Boris Feld <boris.feld@octobus.net> [Fri, 30 Jun 2017 03:42:40 +0200] rev 34474
configitems: register the 'histedit.singletransaction' config
Boris Feld <boris.feld@octobus.net> [Fri, 30 Jun 2017 03:42:39 +0200] rev 34473
configitems: register the 'histedit.linelen' config
Boris Feld <boris.feld@octobus.net> [Fri, 30 Jun 2017 03:42:38 +0200] rev 34472
configitems: register the 'histedit.dropmissing' config
Boris Feld <boris.feld@octobus.net> [Fri, 30 Jun 2017 03:42:37 +0200] rev 34471
configitems: register the 'histedit.defaultrev' config
Boris Feld <boris.feld@octobus.net> [Fri, 30 Jun 2017 03:44:30 +0200] rev 34470
configitems: register the 'transplant.log' config
Boris Feld <boris.feld@octobus.net> [Fri, 30 Jun 2017 03:44:29 +0200] rev 34469
configitems: register the 'transplant.filter' config
Augie Fackler <augie@google.com> [Wed, 04 Oct 2017 11:58:00 -0400] rev 34468
urllibcompat: move some adapters from pycompat to urllibcompat
These are all the httpserver and urllib.* aliases. They seem to make
more sense in the slightly-more-specific urllibcompat package than the
general-purpose pycompat.
Differential Revision: https://phab.mercurial-scm.org/D935
Augie Fackler <augie@google.com> [Sun, 01 Oct 2017 12:14:21 -0400] rev 34467
cleanup: use urllibcompat for renamed methods on urllib request objects
Differential Revision: https://phab.mercurial-scm.org/D891
Augie Fackler <augie@google.com> [Sun, 01 Oct 2017 10:45:03 -0400] rev 34466
urllibcompat: new library to help abstract out some python3 urllib2 stuff
Doing a new file instead of pycompat because I'm starting to feel like
pycompat is getting a little enormous in terms of scope.
Differential Revision: https://phab.mercurial-scm.org/D890
Saurabh Singh <singhsrb@fb.com> [Wed, 04 Oct 2017 10:42:55 -0700] rev 34465
test-devel-warnings: make the test compatible with chg
The test fails when run with the "--chg" option. Therefore, this
commit makes it compatible with chg.
Test Plan:
Ran the test "test-devel-warnings.t' with and without the "--chg"
option
Differential Revision: https://phab.mercurial-scm.org/D915
Gregory Szorc <gregory.szorc@gmail.com> [Sun, 01 Oct 2017 22:26:24 +0100] rev 34464
fsmonitor: use configitem
We might as well get this out of the way.
Differential Revision: https://phab.mercurial-scm.org/D893
Gregory Szorc <gregory.szorc@gmail.com> [Sun, 01 Oct 2017 23:47:16 +0100] rev 34463
fsmonitor: access copymap in new location
fsmonitor has been busted since 0865d25e8a8a due to moving
self._copymap. Fix it.
Differential Revision: https://phab.mercurial-scm.org/D892
Yuya Nishihara <yuya@tcha.org> [Sun, 01 Oct 2017 12:12:56 +0100] rev 34462
extdata: use subprocess so we don't have to chdir() manually
Yuya Nishihara <yuya@tcha.org> [Sun, 01 Oct 2017 11:58:27 +0100] rev 34461
extdata: just use iterator to read lines one by one
Yuya Nishihara <yuya@tcha.org> [Sun, 01 Oct 2017 11:56:41 +0100] rev 34460
extdata: ignore ambiguous identifier as well
Yuya Nishihara <yuya@tcha.org> [Sun, 01 Oct 2017 11:13:09 +0100] rev 34459
templater: add experimental support for extdata
This is minimal and non-controversial implementation of extdata() template
function. Originally extdata sources were exposed to the keyword namespace,
but I've changed it to a plain function for simplicity.
Yuya Nishihara <yuya@tcha.org> [Sun, 01 Oct 2017 10:50:00 +0100] rev 34458
revset: add experimental support for extdata
This is minimal and non-controversial implementation of extdata() revset.
Originally extdata sources were exposed to the symbol namespace, but I've
changed it to a plain function for simplicity.
Matt Mackall <mpm@selenic.com> [Tue, 13 Sep 2016 14:14:05 -0500] rev 34457
extdata: add extdatasource reader
This adds basic support for extdata, a way to add external data
sources for revsets and templates. An extdata data source is simply a
list of lines of the form:
<revision identifier>[<space><freeform text>]\n
An extdata source is configured thusly:
[extdata]
name = <a url or path>
urls of the form shell: are launch shell commands to generate data.
This patch is slightly modified by Yuya Nishihara as follows:
- fix typo
- remove unused function
- remove future expansion point for parameter (which can be added later
as the extdata revset/template are experimental)
You can see the original patch at
https://www.mercurial-scm.org/pipermail/mercurial-devel/2016-September/088426.html
Denis Laxalde <denis.laxalde@logilab.fr> [Wed, 04 Oct 2017 10:02:15 +0200] rev 34456
tests: change to parent directory before all "hg init" in test-log.t
Add a "cd .." before the second "hg init" so that all repositories are on top
level of test directory. Makes inspection of test directory easier.
Jun Wu <quark@fb.com> [Tue, 03 Oct 2017 12:00:07 -0700] rev 34455
config: add a missing preparewrite() call
Thanks Yuya for pointing this out in D808.
Differential Revision: https://phab.mercurial-scm.org/D924
Saurabh Singh <singhsrb@fb.com> [Tue, 03 Oct 2017 16:59:17 -0700] rev 34454
test-strip: make test compatible with chg
The test was using reposetup which had the logic for stripping
commits. This leads to a situation where if the reposetup was called twice for
an extension (which can happen with chg running), the stripped node would not
be found the second time. Therefore, this commit changes the test to put the
stripping logic inside commands instead of the reposetup. This ensures that the
stripping logic is invoked only when the command is invoked and thus, avoids
any problems.
Test Plan:
Ran the test 'test-strip.t' with and without the '--chg' option.
Differential Revision: https://phab.mercurial-scm.org/D928
Saurabh Singh <singhsrb@fb.com> [Tue, 03 Oct 2017 14:35:24 -0700] rev 34453
test-hook: make test compatible with chg
The test uses the 'print' method instead of writing to stdout using
'ui.write' which leads to incompatibility with chg. This commit modifies the
test to use 'ui' instead which fixes the problem.
Test Plan:
Ran the test 'test-hook.t' with and without '--chg' option.
Differential Revision: https://phab.mercurial-scm.org/D927
Saurabh Singh <singhsrb@fb.com> [Tue, 03 Oct 2017 13:30:36 -0700] rev 34452
test-setdiscovery: make test compatible with chg
The test checks the output of the blackbox extension which will
contain logs corresponding to chg in case chg is running. Therefore, this
commit modifies the test to take chg into consideration while working with the
blackbox extension.
Test Plan:
Ran the test 'test-setdiscovery.t' with and without the '--chg'
option.
Differential Revision: https://phab.mercurial-scm.org/D926
Saurabh Singh <singhsrb@fb.com> [Tue, 03 Oct 2017 13:05:58 -0700] rev 34451
test-merge-subrepos: make test compatible with chg
The test checks the output of '.hg/blackbox.log' which will contain
logs corresponding to chg in case chg is running. Therefore, this commit
modifies the test to take chg into consideration while checking the
blackbox.log contents.
Test Plan:
Ran the test 'test-merge-subrepos.t' with and without the '--chg'
option.
Differential Revision: https://phab.mercurial-scm.org/D925
Saurabh Singh <singhsrb@fb.com> [Tue, 03 Oct 2017 12:49:28 -0700] rev 34450
test-convert-cvs: make test compatible with chg
The test uses the 'print' method instead of writing to stdout using
'ui.write' which leads to incompatibility with chg. This commit modifies the
test to use the 'ui' object instead which fixes the problem.
Test Plan:
Ran the test 'test-convert-cvs.t' with and without '--chg' option.
Differential Revision: https://phab.mercurial-scm.org/D923
Saurabh Singh <singhsrb@fb.com> [Tue, 03 Oct 2017 12:09:23 -0700] rev 34449
test-basic: make test compatible with chg
The error codes returned when writing to /dev/full are different after
the first failure with and without '--chg' option. Therefore, this commit
conditionally handles the error codes as appropriate.
Test Plan:
Ran the test 'test-basic.t' with and without '--chg' option.
Differential Revision: https://phab.mercurial-scm.org/D922
Jun Wu <quark@fb.com> [Mon, 02 Oct 2017 20:23:25 -0700] rev 34448
zeroconf: do not crash if socket being read is closed by another thread
In zeroconf/__init__.py, there is:
server = Zeroconf.Zeroconf(ip)
l = listener()
Zeroconf.ServiceBrowser(server, "_hg._tcp.local.", l)
time.sleep(1)
server.close()
`server.close()` closes the underlying socket while the `ServiceBrowser` may
still have a background thread reading the socket. There could be a race
condition where the reading thread reads the closed socket, resulting in
EBADF crash. This patch catches the exception.
This makes test-paths.t pass with chg.
Differential Revision: https://phab.mercurial-scm.org/D919
Jun Wu <quark@fb.com> [Mon, 02 Oct 2017 19:31:33 -0700] rev 34447
test-revlog-mmapindex: make it compatible with chg
The test misses an explicit flush().
Differential Revision: https://phab.mercurial-scm.org/D918
Jun Wu <quark@fb.com> [Mon, 02 Oct 2017 19:10:32 -0700] rev 34446
test-profile: gate chg-incompatible part with '#if chg'
chg has a different extension loading logic, which affects the profiler
extension test case. Gate the block with '#if chg' so the test passes with
chg.
Differential Revision: https://phab.mercurial-scm.org/D916
Jun Wu <quark@fb.com> [Mon, 02 Oct 2017 18:22:43 -0700] rev 34445
test-logtoprocess: make it compatible with chg
chg runs more commands and outputs more lines. This patch matches them.
Differential Revision: https://phab.mercurial-scm.org/D914