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
181
182
183
184
185
186
187
188
189
|
/*
* Copyright (C) 2024 Yomitan 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/>.
*/
import type {TextProcessor, ReadingNormalizer, BidirectionalConversionPreprocessor} from './language';
import type {LanguageTransformDescriptor} from './language-transformer';
import type {SafeAny} from './core';
export type IsTextLookupWorthyFunction = (text: string) => boolean;
type LanguageDescriptor<
TIso extends string,
TTextPreprocessorDescriptor extends TextProcessorDescriptor = Record<string, never>,
TTextPostprocessorDescriptor extends TextProcessorDescriptor = Record<string, never>,
> = {
iso: TIso;
iso639_3: string;
name: string;
exampleText: string;
/**
* An optional function which returns whether or not a given string may be translatable.
* This is used as a filter for several situations, such as whether the clipboard monitor
* window should activate when text is copied to the clipboard.
* If no value is provided, `true` is assumed for all inputs.
*/
isTextLookupWorthy?: IsTextLookupWorthyFunction;
readingNormalizer?: ReadingNormalizer;
textPreprocessors?: TTextPreprocessorDescriptor;
textPostprocessors?: TTextPostprocessorDescriptor;
languageTransforms?: LanguageTransformDescriptor;
};
type TextProcessorDescriptor = {
[key: string]: TextProcessor<SafeAny>;
};
type LanguageDescriptorObjectMap = {
[key in keyof AllTextProcessors]: LanguageDescriptor<
key,
AllTextProcessors[key] extends {pre: TextProcessorDescriptor} ? AllTextProcessors[key]['pre'] : Record<string, never>,
AllTextProcessors[key] extends {post: TextProcessorDescriptor} ? AllTextProcessors[key]['post'] : Record<string, never>
>;
};
export type LanguageDescriptorAny = LanguageDescriptorObjectMap[keyof LanguageDescriptorObjectMap];
type CapitalizationPreprocessors = {
capitalizeFirstLetter: TextProcessor<boolean>;
decapitalize: TextProcessor<boolean>;
};
/**
* This is a mapping of the iso tag to all of the text processors for that language.
* Any new language should be added to this object.
*/
type AllTextProcessors = {
ar: {
pre: {
removeArabicScriptDiacritics: TextProcessor<boolean>;
};
};
de: {
pre: CapitalizationPreprocessors & {
eszettPreprocessor: BidirectionalConversionPreprocessor;
};
};
el: {
pre: CapitalizationPreprocessors;
};
en: {
pre: CapitalizationPreprocessors;
};
es: {
pre: CapitalizationPreprocessors;
};
fa: {
pre: {
removeArabicScriptDiacritics: TextProcessor<boolean>;
};
};
fi: {
pre: CapitalizationPreprocessors;
};
fr: {
pre: CapitalizationPreprocessors;
};
grc: {
pre: CapitalizationPreprocessors & {
removeAlphabeticDiacritics: TextProcessor<boolean>;
};
};
hu: {
pre: CapitalizationPreprocessors;
};
id: {
pre: CapitalizationPreprocessors;
};
it: {
pre: CapitalizationPreprocessors;
};
la: {
pre: CapitalizationPreprocessors & {
removeAlphabeticDiacritics: TextProcessor<boolean>;
};
};
lo: Record<string, never>;
ja: {
pre: {
convertHalfWidthCharacters: TextProcessor<boolean>;
alphabeticToHiragana: TextProcessor<boolean>;
normalizeCombiningCharacters: TextProcessor<boolean>;
alphanumericWidthVariants: BidirectionalConversionPreprocessor;
convertHiraganaToKatakana: BidirectionalConversionPreprocessor;
collapseEmphaticSequences: TextProcessor<[collapseEmphatic: boolean, collapseEmphaticFull: boolean]>;
};
};
ko: {
pre: {
disassembleHangul: TextProcessor<boolean>;
};
post: {
reassembleHangul: TextProcessor<boolean>;
};
};
km: Record<string, never>;
mn: {
pre: CapitalizationPreprocessors;
};
nl: {
pre: CapitalizationPreprocessors;
};
pl: {
pre: CapitalizationPreprocessors;
};
pt: {
pre: CapitalizationPreprocessors;
};
ro: {
pre: CapitalizationPreprocessors & {
removeAlphabeticDiacritics: TextProcessor<boolean>;
};
};
ru: {
pre: CapitalizationPreprocessors & {
yoToE: TextProcessor<boolean>;
removeRussianDiacritics: TextProcessor<boolean>;
};
};
sga: {
pre: CapitalizationPreprocessors & {
removeAlphabeticDiacritics: TextProcessor<boolean>;
};
};
sh: {
pre: CapitalizationPreprocessors & {
removeSerboCroatianAccentMarks: TextProcessor<boolean>;
};
};
sq: {
pre: CapitalizationPreprocessors;
};
sv: {
pre: CapitalizationPreprocessors;
};
th: Record<string, never>;
tr: {
pre: CapitalizationPreprocessors;
};
vi: {
pre: CapitalizationPreprocessors & {
normalizeDiacritics: TextProcessor<'old' | 'new' | 'off'>;
};
};
yue: Record<string, never>;
zh: Record<string, never>;
};
|