Jun Wu <quark@fb.com> [Wed, 11 Oct 2017 17:42:35 -0700] rev 34641
largefiles: do not use platform.system()
See the previous patch for the reason.
Differential Revision: https://phab.mercurial-scm.org/D1020
Jun Wu <quark@fb.com> [Wed, 11 Oct 2017 17:38:20 -0700] rev 34640
logtoprocess: do not use platform.system()
See the previous patch for the reason.
Differential Revision: https://phab.mercurial-scm.org/D1019
Jun Wu <quark@fb.com> [Wed, 11 Oct 2017 17:27:21 -0700] rev 34639
selectors2: do not use platform.system()
`platform.system()` may have a side effect spawning a shell executing
`uname -p`, which may print a warning when the current directory is removed:
shell-init: error retrieving current directory: getcwd: cannot access parent directories: No such file or directory
This patch changes selectors2 to test the `sys.platform` string, which is a
much safer way to detect Jython.
Jython's `sys.platform` looks like this:
Jython 2.7.1 (default:
0df7adb1b397, Jun 30 2017, 19:02:43)
[OpenJDK 64-Bit Server VM (Oracle Corporation)] on java1.8.0_144
Type "help", "copyright", "credits" or "license" for more information.
>>> import sys
>>> sys.platform
'java1.8.0_144 ( ==linux2 for targets )'
Differential Revision: https://phab.mercurial-scm.org/D1018
Jun Wu <quark@fb.com> [Mon, 09 Oct 2017 12:42:28 -0700] rev 34638
dispatch: when --pager=no is passed, also disable pager on req.repo.ui
With a future chg change, `req.repo` could be set and currently it is
unaffected by `--pager=on`. This patch makes it so.
This could make one of the test cases in `test-pager.t` pass with future chg
changes.
Differential Revision: https://phab.mercurial-scm.org/D990
Durham Goode <durham@fb.com> [Wed, 11 Oct 2017 10:36:59 -0700] rev 34637
bundle2: immediate exit for ctrl+c (
issue5692)
21c2df59a regressed bundle2 by catching all exceptions and trying to handle
them. The old behavior was to allow KeyboardInterrupts to throw and not have
graceful cleanup, which allowed it to exit immediately. Let's go back to that
behavior.
Differential Revision: https://phab.mercurial-scm.org/D960
Augie Fackler <augie@google.com> [Wed, 04 Oct 2017 11:04:18 -0400] rev 34636
exewrapper: format with clang-format
A few *s move around, some spaces around parens, a couple of
braces. Nothing remarkable.
Differential Revision: https://phab.mercurial-scm.org/D1032
Augie Fackler <augie@google.com> [Wed, 04 Oct 2017 11:02:44 -0400] rev 34635
util: add clang-format control comment around struct and format macro
clang-format is not a fan of PyObject_HEAD.
Differential Revision: https://phab.mercurial-scm.org/D1031
Augie Fackler <augie@google.com> [Wed, 04 Oct 2017 10:57:23 -0400] rev 34634
mpatch: reflow two oddly formatted else blocks with clang-format
Differential Revision: https://phab.mercurial-scm.org/D1029
Augie Fackler <augie@google.com> [Wed, 04 Oct 2017 10:55:51 -0400] rev 34633
mpatch: re-wrap wide line with clang-format
Differential Revision: https://phab.mercurial-scm.org/D1027
Augie Fackler <augie@google.com> [Wed, 04 Oct 2017 10:51:39 -0400] rev 34632
bdiff: remove trailing newlines
Differential Revision: https://phab.mercurial-scm.org/D1009
Augie Fackler <augie@google.com> [Wed, 04 Oct 2017 10:51:25 -0400] rev 34631
bdiff: rewrap function prototypes per clang-format
Differential Revision: https://phab.mercurial-scm.org/D1008
Augie Fackler <augie@google.com> [Wed, 04 Oct 2017 10:50:54 -0400] rev 34630
bdiff: re-wrap lines per clang-format
A few too-wide lines corrected, and some places where clang-format
prefers to wrap after the binary operator instead of before. I don't
feel strongly, so I'm leaving the auto-format result as "after the
binary operator".
Differential Revision: https://phab.mercurial-scm.org/D1007
Augie Fackler <augie@google.com> [Wed, 04 Oct 2017 10:49:34 -0400] rev 34629
bdiff: remove extra space after * per clang-format
Differential Revision: https://phab.mercurial-scm.org/D1006
Augie Fackler <augie@google.com> [Wed, 04 Oct 2017 10:48:46 -0400] rev 34628
bdiff: fix misplaced comma in macro definition with clang-format
Differential Revision: https://phab.mercurial-scm.org/D1005
Augie Fackler <augie@google.com> [Wed, 04 Oct 2017 10:47:51 -0400] rev 34627
bdiff: format header file with clang-format
Differential Revision: https://phab.mercurial-scm.org/D1004
Augie Fackler <augie@google.com> [Wed, 04 Oct 2017 10:47:19 -0400] rev 34626
bdiff: sort includes using clang-format
Differential Revision: https://phab.mercurial-scm.org/D1003
muxator <a.mux@inwind.it> [Wed, 11 Oct 2017 01:47:00 +0200] rev 34625
build: "make deb" failed when the base path contained spaces
With these changes, all the commands triggered by "make deb" use proper quoting
and succeed even when invoked from a directory containing spaces.
muxator <a.mux@inwind.it> [Wed, 11 Oct 2017 02:06:12 +0200] rev 34624
build: chg build was failing when the base directory contained spaces
muxator <a.mux@inwind.it> [Wed, 11 Oct 2017 01:37:43 +0200] rev 34623
build: initial version detection by make deb/rpm was missing quoting
muxator <a.mux@inwind.it> [Wed, 11 Oct 2017 01:19:48 +0200] rev 34622
build: make install in "/doc" failed if the destination dir contained spaces
This and the following commits try to add the necessary quoting in the build
scripts to make the process more robust.
The target for now is rendering "make deb" successful even when the base
directory contains spaces (eg. "/opt/mercu rial").
The build process should succeed without scattering files in spurious
directories (eg.: "/opt/mercu/usr/bin/hg").
Paul Morelle <paul.morelle@octobus.net> [Thu, 05 Oct 2017 16:13:05 +0200] rev 34621
strip: take branch into account when selecting update target (
issue5540)
Test contributed by Matt Harbison
Keep the same behavior in most cases (i.e. first parent of the first root of
stripped changsets), but if the branch differs from wdir's, try to find another
parent of stripped commits that is on the same branch.
Denis Laxalde <denis.laxalde@logilab.fr> [Wed, 04 Oct 2017 18:49:09 +0200] rev 34620
scmutil: factor out building of transaction summary callback
In registersummarycallback(), we extra generic bits of the existing
"reportsummary" function into a decorator which will be used in forthcoming
changesets to add new summary callbacks.
Denis Laxalde <denis.laxalde@logilab.fr> [Sun, 01 Oct 2017 09:52:44 +0200] rev 34619
scmutil: factor out transaction name lookup in registersummarycallback()
Add an inner txmatch function in registersummarycallback() factoring out the
logic to determine if the transaction matches a particular sources set. We'll
reuse this function to add some new report logic in the new changeset.
Boris Feld <boris.feld@octobus.net> [Wed, 11 Oct 2017 05:23:45 +0200] rev 34618
configitems: register the annotate diff options
Boris Feld <boris.feld@octobus.net> [Wed, 11 Oct 2017 05:42:56 +0200] rev 34617
configitems: register the 'convert.cvsps.logencoding' config
Boris Feld <boris.feld@octobus.net> [Wed, 11 Oct 2017 05:36:10 +0200] rev 34616
configitems: register the 'ui.interface.chunkselector' config
Boris Feld <boris.feld@octobus.net> [Wed, 11 Oct 2017 05:18:20 +0200] rev 34615
configitems: register the 'experimental.archivemetatemplate' config
Boris Feld <boris.feld@octobus.net> [Wed, 11 Oct 2017 04:57:54 +0200] rev 34614
configitems: register the 'rebase.singletransaction' config
Boris Feld <boris.feld@octobus.net> [Wed, 11 Oct 2017 17:51:40 +0200] rev 34613
configitems: register the 'server.bundle*' family of config
All these config use the same function specifying a default value. We need to
register them all at the same time.
Boris Feld <boris.feld@octobus.net> [Wed, 11 Oct 2017 04:16:17 +0200] rev 34612
configitems: register the 'web.logourl' config