MIME name)
-Alias: latin1
-Alias: l1
-Alias: IBM819
-Alias: CP819
-Alias: csISOLatin1
-
-Name: ISO_8859-2:1987 [RFC1345,KXS2]
-MIBenum: 5
-Source: ECMA registry
-Alias: iso-ir-101
-Alias: ISO_8859-2
-Alias: ISO-8859-2 (preferred MIME name)
-Alias: latin2
-Alias: l2
-Alias: csISOLatin2
-
-Name: T.61-7bit [RFC1345,KXS2]
-MIBenum: 75
-Source: ECMA registry
-Alias: iso-ir-102
-Alias: csISO102T617bit
-
-Name: T.61-8bit [RFC1345,KXS2]
-MIBenum: 76
-Alias: T.61
-Source: ECMA registry
-Alias: iso-ir-103
-Alias: csISO103T618bit
-
-Name: ISO_8859-3:1988 [RFC1345,KXS2]
-MIBenum: 6
-Source: ECMA registry
-Alias: iso-ir-109
-Alias: ISO_8859-3
-Alias: ISO-8859-3 (preferred MIME name)
-Alias: latin3
-Alias: l3
-Alias: csISOLatin3
-
-Name: ISO_8859-4:1988 [RFC1345,KXS2]
-MIBenum: 7
-Source: ECMA registry
-Alias: iso-ir-110
-Alias: ISO_8859-4
-Alias: ISO-8859-4 (preferred MIME name)
-Alias: latin4
-Alias: l4
-Alias: csISOLatin4
-
-Name: ECMA-cyrillic
-MIBenum: 77
-Source: ISO registry (formerly ECMA registry)
- http://www.itscj.ipsj.jp/ISO-IR/111.pdf
-Alias: iso-ir-111
-Alias: KOI8-E
-Alias: csISO111ECMACyrillic
-
-Name: CSA_Z243.4-1985-1 [RFC1345,KXS2]
-MIBenum: 78
-Source: ECMA registry
-Alias: iso-ir-121
-Alias: ISO646-CA
-Alias: csa7-1
-Alias: ca
-Alias: csISO121Canadian1
-
-Name: CSA_Z243.4-1985-2 [RFC1345,KXS2]
-MIBenum: 79
-Source: ECMA registry
-Alias: iso-ir-122
-Alias: ISO646-CA2
-Alias: csa7-2
-Alias: csISO122Canadian2
-
-Name: CSA_Z243.4-1985-gr [RFC1345,KXS2]
-MIBenum: 80
-Source: ECMA registry
-Alias: iso-ir-123
-Alias: csISO123CSAZ24341985gr
-
-Name: ISO_8859-6:1987 [RFC1345,KXS2]
-MIBenum: 9
-Source: ECMA registry
-Alias: iso-ir-127
-Alias: ISO_8859-6
-Alias: ISO-8859-6 (preferred MIME name)
-Alias: ECMA-114
-Alias: ASMO-708
-Alias: arabic
-Alias: csISOLatinArabic
-
-Name: ISO_8859-6-E [RFC1556,IANA]
-MIBenum: 81
-Source: RFC1556
-Alias: csISO88596E
-Alias: ISO-8859-6-E (preferred MIME name)
-
-Name: ISO_8859-6-I [RFC1556,IANA]
-MIBenum: 82
-Source: RFC1556
-Alias: csISO88596I
-Alias: ISO-8859-6-I (preferred MIME name)
-
-Name: ISO_8859-7:1987 [RFC1947,RFC1345,KXS2]
-MIBenum: 10
-Source: ECMA registry
-Alias: iso-ir-126
-Alias: ISO_8859-7
-Alias: ISO-8859-7 (preferred MIME name)
-Alias: ELOT_928
-Alias: ECMA-118
-Alias: greek
-Alias: greek8
-Alias: csISOLatinGreek
-
-Name: T.101-G2 [RFC1345,KXS2]
-MIBenum: 83
-Source: ECMA registry
-Alias: iso-ir-128
-Alias: csISO128T101G2
-
-Name: ISO_8859-8:1988 [RFC1345,KXS2]
-MIBenum: 11
-Source: ECMA registry
-Alias: iso-ir-138
-Alias: ISO_8859-8
-Alias: ISO-8859-8 (preferred MIME name)
-Alias: hebrew
-Alias: csISOLatinHebrew
-
-Name: ISO_8859-8-E [RFC1556,Nussbacher]
-MIBenum: 84
-Source: RFC1556
-Alias: csISO88598E
-Alias: ISO-8859-8-E (preferred MIME name)
-
-Name: ISO_8859-8-I [RFC1556,Nussbacher]
-MIBenum: 85
-Source: RFC1556
-Alias: csISO88598I
-Alias: ISO-8859-8-I (preferred MIME name)
-
-Name: CSN_369103 [RFC1345,KXS2]
-MIBenum: 86
-Source: ECMA registry
-Alias: iso-ir-139
-Alias: csISO139CSN369103
-
-Name: JUS_I.B1.002 [RFC1345,KXS2]
-MIBenum: 87
-Source: ECMA registry
-Alias: iso-ir-141
-Alias: ISO646-YU
-Alias: js
-Alias: yu
-Alias: csISO141JUSIB1002
-
-Name: ISO_6937-2-add [RFC1345,KXS2]
-MIBenum: 14
-Source: ECMA registry and ISO 6937-2:1983
-Alias: iso-ir-142
-Alias: csISOTextComm
-
-Name: IEC_P27-1 [RFC1345,KXS2]
-MIBenum: 88
-Source: ECMA registry
-Alias: iso-ir-143
-Alias: csISO143IECP271
-
-Name: ISO_8859-5:1988 [RFC1345,KXS2]
-MIBenum: 8
-Source: ECMA registry
-Alias: iso-ir-144
-Alias: ISO_8859-5
-Alias: ISO-8859-5 (preferred MIME name)
-Alias: cyrillic
-Alias: csISOLatinCyrillic
-
-Name: JUS_I.B1.003-serb [RFC1345,KXS2]
-MIBenum: 89
-Source: ECMA registry
-Alias: iso-ir-146
-Alias: serbian
-Alias: csISO146Serbian
-
-Name: JUS_I.B1.003-mac [RFC1345,KXS2]
-MIBenum: 90
-Source: ECMA registry
-Alias: macedonian
-Alias: iso-ir-147
-Alias: csISO147Macedonian
-
-Name: ISO_8859-9:1989 [RFC1345,KXS2]
-MIBenum: 12
-Source: ECMA registry
-Alias: iso-ir-148
-Alias: ISO_8859-9
-Alias: ISO-8859-9 (preferred MIME name)
-Alias: latin5
-Alias: l5
-Alias: csISOLatin5
-
-Name: greek-ccitt [RFC1345,KXS2]
-MIBenum: 91
-Source: ECMA registry
-Alias: iso-ir-150
-Alias: csISO150
-Alias: csISO150GreekCCITT
-
-Name: NC_NC00-10:81 [RFC1345,KXS2]
-MIBenum: 92
-Source: ECMA registry
-Alias: cuba
-Alias: iso-ir-151
-Alias: ISO646-CU
-Alias: csISO151Cuba
-
-Name: ISO_6937-2-25 [RFC1345,KXS2]
-MIBenum: 93
-Source: ECMA registry
-Alias: iso-ir-152
-Alias: csISO6937Add
-
-Name: GOST_19768-74 [RFC1345,KXS2]
-MIBenum: 94
-Source: ECMA registry
-Alias: ST_SEV_358-88
-Alias: iso-ir-153
-Alias: csISO153GOST1976874
-
-Name: ISO_8859-supp [RFC1345,KXS2]
-MIBenum: 95
-Source: ECMA registry
-Alias: iso-ir-154
-Alias: latin1-2-5
-Alias: csISO8859Supp
-
-Name: ISO_10367-box [RFC1345,KXS2]
-MIBenum: 96
-Source: ECMA registry
-Alias: iso-ir-155
-Alias: csISO10367Box
-
-Name: ISO-8859-10 (preferred MIME name) [RFC1345,KXS2]
-MIBenum: 13
-Source: ECMA registry
-Alias: iso-ir-157
-Alias: l6
-Alias: ISO_8859-10:1992
-Alias: csISOLatin6
-Alias: latin6
-
-Name: latin-lap [RFC1345,KXS2]
-MIBenum: 97
-Source: ECMA registry
-Alias: lap
-Alias: iso-ir-158
-Alias: csISO158Lap
-
-Name: JIS_X0212-1990 [RFC1345,KXS2]
-MIBenum: 98
-Source: ECMA registry
-Alias: x0212
-Alias: iso-ir-159
-Alias: csISO159JISX02121990
-
-Name: DS_2089 [RFC1345,KXS2]
-MIBenum: 99
-Source: Danish Standard, DS 2089, February 1974
-Alias: DS2089
-Alias: ISO646-DK
-Alias: dk
-Alias: csISO646Danish
-
-Name: us-dk [RFC1345,KXS2]
-MIBenum: 100
-Alias: csUSDK
-
-Name: dk-us [RFC1345,KXS2]
-MIBenum: 101
-Alias: csDKUS
-
-Name: JIS_X0201 [RFC1345,KXS2]
-MIBenum: 15
-Source: JIS X 0201-1976. One byte only, this is equivalent to
- JIS/Roman (similar to ASCII) plus eight-bit half-width
- Katakana
-Alias: X0201
-Alias: csHalfWidthKatakana
-
-Name: KSC5636 [RFC1345,KXS2]
-MIBenum: 102
-Alias: ISO646-KR
-Alias: csKSC5636
-
-Name: ISO-10646-UCS-2
-MIBenum: 1000
-Source: the 2-octet Basic Multilingual Plane, aka Unicode
- this needs to specify network byte order: the standard
- does not specify (it is a 16-bit integer space)
-Alias: csUnicode
-
-Name: ISO-10646-UCS-4
-MIBenum: 1001
-Source: the full code space. (same comment about byte order,
- these are 31-bit numbers.
-Alias: csUCS4
-
-Name: DEC-MCS [RFC1345,KXS2]
-MIBenum: 2008
-Source: VAX/VMS User's Manual,
- Order Number: AI-Y517A-TE, April 1986.
-Alias: dec
-Alias: csDECMCS
-
-Name: hp-roman8 [HP-PCL5,RFC1345,KXS2]
-MIBenum: 2004
-Source: LaserJet IIP Printer User's Manual,
- HP part no 33471-90901, Hewlet-Packard, June 1989.
-Alias: roman8
-Alias: r8
-Alias: csHPRoman8
-
-Name: macintosh [RFC1345,KXS2]
-MIBenum: 2027
-Source: The Unicode Standard ver1.0, ISBN 0-201-56788-1, Oct 1991
-Alias: mac
-Alias: csMacintosh
-
-Name: IBM037 [RFC1345,KXS2]
-MIBenum: 2028
-Source: IBM NLS RM Vol2 SE09-8002-01, March 1990
-Alias: cp037
-Alias: ebcdic-cp-us
-Alias: ebcdic-cp-ca
-Alias: ebcdic-cp-wt
-Alias: ebcdic-cp-nl
-Alias: csIBM037
-
-Name: IBM038 [RFC1345,KXS2]
-MIBenum: 2029
-Source: IBM 3174 Character Set Ref, GA27-3831-02, March 1990
-Alias: EBCDIC-INT
-Alias: cp038
-Alias: csIBM038
-
-Name: IBM273 [RFC1345,KXS2]
-MIBenum: 2030
-Source: IBM NLS RM Vol2 SE09-8002-01, March 1990
-Alias: CP273
-Alias: csIBM273
-
-Name: IBM274 [RFC1345,KXS2]
-MIBenum: 2031
-Source: IBM 3174 Character Set Ref, GA27-3831-02, March 1990
-Alias: EBCDIC-BE
-Alias: CP274
-Alias: csIBM274
-
-Name: IBM275 [RFC1345,KXS2]
-MIBenum: 2032
-Source: IBM NLS RM Vol2 SE09-8002-01, March 1990
-Alias: EBCDIC-BR
-Alias: cp275
-Alias: csIBM275
-
-Name: IBM277 [RFC1345,KXS2]
-MIBenum: 2033
-Source: IBM NLS RM Vol2 SE09-8002-01, March 1990
-Alias: EBCDIC-CP-DK
-Alias: EBCDIC-CP-NO
-Alias: csIBM277
-
-Name: IBM278 [RFC1345,KXS2]
-MIBenum: 2034
-Source: IBM NLS RM Vol2 SE09-8002-01, March 1990
-Alias: CP278
-Alias: ebcdic-cp-fi
-Alias: ebcdic-cp-se
-Alias: csIBM278
-
-Name: IBM280 [RFC1345,KXS2]
-MIBenum: 2035
-Source: IBM NLS RM Vol2 SE09-8002-01, March 1990
-Alias: CP280
-Alias: ebcdic-cp-it
-Alias: csIBM280
-
-Name: IBM281 [RFC1345,KXS2]
-MIBenum: 2036
-Source: IBM 3174 Character Set Ref, GA27-3831-02, March 1990
-Alias: EBCDIC-JP-E
-Alias: cp281
-Alias: csIBM281
-
-Name: IBM284 [RFC1345,KXS2]
-MIBenum: 2037
-Source: IBM NLS RM Vol2 SE09-8002-01, March 1990
-Alias: CP284
-Alias: ebcdic-cp-es
-Alias: csIBM284
-
-Name: IBM285 [RFC1345,KXS2]
-MIBenum: 2038
-Source: IBM NLS RM Vol2 SE09-8002-01, March 1990
-Alias: CP285
-Alias: ebcdic-cp-gb
-Alias: csIBM285
-
-Name: IBM290 [RFC1345,KXS2]
-MIBenum: 2039
-Source: IBM 3174 Character Set Ref, GA27-3831-02, March 1990
-Alias: cp290
-Alias: EBCDIC-JP-kana
-Alias: csIBM290
-
-Name: IBM297 [RFC1345,KXS2]
-MIBenum: 2040
-Source: IBM NLS RM Vol2 SE09-8002-01, March 1990
-Alias: cp297
-Alias: ebcdic-cp-fr
-Alias: csIBM297
-
-Name: IBM420 [RFC1345,KXS2]
-MIBenum: 2041
-Source: IBM NLS RM Vol2 SE09-8002-01, March 1990,
- IBM NLS RM p 11-11
-Alias: cp420
-Alias: ebcdic-cp-ar1
-Alias: csIBM420
-
-Name: IBM423 [RFC1345,KXS2]
-MIBenum: 2042
-Source: IBM NLS RM Vol2 SE09-8002-01, March 1990
-Alias: cp423
-Alias: ebcdic-cp-gr
-Alias: csIBM423
-
-Name: IBM424 [RFC1345,KXS2]
-MIBenum: 2043
-Source: IBM NLS RM Vol2 SE09-8002-01, March 1990
-Alias: cp424
-Alias: ebcdic-cp-he
-Alias: csIBM424
-
-Name: IBM437 [RFC1345,KXS2]
-MIBenum: 2011
-Source: IBM NLS RM Vol2 SE09-8002-01, March 1990
-Alias: cp437
-Alias: 437
-Alias: csPC8CodePage437
-
-Name: IBM500 [RFC1345,KXS2]
-MIBenum: 2044
-Source: IBM NLS RM Vol2 SE09-8002-01, March 1990
-Alias: CP500
-Alias: ebcdic-cp-be
-Alias: ebcdic-cp-ch
-Alias: csIBM500
-
-Name: IBM775 [HP-PCL5]
-MIBenum: 2087
-Source: HP PCL 5 Comparison Guide (P/N 5021-0329) pp B-13, 1996
-Alias: cp775
-Alias: csPC775Baltic
-
-Name: IBM850 [RFC1345,KXS2]
-MIBenum: 2009
-Source: IBM NLS RM Vol2 SE09-8002-01, March 1990
-Alias: cp850
-Alias: 850
-Alias: csPC850Multilingual
-
-Name: IBM851 [RFC1345,KXS2]
-MIBenum: 2045
-Source: IBM NLS RM Vol2 SE09-8002-01, March 1990
-Alias: cp851
-Alias: 851
-Alias: csIBM851
-
-Name: IBM852 [RFC1345,KXS2]
-MIBenum: 2010
-Source: IBM NLS RM Vol2 SE09-8002-01, March 1990
-Alias: cp852
-Alias: 852
-Alias: csPCp852
-
-Name: IBM855 [RFC1345,KXS2]
-MIBenum: 2046
-Source: IBM NLS RM Vol2 SE09-8002-01, March 1990
-Alias: cp855
-Alias: 855
-Alias: csIBM855
-
-Name: IBM857 [RFC1345,KXS2]
-MIBenum: 2047
-Source: IBM NLS RM Vol2 SE09-8002-01, March 1990
-Alias: cp857
-Alias: 857
-Alias: csIBM857
-
-Name: IBM860 [RFC1345,KXS2]
-MIBenum: 2048
-Source: IBM NLS RM Vol2 SE09-8002-01, March 1990
-Alias: cp860
-Alias: 860
-Alias: csIBM860
-
-Name: IBM861 [RFC1345,KXS2]
-MIBenum: 2049
-Source: IBM NLS RM Vol2 SE09-8002-01, March 1990
-Alias: cp861
-Alias: 861
-Alias: cp-is
-Alias: csIBM861
-
-Name: IBM862 [RFC1345,KXS2]
-MIBenum: 2013
-Source: IBM NLS RM Vol2 SE09-8002-01, March 1990
-Alias: cp862
-Alias: 862
-Alias: csPC862LatinHebrew
-
-Name: IBM863 [RFC1345,KXS2]
-MIBenum: 2050
-Source: IBM Keyboard layouts and code pages, PN 07G4586 June 1991
-Alias: cp863
-Alias: 863
-Alias: csIBM863
-
-Name: IBM864 [RFC1345,KXS2]
-MIBenum: 2051
-Source: IBM Keyboard layouts and code pages, PN 07G4586 June 1991
-Alias: cp864
-Alias: csIBM864
-
-Name: IBM865 [RFC1345,KXS2]
-MIBenum: 2052
-Source: IBM DOS 3.3 Ref (Abridged), 94X9575 (Feb 1987)
-Alias: cp865
-Alias: 865
-Alias: csIBM865
-
-Name: IBM866 [Pond]
-MIBenum: 2086
-Source: IBM NLDG Volume 2 (SE09-8002-03) August 1994
-Alias: cp866
-Alias: 866
-Alias: csIBM866
-
-Name: IBM868 [RFC1345,KXS2]
-MIBenum: 2053
-Source: IBM NLS RM Vol2 SE09-8002-01, March 1990
-Alias: CP868
-Alias: cp-ar
-Alias: csIBM868
-
-Name: IBM869 [RFC1345,KXS2]
-MIBenum: 2054
-Source: IBM Keyboard layouts and code pages, PN 07G4586 June 1991
-Alias: cp869
-Alias: 869
-Alias: cp-gr
-Alias: csIBM869
-
-Name: IBM870 [RFC1345,KXS2]
-MIBenum: 2055
-Source: IBM NLS RM Vol2 SE09-8002-01, March 1990
-Alias: CP870
-Alias: ebcdic-cp-roece
-Alias: ebcdic-cp-yu
-Alias: csIBM870
-
-Name: IBM871 [RFC1345,KXS2]
-MIBenum: 2056
-Source: IBM NLS RM Vol2 SE09-8002-01, March 1990
-Alias: CP871
-Alias: ebcdic-cp-is
-Alias: csIBM871
-
-Name: IBM880 [RFC1345,KXS2]
-MIBenum: 2057
-Source: IBM NLS RM Vol2 SE09-8002-01, March 1990
-Alias: cp880
-Alias: EBCDIC-Cyrillic
-Alias: csIBM880
-
-Name: IBM891 [RFC1345,KXS2]
-MIBenum: 2058
-Source: IBM NLS RM Vol2 SE09-8002-01, March 1990
-Alias: cp891
-Alias: csIBM891
-
-Name: IBM903 [RFC1345,KXS2]
-MIBenum: 2059
-Source: IBM NLS RM Vol2 SE09-8002-01, March 1990
-Alias: cp903
-Alias: csIBM903
-
-Name: IBM904 [RFC1345,KXS2]
-MIBenum: 2060
-Source: IBM NLS RM Vol2 SE09-8002-01, March 1990
-Alias: cp904
-Alias: 904
-Alias: csIBBM904
-
-Name: IBM905 [RFC1345,KXS2]
-MIBenum: 2061
-Source: IBM 3174 Character Set Ref, GA27-3831-02, March 1990
-Alias: CP905
-Alias: ebcdic-cp-tr
-Alias: csIBM905
-
-Name: IBM918 [RFC1345,KXS2]
-MIBenum: 2062
-Source: IBM NLS RM Vol2 SE09-8002-01, March 1990
-Alias: CP918
-Alias: ebcdic-cp-ar2
-Alias: csIBM918
-
-Name: IBM1026 [RFC1345,KXS2]
-MIBenum: 2063
-Source: IBM NLS RM Vol2 SE09-8002-01, March 1990
-Alias: CP1026
-Alias: csIBM1026
-
-Name: EBCDIC-AT-DE [RFC1345,KXS2]
-MIBenum: 2064
-Source: IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987
-Alias: csIBMEBCDICATDE
-
-Name: EBCDIC-AT-DE-A [RFC1345,KXS2]
-MIBenum: 2065
-Source: IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987
-Alias: csEBCDICATDEA
-
-Name: EBCDIC-CA-FR [RFC1345,KXS2]
-MIBenum: 2066
-Source: IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987
-Alias: csEBCDICCAFR
-
-Name: EBCDIC-DK-NO [RFC1345,KXS2]
-MIBenum: 2067
-Source: IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987
-Alias: csEBCDICDKNO
-
-Name: EBCDIC-DK-NO-A [RFC1345,KXS2]
-MIBenum: 2068
-Source: IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987
-Alias: csEBCDICDKNOA
-
-Name: EBCDIC-FI-SE [RFC1345,KXS2]
-MIBenum: 2069
-Source: IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987
-Alias: csEBCDICFISE
-
-Name: EBCDIC-FI-SE-A [RFC1345,KXS2]
-MIBenum: 2070
-Source: IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987
-Alias: csEBCDICFISEA
-
-Name: EBCDIC-FR [RFC1345,KXS2]
-MIBenum: 2071
-Source: IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987
-Alias: csEBCDICFR
-
-Name: EBCDIC-IT [RFC1345,KXS2]
-MIBenum: 2072
-Source: IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987
-Alias: csEBCDICIT
-
-Name: EBCDIC-PT [RFC1345,KXS2]
-MIBenum: 2073
-Source: IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987
-Alias: csEBCDICPT
-
-Name: EBCDIC-ES [RFC1345,KXS2]
-MIBenum: 2074
-Source: IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987
-Alias: csEBCDICES
-
-Name: EBCDIC-ES-A [RFC1345,KXS2]
-MIBenum: 2075
-Source: IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987
-Alias: csEBCDICESA
-
-Name: EBCDIC-ES-S [RFC1345,KXS2]
-MIBenum: 2076
-Source: IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987
-Alias: csEBCDICESS
-
-Name: EBCDIC-UK [RFC1345,KXS2]
-MIBenum: 2077
-Source: IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987
-Alias: csEBCDICUK
-
-Name: EBCDIC-US [RFC1345,KXS2]
-MIBenum: 2078
-Source: IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987
-Alias: csEBCDICUS
-
-Name: UNKNOWN-8BIT [RFC1428]
-MIBenum: 2079
-Alias: csUnknown8BiT
-
-Name: MNEMONIC [RFC1345,KXS2]
-MIBenum: 2080
-Source: RFC 1345, also known as "mnemonic+ascii+38"
-Alias: csMnemonic
-
-Name: MNEM [RFC1345,KXS2]
-MIBenum: 2081
-Source: RFC 1345, also known as "mnemonic+ascii+8200"
-Alias: csMnem
-
-Name: VISCII [RFC1456]
-MIBenum: 2082
-Source: RFC 1456
-Alias: csVISCII
-
-Name: VIQR [RFC1456]
-MIBenum: 2083
-Source: RFC 1456
-Alias: csVIQR
-
-Name: KOI8-R (preferred MIME name) [RFC1489]
-MIBenum: 2084
-Source: RFC 1489, based on GOST-19768-74, ISO-6937/8,
- INIS-Cyrillic, ISO-5427.
-Alias: csKOI8R
-
-Name: KOI8-U [RFC2319]
-MIBenum: 2088
-Source: RFC 2319
-
-Name: IBM00858
-MIBenum: 2089
-Source: IBM See (http://www.iana.org/assignments/charset-reg/IBM00858) [Mahdi]
-Alias: CCSID00858
-Alias: CP00858
-Alias: PC-Multilingual-850+euro
-
-Name: IBM00924
-MIBenum: 2090
-Source: IBM See (http://www.iana.org/assignments/charset-reg/IBM00924) [Mahdi]
-Alias: CCSID00924
-Alias: CP00924
-Alias: ebcdic-Latin9--euro
-
-Name: IBM01140
-MIBenum: 2091
-Source: IBM See (http://www.iana.org/assignments/charset-reg/IBM01140) [Mahdi]
-Alias: CCSID01140
-Alias: CP01140
-Alias: ebcdic-us-37+euro
-
-Name: IBM01141
-MIBenum: 2092
-Source: IBM See (http://www.iana.org/assignments/charset-reg/IBM01141) [Mahdi]
-Alias: CCSID01141
-Alias: CP01141
-Alias: ebcdic-de-273+euro
-
-Name: IBM01142
-MIBenum: 2093
-Source: IBM See (http://www.iana.org/assignments/charset-reg/IBM01142) [Mahdi]
-Alias: CCSID01142
-Alias: CP01142
-Alias: ebcdic-dk-277+euro
-Alias: ebcdic-no-277+euro
-
-Name: IBM01143
-MIBenum: 2094
-Source: IBM See (http://www.iana.org/assignments/charset-reg/IBM01143) [Mahdi]
-Alias: CCSID01143
-Alias: CP01143
-Alias: ebcdic-fi-278+euro
-Alias: ebcdic-se-278+euro
-
-Name: IBM01144
-MIBenum: 2095
-Source: IBM See (http://www.iana.org/assignments/charset-reg/IBM01144) [Mahdi]
-Alias: CCSID01144
-Alias: CP01144
-Alias: ebcdic-it-280+euro
-
-Name: IBM01145
-MIBenum: 2096
-Source: IBM See (http://www.iana.org/assignments/charset-reg/IBM01145) [Mahdi]
-Alias: CCSID01145
-Alias: CP01145
-Alias: ebcdic-es-284+euro
-
-Name: IBM01146
-MIBenum: 2097
-Source: IBM See (http://www.iana.org/assignments/charset-reg/IBM01146) [Mahdi]
-Alias: CCSID01146
-Alias: CP01146
-Alias: ebcdic-gb-285+euro
-
-Name: IBM01147
-MIBenum: 2098
-Source: IBM See (http://www.iana.org/assignments/charset-reg/IBM01147) [Mahdi]
-Alias: CCSID01147
-Alias: CP01147
-Alias: ebcdic-fr-297+euro
-
-Name: IBM01148
-MIBenum: 2099
-Source: IBM See (http://www.iana.org/assignments/charset-reg/IBM01148) [Mahdi]
-Alias: CCSID01148
-Alias: CP01148
-Alias: ebcdic-international-500+euro
-
-Name: IBM01149
-MIBenum: 2100
-Source: IBM See (http://www.iana.org/assignments/charset-reg/IBM01149) [Mahdi]
-Alias: CCSID01149
-Alias: CP01149
-Alias: ebcdic-is-871+euro
-
-Name: Big5-HKSCS [Yick]
-MIBenum: 2101
-Source: See (http://www.iana.org/assignments/charset-reg/Big5-HKSCS)
-Alias: None
-
-Name: IBM1047 [Robrigado]
-MIBenum: 2102
-Source: IBM1047 (EBCDIC Latin 1/Open Systems)
-http://www-1.ibm.com/servers/eserver/iseries/software/globalization/pdf/cp01047z.pdf
-Alias: IBM-1047
-
-Name: PTCP154 [Uskov]
-MIBenum: 2103
-Source: See (http://www.iana.org/assignments/charset-reg/PTCP154)
-Alias: csPTCP154
-Alias: PT154
-Alias: CP154
-Alias: Cyrillic-Asian
-
-Name: Amiga-1251
-MIBenum: 2104
-Source: See (http://www.amiga.ultranet.ru/Amiga-1251.html)
-Alias: Ami1251
-Alias: Amiga1251
-Alias: Ami-1251
-(Aliases are provided for historical reasons and should not be used)
- [Malyshev]
-
-Name: KOI7-switched
-MIBenum: 2105
-Source: See <http://www.iana.org/assignments/charset-reg/KOI7-switched>
-Aliases: None
-
-Name: UNICODE-1-1 [RFC1641]
-MIBenum: 1010
-Source: RFC 1641
-Alias: csUnicode11
-
-Name: SCSU
-MIBenum: 1011
-Source: SCSU See (http://www.iana.org/assignments/charset-reg/SCSU) [Scherer]
-Alias: None
-
-Name: UTF-7 [RFC2152]
-MIBenum: 1012
-Source: RFC 2152
-Alias: None
-
-Name: UTF-16BE [RFC2781]
-MIBenum: 1013
-Source: RFC 2781
-Alias: None
-
-Name: UTF-16LE [RFC2781]
-MIBenum: 1014
-Source: RFC 2781
-Alias: None
-
-Name: UTF-16 [RFC2781]
-MIBenum: 1015
-Source: RFC 2781
-Alias: None
-
-Name: CESU-8 [Phipps]
-MIBenum: 1016
-Source: <http://www.unicode.org/unicode/reports/tr26>
-Alias: csCESU-8
-
-Name: UTF-32 [Davis]
-MIBenum: 1017
-Source: <http://www.unicode.org/unicode/reports/tr19/>
-Alias: None
-
-Name: UTF-32BE [Davis]
-MIBenum: 1018
-Source: <http://www.unicode.org/unicode/reports/tr19/>
-Alias: None
-
-Name: UTF-32LE [Davis]
-MIBenum: 1019
-Source: <http://www.unicode.org/unicode/reports/tr19/>
-Alias: None
-
-Name: BOCU-1 [Scherer]
-MIBenum: 1020
-Source: http://www.unicode.org/notes/tn6/
-Alias: csBOCU-1
-
-Name: UNICODE-1-1-UTF-7 [RFC1642]
-MIBenum: 103
-Source: RFC 1642
-Alias: csUnicode11UTF7
-
-Name: UTF-8 [RFC3629]
-MIBenum: 106
-Source: RFC 3629
-Alias: None
-
-Name: ISO-8859-13
-MIBenum: 109
-Source: ISO See (http://www.iana.org/assignments/charset-reg/iso-8859-13)[Tumasonis]
-Alias: None
-
-Name: ISO-8859-14
-MIBenum: 110
-Source: ISO See (http://www.iana.org/assignments/charset-reg/iso-8859-14) [Simonsen]
-Alias: iso-ir-199
-Alias: ISO_8859-14:1998
-Alias: ISO_8859-14
-Alias: latin8
-Alias: iso-celtic
-Alias: l8
-
-Name: ISO-8859-15
-MIBenum: 111
-Source: ISO
- Please see: <http://www.iana.org/assignments/charset-reg/ISO-8859-15>
-Alias: ISO_8859-15
-Alias: Latin-9
-
-Name: ISO-8859-16
-MIBenum: 112
-Source: ISO
-Alias: iso-ir-226
-Alias: ISO_8859-16:2001
-Alias: ISO_8859-16
-Alias: latin10
-Alias: l10
-
-Name: GBK
-MIBenum: 113
-Source: Chinese IT Standardization Technical Committee
- Please see: <http://www.iana.org/assignments/charset-reg/GBK>
-Alias: CP936
-Alias: MS936
-Alias: windows-936
-
-Name: GB18030
-MIBenum: 114
-Source: Chinese IT Standardization Technical Committee
- Please see: <http://www.iana.org/assignments/charset-reg/GB18030>
-Alias: None
-
-Name: OSD_EBCDIC_DF04_15
-MIBenum: 115
-Source: Fujitsu-Siemens standard mainframe EBCDIC encoding
- Please see: <http://www.iana.org/assignments/charset-reg/OSD-EBCDIC-DF04-15>
-Alias: None
-
-Name: OSD_EBCDIC_DF03_IRV
-MIBenum: 116
-Source: Fujitsu-Siemens standard mainframe EBCDIC encoding
- Please see: <http://www.iana.org/assignments/charset-reg/OSD-EBCDIC-DF03-IRV>
-Alias: None
-
-Name: OSD_EBCDIC_DF04_1
-MIBenum: 117
-Source: Fujitsu-Siemens standard mainframe EBCDIC encoding
- Please see: <http://www.iana.org/assignments/charset-reg/OSD-EBCDIC-DF04-1>
-Alias: None
-
-Name: JIS_Encoding
-MIBenum: 16
-Source: JIS X 0202-1991. Uses ISO 2022 escape sequences to
- shift code sets as documented in JIS X 0202-1991.
-Alias: csJISEncoding
-
-Name: Shift_JIS (preferred MIME name)
-MIBenum: 17
-Source: This charset is an extension of csHalfWidthKatakana by
- adding graphic characters in JIS X 0208. The CCS's are
- JIS X0201:1997 and JIS X0208:1997. The
- complete definition is shown in Appendix 1 of JIS
- X0208:1997.
- This charset can be used for the top-level media type "text".
-Alias: MS_Kanji
-Alias: csShiftJIS
-
-Name: Extended_UNIX_Code_Packed_Format_for_Japanese
-MIBenum: 18
-Source: Standardized by OSF, UNIX International, and UNIX Systems
- Laboratories Pacific. Uses ISO 2022 rules to select
- code set 0: US-ASCII (a single 7-bit byte set)
- code set 1: JIS X0208-1990 (a double 8-bit byte set)
- restricted to A0-FF in both bytes
- code set 2: Half Width Katakana (a single 7-bit byte set)
- requiring SS2 as the character prefix
- code set 3: JIS X0212-1990 (a double 7-bit byte set)
- restricted to A0-FF in both bytes
- requiring SS3 as the character prefix
-Alias: csEUCPkdFmtJapanese
-Alias: EUC-JP (preferred MIME name)
-
-Name: Extended_UNIX_Code_Fixed_Width_for_Japanese
-MIBenum: 19
-Source: Used in Japan. Each character is 2 octets.
- code set 0: US-ASCII (a single 7-bit byte set)
- 1st byte = 00
- 2nd byte = 20-7E
- code set 1: JIS X0208-1990 (a double 7-bit byte set)
- restricted to A0-FF in both bytes
- code set 2: Half Width Katakana (a single 7-bit byte set)
- 1st byte = 00
- 2nd byte = A0-FF
- code set 3: JIS X0212-1990 (a double 7-bit byte set)
- restricted to A0-FF in
- the first byte
- and 21-7E in the second byte
-Alias: csEUCFixWidJapanese
-
-Name: ISO-10646-UCS-Basic
-MIBenum: 1002
-Source: ASCII subset of Unicode. Basic Latin = collection 1
- See ISO 10646, Appendix A
-Alias: csUnicodeASCII
-
-Name: ISO-10646-Unicode-Latin1
-MIBenum: 1003
-Source: ISO Latin-1 subset of Unicode. Basic Latin and Latin-1
- Supplement = collections 1 and 2. See ISO 10646,
- Appendix A. See RFC 1815.
-Alias: csUnicodeLatin1
-Alias: ISO-10646
-
-Name: ISO-10646-J-1
-Source: ISO 10646 Japanese, see RFC 1815.
-
-Name: ISO-Unicode-IBM-1261
-MIBenum: 1005
-Source: IBM Latin-2, -3, -5, Extended Presentation Set, GCSGID: 1261
-Alias: csUnicodeIBM1261
-
-Name: ISO-Unicode-IBM-1268
-MIBenum: 1006
-Source: IBM Latin-4 Extended Presentation Set, GCSGID: 1268
-Alias: csUnicodeIBM1268
-
-Name: ISO-Unicode-IBM-1276
-MIBenum: 1007
-Source: IBM Cyrillic Greek Extended Presentation Set, GCSGID: 1276
-Alias: csUnicodeIBM1276
-
-Name: ISO-Unicode-IBM-1264
-MIBenum: 1008
-Source: IBM Arabic Presentation Set, GCSGID: 1264
-Alias: csUnicodeIBM1264
-
-Name: ISO-Unicode-IBM-1265
-MIBenum: 1009
-Source: IBM Hebrew Presentation Set, GCSGID: 1265
-Alias: csUnicodeIBM1265
-
-Name: ISO-8859-1-Windows-3.0-Latin-1 [HP-PCL5]
-MIBenum: 2000
-Source: Extended ISO 8859-1 Latin-1 for Windows 3.0.
- PCL Symbol Set id: 9U
-Alias: csWindows30Latin1
-
-Name: ISO-8859-1-Windows-3.1-Latin-1 [HP-PCL5]
-MIBenum: 2001
-Source: Extended ISO 8859-1 Latin-1 for Windows 3.1.
- PCL Symbol Set id: 19U
-Alias: csWindows31Latin1
-
-Name: ISO-8859-2-Windows-Latin-2 [HP-PCL5]
-MIBenum: 2002
-Source: Extended ISO 8859-2. Latin-2 for Windows 3.1.
- PCL Symbol Set id: 9E
-Alias: csWindows31Latin2
-
-Name: ISO-8859-9-Windows-Latin-5 [HP-PCL5]
-MIBenum: 2003
-Source: Extended ISO 8859-9. Latin-5 for Windows 3.1
- PCL Symbol Set id: 5T
-Alias: csWindows31Latin5
-
-Name: Adobe-Standard-Encoding [Adobe]
-MIBenum: 2005
-Source: PostScript Language Reference Manual
- PCL Symbol Set id: 10J
-Alias: csAdobeStandardEncoding
-
-Name: Ventura-US [HP-PCL5]
-MIBenum: 2006
-Source: Ventura US. ASCII plus characters typically used in
- publishing, like pilcrow, copyright, registered, trade mark,
- section, dagger, and double dagger in the range A0 (hex)
- to FF (hex).
- PCL Symbol Set id: 14J
-Alias: csVenturaUS
-
-Name: Ventura-International [HP-PCL5]
-MIBenum: 2007
-Source: Ventura International. ASCII plus coded characters similar
- to Roman8.
- PCL Symbol Set id: 13J
-Alias: csVenturaInternational
-
-Name: PC8-Danish-Norwegian [HP-PCL5]
-MIBenum: 2012
-Source: PC Danish Norwegian
- 8-bit PC set for Danish Norwegian
- PCL Symbol Set id: 11U
-Alias: csPC8DanishNorwegian
-
-Name: PC8-Turkish [HP-PCL5]
-MIBenum: 2014
-Source: PC Latin Turkish. PCL Symbol Set id: 9T
-Alias: csPC8Turkish
-
-Name: IBM-Symbols [IBM-CIDT]
-MIBenum: 2015
-Source: Presentation Set, CPGID: 259
-Alias: csIBMSymbols
-
-Name: IBM-Thai [IBM-CIDT]
-MIBenum: 2016
-Source: Presentation Set, CPGID: 838
-Alias: csIBMThai
-
-Name: HP-Legal [HP-PCL5]
-MIBenum: 2017
-Source: PCL 5 Comparison Guide, Hewlett-Packard,
- HP part number 5961-0510, October 1992
- PCL Symbol Set id: 1U
-Alias: csHPLegal
-
-Name: HP-Pi-font [HP-PCL5]
-MIBenum: 2018
-Source: PCL 5 Comparison Guide, Hewlett-Packard,
- HP part number 5961-0510, October 1992
- PCL Symbol Set id: 15U
-Alias: csHPPiFont
-
-Name: HP-Math8 [HP-PCL5]
-MIBenum: 2019
-Source: PCL 5 Comparison Guide, Hewlett-Packard,
- HP part number 5961-0510, October 1992
- PCL Symbol Set id: 8M
-Alias: csHPMath8
-
-Name: Adobe-Symbol-Encoding [Adobe]
-MIBenum: 2020
-Source: PostScript Language Reference Manual
- PCL Symbol Set id: 5M
-Alias: csHPPSMath
-
-Name: HP-DeskTop [HP-PCL5]
-MIBenum: 2021
-Source: PCL 5 Comparison Guide, Hewlett-Packard,
- HP part number 5961-0510, October 1992
- PCL Symbol Set id: 7J
-Alias: csHPDesktop
-
-Name: Ventura-Math [HP-PCL5]
-MIBenum: 2022
-Source: PCL 5 Comparison Guide, Hewlett-Packard,
- HP part number 5961-0510, October 1992
- PCL Symbol Set id: 6M
-Alias: csVenturaMath
-
-Name: Microsoft-Publishing [HP-PCL5]
-MIBenum: 2023
-Source: PCL 5 Comparison Guide, Hewlett-Packard,
- HP part number 5961-0510, October 1992
- PCL Symbol Set id: 6J
-Alias: csMicrosoftPublishing
-
-Name: Windows-31J
-MIBenum: 2024
-Source: Windows Japanese. A further extension of Shift_JIS
- to include NEC special characters (Row 13), NEC
- selection of IBM extensions (Rows 89 to 92), and IBM
- extensions (Rows 115 to 119). The CCS's are
- JIS X0201:1997, JIS X0208:1997, and these extensions.
- This charset can be used for the top-level media type "text",
- but it is of limited or specialized use (see RFC2278).
- PCL Symbol Set id: 19K
-Alias: csWindows31J
-
-Name: GB2312 (preferred MIME name)
-MIBenum: 2025
-Source: Chinese for People's Republic of China (PRC) mixed one byte,
- two byte set:
- 20-7E = one byte ASCII
- A1-FE = two byte PRC Kanji
- See GB 2312-80
- PCL Symbol Set Id: 18C
-Alias: csGB2312
-
-Name: Big5 (preferred MIME name)
-MIBenum: 2026
-Source: Chinese for Taiwan Multi-byte set.
- PCL Symbol Set Id: 18T
-Alias: csBig5
-
-Name: windows-1250
-MIBenum: 2250
-Source: Microsoft (http://www.iana.org/assignments/charset-reg/windows-1250) [Lazhintseva]
-Alias: None
-
-Name: windows-1251
-MIBenum: 2251
-Source: Microsoft (http://www.iana.org/assignments/charset-reg/windows-1251) [Lazhintseva]
-Alias: None
-
-Name: windows-1252
-MIBenum: 2252
-Source: Microsoft (http://www.iana.org/assignments/charset-reg/windows-1252) [Wendt]
-Alias: None
-
-Name: windows-1253
-MIBenum: 2253
-Source: Microsoft (http://www.iana.org/assignments/charset-reg/windows-1253) [Lazhintseva]
-Alias: None
-
-Name: windows-1254
-MIBenum: 2254
-Source: Microsoft (http://www.iana.org/assignments/charset-reg/windows-1254) [Lazhintseva]
-Alias: None
-
-Name: windows-1255
-MIBenum: 2255
-Source: Microsoft (http://www.iana.org/assignments/charset-reg/windows-1255) [Lazhintseva]
-Alias: None
-
-Name: windows-1256
-MIBenum: 2256
-Source: Microsoft (http://www.iana.org/assignments/charset-reg/windows-1256) [Lazhintseva]
-Alias: None
-
-Name: windows-1257
-MIBenum: 2257
-Source: Microsoft (http://www.iana.org/assignments/charset-reg/windows-1257) [Lazhintseva]
-Alias: None
-
-Name: windows-1258
-MIBenum: 2258
-Source: Microsoft (http://www.iana.org/assignments/charset-reg/windows-1258) [Lazhintseva]
-Alias: None
-
-Name: TIS-620
-MIBenum: 2259
-Source: Thai Industrial Standards Institute (TISI) [Tantsetthi]
-
-Name: HZ-GB-2312
-MIBenum: 2085
-Source: RFC 1842, RFC 1843 [RFC1842, RFC1843]
-
-
-REFERENCES
-----------
-
-[RFC1345] Simonsen, K., "Character Mnemonics & Character Sets",
- RFC 1345, Rationel Almen Planlaegning, Rationel Almen
- Planlaegning, June 1992.
-
-[RFC1428] Vaudreuil, G., "Transition of Internet Mail from
- Just-Send-8 to 8bit-SMTP/MIME", RFC1428, CNRI, February
- 1993.
-
-[RFC1456] Vietnamese Standardization Working Group, "Conventions for
- Encoding the Vietnamese Language VISCII: VIetnamese
- Standard Code for Information Interchange VIQR: VIetnamese
- Quoted-Readable Specification Revision 1.1", RFC 1456, May
- 1993.
-
-[RFC1468] Murai, J., Crispin, M., and E. van der Poel, "Japanese
- Character Encoding for Internet Messages", RFC 1468,
- Keio University, Panda Programming, June 1993.
-
-[RFC1489] Chernov, A., "Registration of a Cyrillic Character Set",
- RFC1489, RELCOM Development Team, July 1993.
-
-[RFC1554] Ohta, M., and K. Handa, "ISO-2022-JP-2: Multilingual
- Extension of ISO-2022-JP", RFC1554, Tokyo Institute of
- Technology, ETL, December 1993.
-
-[RFC1556] Nussbacher, H., "Handling of Bi-directional Texts in MIME",
- RFC1556, Israeli Inter-University, December 1993.
-
-[RFC1557] Choi, U., Chon, K., and H. Park, "Korean Character Encoding
- for Internet Messages", KAIST, Solvit Chosun Media,
- December 1993.
-
-[RFC1641] Goldsmith, D., and M. Davis, "Using Unicode with MIME",
- RFC1641, Taligent, Inc., July 1994.
-
-[RFC1642] Goldsmith, D., and M. Davis, "UTF-7", RFC1642, Taligent,
- Inc., July 1994.
-
-[RFC1815] Ohta, M., "Character Sets ISO-10646 and ISO-10646-J-1",
- RFC 1815, Tokyo Institute of Technology, July 1995.
-
-
-[Adobe] Adobe Systems Incorporated, PostScript Language Reference
- Manual, second edition, Addison-Wesley Publishing Company,
- Inc., 1990.
-
-[ECMA Registry] ISO-IR: International Register of Escape Sequences
- http://www.itscj.ipsj.or.jp/ISO-IE/ Note: The current
- registration authority is IPSJ/ITSCJ, Japan.
-
-[HP-PCL5] Hewlett-Packard Company, "HP PCL 5 Comparison Guide",
- (P/N 5021-0329) pp B-13, 1996.
-
-[IBM-CIDT] IBM Corporation, "ABOUT TYPE: IBM's Technical Reference
- for Core Interchange Digitized Type", Publication number
- S544-3708-01
-
-[RFC1842] Wei, Y., J. Li, and Y. Jiang, "ASCII Printable
- Characters-Based Chinese Character Encoding for Internet
- Messages", RFC 1842, Harvard University, Rice University,
- University of Maryland, August 1995.
-
-[RFC1843] Lee, F., "HZ - A Data Format for Exchanging Files of
- Arbitrarily Mixed Chinese and ASCII Characters", RFC 1843,
- Stanford University, August 1995.
-
-[RFC2152] Goldsmith, D., M. Davis, "UTF-7: A Mail-Safe Transformation
- Format of Unicode", RFC 2152, Apple Inc.,
- Taligent Inc., May 1997.
-
-[RFC2279] Yergeau, F., "UTF-8, A Transformation Format of ISO 10646",
- RFC 2279, Alis Technologies, January, 1998.
-
-[RFC2781] Hoffman, P., Yergeau, F., "UTF-16, an encoding of ISO 10646",
- RFC 2781, February 2000.
-
-[RFC3629] Yergeau, F., "UTF-8, a transformation format of ISO 10646",
- RFC3629, November 2003.
-
-PEOPLE
-------
-
-[KXS2] Keld Simonsen <keld.simon...@dkuug.dk>
-
-[Choi] Woohyong Choi <whc...@cosmos.kaist.ac.kr>
-
-[Davis] Mark Davis, <m...@unicode.org>, April 2002.
-
-[Lazhintseva] Katya Lazhintseva, <kat...@microsoft.com>, May 1996.
-
-[Mahdi] Tamer Mahdi, <ta...@ca.ibm.com>, August 2000.
-
-[Malyshev] Michael Malyshev, <michael_malys...@mail.ru>, January 2004
-
-[Murai] Jun Murai <j...@wide.ad.jp>
-
-[Nussbacher] Hank Nussbacher, <h...@vm.tau.ac.il>
-
-[Ohta] Masataka Ohta, <mo...@cc.titech.ac.jp>, July 1995.
-
-[Phipps] Toby Phipps, <tphi...@peoplesoft.com>, March 2002.
-
-[Pond] Rick Pond, <rickp...@vnet.ibm.com>, March 1997.
-
-[Robrigado] Reuel Robrigado, <reu...@ca.ibm.com>, September 2002.
-
-[Scherer] Markus Scherer, <markus.sche...@jtcsv.com>, August 2000,
- September 2002.
-
-[Simonsen] Keld Simonsen, <keld.simon...@rap.dk>, August 2000.
-
-[Tantsetthi] Trin Tantsetthi, <t...@mozart.inet.co.th>, September 1998.
-
-[Tumasonis] Vladas Tumasonis, <vladas.tumaso...@maf.vu.lt>, August 2000.
-
-[Uskov] Alexander Uskov, <aus...@idc.kz>, September 2002.
-
-[Wendt] Chris Wendt, <chri...@microsoft.com>, December 1999.
-
-[Yick] Nicky Yick, <cl...@itsd.gcn.gov.hk>, October 2000.
-
-[]
-
-
-
-
-
-
-
Deleted: trunk/Source/WebCore/platform/text/mac/ios-encodings.txt (225026 => 225027)
--- trunk/Source/WebCore/platform/text/mac/ios-encodings.txt 2017-11-19 01:55:37 UTC (rev 225026)
+++ trunk/Source/WebCore/platform/text/mac/ios-encodings.txt 2017-11-19 03:42:49 UTC (rev 225027)
@@ -1,11 +0,0 @@
-# We'd like to eliminate this file.
-# It would be nice to get rid of dependence on the TextEncodingConvert entirely.
-# Perhaps we can prove these are not used on the web and remove them.
-# Or perhaps we can get them added to ICU.
-
-# The items on the left are names of TEC TextEncoding values (without the leading kTextEncoding).
-# The items on the right are IANA character set names. Names listed in character-sets.txt are not
-# repeated here; mentioning any one character set from a group in there pulls in all the aliases in
-# that group.
-
-# No encodings for iOS
Deleted: trunk/Source/WebCore/platform/text/mac/mac-encodings.txt (225026 => 225027)
--- trunk/Source/WebCore/platform/text/mac/mac-encodings.txt 2017-11-19 01:55:37 UTC (rev 225026)
+++ trunk/Source/WebCore/platform/text/mac/mac-encodings.txt 2017-11-19 03:42:49 UTC (rev 225027)
@@ -1,40 +0,0 @@
-# We'd like to eliminate this file.
-# It would be nice to get rid of dependence on the TextEncodingConvert entirely.
-# Perhaps we can prove these are not used on the web and remove them.
-# Or perhaps we can get them added to ICU.
-
-# The items on the left are names of TEC TextEncoding values (without the leading kTextEncoding).
-# The items on the right are IANA character set names. Names listed in character-sets.txt are not
-# repeated here; mentioning any one character set from a group in there pulls in all the aliases in
-# that group.
-
-DOSChineseTrad: cp950
-DOSGreek: cp737, ibm737
-EUC_TW: EUC-TW
-ISO_2022_JP_3: ISO-2022-JP-3
-JIS_C6226_78: JIS_C6226-1978
-JIS_X0208_83: JIS_X0208-1983
-JIS_X0208_90: JIS_X0208-1990
-JIS_X0212_90: JIS_X0212-1990
-MacArabic: x-mac-arabic
-MacChineseSimp: x-mac-chinesesimp, xmacsimpchinese
-MacChineseTrad: x-mac-chinesetrad, xmactradchinese
-MacCroatian: x-mac-croatian
-MacDevanagari: x-mac-devanagari
-MacDingbats: x-mac-dingbats
-MacFarsi: x-mac-farsi
-MacGujarati: x-mac-gujarati
-MacGurmukhi: x-mac-gurmukhi
-MacHebrew: x-mac-hebrew
-MacIcelandic: x-mac-icelandic
-MacJapanese: x-mac-japanese
-MacKorean: x-mac-korean
-MacRomanLatin1: x-mac-roman-latin1
-MacRomanian: x-mac-romanian
-MacSymbol: x-mac-symbol
-MacThai: x-mac-thai
-MacTibetan: x-mac-tibetan
-MacVT100: x-mac-vt100
-NextStepLatin: x-nextstep
-ShiftJIS_X0213_00: Shift_JIS_X0213-2000
-WindowsKoreanJohab: johab
Deleted: trunk/Source/WebCore/platform/text/mac/make-charset-table.pl (225026 => 225027)
--- trunk/Source/WebCore/platform/text/mac/make-charset-table.pl 2017-11-19 01:55:37 UTC (rev 225026)
+++ trunk/Source/WebCore/platform/text/mac/make-charset-table.pl 2017-11-19 03:42:49 UTC (rev 225027)
@@ -1,225 +0,0 @@
-#!/usr/bin/perl -w
-
-# Copyright (C) 2003, 2004, 2005, 2006 Apple Inc. All rights reserved.
-#
-# 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.
-# 3. Neither the name of Apple Inc. ("Apple") nor the names of
-# its contributors may be used to endorse or promote products derived
-# from this software without specific prior written permission.
-#
-# THIS SOFTWARE IS PROVIDED BY APPLE AND ITS CONTRIBUTORS "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 OR ITS 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.
-
-use strict;
-
-my %aliasesFromCharsetsFile;
-my %namesWritten;
-
-my $output = "";
-
-my $error = 0;
-
-sub error ($)
-{
- print STDERR @_, "\n";
- $error = 1;
-}
-
-sub emit_line
-{
- my ($name, $prefix, $encoding, $flags) = @_;
-
- error "$name shows up twice in output" if $namesWritten{$name};
- $namesWritten{$name} = 1;
-
- $output .= " { \"$name\", $prefix$encoding },\n";
-}
-
-sub process_platform_encodings
-{
- my ($filename, $PlatformPrefix) = @_;
- my $baseFilename = $filename;
- $baseFilename =~ s|.*/||;
-
- my %seenPlatformNames;
- my %seenIANANames;
-
- open PLATFORM_ENCODINGS, $filename or die;
-
- while (<PLATFORM_ENCODINGS>) {
- chomp;
- s/\#.*$//;
- s/\s+$//;
- if (my ($PlatformName, undef, $flags, $IANANames) = /^(.+?)(, (.+))?: (.+)$/) {
- my %aliases;
-
- my $PlatformNameWithFlags = $PlatformName;
- if ($flags) {
- $PlatformNameWithFlags .= ", " . $flags;
- } else {
- $flags = "NoEncodingFlags";
- }
- error "Platform encoding name $PlatformName is mentioned twice in $baseFilename" if $seenPlatformNames{$PlatformNameWithFlags};
- $seenPlatformNames{$PlatformNameWithFlags} = 1;
-
- # Build the aliases list.
- # Also check that no two names are part of the same entry in the charsets file.
- my @IANANames = split ", ", $IANANames;
- my $firstName = "";
- my $canonicalFirstName = "";
- my $prevName = "";
- for my $name (@IANANames) {
- if ($firstName eq "") {
- if ($name !~ /^[-A-Za-z0-9_]+$/) {
- error "$name, in $baseFilename, has illegal characters in it";
- next;
- }
- $firstName = $name;
- } else {
- if ($name !~ /^[a-z0-9]+$/) {
- error "$name, in $baseFilename, has illegal characters in it (must be all lowercase alphanumeric)";
- next;
- }
- if ($name le $prevName) {
- error "$name comes after $prevName in $baseFilename, but everything must be in alphabetical order";
- }
- $prevName = $name;
- }
-
- my $canonicalName = lc $name;
- $canonicalName =~ tr/-_//d;
-
- $canonicalFirstName = $canonicalName if $canonicalFirstName eq "";
-
- error "$name is mentioned twice in $baseFilename" if $seenIANANames{$canonicalName};
- $seenIANANames{$canonicalName} = 1;
-
- $aliases{$canonicalName} = 1;
- next if !$aliasesFromCharsetsFile{$canonicalName};
- for my $alias (@{$aliasesFromCharsetsFile{$canonicalName}}) {
- $aliases{$alias} = 1;
- }
- for my $otherName (@IANANames) {
- next if $canonicalName eq $otherName;
- if ($aliasesFromCharsetsFile{$otherName}
- && $aliasesFromCharsetsFile{$canonicalName} eq $aliasesFromCharsetsFile{$otherName}
- && $canonicalName le $otherName) {
- error "$baseFilename lists both $name and $otherName under $PlatformName, but that aliasing is already specified in character-sets.txt";
- }
- }
- }
-
- # write out
- emit_line($firstName, $PlatformPrefix, $PlatformName, $flags);
- for my $alias (sort keys %aliases) {
- emit_line($alias, $PlatformPrefix, $PlatformName, $flags) if $alias ne $canonicalFirstName;
- }
- } elsif (/^([a-zA-Z0-9_]+)(, (.+))?$/) {
- my $PlatformName = $1;
-
- error "Platform encoding name $PlatformName is mentioned twice in $baseFilename" if $seenPlatformNames{$PlatformName};
- $seenPlatformNames{$PlatformName} = 1;
- } elsif (/./) {
- error "syntax error in $baseFilename, line $.";
- }
- }
-
- close PLATFORM_ENCODINGS;
-}
-
-sub process_iana_charset
-{
- my ($canonical_name, @aliases) = @_;
-
- return if !$canonical_name;
-
- my @names = sort $canonical_name, @aliases;
-
- for my $name (@names) {
- $aliasesFromCharsetsFile{$name} = \@names;
- }
-}
-
-sub process_iana_charsets
-{
- my ($filename) = @_;
-
- open CHARSETS, $filename or die;
-
- my %seen;
-
- my $canonical_name;
- my @aliases;
-
- my %exceptions = ( isoir91 => 1, isoir92 => 1 );
-
- while (<CHARSETS>) {
- chomp;
- if ((my $new_canonical_name) = /Name: ([^ \t]*).*/) {
- $new_canonical_name = lc $new_canonical_name;
- $new_canonical_name =~ tr/a-z0-9//cd;
-
- error "saw $new_canonical_name twice in character-sets.txt", if $seen{$new_canonical_name};
- $seen{$new_canonical_name} = $new_canonical_name;
-
- process_iana_charset $canonical_name, @aliases;
-
- $canonical_name = $new_canonical_name;
- @aliases = ();
- } elsif ((my $new_alias) = /Alias: ([^ \t]*).*/) {
- $new_alias = lc $new_alias;
- $new_alias =~ tr/a-z0-9//cd;
-
- # do this after normalizing the alias, sometimes character-sets.txt
- # has weird escape characters, e.g. \b after None
- next if $new_alias eq "none";
-
- error "saw $new_alias twice in character-sets.txt $seen{$new_alias}, $canonical_name", if $seen{$new_alias} && $seen{$new_alias} ne $canonical_name && !$exceptions{$new_alias};
- push @aliases, $new_alias if !$seen{$new_alias};
- $seen{$new_alias} = $canonical_name;
- }
- }
-
- process_iana_charset $canonical_name, @aliases;
-
- close CHARSETS;
-}
-
-# Program body
-
-process_iana_charsets($ARGV[0]);
-process_platform_encodings($ARGV[1], $ARGV[2]);
-
-exit 1 if $error;
-
-print <<EOF
-// File generated by make-charset-table.pl. Do not edit!
-
-#include "config.h"
-#include "CharsetData.h"
-
-namespace WebCore {
-
- const CharsetEntry CharsetTable[] = {
-$output
- { 0, 0 }
- };
-
-}
-EOF
