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

1from pydantic import BaseModel, ConfigDict, Field 

2 

3 

4class BaseModelWrap(BaseModel): 

5 model_config = ConfigDict( 

6 extra="forbid", 

7 strict=True, 

8 validate_assignment=True, 

9 validate_default=True, 

10 ) 

11 

12 

13class Translation(BaseModelWrap): 

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

15 lang_code: str = Field( 

16 default="", 

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

18 ) 

19 lang: str = Field( 

20 description="Localized language name of the translation term" 

21 ) 

22 sense: str = Field( 

23 default="", 

24 description="An optional gloss describing the sense translated", 

25 ) 

26 roman: str = Field(default="", description="Romanization of the word") 

27 tags: list[str] = [] 

28 raw_tags: list[str] = [] 

29 other: str = "" 

30 

31 

32class Linkage(BaseModelWrap): 

33 word: str = "" 

34 tags: list[str] = [] 

35 raw_tags: list[str] = [] 

36 sense: str = "" 

37 sense_index: int = Field( 

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

39 ) 

40 

41 

42class Sound(BaseModelWrap): 

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

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

45 wav_url: str = "" 

46 ogg_url: str = "" 

47 oga_url: str = "" 

48 mp3_url: str = "" 

49 opus_url: str = "" 

50 flac_url: str = "" 

51 tags: list[str] = Field( 

52 default=[], description="Specifying the variant of the pronunciation" 

53 ) 

54 raw_tags: list[str] = [] 

55 homophones: list[str] = Field( 

56 default=[], description="Words with same pronunciation" 

57 ) 

58 rhymes: str = "" 

59 

60 

61class Example(BaseModelWrap): 

62 text: str = Field(description="Example usage sentence") 

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

64 translation: str = Field( 

65 default="", description="Russian translation of the example sentence" 

66 ) 

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

68 ref: str = Field( 

69 default="", 

70 description="Example reference, combine data like author and title", 

71 ) 

72 

73 

74class AltForm(BaseModelWrap): 

75 word: str 

76 

77 

78class Sense(BaseModelWrap): 

79 glosses: list[str] = Field( 

80 default=[], 

81 description="Gloss string for the word sense. This has been cleaned, " 

82 "and should be straightforward text with no tags.", 

83 ) 

84 tags: list[str] = Field( 

85 default=[], 

86 description="List of tags affecting the word sense.", 

87 ) 

88 raw_tags: list[str] = [] 

89 topics: list[str] = [] 

90 categories: list[str] = [] 

91 examples: list[Example] = Field(default=[], description="List of examples") 

92 form_of: list[AltForm] = [] 

93 

94 

95class Form(BaseModelWrap): 

96 form: str 

97 tags: list[str] = [] 

98 raw_tags: list[str] = [] 

99 

100 

101class Hyphenation(BaseModelWrap): 

102 parts: list[str] = [] 

103 tags: list[str] = [] 

104 raw_tags: list[str] = [] 

105 

106 

107class WordEntry(BaseModelWrap): 

108 """ 

109 WordEntry is a dictionary containing lexical information of a single word 

110 extracted from Wiktionary with wiktextract. 

111 """ 

112 

113 model_config = ConfigDict(title="Russian Wiktionary") 

114 

115 word: str = Field(description="word string") 

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

117 pos_title: str = Field(default="", description="Original POS title") 

118 lang_code: str = Field( 

119 description="Wiktionary language code", examples=["ru"] 

120 ) 

121 lang: str = Field( 

122 description="Localized language name of the word", examples=["Русский"] 

123 ) 

124 categories: list[str] = Field( 

125 default=[], 

126 description="list of non-disambiguated categories for the word", 

127 ) 

128 sounds: list[Sound] = [] 

129 senses: list[Sense] = [] 

130 translations: list[Translation] = [] 

131 forms: list[Form] = [] 

132 tags: list[str] = [] 

133 raw_tags: list[str] = [] 

134 antonyms: list[Linkage] = Field(default=[], description="List of antonyms") 

135 anagrams: list[Linkage] = Field(default=[], description="List of anagrams") 

136 variants: list[Linkage] = Field(default=[], description="List of variants") 

137 hypernyms: list[Linkage] = Field( 

138 default=[], description="List of hypernyms" 

139 ) 

140 hyponyms: list[Linkage] = Field(default=[], description="List of hyponyms") 

141 derived: list[Linkage] = Field( 

142 default=[], description="List of derived terms" 

143 ) 

144 meronyms: list[Linkage] = Field(default=[], description="List of meronyms") 

145 synonyms: list[Linkage] = Field(default=[], description="List of synonyms") 

146 coordinate_terms: list[Linkage] = Field( 

147 default=[], description="List of coordinate terms" 

148 ) 

149 holonyms: list[Linkage] = Field(default=[], description="List of holonyms") 

150 etymology_texts: list[str] = [] 

151 related: list[Linkage] = [] 

152 metagrams: list[Linkage] = [] 

153 proverbs: list[Linkage] = [] 

154 literal_meaning: str = "" 

155 hyphenations: list[Hyphenation] = []