jlabel 0.1.9

HTS-style full-context label structure and parser/serializer from/to string
Documentation
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
use jlabel::{
    AccentPhraseCurrent, AccentPhrasePrevNext, BreathGroupCurrent, BreathGroupPrevNext, Label,
    Mora, Phoneme, Utterance, Word,
};

pub fn fixtures() -> [(&'static str, Label); 12] {
    [
        // こんにちは
        (
            "xx^xx-sil+k=o/A:xx+xx+xx/B:xx-xx_xx/C:xx_xx+xx/D:xx+xx_xx/E:xx_xx!xx_xx-xx/F:xx_xx#xx_xx@xx_xx|xx_xx/G:5_5%0_xx_xx/H:xx_xx/I:xx-xx@xx+xx&xx-xx|xx+xx/J:1_5/K:1+1-5",
            Label {
                phoneme: Phoneme {
                    p2: None,
                    p1: None,
                    c: Some("sil".to_string()),
                    n1: Some("k".to_string()),
                    n2: Some("o".to_string()),
                },
                mora: None,
                word_prev: None,
                word_curr: None,
                word_next: None,
                accent_phrase_prev: None,
                accent_phrase_curr: None,
                accent_phrase_next: Some(AccentPhrasePrevNext {
                    mora_count: 5,
                    accent_position: 5,
                    is_interrogative: false,
                    is_pause_insertion: None,
                }),
                breath_group_prev: None,
                breath_group_curr: None,
                breath_group_next: Some(BreathGroupPrevNext {
                    accent_phrase_count: 1,
                    mora_count: 5,
                }),
                utterance: Utterance {
                    breath_group_count: 1,
                    accent_phrase_count: 1,
                    mora_count: 5,
                },
            },
        ),
        (
            "xx^sil-k+o=N/A:-4+1+5/B:xx-xx_xx/C:09_xx+xx/D:xx+xx_xx/E:xx_xx!xx_xx-xx/F:5_5#0_xx@1_1|1_5/G:xx_xx%xx_xx_xx/H:xx_xx/I:1-5@1+1&1-1|1+5/J:xx_xx/K:1+1-5",
            Label {
                phoneme: Phoneme {
                    p2: None,
                    p1: Some("sil".to_string()),
                    c: Some("k".to_string()),
                    n1: Some("o".to_string()),
                    n2: Some("N".to_string()),
                },
                mora: Some(Mora {
                    relative_accent_position: -4,
                    position_forward: 1,
                    position_backward: 5,
                }),
                word_prev: None,
                word_curr: Some(Word {
                    pos: Some(9),
                    ctype: None,
                    cform: None,
                }),
                word_next: None,
                accent_phrase_prev: None,
                accent_phrase_curr: Some(AccentPhraseCurrent {
                    mora_count: 5,
                    accent_position: 5,
                    is_interrogative: false,
                    accent_phrase_position_forward: 1,
                    accent_phrase_position_backward: 1,
                    mora_position_forward: 1,
                    mora_position_backward: 5,
                }),
                accent_phrase_next: None,
                breath_group_prev: None,
                breath_group_curr: Some(BreathGroupCurrent {
                    accent_phrase_count: 1,
                    mora_count: 5,
                    breath_group_position_forward: 1,
                    breath_group_position_backward: 1,
                    accent_phrase_position_forward: 1,
                    accent_phrase_position_backward: 1,
                    mora_position_forward: 1,
                    mora_position_backward: 5,
                }),
                breath_group_next: None,
                utterance: Utterance {
                    breath_group_count: 1,
                    accent_phrase_count: 1,
                    mora_count: 5,
                },
            },
        ),
        (
            "sil^k-o+N=n/A:-4+1+5/B:xx-xx_xx/C:09_xx+xx/D:xx+xx_xx/E:xx_xx!xx_xx-xx/F:5_5#0_xx@1_1|1_5/G:xx_xx%xx_xx_xx/H:xx_xx/I:1-5@1+1&1-1|1+5/J:xx_xx/K:1+1-5",
            Label {
                phoneme: Phoneme {
                    p2: Some("sil".to_string()),
                    p1: Some("k".to_string()),
                    c: Some("o".to_string()),
                    n1: Some("N".to_string()),
                    n2: Some("n".to_string()),
                },
                mora: Some(Mora {
                    relative_accent_position: -4,
                    position_forward: 1,
                    position_backward: 5,
                }),
                word_prev: None,
                word_curr: Some(Word {
                    pos: Some(9),
                    ctype: None,
                    cform: None,
                }),
                word_next: None,
                accent_phrase_prev: None,
                accent_phrase_curr: Some(AccentPhraseCurrent {
                    mora_count: 5,
                    accent_position: 5,
                    is_interrogative: false,
                    accent_phrase_position_forward: 1,
                    accent_phrase_position_backward: 1,
                    mora_position_forward: 1,
                    mora_position_backward: 5,
                }),
                accent_phrase_next: None,
                breath_group_prev: None,
                breath_group_curr: Some(BreathGroupCurrent {
                    accent_phrase_count: 1,
                    mora_count: 5,
                    breath_group_position_forward: 1,
                    breath_group_position_backward: 1,
                    accent_phrase_position_forward: 1,
                    accent_phrase_position_backward: 1,
                    mora_position_forward: 1,
                    mora_position_backward: 5,
                }),
                breath_group_next: None,
                utterance: Utterance {
                    breath_group_count: 1,
                    accent_phrase_count: 1,
                    mora_count: 5,
                },
            },
        ),
        (
            "k^o-N+n=i/A:-3+2+4/B:xx-xx_xx/C:09_xx+xx/D:xx+xx_xx/E:xx_xx!xx_xx-xx/F:5_5#0_xx@1_1|1_5/G:xx_xx%xx_xx_xx/H:xx_xx/I:1-5@1+1&1-1|1+5/J:xx_xx/K:1+1-5",
            Label {
                phoneme: Phoneme {
                    p2: Some("k".to_string()),
                    p1: Some("o".to_string()),
                    c: Some("N".to_string()),
                    n1: Some("n".to_string()),
                    n2: Some("i".to_string()),
                },
                mora: Some(Mora {
                    relative_accent_position: -3,
                    position_forward: 2,
                    position_backward: 4,
                }),
                word_prev: None,
                word_curr: Some(Word {
                    pos: Some(9),
                    ctype: None,
                    cform: None,
                }),
                word_next: None,
                accent_phrase_prev: None,
                accent_phrase_curr: Some(AccentPhraseCurrent {
                    mora_count: 5,
                    accent_position: 5,
                    is_interrogative: false,
                    accent_phrase_position_forward: 1,
                    accent_phrase_position_backward: 1,
                    mora_position_forward: 1,
                    mora_position_backward: 5,
                }),
                accent_phrase_next: None,
                breath_group_prev: None,
                breath_group_curr: Some(BreathGroupCurrent {
                    accent_phrase_count: 1,
                    mora_count: 5,
                    breath_group_position_forward: 1,
                    breath_group_position_backward: 1,
                    accent_phrase_position_forward: 1,
                    accent_phrase_position_backward: 1,
                    mora_position_forward: 1,
                    mora_position_backward: 5,
                }),
                breath_group_next: None,
                utterance: Utterance {
                    breath_group_count: 1,
                    accent_phrase_count: 1,
                    mora_count: 5,
                },
            },
        ),
        (
            "o^N-n+i=ch/A:-2+3+3/B:xx-xx_xx/C:09_xx+xx/D:xx+xx_xx/E:xx_xx!xx_xx-xx/F:5_5#0_xx@1_1|1_5/G:xx_xx%xx_xx_xx/H:xx_xx/I:1-5@1+1&1-1|1+5/J:xx_xx/K:1+1-5",
            Label {
                phoneme: Phoneme {
                    p2: Some("o".to_string()),
                    p1: Some("N".to_string()),
                    c: Some("n".to_string()),
                    n1: Some("i".to_string()),
                    n2: Some("ch".to_string()),
                },
                mora: Some(Mora {
                    relative_accent_position: -2,
                    position_forward: 3,
                    position_backward: 3,
                }),
                word_prev: None,
                word_curr: Some(Word {
                    pos: Some(9),
                    ctype: None,
                    cform: None,
                }),
                word_next: None,
                accent_phrase_prev: None,
                accent_phrase_curr: Some(AccentPhraseCurrent {
                    mora_count: 5,
                    accent_position: 5,
                    is_interrogative: false,
                    accent_phrase_position_forward: 1,
                    accent_phrase_position_backward: 1,
                    mora_position_forward: 1,
                    mora_position_backward: 5,
                }),
                accent_phrase_next: None,
                breath_group_prev: None,
                breath_group_curr: Some(BreathGroupCurrent {
                    accent_phrase_count: 1,
                    mora_count: 5,
                    breath_group_position_forward: 1,
                    breath_group_position_backward: 1,
                    accent_phrase_position_forward: 1,
                    accent_phrase_position_backward: 1,
                    mora_position_forward: 1,
                    mora_position_backward: 5,
                }),
                breath_group_next: None,
                utterance: Utterance {
                    breath_group_count: 1,
                    accent_phrase_count: 1,
                    mora_count: 5,
                },
            },
        ),
        (
            "N^n-i+ch=i/A:-2+3+3/B:xx-xx_xx/C:09_xx+xx/D:xx+xx_xx/E:xx_xx!xx_xx-xx/F:5_5#0_xx@1_1|1_5/G:xx_xx%xx_xx_xx/H:xx_xx/I:1-5@1+1&1-1|1+5/J:xx_xx/K:1+1-5",
            Label {
                phoneme: Phoneme {
                    p2: Some("N".to_string()),
                    p1: Some("n".to_string()),
                    c: Some("i".to_string()),
                    n1: Some("ch".to_string()),
                    n2: Some("i".to_string()),
                },
                mora: Some(Mora {
                    relative_accent_position: -2,
                    position_forward: 3,
                    position_backward: 3,
                }),
                word_prev: None,
                word_curr: Some(Word {
                    pos: Some(9),
                    ctype: None,
                    cform: None,
                }),
                word_next: None,
                accent_phrase_prev: None,
                accent_phrase_curr: Some(AccentPhraseCurrent {
                    mora_count: 5,
                    accent_position: 5,
                    is_interrogative: false,
                    accent_phrase_position_forward: 1,
                    accent_phrase_position_backward: 1,
                    mora_position_forward: 1,
                    mora_position_backward: 5,
                }),
                accent_phrase_next: None,
                breath_group_prev: None,
                breath_group_curr: Some(BreathGroupCurrent {
                    accent_phrase_count: 1,
                    mora_count: 5,
                    breath_group_position_forward: 1,
                    breath_group_position_backward: 1,
                    accent_phrase_position_forward: 1,
                    accent_phrase_position_backward: 1,
                    mora_position_forward: 1,
                    mora_position_backward: 5,
                }),
                breath_group_next: None,
                utterance: Utterance {
                    breath_group_count: 1,
                    accent_phrase_count: 1,
                    mora_count: 5,
                },
            },
        ),
        (
            "n^i-ch+i=w/A:-1+4+2/B:xx-xx_xx/C:09_xx+xx/D:xx+xx_xx/E:xx_xx!xx_xx-xx/F:5_5#0_xx@1_1|1_5/G:xx_xx%xx_xx_xx/H:xx_xx/I:1-5@1+1&1-1|1+5/J:xx_xx/K:1+1-5",
            Label {
                phoneme: Phoneme {
                    p2: Some("n".to_string()),
                    p1: Some("i".to_string()),
                    c: Some("ch".to_string()),
                    n1: Some("i".to_string()),
                    n2: Some("w".to_string()),
                },
                mora: Some(Mora {
                    relative_accent_position: -1,
                    position_forward: 4,
                    position_backward: 2,
                }),
                word_prev: None,
                word_curr: Some(Word {
                    pos: Some(9),
                    ctype: None,
                    cform: None,
                }),
                word_next: None,
                accent_phrase_prev: None,
                accent_phrase_curr: Some(AccentPhraseCurrent {
                    mora_count: 5,
                    accent_position: 5,
                    is_interrogative: false,
                    accent_phrase_position_forward: 1,
                    accent_phrase_position_backward: 1,
                    mora_position_forward: 1,
                    mora_position_backward: 5,
                }),
                accent_phrase_next: None,
                breath_group_prev: None,
                breath_group_curr: Some(BreathGroupCurrent {
                    accent_phrase_count: 1,
                    mora_count: 5,
                    breath_group_position_forward: 1,
                    breath_group_position_backward: 1,
                    accent_phrase_position_forward: 1,
                    accent_phrase_position_backward: 1,
                    mora_position_forward: 1,
                    mora_position_backward: 5,
                }),
                breath_group_next: None,
                utterance: Utterance {
                    breath_group_count: 1,
                    accent_phrase_count: 1,
                    mora_count: 5,
                },
            },
        ),
        (
            "i^ch-i+w=a/A:-1+4+2/B:xx-xx_xx/C:09_xx+xx/D:xx+xx_xx/E:xx_xx!xx_xx-xx/F:5_5#0_xx@1_1|1_5/G:xx_xx%xx_xx_xx/H:xx_xx/I:1-5@1+1&1-1|1+5/J:xx_xx/K:1+1-5",
            Label {
                phoneme: Phoneme {
                    p2: Some("i".to_string()),
                    p1: Some("ch".to_string()),
                    c: Some("i".to_string()),
                    n1: Some("w".to_string()),
                    n2: Some("a".to_string()),
                },
                mora: Some(Mora {
                    relative_accent_position: -1,
                    position_forward: 4,
                    position_backward: 2,
                }),
                word_prev: None,
                word_curr: Some(Word {
                    pos: Some(9),
                    ctype: None,
                    cform: None,
                }),
                word_next: None,
                accent_phrase_prev: None,
                accent_phrase_curr: Some(AccentPhraseCurrent {
                    mora_count: 5,
                    accent_position: 5,
                    is_interrogative: false,
                    accent_phrase_position_forward: 1,
                    accent_phrase_position_backward: 1,
                    mora_position_forward: 1,
                    mora_position_backward: 5,
                }),
                accent_phrase_next: None,
                breath_group_prev: None,
                breath_group_curr: Some(BreathGroupCurrent {
                    accent_phrase_count: 1,
                    mora_count: 5,
                    breath_group_position_forward: 1,
                    breath_group_position_backward: 1,
                    accent_phrase_position_forward: 1,
                    accent_phrase_position_backward: 1,
                    mora_position_forward: 1,
                    mora_position_backward: 5,
                }),
                breath_group_next: None,
                utterance: Utterance {
                    breath_group_count: 1,
                    accent_phrase_count: 1,
                    mora_count: 5,
                },
            },
        ),
        (
            "ch^i-w+a=sil/A:0+5+1/B:xx-xx_xx/C:09_xx+xx/D:xx+xx_xx/E:xx_xx!xx_xx-xx/F:5_5#0_xx@1_1|1_5/G:xx_xx%xx_xx_xx/H:xx_xx/I:1-5@1+1&1-1|1+5/J:xx_xx/K:1+1-5",
            Label {
                phoneme: Phoneme {
                    p2: Some("ch".to_string()),
                    p1: Some("i".to_string()),
                    c: Some("w".to_string()),
                    n1: Some("a".to_string()),
                    n2: Some("sil".to_string()),
                },
                mora: Some(Mora {
                    relative_accent_position: 0,
                    position_forward: 5,
                    position_backward: 1,
                }),
                word_prev: None,
                word_curr: Some(Word {
                    pos: Some(9),
                    ctype: None,
                    cform: None,
                }),
                word_next: None,
                accent_phrase_prev: None,
                accent_phrase_curr: Some(AccentPhraseCurrent {
                    mora_count: 5,
                    accent_position: 5,
                    is_interrogative: false,
                    accent_phrase_position_forward: 1,
                    accent_phrase_position_backward: 1,
                    mora_position_forward: 1,
                    mora_position_backward: 5,
                }),
                accent_phrase_next: None,
                breath_group_prev: None,
                breath_group_curr: Some(BreathGroupCurrent {
                    accent_phrase_count: 1,
                    mora_count: 5,
                    breath_group_position_forward: 1,
                    breath_group_position_backward: 1,
                    accent_phrase_position_forward: 1,
                    accent_phrase_position_backward: 1,
                    mora_position_forward: 1,
                    mora_position_backward: 5,
                }),
                breath_group_next: None,
                utterance: Utterance {
                    breath_group_count: 1,
                    accent_phrase_count: 1,
                    mora_count: 5,
                },
            },
        ),
        (
            "i^w-a+sil=xx/A:0+5+1/B:xx-xx_xx/C:09_xx+xx/D:xx+xx_xx/E:xx_xx!xx_xx-xx/F:5_5#0_xx@1_1|1_5/G:xx_xx%xx_xx_xx/H:xx_xx/I:1-5@1+1&1-1|1+5/J:xx_xx/K:1+1-5",
            Label {
                phoneme: Phoneme {
                    p2: Some("i".to_string()),
                    p1: Some("w".to_string()),
                    c: Some("a".to_string()),
                    n1: Some("sil".to_string()),
                    n2: None,
                },
                mora: Some(Mora {
                    relative_accent_position: 0,
                    position_forward: 5,
                    position_backward: 1,
                }),
                word_prev: None,
                word_curr: Some(Word {
                    pos: Some(9),
                    ctype: None,
                    cform: None,
                }),
                word_next: None,
                accent_phrase_prev: None,
                accent_phrase_curr: Some(AccentPhraseCurrent {
                    mora_count: 5,
                    accent_position: 5,
                    is_interrogative: false,
                    accent_phrase_position_forward: 1,
                    accent_phrase_position_backward: 1,
                    mora_position_forward: 1,
                    mora_position_backward: 5,
                }),
                accent_phrase_next: None,
                breath_group_prev: None,
                breath_group_curr: Some(BreathGroupCurrent {
                    accent_phrase_count: 1,
                    mora_count: 5,
                    breath_group_position_forward: 1,
                    breath_group_position_backward: 1,
                    accent_phrase_position_forward: 1,
                    accent_phrase_position_backward: 1,
                    mora_position_forward: 1,
                    mora_position_backward: 5,
                }),
                breath_group_next: None,
                utterance: Utterance {
                    breath_group_count: 1,
                    accent_phrase_count: 1,
                    mora_count: 5,
                },
            },
        ),
        (
            "w^a-sil+xx=xx/A:xx+xx+xx/B:xx-xx_xx/C:xx_xx+xx/D:xx+xx_xx/E:5_5!0_xx-xx/F:xx_xx#xx_xx@xx_xx|xx_xx/G:xx_xx%xx_xx_xx/H:1_5/I:xx-xx@xx+xx&xx-xx|xx+xx/J:xx_xx/K:1+1-5",
            Label {
                phoneme: Phoneme {
                    p2: Some("w".to_string()),
                    p1: Some("a".to_string()),
                    c: Some("sil".to_string()),
                    n1: None,
                    n2: None,
                },
                mora: None,
                word_prev: None,
                word_curr: None,
                word_next: None,
                accent_phrase_prev: Some(AccentPhrasePrevNext {
                    mora_count: 5,
                    accent_position: 5,
                    is_interrogative: false,
                    is_pause_insertion: None,
                }),
                accent_phrase_curr: None,
                accent_phrase_next: None,
                breath_group_prev: Some(BreathGroupPrevNext {
                    accent_phrase_count: 1,
                    mora_count: 5,
                }),
                breath_group_curr: None,
                breath_group_next: None,
                utterance: Utterance {
                    breath_group_count: 1,
                    accent_phrase_count: 1,
                    mora_count: 5,
                },
            },
        ),
        // 「なにを言っているのですか,それはスマホですよ.」
        // (partial; 6th phoneme including the first sil)
        (
            "n^i-o+i=cl/A:2+3+1/B:04-xx_xx/C:13_xx+xx/D:20+1_1/E:xx_xx!xx_xx-xx/F:3_1#0_xx@1_4|1_12/G:3_3%0_xx_1/H:xx_xx/I:4-12@1+2&1-6|1+21/J:2_9/K:2+6-21",
            Label {
                phoneme: Phoneme {
                    p2: Some("n".to_string()),
                    p1: Some("i".to_string()),
                    c: Some("o".to_string()),
                    n1: Some("i".to_string()),
                    n2: Some("cl".to_string()),
                },
                mora: Some(Mora {
                    relative_accent_position: 2,
                    position_forward: 3,
                    position_backward: 1,
                }),
                word_prev: Some(Word {
                    pos: Some(4),
                    ctype: None,
                    cform: None,
                }),
                word_curr: Some(Word {
                    pos: Some(13),
                    ctype: None,
                    cform: None,
                }),
                word_next: Some(Word {
                    pos: Some(20),
                    ctype: Some(1),
                    cform: Some(1),
                }),
                accent_phrase_prev: None,
                accent_phrase_curr: Some(AccentPhraseCurrent {
                    mora_count: 3,
                    accent_position: 1,
                    is_interrogative: false,
                    accent_phrase_position_forward: 1,
                    accent_phrase_position_backward: 4,
                    mora_position_forward: 1,
                    mora_position_backward: 12,
                }),
                accent_phrase_next: Some(AccentPhrasePrevNext {
                    mora_count: 3,
                    accent_position: 3,
                    is_interrogative: false,
                    is_pause_insertion: Some(false),
                }),
                breath_group_prev: None,
                breath_group_curr: Some(BreathGroupCurrent {
                    accent_phrase_count: 4,
                    mora_count: 12,
                    breath_group_position_forward: 1,
                    breath_group_position_backward: 2,
                    accent_phrase_position_forward: 1,
                    accent_phrase_position_backward: 6,
                    mora_position_forward: 1,
                    mora_position_backward: 21,
                }),
                breath_group_next: Some(BreathGroupPrevNext {
                    accent_phrase_count: 2,
                    mora_count: 9,
                }),
                utterance: Utterance {
                    breath_group_count: 2,
                    accent_phrase_count: 6,
                    mora_count: 21,
                },
            },
        ),
    ]
}