emkornfield commented on a change in pull request #4081:
URL: https://github.com/apache/iceberg/pull/4081#discussion_r808653272



##########
File path: python/tests/io/test_pyarrow.py
##########
@@ -0,0 +1,126 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied.  See the License for the
+# specific language governing permissions and limitations
+# under the License.
+
+import os
+import tempfile
+from unittest.mock import MagicMock
+
+import pytest
+from pyarrow.fs import FileType
+
+from iceberg.io.pyarrow import PyArrowFile
+
+
+def test_pyarrow_input_file():
+    """Test reading a file using PyArrowFile"""
+
+    with tempfile.TemporaryDirectory() as tmpdirname:
+        file_location = os.path.join(tmpdirname, "foo.txt")
+        with open(file_location, "wb") as f:
+            f.write(b"foo")
+
+        # Confirm that the file initially exists
+        assert os.path.exists(file_location)
+
+        # Instantiate the input file
+        absolute_file_location = os.path.abspath(file_location)
+        input_file = PyArrowFile(location=f"{absolute_file_location}")
+
+        # Test opening and reading the file
+        f = input_file.open()
+        data = f.read()
+        assert data == b"foo"
+        assert len(input_file) == 3
+
+
+def test_pyarrow_output_file():
+    """Test writing a file using PyArrowFile"""
+
+    with tempfile.TemporaryDirectory() as tmpdirname:
+        file_location = os.path.join(tmpdirname, "foo.txt")
+
+        # Instantiate the output file
+        absolute_file_location = os.path.abspath(file_location)
+        output_file = PyArrowFile(location=f"{absolute_file_location}")
+
+        # Create the output file and write to it
+        f = output_file.create()
+        f.write(b"foo")
+
+        # Confirm that bytes were written
+        with open(file_location, "rb") as f:
+            assert f.read() == b"foo"
+
+        assert len(output_file) == 3
+
+
+def test_pyarrow_invalid_scheme():
+    """Test that a ValueError is raised if a location is provided with an 
invalid scheme"""
+
+    with pytest.raises(ValueError) as exc_info:
+        PyArrowFile("foo://bar/baz.txt")
+
+    assert ("Unrecognized filesystem type in URI") in str(exc_info.value)
+
+    with pytest.raises(ValueError) as exc_info:
+        PyArrowFile("foo://bar/baz.txt")
+
+    assert ("Unrecognized filesystem type in URI") in str(exc_info.value)
+
+
+def test_pyarrow_violating_input_stream_protocol():
+    """Test that a TypeError is raised if an input file is provided that 
violates the InputStream protocol"""
+
+    # Missing seek, tell, closed, and close
+    input_file_mock = MagicMock(spec=["read"])
+
+    # Create a mocked filesystem that returns input_file_mock
+    filesystem_mock = MagicMock()
+    filesystem_mock.open_input_file.return_value = input_file_mock
+
+    input_file = PyArrowFile("foo.txt")
+    input_file._filesystem = filesystem_mock
+    with pytest.raises(TypeError) as exc_info:
+        input_file.open()
+
+    assert ("Object of type") in str(exc_info.value)
+    assert ("returned from PyArrowFile.open does not match the InputStream 
protocol.") in str(exc_info.value)
+
+
+def test_pyarrow_violating_output_stream_protocol():

Review comment:
       Thats what I was thinking.  The comment you mentioned above about having 
to adjust constructor above really covers my main concern in terms of 
consistent user experience.  It might be too heavy weight here.  I think for 
different implementations that access s3 (and other remote file systems) we 
might just need to accept that there might be quirks in behavior.




-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]



---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to