# Copyright (C) 2016 and later: Unicode, Inc. and others.
# License & terms of use:
http://www.unicode.org/copyright.html
# ******************************************************************************
# *
# * Copyright (C) 1995-2014, International Business Machines
# * Corporation and others. All Rights Reserved.
# *
# ******************************************************************************
# If this converter alias table looks very confusing, a much easier to
# understand view can be found at this demo:
#
https://icu4c-demos.unicode.org/icu-bin/convexp
# IMPORTANT NOTE
#
# This file is not read directly by ICU. If you change it, you need to
# run gencnval, and eventually run pkgdata to update the representation that
# ICU uses for aliases. The gencnval tool will normally compile this file into
# cnvalias.icu. The gencnval -v verbose option will help you when you edit
# this file.
# Please be friendly to the rest of us that edit this table by
# keeping this table free of tabs.
# This is an alias file used by the character set converter.
# A lot of converter information can be found in unicode/ucnv.h, but here
# is more information about this file.
#
# If you are adding a new converter to this list and want to include it in the
# icu data library, please be sure to add an entry to the appropriate ucm*.mk file
# (see ucmfiles.mk for more information).
#
# Here is the file format using BNF-like syntax:
#
# converterTable ::= tags { converterLine* }
# converterLine ::= converterName [ tags ] { taggedAlias* }'\n'
# taggedAlias ::= alias [ tags ]
# tags ::= '{' { tag+ } '}'
# tag ::= standard['*']
# converterName ::= [0-9a-zA-Z:_'-']+
# alias ::= converterName
#
# Except for the converter name, aliases are case insensitive.
# Names are separated by whitespace.
# Line continuation and comment sytax are similar to the GNU make syntax.
# Any lines beginning with whitespace (e.g. U+0020 SPACE or U+0009 HORIZONTAL
# TABULATION) are presumed to be a continuation of the previous line.
# The # symbol starts a comment and the comment continues till the end of
# the line.
#
# The converter
#
# All names can be tagged by including a space-separated list of tags in
# curly braces, as in ISO_8859-1:1987{IANA*} iso-8859-1 { MIME* } or
# some-charset{MIME* IANA*}. The order of tags does not matter, and
# whitespace is allowed between the tagged name and the tags list.
#
# The tags can be used to get standard names using ucnv_getStandardName().
#
# The complete list of recognized tags used in this file is defined in
# the affinity list near the beginning of the file.
#
# The * after the standard tag denotes that the previous alias is the
# preferred (default) charset name for that standard. There can only
# be one of these default charset names per converter.
# The world is getting more complicated...
# Supporting XML parsers, HTML, MIME, and similar applications
# that mark encodings with a charset name can be difficult.
# Many of these applications and operating systems will update
# their codepages over time.
# It means that a new codepage, one that differs from an
# old one by changing a code point, e.g., to the Euro sign,
# must not get an old alias, because it would mean that
# old files with this alias would be interpreted differently.
# If an codepage gets updated by assigning characters to previously
# unassigned code points, then a new name is not necessary.
# Also, some codepages map unassigned codepage byte values
# to the same numbers in Unicode for roundtripping. It may be
# industry practice to keep the encoding name in such a case, too
# (example: Windows codepages).
# The aliases listed in the list of character sets
# that is maintained by the IANA (
http://www.iana.org/) must
# not be changed to mean encodings different from what this
# list shows. Currently, the IANA list is at
#
http://www.iana.org/assignments/character-sets
# It should also be mentioned that the exact mapping table used for each
# IANA names usually isn't specified. This means that some other applications
# and operating systems are left to interpret the exact mappings for the
# underspecified aliases. For instance, Shift-JIS on a Solaris platform
# may be different from Shift-JIS on a Windows platform. This is why
# some of the aliases can be tagged to differentiate different mapping
# tables with the same alias. If an alias is given to more than one converter,
# it is considered to be an ambiguous alias, and the affinity list will
# choose the converter to use when a standard isn't specified with the alias.
# Name matching is case-insensitive. Also, dashes '-', underscores '_'
# and spaces ' ' are ignored in names (thus cs-iso_latin-1, csisolatin1
# and "cs iso latin 1" are the same).
# However, the names in the left column are directly file names
# or names of algorithmic converters, and their case must not
# be changed - or else code and/or file names must also be changed.
# For example, the converter ibm-921 is expected to be the file ibm-921.cnv.
# The immediately following list is the affinity list of supported standard tags.
# When multiple converters have the same alias under different standards,
# the standard nearest to the top of this list with that alias will
# be the first converter that will be opened. The ordering of the aliases
# after this affinity list does not affect the preferred alias, but it may
# affect the order of the returned list of aliases for a given converter.
#
# The general ordering is from specific and frequently used to more general
# or rarely used at the bottom.
{ UTR22 # Name format specified by
https://www.unicode.org/reports/tr22/
# ICU # Can also use ICU_FEATURE
IBM # The IBM CCSID number is specified by ibm-*
WINDOWS # The Microsoft code page identifier number is specified by windows-*. The rest are rec
ognized IE names.
JAVA # Source: Sun JDK. Alias name case is ignored, but dashes are not ignored.
# GLIBC
# AIX
# DB2
# SOLARIS
# APPLE
# HPUX
IANA # Source: http://www.iana.org/assignments/character-sets
MIME # Source: http://www.iana.org/assignments/character-sets
# MSIE # MSIE is Internet Explorer, which can be different from Windows (From the IMultiLanguage COM interface)
# ZOS_USS # z/OS (os/390) Unix System Services (USS), which has NL<->LF swapping. They have the same format as the IBM tag.
}
# Fully algorithmic converters
UTF-8 { IANA* MIME* JAVA* WINDOWS }
ibm-1208 { IBM* } # UTF-8 with IBM PUA
ibm-1209 { IBM } # UTF-8
ibm-5304 { IBM } # Unicode 2.0, UTF-8 with IBM PUA
ibm-5305 { IBM } # Unicode 2.0, UTF-8
ibm-13496 { IBM } # Unicode 3.0, UTF-8 with IBM PUA
ibm-13497 { IBM } # Unicode 3.0, UTF-8
ibm-17592 { IBM } # Unicode 4.0, UTF-8 with IBM PUA
ibm-17593 { IBM } # Unicode 4.0, UTF-8
windows-65001 { WINDOWS* }
cp1208
x-UTF_8J
unicode-1-1-utf-8
unicode-2-0-utf-8
# The ICU 2.2 UTF-16/32 converters detect and write a BOM.
UTF-16 { IANA* MIME* JAVA* } ISO-10646-UCS-2 { IANA }
ibm-1204 { IBM* } # UTF-16 with IBM PUA and BOM sensitive
ibm-1205 { IBM } # UTF-16 BOM sensitive
unicode
csUnicode
ucs-2
# The following Unicode CCSIDs (IBM) are not valid in ICU because they are
# considered pure DBCS (exactly 2 bytes) of Unicode,
# and they are a subset of Unicode. ICU does not support their encoding structures.
# 1400 1401 1402 1410 1414 1415 1446 1447 1448 1449 64770 64771 65520 5496 5497 5498 9592 13688
UTF-16BE { IANA* MIME* JAVA* } x-utf-16be { JAVA }
UnicodeBigUnmarked { JAVA } # java.io name
ibm-1200 { IBM* } # UTF-16 BE with IBM PUA
ibm-1201 { IBM } # UTF-16 BE
ibm-13488 { IBM } # Unicode 2.0, UTF-16 BE with IBM PUA
ibm-13489 { IBM } # Unicode 2.0, UTF-16 BE
ibm-17584 { IBM } # Unicode 3.0, UTF-16 BE with IBM PUA
ibm-17585 { IBM } # Unicode 3.0, UTF-16 BE
ibm-21680 { IBM } # Unicode 4.0, UTF-16 BE with IBM PUA
ibm-21681 { IBM } # Unicode 4.0, UTF-16 BE
ibm-25776 { IBM } # Unicode 4.1, UTF-16 BE with IBM PUA
ibm-25777 { IBM } # Unicode 4.1, UTF-16 BE
ibm-29872 { IBM } # Unicode 5.0, UTF-16 BE with IBM PUA
ibm-29873 { IBM } # Unicode 5.0, UTF-16 BE
ibm-61955 { IBM } # UTF-16BE with Gaidai University (Japan) PUA
ibm-61956 { IBM } # UTF-16BE with Microsoft HKSCS-Big 5 PUA
windows-1201 { WINDOWS* }
cp1200
cp1201
UTF16_BigEndian
# ibm-5297 { IBM } # Unicode 2.0, UTF-16 (BE) (reserved, never used)
# iso-10646-ucs-2 { JAVA } # This is ambiguous
# ibm-61952 is not a valid CCSID because it's Unicode 1.1
# ibm-61953 is not a valid CCSID because it's Unicode 1.0
UTF-16LE { IANA* MIME* JAVA* } x-utf-16le { JAVA }
UnicodeLittleUnmarked { JAVA } # java.io name
ibm-1202 { IBM* } # UTF-16 LE with IBM PUA
ibm-1203 { IBM } # UTF-16 LE
ibm-13490 { IBM } # Unicode 2.0, UTF-16 LE with IBM PUA
ibm-13491 { IBM } # Unicode 2.0, UTF-16 LE
ibm-17586 { IBM } # Unicode 3.0, UTF-16 LE with IBM PUA
ibm-17587 { IBM } # Unicode 3.0, UTF-16 LE
ibm-21682 { IBM } # Unicode 4.0, UTF-16 LE with IBM PUA
ibm-21683 { IBM } # Unicode 4.0, UTF-16 LE
ibm-25778 { IBM } # Unicode 4.1, UTF-16 LE with IBM PUA
ibm-25779 { IBM } # Unicode 4.1, UTF-16 LE
ibm-29874 { IBM } # Unicode 5.0, UTF-16 LE with IBM PUA
ibm-29875 { IBM } # Unicode 5.0, UTF-16 LE
UTF16_LittleEndian
windows-1200 { WINDOWS* }
UTF-32 { IANA* MIME* } ISO-10646-UCS-4 { IANA }
ibm-1236 { IBM* } # UTF-32 with IBM PUA and BOM sensitive
ibm-1237 { IBM } # UTF-32 BOM sensitive
csUCS4
ucs-4
UTF-32BE { IANA* } UTF32_BigEndian
ibm-1232 { IBM* } # UTF-32 BE with IBM PUA
ibm-1233 { IBM } # UTF-32 BE
ibm-9424 { IBM } # Unicode 4.1, UTF-32 BE with IBM PUA
UTF-32LE { IANA* } UTF32_LittleEndian
ibm-1234 { IBM* } # UTF-32 LE, with IBM PUA
ibm-1235 { IBM } # UTF-32 LE
# ICU-specific names for special uses
UTF16_PlatformEndian
UTF16_OppositeEndian
UTF32_PlatformEndian
UTF32_OppositeEndian
# Java-specific, non-Unicode-standard UTF-16 variants.
# These are in the Java "Basic Encoding Set (contained in lib/rt.jar)".
# See the "Supported Encodings" at
# http://java.sun.com/javase/6/docs/technotes/guides/intl/encoding.doc.html
# or a newer version of this document.
#
# Aliases marked with { JAVA* } are canonical names for java.io and java.lang APIs.
# Aliases marked with { JAVA } are canonical names for the java.nio API.
#
# "BOM" means the Unicode Byte Order Mark, which is the encoding-scheme-specific
# byte sequence for U+FEFF.
# "Reverse BOM" means the BOM for the sibling encoding scheme with the
# opposite endianness. (LE<->BE)
# "Sixteen-bit Unicode (or UCS) Transformation Format, big-endian byte order,
# with byte-order mark"
#
# From Unicode: Writes BOM.
# To Unicode: Detects and consumes BOM.
# If there is a "reverse BOM", Java throws
# MalformedInputException: Incorrect byte-order mark.
# In this case, ICU4C sets a U_ILLEGAL_ESCAPE_SEQUENCE UErrorCode value
# and a UCNV_ILLEGAL UConverterCallbackReason.
UTF-16BE,version=1 UnicodeBig { JAVA* }
# "Sixteen-bit Unicode (or UCS) Transformation Format, little-endian byte order,
# with byte-order mark"
#
# From Unicode: Writes BOM.
# To Unicode: Detects and consumes BOM.
# If there is a "reverse BOM", Java throws
# MalformedInputException: Incorrect byte-order mark.
# In this case, ICU4C sets a U_ILLEGAL_ESCAPE_SEQUENCE UErrorCode value
# and a UCNV_ILLEGAL UConverterCallbackReason.
UTF-16LE,version=1 UnicodeLittle { JAVA* } x-UTF-16LE-BOM { JAVA }
# This one is not mentioned on the "Supported Encodings" page
# but is available in Java.
# In Java, this is called "Unicode" but we cannot give it that alias
# because the standard UTF-16 converter already has a "unicode" alias.
#
# From Unicode: Writes BOM.
# To Unicode: Detects and consumes BOM.
# If there is no BOM, rather than defaulting to BE, Java throws
# MalformedInputException: Missing byte-order mark.
# In this case, ICU4C sets a U_ILLEGAL_ESCAPE_SEQUENCE UErrorCode value
# and a UCNV_ILLEGAL UConverterCallbackReason.
UTF-16,version=1
# This is the same as standard UTF-16 but always writes a big-endian byte stream,
# regardless of the platform endianness, as expected by the Java compatibility tests.
# See the java.nio.charset.Charset API documentation at
# http://java.sun.com/javase/6/docs/api/java/nio/charset/Charset.html
# or a newer version of this document.
#
# From Unicode: Write BE BOM and BE bytes
# To Unicode: Detects and consumes BOM. Defaults to BE.
UTF-16,version=2
# Note: ICU does not currently support Java-specific, non-Unicode-standard UTF-32 variants.
# Presumably, these behave analogously to the UTF-16 variants with similar names.
# UTF_32BE_BOM x-UTF-32BE-BOM
# UTF_32LE_BOM x-UTF-32LE-BOM
# End of Java-specific, non-Unicode-standard UTF variants.
# On UTF-7:
# RFC 2152 (http://www.imc.org/rfc2152) allows to encode some US-ASCII
# characters directly or in base64. Especially, the characters in set O
# as defined in the RFC (!"#$%&*;<=>@[]^_`{|}) may be encoded directly
# but are not allowed in, e.g., email headers.
# By default, the ICU UTF-7 converter encodes set O directly.
# By choosing the option "version=1", set O will be escaped instead.
# For example:
# utf7Converter=ucnv_open("UTF-7,version=1");
#
# For details about email headers see RFC 2047.
UTF-7 { IANA* MIME* WINDOWS } windows-65000 { WINDOWS* }
unicode-1-1-utf-7
unicode-2-0-utf-7
# UTF-EBCDIC doesn't exist in ICU, but the aliases are here for reference.
#UTF-EBCDIC ibm-1210 { IBM* } ibm-1211 { IBM }
# IMAP-mailbox-name is an ICU-specific name for the encoding of IMAP mailbox names.
# It is a substantially modified UTF-7 encoding. See the specification in:
#
# RFC 2060: INTERNET MESSAGE ACCESS PROTOCOL - VERSION 4rev1
# (http://www.ietf.org/rfc/rfc2060.txt)
# Section 5.1.3. Mailbox International Naming Convention
IMAP-mailbox-name
SCSU { IANA* }
ibm-1212 { IBM } # SCSU with IBM PUA
ibm-1213 { IBM* } # SCSU
BOCU-1 { IANA* }
csBOCU-1 { IANA }
ibm-1214 { IBM } # BOCU-1 with IBM PUA
ibm-1215 { IBM* } # BOCU-1
# See https://www.unicode.org/reports/tr26 for this Compatibility Encoding Scheme for UTF-16
# The Unicode Consortium does not encourage the use of CESU-8
CESU-8 { IANA* } ibm-9400 { IBM* }
# Standard iso-8859-1, which does not have the Euro update.
# See iso-8859-15 (latin9) for the Euro update
ISO-8859-1 { MIME* IANA JAVA* }
ibm-819 { IBM* JAVA } # This is not truely ibm-819 because it's missing the fallbacks.
IBM819 { IANA }
cp819 { IANA JAVA }
latin1 { IANA JAVA }
8859_1 { JAVA }
csISOLatin1 { IANA JAVA }
iso-ir-100 { IANA JAVA }
ISO_8859-1:1987 { IANA* JAVA }
l1 { IANA JAVA }
819 { JAVA }
# windows-28591 { WINDOWS* } # This has odd behavior because it has the Euro update, which isn't correct.
# LATIN_1 # Old ICU name
# ANSI_X3.110-1983 # This is for a different IANA alias. This isn't iso-8859-1.
US-ASCII { MIME* IANA JAVA WINDOWS }
ASCII { JAVA* IANA WINDOWS }
ANSI_X3.4-1968 { IANA* WINDOWS }
ANSI_X3.4-1986 { IANA WINDOWS }
ISO_646.irv:1991 { IANA WINDOWS }
iso_646.irv:1983 { JAVA }
ISO646-US { JAVA IANA WINDOWS }
us { IANA }
csASCII { IANA WINDOWS }
iso-ir-6 { IANA }
cp367 { IANA WINDOWS }
ascii7 { JAVA }
646 { JAVA }
windows-20127 { WINDOWS* }
ibm-367 { IBM* } IBM367 { IANA WINDOWS } # This is not truely ibm-367 because it's missing the fallbacks.
# GB 18030 is partly algorithmic, using the MBCS converter
gb18030-2022 ibm-1392 { IBM* } windows-54936 { WINDOWS* } GB18030 { MIME* IANA* }
# Table-based interchange codepages
# Central Europe
ibm-912_P100-1995 { UTR22* }
ibm-912 { IBM* JAVA }
ISO-8859-2 { MIME* IANA JAVA* WINDOWS }
ISO_8859-2:1987 { IANA* WINDOWS JAVA }
latin2 { IANA WINDOWS JAVA }
csISOLatin2 { IANA WINDOWS JAVA }
iso-ir-101 { IANA WINDOWS JAVA }
l2 { IANA WINDOWS JAVA }
8859_2 { JAVA }
cp912 { JAVA }
912 { JAVA }
windows-28592 { WINDOWS* }
# Maltese Esperanto
ibm-913_P100-2000 { UTR22* }
ibm-913 { IBM* JAVA }
ISO-8859-3 { MIME* IANA WINDOWS JAVA* }
ISO_8859-3:1988 { IANA* WINDOWS JAVA }
latin3 { IANA JAVA WINDOWS }
csISOLatin3 { IANA WINDOWS }
iso-ir-109 { IANA WINDOWS JAVA }
l3 { IANA WINDOWS JAVA }
8859_3 { JAVA }
cp913 { JAVA }
913 { JAVA }
windows-28593 { WINDOWS* }
# Baltic
ibm-914_P100-1995 { UTR22* }
ibm-914 { IBM* JAVA }
ISO-8859-4 { MIME* IANA WINDOWS JAVA* }
latin4 { IANA WINDOWS JAVA }
csISOLatin4 { IANA WINDOWS JAVA }
iso-ir-110 { IANA WINDOWS JAVA }
ISO_8859-4:1988 { IANA* WINDOWS JAVA }
l4 { IANA WINDOWS JAVA }
8859_4 { JAVA }
cp914 { JAVA }
914 { JAVA }
windows-28594 { WINDOWS* }
# Cyrillic
ibm-915_P100-1995 { UTR22* }
ibm-915 { IBM* JAVA }
ISO-8859-5 { MIME* IANA WINDOWS JAVA* }
cyrillic { IANA WINDOWS JAVA }
csISOLatinCyrillic { IANA WINDOWS JAVA }
iso-ir-144 { IANA WINDOWS JAVA }
ISO_8859-5:1988 { IANA* WINDOWS JAVA }
8859_5 { JAVA }
cp915 { JAVA }
915 { JAVA }
windows-28595 { WINDOWS* }
glibc-PT154-2.3.3 { UTR22* }
PTCP154 { IANA* }
csPTCP154
PT154
CP154
Cyrillic-Asian
# Arabic
# ISO_8859-6-E and ISO_8859-6-I are similar to this charset, but BiDi is done differently
# From a narrow mapping point of view, there is no difference.
# -E means explicit. -I means implicit.
# -E requires the client to handle the ISO 6429 bidirectional controls
ibm-1089_P100-1995 { UTR22* }
ibm-1089 { IBM* JAVA }
ISO-8859-6 { MIME* IANA WINDOWS JAVA* }
arabic { IANA WINDOWS JAVA }
csISOLatinArabic { IANA WINDOWS JAVA }
iso-ir-127 { IANA WINDOWS JAVA }
ISO_8859-6:1987 { IANA* WINDOWS JAVA }
ECMA-114 { IANA JAVA }
ASMO-708 { IANA JAVA }
8859_6 { JAVA }
cp1089 { JAVA }
1089 { JAVA }
windows-28596 { WINDOWS* }
ISO-8859-6-I { IANA MIME } # IANA considers this alias different and BiDi needs to be applied.
ISO-8859-6-E { IANA MIME } # IANA considers this alias different and BiDi needs to be applied.
x-ISO-8859-6S { JAVA }
# ISO Greek (with euro update). This is really ISO_8859-7:2003
ibm-9005_X110-2007 { UTR22* }
ibm-9005 { IBM* }
ISO-8859-7 { MIME* IANA JAVA* WINDOWS }
8859_7 { JAVA }
greek { IANA JAVA WINDOWS }
greek8 { IANA JAVA WINDOWS }
ELOT_928 { IANA JAVA WINDOWS }
ECMA-118 { IANA JAVA WINDOWS }
csISOLatinGreek { IANA JAVA WINDOWS }
iso-ir-126 { IANA JAVA WINDOWS }
ISO_8859-7:1987 { IANA* JAVA WINDOWS }
windows-28597 { WINDOWS* }
sun_eu_greek # For Solaris
# ISO Greek (w/o euro update)
# JDK 1.5 has these aliases.
ibm-813_P100-1995 { UTR22* }
ibm-813 { IBM* JAVA* }
cp813 { JAVA }
813 { JAVA }
# hebrew
# ISO_8859-8-E and ISO_8859-8-I are similar to this charset, but BiDi is done differently
# From a narrow mapping point of view, there is no difference.
# -E means explicit. -I means implicit.
# -E requires the client to handle the ISO 6429 bidirectional controls
# This matches the official mapping on unicode.org
ibm-5012_P100-1999 { UTR22* }
ibm-5012 { IBM* }
ISO-8859-8 { MIME* IANA WINDOWS JAVA* }
hebrew { IANA WINDOWS JAVA }
csISOLatinHebrew { IANA WINDOWS JAVA }
iso-ir-138 { IANA WINDOWS JAVA }
ISO_8859-8:1988 { IANA* WINDOWS JAVA }
ISO-8859-8-I { IANA MIME } # IANA and Windows considers this alias different and BiDi needs to be applied.
ISO-8859-8-E { IANA MIME } # IANA and Windows considers this alias different and BiDi needs to be applied.
8859_8 { JAVA }
windows-28598 { WINDOWS* } # Hebrew (ISO-Visual). A hybrid between ibm-5012 and ibm-916 with extra PUA mappings.
hebrew8 # Reflect HP-UX code page update
# Unfortunately, the Java aliases are split across ibm-916 and ibm-5012
# Also many platforms are a combination between ibm-916 and ibm-5012 behaviors
ibm-916_P100-1995 { UTR22* }
ibm-916 { IBM* JAVA* }
cp916 { JAVA }
916 { JAVA }
# Turkish
ibm-920_P100-1995 { UTR22* }
ibm-920 { IBM* JAVA }
ISO-8859-9 { MIME* IANA WINDOWS JAVA* }
latin5 { IANA WINDOWS JAVA }
csISOLatin5 { IANA JAVA }
iso-ir-148 { IANA WINDOWS JAVA }
ISO_8859-9:1989 { IANA* WINDOWS }
l5 { IANA WINDOWS JAVA }
8859_9 { JAVA }
cp920 { JAVA }
920 { JAVA }
windows-28599 { WINDOWS* }
ECMA-128 # IANA doesn't have this alias 6/24/2002
turkish8 # Reflect HP-UX codepage update 8/1/2008
turkish # Reflect HP-UX codepage update 8/1/2008
# Nordic languages
iso-8859_10-1998 { UTR22* } ISO-8859-10 { MIME* IANA* }
iso-ir-157 { IANA }
l6 { IANA }
ISO_8859-10:1992 { IANA }
csISOLatin6 { IANA }
latin6 { IANA }
# Thai
# Be warned. There several iso-8859-11 codepage variants, and they are all incompatible.
# ISO-8859-11 is a superset of TIS-620. The difference is that ISO-8859-11 contains the C1 control codes.
iso-8859_11-2001 { UTR22* } ISO-8859-11
thai8 # HP-UX alias. HP-UX says TIS-620, but it's closer to ISO-8859-11.
x-iso-8859-11 { JAVA* }
# iso-8859-13, PC Baltic (w/o euro update)
ibm-921_P100-1995 { UTR22* }
ibm-921 { IBM* }
ISO-8859-13 { IANA* MIME* JAVA* }
8859_13 { JAVA }
windows-28603 { WINDOWS* }
cp921
921
x-IBM921 { JAVA }
# Celtic
iso-8859_14-1998 { UTR22* } ISO-8859-14 { IANA* }
iso-ir-199 { IANA }
ISO_8859-14:1998 { IANA }
latin8 { IANA }
iso-celtic { IANA }
l8 { IANA }
# Latin 9
ibm-923_P100-1998 { UTR22* }
ibm-923 { IBM* JAVA }
ISO-8859-15 { IANA* MIME* WINDOWS JAVA* }
Latin-9 { IANA WINDOWS }
l9 { WINDOWS }
8859_15 { JAVA }
latin0 { JAVA }
csisolatin0 { JAVA }
csisolatin9 { JAVA }
iso8859_15_fdis { JAVA }
cp923 { JAVA }
923 { JAVA }
windows-28605 { WINDOWS* }
# CJK encodings
ibm-942_P12A-1999 { UTR22* } # ibm-942_P120 is a rarely used alternate mapping (sjis78 is already old)
ibm-942 { IBM* }
ibm-932 { IBM }
cp932
shift_jis78
sjis78
ibm-942_VSUB_VPUA
ibm-932_VSUB_VPUA
x-IBM942 { JAVA* }
x-IBM942C { JAVA }
# Is this "JIS_C6226-1978"?
# ibm-943_P15A-2003 differs from windows-932-2000 only in a few roundtrip mappings:
# - the usual IBM PC control code rotation (1A-1C-7F)
# - the Windows table has roundtrips for bytes 80, A0, and FD-FF to U+0080 and PUA
ibm-943_P15A-2003 { UTR22* }
ibm-943 # Leave untagged because this isn't the default
Shift_JIS { IANA* MIME* WINDOWS JAVA }
MS_Kanji { IANA WINDOWS JAVA }
csShiftJIS { IANA WINDOWS JAVA }
windows-31j { IANA JAVA } # A further extension of Shift_JIS to include NEC special characters (Row 13)
csWindows31J { IANA WINDOWS JAVA } # A further extension of Shift_JIS to include NEC special characters (Row 13)
x-sjis { WINDOWS JAVA }
x-ms-cp932 { WINDOWS }
cp932 { WINDOWS }
windows-932 { WINDOWS* }
cp943c { JAVA* } # This is slightly different, but the backslash mapping is the same.
IBM-943C #{ AIX* } # Add this tag once AIX aliases becomes available
ms932
pck # Probably SOLARIS
sjis # This might be for ibm-1351
ibm-943_VSUB_VPUA
x-MS932_0213 { JAVA }
x-JISAutoDetect { JAVA }
# cp943 # This isn't Windows, and no one else uses it.
# IANA says that Windows-31J is an extension to csshiftjis ibm-932
ibm-943_P130-1999 { UTR22* }
ibm-943 { IBM* JAVA }
Shift_JIS # Leave untagged because this isn't the default
cp943 { JAVA* } # This is slightly different, but the backslash mapping is the same.
943 { JAVA }
ibm-943_VASCII_VSUB_VPUA
x-IBM943 { JAVA }
# japanese. Unicode name is \u30b7\u30d5\u30c8\u7b26\u53f7\u5316\u8868\u73fe
ibm-33722_P12A_P12A-2009_U2 { UTR22* }
ibm-33722 # Leave untagged because this isn't the default
ibm-5050 # Leave untagged because this isn't the default, and yes this alias is correct
ibm-33722_VPUA
IBM-eucJP
windows-51932-2006 { UTR22* }
windows-51932 { WINDOWS* }
CP51932 { IANA* }
csCP51932
ibm-33722_P120-1999 { UTR22* } # Japan EUC with \ <-> Yen mapping
ibm-33722 { IBM* JAVA }
ibm-5050 { IBM } # Yes this is correct
cp33722 { JAVA* }
33722 { JAVA }
ibm-33722_VASCII_VPUA
x-IBM33722 { JAVA }
x-IBM33722A { JAVA }
x-IBM33722C { JAVA }
# ibm-954 seems to be almost a superset of ibm-33722 and ibm-1350
# ibm-1350 seems to be almost a superset of ibm-33722
# ibm-954 contains more PUA characters than the others.
ibm-954_P101-2007 { UTR22* }
ibm-954 { IBM* }
x-IBM954 { JAVA* }
x-IBM954C { JAVA }
# eucJP # This is closest to Solaris EUC-JP.
euc-jp-2007 { UTR22* }
EUC-JP { MIME* IANA JAVA* WINDOWS* }
Extended_UNIX_Code_Packed_Format_for_Japanese { IANA* JAVA WINDOWS }
csEUCPkdFmtJapanese { IANA JAVA WINDOWS }
X-EUC-JP { MIME JAVA WINDOWS } # Japan EUC. x-euc-jp is a MIME name
eucjis {JAVA}
ujis # Linux sometimes uses this name. This is an unfortunate generic and rarely used name. Its use is discouraged.
aix-IBM_udcJP-4.3.6 { UTR22* }
x-IBM-udcJP { JAVA* }
java-euc_jp_linux-1.6_P { UTR22* }
euc-jp-linux
x-EUC_JP_LINUX { JAVA* }
java-sjis_0213-1.6_P { UTR22* }
x-SJIS_0213 { JAVA* }
# Here are various interpretations and extensions of Big5
ibm-1373_P100-2002 { UTR22* } # IBM's interpretation of Windows' Taiwan Big-5 without HKSCS extensions
ibm-1373 { IBM* }
windows-950 # Alternate mapping. Leave untagged. This is the IBM interpretation of a Windows codepage.
windows-950-2000 { UTR22* }
Big5 { IANA* MIME* JAVA* WINDOWS }
csBig5 { IANA WINDOWS }
windows-950 { WINDOWS* }
x-windows-950 { JAVA }
x-big5
ms950
ibm-950_P110-1999 { UTR22* } # Taiwan Big-5 (w/o euro update)
ibm-950 { IBM* JAVA }
cp950 { JAVA* }
950 { JAVA }
x-IBM950 { JAVA }
ibm-1375_P100-2008 { UTR22* } # Big5-HKSCS-2004 with Unicode 3.1 mappings. This uses supplementary characters.
ibm-1375 { IBM* }
Big5-HKSCS { IANA* JAVA* }
big5hk { JAVA }
HKSCS-BIG5 # From http://www.openi18n.org/localenameguide/
ibm-5471_P100-2006 { UTR22* } # Big5-HKSCS-2001 with Unicode 3.0 mappings. This uses many PUA characters.
ibm-5471 { IBM* }
Big5-HKSCS
MS950_HKSCS { JAVA* }
hkbig5 # from HP-UX 11i, which can't handle supplementary characters.
big5-hkscs:unicode3.0
x-MS950-HKSCS { JAVA }
# windows-950 # Windows-950 can be w/ or w/o HKSCS extensions. By default it's not.
# windows-950_hkscs
solaris-zh_TW_big5-2.7 { UTR22* }
Big5_Solaris { JAVA* }
x-Big5-Solaris { JAVA }
# GBK
ibm-1386_P100-2001 { UTR22* }
ibm-1386 { IBM* }
cp1386
windows-936 # Alternate mapping. Leave untagged. This is the IBM interpretation of a Windows codepage.
ibm-1386_VSUB_VPUA
windows-936-2000 { UTR22* }
GBK { IANA* WINDOWS JAVA* }
CP936 { IANA JAVA }
MS936 { IANA } # In JDK 1.5, this goes to x-mswin-936. This is an IANA name split.
windows-936 { IANA WINDOWS* JAVA }
# Java has two different tables for ibm-1383 and gb2312. We pick closest set for tagging.
ibm-1383_P110-1999 { UTR22* } # China EUC.
ibm-1383 { IBM* JAVA }
GB2312 { IANA* MIME* }
csGB2312 { IANA }
cp1383 { JAVA* }
1383 { JAVA }
EUC-CN # According to other platforms, windows-20936 looks more like euc-cn. x-euc-cn is also a MIME name
ibm-eucCN
hp15CN # From HP-UX?
ibm-1383_VPUA
# gb # This is not an IANA name. gb in IANA means Great Britain.
ibm-5478_P100-1995 { UTR22* } ibm-5478 { IBM* } # This gb_2312_80 DBCS mapping is needed by iso-2022.
GB_2312-80 { IANA* } # Windows maps this alias incorrectly
chinese { IANA }
iso-ir-58 { IANA }
csISO58GB231280 { IANA }
gb2312-1980
GB2312.1980-0 # From X11R6
euc-tw-2014 { UTR22* } # Updated EUC-TW converter based on ibm-964
EUC-TW
ibm-964_P110-1999 { UTR22* } # Taiwan EUC. x-euc-tw is a MIME name
ibm-964 { IBM* JAVA }
ibm-eucTW
cns11643
cp964 { JAVA* }
964 { JAVA }
ibm-964_VPUA
x-IBM964 { JAVA }
# ISO-2022 needs one, and other people may need others.
ibm-949_P110-1999 { UTR22* }
ibm-949 { IBM* JAVA }
cp949 { JAVA* }
949 { JAVA }
ibm-949_VASCII_VSUB_VPUA
x-IBM949 { JAVA }
ibm-949_P11A-1999 { UTR22* }
ibm-949 # Leave untagged because this isn't the default
cp949c { JAVA* }
ibm-949_VSUB_VPUA
x-IBM949C { JAVA }
IBM-949C { JAVA }
# Korean EUC.
#
# <quote from="Jungshik Shin">
# 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.
#
# Although widely spread on MS Windows, using
# KS C 5601 or related names to denote EUC-KR or
# windows-949 is very much misleading. KS C 5601-1987
# is NOT suitable as a designation for MIME charset
# and MBCS. It's just the name of a 94 x 94 Korean
# coded character set standard which can be invoked
# on either GL (with MSB reset) or GR (with MSB set).
# Note that JOHAB (windows-1361) specified in
# KS X 1001:1998 annex 3 (KS C 5601-1992 annex 3)
# is a _seprate_ MBCS with a _completely different_
# mapping.
# </quote>
#
# The following aliases tries to mirror the poor state of alias recognition
# on these platforms.
#
# ibm-970 is almost a subset of ibm-1363.
# Java, Solaris and AIX use euc-kr to also mean ksc5601.
# Java has both ibm-970 and EUC-KR as separate converters.
ibm-970_P110_P110-2006_U2 { UTR22* }
ibm-970 { IBM* JAVA }
EUC-KR { IANA* MIME* WINDOWS JAVA }
KS_C_5601-1987 { JAVA }
windows-51949 { WINDOWS* }
csEUCKR { IANA WINDOWS } # x-euc-kr is also a MIME name
ibm-eucKR { JAVA }
KSC_5601 { JAVA } # Needed by iso-2022
5601 { JAVA }
cp970 { JAVA* }
970 { JAVA }
ibm-970_VPUA
x-IBM970 { JAVA }
# ibm-971 is almost the set of DBCS mappings of ibm-970
ibm-971_P100-1995 ibm-971 { IBM* } ibm-971_VPUA x-IBM971 { JAVA* }
# Java, Solaris and AIX use euc-kr to also mean ksc5601, and _sometimes_ for Windows too.
# ibm-1363 is almost a superset of ibm-970.
ibm-1363_P11B-1998 { UTR22* }
ibm-1363 # Leave untagged because this isn't the default
KS_C_5601-1987 { IANA* }
KS_C_5601-1989 { IANA }
KSC_5601 { IANA }
csKSC56011987 { IANA }
korean { IANA }
iso-ir-149 { IANA }
cp1363 { MIME* }
5601
ksc
windows-949 # Alternate mapping. Leave untagged. This is the IBM interpretation of a Windows codepage.
ibm-1363_VSUB_VPUA
x-IBM1363C { JAVA* }
# ks_x_1001:1992
# ksc5601-1992
ibm-1363_P110-1997 { UTR22* } # Korean KSC MBCS with \ <-> Won mapping
ibm-1363 { IBM* }
ibm-1363_VASCII_VSUB_VPUA
x-IBM1363 { JAVA* }
windows-949-2000 { UTR22* }
windows-949 { JAVA* WINDOWS* }
KS_C_5601-1987 { WINDOWS }
KS_C_5601-1989 { WINDOWS }
KSC_5601 { MIME* WINDOWS } # Needed by iso-2022
csKSC56011987 { WINDOWS }
korean { WINDOWS }
iso-ir-149 { WINDOWS }
ms949 { JAVA }
x-KSC5601 { JAVA }
windows-1361-2000 { UTR22* }
ksc5601_1992
ms1361
johab
x-Johab { JAVA* }
windows-874-2000 { UTR22* } # Thai (w/ euro update)
TIS-620 { WINDOWS }
windows-874 { JAVA* WINDOWS* }
MS874 { JAVA }
x-windows-874 { JAVA }
# iso-8859-11 { WINDOWS } # iso-8859-11 is similar to TIS-620. ibm-13162 is a closer match.
ibm-874_P100-1995 { UTR22* } # Thai PC (w/o euro update).
ibm-874 { IBM* JAVA }
ibm-9066 { IBM } # Yes ibm-874 == ibm-9066. ibm-1161 has the euro update.
cp874 { JAVA* }
TIS-620 { IANA* JAVA } # This is actually separate from ibm-874, which is similar to this table
tis620.2533 { JAVA } # This is actually separate from ibm-874, which is similar to this table
eucTH # eucTH is an unusual alias from Solaris. eucTH has fewer mappings than TIS620
x-IBM874 { JAVA }
ibm-1162_P100-1999 { UTR22* } # Thai (w/ euro update)
ibm-1162 { IBM* }
windows-864-2000 { UTR22* }
ibm-864s
cp864s
x-IBM864S { JAVA* }
# Platform codepages
# If Java supports the IBM prefix, it should also support the ibm- prefix too.
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
ibm-720_P100-1997 { UTR22* } ibm-720 { IBM* } windows-720 { WINDOWS* } DOS-720 { WINDOWS } x-IBM720 { JAVA* } # PC Arabic
ibm-737_P100-1997 { UTR22* } ibm-737 { IBM* } IBM737 { WINDOWS JAVA } cp737 { JAVA* } windows-737 { WINDOWS* } 737 { JAVA } x-IBM737 { JAVA } # PC Greek
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
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
ibm-851_P100-1995 { UTR22* } ibm-851 { IBM* } IBM851 { IANA* } cp851 { IANA MIME* } 851 { IANA } csPC851 { IANA } # PC DOS Greek (w/o euro)
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)
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)
ibm-856_P100-1995 { UTR22* } ibm-856 { IBM* } IBM856 { JAVA } cp856 { JAVA* } 856 { JAVA } x-IBM856 { JAVA } # PC Hebrew implicit order
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)
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
ibm-860_P100-1995 { UTR22* } ibm-860 { IBM* } IBM860 { IANA* MIME* JAVA } cp860 { IANA MIME JAVA* } 860 { IANA JAVA } csIBM860 { IANA JAVA } # PC Portugal
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
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)
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
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)
ibm-865_P100-1995 { UTR22* } ibm-865 { IBM* } IBM865 { IANA* MIME* JAVA } cp865 { IANA MIME JAVA* } 865 { IANA JAVA } csIBM865 { IANA JAVA } # PC Nordic
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)
ibm-867_P100-1998 { UTR22* } ibm-867 { IBM* } x-IBM867 { JAVA* } # PC Hebrew (w/ euro update) Updated version of ibm-862
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
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)
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
ibm-901_P100-1999 { UTR22* } ibm-901 { IBM* } # PC Baltic (w/ euro update), update of ibm-921
ibm-902_P100-1999 { UTR22* } ibm-902 { IBM* } # PC Estonian (w/ euro update), update of ibm-922
ibm-922_P100-1999 { UTR22* } ibm-922 { IBM* } IBM922 { JAVA } cp922 { JAVA* } 922 { JAVA } x-IBM922 { JAVA } # PC Estonian (w/o euro update)
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.
ibm-4909_P100-1999 { UTR22* } ibm-4909 { IBM* } # ISO Greek (w/ euro update), update of ibm-813
# The cp aliases in this section aren't really windows aliases, but it was used by ICU for Windows.
# cp is usually used to denote IBM in Java, and that is why we don't do that anymore.
# The windows-* aliases mean windows codepages.
ibm-5346_P100-1998 { UTR22* } ibm-5346 { IBM* } windows-1250 { IANA* JAVA* WINDOWS* } cp1250 { WINDOWS JAVA } # Windows Latin2 (w/ euro update)
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
ibm-5348_P100-1997 { UTR22* } ibm-5348 { IBM* } windows-1252 { IANA* JAVA* WINDOWS* } cp1252 { JAVA } # Windows Latin1 (w/ euro update)
ibm-5349_P100-1998 { UTR22* } ibm-5349 { IBM* } windows-1253 { IANA* JAVA* WINDOWS* } cp1253 { JAVA } # Windows Greek (w/ euro update)
ibm-5350_P100-1998 { UTR22* } ibm-5350 { IBM* } windows-1254 { IANA* JAVA* WINDOWS* } cp1254 { JAVA } # Windows Turkish (w/ euro update)
ibm-9447_P100-2002 { UTR22* } ibm-9447 { IBM* } windows-1255 { IANA* JAVA* WINDOWS* } cp1255 { JAVA } # Windows Hebrew (w/ euro update)
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)
ibm-9449_P100-2002 { UTR22* } ibm-9449 { IBM* } windows-1257 { IANA* JAVA* WINDOWS* } cp1257 { JAVA } # Windows Baltic (w/ euro update)
ibm-5354_P100-1998 { UTR22* } ibm-5354 { IBM* } windows-1258 { IANA* JAVA* WINDOWS* } cp1258 { JAVA } # Windows Vietnamese (w/ euro update)
# These tables are out of date, and most don't have the Euro
# Leave the windows- variants untagged. They are alternate tables of the newer ones above.
ibm-1250_P100-1995 { UTR22* } ibm-1250 { IBM* } windows-1250 # Old Windows Latin2 (w/o euro update)
ibm-1251_P100-1995 { UTR22* } ibm-1251 { IBM* } windows-1251 # Old Windows Cyrillic (w/o euro update)
ibm-1252_P100-2000 { UTR22* } ibm-1252 { IBM* } windows-1252 # Old Windows Latin 1 without Euro
ibm-1253_P100-1995 { UTR22* } ibm-1253 { IBM* } windows-1253 # Old Windows Greek (w/o euro update)
ibm-1254_P100-1995 { UTR22* } ibm-1254 { IBM* } windows-1254 # Old Windows Turkish (w/o euro update)
ibm-1255_P100-1995 { UTR22* } ibm-1255 { IBM* } # Very old Windows Hebrew (w/o euro update)
ibm-5351_P100-1998 { UTR22* } ibm-5351 { IBM* } windows-1255 # Old Windows Hebrew (w/ euro update)
ibm-1256_P110-1997 { UTR22* } ibm-1256 { IBM* } # Old Windows Arabic (w/o euro update)
ibm-5352_P100-1998 { UTR22* } ibm-5352 { IBM* } windows-1256 # Somewhat old Windows Arabic (w/ euro update)
ibm-1257_P100-1995 { UTR22* } ibm-1257 { IBM* } # Old Windows Baltic (w/o euro update)
ibm-5353_P100-1998 { UTR22* } ibm-5353 { IBM* } windows-1257 # Somewhat old Windows Baltic (w/ euro update)
ibm-1258_P100-1997 { UTR22* } ibm-1258 { IBM* } windows-1258 # Old Windows Vietnamese (w/o euro update)
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
macos-6_2-10.4 { UTR22* } x-mac-greek { MIME* WINDOWS } windows-10006 { WINDOWS* } macgr x-MacGreek { JAVA* } # Apple Greek
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
macos-21-10.5 { UTR22* } x-mac-thai { MIME* } x-MacThai { JAVA* } MacThai { JAVA }
macos-29-10.2 { UTR22* } x-mac-centraleurroman { MIME* } windows-10029 { WINDOWS* } x-mac-ce { WINDOWS } macce maccentraleurope x-MacCentralEurope { JAVA* } # Apple Central Europe
macos-33-10.5 { UTR22* } x-mac-symbol { MIME* } x-MacSymbol { JAVA* } MacSymbol { JAVA }
macos-34-10.2 { UTR22* } x-mac-dingbat { MIME* } x-MacDingbat { JAVA* } MacDingbat { JAVA }
macos-35-10.2 { UTR22* } x-mac-turkish { MIME* WINDOWS } windows-10081 { WINDOWS* } mactr x-MacTurkish { JAVA* } # Apple Turkish
macos-36_2-10.2 { UTR22* } x-mac-croatian { MIME* } x-MacCroatian { JAVA* } MacCroatian { JAVA }
macos-37_5-10.2 { UTR22* } x-mac-iceland { MIME* } x-MacIceland { JAVA* } MacIceland { JAVA }
macos-38_2-10.2 { UTR22* } x-mac-romania { MIME* } x-MacRomania { JAVA* } MacRomania { JAVA }
macos-518-10.2 { UTR22* } x-mac-arabic { MIME* } x-MacArabic { JAVA* } MacArabic { JAVA }
macos-1285-10.2 { UTR22* } x-mac-hebrew { MIME* } x-MacHebrew { JAVA* } MacHebrew { JAVA }
ibm-1051_P100-1995 { UTR22* } ibm-1051 { IBM* } hp-roman8 { IANA* } roman8 { IANA } r8 { IANA } csHPRoman8 { IANA } x-roman8 { JAVA* } # HP Latin1
ibm-1276_P100-1995 { UTR22* } ibm-1276 { IBM* } Adobe-Standard-Encoding { IANA* } csAdobeStandardEncoding { IANA } # Different from ISO-Unicode-IBM-1276 (GCSGID: 1276)
ibm-1006_P100-1995 { UTR22* } ibm-1006 { IBM* } IBM1006 { JAVA } cp1006 { JAVA* } 1006 { JAVA } x-IBM1006 { JAVA } # Urdu
ibm-1098_P100-1995 { UTR22* } ibm-1098 { IBM* } IBM1098 { JAVA } cp1098 { JAVA* } 1098 { JAVA } x-IBM1098 { JAVA } # PC Farsi
ibm-1124_P100-1996 { UTR22* } ibm-1124 { IBM* JAVA } cp1124 { JAVA* } 1124 { JAVA } x-IBM1124 { JAVA } # ISO Cyrillic Ukraine
ibm-1125_P100-1997 { UTR22* } ibm-1125 { IBM* } cp1125 # Cyrillic Ukraine PC
ibm-1129_P100-1997 { UTR22* } ibm-1129 { IBM* } # ISO Vietnamese
ibm-1131_P100-1997 { UTR22* } ibm-1131 { IBM* } cp1131 # Cyrillic Belarus PC
ibm-1133_P100-1997 { UTR22* } ibm-1133 { IBM* } # ISO Lao
# GSM 03.38
gsm-03.38-2009 { UTR22* } GSM0338 # GSM0338 alias is from Perl
# Partially algorithmic converters
# [U_ENABLE_GENERIC_ISO_2022]
# The _generic_ ISO-2022 converter is disabled starting 2003-dec-03 (ICU 2.8).
# For details see the icu mailing list from 2003-dec-01 and the ucnv2022.c file.
# Language-specific variants of ISO-2022 continue to be available as listed below.
# ISO_2022 ISO-2022
ISO_2022,locale=ja,version=0 ISO-2022-JP { IANA* MIME* JAVA* } csISO2022JP { IANA JAVA } x-windows-iso2022jp { JAVA } x-windows-50220 { JAVA }
ISO_2022,locale=ja,version=1 ISO-2022-JP-1 { MIME* } JIS_Encoding { IANA* } csJISEncoding { IANA } ibm-5054 { IBM* } JIS x-windows-50221 { JAVA* }
ISO_2022,locale=ja,version=2 ISO-2022-JP-2 { IANA* MIME* } csISO2022JP2 { IANA }
ISO_2022,locale=ja,version=3 JIS7
ISO_2022,locale=ja,version=4 JIS8
ISO_2022,locale=ko,version=0 ISO-2022-KR { IANA* MIME* JAVA* } csISO2022KR { IANA JAVA } # This uses ibm-949
ISO_2022,locale=ko,version=1 ibm-25546 { IBM* }
ISO_2022,locale=zh,version=0 ISO-2022-CN { IANA* JAVA* } csISO2022CN { JAVA } x-ISO-2022-CN-GB { JAVA }
ISO_2022,locale=zh,version=1 ISO-2022-CN-EXT { IANA* }
ISO_2022,locale=zh,version=2 ISO-2022-CN-CNS x-ISO-2022-CN-CNS { JAVA* }
HZ HZ-GB-2312 { IANA* }
x11-compound-text COMPOUND_TEXT x-compound-text { JAVA* }
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.
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.
ISCII,version=2 x-iscii-pa { WINDOWS } windows-57011 { WINDOWS* } iscii-gur
ISCII,version=3 x-iscii-gu { WINDOWS } windows-57010 { WINDOWS* } iscii-guj
ISCII,version=4 x-iscii-or { WINDOWS } windows-57007 { WINDOWS* } iscii-ori
ISCII,version=5 x-iscii-ta { WINDOWS } windows-57004 { WINDOWS* } iscii-tml
ISCII,version=6 x-iscii-te { WINDOWS } windows-57005 { WINDOWS* } iscii-tlg
ISCII,version=7 x-iscii-ka { WINDOWS } windows-57008 { WINDOWS* } iscii-knd
ISCII,version=8 x-iscii-ma { WINDOWS } windows-57009 { WINDOWS* } iscii-mlm
# Lotus specific
LMBCS-1 lmbcs ibm-65025 { IBM* }
# These Lotus specific converters still work, but they aren't advertised in this alias table.
# These are almost never used outside of Lotus software,
# and they take a lot of time when creating the available converter list.
# Also Lotus doesn't really use them anyway. It was a mistake to create these LMBCS variant converters in ICU.
#LMBCS-2
#LMBCS-3
#LMBCS-4
#LMBCS-5
#LMBCS-6
#LMBCS-8
#LMBCS-11
#LMBCS-16
#LMBCS-17
#LMBCS-18
#LMBCS-19
# EBCDIC codepages according to the CDRA
# without Euro
ibm-37_P100-1995 { UTR22* } # EBCDIC US
ibm-37 { IBM* }
IBM037 { IANA* JAVA }
ibm-037 # { JAVA }
ebcdic-cp-us { IANA JAVA }
ebcdic-cp-ca { IANA JAVA }
ebcdic-cp-wt { IANA JAVA }
ebcdic-cp-nl { IANA JAVA }
csIBM037 { IANA JAVA }
cp037 { JAVA* }
037 { JAVA }
cpibm37 { JAVA }
cp37
ibm-273_P100-1995 { UTR22* } ibm-273 { IBM* } IBM273 { IANA* JAVA } CP273 { IANA JAVA* } csIBM273 { IANA } ebcdic-de 273 { JAVA } # EBCDIC Germanay, Austria
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
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
ibm-280_P100-1995 { UTR22* } ibm-280 { IBM* } IBM280 { IANA* JAVA } CP280 { IANA JAVA* } ebcdic-cp-it { IANA } csIBM280 { IANA } 280 { JAVA } # EBCDIC Italy
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
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
ibm-290_P100-1995 { UTR22* } ibm-290 { IBM* } IBM290 { IANA* } cp290 { IANA } EBCDIC-JP-kana { IANA } csIBM290 { IANA } # host SBCS (Katakana)
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
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)
ibm-424_P100-1995 { UTR22* } ibm-424 { IBM* } IBM424 { IANA* JAVA } cp424 { IANA JAVA* } ebcdic-cp-he { IANA } csIBM424 { IANA } 424 { JAVA } # EBCDIC Hebrew
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
ibm-803_P100-1999 { UTR22* } ibm-803 { IBM* } cp803 # Old EBCDIC Hebrew
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.
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
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
ibm-875_P100-1995 { UTR22* } ibm-875 { IBM* } IBM875 { JAVA } cp875 { JAVA* } 875 { JAVA } x-IBM875 { JAVA } # EBCDIC Greek
ibm-918_P100-1995 { UTR22* } ibm-918 { IBM* } IBM918 { IANA* JAVA } CP918 { IANA JAVA* } ebcdic-cp-ar2 { IANA } csIBM918 { IANA } # EBCDIC Urdu
ibm-930_P120-1999 { UTR22* } # EBCDIC_STATEFUL Katakana-Kanji Host Mixed.
ibm-930 { IBM* }
ibm-5026 { IBM } # Yes this is correct
IBM930 { JAVA }
cp930 { JAVA* }
930 { JAVA }
x-IBM930 { JAVA }
x-IBM930A { JAVA }
ibm-933_P110-1995 { UTR22* } ibm-933 { IBM* JAVA } cp933 { JAVA* } 933 { JAVA } x-IBM933 { JAVA } # Korea EBCDIC MIXED
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.
ibm-937_P110-1999 { UTR22* } ibm-937 { IBM* JAVA } cp937 { JAVA* } 937 { JAVA } x-IBM937 { JAVA } # Taiwan EBCDIC MIXED
ibm-939_P120-1999 { UTR22* } # EBCDIC_STATEFUL Latin-Kanji Host Mixed.
ibm-939 { IBM* }
ibm-931 { IBM } # Yes this is correct
ibm-5035 { IBM } # Yes this is also correct
IBM939 { JAVA }
cp939 { JAVA* }
939 { JAVA }
x-IBM939 { JAVA }
x-IBM939A { JAVA }
ibm-1025_P100-1995 { UTR22* } ibm-1025 { IBM* JAVA } cp1025 { JAVA* } 1025 { JAVA } x-IBM1025 { JAVA } # EBCDIC Cyrillic
ibm-1026_P100-1995 { UTR22* } ibm-1026 { IBM* } IBM1026 { IANA* JAVA } CP1026 { IANA JAVA* } csIBM1026 { IANA } 1026 { JAVA } # EBCDIC Turkey
ibm-1047_P100-1995 { UTR22* } ibm-1047 { IBM* } IBM1047 { IANA* JAVA } cp1047 { JAVA* } 1047 { JAVA } # EBCDIC Open systems Latin1
ibm-1097_P100-1995 { UTR22* } ibm-1097 { IBM* JAVA } cp1097 { JAVA* } 1097 { JAVA } x-IBM1097 { JAVA } # EBCDIC Farsi
ibm-1112_P100-1995 { UTR22* } ibm-1112 { IBM* JAVA } cp1112 { JAVA* } 1112 { JAVA } x-IBM1112 { JAVA } # EBCDIC Baltic
ibm-1114_P100-2001 { UTR22* } ibm-1114 { IBM* } x-IBM1114 { JAVA* }
ibm-1115_P100-1995 { UTR22* } ibm-1115 { IBM* } x-IBM1115 { JAVA* }
ibm-1122_P100-1999 { UTR22* } ibm-1122 { IBM* JAVA } cp1122 { JAVA* } 1122 { JAVA } x-IBM1122 { JAVA } # EBCDIC Estonia
ibm-1123_P100-1995 { UTR22* } ibm-1123 { IBM* JAVA } cp1123 { JAVA* } 1123 { JAVA } x-IBM1123 { JAVA } # EBCDIC Cyrillic Ukraine
ibm-1130_P100-1997 { UTR22* } ibm-1130 { IBM* } # EBCDIC Vietnamese
ibm-1132_P100-1998 { UTR22* } ibm-1132 { IBM* } # EBCDIC Lao
ibm-1137_P100-1999 { UTR22* } ibm-1137 { IBM* } # Devanagari EBCDIC (based on Unicode character set)
ibm-4517_P100-2005 { UTR22* } ibm-4517 { IBM* } # EBCDIC Arabic. Update of ibm-421
# with Euro
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
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
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
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
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
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
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
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
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
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
ibm-1153_P100-1999 { UTR22* } ibm-1153 { IBM* } IBM1153 { JAVA } x-IBM1153 { JAVA* } # EBCDIC latin 2
ibm-1154_P100-1999 { UTR22* } ibm-1154 { IBM* } # EBCDIC Cyrillic Multilingual
ibm-1155_P100-1999 { UTR22* } ibm-1155 { IBM* } # EBCDIC Turkey
ibm-1156_P100-1999 { UTR22* } ibm-1156 { IBM* } # EBCDIC Baltic Multilingual
ibm-1157_P100-1999 { UTR22* } ibm-1157 { IBM* } # EBCDIC Estonia
ibm-1158_P100-1999 { UTR22* } ibm-1158 { IBM* } # EBCDIC Cyrillic Ukraine
ibm-1160_P100-1999 { UTR22* } ibm-1160 { IBM* } # EBCDIC Thailand
ibm-1164_P100-1999 { UTR22* } ibm-1164 { IBM* } # EBCDIC Viet Nam
ibm-1364_P110-2007 { UTR22* } ibm-1364 { IBM* } x-IBM1364 { JAVA* } # Korean Host Mixed
ibm-1370_P100-1999 { UTR22* } ibm-1370 { IBM* } x-IBM1370 { JAVA* }
ibm-1371_P100-1999 { UTR22* } ibm-1371 { IBM* } x-IBM1371 { JAVA* } # Taiwan EBCDIC MIXED (Euro update of ibm-937)
ibm-1388_P100-2024 { UTR22* } ibm-1388 { IBM* } ibm-9580 { IBM } x-IBM1388 { JAVA* } # S-Ch DBCS-Host Data GBK EBCDIC_STATEFUL. Yes ibm-9580 is an alias.
ibm-1390_P110-2003 { UTR22* } ibm-1390 { IBM* } x-IBM1390 { JAVA* } # Japan EBCDIC MIXED (JIS X 0213)
ibm-1399_P110-2003 { UTR22* } ibm-1399 { IBM* } x-IBM1399 { JAVA* } # Host MBCS (Latin-Kanji) (JIS X 0213)
ibm-5123_P100-1999 { UTR22* } ibm-5123 { IBM* } # Host Roman Jis. Euro update of ibm-1027. SBCS portion of ibm-1390.
ibm-8482_P100-1999 { UTR22* } ibm-8482 { IBM* } # host SBCS (Katakana). Euro update of ibm-290. SBCS portion of ibm-1399.
# Yes ibm-20780 is the same as ibm-16684
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).
ibm-4899_P100-1998 { UTR22* } ibm-4899 { IBM* } # Old EBCDIC Hebrew. Update of ibm-803
ibm-4971_P100-1999 { UTR22* } ibm-4971 { IBM* } # EBCDIC Greek. Update of ibm-875 and superceded by ibm-9067
ibm-9067_X100-2005 { UTR22* } ibm-9067 { IBM* } # EBCDIC Greek. Update of ibm-875 and ibm-4971
ibm-12712_P100-1998 { UTR22* } ibm-12712 { IBM* } ebcdic-he # EBCDIC Hebrew (new sheqel, control characters update). Update of ibm-424
ibm-16804_X110-1999 { UTR22* } ibm-16804 { IBM* } ebcdic-ar # EBCDIC Arabic. Update of ibm-420
java-Cp1399A-1.6_P { UTR22* } x-IBM1399A { JAVA* }
java-Cp420s-1.6_P { UTR22* } x-IBM420S { JAVA* }
java-Cp1390A-1.6_P { UTR22* } x-IBM1390A { JAVA* }
# EBCDIC codepages for S/390, with LF and NL codes swapped
# Starting with ICU 2.4, the swapping is done by modifying the
# normal tables at runtime instead of at build time.
# Append UCNV_SWAP_LFNL_OPTION_STRING to the "ibm-CCSID" name to select this.
#
# Example: "ibm-1047,swaplfnl" or "ibm-1047" UCNV_SWAP_LFNL_OPTION_STRING
#
# This avoids the duplication of all EBCDIC SBCS and mixed-SBCS/DBCS
# mapping files.
# Some examples below for declaring old-style, obsolete aliases with the "-s390"
--> --------------------
--> maximum size reached
--> --------------------
