ENH: enable more ruff rules + make appropriate changes (#415)

Author: theroggy

.pre-commit-config.yaml

@@ -1,7 +1,7 @@
 files: 'pyogrio\/'
 repos:
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: "v0.1.13"
+    rev: "v0.5.2"
     hooks:
       - id: ruff-format
-      - id: ruff
+      - id: ruff

environment-dev.yml

@@ -14,5 +14,5 @@ dependencies:
   - cython
   - pre-commit
   - pytest
-  - ruff
-  - versioneer
+  - ruff==0.5.2
+  - versioneer

pyogrio/__init__.py

@@ -1,28 +1,29 @@
+"""Vectorized vector I/O using OGR."""
+
 try:
     # we try importing shapely, to ensure it is imported (and it can load its
     # own GEOS copy) before we load GDAL and its linked GEOS
-    import shapely  # noqa
-    import shapely.geos  # noqa
+    import shapely
+    import shapely.geos  # noqa: F401
 except Exception:
     pass
 
+from pyogrio._version import get_versions
 from pyogrio.core import (
-    list_drivers,
+    __gdal_geos_version__,
+    __gdal_version__,
+    __gdal_version_string__,
     detect_write_driver,
+    get_gdal_config_option,
+    get_gdal_data_path,
+    list_drivers,
     list_layers,
     read_bounds,
     read_info,
     set_gdal_config_options,
-    get_gdal_config_option,
-    get_gdal_data_path,
-    __gdal_version__,
-    __gdal_version_string__,
-    __gdal_geos_version__,
 )
-from pyogrio.raw import read_arrow, open_arrow, write_arrow
 from pyogrio.geopandas import read_dataframe, write_dataframe
-from pyogrio._version import get_versions
-
+from pyogrio.raw import open_arrow, read_arrow, write_arrow
 
 __version__ = get_versions()["version"]
 del get_versions

pyogrio/_compat.py

@@ -1,6 +1,6 @@
 from packaging.version import Version
 
-from pyogrio.core import __gdal_version__, __gdal_geos_version__
+from pyogrio.core import __gdal_geos_version__, __gdal_version__
 
 # detect optional dependencies
 try:

pyogrio/_env.py

@@ -4,13 +4,12 @@
 # adapted from Fiona: https://github.com/Toblerity/Fiona/pull/875
 
 
-from contextlib import contextmanager
 import logging
 import os
-from pathlib import Path
 import platform
 import sys
-
+from contextlib import contextmanager
+from pathlib import Path
 
 log = logging.getLogger(__name__)
 log.addHandler(logging.NullHandler())
@@ -32,7 +31,7 @@
 if platform.system() == "Windows" and sys.version_info >= (3, 8):
     # if loading of extension modules fails, search for gdal dll directory
     try:
-        import pyogrio._io  # NOQA
+        import pyogrio._io  # noqa: F401
 
     except ImportError:
         for path in os.getenv("PATH", "").split(os.pathsep):

pyogrio/core.py

@@ -1,27 +1,28 @@
+"""Core functions to interact with OGR data sources."""
+
 from pyogrio._env import GDALEnv
 from pyogrio.util import (
-    get_vsi_path_or_buffer,
-    _preprocess_options_key_value,
     _mask_to_wkb,
+    _preprocess_options_key_value,
+    get_vsi_path_or_buffer,
 )
 
-
 with GDALEnv():
+    from pyogrio._err import _register_error_handler
+    from pyogrio._io import ogr_list_layers, ogr_read_bounds, ogr_read_info
     from pyogrio._ogr import (
-        get_gdal_version,
-        get_gdal_version_string,
-        get_gdal_geos_version,
-        ogr_list_drivers,
-        set_gdal_config_options as _set_gdal_config_options,
+        _get_drivers_for_path,
+        _register_drivers,
         get_gdal_config_option as _get_gdal_config_option,
         get_gdal_data_path as _get_gdal_data_path,
+        get_gdal_geos_version,
+        get_gdal_version,
+        get_gdal_version_string,
         init_gdal_data as _init_gdal_data,
         init_proj_data as _init_proj_data,
-        _register_drivers,
-        _get_drivers_for_path,
+        ogr_list_drivers,
+        set_gdal_config_options as _set_gdal_config_options,
     )
-    from pyogrio._err import _register_error_handler
-    from pyogrio._io import ogr_list_layers, ogr_read_bounds, ogr_read_info
 
     _init_gdal_data()
     _init_proj_data()
@@ -48,8 +49,8 @@ def list_drivers(read=False, write=False):
     dict
         Mapping of driver name to file mode capabilities: ``"r"``: read, ``"w"``: write.
         Drivers that are available but with unknown support are marked with ``"?"``
-    """
 
+    """
     drivers = ogr_list_drivers()
 
     if read:
@@ -62,20 +63,23 @@ def list_drivers(read=False, write=False):
 
 
 def detect_write_driver(path):
-    """Attempt to infer the driver for a path by extension or prefix.  Only
-    drivers that support write capabilities will be detected.
+    """Attempt to infer the driver for a path by extension or prefix.
+
+    Only drivers that support write capabilities will be detected.
 
     If the path cannot be resolved to a single driver, a ValueError will be
     raised.
 
     Parameters
     ----------
     path : str
+        data source path
 
     Returns
     -------
     str
         name of the driver, if detected
+
     """
     # try to infer driver from path
     drivers = _get_drivers_for_path(path)
@@ -106,14 +110,15 @@ def list_layers(path_or_buffer, /):
     Parameters
     ----------
     path_or_buffer : str, pathlib.Path, bytes, or file-like
+        A dataset path or URI, raw buffer, or file-like object with a read method.
 
     Returns
     -------
     ndarray shape (2, n)
         array of pairs of [<layer name>, <layer geometry type>]
         Note: geometry is `None` for nonspatial layers.
-    """
 
+    """
     return ogr_list_layers(get_vsi_path_or_buffer(path_or_buffer))
 
 
@@ -136,6 +141,7 @@ def read_bounds(
     Parameters
     ----------
     path_or_buffer : str, pathlib.Path, bytes, or file-like
+        A dataset path or URI, raw buffer, or file-like object with a read method.
     layer : int or str, optional (default: first layer)
         If an integer is provided, it corresponds to the index of the layer
         with the data source.  If a string is provided, it must match the name
@@ -172,8 +178,8 @@ def read_bounds(
         fids are global IDs read from the FID field of the dataset
         bounds are ndarray of shape(4, n) containing ``xmin``, ``ymin``, ``xmax``,
         ``ymax``
-    """
 
+    """
     return ogr_read_bounds(
         get_vsi_path_or_buffer(path_or_buffer),
         layer=layer,
@@ -222,6 +228,7 @@ def read_info(
     Parameters
     ----------
     path_or_buffer : str, pathlib.Path, bytes, or file-like
+        A dataset path or URI, raw buffer, or file-like object with a read method.
     layer : [type], optional
         Name or index of layer in data source.  Reads the first layer by default.
     encoding : [type], optional (default: None)
@@ -257,8 +264,8 @@ def read_info(
                 "dataset_metadata": "<dict of dataset metadata or None>"
                 "layer_metadata": "<dict of layer metadata or None>"
             }
-    """
 
+    """
     dataset_kwargs = _preprocess_options_key_value(kwargs) if kwargs else {}
 
     return ogr_read_info(
@@ -288,8 +295,8 @@ def set_gdal_config_options(options):
         configuration options.  ``True`` / ``False`` are normalized to ``'ON'``
         / ``'OFF'``. A value of ``None`` for a config option can be used to clear out a
         previously set value.
-    """
 
+    """
     _set_gdal_config_options(options)
 
 
@@ -305,8 +312,8 @@ def get_gdal_config_option(name):
     -------
     value of the option or None if not set
         ``'ON'`` / ``'OFF'`` are normalized to ``True`` / ``False``.
-    """
 
+    """
     return _get_gdal_config_option(name)
 
 
@@ -316,5 +323,6 @@ def get_gdal_data_path():
     Returns
     -------
     str, or None if data directory was not found
+
     """
     return _get_gdal_data_path()

pyogrio/errors.py

@@ -1,32 +1,25 @@
-class DataSourceError(RuntimeError):
-    """Errors relating to opening or closing an OGRDataSource (with >= 1 layers)"""
+"""Custom errors."""
+
 
-    pass
+class DataSourceError(RuntimeError):
+    """Errors relating to opening or closing an OGRDataSource (with >= 1 layers)."""
 
 
 class DataLayerError(RuntimeError):
-    """Errors relating to working with a single OGRLayer"""
-
-    pass
+    """Errors relating to working with a single OGRLayer."""
 
 
 class CRSError(DataLayerError):
-    """Errors relating to getting or setting CRS values"""
-
-    pass
+    """Errors relating to getting or setting CRS values."""
 
 
 class FeatureError(DataLayerError):
-    """Errors related to reading or writing a feature"""
-
-    pass
+    """Errors related to reading or writing a feature."""
 
 
 class GeometryError(DataLayerError):
-    """Errors relating to getting or setting a geometry field"""
-
-    pass
+    """Errors relating to getting or setting a geometry field."""
 
 
 class FieldError(DataLayerError):
-    """Errors relating to getting or setting a non-geometry field"""
+    """Errors relating to getting or setting a non-geometry field."""