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

107 statements  

« prev     ^ index     » next       coverage.py v7.9.2, created at 2025-07-11 10:26 +0000

1from pydantic import BaseModel, ConfigDict, Field 

2 

3 

4class FrenchBaseModel(BaseModel): 

5 model_config = ConfigDict( 

6 extra="forbid", 

7 strict=True, 

8 validate_assignment=True, 

9 validate_default=True, 

10 ) 

11 

12 

13class Example(FrenchBaseModel): 

14 text: str = Field(default="", description="Example usage sentence") 

15 bold_text_offsets: list[tuple[int, int]] = [] 

16 translation: str = Field( 

17 default="", description="French translation of the example sentence" 

18 ) 

19 bold_translation_offsets: list[tuple[int, int]] = [] 

20 roman: str = Field( 

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

22 ) 

23 bold_roman_offsets: list[tuple[int, int]] = [] 

24 ref: str = Field( 

25 default="", 

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

27 ) 

28 time: str = Field( 

29 default="", 

30 description="For examples in 'Attestations historiques' section", 

31 ) 

32 note: str = "" 

33 

34 

35class Form(FrenchBaseModel): 

36 form: str = "" 

37 tags: list[str] = [] 

38 raw_tags: list[str] = [] 

39 ipas: list[str] = [] 

40 source: str = Field( 

41 default="", 

42 description="Form line template name or Conjugaison page title", 

43 ) 

44 hiragana: str = "" 

45 roman: str = "" 

46 sense: str = Field(default="", description="Definition of the word") 

47 sense_index: int = Field(default=0, ge=0) 

48 

49 

50class Sound(FrenchBaseModel): 

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

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

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

54 wav_url: str = "" 

55 oga_url: str = "" 

56 ogg_url: str = "" 

57 mp3_url: str = "" 

58 opus_url: str = "" 

59 flac_url: str = "" 

60 tags: list[str] = [] 

61 raw_tags: list[str] = [] 

62 rhymes: str = "" 

63 categories: list[str] = Field(default=[], exclude=True) 

64 homophone: str = "" 

65 roman: str = "" 

66 

67 

68class Translation(FrenchBaseModel): 

69 lang_code: str = Field( 

70 default="", 

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

72 ) 

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

74 word: str = Field(default="", description="Translation term") 

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

76 sense_index: int = Field( 

77 default=0, ge=0, description="Number of the definition, start from 1" 

78 ) 

79 tags: list[str] = [] 

80 raw_tags: list[str] = [] 

81 roman: str = "" 

82 traditional_writing: str = Field( 

83 default="", 

84 description="Alternative writting for Chinese, Korean and Mongolian", 

85 ) 

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

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

88 ) 

89 

90 

91class Linkage(FrenchBaseModel): 

92 word: str 

93 tags: list[str] = [] 

94 raw_tags: list[str] = [] 

95 topics: list[str] = [] 

96 roman: str = "" 

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

98 translation: str = Field(default="", description="French translation") 

99 sense: str = Field(default="", description="Definition of the word") 

100 sense_index: int = Field( 

101 default=0, ge=0, description="Number of the definition, start from 1" 

102 ) 

103 lang: str = Field(default="", description="Localized language name") 

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

105 

106 

107class AltForm(FrenchBaseModel): 

108 word: str 

109 

110 

111class Sense(FrenchBaseModel): 

112 glosses: list[str] = [] 

113 tags: list[str] = [] 

114 raw_tags: list[str] = [] 

115 topics: list[str] = [] 

116 categories: list[str] = [] 

117 examples: list[Example] = [] 

118 note: str = "" 

119 alt_of: list[AltForm] = [] 

120 form_of: list[AltForm] = [] 

121 

122 

123class WordEntry(FrenchBaseModel): 

124 model_config = ConfigDict(title="French Wiktionary") 

125 

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

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

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

129 pos: str = Field(default="", description="Part of speech type") 

130 pos_title: str = Field( 

131 default="", 

132 description="Original POS title for matching etymology texts", 

133 ) 

134 pos_id: str = Field( 

135 default="", 

136 description="POS id for matching etymology texts", 

137 exclude=True, 

138 ) 

139 etymology_texts: list[str] = Field(default=[], description="Etymology list") 

140 etymology_examples: list[Example] = Field( 

141 default=[], description="Data in 'Attestations historiques' section" 

142 ) 

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

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

145 sounds: list[Sound] = [] 

146 translations: list[Translation] = [] 

147 antonyms: list[Linkage] = [] 

148 synonyms: list[Linkage] = [] 

149 hyponyms: list[Linkage] = [] 

150 hypernyms: list[Linkage] = [] 

151 holonyms: list[Linkage] = [] 

152 meronyms: list[Linkage] = [] 

153 derived: list[Linkage] = [] 

154 troponyms: list[Linkage] = [] 

155 paronyms: list[Linkage] = [] 

156 related: list[Linkage] = [] 

157 abbreviation: list[Linkage] = [] 

158 proverbs: list[Linkage] = [] 

159 anagrams: list[Linkage] = [] 

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

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

162 categories: list[str] = [] 

163 notes: list[str] = [] 

164 tags: list[str] = [] 

165 raw_tags: list[str] = []