summaryrefslogtreecommitdiff
path: root/ext/js/language/sandbox/dictionary-data-util.js
blob: 951e10ff70f4be368d5dbe7502125cae9a4a154d (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
/*
 * Copyright (C) 2020-2021  Yomichan Authors
 *
 * 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/>.
 */

class DictionaryDataUtil {
    static groupTermTags(dictionaryEntry) {
        const {headwords} = dictionaryEntry;
        const headwordCount = headwords.length;
        const uniqueCheck = (headwordCount > 1);
        const resultsIndexMap = new Map();
        const results = [];
        for (let i = 0; i < headwordCount; ++i) {
            const {tags} = headwords[i];
            for (const tag of tags) {
                if (uniqueCheck) {
                    const {name, category, notes, dictionary} = tag;
                    const key = this._createMapKey([name, category, notes, dictionary]);
                    const index = resultsIndexMap.get(key);
                    if (typeof index !== 'undefined') {
                        const existingItem = results[index];
                        existingItem.headwordIndices.push(i);
                        continue;
                    }
                    resultsIndexMap.set(key, results.length);
                }

                const item = {tag, headwordIndices: [i]};
                results.push(item);
            }
        }
        return results;
    }

    static groupTermFrequencies(dictionaryEntry) {
        const {headwords, frequencies} = dictionaryEntry;

        const map1 = new Map();
        for (const {headwordIndex, dictionary, hasReading, frequency} of frequencies) {
            const {term, reading} = headwords[headwordIndex];

            let map2 = map1.get(dictionary);
            if (typeof map2 === 'undefined') {
                map2 = new Map();
                map1.set(dictionary, map2);
            }

            const readingKey = hasReading ? reading : null;
            const key = this._createMapKey([term, readingKey]);
            let frequencyData = map2.get(key);
            if (typeof frequencyData === 'undefined') {
                frequencyData = {term, reading: readingKey, values: new Set()};
                map2.set(key, frequencyData);
            }

            frequencyData.values.add(frequency);
        }
        return this._createFrequencyGroupsFromMap(map1);
    }

    static groupKanjiFrequencies(frequencies) {
        const map1 = new Map();
        for (const {dictionary, character, frequency} of frequencies) {
            let map2 = map1.get(dictionary);
            if (typeof map2 === 'undefined') {
                map2 = new Map();
                map1.set(dictionary, map2);
            }

            let frequencyData = map2.get(character);
            if (typeof frequencyData === 'undefined') {
                frequencyData = {character, values: new Set()};
                map2.set(character, frequencyData);
            }

            frequencyData.values.add(frequency);
        }
        return this._createFrequencyGroupsFromMap(map1);
    }

    static getPitchAccentInfos(dictionaryEntry) {
        const {headwords, pronunciations} = dictionaryEntry;

        const allTerms = new Set();
        const allReadings = new Set();
        for (const {term, reading} of headwords) {
            allTerms.add(term);
            allReadings.add(reading);
        }

        const pitchAccentInfoMap = new Map();
        for (const {headwordIndex, dictionary, pitches} of pronunciations) {
            const {term, reading} = headwords[headwordIndex];
            let dictionaryPitchAccentInfoList = pitchAccentInfoMap.get(dictionary);
            if (typeof dictionaryPitchAccentInfoList === 'undefined') {
                dictionaryPitchAccentInfoList = [];
                pitchAccentInfoMap.set(dictionary, dictionaryPitchAccentInfoList);
            }
            for (const {position, nasalPositions, devoicePositions, tags} of pitches) {
                let pitchAccentInfo = this._findExistingPitchAccentInfo(reading, position, nasalPositions, devoicePositions, tags, dictionaryPitchAccentInfoList);
                if (pitchAccentInfo === null) {
                    pitchAccentInfo = {
                        terms: new Set(),
                        reading,
                        position,
                        nasalPositions,
                        devoicePositions,
                        tags,
                        exclusiveTerms: [],
                        exclusiveReadings: []
                    };
                    dictionaryPitchAccentInfoList.push(pitchAccentInfo);
                }
                pitchAccentInfo.terms.add(term);
            }
        }

        const multipleReadings = (allReadings.size > 1);
        for (const dictionaryPitchAccentInfoList of pitchAccentInfoMap.values()) {
            for (const pitchAccentInfo of dictionaryPitchAccentInfoList) {
                const {terms, reading, exclusiveTerms, exclusiveReadings} = pitchAccentInfo;
                if (!this._areSetsEqual(terms, allTerms)) {
                    exclusiveTerms.push(...this._getSetIntersection(terms, allTerms));
                }
                if (multipleReadings) {
                    exclusiveReadings.push(reading);
                }
                pitchAccentInfo.terms = [...terms];
            }
        }

        const results2 = [];
        for (const [dictionary, pitches] of pitchAccentInfoMap.entries()) {
            results2.push({dictionary, pitches});
        }
        return results2;
    }

    static getTermFrequency(termTags) {
        let totalScore = 0;
        for (const {score} of termTags) {
            totalScore += score;
        }
        if (totalScore > 0) {
            return 'popular';
        } else if (totalScore < 0) {
            return 'rare';
        } else {
            return 'normal';
        }
    }

    static getDisambiguations(headwords, headwordIndices, allTermsSet, allReadingsSet) {
        if (allTermsSet.size <= 1 && allReadingsSet.size <= 1) { return []; }

        const terms = new Set();
        const readings = new Set();
        for (const headwordIndex of headwordIndices) {
            const {term, reading} = headwords[headwordIndex];
            terms.add(term);
            readings.add(reading);
        }

        const disambiguations = [];
        const addTerms = !this._areSetsEqual(terms, allTermsSet);
        const addReadings = !this._areSetsEqual(readings, allReadingsSet);
        if (addTerms) {
            disambiguations.push(...this._getSetIntersection(terms, allTermsSet));
        }
        if (addReadings) {
            if (addTerms) {
                for (const term of terms) {
                    readings.delete(term);
                }
            }
            disambiguations.push(...this._getSetIntersection(readings, allReadingsSet));
        }
        return disambiguations;
    }

    static isNonNounVerbOrAdjective(wordClasses) {
        let isVerbOrAdjective = false;
        let isSuruVerb = false;
        let isNoun = false;
        for (const wordClass of wordClasses) {
            switch (wordClass) {
                case 'v1':
                case 'v5':
                case 'vk':
                case 'vz':
                case 'adj-i':
                    isVerbOrAdjective = true;
                    break;
                case 'vs':
                    isVerbOrAdjective = true;
                    isSuruVerb = true;
                    break;
                case 'n':
                    isNoun = true;
                    break;
            }
        }
        return isVerbOrAdjective && !(isSuruVerb && isNoun);
    }

    // Private

    static _createFrequencyGroupsFromMap(map) {
        const results = [];
        for (const [dictionary, map2] of map.entries()) {
            const frequencies = [];
            for (const frequencyData of map2.values()) {
                frequencyData.values = [...frequencyData.values];
                frequencies.push(frequencyData);
            }
            results.push({dictionary, frequencies});
        }
        return results;
    }

    static _findExistingPitchAccentInfo(reading, position, nasalPositions, devoicePositions, tags, pitchAccentInfoList) {
        for (const pitchInfo of pitchAccentInfoList) {
            if (
                pitchInfo.reading === reading &&
                pitchInfo.position === position &&
                this._areArraysEqual(pitchInfo.nasalPositions, nasalPositions) &&
                this._areArraysEqual(pitchInfo.devoicePositions, devoicePositions) &&
                this._areTagListsEqual(pitchInfo.tags, tags)
            ) {
                return pitchInfo;
            }
        }
        return null;
    }

    static _areArraysEqual(array1, array2) {
        const ii = array1.length;
        if (ii !== array2.length) { return false; }
        for (let i = 0; i < ii; ++i) {
            if (array1[i] !== array2[i]) { return false; }
        }
        return true;
    }

    static _areTagListsEqual(tagList1, tagList2) {
        const ii = tagList1.length;
        if (tagList2.length !== ii) { return false; }

        for (let i = 0; i < ii; ++i) {
            const tag1 = tagList1[i];
            const tag2 = tagList2[i];
            if (tag1.name !== tag2.name || tag1.dictionary !== tag2.dictionary) {
                return false;
            }
        }

        return true;
    }

    static _areSetsEqual(set1, set2) {
        if (set1.size !== set2.size) {
            return false;
        }

        for (const value of set1) {
            if (!set2.has(value)) {
                return false;
            }
        }

        return true;
    }

    static _getSetIntersection(set1, set2) {
        const result = [];
        for (const value of set1) {
            if (set2.has(value)) {
                result.push(value);
            }
        }
        return result;
    }

    static _createMapKey(array) {
        return JSON.stringify(array);
    }
}