Set extra='forbid' and remove pydantic logging in 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/models.py

@@ -1,49 +1,14 @@
 import json
-import logging
-from typing import Optional
 
 from pydantic import BaseModel, ConfigDict, Field, model_validator
 from pydantic.json_schema import GenerateJsonSchema
 
-from wiktextract.wxr_context import WiktextractContext
-
-
-class PydanticLogger:
-    wxr: Optional[WiktextractContext] = None
-
-    @classmethod
-    def debug(
-        cls, msg: str, trace: Optional[str] = None, sortid: str = "XYZunsorted"
-    ):
-        if cls.wxr:
-            cls.wxr.wtp.debug(msg, trace=trace, sortid=sortid)
-        else:
-            logging.debug(msg)
-
 
 class BaseModelWrap(BaseModel):
-    model_config = ConfigDict(validate_assignment=True)
-
-
-class LoggingExtraFieldsModel(BaseModelWrap):
-    @model_validator(mode="before")
-    def log_extra_fields(cls, values):
-        all_allowed_field_names = cls.model_fields.keys()
-        extra_fields = {
-            name: str(value)
-            for name, value in values.items()
-            if name not in all_allowed_field_names
-        }
-        if extra_fields:
-            class_full_name = cls.__name__
-            PydanticLogger.debug(
-                msg=f"Pydantic - Got extra fields in {class_full_name}: {extra_fields}",
-                sortid="wiktextract/extractor/es/pydantic/extra_fields/33",
-            )
-        return values
+    model_config = ConfigDict(validate_assignment=True, extra="forbid")
 
 
-class WordEntry(LoggingExtraFieldsModel):
+class WordEntry(BaseModelWrap):
     """WordEntry is a dictionary containing lexical information of a single word extracted from Wiktionary with wiktextract."""
 
     word: str = Field(description="word string")

src/wiktextract/extractor/ru/page.py

@@ -4,7 +4,7 @@
 
 from wikitextprocessor import NodeKind, WikiNode
 
-from wiktextract.extractor.ru.models import PydanticLogger, WordEntry
+from wiktextract.extractor.ru.models import WordEntry
 from wiktextract.extractor.ru.pronunciation import extract_pronunciation
 from wiktextract.page import clean_node
 from wiktextract.wxr_context import WiktextractContext
@@ -153,8 +153,6 @@ def parse_page(
 
     if wxr.config.verbose:
         logging.info(f"Parsing page: {page_title}")
-        # Pass current wiktextractcontext to pydantic for more better logging
-        PydanticLogger.wxr = wxr
 
     wxr.config.word = page_title
     wxr.wtp.start_page(page_title)