1.1 --- /dev/null Thu Jan 01 00:00:00 1970 +0000
1.2 +++ b/intl/icu/source/data/mappings/convrtrs.txt Wed Dec 31 06:09:35 2014 +0100
1.3 @@ -0,0 +1,1264 @@
1.4 +# ******************************************************************************
1.5 +# *
1.6 +# * Copyright (C) 1995-2013, International Business Machines
1.7 +# * Corporation and others. All Rights Reserved.
1.8 +# *
1.9 +# ******************************************************************************
1.10 +
1.11 +# If this converter alias table looks very confusing, a much easier to
1.12 +# understand view can be found at this demo:
1.13 +# http://demo.icu-project.org/icu-bin/convexp
1.14 +
1.15 +# IMPORTANT NOTE
1.16 +#
1.17 +# This file is not read directly by ICU. If you change it, you need to
1.18 +# run gencnval, and eventually run pkgdata to update the representation that
1.19 +# ICU uses for aliases. The gencnval tool will normally compile this file into
1.20 +# cnvalias.icu. The gencnval -v verbose option will help you when you edit
1.21 +# this file.
1.22 +
1.23 +# Please be friendly to the rest of us that edit this table by
1.24 +# keeping this table free of tabs.
1.25 +
1.26 +# This is an alias file used by the character set converter.
1.27 +# A lot of converter information can be found in unicode/ucnv.h, but here
1.28 +# is more information about this file.
1.29 +#
1.30 +# If you are adding a new converter to this list and want to include it in the
1.31 +# icu data library, please be sure to add an entry to the appropriate ucm*.mk file
1.32 +# (see ucmfiles.mk for more information).
1.33 +#
1.34 +# Here is the file format using BNF-like syntax:
1.35 +#
1.36 +# converterTable ::= tags { converterLine* }
1.37 +# converterLine ::= converterName [ tags ] { taggedAlias* }'\n'
1.38 +# taggedAlias ::= alias [ tags ]
1.39 +# tags ::= '{' { tag+ } '}'
1.40 +# tag ::= standard['*']
1.41 +# converterName ::= [0-9a-zA-Z:_'-']+
1.42 +# alias ::= converterName
1.43 +#
1.44 +# Except for the converter name, aliases are case insensitive.
1.45 +# Names are separated by whitespace.
1.46 +# Line continuation and comment sytax are similar to the GNU make syntax.
1.47 +# Any lines beginning with whitespace (e.g. U+0020 SPACE or U+0009 HORIZONTAL
1.48 +# TABULATION) are presumed to be a continuation of the previous line.
1.49 +# The # symbol starts a comment and the comment continues till the end of
1.50 +# the line.
1.51 +#
1.52 +# The converter
1.53 +#
1.54 +# All names can be tagged by including a space-separated list of tags in
1.55 +# curly braces, as in ISO_8859-1:1987{IANA*} iso-8859-1 { MIME* } or
1.56 +# some-charset{MIME* IANA*}. The order of tags does not matter, and
1.57 +# whitespace is allowed between the tagged name and the tags list.
1.58 +#
1.59 +# The tags can be used to get standard names using ucnv_getStandardName().
1.60 +#
1.61 +# The complete list of recognized tags used in this file is defined in
1.62 +# the affinity list near the beginning of the file.
1.63 +#
1.64 +# The * after the standard tag denotes that the previous alias is the
1.65 +# preferred (default) charset name for that standard. There can only
1.66 +# be one of these default charset names per converter.
1.67 +
1.68 +
1.69 +
1.70 +# The world is getting more complicated...
1.71 +# Supporting XML parsers, HTML, MIME, and similar applications
1.72 +# that mark encodings with a charset name can be difficult.
1.73 +# Many of these applications and operating systems will update
1.74 +# their codepages over time.
1.75 +
1.76 +# It means that a new codepage, one that differs from an
1.77 +# old one by changing a code point, e.g., to the Euro sign,
1.78 +# must not get an old alias, because it would mean that
1.79 +# old files with this alias would be interpreted differently.
1.80 +
1.81 +# If an codepage gets updated by assigning characters to previously
1.82 +# unassigned code points, then a new name is not necessary.
1.83 +# Also, some codepages map unassigned codepage byte values
1.84 +# to the same numbers in Unicode for roundtripping. It may be
1.85 +# industry practice to keep the encoding name in such a case, too
1.86 +# (example: Windows codepages).
1.87 +
1.88 +# The aliases listed in the list of character sets
1.89 +# that is maintained by the IANA (http://www.iana.org/) must
1.90 +# not be changed to mean encodings different from what this
1.91 +# list shows. Currently, the IANA list is at
1.92 +# http://www.iana.org/assignments/character-sets
1.93 +# It should also be mentioned that the exact mapping table used for each
1.94 +# IANA names usually isn't specified. This means that some other applications
1.95 +# and operating systems are left to interpret the exact mappings for the
1.96 +# underspecified aliases. For instance, Shift-JIS on a Solaris platform
1.97 +# may be different from Shift-JIS on a Windows platform. This is why
1.98 +# some of the aliases can be tagged to differentiate different mapping
1.99 +# tables with the same alias. If an alias is given to more than one converter,
1.100 +# it is considered to be an ambiguous alias, and the affinity list will
1.101 +# choose the converter to use when a standard isn't specified with the alias.
1.102 +
1.103 +# Name matching is case-insensitive. Also, dashes '-', underscores '_'
1.104 +# and spaces ' ' are ignored in names (thus cs-iso_latin-1, csisolatin1
1.105 +# and "cs iso latin 1" are the same).
1.106 +# However, the names in the left column are directly file names
1.107 +# or names of algorithmic converters, and their case must not
1.108 +# be changed - or else code and/or file names must also be changed.
1.109 +# For example, the converter ibm-921 is expected to be the file ibm-921.cnv.
1.110 +
1.111 +
1.112 +
1.113 +# The immediately following list is the affinity list of supported standard tags.
1.114 +# When multiple converters have the same alias under different standards,
1.115 +# the standard nearest to the top of this list with that alias will
1.116 +# be the first converter that will be opened. The ordering of the aliases
1.117 +# after this affinity list does not affect the preferred alias, but it may
1.118 +# affect the order of the returned list of aliases for a given converter.
1.119 +#
1.120 +# The general ordering is from specific and frequently used to more general
1.121 +# or rarely used at the bottom.
1.122 +{ UTR22 # Name format specified by http://www.unicode.org/unicode/reports/tr22/
1.123 + # ICU # Can also use ICU_FEATURE
1.124 + IBM # The IBM CCSID number is specified by ibm-*
1.125 + WINDOWS # The Microsoft code page identifier number is specified by windows-*. The rest are recognized IE names.
1.126 + JAVA # Source: Sun JDK. Alias name case is ignored, but dashes are not ignored.
1.127 + # GLIBC
1.128 + # AIX
1.129 + # DB2
1.130 + # SOLARIS
1.131 + # APPLE
1.132 + # HPUX
1.133 + IANA # Source: http://www.iana.org/assignments/character-sets
1.134 + MIME # Source: http://www.iana.org/assignments/character-sets
1.135 + # MSIE # MSIE is Internet Explorer, which can be different from Windows (From the IMultiLanguage COM interface)
1.136 + # ZOS_USS # z/OS (os/390) Unix System Services (USS), which has NL<->LF swapping. They have the same format as the IBM tag.
1.137 + }
1.138 +
1.139 +
1.140 +
1.141 +# Fully algorithmic converters
1.142 +
1.143 +UTF-8 { IANA* MIME* JAVA* WINDOWS }
1.144 + ibm-1208 { IBM* } # UTF-8 with IBM PUA
1.145 + ibm-1209 { IBM } # UTF-8
1.146 + ibm-5304 { IBM } # Unicode 2.0, UTF-8 with IBM PUA
1.147 + ibm-5305 { IBM } # Unicode 2.0, UTF-8
1.148 + ibm-13496 { IBM } # Unicode 3.0, UTF-8 with IBM PUA
1.149 + ibm-13497 { IBM } # Unicode 3.0, UTF-8
1.150 + ibm-17592 { IBM } # Unicode 4.0, UTF-8 with IBM PUA
1.151 + ibm-17593 { IBM } # Unicode 4.0, UTF-8
1.152 + windows-65001 { WINDOWS* }
1.153 + cp1208
1.154 + x-UTF_8J
1.155 + unicode-1-1-utf-8
1.156 + unicode-2-0-utf-8
1.157 +
1.158 +# The ICU 2.2 UTF-16/32 converters detect and write a BOM.
1.159 +UTF-16 { IANA* MIME* JAVA* } ISO-10646-UCS-2 { IANA }
1.160 + ibm-1204 { IBM* } # UTF-16 with IBM PUA and BOM sensitive
1.161 + ibm-1205 { IBM } # UTF-16 BOM sensitive
1.162 + unicode
1.163 + csUnicode
1.164 + ucs-2
1.165 +# The following Unicode CCSIDs (IBM) are not valid in ICU because they are
1.166 +# considered pure DBCS (exactly 2 bytes) of Unicode,
1.167 +# and they are a subset of Unicode. ICU does not support their encoding structures.
1.168 +# 1400 1401 1402 1410 1414 1415 1446 1447 1448 1449 64770 64771 65520 5496 5497 5498 9592 13688
1.169 +UTF-16BE { IANA* MIME* JAVA* } x-utf-16be { JAVA }
1.170 + UnicodeBigUnmarked { JAVA } # java.io name
1.171 + ibm-1200 { IBM* } # UTF-16 BE with IBM PUA
1.172 + ibm-1201 { IBM } # UTF-16 BE
1.173 + ibm-13488 { IBM } # Unicode 2.0, UTF-16 BE with IBM PUA
1.174 + ibm-13489 { IBM } # Unicode 2.0, UTF-16 BE
1.175 + ibm-17584 { IBM } # Unicode 3.0, UTF-16 BE with IBM PUA
1.176 + ibm-17585 { IBM } # Unicode 3.0, UTF-16 BE
1.177 + ibm-21680 { IBM } # Unicode 4.0, UTF-16 BE with IBM PUA
1.178 + ibm-21681 { IBM } # Unicode 4.0, UTF-16 BE
1.179 + ibm-25776 { IBM } # Unicode 4.1, UTF-16 BE with IBM PUA
1.180 + ibm-25777 { IBM } # Unicode 4.1, UTF-16 BE
1.181 + ibm-29872 { IBM } # Unicode 5.0, UTF-16 BE with IBM PUA
1.182 + ibm-29873 { IBM } # Unicode 5.0, UTF-16 BE
1.183 + ibm-61955 { IBM } # UTF-16BE with Gaidai University (Japan) PUA
1.184 + ibm-61956 { IBM } # UTF-16BE with Microsoft HKSCS-Big 5 PUA
1.185 + windows-1201 { WINDOWS* }
1.186 + cp1200
1.187 + cp1201
1.188 + UTF16_BigEndian
1.189 + # ibm-5297 { IBM } # Unicode 2.0, UTF-16 (BE) (reserved, never used)
1.190 + # iso-10646-ucs-2 { JAVA } # This is ambiguous
1.191 + # ibm-61952 is not a valid CCSID because it's Unicode 1.1
1.192 + # ibm-61953 is not a valid CCSID because it's Unicode 1.0
1.193 +UTF-16LE { IANA* MIME* JAVA* } x-utf-16le { JAVA }
1.194 + UnicodeLittleUnmarked { JAVA } # java.io name
1.195 + ibm-1202 { IBM* } # UTF-16 LE with IBM PUA
1.196 + ibm-1203 { IBM } # UTF-16 LE
1.197 + ibm-13490 { IBM } # Unicode 2.0, UTF-16 LE with IBM PUA
1.198 + ibm-13491 { IBM } # Unicode 2.0, UTF-16 LE
1.199 + ibm-17586 { IBM } # Unicode 3.0, UTF-16 LE with IBM PUA
1.200 + ibm-17587 { IBM } # Unicode 3.0, UTF-16 LE
1.201 + ibm-21682 { IBM } # Unicode 4.0, UTF-16 LE with IBM PUA
1.202 + ibm-21683 { IBM } # Unicode 4.0, UTF-16 LE
1.203 + ibm-25778 { IBM } # Unicode 4.1, UTF-16 LE with IBM PUA
1.204 + ibm-25779 { IBM } # Unicode 4.1, UTF-16 LE
1.205 + ibm-29874 { IBM } # Unicode 5.0, UTF-16 LE with IBM PUA
1.206 + ibm-29875 { IBM } # Unicode 5.0, UTF-16 LE
1.207 + UTF16_LittleEndian
1.208 + windows-1200 { WINDOWS* }
1.209 +
1.210 +UTF-32 { IANA* MIME* } ISO-10646-UCS-4 { IANA }
1.211 + ibm-1236 { IBM* } # UTF-32 with IBM PUA and BOM sensitive
1.212 + ibm-1237 { IBM } # UTF-32 BOM sensitive
1.213 + csUCS4
1.214 + ucs-4
1.215 +UTF-32BE { IANA* } UTF32_BigEndian
1.216 + ibm-1232 { IBM* } # UTF-32 BE with IBM PUA
1.217 + ibm-1233 { IBM } # UTF-32 BE
1.218 + ibm-9424 { IBM } # Unicode 4.1, UTF-32 BE with IBM PUA
1.219 +UTF-32LE { IANA* } UTF32_LittleEndian
1.220 + ibm-1234 { IBM* } # UTF-32 LE, with IBM PUA
1.221 + ibm-1235 { IBM } # UTF-32 LE
1.222 +
1.223 +# ICU-specific names for special uses
1.224 +UTF16_PlatformEndian
1.225 +UTF16_OppositeEndian
1.226 +
1.227 +UTF32_PlatformEndian
1.228 +UTF32_OppositeEndian
1.229 +
1.230 +
1.231 +# Java-specific, non-Unicode-standard UTF-16 variants.
1.232 +# These are in the Java "Basic Encoding Set (contained in lib/rt.jar)".
1.233 +# See the "Supported Encodings" at
1.234 +# http://java.sun.com/javase/6/docs/technotes/guides/intl/encoding.doc.html
1.235 +# or a newer version of this document.
1.236 +#
1.237 +# Aliases marked with { JAVA* } are canonical names for java.io and java.lang APIs.
1.238 +# Aliases marked with { JAVA } are canonical names for the java.nio API.
1.239 +#
1.240 +# "BOM" means the Unicode Byte Order Mark, which is the encoding-scheme-specific
1.241 +# byte sequence for U+FEFF.
1.242 +# "Reverse BOM" means the BOM for the sibling encoding scheme with the
1.243 +# opposite endianness. (LE<->BE)
1.244 +
1.245 +# "Sixteen-bit Unicode (or UCS) Transformation Format, big-endian byte order,
1.246 +# with byte-order mark"
1.247 +#
1.248 +# From Unicode: Writes BOM.
1.249 +# To Unicode: Detects and consumes BOM.
1.250 +# If there is a "reverse BOM", Java throws
1.251 +# MalformedInputException: Incorrect byte-order mark.
1.252 +# In this case, ICU4C sets a U_ILLEGAL_ESCAPE_SEQUENCE UErrorCode value
1.253 +# and a UCNV_ILLEGAL UConverterCallbackReason.
1.254 +UTF-16BE,version=1 UnicodeBig { JAVA* }
1.255 +
1.256 +# "Sixteen-bit Unicode (or UCS) Transformation Format, little-endian byte order,
1.257 +# with byte-order mark"
1.258 +#
1.259 +# From Unicode: Writes BOM.
1.260 +# To Unicode: Detects and consumes BOM.
1.261 +# If there is a "reverse BOM", Java throws
1.262 +# MalformedInputException: Incorrect byte-order mark.
1.263 +# In this case, ICU4C sets a U_ILLEGAL_ESCAPE_SEQUENCE UErrorCode value
1.264 +# and a UCNV_ILLEGAL UConverterCallbackReason.
1.265 +UTF-16LE,version=1 UnicodeLittle { JAVA* } x-UTF-16LE-BOM { JAVA }
1.266 +
1.267 +# This one is not mentioned on the "Supported Encodings" page
1.268 +# but is available in Java.
1.269 +# In Java, this is called "Unicode" but we cannot give it that alias
1.270 +# because the standard UTF-16 converter already has a "unicode" alias.
1.271 +#
1.272 +# From Unicode: Writes BOM.
1.273 +# To Unicode: Detects and consumes BOM.
1.274 +# If there is no BOM, rather than defaulting to BE, Java throws
1.275 +# MalformedInputException: Missing byte-order mark.
1.276 +# In this case, ICU4C sets a U_ILLEGAL_ESCAPE_SEQUENCE UErrorCode value
1.277 +# and a UCNV_ILLEGAL UConverterCallbackReason.
1.278 +UTF-16,version=1
1.279 +
1.280 +# This is the same as standard UTF-16 but always writes a big-endian byte stream,
1.281 +# regardless of the platform endianness, as expected by the Java compatibility tests.
1.282 +# See the java.nio.charset.Charset API documentation at
1.283 +# http://java.sun.com/javase/6/docs/api/java/nio/charset/Charset.html
1.284 +# or a newer version of this document.
1.285 +#
1.286 +# From Unicode: Write BE BOM and BE bytes
1.287 +# To Unicode: Detects and consumes BOM. Defaults to BE.
1.288 +UTF-16,version=2
1.289 +
1.290 +# Note: ICU does not currently support Java-specific, non-Unicode-standard UTF-32 variants.
1.291 +# Presumably, these behave analogously to the UTF-16 variants with similar names.
1.292 +# UTF_32BE_BOM x-UTF-32BE-BOM
1.293 +# UTF_32LE_BOM x-UTF-32LE-BOM
1.294 +
1.295 +# End of Java-specific, non-Unicode-standard UTF variants.
1.296 +
1.297 +
1.298 +# On UTF-7:
1.299 +# RFC 2152 (http://www.imc.org/rfc2152) allows to encode some US-ASCII
1.300 +# characters directly or in base64. Especially, the characters in set O
1.301 +# as defined in the RFC (!"#$%&*;<=>@[]^_`{|}) may be encoded directly
1.302 +# but are not allowed in, e.g., email headers.
1.303 +# By default, the ICU UTF-7 converter encodes set O directly.
1.304 +# By choosing the option "version=1", set O will be escaped instead.
1.305 +# For example:
1.306 +# utf7Converter=ucnv_open("UTF-7,version=1");
1.307 +#
1.308 +# For details about email headers see RFC 2047.
1.309 +UTF-7 { IANA* MIME* WINDOWS } windows-65000 { WINDOWS* }
1.310 + unicode-1-1-utf-7
1.311 + unicode-2-0-utf-7
1.312 +
1.313 +# UTF-EBCDIC doesn't exist in ICU, but the aliases are here for reference.
1.314 +#UTF-EBCDIC ibm-1210 { IBM* } ibm-1211 { IBM }
1.315 +
1.316 +# IMAP-mailbox-name is an ICU-specific name for the encoding of IMAP mailbox names.
1.317 +# It is a substantially modified UTF-7 encoding. See the specification in:
1.318 +#
1.319 +# RFC 2060: INTERNET MESSAGE ACCESS PROTOCOL - VERSION 4rev1
1.320 +# (http://www.ietf.org/rfc/rfc2060.txt)
1.321 +# Section 5.1.3. Mailbox International Naming Convention
1.322 +IMAP-mailbox-name
1.323 +
1.324 +SCSU { IANA* }
1.325 + ibm-1212 { IBM } # SCSU with IBM PUA
1.326 + ibm-1213 { IBM* } # SCSU
1.327 +BOCU-1 { IANA* }
1.328 + csBOCU-1 { IANA }
1.329 + ibm-1214 { IBM } # BOCU-1 with IBM PUA
1.330 + ibm-1215 { IBM* } # BOCU-1
1.331 +
1.332 +# See http://www.unicode.org/unicode/reports/tr26 for this Compatibility Encoding Scheme for UTF-16
1.333 +# The Unicode Consortium does not encourage the use of CESU-8
1.334 +CESU-8 { IANA* } ibm-9400 { IBM* }
1.335 +
1.336 +# Standard iso-8859-1, which does not have the Euro update.
1.337 +# See iso-8859-15 (latin9) for the Euro update
1.338 +ISO-8859-1 { MIME* IANA JAVA* }
1.339 + ibm-819 { IBM* JAVA } # This is not truely ibm-819 because it's missing the fallbacks.
1.340 + IBM819 { IANA }
1.341 + cp819 { IANA JAVA }
1.342 + latin1 { IANA JAVA }
1.343 + 8859_1 { JAVA }
1.344 + csISOLatin1 { IANA JAVA }
1.345 + iso-ir-100 { IANA JAVA }
1.346 + ISO_8859-1:1987 { IANA* JAVA }
1.347 + l1 { IANA JAVA }
1.348 + 819 { JAVA }
1.349 + # windows-28591 { WINDOWS* } # This has odd behavior because it has the Euro update, which isn't correct.
1.350 + # LATIN_1 # Old ICU name
1.351 + # ANSI_X3.110-1983 # This is for a different IANA alias. This isn't iso-8859-1.
1.352 +
1.353 +US-ASCII { MIME* IANA JAVA WINDOWS }
1.354 + ASCII { JAVA* IANA WINDOWS }
1.355 + ANSI_X3.4-1968 { IANA* WINDOWS }
1.356 + ANSI_X3.4-1986 { IANA WINDOWS }
1.357 + ISO_646.irv:1991 { IANA WINDOWS }
1.358 + iso_646.irv:1983 { JAVA }
1.359 + ISO646-US { JAVA IANA WINDOWS }
1.360 + us { IANA }
1.361 + csASCII { IANA WINDOWS }
1.362 + iso-ir-6 { IANA }
1.363 + cp367 { IANA WINDOWS }
1.364 + ascii7 { JAVA }
1.365 + 646 { JAVA }
1.366 + windows-20127 { WINDOWS* }
1.367 + ibm-367 { IBM* } IBM367 { IANA WINDOWS } # This is not truely ibm-367 because it's missing the fallbacks.
1.368 +
1.369 +# GB 18030 is partly algorithmic, using the MBCS converter
1.370 +gb18030 { IANA* } ibm-1392 { IBM* } windows-54936 { WINDOWS* } GB18030 { MIME* }
1.371 +
1.372 +# Table-based interchange codepages
1.373 +
1.374 +# Central Europe
1.375 +ibm-912_P100-1995 { UTR22* }
1.376 + ibm-912 { IBM* JAVA }
1.377 + ISO-8859-2 { MIME* IANA JAVA* WINDOWS }
1.378 + ISO_8859-2:1987 { IANA* WINDOWS JAVA }
1.379 + latin2 { IANA WINDOWS JAVA }
1.380 + csISOLatin2 { IANA WINDOWS JAVA }
1.381 + iso-ir-101 { IANA WINDOWS JAVA }
1.382 + l2 { IANA WINDOWS JAVA }
1.383 + 8859_2 { JAVA }
1.384 + cp912 { JAVA }
1.385 + 912 { JAVA }
1.386 + windows-28592 { WINDOWS* }
1.387 +
1.388 +# Maltese Esperanto
1.389 +ibm-913_P100-2000 { UTR22* }
1.390 + ibm-913 { IBM* JAVA }
1.391 + ISO-8859-3 { MIME* IANA WINDOWS JAVA* }
1.392 + ISO_8859-3:1988 { IANA* WINDOWS JAVA }
1.393 + latin3 { IANA JAVA WINDOWS }
1.394 + csISOLatin3 { IANA WINDOWS }
1.395 + iso-ir-109 { IANA WINDOWS JAVA }
1.396 + l3 { IANA WINDOWS JAVA }
1.397 + 8859_3 { JAVA }
1.398 + cp913 { JAVA }
1.399 + 913 { JAVA }
1.400 + windows-28593 { WINDOWS* }
1.401 +
1.402 +# Baltic
1.403 +ibm-914_P100-1995 { UTR22* }
1.404 + ibm-914 { IBM* JAVA }
1.405 + ISO-8859-4 { MIME* IANA WINDOWS JAVA* }
1.406 + latin4 { IANA WINDOWS JAVA }
1.407 + csISOLatin4 { IANA WINDOWS JAVA }
1.408 + iso-ir-110 { IANA WINDOWS JAVA }
1.409 + ISO_8859-4:1988 { IANA* WINDOWS JAVA }
1.410 + l4 { IANA WINDOWS JAVA }
1.411 + 8859_4 { JAVA }
1.412 + cp914 { JAVA }
1.413 + 914 { JAVA }
1.414 + windows-28594 { WINDOWS* }
1.415 +
1.416 +# Cyrillic
1.417 +ibm-915_P100-1995 { UTR22* }
1.418 + ibm-915 { IBM* JAVA }
1.419 + ISO-8859-5 { MIME* IANA WINDOWS JAVA* }
1.420 + cyrillic { IANA WINDOWS JAVA }
1.421 + csISOLatinCyrillic { IANA WINDOWS JAVA }
1.422 + iso-ir-144 { IANA WINDOWS JAVA }
1.423 + ISO_8859-5:1988 { IANA* WINDOWS JAVA }
1.424 + 8859_5 { JAVA }
1.425 + cp915 { JAVA }
1.426 + 915 { JAVA }
1.427 + windows-28595 { WINDOWS* }
1.428 +
1.429 +glibc-PT154-2.3.3 { UTR22* }
1.430 + PTCP154 { IANA* }
1.431 + csPTCP154
1.432 + PT154
1.433 + CP154
1.434 + Cyrillic-Asian
1.435 +
1.436 +# Arabic
1.437 +# ISO_8859-6-E and ISO_8859-6-I are similar to this charset, but BiDi is done differently
1.438 +# From a narrow mapping point of view, there is no difference.
1.439 +# -E means explicit. -I means implicit.
1.440 +# -E requires the client to handle the ISO 6429 bidirectional controls
1.441 +ibm-1089_P100-1995 { UTR22* }
1.442 + ibm-1089 { IBM* JAVA }
1.443 + ISO-8859-6 { MIME* IANA WINDOWS JAVA* }
1.444 + arabic { IANA WINDOWS JAVA }
1.445 + csISOLatinArabic { IANA WINDOWS JAVA }
1.446 + iso-ir-127 { IANA WINDOWS JAVA }
1.447 + ISO_8859-6:1987 { IANA* WINDOWS JAVA }
1.448 + ECMA-114 { IANA JAVA }
1.449 + ASMO-708 { IANA JAVA }
1.450 + 8859_6 { JAVA }
1.451 + cp1089 { JAVA }
1.452 + 1089 { JAVA }
1.453 + windows-28596 { WINDOWS* }
1.454 + ISO-8859-6-I { IANA MIME } # IANA considers this alias different and BiDi needs to be applied.
1.455 + ISO-8859-6-E { IANA MIME } # IANA considers this alias different and BiDi needs to be applied.
1.456 + x-ISO-8859-6S { JAVA }
1.457 +
1.458 +# ISO Greek (with euro update). This is really ISO_8859-7:2003
1.459 +ibm-9005_X110-2007 { UTR22* }
1.460 + ibm-9005 { IBM* }
1.461 + ISO-8859-7 { MIME* IANA JAVA* WINDOWS }
1.462 + 8859_7 { JAVA }
1.463 + greek { IANA JAVA WINDOWS }
1.464 + greek8 { IANA JAVA WINDOWS }
1.465 + ELOT_928 { IANA JAVA WINDOWS }
1.466 + ECMA-118 { IANA JAVA WINDOWS }
1.467 + csISOLatinGreek { IANA JAVA WINDOWS }
1.468 + iso-ir-126 { IANA JAVA WINDOWS }
1.469 + ISO_8859-7:1987 { IANA* JAVA WINDOWS }
1.470 + windows-28597 { WINDOWS* }
1.471 + sun_eu_greek # For Solaris
1.472 +
1.473 +# ISO Greek (w/o euro update)
1.474 +# JDK 1.5 has these aliases.
1.475 +ibm-813_P100-1995 { UTR22* }
1.476 + ibm-813 { IBM* JAVA* }
1.477 + cp813 { JAVA }
1.478 + 813 { JAVA }
1.479 +
1.480 +# hebrew
1.481 +# ISO_8859-8-E and ISO_8859-8-I are similar to this charset, but BiDi is done differently
1.482 +# From a narrow mapping point of view, there is no difference.
1.483 +# -E means explicit. -I means implicit.
1.484 +# -E requires the client to handle the ISO 6429 bidirectional controls
1.485 +# This matches the official mapping on unicode.org
1.486 +ibm-5012_P100-1999 { UTR22* }
1.487 + ibm-5012 { IBM* }
1.488 + ISO-8859-8 { MIME* IANA WINDOWS JAVA* }
1.489 + hebrew { IANA WINDOWS JAVA }
1.490 + csISOLatinHebrew { IANA WINDOWS JAVA }
1.491 + iso-ir-138 { IANA WINDOWS JAVA }
1.492 + ISO_8859-8:1988 { IANA* WINDOWS JAVA }
1.493 + ISO-8859-8-I { IANA MIME } # IANA and Windows considers this alias different and BiDi needs to be applied.
1.494 + ISO-8859-8-E { IANA MIME } # IANA and Windows considers this alias different and BiDi needs to be applied.
1.495 + 8859_8 { JAVA }
1.496 + windows-28598 { WINDOWS* } # Hebrew (ISO-Visual). A hybrid between ibm-5012 and ibm-916 with extra PUA mappings.
1.497 + hebrew8 # Reflect HP-UX code page update
1.498 +
1.499 +# Unfortunately, the Java aliases are split across ibm-916 and ibm-5012
1.500 +# Also many platforms are a combination between ibm-916 and ibm-5012 behaviors
1.501 +ibm-916_P100-1995 { UTR22* }
1.502 + ibm-916 { IBM* JAVA* }
1.503 + cp916 { JAVA }
1.504 + 916 { JAVA }
1.505 +
1.506 +# Turkish
1.507 +ibm-920_P100-1995 { UTR22* }
1.508 + ibm-920 { IBM* JAVA }
1.509 + ISO-8859-9 { MIME* IANA WINDOWS JAVA* }
1.510 + latin5 { IANA WINDOWS JAVA }
1.511 + csISOLatin5 { IANA JAVA }
1.512 + iso-ir-148 { IANA WINDOWS JAVA }
1.513 + ISO_8859-9:1989 { IANA* WINDOWS }
1.514 + l5 { IANA WINDOWS JAVA }
1.515 + 8859_9 { JAVA }
1.516 + cp920 { JAVA }
1.517 + 920 { JAVA }
1.518 + windows-28599 { WINDOWS* }
1.519 + ECMA-128 # IANA doesn't have this alias 6/24/2002
1.520 + turkish8 # Reflect HP-UX codepage update 8/1/2008
1.521 + turkish # Reflect HP-UX codepage update 8/1/2008
1.522 +
1.523 +# Nordic languages
1.524 +iso-8859_10-1998 { UTR22* } ISO-8859-10 { MIME* IANA* }
1.525 + iso-ir-157 { IANA }
1.526 + l6 { IANA }
1.527 + ISO_8859-10:1992 { IANA }
1.528 + csISOLatin6 { IANA }
1.529 + latin6 { IANA }
1.530 +
1.531 +# Thai
1.532 +# Be warned. There several iso-8859-11 codepage variants, and they are all incompatible.
1.533 +# ISO-8859-11 is a superset of TIS-620. The difference is that ISO-8859-11 contains the C1 control codes.
1.534 +iso-8859_11-2001 { UTR22* } ISO-8859-11
1.535 + thai8 # HP-UX alias. HP-UX says TIS-620, but it's closer to ISO-8859-11.
1.536 + x-iso-8859-11 { JAVA* }
1.537 +
1.538 +# iso-8859-13, PC Baltic (w/o euro update)
1.539 +ibm-921_P100-1995 { UTR22* }
1.540 + ibm-921 { IBM* }
1.541 + ISO-8859-13 { IANA* MIME* JAVA* }
1.542 + 8859_13 { JAVA }
1.543 + windows-28603 { WINDOWS* }
1.544 + cp921
1.545 + 921
1.546 + x-IBM921 { JAVA }
1.547 +
1.548 +# Celtic
1.549 +iso-8859_14-1998 { UTR22* } ISO-8859-14 { IANA* }
1.550 + iso-ir-199 { IANA }
1.551 + ISO_8859-14:1998 { IANA }
1.552 + latin8 { IANA }
1.553 + iso-celtic { IANA }
1.554 + l8 { IANA }
1.555 +
1.556 +# Latin 9
1.557 +ibm-923_P100-1998 { UTR22* }
1.558 + ibm-923 { IBM* JAVA }
1.559 + ISO-8859-15 { IANA* MIME* WINDOWS JAVA* }
1.560 + Latin-9 { IANA WINDOWS }
1.561 + l9 { WINDOWS }
1.562 + 8859_15 { JAVA }
1.563 + latin0 { JAVA }
1.564 + csisolatin0 { JAVA }
1.565 + csisolatin9 { JAVA }
1.566 + iso8859_15_fdis { JAVA }
1.567 + cp923 { JAVA }
1.568 + 923 { JAVA }
1.569 + windows-28605 { WINDOWS* }
1.570 +
1.571 +# CJK encodings
1.572 +
1.573 +ibm-942_P12A-1999 { UTR22* } # ibm-942_P120 is a rarely used alternate mapping (sjis78 is already old)
1.574 + ibm-942 { IBM* }
1.575 + ibm-932 { IBM }
1.576 + cp932
1.577 + shift_jis78
1.578 + sjis78
1.579 + ibm-942_VSUB_VPUA
1.580 + ibm-932_VSUB_VPUA
1.581 + x-IBM942 { JAVA* }
1.582 + x-IBM942C { JAVA }
1.583 + # Is this "JIS_C6226-1978"?
1.584 +
1.585 +# ibm-943_P15A-2003 differs from windows-932-2000 only in a few roundtrip mappings:
1.586 +# - the usual IBM PC control code rotation (1A-1C-7F)
1.587 +# - the Windows table has roundtrips for bytes 80, A0, and FD-FF to U+0080 and PUA
1.588 +ibm-943_P15A-2003 { UTR22* }
1.589 + ibm-943 # Leave untagged because this isn't the default
1.590 + Shift_JIS { IANA* MIME* WINDOWS JAVA }
1.591 + MS_Kanji { IANA WINDOWS JAVA }
1.592 + csShiftJIS { IANA WINDOWS JAVA }
1.593 + windows-31j { IANA JAVA } # A further extension of Shift_JIS to include NEC special characters (Row 13)
1.594 + csWindows31J { IANA WINDOWS JAVA } # A further extension of Shift_JIS to include NEC special characters (Row 13)
1.595 + x-sjis { WINDOWS JAVA }
1.596 + x-ms-cp932 { WINDOWS }
1.597 + cp932 { WINDOWS }
1.598 + windows-932 { WINDOWS* }
1.599 + cp943c { JAVA* } # This is slightly different, but the backslash mapping is the same.
1.600 + IBM-943C #{ AIX* } # Add this tag once AIX aliases becomes available
1.601 + ms932
1.602 + pck # Probably SOLARIS
1.603 + sjis # This might be for ibm-1351
1.604 + ibm-943_VSUB_VPUA
1.605 + x-MS932_0213 { JAVA }
1.606 + x-JISAutoDetect { JAVA }
1.607 + # cp943 # This isn't Windows, and no one else uses it.
1.608 + # IANA says that Windows-31J is an extension to csshiftjis ibm-932
1.609 +ibm-943_P130-1999 { UTR22* }
1.610 + ibm-943 { IBM* JAVA }
1.611 + Shift_JIS # Leave untagged because this isn't the default
1.612 + cp943 { JAVA* } # This is slightly different, but the backslash mapping is the same.
1.613 + 943 { JAVA }
1.614 + ibm-943_VASCII_VSUB_VPUA
1.615 + x-IBM943 { JAVA }
1.616 + # japanese. Unicode name is \u30b7\u30d5\u30c8\u7b26\u53f7\u5316\u8868\u73fe
1.617 +ibm-33722_P12A_P12A-2009_U2 { UTR22* }
1.618 + ibm-33722 # Leave untagged because this isn't the default
1.619 + ibm-5050 # Leave untagged because this isn't the default, and yes this alias is correct
1.620 + ibm-33722_VPUA
1.621 + IBM-eucJP
1.622 +windows-51932-2006 { UTR22* }
1.623 + windows-51932 { WINDOWS* }
1.624 + CP51932 { IANA* }
1.625 + csCP51932
1.626 +ibm-33722_P120-1999 { UTR22* } # Japan EUC with \ <-> Yen mapping
1.627 + ibm-33722 { IBM* JAVA }
1.628 + ibm-5050 { IBM } # Yes this is correct
1.629 + cp33722 { JAVA* }
1.630 + 33722 { JAVA }
1.631 + ibm-33722_VASCII_VPUA
1.632 + x-IBM33722 { JAVA }
1.633 + x-IBM33722A { JAVA }
1.634 + x-IBM33722C { JAVA }
1.635 +# ibm-954 seems to be almost a superset of ibm-33722 and ibm-1350
1.636 +# ibm-1350 seems to be almost a superset of ibm-33722
1.637 +# ibm-954 contains more PUA characters than the others.
1.638 +ibm-954_P101-2007 { UTR22* }
1.639 + ibm-954 { IBM* }
1.640 + x-IBM954 { JAVA* }
1.641 + x-IBM954C { JAVA }
1.642 + # eucJP # This is closest to Solaris EUC-JP.
1.643 +euc-jp-2007 { UTR22* }
1.644 + EUC-JP { MIME* IANA JAVA* WINDOWS* }
1.645 + Extended_UNIX_Code_Packed_Format_for_Japanese { IANA* JAVA WINDOWS }
1.646 + csEUCPkdFmtJapanese { IANA JAVA WINDOWS }
1.647 + X-EUC-JP { MIME JAVA WINDOWS } # Japan EUC. x-euc-jp is a MIME name
1.648 + eucjis {JAVA}
1.649 + ujis # Linux sometimes uses this name. This is an unfortunate generic and rarely used name. Its use is discouraged.
1.650 +
1.651 +aix-IBM_udcJP-4.3.6 { UTR22* }
1.652 + x-IBM-udcJP { JAVA* }
1.653 +
1.654 +java-euc_jp_linux-1.6_P { UTR22* }
1.655 + euc-jp-linux
1.656 + x-EUC_JP_LINUX { JAVA* }
1.657 +
1.658 +java-sjis_0213-1.6_P { UTR22* }
1.659 + x-SJIS_0213 { JAVA* }
1.660 +
1.661 +# Here are various interpretations and extentions of Big5
1.662 +ibm-1373_P100-2002 { UTR22* } # IBM's interpretation of Windows' Taiwan Big-5 without HKSCS extensions
1.663 + ibm-1373 { IBM* }
1.664 + windows-950 # Alternate mapping. Leave untagged. This is the IBM interpretation of a Windows codepage.
1.665 +windows-950-2000 { UTR22* }
1.666 + Big5 { IANA* MIME* JAVA* WINDOWS }
1.667 + csBig5 { IANA WINDOWS }
1.668 + windows-950 { WINDOWS* }
1.669 + x-windows-950 { JAVA }
1.670 + x-big5
1.671 + ms950
1.672 +ibm-950_P110-1999 { UTR22* } # Taiwan Big-5 (w/o euro update)
1.673 + ibm-950 { IBM* JAVA }
1.674 + cp950 { JAVA* }
1.675 + 950 { JAVA }
1.676 + x-IBM950 { JAVA }
1.677 +ibm-1375_P100-2007 { UTR22* } # Big5-HKSCS-2004 with Unicode 3.1 mappings. This uses supplementary characters.
1.678 + ibm-1375 { IBM* }
1.679 + Big5-HKSCS { IANA* JAVA* }
1.680 + big5hk { JAVA }
1.681 + HKSCS-BIG5 # From http://www.openi18n.org/localenameguide/
1.682 +ibm-5471_P100-2006 { UTR22* } # Big5-HKSCS-2001 with Unicode 3.0 mappings. This uses many PUA characters.
1.683 + ibm-5471 { IBM* }
1.684 + Big5-HKSCS
1.685 + MS950_HKSCS { JAVA* }
1.686 + hkbig5 # from HP-UX 11i, which can't handle supplementary characters.
1.687 + big5-hkscs:unicode3.0
1.688 + x-MS950-HKSCS { JAVA }
1.689 + # windows-950 # Windows-950 can be w/ or w/o HKSCS extensions. By default it's not.
1.690 + # windows-950_hkscs
1.691 +solaris-zh_TW_big5-2.7 { UTR22* }
1.692 + Big5_Solaris { JAVA* }
1.693 + x-Big5-Solaris { JAVA }
1.694 +# GBK
1.695 +ibm-1386_P100-2001 { UTR22* }
1.696 + ibm-1386 { IBM* }
1.697 + cp1386
1.698 + windows-936 # Alternate mapping. Leave untagged. This is the IBM interpretation of a Windows codepage.
1.699 + ibm-1386_VSUB_VPUA
1.700 +windows-936-2000 { UTR22* }
1.701 + GBK { IANA* WINDOWS JAVA* }
1.702 + CP936 { IANA JAVA }
1.703 + MS936 { IANA } # In JDK 1.5, this goes to x-mswin-936. This is an IANA name split.
1.704 + windows-936 { IANA WINDOWS* JAVA }
1.705 +
1.706 +# Java has two different tables for ibm-1383 and gb2312. We pick closest set for tagging.
1.707 +ibm-1383_P110-1999 { UTR22* } # China EUC.
1.708 + ibm-1383 { IBM* JAVA }
1.709 + GB2312 { IANA* MIME* }
1.710 + csGB2312 { IANA }
1.711 + cp1383 { JAVA* }
1.712 + 1383 { JAVA }
1.713 + EUC-CN # According to other platforms, windows-20936 looks more like euc-cn. x-euc-cn is also a MIME name
1.714 + ibm-eucCN
1.715 + hp15CN # From HP-UX?
1.716 + ibm-1383_VPUA
1.717 + # gb # This is not an IANA name. gb in IANA means Great Britain.
1.718 +
1.719 +ibm-5478_P100-1995 { UTR22* } ibm-5478 { IBM* } # This gb_2312_80 DBCS mapping is needed by iso-2022.
1.720 + GB_2312-80 { IANA* } # Windows maps this alias incorrectly
1.721 + chinese { IANA }
1.722 + iso-ir-58 { IANA }
1.723 + csISO58GB231280 { IANA }
1.724 + gb2312-1980
1.725 + GB2312.1980-0 # From X11R6
1.726 +
1.727 +ibm-964_P110-1999 { UTR22* } # Taiwan EUC. x-euc-tw is a MIME name
1.728 + ibm-964 { IBM* JAVA }
1.729 + EUC-TW
1.730 + ibm-eucTW
1.731 + cns11643
1.732 + cp964 { JAVA* }
1.733 + 964 { JAVA }
1.734 + ibm-964_VPUA
1.735 + x-IBM964 { JAVA }
1.736 +
1.737 +# ISO-2022 needs one, and other people may need others.
1.738 +ibm-949_P110-1999 { UTR22* }
1.739 + ibm-949 { IBM* JAVA }
1.740 + cp949 { JAVA* }
1.741 + 949 { JAVA }
1.742 + ibm-949_VASCII_VSUB_VPUA
1.743 + x-IBM949 { JAVA }
1.744 +ibm-949_P11A-1999 { UTR22* }
1.745 + ibm-949 # Leave untagged because this isn't the default
1.746 + cp949c { JAVA* }
1.747 + ibm-949_VSUB_VPUA
1.748 + x-IBM949C { JAVA }
1.749 + IBM-949C { JAVA }
1.750 +
1.751 +# Korean EUC.
1.752 +#
1.753 +# <quote from="Jungshik Shin">
1.754 +# EUC-KR = KS X 1003/ISO 646-KR or ISO 646-IRV/US-ASCII in GL and KS X 1001:1998 (formerly KS C 5601-1987) in GR.
1.755 +#
1.756 +# Although widely spread on MS Windows, using
1.757 +# KS C 5601 or related names to denote EUC-KR or
1.758 +# windows-949 is very much misleading. KS C 5601-1987
1.759 +# is NOT suitable as a designation for MIME charset
1.760 +# and MBCS. It's just the name of a 94 x 94 Korean
1.761 +# coded character set standard which can be invoked
1.762 +# on either GL (with MSB reset) or GR (with MSB set).
1.763 +# Note that JOHAB (windows-1361) specified in
1.764 +# KS X 1001:1998 annex 3 (KS C 5601-1992 annex 3)
1.765 +# is a _seprate_ MBCS with a _completely different_
1.766 +# mapping.
1.767 +# </quote>
1.768 +#
1.769 +# The following aliases tries to mirror the poor state of alias recognition
1.770 +# on these platforms.
1.771 +#
1.772 +# ibm-970 is almost a subset of ibm-1363.
1.773 +# Java, Solaris and AIX use euc-kr to also mean ksc5601.
1.774 +# Java has both ibm-970 and EUC-KR as separate converters.
1.775 +ibm-970_P110_P110-2006_U2 { UTR22* }
1.776 + ibm-970 { IBM* JAVA }
1.777 + EUC-KR { IANA* MIME* WINDOWS JAVA }
1.778 + KS_C_5601-1987 { JAVA }
1.779 + windows-51949 { WINDOWS* }
1.780 + csEUCKR { IANA WINDOWS } # x-euc-kr is also a MIME name
1.781 + ibm-eucKR { JAVA }
1.782 + KSC_5601 { JAVA } # Needed by iso-2022
1.783 + 5601 { JAVA }
1.784 + cp970 { JAVA* }
1.785 + 970 { JAVA }
1.786 + ibm-970_VPUA
1.787 + x-IBM970 { JAVA }
1.788 +
1.789 +# ibm-971 is almost the set of DBCS mappings of ibm-970
1.790 +ibm-971_P100-1995 ibm-971 { IBM* } ibm-971_VPUA x-IBM971 { JAVA* }
1.791 +
1.792 +# Java, Solaris and AIX use euc-kr to also mean ksc5601, and _sometimes_ for Windows too.
1.793 +# ibm-1363 is almost a superset of ibm-970.
1.794 +ibm-1363_P11B-1998 { UTR22* }
1.795 + ibm-1363 # Leave untagged because this isn't the default
1.796 + KS_C_5601-1987 { IANA* }
1.797 + KS_C_5601-1989 { IANA }
1.798 + KSC_5601 { IANA }
1.799 + csKSC56011987 { IANA }
1.800 + korean { IANA }
1.801 + iso-ir-149 { IANA }
1.802 + cp1363 { MIME* }
1.803 + 5601
1.804 + ksc
1.805 + windows-949 # Alternate mapping. Leave untagged. This is the IBM interpretation of a Windows codepage.
1.806 + ibm-1363_VSUB_VPUA
1.807 + x-IBM1363C { JAVA* }
1.808 + # ks_x_1001:1992
1.809 + # ksc5601-1992
1.810 +
1.811 +ibm-1363_P110-1997 { UTR22* } # Korean KSC MBCS with \ <-> Won mapping
1.812 + ibm-1363 { IBM* }
1.813 + ibm-1363_VASCII_VSUB_VPUA
1.814 + x-IBM1363 { JAVA* }
1.815 +
1.816 +windows-949-2000 { UTR22* }
1.817 + windows-949 { JAVA* WINDOWS* }
1.818 + KS_C_5601-1987 { WINDOWS }
1.819 + KS_C_5601-1989 { WINDOWS }
1.820 + KSC_5601 { MIME* WINDOWS } # Needed by iso-2022
1.821 + csKSC56011987 { WINDOWS }
1.822 + korean { WINDOWS }
1.823 + iso-ir-149 { WINDOWS }
1.824 + ms949 { JAVA }
1.825 + x-KSC5601 { JAVA }
1.826 +
1.827 +windows-1361-2000 { UTR22* }
1.828 + ksc5601_1992
1.829 + ms1361
1.830 + johab
1.831 + x-Johab { JAVA* }
1.832 +
1.833 +windows-874-2000 { UTR22* } # Thai (w/ euro update)
1.834 + TIS-620 { WINDOWS }
1.835 + windows-874 { JAVA* WINDOWS* }
1.836 + MS874 { JAVA }
1.837 + x-windows-874 { JAVA }
1.838 + # iso-8859-11 { WINDOWS } # iso-8859-11 is similar to TIS-620. ibm-13162 is a closer match.
1.839 +
1.840 +ibm-874_P100-1995 { UTR22* } # Thai PC (w/o euro update).
1.841 + ibm-874 { IBM* JAVA }
1.842 + ibm-9066 { IBM } # Yes ibm-874 == ibm-9066. ibm-1161 has the euro update.
1.843 + cp874 { JAVA* }
1.844 + TIS-620 { IANA* JAVA } # This is actually separate from ibm-874, which is similar to this table
1.845 + tis620.2533 { JAVA } # This is actually separate from ibm-874, which is similar to this table
1.846 + eucTH # eucTH is an unusual alias from Solaris. eucTH has fewer mappings than TIS620
1.847 + x-IBM874 { JAVA }
1.848 +
1.849 +ibm-1162_P100-1999 { UTR22* } # Thai (w/ euro update)
1.850 + ibm-1162 { IBM* }
1.851 +
1.852 +windows-864-2000 { UTR22* }
1.853 + ibm-864s
1.854 + cp864s
1.855 + x-IBM864S { JAVA* }
1.856 +
1.857 +# Platform codepages
1.858 +# If Java supports the IBM prefix, it should also support the ibm- prefix too.
1.859 +ibm-437_P100-1995 { UTR22* } ibm-437 { IBM* } IBM437 { IANA* WINDOWS JAVA } cp437 { IANA WINDOWS JAVA* } 437 { IANA WINDOWS JAVA } csPC8CodePage437 { IANA JAVA } windows-437 { WINDOWS* } # PC US
1.860 +ibm-720_P100-1997 { UTR22* } ibm-720 { IBM* } windows-720 { WINDOWS* } DOS-720 { WINDOWS } x-IBM720 { JAVA* } # PC Arabic
1.861 +ibm-737_P100-1997 { UTR22* } ibm-737 { IBM* } IBM737 { WINDOWS JAVA } cp737 { JAVA* } windows-737 { WINDOWS* } 737 { JAVA } x-IBM737 { JAVA } # PC Greek
1.862 +ibm-775_P100-1996 { UTR22* } ibm-775 { IBM* } IBM775 { IANA* WINDOWS JAVA } cp775 { IANA WINDOWS JAVA* } csPC775Baltic { IANA } windows-775 { WINDOWS* } 775 { JAVA } # PC Baltic
1.863 +ibm-850_P100-1995 { UTR22* } ibm-850 { IBM* } IBM850 { IANA* MIME* WINDOWS JAVA } cp850 { IANA MIME WINDOWS JAVA* } 850 { IANA JAVA } csPC850Multilingual { IANA JAVA } windows-850 { WINDOWS* } # PC latin1
1.864 +ibm-851_P100-1995 { UTR22* } ibm-851 { IBM* } IBM851 { IANA* } cp851 { IANA MIME* } 851 { IANA } csPC851 { IANA } # PC DOS Greek (w/o euro)
1.865 +ibm-852_P100-1995 { UTR22* } ibm-852 { IBM* } IBM852 { IANA* WINDOWS JAVA } cp852 { IANA WINDOWS JAVA* } 852 { IANA WINDOWS JAVA } csPCp852 { IANA JAVA } windows-852 { WINDOWS* } # PC latin2 (w/o euro update)
1.866 +ibm-855_P100-1995 { UTR22* } ibm-855 { IBM* } IBM855 { IANA* JAVA } cp855 { IANA JAVA* } 855 { IANA } csIBM855 { IANA } csPCp855 { JAVA } windows-855 { WINDOWS* } # PC cyrillic (w/o euro update)
1.867 +ibm-856_P100-1995 { UTR22* } ibm-856 { IBM* } IBM856 { JAVA } cp856 { JAVA* } 856 { JAVA } x-IBM856 { JAVA } # PC Hebrew implicit order
1.868 +ibm-857_P100-1995 { UTR22* } ibm-857 { IBM* } IBM857 { IANA* MIME* WINDOWS JAVA } cp857 { IANA MIME JAVA* } 857 { IANA JAVA } csIBM857 { IANA JAVA } windows-857 { WINDOWS* } # PC Latin 5 (w/o euro update)
1.869 +ibm-858_P100-1997 { UTR22* } ibm-858 { IBM* } IBM00858 { IANA* MIME* JAVA } CCSID00858 { IANA JAVA } CP00858 { IANA JAVA } PC-Multilingual-850+euro { IANA } cp858 { MIME JAVA* } windows-858 { WINDOWS* } # PC latin1 with Euro
1.870 +ibm-860_P100-1995 { UTR22* } ibm-860 { IBM* } IBM860 { IANA* MIME* JAVA } cp860 { IANA MIME JAVA* } 860 { IANA JAVA } csIBM860 { IANA JAVA } # PC Portugal
1.871 +ibm-861_P100-1995 { UTR22* } ibm-861 { IBM* } IBM861 { IANA* MIME* WINDOWS JAVA } cp861 { IANA MIME JAVA* } 861 { IANA JAVA } cp-is { IANA JAVA } csIBM861 { IANA JAVA } windows-861 { WINDOWS* } # PC Iceland
1.872 +ibm-862_P100-1995 { UTR22* } ibm-862 { IBM* } IBM862 { IANA* MIME* JAVA } cp862 { IANA MIME JAVA* } 862 { IANA JAVA } csPC862LatinHebrew { IANA JAVA } DOS-862 { WINDOWS } windows-862 { WINDOWS* } # PC Hebrew visual order (w/o euro update)
1.873 +ibm-863_P100-1995 { UTR22* } ibm-863 { IBM* } IBM863 { IANA* MIME* JAVA } cp863 { IANA MIME JAVA* } 863 { IANA JAVA } csIBM863 { IANA JAVA } # PC Canadian French
1.874 +ibm-864_X110-1999 { UTR22* } ibm-864 { IBM* } IBM864 { IANA* MIME* JAVA } cp864 { IANA MIME JAVA* } csIBM864 { IANA JAVA } # PC Arabic (w/o euro update)
1.875 +ibm-865_P100-1995 { UTR22* } ibm-865 { IBM* } IBM865 { IANA* MIME* JAVA } cp865 { IANA MIME JAVA* } 865 { IANA JAVA } csIBM865 { IANA JAVA } # PC Nordic
1.876 +ibm-866_P100-1995 { UTR22* } ibm-866 { IBM* } IBM866 { IANA* MIME* JAVA } cp866 { IANA MIME WINDOWS JAVA* } 866 { IANA JAVA } csIBM866 { IANA JAVA } windows-866 { WINDOWS* } # PC Russian (w/o euro update)
1.877 +ibm-867_P100-1998 { UTR22* } ibm-867 { IBM* } x-IBM867 { JAVA* } # PC Hebrew (w/ euro update) Updated version of ibm-862
1.878 +ibm-868_P100-1995 { UTR22* } ibm-868 { IBM* } IBM868 { IANA* MIME* JAVA } CP868 { IANA MIME JAVA* } 868 { JAVA } csIBM868 { IANA } cp-ar { IANA } # PC Urdu
1.879 +ibm-869_P100-1995 { UTR22* } ibm-869 { IBM* } IBM869 { IANA* MIME* WINDOWS JAVA } cp869 { IANA MIME JAVA* } 869 { IANA JAVA } cp-gr { IANA JAVA } csIBM869 { IANA JAVA } windows-869 { WINDOWS* } # PC Greek (w/o euro update)
1.880 +ibm-878_P100-1996 { UTR22* } ibm-878 { IBM* } KOI8-R { IANA* MIME* WINDOWS JAVA* } koi8 { WINDOWS JAVA } csKOI8R { IANA WINDOWS JAVA } windows-20866 { WINDOWS* } cp878 # Russian internet
1.881 +ibm-901_P100-1999 { UTR22* } ibm-901 { IBM* } # PC Baltic (w/ euro update), update of ibm-921
1.882 +ibm-902_P100-1999 { UTR22* } ibm-902 { IBM* } # PC Estonian (w/ euro update), update of ibm-922
1.883 +ibm-922_P100-1999 { UTR22* } ibm-922 { IBM* } IBM922 { JAVA } cp922 { JAVA* } 922 { JAVA } x-IBM922 { JAVA } # PC Estonian (w/o euro update)
1.884 +ibm-1168_P100-2002 { UTR22* } ibm-1168 { IBM* } KOI8-U { IANA* WINDOWS } windows-21866 { WINDOWS* } # Ukrainian KOI8. koi8-ru != KOI8-U and Microsoft is wrong for aliasing them as the same.
1.885 +ibm-4909_P100-1999 { UTR22* } ibm-4909 { IBM* } # ISO Greek (w/ euro update), update of ibm-813
1.886 +
1.887 +# The cp aliases in this section aren't really windows aliases, but it was used by ICU for Windows.
1.888 +# cp is usually used to denote IBM in Java, and that is why we don't do that anymore.
1.889 +# The windows-* aliases mean windows codepages.
1.890 +ibm-5346_P100-1998 { UTR22* } ibm-5346 { IBM* } windows-1250 { IANA* JAVA* WINDOWS* } cp1250 { WINDOWS JAVA } # Windows Latin2 (w/ euro update)
1.891 +ibm-5347_P100-1998 { UTR22* } ibm-5347 { IBM* } windows-1251 { IANA* JAVA* WINDOWS* } cp1251 { WINDOWS JAVA } ANSI1251 # Windows Cyrillic (w/ euro update). ANSI1251 is from Solaris
1.892 +ibm-5348_P100-1997 { UTR22* } ibm-5348 { IBM* } windows-1252 { IANA* JAVA* WINDOWS* } cp1252 { JAVA } # Windows Latin1 (w/ euro update)
1.893 +ibm-5349_P100-1998 { UTR22* } ibm-5349 { IBM* } windows-1253 { IANA* JAVA* WINDOWS* } cp1253 { JAVA } # Windows Greek (w/ euro update)
1.894 +ibm-5350_P100-1998 { UTR22* } ibm-5350 { IBM* } windows-1254 { IANA* JAVA* WINDOWS* } cp1254 { JAVA } # Windows Turkish (w/ euro update)
1.895 +ibm-9447_P100-2002 { UTR22* } ibm-9447 { IBM* } windows-1255 { IANA* JAVA* WINDOWS* } cp1255 { JAVA } # Windows Hebrew (w/ euro update)
1.896 +ibm-9448_X100-2005 { UTR22* } ibm-9448 { IBM* } windows-1256 { IANA* JAVA* WINDOWS* } cp1256 { WINDOWS JAVA } x-windows-1256S { JAVA } # Windows Arabic (w/ euro update)
1.897 +ibm-9449_P100-2002 { UTR22* } ibm-9449 { IBM* } windows-1257 { IANA* JAVA* WINDOWS* } cp1257 { JAVA } # Windows Baltic (w/ euro update)
1.898 +ibm-5354_P100-1998 { UTR22* } ibm-5354 { IBM* } windows-1258 { IANA* JAVA* WINDOWS* } cp1258 { JAVA } # Windows Vietnamese (w/ euro update)
1.899 +
1.900 +# These tables are out of date, and most don't have the Euro
1.901 +# Leave the windows- variants untagged. They are alternate tables of the newer ones above.
1.902 +ibm-1250_P100-1995 { UTR22* } ibm-1250 { IBM* } windows-1250 # Old Windows Latin2 (w/o euro update)
1.903 +ibm-1251_P100-1995 { UTR22* } ibm-1251 { IBM* } windows-1251 # Old Windows Cyrillic (w/o euro update)
1.904 +ibm-1252_P100-2000 { UTR22* } ibm-1252 { IBM* } windows-1252 # Old Windows Latin 1 without Euro
1.905 +ibm-1253_P100-1995 { UTR22* } ibm-1253 { IBM* } windows-1253 # Old Windows Greek (w/o euro update)
1.906 +ibm-1254_P100-1995 { UTR22* } ibm-1254 { IBM* } windows-1254 # Old Windows Turkish (w/o euro update)
1.907 +ibm-1255_P100-1995 { UTR22* } ibm-1255 { IBM* } # Very old Windows Hebrew (w/o euro update)
1.908 +ibm-5351_P100-1998 { UTR22* } ibm-5351 { IBM* } windows-1255 # Old Windows Hebrew (w/ euro update)
1.909 +ibm-1256_P110-1997 { UTR22* } ibm-1256 { IBM* } # Old Windows Arabic (w/o euro update)
1.910 +ibm-5352_P100-1998 { UTR22* } ibm-5352 { IBM* } windows-1256 # Somewhat old Windows Arabic (w/ euro update)
1.911 +ibm-1257_P100-1995 { UTR22* } ibm-1257 { IBM* } # Old Windows Baltic (w/o euro update)
1.912 +ibm-5353_P100-1998 { UTR22* } ibm-5353 { IBM* } windows-1257 # Somewhat old Windows Baltic (w/ euro update)
1.913 +ibm-1258_P100-1997 { UTR22* } ibm-1258 { IBM* } windows-1258 # Old Windows Vietnamese (w/o euro update)
1.914 +
1.915 +macos-0_2-10.2 { UTR22* } macintosh { IANA* MIME* WINDOWS } mac { IANA } csMacintosh { IANA } windows-10000 { WINDOWS* } macroman { JAVA } x-macroman { JAVA* } # Apple latin 1
1.916 +macos-6_2-10.4 { UTR22* } x-mac-greek { MIME* WINDOWS } windows-10006 { WINDOWS* } macgr x-MacGreek { JAVA* } # Apple Greek
1.917 +macos-7_3-10.2 { UTR22* } x-mac-cyrillic { MIME* WINDOWS } windows-10007 { WINDOWS* } mac-cyrillic maccy x-MacCyrillic { JAVA } x-MacUkraine { JAVA* } # Apple Cyrillic
1.918 +macos-21-10.5 { UTR22* } x-mac-thai { MIME* } x-MacThai { JAVA* } MacThai { JAVA }
1.919 +macos-29-10.2 { UTR22* } x-mac-centraleurroman { MIME* } windows-10029 { WINDOWS* } x-mac-ce { WINDOWS } macce maccentraleurope x-MacCentralEurope { JAVA* } # Apple Central Europe
1.920 +macos-33-10.5 { UTR22* } x-mac-symbol { MIME* } x-MacSymbol { JAVA* } MacSymbol { JAVA }
1.921 +macos-34-10.2 { UTR22* } x-mac-dingbat { MIME* } x-MacDingbat { JAVA* } MacDingbat { JAVA }
1.922 +macos-35-10.2 { UTR22* } x-mac-turkish { MIME* WINDOWS } windows-10081 { WINDOWS* } mactr x-MacTurkish { JAVA* } # Apple Turkish
1.923 +macos-36_2-10.2 { UTR22* } x-mac-croatian { MIME* } x-MacCroatian { JAVA* } MacCroatian { JAVA }
1.924 +macos-37_5-10.2 { UTR22* } x-mac-iceland { MIME* } x-MacIceland { JAVA* } MacIceland { JAVA }
1.925 +macos-38_2-10.2 { UTR22* } x-mac-romania { MIME* } x-MacRomania { JAVA* } MacRomania { JAVA }
1.926 +macos-518-10.2 { UTR22* } x-mac-arabic { MIME* } x-MacArabic { JAVA* } MacArabic { JAVA }
1.927 +macos-1285-10.2 { UTR22* } x-mac-hebrew { MIME* } x-MacHebrew { JAVA* } MacHebrew { JAVA }
1.928 +
1.929 +ibm-1051_P100-1995 { UTR22* } ibm-1051 { IBM* } hp-roman8 { IANA* } roman8 { IANA } r8 { IANA } csHPRoman8 { IANA } x-roman8 { JAVA* } # HP Latin1
1.930 +ibm-1276_P100-1995 { UTR22* } ibm-1276 { IBM* } Adobe-Standard-Encoding { IANA* } csAdobeStandardEncoding { IANA } # Different from ISO-Unicode-IBM-1276 (GCSGID: 1276)
1.931 +
1.932 +ibm-1006_P100-1995 { UTR22* } ibm-1006 { IBM* } IBM1006 { JAVA } cp1006 { JAVA* } 1006 { JAVA } x-IBM1006 { JAVA } # Urdu
1.933 +ibm-1098_P100-1995 { UTR22* } ibm-1098 { IBM* } IBM1098 { JAVA } cp1098 { JAVA* } 1098 { JAVA } x-IBM1098 { JAVA } # PC Farsi
1.934 +ibm-1124_P100-1996 { UTR22* } ibm-1124 { IBM* JAVA } cp1124 { JAVA* } 1124 { JAVA } x-IBM1124 { JAVA } # ISO Cyrillic Ukraine
1.935 +ibm-1125_P100-1997 { UTR22* } ibm-1125 { IBM* } cp1125 # Cyrillic Ukraine PC
1.936 +ibm-1129_P100-1997 { UTR22* } ibm-1129 { IBM* } # ISO Vietnamese
1.937 +ibm-1131_P100-1997 { UTR22* } ibm-1131 { IBM* } cp1131 # Cyrillic Belarus PC
1.938 +ibm-1133_P100-1997 { UTR22* } ibm-1133 { IBM* } # ISO Lao
1.939 +
1.940 +
1.941 +# Partially algorithmic converters
1.942 +
1.943 +# [U_ENABLE_GENERIC_ISO_2022]
1.944 +# The _generic_ ISO-2022 converter is disabled starting 2003-dec-03 (ICU 2.8).
1.945 +# For details see the icu mailing list from 2003-dec-01 and the ucnv2022.c file.
1.946 +# Language-specific variants of ISO-2022 continue to be available as listed below.
1.947 +# ISO_2022 ISO-2022
1.948 +
1.949 +ISO_2022,locale=ja,version=0 ISO-2022-JP { IANA* MIME* JAVA* } csISO2022JP { IANA JAVA } x-windows-iso2022jp { JAVA } x-windows-50220 { JAVA }
1.950 +ISO_2022,locale=ja,version=1 ISO-2022-JP-1 { MIME* } JIS_Encoding { IANA* } csJISEncoding { IANA } ibm-5054 { IBM* } JIS x-windows-50221 { JAVA* }
1.951 +ISO_2022,locale=ja,version=2 ISO-2022-JP-2 { IANA* MIME* } csISO2022JP2 { IANA }
1.952 +ISO_2022,locale=ja,version=3 JIS7
1.953 +ISO_2022,locale=ja,version=4 JIS8
1.954 +ISO_2022,locale=ko,version=0 ISO-2022-KR { IANA* MIME* JAVA* } csISO2022KR { IANA JAVA } # This uses ibm-949
1.955 +ISO_2022,locale=ko,version=1 ibm-25546 { IBM* }
1.956 +ISO_2022,locale=zh,version=0 ISO-2022-CN { IANA* JAVA* } csISO2022CN { JAVA } x-ISO-2022-CN-GB { JAVA }
1.957 +ISO_2022,locale=zh,version=1 ISO-2022-CN-EXT { IANA* }
1.958 +ISO_2022,locale=zh,version=2 ISO-2022-CN-CNS x-ISO-2022-CN-CNS { JAVA* }
1.959 +HZ HZ-GB-2312 { IANA* }
1.960 +x11-compound-text COMPOUND_TEXT x-compound-text { JAVA* }
1.961 +
1.962 +ISCII,version=0 x-ISCII91 { JAVA* } x-iscii-de { WINDOWS } windows-57002 { WINDOWS* } iscii-dev ibm-4902 { IBM* } # ibm-806 contains non-standard box drawing symbols.
1.963 +ISCII,version=1 x-iscii-be { WINDOWS } windows-57003 { WINDOWS* } iscii-bng windows-57006 { WINDOWS } x-iscii-as { WINDOWS } # be is different from as on Windows.
1.964 +ISCII,version=2 x-iscii-pa { WINDOWS } windows-57011 { WINDOWS* } iscii-gur
1.965 +ISCII,version=3 x-iscii-gu { WINDOWS } windows-57010 { WINDOWS* } iscii-guj
1.966 +ISCII,version=4 x-iscii-or { WINDOWS } windows-57007 { WINDOWS* } iscii-ori
1.967 +ISCII,version=5 x-iscii-ta { WINDOWS } windows-57004 { WINDOWS* } iscii-tml
1.968 +ISCII,version=6 x-iscii-te { WINDOWS } windows-57005 { WINDOWS* } iscii-tlg
1.969 +ISCII,version=7 x-iscii-ka { WINDOWS } windows-57008 { WINDOWS* } iscii-knd
1.970 +ISCII,version=8 x-iscii-ma { WINDOWS } windows-57009 { WINDOWS* } iscii-mlm
1.971 +
1.972 +# Lotus specific
1.973 +LMBCS-1 lmbcs ibm-65025 { IBM* }
1.974 +
1.975 +# These Lotus specific converters still work, but they aren't advertised in this alias table.
1.976 +# These are almost never used outside of Lotus software,
1.977 +# and they take a lot of time when creating the available converter list.
1.978 +# Also Lotus doesn't really use them anyway. It was a mistake to create these LMBCS variant converters in ICU.
1.979 +#LMBCS-2
1.980 +#LMBCS-3
1.981 +#LMBCS-4
1.982 +#LMBCS-5
1.983 +#LMBCS-6
1.984 +#LMBCS-8
1.985 +#LMBCS-11
1.986 +#LMBCS-16
1.987 +#LMBCS-17
1.988 +#LMBCS-18
1.989 +#LMBCS-19
1.990 +
1.991 +# EBCDIC codepages according to the CDRA
1.992 +
1.993 +# without Euro
1.994 +ibm-37_P100-1995 { UTR22* } # EBCDIC US
1.995 + ibm-37 { IBM* }
1.996 + IBM037 { IANA* JAVA }
1.997 + ibm-037 # { JAVA }
1.998 + ebcdic-cp-us { IANA JAVA }
1.999 + ebcdic-cp-ca { IANA JAVA }
1.1000 + ebcdic-cp-wt { IANA JAVA }
1.1001 + ebcdic-cp-nl { IANA JAVA }
1.1002 + csIBM037 { IANA JAVA }
1.1003 + cp037 { JAVA* }
1.1004 + 037 { JAVA }
1.1005 + cpibm37 { JAVA }
1.1006 + cp37
1.1007 +
1.1008 +ibm-273_P100-1995 { UTR22* } ibm-273 { IBM* } IBM273 { IANA* JAVA } CP273 { IANA JAVA* } csIBM273 { IANA } ebcdic-de 273 { JAVA } # EBCDIC Germanay, Austria
1.1009 +ibm-277_P100-1995 { UTR22* } ibm-277 { IBM* } IBM277 { IANA* JAVA } cp277 { JAVA* } EBCDIC-CP-DK { IANA } EBCDIC-CP-NO { IANA } csIBM277 { IANA } ebcdic-dk 277 { JAVA } # EBCDIC Denmark
1.1010 +ibm-278_P100-1995 { UTR22* } ibm-278 { IBM* } IBM278 { IANA* JAVA } cp278 { JAVA* } ebcdic-cp-fi { IANA } ebcdic-cp-se { IANA } csIBM278 { IANA } ebcdic-sv { JAVA } 278 { JAVA } # EBCDIC Sweden
1.1011 +ibm-280_P100-1995 { UTR22* } ibm-280 { IBM* } IBM280 { IANA* JAVA } CP280 { IANA JAVA* } ebcdic-cp-it { IANA } csIBM280 { IANA } 280 { JAVA } # EBCDIC Italy
1.1012 +ibm-284_P100-1995 { UTR22* } ibm-284 { IBM* } IBM284 { IANA* JAVA } CP284 { IANA JAVA* } ebcdic-cp-es { IANA } csIBM284 { IANA } cpibm284 { JAVA } 284 { JAVA } # EBCDIC Spain
1.1013 +ibm-285_P100-1995 { UTR22* } ibm-285 { IBM* } IBM285 { IANA* JAVA } CP285 { IANA JAVA* } ebcdic-cp-gb { IANA } csIBM285 { IANA } cpibm285 { JAVA } ebcdic-gb { JAVA } 285 { JAVA } # EBCDIC UK Ireland
1.1014 +ibm-290_P100-1995 { UTR22* } ibm-290 { IBM* } IBM290 { IANA* } cp290 { IANA } EBCDIC-JP-kana { IANA } csIBM290 { IANA } # host SBCS (Katakana)
1.1015 +ibm-297_P100-1995 { UTR22* } ibm-297 { IBM* } IBM297 { IANA* JAVA } cp297 { IANA JAVA* } ebcdic-cp-fr { IANA } csIBM297 { IANA } cpibm297 { JAVA } 297 { JAVA } # EBCDIC France
1.1016 +ibm-420_X120-1999 { UTR22* } ibm-420 { IBM* } IBM420 { IANA* JAVA } cp420 { IANA JAVA* } ebcdic-cp-ar1 { IANA } csIBM420 { IANA } 420 { JAVA } # EBCDIC Arabic (all presentation shapes)
1.1017 +ibm-424_P100-1995 { UTR22* } ibm-424 { IBM* } IBM424 { IANA* JAVA } cp424 { IANA JAVA* } ebcdic-cp-he { IANA } csIBM424 { IANA } 424 { JAVA } # EBCDIC Hebrew
1.1018 +ibm-500_P100-1995 { UTR22* } ibm-500 { IBM* } IBM500 { IANA* JAVA } CP500 { IANA JAVA* } ebcdic-cp-be { IANA } csIBM500 { IANA } ebcdic-cp-ch { IANA } 500 # EBCDIC International Latin1
1.1019 +ibm-803_P100-1999 { UTR22* } ibm-803 { IBM* } cp803 # Old EBCDIC Hebrew
1.1020 +ibm-838_P100-1995 { UTR22* } ibm-838 { IBM* } IBM838 { JAVA } IBM-Thai { IANA* JAVA } csIBMThai { IANA } cp838 { JAVA* } 838 { JAVA } ibm-9030 { IBM } # EBCDIC Thai. Yes ibm-9030 is an alias.
1.1021 +ibm-870_P100-1995 { UTR22* } ibm-870 { IBM* } IBM870 { IANA* JAVA } CP870 { IANA JAVA* } ebcdic-cp-roece { IANA } ebcdic-cp-yu { IANA } csIBM870 { IANA } # EBCDIC Latin 2
1.1022 +ibm-871_P100-1995 { UTR22* } ibm-871 { IBM* } IBM871 { IANA* JAVA } ebcdic-cp-is { IANA JAVA } csIBM871 { IANA JAVA } CP871 { IANA JAVA* } ebcdic-is { JAVA } 871 { JAVA } # EBCDIC Iceland
1.1023 +ibm-875_P100-1995 { UTR22* } ibm-875 { IBM* } IBM875 { JAVA } cp875 { JAVA* } 875 { JAVA } x-IBM875 { JAVA } # EBCDIC Greek
1.1024 +ibm-918_P100-1995 { UTR22* } ibm-918 { IBM* } IBM918 { IANA* JAVA } CP918 { IANA JAVA* } ebcdic-cp-ar2 { IANA } csIBM918 { IANA } # EBCDIC Urdu
1.1025 +ibm-930_P120-1999 { UTR22* } # EBCDIC_STATEFUL Katakana-Kanji Host Mixed.
1.1026 + ibm-930 { IBM* }
1.1027 + ibm-5026 { IBM } # Yes this is correct
1.1028 + IBM930 { JAVA }
1.1029 + cp930 { JAVA* }
1.1030 + 930 { JAVA }
1.1031 + x-IBM930 { JAVA }
1.1032 + x-IBM930A { JAVA }
1.1033 +ibm-933_P110-1995 { UTR22* } ibm-933 { IBM* JAVA } cp933 { JAVA* } 933 { JAVA } x-IBM933 { JAVA } # Korea EBCDIC MIXED
1.1034 +ibm-935_P110-1999 { UTR22* } ibm-935 { IBM* JAVA } cp935 { JAVA* } 935 { JAVA } x-IBM935 { JAVA } # China EBCDIC MIXED. Need to use Unicode, ibm-1388 or gb18030 instead because it is required by the government of China.
1.1035 +ibm-937_P110-1999 { UTR22* } ibm-937 { IBM* JAVA } cp937 { JAVA* } 937 { JAVA } x-IBM937 { JAVA } # Taiwan EBCDIC MIXED
1.1036 +ibm-939_P120-1999 { UTR22* } # EBCDIC_STATEFUL Latin-Kanji Host Mixed.
1.1037 + ibm-939 { IBM* }
1.1038 + ibm-931 { IBM } # Yes this is correct
1.1039 + ibm-5035 { IBM } # Yes this is also correct
1.1040 + IBM939 { JAVA }
1.1041 + cp939 { JAVA* }
1.1042 + 939 { JAVA }
1.1043 + x-IBM939 { JAVA }
1.1044 + x-IBM939A { JAVA }
1.1045 +ibm-1025_P100-1995 { UTR22* } ibm-1025 { IBM* JAVA } cp1025 { JAVA* } 1025 { JAVA } x-IBM1025 { JAVA } # EBCDIC Cyrillic
1.1046 +ibm-1026_P100-1995 { UTR22* } ibm-1026 { IBM* } IBM1026 { IANA* JAVA } CP1026 { IANA JAVA* } csIBM1026 { IANA } 1026 { JAVA } # EBCDIC Turkey
1.1047 +ibm-1047_P100-1995 { UTR22* } ibm-1047 { IBM* } IBM1047 { IANA* JAVA } cp1047 { JAVA* } 1047 { JAVA } # EBCDIC Open systems Latin1
1.1048 +ibm-1097_P100-1995 { UTR22* } ibm-1097 { IBM* JAVA } cp1097 { JAVA* } 1097 { JAVA } x-IBM1097 { JAVA } # EBCDIC Farsi
1.1049 +ibm-1112_P100-1995 { UTR22* } ibm-1112 { IBM* JAVA } cp1112 { JAVA* } 1112 { JAVA } x-IBM1112 { JAVA } # EBCDIC Baltic
1.1050 +ibm-1114_P100-2001 { UTR22* } ibm-1114 { IBM* } x-IBM1114 { JAVA* }
1.1051 +ibm-1115_P100-1995 { UTR22* } ibm-1115 { IBM* } x-IBM1115 { JAVA* }
1.1052 +ibm-1122_P100-1999 { UTR22* } ibm-1122 { IBM* JAVA } cp1122 { JAVA* } 1122 { JAVA } x-IBM1122 { JAVA } # EBCDIC Estonia
1.1053 +ibm-1123_P100-1995 { UTR22* } ibm-1123 { IBM* JAVA } cp1123 { JAVA* } 1123 { JAVA } x-IBM1123 { JAVA } # EBCDIC Cyrillic Ukraine
1.1054 +ibm-1130_P100-1997 { UTR22* } ibm-1130 { IBM* } # EBCDIC Vietnamese
1.1055 +ibm-1132_P100-1998 { UTR22* } ibm-1132 { IBM* } # EBCDIC Lao
1.1056 +ibm-1137_P100-1999 { UTR22* } ibm-1137 { IBM* } # Devanagari EBCDIC (based on Unicode character set)
1.1057 +ibm-4517_P100-2005 { UTR22* } ibm-4517 { IBM* } # EBCDIC Arabic. Update of ibm-421
1.1058 +
1.1059 +# with Euro
1.1060 +ibm-1140_P100-1997 { UTR22* } ibm-1140 { IBM* } IBM01140 { IANA* JAVA } CCSID01140 { IANA JAVA } CP01140 { IANA JAVA } cp1140 { JAVA* } ebcdic-us-37+euro { IANA } # EBCDIC US
1.1061 +ibm-1141_P100-1997 { UTR22* } ibm-1141 { IBM* } IBM01141 { IANA* JAVA } CCSID01141 { IANA JAVA } CP01141 { IANA JAVA } cp1141 { JAVA* } ebcdic-de-273+euro { IANA } # EBCDIC Germanay, Austria
1.1062 +ibm-1142_P100-1997 { UTR22* } ibm-1142 { IBM* } IBM01142 { IANA* JAVA } CCSID01142 { IANA JAVA } CP01142 { IANA JAVA } cp1142 { JAVA* } ebcdic-dk-277+euro { IANA } ebcdic-no-277+euro { IANA } # EBCDIC Denmark
1.1063 +ibm-1143_P100-1997 { UTR22* } ibm-1143 { IBM* } IBM01143 { IANA* JAVA } CCSID01143 { IANA JAVA } CP01143 { IANA JAVA } cp1143 { JAVA* } ebcdic-fi-278+euro { IANA } ebcdic-se-278+euro { IANA } # EBCDIC Sweden
1.1064 +ibm-1144_P100-1997 { UTR22* } ibm-1144 { IBM* } IBM01144 { IANA* JAVA } CCSID01144 { IANA JAVA } CP01144 { IANA JAVA } cp1144 { JAVA* } ebcdic-it-280+euro { IANA } # EBCDIC Italy
1.1065 +ibm-1145_P100-1997 { UTR22* } ibm-1145 { IBM* } IBM01145 { IANA* JAVA } CCSID01145 { IANA JAVA } CP01145 { IANA JAVA } cp1145 { JAVA* } ebcdic-es-284+euro { IANA } # EBCDIC Spain
1.1066 +ibm-1146_P100-1997 { UTR22* } ibm-1146 { IBM* } IBM01146 { IANA* JAVA } CCSID01146 { IANA JAVA } CP01146 { IANA JAVA } cp1146 { JAVA* } ebcdic-gb-285+euro { IANA } # EBCDIC UK Ireland
1.1067 +ibm-1147_P100-1997 { UTR22* } ibm-1147 { IBM* } IBM01147 { IANA* JAVA } CCSID01147 { IANA JAVA } CP01147 { IANA JAVA } cp1147 { JAVA* } ebcdic-fr-297+euro { IANA } # EBCDIC France
1.1068 +ibm-1148_P100-1997 { UTR22* } ibm-1148 { IBM* } IBM01148 { IANA* JAVA } CCSID01148 { IANA JAVA } CP01148 { IANA JAVA } cp1148 { JAVA* } ebcdic-international-500+euro { IANA } # EBCDIC International Latin1
1.1069 +ibm-1149_P100-1997 { UTR22* } ibm-1149 { IBM* } IBM01149 { IANA* JAVA } CCSID01149 { IANA JAVA } CP01149 { IANA JAVA } cp1149 { JAVA* } ebcdic-is-871+euro { IANA } # EBCDIC Iceland
1.1070 +ibm-1153_P100-1999 { UTR22* } ibm-1153 { IBM* } IBM1153 { JAVA } x-IBM1153 { JAVA* } # EBCDIC latin 2
1.1071 +ibm-1154_P100-1999 { UTR22* } ibm-1154 { IBM* } # EBCDIC Cyrillic Multilingual
1.1072 +ibm-1155_P100-1999 { UTR22* } ibm-1155 { IBM* } # EBCDIC Turkey
1.1073 +ibm-1156_P100-1999 { UTR22* } ibm-1156 { IBM* } # EBCDIC Baltic Multilingual
1.1074 +ibm-1157_P100-1999 { UTR22* } ibm-1157 { IBM* } # EBCDIC Estonia
1.1075 +ibm-1158_P100-1999 { UTR22* } ibm-1158 { IBM* } # EBCDIC Cyrillic Ukraine
1.1076 +ibm-1160_P100-1999 { UTR22* } ibm-1160 { IBM* } # EBCDIC Thailand
1.1077 +ibm-1164_P100-1999 { UTR22* } ibm-1164 { IBM* } # EBCDIC Viet Nam
1.1078 +ibm-1364_P110-2007 { UTR22* } ibm-1364 { IBM* } x-IBM1364 { JAVA* } # Korean Host Mixed
1.1079 +ibm-1370_P100-1999 { UTR22* } ibm-1370 { IBM* } x-IBM1370 { JAVA* }
1.1080 +ibm-1371_P100-1999 { UTR22* } ibm-1371 { IBM* } x-IBM1371 { JAVA* } # Taiwan EBCDIC MIXED (Euro update of ibm-937)
1.1081 +ibm-1388_P103-2001 { UTR22* } ibm-1388 { IBM* } ibm-9580 { IBM } x-IBM1388 { JAVA* } # S-Ch DBCS-Host Data GBK EBCDIC_STATEFUL. Yes ibm-9580 is an alias.
1.1082 +ibm-1390_P110-2003 { UTR22* } ibm-1390 { IBM* } x-IBM1390 { JAVA* } # Japan EBCDIC MIXED (JIS X 0213)
1.1083 +ibm-1399_P110-2003 { UTR22* } ibm-1399 { IBM* } x-IBM1399 { JAVA* } # Host MBCS (Latin-Kanji) (JIS X 0213)
1.1084 +ibm-5123_P100-1999 { UTR22* } ibm-5123 { IBM* } # Host Roman Jis. Euro update of ibm-1027. SBCS portion of ibm-1390.
1.1085 +ibm-8482_P100-1999 { UTR22* } ibm-8482 { IBM* } # host SBCS (Katakana). Euro update of ibm-290. SBCS portion of ibm-1399.
1.1086 +# Yes ibm-20780 is the same as ibm-16684
1.1087 +ibm-16684_P110-2003 { UTR22* } ibm-16684 { IBM* } ibm-20780 { IBM } # DBCS Jis + Roman Jis Host. This is the DBCS portion of ibm-1390 and ibm-1399 (JIS X 0213).
1.1088 +ibm-4899_P100-1998 { UTR22* } ibm-4899 { IBM* } # Old EBCDIC Hebrew. Update of ibm-803
1.1089 +ibm-4971_P100-1999 { UTR22* } ibm-4971 { IBM* } # EBCDIC Greek. Update of ibm-875 and superceded by ibm-9067
1.1090 +ibm-9067_X100-2005 { UTR22* } ibm-9067 { IBM* } # EBCDIC Greek. Update of ibm-875 and ibm-4971
1.1091 +ibm-12712_P100-1998 { UTR22* } ibm-12712 { IBM* } ebcdic-he # EBCDIC Hebrew (new sheqel, control charaters update). Update of ibm-424
1.1092 +ibm-16804_X110-1999 { UTR22* } ibm-16804 { IBM* } ebcdic-ar # EBCDIC Arabic. Update of ibm-420
1.1093 +
1.1094 +java-Cp1399A-1.6_P { UTR22* } x-IBM1399A { JAVA* }
1.1095 +java-Cp420s-1.6_P { UTR22* } x-IBM420S { JAVA* }
1.1096 +java-Cp1390A-1.6_P { UTR22* } x-IBM1390A { JAVA* }
1.1097 +
1.1098 +# EBCDIC codepages for S/390, with LF and NL codes swapped
1.1099 +# Starting with ICU 2.4, the swapping is done by modifying the
1.1100 +# normal tables at runtime instead of at build time.
1.1101 +# Append UCNV_SWAP_LFNL_OPTION_STRING to the "ibm-CCSID" name to select this.
1.1102 +#
1.1103 +# Example: "ibm-1047,swaplfnl" or "ibm-1047" UCNV_SWAP_LFNL_OPTION_STRING
1.1104 +#
1.1105 +# This avoids the duplication of all EBCDIC SBCS and mixed-SBCS/DBCS
1.1106 +# mapping files.
1.1107 +
1.1108 +# Some examples below for declaring old-style, obsolete aliases with the "-s390"
1.1109 +# suffix to map to the new-style, recommended names with the option added.
1.1110 +# These are listed here for backward compatibility.
1.1111 +# Do not use these; instead use the normal converter name with the option
1.1112 +# added as recommended above.
1.1113 +
1.1114 +# Note: It is not possible to define an alias (non-initial name in a line here)
1.1115 +# that itself contains a converter option like this one for swapping LF<->NL.
1.1116 +# Such names would never be found because ucnv_open() will first parse and strip
1.1117 +# options before looking up a name in this table.
1.1118 +# ucnv_open() then parses the lookup result (the canonical name on the left
1.1119 +# in lines here) as well.
1.1120 +
1.1121 +# This also means that it is not necessary to add anything to convrtrs.txt
1.1122 +# for converter names like "ibm-1026,swaplfnl" to work -
1.1123 +# they are already covered by the normal option parsing together with the
1.1124 +# regular, option-less alias elsewhere in this file.
1.1125 +
1.1126 +ibm-37_P100-1995,swaplfnl ibm-37-s390 # ibm037-s390 also matches ibm-37-s390
1.1127 +ibm-924_P100-1998,swaplfnl ibm-924-s390 IBM924_LF { JAVA* }
1.1128 +ibm-1047_P100-1995,swaplfnl ibm-1047-s390 IBM1047_LF { JAVA* }
1.1129 +ibm-1140_P100-1997,swaplfnl ibm-1140-s390
1.1130 +ibm-1141_P100-1997,swaplfnl ibm-1141-s390 IBM1141_LF { JAVA* }
1.1131 +ibm-1142_P100-1997,swaplfnl ibm-1142-s390
1.1132 +ibm-1143_P100-1997,swaplfnl ibm-1143-s390
1.1133 +ibm-1144_P100-1997,swaplfnl ibm-1144-s390
1.1134 +ibm-1145_P100-1997,swaplfnl ibm-1145-s390
1.1135 +ibm-1146_P100-1997,swaplfnl ibm-1146-s390
1.1136 +ibm-1147_P100-1997,swaplfnl ibm-1147-s390
1.1137 +ibm-1148_P100-1997,swaplfnl ibm-1148-s390
1.1138 +ibm-1149_P100-1997,swaplfnl ibm-1149-s390
1.1139 +ibm-1153_P100-1999,swaplfnl ibm-1153-s390
1.1140 +ibm-12712_P100-1998,swaplfnl ibm-12712-s390
1.1141 +ibm-16804_X110-1999,swaplfnl ibm-16804-s390
1.1142 +
1.1143 +# This is a special version of ibm-1140 that the XML4C (Xerces) parser team
1.1144 +# requested in 2000.
1.1145 +# It maps both EBCDIC LF and NL controls to Unicode LF U+000A.
1.1146 +
1.1147 +ebcdic-xml-us
1.1148 +
1.1149 +# These are not installed by default. They are rarely used.
1.1150 +# Many of them can be added through the online ICU Data Library Customization tool
1.1151 +
1.1152 +gsm-03.38-2000 { UTR22* } GSM0338 # GSM0338 alias is from Perl
1.1153 +ibm-1004_P100-1995 { UTR22* } ibm-1004 { IBM* }
1.1154 +ibm-1008_P100-1995 { UTR22* } ibm-1008 { IBM* } # cp1008, 8-bit Arabic (w/o euro update)
1.1155 +ibm-1009_P100-1995 { UTR22* } ibm-1009 { IBM* }
1.1156 +ibm-1010_P100-1995 { UTR22* } ibm-1010 { IBM* } NF_Z_62-010 { IANA* } iso-ir-69 { IANA } ISO646-FR { IANA } fr { IANA } csISO69French { IANA }
1.1157 +ibm-1011_P100-1995 { UTR22* } ibm-1011 { IBM* } DIN_66003 { IANA* } iso-ir-21 { IANA } de { IANA } ISO646-DE { IANA } csISO21German { IANA }
1.1158 +ibm-1012_P100-1995 { UTR22* } ibm-1012 { IBM* } IT { IANA* } iso-ir-15 { IANA } ISO646-IT { IANA } csISO15Italian { IANA }
1.1159 +ibm-1013_P100-1995 { UTR22* } ibm-1013 { IBM* } BS_4730 { IANA* } iso-ir-4 { IANA } ISO646-GB { IANA } gb { IANA } uk { IANA } csISO4UnitedKingdom { IANA }
1.1160 +ibm-1014_P100-1995 { UTR22* } ibm-1014 { IBM* } ES2 { IANA* } iso-ir-85 { IANA } ISO646-ES2 { IANA } csISO85Spanish2 { IANA }
1.1161 +ibm-1015_P100-1995 { UTR22* } ibm-1015 { IBM* } PT2 { IANA* } iso-ir-84 { IANA } ISO646-PT2 { IANA } csISO84Portuguese2 { IANA }
1.1162 +ibm-1016_P100-1995 { UTR22* } ibm-1016 { IBM* } NS_4551-1 { IANA* } iso-ir-60 { IANA } ISO646-NO { IANA } no { IANA } csISO60DanishNorwegian { IANA } csISO60Norwegian1 { IANA }
1.1163 +ibm-1017_P100-1995 { UTR22* } ibm-1017 { IBM* }
1.1164 +ibm-1018_P100-1995 { UTR22* } ibm-1018 { IBM* } SEN_850200_B { IANA* } iso-ir-10 { IANA } FI { IANA } ISO646-FI { IANA } ISO646-SE { IANA } se { IANA } csISO10Swedish { IANA }
1.1165 +ibm-1019_P100-1995 { UTR22* } ibm-1019 { IBM* }
1.1166 +ibm-1020_P100-2003 { UTR22* } ibm-1020 { IBM* } CSA_Z243.4-1985-1 { IANA* } iso-ir-121 { IANA } ISO646-CA { IANA } csa7-1 { IANA } ca { IANA } csISO121Canadian1 { IANA }
1.1167 +ibm-1021_P100-2003 { UTR22* } ibm-1021 { IBM* }
1.1168 +ibm-1023_P100-2003 { UTR22* } ibm-1023 { IBM* } ES { IANA* } iso-ir-17 { IANA } ISO646-ES { IANA } csISO17Spanish { IANA }
1.1169 +ibm-1027_P100-1995 { UTR22* } ibm-1027 { IBM* } x-IBM1027 { JAVA* }
1.1170 +ibm-1041_P100-1995 { UTR22* } ibm-1041 { IBM* } x-IBM1041 { JAVA* }
1.1171 +ibm-1043_P100-1995 { UTR22* } ibm-1043 { IBM* } x-IBM1043 { JAVA* }
1.1172 +ibm-1046_X110-1999 { UTR22* } ibm-1046 { IBM* } x-IBM1046 { JAVA* } x-IBM1046S { JAVA } # Arabic
1.1173 +ibm-1088_P100-1995 { UTR22* } ibm-1088 { IBM* } x-IBM1088 { JAVA* }
1.1174 +ibm-1100_P100-2003 { UTR22* } ibm-1100 { IBM* } DEC-MCS { IANA* } dec { IANA } csDECMCS { IANA }
1.1175 +ibm-1101_P100-2003 { UTR22* } ibm-1101 { IBM* }
1.1176 +ibm-1102_P100-2003 { UTR22* } ibm-1102 { IBM* }
1.1177 +ibm-1103_P100-2003 { UTR22* } ibm-1103 { IBM* }
1.1178 +ibm-1104_P100-2003 { UTR22* } ibm-1104 { IBM* } NF_Z_62-010_1973 iso-ir-25 { IANA* } ISO646-FR1 { IANA } csISO25French { IANA } # NF_Z_62-010_(1973) is the real IANA alias, but () aren't invariant characters.
1.1179 +ibm-1105_P100-2003 { UTR22* } ibm-1105 { IBM* }
1.1180 +ibm-1106_P100-2003 { UTR22* } ibm-1106 { IBM* }
1.1181 +ibm-1107_P100-2003 { UTR22* } ibm-1107 { IBM* } DS_2089 { IANA* } ISO646-DK { IANA } dk { IANA } csISO646Danish { IANA }
1.1182 +ibm-1127_P100-2004 { UTR22* } ibm-1127 { IBM* }
1.1183 +ibm-1161_P100-1999 { UTR22* } ibm-1161 { IBM* } # Thai (Euro update of ibm-1129)
1.1184 +ibm-1163_P100-1999 { UTR22* } ibm-1163 { IBM* } # Vietnamese
1.1185 +ibm-1165_P101-2000 { UTR22* } ibm-1165 { IBM* } # Vietnamese (EBCDIC)
1.1186 +ibm-1166_P100-2002 { UTR22* } ibm-1166 { IBM* } # Cyrillic for Kazakhstan
1.1187 +ibm-1167_P100-2002 { UTR22* } ibm-1167 { IBM* } KOI8-RU x-KOI8_RU { JAVA* }
1.1188 +ibm-1174_X100-2007 { UTR22* } ibm-1174 { IBM* } KZ-1048 { IANA* } STRK1048-2002 { IANA } RK1048 { IANA } csKZ1048 { IANA }
1.1189 +ibm-1277_P100-1995 { UTR22* } ibm-1277 { IBM* } # Adobe (Postscript) Latin-1
1.1190 +ibm-13125_P100-1997 { UTR22* } ibm-13125 { IBM* } # S-Ch (DBCS subset of ibm-4933, ibm-1388)
1.1191 +ibm-13140_P101-2000 { UTR22* } ibm-13140 { IBM* }
1.1192 +ibm-13218_P100-1996 { UTR22* } ibm-13218 { IBM* } # Japanese (EBCDIC update of ibm-930)
1.1193 +ibm-1350_P110-1997 { UTR22* } ibm-1350 { IBM* } x-eucJP-Open { JAVA* } eucJP-Open { JAVA } # Japanese (EUC-JP variant)
1.1194 +ibm-1351_P110-1997 { UTR22* } ibm-1351 { IBM* } x-IBM1351 { JAVA* } # Japanese (DBCS subset of ibm-5039)
1.1195 +ibm-1362_P110-1999 { UTR22* } ibm-1362 { IBM* } x-IBM1362 { JAVA* } # Korean (DBCS subset of ibm-1363)
1.1196 +ibm-13676_P102-2001 { UTR22* } ibm-13676 { IBM* } # Simplified Chinese (EBCDIC)
1.1197 +ibm-1380_P100-1995 { UTR22* } ibm-1380 { IBM* } x-IBM1380 { JAVA* } # Simplified Chinese (DBCS subset of ibm-1381)
1.1198 +ibm-1381_P110-1999 { UTR22* } ibm-1381 { IBM* JAVA } cp1381 { JAVA* } 1381 { JAVA } x-IBM1381 { JAVA } # Simplified Chinese PC Data mixed (IBM GB)
1.1199 +ibm-1382_P100-1995 { UTR22* } ibm-1382 { IBM* } x-IBM1382 { JAVA* } # Simplified Chinese (DBCS subset of ibm-1383)
1.1200 +ibm-17221_P100-2001 { UTR22* } ibm-17221 { IBM* } # Simplified Chinese (EBCDIC)
1.1201 +ibm-17248_X110-1999 { UTR22* } ibm-17248 { IBM* } # PC Arabic (w/ euro update) Updated version of ibm-864
1.1202 +ibm-21344_P101-2000 { UTR22* } ibm-21344 { IBM* } # PC Arabic. Updated version of ibm-864
1.1203 +ibm-21427_P100-1999 { UTR22* } ibm-21427 { IBM* } # Traditional Chinese (DBCS subset of ibm-1370)
1.1204 +ibm-256_P100-1995 { UTR22* } ibm-256 { IBM* } # Latin 1 EBCDIC
1.1205 +ibm-259_P100-1995 { UTR22* } ibm-259 { IBM* } IBM-Symbols { IANA* } csIBMSymbols { IANA }
1.1206 +ibm-274_P100-2000 { UTR22* } ibm-274 { IBM* } IBM274 { IANA* } EBCDIC-BE { IANA } CP274 { IANA } csIBM274 { IANA }
1.1207 +ibm-275_P100-1995 { UTR22* } ibm-275 { IBM* } IBM275 { IANA* } EBCDIC-BR { IANA } cp275 { IANA } csIBM275 { IANA }
1.1208 +ibm-286_P100-2003 { UTR22* } ibm-286 { IBM* } EBCDIC-AT-DE-A { IANA* } csEBCDICATDEA { IANA }
1.1209 +ibm-293_P100-1995 { UTR22* } ibm-293 { IBM* } # APL EBCDIC (APL: A Programming Language)
1.1210 +ibm-300_P120-2006 { UTR22* } ibm-300 { IBM* } x-IBM300 { JAVA* } # Japanese (DBCS subset of ibm-930 and ibm-939)
1.1211 +ibm-301_P110-1997 { UTR22* } ibm-301 { IBM* } x-IBM301 { JAVA* } # Japanese (DBCS subset of ibm-943)
1.1212 +ibm-33058_P100-2000 { UTR22* } ibm-33058 { IBM* } # SBCS (Katakana)
1.1213 +ibm-425_P101-2000 { UTR22* } ibm-425 { IBM* } # Arabic (EBCDIC)
1.1214 +ibm-4930_P110-1999 { UTR22* } ibm-4930 { IBM* } # Korean (DBCS subset of ibm-1364)
1.1215 +ibm-4933_P100-2002 { UTR22* } ibm-4933 { IBM* } # S-Ch (DBCS subset of ibm-1388)
1.1216 +ibm-4948_P100-1995 { UTR22* } ibm-4948 { IBM* }
1.1217 +ibm-4951_P100-1995 { UTR22* } ibm-4951 { IBM* }
1.1218 +ibm-4952_P100-1995 { UTR22* } ibm-4952 { IBM* }
1.1219 +ibm-4960_P100-1995 { UTR22* } ibm-4960 { IBM* }
1.1220 +ibm-5039_P11A-1998 { UTR22* } ibm-5039 { IBM* } # Japanese (HP Shift-JIS variant)
1.1221 +ibm-5048_P100-1995 { UTR22* } ibm-5048 { IBM* } # Japanese (DBCS subset of ibm-1350, JIS X208-1990)
1.1222 +ibm-5049_P100-1995 { UTR22* } ibm-5049 { IBM* } # Japanese (DBCS subset of ibm-1350, JIS X212)
1.1223 +ibm-5067_P100-1995 { UTR22* } ibm-5067 { IBM* } # Korean (DBCS subset of ibm-21450)
1.1224 +ibm-5104_X110-1999 { UTR22* } ibm-5104 { IBM* } # cp1008, 8-bit Arabic (w/ euro update)
1.1225 +ibm-5233_P100-2011 { UTR22* } ibm-5233 { IBM* } # Devanagari EBCDIC, including Indian Rupee
1.1226 +ibm-806_P100-1998 { UTR22* } ibm-806 { IBM* } # Hindi (ISCII variant)
1.1227 +ibm-808_P100-1999 { UTR22* } ibm-808 { IBM* } x-IBM808 { JAVA* } # Cyrillic
1.1228 +ibm-833_P100-1995 { UTR22* } ibm-833 { IBM* } x-IBM833 { JAVA* }
1.1229 +ibm-834_P100-1995 { UTR22* } ibm-834 { IBM* } x-IBM834 { JAVA* } # Korean (DBCS subset of ibm-933)
1.1230 +ibm-835_P100-1995 { UTR22* } ibm-835 { IBM* } x-IBM835 { JAVA* } # Traditional Chinese (DBCS subset of ibm-5033)
1.1231 +ibm-836_P100-1995 { UTR22* } ibm-836 { IBM* } x-IBM836 { JAVA* }
1.1232 +ibm-837_P100-2011 { UTR22* } ibm-837 { IBM* } x-IBM837 { JAVA* } # Simplified Chinese (DBCS subset of ibm-5031)
1.1233 +ibm-848_P100-1999 { UTR22* } ibm-848 { IBM* } # Cyrillic (euro update of ibm-1125)
1.1234 +ibm-849_P100-1999 { UTR22* } ibm-849 { IBM* } # Cyrillic Belarus (euro update of ibm-1131)
1.1235 +ibm-859_P100-1999 { UTR22* } ibm-859 { IBM* } x-IBM859 { JAVA* } # PC Latin 9 (w/ euro update)
1.1236 +ibm-8612_P100-1995 { UTR22* } ibm-8612 { IBM* } # Arabic (EBCDIC update of ibm-420)
1.1237 +ibm-872_P100-1999 { UTR22* } ibm-872 { IBM* } # Cyrillic (Euro update of ibm-855)
1.1238 +ibm-880_P100-1995 { UTR22* } ibm-880 { IBM* } IBM880 { IANA* } cp880 { IANA } EBCDIC-Cyrillic { IANA } csIBM880 { IANA } windows-20880 { WINDOWS* }
1.1239 +ibm-896_P100-1995 { UTR22* } ibm-896 { IBM* } # SBCS Katakana
1.1240 +ibm-897_P100-1995 { UTR22* } ibm-897 { IBM* } JIS_X0201 { IANA* } X0201 { IANA } csHalfWidthKatakana { IANA } x-IBM897 { JAVA* }
1.1241 +ibm-9027_P100-1999 { UTR22* } ibm-9027 { IBM* } # DBCS T-Ch Host. Euro update of ibm-835. DBCS portion of ibm-1371.
1.1242 +ibm-9048_P100-1998 { UTR22* } ibm-9048 { IBM* } # Hebrew (Euro and Sequel update of ibm-856)
1.1243 +ibm-905_P100-1995 { UTR22* } ibm-905 { IBM* } IBM905 { IANA* } CP905 { IANA } ebcdic-cp-tr { IANA } csIBM905 { IANA } windows-20905 { WINDOWS* }
1.1244 +ibm-9056_P100-1995 { UTR22* } ibm-9056 { IBM* } # Arabic
1.1245 +ibm-9061_P100-1999 { UTR22* } ibm-9061 { IBM* } # Greek (w/ euro update)
1.1246 +ibm-9145_P110-1997 { UTR22* } ibm-9145 { IBM* } # Japanese (DBCS subset of ibm-5050)
1.1247 +ibm-9238_X110-1999 { UTR22* } ibm-9238 { IBM* } # cp1046, PC Arabic Extended (w/ euro update)
1.1248 +ibm-924_P100-1998 { UTR22* } ibm-924 { IBM* } IBM00924 { IANA* } CCSID00924 { IANA } CP00924 { IANA } ebcdic-Latin9--euro { IANA }
1.1249 +ibm-926_P100-2000 { UTR22* } ibm-926 { IBM* } # Korean (DBCS subset of ibm-944)
1.1250 +ibm-927_P100-1995 { UTR22* } ibm-927 { IBM* } x-IBM927 { JAVA* } # Traditional Chinese (DBCS subset of ibm-948)
1.1251 +ibm-928_P100-1995 { UTR22* } ibm-928 { IBM* } # Simplified Chinese (DBCS subset of ibm-936)
1.1252 +ibm-941_P13A-2001 { UTR22* } ibm-941 { IBM* } # DBCS portion of ibm-943
1.1253 +ibm-944_P100-1995 { UTR22* } ibm-944 { IBM* } # Korean
1.1254 +ibm-946_P100-1995 { UTR22* } ibm-946 { IBM* } # Simplified Chinese
1.1255 +ibm-947_P100-1995 { UTR22* } ibm-947 { IBM* } x-IBM947 { JAVA* } # Traditional Chinese (DBCS subset of ibm-950)
1.1256 +ibm-948_P110-1999 { UTR22* } ibm-948 { IBM* } x-IBM948 { JAVA* } # Traditional Chinese
1.1257 +ibm-951_P100-1995 { UTR22* } ibm-951 { IBM* } x-IBM951 { JAVA* } # Korean (DBCS subset of ibm-949)
1.1258 +ibm-952_P110-1997 { UTR22* } ibm-952 { IBM* } x-JIS0208 # Pure DBCS, Japanese EUC, G1 - JIS X208-1990
1.1259 +ibm-953_P100-2000 { UTR22* } ibm-953 { IBM* } JIS_X0212-1990 { IANA* } # Pure DBCS, Japanese EUC, G3 - JIS X 0212-1990
1.1260 +ibm-955_P110-1997 { UTR22* } ibm-955 { IBM* } # Pure DBCS, Japanese EUC, G0 - JIS X208-1978
1.1261 +ibm-9577_P100-2001 { UTR22* } ibm-9577 { IBM* } ibm-1385 { IBM } x-IBM1385 { JAVA* } # ibm-9577 and ibm-1385 are identical DBCS tables.
1.1262 +iso-8859_16-2001 { UTR22* } ISO-8859-16 { IANA* } iso-ir-226 { IANA } ISO_8859-16:2001 { IANA } latin10 { IANA } l10 { IANA }
1.1263 +
1.1264 +# To be considered for listing at a later date for the data library customization tool
1.1265 +#ibm-1159_P100-1999 { UTR22* } ibm-1159 { IBM* } # SBCS T-Ch Host. Euro update of ibm-28709. This is used in combination with another CCSID mapping.
1.1266 +#ibm-960_P100-2000 { UTR22* } ibm-960 { IBM* } # Pure DBCS, CNS11643 plane 1
1.1267 +#ibm-963_P100-1995 { UTR22* } ibm-963 { IBM* } # Pure DBCS, CNS11643 plane 2 Traditional Chinese (DBCS subset of ibm-965)
