Commit 19eed79a authored by Jan Reimes's avatar Jan Reimes
Browse files

feat(database): update TDocMetadata initialization with default values 

- Set required fields with default values in TDocMetadata.
- Use 0 as a placeholder for meeting_id.
- Provide default values for title, contact, tdoc_type, and agenda_item_text.
- Ensure optional fields are clearly defined.
parent 2ac47377

src/tdoc_crawler/database/connection.py

+17 −16
Original line number Diff line number Diff line
@@ -5,6 +5,7 @@ from __future__ import annotations 
from collections import defaultdict

from collections.abc import Callable, Iterable

from datetime import UTC, datetime

from decimal import Decimal

from pathlib import Path



from pydantic_sqlite import DataBase
@@ -87,7 +88,7 @@ class TDocDatabase: 
                        try:

                            if "T" in value and value.endswith(("Z", "+00:00")):

                                row_dict[key] = datetime.fromisoformat(value)

                        except ValueError, AttributeError:

                        except (ValueError, AttributeError):

                            pass

                result.append(model_class(**row_dict))

            return result
@@ -326,21 +327,21 @@ class TDocDatabase: 
        metadata = TDocMetadata(

            tdoc_id=tdoc_id,

            url=url,

            meeting_id=None,

            file_size=None,

            title=None,

            contact=None,

            tdoc_type=None,

            for_purpose=None,

            agenda_item=None,

            status=None,

            is_revision_of=None,

            document_type=None,

            checksum=None,

            source_path=None,

            date_created=None,

            validated=False,

            validation_failed=True,

            meeting_id=0,  # Required field, use 0 as placeholder

            title="Unknown",  # Required field

            contact="Unknown",  # Required field

            source="Unknown",  # Required field

            tdoc_type="unknown",  # Required field with default

            for_purpose="unknown",  # Required field with default

            agenda_item_nbr=Decimal("0.0"),  # Required field

            agenda_item_text="Unknown",  # Required field with default

            status=None,  # Optional field

            meeting_name=None,  # Optional field

            is_revision_of=None,  # Optional field

            file_size=None,  # Optional field

            date_created=None,  # Optional field

            validated=False,  # Required field with default

            validation_failed=True,  # Required field with default

        )

        self.connection.add("tdocs", metadata.model_copy(update={"date_updated": utc_now()}), pk="tdoc_id")