pitrou commented on code in PR #13264:
URL: https://github.com/apache/arrow/pull/13264#discussion_r885005532
##########
python/pyarrow/tests/test_io.py:
##########
@@ -1201,6 +1202,46 @@ def test_native_file_TextIOWrapper(tmpdir):
assert res == data
+def test_native_file_TextIOWrapper_perf(tmpdir):
+ # ARROW-16272: TextIOWrapper.readline() shouldn't exhaust a large
+ # Arrow input stream.
+ data = b'foo\nquux\n'
+ path = str(tmpdir / 'largefile.txt')
+ with open(path, 'wb') as f:
+ f.write(data * 100_000)
+
+ binary_file = pa.OSFile(path, mode='rb')
+ with TextIOWrapper(binary_file) as f:
+ assert binary_file.tell() == 0
+ nbytes = 20_000
+ lines = f.readlines(nbytes)
+ assert len(lines) == math.ceil(2 * nbytes / len(data))
+ assert nbytes <= binary_file.tell() <= nbytes * 2
Review Comment:
Hmm, for some reason this test doesn't fail without the fix.
--
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]
