blob: a695d2e7f8dd341a02005228fef4c72a289f1c1b (
plain) (
blame)
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
|
package com.yahoo.language.simple;
import com.yahoo.language.process.TokenScript;
/**
* @author mariusarhaug
*/
class SimpleTokenScript {
static TokenScript valueOf(int codePoint) {
return switch(Character.UnicodeScript.of(codePoint))
{
case COMMON -> TokenScript.COMMON;
case LATIN -> TokenScript.LATIN;
case GREEK -> TokenScript.GREEK;
case CYRILLIC -> TokenScript.CYRILLIC;
case ARMENIAN -> TokenScript.ARMENIAN;
case HEBREW -> TokenScript.HEBREW;
case ARABIC -> TokenScript.ARABIC;
case SYRIAC -> TokenScript.SYRIAC;
case THAANA -> TokenScript.THAANA;
case DEVANAGARI -> TokenScript.DEVANAGARI;
case GURMUKHI -> TokenScript.GURMUKHI;
case GUJARATI -> TokenScript.GUJARATI;
case ORIYA -> TokenScript.ORIYA;
case TAMIL -> TokenScript.TAMIL;
case TELUGU -> TokenScript.TELUGU;
case KANNADA -> TokenScript.KANNADA;
case MALAYALAM -> TokenScript.MALAYALAM;
case SINHALA -> TokenScript.SINHALA;
case THAI -> TokenScript.THAI;
case LAO -> TokenScript.LAO;
case TIBETAN -> TokenScript.TIBETAN;
case MYANMAR -> TokenScript.MYANMAR;
case GEORGIAN -> TokenScript.GEORGIAN;
case HANGUL -> TokenScript.HANGUL;
case ETHIOPIC -> TokenScript.ETHIOPIC;
case CHEROKEE -> TokenScript.CHEROKEE;
case OGHAM -> TokenScript.OGHAM;
case RUNIC -> TokenScript.RUNIC;
case KHMER -> TokenScript.KHMER;
case MONGOLIAN -> TokenScript.MONGOLIAN;
case HIRAGANA -> TokenScript.HIRAGANA;
case KATAKANA -> TokenScript.KATAKANA;
case HAN -> TokenScript.HAN;
case YI -> TokenScript.YI;
case GOTHIC -> TokenScript.GOTHIC;
case DESERET -> TokenScript.DESERET;
case INHERITED -> TokenScript.INHERITED;
case TAGALOG -> TokenScript.TAGALOG;
case HANUNOO -> TokenScript.HANUNOO;
case BUHID -> TokenScript.BUHID;
case TAGBANWA -> TokenScript.TAGBANWA;
case LIMBU -> TokenScript.LIMBU;
case UGARITIC -> TokenScript.UGARITIC;
case SHAVIAN -> TokenScript.SHAVIAN;
case OSMANYA -> TokenScript.OSMANYA;
case CYPRIOT -> TokenScript.CYPRIOT;
case BRAILLE -> TokenScript.BRAILLE;
case BUGINESE -> TokenScript.BUGINESE;
case COPTIC -> TokenScript.COPTIC;
case GLAGOLITIC -> TokenScript.GLAGOLITIC;
case KHAROSHTHI -> TokenScript.KHAROSHTHI;
case TIFINAGH -> TokenScript.TIFINAGH;
default -> TokenScript.UNKNOWN;
};
}
}
|
