Coverage for src / wiktextract / extractor / zh / tags.py: 98%
35 statements
« prev ^ index » next coverage.py v7.12.0, created at 2025-12-05 07:46 +0000
1from .models import WordEntry
2from .topics import LABEL_TOPICS
4GENDER_TAGS: dict[str, str] = {
5 "陰性": "feminine",
6 "阴性": "feminine",
7 "陰性形式": "feminine",
8 "陰性等價詞": "feminine",
9 "陽性": "masculine",
10 "陽性形式": "masculine",
11 "中性": "neuter",
12 "中性形式": "neuter",
13}
15NUMBER_TAGS: dict[str, str | list[str]] = {
16 "單數": "singular",
17 "单数": "singular",
18 "複數": "plural",
19 "复数": "plural",
20 "定單數": ["definite", "singular"],
21 "定单数": ["definite", "singular"],
22 "不定單數": ["indefinite", "singular"],
23 "不定单数": ["indefinite", "singular"],
24 "不定複數": ["indefinite", "plural"],
25 "不定复数": ["indefinite", "plural"],
26 "定複數": ["definite", "plural"],
27 "斜格複數": ["oblique", "plural"],
28 "主格單數": ["nominative", "singular"],
29 "主格複數": ["nominative", "plural"],
30 "屬格單數": ["genitive", "singular"],
31 "屬格複數": ["genitive", "plural"],
32 "陰性單數": ["feminine", "singular"],
33 "陽性單數": ["masculine", "singular"],
34 "陰性複數": ["feminine", "plural"],
35 "陽性複數": ["masculine", "plural"],
36 "中性複數": ["neuter", "plural"],
37 "中性單數": ["neuter", "singular"],
38 "賓格單數": ["accusative", "singular"],
39 "賓格複數": ["accusative", "plural"],
40 "無複數": "no-plural",
41 # Template:nb-noun-m1
42 "定指單數": ["definite", "singular"],
43 "定指複數": ["definite", "plural"],
44 "複": "plural",
45 "單": "singular",
46}
48# https://en.wikipedia.org/wiki/Count_noun
49COUNT_TAGS: dict[str, str] = {
50 "可數": "countable",
51 "不可數": "uncountable",
52}
54OTHER_TAGS: dict[str, str] = {
55 "指小詞": "diminutive",
56 "指小": "diminutive",
57 "變格類型": "declension-pattern-of",
58 "屬格": "genitive",
59 "部分格": "partitive",
60 "個人": "person",
61 "無屈折": "indeclinable",
62 "諺文": "hangeul",
63 "漢字": "hanja",
64 # Template:cs-proper noun
65 "相關形容詞": ["relational", "adjective"],
66 "關係形容詞": ["relational", "adjective"],
67 "居民稱謂詞": "demonym",
68 "女性居民稱謂詞": ["feminine", "demonym"],
69 "定賓格": ["definite", "accusative"],
70 "定宾格": ["definite", "accusative"],
71 "拉丁字母拼寫": "romanization",
72 "定指賓格": ["definite", "accusative"],
73 "前元音和諧變體": "front-vowel-harmony",
74 # Template:zh-forms
75 "正體": "Standard-Chinese",
76 "繁體": "Traditional-Chinese",
77 "簡體": "Simplified-Chinese",
78 "異體": "alternative",
79 "仿譯詞": "calque",
80 "貶稱詞": "pejorative",
81 # Template:ms-noun
82 "爪夷文": "Jawi",
83 "非正式第一人稱屬格": ["informal", "first-person", "genitive"],
84 "不禮貌第二人稱屬格": ["impolite", "second-person", "genitive"],
85 "第三人稱屬格": ["third-person", "genitive"],
86 "印尼語": "Indonesian",
87 "姓氏": "surname",
88}
90VERB_TAGS: dict[str, str] = {
91 "及物": "transitive",
92 "不及物": "intransitive",
93 "动宾结构": "verb-object",
94 "非完": "imperfective",
95 "完": "perfective",
96 "強變化": "strong",
97 "動名詞": "supine",
98 "命令式": "imperative",
99 # Template:ar-verb
100 "第I類": "form-i",
101 "第II類": "form-ii",
102 "第III類": "form-iii",
103 "第IV類": "form-iv",
104 "第V類": "form-v",
105 "第VI類": "form-vi",
106 "第VII類": "form-vii",
107 "第IX類": "form-ix",
108 "第X類": "form-x",
109 "第XII類": "form-xii",
110 "第XIII類": "form-xiii",
111 "第XIV類": "form-xiv",
112 "第XV類": "form-xv",
113 "第Iq類": "form-iq",
114 "第IIq類": "form-iiq",
115 "第IIIq類": "form-iiiq",
116 "第IVq類": "form-ivq",
117 # Module:Jpan-headword
118 "他動詞": "transitive",
119 "自動詞": "intransitive",
120 "自、他動詞": ["transitive", "intransitive"],
121 "五段": "godan",
122 "一段": "ichidan",
123 "サ行": "suru",
124 "カ行": "kuru",
125 "イ形": "-i",
126 "ナ形": "-na",
127 "四段": "yodan",
128 "二段": "nidan",
129 "ラ行": "-ri",
130 "ナリ": "-nari",
131 "タリ": "-tari",
132 # Template:ja-conj-bungo
133 "語幹形態": "stem",
134 "對比連接詞": ["contrastive", "conjunction"],
135 "因果連接詞": ["causative", "conjunction"],
136 "條件連接詞": ["conditional", "conjunction"],
137 "過去式 (第一手消息)": "past",
138 "過去式 (第二手消息)": "past",
139 "完成式 (自覺動作)": "perfect",
140 "完成式 (自然事件)": ["perfect", "natural"],
141 "完成進行式": ["perfect", "continuative"],
142 "意志形": "volitional",
143 "副詞": "adverbial",
144 "無助動詞": "no-auxiliary",
145 "有助動詞": "auxiliary",
146 # Template:ja-na
147 "簡體否定": ["informal", "negative"],
148 "簡體過去": ["informal", "past"],
149 "簡體過去否定": ["informal", "past", "negative"],
150 "敬體": "formal",
151 "敬體否定": ["formal", "negative"],
152 "敬體過去": ["formal", "past"],
153 "敬體過去否定": ["formal", "past", "negative"],
154 "連接形": "conjunctive",
155 "暫定形": "provisional",
156 "推量形": "volitional",
157 "連用形": "adverbial",
158 "程度形": "degree",
159}
161# https://en.wikipedia.org/wiki/Japanese_grammar#Stem_forms
162JA_STEM_FORMS: dict[str, str] = {
163 "未然形": "imperfective",
164 "連用形": "continuative",
165 "終止形": "terminal",
166 "連體形": "attributive",
167 "連体形": "attributive",
168 "假定形": "hypothetical",
169 "仮定形": "hypothetical",
170 "命令形": "imperative",
171 "已然形": "realis",
172}
174# https://en.wikipedia.org/wiki/Voice_(grammar)
175VOICE_TAGS: dict[str, str | list[str]] = {
176 "被動形": "passive",
177 "使役形": "causative",
178 "可能形": "potential",
179 "意志形": "volitional",
180 "否定形": "negative",
181 "否定連用形": ["negative", "continuative"],
182 "尊敬形": "formal",
183 "完成形": "perfective",
184 "接續形": "conjunctive",
185 "條件形": ["hypothetical", "conditional"],
186}
188COMPARISON_TAGS: dict[str, str] = {
189 # https://en.wikipedia.org/wiki/Comparison_(grammar)
190 "原级": "positive",
191 "比較級": "comparative",
192 "最高級": "superlative",
193}
195TENSE_TAGS = {
196 "過去時": "preterite",
197 "過去式": "past",
198 "過去分詞": ["past", "participle"],
199 "現在時": "present",
200 "第三人稱單數現在時": ["third-person", "singular", "present"],
201 "助動詞": "auxiliary",
202 # Template:de-verb
203 "弱變化": "weak",
204 "弱变化": "weak",
205 "第三人稱單數簡單現在時": ["third-person", "singular", "present"],
206 "現在分詞": ["present", "participle"],
207 "一般過去時及過去分詞": ["past", "participle"],
208 # Template:it-verb
209 "第一人稱單數 現在時": ["first-person", "singular", "present"],
210 "第一人稱單數 先過去時": ["first-person", "singular", "past", "historic"],
211 # Template:de-adj
212 "強變化主格陽性單數": ["strong", "nominative", "masculine", "singular"],
213 # Template:la-verb
214 "现在时不定式": ["present", "infinitive"],
215 "完成时主动式": ["perfect", "active"],
216 "目的动名词": "supine",
217 # Template:ar-verb
218 "非過去時": "non-past",
219 "動詞性名詞": "noun-from-verb",
220 "主動分詞": ["active", "participle"],
221 "被動分詞": ["passive", "participle"],
222 # Template:it-verb
223 # https://zh.wiktionary.org/wiki/Module:It-headword
224 "第一人稱單數現在時": ["first-person", "singular", "present"],
225 "第一人稱單數先過去時": ["first-person", "singular", "past", "historic"],
226 "第三人稱單數先過去時": ["third-person", "singular", "past", "historic"],
227 "第一人稱單數過去分詞": ["first-person", "singular", "past", "participle"],
228 "第三人稱單數過去分詞": ["third-person", "singular", "past", "participle"],
229 "第一人稱單數未完成時": ["first-person", "singular", "imperfect"],
230 "第三人稱單數未完成時": ["third-person", "singular", "imperfect"],
231 "第一人稱單數未來時": ["first-person", "singular", "future"],
232 "第三人稱單數未來時": ["third-person", "singular", "future"],
233 "第一人稱單數現在時虛擬式": ["first-person", "singular", "subjunctive"],
234 "第三人稱單數現在時虛擬式": ["third-person", "singular", "subjunctive"],
235 "第一人稱單數未完成時虛擬式": [
236 "first-person",
237 "singular",
238 "imperfect",
239 "subjunctive",
240 ],
241 "第三人稱單數未完成時虛擬式": [
242 "third-person",
243 "singular",
244 "imperfect",
245 "subjunctive",
246 ],
247 # Template:es-verb
248 "第一人稱單數過去時": ["first-person", "singular", "past"],
249 # Template:ast-verb-ar
250 "第一人稱單數直陳現在時": [
251 "first-person",
252 "singular",
253 "indicative",
254 "present",
255 ],
256}
258GRAMMATICAL_TAGS: dict[str, str] = {
259 **GENDER_TAGS,
260 **NUMBER_TAGS,
261 **COUNT_TAGS,
262 **OTHER_TAGS,
263 **VERB_TAGS,
264 **JA_STEM_FORMS,
265 **VOICE_TAGS,
266 **COMPARISON_TAGS,
267 **TENSE_TAGS,
268}
270# https://zh.wiktionary.org/wiki/Template:Label
271# https://zh.wiktionary.org/wiki/Module:Labels/data
272# https://zh.wiktionary.org/wiki/Template:Qualifier
273# https://zh.wiktionary.org/wiki/Template:古
274# https://zh.wiktionary.org/wiki/Template:注释
275LABEL_TAGS = {
276 "棄用": "obsolete",
277 "弃用": "obsolete",
278 "比喻": "figuratively",
279 "古": "archaic",
280 "陽": "masculine",
281 "陰": "feminine",
282 "喻": "figuratively",
283 "書": "literary",
284 "口": "colloquial",
285 "俚": "slang",
286 "俗": "slang",
287 "方": "dialectal",
288 "废": "obsolete",
289 "貶": "derogatory",
290 "罕": "rare",
291 "引": "broadly",
292 "現已罕用": "archaic",
293 # Module:Labels/data
294 "back slang": "slang",
295 "synecdochically": "synecdoche",
296 "不再自由造詞": "idiomatic",
297 "不及物": "intransitive",
298 "不可數": "uncountable",
299 "不定": "indefinite",
300 "不常見": "uncommon",
301 "不推薦使用": "proscribed",
302 "中性": "neuter",
303 "中間被動語態": "mediopassive",
304 "中間語態": "middle",
305 "主動語態": "active",
306 "主要用於否定": ["usually", "with-negation"],
307 "交互": "reciprocal",
308 "以單數形式": "singular",
309 "以複數形式": "in-plural",
310 "作定語": "attributive",
311 "作格": "ergative",
312 "作表語": "predicative",
313 "使役": "causative",
314 "俗語": "idiomatic",
315 "俚語": "slang",
316 "俚语": "slang",
317 "兒童用語": "childish",
318 "公文": "bureaucratese",
319 "冒犯": "offensive",
320 "分詞": "participle",
321 "前古典": "pre-Classical",
322 "助動詞": "auxiliary",
323 "助記符": "mnemonic",
324 "及物": "transitive",
325 "反問句": "rhetoric",
326 "反身": "reflexive",
327 "口語": "colloquial",
328 "口语": "colloquial",
329 "古舊": "archaic",
330 "可數": "countable",
331 "同性戀俚語": ["slang", "LGBT"],
332 "名詞化": "noun-from-verb",
333 "唯單": "singular-only",
334 "唯複": "plural-only",
335 "國際音標": "IPA",
336 "基數詞": "cardinal",
337 "大寫": "capitalized",
338 "委婉": "euphemistic",
339 "字面義": "literally",
340 "完整": "perfect",
341 "完整體": "perfective",
342 "定語": "attributive",
343 "實詞": "substantive",
344 "尊敬": "honorific",
345 "敬語": "honorific",
346 "敬语": "honorific",
347 "常用複數": "plural-normally",
348 "幽默": "humorous",
349 "序數詞": "ordinal",
350 "廣義來說": "broadly",
351 "引申": "broadly",
352 "弱祈使式": "jussive",
353 "強調": "emphatic",
354 "後古典": "obsolete",
355 "性別中立": "gender-neutral",
356 "情態": "modal",
357 "愛稱": "endearing",
358 "所有格代詞": ["possessive", "pronoun", "without-noun"],
359 "押韻俚語": "slang",
360 "抽象名詞": "abstract-noun",
361 "擬態詞": "ideophonic",
362 "擬聲詞": "onomatopoeic",
363 "新詞": "neologism",
364 "方言": "dialectal",
365 "書面": "literary",
366 "书面": "literary",
367 "有比較級": "comparable",
368 "有生": "animate",
369 "正式": "formal",
370 "歷史": "historical",
371 "比喻義": "figuratively",
372 "無人稱": "impersonal",
373 "無比較級": "not-comparable",
374 "無生": "inanimate",
375 "焦點": "focus",
376 "狹義": "narrowly",
377 "監獄俚語": "slang",
378 "直陳語氣": "indicative",
379 "短信": "Internet",
380 "祈使語氣": "imperative",
381 "禮貌": "polite",
382 "種族歧視語": "slur",
383 "粉絲用語": ["slang", "lifestyle"],
384 "粗俗": "vulgar",
385 "系動詞": "copulative",
386 "網路用語": "Internet",
387 "縮寫": "abbreviation",
388 "罕用": "rare",
389 "臨時語": "nonce-word",
390 "虛擬語氣": "subjunctive",
391 "表語": "predicative",
392 "被動語態": "passive",
393 "視覺方言": "pronunciation-spelling",
394 "親切": "familiar",
395 "詈語": "expletive",
396 "詩歌": "poetic",
397 "誇飾": "excessive",
398 "語中音省略": "syncope",
399 "諷刺": "sarcastic",
400 "謙遜": "humble",
401 "貶義": "derogatory",
402 "轉喻義": "metonymically",
403 "返璞詞": "retronym",
404 "過時": "dated",
405 "陰性": "feminine",
406 "陽性": "masculine",
407 "雙及物動詞": "ditransitive",
408 "靜態動詞": "stative",
409 "非完整": "imperfect",
410 "非完整體": "imperfective",
411 "非常罕用": "rare",
412 "非標準": "nonstandard",
413 "非标准": "nonstandard",
414 "非標準形式": "nonstandard",
415 "非正式": "informal",
416 "首字母縮略詞": "initialism",
417 "駭客語": ["Leet", "Internet"],
418 "高語域": "honorific",
419 "中醫": "Traditional-Chinese-Medicine",
420 "修辭學": "rhetoric",
421 "印度教": "Hinduism",
422 "摩門教": "Mormonism",
423 "物理": "particle",
424 "猶太教": "Judaism",
425 "納粹主義": "Nazism",
426 "網際網路": "Internet",
427 "耆那教": "Jainism",
428 "聖經": "Biblical",
429 "解剖學": "anatomy",
430 "貴格會": "Quakerism",
431 "錫克教": "Sikhism",
432 "馬克思主義": "Marxism",
433 # also from Module:Labels/data, but translated manually
434 "喃字": "Chu-Nom",
435 "反身代詞": "reflexive",
436 "字面意義": "literally",
437 "成語": "Chengyu",
438 "及物、不及物": ["transitive", "intransitive"],
439 "集合名詞": "collective",
440 "控制動詞": "control-verb",
441 "省略": "ellipsis",
442 "分數": "fractional",
443 "以雙數形式": "dual",
444 "主要用於否定複數": ["negative", "plural"],
445 "數詞縮寫": ["numeral", "abbreviation"],
446 "主要用於肯定": "positive",
447 "古典": "Classical",
448 "中國大陸": "Mainland-China",
449 "書面語": "literary",
450 "文言": "literary",
451 "詞幹": "stem",
452 "烏爾都語寫法": "Urdu",
453 "波斯-阿拉伯字母": "Perso-Arabic",
454 # Template:kok-pos
455 "拉丁字母": ["Latin", "character"],
456 "卡納達文": ["Kannada", "character"],
457 "尼瓦爾文拼寫": "Newa",
458}
460# example sentence template
461# https://zh.wiktionary.org/wiki/Template:Zh-x
462# https://zh.wiktionary.org/wiki/Module:Zh-usex/data
463ZH_X_TAGS = {
464 "繁體": "Traditional-Chinese",
465 "繁體和": "Traditional-Chinese",
466 "簡體": "Simplified-Chinese",
467 "繁體和簡體": ["Traditional-Chinese", "Simplified-Chinese"],
468 "漢語拼音": "Pinyin",
469 "粵拼": "Jyutping",
470 "現代標準漢語": "Standard-Chinese",
471 "文言文": "Classical-Chinese",
472 "官話白話文": "Written-vernacular-Chinese",
473 "粵語": "Cantonese",
474 "吳語": "Wu",
475 "廣州話": "Cantonese",
476 "臺灣華語": "Taiwanese-Mandarin",
477}
479# classifier tags
480# https://zh.wiktionary.org/wiki/Template:zh-mw
481# https://zh.wiktionary.org/wiki/Module:Zh/templates
482ZH_TAGS = {
483 "官話": "Mandarin",
484 "贛語": "Gan",
485 "客家話": "Hakka",
486 "晉語": "Jin",
487 "閩北語": "Min-Bei",
488 "閩東語": "Min-Dong",
489 "閩南語": "Min-Nan",
490 "潮州話": "Teochew",
491 "湘語": "Xiang",
492}
494# https://zh.wiktionary.org/wiki/Template:Zh-pron
495# https://zh.wiktionary.org/wiki/Module:Zh-pron
496ZH_PRON_TAGS = {
497 "拼音": "Pinyin",
498 "注音": "Bopomofo",
499 "潮州話拼音": "Peng'im",
500 "上海": "Shanghai",
501 "吳語學堂拼音": "Wugniu",
502 "通用拼音": "Tongyong-Pinyin",
503 "威妥瑪拼音": "Wade–Giles",
504 "耶魯官話拼音": "Yale",
505 "國語羅馬字": "Gwoyeu-Romatsyh",
506 "西里爾字母轉寫": "Cyrillic",
507 "西里爾字母": "Cyrillic",
508 "漢語國際音標": "Sinological-IPA",
509 "耶魯粵拼": ["Yale", "Jyutping"],
510 "廣州話拼音": ["Cantonese", "Pinyin"],
511 "廣東拼音": "Guangdong-Romanization",
512 "國際音標": "IPA",
513 "模仿白話字": "POJ",
514 "標準粵語": "Standard-Cantonese",
515 "廣州–香港話": ["Guangzhou", "Hong Kong"],
516 "福州話": "Fuzhou",
517 "平話字": "Foochow-Romanized",
518 "客家語": "Hakka",
519 "白話字": "Phak-fa-su",
520 "泉漳話": "Hokkien",
521 "泉州": "Quanzhou",
522 "廈門": "Xiamen",
523 "輕尾聲異讀": "toneless-final-syllable-variant",
524 "維基詞典": "Wiktionary-specific",
525 "維基詞典拼音": ["Wiktionary-specific", "Pinyin"],
526 "維基詞典轉寫": "Wiktionary-specific",
527 "成都話": "Chengdu",
528 "四川話拼音": ["Sichuanese", "Pinyin"],
529 "東干語": "Dongan",
530 "台山話": "Taishanese",
531 "四縣": "Sixian",
532 "長沙話": "Changsha",
533 "四川話拉丁化新文字": "Latinxua-Sin-Wenz",
534 "台城": "Taicheng",
535 "南昌話": "Nanchang",
536 "四縣話": "Sixian",
537 "苗栗": "Miaoli",
538 "美濃": "Neipu",
539 "客家語拼音": "Hakka-Romanization-System",
540 "客家話拼音方案": "Hagfa-Pinyim",
541 "太原話": "Taiyuan",
542 "老派": "dated",
543 "新加坡": "Singapore",
544 "臺羅": "Tâi-lô",
545 "普實台文": "Phofsit-Daibuun",
546 "太湖片": "Northern",
547 "吳音小字典": "MiniDict",
548 "維基詞典羅馬化": ["Wiktionary-specific", "romanization"],
549 "上海話": "Shanghai",
550 "中古漢語": "Middle-Chinese",
551 "莆仙語": "Puxian-Min",
552 "莆仙話拼音": "Pouseng-Ping'ing",
553 "莆田": "Putian",
554 "仙遊": "Xianyou",
555 "漳州": "Zhangzhou",
556 "臺北": "Taibei",
557 "高雄": "Kaohsiung",
558 "實際讀音": "phonetic",
559 "臺灣話": "Taiwanese",
560 "常用": "general",
561 "檳城": "Penang",
562 "兒化": "Erhua",
563 "文讀": "literary",
564 "中國大陸標準讀法": ["Mainland-China", "standard"],
565 "臺灣異讀法": ["Taiwan", "variant"],
566 "中國大陸與臺灣標準讀法": ["Mainland-China", "Taiwan", "standard"],
567 "異讀": "variant",
568 "上古": "Old-Chinese",
569 "白–沙": "Baxter–Sagart",
570 "鄭張": "Zhengzhang",
571}
573ZH_DIAL_TAGS = {
574 "白話文": "Written-vernacular-Chinese",
575 "北京": "Beijing",
576 "燕京官話": "Northeastern-Mandarin",
577 "冀魯官話": "Jilu-Mandarin",
578 "膠遼官話": "Jiaoliao-Mandarin",
579 "中原官話": "Central-Plains-Mandarin",
580 "蘭銀官話": "Lanyin-Mandarin",
581 "西南官話": "Southwestern-Mandarin",
582 "江淮官話": "Jianghuai-Mandarin",
583 "徽語": "Huizhou",
584 "南部平話": "Southern-Pinghua",
585 "濟南": "Jinan",
586 "臺灣": "Taiwan",
587}
589TH_PRON_TAGS = {
590 "寫法": "orthographic",
591 "音素": "phoneme",
592 "泰語羅馬化": "romanization",
593 "派汶拼音": "Paiboon",
594 "皇家轉寫": "Royal-Institute",
595 "非正字法": "unorthographical",
596 "短音": "short",
597}
600ALL_TAGS = {
601 **GRAMMATICAL_TAGS,
602 **LABEL_TAGS,
603 **ZH_X_TAGS,
604 **ZH_TAGS,
605 **ZH_PRON_TAGS,
606 **ZH_DIAL_TAGS,
607 **TH_PRON_TAGS,
608 # Template:vi-ipa
609 "河內": "Hà-Nội",
610 "順化": "Huế",
611 "胡志明市": "Saigon",
612 # Template:hi-ipa
613 "德里": "Delhi",
614 # Template:hi-noun
615 "烏爾都文拼寫": "Urdu",
616 # Template:sa-ipa
617 "吠陀": "Vedic",
618 "古典梵語": "Classical-Sanskrit",
619}
622def translate_raw_tags(data: WordEntry) -> WordEntry:
623 raw_tags = []
624 for raw_tag in data.raw_tags:
625 if raw_tag in ALL_TAGS:
626 tr_tag = ALL_TAGS[raw_tag]
627 if isinstance(tr_tag, str) and tr_tag not in data.tags:
628 data.tags.append(tr_tag)
629 elif isinstance(tr_tag, list):
630 data.tags.extend(tr_tag)
631 elif raw_tag in LABEL_TOPICS and hasattr(data, "topics"):
632 data.topics.append(LABEL_TOPICS[raw_tag])
633 elif raw_tag not in raw_tags: 633 ↛ 624line 633 didn't jump to line 624 because the condition on line 633 was always true
634 raw_tags.append(raw_tag)
635 data.raw_tags = raw_tags
636 return data
639# https://zh.wiktionary.org/wiki/Template:T
640# https://zh.wiktionary.org/wiki/Template:Head
641# https://zh.wiktionary.org/wiki/Module:Gender_and_number
642TEMPLATE_TAG_ARGS = {
643 "f": "feminine",
644 "m": "masculine",
645 "n": "neuter",
646 "c": "common",
647 # Animacy
648 "an": "animate",
649 "in": "inanimate",
650 # Animal (for Ukrainian, Belarusian, Polish)
651 "anml": "animal",
652 # Personal (for Ukrainian, Belarusian, Polish)
653 "pr": "personal",
654 # Nonpersonal not currently used
655 "np": "nonpersonal",
656 # Virility (for Polish)
657 "vr": "virile",
658 "nv": "nonvirile",
659 # Numbers
660 "s": "singular number",
661 "d": "dual number",
662 "p": "plural number",
663 # Verb qualifiers
664 "impf": "imperfective",
665 "pf": "perfective",
666 "mf": ["masculine", "feminine"],
667}