westonpace commented on code in PR #36266:
URL: https://github.com/apache/arrow/pull/36266#discussion_r1254516487
##########
python/pyarrow/tests/test_csv.py:
##########
@@ -1968,3 +1968,27 @@ def test_write_csv_decimal(tmpdir, type_factory):
out = read_csv(tmpdir / "out.csv")
assert out.column('col').cast(type) == table.column('col')
+
+
[email protected]("data_size", (
+ int(1E2),
+ int(1E4),
+ int(1E6)
+))
+def test_large_binary_write_to_csv(tmpdir, data_size):
+ file_name = tmpdir / "fixedsize_"+str(data_size)+".csv"
+
+ nparr = np.frombuffer(np.random.randint(65, 91, data_size, 'u1'), 'S4')
+
+ fixed_arr = pa.array(nparr, pa.binary(4))
+ fixed_table = pa.Table.from_arrays([fixed_arr], names=['fixedsize'])
+
+ csvoption = WriteOptions(include_header=True, batch_size=2048,
+ delimiter='|', quoting_style='none')
+
+ write_csv(fixed_table, file_name, write_options=csvoption)
+
+ assert os.path.exists(file_name)
+
+ res_table = read_csv(file_name)
+ assert fixed_table.shape, res_table.shape
Review Comment:
```suggestion
assert fixed_table.shape == res_table.shape
```
Also, why not compare the tables themselves and not just the shape?
--
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]
