Tue, 22 Aug 2017 16:59:17 -0400 tests: update test-requires to pass our import checker
Augie Fackler <raf@durin42.com> [Tue, 22 Aug 2017 16:59:17 -0400] rev 34003
tests: update test-requires to pass our import checker
Tue, 22 Aug 2017 16:59:12 -0400 tests: update test-progress to pass our import checker
Augie Fackler <raf@durin42.com> [Tue, 22 Aug 2017 16:59:12 -0400] rev 34002
tests: update test-progress to pass our import checker
Tue, 22 Aug 2017 16:59:06 -0400 tests: update test-patchbomb to pass our import checker
Augie Fackler <raf@durin42.com> [Tue, 22 Aug 2017 16:59:06 -0400] rev 34001
tests: update test-patchbomb to pass our import checker
Mon, 28 Aug 2017 17:40:03 -0400 merge with stable
Augie Fackler <augie@google.com> [Mon, 28 Aug 2017 17:40:03 -0400] rev 34000
merge with stable
Wed, 23 Aug 2017 18:24:57 +0000 dirstate: perform transactions with _copymap using single call, where possible
Michael Bolin <mbolin@fb.com> [Wed, 23 Aug 2017 18:24:57 +0000] rev 33999
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
Thu, 24 Aug 2017 20:25:16 -0700 pull: do not prompt "hg update" if update.requiredest is set
Jun Wu <quark@fb.com> [Thu, 24 Aug 2017 20:25:16 -0700] rev 33998
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
Fri, 25 Aug 2017 22:05:10 -0700 changelog: abort on attempt to write wdir revision
Martin von Zweigbergk <martinvonz@google.com> [Fri, 25 Aug 2017 22:05:10 -0700] rev 33997
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
Thu, 24 Aug 2017 17:44:08 -0700 phabsend: show associated Differential Revisions with --confirm
Jun Wu <quark@fb.com> [Thu, 24 Aug 2017 17:44:08 -0700] rev 33996
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
Thu, 24 Aug 2017 17:31:33 -0700 phabsend: print the actual URL with --confirm
Jun Wu <quark@fb.com> [Thu, 24 Aug 2017 17:31:33 -0700] rev 33995
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
Thu, 24 Aug 2017 17:25:18 -0700 phabsend: detect patch change with larger context
Jun Wu <quark@fb.com> [Thu, 24 Aug 2017 17:25:18 -0700] rev 33994
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
Thu, 24 Aug 2017 16:52:28 -0700 phabsend: make --amend the default
Jun Wu <quark@fb.com> [Thu, 24 Aug 2017 16:52:28 -0700] rev 33993
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
Thu, 24 Aug 2017 17:26:10 -0700 phabsend: polish the docstring a bit
Jun Wu <quark@fb.com> [Thu, 24 Aug 2017 17:26:10 -0700] rev 33992
phabsend: polish the docstring a bit Differential Revision: https://phab.mercurial-scm.org/D510
(0) -30000 -10000 -3000 -1000 -300 -100 -12 +12 +100 +300 +1000 +3000 +10000 tip