Coverage for src/wiktextract/extractor/pt/head_line.py: 96%

1from wikitextprocessor import NodeKind, TemplateNode, WikiNode 

2 

3from ...page import clean_node 

4from ...wxr_context import WiktextractContext 

5from .models import 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 for node in nodes: 

15 if isinstance(node, TemplateNode): 

16 match node.template_name: 

17 case "g" | "gramática": 

18 extract_gramática_template(wxr, word_entry, node) 

19 

20 

21def extract_gramática_template( 

22 wxr: WiktextractContext, 

23 word_entry: WordEntry, 

24 t_node: TemplateNode, 

25) -> None: 

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

27 expanded_node = wxr.wtp.parse( 

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

29 ) 

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

31 raw_tag = clean_node(wxr, None, italic_node) 

32 if raw_tag != "": 32 ↛ 30line 32 didn't jump to line 30 because the condition on line 32 was always true

33 word_entry.raw_tags.append(raw_tag) 

34 translate_raw_tags(word_entry)