Yuya Nishihara <yuya@tcha.org> [Sun, 03 Sep 2017 14:32:11 +0900] rev 34146
doctest: bulk-replace string literals with b'' for Python 3
Our code transformer can't rewrite string literals in docstrings, and I
don't want to make the transformer more complex.
Yuya Nishihara <yuya@tcha.org> [Thu, 07 Sep 2017 22:36:54 +0900] rev 34145
debuginstall: do not pass exception object to formatter (issue5676)
Yuya Nishihara <yuya@tcha.org> [Thu, 07 Sep 2017 22:27:23 +0900] rev 34144
debuginstall: use codecs.lookup() to detect invalid encoding
encoding.fromlocal() never tries to decode an ascii string since 853574db5b12,
and there's no universal non-ascii string which can be decoded as any valid
character set.
Yuya Nishihara <yuya@tcha.org> [Sun, 10 Sep 2017 23:37:14 +0900] rev 34143
extensions: fix wrapcommand/function of class instance
5361771f9714 changed _updatewrapper() to copy the __name__ attribute, but
not all callable objects has __name__.
Spotted by loading mq with extdiff.
Durham Goode <durham@fb.com> [Tue, 12 Sep 2017 09:13:02 -0700] rev 34142
changegroup: avoid creating empty changegroup part
Previously this check happened in the changegroup code itself. Since its
refactor, this logic needs to move out to callers that care about it, such as
this one. Otherwise we get empty bundle devel-warnings in certain extensions.
Differential Revision: https://phab.mercurial-scm.org/D690
Durham Goode <durham@fb.com> [Tue, 12 Sep 2017 15:12:27 -0700] rev 34141
tests: split test-revset.t in half
This test has gotten so large that running it can exceed the normal timeout on
systems under load (like if we're running all the tests in parallel). This patch
splits the test cleanly in half.
Differential Revision: https://phab.mercurial-scm.org/D694
Phil Cohen <phillco@fb.com> [Mon, 11 Sep 2017 13:17:43 -0700] rev 34140
merge: flush any deferred writes just before recordupdates()
``recordupdates`` calls into the dirstate which requires the files to be
there, so this is the last possible moment we can flush anything.
Differential Revision: https://phab.mercurial-scm.org/D673
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