Coverage for src/wiktextract/extractor/zh/models.py: 100%

1from pydantic import BaseModel, ConfigDict, Field 

2 

3 

4class ChineseBaseModel(BaseModel): 

5 model_config = ConfigDict( 

6 extra="forbid", 

7 strict=True, 

8 validate_assignment=True, 

9 validate_default=True, 

10 ) 

11 

12 

13class Example(ChineseBaseModel): 

14 text: str = Field( 

15 default="", 

16 description="Example usage sentences, some might have have both " 

17 "Simplified and Traditional Chinese forms", 

18 ) 

19 translation: str = Field( 

20 default="", description="Chinese translation of the example sentence" 

21 ) 

22 literal_meaning: str = "" 

23 roman: str = Field( 

24 default="", description="Romanization of the example sentence" 

25 ) 

26 ref: str = Field( 

27 default="", 

28 description="Source of the sentence, like book title and page number", 

29 ) 

30 ruby: list[tuple[str, ...]] = Field( 

31 default=[], description="Japanese Kanji and furigana" 

32 ) 

33 tags: list[str] = [] 

34 raw_tags: list[str] = [] 

35 

36 

37class AltForm(ChineseBaseModel): 

38 word: str 

39 tags: list[str] = [] 

40 

41 

42class Classifier(ChineseBaseModel): 

43 classifier: str = "" 

44 tags: list[str] = [] 

45 raw_tags: list[str] = [] 

46 

47 

48class Sense(ChineseBaseModel): 

49 glosses: list[str] = [] 

50 tags: list[str] = [] 

51 raw_tags: list[str] = [] 

52 topics: list[str] = [] 

53 categories: list[str] = [] 

54 examples: list[Example] = [] 

55 ruby: list[tuple[str, ...]] = Field( 

56 default=[], description="Japanese Kanji and furigana" 

57 ) 

58 alt_of: list[AltForm] = [] 

59 form_of: list[AltForm] = [] 

60 classifiers: list[Classifier] = [] 

61 

62 

63class Form(ChineseBaseModel): 

64 form: str = "" 

65 tags: list[str] = [] 

66 raw_tags: list[str] = [] 

67 source: str = "" 

68 ruby: list[tuple[str, ...]] = Field( 

69 default=[], description="Japanese Kanji and furigana" 

70 ) 

71 hiragana: str = "" 

72 roman: str = "" 

73 

74 

75class Sound(ChineseBaseModel): 

76 zh_pron: str = Field(default="", description="Chinese word pronunciation") 

77 ipa: str = Field(default="", description="International Phonetic Alphabet") 

78 audio: str = Field(default="", description="Audio file name") 

79 wav_url: str = "" 

80 oga_url: str = "" 

81 ogg_url: str = "" 

82 mp3_url: str = "" 

83 opus_url: str = "" 

84 flac_url: str = "" 

85 tags: list[str] = [] 

86 raw_tags: list[str] = [] 

87 homophone: str = "" 

88 enpr: str = Field(default="", description="English pronunciation") 

89 

90 

91class Translation(ChineseBaseModel): 

92 lang_code: str = Field( 

93 default="", 

94 description="Wiktionary language code of the translation term", 

95 ) 

96 lang: str = Field(default="", description="Translation language name") 

97 word: str = Field(description="Translation term") 

98 sense: str = Field(default="", description="Translation gloss") 

99 tags: list[str] = [] 

100 raw_tags: list[str] = [] 

101 roman: str = Field(default="", description="Roman script") 

102 alt: str = Field(default="", description="Alternative form") 

103 lit: str = Field(default="", description="Literal translation for the term") 

104 

105 

106class Linkage(ChineseBaseModel): 

107 word: str = "" 

108 tags: list[str] = [] 

109 raw_tags: list[str] = [] 

110 roman: str = "" 

111 sense: str = "" 

112 ruby: list[tuple[str, ...]] = Field( 

113 default=[], description="Japanese Kanji and furigana" 

114 ) 

115 

116 

117class Descendant(ChineseBaseModel): 

118 lang_code: str = Field(default="", description="Wiktionary language code") 

119 lang: str = Field(default="", description="Language name") 

120 word: str = "" 

121 roman: str = "" 

122 tags: list[str] = [] 

123 raw_tags: list[str] = [] 

124 descendants: list["Descendant"] = [] 

125 ruby: list[tuple[str, ...]] = Field( 

126 default=[], description="Japanese Kanji and furigana" 

127 ) 

128 

129 

130class WordEntry(ChineseBaseModel): 

131 model_config = ConfigDict(title="Chinese Wiktionary") 

132 

133 word: str = Field(description="Word string") 

134 lang_code: str = Field(description="Wiktionary language code") 

135 lang: str = Field(description="Localized language name") 

136 pos: str = Field(description="Part of speech type") 

137 etymology_text: str = "" 

138 etymology_examples: list[Example] = [] 

139 senses: list[Sense] = Field(default=[], description="Sense list") 

140 forms: list[Form] = Field(default=[], description="Inflection forms list") 

141 sounds: list[Sound] = [] 

142 translations: list[Translation] = [] 

143 synonyms: list[Linkage] = [] 

144 hyponyms: list[Linkage] = [] 

145 hypernyms: list[Linkage] = [] 

146 holonyms: list[Linkage] = [] 

147 meronyms: list[Linkage] = [] 

148 derived: list[Linkage] = [] 

149 troponyms: list[Linkage] = [] 

150 paronyms: list[Linkage] = [] 

151 related: list[Linkage] = [] 

152 abbreviation: list[Linkage] = [] 

153 proverbs: list[Linkage] = [] 

154 antonyms: list[Linkage] = [] 

155 coordinate_terms: list[Linkage] = [] 

156 various: list[Linkage] = [] 

157 compounds: list[Linkage] = [] 

158 title: str = Field(default="", description="Redirect page source title") 

159 redirect: str = Field(default="", description="Redirect page target title") 

160 categories: list[str] = [] 

161 notes: list[str] = [] 

162 tags: list[str] = [] 

163 raw_tags: list[str] = [] 

164 descendants: list[Descendant] = [] 

165 redirects: list[str] = Field( 

166 default=[], 

167 description="Soft redirect page, extracted from template zh-see ja-see", 

168 ) 

169 literal_meaning: str = ""