Coverage for src/wiktextract/extractor/de/translation.py: 86%

1import re 

2 

3from mediawiki_langcodes import code_to_name, name_to_code 

4from wikitextprocessor import NodeKind, WikiNode 

5from wikitextprocessor.parser import TemplateNode 

6 

7from ...page import clean_node 

8from ...wxr_context import WiktextractContext 

9from .models import Translation, WordEntry 

10from .tags import translate_raw_tags 

11 

12 

13def extract_translation( 

14 wxr: WiktextractContext, word_entry: WordEntry, level_node: WikiNode 

15) -> None: 

16 for template_node in level_node.find_child(NodeKind.TEMPLATE): 

17 if template_node.template_name == "Ü-Tabelle": 17 ↛ 16line 17 didn't jump to line 16 because the condition on line 17 was always true

18 process_u_tabelle_template(wxr, word_entry, template_node) 

19 

20 

21def process_u_tabelle_template( 

22 wxr: WiktextractContext, word_entry: WordEntry, template_node: TemplateNode 

23) -> None: 

24 # https://de.wiktionary.org/wiki/Vorlage:Ü-Tabelle 

25 sense_idx = clean_node( 

26 wxr, None, template_node.template_parameters.get(1, "") 

27 ) 

28 sense = clean_node( 

29 wxr, None, template_node.template_parameters.get("G", "") 

30 ) 

31 for list_arg_name in ["Ü-Liste", "Dialekttabelle"]: 

32 list_arg_value = template_node.template_parameters.get(list_arg_name) 

33 if list_arg_value is None: 

34 continue 

35 tr_list = wxr.wtp.parse(wxr.wtp.node_to_wikitext(list_arg_value)) 

36 for list_item in tr_list.find_child_recursively(NodeKind.LIST_ITEM): 

37 process_u_tabelle_list_item( 

38 wxr, word_entry, list_item, sense, sense_idx 

39 ) 

40 

41 

42def process_u_tabelle_list_item( 

43 wxr: WiktextractContext, 

44 word_entry: WordEntry, 

45 list_item_node: WikiNode, 

46 sense: str, 

47 sense_idx: str, 

48) -> None: 

49 before_colon = True 

50 tr_data = Translation(sense=sense, sense_index=sense_idx) 

51 for node in list_item_node.children: 

52 if isinstance(node, str): 

53 node = node.strip() 

54 if len(node) == 0: 

55 continue 

56 elif ":" in node: 

57 lang_str = node[: node.index(":")].strip() 

58 if len(lang_str) > 0 and len(tr_data.lang) == 0: 

59 tr_data.lang = lang_str 

60 if len(tr_data.lang_code) == 0: 60 ↛ 62line 60 didn't jump to line 62 because the condition on line 60 was always true

61 tr_data.lang_code = name_to_code(lang_str, "de") 

62 before_colon = False 

63 elif node == "," and len(tr_data.word) > 0: 63 ↛ 66line 63 didn't jump to line 66 because the condition on line 63 was always true

64 tr_data = append_tr_data(word_entry, tr_data) 

65 

66 if before_colon and len(tr_data.lang) == 0: 

67 tr_data.lang = clean_node(wxr, None, node) 

68 if isinstance(node, TemplateNode): 

69 tr_data.lang_code = node.template_name.lower() 

70 else: 

71 tr_data.lang_code = name_to_code(tr_data.lang_code, "de") 

72 elif isinstance(node, TemplateNode): 

73 if node.template_name.startswith("Ü"): 

74 if len(tr_data.word) > 0: 74 ↛ 75line 74 didn't jump to line 75 because the condition on line 74 was never true

75 tr_data = append_tr_data(word_entry, tr_data) 

76 process_u_template(wxr, tr_data, node) 

77 else: 

78 tr_data.raw_tags.append(clean_node(wxr, None, node)) 

79 elif isinstance(node, WikiNode) and node.kind == NodeKind.ITALIC: 

80 raw_tag_str = clean_node(wxr, None, node).removesuffix(":") 

81 for raw_tag in filter(None, raw_tag_str.split(", ")): 

82 tr_data.raw_tags.append(raw_tag) 

83 

84 if len(tr_data.word) > 0: 

85 append_tr_data(word_entry, tr_data) 

86 

87 

88def append_tr_data(word_entry: WordEntry, tr_data: Translation) -> Translation: 

89 translate_raw_tags(tr_data) 

90 word_entry.translations.append(tr_data.model_copy(deep=True)) 

91 return Translation( 

92 sense=tr_data.sense, 

93 sense_index=tr_data.sense_index, 

94 lang=tr_data.lang, 

95 lang_code=tr_data.lang_code, 

96 ) 

97 

98 

99def process_u_template( 

100 wxr: WiktextractContext, tr_data: Translation, u_template: TemplateNode 

101) -> None: 

102 # https://de.wiktionary.org/wiki/Vorlage:Ü 

103 # also "Ü?", "Üt", "Üt?", "Üxx4", "Üxx4?" 

104 if len(tr_data.lang_code) == 0: 

105 tr_data.lang_code = clean_node( 

106 wxr, None, u_template.template_parameters.get(1, "") 

107 ) 

108 if len(tr_data.lang) == 0: 108 ↛ 109line 108 didn't jump to line 109 because the condition on line 108 was never true

109 tr_data.lang = code_to_name(tr_data, "de") 

110 

111 tr_data.word = clean_node( 

112 wxr, None, u_template.template_parameters.get(2, "") 

113 ) 

114 template_name = u_template.template_name 

115 tr_data.uncertain = template_name.endswith("?") 

116 template_name = template_name.removesuffix("?") 

117 display_arg = -1 

118 if template_name == "Ü": 

119 display_arg = 3 

120 elif template_name == "Üt": 120 ↛ 132line 120 didn't jump to line 132 because the condition on line 120 was always true

121 display_arg = 4 

122 if 3 in u_template.template_parameters: 

123 tr_data.roman = clean_node( 

124 wxr, None, u_template.template_parameters.get(3, "") 

125 ) 

126 else: 

127 # this template could create roman without the third arg 

128 expanded_text = clean_node(wxr, None, u_template) 

129 m = re.search(r"\(([^)]+?)\^\☆\)", expanded_text) 

130 if m is not None: 130 ↛ 140line 130 didn't jump to line 140 because the condition on line 130 was always true

131 tr_data.roman = m.group(1) 

132 elif template_name == "Üxx4": 

133 display_arg = "v" 

134 if 3 in u_template.template_parameters: 

135 display_arg = 3 

136 tr_data.roman = clean_node( 

137 wxr, None, u_template.template_parameters.get("d", "") 

138 ) 

139 

140 tr_word = clean_node( 

141 wxr, None, u_template.template_parameters.get(display_arg, "") 

142 ) 

143 if len(tr_word) > 0: 143 ↛ 144line 143 didn't jump to line 144 because the condition on line 143 was never true

144 tr_data.word = tr_word