vecorel-cli 0.2.16__tar.gz → 0.2.17__tar.gz

{vecorel_cli-0.2.16/vecorel_cli.egg-info → vecorel_cli-0.2.17}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: vecorel-cli
-Version: 0.2.16
+Version: 0.2.17
 Summary: CLI tools such as validation and file format conversion for vecorel.
 Author: Matthias Mohr
 License-Expression: Apache-2.0

{vecorel_cli-0.2.16 → vecorel_cli-0.2.17}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "vecorel-cli"
-version = "0.2.16"
+version = "0.2.17"
 description = "CLI tools such as validation and file format conversion for vecorel."
 readme = "README.md"
 license = "Apache-2.0"

{vecorel_cli-0.2.16 → vecorel_cli-0.2.17}/tests/test_convert.py

@@ -1,3 +1,4 @@
+import json
 import sys
 from pathlib import Path
 
@@ -146,6 +147,26 @@ def test_template_from_package_folder():
     assert isinstance(converter, ConvertData), "Should succeed and not throw an exception"
 
 
+@pytest.mark.parametrize("bom", [False, True], ids=["without-bom", "with-bom"])
+def test_read_geojson_decodes_utf8(tmp_folder, cp1252_locale, bom):
+    file_path = tmp_folder / "umlaut.json"
+    feature = {
+        "type": "Feature",
+        "id": "1",
+        "properties": {"name": "Grünland"},
+        "geometry": {"type": "Point", "coordinates": [0, 0]},
+    }
+    file_path.write_text(
+        # ensure_ascii=False so the file really holds multi-byte UTF-8, not an escape sequence
+        json.dumps({"type": "FeatureCollection", "features": [feature]}, ensure_ascii=False),
+        encoding="utf-8-sig" if bom else "utf-8",
+    )
+
+    gdf = BaseConverter().read_geojson(str(file_path))
+
+    assert gdf["name"].iloc[0] == "Grünland"
+
+
 def test_data_access_exception(capsys, tmp_folder):
     # todo: use fixture
     logger.remove()

{vecorel_cli-0.2.16 → vecorel_cli-0.2.17}/tests/test_encoding_geojson.py

@@ -1,3 +1,4 @@
+import json
 from pathlib import Path
 
 import pytest
@@ -55,3 +56,25 @@ def test_get_collection_returns_existing(tmp_folder):
 
     result = geojson.get_collection()
     assert result == expected
+
+
+@pytest.mark.parametrize("bom", [False, True], ids=["without-bom", "with-bom"])
+def test_read_geojson_decodes_utf8(tmp_folder, cp1252_locale, bom):
+    feature = {
+        "type": "Feature",
+        "id": "1",
+        "properties": {"name": "Grünland"},
+        "geometry": {"type": "Point", "coordinates": [0, 0]},
+    }
+    file_path = tmp_folder / "umlaut.json"
+    file_path.write_text(
+        # ensure_ascii=False so the file really holds multi-byte UTF-8, not an escape sequence
+        json.dumps({"type": "FeatureCollection", "features": [feature]}, ensure_ascii=False),
+        encoding="utf-8-sig" if bom else "utf-8",
+    )
+
+    geojson = GeoJSON(file_path)
+
+    assert geojson.read_geojson()["features"][0]["properties"]["name"] == "Grünland"
+    # read(num=...) takes the streaming branch, which opens the file separately
+    assert geojson.read(num=1)["name"].iloc[0] == "Grünland"

{vecorel_cli-0.2.16 → vecorel_cli-0.2.17}/vecorel_cli/conversion/base.py

@@ -24,6 +24,7 @@ from geopandas import GeoDataFrame
 
 from ..cli.logger import LoggerMixin
 from ..cli.util import display_pandas_unrestricted
+from ..encoding.geojson import READ_ENCODING
 from ..encoding.geoparquet import GeoParquet
 from ..vecorel.collection import Collection
 from ..vecorel.hilbert import hilbert_sort_geodataframe
@@ -218,6 +219,9 @@ class BaseConverter(LoggerMixin):
                 yield GeoDataFrame(data), path, uri, layer
 
     def read_geojson(self, path, **kwargs):
+        # open_options is shared with gpd.read_parquet() and gpd.read_file(), so a converter
+        # cannot set a default encoding there without breaking the other two readers.
+        kwargs.setdefault("encoding", READ_ENCODING)
         with open(path, **kwargs) as f:
             obj = json.load(f)
 

{vecorel_cli-0.2.16 → vecorel_cli-0.2.17}/vecorel_cli/encoding/geojson.py

@@ -17,6 +17,11 @@ from ..vecorel.util import load_file, to_iso8601
 from ..vecorel.version import vecorel_version
 from .base import BaseEncoding
 
+# GeoJSON is UTF-8 (RFC 8259, section 8.1). Reading tolerates a byte order mark, which some
+# producers emit; writing must not add one, so the two differ.
+READ_ENCODING = "utf-8-sig"
+WRITE_ENCODING = "utf-8"
+
 
 class GeoJSON(BaseEncoding):
     feature_properties = {"type", "id", "geometry", "bbox", "properties"}
@@ -152,7 +157,7 @@ class GeoJSON(BaseEncoding):
         enforce_featurecollection: bool = False,
     ) -> Union[FeatureCollection, Feature]:
         # num only applies to FeatureCollections
-        with open(self.uri, "r") as f:
+        with open(self.uri, "r", encoding=READ_ENCODING) as f:
             obj = json.load(f)
 
         if not isinstance(obj, dict):
@@ -233,7 +238,7 @@ class GeoJSON(BaseEncoding):
         schema_map: SchemaMapping = {},
         properties: Optional[list[str]] = None,
     ) -> GeoDataFrame:
-        with open(self.uri, "r") as f:
+        with open(self.uri, "r", encoding=READ_ENCODING) as f:
             stream = json_stream.load(f)
             data = {
                 "id": [],
@@ -291,7 +296,7 @@ class GeoJSON(BaseEncoding):
             return gdf
 
     def _write_json(self, obj, path, indent=None) -> bool:
-        with open(path, "w") as f:
+        with open(path, "w", encoding=WRITE_ENCODING) as f:
             json.dump(obj, f, allow_nan=False, indent=indent, cls=VecorelJSONEncoder)
         return True
 

{vecorel_cli-0.2.16 → vecorel_cli-0.2.17/vecorel_cli.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: vecorel-cli
-Version: 0.2.16
+Version: 0.2.17
 Summary: CLI tools such as validation and file format conversion for vecorel.
 Author: Matthias Mohr
 License-Expression: Apache-2.0