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

82 statements  

« prev     ^ index     » next       coverage.py v7.9.2, created at 2025-07-04 10:58 +0000

1from pydantic import BaseModel, ConfigDict, Field 

2 

3 

4class ItalianBaseModel(BaseModel): 

5 model_config = ConfigDict( 

6 extra="forbid", 

7 strict=True, 

8 validate_assignment=True, 

9 validate_default=True, 

10 ) 

11 

12 

13class Example(ItalianBaseModel): 

14 text: str = "" 

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

16 translation: str = "" 

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

18 ref: str = "" 

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

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

21 ) 

22 roman: str = "" 

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

24 tags: list[str] = [] 

25 raw_tags: list[str] = [] 

26 

27 

28class AltForm(ItalianBaseModel): 

29 word: str 

30 

31 

32class Sense(ItalianBaseModel): 

33 glosses: list[str] = [] 

34 tags: list[str] = [] 

35 raw_tags: list[str] = [] 

36 categories: list[str] = [] 

37 examples: list[Example] = [] 

38 topics: list[str] = [] 

39 form_of: list[AltForm] = [] 

40 

41 

42class Translation(ItalianBaseModel): 

43 lang_code: str = Field( 

44 default="", 

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

46 ) 

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

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

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

50 tags: list[str] = [] 

51 raw_tags: list[str] = [] 

52 roman: str = "" 

53 

54 

55class Form(ItalianBaseModel): 

56 form: str = "" 

57 tags: list[str] = [] 

58 raw_tags: list[str] = [] 

59 source: str = "" 

60 

61 

62class Sound(ItalianBaseModel): 

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

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

65 wav_url: str = "" 

66 oga_url: str = "" 

67 ogg_url: str = "" 

68 mp3_url: str = "" 

69 opus_url: str = "" 

70 flac_url: str = "" 

71 tags: list[str] = [] 

72 raw_tags: list[str] = [] 

73 sense: str = "" 

74 

75 

76class Hyphenation(ItalianBaseModel): 

77 hyphenation: str = "" 

78 sense: str = "" 

79 

80 

81class Linkage(ItalianBaseModel): 

82 word: str 

83 tags: list[str] = [] 

84 raw_tags: list[str] = [] 

85 sense: str = "" 

86 

87 

88class WordEntry(ItalianBaseModel): 

89 model_config = ConfigDict(title="Italian Wiktionary") 

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

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

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

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

94 pos_title: str = "" 

95 senses: list[Sense] = [] 

96 categories: list[str] = [] 

97 tags: list[str] = [] 

98 raw_tags: list[str] = [] 

99 translations: list[Translation] = [] 

100 forms: list[Form] = [] 

101 etymology_texts: list[str] = [] 

102 etymology_examples: list[Example] = [] 

103 hyphenations: list[Hyphenation] = [] 

104 sounds: list[Sound] = [] 

105 synonyms: list[Linkage] = [] 

106 antonyms: list[Linkage] = [] 

107 derived: list[Linkage] = [] 

108 related: list[Linkage] = [] 

109 hyponyms: list[Linkage] = [] 

110 hypernyms: list[Linkage] = [] 

111 proverbs: list[Linkage] = [] 

112 notes: list[str] = []