feat: Add default handling for missing column_io_type in header building

Author: Zalfsten

middleware/sql_to_arc/src/middleware/sql_to_arc/builder.py

@@ -175,6 +175,14 @@ def _build_header(key: tuple[Any, ...]) -> CompositeHeader | None:
     try:
         oa = OntologyAnnotation(c_ann_term or "", c_ann_uri or "", c_ann_ver or "")
 
+        if c_type in {"input", "output"} and not c_io:
+            default_io = "source_name" if c_type == "input" else "sample_name"
+            logger.warning(
+                "column_io_type missing for column_type '%s'; defaulting to '%s'",
+                c_type,
+                default_io,
+            )
+
         # Dispatch table for different header types
         handlers = {
             "input": lambda: CompositeHeader.input(IOType.of_string(c_io or "source_name")),

middleware/sql_to_arc/src/middleware/sql_to_arc/models.py

@@ -1,14 +1,11 @@
 """Data models for the SQL-to-ARC conversion process."""
 
-import logging
 from datetime import datetime
 from typing import Any, ClassVar, Literal
 
 from pydantic import BaseModel, ConfigDict, Field, Json, model_validator
 from pydantic_core import PydanticUndefined
 
-logger = logging.getLogger(__name__)
-
 # JSON types representing the expected structure after parsing
 type JsonList = list[Any]
 
@@ -189,13 +186,3 @@ class AnnotationTableRow(BaseRow):
     cell_annotation_term: str | None = spec_field(default=None)
     cell_annotation_uri: str | None = spec_field(default=None)
     cell_annotation_version: str | None = spec_field(default=None)
-
-    @model_validator(mode="after")
-    def validate_column_io_type(self) -> "AnnotationTableRow":
-        """Warn when column_io_type is absent for input/output columns."""
-        if self.column_type in {"input", "output"} and not self.column_io_type:
-            logger.warning(
-                "column_io_type is required when column_type is '%s' but was not provided",
-                self.column_type,
-            )
-        return self