summaryrefslogtreecommitdiff
path: root/ext/mixed/js/audio.js
blob: 8198f5ec32c535a836a9d4d3d6a0120ddca818df (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
/*
 * Copyright (C) 2019  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 <http://www.gnu.org/licenses/>.
 */


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 = {};
        for (const group of m[1].split('&')) {
            const sep = group.indexOf('=');
            if (sep < 0) { continue; }
            searchParameters[decodeURIComponent(group.substr(0, sep))] = decodeURIComponent(group.substr(sep + 1));
        }

        if (!searchParameters.text) { return null; }

        const voice = audioGetTextToSpeechVoice(searchParameters.voice);
        if (voice === null) { return null; }

        return new TextToSpeechAudio(searchParameters.text, voice);
    }

}

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 && cache.hasOwnProperty(expression)) {
        return cache[key];
    }

    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 {
            const audio = await audioGetFromUrl(url, willDownload);
            if (willDownload) {
                // AnkiConnect handles downloading URLs into cards
                audio = null
            }
            const result = {audio, url, source};
            if (cache !== null) {
                cache[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;