summaryrefslogtreecommitdiff
path: root/ext/bg/js/japanese.js
blob: fa40fc98113290fd75acfaed7e9173f56559403e (plain)
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
/*
 * Copyright (C) 2016-2020  Alex Yatskov <alex@foosoft.net>
 * Author: Alex Yatskov <alex@foosoft.net>
 *
 * This program is free software: you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation, either version 3 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program.  If not, see <https://www.gnu.org/licenses/>.
 */

/* global
 * wanakana
 */

const jp = (() => {
    const HALFWIDTH_KATAKANA_MAPPING = new Map([
        ['ヲ', 'ヲヺ-'],
        ['ァ', 'ァ--'],
        ['ィ', 'ィ--'],
        ['ゥ', 'ゥ--'],
        ['ェ', 'ェ--'],
        ['ォ', 'ォ--'],
        ['ャ', 'ャ--'],
        ['ュ', 'ュ--'],
        ['ョ', 'ョ--'],
        ['ッ', 'ッ--'],
        ['ー', 'ー--'],
        ['ア', 'ア--'],
        ['イ', 'イ--'],
        ['ウ', 'ウヴ-'],
        ['エ', 'エ--'],
        ['オ', 'オ--'],
        ['カ', 'カガ-'],
        ['キ', 'キギ-'],
        ['ク', 'クグ-'],
        ['ケ', 'ケゲ-'],
        ['コ', 'コゴ-'],
        ['サ', 'サザ-'],
        ['シ', 'シジ-'],
        ['ス', 'スズ-'],
        ['セ', 'セゼ-'],
        ['ソ', 'ソゾ-'],
        ['タ', 'タダ-'],
        ['チ', 'チヂ-'],
        ['ツ', 'ツヅ-'],
        ['テ', 'テデ-'],
        ['ト', 'トド-'],
        ['ナ', 'ナ--'],
        ['ニ', 'ニ--'],
        ['ヌ', 'ヌ--'],
        ['ネ', 'ネ--'],
        ['ノ', 'ノ--'],
        ['ハ', 'ハバパ'],
        ['ヒ', 'ヒビピ'],
        ['フ', 'フブプ'],
        ['ヘ', 'ヘベペ'],
        ['ホ', 'ホボポ'],
        ['マ', 'マ--'],
        ['ミ', 'ミ--'],
        ['ム', 'ム--'],
        ['メ', 'メ--'],
        ['モ', 'モ--'],
        ['ヤ', 'ヤ--'],
        ['ユ', 'ユ--'],
        ['ヨ', 'ヨ--'],
        ['ラ', 'ラ--'],
        ['リ', 'リ--'],
        ['ル', 'ル--'],
        ['レ', 'レ--'],
        ['ロ', 'ロ--'],
        ['ワ', 'ワ--'],
        ['ン', 'ン--']
    ]);

    const HIRAGANA_RANGE = [0x3040, 0x309f];
    const KATAKANA_RANGE = [0x30a0, 0x30ff];
    const KANA_RANGES = [HIRAGANA_RANGE, KATAKANA_RANGE];

    const CJK_UNIFIED_IDEOGRAPHS_RANGE = [0x4e00, 0x9fff];
    const CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A_RANGE = [0x3400, 0x4dbf];
    const CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B_RANGE = [0x20000, 0x2a6df];
    const CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C_RANGE = [0x2a700, 0x2b73f];
    const CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D_RANGE = [0x2b740, 0x2b81f];
    const CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E_RANGE = [0x2b820, 0x2ceaf];
    const CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F_RANGE = [0x2ceb0, 0x2ebef];
    const CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT_RANGE = [0x2f800, 0x2fa1f];
    const CJK_UNIFIED_IDEOGRAPHS_RANGES = [
        CJK_UNIFIED_IDEOGRAPHS_RANGE,
        CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A_RANGE,
        CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B_RANGE,
        CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C_RANGE,
        CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D_RANGE,
        CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E_RANGE,
        CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F_RANGE,
        CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT_RANGE
    ];

    const ITERATION_MARK_CODE_POINT = 0x3005;

    // Japanese character ranges, roughly ordered in order of expected frequency
    const JAPANESE_RANGES = [
        HIRAGANA_RANGE,
        KATAKANA_RANGE,

        ...CJK_UNIFIED_IDEOGRAPHS_RANGES,

        [0xff66, 0xff9f], // Halfwidth katakana

        [0x30fb, 0x30fc], // Katakana punctuation
        [0xff61, 0xff65], // Kana punctuation
        [0x3000, 0x303f], // CJK punctuation

        [0xff10, 0xff19], // Fullwidth numbers
        [0xff21, 0xff3a], // Fullwidth upper case Latin letters
        [0xff41, 0xff5a], // Fullwidth lower case Latin letters

        [0xff01, 0xff0f], // Fullwidth punctuation 1
        [0xff1a, 0xff1f], // Fullwidth punctuation 2
        [0xff3b, 0xff3f], // Fullwidth punctuation 3
        [0xff5b, 0xff60], // Fullwidth punctuation 4
        [0xffe0, 0xffee]  // Currency markers
    ];


    // Character code testing functions

    function isCodePointKanji(codePoint) {
        return isCodePointInRanges(codePoint, CJK_UNIFIED_IDEOGRAPHS_RANGES);
    }

    function isCodePointKana(codePoint) {
        return isCodePointInRanges(codePoint, KANA_RANGES);
    }

    function isCodePointJapanese(codePoint) {
        return isCodePointInRanges(codePoint, JAPANESE_RANGES);
    }

    function isCodePointInRanges(codePoint, ranges) {
        for (const [min, max] of ranges) {
            if (codePoint >= min && codePoint <= max) {
                return true;
            }
        }
        return false;
    }


    // String testing functions

    function isStringEntirelyKana(str) {
        if (str.length === 0) { return false; }
        for (const c of str) {
            if (!isCodePointKana(c.codePointAt(0))) {
                return false;
            }
        }
        return true;
    }

    function isStringPartiallyJapanese(str) {
        if (str.length === 0) { return false; }
        for (const c of str) {
            if (isCodePointJapanese(c.codePointAt(0))) {
                return true;
            }
        }
        return false;
    }


    // Conversion functions

    function convertKatakanaToHiragana(text) {
        let result = '';
        for (const c of text) {
            if (wanakana.isKatakana(c)) {
                result += wanakana.toHiragana(c);
            } else {
                result += c;
            }
        }

        return result;
    }

    function convertHiraganaToKatakana(text) {
        let result = '';
        for (const c of text) {
            if (wanakana.isHiragana(c)) {
                result += wanakana.toKatakana(c);
            } else {
                result += c;
            }
        }

        return result;
    }

    function convertToRomaji(text) {
        return wanakana.toRomaji(text);
    }

    function convertReading(expressionFragment, readingFragment, readingMode) {
        switch (readingMode) {
            case 'hiragana':
                return convertKatakanaToHiragana(readingFragment || '');
            case 'katakana':
                return convertHiraganaToKatakana(readingFragment || '');
            case 'romaji':
                if (readingFragment) {
                    return convertToRomaji(readingFragment);
                } else {
                    if (isStringEntirelyKana(expressionFragment)) {
                        return convertToRomaji(expressionFragment);
                    }
                }
                return readingFragment;
            case 'none':
                return null;
            default:
                return readingFragment;
        }
    }

    function convertNumericToFullWidth(text) {
        let result = '';
        for (const char of text) {
            let c = char.codePointAt(0);
            if (c >= 0x30 && c <= 0x39) { // ['0', '9']
                c += 0xff10 - 0x30; // 0xff10 = '0' full width
                result += String.fromCodePoint(c);
            } else {
                result += char;
            }
        }
        return result;
    }

    function convertHalfWidthKanaToFullWidth(text, sourceMapping) {
        let result = '';
        const hasSourceMapping = Array.isArray(sourceMapping);

        // This function is safe to use charCodeAt instead of codePointAt, since all
        // the relevant characters are represented with a single UTF-16 character code.
        for (let i = 0, ii = text.length; i < ii; ++i) {
            const c = text[i];
            const mapping = HALFWIDTH_KATAKANA_MAPPING.get(c);
            if (typeof mapping !== 'string') {
                result += c;
                continue;
            }

            let index = 0;
            switch (text.charCodeAt(i + 1)) {
                case 0xff9e: // dakuten
                    index = 1;
                    break;
                case 0xff9f: // handakuten
                    index = 2;
                    break;
            }

            let c2 = mapping[index];
            if (index > 0) {
                if (c2 === '-') { // invalid
                    index = 0;
                    c2 = mapping[0];
                } else {
                    ++i;
                }
            }

            if (hasSourceMapping && index > 0) {
                index = result.length;
                const v = sourceMapping.splice(index + 1, 1)[0];
                sourceMapping[index] += v;
            }
            result += c2;
        }

        return result;
    }

    function convertAlphabeticToKana(text, sourceMapping) {
        let part = '';
        let result = '';
        const ii = text.length;

        if (sourceMapping.length === ii) {
            sourceMapping.length = ii;
            sourceMapping.fill(1);
        }

        for (const char of text) {
            // Note: 0x61 is the character code for 'a'
            let c = char.codePointAt(0);
            if (c >= 0x41 && c <= 0x5a) { // ['A', 'Z']
                c += (0x61 - 0x41);
            } else if (c >= 0x61 && c <= 0x7a) { // ['a', 'z']
                // NOP; c += (0x61 - 0x61);
            } else if (c >= 0xff21 && c <= 0xff3a) { // ['A', 'Z'] fullwidth
                c += (0x61 - 0xff21);
            } else if (c >= 0xff41 && c <= 0xff5a) { // ['a', 'z'] fullwidth
                c += (0x61 - 0xff41);
            } else if (c === 0x2d || c === 0xff0d) { // '-' or fullwidth dash
                c = 0x2d; // '-'
            } else {
                if (part.length > 0) {
                    result += convertAlphabeticPartToKana(part, sourceMapping, result.length);
                    part = '';
                }
                result += char;
                continue;
            }
            part += String.fromCodePoint(c);
        }

        if (part.length > 0) {
            result += convertAlphabeticPartToKana(part, sourceMapping, result.length);
        }
        return result;
    }

    function convertAlphabeticPartToKana(text, sourceMapping, sourceMappingStart) {
        const result = wanakana.toHiragana(text);

        // Generate source mapping
        if (Array.isArray(sourceMapping)) {
            if (typeof sourceMappingStart !== 'number') { sourceMappingStart = 0; }
            let i = 0;
            let resultPos = 0;
            const ii = text.length;
            while (i < ii) {
                // Find smallest matching substring
                let iNext = i + 1;
                let resultPosNext = result.length;
                while (iNext < ii) {
                    const t = wanakana.toHiragana(text.substring(0, iNext));
                    if (t === result.substring(0, t.length)) {
                        resultPosNext = t.length;
                        break;
                    }
                    ++iNext;
                }

                // Merge characters
                const removals = iNext - i - 1;
                if (removals > 0) {
                    let sum = 0;
                    const vs = sourceMapping.splice(sourceMappingStart + 1, removals);
                    for (const v of vs) { sum += v; }
                    sourceMapping[sourceMappingStart] += sum;
                }
                ++sourceMappingStart;

                // Empty elements
                const additions = resultPosNext - resultPos - 1;
                for (let j = 0; j < additions; ++j) {
                    sourceMapping.splice(sourceMappingStart, 0, 0);
                    ++sourceMappingStart;
                }

                i = iNext;
                resultPos = resultPosNext;
            }
        }

        return result;
    }


    // Furigana distribution

    function distributeFurigana(expression, reading) {
        const fallback = [{furigana: reading, text: expression}];
        if (!reading) {
            return fallback;
        }

        let isAmbiguous = false;
        const segmentize = (reading2, groups) => {
            if (groups.length === 0 || isAmbiguous) {
                return [];
            }

            const group = groups[0];
            if (group.mode === 'kana') {
                if (convertKatakanaToHiragana(reading2).startsWith(convertKatakanaToHiragana(group.text))) {
                    const readingLeft = reading2.substring(group.text.length);
                    const segs = segmentize(readingLeft, groups.splice(1));
                    if (segs) {
                        return [{text: group.text}].concat(segs);
                    }
                }
            } else {
                let foundSegments = null;
                for (let i = reading2.length; i >= group.text.length; --i) {
                    const readingUsed = reading2.substring(0, i);
                    const readingLeft = reading2.substring(i);
                    const segs = segmentize(readingLeft, groups.slice(1));
                    if (segs) {
                        if (foundSegments !== null) {
                            // more than one way to segmentize the tail, mark as ambiguous
                            isAmbiguous = true;
                            return null;
                        }
                        foundSegments = [{text: group.text, furigana: readingUsed}].concat(segs);
                    }
                    // there is only one way to segmentize the last non-kana group
                    if (groups.length === 1) {
                        break;
                    }
                }
                return foundSegments;
            }
        };

        const groups = [];
        let modePrev = null;
        for (const c of expression) {
            const codePoint = c.codePointAt(0);
            const modeCurr = isCodePointKanji(codePoint) || codePoint === ITERATION_MARK_CODE_POINT ? 'kanji' : 'kana';
            if (modeCurr === modePrev) {
                groups[groups.length - 1].text += c;
            } else {
                groups.push({mode: modeCurr, text: c});
                modePrev = modeCurr;
            }
        }

        const segments = segmentize(reading, groups);
        if (segments && !isAmbiguous) {
            return segments;
        }
        return fallback;
    }

    function distributeFuriganaInflected(expression, reading, source) {
        const output = [];

        let stemLength = 0;
        const shortest = Math.min(source.length, expression.length);
        const sourceHiragana = convertKatakanaToHiragana(source);
        const expressionHiragana = convertKatakanaToHiragana(expression);
        while (stemLength < shortest && sourceHiragana[stemLength] === expressionHiragana[stemLength]) {
            ++stemLength;
        }
        const offset = source.length - stemLength;

        const stemExpression = source.substring(0, source.length - offset);
        const stemReading = reading.substring(
            0,
            offset === 0 ? reading.length : reading.length - expression.length + stemLength
        );
        for (const segment of distributeFurigana(stemExpression, stemReading)) {
            output.push(segment);
        }

        if (stemLength !== source.length) {
            output.push({text: source.substring(stemLength)});
        }

        return output;
    }


    // Exports

    return {
        isCodePointKanji,
        isCodePointKana,
        isCodePointJapanese,
        isStringEntirelyKana,
        isStringPartiallyJapanese,
        convertKatakanaToHiragana,
        convertHiraganaToKatakana,
        convertToRomaji,
        convertReading,
        convertNumericToFullWidth,
        convertHalfWidthKanaToFullWidth,
        convertAlphabeticToKana,
        distributeFurigana,
        distributeFuriganaInflected
    };
})();