697 lines
33 KiB
Plaintext
697 lines
33 KiB
Plaintext
# *******************************************************************************
|
|
# *
|
|
# * Copyright (C) 1995-2002, International Business Machines
|
|
# * Corporation and others. All Rights Reserved.
|
|
# *
|
|
# *******************************************************************************
|
|
|
|
# IMPORTANT NOTE
|
|
#
|
|
# This file is not read directly by ICU. If you change it, you need to
|
|
# run gencnval, and eventually pkgdata to update the representation that
|
|
# ICU uses for aliases.
|
|
|
|
# Please be friendly to the rest of use that edit this table by
|
|
# keeping this table free of tabs.
|
|
|
|
# This is an alias file used by the character set converter.
|
|
#
|
|
# Format:
|
|
#
|
|
# Actual file name || Algorithm name alias1 alias2 ...
|
|
#
|
|
# except for column 1 (file names) case insensitive. Names are separated
|
|
# by whitespace.
|
|
#
|
|
# 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().
|
|
#
|
|
# Here is a list of tags used in this file:
|
|
#
|
|
# IANA The IANA charset name, as documented in RFC 1700.
|
|
# MIME The MIME charset name, used for content type tagging.
|
|
#
|
|
# 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 unique charset names, we are forced to
|
|
# make this table much more static than before.
|
|
|
|
# It means that a new encoding, 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 encoding 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).
|
|
|
|
# Especially, 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
|
|
|
|
# Name matching is case-insensitive. Also, dashes '-', underscores '_'
|
|
# and spaces ' ' are ignored in names (thus cs-iso-latin-1 and csisolatin1
|
|
# 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.
|
|
|
|
|
|
|
|
# This is the 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 general ordering is from specific and frequently used to more general
|
|
# or rarely used.
|
|
{ UTR22 # Name format specified by http://www.unicode.org/unicode/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 cp*
|
|
JAVA # Source: Sun JDK. Preferred name must be an exact match. 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* } ibm-1208 { IBM* }
|
|
ibm-1209 { IBM }
|
|
ibm-5304 { IBM }
|
|
ibm-5305 { IBM }
|
|
cp1208
|
|
cp65001
|
|
|
|
# The ICU 2.2 UTF-16/32 converters detect and write a BOM.
|
|
UTF-16 { IANA* MIME* } ISO-10646-UCS-2 { IANA } csUnicode ucs-2
|
|
UTF-16BE { IANA* MIME* } UTF16_BigEndian
|
|
x-utf-16be
|
|
ibm-1200 { IBM* }
|
|
ibm-1201 { IBM }
|
|
ibm-5297 { IBM }
|
|
ibm-13488 { IBM }
|
|
ibm-17584 { IBM }
|
|
cp1201
|
|
UTF-16LE { IANA* MIME* } UTF16_LittleEndian
|
|
x-utf-16le
|
|
ibm-1202 { IBM* }
|
|
ibm-13490 { IBM }
|
|
ibm-17586 { IBM }
|
|
cp1200
|
|
|
|
UTF-32 { IANA* MIME* } ISO-10646-UCS-4 { IANA } csUCS4 ucs-4
|
|
UTF-32BE { IANA* } UTF32_BigEndian ibm-1232 { IBM* } ibm-1233 { IBM }
|
|
UTF-32LE { IANA* } UTF32_LittleEndian ibm-1234 { IBM* }
|
|
|
|
# ICU-specific names for special uses
|
|
UTF16_PlatformEndian
|
|
UTF16_OppositeEndian
|
|
|
|
UTF32_PlatformEndian
|
|
UTF32_OppositeEndian
|
|
|
|
# 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* } cp65000
|
|
|
|
# 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* }
|
|
BOCU-1 { IANA* } csBOCU-1 { IANA }
|
|
|
|
# See http://www.unicode.org/unicode/reports/tr26 for this Compatibility Encoding Scheme for UTF-16
|
|
# The Unicode Consortium does not encourage the use of CESU-8
|
|
CESU-8 { IANA* }
|
|
|
|
# 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 }
|
|
LATIN_1 # Old ICU name
|
|
ibm-819 { IBM* } # This is not truely ibm-819 because it's missing the fallbacks.
|
|
IBM819 { IANA }
|
|
cp819 { IANA }
|
|
latin1 { IANA }
|
|
8859-1
|
|
csISOLatin1 { IANA }
|
|
iso-ir-100 { IANA }
|
|
ISO_8859-1:1987 { IANA* }
|
|
l1 { IANA }
|
|
819
|
|
# ANSI_X3.110-1983 # This is for a different IANA alias. This isn't iso-8859-1.
|
|
|
|
US-ASCII { MIME* IANA }
|
|
ASCII { JAVA* IANA }
|
|
ascii-7 { JAVA }
|
|
ANSI_X3.4-1968 { IANA* }
|
|
ANSI_X3.4-1986 { IANA }
|
|
ISO_646.irv:1991 { IANA }
|
|
iso_646.irv:1983 { JAVA }
|
|
ISO646-US { JAVA IANA }
|
|
us { IANA }
|
|
csASCII { IANA }
|
|
646 { JAVA }
|
|
iso-ir-6 { IANA }
|
|
cp367 { IANA }
|
|
# IBM367 { IANA } # Leave this on ibm-367 so it can have an IANA name
|
|
# Java says "default" too, but that makes no sense.
|
|
|
|
# Partially algorithmic converters
|
|
|
|
ISO_2022 ISO-2022 { MIME* } 2022 cp2022
|
|
ISO_2022,locale=ja,version=0 ISO-2022-JP { IANA* MIME* } csISO2022JP
|
|
ISO_2022,locale=ja,version=1 ISO-2022-JP-1 JIS JIS_Encoding { IANA* }
|
|
ISO_2022,locale=ja,version=2 ISO-2022-JP-2 { IANA* MIME* } csISO2022JP2
|
|
ISO_2022,locale=ja,version=3 JIS7 csJISEncoding
|
|
ISO_2022,locale=ja,version=4 JIS8
|
|
ISO_2022,locale=ko,version=0 ISO-2022-KR { IANA* MIME* } csISO2022KR
|
|
ISO_2022,locale=ko,version=1 ibm-25546 ibm-25546_P100 25546
|
|
ISO_2022,locale=zh,version=0 ISO-2022-CN { IANA* MIME* } # csISO2022CN
|
|
ISO_2022,locale=zh,version=1 ISO-2022-CN-EXT { IANA* MIME* }
|
|
HZ HZ-GB-2312 { IANA* MIME* }
|
|
ISCII,version=0 iscii-dev x-iscii-de
|
|
ISCII,version=1 iscii-bng x-iscii-as x-iscii-be
|
|
ISCII,version=2 iscii-gur x-iscii-pa
|
|
ISCII,version=3 iscii-guj x-iscii-gu
|
|
ISCII,version=4 iscii-ori x-iscii-or
|
|
ISCII,version=5 iscii-tml x-iscii-ta
|
|
ISCII,version=6 iscii-tlg x-iscii-te
|
|
ISCII,version=7 iscii-knd x-iscii-ka
|
|
ISCII,version=8 iscii-mlm x-iscii-ma
|
|
|
|
# GB 18030 is partly algorithmic, using the MBCS converter
|
|
gb18030 { IANA* } ibm-1392
|
|
|
|
# Lotus specific
|
|
LMBCS-1 lmbcs
|
|
LMBCS-2
|
|
LMBCS-3
|
|
LMBCS-4
|
|
LMBCS-5
|
|
LMBCS-6
|
|
LMBCS-8
|
|
LMBCS-11
|
|
LMBCS-16
|
|
LMBCS-17
|
|
LMBCS-18
|
|
LMBCS-19
|
|
|
|
|
|
# Table-based interchange codepages
|
|
|
|
ibm-367 { IBM* } IBM367 { IANA* } # This is ASCII, but it has fallbacks
|
|
|
|
# Central Europe
|
|
ibm-912 { IBM* } iso-8859-2 { MIME* IANA }
|
|
latin2 { IANA }
|
|
# ISO8859_2 { JAVA* } # This is really the default for Java and many others.
|
|
8859-2
|
|
csISOLatin2 { IANA }
|
|
iso-ir-101 { IANA }
|
|
ISO_8859-2:1987 { IANA* }
|
|
l2 { IANA }
|
|
cp912
|
|
912
|
|
|
|
# Maltese Esperanto
|
|
ibm-913 { IBM* } iso-8859-3 { MIME* IANA }
|
|
latin3 { IANA }
|
|
8859-3
|
|
csISOLatin3 { IANA }
|
|
iso-ir-109
|
|
ISO_8859-3:1988 { IANA* }
|
|
l3 { IANA }
|
|
cp913
|
|
913
|
|
|
|
# Baltic
|
|
ibm-914 { IBM* } iso-8859-4 { MIME* IANA }
|
|
latin4 { IANA }
|
|
8859-4
|
|
csISOLatin4 { IANA }
|
|
iso-ir-110 { IANA }
|
|
ISO_8859-4:1988 { IANA* }
|
|
l4 { IANA }
|
|
cp914
|
|
914
|
|
|
|
# Cyrillic
|
|
ibm-915 { IBM* } iso-8859-5 { MIME* IANA }
|
|
cyrillic { IANA }
|
|
8859-5
|
|
csISOLatinCyrillic { IANA }
|
|
iso-ir-144 { IANA }
|
|
ISO_8859-5:1988 { IANA* }
|
|
cp915
|
|
915
|
|
|
|
# Arabic
|
|
# ISO_8859-6-E and ISO_8859-6-I are similar to this charset, but they are not the same
|
|
# -E means explicit. -I means implicit. However those aliases are rarely used.
|
|
ibm-1089 { IBM* } iso-8859-6 { MIME* IANA }
|
|
arabic { IANA }
|
|
8859-6
|
|
csISOLatinArabic { IANA }
|
|
iso-ir-127 { IANA }
|
|
ISO_8859-6:1987 { IANA* }
|
|
ecma-114 { IANA }
|
|
asmo-708 { IANA }
|
|
cp1089
|
|
1089
|
|
|
|
# ISO Greek (w/ euro update)
|
|
ibm-4909 { IBM* }
|
|
# ISO Greek (w/o euro update)
|
|
ibm-813 iso-8859-7 { MIME* IANA }
|
|
greek { IANA }
|
|
greek8 { IANA }
|
|
elot_928 { IANA }
|
|
ecma-118 { IANA }
|
|
8859-7
|
|
csISOLatinGreek { IANA }
|
|
iso-ir-126 { IANA }
|
|
ISO_8859-7:1987 { IANA* }
|
|
cp813
|
|
813
|
|
|
|
# hebrew
|
|
# ISO_8859-8-E and ISO_8859-8-I are similar to this charset, but they are not the same
|
|
# -E means explicit. -I means implicit.
|
|
ibm-916 { IBM* } iso-8859-8 { MIME* IANA }
|
|
hebrew { IANA }
|
|
8859-8
|
|
csISOLatinHebrew { IANA }
|
|
iso-ir-138 { IANA }
|
|
ISO_8859-8:1988 { IANA* }
|
|
cp916
|
|
916
|
|
|
|
# Turkish
|
|
ibm-920 { IBM* } iso-8859-9 { MIME* IANA }
|
|
ECMA-128 # IANA doesn't have this alias 6/24/2002
|
|
latin5 { IANA }
|
|
8859-9
|
|
csISOLatin5 { IANA }
|
|
iso-ir-148 { IANA }
|
|
ISO_8859-9:1989 { IANA* }
|
|
l5 { IANA }
|
|
cp920
|
|
920
|
|
|
|
# PC Baltic (w/ euro update)
|
|
ibm-901 { IBM* } cp921 { MIME* } 921
|
|
# iso-8859-13, PC Baltic (w/o euro update)
|
|
ibm-921 { IBM* } iso-8859-13 { IANA* }
|
|
|
|
# Latin 9
|
|
ibm-923 { IBM* } iso-8859-15 { IANA* MIME* } # IANA only has iso-8859-15 (6/24/2002)
|
|
# ISO8859_15 { JAVA* } # This is really the default for Java and many others.
|
|
8859-15
|
|
latin9
|
|
latin0
|
|
csisolatin0
|
|
csisolatin9
|
|
iso8859_15_fdis
|
|
cp923
|
|
923
|
|
|
|
# Windows Latin 1 without Euro
|
|
ibm-1252 { IBM* } # ibm-1004 and cp1004 are different from this mapping table
|
|
|
|
|
|
# CJK encodings
|
|
|
|
ibm-942_P120-2000 { UTR22* }
|
|
ibm-942 { IBM* }
|
|
ibm-942_VASCII_VSUB_VPUA
|
|
ibm-932 { IBM }
|
|
ibm-932_VASCII_VSUB_VPUA # Old s_jis
|
|
ibm-942_P12A-2000 { UTR22* } # The normal mapping
|
|
ibm-942 # Leave untagged because this isn't the default
|
|
ibm-942_VSUB_VPUA
|
|
shift_jis78
|
|
sjis78
|
|
ibm-932_VSUB_VPUA
|
|
|
|
ibm-943_P130-2000 { UTR22* }
|
|
ibm-943 { IBM* }
|
|
ibm-943_VASCII_VSUB_VPUA
|
|
Shift_JIS # Leave untagged because this isn't the default
|
|
# japanese. Unicode name is \u30b7\u30d5\u30c8\u7b26\u53f7\u5316\u8868\u73fe
|
|
ibm-943_P14A-2000 { UTR22* }
|
|
ibm-943 # Leave untagged because this isn't the default
|
|
ibm-943_VSUB_VPUA
|
|
Shift_JIS { IANA* MIME* }
|
|
sjis
|
|
cp943
|
|
cp932
|
|
pck # Probably SOLARIS
|
|
MS_Kanji { IANA }
|
|
csShiftJIS { IANA }
|
|
windows-31j { IANA } # A further extension of Shift_JIS to include NEC special characters (Row 13)
|
|
csWindows31J { IANA } # A further extension of Shift_JIS to include NEC special characters (Row 13)
|
|
x-sjis # Probably MIME
|
|
943
|
|
# Iana says that Windows-31J is an extension to csshiftjis ibm-932
|
|
ibm-949_P110-2000 { UTR22* }
|
|
ibm-949 { IBM* }
|
|
ibm-949_VASCII_VSUB_VPUA
|
|
|
|
ibm-949_P11A-2000 { UTR22* }
|
|
ibm-949
|
|
ibm-949_VSUB_VPUA
|
|
KS_C_5601-1987 { IANA* }
|
|
iso-ir-149 { IANA }
|
|
KS_C_5601-1989 { IANA }
|
|
csKSC56011987 { IANA }
|
|
KSC_5601 { MIME* IANA }
|
|
ks_x_1001:1992
|
|
949
|
|
korean { IANA }
|
|
ksc5601_1992 # KSC-5601-1992
|
|
ksc5601_1987 # Needed by Java
|
|
|
|
ibm-1370_P100-2000 { UTR22* }
|
|
ibm-1370 { IBM* }
|
|
ibm-1370_VSUB_VPUA
|
|
Big5 { IANA* MIME* }
|
|
csBig5 { IANA }
|
|
x-big5
|
|
cp950
|
|
950 # Taiwan Big-5 (w/ euro update)
|
|
ibm-950 { IBM* } # Taiwan Big-5 (w/o euro update)
|
|
|
|
ibm-1386_P100-2002 { UTR22* }
|
|
ibm-1386 { IBM* }
|
|
ibm-1386_VSUB_VPUA
|
|
GBK { IANA* }
|
|
CP936 { IANA }
|
|
windows-936 { IANA }
|
|
MS936 { IANA }
|
|
zh_cn # Chinese GBK removed
|
|
|
|
ibm-33722_P120-2000 { UTR22* } # Japan EUC with \ <-> Yen mapping
|
|
ibm-33722 { IBM* }
|
|
ibm-33722_VASCII_VPUA
|
|
cp33722
|
|
33722
|
|
ibm-5050
|
|
ibm-33722_P12A-2000 { UTR22* }
|
|
ibm-33722 # Leave untagged because this isn't the default
|
|
ibm-33722_VPUA
|
|
EUC-JP { IANA MIME* }
|
|
ibm-eucJP
|
|
eucjis
|
|
Extended_UNIX_Code_Packed_Format_for_Japanese { IANA* }
|
|
csEUCPkdFmtJapanese { IANA }
|
|
X-EUC-JP # Japan EUC. x-euc-jp is a MIME name
|
|
ibm-970_P110-2000 { UTR22* }
|
|
ibm-970 { IBM* }
|
|
ibm-970_VPUA
|
|
EUC-KR { IANA* MIME* }
|
|
ibm-eucKR
|
|
csEUCKR { IANA } # Korean EUC. x-euc-kr is a MIME name
|
|
ibm-964_P110-2000 { UTR22* }
|
|
ibm-964 { IBM* }
|
|
ibm-964_VPUA
|
|
EUC-TW
|
|
ibm-eucTW
|
|
cns11643 # Taiwan EUC. x-euc-tw is a MIME name
|
|
|
|
ibm-1363_P110-2000 { UTR22* } # Korean KSC Korean Windows MBCS
|
|
ibm-1363 { IBM* }
|
|
ibm-1363_VASCII_VSUB_VPUA
|
|
# ibm-1362 { IBM } # ibm-1362 is a DBCS codepage, not MBCS
|
|
|
|
ibm-1363_P11B-2000 { UTR22* }
|
|
ibm-1363 # Leave untagged because this isn't the default
|
|
ibm-1363_VSUB_VPUA
|
|
windows-949
|
|
cp949
|
|
cp1363
|
|
ksc
|
|
# korean # The korean alias from IANA goes to ibm-949_P11A-2000
|
|
|
|
ibm-1383_P110-2000 { UTR22* }
|
|
ibm-1383_VPUA
|
|
ibm-1383
|
|
EUC-CN
|
|
ibm-eucCN
|
|
GB_2312-80 { IANA* }
|
|
chinese { IANA }
|
|
gb # This is not an IANA name. gb in IANA means Great Britain.
|
|
iso-ir-58 { IANA }
|
|
csISO58GB231280 { IANA }
|
|
GB2312 { MIME* }
|
|
gb2312-1980
|
|
cp1383
|
|
1383
|
|
csGB2312 # China EUC. x-euc-cn is a MIME name
|
|
|
|
ibm-1162 { IBM* } TIS-620 { IANA* } cp874 windows-874 ms874 cp9066 874 # Thai (w/ euro update)
|
|
ibm-874 { IBM* } ibm-1161 # Same as 1162 (w/o euro update)
|
|
|
|
# Platform codepages
|
|
ibm-437 { IBM* } IBM437 { IANA* } cp437 { IANA } 437 { IANA } csPC8CodePage437 { IANA } # PC US
|
|
ibm-850 { IBM* } IBM850 { IANA* } cp850 { IANA MIME* } 850 { IANA } csPC850Multilingual { IANA } # PC latin1
|
|
ibm-851 { IBM* } IBM851 { IANA* } cp851 { IANA MIME* } 851 { IANA } csPC851 { IANA } # PC DOS Greek (w/o euro)
|
|
ibm-858 { IBM* } IBM00858 { IANA* } CCSID00858 { IANA } CP00858 { IANA } PC-Multilingual-850+euro { IANA } cp858 { MIME* } # PC latin1 with Euro
|
|
ibm-9044 { IBM* } # PC latin2 (w/ euro update) Updated version of ibm-852. cp852 is a MIME name for IBM-852
|
|
ibm-852 { IBM* } IBM852 { IANA* } cp852 { IANA } 852 { IANA } csPCp852 { IANA } # PC latin2 (w/o euro update)
|
|
ibm-872 { IBM* } # PC cyrillic (w/ euro update) Updated version of ibm-855. cp855 is a MIME name for IBM-855
|
|
ibm-855 { IBM* } IBM855 { IANA* } cp855 { IANA } 855 { IANA } csIBM855 { IANA } csPCp855 # PC cyrillic (w/o euro update)
|
|
ibm-856 { IBM* } cp856 { MIME* } 856 # PC Hebrew (old)
|
|
ibm-9049 { IBM* } # PC Latin 5 (Turkish) (w/ euro update) Updated version of ibm-857
|
|
ibm-857 { IBM* } IBM857 { IANA* } 857 { IANA } csIBM857 { IANA } cp857 { IANA MIME* } # PC Latin 5 (w/o euro update)
|
|
ibm-859 { IBM* } cp859 { MIME* } # PC Latin 9 (w/ euro update)
|
|
ibm-860 { IBM* } IBM860 { IANA* } cp860 { IANA MIME* } 860 { IANA } csIBM860 { IANA } # PC Portugal
|
|
ibm-861 { IBM* } IBM861 { IANA* } cp861 { IANA MIME* } 861 { IANA } cp-is { IANA } csIBM861 { IANA } # PC Iceland
|
|
ibm-867 { IBM* } cp867 # PC Hebrew (w/ euro update) Updated version of ibm-862
|
|
ibm-862 { IBM* } IBM862 { IANA* } cp862 { IANA MIME* } 862 { IANA } csPC862LatinHebrew { IANA } # PC Hebrew (w/o euro update)
|
|
ibm-863 { IBM* } IBM863 { IANA* } cp863 { IANA MIME* } 863 { IANA } csIBM863 { IANA } # PC Canadian French
|
|
ibm-17248 { IBM* } # PC Arabic (w/ euro update) Updated version of ibm-864
|
|
ibm-864 { IBM* } IBM864 { IANA* } cp864 { IANA MIME* } csIBM864 { IANA } # PC Arabic (w/o euro update)
|
|
ibm-865 { IBM* } IBM865 { IANA* } cp865 { IANA MIME* } 865 { IANA } csIBM865 { IANA } # PC Nordic
|
|
ibm-808 { IBM* } # PC Russian (w/ euro update) Updated version of ibm-866
|
|
ibm-866 { IBM* } IBM866 { IANA* } cp866 { IANA MIME* } 866 { IANA } csIBM866 { IANA } # PC Russian (w/o euro update)
|
|
ibm-868 { IBM* } IBM868 { IANA* } CP868 { IANA MIME* } cp-ar { IANA } csIBM868 { IANA } 868 # PC Urdu
|
|
ibm-9061 { IBM* } # PC Greek (w/ euro update) Updated version of ibm-869
|
|
ibm-869 { IBM* } IBM869 { IANA* } cp869 { IANA MIME* } 869 { IANA } cp-gr { IANA } csIBM869 { IANA } # PC Greek (w/o euro update)
|
|
ibm-878 { IBM* } KOI8-R { IANA* MIME* } cp878 koi8 csKOI8R { IANA } # Russian internet
|
|
ibm-902 { IBM* } cp922 { MIME* } 922 # PC Estonian (w/ euro update)
|
|
ibm-922 { IBM* } # PC Estonian (w/o euro update)
|
|
# ibm-941 jis-208 jisx-208 # Pure DBCS jisx-208 # ibm-941 is not JISX 208 code page
|
|
|
|
ibm-5346 { IBM* } windows-1250 { IANA* } cp1250 # Windows Latin2 (w/ euro update)
|
|
ibm-5347 { IBM* } windows-1251 { IANA* } cp1251 # Windows Cyrillic (w/ euro update)
|
|
ibm-5348 { IBM* } windows-1252 { IANA* } cp1252 # Windows Latin1 (w/ euro update)
|
|
ibm-5349 { IBM* } windows-1253 { IANA* } cp1253 # Windows Greek (w/ euro update)
|
|
ibm-5350 { IBM* } windows-1254 { IANA* } cp1254 # Windows Turkish (w/ euro update)
|
|
ibm-5351 { IBM* } windows-1255 { IANA* } cp1255 # Windows Hebrew (w/ euro update)
|
|
ibm-5352 { IBM* } windows-1256 { IANA* } cp1256 # Windows Arabic (w/ euro update)
|
|
ibm-5353 { IBM* } windows-1257 { IANA* } cp1257 # Windows Baltic (w/ euro update)
|
|
ibm-5354 { IBM* } windows-1258 { IANA* } cp1258 # Windows Vietnamese (w/ euro update)
|
|
ibm-1250 { IBM* } # Windows Latin2 (w/o euro update)
|
|
ibm-1251 { IBM* } # Windows Cyrillic (w/o euro update)
|
|
ibm-1253 { IBM* } # Windows Greek (w/o euro update)
|
|
ibm-1254 { IBM* } # Windows Turkish (w/o euro update)
|
|
ibm-1255 { IBM* } # Windows Hebrew (w/o euro update)
|
|
ibm-1256 { IBM* } # Windows Arabic (w/o euro update)
|
|
ibm-1257 { IBM* } # Windows Baltic (w/o euro update)
|
|
ibm-1258 { IBM* } # Windows Vietnamese (w/o euro update)
|
|
|
|
ibm-1275 { IBM* } macintosh { IANA* } mac { IANA MIME* } csMacintosh { IANA } # Apple latin 1
|
|
ibm-1276 { IBM* } Adobe-Standard-Encoding { IANA* } csAdobeStandardEncoding { IANA } # Different from ISO-Unicode-IBM-1276 (GCSGID: 1276)
|
|
ibm-1277 { IBM* } Adobe-Latin1-Encoding
|
|
ibm-1280 { IBM* } macgr # Apple Greek
|
|
ibm-1281 { IBM* } mactr # Apple Turkish
|
|
ibm-1282 { IBM* } macce # Apple Central Europe
|
|
ibm-1283 { IBM* } maccy # Apple Cyrillic
|
|
|
|
ibm-1051 { IBM* } hp-roman8 { IANA* } roman8 r8 csHPRoman8 # HP Latin1
|
|
|
|
ibm-806_P100-2000 { UTR22* } ibm-806 { IBM* } ibm-806_VSUB # PC ISCII-91: Indian Script Code
|
|
ibm-1006_P100-2000 { UTR22* } ibm-1006 { IBM* } ibm-1006_VPUA # Urdu
|
|
ibm-1006_X100-2000 { UTR22* } ibm-1006_STD # Urdu
|
|
ibm-1098_P100-2000 { UTR22* } ibm-1098 { IBM* } ibm-1098_VSUB_VPUA # Farsi
|
|
ibm-1098_X100-2000 { UTR22* } ibm-1098_VSUB # Farsi
|
|
ibm-1124_P100-2000 { UTR22* } ibm-1124 { IBM* } ibm-1124_STD # ISO Cyrillic Ukraine
|
|
ibm-1125_P100-2000 { UTR22* } ibm-1125 { IBM* } ibm-1125_VSUB # Cyrillic Ukraine PC
|
|
ibm-1129_P100-2000 { UTR22* } ibm-112 { IBM* }9 ibm-1129_STD # ISO Vietnamese
|
|
ibm-1131_P100-2000 { UTR22* } ibm-1131 { IBM* } ibm-1131_VSUB # Cyrillic Belarus PC
|
|
ibm-1133_P100-2000 { UTR22* } ibm-1133 { IBM* } ibm-1133_STD # ISO Lao
|
|
ibm-1381_P110-2000 { UTR22* } ibm-1381 { IBM* } ibm-1381_VSUB_VPUA # S-Ch PC Data mixed (IBM GB)
|
|
ibm-9066_P100-2000 { UTR22* } ibm-9066 { IBM* } ibm-9066_VSUB # Thai PC
|
|
|
|
# Added for more euro support
|
|
|
|
ibm-849 { IBM* } cp1131 # PC Belarus (w/ euro update)
|
|
ibm-848 { IBM* } cp1125 # PC Ukraine (w/ euro update)
|
|
ibm-5104 { IBM* } cp1008 # 8-bit Arabic (w/ euro update)
|
|
ibm-9238 { IBM* } cp1046 # PC Arabic Extended (w/ euro update)
|
|
# ibm-5210 cp1114 # PC SBCS Big-5 (w/ euro update)
|
|
# ibm-21427 cp947 # PC DBCS Big-5 (w/ euro update)
|
|
|
|
# ibm-1046 # PC Arabic without EURO
|
|
|
|
# EBCDIC codepages according to the CDRA
|
|
|
|
# without Euro
|
|
ibm-37 { IBM* } IBM037 { IANA* } # EBCDIC US
|
|
ibm-037
|
|
cpibm37
|
|
ebcdic-cp-us { IANA }
|
|
ebcdic-cp-ca { IANA }
|
|
ebcdic-cp-wt { IANA }
|
|
ebcdic-cp-nl { IANA }
|
|
csIBM037 { IANA }
|
|
cp37
|
|
cp037
|
|
037
|
|
ibm-273 { IBM* } IBM273 { IANA* } csIBM273 { IANA } ebcdic-de CP273 { IANA } cpibm273 273 # EBCDIC Germanay, Austria
|
|
ibm-277 { IBM* } IBM277 { IANA* } EBCDIC-CP-DK { IANA } EBCDIC-CP-NO { IANA } csIBM277 { IANA } ebcdic-dk cp277 cpibm277 277 # EBCDIC Denmark
|
|
ibm-278 { IBM* } IBM278 { IANA* } ebcdic-cp-fi { IANA } ebcdic-cp-se { IANA } csIBM278 { IANA } ebcdic-sv cp278 cpibm278 278 # EBCDIC Sweden
|
|
ibm-280 { IBM* } IBM280 { IANA* } ebcdic-cp-it { IANA } csIBM280 { IANA } CP280 { IANA } cpibm280 280 # EBCDIC Italy
|
|
ibm-284 { IBM* } IBM284 { IANA* } ebcdic-cp-es { IANA } csIBM284 { IANA } CP284 { IANA } cpibm284 284 # EBCDIC Spain
|
|
ibm-285 { IBM* } IBM285 { IANA* } ebcdic-cp-gb { IANA } csIBM285 { IANA } CP285 { IANA } ebcdic-gb cpibm285 285 # EBCDIC UK Ireland
|
|
ibm-290 { IBM* } IBM290 { IANA* } EBCDIC-JP-kana { IANA } csIBM290 { IANA } cp290 { IANA } # host SBCS (Katakana)
|
|
ibm-297 { IBM* } IBM297 { IANA* } ebcdic-cp-fr { IANA } csIBM297 { IANA } cp297 { IANA } cpibm297 297 # EBCDIC France
|
|
ibm-420 { IBM* } IBM420 { IANA* } ebcdic-cp-ar1 { IANA } csIBM420 { IANA } cp420 { IANA } 420
|
|
ibm-424 { IBM* } IBM424 { IANA* } ebcdic-cp-he { IANA } csIBM424 { IANA } cp424 { IANA } 424
|
|
ibm-500 { IBM* } IBM500 { IANA* } cpibm500 csIBM500 { IANA } CP500 { IANA } ebcdic-cp-be { IANA } ebcdic-cp-ch { IANA } 500 # EBCDIC International Latin1
|
|
ibm-803 { IBM* } cp803 # Old EBCDIC Hebrew
|
|
#ibm-834 cp834 # Korean DBCS Host (ibm-933 is the mixed host version of this codepage)
|
|
#ibm-835 cp835 # DBCS T-Ch Host (ibm-9027 is the Euro update of this codepage)
|
|
ibm-870_P100-2000 { UTR22* } IBM870 { IANA* } ibm-870 { IBM* } CP870 { IANA } ibm-870_STD ebcdic-cp-roece { IANA } ebcdic-cp-yu { IANA } csIBM870 { IANA }
|
|
ibm-871 { IBM* } IBM871 { IANA* } ebcdic-cp-is { IANA } csIBM871 { IANA } ebcdic-is cpibm871 CP871 { IANA } 871 # EBCDIC Iceland
|
|
ibm-875_P100-2000 { UTR22* } ibm-875 { IBM* } cp875 875 ibm-875_STD
|
|
ibm-918_P100-2000 { UTR22* } IBM918 { IANA* } ibm-918 { IBM* } CP918 { IANA } ibm-918_VPUA ebcdic-cp-ar2 { IANA } csIBM918 { IANA }
|
|
ibm-918_X100-2000 { UTR22* } ibm-918_STD
|
|
ibm-930 { IBM* } cp930 cpibm930 930 #ibm-5026 # EBCDIC_STATEFUL Katakana-Kanji Host Mixed. ibm-930 =? ibm-5026
|
|
ibm-933 { IBM* } cp933 cpibm933 933 # Korea EBCDIC MIXED
|
|
ibm-935 { IBM* } cp935 cpibm935 935 # China EBCDIC MIXED
|
|
ibm-937 { IBM* } cp937 cpibm937 937 # Taiwan EBCDIC MIXED
|
|
ibm-939 { IBM* } cp939 939 #ibm-5035 # EBCDIC_STATEFUL Latin-Kanji Host Mixed. ibm-939 =? ibm-5035
|
|
ibm-1025_P100-2000 { UTR22* } ibm-1025 { IBM* } ibm-1025_STD
|
|
ibm-1026_P100-2000 { UTR22* } IBM1026 { IANA* } ibm-1026 { IBM* } CP1026 { IANA } csIBM1026 { IANA } ibm-1026_STD
|
|
ibm-1047 cpibm1047 # EBCDIC Open systems Latin1
|
|
ibm-1097_P100-2000 { UTR22* } ibm-1097 { IBM* } ibm-1097_VPUA
|
|
ibm-1097_X100-2000 { UTR22* } ibm-1097_STD
|
|
ibm-1112_P100-2000 { UTR22* } ibm-1112 { IBM* } cp1112 1112 ibm-1112_STD
|
|
ibm-1122_P100-2000 { UTR22* } ibm-1122 { IBM* } cp1122 1122 ibm-1122_STD
|
|
ibm-1130_P100-2000 { UTR22* } ibm-1130 { IBM* } ibm-1130_STD
|
|
ibm-1132_P100-2000 { UTR22* } ibm-1132 { IBM* } ibm-1132_STD
|
|
ibm-1137_P100-2000 { UTR22* } ibm-1137 { IBM* } ibm-1137_STD
|
|
ibm-1388_P103-2001 { UTR22* } ibm-1388 { IBM* } # S-Ch DBCS-Host Data GBK mixed MBCS
|
|
ibm-9030_P100-2000 { UTR22* } ibm-9030 { IBM* } ibm-9030_STD
|
|
|
|
# with Euro
|
|
ibm-1123 { IBM* } cpibm1123 # EBCDIC Cyrillic Ukraine
|
|
ibm-1140 { IBM* } cpibm1140 IBM01140 { IANA* } CCSID01140 { IANA } CP01140 { IANA } ebcdic-us-37+euro { IANA } # EBCDIC US
|
|
ibm-1141 { IBM* } cpibm1141 IBM01141 { IANA* } CCSID01141 { IANA } CP01141 { IANA } ebcdic-de-273+euro { IANA } # EBCDIC Germanay, Austria
|
|
ibm-1142 { IBM* } cpibm1142 IBM01142 { IANA* } CCSID01142 { IANA } CP01142 { IANA } ebcdic-dk-277+euro { IANA } ebcdic-no-277+euro { IANA } # EBCDIC Denmark
|
|
ibm-1143 { IBM* } cpibm1143 IBM01143 { IANA* } CCSID01143 { IANA } CP01143 { IANA } ebcdic-fi-278+euro { IANA } ebcdic-se-278+euro { IANA } # EBCDIC Sweden
|
|
ibm-1144 { IBM* } cpibm1144 IBM01144 { IANA* } CCSID01144 { IANA } CP01144 { IANA } ebcdic-it-280+euro { IANA } # EBCDIC Italy
|
|
ibm-1145 { IBM* } cpibm1145 IBM01145 { IANA* } CCSID01145 { IANA } CP01145 { IANA } ebcdic-es-284+euro { IANA } # EBCDIC Spain
|
|
ibm-1146 { IBM* } cpibm1146 IBM01146 { IANA* } CCSID01146 { IANA } CP01146 { IANA } ebcdic-gb-285+euro { IANA } # EBCDIC UK Ireland
|
|
ibm-1147 { IBM* } cpibm1147 IBM01147 { IANA* } CCSID01147 { IANA } CP01147 { IANA } ebcdic-fr-297+euro { IANA } # EBCDIC France
|
|
ibm-1148 { IBM* } cpibm1148 IBM01148 { IANA* } CCSID01148 { IANA } CP01148 { IANA } ebcdic-international-500+euro { IANA } # EBCDIC International Latin1
|
|
ibm-1149 { IBM* } cpibm1149 IBM01149 { IANA* } CCSID01149 { IANA } CP01149 { IANA } ebcdic-is-871+euro { IANA } # EBCDIC Iceland
|
|
ibm-1153 { IBM* } cpibm1153 # EBCDIC latin 2
|
|
ibm-1154 { IBM* } cp1025 cpibm1154 # EBCDIC Cyrillic Multilingual
|
|
ibm-1155 { IBM* } cpibm1155 # EBCDIC Turkey
|
|
ibm-1156 { IBM* } cpibm1156 # EBCDIC Baltic Multilingual
|
|
ibm-1157 { IBM* } cpibm1157 # EBCDIC Estonia
|
|
ibm-1158 { IBM* } cp1123 cpibm1158 1123 # EBCDIC Cyrillic Ukraine
|
|
ibm-1159 { IBM* } cp28709 # SBCS T-Ch Host
|
|
ibm-1160 { IBM* } cp9030 cpibm1160 # EBCDIC Thailand
|
|
ibm-1164 { IBM* } cp1130 cpibm1164 # EBCDIC Viet Nam
|
|
ibm-1364_P110-2000 { UTR22* } ibm-1364 { IBM* } ibm-1364_VPUA cp1364 # Korean Host Mixed
|
|
ibm-1371 { IBM* } cpibm1371 # Taiwan EBCDIC MIXED
|
|
ibm-1390 { IBM* } cpibm1390 # Japan EBCDIC MIXED
|
|
ibm-1399 { IBM* } # Host MBCS (Latin-Kanji)
|
|
ibm-4899 { IBM* } cpibm4899 # Old EBCDIC Hebrew
|
|
ibm-4971 { IBM* } cpibm4971 # EBCDIC Greek
|
|
ibm-5123 { IBM* } cp1027 # Host Roman Jis
|
|
ibm-8482 { IBM* } # host SBCS (Katakana)
|
|
ibm-9027 { IBM* } # DBCS T-Ch Host (simlar to ibm-835)
|
|
ibm-12712 { IBM* } cpibm12712 ebcdic-he # EBCDIC Hebrew (new sheqel, control charaters update)
|
|
ibm-16684 { IBM* } cp300 # DBCS Jis + Roman Jis Host
|
|
ibm-16804 { IBM* } cpibm16804 ebcdic-ar # EBCDIC Arabic
|
|
|
|
# unsupported IANA names
|
|
# ebcdic-it csEBCDICIT
|
|
# ebcdic-es csEBCDICES
|
|
# ebcdic-fr csEBCDICFR
|
|
# ibm-274 IBM274 { IANA* } cp274 csIBM274 ebcdic-be
|
|
# ibm-870 IBM870 { IANA* } ebcdic-cp-roece ebcdic-cp-yu csIBM870 cp870 870
|
|
|
|
# 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.
|
|
|
|
# This avoids the duplication of all EBCDIC SBCS and mixed-SBCS/DBCS
|
|
# mapping files.
|
|
|
|
# Some examples
|
|
ibm-37,swaplfnl ibm-37-s390 ibm037-s390
|
|
ibm-1047,swaplfnl ibm-1047-s390
|
|
ibm-1140,swaplfnl ibm-1140-s390
|
|
ibm-1142,swaplfnl ibm-1142-s390
|
|
ibm-1143,swaplfnl ibm-1143-s390
|
|
ibm-1144,swaplfnl ibm-1144-s390
|
|
ibm-1145,swaplfnl ibm-1145-s390
|
|
ibm-1146,swaplfnl ibm-1146-s390
|
|
ibm-1147,swaplfnl ibm-1147-s390
|
|
ibm-1148,swaplfnl ibm-1148-s390
|
|
ibm-1149,swaplfnl ibm-1149-s390
|
|
ibm-1153,swaplfnl ibm-1153-s390
|
|
ibm-12712,swaplfnl ibm-12712-s390
|
|
ibm-16804,swaplfnl ibm-16804-s390
|
|
|
|
# This is a special version of ibm-1140 that the XML4C (Xerces) parser team
|
|
# requested in 2000.
|
|
# It maps both EBCDIC LF and NL controls to Unicode LF U+000A.
|
|
|
|
ebcdic-xml-us
|