johnjcasey commented on code in PR #17380:
URL: https://github.com/apache/beam/pull/17380#discussion_r860099004
##########
sdks/python/apache_beam/io/hadoopfilesystem_test.py:
##########
@@ -538,6 +539,14 @@ def test_checksum(self):
self.assertEqual(
'fake_algo-5-checksum_byte_sequence', self.fs.checksum(url))
+ def test_last_updated(self):
+ url = self.fs.join(self.tmpdir, 'f1')
+ with self.fs.create(url) as f:
+ f.write(b'Hello')
+ tolerance = 60 # 1 min
+ result = self.fs.last_updated(url)
+ self.assertAlmostEqual(result, time.time(), delta=tolerance)
Review Comment:
1 minute is a reasonable window, but this test looks like it could be flaky
still. Is there a way to make this deterministic?
##########
sdks/python/apache_beam/io/hadoopfilesystem_test.py:
##########
@@ -36,17 +37,16 @@ class FakeFile(io.BytesIO):
"""File object for FakeHdfs"""
__hash__ = None # type: ignore[assignment]
- def __init__(self, path, mode='', type='FILE'):
+ def __init__(self, path, mode='', type='FILE', time_ms=None):
io.BytesIO.__init__(self)
-
- self.stat = {
- 'path': path,
- 'mode': mode,
- 'type': type,
- }
+ if time_ms is None:
+ time_ms = int(time.time() * 1000)
+ self.time_ms = time_ms
+ self.stat = {'path': path, 'mode': mode, 'type': type}
self.saved_data = None
def __eq__(self, other):
+ """Equality of two files. Timestamp not included in comparison"""
Review Comment:
Should timestamp be included?
--
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]
