src/catalog/validator.py

"""CatalogValidator — Pydantic + business-rule validation for a catalog.

Pydantic handles shape; this layer adds invariants that span fields.
"""

from .models import Catalog


class CatalogValidationError(Exception):
    pass


class CatalogValidator:
    """Validates a Catalog beyond Pydantic schema checks.

    Business rules:
    - All source_ids unique within a user
    - All table_ids unique within a source
    - All column_ids unique within a table
    - foreign_keys (when added) reference existing tables/columns
    """

    def validate(self, catalog: Catalog) -> None:
        seen_sources: set[str] = set()
        for source in catalog.sources:
            if source.source_id in seen_sources:
                raise CatalogValidationError(
                    f"duplicate source_id {source.source_id!r} in catalog "
                    f"for user_id={catalog.user_id!r}"
                )
            seen_sources.add(source.source_id)

            seen_tables: set[str] = set()
            for table in source.tables:
                if table.table_id in seen_tables:
                    raise CatalogValidationError(
                        f"duplicate table_id {table.table_id!r} in source "
                        f"{source.source_id!r}"
                    )
                seen_tables.add(table.table_id)

                seen_columns: set[str] = set()
                for column in table.columns:
                    if column.column_id in seen_columns:
                        raise CatalogValidationError(
                            f"duplicate column_id {column.column_id!r} in table "
                            f"{table.table_id!r} (source {source.source_id!r})"
                        )
                    seen_columns.add(column.column_id)