summaryrefslogtreecommitdiff
path: root/ext/mixed/js/audio-system.js
blob: 19c856905fc316358baa940e21d222b9d46f93ea (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
/*
 * Copyright (C) 2019-2021  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/>.
 */

/* global
 * CacheMap
 * TextToSpeechAudio
 * api
 */

class AudioSystem {
    constructor(useCache) {
        this._cache = new CacheMap(useCache ? 32 : 0);
        this._fallbackAudio = null;
    }

    prepare() {
        // speechSynthesis.getVoices() will not be populated unless some API call is made.
        if (typeof speechSynthesis === 'undefined') { return; }

        const eventListeners = new EventListenerCollection();
        const onVoicesChanged = () => { eventListeners.removeAllEventListeners(); };
        eventListeners.addEventListener(speechSynthesis, 'voiceschanged', onVoicesChanged, false);
    }

    async createDefinitionAudio(sources, expression, reading, details) {
        const key = [expression, reading];

        const cacheValue = this._cache.get(key);
        if (typeof cacheValue !== 'undefined') {
            const {audio, source} = cacheValue;
            const index = sources.indexOf(source);
            if (index >= 0) {
                return {audio, index};
            }
        }

        for (let i = 0, ii = sources.length; i < ii; ++i) {
            const source = sources[i];
            const info = await this._getAudioInfo(source, expression, reading, details);
            if (info === null) { continue; }

            let audio;
            try {
                switch (info.type) {
                    case 'url':
                        {
                            const {details: {url}} = info;
                            audio = await this.createAudio(url);
                        }
                        break;
                    case 'tts':
                        {
                            const {details: {text, voice}} = info;
                            audio = this.createTextToSpeechAudio(text, voice);
                        }
                        break;
                    default:
                        throw new Error(`Unsupported type: ${info.type}`);
                }
            } catch (e) {
                continue;
            }

            this._cache.set(key, {audio, source});
            return {audio, index: i};
        }

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

    getFallbackAudio() {
        if (this._fallbackAudio === null) {
            this._fallbackAudio = new Audio('/mixed/mp3/button.mp3');
        }
        return this._fallbackAudio;
    }

    createAudio(url) {
        return new Promise((resolve, reject) => {
            const audio = new Audio(url);
            audio.addEventListener('loadeddata', () => {
                if (!this._isAudioValid(audio)) {
                    reject(new Error('Could not retrieve audio'));
                } else {
                    resolve(audio);
                }
            });
            audio.addEventListener('error', () => reject(audio.error));
        });
    }

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

    // Private

    async _getAudioInfo(source, expression, reading, details) {
        return await api.getDefinitionAudioInfo(source, expression, reading, details);
    }

    _isAudioValid(audio) {
        const duration = audio.duration;
        return (
            duration !== 5.694694 && // jpod101 invalid audio (Chrome)
            duration !== 5.720718 // jpod101 invalid audio (Firefox)
        );
    }

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