FIX: Raise NotImplementedError if user passes an open file handle to write

CHANGES.md

@@ -5,7 +5,8 @@
 ### Bug fixes
 
 -   Silence warning from `write_dataframe` with `GeoSeries.notna()` (#435).
--   BUG: Enable mask & bbox filter when geometry column not read (#431).
+-   Enable mask & bbox filter when geometry column not read (#431).
+-   Raise NotImplmentedError when user attempts to write to an open file handle (#442).
 -   Prevent seek on read from compressed inputs (#443).
 
 ## 0.9.0 (2024-06-17)

pyogrio/geopandas.py

@@ -360,7 +360,8 @@ def write_dataframe(
         in the output file.
     path : str or io.BytesIO
         path to output file on writeable file system or an io.BytesIO object to
-        allow writing to memory
+        allow writing to memory.  Will raise NotImplementedError if an open file
+        handle is passed; use BytesIO instead.
         NOTE: support for writing to memory is limited to specific drivers.
     layer : str, optional (default: None)
         layer name to create.  If writing to memory and layer name is not

pyogrio/raw.py

@@ -1,4 +1,5 @@
 from io import BytesIO
+from pathlib import Path
 import warnings
 
 from pyogrio._env import GDALEnv
@@ -522,7 +523,8 @@ def _get_write_path_driver(path, driver, append=False):
     ----------
     path : str or io.BytesIO
         path to output file on writeable file system or an io.BytesIO object to
-        allow writing to memory
+        allow writing to memory.  Will raise NotImplementedError if an open file
+        handle is passed.
     driver : str, optional (default: None)
         The OGR format driver used to write the vector file. By default attempts
         to infer driver from path.  Must be provided to write to a file-like
@@ -554,6 +556,11 @@ def _get_write_path_driver(path, driver, append=False):
         if append:
             raise NotImplementedError("append is not supported for in-memory files")
 
+    elif hasattr(path, "write") and not isinstance(path, Path):
+        raise NotImplementedError(
+            "writing to an open file handle is not yet supported; instead, write to a BytesIO instance and then read bytes from that to write to the file handle"
+        )
+
     else:
         path = vsi_path(str(path))
 
@@ -605,7 +612,8 @@ def write(
     ----------
     path : str or io.BytesIO
         path to output file on writeable file system or an io.BytesIO object to
-        allow writing to memory
+        allow writing to memory.  Will raise NotImplementedError if an open file
+        handle is passed; use BytesIO instead.
         NOTE: support for writing to memory is limited to specific drivers.
     geometry : ndarray of WKB encoded geometries or None
         If None, geometries will not be written to output file

pyogrio/tests/test_arrow.py

@@ -5,6 +5,7 @@
 import os
 from packaging.version import Version
 import sys
+from zipfile import ZipFile
 
 import pytest
 import numpy as np
@@ -951,6 +952,45 @@ def test_write_memory_existing_unsupported(naturalearth_lowres):
         )
 
 
+@requires_arrow_write_api
+def test_write_open_file_handle(tmp_path, naturalearth_lowres):
+    """Verify that writing to an open file handle is not currently supported"""
+
+    meta, table = read_arrow(naturalearth_lowres, max_features=1)
+    meta["geometry_type"] = "MultiPolygon"
+
+    # verify it fails for regular file handle
+    with pytest.raises(
+        NotImplementedError, match="writing to an open file handle is not yet supported"
+    ):
+        with open(tmp_path / "test.geojson", "wb") as f:
+            write_arrow(
+                table,
+                f,
+                driver="GeoJSON",
+                layer="test",
+                crs=meta["crs"],
+                geometry_type=meta["geometry_type"],
+                geometry_name=meta["geometry_name"] or "wkb_geometry",
+            )
+
+    # verify it fails for ZipFile
+    with pytest.raises(
+        NotImplementedError, match="writing to an open file handle is not yet supported"
+    ):
+        with ZipFile(tmp_path / "test.geojson.zip", "w") as z:
+            with z.open("test.geojson", "w") as f:
+                write_arrow(
+                    table,
+                    f,
+                    driver="GeoJSON",
+                    layer="test",
+                    crs=meta["crs"],
+                    geometry_type=meta["geometry_type"],
+                    geometry_name=meta["geometry_name"] or "wkb_geometry",
+                )
+
+
 @requires_arrow_write_api
 def test_non_utf8_encoding_io_shapefile(tmp_path, encoded_text):
     encoding, text = encoded_text

pyogrio/tests/test_geopandas_io.py

@@ -3,6 +3,7 @@
 from io import BytesIO
 import locale
 import warnings
+from zipfile import ZipFile
 
 import numpy as np
 import pytest
@@ -1971,6 +1972,27 @@ def test_write_memory_existing_unsupported(naturalearth_lowres):
         write_dataframe(df.head(1), buffer, driver="GeoJSON", layer="test")
 
 
+def test_write_open_file_handle(tmp_path, naturalearth_lowres):
+    """Verify that writing to an open file handle is not currently supported"""
+
+    df = read_dataframe(naturalearth_lowres)
+
+    # verify it fails for regular file handle
+    with pytest.raises(
+        NotImplementedError, match="writing to an open file handle is not yet supported"
+    ):
+        with open(tmp_path / "test.geojson", "wb") as f:
+            write_dataframe(df.head(1), f)
+
+    # verify it fails for ZipFile
+    with pytest.raises(
+        NotImplementedError, match="writing to an open file handle is not yet supported"
+    ):
+        with ZipFile(tmp_path / "test.geojson.zip", "w") as z:
+            with z.open("test.geojson", "w") as f:
+                write_dataframe(df.head(1), f)
+
+
 @pytest.mark.parametrize("ext", ["gpkg", "geojson"])
 def test_non_utf8_encoding_io(tmp_path, ext, encoded_text):
     """Verify that we write non-UTF data to the data source

pyogrio/tests/test_raw_io.py

@@ -3,6 +3,7 @@
 from io import BytesIO
 import json
 import sys
+from zipfile import ZipFile
 
 import numpy as np
 from numpy import array_equal
@@ -1177,6 +1178,27 @@ def test_write_memory_existing_unsupported(naturalearth_lowres):
         write(buffer, geometry, field_data, driver="GeoJSON", layer="test", **meta)
 
 
+def test_write_open_file_handle(tmp_path, naturalearth_lowres):
+    """Verify that writing to an open file handle is not currently supported"""
+
+    meta, _, geometry, field_data = read(naturalearth_lowres)
+
+    # verify it fails for regular file handle
+    with pytest.raises(
+        NotImplementedError, match="writing to an open file handle is not yet supported"
+    ):
+        with open(tmp_path / "test.geojson", "wb") as f:
+            write(f, geometry, field_data, driver="GeoJSON", layer="test", **meta)
+
+    # verify it fails for ZipFile
+    with pytest.raises(
+        NotImplementedError, match="writing to an open file handle is not yet supported"
+    ):
+        with ZipFile(tmp_path / "test.geojson.zip", "w") as z:
+            with z.open("test.geojson", "w") as f:
+                write(f, geometry, field_data, driver="GeoJSON", layer="test", **meta)
+
+
 @pytest.mark.parametrize("ext", ["fgb", "gpkg", "geojson"])
 @pytest.mark.parametrize(
     "read_encoding,write_encoding",