Yuya Nishihara <yuya@tcha.org> [Sun, 01 Oct 2017 10:50:00 +0100] rev 34457
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 34456
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 34455
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 34454
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 34453
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 34452
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 34451
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 34450
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 34449
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 34448
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 34447
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 34446
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 34445
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 34444
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
Saurabh Singh <singhsrb@fb.com> [Tue, 03 Oct 2017 11:10:03 -0700] rev 34443
test-globalopts: make the test compatible with chg
The test fails when run with the '--chg' option. Therefore, this
commit modifies the test to make it compatible with chg.
Test Plan:
Ran 'test-globalopts.t' with and without the '--chg' option.
Differential Revision: https://phab.mercurial-scm.org/D913
Jun Wu <quark@fb.com> [Mon, 02 Oct 2017 16:11:57 -0700] rev 34442
test-pager: make it compatible with chg
chg's runpager implementation is different. It behaves differently for the
"shell=False, command not found" case.
Differential Revision: https://phab.mercurial-scm.org/D911
Gregory Szorc <gregory.szorc@gmail.com> [Mon, 02 Oct 2017 11:03:53 +0100] rev 34441
changelog: use a Factory for default value for files
The default value is compiled into the generated type. This means
that default values are shared between instances. For immutable types
like bool, str, int, and tuple, this is fine. But for mutable types
like list and dict, we need to use attr.Factory() to instantiate a
new instance of the default for each object.
Differential Revision: https://phab.mercurial-scm.org/D901
Gregory Szorc <gregory.szorc@gmail.com> [Mon, 02 Oct 2017 19:28:41 +0100] rev 34440
cext: wrap before brace for functions
This is our prevailing style.
Differential Revision: https://phab.mercurial-scm.org/D910
Gregory Szorc <gregory.szorc@gmail.com> [Mon, 02 Oct 2017 19:09:52 +0100] rev 34439
cext: put case statements on separate line
This seems to be the prevailing style, even though it is a bit more
verbose for very simple switch statements.
Differential Revision: https://phab.mercurial-scm.org/D909
Gregory Szorc <gregory.szorc@gmail.com> [Mon, 02 Oct 2017 19:06:00 +0100] rev 34438
cext: reorder #include
We mostly abide by this style.
In one case, a blank line was inserted to prevent a local
`#include "file"` from coming before a `#include <file>`.
Differential Revision: https://phab.mercurial-scm.org/D908
Gregory Szorc <gregory.szorc@gmail.com> [Mon, 02 Oct 2017 19:02:43 +0100] rev 34437
cext: move braces for control statements to same line
This seems to be the prevailing style in the code by a wide margin.
Differential Revision: https://phab.mercurial-scm.org/D907
Saurabh Singh <singhsrb@fb.com> [Mon, 02 Oct 2017 19:17:04 +0100] rev 34436
registrar: fixing typo in comment
I was just going through the module and noticed the typo. This commit
fixes 'onfalure' -> 'onfailure'.
Differential Revision: https://phab.mercurial-scm.org/D906
Alex Gaynor <agaynor@mozilla.com> [Fri, 29 Sep 2017 15:49:20 +0000] rev 34435
style: never put multiple statements on one line
Differential Revision: https://phab.mercurial-scm.org/D905
Siddharth Agarwal <sid0@fb.com> [Mon, 02 Oct 2017 18:18:57 +0100] rev 34434
annotate: mark lines affected by skip-annotate with *
This is to prevent weird surprises from happening with skips being attributed
to the wrong changeset.
.. feature::
`hg annotate --skip` now prints a `*` on lines with skipped revisions
Differential Revision: https://phab.mercurial-scm.org/D900
Siddharth Agarwal <sid0@fb.com> [Mon, 02 Oct 2017 02:34:47 -0700] rev 34433
annotate: track whether a particular annotation was the result of a skip
We're going to expose this information in the UI in an upcoming patch.
Differential Revision: https://phab.mercurial-scm.org/D899
Siddharth Agarwal <sid0@fb.com> [Mon, 02 Oct 2017 02:34:47 -0700] rev 34432
annotate: introduce attr for storing per-line annotate data
We're going to extend this a bit -- at first by simply adding whether this was
a skipped child. We're well on our way to outgrowing tuples, though -- adding
more and more fields to tuples becomes annoying very quickly.
Differential Revision: https://phab.mercurial-scm.org/D898
Siddharth Agarwal <sid0@fb.com> [Mon, 02 Oct 2017 02:34:47 -0700] rev 34431
context: rename local 'attr' to 'attr_'
In the next diff we're going to import mercurial.thirdparty.attr, and pyflakes
complains about this if this rename isn't done.
Differential Revision: https://phab.mercurial-scm.org/D897
Siddharth Agarwal <sid0@fb.com> [Mon, 02 Oct 2017 02:34:47 -0700] rev 34430
annotate: move annotatepair unit tests to a separate file
In upcoming patches the output is going to be significantly longer than it is
today, and doctests don't allow wrapping the output.
Differential Revision: https://phab.mercurial-scm.org/D896
Siddharth Agarwal <sid0@fb.com> [Mon, 02 Oct 2017 02:34:47 -0700] rev 34429
check-code: allow an exception for camelcase where required
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
Augie Fackler <augie@google.com> [Sun, 01 Oct 2017 12:16:34 -0400] rev 34428
url: use native strings for header values
Differential Revision: https://phab.mercurial-scm.org/D889