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

1from pydantic import BaseModel, ConfigDict, Field 

2 

3 

4class KoreanBaseModel(BaseModel): 

5 model_config = ConfigDict( 

6 extra="forbid", 

7 strict=True, 

8 validate_assignment=True, 

9 validate_default=True, 

10 ) 

11 

12 

13class Sound(KoreanBaseModel): 

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

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

16 wav_url: str = "" 

17 oga_url: str = "" 

18 ogg_url: str = "" 

19 mp3_url: str = "" 

20 opus_url: str = "" 

21 flac_url: str = "" 

22 tags: list[str] = [] 

23 raw_tags: list[str] = [] 

24 hangul: str = "" 

25 roman: str = "" 

26 other: str = "" 

27 

28 

29class Example(KoreanBaseModel): 

30 text: str = "" 

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

32 translation: str = "" 

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

34 ref: str = "" 

35 roman: str = "" 

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

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

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

39 ) 

40 tags: list[str] = [] 

41 literal_meaning: str = "" 

42 bold_literal_offsets: list[tuple[int, int]] = [] 

43 note: str = "" 

44 sounds: list[Sound] = [] 

45 tags: list[str] = [] 

46 raw_tags: list[str] = [] 

47 

48 

49class AltForm(KoreanBaseModel): 

50 word: str 

51 

52 

53class Classifier(KoreanBaseModel): 

54 classifier: str = "" 

55 tags: list[str] = [] 

56 raw_tags: list[str] = [] 

57 

58 

59class Sense(KoreanBaseModel): 

60 glosses: list[str] = [] 

61 tags: list[str] = [] 

62 raw_tags: list[str] = [] 

63 topics: list[str] = [] 

64 categories: list[str] = [] 

65 examples: list[Example] = [] 

66 note: str = "" 

67 form_of: list[AltForm] = [] 

68 pattern: str = Field(default="", description="Sentence structure, 문형") 

69 classifiers: list[Classifier] = [] 

70 

71 

72class Linkage(KoreanBaseModel): 

73 word: str 

74 sense: str = "" 

75 roman: str = "" 

76 raw_tags: list[str] = [] 

77 tags: list[str] = [] 

78 sense_index: str = "" 

79 

80 

81class Translation(KoreanBaseModel): 

82 lang_code: str = Field( 

83 description="Wiktionary language code of the translation term" 

84 ) 

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

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

87 roman: str = "" 

88 tags: list[str] = [] 

89 raw_tags: list[str] = [] 

90 sense: str = "" 

91 

92 

93class Form(KoreanBaseModel): 

94 form: str = "" 

95 tags: list[str] = [] 

96 raw_tags: list[str] = [] 

97 roman: str = "" 

98 

99 

100class WordEntry(KoreanBaseModel): 

101 model_config = ConfigDict(title="Korean Wiktionary") 

102 word: str = Field(description="Word string", min_length=1) 

103 lang_code: str = Field(description="Wiktionary language code", min_length=1) 

104 lang: str = Field(description="Localized language name", min_length=1) 

105 pos: str = Field(description="Part of speech type", min_length=1) 

106 pos_title: str = "" 

107 senses: list[Sense] = [] 

108 categories: list[str] = [] 

109 tags: list[str] = [] 

110 raw_tags: list[str] = [] 

111 sounds: list[Sound] = [] 

112 proverbs: list[Linkage] = [] 

113 derived: list[Linkage] = [] 

114 related: list[Linkage] = [] 

115 synonyms: list[Linkage] = [] 

116 antonyms: list[Linkage] = [] 

117 translations: list[Translation] = [] 

118 etymology_texts: list[str] = [] 

119 note: str = "" 

120 forms: list[Form] = [] 

121 pattern: str = Field( 

122 default="", description="Sentence structure, 문형", exclude=True 

123 ) 

124 idioms: list[Translation] = [] 

125 hyponyms: list[Translation] = [] 

126 redirects: list[str] = [] 

127 literal_meaning: str = "" 

128 anagrams: list[Linkage] = []