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
|
/*
* 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/>.
*/
function jpIsKanji(c) {
const code = c.charCodeAt(0);
return code >= 0x4e00 && code < 0x9fb0 || code >= 0x3400 && code < 0x4dc0;
}
function jpIsKana(c) {
return wanakana.isKana(c);
}
function jpKatakanaToHiragana(text) {
let result = '';
for (const c of text) {
if (wanakana.isKatakana(c)) {
result += wanakana.toHiragana(c);
} else {
result += c;
}
}
return result;
}
function distributeFurigana(word, reading) {
reading = reading || wanakana.toHiragana(word);
function span(str, pred) {
let i = 0;
while (i < str.length && pred(str[i])) {
i++;
}
return [str.substring(0, i), str.substring(i)];
}
const isKanji = c => jpIsKanji(c) ||
c === '\u3005'; /* kurikaeshi */
const isKana = c => jpIsKana(c) ||
c === '\u30fc'; /* chouonpu */
function parse(word) {
const res = [];
while (word.length > 0) {
const c = word.charAt(0);
if (isKana(c)) {
const [text, rest] = span(word, isKana);
res.push({ type: 'kana', text });
word = rest;
} else if (isKanji(c)) {
const [text, rest] = span(word, isKanji);
res.push({ type: 'kanji', text });
word = rest;
} else return null;
}
return res;
}
const fallback = () => [{ text: word, furigana: reading }];
const parts = parse(word);
if (!parts) return fallback();
let parti = 0;
let readingi = 0;
const res = [];
let current = null;
function backtrack() {
parti--;
const prev = res.pop();
current = prev.furigana;
}
while (parti < parts.length) {
const part = parts[parti];
switch (part.type) {
case 'kana':
if (reading.startsWith(wanakana.toHiragana(part.text), readingi)) {
if (parti === parts.length - 1 && readingi !== reading.length - part.text.length) {
backtrack();
} else {
readingi += part.text.length;
res.push({ text: part.text });
parti++;
}
} else backtrack();
break;
case 'kanji':
current = current || '';
if (parti === parts.length - 1) {
// last part, consume all
current += reading.substring(readingi);
} else {
const nextText = parts[parti + 1].text;
const end = reading.indexOf(nextText, readingi + 1); // consume at least one character
if (end === -1) {
return fallback();
}
current += reading.substring(readingi, end);
readingi = end;
}
res.push({ text: part.text, furigana: current });
current = null;
parti++;
}
}
return res;
}
|