File: edict_doc.txt

package info (click to toggle)
edict 2006.10.09-1
  • links: PTS
  • area: main
  • in suites: etch, etch-m68k
  • size: 9,452 kB
  • ctags: 13
  • sloc: sh: 111; makefile: 41
file content (541 lines) | stat: -rw-r--r-- 24,000 bytes parent folder | download | duplicates (8)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
                                 E D I C T

                      JAPANESE/ENGLISH DICTIONARY FILE

Copyright (C) 2001 The Electronic Dictionary Research and Development Group,
Monash University.

Contents:

   * INTRODUCTION
   * CURRENT VERSION
   * FORMAT
   * EDICT HISTORY
   * COPYRIGHT ISSUES
   * LEXICOGRAPHICAL DETAILS
   * NEW JMDICT PROJECT
   * USAGE
   * CONTRIBUTIONS
   * ACKNOWLEDGEMENTS
   * APPENDIX A: EDICT LICENCE STATEMENT
   * APPENDIX B. LANGUAGE CODES FROM ISO 639

INTRODUCTION

The EDICT file results from a long-running project to produce a freely
available Japanese/English Dictionary in machine-readable form.

The EDICT file is copyright, and is distributed in accordance with the
Licence Statement, which can found at the WWW site of the Electronic
Dictionary Research and Development Group who are the owners of the
copyright.

CURRENT VERSION

The version date and sequence number is included in the dictionary itself
under the entry "EDICT". (Actually it is under the JIS-ASCII code "????".
This keeps it as the first entry when it is sorted.)

The master copy of EDICT is in the pub/nihongo directory of
ftp.cc.monash.edu.au. There are other copies around, but they may not be as
up-to-date. The easy way to check if the version you have is the latest is
from the size/date.

As of V96-001, the EDICT file no longer contains proper names. These have
been moved to a separate file called "ENAMDICT". From V99-002, the EDICT
file has been generated from an extended dictionary database which includes
additional fields and information. See the later section on the new JMdict
project for details of this.

FORMAT

EDICT's format is that of the original "EDICT" format used by the early PC
Japanese word-processor MOKE (Mark's Own Kanji Editor). It uses EUC-JP
coding for kana and kanji, however this can be converted to JIS
(ISO-2022-JP) or Shift-JIS by any of the several conversion programs around.
It is a text file with one entry per line. The format of entries is:

KANJI [KANA] /English_1/English_2/.../

or

KANA /English_1/.../

(NB: Only the KANJI and KANA are in EUC; all the other characters, including
spaces, must be ASCII.)

The English translations are deliberately brief, as the application of the
dictionary is expected to be primarily on-line look-ups, etc.

The EDICT file is not intended to have its entries in any particular order.
In fact it almost always is in order as a by-product of the update method I
use, however there is no guarantee of this. (The order is almost always JIS
+ alphabetical, starting with the head-word.)

EDICT HISTORY

EDICT has developed as follows:

  a. it began with the basic EDICT distributed with MOKE 2.0. This was
     compiled by MOKE's author, Mark Edwards, with assistance from Spencer
     Green. Mark kindly released this material to the EDICT project. A
     number of corrections were made to the MOKE original, e.g. spelling
     mistakes, minor mistranslations, etc. It also had a lot of
     duplications, which have been removed. It contained about 1900 unique
     entries. Mark Edwards has also kindly given permission for the
     vocabulary files developed for KG (Kanji Guess) to be added to EDICT.
  b. additions by Jim Breen. I laboriously keyed in a ~2000 entry dictionary
     used in my first year nihongo course at Swinburne Institute of
     Technology years ago (I was given permission by the authors to do
     this). I then worked through other vocabulary lists trying to make sure
     major entries were not omitted. The English-to-kana entries in the SKK
     files were added also. This task is continuing, although it has slowed
     down, and I suspect I will run out of energy eventually. Apart from
     that, I have made a large number of additions during normal reading of
     Japanese text and fj.* news using JREADER and XJDIC. (As of November
     2001 I am still adding entries.)

  c. additions by others. Many people have contributed entries and
     corrections to EDICT. I am forever on the lookout for sources of
     material, provided it is genuinely available for use in the Project. I
     am grateful to Theresa Martin who an early supplier a lot of useful
     material, plus very perceptive corrections. Hidekazu Tozaki has also
     been a great help with tidying up a lot of awry entries, and helping me
     identify obscure kanji compounds. Kurt Stueber has been an assiduous
     keyer of many useful entries. A large group of contributions came from
     Sony, where Rik Smoody had put together a large online dictionary.
     Another batch came from the Japanese-German JDDICT file in similar
     format that Helmut Goldenstein keyed (with permission) from the
     Langenscheidt edited by Hadamitzky. Harold Rowe was great help with
     much of the translation. During 1994, Dr Yo Tomita, then at the
     University of Leeds, conducted a massive proof-reading of the entire
     file, for which I am most grateful. Jeffrey Friedl at Omron in Kyoto
     has also been a most helpful contributor and error-detector. During
     1995, I have been keeping an eye on the "honyaku" mailing list, wherein
     Japanese-English translators discuss thorny issues. From this I have
     derived many new entries, and many updates to existing entries. To the
     many honyakujin, my thanks.

A reasonably full list of contributors is at the back of this file, although
I am sure to have missed a few.

At this stage EDICT has many more entries than many good commercial
dictionaries, which typically have 20,000+ non-name entries with examples,
etc. It is certainly bigger than some of the smaller printed dictionaries,
and when used in conjunction with a search-and-display program like JDIC or
XJDIC it provides a highly effective on-line dictionary service.

COPYRIGHT ISSUES

Dictionary copyright is a difficult point, because clearly the first
lexicographer who published "inu means dog" could not claim a copyright
violation over all subsequent Japanese dictionaries. While it is usual to
consult other dictionaries for "accurate lexicographic information", as
Nelson put it, wholesale copying is, of course, not permissible. What makes
each dictionary unique (and copyrightable) is the particular selection of
words, the phrasing of the meanings, the presentation of the contents (a
very important point in the case of EDICT), and the means of publication. Of
course, the fact that for the most part the kanji and kana of each entry are
coming from public sources, and the structure and layout of the entries
themselves are quite unlike those in any published dictionary, adds a degree
of protection to EDICT.

The advice I have received from people who know about these things is that
EDICT is just as much a new dictionary as any others on the market. Readers
may see an entry which looks familiar, and say "Aha! That comes from the XYZ
Jiten!". They may be right, and they may be wrong. After all there aren't
too many translations of neko. Let me make one thing quite clear, despite
considerable temptation (Electronic Books can be easily decoded), NONE of
this dictionary came from commercial machine-readable dictionaries. I have a
case of RSI in my right elbow to prove it.

Please do not contribute entries to EDICT which have come directly from
copyrightable sources. It is hard to check these, and you may be
jeopardizing EDICT's status.

LEXICOGRAPHICAL DETAILS

Introduction

EDICT is actually a Japanese->English dictionary, although the words within
it can be selected in either language using appropriate software. (JDIC uses
it to provide both E->J and J->E functionality.)

The early stages of EDICT had size limitations due to its usage (MOKE scans
it sequentially and JDXGEN, which is JDIC's index generator, held it in
RAM.) This meant that examples of usage could not be included, and inclusion
of phrases was very limited. JDIC/JDXGEN can now handle a much larger
dictionary, but the compact format has continued.

No inflections of verbs or adjectives have been included, except in
idiomatic expressions. Similarly particles are handled as separate entries.
Adverbs formed from adjectives (-ku or ni) are generally not included. Verbs
are, of course, in the plain or "dictionary" form.

Priority Entries

Starting with the 2001 editions, approximately 20,000 entries comprising the
most commonly-used words in Japanese are marked with a "(P)" at the end of
the entry. This list has been identified by examining several small
dictionaries, and lists of common gairaigo from Japanese newspapers.

Parts of Speech

In working on EDICT, bearing in mind I want to use it in MOKE and with JDIC,
I had to come up with a solution to the problem of adjectival nouns
[keiyoudoushi] (e.g. kirei and kantan), nouns which can be used adjectivally
with the particle "no" and verbs formed by adding suru (e.g. benkyousuru).
If I put entries in EDICT with the "na" and "suru" included, MOKE would not
find a match when they are omitted or, the case of suru, inflected. What I
decided to do is to put the basic noun into the dictionary and add "(vs)"
where it can be used to form a verb with suru, "(a-no)" for common "no"
usage, and "(an)" if it is an adjectival noun. Entries appeared as:

KANJI [benkyou] /study (vs)/
KANJI [kantan] /simple (an)/

In early 2001, as part of the JMdict project (see below), I completely
revised this system, instead introducing a comprehensive system of Part of
Speech (POS) tags. In the EDICT version of the file these tags appear in
parentheses at the start of the entry, separated into general tags and POS
tags.

The (hopefully) full list of such markers is:

abbr       abbreviation
adj        adjective (keiyoushi)
adv        adverb (fukushi)
adj-na    adjectival nouns or quasi-adjectives (keiyodoshi)
adj-no    nouns which may take the genitive case particle "no"
adj-pn     pre-noun adjectival (rentaishi)
adj-s      special adjective (e.g. ookii)
adj-t      "taru" adjective
arch       archaism
aux        auxiliary word or phrase
aux-v      auxiliary verb
conj       conjunction
col        colloquialism
exp        Expressions (phrases, clauses, etc.)
ek         exclusively kanji, rarely just in kana
fam        familiar language
fem        female term or language
gikun      gikun (meaning) reading
gram       grammatical term
hon        honorific or respectful (sonkeigo) language
hum        humble (kenjougo) language
id         idiomatic expression
int        interjection (kandoushi)
iK         word containing irregular kanji usage
ik         word containing irregular kana usage
io         irregular okurigana usage
MA         martial arts term
male       male term or language
m-sl       manga slang
n          noun (common) (futsuumeishi)
n-adv      adverbial noun (fukushitekimeishi)
n-t        noun (temporal) (jisoumeishi)
n-suf     noun, used as a suffix
neg        negative (in a negative sentence, or with negative verb)
neg-v      negative verb (when used with)
obs        obsolete term
obsc       obscure term
oK         word containing out-dated kanji
ok         out-dated or obsolete kana usage
pol        polite (teineigo) language
pref       prefix
qv         quod vide (see another entry)
sl         slang
suf        suffix
uK         word usually written using kanji alone
uk         word usually written using kana alone
v1         Ichidan verb
v5         Godan verb (not completely classified)
v5u        Godan verb with `u' ending
v5k        Godan verb with `ku' ending
v5g        Godan verb with `gu' ending
v5s        Godan verb with `su' ending
v5t        Godan verb with `tsu' ending
v5n        Godan verb with `nu' ending
v5b        Godan verb with `bu' ending
v5m        Godan verb with `mu' ending
v5r        Godan verb with `ru' ending
v5k-s      Godan verb - Iku/Yuku special class
v5z        Godan verb - -zuru special class (alternative form of -jiru verbs)
v5aru      Godan verb - -aru special class
v5uru      Godan verb - Uru old class verb (old form of Eru)
vi         intransitive verb
vs         noun or participle which takes the aux. verb suru
vs-s       suru verb - special class
vk         Kuru verb - special class
vt         transitive verb
vulg       vulgar expression or word
X          rude or X-rated term (not displayed in educational software)

Multiple Senses

From the 2001 editions of EDICT, the differing senses associated with the
Japanese head-words are being progessively marked. The marking takes the
form of a "(1)", "(2)", etc. in front of the senses.

Spellings

I have endeavoured to cater for many possible variants of English
translation and spelling. Where appropriate different translations are
included for national variants (e.g. autumn/fall). I use Oxford (British)
standard spelling (-our, -ize) for the entries I make, but I leave other
entries in the national spelling of the submitter.

At some stage in the future I intend to regularize the English spellings in
such a way that allows searches on either British or American spellings to
be successful.

Gairaigo and Regional Words

For gairaigo which have not been derived from English words, I have
attempted to indicate the source language and the word in that language.
Languages have been coded in the two-letter codes from the ISO 639:1988
"Code for the representation of names of languages" standard, e.g. "(fr:
avec)". See Appendix C for more on this. (Thanks to Holger Gruber for
suggesting this language coding.)

In addition to the language codes described in Appendix C, a number of tags
are used to indicate that a word or phrase is associated with a particular
regional language variant within Japan. The tags are:

kyb     Kyoto-ben
osb     Osaka-ben
ksb     Kansai-ben
ktb     Kantou-ben
tsb     Tosa-ben

In the case of gairaigo which have a meaning which is not apparent from the
original (English) words, the literal transcription is included, with the
tag (lit).

NEW JMDICT PROJECT

Early in 1999 work began on the JMdict project, which aims to extend the
structure and content of the EDICT file to enable it to contain additional
information and provided an improved service to users.

The project has several broad goals:

  a. to convert the EDICT file to a new dictionary structure which overcomes
     the deficiencies in the current structure. With regard to this goal,
     the particular structural and content aspects to be addressed include,
     but are not limited to:
       i. the handling of orthographical variation (e.g. in kanji usage,
          okurigana usage, readings) within the single entry;
      ii. additional and more appropriately associated tagging of
          grammatical and other information;
     iii. provision for separation of different senses (polysemy) in the
          translations;
      iv. provision for the inclusion of translational equivalents from
          several languages;
       v. provision for inclusion of examples of the usage of words;
      vi. provision for cross-references to related entries.
  b. to publish the dictionary in a standard format which is accessible by a
     wide range of software tools; [It is proposed that this goal be
     addressed by developing the structure so that it can be released as an
     XML document, with an associated XML DTD.
  c. to retain backward compatibility with the original EDICT structure in
     order to enable legacy software systems to use later versions of the
     EDICT files.

For more information on the JMdict project, please see the documentation
files.

By May 1999 the EDICT file had been converted into the new format. A major
part of this consisted of identifying and combining entries which were
effectively variants of each other.

Since V99-002, the EDICT file has been generated from the new format. This
has meant:

  a. a marginal increase in the number of entries, as there is an increased
     number of variants;
  b. the English fields of the variant entries are now exactly the same, as
     they have generated from the single expanded entry;
  c. the tags such as (vs), (an), etc. now appear before the first word of
     the English fields.

USAGE

EDICT can be used, with acknowledgement, for any free software or server, or
included in file and software distributions at a nominal charge for the
distribution medium. It is also available under non-exclusive licence for
commercial uses. Consult the Licence Statement information at Appendix A.

It is, of course, the main dictionary used by PD and GPL Copyright software
such as JDIC, JREADER, XJDIC, MacJDic, etc. It can be used as the dictionary
within MOKE (it may need to be renamed JTOE.DCT if used with version 2.1 of
MOKE), and it is also used by the NJSTAR and JWP Word Processor packages.

CONTRIBUTIONS

I will be delighted if people send me corrections, suggestions, and
ESPECIALLY additions. Before ripping in with a lot of suggestions, make sure
you have the latest version, as others may have already made the same
comments.

The preferred format for submissions is a JIS, EUC or Shift-JIS file
(uuencoded for safety) containing replacement/new entries. This can be
emailed to me at the address at the end of this file.

Feel free to use the following format:

NEW: KANJI1 [kana1] /new entry #1/

NEW: KANJI2 [kana2] /new entry #2/

old: KANJI3 [kana3] /old entry to be replaced/
new: KANJI3 [kana3] /replacement entry/

DEL: KANJI4 [kana4] /entry to be deleted/

Please provide an annotated reason for any deletions or amendments you send.

I prefer not to get a "diff" or "patch" file as the master EDICT is under
continuous revision, and may have had quite a few changes since you got your
copy.

Users intending to make submissions to EDICT should follow the following
simple rules:

   * all verbs in plain form. The English must begin with "to ....". Add the
     verb type in some prominent place.

   * add (adj-na) or (adj-no) or (vs) as appropriate to nouns. Do not put
     the "na" or "no" particles on the Japanese, or the "suru" auxiliary
     verb. For entries which have (vs), do not enter them as verb
     infinitives (e.g. "to cook"), instead enter them as
     gerunds/participles/whatever (e.g. cooking (vs)).

   * indicate prefixes and suffixes by "(pref)" and "(suf)" in the first
     English entry, not by using "-" in the kanji or kana.

   * do not add definite or indefinite articles (e.g. "a", "an", "the", etc)
     to English nouns unless they are necessary to distinguish the word from
     another usage type or homonym.

   * do not guess the kanji or the reading. If you don't know them, don't
     send it to me. I will check all incoming suggestions, and I get grumpy
     when I find sloppy errors. One of the most persistent problems in
     editing EDICT is finding and eliminating incorrect kanji and kana.

   * do not use the "/", "[" or "]" characters except in their separating
     roles.

   * if you are using a reference in romaji form, make sure you have the
     correct kana for "too/tou" and "zu", where the Hepburn romaji is often
     ambiguous.

   * do not use kana or kanji in the "English" fields. Where it is necessary
     to use a Japanese word, e.g. kanto, use Hepburn romaji.

   * make sure your kana is correct. A persistent problem is the submission
     of words like "honyaku" as ho+nya+ku instead of the correct ho+n+ya+ku.

   * do not include words formed by common Japanese suffixes, such as
     "-teki", unless they cannot be deduced from the root.

ACKNOWLEDGEMENTS

The following people, in roughly chronological order, have played a part in
the development of EDICT. (I stopped adding to this list some years ago, so
it is of historical interest now.)

Mark Edwards, Spencer Green, Alina Skoutarides, Takako Machida, Theresa
Martin, Satoshi Tadokoro, Stephen Chung, Hidekazu Tozaki, Clifford Olling,
David Cooper, Ken Lunde, Joel Schulman, Hiroto Kagotani, Truett Smith, Mike
Rosenlof, Harold Rowe, Al Harkom, Per Hammarlund, Atsushi Fukumoto, John
Crossley, Bob Kerns, Frank O'Carroll, Rik Smoody, Scott Trent, Curtis
Eubanks, Jamie Packer, Hitoshi Doi, Thalawyn Silverwood, Makato Shimojima,
Bart Mathias, Koichi Mori, Steven Sprouse, Jeffrey Friedl, Yazuru Hiraga,
Kurt Stueber, Rafael Santos, Bruce Casner, Masato Toho, Carolyn Norton,
Simon Clippingdale, Shiino Masayoshi, Susumu Miki, Yushi Kaneda, Masahiko
Tachibana, Naoki Shibata, Yuzuru Hiraga, Yasuaki Nakano, Atsu Yagasaki,
Hitoshi Oi, Chizuko Kanazawa, Lars Huttar, Jonathan Hanna, Yoshimasa Tsuji,
Masatsugu Mamimura, Keiichi Nakata, Masako Nomura, Hiroshi Kamabe, Shi-Wen
Peng, Norihiro Okada, Jun-ichi Nakamura, Yoshiyuki Mizuno, Minoru Terada,
Itaru Ichikawa, Toru Matsuda, Katsumi Inoue, John Finlayson, David Luke,
Iain Sinclair, Warwick Hockley, Jamii Corley, Howard Landman, Tom Bryce, Jim
Thomas, Paul Burchard, Kenji Saito, Ken Eto, Niibe Yutaka, Hideyuki Ozaki,
Kouichi Suzuki, Sakaguchi Takeyuki, Haruo Furuhashi, Takashi Hattori,
Yoshiyuki Kondo, Kusakabe Youichi, Nobuo Sakiyama, Kouhei Matsuda, Toru
Sato, Takayuki Ito, Masayuki Tokoshima, Kiyo Inaba, Dan Cohn, Yo Tomita, Ed
Hall, Takashi Imamura, Bernard Greenberg, Michael Raine, Akiko Nagase, Ben
Bullock, Scott Draves, Matthew Haines, Andy Howells, Takayuki Ito, Anders
Brabaek, Michael Chachich, Masaki Muranaka, Paul Randolph, Vesa Karhu, Bruce
Bailey, Gal Shalif, Riichiro Saito, Keith Rogers, Steve Petersen, Bill
Smith, Barry Byrne, Satoshi Kuramoto, Jason Molenda, Travis Stewart,
Yuichiro Kushiro Keiko Okushi, Wayne Lammers, Koichi Fujino, Joerg Fischer,
Satoru Miyazaki, Gaspard Gendreau, David Olson, Peter Evans, Steven
Zaveloff, Larry Tyrrell, Heinz Clemencon, Justin Mayer, David Jones, Holger
Gruber, David Wilson, John De Hoog, Stephen Davis, Dan Crevier, Ron Granich,
Bruce Raup, Scott Childress, Richard Warmington, Jean-Jacques Labarthe, Matt
Bloedel, Szabolcs Varga, Alan Bram, Hidetaka Koie, David Villareale,
Hirokazu Ohata, Toshiki Sasabe, William Maton, Tom Salmon, Kian Yap, Paul
Denisowski, Glen Pankow, Richard Northcott, Roger Meunier, Petteri Kettunen,
Jeff Korpa, Kanji Haitani, Liam O'Brien, Serdar Yegulalp, Jonathan Way,
Gururaj Rao, Yoichiro Niitsu, Ralph Seewald, Andreas Jordell, Chua Hian
Koon, Hartmut Pilch, Shouichi Takeuchi, Ayumu Yasutomi, Mike Wright, James
Rose, Nich Hill.

Jim Breen
(jwb@csse.monash.edu.au)
School of Computer Science & Software Engineering
Monash University
Clayton 3168
AUSTRALIA
  ------------------------------------------------------------------------
APPENDIX A: EDICT LICENCE STATEMENT

In March 2000, James William Breen assigned ownership of the copyright of
the dictionary files assembled, coordinated and edited by him to the The
Electronic Dictionary Research and Development Group at Monash University.

Information about the formal usage arrangement for EDICT can be found on the
Group's WWW page at: http://www.csse.monash.edu.au/groups/edrdg/

In summary, EDICT can be used, with acknowledgement, for any free software
or server, or included in file and software distributions at a nominal
charge for the distribution medium. It is also available under non-exclusive
licence for commercial uses.

  ------------------------------------------------------------------------
APPENDIX B. LANGUAGE CODES FROM ISO 639

The following language codes have been used with non-English derived
gairaigo. They have been derived from the ISO 639:1988 "Code for the
representation of names of languages" standard.

ar      Arabic
zh      Chinese (Zhongwen)
de      German (Deutsch)
en      English
fr      French
el      Greek (Ellinika)
iw      Hebrew (Iwrith)
ja      Japanese
ko      Korean
nl      Dutch (Nederlands)
no      Norwegian
pl      Polish
ru      Russian
sv      Swedish
bo      Tibetan (Bodskad)
eo      Esperanto
es      Spanish
in      Indonesian
it      Italian
lt      Latin
pt      Portugese
hi      Hindi
ur      Urdu
mn      Mongolian
kl      Inuit (formerly Eskimo)

And I have added the following, which are not in the Standard:

ai      Ainu