CAN-24: Fix ValueError when reading adats with Empty RFUs

Author: kyoung73

README.md

@@ -53,8 +53,8 @@ pip install -e ./somadata
 
 ### Dependencies
 
-`Python >=3.8` is required to install `somadata`. The following package dependencies are installed on a `pip install`:
-  - `pandas >= 1.1.0`
+`Python >=3.9` is required to install `somadata`. The following package dependencies are installed on a `pip install`:
+  - `pandas >= 1.1.2`
   - `numpy >= 1.19.1`
 
 [return to top](#toptoc)

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "somadata"
-version = "1.2.1"
+version = "1.2.2"
 description = "SomaLogic Python Data Input/Output Library"
 authors = [
     "Joseph Allison",

somadata/io/adat/file.py

@@ -46,8 +46,8 @@ def parse_file(
     """
     if type(f) == str:
         f = open(f, 'r')
-    elif type(f) != io.TextIOWrapper:
-        raise AdatReadError('File must be a string or file object.')
+    elif not hasattr(f, 'read'):
+        raise AdatReadError('File must be a string or file-like object.')
 
     current_section = None
 
@@ -161,9 +161,16 @@ def parse_file(
             elif matrix_depth > col_metadata_length:
                 # Store in row metadata into dictionary
                 row_metadata_data = line[:row_metadata_offset]
+                # Check for missing metadata and handle it
+                if len(row_metadata_data) < len(row_metadata_names):
+                    missing_count = len(row_metadata_names) - len(row_metadata_data)
+                    logging.warning(
+                        f"Row metadata has {missing_count} missing values. "
+                        f"Filling missing entries with empty strings."
+                    )
+                    row_metadata_data = list(row_metadata_data) + [""] * missing_count
                 for name, data in zip(row_metadata_names, row_metadata_data):
                     row_metadata[name].append(data)
-
                 # Store the RFU data
                 rfu_row_data = line[row_metadata_offset + 1 :]
                 converted_rfu_row_data = list(map(float, rfu_row_data))

tests/conftest.py

@@ -0,0 +1,33 @@
+import csv
+from pathlib import Path
+
+import numpy as np
+import pytest
+
+import somadata as sd
+
+
+@pytest.fixture(scope="session")
+def control_data_path() -> str:
+    return str(Path(__file__).parent / 'data' / 'control_data.adat')
+
+
+@pytest.fixture(scope="session")
+def control_data(control_data_path: str) -> sd.Adat:
+    return sd.read_adat(control_data_path)
+
+
+@pytest.fixture(scope="session")
+def missing_rfu_adat_path(control_data_path: str, tmp_path_factory) -> str:
+    fn = str(tmp_path_factory.mktemp("data") / "missing_rfu_test.adat")
+    # Read ADAT as TSV
+    with open(control_data_path, "r", newline="", encoding="utf-8") as f:
+        reader = [row for row in csv.reader(f, delimiter="\t")]
+    # Modify only the last row
+    if reader:
+        reader[-1] = reader[-1][:33]  # Keep only the first 33 columns (up to column AG)
+    # Write back to the file while preserving tab delimiters
+    with open(fn, "w", newline="", encoding="utf-8") as f:
+        writer = csv.writer(f, delimiter="\t")
+        writer.writerows(reader)
+    return fn

tests/io/adat/__init__.py

@@ -0,0 +1,50 @@
+import io
+import logging
+
+import pytest
+
+from somadata.io.adat.file import parse_file
+
+
+def test_parse_file_with_missing_row_metadata(missing_rfu_adat_path: str, caplog):
+    with caplog.at_level(logging.WARNING):
+        rfu_matrix, row_metadata, column_metadata, header_metadata = parse_file(
+            missing_rfu_adat_path
+        )
+
+    # Assert that the warning was logged about missing row metadata
+    warning_message = (
+        "Row metadata has 3 missing values. Filling missing entries with empty strings."
+    )
+    assert any(
+        warning_message in record.message for record in caplog.records
+    ), "Expected warning about missing row metadata not found."
+
+    # Verify row_metadata structure is correctly filled
+    # First row is fine
+    assert row_metadata["ANMLFractionUsed_20"] == [
+        '',
+        '',
+        '0.817',
+        '',
+        '',
+        '0.791',
+        '',
+        '',
+        '',
+        '0.832',
+        '',
+    ]
+    assert row_metadata["ANMLFractionUsed_0_5"] == [
+        '',
+        '',
+        '0.836',
+        '',
+        '',
+        '0.829',
+        '',
+        '',
+        '',
+        '0.840',
+        '',
+    ]