Implement code review suggestions for Russian Wiktionary

This work is a contribution to the EWOK project, which receives funding from LABEX ASLAN (ANR–10–LABX–0081) at the Université de Lyon, as part of the "Investissements d'Avenir" program initiated and overseen by the Agence Nationale de la Recherche (ANR) in France.

src/wiktextract/extractor/ru/example.py

@@ -13,6 +13,11 @@
     "ответственный": "editor",
     "перев": "translator",
     "источник": "source",
+    2: "author",
+    3: "title",
+    4: "date",
+    5: "collection",
+    6: "date_published",
 }
 
 
@@ -27,21 +32,11 @@ def process_example_template(
         value = clean_node(wxr, {}, value_raw).strip()
         if not value:
             continue
-        if isinstance(key, int):
-            if int(key) == 1:
-                example.text = value
-            elif int(key) == 2:
-                reference.author = value
-            elif int(key) == 3:
-                reference.title = value
-            elif int(key) == 4:
-                reference.date = value
-            elif int(key) == 5:
-                reference.collection = value
-            elif int(key) == 6:
-                reference.date_published = value
+        if isinstance(key, int) and key == 1:
+            example.text = value
+
         else:
-            key = clean_node(wxr, {}, key)
+            key = clean_node(wxr, {}, key) if not isinstance(key, int) else key
             if key == "текст":
                 example.text = value
             elif key == "перевод":

src/wiktextract/extractor/ru/models.py

@@ -39,38 +39,6 @@ class Sound(BaseModelWrap):
     )
 
 
-class Sense(BaseModelWrap):
-    raw_gloss: Optional[str] = Field(
-        default=None,
-        description="Raw gloss string for the word sense. This might contain tags and other markup.",
-    )
-    gloss: Optional[str] = Field(
-        default=None,
-        description="Gloss string for the word sense. This has been cleaned, and should be straightforward text with no tags.",
-    )
-    tags: list[str] = Field(
-        default=[],
-        description="List of tags affecting the word sense.",
-    )
-    notes: list[str] = Field(
-        default=[],
-        description="List of notes for the word sense. Usually describing usage.",
-    )
-    categories: list[str] = Field(
-        default=[],
-        description="list of sense-disambiguated category names extracted from (a subset) of the Category links on the page",
-    )
-    examples: list["Example"] = Field(
-        default=[], description="List of examples"
-    )
-    # subsenses: list["Sense"] = Field(
-    #     default=[], description="List of subsenses"
-    # )
-    # senseid: Optional[int] = Field(
-    #     default=None, description="Sense number used in Wiktionary"
-    # )
-
-
 class Reference(BaseModelWrap):
     author: Optional[str] = Field(default=None, description="Author's name")
     title: Optional[str] = Field(
@@ -100,7 +68,31 @@ class Example(BaseModelWrap):
     translation: Optional[str] = Field(
         default=None, description="Spanish translation of the example sentence"
     )
-    ref: Optional["Reference"] = Field(default=None, description="")
+    ref: Optional[Reference] = Field(default=None, description="")
+
+
+class Sense(BaseModelWrap):
+    raw_gloss: Optional[str] = Field(
+        default=None,
+        description="Raw gloss string for the word sense. This might contain tags and other markup.",
+    )
+    gloss: Optional[str] = Field(
+        default=None,
+        description="Gloss string for the word sense. This has been cleaned, and should be straightforward text with no tags.",
+    )
+    tags: list[str] = Field(
+        default=[],
+        description="List of tags affecting the word sense.",
+    )
+    notes: list[str] = Field(
+        default=[],
+        description="List of notes for the word sense. Usually describing usage.",
+    )
+    categories: list[str] = Field(
+        default=[],
+        description="list of sense-disambiguated category names extracted from (a subset) of the Category links on the page",
+    )
+    examples: list[Example] = Field(default=[], description="List of examples")
 
 
 class WordEntry(BaseModelWrap):

src/wiktextract/extractor/ru/page.py

@@ -198,7 +198,6 @@ def parse_page(
                 wxr.config.capture_language_codes is not None
                 and lang_code not in wxr.config.capture_language_codes
             ):
-                print(f"Skipping language {lang_code}")
                 continue
 
             categories = {"categories": []}

tests/test_ru_example.py

@@ -43,11 +43,11 @@ def test_ru_extract_example(self):
             },
             # https://ru.wiktionary.org/wiki/house
             {
-                "input": "{{пример|This is my {{выдел|house}} and my family’s ancestral home.||перевод=Это мой {{выдел|дом}} и поселение моих семейных предков.}}",
+                "input": "{{пример|This is my house and my family’s ancestral home.||перевод=Это мой дом и поселение моих семейных предков.}}",
                 "expected": [
                     {
-                        "text": "This is my and my family’s ancestral home.",
-                        "translation": "Это мой и поселение моих семейных предков.",
+                        "text": "This is my house and my family’s ancestral home.",
+                        "translation": "Это мой дом и поселение моих семейных предков.",
                     }
                 ],
             },