Martin von Zweigbergk <martinvonz@google.com> [Fri, 15 Dec 2017 08:47:28 -0800] rev 35431
debugdiscovery: correct and clean up command synopsis
This does a few things:
* Changes "-r" to "--rev", since "-r" is not a valid short form
* Removes non-existent "-l" and "-b" options
* Removes "..." after options, since we don't usually have that
Differential Revision: https://phab.mercurial-scm.org/D1706
Martin von Zweigbergk <martinvonz@google.com> [Thu, 14 Dec 2017 00:25:03 -0800] rev 35430
copies: group wdir-handling in one place
I think this makes it both easier to follow and shorter.
Differential Revision: https://phab.mercurial-scm.org/D1698
Martin von Zweigbergk <martinvonz@google.com> [Thu, 14 Dec 2017 00:18:38 -0800] rev 35429
copies: extract method for getting non-wdir forward copies
I may add an alternative way of getting copy metadata (from changelog,
not filelog) but the chaining with the dirstate copy metadata will be
the same, so it will probably help to have this extracted. Even if
that doesn't happen, the next patch will show that we can simplify
this a bit after this refactoring, so it seems worth it regardless.
Differential Revision: https://phab.mercurial-scm.org/D1697
Martin von Zweigbergk <martinvonz@google.com> [Thu, 14 Dec 2017 08:27:22 -0800] rev 35428
copies: consistently use """ for docstrings
Differential Revision: https://phab.mercurial-scm.org/D1696
Martin von Zweigbergk <martinvonz@google.com> [Mon, 11 Dec 2017 10:24:38 -0800] rev 35427
copies: always respect matcher arg to _forwardcopies()
The function would ignore the matcher if the dirstate copies were
requested. It doesn't matter in practice because all callers used the
returned map only for looking up specific files from and those files
had already been filtered by the matcher (AFACT). Still, it's a little
confusing, so let's make it clearer by respecting the matcher in this
case too.
Differential Revision: https://phab.mercurial-scm.org/D1695
Martin von Zweigbergk <martinvonz@google.com> [Wed, 13 Dec 2017 11:21:25 -0800] rev 35426
debugdiscovery: drop reference to non-existent --remote-head option
It seems like it didn't even exist when debugdiscovery was introduced
in cb98fed52495 (discovery: add new set-based discovery, 2011-05-02).
Differential Revision: https://phab.mercurial-scm.org/D1693
Martin von Zweigbergk <martinvonz@google.com> [Wed, 13 Dec 2017 11:20:52 -0800] rev 35425
debugdiscovery: drop reference to non-existent --serverlog option
It seems like it didn't even exist when debugdiscovery was introduced
in cb98fed52495 (discovery: add new set-based discovery, 2011-05-02).
Differential Revision: https://phab.mercurial-scm.org/D1692
Martin von Zweigbergk <martinvonz@google.com> [Wed, 13 Dec 2017 11:19:24 -0800] rev 35424
debugdiscovery: drop reference to invalid --branch option
It seems like it didn't even exist when debugdiscovery was introduced
in cb98fed52495 (discovery: add new set-based discovery, 2011-05-02).
Differential Revision: https://phab.mercurial-scm.org/D1691
Martin von Zweigbergk <martinvonz@google.com> [Thu, 14 Dec 2017 22:30:03 -0800] rev 35423
tests: avoid echo with backslash escapes
Some shells' echo (e.g. Bash's) do not interpret backslash escapes by
default, while others shells' do (e.g. Dash's). This led to a failure
in test-run-tests.t. We could switch to the more compatible printf,
but using a heredoc seems simpler, so that's what this patch does.
For anyone who wants to test this for themselves, remove the "unset
HGTEST_SHELL" line in helper-runtests.sh and pass
e.g. "--shell=/bin/dash" to the test runner.
Differential Revision: https://phab.mercurial-scm.org/D1699
Anton Shestakov <av6@dwimlabs.net> [Fri, 15 Dec 2017 12:15:58 +0800] rev 35422
hgweb: stop using HTML comments in <script>
Once upon a time, in 1995, there were browsers that didn't understand <script>
tags and they would simply show the code inside as text. This started a
tradition of wrapping everything inside <script> in <!-- HTML comments -->.
Nowadays, it's not only not needed, but can be considered harmful[1]:
- within XHTML documents, the source will actually be hidden from all browsers
and rendered useless
- `--` is not allowed within HTML comments, so any decrement operations in
script are invalid
[1]: http://www.javascripttoolbox.com/bestpractices/#comments
Augie Fackler <augie@google.com> [Thu, 14 Dec 2017 16:01:28 -0500] rev 35421
merge with stable
Alex Gaynor <agaynor@mozilla.com> [Thu, 14 Dec 2017 20:18:15 +0000] rev 35420
statprof: remove a line of deadcode
Differential Revision: https://phab.mercurial-scm.org/D1689
Yuya Nishihara <yuya@tcha.org> [Sun, 01 Oct 2017 12:21:50 +0100] rev 35419
extdata: abort if external command exits with non-zero status (BC)
Per the last discussion, this is more reliable and consistent way than
suppressing an error. For grep, erroring out might be inconvenient, but
for curl, non-zero exit status should be detected. The latter wouldn't be
possible if non-zero status is ignored.
https://www.mercurial-scm.org/pipermail/mercurial-devel/2017-October/105727.html
Anton Shestakov <av6@dwimlabs.net> [Thu, 14 Dec 2017 21:30:00 +0800] rev 35418
hgweb: update graph function docstring
Phil Cohen <phillco@fb.com> [Tue, 12 Dec 2017 22:05:21 -0800] rev 35417
rebase: fix for hgsubversion
5c25fe7fb1e broke something in the hgsubversion test path, causing it raise an
abort (Abort: nothing to merge) during a perfectly good rebase. I tracked it
down to this change. It's probably not hgsubversion related.
I suspect that using the same `wctx` from before the initial update causes
problems with the wctx's cached manifest property. I noticed we also sometimes
stick random gunk on the wctx object in other places (like in `copies.py`) so
it's probably best to reset it for now.
The line I added before was actually useless since we don't pass wctx to the
initial `merge.update`, so it defaults to `repo[None]`. So I just removed it.
Differential Revision: https://phab.mercurial-scm.org/D1679
Anton Shestakov <av6@dwimlabs.net> [Mon, 11 Dec 2017 15:43:56 +0800] rev 35416
hgweb: render next pages on /graph incrementally
Previously, when user scrolled down to see the next page on /graph, all hgweb
did was re-render everything that would be visible (by simply incrementing
revcount). It was not efficient at all, and this patch makes /graph page behave
similarly to the regular /log: every new page only consists of new changesets,
no duplication, and only jsdata is based on the full set of changesets required
to build accurate graph.
This is achieved by adding "?graphtop=<node>" to the next page URL template,
effectively remembering where the graph started, and using that value to create
the new `tree` that covers the whole visible graph. That variable is then used
to produce jsdata for redrawing graph client-side.
nextentry is used for the same purpose as on /log page (to format the next page
URL), but it's not a part of the graph.