Temp commit

src/wiktextract/extractor/en/page.py

@@ -681,7 +681,7 @@ def parse_sense_linkage(
         w = clean_node(wxr, data, w)
         for alias in ns_title_prefix_tuple(wxr, "Thesaurus"):
             if w.startswith(alias):
-                w = w[len(alias):]
+                w = w[len(alias) :]
                 break
         if not w:
             break
@@ -795,8 +795,7 @@ def merge_base(data: WordData, base: WordData) -> None:
                     sortid="page/904",
                 )
 
-        def complementary_pop(pron: WordData, key: str
-        ) -> WordData:
+        def complementary_pop(pron: WordData, key: str) -> WordData:
             """Remove unnecessary keys from dict values
             in a list comprehension..."""
             if key in pron:
@@ -807,7 +806,9 @@ def complementary_pop(pron: WordData, key: str
         # does not match "word" or one of "forms"
         if "sounds" in data and "word" in data:
             accepted = [data["word"]]
-            accepted.extend(f["form"] for f in data.get("forms", dict()))  # type:ignore
+            accepted.extend(
+                f["form"] for f in data.get("forms", dict())  # type:ignore
+            )
             data["sounds"] = list(
                 s
                 for s in data["sounds"]  # type:ignore
@@ -822,7 +823,7 @@ def complementary_pop(pron: WordData, key: str
                 if "pos" not in s or s["pos"] == data["pos"]  # type:ignore
             )
 
-    def push_sense():
+    def push_sense() -> bool:
         """Starts collecting data for a new word sense.  This returns True
         if a sense was added."""
         nonlocal sense_data

src/wiktextract/type_utils.py

@@ -1,14 +1,56 @@
 from typing import (
+    TypedDict,
     Union,
 )
 
 
-WordData = dict[str, Union[
-                           str,
-                           int,
-                           list[str],
-                           list[list[str]],
-                           "WordData",
-                           list["WordData"]
-                        ]
-                ]
+# WordData = dict[str, Union[
+#                            str,
+#                            int,
+#                            list[str],
+#                            list[list[str]],
+#                            "WordData",
+#                            list["WordData"]
+#                         ]
+#                 ]
+
+class WordData(TypedDict, total=False):
+    word: str
+    etymology_number: int
+    etymology_text: str
+    hyphenation: str
+    lang: str
+    lang_code: str
+    original_title: str
+    pos: str
+    source: str
+
+    categories: list[str]
+    redirects: list[str]
+    topics: list[str]
+    wikidata: list[WikidataReference]
+    wikipedia: list[WikipediaReference]
+
+    abbreviations: list[Abbreviation]
+    alt_of: list[Alt]
+    antonym: list[Antonym]
+    coordinate_terms: list[CoordinateTerm]
+    derived: list[Derived]
+    descendants: list[Descendant]
+    etymology_templates: list[EtymologyTemplate]
+    form_of: list[OriginalForm]
+    forms: list[Form]
+    head_templates: list[HeadTemplate]
+    holonyms: list[Holonym]
+    hypernyms: list[Hypernym]
+    hyponyms: list[Hyponym]
+    inflection_templates: list[InflectionTemplate]
+    instances: list[Instance]
+    meronyms: list[Meronym]
+    proverbs: list[Proverb]
+    related: list[Related]
+    senses: list[Sense]
+    sounds: list[Sound]
+    synonyms: list[Synonym]
+    translations: list[Translation]
+    troponyms: list[Troponym]