Phil Cohen <phillco@fb.com> [Mon, 11 Sep 2017 13:03:27 -0700] rev 34139
merge: flush any deferred writes before, and after, running any workers
Since we fork to create workers, any changes they queue up will be lost after
the worker terminates, so the easiest solution is to have each worker flush
the writes they accumulate--we are close to the end of the merge in any case.
To prevent duplicated writes, we also have the master processs flush before
forking.
In an in-memory merge (M2), we'll instead disable the use of workers.
Differential Revision: https://phab.mercurial-scm.org/D628
Phil Cohen <phillco@fb.com> [Mon, 11 Sep 2017 13:03:27 -0700] rev 34138
filemerge: flush if using deferred writes when running a merge tool
Since merge tools might read from the filesystem, we need to write out our
deferred writes here.
No-ops if not using deferred writes.
Differential Revision: https://phab.mercurial-scm.org/D627
Phil Cohen <phillco@fb.com> [Mon, 11 Sep 2017 13:03:27 -0700] rev 34137
merge: pass wctx to premerge, filemerge
In the in-memory merge branch. we'll need to call a function (``flushall``) on
the wctx inside of _xmerge.
This prepares the way so it can be done without hacks like ``fcd.ctx()``.
Differential Revision: https://phab.mercurial-scm.org/D449
Boris Feld <boris.feld@octobus.net> [Mon, 11 Sep 2017 18:07:29 +0200] rev 34136
cmdutil: fix amend when passing a date
Following https://phab.mercurial-scm.org/D636, passing the same date that the
changeset to amend would results in no new commits but the output changed
from:
$ hg amend -d '0 0'
nothing changed
[1]
to:
$ hg amend -d '0 0'
Restore the old behavior by parsing the date passed as parameter so the
condition "date == old.date()" correctly works in cases both dates are
identical.
Add a test for covering this regression.
This bug was found thanks to Evolve test suite.
Differential Revision: https://phab.mercurial-scm.org/D691