Coverage for src/wiktextract/extractor/zh/etymology.py: 85%

1from wikitextprocessor.parser import ( 

2 LEVEL_KIND_FLAGS, 

3 NodeKind, 

4 TemplateNode, 

5 WikiNode, 

6) 

7 

8from ...page import clean_node 

9from ...wxr_context import WiktextractContext 

10from .models import Example, WordEntry 

11 

12 

13def extract_etymology( 

14 wxr: WiktextractContext, 

15 page_data: list[WordEntry], 

16 base_data: WordEntry, 

17 level_node: WikiNode, 

18) -> None: 

19 from .example import extract_template_zh_x 

20 

21 etymology_nodes = [] 

22 level_node_index = len(level_node.children) 

23 for next_level_index, next_level_node in level_node.find_child( 23 ↛ 26line 23 didn't jump to line 26 because the loop on line 23 never started

24 LEVEL_KIND_FLAGS, True 

25 ): 

26 level_node_index = next_level_index 

27 break 

28 for etymology_node in level_node.children[:level_node_index]: 

29 if isinstance( 

30 etymology_node, TemplateNode 

31 ) and etymology_node.template_name in ["zh-x", "zh-q"]: 

32 for example_data in extract_template_zh_x( 

33 wxr, etymology_node, Example() 

34 ): 

35 base_data.etymology_examples.append(example_data) 

36 clean_node(wxr, base_data, etymology_node) 

37 elif ( 37 ↛ 41line 37 didn't jump to line 41

38 isinstance(etymology_node, TemplateNode) 

39 and etymology_node.template_name.lower() == "rfe" 

40 ): 

41 pass # missing etymology 

42 elif ( 

43 isinstance(etymology_node, WikiNode) 

44 and etymology_node.kind == NodeKind.LIST 

45 ): 

46 has_zh_x = False 

47 for template_node in etymology_node.find_child_recursively( 

48 NodeKind.TEMPLATE 

49 ): 

50 if template_node.template_name in ["zh-x", "zh-q"]: 

51 has_zh_x = True 

52 for example_data in extract_template_zh_x( 

53 wxr, template_node, Example() 

54 ): 

55 base_data.etymology_examples.append(example_data) 

56 clean_node(wxr, base_data, template_node) 

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

58 etymology_nodes.append(etymology_node) 

59 else: 

60 etymology_nodes.append(etymology_node) 

61 

62 etymology_text = clean_node(wxr, base_data, etymology_nodes) 

63 if len(etymology_text) > 0: 63 ↛ exitline 63 didn't return from function 'extract_etymology' because the condition on line 63 was always true

64 base_data.etymology_text = etymology_text