Coverage for src/wiktextract/extractor/de/example.py: 85%
80 statements
« prev ^ index » next coverage.py v7.9.0, created at 2025-06-13 07:43 +0000
1import re
3from wikitextprocessor import LevelNode, NodeKind, WikiNode
5from ...page import clean_node
6from ...wxr_context import WiktextractContext
7from ..share import calculate_bold_offsets
8from .models import Example, Sense, WordEntry
9from .tags import translate_raw_tags
10from .utils import extract_sense_index
12LITERATUR_TEMPLATE_ARGS = {
13 "autor": "author",
14 "a": "author",
15 "titel": "title",
16 "titelerg": "title_complement",
17 "auflage": "edition",
18 "verlag": "publisher",
19 "ort": "place",
20 "jahr": "year",
21 "seiten": "pages",
22 "isbn": "isbn",
23 "übersetzer": "translator",
24 "herausgeber": "editor",
25 "sammelwerk": "collection",
26 "werk": "collection",
27 "band": "volume",
28 "kommentar": "comment",
29 "online": "url",
30 "tag": "day",
31 "monat": "month",
32 "zugriff": "accessdate",
33 "nummer": "number",
34 "datum": "date",
35 "hrsg": "editor",
36}
39def extract_examples(
40 wxr: WiktextractContext,
41 word_entry: WordEntry,
42 level_node: LevelNode,
43) -> None:
44 last_example = None
45 raw_tags = []
46 for list_item_node in level_node.find_child_recursively(NodeKind.LIST_ITEM):
47 if not list_item_node.sarg.endswith(":"):
48 raw_tags.clear()
49 raw_tag = clean_node(wxr, None, list_item_node.children)
50 raw_tag = raw_tag.strip(": ")
51 if raw_tag != "": 51 ↛ 46line 51 didn't jump to line 46 because the condition on line 51 was always true
52 raw_tags.append(raw_tag)
53 else:
54 example_data = Example(raw_tags=raw_tags)
55 for ref_tag in list_item_node.find_html("ref"):
56 extract_reference(wxr, example_data, ref_tag)
57 example_text_node = wxr.wtp.parse(
58 wxr.wtp.node_to_wikitext(
59 list(list_item_node.invert_find_child(NodeKind.LIST))
60 )
61 )
62 example_text = clean_node(wxr, None, example_text_node)
63 sense_idx, example_text = extract_sense_index(example_text)
64 if len(example_text) > 0:
65 translate_raw_tags(example_data)
66 example_data.text = example_text
67 calculate_bold_offsets(
68 wxr,
69 example_text_node,
70 example_text,
71 example_data,
72 "italic_text_offsets",
73 extra_node_kind=NodeKind.ITALIC,
74 )
75 if len(sense_idx) > 0:
76 find_sense = False
77 for sense in word_entry.senses:
78 if match_sense_index(sense_idx, sense):
79 sense.examples.append(example_data)
80 find_sense = True
81 if not find_sense:
82 new_sense = Sense(
83 sense_index=sense_idx, tags=["no-gloss"]
84 )
85 new_sense.examples.append(example_data)
86 word_entry.senses.append(new_sense)
87 last_example = example_data
88 elif last_example is not None: 88 ↛ 99line 88 didn't jump to line 99 because the condition on line 88 was always true
89 last_example.translation = example_text
90 calculate_bold_offsets(
91 wxr,
92 example_text_node,
93 example_text,
94 example_data,
95 "italic_translation_offsets",
96 extra_node_kind=NodeKind.ITALIC,
97 )
98 else:
99 wxr.wtp.debug(
100 f"Found example data without senseid: {example_data}",
101 sortid="extractor/de/examples/extract_examples/28",
102 )
103 last_example = None
105 for non_list_node in level_node.invert_find_child(NodeKind.LIST): 105 ↛ 106line 105 didn't jump to line 106 because the loop on line 105 never started
106 wxr.wtp.debug(
107 f"Found unexpected non-list node in examples: {non_list_node}",
108 sortid="extractor/de/examples/extract_examples/33",
109 )
112def extract_reference(
113 wxr: WiktextractContext, example_data: Example, ref_node: WikiNode
114):
115 example_data.ref = clean_node(wxr, None, ref_node.children)
116 for template_node in ref_node.find_child(NodeKind.TEMPLATE):
117 if template_node.template_name == "Literatur":
118 # https://de.wiktionary.org/wiki/Vorlage:Literatur
119 for key, value in template_node.template_parameters.items():
120 if not isinstance(key, str):
121 continue
122 if key.lower() in LITERATUR_TEMPLATE_ARGS: 122 ↛ 128line 122 didn't jump to line 128 because the condition on line 122 was always true
123 field = LITERATUR_TEMPLATE_ARGS[key.lower()]
124 if field in example_data.model_fields: 124 ↛ 119line 124 didn't jump to line 119 because the condition on line 124 was always true
125 setattr(
126 example_data, field, clean_node(wxr, None, value)
127 )
128 elif isinstance(key, str):
129 wxr.wtp.debug(
130 f"Unexpected key in Literatur template: {key}",
131 sortid="extractor/de/examples/extract_examples/77",
132 )
134 # XXX: Treat other templates as well.
135 # E.g. https://de.wiktionary.org/wiki/Vorlage:Ref-OWID
138def match_sense_index(sense_idx: str, sense: Sense) -> bool:
139 exact_match = not (
140 "," in sense_idx or "-" in sense_idx or "." not in sense_idx
141 )
142 if exact_match: 142 ↛ 143line 142 didn't jump to line 143 because the condition on line 142 was never true
143 return sense_idx == sense.sense_index
145 if sense_idx == sense.sense_index:
146 return True
147 first_number_str = re.split(r",|\.|-|–", sense.sense_index, maxsplit=1)[0]
148 first_number = 0
149 if first_number_str.isdigit():
150 first_number = int(first_number_str)
151 else:
152 return False
154 for try_idx in sense_idx.split(","):
155 try_idx = try_idx.strip()
156 if try_idx == sense.sense_index:
157 return True
158 elif re.fullmatch(r"\d+[\-–]\d+", try_idx): 158 ↛ 159line 158 didn't jump to line 159 because the condition on line 158 was never true
159 start_str, end_str = re.split(r"-|–", try_idx, maxsplit=1)
160 if int(start_str) <= first_number and first_number <= int(end_str):
161 return True
163 return False