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

1from pydantic import BaseModel, ConfigDict, Field 

2 

3 

4class VietnameseBaseModel(BaseModel): 

5 model_config = ConfigDict( 

6 extra="forbid", 

7 strict=True, 

8 validate_assignment=True, 

9 validate_default=True, 

10 ) 

11 

12 

13class Example(VietnameseBaseModel): 

14 text: str 

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

16 translation: str = "" 

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

18 literal_meaning: str = "" 

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

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

30 ) 

31 tags: list[str] = [] 

32 raw_tags: list[str] = [] 

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

34 

35 

36class AltForm(VietnameseBaseModel): 

37 word: str 

38 roman: str = "" 

39 

40 

41class Sense(VietnameseBaseModel): 

42 glosses: list[str] = [] 

43 tags: list[str] = [] 

44 raw_tags: list[str] = [] 

45 categories: list[str] = [] 

46 topics: list[str] = [] 

47 examples: list[Example] = [] 

48 form_of: list[AltForm] = [] 

49 alt_of: list[AltForm] = [] 

50 

51 

52class Linkage(VietnameseBaseModel): 

53 word: str 

54 tags: list[str] = [] 

55 raw_tags: list[str] = [] 

56 roman: str = "" 

57 sense: str = "" 

58 other: str = "" 

59 translation: str = "" 

60 senses: list[str] = [] 

61 

62 

63class Form(VietnameseBaseModel): 

64 form: str 

65 tags: list[str] = [] 

66 raw_tags: list[str] = [] 

67 roman: str = "" 

68 sense: str = "" 

69 

70 

71class Translation(VietnameseBaseModel): 

72 lang_code: str = Field( 

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

74 ) 

75 lang: str = Field(description="Translation language name") 

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

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

78 tags: list[str] = [] 

79 raw_tags: list[str] = [] 

80 roman: str = "" 

81 lit: str = Field(default="", description="Literal translation") 

82 source: str = "" 

83 other: str = "" 

84 

85 

86class Sound(VietnameseBaseModel): 

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

88 tags: list[str] = [] 

89 raw_tags: list[str] = [] 

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

91 wav_url: str = "" 

92 oga_url: str = "" 

93 ogg_url: str = "" 

94 mp3_url: str = "" 

95 opus_url: str = "" 

96 flac_url: str = "" 

97 rhymes: str = "" 

98 

99 

100class Hyphenation(VietnameseBaseModel): 

101 parts: list[str] = [] 

102 

103 

104class WordEntry(VietnameseBaseModel): 

105 model_config = ConfigDict(title="Vietnamese Wiktionary") 

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

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

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

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

110 pos_title: str = "" 

111 senses: list[Sense] = [] 

112 categories: list[str] = [] 

113 tags: list[str] = [] 

114 raw_tags: list[str] = [] 

115 antonyms: list[Linkage] = [] 

116 synonyms: list[Linkage] = [] 

117 coordinate_terms: list[Linkage] = [] 

118 derived: list[Linkage] = [] 

119 related: list[Linkage] = [] 

120 holonyms: list[Linkage] = [] 

121 hypernyms: list[Linkage] = [] 

122 hyponyms: list[Linkage] = [] 

123 meronyms: list[Linkage] = [] 

124 forms: list[Form] = [] 

125 translations: list[Translation] = [] 

126 sounds: list[Sound] = [] 

127 etymology_text: str = "" 

128 hyphenations: list[Hyphenation] = [] 

129 notes: list[str] = [] 

130 anagrams: list[Linkage] = []