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

1from pydantic import BaseModel, ConfigDict, Field 

2 

3 

4class CzechBaseModel(BaseModel): 

5 model_config = ConfigDict( 

6 extra="forbid", 

7 strict=True, 

8 validate_assignment=True, 

9 validate_default=True, 

10 ) 

11 

12 

13class Example(CzechBaseModel): 

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 = Field( 

19 default="", 

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

21 ) 

22 

23 

24class Sense(CzechBaseModel): 

25 glosses: list[str] = [] 

26 tags: list[str] = [] 

27 raw_tags: list[str] = [] 

28 categories: list[str] = [] 

29 topics: list[str] = [] 

30 examples: list[Example] = [] 

31 

32 

33class Sound(CzechBaseModel): 

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

35 tags: list[str] = [] 

36 raw_tags: list[str] = [] 

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

38 wav_url: str = "" 

39 oga_url: str = "" 

40 ogg_url: str = "" 

41 mp3_url: str = "" 

42 opus_url: str = "" 

43 flac_url: str = "" 

44 

45 

46class Hyphenation(CzechBaseModel): 

47 parts: list[str] = [] 

48 

49 

50class Form(CzechBaseModel): 

51 form: str 

52 tags: list[str] = [] 

53 raw_tags: list[str] = [] 

54 

55 

56class WordEntry(CzechBaseModel): 

57 model_config = ConfigDict(title="Czech Wiktionary") 

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

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

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

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

62 pos_title: str = "" 

63 senses: list[Sense] = [] 

64 categories: list[str] = [] 

65 tags: list[str] = [] 

66 raw_tags: list[str] = [] 

67 sounds: list[Sound] = [] 

68 hyphenations: list[Hyphenation] = [] 

69 etymology_text: str = "" 

70 forms: list[Form] = []