2016-03-20 17:52:27 +00:00
|
|
|
/*
|
|
|
|
* Copyright (C) 2016 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/>.
|
|
|
|
*/
|
|
|
|
|
2016-03-24 02:25:32 +00:00
|
|
|
|
2016-03-20 17:52:27 +00:00
|
|
|
class Translator {
|
2016-03-26 21:16:21 +00:00
|
|
|
constructor() {
|
2016-04-04 05:22:38 +00:00
|
|
|
this.loaded = false;
|
|
|
|
this.paths = {
|
|
|
|
rules: 'bg/data/rules.json',
|
|
|
|
edict: 'bg/data/edict.csv',
|
|
|
|
enamdict: 'bg/data/enamdict.csv',
|
|
|
|
kanjidic: 'bg/data/kanjidic.csv'
|
|
|
|
};
|
|
|
|
|
2016-04-02 19:56:47 +00:00
|
|
|
this.dictionary = new Dictionary();
|
|
|
|
this.deinflector = new Deinflector();
|
2016-03-26 21:16:21 +00:00
|
|
|
}
|
|
|
|
|
2016-04-04 05:22:38 +00:00
|
|
|
loadData(callback) {
|
|
|
|
if (this.loaded) {
|
2016-03-26 21:16:21 +00:00
|
|
|
callback();
|
|
|
|
return;
|
|
|
|
}
|
2016-03-20 17:52:27 +00:00
|
|
|
|
2016-04-02 19:56:47 +00:00
|
|
|
const pendingLoads = [];
|
2016-03-20 19:26:10 +00:00
|
|
|
for (const key of ['rules', 'edict', 'enamdict', 'kanjidic']) {
|
2016-04-02 19:56:47 +00:00
|
|
|
pendingLoads.push(key);
|
2016-04-04 05:22:38 +00:00
|
|
|
Translator.loadData(this.paths[key], (response) => {
|
2016-04-02 05:13:37 +00:00
|
|
|
switch (key) {
|
|
|
|
case 'rules':
|
|
|
|
this.deinflector.setRules(JSON.parse(response));
|
|
|
|
break;
|
|
|
|
case 'kanjidic':
|
|
|
|
this.dictionary.addKanjiData(Translator.parseCsv(response));
|
|
|
|
break;
|
|
|
|
case 'edict':
|
|
|
|
case 'enamdict':
|
2016-04-02 05:30:30 +00:00
|
|
|
this.dictionary.addTermData(Translator.parseCsv(response));
|
2016-04-02 05:13:37 +00:00
|
|
|
break;
|
|
|
|
}
|
2016-03-20 17:52:27 +00:00
|
|
|
|
2016-04-02 19:56:47 +00:00
|
|
|
pendingLoads.splice(pendingLoads.indexOf(key), 1);
|
|
|
|
if (pendingLoads.length === 0) {
|
2016-04-04 05:22:38 +00:00
|
|
|
this.loaded = true;
|
2016-04-02 05:13:37 +00:00
|
|
|
callback();
|
|
|
|
}
|
|
|
|
});
|
|
|
|
}
|
2016-03-20 17:52:27 +00:00
|
|
|
}
|
2016-03-21 01:45:37 +00:00
|
|
|
|
|
|
|
findTerm(text) {
|
2016-03-21 03:34:50 +00:00
|
|
|
const groups = {};
|
2016-03-25 03:20:46 +00:00
|
|
|
for (let i = text.length; i > 0; --i) {
|
2016-03-21 01:45:37 +00:00
|
|
|
const term = text.slice(0, i);
|
|
|
|
|
2016-03-23 03:17:11 +00:00
|
|
|
const dfs = this.deinflector.deinflect(term, t => {
|
|
|
|
const tags = [];
|
|
|
|
for (const d of this.dictionary.findTerm(t)) {
|
|
|
|
tags.push(d.tags);
|
|
|
|
}
|
|
|
|
|
|
|
|
return tags;
|
|
|
|
});
|
|
|
|
|
2016-03-21 03:34:50 +00:00
|
|
|
if (dfs === null) {
|
2016-03-21 01:45:37 +00:00
|
|
|
this.processTerm(groups, term);
|
|
|
|
} else {
|
2016-03-21 03:34:50 +00:00
|
|
|
for (const df of dfs) {
|
|
|
|
this.processTerm(groups, df.source, df.rules, df.root);
|
2016-03-21 01:45:37 +00:00
|
|
|
}
|
|
|
|
}
|
2016-03-24 01:12:33 +00:00
|
|
|
}
|
2016-03-21 01:45:37 +00:00
|
|
|
|
2016-03-24 01:12:33 +00:00
|
|
|
let results = [];
|
|
|
|
for (const key in groups) {
|
|
|
|
results.push(groups[key]);
|
|
|
|
}
|
2016-03-21 01:45:37 +00:00
|
|
|
|
2016-04-02 05:13:37 +00:00
|
|
|
results = results.sort((v1, v2) => {
|
|
|
|
const sl1 = v1.source.length;
|
|
|
|
const sl2 = v2.source.length;
|
|
|
|
if (sl1 > sl2) {
|
|
|
|
return -1;
|
|
|
|
} else if (sl1 < sl2) {
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
const p1 = v1.tags.indexOf('P') >= 0;
|
|
|
|
const p2 = v2.tags.indexOf('P') >= 0;
|
|
|
|
if (p1 && !p2) {
|
|
|
|
return -1;
|
|
|
|
} else if (!p1 && p2) {
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
const rl1 = v1.rules.length;
|
|
|
|
const rl2 = v2.rules.length;
|
|
|
|
if (rl1 < rl2) {
|
|
|
|
return -1;
|
|
|
|
} else if (rl2 > rl1) {
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
});
|
2016-03-21 01:45:37 +00:00
|
|
|
|
2016-03-24 01:12:33 +00:00
|
|
|
let length = 0;
|
|
|
|
for (const result of results) {
|
|
|
|
length = Math.max(length, result.source.length);
|
2016-03-21 03:34:50 +00:00
|
|
|
}
|
2016-03-24 01:12:33 +00:00
|
|
|
|
|
|
|
return {results: results, length: length};
|
2016-03-21 01:45:37 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
findKanji(text) {
|
2016-03-21 03:34:50 +00:00
|
|
|
let results = [];
|
|
|
|
|
|
|
|
const processed = {};
|
|
|
|
for (const c of text) {
|
|
|
|
if (!processed.has(c)) {
|
|
|
|
results = results.concat(this.dictionary.findKanji(c));
|
|
|
|
processed[c] = true;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
return results;
|
2016-03-21 01:45:37 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
processTerm(groups, source, rules=[], root='') {
|
2016-03-23 03:02:41 +00:00
|
|
|
for (const entry of this.dictionary.findTerm(root || source)) {
|
2016-03-26 03:54:04 +00:00
|
|
|
if (entry.id in groups) {
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
2016-03-23 03:02:41 +00:00
|
|
|
groups[entry.id] = {
|
|
|
|
expression: entry.expression,
|
|
|
|
reading: entry.reading,
|
|
|
|
glossary: entry.glossary,
|
|
|
|
tags: entry.tags,
|
2016-03-21 03:34:50 +00:00
|
|
|
source: source,
|
2016-03-23 03:02:41 +00:00
|
|
|
rules: rules
|
|
|
|
};
|
2016-03-21 03:34:50 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2016-04-02 05:13:37 +00:00
|
|
|
static loadData(url, callback) {
|
|
|
|
const xhr = new XMLHttpRequest();
|
|
|
|
xhr.addEventListener('load', () => callback(xhr.responseText));
|
|
|
|
xhr.open('GET', chrome.extension.getURL(url), true);
|
|
|
|
xhr.send();
|
|
|
|
}
|
2016-03-21 03:34:50 +00:00
|
|
|
|
2016-04-02 05:13:37 +00:00
|
|
|
static parseCsv(data) {
|
|
|
|
const result = [];
|
2016-04-02 05:30:30 +00:00
|
|
|
for (const row of data.split('\n')) {
|
2016-04-02 19:56:47 +00:00
|
|
|
if (row.length > 0) {
|
|
|
|
result.push(row.split('\t'));
|
|
|
|
}
|
2016-03-21 03:34:50 +00:00
|
|
|
}
|
|
|
|
|
2016-04-02 05:13:37 +00:00
|
|
|
return result;
|
2016-03-21 01:45:37 +00:00
|
|
|
}
|
2016-03-20 17:52:27 +00:00
|
|
|
}
|