Coverage for src/wiktextract/extractor/ja/conjugation.py: 94%

1from wikitextprocessor import LevelNode, NodeKind, TemplateNode 

2 

3from ...page import clean_node 

4from ...wxr_context import WiktextractContext 

5from .models import Form, WordEntry 

6 

7 

8def extract_conjugation_section( 

9 wxr: WiktextractContext, word_entry: WordEntry, level_node: LevelNode 

10) -> None: 

11 for t_node in level_node.find_child(NodeKind.TEMPLATE): 

12 if t_node.template_name in { 12 ↛ 11line 12 didn't jump to line 11 because the condition on line 12 was always true

13 "日本語形容動詞活用", 

14 "日本語五段活用", 

15 "日本語五段活用/表示", 

16 "日本語上一段活用", 

17 "日本語下一段活用", 

18 "日本語形容詞活用/表示", 

19 "日本語タルト活用", 

20 "日本語ダ活用", 

21 "日本語サ変活用", 

22 "日本語一段活用", 

23 "日本語カ変活用", 

24 "日本語ザ変活用", 

25 }: 

26 extract_ja_conjugation_table_template(wxr, word_entry, t_node) 

27 

28 

29def extract_ja_conjugation_table_template( 

30 wxr: WiktextractContext, word_entry: WordEntry, t_node: TemplateNode 

31) -> None: 

32 # extract templates use this Lua module 

33 # https://ja.wiktionary.org/wiki/モジュール:日本語活用表 

34 expanded_node = wxr.wtp.parse( 

35 wxr.wtp.node_to_wikitext(t_node), expand_all=True 

36 ) 

37 for link_node in expanded_node.find_child(NodeKind.LINK): 

38 clean_node(wxr, word_entry, link_node) 

39 for table_index, table_node in enumerate( 

40 expanded_node.find_child_recursively(NodeKind.TABLE) 

41 ): 

42 table_name = "" 

43 column_headers = [] 

44 row_header = "" 

45 for row_or_caption in table_node.find_child( 

46 NodeKind.TABLE_CAPTION | NodeKind.TABLE_ROW 

47 ): 

48 if row_or_caption.kind == NodeKind.TABLE_CAPTION: 

49 table_name = clean_node(wxr, None, row_or_caption.children) 

50 elif row_or_caption.kind == NodeKind.TABLE_ROW: 50 ↛ 45line 50 didn't jump to line 45 because the condition on line 50 was always true

51 for cell_index, cell_node in enumerate( 

52 row_or_caption.find_child( 

53 NodeKind.TABLE_HEADER_CELL | NodeKind.TABLE_CELL 

54 ) 

55 ): 

56 if cell_node.kind == NodeKind.TABLE_HEADER_CELL: 

57 if ( 

58 len(list(row_or_caption.filter_empty_str_child())) 

59 == 1 

60 ): 

61 table_name = clean_node(wxr, None, cell_node) 

62 else: 

63 column_headers.append( 

64 clean_node(wxr, None, cell_node) 

65 ) 

66 elif cell_node.kind == NodeKind.TABLE_CELL: 66 ↛ 51line 66 didn't jump to line 51 because the condition on line 66 was always true

67 if table_index == 1 and cell_index == 0: 

68 row_header = clean_node(wxr, None, cell_node) 

69 else: 

70 for line in clean_node( 

71 wxr, None, cell_node 

72 ).splitlines(): 

73 form = Form(form=line) 

74 form.raw_tags.append(table_name) 

75 if cell_index < len(column_headers): 75 ↛ 79line 75 didn't jump to line 79 because the condition on line 75 was always true

76 form.raw_tags.append( 

77 column_headers[cell_index] 

78 ) 

79 if len(row_header) > 0: 

80 form.raw_tags.append(row_header) 

81 word_entry.forms.append(form)