R-JunmingChen commented on code in PR #34586:
URL: https://github.com/apache/arrow/pull/34586#discussion_r1162263290
##########
python/pyarrow/tests/test_dataset.py:
##########
@@ -3172,6 +3202,58 @@ def test_csv_fragment_options(tempdir, dataset_reader):
assert result.equals(
pa.table({'col0': pa.array(['foo', 'spam', 'MYNULL'])}))
[email protected]
+def test_json_format(tempdir, dataset_reader):
+ table = pa.table({'a': pa.array([1, 2, 3], type="int64"),
+ 'b': pa.array([.1, .2, .3], type="float64")})
+
+ path = str(tempdir / 'test.json')
+ out = table.to_pandas().to_json(orient='records')[1:-1].replace('},{',
'}\n{')
+ with open(path, 'w') as f:
+ f.write(out)
+
+ dataset = ds.dataset(path, format=ds.JsonFileFormat())
+ result = dataset_reader.to_table(dataset)
+ assert result.equals(table)
+
+ assert_dataset_fragment_convenience_methods(dataset)
+
+ dataset = ds.dataset(path, format='json')
+ result = dataset_reader.to_table(dataset)
+ assert result.equals(table)
+
+def test_json_format_options(tempdir, dataset_reader):
+ table = pa.table({'a': pa.array([1, 2, 3], type="int64"),
+ 'b': pa.array([.1, .2, .3], type="float64")})
+
+ path = str(tempdir / 'test.json')
+ out = table.to_pandas().to_json(orient='records')[1:-1].replace('},{',
'}\n{')
+ with open(path, 'w') as f:
+ f.write(out)
+
+ dataset = ds.dataset(path, format=ds.JsonFileFormat(
+ read_options=pa.json.ReadOptions(block_size=64)))
Review Comment:
Thanks for useful suggestions.
The `blocksize` is indeed inappropriate here. I will change to
`newlines_in_values` soon.
--
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]
