1 Index: source/data/mappings/windows-949-2000.ucm 2 =================================================================== 3 --- source/data/mappings/windows-949-2000.ucm (revision 259715) 4 +++ source/data/mappings/windows-949-2000.ucm (working copy) 5 @@ -32,18 +32,17 @@ 6 # Suggested ICU specific alias information 7 #<icu:alias> "windows-949_VPUA" 8 9 -<icu:state> 0-80, 81-fe:1, ff 10 -<icu:state> 40-7e, 80-fe 11 +# CHROME: Uses the generated state table. 12 +<icu:state> 0-80, 81-fe:1, ff 13 +<icu:state> 41-5a, 61-7a, 81-fe 14 +#<icu:state> 0-80, 81-fe:1, ff 15 +#<icu:state> 40-7e, 80-fe 16 17 # build an extension-only (delta) .cnv file 18 # requires the base .cnv file at runtime 19 -<icu:base> "ibm-1363_P11B-1998" 20 +# CHROME: We don't want to include ibm-1363. 21 +#<icu:base> "ibm-1363_P11B-1998" 22 23 -# The following was the generated state table. 24 -# This does not account for unassigned characters 25 -#<icu:state> 0-80, 81-fe:1, ff 26 -#<icu:state> 41-5a, 61-7a, 81-fe 27 -# 28 CHARMAP 29 <U0000> \x00 |0 30 <U0001> \x01 |0 31 Index: source/data/mappings/windows-950-2000.ucm 32 =================================================================== 33 --- source/data/mappings/windows-950-2000.ucm (revision 259715) 34 +++ source/data/mappings/windows-950-2000.ucm (working copy) 35 @@ -32,18 +32,15 @@ 36 # Suggested ICU specific alias information 37 #<icu:alias> "windows-950_VPUA" 38 39 -<icu:state> 0-80, 81-fe:1, ff 40 -<icu:state> 40-7e, 80-fe 41 +# CHROME: use the generated state table. 42 +<icu:state> 0-80, 81-fe:1, ff 43 +<icu:state> 40-7e, a1-fe 44 45 # build an extension-only (delta) .cnv file 46 # requires the base .cnv file at runtime 47 -<icu:base> "ibm-1373_P100-2002" 48 +# CHROME : we don't want to include ibm-1373 49 +#<icu:base> "ibm-1373_P100-2002" 50 51 -# The following was the generated state table. 52 -# This does not account for unassigned characters 53 -#<icu:state> 0-80, 81-fe:1, ff 54 -#<icu:state> 40-7e, a1-fe 55 -# 56 CHARMAP 57 <U0000> \x00 |0 58 <U0001> \x01 |0 59 Index: source/data/mappings/windows-936-2000.ucm 60 =================================================================== 61 --- source/data/mappings/windows-936-2000.ucm (revision 259715) 62 +++ source/data/mappings/windows-936-2000.ucm (working copy) 63 @@ -37,7 +37,8 @@ 64 65 # build an extension-only (delta) .cnv file 66 # requires the base .cnv file at runtime 67 -<icu:base> "ibm-1386_P100-2001" 68 +# CHROME : we don't want ibm-1386 69 +#<icu:base> "ibm-1386_P100-2001" 70 71 # The following was the generated state table. 72 # This does not account for unassigned characters 73 @@ -259,6 +260,7 @@ 74 <U01DA> \xA8\xB7 |0 75 <U01DB> \xA8\xB8 |1 76 <U01DC> \xA8\xB8 |0 77 +<U01F9> \xA8\xBF |1 78 <U0251> \xA8\xBB |0 79 <U0261> \xA8\xC0 |0 80 <U02C7> \xA1\xA6 |0 81 @@ -380,6 +382,7 @@ 82 <U044E> \xA7\xF0 |0 83 <U044F> \xA7\xF1 |0 84 <U0451> \xA7\xD7 |0 85 +<U1E3F> \xA8\xBC |1 86 <U2010> \xA9\x5C |0 87 <U2013> \xA8\x43 |0 88 <U2014> \xA1\xAA |0 89 @@ -472,6 +475,7 @@ 90 <U2299> \xA1\xD1 |0 91 <U22A5> \xA1\xCD |0 92 <U22BF> \xA8\x53 |0 93 +<U22EF> \xA1\xAD |1 94 <U2312> \xA1\xD0 |0 95 <U2460> \xA2\xD9 |0 96 <U2461> \xA2\xDA |0 97 @@ -696,6 +700,7 @@ 98 <U3015> \xA1\xB3 |0 99 <U3016> \xA1\xBC |0 100 <U3017> \xA1\xBD |0 101 +<U301C> \xA1\xAB |1 102 <U301D> \xA8\x94 |0 103 <U301E> \xA8\x95 |0 104 <U3021> \xA9\x40 |0 105 Index: source/data/mappings/convrtrs.txt 106 =================================================================== 107 --- source/data/mappings/convrtrs.txt (revision 259715) 108 +++ source/data/mappings/convrtrs.txt (working copy) 109 @@ -292,44 +292,8 @@ 110 # End of Java-specific, non-Unicode-standard UTF variants. 111 112 113 -# On UTF-7: 114 -# RFC 2152 (http://www.imc.org/rfc2152) allows to encode some US-ASCII 115 -# characters directly or in base64. Especially, the characters in set O 116 -# as defined in the RFC (!"#$%&*;<=>@[]^_`{|}) may be encoded directly 117 -# but are not allowed in, e.g., email headers. 118 -# By default, the ICU UTF-7 converter encodes set O directly. 119 -# By choosing the option "version=1", set O will be escaped instead. 120 -# For example: 121 -# utf7Converter=ucnv_open("UTF-7,version=1"); 122 -# 123 -# For details about email headers see RFC 2047. 124 -UTF-7 { IANA* MIME* WINDOWS } windows-65000 { WINDOWS* } 125 - unicode-1-1-utf-7 126 - unicode-2-0-utf-7 127 +# Chrome: Remove all the entries for UTF-7, SCSU, BOCU, CESU-8. 128 129 -# UTF-EBCDIC doesn't exist in ICU, but the aliases are here for reference. 130 -#UTF-EBCDIC ibm-1210 { IBM* } ibm-1211 { IBM } 131 - 132 -# IMAP-mailbox-name is an ICU-specific name for the encoding of IMAP mailbox names. 133 -# It is a substantially modified UTF-7 encoding. See the specification in: 134 -# 135 -# RFC 2060: INTERNET MESSAGE ACCESS PROTOCOL - VERSION 4rev1 136 -# (http://www.ietf.org/rfc/rfc2060.txt) 137 -# Section 5.1.3. Mailbox International Naming Convention 138 -IMAP-mailbox-name 139 - 140 -SCSU { IANA* } 141 - ibm-1212 { IBM } # SCSU with IBM PUA 142 - ibm-1213 { IBM* } # SCSU 143 -BOCU-1 { IANA* } 144 - csBOCU-1 { IANA } 145 - ibm-1214 { IBM } # BOCU-1 with IBM PUA 146 - ibm-1215 { IBM* } # BOCU-1 147 - 148 -# See http://www.unicode.org/unicode/reports/tr26 for this Compatibility Encoding Scheme for UTF-16 149 -# The Unicode Consortium does not encourage the use of CESU-8 150 -CESU-8 { IANA* } ibm-9400 { IBM* } 151 - 152 # Standard iso-8859-1, which does not have the Euro update. 153 # See iso-8859-15 (latin9) for the Euro update 154 ISO-8859-1 { MIME* IANA JAVA* } 155 @@ -364,7 +328,9 @@ 156 ibm-367 { IBM* } IBM367 { IANA WINDOWS } # This is not truely ibm-367 because it's missing the fallbacks. 157 158 # GB 18030 is partly algorithmic, using the MBCS converter 159 -gb18030 { IANA* } ibm-1392 { IBM* } windows-54936 { WINDOWS* } GB18030 { MIME* } 160 +# Chrome: HTML5 GBK an alias for GB18030 161 +# TODO(jshin): Decide if Chrome should follow spec. crbug.com/339862 162 +gb18030 { IANA* } ibm-1392 { IBM* } windows-54936 { WINDOWS* } gb18030 { MIME* } 163 164 # Table-based interchange codepages 165 166 @@ -423,13 +389,6 @@ 167 915 { JAVA } 168 windows-28595 { WINDOWS* } 169 170 -glibc-PT154-2.3.3 { UTR22* } 171 - PTCP154 { IANA* } 172 - csPTCP154 173 - PT154 174 - CP154 175 - Cyrillic-Asian 176 - 177 # Arabic 178 # ISO_8859-6-E and ISO_8859-6-I are similar to this charset, but BiDi is done differently 179 # From a narrow mapping point of view, there is no difference. 180 @@ -467,13 +426,6 @@ 181 windows-28597 { WINDOWS* } 182 sun_eu_greek # For Solaris 183 184 -# ISO Greek (w/o euro update) 185 -# JDK 1.5 has these aliases. 186 -ibm-813_P100-1995 { UTR22* } 187 - ibm-813 { IBM* JAVA* } 188 - cp813 { JAVA } 189 - 813 { JAVA } 190 - 191 # hebrew 192 # ISO_8859-8-E and ISO_8859-8-I are similar to this charset, but BiDi is done differently 193 # From a narrow mapping point of view, there is no difference. 194 @@ -493,23 +445,17 @@ 195 windows-28598 { WINDOWS* } # Hebrew (ISO-Visual). A hybrid between ibm-5012 and ibm-916 with extra PUA mappings. 196 hebrew8 # Reflect HP-UX code page update 197 198 -# Unfortunately, the Java aliases are split across ibm-916 and ibm-5012 199 -# Also many platforms are a combination between ibm-916 and ibm-5012 behaviors 200 -ibm-916_P100-1995 { UTR22* } 201 - ibm-916 { IBM* JAVA* } 202 - cp916 { JAVA } 203 - 916 { JAVA } 204 - 205 # Turkish 206 +# Chrome: ISO-8859-9 and its aliases are moved to windows-1254 per 207 +# HTML5. 208 ibm-920_P100-1995 { UTR22* } 209 ibm-920 { IBM* JAVA } 210 - ISO-8859-9 { MIME* IANA WINDOWS JAVA* } 211 - latin5 { IANA WINDOWS JAVA } 212 - csISOLatin5 { IANA JAVA } 213 - iso-ir-148 { IANA WINDOWS JAVA } 214 - ISO_8859-9:1989 { IANA* WINDOWS } 215 - l5 { IANA WINDOWS JAVA } 216 - 8859_9 { JAVA } 217 + ISO-8859-9 218 + latin5 219 + csISOLatin5 220 + iso-ir-148 221 + ISO_8859-9:1989 222 + l5 223 cp920 { JAVA } 224 920 { JAVA } 225 windows-28599 { WINDOWS* } 226 @@ -567,22 +513,11 @@ 227 228 # CJK encodings 229 230 -ibm-942_P12A-1999 { UTR22* } # ibm-942_P120 is a rarely used alternate mapping (sjis78 is already old) 231 - ibm-942 { IBM* } 232 - ibm-932 { IBM } 233 - cp932 234 - shift_jis78 235 - sjis78 236 - ibm-942_VSUB_VPUA 237 - ibm-932_VSUB_VPUA 238 - x-IBM942 { JAVA* } 239 - x-IBM942C { JAVA } 240 - # Is this "JIS_C6226-1978"? 241 +# Chrome: Instead of ibm-943_P15A-2003, we use what's specified in the WHATWG 242 +# encoding standard (HTML5) for Shift_JIS. Keep all the aliases (even though 243 +not all of them not required by the encoding spec) for now. 244 245 -# ibm-943_P15A-2003 differs from windows-932-2000 only in a few roundtrip mappings: 246 -# - the usual IBM PC control code rotation (1A-1C-7F) 247 -# - the Windows table has roundtrips for bytes 80, A0, and FD-FF to U+0080 and PUA 248 -ibm-943_P15A-2003 { UTR22* } 249 +shift_jis-html5 { UTR22* } 250 ibm-943 # Leave untagged because this isn't the default 251 Shift_JIS { IANA* MIME* WINDOWS JAVA } 252 MS_Kanji { IANA WINDOWS JAVA } 253 @@ -601,64 +536,20 @@ 254 ibm-943_VSUB_VPUA 255 x-MS932_0213 { JAVA } 256 x-JISAutoDetect { JAVA } 257 - # cp943 # This isn't Windows, and no one else uses it. 258 - # IANA says that Windows-31J is an extension to csshiftjis ibm-932 259 -ibm-943_P130-1999 { UTR22* } 260 - ibm-943 { IBM* JAVA } 261 - Shift_JIS # Leave untagged because this isn't the default 262 - cp943 { JAVA* } # This is slightly different, but the backslash mapping is the same. 263 - 943 { JAVA } 264 - ibm-943_VASCII_VSUB_VPUA 265 - x-IBM943 { JAVA } 266 - # japanese. Unicode name is \u30b7\u30d5\u30c8\u7b26\u53f7\u5316\u8868\u73fe 267 -ibm-33722_P12A_P12A-2009_U2 { UTR22* } 268 - ibm-33722 # Leave untagged because this isn't the default 269 - ibm-5050 # Leave untagged because this isn't the default, and yes this alias is correct 270 - ibm-33722_VPUA 271 - IBM-eucJP 272 -windows-51932-2006 { UTR22* } 273 - windows-51932 { WINDOWS* } 274 - CP51932 { IANA* } 275 - csCP51932 276 -ibm-33722_P120-1999 { UTR22* } # Japan EUC with \ <-> Yen mapping 277 - ibm-33722 { IBM* JAVA } 278 - ibm-5050 { IBM } # Yes this is correct 279 - cp33722 { JAVA* } 280 - 33722 { JAVA } 281 - ibm-33722_VASCII_VPUA 282 - x-IBM33722 { JAVA } 283 - x-IBM33722A { JAVA } 284 - x-IBM33722C { JAVA } 285 -# ibm-954 seems to be almost a superset of ibm-33722 and ibm-1350 286 -# ibm-1350 seems to be almost a superset of ibm-33722 287 -# ibm-954 contains more PUA characters than the others. 288 -ibm-954_P101-2007 { UTR22* } 289 - ibm-954 { IBM* } 290 - x-IBM954 { JAVA* } 291 - x-IBM954C { JAVA } 292 - # eucJP # This is closest to Solaris EUC-JP. 293 -euc-jp-2007 { UTR22* } 294 - EUC-JP { MIME* IANA JAVA* WINDOWS* } 295 + 296 +# Chrome: Instead of ibm-33722_P*, we use what's specified in the WHATWG 297 +# encoding standard (HTML5). All the 298 +# 3-byte seqeunces in the normative EUC-JP are now decode-only. 299 +euc-jp-html5 { UTR22* } 300 + EUC-JP { MIME* IANA JAVA* WINDOWS*} 301 Extended_UNIX_Code_Packed_Format_for_Japanese { IANA* JAVA WINDOWS } 302 csEUCPkdFmtJapanese { IANA JAVA WINDOWS } 303 + windows-51932 { WINDOWS } 304 X-EUC-JP { MIME JAVA WINDOWS } # Japan EUC. x-euc-jp is a MIME name 305 eucjis {JAVA} 306 ujis # Linux sometimes uses this name. This is an unfortunate generic and rarely used name. Its use is discouraged. 307 308 -aix-IBM_udcJP-4.3.6 { UTR22* } 309 - x-IBM-udcJP { JAVA* } 310 311 -java-euc_jp_linux-1.6_P { UTR22* } 312 - euc-jp-linux 313 - x-EUC_JP_LINUX { JAVA* } 314 - 315 -java-sjis_0213-1.6_P { UTR22* } 316 - x-SJIS_0213 { JAVA* } 317 - 318 -# Here are various interpretations and extentions of Big5 319 -ibm-1373_P100-2002 { UTR22* } # IBM's interpretation of Windows' Taiwan Big-5 without HKSCS extensions 320 - ibm-1373 { IBM* } 321 - windows-950 # Alternate mapping. Leave untagged. This is the IBM interpretation of a Windows codepage. 322 windows-950-2000 { UTR22* } 323 Big5 { IANA* MIME* JAVA* WINDOWS } 324 csBig5 { IANA WINDOWS } 325 @@ -666,16 +557,14 @@ 326 x-windows-950 { JAVA } 327 x-big5 328 ms950 329 -ibm-950_P110-1999 { UTR22* } # Taiwan Big-5 (w/o euro update) 330 - ibm-950 { IBM* JAVA } 331 - cp950 { JAVA* } 332 - 950 { JAVA } 333 - x-IBM950 { JAVA } 334 ibm-1375_P100-2007 { UTR22* } # Big5-HKSCS-2004 with Unicode 3.1 mappings. This uses supplementary characters. 335 ibm-1375 { IBM* } 336 Big5-HKSCS { IANA* JAVA* } 337 big5hk { JAVA } 338 HKSCS-BIG5 # From http://www.openi18n.org/localenameguide/ 339 + 340 +# Chrome: HTML5 has big5-hkscs as an alias for big5 341 +# TODO(jshin): Decide if Chrome should follow spec. crbug.com/277040 342 ibm-5471_P100-2006 { UTR22* } # Big5-HKSCS-2001 with Unicode 3.0 mappings. This uses many PUA characters. 343 ibm-5471 { IBM* } 344 Big5-HKSCS 345 @@ -685,201 +574,68 @@ 346 x-MS950-HKSCS { JAVA } 347 # windows-950 # Windows-950 can be w/ or w/o HKSCS extensions. By default it's not. 348 # windows-950_hkscs 349 -solaris-zh_TW_big5-2.7 { UTR22* } 350 - Big5_Solaris { JAVA* } 351 - x-Big5-Solaris { JAVA } 352 # GBK 353 -ibm-1386_P100-2001 { UTR22* } 354 - ibm-1386 { IBM* } 355 - cp1386 356 - windows-936 # Alternate mapping. Leave untagged. This is the IBM interpretation of a Windows codepage. 357 - ibm-1386_VSUB_VPUA 358 +# Chrome: Added 4 GB2312 aliases and EUC-CN to Windows-936 to reflect the 359 +# reality of the web (GB2312 is treated synonymously with its 360 +# superset, Windows-936/GBK) 361 +# All the aliases listed for this converter (windows-936-2000) 362 +# are removed from the list of aliases for other simplified Chinese 363 +# converters above. 364 +# HTML5 makes GBK an alias for GB18030 365 +# TODO(jshin): Decide if Chrome should follow spec. crbug.com/339862 366 windows-936-2000 { UTR22* } 367 - GBK { IANA* WINDOWS JAVA* } 368 + GB2312 { IANA MIME } 369 + GBK { IANA* MIME* WINDOWS JAVA* } 370 CP936 { IANA JAVA } 371 MS936 { IANA } # In JDK 1.5, this goes to x-mswin-936. This is an IANA name split. 372 windows-936 { IANA WINDOWS* JAVA } 373 - 374 -# Java has two different tables for ibm-1383 and gb2312. We pick closest set for tagging. 375 -ibm-1383_P110-1999 { UTR22* } # China EUC. 376 - ibm-1383 { IBM* JAVA } 377 - GB2312 { IANA* MIME* } 378 - csGB2312 { IANA } 379 - cp1383 { JAVA* } 380 - 1383 { JAVA } 381 - EUC-CN # According to other platforms, windows-20936 looks more like euc-cn. x-euc-cn is also a MIME name 382 - ibm-eucCN 383 - hp15CN # From HP-UX? 384 - ibm-1383_VPUA 385 - # gb # This is not an IANA name. gb in IANA means Great Britain. 386 - 387 -ibm-5478_P100-1995 { UTR22* } ibm-5478 { IBM* } # This gb_2312_80 DBCS mapping is needed by iso-2022. 388 - GB_2312-80 { IANA* } # Windows maps this alias incorrectly 389 chinese { IANA } 390 iso-ir-58 { IANA } 391 - csISO58GB231280 { IANA } 392 gb2312-1980 393 - GB2312.1980-0 # From X11R6 394 + EUC-CN 395 + csGB2312 { IANA } 396 + GB_2312-80 { IANA } 397 398 -ibm-964_P110-1999 { UTR22* } # Taiwan EUC. x-euc-tw is a MIME name 399 - ibm-964 { IBM* JAVA } 400 - EUC-TW 401 - ibm-eucTW 402 - cns11643 403 - cp964 { JAVA* } 404 - 964 { JAVA } 405 - ibm-964_VPUA 406 - x-IBM964 { JAVA } 407 408 -# ISO-2022 needs one, and other people may need others. 409 -ibm-949_P110-1999 { UTR22* } 410 - ibm-949 { IBM* JAVA } 411 - cp949 { JAVA* } 412 - 949 { JAVA } 413 - ibm-949_VASCII_VSUB_VPUA 414 - x-IBM949 { JAVA } 415 -ibm-949_P11A-1999 { UTR22* } 416 - ibm-949 # Leave untagged because this isn't the default 417 - cp949c { JAVA* } 418 - ibm-949_VSUB_VPUA 419 - x-IBM949C { JAVA } 420 - IBM-949C { JAVA } 421 +# Chrome: ibm-5478 and ibm-949 are replaced by noop-gb2312_gl and windows-949 422 +# (ksc_5601), respectively, in ucnv2022.c 423 424 # Korean EUC. 425 -# 426 -# <quote from="Jungshik Shin"> 427 -# 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. 428 -# 429 -# Although widely spread on MS Windows, using 430 -# KS C 5601 or related names to denote EUC-KR or 431 -# windows-949 is very much misleading. KS C 5601-1987 432 -# is NOT suitable as a designation for MIME charset 433 -# and MBCS. It's just the name of a 94 x 94 Korean 434 -# coded character set standard which can be invoked 435 -# on either GL (with MSB reset) or GR (with MSB set). 436 -# Note that JOHAB (windows-1361) specified in 437 -# KS X 1001:1998 annex 3 (KS C 5601-1992 annex 3) 438 -# is a _seprate_ MBCS with a _completely different_ 439 -# mapping. 440 -# </quote> 441 -# 442 -# The following aliases tries to mirror the poor state of alias recognition 443 -# on these platforms. 444 -# 445 -# ibm-970 is almost a subset of ibm-1363. 446 -# Java, Solaris and AIX use euc-kr to also mean ksc5601. 447 -# Java has both ibm-970 and EUC-KR as separate converters. 448 -ibm-970_P110_P110-2006_U2 { UTR22* } 449 - ibm-970 { IBM* JAVA } 450 - EUC-KR { IANA* MIME* WINDOWS JAVA } 451 - KS_C_5601-1987 { JAVA } 452 - windows-51949 { WINDOWS* } 453 - csEUCKR { IANA WINDOWS } # x-euc-kr is also a MIME name 454 - ibm-eucKR { JAVA } 455 - KSC_5601 { JAVA } # Needed by iso-2022 456 - 5601 { JAVA } 457 - cp970 { JAVA* } 458 - 970 { JAVA } 459 - ibm-970_VPUA 460 - x-IBM970 { JAVA } 461 462 -# ibm-971 is almost the set of DBCS mappings of ibm-970 463 -ibm-971_P100-1995 ibm-971 { IBM* } ibm-971_VPUA x-IBM971 { JAVA* } 464 - 465 -# Java, Solaris and AIX use euc-kr to also mean ksc5601, and _sometimes_ for Windows too. 466 -# ibm-1363 is almost a superset of ibm-970. 467 -ibm-1363_P11B-1998 { UTR22* } 468 - ibm-1363 # Leave untagged because this isn't the default 469 - KS_C_5601-1987 { IANA* } 470 - KS_C_5601-1989 { IANA } 471 - KSC_5601 { IANA } 472 - csKSC56011987 { IANA } 473 - korean { IANA } 474 - iso-ir-149 { IANA } 475 - cp1363 { MIME* } 476 - 5601 477 - ksc 478 - windows-949 # Alternate mapping. Leave untagged. This is the IBM interpretation of a Windows codepage. 479 - ibm-1363_VSUB_VPUA 480 - x-IBM1363C { JAVA* } 481 - # ks_x_1001:1992 482 - # ksc5601-1992 483 - 484 -ibm-1363_P110-1997 { UTR22* } # Korean KSC MBCS with \ <-> Won mapping 485 - ibm-1363 { IBM* } 486 - ibm-1363_VASCII_VSUB_VPUA 487 - x-IBM1363 { JAVA* } 488 - 489 +# Chrome: Windows-949 is not EUC-KR, but a superset of EUC-KR with 8,822 490 +# additional Hangul syllables. However, the reality of the web 491 +# and HTML5 require that we treat EUC-KR a 492 +# synonym of windows-949. 493 +# All the aliases listed for this converter (windows-949-2000) 494 +# are removed from the list of aliases for other Korean converters 495 +# above. 496 windows-949-2000 { UTR22* } 497 windows-949 { JAVA* WINDOWS* } 498 - KS_C_5601-1987 { WINDOWS } 499 - KS_C_5601-1989 { WINDOWS } 500 - KSC_5601 { MIME* WINDOWS } # Needed by iso-2022 501 + EUC-KR { IANA* MIME* WINDOWS } 502 + KS_C_5601-1987 { WINDOWS IANA } 503 + KS_C_5601-1989 { WINDOWS IANA } 504 + KSC_5601 { IANA WINDOWS } # Needed by iso-2022 505 csKSC56011987 { WINDOWS } 506 - korean { WINDOWS } 507 - iso-ir-149 { WINDOWS } 508 - ms949 { JAVA } 509 - x-KSC5601 { JAVA } 510 + korean { IANA WINDOWS } 511 + iso-ir-149 { IANA WINDOWS } 512 + csEUCKR { IANA WINDOWS } 513 514 -windows-1361-2000 { UTR22* } 515 - ksc5601_1992 516 - ms1361 517 - johab 518 - x-Johab { JAVA* } 519 - 520 +#Chrome: TIS-620, ISO-8859-11 and Windows-874 are slightly different from 521 +# each other, but they're used as if they're identical on the web. This is 522 +# also per HTML5. 523 windows-874-2000 { UTR22* } # Thai (w/ euro update) 524 - TIS-620 { WINDOWS } 525 - windows-874 { JAVA* WINDOWS* } 526 + TIS-620 { IANA* WINDOWS MIME* } 527 + windows-874 { JAVA* WINDOWS* MIME } 528 MS874 { JAVA } 529 x-windows-874 { JAVA } 530 - # iso-8859-11 { WINDOWS } # iso-8859-11 is similar to TIS-620. ibm-13162 is a closer match. 531 + iso-8859-11 { IANA WINDOWS MIME } # iso-8859-11 is similar to TIS-620. ibm-13162 is a closer match. 532 533 -ibm-874_P100-1995 { UTR22* } # Thai PC (w/o euro update). 534 - ibm-874 { IBM* JAVA } 535 - ibm-9066 { IBM } # Yes ibm-874 == ibm-9066. ibm-1161 has the euro update. 536 - cp874 { JAVA* } 537 - TIS-620 { IANA* JAVA } # This is actually separate from ibm-874, which is similar to this table 538 - tis620.2533 { JAVA } # This is actually separate from ibm-874, which is similar to this table 539 - eucTH # eucTH is an unusual alias from Solaris. eucTH has fewer mappings than TIS620 540 - x-IBM874 { JAVA } 541 - 542 -ibm-1162_P100-1999 { UTR22* } # Thai (w/ euro update) 543 - ibm-1162 { IBM* } 544 - 545 -windows-864-2000 { UTR22* } 546 - ibm-864s 547 - cp864s 548 - x-IBM864S { JAVA* } 549 - 550 # Platform codepages 551 -# If Java supports the IBM prefix, it should also support the ibm- prefix too. 552 -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 553 -ibm-720_P100-1997 { UTR22* } ibm-720 { IBM* } windows-720 { WINDOWS* } DOS-720 { WINDOWS } x-IBM720 { JAVA* } # PC Arabic 554 -ibm-737_P100-1997 { UTR22* } ibm-737 { IBM* } IBM737 { WINDOWS JAVA } cp737 { JAVA* } windows-737 { WINDOWS* } 737 { JAVA } x-IBM737 { JAVA } # PC Greek 555 -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 556 -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 557 -ibm-851_P100-1995 { UTR22* } ibm-851 { IBM* } IBM851 { IANA* } cp851 { IANA MIME* } 851 { IANA } csPC851 { IANA } # PC DOS Greek (w/o euro) 558 -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) 559 -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) 560 -ibm-856_P100-1995 { UTR22* } ibm-856 { IBM* } IBM856 { JAVA } cp856 { JAVA* } 856 { JAVA } x-IBM856 { JAVA } # PC Hebrew implicit order 561 -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) 562 -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 563 -ibm-860_P100-1995 { UTR22* } ibm-860 { IBM* } IBM860 { IANA* MIME* JAVA } cp860 { IANA MIME JAVA* } 860 { IANA JAVA } csIBM860 { IANA JAVA } # PC Portugal 564 -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 565 -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) 566 -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 567 -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) 568 -ibm-865_P100-1995 { UTR22* } ibm-865 { IBM* } IBM865 { IANA* MIME* JAVA } cp865 { IANA MIME JAVA* } 865 { IANA JAVA } csIBM865 { IANA JAVA } # PC Nordic 569 -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) 570 -ibm-867_P100-1998 { UTR22* } ibm-867 { IBM* } x-IBM867 { JAVA* } # PC Hebrew (w/ euro update) Updated version of ibm-862 571 -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 572 -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) 573 +# Chrome: only keep ibm-878 for KOI8-R, ibm-1168 for KOI8-RU and ibm-866 574 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 575 -ibm-901_P100-1999 { UTR22* } ibm-901 { IBM* } # PC Baltic (w/ euro update), update of ibm-921 576 -ibm-902_P100-1999 { UTR22* } ibm-902 { IBM* } # PC Estonian (w/ euro update), update of ibm-922 577 -ibm-922_P100-1999 { UTR22* } ibm-922 { IBM* } IBM922 { JAVA } cp922 { JAVA* } 922 { JAVA } x-IBM922 { JAVA } # PC Estonian (w/o euro update) 578 +# Chrome: Use the table from the WHATWG encoding standard (HTML5). 579 +ibm-866_html5-2012 { UTR22* } ibm-866 { IBM* } IBM866 { IANA* MIME* JAVA } cp866 { IANA MIME WINDOWS JAVA* } 866 { IANA JAVA } csIBM866 { IANA JAVA } # PC Russian (w/o euro update) 580 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. 581 -ibm-4909_P100-1999 { UTR22* } ibm-4909 { IBM* } # ISO Greek (w/ euro update), update of ibm-813 582 583 # The cp aliases in this section aren't really windows aliases, but it was used by ICU for Windows. 584 # cp is usually used to denote IBM in Java, and that is why we don't do that anymore. 585 @@ -888,53 +644,26 @@ 586 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 587 ibm-5348_P100-1997 { UTR22* } ibm-5348 { IBM* } windows-1252 { IANA* JAVA* WINDOWS* } cp1252 { JAVA } # Windows Latin1 (w/ euro update) 588 ibm-5349_P100-1998 { UTR22* } ibm-5349 { IBM* } windows-1253 { IANA* JAVA* WINDOWS* } cp1253 { JAVA } # Windows Greek (w/ euro update) 589 -ibm-5350_P100-1998 { UTR22* } ibm-5350 { IBM* } windows-1254 { IANA* JAVA* WINDOWS* } cp1254 { JAVA } # Windows Turkish (w/ euro update) 590 + 591 +#CHROME : Make ISO-8859-9 an alias to windows-1254 per HTML5. Move 592 +# other IANA aliases for ISO-8859-9 as well. 593 +ibm-5350_P100-1998 { UTR22* } ibm-5350 { IBM* } windows-1254 { MIME* IANA* JAVA* WINDOWS* } cp1254 { JAVA } # Windows Turkish (w/ euro update) 594 + ISO-8859-9 { MIME } 595 + latin5 { IANA } 596 + csISOLatin5 { IANA } 597 + iso-ir-148 { IANA } 598 + ISO_8859-9:1989 { IANA } 599 + l5 { IANA } 600 + 8859_9 { JAVA } 601 ibm-9447_P100-2002 { UTR22* } ibm-9447 { IBM* } windows-1255 { IANA* JAVA* WINDOWS* } cp1255 { JAVA } # Windows Hebrew (w/ euro update) 602 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) 603 ibm-9449_P100-2002 { UTR22* } ibm-9449 { IBM* } windows-1257 { IANA* JAVA* WINDOWS* } cp1257 { JAVA } # Windows Baltic (w/ euro update) 604 ibm-5354_P100-1998 { UTR22* } ibm-5354 { IBM* } windows-1258 { IANA* JAVA* WINDOWS* } cp1258 { JAVA } # Windows Vietnamese (w/ euro update) 605 606 -# These tables are out of date, and most don't have the Euro 607 -# Leave the windows- variants untagged. They are alternate tables of the newer ones above. 608 -ibm-1250_P100-1995 { UTR22* } ibm-1250 { IBM* } windows-1250 # Old Windows Latin2 (w/o euro update) 609 -ibm-1251_P100-1995 { UTR22* } ibm-1251 { IBM* } windows-1251 # Old Windows Cyrillic (w/o euro update) 610 -ibm-1252_P100-2000 { UTR22* } ibm-1252 { IBM* } windows-1252 # Old Windows Latin 1 without Euro 611 -ibm-1253_P100-1995 { UTR22* } ibm-1253 { IBM* } windows-1253 # Old Windows Greek (w/o euro update) 612 -ibm-1254_P100-1995 { UTR22* } ibm-1254 { IBM* } windows-1254 # Old Windows Turkish (w/o euro update) 613 -ibm-1255_P100-1995 { UTR22* } ibm-1255 { IBM* } # Very old Windows Hebrew (w/o euro update) 614 -ibm-5351_P100-1998 { UTR22* } ibm-5351 { IBM* } windows-1255 # Old Windows Hebrew (w/ euro update) 615 -ibm-1256_P110-1997 { UTR22* } ibm-1256 { IBM* } # Old Windows Arabic (w/o euro update) 616 -ibm-5352_P100-1998 { UTR22* } ibm-5352 { IBM* } windows-1256 # Somewhat old Windows Arabic (w/ euro update) 617 -ibm-1257_P100-1995 { UTR22* } ibm-1257 { IBM* } # Old Windows Baltic (w/o euro update) 618 -ibm-5353_P100-1998 { UTR22* } ibm-5353 { IBM* } windows-1257 # Somewhat old Windows Baltic (w/ euro update) 619 -ibm-1258_P100-1997 { UTR22* } ibm-1258 { IBM* } windows-1258 # Old Windows Vietnamese (w/o euro update) 620 - 621 +# Chrome: Only MacRoman and MacCyrillic are necessary for HTML5. 622 macos-0_2-10.2 { UTR22* } macintosh { IANA* MIME* WINDOWS } mac { IANA } csMacintosh { IANA } windows-10000 { WINDOWS* } macroman { JAVA } x-macroman { JAVA* } # Apple latin 1 623 -macos-6_2-10.4 { UTR22* } x-mac-greek { MIME* WINDOWS } windows-10006 { WINDOWS* } macgr x-MacGreek { JAVA* } # Apple Greek 624 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 625 -macos-21-10.5 { UTR22* } x-mac-thai { MIME* } x-MacThai { JAVA* } MacThai { JAVA } 626 -macos-29-10.2 { UTR22* } x-mac-centraleurroman { MIME* } windows-10029 { WINDOWS* } x-mac-ce { WINDOWS } macce maccentraleurope x-MacCentralEurope { JAVA* } # Apple Central Europe 627 -macos-33-10.5 { UTR22* } x-mac-symbol { MIME* } x-MacSymbol { JAVA* } MacSymbol { JAVA } 628 -macos-34-10.2 { UTR22* } x-mac-dingbat { MIME* } x-MacDingbat { JAVA* } MacDingbat { JAVA } 629 -macos-35-10.2 { UTR22* } x-mac-turkish { MIME* WINDOWS } windows-10081 { WINDOWS* } mactr x-MacTurkish { JAVA* } # Apple Turkish 630 -macos-36_2-10.2 { UTR22* } x-mac-croatian { MIME* } x-MacCroatian { JAVA* } MacCroatian { JAVA } 631 -macos-37_5-10.2 { UTR22* } x-mac-iceland { MIME* } x-MacIceland { JAVA* } MacIceland { JAVA } 632 -macos-38_2-10.2 { UTR22* } x-mac-romania { MIME* } x-MacRomania { JAVA* } MacRomania { JAVA } 633 -macos-518-10.2 { UTR22* } x-mac-arabic { MIME* } x-MacArabic { JAVA* } MacArabic { JAVA } 634 -macos-1285-10.2 { UTR22* } x-mac-hebrew { MIME* } x-MacHebrew { JAVA* } MacHebrew { JAVA } 635 636 -ibm-1051_P100-1995 { UTR22* } ibm-1051 { IBM* } hp-roman8 { IANA* } roman8 { IANA } r8 { IANA } csHPRoman8 { IANA } x-roman8 { JAVA* } # HP Latin1 637 -ibm-1276_P100-1995 { UTR22* } ibm-1276 { IBM* } Adobe-Standard-Encoding { IANA* } csAdobeStandardEncoding { IANA } # Different from ISO-Unicode-IBM-1276 (GCSGID: 1276) 638 - 639 -ibm-1006_P100-1995 { UTR22* } ibm-1006 { IBM* } IBM1006 { JAVA } cp1006 { JAVA* } 1006 { JAVA } x-IBM1006 { JAVA } # Urdu 640 -ibm-1098_P100-1995 { UTR22* } ibm-1098 { IBM* } IBM1098 { JAVA } cp1098 { JAVA* } 1098 { JAVA } x-IBM1098 { JAVA } # PC Farsi 641 -ibm-1124_P100-1996 { UTR22* } ibm-1124 { IBM* JAVA } cp1124 { JAVA* } 1124 { JAVA } x-IBM1124 { JAVA } # ISO Cyrillic Ukraine 642 -ibm-1125_P100-1997 { UTR22* } ibm-1125 { IBM* } cp1125 # Cyrillic Ukraine PC 643 -ibm-1129_P100-1997 { UTR22* } ibm-1129 { IBM* } # ISO Vietnamese 644 -ibm-1131_P100-1997 { UTR22* } ibm-1131 { IBM* } cp1131 # Cyrillic Belarus PC 645 -ibm-1133_P100-1997 { UTR22* } ibm-1133 { IBM* } # ISO Lao 646 - 647 - 648 # Partially algorithmic converters 649 650 # [U_ENABLE_GENERIC_ISO_2022] 651 @@ -943,322 +672,25 @@ 652 # Language-specific variants of ISO-2022 continue to be available as listed below. 653 # ISO_2022 ISO-2022 654 655 +# Chrome: The encoding standard only supports ISO-2022-JP and HZ-GB. 656 +# Keep ISO-2022-{KR,CN,CN-Ext} until we're sure what to do about 657 +# replacement encodings. See crbug.com/277037 658 +# TODO(jshin): Remove them when the bug is resolved. 659 ISO_2022,locale=ja,version=0 ISO-2022-JP { IANA* MIME* JAVA* } csISO2022JP { IANA JAVA } x-windows-iso2022jp { JAVA } x-windows-50220 { JAVA } 660 -ISO_2022,locale=ja,version=1 ISO-2022-JP-1 { MIME* } JIS_Encoding { IANA* } csJISEncoding { IANA } ibm-5054 { IBM* } JIS x-windows-50221 { JAVA* } 661 -ISO_2022,locale=ja,version=2 ISO-2022-JP-2 { IANA* MIME* } csISO2022JP2 { IANA } 662 -ISO_2022,locale=ja,version=3 JIS7 663 -ISO_2022,locale=ja,version=4 JIS8 664 ISO_2022,locale=ko,version=0 ISO-2022-KR { IANA* MIME* JAVA* } csISO2022KR { IANA JAVA } # This uses ibm-949 665 -ISO_2022,locale=ko,version=1 ibm-25546 { IBM* } 666 ISO_2022,locale=zh,version=0 ISO-2022-CN { IANA* JAVA* } csISO2022CN { JAVA } x-ISO-2022-CN-GB { JAVA } 667 ISO_2022,locale=zh,version=1 ISO-2022-CN-EXT { IANA* } 668 -ISO_2022,locale=zh,version=2 ISO-2022-CN-CNS x-ISO-2022-CN-CNS { JAVA* } 669 HZ HZ-GB-2312 { IANA* } 670 -x11-compound-text COMPOUND_TEXT x-compound-text { JAVA* } 671 672 -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. 673 -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. 674 -ISCII,version=2 x-iscii-pa { WINDOWS } windows-57011 { WINDOWS* } iscii-gur 675 -ISCII,version=3 x-iscii-gu { WINDOWS } windows-57010 { WINDOWS* } iscii-guj 676 -ISCII,version=4 x-iscii-or { WINDOWS } windows-57007 { WINDOWS* } iscii-ori 677 -ISCII,version=5 x-iscii-ta { WINDOWS } windows-57004 { WINDOWS* } iscii-tml 678 -ISCII,version=6 x-iscii-te { WINDOWS } windows-57005 { WINDOWS* } iscii-tlg 679 -ISCII,version=7 x-iscii-ka { WINDOWS } windows-57008 { WINDOWS* } iscii-knd 680 -ISCII,version=8 x-iscii-ma { WINDOWS } windows-57009 { WINDOWS* } iscii-mlm 681 +# Chrome: HTML5 does not need ISCII. 682 +# Remove all Lotus entries as well. 683 684 -# Lotus specific 685 -LMBCS-1 lmbcs ibm-65025 { IBM* } 686 - 687 -# These Lotus specific converters still work, but they aren't advertised in this alias table. 688 -# These are almost never used outside of Lotus software, 689 -# and they take a lot of time when creating the available converter list. 690 -# Also Lotus doesn't really use them anyway. It was a mistake to create these LMBCS variant converters in ICU. 691 -#LMBCS-2 692 -#LMBCS-3 693 -#LMBCS-4 694 -#LMBCS-5 695 -#LMBCS-6 696 -#LMBCS-8 697 -#LMBCS-11 698 -#LMBCS-16 699 -#LMBCS-17 700 -#LMBCS-18 701 -#LMBCS-19 702 - 703 # EBCDIC codepages according to the CDRA 704 +# Chrome: Removed all EBCDIC code pages. 705 706 -# without Euro 707 -ibm-37_P100-1995 { UTR22* } # EBCDIC US 708 - ibm-37 { IBM* } 709 - IBM037 { IANA* JAVA } 710 - ibm-037 # { JAVA } 711 - ebcdic-cp-us { IANA JAVA } 712 - ebcdic-cp-ca { IANA JAVA } 713 - ebcdic-cp-wt { IANA JAVA } 714 - ebcdic-cp-nl { IANA JAVA } 715 - csIBM037 { IANA JAVA } 716 - cp037 { JAVA* } 717 - 037 { JAVA } 718 - cpibm37 { JAVA } 719 - cp37 720 - 721 -ibm-273_P100-1995 { UTR22* } ibm-273 { IBM* } IBM273 { IANA* JAVA } CP273 { IANA JAVA* } csIBM273 { IANA } ebcdic-de 273 { JAVA } # EBCDIC Germanay, Austria 722 -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 723 -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 724 -ibm-280_P100-1995 { UTR22* } ibm-280 { IBM* } IBM280 { IANA* JAVA } CP280 { IANA JAVA* } ebcdic-cp-it { IANA } csIBM280 { IANA } 280 { JAVA } # EBCDIC Italy 725 -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 726 -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 727 -ibm-290_P100-1995 { UTR22* } ibm-290 { IBM* } IBM290 { IANA* } cp290 { IANA } EBCDIC-JP-kana { IANA } csIBM290 { IANA } # host SBCS (Katakana) 728 -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 729 -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) 730 -ibm-424_P100-1995 { UTR22* } ibm-424 { IBM* } IBM424 { IANA* JAVA } cp424 { IANA JAVA* } ebcdic-cp-he { IANA } csIBM424 { IANA } 424 { JAVA } # EBCDIC Hebrew 731 -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 732 -ibm-803_P100-1999 { UTR22* } ibm-803 { IBM* } cp803 # Old EBCDIC Hebrew 733 -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. 734 -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 2 735 -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 736 -ibm-875_P100-1995 { UTR22* } ibm-875 { IBM* } IBM875 { JAVA } cp875 { JAVA* } 875 { JAVA } x-IBM875 { JAVA } # EBCDIC Greek 737 -ibm-918_P100-1995 { UTR22* } ibm-918 { IBM* } IBM918 { IANA* JAVA } CP918 { IANA JAVA* } ebcdic-cp-ar2 { IANA } csIBM918 { IANA } # EBCDIC Urdu 738 -ibm-930_P120-1999 { UTR22* } # EBCDIC_STATEFUL Katakana-Kanji Host Mixed. 739 - ibm-930 { IBM* } 740 - ibm-5026 { IBM } # Yes this is correct 741 - IBM930 { JAVA } 742 - cp930 { JAVA* } 743 - 930 { JAVA } 744 - x-IBM930 { JAVA } 745 - x-IBM930A { JAVA } 746 -ibm-933_P110-1995 { UTR22* } ibm-933 { IBM* JAVA } cp933 { JAVA* } 933 { JAVA } x-IBM933 { JAVA } # Korea EBCDIC MIXED 747 -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. 748 -ibm-937_P110-1999 { UTR22* } ibm-937 { IBM* JAVA } cp937 { JAVA* } 937 { JAVA } x-IBM937 { JAVA } # Taiwan EBCDIC MIXED 749 -ibm-939_P120-1999 { UTR22* } # EBCDIC_STATEFUL Latin-Kanji Host Mixed. 750 - ibm-939 { IBM* } 751 - ibm-931 { IBM } # Yes this is correct 752 - ibm-5035 { IBM } # Yes this is also correct 753 - IBM939 { JAVA } 754 - cp939 { JAVA* } 755 - 939 { JAVA } 756 - x-IBM939 { JAVA } 757 - x-IBM939A { JAVA } 758 -ibm-1025_P100-1995 { UTR22* } ibm-1025 { IBM* JAVA } cp1025 { JAVA* } 1025 { JAVA } x-IBM1025 { JAVA } # EBCDIC Cyrillic 759 -ibm-1026_P100-1995 { UTR22* } ibm-1026 { IBM* } IBM1026 { IANA* JAVA } CP1026 { IANA JAVA* } csIBM1026 { IANA } 1026 { JAVA } # EBCDIC Turkey 760 -ibm-1047_P100-1995 { UTR22* } ibm-1047 { IBM* } IBM1047 { IANA* JAVA } cp1047 { JAVA* } 1047 { JAVA } # EBCDIC Open systems Latin1 761 -ibm-1097_P100-1995 { UTR22* } ibm-1097 { IBM* JAVA } cp1097 { JAVA* } 1097 { JAVA } x-IBM1097 { JAVA } # EBCDIC Farsi 762 -ibm-1112_P100-1995 { UTR22* } ibm-1112 { IBM* JAVA } cp1112 { JAVA* } 1112 { JAVA } x-IBM1112 { JAVA } # EBCDIC Baltic 763 -ibm-1114_P100-2001 { UTR22* } ibm-1114 { IBM* } x-IBM1114 { JAVA* } 764 -ibm-1115_P100-1995 { UTR22* } ibm-1115 { IBM* } x-IBM1115 { JAVA* } 765 -ibm-1122_P100-1999 { UTR22* } ibm-1122 { IBM* JAVA } cp1122 { JAVA* } 1122 { JAVA } x-IBM1122 { JAVA } # EBCDIC Estonia 766 -ibm-1123_P100-1995 { UTR22* } ibm-1123 { IBM* JAVA } cp1123 { JAVA* } 1123 { JAVA } x-IBM1123 { JAVA } # EBCDIC Cyrillic Ukraine 767 -ibm-1130_P100-1997 { UTR22* } ibm-1130 { IBM* } # EBCDIC Vietnamese 768 -ibm-1132_P100-1998 { UTR22* } ibm-1132 { IBM* } # EBCDIC Lao 769 -ibm-1137_P100-1999 { UTR22* } ibm-1137 { IBM* } # Devanagari EBCDIC (based on Unicode character set) 770 -ibm-4517_P100-2005 { UTR22* } ibm-4517 { IBM* } # EBCDIC Arabic. Update of ibm-421 771 - 772 -# with Euro 773 -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 774 -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 775 -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 776 -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 777 -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 778 -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 779 -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 780 -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 781 -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 782 -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 783 -ibm-1153_P100-1999 { UTR22* } ibm-1153 { IBM* } IBM1153 { JAVA } x-IBM1153 { JAVA* } # EBCDIC latin 2 784 -ibm-1154_P100-1999 { UTR22* } ibm-1154 { IBM* } # EBCDIC Cyrillic Multilingual 785 -ibm-1155_P100-1999 { UTR22* } ibm-1155 { IBM* } # EBCDIC Turkey 786 -ibm-1156_P100-1999 { UTR22* } ibm-1156 { IBM* } # EBCDIC Baltic Multilingual 787 -ibm-1157_P100-1999 { UTR22* } ibm-1157 { IBM* } # EBCDIC Estonia 788 -ibm-1158_P100-1999 { UTR22* } ibm-1158 { IBM* } # EBCDIC Cyrillic Ukraine 789 -ibm-1160_P100-1999 { UTR22* } ibm-1160 { IBM* } # EBCDIC Thailand 790 -ibm-1164_P100-1999 { UTR22* } ibm-1164 { IBM* } # EBCDIC Viet Nam 791 -ibm-1364_P110-2007 { UTR22* } ibm-1364 { IBM* } x-IBM1364 { JAVA* } # Korean Host Mixed 792 -ibm-1370_P100-1999 { UTR22* } ibm-1370 { IBM* } x-IBM1370 { JAVA* } 793 -ibm-1371_P100-1999 { UTR22* } ibm-1371 { IBM* } x-IBM1371 { JAVA* } # Taiwan EBCDIC MIXED (Euro update of ibm-937) 794 -ibm-1388_P103-2001 { UTR22* } ibm-1388 { IBM* } ibm-9580 { IBM } x-IBM1388 { JAVA* } # S-Ch DBCS-Host Data GBK EBCDIC_STATEFUL. Yes ibm-9580 is an alias. 795 -ibm-1390_P110-2003 { UTR22* } ibm-1390 { IBM* } x-IBM1390 { JAVA* } # Japan EBCDIC MIXED (JIS X 0213) 796 -ibm-1399_P110-2003 { UTR22* } ibm-1399 { IBM* } x-IBM1399 { JAVA* } # Host MBCS (Latin-Kanji) (JIS X 0213) 797 -ibm-5123_P100-1999 { UTR22* } ibm-5123 { IBM* } # Host Roman Jis. Euro update of ibm-1027. SBCS portion of ibm-1390. 798 -ibm-8482_P100-1999 { UTR22* } ibm-8482 { IBM* } # host SBCS (Katakana). Euro update of ibm-290. SBCS portion of ibm-1399. 799 -# Yes ibm-20780 is the same as ibm-16684 800 -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). 801 -ibm-4899_P100-1998 { UTR22* } ibm-4899 { IBM* } # Old EBCDIC Hebrew. Update of ibm-803 802 -ibm-4971_P100-1999 { UTR22* } ibm-4971 { IBM* } # EBCDIC Greek. Update of ibm-875 and superceded by ibm-9067 803 -ibm-9067_X100-2005 { UTR22* } ibm-9067 { IBM* } # EBCDIC Greek. Update of ibm-875 and ibm-4971 804 -ibm-12712_P100-1998 { UTR22* } ibm-12712 { IBM* } ebcdic-he # EBCDIC Hebrew (new sheqel, control charaters update). Update of ibm-424 805 -ibm-16804_X110-1999 { UTR22* } ibm-16804 { IBM* } ebcdic-ar # EBCDIC Arabic. Update of ibm-420 806 - 807 -java-Cp1399A-1.6_P { UTR22* } x-IBM1399A { JAVA* } 808 -java-Cp420s-1.6_P { UTR22* } x-IBM420S { JAVA* } 809 -java-Cp1390A-1.6_P { UTR22* } x-IBM1390A { JAVA* } 810 - 811 -# EBCDIC codepages for S/390, with LF and NL codes swapped 812 -# Starting with ICU 2.4, the swapping is done by modifying the 813 -# normal tables at runtime instead of at build time. 814 -# Append UCNV_SWAP_LFNL_OPTION_STRING to the "ibm-CCSID" name to select this. 815 -# 816 -# Example: "ibm-1047,swaplfnl" or "ibm-1047" UCNV_SWAP_LFNL_OPTION_STRING 817 -# 818 -# This avoids the duplication of all EBCDIC SBCS and mixed-SBCS/DBCS 819 -# mapping files. 820 - 821 -# Some examples below for declaring old-style, obsolete aliases with the "-s390" 822 -# suffix to map to the new-style, recommended names with the option added. 823 -# These are listed here for backward compatibility. 824 -# Do not use these; instead use the normal converter name with the option 825 -# added as recommended above. 826 - 827 -# Note: It is not possible to define an alias (non-initial name in a line here) 828 -# that itself contains a converter option like this one for swapping LF<->NL. 829 -# Such names would never be found because ucnv_open() will first parse and strip 830 -# options before looking up a name in this table. 831 -# ucnv_open() then parses the lookup result (the canonical name on the left 832 -# in lines here) as well. 833 - 834 -# This also means that it is not necessary to add anything to convrtrs.txt 835 -# for converter names like "ibm-1026,swaplfnl" to work - 836 -# they are already covered by the normal option parsing together with the 837 -# regular, option-less alias elsewhere in this file. 838 - 839 -ibm-37_P100-1995,swaplfnl ibm-37-s390 # ibm037-s390 also matches ibm-37-s390 840 -ibm-924_P100-1998,swaplfnl ibm-924-s390 IBM924_LF { JAVA* } 841 -ibm-1047_P100-1995,swaplfnl ibm-1047-s390 IBM1047_LF { JAVA* } 842 -ibm-1140_P100-1997,swaplfnl ibm-1140-s390 843 -ibm-1141_P100-1997,swaplfnl ibm-1141-s390 IBM1141_LF { JAVA* } 844 -ibm-1142_P100-1997,swaplfnl ibm-1142-s390 845 -ibm-1143_P100-1997,swaplfnl ibm-1143-s390 846 -ibm-1144_P100-1997,swaplfnl ibm-1144-s390 847 -ibm-1145_P100-1997,swaplfnl ibm-1145-s390 848 -ibm-1146_P100-1997,swaplfnl ibm-1146-s390 849 -ibm-1147_P100-1997,swaplfnl ibm-1147-s390 850 -ibm-1148_P100-1997,swaplfnl ibm-1148-s390 851 -ibm-1149_P100-1997,swaplfnl ibm-1149-s390 852 -ibm-1153_P100-1999,swaplfnl ibm-1153-s390 853 -ibm-12712_P100-1998,swaplfnl ibm-12712-s390 854 -ibm-16804_X110-1999,swaplfnl ibm-16804-s390 855 - 856 -# This is a special version of ibm-1140 that the XML4C (Xerces) parser team 857 -# requested in 2000. 858 -# It maps both EBCDIC LF and NL controls to Unicode LF U+000A. 859 - 860 -ebcdic-xml-us 861 - 862 # These are not installed by default. They are rarely used. 863 # Many of them can be added through the online ICU Data Library Customization tool 864 +# Chrome: Removed all these entries except for ISO-8859-16 required by HTML5. 865 866 -gsm-03.38-2000 { UTR22* } GSM0338 # GSM0338 alias is from Perl 867 -ibm-1004_P100-1995 { UTR22* } ibm-1004 { IBM* } 868 -ibm-1008_P100-1995 { UTR22* } ibm-1008 { IBM* } # cp1008, 8-bit Arabic (w/o euro update) 869 -ibm-1009_P100-1995 { UTR22* } ibm-1009 { IBM* } 870 -ibm-1010_P100-1995 { UTR22* } ibm-1010 { IBM* } NF_Z_62-010 { IANA* } iso-ir-69 { IANA } ISO646-FR { IANA } fr { IANA } csISO69French { IANA } 871 -ibm-1011_P100-1995 { UTR22* } ibm-1011 { IBM* } DIN_66003 { IANA* } iso-ir-21 { IANA } de { IANA } ISO646-DE { IANA } csISO21German { IANA } 872 -ibm-1012_P100-1995 { UTR22* } ibm-1012 { IBM* } IT { IANA* } iso-ir-15 { IANA } ISO646-IT { IANA } csISO15Italian { IANA } 873 -ibm-1013_P100-1995 { UTR22* } ibm-1013 { IBM* } BS_4730 { IANA* } iso-ir-4 { IANA } ISO646-GB { IANA } gb { IANA } uk { IANA } csISO4UnitedKingdom { IANA } 874 -ibm-1014_P100-1995 { UTR22* } ibm-1014 { IBM* } ES2 { IANA* } iso-ir-85 { IANA } ISO646-ES2 { IANA } csISO85Spanish2 { IANA } 875 -ibm-1015_P100-1995 { UTR22* } ibm-1015 { IBM* } PT2 { IANA* } iso-ir-84 { IANA } ISO646-PT2 { IANA } csISO84Portuguese2 { IANA } 876 -ibm-1016_P100-1995 { UTR22* } ibm-1016 { IBM* } NS_4551-1 { IANA* } iso-ir-60 { IANA } ISO646-NO { IANA } no { IANA } csISO60DanishNorwegian { IANA } csISO60Norwegian1 { IANA } 877 -ibm-1017_P100-1995 { UTR22* } ibm-1017 { IBM* } 878 -ibm-1018_P100-1995 { UTR22* } ibm-1018 { IBM* } SEN_850200_B { IANA* } iso-ir-10 { IANA } FI { IANA } ISO646-FI { IANA } ISO646-SE { IANA } se { IANA } csISO10Swedish { IANA } 879 -ibm-1019_P100-1995 { UTR22* } ibm-1019 { IBM* } 880 -ibm-1020_P100-2003 { UTR22* } ibm-1020 { IBM* } CSA_Z243.4-1985-1 { IANA* } iso-ir-121 { IANA } ISO646-CA { IANA } csa7-1 { IANA } ca { IANA } csISO121Canadian1 { IANA } 881 -ibm-1021_P100-2003 { UTR22* } ibm-1021 { IBM* } 882 -ibm-1023_P100-2003 { UTR22* } ibm-1023 { IBM* } ES { IANA* } iso-ir-17 { IANA } ISO646-ES { IANA } csISO17Spanish { IANA } 883 -ibm-1027_P100-1995 { UTR22* } ibm-1027 { IBM* } x-IBM1027 { JAVA* } 884 -ibm-1041_P100-1995 { UTR22* } ibm-1041 { IBM* } x-IBM1041 { JAVA* } 885 -ibm-1043_P100-1995 { UTR22* } ibm-1043 { IBM* } x-IBM1043 { JAVA* } 886 -ibm-1046_X110-1999 { UTR22* } ibm-1046 { IBM* } x-IBM1046 { JAVA* } x-IBM1046S { JAVA } # Arabic 887 -ibm-1088_P100-1995 { UTR22* } ibm-1088 { IBM* } x-IBM1088 { JAVA* } 888 -ibm-1100_P100-2003 { UTR22* } ibm-1100 { IBM* } DEC-MCS { IANA* } dec { IANA } csDECMCS { IANA } 889 -ibm-1101_P100-2003 { UTR22* } ibm-1101 { IBM* } 890 -ibm-1102_P100-2003 { UTR22* } ibm-1102 { IBM* } 891 -ibm-1103_P100-2003 { UTR22* } ibm-1103 { IBM* } 892 -ibm-1104_P100-2003 { UTR22* } ibm-1104 { IBM* } NF_Z_62-010_1973 iso-ir-25 { IANA* } ISO646-FR1 { IANA } csISO25French { IANA } # NF_Z_62-010_(1973) is the real IANA alias, but () aren't invariant characters. 893 -ibm-1105_P100-2003 { UTR22* } ibm-1105 { IBM* } 894 -ibm-1106_P100-2003 { UTR22* } ibm-1106 { IBM* } 895 -ibm-1107_P100-2003 { UTR22* } ibm-1107 { IBM* } DS_2089 { IANA* } ISO646-DK { IANA } dk { IANA } csISO646Danish { IANA } 896 -ibm-1127_P100-2004 { UTR22* } ibm-1127 { IBM* } 897 -ibm-1161_P100-1999 { UTR22* } ibm-1161 { IBM* } # Thai (Euro update of ibm-1129) 898 -ibm-1163_P100-1999 { UTR22* } ibm-1163 { IBM* } # Vietnamese 899 -ibm-1165_P101-2000 { UTR22* } ibm-1165 { IBM* } # Vietnamese (EBCDIC) 900 -ibm-1166_P100-2002 { UTR22* } ibm-1166 { IBM* } # Cyrillic for Kazakhstan 901 -ibm-1167_P100-2002 { UTR22* } ibm-1167 { IBM* } KOI8-RU x-KOI8_RU { JAVA* } 902 -ibm-1174_X100-2007 { UTR22* } ibm-1174 { IBM* } KZ-1048 { IANA* } STRK1048-2002 { IANA } RK1048 { IANA } csKZ1048 { IANA } 903 -ibm-1277_P100-1995 { UTR22* } ibm-1277 { IBM* } # Adobe (Postscript) Latin-1 904 -ibm-13125_P100-1997 { UTR22* } ibm-13125 { IBM* } # S-Ch (DBCS subset of ibm-4933, ibm-1388) 905 -ibm-13140_P101-2000 { UTR22* } ibm-13140 { IBM* } 906 -ibm-13218_P100-1996 { UTR22* } ibm-13218 { IBM* } # Japanese (EBCDIC update of ibm-930) 907 -ibm-1350_P110-1997 { UTR22* } ibm-1350 { IBM* } x-eucJP-Open { JAVA* } eucJP-Open { JAVA } # Japanese (EUC-JP variant) 908 -ibm-1351_P110-1997 { UTR22* } ibm-1351 { IBM* } x-IBM1351 { JAVA* } # Japanese (DBCS subset of ibm-5039) 909 -ibm-1362_P110-1999 { UTR22* } ibm-1362 { IBM* } x-IBM1362 { JAVA* } # Korean (DBCS subset of ibm-1363) 910 -ibm-13676_P102-2001 { UTR22* } ibm-13676 { IBM* } # Simplified Chinese (EBCDIC) 911 -ibm-1380_P100-1995 { UTR22* } ibm-1380 { IBM* } x-IBM1380 { JAVA* } # Simplified Chinese (DBCS subset of ibm-1381) 912 -ibm-1381_P110-1999 { UTR22* } ibm-1381 { IBM* JAVA } cp1381 { JAVA* } 1381 { JAVA } x-IBM1381 { JAVA } # Simplified Chinese PC Data mixed (IBM GB) 913 -ibm-1382_P100-1995 { UTR22* } ibm-1382 { IBM* } x-IBM1382 { JAVA* } # Simplified Chinese (DBCS subset of ibm-1383) 914 -ibm-17221_P100-2001 { UTR22* } ibm-17221 { IBM* } # Simplified Chinese (EBCDIC) 915 -ibm-17248_X110-1999 { UTR22* } ibm-17248 { IBM* } # PC Arabic (w/ euro update) Updated version of ibm-864 916 -ibm-21344_P101-2000 { UTR22* } ibm-21344 { IBM* } # PC Arabic. Updated version of ibm-864 917 -ibm-21427_P100-1999 { UTR22* } ibm-21427 { IBM* } # Traditional Chinese (DBCS subset of ibm-1370) 918 -ibm-256_P100-1995 { UTR22* } ibm-256 { IBM* } # Latin 1 EBCDIC 919 -ibm-259_P100-1995 { UTR22* } ibm-259 { IBM* } IBM-Symbols { IANA* } csIBMSymbols { IANA } 920 -ibm-274_P100-2000 { UTR22* } ibm-274 { IBM* } IBM274 { IANA* } EBCDIC-BE { IANA } CP274 { IANA } csIBM274 { IANA } 921 -ibm-275_P100-1995 { UTR22* } ibm-275 { IBM* } IBM275 { IANA* } EBCDIC-BR { IANA } cp275 { IANA } csIBM275 { IANA } 922 -ibm-286_P100-2003 { UTR22* } ibm-286 { IBM* } EBCDIC-AT-DE-A { IANA* } csEBCDICATDEA { IANA } 923 -ibm-293_P100-1995 { UTR22* } ibm-293 { IBM* } # APL EBCDIC (APL: A Programming Language) 924 -ibm-300_P120-2006 { UTR22* } ibm-300 { IBM* } x-IBM300 { JAVA* } # Japanese (DBCS subset of ibm-930 and ibm-939) 925 -ibm-301_P110-1997 { UTR22* } ibm-301 { IBM* } x-IBM301 { JAVA* } # Japanese (DBCS subset of ibm-943) 926 -ibm-33058_P100-2000 { UTR22* } ibm-33058 { IBM* } # SBCS (Katakana) 927 -ibm-425_P101-2000 { UTR22* } ibm-425 { IBM* } # Arabic (EBCDIC) 928 -ibm-4930_P110-1999 { UTR22* } ibm-4930 { IBM* } # Korean (DBCS subset of ibm-1364) 929 -ibm-4933_P100-2002 { UTR22* } ibm-4933 { IBM* } # S-Ch (DBCS subset of ibm-1388) 930 -ibm-4948_P100-1995 { UTR22* } ibm-4948 { IBM* } 931 -ibm-4951_P100-1995 { UTR22* } ibm-4951 { IBM* } 932 -ibm-4952_P100-1995 { UTR22* } ibm-4952 { IBM* } 933 -ibm-4960_P100-1995 { UTR22* } ibm-4960 { IBM* } 934 -ibm-5039_P11A-1998 { UTR22* } ibm-5039 { IBM* } # Japanese (HP Shift-JIS variant) 935 -ibm-5048_P100-1995 { UTR22* } ibm-5048 { IBM* } # Japanese (DBCS subset of ibm-1350, JIS X208-1990) 936 -ibm-5049_P100-1995 { UTR22* } ibm-5049 { IBM* } # Japanese (DBCS subset of ibm-1350, JIS X212) 937 -ibm-5067_P100-1995 { UTR22* } ibm-5067 { IBM* } # Korean (DBCS subset of ibm-21450) 938 -ibm-5104_X110-1999 { UTR22* } ibm-5104 { IBM* } # cp1008, 8-bit Arabic (w/ euro update) 939 -ibm-5233_P100-2011 { UTR22* } ibm-5233 { IBM* } # Devanagari EBCDIC, including Indian Rupee 940 -ibm-806_P100-1998 { UTR22* } ibm-806 { IBM* } # Hindi (ISCII variant) 941 -ibm-808_P100-1999 { UTR22* } ibm-808 { IBM* } x-IBM808 { JAVA* } # Cyrillic 942 -ibm-833_P100-1995 { UTR22* } ibm-833 { IBM* } x-IBM833 { JAVA* } 943 -ibm-834_P100-1995 { UTR22* } ibm-834 { IBM* } x-IBM834 { JAVA* } # Korean (DBCS subset of ibm-933) 944 -ibm-835_P100-1995 { UTR22* } ibm-835 { IBM* } x-IBM835 { JAVA* } # Traditional Chinese (DBCS subset of ibm-5033) 945 -ibm-836_P100-1995 { UTR22* } ibm-836 { IBM* } x-IBM836 { JAVA* } 946 -ibm-837_P100-2011 { UTR22* } ibm-837 { IBM* } x-IBM837 { JAVA* } # Simplified Chinese (DBCS subset of ibm-5031) 947 -ibm-848_P100-1999 { UTR22* } ibm-848 { IBM* } # Cyrillic (euro update of ibm-1125) 948 -ibm-849_P100-1999 { UTR22* } ibm-849 { IBM* } # Cyrillic Belarus (euro update of ibm-1131) 949 -ibm-859_P100-1999 { UTR22* } ibm-859 { IBM* } x-IBM859 { JAVA* } # PC Latin 9 (w/ euro update) 950 -ibm-8612_P100-1995 { UTR22* } ibm-8612 { IBM* } # Arabic (EBCDIC update of ibm-420) 951 -ibm-872_P100-1999 { UTR22* } ibm-872 { IBM* } # Cyrillic (Euro update of ibm-855) 952 -ibm-880_P100-1995 { UTR22* } ibm-880 { IBM* } IBM880 { IANA* } cp880 { IANA } EBCDIC-Cyrillic { IANA } csIBM880 { IANA } windows-20880 { WINDOWS* } 953 -ibm-896_P100-1995 { UTR22* } ibm-896 { IBM* } # SBCS Katakana 954 -ibm-897_P100-1995 { UTR22* } ibm-897 { IBM* } JIS_X0201 { IANA* } X0201 { IANA } csHalfWidthKatakana { IANA } x-IBM897 { JAVA* } 955 -ibm-9027_P100-1999 { UTR22* } ibm-9027 { IBM* } # DBCS T-Ch Host. Euro update of ibm-835. DBCS portion of ibm-1371. 956 -ibm-9048_P100-1998 { UTR22* } ibm-9048 { IBM* } # Hebrew (Euro and Sequel update of ibm-856) 957 -ibm-905_P100-1995 { UTR22* } ibm-905 { IBM* } IBM905 { IANA* } CP905 { IANA } ebcdic-cp-tr { IANA } csIBM905 { IANA } windows-20905 { WINDOWS* } 958 -ibm-9056_P100-1995 { UTR22* } ibm-9056 { IBM* } # Arabic 959 -ibm-9061_P100-1999 { UTR22* } ibm-9061 { IBM* } # Greek (w/ euro update) 960 -ibm-9145_P110-1997 { UTR22* } ibm-9145 { IBM* } # Japanese (DBCS subset of ibm-5050) 961 -ibm-9238_X110-1999 { UTR22* } ibm-9238 { IBM* } # cp1046, PC Arabic Extended (w/ euro update) 962 -ibm-924_P100-1998 { UTR22* } ibm-924 { IBM* } IBM00924 { IANA* } CCSID00924 { IANA } CP00924 { IANA } ebcdic-Latin9--euro { IANA } 963 -ibm-926_P100-2000 { UTR22* } ibm-926 { IBM* } # Korean (DBCS subset of ibm-944) 964 -ibm-927_P100-1995 { UTR22* } ibm-927 { IBM* } x-IBM927 { JAVA* } # Traditional Chinese (DBCS subset of ibm-948) 965 -ibm-928_P100-1995 { UTR22* } ibm-928 { IBM* } # Simplified Chinese (DBCS subset of ibm-936) 966 -ibm-941_P13A-2001 { UTR22* } ibm-941 { IBM* } # DBCS portion of ibm-943 967 -ibm-944_P100-1995 { UTR22* } ibm-944 { IBM* } # Korean 968 -ibm-946_P100-1995 { UTR22* } ibm-946 { IBM* } # Simplified Chinese 969 -ibm-947_P100-1995 { UTR22* } ibm-947 { IBM* } x-IBM947 { JAVA* } # Traditional Chinese (DBCS subset of ibm-950) 970 -ibm-948_P110-1999 { UTR22* } ibm-948 { IBM* } x-IBM948 { JAVA* } # Traditional Chinese 971 -ibm-951_P100-1995 { UTR22* } ibm-951 { IBM* } x-IBM951 { JAVA* } # Korean (DBCS subset of ibm-949) 972 -ibm-952_P110-1997 { UTR22* } ibm-952 { IBM* } x-JIS0208 # Pure DBCS, Japanese EUC, G1 - JIS X208-1990 973 -ibm-953_P100-2000 { UTR22* } ibm-953 { IBM* } JIS_X0212-1990 { IANA* } # Pure DBCS, Japanese EUC, G3 - JIS X 0212-1990 974 -ibm-955_P110-1997 { UTR22* } ibm-955 { IBM* } # Pure DBCS, Japanese EUC, G0 - JIS X208-1978 975 -ibm-9577_P100-2001 { UTR22* } ibm-9577 { IBM* } ibm-1385 { IBM } x-IBM1385 { JAVA* } # ibm-9577 and ibm-1385 are identical DBCS tables. 976 iso-8859_16-2001 { UTR22* } ISO-8859-16 { IANA* } iso-ir-226 { IANA } ISO_8859-16:2001 { IANA } latin10 { IANA } l10 { IANA } 977 978 -# To be considered for listing at a later date for the data library customization tool 979 -#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. 980 -#ibm-960_P100-2000 { UTR22* } ibm-960 { IBM* } # Pure DBCS, CNS11643 plane 1 981 -#ibm-963_P100-1995 { UTR22* } ibm-963 { IBM* } # Pure DBCS, CNS11643 plane 2 Traditional Chinese (DBCS subset of ibm-965) 982
