Coverage for src / wiktextract / extractor / en / type_utils.py: 100%
174 statements
« prev ^ index » next coverage.py v7.14.0, created at 2026-05-11 04:48 +0000
1from typing import (
2 Sequence,
3 TypedDict,
4 Union,
5)
7from wikitextprocessor.core import TemplateArgs
10class AltOf(TypedDict, total=False):
11 word: str
12 extra: str
15class LinkageData(TypedDict, total=False):
16 alt: str
17 english: str # DEPRECATED in favor of "translation"
18 translation: str
19 extra: str
20 qualifier: str
21 raw_tags: list[str]
22 roman: str
23 ruby: Union[list[Sequence[str]], list[tuple[str, str]]]
24 sense: str
25 source: str
26 tags: list[str]
27 taxonomic: str
28 topics: list[str]
29 urls: list[str]
30 word: str
33class ExampleData(TypedDict, total=False):
34 english: str # DEPRECATED in favor of "translation"
35 translation: str
36 bold_translation_offsets: list[tuple[int, int]]
37 note: str
38 ref: str
39 roman: str
40 bold_roman_offsets: list[tuple[int, int]]
41 ruby: Union[list[tuple[str, str]], list[Sequence[str]]]
42 text: str
43 bold_text_offsets: list[tuple[int, int]]
44 type: str
45 literal_meaning: str
46 bold_literal_offsets: list[tuple[int, int]]
47 tags: list[str]
48 raw_tags: list[str]
51class FormOf(TypedDict, total=False):
52 word: str
53 extra: str
54 roman: str
57LinkData = list[Sequence[str]]
60class PlusObjTemplateData(TypedDict, total=False):
61 tags: list[str]
62 words: list[str]
63 meaning: str
66ExtraTemplateData = Union[PlusObjTemplateData]
69class TemplateData(TypedDict, total=False):
70 args: TemplateArgs
71 expansion: str
72 name: str
73 extra_data: ExtraTemplateData
76class DescendantData(TypedDict, total=False):
77 lang_code: str
78 lang: str
79 word: str
80 roman: str
81 tags: list[str]
82 raw_tags: list[str]
83 descendants: list["DescendantData"]
84 ruby: list[tuple[str, ...]]
85 sense: str
88class FormData(TypedDict, total=False):
89 form: str
90 head_nr: int
91 ipa: str
92 roman: str
93 ruby: Union[list[tuple[str, str]], list[Sequence[str]]]
94 source: str
95 tags: list[str]
96 raw_tags: list[str]
97 topics: list[str]
98 links: list[tuple[str, str]]
101class Hyphenation(TypedDict, total=False):
102 parts: list[str]
103 tags: list[str]
106SoundData = TypedDict(
107 "SoundData",
108 {
109 "audio": str,
110 "audio-ipa": str,
111 "enpr": str,
112 "form": str,
113 "hangeul": str,
114 "homophone": str,
115 "ipa": str,
116 "mp3_url": str,
117 "note": str,
118 "ogg_url": str,
119 "other": str,
120 "rhymes": str,
121 "tags": list[str],
122 "text": str,
123 "topics": list[str],
124 "zh-pron": str,
125 },
126 total=False,
127)
130class TranslationData(TypedDict, total=False):
131 alt: str
132 lang_code: str
133 code: str # DEPRECATED in favor of lang_code
134 english: str # DEPRECATED in favor of "translation"
135 translation: str
136 lang: str
137 note: str
138 roman: str
139 sense: str
140 tags: list[str]
141 taxonomic: str
142 topics: list[str]
143 word: str
146# Xxyzz's East Asian etymology example data
147class EtymologyExample(TypedDict, total=False):
148 english: str # DEPRECATED in favor of "translation"
149 translation: str
150 raw_tags: list[str]
151 ref: str
152 roman: str
153 tags: list[str]
154 text: str
155 type: str
158class ReferenceData(TypedDict, total=False):
159 text: str
160 refn: str
163class AttestationData(TypedDict, total=False):
164 date: str
165 references: list[ReferenceData]
168class SenseData(TypedDict, total=False):
169 alt_of: list[AltOf]
170 antonyms: list[LinkageData]
171 categories: list[str]
172 compound_of: list[AltOf]
173 coordinate_terms: list[LinkageData]
174 examples: list[ExampleData]
175 form_of: list[FormOf]
176 glosses: list[str]
177 head_nr: int
178 holonyms: list[LinkageData]
179 hypernyms: list[LinkageData]
180 hyponyms: list[LinkageData]
181 instances: list[LinkageData]
182 links: list[LinkData]
183 meronyms: list[LinkageData]
184 qualifier: str
185 raw_glosses: list[str]
186 related: list[LinkageData] # also used for "alternative forms"
187 senseid: list[str]
188 synonyms: list[LinkageData]
189 tags: list[str]
190 taxonomic: str
191 topics: list[str]
192 wikidata: list[str]
193 wikipedia: list[str]
194 attestations: list[AttestationData]
197class WordData(TypedDict, total=False):
198 abbreviations: list[LinkageData]
199 alt_of: list[AltOf]
200 antonyms: list[LinkageData]
201 categories: list[str]
202 coordinate_terms: list[LinkageData]
203 derived: list[LinkageData]
204 descendants: list[DescendantData]
205 etymology_examples: list[EtymologyExample]
206 etymology_number: int
207 etymology_templates: list[TemplateData]
208 etymology_text: str
209 form_of: list[FormOf]
210 forms: list[FormData]
211 head_templates: list[TemplateData]
212 holonyms: list[LinkageData]
213 hyphenation: list[str] # Being deprecated
214 hyphenations: list[Hyphenation]
215 hypernyms: list[LinkageData]
216 hyponyms: list[LinkageData]
217 inflection_templates: list[TemplateData]
218 info_templates: list[TemplateData]
219 instances: list[LinkageData]
220 lang: str
221 lang_code: str
222 literal_meaning: str
223 meronyms: list[LinkageData]
224 original_title: str
225 pos: str
226 proverbs: list[LinkageData]
227 redirects: list[str]
228 related: list[LinkageData]
229 senses: list[SenseData]
230 sounds: list[SoundData]
231 synonyms: list[LinkageData]
232 translations: list[TranslationData]
233 troponyms: list[LinkageData]
234 wikidata: list[str]
235 wikipedia: list[str]
236 word: str
237 anagrams: list[LinkageData]