Augie Fackler <raf@durin42.com> [Tue, 22 Aug 2017 16:59:12 -0400] rev 33984
tests: update test-progress to pass our import checker
Augie Fackler <raf@durin42.com> [Tue, 22 Aug 2017 16:59:06 -0400] rev 33983
tests: update test-patchbomb to pass our import checker
Augie Fackler <augie@google.com> [Mon, 28 Aug 2017 17:40:03 -0400] rev 33982
merge with stable
Michael Bolin <mbolin@fb.com> [Wed, 23 Aug 2017 18:24:57 +0000] rev 33981
dirstate: perform transactions with _copymap using single call, where possible
This replaces patterns such as this:
```
if f in self._copymap:
del self._copymap[f]
```
with this:
```
self._copymap.pop(f, None)
```
Although eliminating the extra lookup/call may be a negligible performance win
in the standard dirstate, alternative implementations, such as
[sqldirstate](https://bitbucket.org/facebook/hg-experimental/src/default/sqldirstate/)
may see a bigger win where each of these calls results in an RPC,
so the savings is greater.
Test Plan:
`make tests`
Differential Revision: https://phab.mercurial-scm.org/D493
Jun Wu <quark@fb.com> [Thu, 24 Aug 2017 20:25:16 -0700] rev 33980
pull: do not prompt "hg update" if update.requiredest is set
Previously, after pull, we show:
(run 'hg update' to get a working copy)
unconditionally. People might run `hg update` and get an exception if
`update.requiredest` is set, and get a bit frustrated. This patch changes
the code to not prompt `hg update` in that case.
Differential Revision: https://phab.mercurial-scm.org/D516
Martin von Zweigbergk <martinvonz@google.com> [Fri, 25 Aug 2017 22:05:10 -0700] rev 33979
changelog: abort on attempt to write wdir revision
Similar to the previous patch which prevented writing the null
revision to any revlog, but this is for the wdir revision.
Thanks to Jun for pointing this out.
Differential Revision: https://phab.mercurial-scm.org/D524
Jun Wu <quark@fb.com> [Thu, 24 Aug 2017 17:44:08 -0700] rev 33978
phabsend: show associated Differential Revisions with --confirm
Often people running `phabsend --confirm` just want to check whether a
commit will trigger a creation of new Differential Revision, or update an
existing one. This patch implements that. The `--confirm` message was
changed to use node instead of revision number to be consistent with what
`phabsend` outputs.
An example output looks like:
D487 -
a80f447973a0 test-extension: enable demandimport explicitly
D494 -
cf440ea6e47e test-casecollision-merge: fix the test
NEW -
0a6b97147128 phabsend: polish the docstring a bit
Send the above changes to https://phab.mercurial-scm.org/ (yn)?
Differential Revision: https://phab.mercurial-scm.org/D514
Jun Wu <quark@fb.com> [Thu, 24 Aug 2017 17:31:33 -0700] rev 33977
phabsend: print the actual URL with --confirm
Sometimes people have multiple Phabricator endpoints set in multiple repos.
It seems better for `--confirm` to prompt about the Phabricator endpoint
patches being sent to.
Differential Revision: https://phab.mercurial-scm.org/D513
Jun Wu <quark@fb.com> [Thu, 24 Aug 2017 17:25:18 -0700] rev 33976
phabsend: detect patch change with larger context
Previously phabsend has an optimization that will skip uploading a diff if
the patch (with context line number = 1) remains unchanged. That could be
confusing:
Aug 24 15:52:28 <martinvonz> phillco: something is wrong with phabricator'your patches/
Aug 24 15:52:45 <martinvonz> ... with phabricator's view of your patches again
Aug 24 15:53:38 <martinvonz> if i phabread D388 and then D399, i get a version of filemerge.py with "a, b, c" somewhere on line 344, which is not what phabricator shows for D399
Aug 24 15:53:51 <martinvonz> junw: maybe that's more for you ^
Fix that by checking context with 32767 lines, which is the same as what
will be actually sent.
Differential Revision: https://phab.mercurial-scm.org/D512
Jun Wu <quark@fb.com> [Thu, 24 Aug 2017 16:52:28 -0700] rev 33975
phabsend: make --amend the default
The local tag feature was intended to make `phabsend` closer to `email`
workflow. But its experience is not great in multiple ways:
- after rebase, obsoleted changesets are still visible because of tags
- without obsstore, the association information will get lost
- even with obsstore, things could go wrong with graft, export+import
- no easy way to tell which Differential Revision a commit is associated
Therefore make `--amend` the default. People wanting the old behavior can
use `--no-amend`.
Differential Revision: https://phab.mercurial-scm.org/D511