icuSources/data/mappings/convrtrs.txt

   1 # ******************************************************************************
   2 # *
   3 # *   Copyright (C) 1995-2004, International Business Machines
   4 # *   Corporation and others.  All Rights Reserved.
   5 # *
   6 # ******************************************************************************
   7
   8 # If this converter alias table looks very confusing, a much easier to
   9 # understand view can be found at this demo:
  10 # http://oss.software.ibm.com/cgi-bin/icu/convexp
  11
  12 # IMPORTANT NOTE
  13 #
  14 # This file is not read directly by ICU. If you change it, you need to
  15 # run gencnval, and eventually run pkgdata to update the representation that
  16 # ICU uses for aliases. The gencnval tool will normally compile this file into
  17 # cnvalias.icu. The gencnval -v verbose option will help you when you edit
  18 # this file.
  19
  20 # Please be friendly to the rest of us that edit this table by
  21 # keeping this table free of tabs.
  22
  23 # This is an alias file used by the character set converter.
  24 # A lot of converter information can be found in unicode/ucnv.h, but here
  25 # is more information about this file.
  26 #
  27 # Here is the file format using BNF-like syntax:
  28 #
  29 # converterTable ::= tags { converterLine* }
  30 # converterLine ::= converterName [ tags ] { taggedAlias* }'\n'
  31 # taggedAlias ::= alias [ tags ]
  32 # tags ::= '{' { tag+ } '}'
  33 # tag ::= standard['*']
  34 # converterName ::= [0-9a-zA-Z:_'-']+
  35 # alias ::= converterName
  36 #
  37 # Except for the converter name, aliases are case insensitive.
  38 # Names are separated by whitespace.
  39 # Line continuation and comment sytax are similar to the GNU make syntax.
  40 # Any lines beginning with whitespace (e.g. U+0020 SPACE or U+0009 HORIZONTAL
  41 # TABULATION) are presumed to be a continuation of the previous line.
  42 # The # symbol starts a comment and the comment continues till the end of
  43 # the line.
  44 #
  45 # The converter
  46 #
  47 # All names can be tagged by including a space-separated list of tags in
  48 # curly braces, as in ISO_8859-1:1987{IANA*} iso-8859-1 { MIME* } or
  49 # some-charset{MIME* IANA*}. The order of tags does not matter, and
  50 # whitespace is allowed between the tagged name and the tags list.
  51 #
  52 # The tags can be used to get standard names using ucnv_getStandardName().
  53 #
  54 # The complete list of recognized tags used in this file is defined in
  55 # the affinity list near the beginning of the file.
  56 #
  57 # The * after the standard tag denotes that the previous alias is the
  58 # preferred (default) charset name for that standard. There can only
  59 # be one of these default charset names per converter.
  60
  61
  62
  63 # The world is getting more complicated...
  64 # Supporting XML parsers, HTML, MIME, and similar applications
  65 # that mark encodings with a charset name can be difficult.
  66 # Many of these applications and operating systems will update
  67 # their codepages over time.
  68
  69 # It means that a new codepage, one that differs from an
  70 # old one by changing a code point, e.g., to the Euro sign,
  71 # must not get an old alias, because it would mean that
  72 # old files with this alias would be interpreted differently.
  73
  74 # If an codepage gets updated by assigning characters to previously
  75 # unassigned code points, then a new name is not necessary.
  76 # Also, some codepages map unassigned codepage byte values
  77 # to the same numbers in Unicode for roundtripping. It may be
  78 # industry practice to keep the encoding name in such a case, too
  79 # (example: Windows codepages).
  80
  81 # The aliases listed in the list of character sets
  82 # that is maintained by the IANA (http://www.iana.org/) must
  83 # not be changed to mean encodings different from what this
  84 # list shows. Currently, the IANA list is at
  85 # http://www.iana.org/assignments/character-sets
  86 # It should also be mentioned that the exact mapping table used for each
  87 # IANA names usually isn't specified. This means that some other applications
  88 # and operating systems are left to interpret the exact mappings for the
  89 # underspecified aliases. For instance, Shift-JIS on a Solaris platform
  90 # may be different from Shift-JIS on a Windows platform. This is why
  91 # some of the aliases can be tagged to differentiate different mapping
  92 # tables with the same alias. If an alias is given to more than one converter,
  93 # it is considered to be an ambiguous alias, and the affinity list will
  94 # choose the converter to use when a standard isn't specified with the alias.
  95
  96 # Name matching is case-insensitive. Also, dashes '-', underscores '_'
  97 # and spaces ' ' are ignored in names (thus cs-iso_latin-1, csisolatin1
  98 # and "cs iso latin 1" are the same).
  99 # However, the names in the left column are directly file names
 100 # or names of algorithmic converters, and their case must not
 101 # be changed - or else code and/or file names must also be changed.
 102 # For example, the converter ibm-921 is expected to be the file ibm-921.cnv.
 103
 104
 105
 106 # The immediately following list is the affinity list of supported standard tags.
 107 # When multiple converters have the same alias under different standards,
 108 # the standard nearest to the top of this list with that alias will
 109 # be the first converter that will be opened. The ordering of the aliases
 110 # after this affinity list does not affect the preferred alias, but it may
 111 # affect the order of the returned list of aliases for a given converter.
 112 #
 113 # The general ordering is from specific and frequently used to more general
 114 # or rarely used at the bottom.
 115 {   UTR22           # Name format specified by http://www.unicode.org/unicode/reports/tr22/
 116     # ICU             # Can also use ICU_FEATURE
 117     IBM             # The IBM CCSID number is specified by ibm-*
 118     WINDOWS         # The Microsoft code page identifier number is specified by windows-*. The rest are recognized IE names.
 119     JAVA            # Source: Sun JDK. Alias name case is ignored, but dashes are not ignored.
 120     # GLIBC
 121     # AIX
 122     # DB2
 123     # SOLARIS
 124     # APPLE
 125     # HPUX
 126     IANA            # Source: http://www.iana.org/assignments/character-sets
 127     MIME            # Source: http://www.iana.org/assignments/character-sets
 128     # MSIE            # MSIE is Internet Explorer, which can be different from Windows (From the IMultiLanguage COM interface)
 129     # ZOS_USS         # z/OS (os/390) Unix System Services (USS), which has NL<->LF swapping. They have the same format as the IBM tag.
 130     }
 131
 132
 133
 134 # Fully algorithmic converters
 135
 136 UTF-8 { IANA* MIME* JAVA* WINDOWS }
 137                                 ibm-1208 { IBM* }
 138                                 ibm-1209 { IBM }
 139                                 ibm-5304 { IBM }
 140                                 ibm-5305 { IBM }
 141                                 windows-65001 { WINDOWS* }
 142                                 cp1208
 143
 144 # The ICU 2.2 UTF-16/32 converters detect and write a BOM.
 145 UTF-16 { IANA* MIME* JAVA* }    ISO-10646-UCS-2 { IANA } unicode csUnicode ucs-2
 146 UTF-16BE { IANA* MIME* JAVA* }  x-utf-16be { JAVA }
 147                                 # iso-10646-ucs-2 { JAVA } # This is ambiguous
 148                                 ibm-1200 { IBM* }
 149                                 ibm-1201 { IBM }
 150                                 ibm-5297 { IBM }
 151                                 ibm-13488 { IBM }
 152                                 ibm-17584 { IBM }
 153                                 windows-1201 { WINDOWS* }
 154                                 cp1200
 155                                 cp1201
 156                                 UTF16_BigEndian
 157 UTF-16LE { IANA* MIME* JAVA* }  x-utf-16le { JAVA }
 158                                 ibm-1202 { IBM* }
 159                                 ibm-13490 { IBM }
 160                                 ibm-17586 { IBM }
 161                                 UTF16_LittleEndian
 162                                 windows-1200 { WINDOWS* }
 163
 164 UTF-32 { IANA* MIME* }          ISO-10646-UCS-4 { IANA } csUCS4 ucs-4
 165 UTF-32BE { IANA* }              UTF32_BigEndian ibm-1232 { IBM* } ibm-1233 { IBM }
 166 UTF-32LE { IANA* }              UTF32_LittleEndian ibm-1234 { IBM* }
 167
 168 # ICU-specific names for special uses
 169 UTF16_PlatformEndian
 170 UTF16_OppositeEndian
 171
 172 UTF32_PlatformEndian
 173 UTF32_OppositeEndian
 174
 175 # On UTF-7:
 176 # RFC 2152 (http://www.imc.org/rfc2152) allows to encode some US-ASCII
 177 # characters directly or in base64. Especially, the characters in set O
 178 # as defined in the RFC (!"#$%&*;<=>@[]^_`{|}) may be encoded directly
 179 # but are not allowed in, e.g., email headers.
 180 # By default, the ICU UTF-7 converter encodes set O directly.
 181 # By choosing the option "version=1", set O will be escaped instead.
 182 # For example:
 183 #     utf7Converter=ucnv_open("UTF-7,version=1");
 184 #
 185 # For details about email headers see RFC 2047.
 186 UTF-7 { IANA* MIME* WINDOWS }   windows-65000 { WINDOWS* }
 187
 188 # IMAP-mailbox-name is an ICU-specific name for the encoding of IMAP mailbox names.
 189 # It is a substantially modified UTF-7 encoding. See the specification in:
 190 #
 191 # RFC 2060: INTERNET MESSAGE ACCESS PROTOCOL - VERSION 4rev1
 192 # (http://www.ietf.org/rfc/rfc2060.txt)
 193 # Section 5.1.3.  Mailbox International Naming Convention
 194 IMAP-mailbox-name
 195
 196 SCSU { IANA* }
 197 BOCU-1 { IANA* } csBOCU-1 { IANA }
 198
 199 # See http://www.unicode.org/unicode/reports/tr26 for this Compatibility Encoding Scheme for UTF-16
 200 # The Unicode Consortium does not encourage the use of CESU-8
 201 CESU-8 { IANA* }
 202
 203 # Standard iso-8859-1, which does not have the Euro update.
 204 # See iso-8859-15 (latin9) for the Euro update
 205 ISO-8859-1 { MIME* IANA JAVA* }
 206     ibm-819 { IBM* JAVA }    # This is not truely ibm-819 because it's missing the fallbacks.
 207     IBM819 { IANA }
 208     cp819 { IANA JAVA }
 209     latin1 { IANA JAVA }
 210     8859_1 { JAVA }
 211     csISOLatin1 { IANA JAVA }
 212     iso-ir-100 { IANA JAVA }
 213     ISO_8859-1:1987 { IANA* JAVA }
 214     l1 { IANA JAVA }
 215     819 { JAVA }
 216     # windows-28591 { WINDOWS* } # This has odd behavior because it has the Euro update, which isn't correct.
 217     # LATIN_1     # Old ICU name
 218     # ANSI_X3.110-1983  # This is for a different IANA alias.  This isn't iso-8859-1.
 219
 220 US-ASCII { MIME* IANA JAVA WINDOWS }
 221     ASCII { JAVA* IANA WINDOWS }
 222     ANSI_X3.4-1968 { IANA* WINDOWS }
 223     ANSI_X3.4-1986 { IANA WINDOWS }
 224     ISO_646.irv:1991 { IANA WINDOWS }
 225     iso_646.irv:1983 { JAVA }
 226     ISO646-US { JAVA IANA WINDOWS }
 227     us { IANA }
 228     csASCII { IANA WINDOWS }
 229     iso-ir-6 { IANA }
 230     cp367 { IANA WINDOWS }
 231     ascii7 { JAVA }
 232     646 { JAVA }
 233     windows-20127 { WINDOWS* }
 234     # IBM367 { IANA WINDOWS } # This isn't the default ibm-367.
 235
 236 # GB 18030 is partly algorithmic, using the MBCS converter
 237 gb18030 { IANA* }       ibm-1392 { IBM* } windows-54936 { WINDOWS* }
 238
 239 # Table-based interchange codepages
 240
 241 ibm-367_P100-1995 { UTR22* }    ibm-367 { IBM* } IBM367 { IANA* }   # This is ASCII, but it has fallbacks
 242
 243 # Central Europe
 244 ibm-912_P100-1995 { UTR22* }
 245                         ibm-912 { IBM* JAVA }
 246                         iso-8859-2 { MIME* IANA JAVA* WINDOWS }
 247                         ISO_8859-2:1987 { IANA* WINDOWS JAVA }
 248                         latin2 { IANA WINDOWS JAVA }
 249                         csISOLatin2 { IANA WINDOWS JAVA }
 250                         iso-ir-101 { IANA WINDOWS JAVA }
 251                         l2 { IANA WINDOWS JAVA }
 252                         8859_2 { JAVA }
 253                         cp912 { JAVA }
 254                         912 { JAVA }
 255                         windows-28592 { WINDOWS* }
 256
 257 # Maltese Esperanto
 258 ibm-913_P100-2000 { UTR22* }
 259                         ibm-913 { IBM* JAVA }
 260                         iso-8859-3 { MIME* IANA WINDOWS JAVA* }
 261                         ISO_8859-3:1988 { IANA* WINDOWS JAVA }
 262                         latin3 { IANA JAVA WINDOWS }
 263                         csISOLatin3 { IANA WINDOWS }
 264                         iso-ir-109 { IANA WINDOWS JAVA }
 265                         l3 { IANA WINDOWS JAVA }
 266                         8859_3 { JAVA }
 267                         cp913 { JAVA }
 268                         913 { JAVA }
 269                         windows-28593 { WINDOWS* }
 270
 271 # Baltic
 272 ibm-914_P100-1995 { UTR22* }
 273                         ibm-914 { IBM* JAVA }
 274                         iso-8859-4 { MIME* IANA WINDOWS JAVA* }
 275                         latin4 { IANA WINDOWS JAVA }
 276                         csISOLatin4 { IANA WINDOWS JAVA }
 277                         iso-ir-110 { IANA WINDOWS JAVA }
 278                         ISO_8859-4:1988 { IANA* WINDOWS JAVA }
 279                         l4 { IANA WINDOWS JAVA }
 280                         8859_4 { JAVA }
 281                         cp914 { JAVA }
 282                         914 { JAVA }
 283                         windows-28594 { WINDOWS* }
 284
 285 # Cyrillic
 286 ibm-915_P100-1995 { UTR22* }
 287                         ibm-915 { IBM* JAVA }
 288                         iso-8859-5 { MIME* IANA WINDOWS JAVA* }
 289                         cyrillic { IANA WINDOWS JAVA }
 290                         csISOLatinCyrillic { IANA WINDOWS JAVA }
 291                         iso-ir-144 { IANA WINDOWS JAVA }
 292                         ISO_8859-5:1988 { IANA* WINDOWS JAVA }
 293                         8859_5 { JAVA }
 294                         cp915 { JAVA }
 295                         915 { JAVA }
 296                         windows-28595 { WINDOWS* }
 297
 298 # Arabic
 299 # ISO_8859-6-E and ISO_8859-6-I are similar to this charset, but BiDi is done differently
 300 # From a narrow mapping point of view, there is no difference.
 301 # -E means explicit. -I means implicit.
 302 # -E requires the client to handle the ISO 6429 bidirectional controls
 303 ibm-1089_P100-1995 { UTR22* }
 304                         ibm-1089 { IBM* JAVA }
 305                         iso-8859-6 { MIME* IANA WINDOWS JAVA* }
 306                         arabic { IANA WINDOWS JAVA }
 307                         csISOLatinArabic { IANA WINDOWS JAVA }
 308                         iso-ir-127 { IANA WINDOWS JAVA }
 309                         ISO_8859-6:1987 { IANA* WINDOWS JAVA }
 310                         ECMA-114 { IANA JAVA }
 311                         ASMO-708 { IANA JAVA }
 312                         8859_6 { JAVA }
 313                         cp1089 { JAVA }
 314                         1089 { JAVA }
 315                         windows-28596 { WINDOWS* }
 316                         ISO-8859-6-I { IANA MIME } # IANA considers this alias different and BiDi needs to be applied.
 317                         ISO-8859-6-E { IANA MIME } # IANA considers this alias different and BiDi needs to be applied.
 318
 319 # ISO Greek (w/o euro update)
 320 ibm-813_P100-1995 { UTR22* }
 321                         ibm-813 { IBM* JAVA }
 322                         iso-8859-7 { MIME* IANA WINDOWS JAVA* }
 323                         greek { IANA WINDOWS JAVA }
 324                         greek8 { IANA WINDOWS JAVA }
 325                         ELOT_928 { IANA WINDOWS JAVA }
 326                         ECMA-118 { IANA WINDOWS JAVA }
 327                         csISOLatinGreek { IANA WINDOWS JAVA }
 328                         iso-ir-126 { IANA WINDOWS JAVA }
 329                         ISO_8859-7:1987 { IANA* WINDOWS JAVA }
 330                         8859_7 { JAVA }
 331                         cp813 { JAVA }
 332                         813 { JAVA }
 333                         windows-28597 { WINDOWS* }
 334
 335 # hebrew
 336 # ISO_8859-8-E and ISO_8859-8-I are similar to this charset, but BiDi is done differently
 337 # From a narrow mapping point of view, there is no difference.
 338 # -E means explicit. -I means implicit.
 339 # -E requires the client to handle the ISO 6429 bidirectional controls
 340 ibm-916_P100-1995 { UTR22* }
 341                         ibm-916 { IBM* JAVA }
 342                         iso-8859-8 { MIME* IANA WINDOWS JAVA* }
 343                         hebrew { IANA WINDOWS JAVA }
 344                         csISOLatinHebrew { IANA WINDOWS JAVA }
 345                         iso-ir-138 { IANA WINDOWS JAVA }
 346                         ISO_8859-8:1988 { IANA* WINDOWS JAVA }
 347                         ISO-8859-8-I { IANA MIME } # IANA and Windows considers this alias different and BiDi needs to be applied.
 348                         ISO-8859-8-E { IANA MIME } # IANA and Windows considers this alias different and BiDi needs to be applied.
 349                         8859_8 { JAVA }
 350                         cp916 { JAVA }
 351                         916 { JAVA }
 352                         windows-28598 { WINDOWS* }
 353
 354 # Turkish
 355 ibm-920_P100-1995 { UTR22* }
 356                         ibm-920 { IBM* JAVA }
 357                         iso-8859-9 { MIME* IANA WINDOWS JAVA* }
 358                         latin5 { IANA WINDOWS JAVA }
 359                         csISOLatin5 { IANA JAVA }
 360                         iso-ir-148 { IANA WINDOWS JAVA }
 361                         ISO_8859-9:1989 { IANA* WINDOWS }
 362                         l5 { IANA WINDOWS JAVA }
 363                         8859_9 { JAVA }
 364                         cp920 { JAVA }
 365                         920 { JAVA }
 366                         windows-28599 { WINDOWS* }
 367                         ECMA-128    # IANA doesn't have this alias 6/24/2002
 368
 369 # iso-8859-13, PC Baltic (w/o euro update)
 370 ibm-921_P100-1995 { UTR22* }
 371                         ibm-921 { IBM* }
 372                         iso-8859-13 { IANA* MIME* JAVA* }
 373                         8859_13 { JAVA }
 374                         cp921
 375                         921
 376
 377 # Latin 9
 378 ibm-923_P100-1998 { UTR22* }
 379                         ibm-923 { IBM* JAVA }
 380                         iso-8859-15 { IANA* MIME* WINDOWS JAVA* }
 381                         Latin-9 { IANA WINDOWS }
 382                         l9 { WINDOWS }
 383                         8859_15 { JAVA }
 384                         latin0 { JAVA }
 385                         csisolatin0 { JAVA }
 386                         csisolatin9 { JAVA }
 387                         iso8859_15_fdis { JAVA }
 388                         cp923 { JAVA }
 389                         923 { JAVA }
 390                         windows-28605 { WINDOWS* }
 391
 392 # CJK encodings
 393
 394 ibm-942_P12A-1999 { UTR22* }    # ibm-942_P120 is a rarely used alternate mapping (sjis78 is already old)
 395                         ibm-942 { IBM* }
 396                         ibm-932 { IBM }
 397                         cp932
 398                         shift_jis78
 399                         sjis78
 400                         ibm-942_VSUB_VPUA
 401                         ibm-932_VSUB_VPUA
 402                         # Is this "JIS_C6226-1978"?
 403
 404 # ibm-943_P15A-2003 differs from windows-932-2000 only in a few roundtrip mappings:
 405 # - the usual IBM PC control code rotation (1A-1C-7F)
 406 # - the Windows table has roundtrips for bytes 80, A0, and FD-FF to U+0080 and PUA
 407 ibm-943_P15A-2003 { UTR22* }
 408                         ibm-943 # Leave untagged because this isn't the default
 409                         Shift_JIS { IANA* MIME* WINDOWS JAVA }
 410                         MS_Kanji { IANA WINDOWS JAVA }
 411                         csShiftJIS { IANA WINDOWS JAVA }
 412                         windows-31j { IANA JAVA } # A further extension of Shift_JIS to include NEC special characters (Row 13)
 413                         csWindows31J { IANA WINDOWS JAVA } # A further extension of Shift_JIS to include NEC special characters (Row 13)
 414                         x-sjis { WINDOWS JAVA }
 415                         x-ms-cp932 { WINDOWS }
 416                         cp932 { WINDOWS }
 417                         windows-932 { WINDOWS* }
 418                         cp943c { JAVA* }    # This is slightly different, but the backslash mapping is the same.
 419                         IBM-943C #{ AIX* } # Add this tag once AIX aliases becomes available
 420                         ms932
 421                         pck     # Probably SOLARIS
 422                         sjis    # This might be for ibm-1351
 423                         ibm-943_VSUB_VPUA
 424                         # cp943 # This isn't Windows, and no one else uses it.
 425                         # IANA says that Windows-31J is an extension to csshiftjis ibm-932
 426 ibm-943_P130-1999 { UTR22* }
 427                         ibm-943 { IBM* JAVA }
 428                         Shift_JIS # Leave untagged because this isn't the default
 429                         cp943 { JAVA* }    # This is slightly different, but the backslash mapping is the same.
 430                         943 { JAVA }
 431                         ibm-943_VASCII_VSUB_VPUA
 432                         # japanese. Unicode name is \u30b7\u30d5\u30c8\u7b26\u53f7\u5316\u8868\u73fe
 433 ibm-33722_P12A-1999 { UTR22* }
 434                         ibm-33722   # Leave untagged because this isn't the default
 435                         ibm-5050    # Leave untagged because this isn't the default, and yes this alias is correct
 436                         EUC-JP { IANA MIME* WINDOWS JAVA* }
 437                         Extended_UNIX_Code_Packed_Format_for_Japanese { IANA* WINDOWS JAVA }
 438                         csEUCPkdFmtJapanese { IANA WINDOWS JAVA }
 439                         X-EUC-JP { WINDOWS JAVA }   # Japan EUC. x-euc-jp is a MIME name
 440                         eucjis { JAVA }
 441                         windows-51932 { WINDOWS* }
 442                         ibm-33722_VPUA
 443                         IBM-eucJP
 444 ibm-33722_P120-1999 { UTR22* }  # Japan EUC with \ <-> Yen mapping
 445                         ibm-33722 { IBM* JAVA }
 446                         ibm-5050 { IBM }    # Yes this is correct
 447                         cp33722 { JAVA* }
 448                         33722 { JAVA }
 449                         ibm-33722_VASCII_VPUA
 450 # ibm-954 seems to be almost a superset of ibm-33722
 451 ibm-954_P101-2000 { UTR22* }
 452                         ibm-954 { IBM* }
 453                         EUC-JP # This is Solaris EUC-JP.
 454                         # eucJP # A closer Solaris alias
 455
 456 ibm-1373_P100-2002 { UTR22* }               # Taiwan Big-5 (w/ euro update)
 457                         ibm-1373 { IBM* }
 458                         windows-950 # Alternate mapping. Leave untagged. This is the IBM interpretation of a Windows codepage.
 459 windows-950-2000 { UTR22* }
 460                         Big5 { IANA* MIME* JAVA* WINDOWS }
 461                         csBig5 { IANA WINDOWS }
 462                         windows-950 { WINDOWS* }
 463                         x-big5
 464 ibm-950_P110-1999 { UTR22* }                # Taiwan Big-5 (w/o euro update)
 465                         ibm-950 { IBM* JAVA }
 466                         cp950 { JAVA* }
 467                         950 { JAVA }
 468 macos-2566-10.2 { UTR22* }      # This uses supplementary characters.
 469                         Big5-HKSCS { IANA* JAVA* }
 470                         big5hk { JAVA }
 471                         HKSCS-BIG5  # From http://www.openi18n.org/localenameguide/
 472                         # big5-hkscs:unicode3.0 # This is actually post 3.0 data, which has different mappings
 473 ibm-1375_P100-2003 { UTR22* }   # IBM's interpretation of Windows' Taiwan Big-5 w/ HKSCS extensions
 474                         ibm-1375 { IBM* }
 475                         Big5-HKSCS
 476                         # windows-950 # Windows-950 can be w/ or w/o HKSCS extensions. By default it's not.
 477                         # windows-950_hkscs
 478
 479 ibm-1386_P100-2002  { UTR22* }
 480                         ibm-1386 { IBM* JAVA }
 481                         cp1386 { JAVA* }
 482                         windows-936 # Alternate mapping. Leave untagged. This is the IBM interpretation of a Windows codepage.
 483                         ibm-1386_VSUB_VPUA
 484                         # zh_cn
 485
 486 windows-936-2000 { UTR22* }
 487                         GBK { IANA* WINDOWS }
 488                         CP936 { IANA }
 489                         MS936 { IANA }
 490                         windows-936 { IANA WINDOWS* }
 491
 492 ibm-1383_P110-1999 { UTR22* }       # China EUC.
 493                         ibm-1383 { IBM* }
 494                         GB2312 { IANA* MIME* }
 495                         csGB2312 { IANA }
 496                         EUC-CN  # According to other platforms, windows-20936 looks more like euc-cn. x-euc-cn is also a MIME name
 497                         ibm-eucCN
 498                         hp15CN  # From HP-UX?
 499                         cp1383
 500                         1383
 501                         ibm-1383_VPUA
 502                         # gb          # This is not an IANA name. gb in IANA means Great Britain.
 503
 504 ibm-5478_P100-1995 { UTR22* } ibm-5478 { IBM* } # This gb_2312_80 DBCS mapping is needed by iso-2022.
 505                         GB_2312-80 { IANA* }    # Windows maps this alias incorrectly
 506                         chinese { IANA }
 507                         iso-ir-58 { IANA }
 508                         csISO58GB231280 { IANA }
 509                         gb2312-1980
 510                         GB2312.1980-0   # From X11R6
 511
 512 ibm-964_P110-1999 { UTR22* }                # Taiwan EUC. x-euc-tw is a MIME name
 513                         ibm-964 { IBM* JAVA }
 514                         EUC-TW
 515                         ibm-eucTW
 516                         cns11643
 517                         cp964 { JAVA* }
 518                         964 { JAVA }
 519                         ibm-964_VPUA
 520
 521 # ISO-2022 needs one, and other people may need others.
 522 ibm-949_P110-1999 { UTR22* }
 523                         ibm-949 { IBM* JAVA }
 524                         cp949 { JAVA* }
 525                         949 { JAVA }
 526                         ibm-949_VASCII_VSUB_VPUA
 527 ibm-949_P11A-1999 { UTR22* }
 528                         ibm-949 # Leave untagged because this isn't the default
 529                         cp949c { JAVA* }
 530                         ibm-949_VSUB_VPUA
 531
 532 # Korean EUC.
 533 #
 534 # <quote from="Jungshik Shin">
 535 # 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.
 536 #
 537 # Although widely spread on MS Windows, using
 538 # KS C 5601 or related names to denote EUC-KR or
 539 # windows-949 is very much misleading. KS C 5601-1987
 540 # is NOT suitable as a designation for MIME charset
 541 # and MBCS. It's just the name of a 94 x 94 Korean
 542 # coded character set standard which can be invoked
 543 # on either GL (with MSB reset) or GR (with MSB set).
 544 # Note that JOHAB (windows-1361) specified in
 545 # KS X 1001:1998 annex 3 (KS C 5601-1992 annex 3)
 546 # is a _seprate_ MBCS with a _completely different_
 547 # mapping.
 548 # </quote>
 549 #
 550 # The following aliases tries to mirror the poor state of alias recognition
 551 # on these platforms.
 552 #
 553 # ibm-970 is almost a subset of ibm-1363.
 554 # Java, Solaris and AIX use euc-kr to also mean ksc5601.
 555 ibm-970_P110-1995 { UTR22* }
 556                         ibm-970 { IBM* JAVA }
 557                         EUC-KR { IANA* MIME* WINDOWS JAVA* }
 558                         KS_C_5601-1987 { JAVA }
 559                         windows-51949 { WINDOWS* }
 560                         csEUCKR { IANA WINDOWS }  # x-euc-kr is also a MIME name
 561                         ibm-eucKR { JAVA }
 562                         KSC_5601 { JAVA } # Needed by iso-2022
 563                         5601 { JAVA }
 564                         ibm-970_VPUA
 565
 566 # ibm-971 is almost the set of DBCS mappings of ibm-970
 567 ibm-971_P100-1995       ibm-971 { IBM* } ibm-971_VPUA
 568
 569 # Java, Solaris and AIX use euc-kr to also mean ksc5601, and _sometimes_ for Windows too.
 570 # ibm-1363 is almost a superset of ibm-970.
 571 ibm-1363_P11B-1998 { UTR22* }
 572                         ibm-1363 # Leave untagged because this isn't the default
 573                         KS_C_5601-1987 { IANA* }
 574                         KS_C_5601-1989 { IANA }
 575                         KSC_5601 { MIME* IANA } # Needed by iso-2022
 576                         csKSC56011987 { IANA }
 577                         korean { IANA }
 578                         iso-ir-149 { IANA }
 579                         5601
 580                         cp1363
 581                         ksc
 582                         windows-949 # Alternate mapping. Leave untagged. This is the IBM interpretation of a Windows codepage.
 583                         ibm-1363_VSUB_VPUA
 584                         # ks_x_1001:1992
 585                         # ksc5601-1992
 586
 587 ibm-1363_P110-1997 { UTR22* } # Korean KSC MBCS with \ <-> Won mapping
 588                         ibm-1363 { IBM* }
 589                         ibm-1363_VASCII_VSUB_VPUA
 590
 591 windows-949-2000 { UTR22* }
 592                         windows-949 { JAVA* WINDOWS* }
 593                         KS_C_5601-1987 { WINDOWS }
 594                         KS_C_5601-1989 { WINDOWS }
 595                         KSC_5601 { WINDOWS } # Needed by iso-2022
 596                         csKSC56011987 { WINDOWS }
 597                         korean { WINDOWS }
 598                         iso-ir-149 { WINDOWS }
 599                         ms949 { JAVA }
 600
 601 ibm-1162_P100-1999 { UTR22* }   # Thai (w/ euro update)
 602                         ibm-1162 { IBM* }
 603
 604 ibm-874_P100-1995 { UTR22* }    # Thai PC (w/o euro update).
 605                         ibm-874 { IBM* JAVA }
 606                         ibm-9066 { IBM }    # Yes ibm-874 == ibm-9066. ibm-1161 has the euro update.
 607                         cp874 { JAVA* }
 608                         TIS-620 { IANA* JAVA }  # This actually separate from ibm-874, which is similar to this table
 609                         tis620.2533 { JAVA }    # This actually separate from ibm-874, which is similar to this table
 610                         eucTH               # eucTH is an unusual alias from Solaris.  eucTH has fewer mappings than TIS620
 611                         cp9066
 612
 613 windows-874-2000 { UTR22* }   # Thai (w/ euro update)
 614                         TIS-620 { WINDOWS }
 615                         windows-874 { JAVA* WINDOWS* }
 616                         MS874 { JAVA }
 617                         # iso-8859-11 { WINDOWS } # iso-8859-11 is similar to TIS-620. ibm-13162 is a closer match.
 618
 619 # Platform codepages
 620 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
 621 ibm-850_P100-1995 { UTR22* }    ibm-850 { IBM* } IBM850 { IANA* WINDOWS JAVA } cp850 { IANA MIME* WINDOWS JAVA* } 850 { IANA JAVA } csPC850Multilingual { IANA JAVA } windows-850 { WINDOWS* } # PC latin1
 622 ibm-851_P100-1995 { UTR22* }    ibm-851 { IBM* } IBM851 { IANA* } cp851 { IANA MIME* } 851 { IANA } csPC851 { IANA }             # PC DOS Greek (w/o euro)
 623 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)
 624 ibm-855_P100-1995 { UTR22* }    ibm-855 { IBM* } IBM855 { IANA* } cp855 { IANA } 855 { IANA } csIBM855 { IANA } csPCp855 # PC cyrillic (w/o euro update)
 625 ibm-856_P100-1995 { UTR22* }    ibm-856 { IBM* JAVA } cp856 { MIME* JAVA* } 856 { JAVA }  # PC Hebrew (old)
 626 ibm-857_P100-1995 { UTR22* }    ibm-857 { IBM* } IBM857 { IANA* WINDOWS JAVA } cp857 { IANA MIME* JAVA* } 857 { IANA JAVA } csIBM857 { IANA JAVA } windows-857 { WINDOWS* }   # PC Latin 5 (w/o euro update)
 627 ibm-858_P100-1997 { UTR22* }    ibm-858 { IBM* JAVA* } IBM00858 { IANA* } CCSID00858 { IANA } CP00858 { IANA } PC-Multilingual-850+euro { IANA } cp858 { MIME* }  # PC latin1 with Euro
 628 ibm-860_P100-1995 { UTR22* }    ibm-860 { IBM* } IBM860 { IANA* JAVA } cp860 { IANA MIME* JAVA* } 860 { IANA JAVA } csIBM860 { IANA JAVA }    # PC Portugal
 629 ibm-861_P100-1995 { UTR22* }    ibm-861 { IBM* } IBM861 { IANA* WINDOWS JAVA } cp861 { IANA MIME* JAVA* } 861 { IANA JAVA } cp-is { IANA JAVA } csIBM861 { IANA JAVA } windows-861 { WINDOWS* } # PC Iceland
 630 ibm-862_P100-1995 { UTR22* }    ibm-862 { IBM* } IBM862 { IANA* JAVA } cp862 { IANA MIME* JAVA* } 862 { IANA JAVA } csPC862LatinHebrew { IANA JAVA } DOS-862 { WINDOWS } windows-862 { WINDOWS* }    # PC Hebrew (w/o euro update)
 631 ibm-863_P100-1995 { UTR22* }    ibm-863 { IBM* } IBM863 { IANA* JAVA } cp863 { IANA MIME* JAVA* } 863 { IANA JAVA } csIBM863 { IANA JAVA }    # PC Canadian French
 632 ibm-864_X110-1999 { UTR22* }    ibm-864 { IBM* } IBM864 { IANA* JAVA } cp864 { IANA MIME* JAVA* } csIBM864 { IANA JAVA } # PC Arabic (w/o euro update)
 633 ibm-865_P100-1995 { UTR22* }    ibm-865 { IBM* } IBM865 { IANA* JAVA } cp865 { IANA MIME* JAVA* } 865 { IANA JAVA } csIBM865 { IANA JAVA }    # PC Nordic
 634 ibm-866_P100-1995 { UTR22* }    ibm-866 { IBM* } IBM866 { IANA* JAVA } cp866 { IANA MIME* WINDOWS JAVA* } 866 { IANA JAVA } csIBM866 { IANA JAVA } windows-866 { WINDOWS* } # PC Russian (w/o euro update)
 635 ibm-867_P100-1998 { UTR22* }    ibm-867 { IBM* } cp867   # PC Hebrew (w/ euro update) Updated version of ibm-862
 636 ibm-868_P100-1995 { UTR22* }    ibm-868 { IBM* } IBM868 { IANA* JAVA } CP868 { IANA MIME* JAVA* } 868 { JAVA } csIBM868 { IANA } cp-ar { IANA }          # PC Urdu
 637 ibm-869_P100-1995 { UTR22* }    ibm-869 { IBM* } IBM869 { IANA* 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)
 638 ibm-878_P100-1996 { UTR22* }    ibm-878 { IBM* } KOI8-R { IANA* MIME* JAVA* } koi8 { JAVA } csKOI8R { IANA JAVA } cp878   # Russian internet
 639 ibm-901_P100-1999 { UTR22* }    ibm-901 { IBM* } # PC Baltic (w/ euro update), update of ibm-921
 640 ibm-902_P100-1999 { UTR22* }    ibm-902 { IBM* } # PC Estonian (w/ euro update), update of ibm-922
 641 ibm-922_P100-1999 { UTR22* }    ibm-922 { IBM* JAVA }   cp922 { MIME* JAVA* } 922 { JAVA } # PC Estonian (w/o euro update)
 642 ibm-4909_P100-1999 { UTR22* }   ibm-4909 { IBM* } # ISO Greek (w/ euro update), update of ibm-813
 643
 644 # The cp aliases in this section aren't really windows aliases, but it was used by ICU for Windows.
 645 # cp is used to denote IBM in Java, and that is why we don't do that anymore.
 646 # The windows-* aliases mean windows codepages.
 647 ibm-5346_P100-1998 { UTR22* }   ibm-5346 { IBM* } windows-1250 { IANA* JAVA* WINDOWS* } cp1250 { WINDOWS }  # Windows Latin2 (w/ euro update)
 648 ibm-5347_P100-1998 { UTR22* }   ibm-5347 { IBM* } windows-1251 { IANA* JAVA* WINDOWS* } cp1251 { WINDOWS }  # Windows Cyrillic (w/ euro update)
 649 ibm-5348_P100-1997 { UTR22* }   ibm-5348 { IBM* } windows-1252 { IANA* JAVA* WINDOWS* } cp1252 { WINDOWS }  # Windows Latin1 (w/ euro update)
 650 ibm-5349_P100-1998 { UTR22* }   ibm-5349 { IBM* } windows-1253 { IANA* JAVA* WINDOWS* } cp1253 { WINDOWS }  # Windows Greek (w/ euro update)
 651 ibm-5350_P100-1998 { UTR22* }   ibm-5350 { IBM* } windows-1254 { IANA* JAVA* WINDOWS* } cp1254 { WINDOWS }  # Windows Turkish (w/ euro update)
 652 ibm-9447_P100-2002 { UTR22* }   ibm-9447 { IBM* } windows-1255 { IANA* JAVA* WINDOWS* } cp1255 { WINDOWS }  # Windows Hebrew (w/ euro update)
 653 windows-1256-2000 { UTR22* }    windows-1256 { IANA* JAVA* WINDOWS* } cp1256 { WINDOWS }                    # Windows Arabic (w/ euro update)
 654 ibm-9449_P100-2002 { UTR22* }   ibm-9449 { IBM* } windows-1257 { IANA* JAVA* WINDOWS* } cp1257 { WINDOWS }  # Windows Baltic (w/ euro update)
 655 ibm-5354_P100-1998 { UTR22* }   ibm-5354 { IBM* } windows-1258 { IANA* JAVA* WINDOWS* } cp1258 { WINDOWS }  # Windows Vietnamese (w/ euro update)
 656
 657 # These tables are out of date, and most don't have the Euro
 658 # Leave the windows- variants untagged. They are alternate tables of the newer ones above.
 659 ibm-1250_P100-1995 { UTR22* }   ibm-1250 { IBM* } windows-1250  # Old Windows Latin2 (w/o euro update)
 660 ibm-1251_P100-1995 { UTR22* }   ibm-1251 { IBM* } windows-1251  # Old Windows Cyrillic (w/o euro update)
 661 ibm-1252_P100-2000 { UTR22* }   ibm-1252 { IBM* } windows-1252  # Old Windows Latin 1 without Euro
 662 ibm-1253_P100-1995 { UTR22* }   ibm-1253 { IBM* } windows-1253  # Old Windows Greek (w/o euro update)
 663 ibm-1254_P100-1995 { UTR22* }   ibm-1254 { IBM* } windows-1254  # Old Windows Turkish (w/o euro update)
 664 ibm-1255_P100-1995 { UTR22* }   ibm-1255 { IBM* }               # Very old Windows Hebrew (w/o euro update)
 665 ibm-5351_P100-1998 { UTR22* }   ibm-5351 { IBM* } windows-1255  # Old Windows Hebrew (w/ euro update)
 666 ibm-1256_P110-1997 { UTR22* }   ibm-1256 { IBM* }               # Old Windows Arabic (w/o euro update)
 667 ibm-5352_P100-1998 { UTR22* }   ibm-5352 { IBM* } windows-1256  # Somewhat old Windows Arabic (w/ euro update)
 668 ibm-1257_P100-1995 { UTR22* }   ibm-1257 { IBM* }               # Old Windows Baltic (w/o euro update)
 669 ibm-5353_P100-1998 { UTR22* }   ibm-5353 { IBM* } windows-1257  # Somewhat old Windows Baltic (w/ euro update)
 670 ibm-1258_P100-1997 { UTR22* }   ibm-1258 { IBM* } windows-1258  # Old Windows Vietnamese (w/o euro update)
 671
 672 macos-0_2-10.2 { UTR22* }       macintosh { IANA* MIME* WINDOWS } mac { IANA } csMacintosh { IANA } windows-10000 { WINDOWS* } # Apple latin 1
 673 macos-6-10.2 { UTR22* }         x-mac-greek { MIME* WINDOWS } windows-10006 { WINDOWS* } macgr           # Apple Greek
 674 macos-7_3-10.2 { UTR22* }       x-mac-cyrillic { MIME* WINDOWS } windows-10007 { WINDOWS* } maccy        # Apple Cyrillic
 675 macos-29-10.2 { UTR22* }        x-mac-centraleurroman { MIME* } windows-10029 { WINDOWS* } x-mac-ce { WINDOWS } macce   # Apple Central Europe
 676 macos-35-10.2 { UTR22* }        x-mac-turkish { MIME* WINDOWS } windows-10081 { WINDOWS* } mactr         # Apple Turkish
 677
 678 ibm-1051_P100-1995 { UTR22* }   ibm-1051 { IBM* } hp-roman8 { IANA* } roman8 { IANA } r8 { IANA } csHPRoman8 { IANA }   # HP Latin1
 679 ibm-1276_P100-1995 { UTR22* }   ibm-1276 { IBM* } Adobe-Standard-Encoding { IANA* } csAdobeStandardEncoding { IANA } # Different from ISO-Unicode-IBM-1276 (GCSGID: 1276)
 680 ibm-1277_P100-1995 { UTR22* }   ibm-1277 { IBM* } Adobe-Latin1-Encoding
 681
 682 ibm-1006_P100-1995 { UTR22* }   ibm-1006 { IBM* JAVA } cp1006 { JAVA* } 1006 { JAVA }   # Urdu
 683 ibm-1098_P100-1995 { UTR22* }   ibm-1098 { IBM* JAVA } cp1098 { JAVA* } 1098 { JAVA }   # PC Farsi
 684 ibm-1124_P100-1996 { UTR22* }   ibm-1124 { IBM* JAVA } cp1124 { JAVA* } 1124 { JAVA }   # ISO Cyrillic Ukraine
 685 ibm-1125_P100-1997 { UTR22* }   ibm-1125 { IBM* JAVA } cp1125 { JAVA* }                 # Cyrillic Ukraine PC
 686 ibm-1129_P100-1997 { UTR22* }   ibm-1129 { IBM* }                                       # ISO Vietnamese
 687 ibm-1131_P100-1997 { UTR22* }   ibm-1131 { IBM* JAVA } cp1131 { JAVA* }                 # Cyrillic Belarus PC
 688 ibm-1133_P100-1997 { UTR22* }   ibm-1133 { IBM* }                                       # ISO Lao
 689 ibm-1381_P110-1999 { UTR22* }   ibm-1381 { IBM* JAVA } cp1381 { JAVA* } 1381 { JAVA }   # S-Ch PC Data mixed (IBM GB)
 690
 691
 692 # Partially algorithmic converters
 693
 694 # [U_ENABLE_GENERIC_ISO_2022]
 695 # The _generic_ ISO-2022 converter is disabled starting 2003-dec-03 (ICU 2.8).
 696 # For details see the icu mailing list from 2003-dec-01 and the ucnv2022.c file.
 697 # Language-specific variants of ISO-2022 continue to be available as listed below.
 698 # ISO_2022                         ISO-2022 { MIME* } 2022 cp2022
 699
 700 ISO_2022,locale=ja,version=0    ISO-2022-JP { IANA* MIME* JAVA* } csISO2022JP { JAVA }
 701 ISO_2022,locale=ja,version=1    ISO-2022-JP-1 JIS JIS_Encoding { IANA* }
 702 ISO_2022,locale=ja,version=2    ISO-2022-JP-2 { IANA* MIME* } csISO2022JP2
 703 ISO_2022,locale=ja,version=3    JIS7 csJISEncoding
 704 ISO_2022,locale=ja,version=4    JIS8
 705 ISO_2022,locale=ko,version=0    ISO-2022-KR { IANA* MIME* } csISO2022KR # This uses ibm-949
 706 ISO_2022,locale=ko,version=1    ibm-25546
 707 ISO_2022,locale=zh,version=0    ISO-2022-CN { IANA* MIME* } # csISO2022CN
 708 ISO_2022,locale=zh,version=1    ISO-2022-CN-EXT { IANA* MIME* }
 709 HZ                              HZ-GB-2312 { IANA* MIME* }
 710
 711 # Part of iso-2022
 712 ibm-897_P100-1995 { UTR22* }    ibm-897 { IBM* } JIS_X0201 { IANA* } X0201 { IANA } csHalfWidthKatakana { IANA }
 713
 714
 715 ISCII,version=0         x-iscii-de { WINDOWS } windows-57002 { WINDOWS* } iscii-dev
 716 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.
 717 ISCII,version=2         x-iscii-pa { WINDOWS } windows-57011 { WINDOWS* } iscii-gur
 718 ISCII,version=3         x-iscii-gu { WINDOWS } windows-57010 { WINDOWS* } iscii-guj
 719 ISCII,version=4         x-iscii-or { WINDOWS } windows-57007 { WINDOWS* } iscii-ori
 720 ISCII,version=5         x-iscii-ta { WINDOWS } windows-57004 { WINDOWS* } iscii-tml
 721 ISCII,version=6         x-iscii-te { WINDOWS } windows-57005 { WINDOWS* } iscii-tlg
 722 ISCII,version=7         x-iscii-ka { WINDOWS } windows-57008 { WINDOWS* } iscii-knd
 723 ISCII,version=8         x-iscii-ma { WINDOWS } windows-57009 { WINDOWS* } iscii-mlm
 724
 725 # Lotus specific
 726 LMBCS-1                 lmbcs
 727 LMBCS-2
 728 LMBCS-3
 729 LMBCS-4
 730 LMBCS-5
 731 LMBCS-6
 732 LMBCS-8
 733 LMBCS-11
 734 LMBCS-16
 735 LMBCS-17
 736 LMBCS-18
 737 LMBCS-19
 738
 739 # EBCDIC codepages according to the CDRA
 740
 741 # without Euro
 742 ibm-37_P100-1995 { UTR22* }              # EBCDIC US
 743                         ibm-37 { IBM* }
 744                         IBM037 { IANA* }
 745                         ibm-037 { JAVA }
 746                         ebcdic-cp-us { IANA }
 747                         ebcdic-cp-ca { IANA }
 748                         ebcdic-cp-wt { IANA }
 749                         ebcdic-cp-nl { IANA }
 750                         csIBM037 { IANA }
 751                         cp037 { JAVA* }
 752                         037 { JAVA }
 753                         cpibm37
 754                         cp37
 755
 756 ibm-273_P100-1995 { UTR22* }    ibm-273 { IBM* } IBM273 { IANA* JAVA } CP273 { IANA JAVA* } csIBM273 { IANA } ebcdic-de cpibm273 273 # EBCDIC Germanay, Austria
 757 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 cpibm277 277 # EBCDIC Denmark
 758 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 cpibm278 278 # EBCDIC Sweden
 759 ibm-280_P100-1995 { UTR22* }    ibm-280 { IBM* } IBM280 { IANA* JAVA } CP280 { IANA JAVA* } ebcdic-cp-it { IANA } csIBM280 { IANA } cpibm280 280 # EBCDIC Italy
 760 ibm-284_P100-1995 { UTR22* }    ibm-284 { IBM* } IBM284 { IANA* JAVA } CP284 { IANA JAVA* } ebcdic-cp-es { IANA } csIBM284 { IANA } cpibm284 284 # EBCDIC Spain
 761 ibm-285_P100-1995 { UTR22* }    ibm-285 { IBM* } IBM285 { IANA* JAVA } CP285 { IANA JAVA* } ebcdic-cp-gb { IANA } csIBM285 { IANA } ebcdic-gb cpibm285 285 # EBCDIC UK Ireland
 762 ibm-290_P100-1995 { UTR22* }    ibm-290 { IBM* } IBM290 { IANA* } cp290 { IANA } EBCDIC-JP-kana { IANA } csIBM290 { IANA } # host SBCS (Katakana)
 763 ibm-297_P100-1995 { UTR22* }    ibm-297 { IBM* } IBM297 { IANA* JAVA } cp297 { IANA JAVA* } ebcdic-cp-fr { IANA } csIBM297 { IANA } cpibm297 297 # EBCDIC France
 764 ibm-420_X120-1999 { UTR22* }    ibm-420 { IBM* } IBM420 { IANA* JAVA } cp420 { IANA JAVA* } ebcdic-cp-ar1 { IANA } csIBM420 { IANA } 420        # EBCDIC Arabic (all presentation shapes)
 765 ibm-424_P100-1995 { UTR22* }    ibm-424 { IBM* } IBM424 { IANA* JAVA } cp424 { IANA JAVA* } ebcdic-cp-he { IANA } csIBM424 { IANA } 424         # EBCDIC Hebrew
 766 ibm-500_P100-1995 { UTR22* }    ibm-500 { IBM* } IBM500 { IANA* JAVA } CP500 { IANA JAVA* } ebcdic-cp-be { IANA } csIBM500 { IANA } ebcdic-cp-ch { IANA } cpibm500 500 # EBCDIC International Latin1
 767 ibm-803_P100-1999 { UTR22* }    ibm-803 { IBM* } cp803   # Old EBCDIC Hebrew
 768 ibm-838_P100-1995 { UTR22* }    ibm-838 { IBM* JAVA } IBM-Thai { IANA* } csIBMThai { IANA } cp838 { JAVA* } 838 { JAVA } ibm-9030 { IBM }   # EBCDIC Thai. Yes ibm-9030 is an alias.
 769 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
 770 ibm-871_P100-1995 { UTR22* }    ibm-871 { IBM* } IBM871 { IANA* } ebcdic-cp-is { IANA } csIBM871 { IANA } CP871 { IANA } ebcdic-is cpibm871 871 # EBCDIC Iceland
 771 ibm-875_P100-1995 { UTR22* }    ibm-875 { IBM* } IBM875 { JAVA } cp875 { JAVA* } 875 # EBCDIC Greek
 772 ibm-918_P100-1995 { UTR22* }    ibm-918 { IBM* } IBM918 { IANA* JAVA } CP918 { IANA JAVA* } ebcdic-cp-ar2 { IANA } csIBM918 { IANA } # EBCDIC Urdu
 773 ibm-930_P120-1999 { UTR22* }    # EBCDIC_STATEFUL Katakana-Kanji Host Mixed.
 774                         ibm-930 { IBM* JAVA }
 775                         ibm-5026 { IBM } # Yes this is correct
 776                         cp930 { JAVA* }
 777                         cpibm930
 778                         930 { JAVA }
 779 ibm-933_P110-1995 { UTR22* }    ibm-933 { IBM* JAVA } cp933 { JAVA* } cpibm933 933 { JAVA } # Korea EBCDIC MIXED
 780 ibm-935_P110-1999 { UTR22* }    ibm-935 { IBM* JAVA } cp935 { JAVA* } cpibm935 935 { JAVA } # China EBCDIC MIXED. Need to use Unicode, ibm-1388 or gb18030 instead because it is required by the government of China.
 781 ibm-937_P110-1999 { UTR22* }    ibm-937 { IBM* JAVA } cp937 { JAVA* } cpibm937 937 { JAVA } # Taiwan EBCDIC MIXED
 782 ibm-939_P120-1999 { UTR22* }    # EBCDIC_STATEFUL Latin-Kanji Host Mixed.
 783                         ibm-939 { IBM* JAVA }
 784                         ibm-931 { IBM }     # Yes this is correct
 785                         ibm-5035 { IBM }    # Yes this is also correct
 786                         cp939 { JAVA* }
 787                         939 { JAVA }
 788 ibm-1025_P100-1995 { UTR22* }   ibm-1025 { IBM* JAVA } cp1025 { JAVA* } 1025 { JAVA }       # EBCDIC Cyrillic
 789 ibm-1026_P100-1995 { UTR22* }   ibm-1026 { IBM* JAVA } IBM1026 { IANA* } CP1026 { IANA JAVA* } csIBM1026 { IANA } 1026 { JAVA } # EBCDIC Turkey
 790 ibm-1047_P100-1995 { UTR22* }   ibm-1047 { IBM* } IBM1047 { IANA* } cpibm1047                       # EBCDIC Open systems Latin1
 791 ibm-1097_P100-1995 { UTR22* }   ibm-1097 { IBM* JAVA } cp1097 { JAVA* } 1097 { JAVA }               # EBCDIC Farsi
 792 ibm-1112_P100-1995 { UTR22* }   ibm-1112 { IBM* JAVA } cp1112 { JAVA* } 1112 { JAVA }               # EBCDIC Baltic
 793 ibm-1122_P100-1999 { UTR22* }   ibm-1122 { IBM* JAVA } cp1122 { JAVA* } 1122 { JAVA }               # EBCDIC Estonia
 794 ibm-1123_P100-1995 { UTR22* }   ibm-1123 { IBM* JAVA } cp1123 { JAVA* } 1123 { JAVA } cpibm1123     # EBCDIC Cyrillic Ukraine
 795 ibm-1130_P100-1997 { UTR22* }   ibm-1130 { IBM* }       # EBCDIC Vietnamese
 796 ibm-1132_P100-1998 { UTR22* }   ibm-1132 { IBM* }       # EBCDIC Lao
 797
 798 # with Euro
 799 ibm-1140_P100-1997 { UTR22* }   ibm-1140 { IBM* JAVA } IBM01140 { IANA* } CCSID01140 { IANA } CP01140 { IANA } cp1140 { JAVA* } cpibm1140 ebcdic-us-37+euro { IANA } # EBCDIC US
 800 ibm-1141_P100-1997 { UTR22* }   ibm-1141 { IBM* JAVA } IBM01141 { IANA* } CCSID01141 { IANA } CP01141 { IANA } cp1141 { JAVA* } cpibm1141 ebcdic-de-273+euro { IANA } # EBCDIC Germanay, Austria
 801 ibm-1142_P100-1997 { UTR22* }   ibm-1142 { IBM* JAVA } IBM01142 { IANA* } CCSID01142 { IANA } CP01142 { IANA } cp1142 { JAVA* } cpibm1142 ebcdic-dk-277+euro { IANA } ebcdic-no-277+euro { IANA } # EBCDIC Denmark
 802 ibm-1143_P100-1997 { UTR22* }   ibm-1143 { IBM* JAVA } IBM01143 { IANA* } CCSID01143 { IANA } CP01143 { IANA } cp1143 { JAVA* } cpibm1143 ebcdic-fi-278+euro { IANA } ebcdic-se-278+euro { IANA } # EBCDIC Sweden
 803 ibm-1144_P100-1997 { UTR22* }   ibm-1144 { IBM* JAVA } IBM01144 { IANA* } CCSID01144 { IANA } CP01144 { IANA } cp1144 { JAVA* } cpibm1144 ebcdic-it-280+euro { IANA } # EBCDIC Italy
 804 ibm-1145_P100-1997 { UTR22* }   ibm-1145 { IBM* JAVA } IBM01145 { IANA* } CCSID01145 { IANA } CP01145 { IANA } cp1145 { JAVA* } cpibm1145 ebcdic-es-284+euro { IANA } # EBCDIC Spain
 805 ibm-1146_P100-1997 { UTR22* }   ibm-1146 { IBM* JAVA } IBM01146 { IANA* } CCSID01146 { IANA } CP01146 { IANA } cp1146 { JAVA* } cpibm1146 ebcdic-gb-285+euro { IANA } # EBCDIC UK Ireland
 806 ibm-1147_P100-1997 { UTR22* }   ibm-1147 { IBM* JAVA } IBM01147 { IANA* } CCSID01147 { IANA } CP01147 { IANA } cp1147 { JAVA* } cpibm1147 ebcdic-fr-297+euro { IANA } # EBCDIC France
 807 ibm-1148_P100-1997 { UTR22* }   ibm-1148 { IBM* JAVA } IBM01148 { IANA* } CCSID01148 { IANA } CP01148 { IANA } cp1148 { JAVA* } cpibm1148 ebcdic-international-500+euro { IANA } # EBCDIC International Latin1
 808 ibm-1149_P100-1997 { UTR22* }   ibm-1149 { IBM* JAVA } IBM01149 { IANA* } CCSID01149 { IANA } CP01149 { IANA } cp1149 { JAVA* } cpibm1149 ebcdic-is-871+euro { IANA } # EBCDIC Iceland
 809 ibm-1153_P100-1999 { UTR22* }   ibm-1153 { IBM* } cpibm1153             # EBCDIC latin 2
 810 ibm-1154_P100-1999 { UTR22* }   ibm-1154 { IBM* } cpibm1154             # EBCDIC Cyrillic Multilingual
 811 ibm-1155_P100-1999 { UTR22* }   ibm-1155 { IBM* } cpibm1155             # EBCDIC Turkey
 812 ibm-1156_P100-1999 { UTR22* }   ibm-1156 { IBM* } cpibm1156             # EBCDIC Baltic Multilingual
 813 ibm-1157_P100-1999 { UTR22* }   ibm-1157 { IBM* } cpibm1157             # EBCDIC Estonia
 814 ibm-1158_P100-1999 { UTR22* }   ibm-1158 { IBM* } cpibm1158             # EBCDIC Cyrillic Ukraine
 815 ibm-1160_P100-1999 { UTR22* }   ibm-1160 { IBM* } cpibm1160             # EBCDIC Thailand
 816 ibm-1164_P100-1999 { UTR22* }   ibm-1164 { IBM* } cpibm1164             # EBCDIC Viet Nam
 817 ibm-1364_P110-1997 { UTR22* }   ibm-1364 { IBM* } cp1364                # Korean Host Mixed
 818 ibm-1371_P100-1999 { UTR22* }   ibm-1371 { IBM* } cpibm1371             # Taiwan EBCDIC MIXED
 819 ibm-1388_P103-2001 { UTR22* }   ibm-1388 { IBM* } ibm-9580 { IBM }      # S-Ch DBCS-Host Data GBK EBCDIC_STATEFUL. Yes ibm-9580 is an alias.
 820 ibm-1390_P110-2003 { UTR22* }   ibm-1390 { IBM* } cpibm1390             # Japan EBCDIC MIXED (JIS X 0213)
 821 ibm-1399_P110-2003 { UTR22* }   ibm-1399 { IBM* }                       # Host MBCS (Latin-Kanji) (JIS X 0213)
 822 ibm-16684_P110-2003 { UTR22* }  ibm-16684 { IBM* }                      # DBCS Jis + Roman Jis Host. This is the DBCS portion of ibm-1390 and ibm-1399 (JIS X 0213)
 823 ibm-4899_P100-1998 { UTR22* }   ibm-4899 { IBM* } cpibm4899             # Old EBCDIC Hebrew
 824 ibm-4971_P100-1999 { UTR22* }   ibm-4971 { IBM* } cpibm4971             # EBCDIC Greek
 825 ibm-12712_P100-1998 { UTR22* }  ibm-12712 { IBM* } cpibm12712 ebcdic-he # EBCDIC Hebrew (new sheqel, control charaters update)
 826 ibm-16804_X110-1999 { UTR22* }  ibm-16804 { IBM* } cpibm16804 ebcdic-ar # EBCDIC Arabic
 827
 828
 829 # TODO: Consider removing the mappings in this section
 830 ibm-1137_P100-1999 { UTR22* }   ibm-1137 { IBM* }   # Devanagari EBCDIC (based on Unicode character set)
 831 ibm-5123_P100-1999 { UTR22* }   ibm-5123 { IBM* }   # Host Roman Jis. Euro update of ibm-1027
 832 ibm-8482_P100-1999 { UTR22* }   ibm-8482 { IBM* }   # host SBCS (Katakana). Euro update of ibm-290
 833
 834
 835 # EBCDIC codepages for S/390, with LF and NL codes swapped
 836 # Starting with ICU 2.4, the swapping is done by modifying the
 837 # normal tables at runtime instead of at build time.
 838 # Append UCNV_SWAP_LFNL_OPTION_STRING to the "ibm-CCSID" name to select this.
 839 #
 840 # Example: "ibm-1047,swaplfnl" or "ibm-1047" UCNV_SWAP_LFNL_OPTION_STRING
 841 #
 842 # This avoids the duplication of all EBCDIC SBCS and mixed-SBCS/DBCS
 843 # mapping files.
 844
 845 # Some examples below for declaring old-style, obsolete aliases with the "-s390"
 846 # suffix to map to the new-style, recommended names with the option added.
 847 # These are listed here for backward compatibility.
 848 # Do not use these; instead use the normal converter name with the option
 849 # added as recommended above.
 850
 851 # Note: It is not possible to define an alias (non-initial name in a line here)
 852 # that itself contains a converter option like this one for swapping LF<->NL.
 853 # Such names would never be found because ucnv_open() will first parse and strip
 854 # options before looking up a name in this table.
 855 # ucnv_open() then parses the lookup result (the canonical name on the left
 856 # in lines here) as well.
 857
 858 # This also means that it is not necessary to add anything to convrtrs.txt
 859 # for converter names like "ibm-1026,swaplfnl" to work -
 860 # they are already covered by the normal option parsing together with the
 861 # regular, option-less alias elsewhere in this file.
 862
 863 ibm-37_P100-1995,swaplfnl     ibm-37-s390 ibm037-s390
 864 ibm-1047_P100-1995,swaplfnl   ibm-1047-s390
 865 ibm-1140_P100-1997,swaplfnl   ibm-1140-s390
 866 ibm-1142_P100-1997,swaplfnl   ibm-1142-s390
 867 ibm-1143_P100-1997,swaplfnl   ibm-1143-s390
 868 ibm-1144_P100-1997,swaplfnl   ibm-1144-s390
 869 ibm-1145_P100-1997,swaplfnl   ibm-1145-s390
 870 ibm-1146_P100-1997,swaplfnl   ibm-1146-s390
 871 ibm-1147_P100-1997,swaplfnl   ibm-1147-s390
 872 ibm-1148_P100-1997,swaplfnl   ibm-1148-s390
 873 ibm-1149_P100-1997,swaplfnl   ibm-1149-s390
 874 ibm-1153_P100-1999,swaplfnl   ibm-1153-s390
 875 ibm-12712_P100-1998,swaplfnl  ibm-12712-s390
 876 ibm-16804_X110-1999,swaplfnl  ibm-16804-s390
 877
 878 # This is a special version of ibm-1140 that the XML4C (Xerces) parser team
 879 # requested in 2000.
 880 # It maps both EBCDIC LF and NL controls to Unicode LF U+000A.
 881
 882 ebcdic-xml-us
 883
 884
 885
 886 # These were removed due to age, and they are rarely used.
 887
 888 # ibm-274   IBM274 { IANA* } cp274 csIBM274 ebcdic-be
 889 # ibm-870   IBM870 { IANA* } ebcdic-cp-roece ebcdic-cp-yu csIBM870 cp870 870
 890
 891 #ibm-942_P120-1999 { UTR22* }
 892 #                        #ibm-942 { IBM* }
 893 #                        ibm-942_VASCII_VSUB_VPUA
 894 #                        #ibm-932 { IBM }
 895 #                        ibm-932_VASCII_VSUB_VPUA   # Old s_jis
 896 #ibm-859 { IBM* }        cp859 { MIME* }     # PC Latin 9 (w/ euro update)
 897 #ibm-5104_X110-1999 { UTR22* }   ibm-5104 { IBM* } cp1008    # 8-bit Arabic (w/ euro update)
 898 #ibm-9238 { IBM* }               cp1046                      # PC Arabic Extended (w/ euro update)
 899 #ibm-17248_X110-1999 { UTR22* }  ibm-17248 { IBM* }          # PC Arabic (w/ euro update) Updated version of ibm-864
 900
 901 #ibm-941                 jis-208 jisx-208    # Pure DBCS jisx-208 # ibm-941 is not JISX 208 code page
 902 #ibm-955                 jis-208 jisx-208    # Pure DBCS jisx-208
 903
 904 #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.
 905 #ibm-9027_P100-1999 { UTR22* }   ibm-9027 { IBM* }   # DBCS T-Ch Host. Euro update of ibm-835. DBCS portion of ibm-1371.
 906
 907