Use fetch_arrow_table for explicitly typed data

.pre-commit-config.yaml

@@ -12,7 +12,7 @@ repos:
     -   id: check-added-large-files
     -   id: check-toml
 -   repo: https://github.com/python-poetry/poetry
-    rev: 2.2.0
+    rev: 2.2.1
     hooks:
     -   id: poetry-check
 -   repo: https://github.com/tox-dev/pyproject-fmt
@@ -42,7 +42,7 @@ repos:
     -   id: yamllint
         exclude: ".pre-commit-config.yaml"
 -   repo: https://github.com/psf/black
-    rev: 25.1.0
+    rev: 25.9.0
     hooks:
     -   id: black
 -   repo: https://github.com/asottile/blacken-docs
@@ -64,7 +64,7 @@ repos:
     hooks:
     -   id: vulture
 -   repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v1.18.1
+    rev: v1.18.2
     hooks:
     -   id: mypy
         exclude: >

cytotable/convert.py

@@ -101,7 +101,7 @@ def _get_table_columns_and_types(
                 ddb_reader.execute(
                     select_query.replace("&select_source", select_source)
                 )
-                .arrow()
+                .fetch_arrow_table()
                 .to_pylist()
             )
 
@@ -122,7 +122,7 @@ def _get_table_columns_and_types(
                     ddb_reader.execute(
                         select_query.replace("&select_source", "arrow_data_tbl")
                     )
-                    .arrow()
+                    .fetch_arrow_table()
                     .to_pylist()
                 )
         else:
@@ -509,7 +509,7 @@ def _source_pageset_to_parquet(
                     /* optional ordering per pageset */
                     {"ORDER BY " + source['page_key'] if sort_output else ""};
                     """
-                ).arrow(),
+                ).fetch_arrow_table(),
                 where=result_filepath,
             )
     # Include exception handling to read mixed-type data
@@ -925,7 +925,7 @@ def _join_source_pageset(
             /* optional sorting per pagset */
             {"ORDER BY " + page_key if sort_output else ""};
             """
-        ).arrow()
+        ).fetch_arrow_table()
 
     # drop nulls if specified
     if drop_null:

cytotable/sources.py

@@ -134,7 +134,7 @@ def _get_source_filepaths(
                         """,
                         parameters=[str(element["source_path"])],
                     )
-                    .arrow()["table_name"]
+                    .fetch_arrow_table()["table_name"]
                     .to_pylist()
                     # make sure the table names match with compartment + metadata names
                     if targets is not None

tests/conftest.py

@@ -500,7 +500,7 @@ def col_renames(name: str, table: pa.Table):
                 AND nuclei.Metadata_ObjectNumber = cytoplasm.Metadata_Cytoplasm_Parent_Nuclei
         """
         )
-        .arrow()
+        .fetch_arrow_table()
     )
 
     # reversed order column check as col removals will change index order
@@ -566,7 +566,7 @@ def fixture_cellprofiler_merged_nf1data(
                 AND nuclei.Nuclei_Number_Object_Number = cytoplasm.Cytoplasm_Parent_Nuclei
         """
         )
-        .arrow()
+        .fetch_arrow_table()
         .drop_null()
     )
 

tests/data/in-carta/colas-lab/shrink_colas_lab_data_for_tests.py

@@ -29,7 +29,7 @@
                     FROM read_csv_auto('{data_file}')
                     """
                 )
-                .arrow()
+                .fetch_arrow_table()
                 .schema,
             }
         )
@@ -65,7 +65,7 @@
                 /* select rows C and D to limit the dataset */
                 AND data_file."ROW" in ('C', 'D')
                 """
-            ).arrow(),
+            ).fetch_arrow_table(),
             # output the filtered data as a CSV to a new location
             output_file=(
                 f"{TARGET_DATA_DIR}/{OUTPUT_FILENAME}"

tests/test_convert.py

@@ -691,7 +691,7 @@ def test_run_export_workflow(
                 ignore_errors=TRUE)
                 """
             )
-            .arrow()
+            .fetch_arrow_table()
         )
         parquet_result = parquet.ParquetDataset(
             path_or_paths=flattened_result["table"],
@@ -756,7 +756,7 @@ def test_run_export_workflow_unsorted(
                 ignore_errors=TRUE)
                 """
             )
-            .arrow()
+            .fetch_arrow_table()
         )
         parquet_result = parquet.ParquetDataset(
             path_or_paths=flattened_result["table"],
@@ -1354,7 +1354,7 @@ def test_in_carta_to_parquet(
                 SELECT *
                 FROM read_csv_auto('{data_dir}/*.csv')
                 """
-            ).arrow()
+            ).fetch_arrow_table()
 
         # process the data with cytotable using in-carta preset
         cytotable_result = convert(