def test_convert_json(): """ Test converting a JSON file to Parquet """ schema = pa.schema( [pa.field("foo", pa.int32()), pa.field("bar", pa.int64())]) input_path = "{}/tests/fixtures/simple_json.txt".format(os.getcwd()) expected_file = "{}/tests/fixtures/simple.parquet".format(os.getcwd()) with tempfile.NamedTemporaryFile() as f: output_path = f.name client.convert_json(input_path, output_path, schema) assert filecmp.cmp(expected_file, output_path)
def test_convert_json(): """ Test converting a JSON file to Parquet """ schema = pa.schema([ pa.field("foo", pa.int32()), pa.field("bar", pa.int64()) ]) input_path = "{}/tests/fixtures/simple_json.txt".format(os.getcwd()) expected_file = "{}/tests/fixtures/simple.parquet".format(os.getcwd()) with tempfile.NamedTemporaryFile() as f: output_file = f.name client.convert_json(input_path, output_file, schema) output = pq.ParquetFile(output_file) expected = pq.ParquetFile(expected_file) assert output.metadata.num_columns == expected.metadata.num_columns assert output.metadata.num_rows == expected.metadata.num_rows assert output.schema.equals(expected.schema) assert output.read_row_group(0).to_pydict() == expected.read_row_group(0).to_pydict()