Coverage for src/wiktextract/extractor/pt/head_line.py: 90%

1from wikitextprocessor import NodeKind, TemplateNode, WikiNode 

2 

3from ...page import clean_node 

4from ...wxr_context import WiktextractContext 

5from .models import Form, WordEntry 

6from .tags import translate_raw_tags 

7 

8 

9def extract_head_line_nodes( 

10 wxr: WiktextractContext, 

11 word_entry: WordEntry, 

12 nodes: list[WikiNode | str], 

13) -> None: 

14 is_first_bold = True 

15 for node in nodes: 

16 if isinstance(node, TemplateNode) and node.template_name in [ 

17 "g", 

18 "gramática", 

19 "gênero", 

20 "m", 

21 "f", 

22 "n", 

23 "c", 

24 "c2g", 

25 "pr", 

26 "c.", 

27 "fp", 

28 "mp", 

29 ]: 

30 extract_gramática_template(wxr, word_entry, node) 

31 elif isinstance(node, TemplateNode) and node.template_name == "datação": 31 ↛ 32line 31 didn't jump to line 32 because the condition on line 31 was never true

32 from .etymology import extract_defdate_template 

33 

34 word_entry.attestations.extend( 

35 extract_defdate_template(wxr, word_entry, node) 

36 ) 

37 elif ( 

38 isinstance(node, WikiNode) 

39 and node.kind == NodeKind.BOLD 

40 and is_first_bold 

41 ): 

42 extract_head_line_bold_node(wxr, word_entry, node) 

43 is_first_bold = False 

44 

45 

46def extract_gramática_template( 

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

48) -> None: 

49 # https://pt.wiktionary.org/wiki/Predefinição:gramática 

50 expanded_node = wxr.wtp.parse( 

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

52 ) 

53 for italic_node in expanded_node.find_child(NodeKind.ITALIC): 

54 raw_tag = clean_node(wxr, None, italic_node) 

55 if raw_tag != "": 55 ↛ 53line 55 didn't jump to line 53 because the condition on line 55 was always true

56 word_entry.raw_tags.append(raw_tag) 

57 translate_raw_tags(word_entry) 

58 

59 

60def extract_head_line_bold_node( 

61 wxr: WiktextractContext, word_entry: WordEntry, bold_node: WikiNode 

62): 

63 word = clean_node(wxr, None, bold_node) 

64 if word != "" and word != wxr.wtp.title: 

65 word_entry.forms.append(Form(form=word, tags=["canonical"]))