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

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 AttestationData(FrenchBaseModel): 

14 date: str 

15 

16 

17class Example(FrenchBaseModel): 

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

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

20 translation: str = Field( 

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

22 ) 

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

24 roman: str = Field( 

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

26 ) 

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

28 ref: str = Field( 

29 default="", 

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

31 ) 

32 attestations: list[AttestationData] = Field( 

33 default=[], 

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

35 ) 

36 note: str = "" 

37 

38 

39class Form(FrenchBaseModel): 

40 form: str = "" 

41 tags: list[str] = [] 

42 raw_tags: list[str] = [] 

43 ipas: list[str] = [] 

44 source: str = Field( 

45 default="", 

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

47 ) 

48 hiragana: str = "" 

49 roman: str = "" 

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

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

52 

53 

54class Sound(FrenchBaseModel): 

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

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

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

58 wav_url: str = "" 

59 oga_url: str = "" 

60 ogg_url: str = "" 

61 mp3_url: str = "" 

62 opus_url: str = "" 

63 flac_url: str = "" 

64 tags: list[str] = [] 

65 raw_tags: list[str] = [] 

66 rhymes: str = "" 

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

68 homophone: str = "" 

69 roman: str = "" 

70 

71 

72class Translation(FrenchBaseModel): 

73 lang_code: str = Field( 

74 default="", 

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

76 ) 

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

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

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

80 sense_index: int = Field( 

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

82 ) 

83 tags: list[str] = [] 

84 raw_tags: list[str] = [] 

85 roman: str = "" 

86 traditional_writing: str = Field( 

87 default="", 

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

89 ) 

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

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

92 ) 

93 

94 

95class Linkage(FrenchBaseModel): 

96 word: str 

97 tags: list[str] = [] 

98 raw_tags: list[str] = [] 

99 topics: list[str] = [] 

100 roman: str = "" 

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

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

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

104 sense_index: int = Field( 

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

106 ) 

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

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

109 

110 

111class AltForm(FrenchBaseModel): 

112 word: str 

113 

114 

115class Sense(FrenchBaseModel): 

116 glosses: list[str] = [] 

117 tags: list[str] = [] 

118 raw_tags: list[str] = [] 

119 topics: list[str] = [] 

120 categories: list[str] = [] 

121 examples: list[Example] = [] 

122 note: str = "" 

123 alt_of: list[AltForm] = [] 

124 form_of: list[AltForm] = [] 

125 attestations: list[AttestationData] = [] 

126 

127 

128class WordEntry(FrenchBaseModel): 

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

130 

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

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

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

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

135 pos_title: str = Field( 

136 default="", 

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

138 ) 

139 pos_id: str = Field( 

140 default="", 

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

142 exclude=True, 

143 ) 

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

145 etymology_examples: list[Example] = Field( 

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

147 ) 

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

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

150 sounds: list[Sound] = [] 

151 translations: list[Translation] = [] 

152 antonyms: list[Linkage] = [] 

153 synonyms: list[Linkage] = [] 

154 hyponyms: list[Linkage] = [] 

155 hypernyms: list[Linkage] = [] 

156 holonyms: list[Linkage] = [] 

157 meronyms: list[Linkage] = [] 

158 derived: list[Linkage] = [] 

159 troponyms: list[Linkage] = [] 

160 paronyms: list[Linkage] = [] 

161 related: list[Linkage] = [] 

162 abbreviation: list[Linkage] = [] 

163 proverbs: list[Linkage] = [] 

164 anagrams: list[Linkage] = [] 

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

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

167 categories: list[str] = [] 

168 notes: list[str] = [] 

169 tags: list[str] = [] 

170 raw_tags: list[str] = [] 

171 attestations: list[AttestationData] = [] 

172 original_title: str = ""