Callbacks registered with 'atexit' are sometimes not called (like when
hg aborts and calls os._exit). On the other hand, callbacks registered with
'ui.atexit' are called in most cases. Therefore, encouraging the use of
'ui.atexit' by failing the test 'test-check-code.t' appropriately.
Test Plan:
Ran the test 'test-check-code.t' after importing 'atexit' in one of
the py files and confirmed that the test fails.
Differential Revision: https://phab.mercurial-scm.org/D961
unittest has a `maxDiff` parameter which has to be set to `None` in order for
large enough failure diffs to be displayed. Add a comment to disable the
camelcase check for `self.maxDiff = None` lines.
Differential Revision: https://phab.mercurial-scm.org/D895
This location is used by debian (and ubuntu) to store completions provided by
other deb packages. The default fpath appears to have this before any of the
zsh-provided instances of the completions, so this should take precedence.
Differential Revision: https://phab.mercurial-scm.org/D882
These have annoyed me for a long time, and I'm tired of commenting on
them in reviews. I'm sorry for how complicated the regular expression
is, but I was too lazy to go crack open pylint's code and add the
check there.
The arguments are especially non-obvious because the order is
different from dirstate.status().
Differential Revision: https://phab.mercurial-scm.org/D846
If the call to dirstate.walk() failed, we would try to fall back to
older versions. These were removed in 869e4a22ee0d (walk: remove
cmdutil.walk, 2008-05-12) and 4f67ccefb6ef (dirstate: fold statwalk
and walk, 2008-06-26). We don't care about testing performance of
versions that old versions at this point, so let's clean up.
Differential Revision: https://phab.mercurial-scm.org/D845
I've poked at this on and off several times, and I can't figure out
what regressed. Let's kick this out of the whitelist for now so that
we can get the *rest* of our progress covered by the buildbots.
Not sure why, but I got `phabsend` hang on work network pretty frequently.
The traceback indicates it hangs at `_sslobj.do_handshake()`:
File "mercurial/sslutil.py", line 404, in wrapsocket
sslsocket = sslcontext.wrap_socket(sock, server_hostname=serverhostname)
File "/usr/lib/python2.7/ssl.py", line 363, in wrap_socket
_context=self)
File "/usr/lib/python2.7/ssl.py", line 611, in __init__
self.do_handshake()
File "/usr/lib/python2.7/ssl.py", line 840, in do_handshake
self._sslobj.do_handshake()
I had tried adding `timeout` in various places but they seem not effective.
It seems easier to just allow shelling out to `curl` with retry and timeout
flags.
This could also be helpful for people with an older Python installed without
modern security (SNI).
Differential Revision: https://phab.mercurial-scm.org/D605
Previously, the `--confirm` text could have colors but the main `phabsend`
does not. This patch adjusts the main command so it also has colors.
A default color table was added so the colors are visible by default.
Differential Revision: https://phab.mercurial-scm.org/D515
Some platforms (ex. FreeBSD) do not have `bash` by default. Therefore it
should not be used in test scripts.
Differential Revision: https://phab.mercurial-scm.org/D609
This would make the checker more friendly for 3rd-party code. For example,
In remotefilelog/x.py, it may have:
from . import shallowutils
That could trigger "relative import of stdlib module" if
"remotefilelog" was installed in the system. If the module being checked
conflicts with the system module, it makes sense to not treat that module as
system module. This patch makes it so.
Differential Revision: https://phab.mercurial-scm.org/D552
Often people running `phabsend --confirm` just want to check whether a
commit will trigger a creation of new Differential Revision, or update an
existing one. This patch implements that. The `--confirm` message was
changed to use node instead of revision number to be consistent with what
`phabsend` outputs.
An example output looks like:
D487 - a80f447973a0 test-extension: enable demandimport explicitly
D494 - cf440ea6e47e test-casecollision-merge: fix the test
NEW - 0a6b97147128 phabsend: polish the docstring a bit
Send the above changes to https://phab.mercurial-scm.org/ (yn)?
Differential Revision: https://phab.mercurial-scm.org/D514
Sometimes people have multiple Phabricator endpoints set in multiple repos.
It seems better for `--confirm` to prompt about the Phabricator endpoint
patches being sent to.
Differential Revision: https://phab.mercurial-scm.org/D513
Previously phabsend has an optimization that will skip uploading a diff if
the patch (with context line number = 1) remains unchanged. That could be
confusing:
Aug 24 15:52:28 <martinvonz> phillco: something is wrong with phabricator'your patches/
Aug 24 15:52:45 <martinvonz> ... with phabricator's view of your patches again
Aug 24 15:53:38 <martinvonz> if i phabread D388 and then D399, i get a version of filemerge.py with "a, b, c" somewhere on line 344, which is not what phabricator shows for D399
Aug 24 15:53:51 <martinvonz> junw: maybe that's more for you ^
Fix that by checking context with 32767 lines, which is the same as what
will be actually sent.
Differential Revision: https://phab.mercurial-scm.org/D512
The local tag feature was intended to make `phabsend` closer to `email`
workflow. But its experience is not great in multiple ways:
- after rebase, obsoleted changesets are still visible because of tags
- without obsstore, the association information will get lost
- even with obsstore, things could go wrong with graft, export+import
- no easy way to tell which Differential Revision a commit is associated
Therefore make `--amend` the default. People wanting the old behavior can
use `--no-amend`.
Differential Revision: https://phab.mercurial-scm.org/D511
run-tests.py and import-checker.py take wholly different approaches to
.t-tests, and the result was that they had different notions about
when a Python heredoc had ended, leading to conflicts. This resolves
part of the issue, and the rest I can deal with by tweaking the one
offending test file.
`simplemerge()` will soon require context-like objects to work. Create a simple
context-like object that wraps the requested files and can be passed to the new
API.
Differential Revision: https://phab.mercurial-scm.org/D378
I didn't do anything to ensure correctness here, just enough to avoid
tracebacks in the import checker, which uses the native ast module to
try and parse all our Python files.