Coverage for src/wiktextract/extractor/simple/etymology.py: 65%

1from wikitextprocessor import WikiNode 

2from wikitextprocessor.core import TemplateArgs 

3from wikitextprocessor.parser import LEVEL_KIND_FLAGS 

4 

5from wiktextract import WiktextractContext 

6from wiktextract.clean import clean_value 

7from wiktextract.page import clean_node 

8 

9from .models import TemplateData, WordEntry 

10from .parse_utils import ETYMOLOGY_TEMPLATES, PANEL_TEMPLATES 

11 

12 

13def process_etym( 

14 wxr: WiktextractContext, 

15 node: WikiNode, 

16 target_data: WordEntry, 

17) -> None: 

18 """Extract etymological data from section.""" 

19 # Get everything except subsections. 

20 etym_nodes = list(node.invert_find_child(LEVEL_KIND_FLAGS)) 

21 etym_templates = [] 

22 

23 # A post-template_fn already has the expanded string from the template. 

24 # If we'd want to suppress something without bothering to expand it, 

25 # we can use a normal template_fn and return an empty string there. 

26 # But returning an empty string here will also do the same thing. 

27 # Returning None means "use whatever we expanded", default behavior. 

28 def post_etym_template_fn( 

29 name: str, ht: TemplateArgs, expanded: str 

30 ) -> str | None: 

31 lname = name.lower().strip() 

32 if lname in PANEL_TEMPLATES: 32 ↛ 33line 32 didn't jump to line 33 because the condition on line 32 was never true

33 return "" 

34 if lname in ETYMOLOGY_TEMPLATES: 34 ↛ 37line 34 didn't jump to line 37 because the condition on line 34 was never true

35 # there are a bunch of clean_ functions: clean_value is to remove 

36 # italics and html tags and stuff like that from strings. 

37 expanded = clean_value(wxr, expanded) 

38 new_args = {} 

39 for k, v in ht.items(): 

40 new_args[str(k)] = str(v) 

41 tdata = TemplateData(name=name, args=new_args, expansion=expanded) 

42 etym_templates.append(tdata) 

43 return None 

44 

45 links: list[tuple[str, str]] = [] 

46 etym_text = clean_node( 

47 wxr, 

48 target_data, 

49 etym_nodes, 

50 post_template_fn=post_etym_template_fn, 

51 link_collector=links, 

52 ) 

53 

54 if etym_text: 54 ↛ exitline 54 didn't return from function 'process_etym' because the condition on line 54 was always true

55 target_data.etymology_text = etym_text 

56 target_data.etymology_links = links 

57 if etym_templates: 57 ↛ 58line 57 didn't jump to line 58 because the condition on line 57 was never true

58 target_data.etymology_templates = etym_templates 

59 

60 # logprint = [] 

61 # for t in etym_templates: 

62 # logprint.append(f"=== {t.name}") 

63 # lp = '\n'.join(logprint) 

64 # logger.info(f"{wxr.wtp.title}\n{lp}")