summaryrefslogtreecommitdiff
path: root/ext/mixed/js/audio.js
blob: 6a338cca87b03f7d4deaa8bc7b326b8bff191569 (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
/*
 * Copyright (C) 2019-2020  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 apiAudioGetUrl*/

class TextToSpeechAudio {
    constructor(text, voice) {
        this.text = text;
        this.voice = voice;
        this._utterance = null;
        this._volume = 1;
    }

    get currentTime() {
        return 0;
    }
    set currentTime(value) {
        // NOP
    }

    get volume() {
        return this._volume;
    }
    set volume(value) {
        this._volume = value;
        if (this._utterance !== null) {
            this._utterance.volume = value;
        }
    }

    play() {
        try {
            if (this._utterance === null) {
                this._utterance = new SpeechSynthesisUtterance(this.text || '');
                this._utterance.lang = 'ja-JP';
                this._utterance.volume = this._volume;
                this._utterance.voice = this.voice;
            }

            speechSynthesis.cancel();
            speechSynthesis.speak(this._utterance);
        } catch (e) {
            // NOP
        }
    }

    pause() {
        try {
            speechSynthesis.cancel();
        } catch (e) {
            // NOP
        }
    }

    static createFromUri(ttsUri) {
        const m = /^tts:[^#?]*\?([^#]*)/.exec(ttsUri);
        if (m === null) { return null; }

        const searchParameters = new URLSearchParams(m[1]);
        const text = searchParameters.get('text');
        let voice = searchParameters.get('voice');
        if (text === null || voice === null) { return null; }

        voice = audioGetTextToSpeechVoice(voice);
        if (voice === null) { return null; }

        return new TextToSpeechAudio(text, voice);
    }
}

class AudioSystem {
    constructor() {
        this._cache = new Map();
        this._cacheSizeMaximum = 32;

        if (typeof speechSynthesis !== 'undefined') {
            // speechSynthesis.getVoices() will not be populated unless some API call is made.
            speechSynthesis.addEventListener('voiceschanged', this._onVoicesChanged.bind(this));
        }
    }

    async getExpressionAudio(expression, sources, optionsContext, details) {
        const key = `${expression.expression}:${expression.reading}`;
        const cacheValue = this._cache.get(expression);
        if (typeof cacheValue !== 'undefined') {
            const {audio, uri, source} = cacheValue;
            return {audio, uri, source};
        }

        for (const source of sources) {
            const uri = await apiAudioGetUrl(expression, source, optionsContext);
            if (uri === null) { continue; }

            try {
                const audio = await this._createAudio(uri, details);
                this._cacheCheck();
                this._cache.set(key, {audio, uri, source});
                return {audio, uri, source};
            } catch (e) {
                // NOP
            }
        }

        throw new Error('Could not create audio');
    }

    createTextToSpeechAudio({text, voiceUri}) {
        const voice = this._getTextToSpeechVoiceFromVoiceUri(voiceUri);
        if (voice === null) {
            throw new Error('Invalid text-to-speech voice');
        }
        return new TextToSpeechAudio(text, voice);
    }

    _onVoicesChanged() {
        // NOP
    }

    async _createAudio(uri, details) {
        const ttsParameters = this._getTextToSpeechParameters(uri);
        if (ttsParameters !== null) {
            if (typeof details === 'object' && details !== null) {
                if (details.tts === false) {
                    throw new Error('Text-to-speech not permitted');
                }
            }
            return this.createTextToSpeechAudio(ttsParameters);
        }

        return await this._createAudioFromUrl(uri);
    }

    _createAudioFromUrl(url) {
        return new Promise((resolve, reject) => {
            const audio = new Audio(url);
            audio.addEventListener('loadeddata', () => {
                const duration = audio.duration;
                if (duration === 5.694694 || duration === 5.720718) {
                    // Hardcoded values for invalid audio
                    reject(new Error('Could not retrieve audio'));
                } else {
                    resolve(audio);
                }
            });
            audio.addEventListener('error', () => reject(audio.error));
        });
    }

    _getTextToSpeechVoiceFromVoiceUri(voiceUri) {
        try {
            for (const voice of speechSynthesis.getVoices()) {
                if (voice.voiceURI === voiceUri) {
                    return voice;
                }
            }
        } catch (e) {
            // NOP
        }
        return null;
    }

    _getTextToSpeechParameters(uri) {
        const m = /^tts:[^#?]*\?([^#]*)/.exec(uri);
        if (m === null) { return null; }

        const searchParameters = new URLSearchParams(m[1]);
        const text = searchParameters.get('text');
        const voiceUri = searchParameters.get('voice');
        return (text !== null && voiceUri !== null ? {text, voiceUri} : null);
    }

    _cacheCheck() {
        const removeCount = this._cache.size - this._cacheSizeMaximum;
        if (removeCount <= 0) { return; }

        const removeKeys = [];
        for (const key of this._cache.keys()) {
            removeKeys.push(key);
            if (removeKeys.length >= removeCount) { break; }
        }

        for (const key of removeKeys) {
            this._cache.delete(key);
        }
    }
}


function audioGetFromUrl(url, willDownload) {
    const tts = TextToSpeechAudio.createFromUri(url);
    if (tts !== null) {
        if (willDownload) {
            throw new Error('AnkiConnect does not support downloading text-to-speech audio.');
        }
        return Promise.resolve(tts);
    }

    return new Promise((resolve, reject) => {
        const audio = new Audio(url);
        audio.addEventListener('loadeddata', () => {
            if (audio.duration === 5.694694 || audio.duration === 5.720718) {
                // Hardcoded values for invalid audio
                reject(new Error('Could not retrieve audio'));
            } else {
                resolve(audio);
            }
        });
        audio.addEventListener('error', () => reject(audio.error));
    });
}

async function audioGetFromSources(expression, sources, optionsContext, willDownload, cache=null) {
    const key = `${expression.expression}:${expression.reading}`;
    if (cache !== null) {
        const cacheValue = cache.get(expression);
        if (typeof cacheValue !== 'undefined') {
            return cacheValue;
        }
    }

    for (let i = 0, ii = sources.length; i < ii; ++i) {
        const source = sources[i];
        const url = await apiAudioGetUrl(expression, source, optionsContext);
        if (url === null) {
            continue;
        }

        try {
            let audio = await audioGetFromUrl(url, willDownload);
            if (willDownload) {
                // AnkiConnect handles downloading URLs into cards
                audio = null;
            }
            const result = {audio, url, source};
            if (cache !== null) {
                cache.set(key, result);
            }
            return result;
        } catch (e) {
            // NOP
        }
    }
    return {audio: null, url: null, source: null};
}

function audioGetTextToSpeechVoice(voiceURI) {
    try {
        for (const voice of speechSynthesis.getVoices()) {
            if (voice.voiceURI === voiceURI) {
                return voice;
            }
        }
    } catch (e) {
        // NOP
    }
    return null;
}

function audioPrepareTextToSpeech(options) {
    if (
        audioPrepareTextToSpeech.state ||
        !options.audio.textToSpeechVoice ||
        !(
            options.audio.sources.includes('text-to-speech') ||
            options.audio.sources.includes('text-to-speech-reading')
        )
    ) {
        // Text-to-speech not in use.
        return;
    }

    // Chrome needs this value called once before it will become populated.
    // The first call will return an empty list.
    audioPrepareTextToSpeech.state = true;
    try {
        speechSynthesis.getVoices();
    } catch (e) {
        // NOP
    }
}
audioPrepareTextToSpeech.state = false;