xref: /illumos-gate/usr/src/lib/iconv_modules/utf-8/alias (revision fed28213d5eafb97b454ced3b52d832ba0155960)
1#
2# CDDL HEADER START
3#
4# The contents of this file are subject to the terms of the
5# Common Development and Distribution License (the "License").
6# You may not use this file except in compliance with the License.
7#
8# You can obtain a copy of the license at src/OPENSOLARIS.LICENSE
9# or http://www.opensolaris.org/os/licensing.
10# See the License for the specific language governing permissions
11# and limitations under the License.
12#
13# When distributing Covered Code, include this CDDL HEADER in each
14# file and include the License file at src/OPENSOLARIS.LICENSE.
15# If applicable, add the following below this CDDL HEADER, with the
16# fields enclosed by brackets "[]" replaced with your own identifying
17# information: Portions Copyright [yyyy] [name of copyright owner]
18#
19# CDDL HEADER END
20#
21# Copyright (c) 2003, 2010, Oracle and/or its affiliates. All rights reserved.
22# Copyright 2025 Oxide Computer Company
23#
24# This file contains a list of iconv aliases that will be applied. These aliases
25# come from various locations over the years. A good reference for these is the
26# IANA character sets assignments and aliases. Additional aliases can be added
27# to support common encodings used in the wild.
28#
29# The logic in libc's iconv implementation checks both for direct matches and
30# case-insensitive matches. Conventionally most items here are capitalized, but
31# it is not strictly required.
32#
33# Alias Canonical
34ISO8859-1 8859-1
35ISO-8859-1 8859-1
36ISO8859_1 8859-1
37ISO_8859_1 8859-1
38iso-ir-100 8859-1
39ISO_8859-1 8859-1
40latin1 8859-1
41l1 8859-1
42IBM819 8859-1
43CP819 8859-1
44csISOLatin1 8859-1
45#
46# While IANA only defines LATIN-9 as a common alias, we also include LATIN9 ala
47# gconv and others due to its similarity to the other LATIN encodings.
48#
49ISO8859-15 8859-15
50ISO-8859-15 8859-15
51ISO8859_15 8859-15
52ISO_8859_15 8859-15
53ISO_8859-15 8859-15
54latin-9 8859-15
55latin9 8859-15
56csISO885915 8859-15
57CP923 8859-15
58IBM923 8859-15
59PCK PCK
60SJIS PCK
61Shift_JIS PCK
62SHIFT-JIS PCK
63ShiftJIS PCK
64MS_Kanji PCK
65csShiftJis PCK
66eucJP eucJP
67EUC-JP eucJP
68EUC_JP eucJP
69csEUCPkdFmtJapanese eucJP
70ISO-2022-JP ISO-2022-JP
71ISO_2022_JP ISO-2022-JP
72ISO2022JP ISO-2022-JP
73ISO-2022JP ISO-2022-JP
74ISO_2022JP ISO-2022-JP
75ISO2022-JP ISO-2022-JP
76ISO2022_JP ISO-2022-JP
77csISO2022JP ISO-2022-JP
78EUC-JP-MS eucJP-ms
79EUCJP-MS eucJP-ms
80EUCJP-OPEN eucJP-ms
81EUCJP-WIN eucJP-ms
82#
83# While IANA has cs aliases for these, we've noticed that other major systems
84# don't provide aliases for those for UTF-8 and as such we've left that out for
85# now.
86#
87UTF-8 UTF-8
88UTF8 UTF-8
89UTF_8 UTF-8
90UTF-16 UTF-16
91UTF16 UTF-16
92UTF_16 UTF-16
93UTF-16BE UTF-16BE
94UTF16BE UTF-16BE
95UTF_16BE UTF-16BE
96UTF-16LE UTF-16LE
97UTF16LE UTF-16LE
98UTF_16LE UTF-16LE
99UTF-32 UTF-32
100UTF32 UTF-32
101UTF_32 UTF-32
102UTF-32BE UTF-32BE
103UTF32BE UTF-32BE
104UTF_32BE UTF-32BE
105UTF-32LE UTF-32LE
106UTF32LE UTF-32LE
107UTF_32LE UTF-32LE
108GB18030 zh_CN.gbk
109GB-18030 zh_CN.gbk
110GB_18030 zh_CN.gbk
111GB2312 zh_CN.euc
112GB-2312 zh_CN.euc
113GB_2312 zh_CN.euc
114csGB2312 zh_CN.euc
115EUC-CN zh_CN.euc
116EUC_CN zh_CN.euc
117eucCN zh_CN.euc
118GBK zh_CN.gbk
119zh_CN.gb18030 zh_CN.gbk
120zh_CN.iso2022-7 zh_CN.iso2022-CN
121EUC-KR EUC-KR
122EUC_KR EUC-KR
123ISO-2022-KR ko_KR-iso2022-7
124ISO_2022_KR ko_KR-iso2022-7
125ISO2022KR ko_KR-iso2022-7
126ISO-2022KR ko_KR-iso2022-7
127ISO_2022KR ko_KR-iso2022-7
128ISO2022-KR ko_KR-iso2022-7
129ISO2022_KR ko_KR-iso2022-7
130Wansung ko_KR-euc
131eucKR ko_KR-euc
132csEUCKR ko_KR-euc
133JOHAB ko_KR.johap92
134JOHAP ko_KR.johap92
1355601 ko_KR-euc
136KSC5601 ko_KR-euc
137csKSC56011987 ko_KR-euc
138ko_KR.euc ko_KR-euc
139ko_KR.johap ko_KR-johap
140ko_KR.johap92 ko_KR-johap92
141ko_KR.iso2022-7 ko_KR-iso2022-7
142ko_KR.nbyte ko_KR-nbyte
143ko_KR.cp933 ko_KR-cp933
144ko_KR.cp949 ko_KR-cp949
145UnifiedHangul ko_KR-cp949
146UHC ko_KR-cp949
147CP949 ko_KR-cp949
148BIG5 zh_TW-big5
149BIG-5 zh_TW-big5
150BIG_5 zh_TW-big5
151EUC-TW zh_TW-euc
152EUC_TW zh_TW-euc
153eucTW zh_TW-euc
154CNS11643 zh_TW-euc
155CNS-11643 zh_TW-euc
156CNS_11643 zh_TW-euc
157BIG5P zh_TW-big5p
158BIG5Plus zh_TW-big5p
159BIG5-Plus zh_TW-big5p
160BIG5_Plus zh_TW-big5p
161BIG-5-Plus zh_TW-big5p
162BIG_5_Plus zh_TW-big5p
163BIG-5Plus zh_TW-big5p
164BIG_5Plus zh_TW-big5p
165zh_TW.iso2022-CN-EXT zh_TW-iso2022-CN-EXT
166zh_TW.big5 zh_TW-big5
167zh_TW.big5p zh_TW-big5p
168zh_TW.euc zh_TW-euc
169zh_TW.iso2022-7 zh_TW-iso2022-7
170zh_TW.iso2022-CN zh_TW-iso2022-7
171zh_TW-iso2022-CN zh_TW-iso2022-7
172zh_TW.cp937 zh_TW-cp937
173Big5HKSCS zh_HK.hkscs
174Big-5HKSCS zh_HK.hkscs
175Big_5HKSCS zh_HK.hkscs
176Big5-HKSCS zh_HK.hkscs
177Big5_HKSCS zh_HK.hkscs
178Big-5-HKSCS zh_HK.hkscs
179Big_5_HKSCS zh_HK.hkscs
180Big5HK zh_HK.hkscs
181Big-5HK zh_HK.hkscs
182Big_5HK zh_HK.hkscs
183Big-5-HK zh_HK.hkscs
184Big_5_HK zh_HK.hkscs
185zh_HK.big5hk zh_HK.hkscs
186zh_HK-big5hk zh_HK.hkscs
187#
188# IBM has a series of pages that map to the various 8859- bits here that
189# sometimes have extensions. We end up aliasing them like others do despite this.
190#
191ISO8859-2 8859-2
192ISO8859_2 8859-2
193ISO-8859-2 8859-2
194ISO_8859_2 8859-2
195iso2 8859-2
196iso-ir-101 8859-2
197latin2 8859-2
198l2 8859-2
199csISOLatin2 8859-2
200CP912 8859-2
201IBM912 8859-2
202ISO8859-5 8859-5
203ISO8859_5 8859-5
204ISO-8859-5 8859-5
205ISO_8859_5 8859-5
206iso5 8859-5
207iso-ir-144 8859-5
208cyrillic 8859-5
209csISOLatinCyrillic 8859-5
210CP915 8859-5
211IBM915 8859-5
212ISO8859-6 8859-6
213ISO8859_6 8859-6
214ISO-8859-6 8859-6
215ISO_8859_6 8859-6
216iso-ir-127 8859-6
217ECMA-114 8859-6
218ASMO-708 8859-6
219arabic 8859-6
220csISOLatinArabic 8859-6
221CP1089 8859-6
222IBM1089 8859-6
223ISO8859-7 8859-7
224ISO8859_7 8859-7
225ISO-8859-7 8859-7
226ISO_8859_7 8859-7
227iso-ir-126 8859-7
228ELOT_928 8859-7
229ECMA-118 8859-7
230greek 8859-7
231greek8 8859-7
232csISOLatinGreek 8859-7
233CP813 8859-7
234IBM813 8859-7
235ISO8859-9 8859-9
236ISO8859_9 8859-9
237ISO-8859-9 8859-9
238ISO_8859_9 8859-9
239so-ir-148 8859-9
240latin5 8859-9
241l5 8859-9
242csISOLatin5 8859-9
243IBM920 8859-9
244CP920 8859-9
245ECMA-128 8859-9
246ISO8859-11 eucTH
247ISO8859_11 eucTH
248ISO-8859-11 eucTH
249ISO_8859_11 eucTH
2508859-11 eucTH
2518859_11 eucTH
252TIS-620 eucTH
253TIS_620 eucTH
254TIS620 eucTH
255TIS620.2533 eucTH
256TIS620:2533 eucTH
257TIS620-2533 eucTH
258TIS620_2533 eucTH
259eucTH eucTH
260EUC-TH eucTH
261EUC_TH eucTH
262ISO8859-13 8859-13
263ISO8859_13 8859-13
264ISO-8859-13 8859-13
265ISO_8859_13 8859-13
266csISO885913 8859-13
267latin7 8859-13
268l7 8859-13
269iso-ir-179 8859-13
270KOI8-R KOI8-R
271KOI8_R KOI8-R
272KOI8R KOI8-R
273KOI8 KOI8-R
274csKOI8R KOI8-R
275ISCII iscii91
276ISCII91 iscii91
277ISO8859-3 8859-3
278ISO8859_3 8859-3
279ISO-8859-3 8859-3
280ISO_8859_3 8859-3
281iso-ir-109 8859-3
282latin3 8859-3
283l3 8859-3
284csISOLatin3 8859-3
285IBM913 8859-3
286CP913 8859-3
287ISO8859-4 8859-4
288ISO8859_4 8859-4
289ISO-8859-4 8859-4
290ISO_8859_4 8859-4
291iso-ir-110 8859-4
292latin4 8859-4
293l4 8859-4
294csISOLatin4 8859-4
295IBM914 8859-4
296CP914 8859-4
297ISO8859-8 8859-8
298ISO8859_8 8859-8
299ISO-8859-8 8859-8
300ISO_8859_8 8859-8
301iso-ir-138 8859-8
302hebrew 8859-8
303csISOLatinHebrew 8859-8
304CP916 8859-8
305IBM916 8859-8
306ISO8859-10 8859-10
307ISO8859_10 8859-10
308ISO-8859-10 8859-10
309ISO_8859_10 8859-10
310iso-ir-157 8859-10
311l6 8859-10
312ISO_8859-10:1992 8859-10
313csISOLatin6 8859-10
314latin6 8859-10
315CP919 8859-10
316IBM919 8859-10
317ISO8859-14 8859-14
318ISO8859_14 8859-14
319ISO-8859-14 8859-14
320ISO_8859_14 8859-14
321iso-ir-199 8859-14
322ISO_8859-14:1998 8859-14
323ISO_8859-14 8859-14
324latin8 8859-14
325iso-celtic 8859-14
326l8 8859-14
327csISO885914 8859-14
328ISO8859-16 8859-16
329ISO8859_16 8859-16
330ISO-8859-16 8859-16
331ISO_8859_16 8859-16
332iso-ir-226 8859-16
333ISO_8859-16:2001 8859-16
334ISO_8859-16 8859-16
335latin10 8859-16
336l10 8859-16
337csISO885916 8859-16
338KOI8-U KOI8-U
339KOI8_U KOI8-U
340KOI8U KOI8-U
341csKOI8U KOI8-U
342UCS-2 UCS-2
343UCS_2 UCS-2
344UCS2 UCS-2
345UCS-2BE UCS-2BE
346UCS_2BE UCS-2BE
347UCS2BE UCS-2BE
348UCS-2LE UCS-2LE
349UCS_2LE UCS-2LE
350UCS2LE UCS-2LE
351UCS-4 UCS-4
352UCS_4 UCS-4
353UCS4 UCS-4
354UCS-4BE UCS-4BE
355UCS_4BE UCS-4BE
356UCS4BE UCS-4BE
357UCS-4LE UCS-4LE
358UCS_4LE UCS-4LE
359UCS4LE UCS-4LE
360UTF-EBCDIC UTF-EBCDIC
361UTF_EBCDIC UTF-EBCDIC
362UTFEBCDIC UTF-EBCDIC
363ASCII 646
364US-ASCII 646
365US_ASCII 646
366USASCII 646
367PTCP154 PTCP154
368ACE ACE
369ACE-ALLOW-UNASSIGNED ACE-ALLOW-UNASSIGNED
370ACE_ALLOW_UNASSIGNED ACE-ALLOW-UNASSIGNED
371ACEALLOWUNASSIGNED ACE-ALLOW-UNASSIGNED
372CP932 ms932
373MS932 ms932
374PC932 ms932
375UTF-8-CP932 UTF-8-ms932
376UTF8-CP932 UTF-8-ms932
377UTF-8CP932 UTF-8-ms932
378UTF_8_CP932 UTF-8-ms932
379UTF8_CP932 UTF-8-ms932
380UTF_8CP932 UTF-8-ms932
381UTF8CP932 UTF-8-ms932
382UTF-8-MS932 UTF-8-ms932
383UTF8-MS932 UTF-8-ms932
384UTF-8MS932 UTF-8-ms932
385UTF_8_MS932 UTF-8-ms932
386UTF8_MS932 UTF-8-ms932
387UTF_8MS932 UTF-8-ms932
388UTF8MS932 UTF-8-ms932
389UTF-8-PC932 UTF-8-ms932
390UTF8-PC932 UTF-8-ms932
391UTF-8PC932 UTF-8-ms932
392UTF_8_PC932 UTF-8-ms932
393UTF8_PC932 UTF-8-ms932
394UTF_8PC932 UTF-8-ms932
395UTF8PC932 UTF-8-ms932
396IBM-930 ibm930
397IBM_930 ibm930
398IBM930 ibm930
399CP930 ibm930
400IBM-931 ibm931
401IBM_931 ibm931
402IBM931 ibm931
403CP931 ibm931
404IBM-939 ibm939
405IBM_939 ibm939
406IBM939 ibm939
407CP939 ibm939
408IBM-5026 ibm5026
409IBM_5026 ibm5026
410IBM5026 ibm5026
411IBM-5035 ibm5035
412IBM_5035 ibm5035
413IBM5035 ibm5035
414IBM-933 ko_KR-cp933
415IBM_933 ko_KR-cp933
416IBM933 ko_KR-cp933
417CP933 ko_KR-cp933
418IBM-937 zh_TW-cp937
419IBM_937 zh_TW-cp937
420IBM937 zh_TW-cp937
421CP937 zh_TW-cp937
422IBM-935 zh_CN-cp935
423IBM_935 zh_CN-cp935
424IBM935 zh_CN-cp935
425IBM-CP838 IBM-838
426IBM-CP874 IBM-874
427CP935 zh_CN-cp935
428CP437 CP437
429CP-437 CP437
430CP_437 CP437
431437 CP437
432IBM437 CP437
433csPC8CodePage437 CP437
434CP737 CP737
435CP-737 CP737
436CP_737 CP737
437737 CP737
438CP775 CP775
439CP-775 CP775
440CP_775 CP775
441775 CP775
442IBM775 CP775
443csPC775Baltic CP775
444CP850 CP850
445CP-850 CP850
446CP_850 CP850
447850 CP850
448IBM-850 IBM-850
449IBM850 IBM-850
450cspc850multilingual IBM-850
451CP852 CP852
452CP-852 CP852
453CP_852 CP852
454852 CP852
455dos2 CP852
456IBM852 CP852
457csPCp852 CP852
458CP855 CP855
459CP-855 CP855
460CP_855 CP855
461855 CP855
462csIBM855 CP855
463CP857 CP857
464CP-857 CP857
465CP_857 CP857
466857 CP857
467IBM857 CP857
468csIBM857 CP857
469CP860 CP860
470CP-860 CP860
471CP_860 CP860
472860 CP860
473csIBM860 CP860
474IBM860 CP860
475CP861 CP861
476CP-861 CP861
477CP_861 CP861
478861 CP861
479cp-is CP861
480IBM861 CP861
481csIBM861 CP861
482CP862 CP862
483CP-862 CP862
484CP_862 CP862
485862 CP862
486IBM862 CP862
487csPC862LatinHebrew CP862
488CP863 CP863
489CP-863 CP863
490CP_863 CP863
491863 CP863
492IBM863 CP863
493csIBM863 CP863
494CP864 CP864
495CP-864 CP864
496CP_864 CP864
497864 CP864
498IBM864 CP864
499csIBM864 CP864
500CP865 CP865
501CP-865 CP865
502CP_865 CP865
503865 CP865
504IBM865 CP865
505csIBM865 CP865
506CP866 CP866
507CP-866 CP866
508CP_866 CP866
509866 CP866
510IBM866 CP866
511csIBM866 CP866
512CP869 CP869
513CP-869 CP869
514CP_869 CP869
515869 CP869
516cp-gr CP869
517csIBM869 CP869
518IBM869 CP869
519CP874 CP874
520CP-874 CP874
521CP_874 CP874
522874 CP874
523IBM874 CP874
524CP1250 CP1250
525CP-1250 CP1250
526CP_1250 CP1250
527WINDOWS-1250 CP1250
528ANSI-1250 CP1250
529ANSI1250 CP1250
5301250 CP1250
531win2 CP1250
532CP1251 CP1251
533CP-1251 CP1251
534CP_1251 CP1251
535WINDOWS-1251 CP1251
536ANSI-1251 CP1251
537ANSI1251 CP1251
5381251 CP1251
539win5 CP1251
540CP1252 CP1252
541CP-1252 CP1252
542CP_1252 CP1252
543WINDOWS-1252 CP1252
544ANSI-1252 CP1252
545ANSI1252 CP1252
5461252 CP1252
547CP1253 CP1253
548CP-1253 CP1253
549CP_1253 CP1253
550WINDOWS-1253 CP1253
551ANSI-1253 CP1253
552ANSI1253 CP1253
5531253 CP1253
554CP1254 CP1254
555CP-1254 CP1254
556CP_1254 CP1254
557WINDOWS-1254 CP1254
558ANSI-1254 CP1254
559ANSI1254 CP1254
5601254 CP1254
561CP1255 CP1255
562CP-1255 CP1255
563CP_1255 CP1255
564WINDOWS-1255 CP1255
565ANSI-1255 CP1255
566ANSI1255 CP1255
5671255 CP1255
568CP1256 CP1256
569CP-1256 CP1256
570CP_1256 CP1256
571WINDOWS-1256 CP1256
572ANSI-1256 CP1256
573ANSI1256 CP1256
5741256 CP1256
575CP1257 CP1257
576CP-1257 CP1257
577CP_1257 CP1257
578WINDOWS-1257 CP1257
579ANSI-1257 CP1257
580ANSI1257 CP1257
5811257 CP1257
582CP1258 CP1258
583CP-1258 CP1258
584CP_1258 CP1258
585WINDOWS-1258 CP1258
586ANSI-1258 CP1258
587ANSI1258 CP1258
5881258 CP1258
589CP720 CP720
590CP-720 CP720
591CP_720 CP720
592720 CP720
593IBM720 CP720
594#
595# We have a group of modules whose canonical name is IBM-<num>. This is in
596# addition to modules whose canonical name are CP<num>. These generally don't
597# overlap except for numbers: 850, 852, 855, 857, 862, 864, 866, and 869. For
598# these entries we don't add aliases as we have an alias for them already. Often
599# in those cases, we have a geniconvtbl UTF-8 binary table for the IBM-<num>,
600# but modules for everything else.
601#
602CP273 IBM-273
603csIBM273 IBM-273
604IBM273 IBM-273
605EBCDIC-CP-DK IBM-277
606EBCDIC-CP-NO IBM-277
607csIBM277 IBM-277
608IBM277 IBM-277
609CP278 IBM-278
610IBM278 IBM-278
611ebcdic-cp-fi IBM-278
612ebcdic-cp-se IBM-278
613csIBM278 IBM-278
614CP280 IBM-280
615IBM280 IBM-280
616ebcdic-cp-it IBM-280
617csIBM280 IBM-280
618IBM284 IBM-284
619CP284 IBM-284
620ebcdic-cp-es IBM-284
621csIBM284 IBM-284
622CP285 IBM-285
623IBM285 IBM-285
624ebcdic-cp-gb IBM-285
625csIBM285 IBM-285
626CP297 IBM-297
627IBM297 IBM-297
628ebcdic-cp-fr IBM-297
629csIBM297 IBM-297
630CP420 IBM-420
631IBM420 IBM-420
632ebcdic-cp-ar1 IBM-420
633csIBM420 IBM-420
634CP424 IBM-424
635IBM424 IBM-424
636ebcdic-cp-he IBM-424
637csIBM424 IBM-424
638CP500 IBM-500
639IBM500 IBM-500
640ebcdic-cp-be IBM-500
641ebcdic-cp-ch IBM-500
642csIBM500 IBM-500
643CP856 IBM-856
644IBM856 IBM-856
645csIBM856 IBM-856
646CP870 IBM-870
647IBM870 IBM-870
648ebcdic-cp-roece IBM-870
649ebcdic-cp-yu IBM-870
650csIBM870 IBM-870
651CP871 IBM-871
652ebcdic-cp-is IBM-871
653csIBM871 IBM-871
654CP875 IBM-875
655IBM875 IBM-875
656IBM921 IBM-921
657CP921 IBM-921
658CP922 IBM-922
659IBM922 IBM-922
660