David Demelier <markand@malikania.fr> [Tue, 26 Sep 2017 08:37:17 +0200] rev 34579
doc: rename README to README.rst
Many hosting services consider README without extension as plain text. By using
.rst extension, we bring better formatting on many services (e.g. bitbucket).
Boris Feld <boris.feld@octobus.net> [Mon, 09 Oct 2017 08:35:55 +0200] rev 34578
test: use current user in the multi-user amend scenario
The obsfate template keyword that will be introduced in a later patch
distinguish between current user and other users when displaying the obsfate
users.
Update the test before for clarity.
Boris Feld <boris.feld@octobus.net> [Fri, 06 Oct 2017 17:05:19 +0200] rev 34577
test: cleanup verbosity variant from fatelog test
Unlike the '{obsfate}' keyword defined in 'hg-evolve', the definition of hg
fatelog in test-obsmarker-template.t is not verbosity dependent. Remove useless
call to fatelog -v and fatelog -q.
Boris Feld <boris.feld@octobus.net> [Fri, 06 Oct 2017 16:36:41 +0200] rev 34576
test: rename obsfate template alias
We will introduce an obsfate templatekw in the next patch that will conflict
with the obsfate template in the test file, rename the one in test file to
avoid this collision.
Boris Feld <boris.feld@octobus.net> [Fri, 06 Oct 2017 16:15:24 +0200] rev 34575
obsolete: add a devel.user.obsmarker
In tests, we often want to use a different username in obs-markers without
changing the default user. Add a 'devel.user.obsmarker'.
Paul Morelle <paul.morelle@octobus.net> [Thu, 05 Oct 2017 15:11:34 +0200] rev 34574
strip: factor out update target selection
The same algorithm was used in two places: one to find out which commit shall
become the parent of wdir, and the other to prepare the wdir when keeping
changes. Factoring it out prevents inconsistent changes in either occurrence.
Augie Fackler <augie@google.com> [Wed, 11 Oct 2017 03:48:11 -0700] rev 34573
contrib: add check-code rule banning use of readlink
readlink doesn't always exist, such as on Solaris-derived platforms.
Differential Revision: https://phab.mercurial-scm.org/D1000
Augie Fackler <augie@google.com> [Tue, 10 Oct 2017 11:03:14 -0400] rev 34572
tests: use readlink.py instead of readlink
The latter doesn't always exist, such as on Solaris-derived platforms.
Differential Revision: https://phab.mercurial-scm.org/D999
Augie Fackler <augie@google.com> [Tue, 10 Oct 2017 11:02:53 -0400] rev 34571
tests: use readlink.py instead of readlink
The latter doesn't always exist, such as on Solaris-derived platforms.
Differential Revision: https://phab.mercurial-scm.org/D998
Augie Fackler <augie@google.com> [Tue, 10 Oct 2017 11:02:40 -0400] rev 34570
tests: use readlink.py instead of readlink
The latter doesn't always exist, such as on Solaris-derived platforms.
Differential Revision: https://phab.mercurial-scm.org/D997
Augie Fackler <augie@google.com> [Tue, 10 Oct 2017 11:02:23 -0400] rev 34569
tests: use readlink.py instead of readlink
The latter doesn't always exist, such as on Solaris-derived platforms.
Differential Revision: https://phab.mercurial-scm.org/D996
Augie Fackler <augie@google.com> [Wed, 11 Oct 2017 01:56:49 -0700] rev 34568
ui: recommend tweakdefaults in the default hgrc template
Were I only slightly bolder, I'd make it on by default in the
suggested user hgrc.
Differential Revision: https://phab.mercurial-scm.org/D1001
Pulkit Goyal <7895pulkit@gmail.com> [Tue, 10 Oct 2017 01:03:24 +0530] rev 34567
tests: optimize test-copytrace-heuristics.t
test-copytrace-heuristics.t tests the heuristics algorithm of copytracing. The
test has a pattern of making a server repo first and then cloning into a local
repo for each test to have public and draft commits. This is done because if we
have all draft commits and we have very less commits, heuristics will fallback
to full copytracing as that will be fast.
To avoid creating the server repo, we set the commit limit to -1 so that
everytime we perform the heuristics algorithm even when having full drafts and
tweak the config setting when we need to test the ability to fallback to full
copytracing.
This optimizes this test by 3 seconds.
Before:
real 0m41.503s
user 0m36.068s
sys 0m3.900s
After:
real 0m38.826s
user 0m33.884s
sys 0m3.396s
Differential Revision: https://phab.mercurial-scm.org/D991
Jun Wu <quark@fb.com> [Thu, 05 Oct 2017 13:38:48 -0700] rev 34566
patch: do not cache translated messages (API)
Previously the code caches `i18n._` results in module variables. That causes
issues after an encoding change. Instead of invalidating them manually, we
now just recalculate the translated messages every time `filterpatch` gets
called.
This makes test-commit-interactive.t pass regardless of whether chg or
demandimport is used or not.
.. api: `patch.messages` now lives in `patch.getmessages()`.
Extensions adding new messages should now wrap the `patch.getmessages`
method instead of changing `patch.messages` directly.
Differential Revision: https://phab.mercurial-scm.org/D959
Eamonn Kent <ekent@fb.com> [Mon, 09 Oct 2017 10:09:36 -0700] rev 34565
fsmonitor: add new watchman notifications to fsmonitor extension
The fsmonitor extension currently sends state-enter and state-leave
notifications to watchman on the update operation. This commit creates
additional notifications for the following events :
- transaction creation and commit/abort. A state-enter notification will be
sent when a transaction is created. It will provide the working copy
parent's hash. A state-leave notification will be sent when the
transaction is committed or aborted. It will provide the working copy
parent's hash.
- calls to set-parent will cause state-enter and state-leave notifications
to be sent. The state-enter notification will be sent prior to the
set-parent operation and the working copy parent's hash will be provided at
this time. The state-leave notification will be sent after the set-parent
operation completes providing the working copy parents hash.
Test Plan:
tested on dev server to check that necessary notifications were sent/received
Differential Revision: https://phab.mercurial-scm.org/D989