Address style issues.

Author: tsalo

docs/conf.py

@@ -1,10 +1,10 @@
 # Configuration file for the Sphinx documentation builder.
 # https://www.sphinx-doc.org/en/master/usage/configuration.html
 
-from datetime import datetime
+from datetime import UTC, datetime
 
 project = 'ModelArrayIO'
-copyright = f'2017-{datetime.today().strftime("%Y")}, PennLINC developers'
+copyright = f'2017-{datetime.now(tz=UTC).strftime("%Y")}, PennLINC developers'
 author = 'PennLINC developers'
 
 extensions = [

src/modelarrayio/cifti.py

@@ -28,6 +28,8 @@
 from .tiledb_storage import write_column_names as tdb_write_column_names
 from .tiledb_storage import write_rows_in_column_stripes as tdb_write_stripes
 
+logger = logging.getLogger(__name__)
+
 
 def _cohort_to_long_dataframe(cohort_df, scalar_columns=None):
     scalar_columns = [col for col in (scalar_columns or []) if col]
@@ -448,9 +450,9 @@ def _h5_to_ciftis(example_cifti, h5_file, analysis_name, cifti_output_dir):
 
     try:
         results_names = names_data.tolist()
-    except Exception:
+    except (AttributeError, OSError, TypeError, ValueError):
         print("Unable to read column names, using 'componentNNN' instead")
-        results_names = ['component%03d' % (n + 1) for n in range(results_matrix.shape[0])]
+        results_names = [f'component{n + 1:03d}' for n in range(results_matrix.shape[0])]
 
     # Make output directory if it does not exist
     if not op.isdir(cifti_output_dir):
@@ -497,7 +499,7 @@ def h5_to_ciftis():
 
     # Get an example cifti
     if args.example_cifti is None:
-        logging.warning(
+        logger.warning(
             'No example cifti file provided, using the first cifti file from the cohort file'
         )
         cohort_df = pd.read_csv(args.cohort_file)

src/modelarrayio/fixels.py

@@ -455,9 +455,9 @@ def h5_to_mifs(example_mif, h5_file, analysis_name, fixel_output_dir):
 
     try:
         results_names = names_data.tolist()
-    except Exception:
+    except (AttributeError, OSError, TypeError, ValueError):
         print("Unable to read column names, using 'componentNNN' instead")
-        results_names = ['component%03d' % (n + 1) for n in range(results_matrix.shape[0])]
+        results_names = [f'component{n + 1:03d}' for n in range(results_matrix.shape[0])]
 
     # Make output directory if it does not exist
     if not op.isdir(fixel_output_dir):

src/modelarrayio/h5_storage.py

@@ -28,7 +28,7 @@ def resolve_compression(compression, compression_level, shuffle):
     if comp == 'gzip':
         try:
             gzip_level = int(compression_level)
-        except Exception:
+        except (TypeError, ValueError):
             gzip_level = 4
         gzip_level = max(0, min(9, gzip_level))
     return comp, gzip_level, use_shuffle

src/modelarrayio/s3_utils.py

@@ -27,7 +27,7 @@ def _make_s3_client():
     except ImportError:
         raise ImportError(
             'boto3 is required for s3:// paths. Install with: pip install modelarrayio[s3]'
-        )
+        ) from None
     anon = os.environ.get('MODELARRAYIO_S3_ANON', '').lower() in ('1', 'true', 'yes')
     if anon:
         from botocore import UNSIGNED

src/modelarrayio/tiledb_storage.py

@@ -29,7 +29,7 @@ def _build_filter_list(compression: str | None, compression_level: int | None, s
         level = None
         try:
             level = int(compression_level) if compression_level is not None else None
-        except Exception:
+        except (TypeError, ValueError):
             level = None
         if comp == 'zstd':
             filters.append(tiledb.ZstdFilter(level=level if level is not None else 5))
@@ -129,7 +129,7 @@ def create_scalar_matrix_array(
         if sources_list is not None:
             try:
                 A.meta['column_names'] = json.dumps(list(sources_list))
-            except Exception:
+            except (TypeError, ValueError, tiledb.TileDBError):
                 # Fallback without metadata if serialization fails
                 logger.warning('Failed to write column_names metadata for %s', uri)
     logger.info('Finished writing array %s', uri)
@@ -182,7 +182,7 @@ def create_empty_scalar_matrix_array(
         try:
             with tiledb.open(uri, 'w') as A:
                 A.meta['column_names'] = json.dumps(list(map(str, sources_list)))
-        except Exception:
+        except (TypeError, ValueError, tiledb.TileDBError):
             logger.warning('Failed to write column_names metadata for %s', uri)
     return uri
 
@@ -258,5 +258,5 @@ def write_column_names(base_uri: str, scalar: str, sources: Sequence[str]):
         try:
             with tiledb.Group(group_uri, 'w') as G:
                 G.meta['column_names'] = json.dumps(sources)
-        except Exception:
+        except (TypeError, ValueError, tiledb.TileDBError):
             logger.warning('Failed to write column_names metadata for group %s', group_uri)

src/modelarrayio/voxels.py

@@ -1,4 +1,5 @@
 import argparse
+import logging
 import os
 import os.path as op
 from collections import defaultdict
@@ -25,6 +26,8 @@
 from .tiledb_storage import create_empty_scalar_matrix_array as tdb_create_empty
 from .tiledb_storage import write_rows_in_column_stripes as tdb_write_stripes
 
+logger = logging.getLogger(__name__)
+
 
 def _load_cohort_voxels(cohort_df, group_mask_matrix, relative_root, s3_workers):
     """Load all voxel rows from the cohort, optionally in parallel.
@@ -137,7 +140,7 @@ def _decode_names(arr):
                 s = s.rstrip('\x00').strip()
                 out.append(s)
             return out
-        except Exception:
+        except (AttributeError, OSError, TypeError, ValueError):
             return None
 
     results_names = None
@@ -146,7 +149,7 @@ def _decode_names(arr):
         names_attr = results_matrix.attrs.get('colnames', None)
         if names_attr is not None:
             results_names = _decode_names(names_attr)
-    except Exception:
+    except (OSError, RuntimeError, TypeError, ValueError):
         results_names = None
 
     # 2) Fallback to dataset-based column names (new format)
@@ -162,13 +165,14 @@ def _decode_names(arr):
                     results_names = _decode_names(names_ds)
                     if results_names:
                         break
-                except Exception:
+                except (KeyError, OSError, RuntimeError, TypeError, ValueError):
+                    logger.debug('Could not read column names from %s', p, exc_info=True)
                     continue
 
     # 3) Final fallback to generated names
     if not results_names:
         print("Unable to read column names, using 'componentNNN' instead")
-        results_names = ['component%03d' % (n + 1) for n in range(results_matrix.shape[0])]
+        results_names = [f'component{n + 1:03d}' for n in range(results_matrix.shape[0])]
 
     # # Make output directory if it does not exist  # has been done in h5_to_volumes_wrapper()
     # if op.isdir(volume_output_dir) == False:

test/test_cifti_cli.py

@@ -76,7 +76,9 @@ def test_concifti_cli_creates_expected_hdf5(tmp_path):
         '1.0',
     ]
     env = os.environ.copy()
-    proc = subprocess.run(cmd, cwd=str(tmp_path), env=env, capture_output=True, text=True)
+    proc = subprocess.run(
+        cmd, cwd=str(tmp_path), env=env, capture_output=True, text=True, check=False
+    )
     assert proc.returncode == 0, f'concifti failed: {proc.stdout}\n{proc.stderr}'
     assert op.exists(out_h5)
 
@@ -103,7 +105,9 @@ def test_concifti_cli_creates_expected_hdf5(tmp_path):
         # Column names exist and match subjects count
         grp = h5['scalars/THICK']
         assert 'column_names' in grp
-        colnames = [x.decode('utf-8') if isinstance(x, bytes) else str(x) for x in grp['column_names'][...]]
+        colnames = [
+            x.decode('utf-8') if isinstance(x, bytes) else str(x) for x in grp['column_names'][...]
+        ]
         assert len(colnames) == 2
 
         # Spot-check a couple values

test/test_voxels_cli.py

@@ -61,7 +61,7 @@ def test_convoxel_cli_creates_expected_hdf5(tmp_path):
     with cohort_csv.open('w', newline='') as f:
         writer = csv.DictWriter(f, fieldnames=['scalar_name', 'source_file', 'source_mask_file'])
         writer.writeheader()
-        for sidx, (scalar_name, mask_name) in enumerate(subjects):
+        for _sidx, (scalar_name, mask_name) in enumerate(subjects):
             writer.writerow(
                 {
                     'scalar_name': 'FA',
@@ -98,7 +98,9 @@ def test_convoxel_cli_creates_expected_hdf5(tmp_path):
         '1.0',
     ]
     env = os.environ.copy()
-    proc = subprocess.run(cmd, cwd=str(tmp_path), env=env, capture_output=True, text=True)
+    proc = subprocess.run(
+        cmd, cwd=str(tmp_path), env=env, capture_output=True, text=True, check=False
+    )
     assert proc.returncode == 0, f'convoxel failed: {proc.stdout}\n{proc.stderr}'
     assert op.exists(out_h5)
 
@@ -122,7 +124,9 @@ def test_convoxel_cli_creates_expected_hdf5(tmp_path):
         # Column names exist and match subjects count
         grp = h5['scalars/FA']
         assert 'column_names' in grp
-        colnames = [x.decode('utf-8') if isinstance(x, bytes) else str(x) for x in grp['column_names'][...]]
+        colnames = [
+            x.decode('utf-8') if isinstance(x, bytes) else str(x) for x in grp['column_names'][...]
+        ]
         assert len(colnames) == 2
 
         # Spot-check a voxel mapping (pick the third voxel)

test/test_voxels_s3.py

@@ -43,14 +43,15 @@ def group_mask_path(tmp_path_factory):
     boto3 = pytest.importorskip('boto3')
     from botocore import UNSIGNED
     from botocore.config import Config
+    from botocore.exceptions import BotoCoreError
 
     tmp = tmp_path_factory.mktemp('s3_group_mask')
     dest = tmp / 'group_mask.nii.gz'
     s3 = boto3.client('s3', config=Config(signature_version=UNSIGNED))
     key = f'{_PREFIX}/func_mask/{OHSU_SUBJECTS[0]}_func_mask.nii.gz'
     try:
         s3.download_file(_BUCKET, key, str(dest))
-    except Exception as exc:
+    except (OSError, BotoCoreError) as exc:
         pytest.skip(f'S3 download unavailable: {exc}')
     return dest
 
@@ -102,7 +103,9 @@ def test_convoxel_s3_parallel(tmp_path, group_mask_path):
         '4',
     ]
     env = {**os.environ, 'MODELARRAYIO_S3_ANON': '1'}
-    proc = subprocess.run(cmd, cwd=str(tmp_path), capture_output=True, text=True, env=env)
+    proc = subprocess.run(
+        cmd, cwd=str(tmp_path), capture_output=True, text=True, env=env, check=False
+    )
     assert proc.returncode == 0, f'convoxel failed:\n{proc.stdout}\n{proc.stderr}'
     assert out_h5.exists()
 
@@ -169,6 +172,7 @@ def test_convoxel_s3_serial_matches_parallel(tmp_path, group_mask_path):
             capture_output=True,
             text=True,
             env=env,
+            check=False,
         )
         assert proc.returncode == 0, f'convoxel failed (workers={workers}):\n{proc.stderr}'