2 files changed, 449 insertions, 0 deletions
diff --git a/ext/js/media/audio-downloader.js b/ext/js/media/audio-downloader.js
new file mode 100644
index 00000000..4e77419b
--- /dev/null
+++ b/ext/js/media/audio-downloader.js
@@ -0,0 +1,317 @@
+/*
+ * Copyright (C) 2017-2021  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
+ * JsonSchemaValidator
+ * NativeSimpleDOMParser
+ * SimpleDOMParser
+ */
+
+class AudioDownloader {
+    constructor({japaneseUtil, requestBuilder}) {
+        this._japaneseUtil = japaneseUtil;
+        this._requestBuilder = requestBuilder;
+        this._customAudioListSchema = null;
+        this._schemaValidator = null;
+        this._getInfoHandlers = new Map([
+            ['jpod101', this._getInfoJpod101.bind(this)],
+            ['jpod101-alternate', this._getInfoJpod101Alternate.bind(this)],
+            ['jisho', this._getInfoJisho.bind(this)],
+            ['text-to-speech', this._getInfoTextToSpeech.bind(this)],
+            ['text-to-speech-reading', this._getInfoTextToSpeechReading.bind(this)],
+            ['custom', this._getInfoCustom.bind(this)]
+        ]);
+    }
+
+    async getExpressionAudioInfoList(source, expression, reading, details) {
+        const handler = this._getInfoHandlers.get(source);
+        if (typeof handler === 'function') {
+            try {
+                return await handler(expression, reading, details);
+            } catch (e) {
+                // NOP
+            }
+        }
+        return [];
+    }
+
+    async downloadExpressionAudio(sources, expression, reading, details) {
+        for (const source of sources) {
+            const infoList = await this.getExpressionAudioInfoList(source, expression, reading, details);
+            for (const info of infoList) {
+                switch (info.type) {
+                    case 'url':
+                        try {
+                            return await this._downloadAudioFromUrl(info.url, source);
+                        } catch (e) {
+                            // NOP
+                        }
+                        break;
+                }
+            }
+        }
+
+        throw new Error('Could not download audio');
+    }
+
+    // Private
+
+    _normalizeUrl(url, base) {
+        return new URL(url, base).href;
+    }
+
+    async _getInfoJpod101(expression, reading) {
+        let kana = reading;
+        let kanji = expression;
+
+        if (!kana && this._japaneseUtil.isStringEntirelyKana(kanji)) {
+            kana = kanji;
+            kanji = null;
+        }
+
+        const params = [];
+        if (kanji) {
+            params.push(`kanji=${encodeURIComponent(kanji)}`);
+        }
+        if (kana) {
+            params.push(`kana=${encodeURIComponent(kana)}`);
+        }
+
+        const url = `https://assets.languagepod101.com/dictionary/japanese/audiomp3.php?${params.join('&')}`;
+        return [{type: 'url', url}];
+    }
+
+    async _getInfoJpod101Alternate(expression, reading) {
+        const fetchUrl = 'https://www.japanesepod101.com/learningcenter/reference/dictionary_post';
+        const data = `post=dictionary_reference&match_type=exact&search_query=${encodeURIComponent(expression)}&vulgar=true`;
+        const response = await this._requestBuilder.fetchAnonymous(fetchUrl, {
+            method: 'POST',
+            mode: 'cors',
+            cache: 'default',
+            credentials: 'omit',
+            redirect: 'follow',
+            referrerPolicy: 'no-referrer',
+            headers: {
+                'Content-Type': 'application/x-www-form-urlencoded'
+            },
+            body: data
+        });
+        const responseText = await response.text();
+
+        const dom = this._createSimpleDOMParser(responseText);
+        for (const row of dom.getElementsByClassName('dc-result-row')) {
+            try {
+                const audio = dom.getElementByTagName('audio', row);
+                if (audio === null) { continue; }
+
+                const source = dom.getElementByTagName('source', audio);
+                if (source === null) { continue; }
+
+                let url = dom.getAttribute(source, 'src');
+                if (url === null) { continue; }
+
+                const htmlReadings = dom.getElementsByClassName('dc-vocab_kana');
+                if (htmlReadings.length === 0) { continue; }
+
+                const htmlReading = dom.getTextContent(htmlReadings[0]);
+                if (htmlReading && (!reading || reading === htmlReading)) {
+                    url = this._normalizeUrl(url, response.url);
+                    return [{type: 'url', url}];
+                }
+            } catch (e) {
+                // NOP
+            }
+        }
+
+        throw new Error('Failed to find audio URL');
+    }
+
+    async _getInfoJisho(expression, reading) {
+        const fetchUrl = `https://jisho.org/search/${expression}`;
+        const response = await this._requestBuilder.fetchAnonymous(fetchUrl, {
+            method: 'GET',
+            mode: 'cors',
+            cache: 'default',
+            credentials: 'omit',
+            redirect: 'follow',
+            referrerPolicy: 'no-referrer'
+        });
+        const responseText = await response.text();
+
+        const dom = this._createSimpleDOMParser(responseText);
+        try {
+            const audio = dom.getElementById(`audio_${expression}:${reading}`);
+            if (audio !== null) {
+                const source = dom.getElementByTagName('source', audio);
+                if (source !== null) {
+                    let url = dom.getAttribute(source, 'src');
+                    if (url !== null) {
+                        url = this._normalizeUrl(url, response.url);
+                        return [{type: 'url', url}];
+                    }
+                }
+            }
+        } catch (e) {
+            // NOP
+        }
+
+        throw new Error('Failed to find audio URL');
+    }
+
+    async _getInfoTextToSpeech(expression, reading, {textToSpeechVoice}) {
+        if (!textToSpeechVoice) {
+            throw new Error('No voice');
+        }
+        return [{type: 'tts', text: expression, voice: textToSpeechVoice}];
+    }
+
+    async _getInfoTextToSpeechReading(expression, reading, {textToSpeechVoice}) {
+        if (!textToSpeechVoice) {
+            throw new Error('No voice');
+        }
+        return [{type: 'tts', text: reading || expression, voice: textToSpeechVoice}];
+    }
+
+    async _getInfoCustom(expression, reading, {customSourceUrl, customSourceType}) {
+        if (typeof customSourceUrl !== 'string') {
+            throw new Error('No custom URL defined');
+        }
+        const data = {expression, reading};
+        const url = customSourceUrl.replace(/\{([^}]*)\}/g, (m0, m1) => (Object.prototype.hasOwnProperty.call(data, m1) ? `${data[m1]}` : m0));
+
+        switch (customSourceType) {
+            case 'json':
+                return await this._getInfoCustomJson(url);
+            default:
+                return [{type: 'url', url}];
+        }
+    }
+
+    async _getInfoCustomJson(url) {
+        const response = await this._requestBuilder.fetchAnonymous(url, {
+            method: 'GET',
+            mode: 'cors',
+            cache: 'default',
+            credentials: 'omit',
+            redirect: 'follow',
+            referrerPolicy: 'no-referrer'
+        });
+
+        if (!response.ok) {
+            throw new Error(`Invalid response: ${response.status}`);
+        }
+
+        const responseJson = await response.json();
+
+        const schema = await this._getCustomAudioListSchema();
+        if (this._schemaValidator === null) {
+            this._schemaValidator = new JsonSchemaValidator();
+        }
+        this._schemaValidator.validate(responseJson, schema);
+
+        const results = [];
+        for (const {url: url2, name} of responseJson.audioSources) {
+            const info = {type: 'url', url: url2};
+            if (typeof name === 'string') { info.name = name; }
+            results.push(info);
+        }
+        return results;
+    }
+
+    async _downloadAudioFromUrl(url, source) {
+        const response = await this._requestBuilder.fetchAnonymous(url, {
+            method: 'GET',
+            mode: 'cors',
+            cache: 'default',
+            credentials: 'omit',
+            redirect: 'follow',
+            referrerPolicy: 'no-referrer'
+        });
+
+        if (!response.ok) {
+            throw new Error(`Invalid response: ${response.status}`);
+        }
+
+        const arrayBuffer = await response.arrayBuffer();
+
+        if (!await this._isAudioBinaryValid(arrayBuffer, source)) {
+            throw new Error('Could not retrieve audio');
+        }
+
+        const data = this._arrayBufferToBase64(arrayBuffer);
+        const contentType = response.headers.get('Content-Type');
+        return {data, contentType};
+    }
+
+    async _isAudioBinaryValid(arrayBuffer, source) {
+        switch (source) {
+            case 'jpod101':
+            {
+                const digest = await this._arrayBufferDigest(arrayBuffer);
+                switch (digest) {
+                    case 'ae6398b5a27bc8c0a771df6c907ade794be15518174773c58c7c7ddd17098906': // Invalid audio
+                        return false;
+                    default:
+                        return true;
+                }
+            }
+            default:
+                return true;
+        }
+    }
+
+    async _arrayBufferDigest(arrayBuffer) {
+        const hash = new Uint8Array(await crypto.subtle.digest('SHA-256', new Uint8Array(arrayBuffer)));
+        let digest = '';
+        for (const byte of hash) {
+            digest += byte.toString(16).padStart(2, '0');
+        }
+        return digest;
+    }
+
+    _arrayBufferToBase64(arrayBuffer) {
+        return btoa(String.fromCharCode(...new Uint8Array(arrayBuffer)));
+    }
+
+    _createSimpleDOMParser(content) {
+        if (typeof NativeSimpleDOMParser !== 'undefined' && NativeSimpleDOMParser.isSupported()) {
+            return new NativeSimpleDOMParser(content);
+        } else if (typeof SimpleDOMParser !== 'undefined' && SimpleDOMParser.isSupported()) {
+            return new SimpleDOMParser(content);
+        } else {
+            throw new Error('DOM parsing not supported');
+        }
+    }
+
+    async _getCustomAudioListSchema() {
+        let schema = this._customAudioListSchema;
+        if (schema === null) {
+            const url = chrome.runtime.getURL('/data/schemas/custom-audio-list-schema.json');
+            const response = await fetch(url, {
+                method: 'GET',
+                mode: 'no-cors',
+                cache: 'default',
+                credentials: 'omit',
+                redirect: 'follow',
+                referrerPolicy: 'no-referrer'
+            });
+            schema = await response.json();
+            this._customAudioListSchema = schema;
+        }
+        return schema;
+    }
+}
diff --git a/ext/js/media/media-utility.js b/ext/js/media/media-utility.js
new file mode 100644
index 00000000..b4fbe04d
--- /dev/null
+++ b/ext/js/media/media-utility.js
@@ -0,0 +1,132 @@
+/*
+ * 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/>.
+ */
+
+/**
+ * MediaUtility is a class containing helper methods related to media processing.
+ */
+class MediaUtility {
+    /**
+     * Gets the file extension of a file path. URL search queries and hash
+     * fragments are not handled.
+     * @param path The path to the file.
+     * @returns The file extension, including the '.', or an empty string
+     *   if there is no file extension.
+     */
+    getFileNameExtension(path) {
+        const match = /\.[^./\\]*$/.exec(path);
+        return match !== null ? match[0] : '';
+    }
+
+    /**
+     * Gets an image file's media type using a file path.
+     * @param path The path to the file.
+     * @returns The media type string if it can be determined from the file path,
+     *   otherwise null.
+     */
+    getImageMediaTypeFromFileName(path) {
+        switch (this.getFileNameExtension(path).toLowerCase()) {
+            case '.apng':
+                return 'image/apng';
+            case '.bmp':
+                return 'image/bmp';
+            case '.gif':
+                return 'image/gif';
+            case '.ico':
+            case '.cur':
+                return 'image/x-icon';
+            case '.jpg':
+            case '.jpeg':
+            case '.jfif':
+            case '.pjpeg':
+            case '.pjp':
+                return 'image/jpeg';
+            case '.png':
+                return 'image/png';
+            case '.svg':
+                return 'image/svg+xml';
+            case '.tif':
+            case '.tiff':
+                return 'image/tiff';
+            case '.webp':
+                return 'image/webp';
+            default:
+                return null;
+        }
+    }
+
+    /**
+     * Gets the file extension for a corresponding media type.
+     * @param mediaType The media type to use.
+     * @returns A file extension including the dot for the media type,
+     *   otherwise null.
+     */
+    getFileExtensionFromImageMediaType(mediaType) {
+        switch (mediaType) {
+            case 'image/apng':
+                return '.apng';
+            case 'image/bmp':
+                return '.bmp';
+            case 'image/gif':
+                return '.gif';
+            case 'image/x-icon':
+                return '.ico';
+            case 'image/jpeg':
+                return '.jpeg';
+            case 'image/png':
+                return '.png';
+            case 'image/svg+xml':
+                return '.svg';
+            case 'image/tiff':
+                return '.tiff';
+            case 'image/webp':
+                return '.webp';
+            default:
+                return null;
+        }
+    }
+
+    /**
+     * Gets the file extension for a corresponding media type.
+     * @param mediaType The media type to use.
+     * @returns A file extension including the dot for the media type,
+     *   otherwise null.
+     */
+    getFileExtensionFromAudioMediaType(mediaType) {
+        switch (mediaType) {
+            case 'audio/mpeg':
+            case 'audio/mp3':
+                return '.mp3';
+            case 'audio/mp4':
+                return '.mp4';
+            case 'audio/ogg':
+            case 'audio/vorbis':
+                return '.ogg';
+            case 'audio/vnd.wav':
+            case 'audio/wave':
+            case 'audio/wav':
+            case 'audio/x-wav':
+            case 'audio/x-pn-wav':
+                return '.wav';
+            case 'audio/flac':
+                return '.flac';
+            case 'audio/webm':
+                return '.webm';
+            default:
+                return null;
+        }
+    }
+}