Mon, 25 Sep 2017 11:05:16 +0200 keepalive: add more context to bad status line errors
Gregory Szorc <gregory.szorc@gmail.com> [Mon, 25 Sep 2017 11:05:16 +0200] rev 34308
keepalive: add more context to bad status line errors As the TODO in the test said, the previous error message was not very helpful. Let's improve things. Differential Revision: https://phab.mercurial-scm.org/D811
Fri, 18 Aug 2017 20:20:38 -0700 tests: add interface checks for bundle, statichttp, and union peers
Gregory Szorc <gregory.szorc@gmail.com> [Fri, 18 Aug 2017 20:20:38 -0700] rev 34307
tests: add interface checks for bundle, statichttp, and union peers I forgot to add these when I initially wrote the test. They inherit from localrepo.localpeer, so they should be explicitly tested. Differential Revision: https://phab.mercurial-scm.org/D810
Sat, 23 Sep 2017 13:46:12 -0700 alias: make alias command lazily resolved
Jun Wu <quark@fb.com> [Sat, 23 Sep 2017 13:46:12 -0700] rev 34306
alias: make alias command lazily resolved With many aliases, resolving them could have some visible overhead. Below is part of traceprof [1] output of `hg bookmark --hidden`: (time unit: ms) 37 \ addaliases dispatch.py:526 37 | __init__ (60 times) dispatch.py:402 33 | findcmd (108 times) cmdutil.py:721 16 | findpossible (49 times) cmdutil.py:683 It may get better by optimizing `findcmd` to do a bisect, but we don't really need to resolve an alias if it's not used, so let's make those command entries lazy. After this patch, `addalias` takes less than 1ms. .. perf:: improved performance when many aliases are defined [1]: https://bitbucket.org/facebook/hg-experimental/src/9aca0dbdbdfc48457e5d2581ca2d6e662fced2e6/hgext3rd/traceprof.pyx Differential Revision: https://phab.mercurial-scm.org/D805
Sat, 23 Sep 2017 13:31:09 -0700 alias: test duplicated definition earlier
Jun Wu <quark@fb.com> [Sat, 23 Sep 2017 13:31:09 -0700] rev 34305
alias: test duplicated definition earlier This patch moves the old definition checking logic introduced by f4b7be3f8430 earlier. So that the test itself does not depend on `aliasdef`. The check is to avoid wrapping a same alias multiple times. It can be done by checking the config name and value (`definition` in code), without constructing a `cmdalias` instance. This makes the next patch easier to review. Differential Revision: https://phab.mercurial-scm.org/D804
Sun, 24 Sep 2017 19:37:55 +0530 uncommit: add a test for uncommit with uncommitondirtywdir config in merge
Pulkit Goyal <7895pulkit@gmail.com> [Sun, 24 Sep 2017 19:37:55 +0530] rev 34304
uncommit: add a test for uncommit with uncommitondirtywdir config in merge Differential Revision: https://phab.mercurial-scm.org/D809
Thu, 14 Sep 2017 13:14:32 -0700 largefiles: force an on-disk merge
Phil Cohen <phillco@fb.com> [Thu, 14 Sep 2017 13:14:32 -0700] rev 34303
largefiles: force an on-disk merge Largefiles isn't a good candidate for in-memory merge (it uses a custom dirstate, matcher, and the files might not fit in memory) so have it always run an old-style merge. Differential Revision: https://phab.mercurial-scm.org/D683
Thu, 14 Sep 2017 13:14:32 -0700 merge: allow a custom working context to be passed to update
Phil Cohen <phillco@fb.com> [Thu, 14 Sep 2017 13:14:32 -0700] rev 34302
merge: allow a custom working context to be passed to update This will allow anyone to enable the first in-menmory merge milestone by wrapping merge.update in an extension and creating an overlayworkingctx. Differential Revision: https://phab.mercurial-scm.org/D682
Wed, 14 Jun 2017 11:13:57 -0400 patchbomb: add test that shows --to and --cc override matching config item
Augie Fackler <augie@google.com> [Wed, 14 Jun 2017 11:13:57 -0400] rev 34301
patchbomb: add test that shows --to and --cc override matching config item As far as I know this has always been true and is intentional (it's in line with many other behaviors), but it wasn't tested.
Thu, 21 Sep 2017 11:10:20 -0700 blackbox: move _openlogfile to a separate method
Jun Wu <quark@fb.com> [Thu, 21 Sep 2017 11:10:20 -0700] rev 34300
blackbox: move _openlogfile to a separate method This removes several `stat` syscalls for accessing `_bbvfs` and makes `ui` object cleaner. Differential Revision: https://phab.mercurial-scm.org/D769
Thu, 21 Sep 2017 11:03:37 -0700 blackbox: do not prevent 'chg init' from working
Jun Wu <quark@fb.com> [Thu, 21 Sep 2017 11:03:37 -0700] rev 34299
blackbox: do not prevent 'chg init' from working Previously, blackbox always appends to blackbox.log and creates the directory for that file on demand. That could be an issue if: 1. chg starts from `$REPO` directory, so `ui._bbrepo` is set. 2. `rm -rf $REPO`. 3. `chg init $REPO`, blackbox writes something and `init` will fail because `$REPO` directory is non-empty. This patch fixes that by verifying whether vfs exists before re-using it. Differential Revision: https://phab.mercurial-scm.org/D768
(0) -30000 -10000 -3000 -1000 -300 -100 -10 +10 +100 +300 +1000 +3000 +10000 tip