pyogrio 0.8.0__tar.gz → 0.9.0__tar.gz

{pyogrio-0.8.0/pyogrio.egg-info → pyogrio-0.9.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pyogrio
-Version: 0.8.0
+Version: 0.9.0
 Summary: Vectorized spatial vector file format I/O using GDAL/OGR
 Home-page: https://github.com/geopandas/pyogrio
 Author: Brendan C. Ward

{pyogrio-0.8.0 → pyogrio-0.9.0}/pyogrio/_io.pyx

@@ -2134,6 +2134,10 @@ cdef create_ogr_dataset_layer(
         if crs is not None:
             try:
                 ogr_crs = create_crs(crs)
+                # force geographic CRS to use lon, lat order and ignore axis order specified by CRS, in order
+                # to correctly write KML and GeoJSON coordinates in correct order
+                OSRSetAxisMappingStrategy(ogr_crs, OAMS_TRADITIONAL_GIS_ORDER)
+
 
             except Exception as exc:
                 if dataset_options != NULL:
@@ -2735,4 +2739,4 @@ cdef create_fields_from_arrow_schema(
                 f"Error while creating field from Arrow for field {i} with name "
                 f"'{get_string(child.name)}' and type {get_string(child.format)}"
                 f"{gdal_msg}."
-            )
+            )

{pyogrio-0.8.0 → pyogrio-0.9.0}/pyogrio/_ogr.pxd

@@ -196,7 +196,10 @@ cdef extern from "ogr_srs_api.h":
     const char*             OSRGetAuthorityName(OGRSpatialReferenceH srs, const char *key)
     const char*             OSRGetAuthorityCode(OGRSpatialReferenceH srs, const char *key)
     OGRErr                  OSRImportFromEPSG(OGRSpatialReferenceH srs, int code)
-
+    ctypedef enum OSRAxisMappingStrategy:
+        OAMS_TRADITIONAL_GIS_ORDER
+        
+    void                    OSRSetAxisMappingStrategy(OGRSpatialReferenceH hSRS, OSRAxisMappingStrategy)
     int                     OSRSetFromUserInput(OGRSpatialReferenceH srs, const char *pszDef)
     void                    OSRSetPROJSearchPaths(const char *const *paths)
     OGRSpatialReferenceH    OSRNewSpatialReference(const char *wkt)

{pyogrio-0.8.0 → pyogrio-0.9.0}/pyogrio/_version.py

@@ -8,11 +8,11 @@ import json
 
 version_json = '''
 {
- "date": "2024-05-06T14:34:51-0700",
+ "date": "2024-06-17T12:28:58-0700",
  "dirty": false,
  "error": null,
- "full-revisionid": "46c35a7e98d85923cfefe73dae7285404e72d9a6",
- "version": "0.8.0"
+ "full-revisionid": "568f87062a65e0452c679624cc33fbf1af535454",
+ "version": "0.9.0"
 }
 '''  # END VERSION_JSON
 

{pyogrio-0.8.0 → pyogrio-0.9.0}/pyogrio/geopandas.py

@@ -87,6 +87,7 @@ def read_dataframe(
     sql_dialect=None,
     fid_as_index=False,
     use_arrow=None,
+    on_invalid="raise",
     arrow_to_pandas_kwargs=None,
     **kwargs,
 ):
@@ -197,6 +198,15 @@ def read_dataframe(
         installed). When enabled, this provides a further speed-up.
         Defaults to False, but this default can also be globally overridden
         by setting the ``PYOGRIO_USE_ARROW=1`` environment variable.
+    on_invalid : str, optional (default: "raise")
+
+        - **raise**: an exception will be raised if a WKB input geometry is
+          invalid.
+        - **warn**: a warning will be raised and invalid WKB geometries will be
+          returned as ``None``.
+        - **ignore**: invalid WKB geometries will be returned as ``None``
+          without a warning.
+
     arrow_to_pandas_kwargs : dict, optional (default: None)
         When `use_arrow` is True, these kwargs will be passed to the `to_pandas`_
         call for the arrow to pandas conversion.
@@ -234,7 +244,6 @@ def read_dataframe(
 
     import pandas as pd
     import geopandas as gp
-    from geopandas.array import from_wkb
     import shapely  # if geopandas is present, shapely is expected to be present
 
     path_or_buffer = _stringify_path(path_or_buffer)
@@ -292,10 +301,10 @@ def read_dataframe(
             if PANDAS_GE_15 and wkb_values.dtype != object:
                 # for example ArrowDtype will otherwise create numpy array with pd.NA
                 wkb_values = wkb_values.to_numpy(na_value=None)
-            df["geometry"] = from_wkb(wkb_values, crs=meta["crs"])
+            df["geometry"] = shapely.from_wkb(wkb_values, on_invalid=on_invalid)
             if force_2d:
                 df["geometry"] = shapely.force_2d(df["geometry"])
-            return gp.GeoDataFrame(df, geometry="geometry")
+            return gp.GeoDataFrame(df, geometry="geometry", crs=meta["crs"])
         else:
             return df
 
@@ -315,9 +324,9 @@ def read_dataframe(
     if geometry is None or not read_geometry:
         return df
 
-    geometry = from_wkb(geometry, crs=meta["crs"])
+    geometry = shapely.from_wkb(geometry, on_invalid=on_invalid)
 
-    return gp.GeoDataFrame(df, geometry=geometry)
+    return gp.GeoDataFrame(df, geometry=geometry, crs=meta["crs"])
 
 
 # TODO: handle index properly

{pyogrio-0.8.0 → pyogrio-0.9.0}/pyogrio/tests/test_geopandas_io.py

@@ -6,7 +6,7 @@ import locale
 import numpy as np
 import pytest
 
-from pyogrio import list_layers, read_info, __gdal_version__
+from pyogrio import list_layers, list_drivers, read_info, __gdal_version__
 from pyogrio.errors import DataLayerError, DataSourceError, FeatureError, GeometryError
 from pyogrio.geopandas import read_dataframe, write_dataframe, PANDAS_GE_20
 from pyogrio.raw import (
@@ -1641,6 +1641,37 @@ def test_write_geometry_z_types_auto(
     assert_geodataframe_equal(gdf, result_gdf)
 
 
+@pytest.mark.parametrize(
+    "on_invalid, message",
+    [
+        (
+            "warn",
+            "Invalid WKB: geometry is returned as None. IllegalArgumentException: "
+            "Invalid number of points in LinearRing found 2 - must be 0 or >=",
+        ),
+        ("raise", "Invalid number of points in LinearRing found 2 - must be 0 or >="),
+        ("ignore", None),
+    ],
+)
+def test_read_invalid_shp(data_dir, use_arrow, on_invalid, message):
+    if on_invalid == "raise":
+        handler = pytest.raises(shapely.errors.GEOSException, match=message)
+    elif on_invalid == "warn":
+        handler = pytest.warns(match=message)
+    elif on_invalid == "ignore":
+        handler = contextlib.nullcontext()
+    else:
+        raise ValueError(f"unknown value for on_invalid: {on_invalid}")
+
+    with handler:
+        df = read_dataframe(
+            data_dir / "poly_not_enough_points.shp.zip",
+            use_arrow=use_arrow,
+            on_invalid=on_invalid,
+        )
+        df.geometry.isnull().all()
+
+
 def test_read_multisurface(data_dir, use_arrow):
     if use_arrow:
         with pytest.raises(shapely.errors.GEOSException):
@@ -2067,3 +2098,77 @@ def test_non_utf8_encoding_shapefile_sql(tmp_path, use_arrow):
     )
     assert actual.columns[0] == mandarin
     assert actual[mandarin].values[0] == mandarin
+
+
+@pytest.mark.requires_arrow_write_api
+def test_write_kml_file_coordinate_order(tmp_path, use_arrow):
+    # confirm KML coordinates are written in lon, lat order even if CRS axis specifies otherwise
+    points = [Point(10, 20), Point(30, 40), Point(50, 60)]
+    gdf = gp.GeoDataFrame(geometry=points, crs="EPSG:4326")
+    output_path = tmp_path / "test.kml"
+    write_dataframe(
+        gdf, output_path, layer="tmp_layer", driver="KML", use_arrow=use_arrow
+    )
+
+    gdf_in = read_dataframe(output_path, use_arrow=use_arrow)
+
+    assert np.array_equal(gdf_in.geometry.values, points)
+
+    if "LIBKML" in list_drivers():
+        # test appending to the existing file only if LIBKML is available
+        # as it appears to fall back on LIBKML driver when appending.
+        points_append = [Point(70, 80), Point(90, 100), Point(110, 120)]
+        gdf_append = gp.GeoDataFrame(geometry=points_append, crs="EPSG:4326")
+
+        write_dataframe(
+            gdf_append,
+            output_path,
+            layer="tmp_layer",
+            driver="KML",
+            use_arrow=use_arrow,
+            append=True,
+        )
+        # force_2d used to only compare xy geometry as z-dimension is undesirably
+        # introduced when the kml file is over-written.
+        gdf_in_appended = read_dataframe(
+            output_path, use_arrow=use_arrow, force_2d=True
+        )
+
+        assert np.array_equal(gdf_in_appended.geometry.values, points + points_append)
+
+
+@pytest.mark.requires_arrow_write_api
+def test_write_geojson_rfc7946_coordinates(tmp_path, use_arrow):
+    points = [Point(10, 20), Point(30, 40), Point(50, 60)]
+    gdf = gp.GeoDataFrame(geometry=points, crs="EPSG:4326")
+    output_path = tmp_path / "test.geojson"
+    write_dataframe(
+        gdf,
+        output_path,
+        layer="tmp_layer",
+        driver="GeoJSON",
+        RFC7946=True,
+        use_arrow=use_arrow,
+    )
+
+    gdf_in = read_dataframe(output_path, use_arrow=use_arrow)
+
+    assert np.array_equal(gdf_in.geometry.values, points)
+
+    # test appending to the existing file
+
+    points_append = [Point(70, 80), Point(90, 100), Point(110, 120)]
+    gdf_append = gp.GeoDataFrame(geometry=points_append, crs="EPSG:4326")
+
+    write_dataframe(
+        gdf_append,
+        output_path,
+        layer="tmp_layer",
+        driver="GeoJSON",
+        RFC7946=True,
+        use_arrow=use_arrow,
+        append=True,
+    )
+
+    gdf_in_appended = read_dataframe(output_path, use_arrow=use_arrow)
+    assert np.array_equal(gdf_in_appended.geometry.values, points + points_append)

{pyogrio-0.8.0 → pyogrio-0.9.0}/pyogrio/tests/test_path.py

@@ -35,6 +35,7 @@ def change_cwd(path):
         ("/home/user/data.gpkg", "/home/user/data.gpkg"),
         (r"C:\User\Documents\data.gpkg", r"C:\User\Documents\data.gpkg"),
         ("file:///home/user/data.gpkg", "/home/user/data.gpkg"),
+        ("/home/folder # with hash/data.gpkg", "/home/folder # with hash/data.gpkg"),
         # cloud URIs
         ("https://testing/data.gpkg", "/vsicurl/https://testing/data.gpkg"),
         ("s3://testing/data.gpkg", "/vsis3/testing/data.gpkg"),

{pyogrio-0.8.0 → pyogrio-0.9.0}/pyogrio/util.py

@@ -115,7 +115,7 @@ def _parse_uri(path: str):
     scheme : str
         URI scheme such as "https" or "zip+s3".
     """
-    parts = urlparse(path)
+    parts = urlparse(path, allow_fragments=False)
 
     # if the scheme is not one of GDAL's supported schemes, return raw path
     if parts.scheme and not all(p in SCHEMES for p in parts.scheme.split("+")):

{pyogrio-0.8.0 → pyogrio-0.9.0/pyogrio.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pyogrio
-Version: 0.8.0
+Version: 0.9.0
 Summary: Vectorized spatial vector file format I/O using GDAL/OGR
 Home-page: https://github.com/geopandas/pyogrio
 Author: Brendan C. Ward

{pyogrio-0.8.0 → pyogrio-0.9.0}/pyogrio.egg-info/SOURCES.txt

@@ -37,6 +37,7 @@ pyogrio/tests/test_geopandas_io.py
 pyogrio/tests/test_path.py
 pyogrio/tests/test_raw_io.py
 pyogrio/tests/fixtures/README.md
+pyogrio/tests/fixtures/poly_not_enough_points.shp.zip
 pyogrio/tests/fixtures/sample.osm.pbf
 pyogrio/tests/fixtures/test_datetime.geojson
 pyogrio/tests/fixtures/test_datetime_tz.geojson

{pyogrio-0.8.0 → pyogrio-0.9.0}/pyproject.toml

@@ -38,6 +38,7 @@ GDAL_VERSION = "3.8.5"
 PYOGRIO_PACKAGE_DATA = 1
 GDAL_DATA = "$VCPKG_INSTALL/share/gdal"
 PROJ_LIB = "$VCPKG_INSTALL/share/proj"
+MACOSX_DEPLOYMENT_TARGET = "12.0"
 
 [tool.cibuildwheel.windows]
 before-build = "pip install delvewheel"

{pyogrio-0.8.0 → pyogrio-0.9.0}/setup.py

@@ -1,3 +1,4 @@
+import logging
 import os
 from pathlib import Path
 import platform
@@ -5,9 +6,7 @@ import shutil
 import subprocess
 import sys
 
-from distutils import log
-from setuptools import setup, find_packages
-from setuptools.extension import Extension
+from setuptools import Extension, setup, find_packages
 import versioneer
 
 # import Cython if available
@@ -18,6 +17,9 @@ except ImportError:
     cythonize = None
 
 
+logger = logging.getLogger(__name__)
+
+
 MIN_PYTHON_VERSION = (3, 8, 0)
 MIN_GDAL_VERSION = (2, 4, 0)
 
@@ -71,7 +73,7 @@ def get_gdal_config():
         }, gdal_version_str
 
     if include_dir or library_dir or gdal_version_str:
-        log.warn(
+        logger.warning(
             "If specifying the GDAL_INCLUDE_PATH, GDAL_LIBRARY_PATH, or GDAL_VERSION "
             "environment variables, you need to specify all of them."
         )
@@ -117,7 +119,7 @@ def get_gdal_config():
                 )
                 sys.exit(1)
 
-            log.info(
+            logger.info(
                 "Building on Windows requires extra options to setup.py to locate "
                 "GDAL files. See the installation documentation."
             )
@@ -174,7 +176,7 @@ else:
     if os.environ.get("PYOGRIO_PACKAGE_DATA"):
         gdal_data = os.environ.get("GDAL_DATA")
         if gdal_data and os.path.exists(gdal_data):
-            log.info(f"Copying gdal data from {gdal_data}")
+            logger.info(f"Copying gdal data from {gdal_data}")
             copy_data_tree(gdal_data, "pyogrio/gdal_data")
         else:
             raise Exception(
@@ -184,7 +186,7 @@ else:
 
         proj_data = os.environ.get("PROJ_LIB")
         if proj_data and os.path.exists(proj_data):
-            log.info(f"Copying proj data from {proj_data}")
+            logger.info(f"Copying proj data from {proj_data}")
             copy_data_tree(proj_data, "pyogrio/proj_data")
         else:
             raise Exception(