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
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
|
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE translit SYSTEM "translit.dtd">
<!--
Transliteration definitions for ISO/R 9:1954
Copyright (C) 2015 Dusan Vuckovic <dusan@dvuckovic.com>
See http://en.wikipedia.org/wiki/ISO_9 for an introduction.
-->
<translit>
<!-- meta information -->
<name>ISO/R 9</name>
<desc>ISO/R 9:1954, Cyrillic to Latin</desc>
<reverse>true</reverse>
<!-- set of transliteration rules -->
<!-- Hexnotation of Unicode codepoints, letter names according
to Unicode Standard 5.0
Abbreviations:
CCL = CYRILLIC CAPITAL LETTER
CSL = CYRILLIC SMALL LETTER
LCL = LATIN CAPITAL LETTER
LSL = LATIN SMALL LETTER
-->
<rules>
<rule>
<from>А</from> <!-- CCL A -->
<to>A</to> <!-- LCL A -->
</rule>
<rule>
<from>а</from> <!-- CSL A -->
<to>a</to> <!-- LSL A -->
</rule>
<rule>
<from>Б</from> <!-- CCL BE -->
<to>B</to> <!-- LCL B -->
</rule>
<rule>
<from>б</from> <!--CSL BE -->
<to>b</to> <!--LSL B -->
</rule>
<rule>
<from>В</from> <!--CCL VE -->
<to>V</to> <!--LCL V -->
</rule>
<rule>
<from>в</from> <!--CSL VE -->
<to>v</to> <!--LSL V -->
</rule>
<rule>
<from>Г</from> <!--CCL GHE -->
<to>G</to> <!--LCL G -->
</rule>
<rule>
<from>г</from> <!--CSL GHE -->
<to>g</to> <!--LSL G -->
</rule>
<rule>
<from>Ґ</from> <!--CCL GHE WITH UPTURN -->
<to>G̀</to> <!--LCL G WITH COMBINING GRAVE ACCENT-->
</rule>
<rule>
<from>ґ</from> <!--CSL GHE WITH UPTURN -->
<to>g̀</to> <!--LCL G WITH COMBINING GRAVE ACCENT-->
</rule>
<rule>
<from>Д</from> <!-- CCL DE -->
<to>D</to> <!-- LCL D -->
</rule>
<rule>
<from>д</from> <!-- CSL DE -->
<to>d</to> <!-- LSL D -->
</rule>
<rule>
<from>Ѓ</from> <!-- CCL GJE -->
<to>Ǵ</to> <!-- LCL G WITH ACUTE -->
</rule>
<rule>
<from>ѓ</from> <!-- CSL GJE -->
<to>ǵ</to> <!-- LSL G WITH ACUTE -->
</rule>
<rule>
<from>Ђ</from> <!-- CCL DJE -->
<to>Đ</to> <!-- LCL D WITH STROKE -->
</rule>
<rule>
<from>ђ</from> <!-- CSL DJE -->
<to>đ</to> <!-- LSL D WITH STROKE -->
</rule>
<rule>
<from>Е</from> <!-- CCL YE -->
<to>E</to> <!-- LCL E -->
</rule>
<rule>
<from>е</from> <!-- CSL YE -->
<to>e</to> <!-- LSL E -->
</rule>
<rule>
<from>Ё</from> <!-- CCL YO -->
<to>Ë</to> <!-- LCL E WITH DIAERESIS -->
</rule>
<rule>
<from>ё</from> <!-- CSL YO -->
<to>ë</to> <!-- LSL E WITH DIAERESIS -->
</rule>
<rule>
<from>Є</from> <!-- CCL UKRAINIAN YE -->
<to>Je</to> <!-- LCL J WITH LSL E -->
</rule>
<rule>
<from>є</from> <!-- CSL UKRAINIAN YE -->
<to>je</to> <!-- LSL J WITH LSL E -->
</rule>
<rule>
<from>Ж</from> <!-- CCL ZHE -->
<to>Ž</to> <!-- LCL Z WITH CARON -->
</rule>
<rule>
<from>ж</from> <!-- CSL ZHE -->
<to>ž</to> <!-- LSL Z WITH CARON -->
</rule>
<rule>
<from>З</from> <!-- CCL ZE -->
<to>Z</to> <!-- LCL Z -->
</rule>
<rule>
<from>з</from> <!-- CSL ZE -->
<to>z</to> <!-- LSL Z -->
</rule>
<rule>
<from>Ѕ</from> <!-- CCL DZE -->
<to>Dz</to> <!-- LCL D WITH LSL Z -->
</rule>
<rule>
<from>ѕ</from> <!-- CSL DZE -->
<to>dz</to> <!-- LSL D WITH LSL Z -->
</rule>
<rule>
<from>И</from> <!-- CCL I -->
<to>I</to> <!-- LCL I -->
</rule>
<rule>
<from>и</from> <!-- CSL I -->
<to>i</to> <!-- LSL I -->
</rule>
<rule>
<from>І</from> <!-- CCL DOTTED I -->
<to>I</to> <!-- LCL I -->
</rule>
<rule>
<from>і</from> <!-- CSL DOTTED I -->
<to>i</to> <!-- LSL I -->
</rule>
<rule>
<from>Ї</from> <!-- CCL YI -->
<to>Ji</to> <!-- LCL J WITH LSL I -->
</rule>
<rule>
<from>ї</from> <!-- CSL YI -->
<to>ji</to> <!-- LSL J WITH LSL I -->
</rule>
<rule>
<from>Й</from> <!-- CCL SHORT I -->
<to>J</to> <!-- LCL J -->
</rule>
<rule>
<from>й</from> <!-- CSL SHORT I -->
<to>j</to> <!-- LSL J -->
</rule>
<rule>
<from>Ј</from> <!-- CCL JE -->
<to>J</to> <!-- LCL J -->
</rule>
<rule>
<from>ј</from> <!-- CSL JE -->
<to>j</to> <!-- LSL J -->
</rule>
<rule>
<from>К</from> <!-- CCL KA -->
<to>K</to> <!-- LCL K -->
</rule>
<rule>
<from>к</from> <!-- CSL KA -->
<to>k</to> <!-- LSL K -->
</rule>
<rule>
<from>Л</from> <!-- CCL EL -->
<to>L</to> <!-- LCL L -->
</rule>
<rule>
<from>л</from> <!-- CSL EL -->
<to>l</to> <!-- LSL L -->
</rule>
<rule>
<from>Љ</from> <!-- CCL LJE -->
<to>LJ</to> <!-- LCL L WITH LSL J -->
<!--
The capital hard sign is very seldom in use.
It may be capital, if everything is written in upper
case - therefore this context may help to identify the
upper case when transliteration is used reverse.
-->
<context>
<after>\p{IsUpper}</after>
</context>
</rule>
<rule>
<from>Љ</from> <!-- CCL LJE -->
<to>Lj</to> <!-- LCL L WITH LSL J -->
</rule>
<rule>
<from>љ</from> <!-- CSL LJE -->
<to>lj</to> <!-- LSL L WITH LSL J -->
</rule>
<rule>
<from>М</from> <!-- CCL EM -->
<to>M</to> <!-- LCL M -->
</rule>
<rule>
<from>м</from> <!-- CSL EM -->
<to>m</to> <!-- LSL M -->
</rule>
<rule>
<from>Н</from> <!-- CCL EN -->
<to>N</to> <!-- LCL N -->
</rule>
<rule>
<from>н</from> <!-- CSL EN -->
<to>n</to> <!-- LSL N -->
</rule>
<rule>
<from>Њ</from> <!-- CCL NJE -->
<to>NJ</to> <!-- LCL N WITH LCL J -->
<!--
The capital hard sign is very seldom in use.
It may be capital, if everything is written in upper
case - therefore this context may help to identify the
upper case when transliteration is used reverse.
-->
<context>
<after>\p{IsUpper}</after>
</context>
</rule>
<rule>
<from>Њ</from> <!-- CCL NJE -->
<to>Nj</to> <!-- LCL N WITH LSL J -->
</rule>
<rule>
<from>њ</from> <!-- CSL NJE -->
<to>nj</to> <!-- LSL N WITH LSL J -->
</rule>
<rule>
<from>О</from> <!-- CCL O -->
<to>O</to> <!-- LCL O -->
</rule>
<rule>
<from>о</from> <!-- CSL O -->
<to>o</to> <!-- LSL O -->
</rule>
<rule>
<from>П</from> <!-- CCL PE -->
<to>P</to> <!-- LCL P -->
</rule>
<rule>
<from>п</from> <!-- CSL PE -->
<to>p</to> <!-- LSL P -->
</rule>
<rule>
<from>Р</from> <!-- CCL ER -->
<to>R</to> <!-- LCL R -->
</rule>
<rule>
<from>р</from> <!-- CSL ER -->
<to>r</to> <!-- LCL R -->
</rule>
<rule>
<from>С</from> <!-- CCL ES -->
<to>S</to> <!-- LCL S -->
</rule>
<rule>
<from>с</from> <!-- CSL ES -->
<to>s</to> <!-- LSL S -->
</rule>
<rule>
<from>Т</from> <!-- CCL TE -->
<to>T</to> <!-- LCL T -->
</rule>
<rule>
<from>т</from> <!-- CSL TE -->
<to>t</to> <!-- LSL T -->
</rule>
<rule>
<from>Ќ</from> <!-- CCL KJE -->
<to>Ḱ</to> <!-- LCL K WITH ACUTE -->
</rule>
<rule>
<from>ќ</from> <!-- CSL KJE -->
<to>ḱ</to> <!-- LSL K WITH ACUTE -->
</rule>
<rule>
<from>Ћ</from> <!-- CCL TSHE -->
<to>Ć</to> <!-- LCL C WITH ACUTE -->
</rule>
<rule>
<from>ћ</from> <!-- CSL TSHE -->
<to>ć</to> <!-- LSL C WITH ACUTE -->
</rule>
<rule>
<from>У</from> <!-- CCL U -->
<to>U</to> <!-- LCL U -->
</rule>
<rule>
<from>у</from> <!-- CSL U -->
<to>u</to> <!-- LSL U -->
</rule>
<rule>
<from>Ў</from> <!-- CCL SHORT U -->
<to>Ŭ</to> <!-- LCL U WITH BREVE -->
</rule>
<rule>
<from>ў</from> <!-- CSL SHORT U -->
<to>ŭ</to> <!-- LCL U WITH BREVE -->
</rule>
<rule>
<from>Ф</from> <!-- CCL EF -->
<to>F</to> <!-- LCL F -->
</rule>
<rule>
<from>ф</from> <!-- CSL EF -->
<to>f</to> <!-- LSL F -->
</rule>
<rule>
<from>Х</from> <!-- CCL HA -->
<to>H</to> <!-- LCL H -->
</rule>
<rule>
<from>х</from> <!-- CSL HA -->
<to>h</to> <!-- LSL H -->
</rule>
<rule>
<from>Ц</from> <!-- CCL TSE -->
<to>C</to> <!-- LCL C -->
</rule>
<rule>
<from>ц</from> <!-- CSL TSE -->
<to>c</to> <!-- LSL C -->
</rule>
<rule>
<from>Ч</from> <!-- CCL CHE -->
<to>Č</to> <!-- LCL C WITH CARON -->
</rule>
<rule>
<from>ч</from> <!-- CSL CHE -->
<to>č</to> <!-- LSL C WITH CARON -->
</rule>
<rule>
<from>Џ</from> <!-- CCL DZHE -->
<to>DŽ</to> <!-- LCL D WITH LCL Z WITH CARON -->
<!--
The capital Dzhe sign is very seldom in use.
It may be capital, if everything is written in upper
case - therefore this context may help to identify the
upper case when transliteration is used reverse.
-->
<context>
<after>\p{IsUpper}</after>
</context>
</rule>
<rule>
<from>Џ</from> <!-- CCL DZHE -->
<to>Dž</to> <!-- LCL D WITH LSL Z WITH CARON -->
</rule>
<rule>
<from>џ</from> <!-- CSL DZHE -->
<to>dž</to> <!-- LSL D WITH LSL Z WITH CARON -->
</rule>
<rule>
<from>Ш</from> <!-- CCL SHA -->
<to>Š</to> <!-- LCL S WITH CARON -->
</rule>
<rule>
<from>ш</from> <!-- CSL SHA -->
<to>š</to> <!-- LSL S WITH CARON -->
</rule>
<rule>
<from>Щ</from> <!-- CCL SHCHA -->
<to>ŠČ</to> <!-- LCL S WITH CARON WITH LSL C WITH CARON -->
</rule>
<rule>
<from>щ</from> <!-- CSL SHCHA -->
<to>šč</to> <!-- LSL S WITH CARON WITH LSL C WITH CARON -->
</rule>
<rule>
<from>Ъ</from> <!-- CCL HARD SIGN -->
<to>Y</to> <!-- MODIFIER LETTER DOUBLE PRIME -->
<!--
The capital hard sign is very seldom in use.
It may be capital, if everything is written in upper
case - therefore this context may help to identify the
upper case when transliteration is used reverse.
-->
<context>
<after>\p{IsUpper}</after>
</context>
</rule>
<rule>
<from>ъ</from> <!-- CSL HARD SIGN -->
<to>y</to> <!-- MODIFIER LETTER DOUBLE PRIME -->
</rule>
<rule>
<from>Ы</from> <!-- CCL YERU -->
<to>Y</to> <!-- LCL Y -->
</rule>
<rule>
<from>ы</from> <!-- CSL YERU -->
<to>y</to> <!-- LSL Y -->
</rule>
<rule>
<from>Ь</from> <!-- CCL SOFT SIGN -->
<to>ʹ</to> <!-- MODIFIER LETTER PRIME -->
<!--
The capital Soft sign is very seldom in use.
It may be capital, if everything is written in upper
case - therefore this context may help to identify the
upper case when transliteration is used reverse.
-->
<context>
<after>\p{IsUpper}</after>
</context>
</rule>
<rule>
<from>ь</from> <!-- CSL SOFT SIGN -->
<to>ʹ</to> <!-- MODIFIER LETTER PRIME -->
</rule>
<rule>
<from>Ѣ</from> <!-- CCL YAT -->
<to>Ě</to> <!-- LCL E WITH CARON -->
</rule>
<rule>
<from>ѣ</from> <!-- CSL YAT -->
<to>ě</to> <!-- LSL E WITH CARON -->
</rule>
<rule>
<from>Э</from> <!-- CCL E -->
<to>È</to> <!-- LCL E WITH GRAVE -->
</rule>
<rule>
<from>э</from> <!-- CSL E -->
<to>è</to> <!-- LSL E WITH GRAVE -->
</rule>
<rule>
<from>Ю</from> <!-- CCL YU -->
<to>JU</to> <!-- LCL J WITH LCL U -->
<!--
The capital Yu sign is very seldom in use.
It may be capital, if everything is written in upper
case - therefore this context may help to identify the
upper case when transliteration is used reverse.
-->
<context>
<after>\p{IsUpper}</after>
</context>
</rule>
<rule>
<from>Ю</from> <!-- CCL YU -->
<to>Ju</to> <!-- LCL J WITH LSL U -->
</rule>
<rule>
<from>ю</from> <!-- CSL YU -->
<to>ju</to> <!-- LSL J WITH LSL U -->
</rule>
<rule>
<from>Я</from> <!-- CCL YA -->
<to>JA</to> <!-- LCL J WITH LCL A -->
<!--
The capital Ya sign is very seldom in use.
It may be capital, if everything is written in upper
case - therefore this context may help to identify the
upper case when transliteration is used reverse.
-->
<context>
<after>\p{IsUpper}</after>
</context>
</rule>
<rule>
<from>Я</from> <!-- CCL YA -->
<to>Ja</to> <!-- LCL J WITH LSL A -->
</rule>
<rule>
<from>я</from> <!-- CSL YA -->
<to>ja</to> <!-- LSL J WITH LSL A -->
</rule>
<rule>
<from>Ѫ</from> <!-- CCL BIG YUS (HISTORICAL) -->
<to>Ȧ</to> <!-- LCL A WITH DOT -->
</rule>
<rule>
<from>ѫ</from> <!-- CSL BIG YUS (HISTORICAL) -->
<to>ȧ</to> <!-- LSL A WITH DOT -->
</rule>
<rule>
<from>Ѳ</from> <!-- CCL FITA (HISTORICAL) -->
<to>Ḟ</to> <!-- LCL F WITH DOT -->
</rule>
<rule>
<from>ѳ</from> <!-- CSL FITA (HISTORICAL) -->
<to>ḟ</to> <!-- LSL F WITH DOT -->
</rule>
<rule>
<from>Ѵ</from> <!-- CCL IZHITSA (HISTORICAL) -->
<to>Ẏ</to> <!-- LCL Y WITH DOT -->
</rule>
<rule>
<from>ѵ</from> <!-- CSL IZHITSA (HISTORICAL) -->
<to>ẏ</to> <!-- LSL Y WITH DOT -->
</rule>
</rules>
</translit>
|
