dispatch: move initialization of sys.std* files I'll add another Python 3 hack.

py3: work around the scope of exception variable in dispatch.run() https://stackoverflow.com/questions/29268892/

chg: just forward --time to command server Since we've removed the use of atexit in de5c9d0e02ea, --time just works.

windows: add an experimental option for long paths support This commit adds an experimental --long-paths-support flag to build_hgexe on Windows. It is off by default, but when supplied, causes setup.py to embed some XML into the generated hg.exe, which in turn tells Windows to allow this exe to use long paths (given that the appropriate registry setting is enabled as well). This was tested on Windows 10 14393 and 15063. This commit introduces a badly-named initialize_options function, but its name is dictated by distutils, rather than chosen. # no-check-commit

configitems: register the 'experimental.graphstyle.grandparent' config

configitems: register the 'experimental.graphstyle.missing' config

configitems: register the 'experimental.graphstyle.parent' config

configitems: register the 'devel.empty-changegroup' config

configitems: register the 'devel.cache-vfs' config

configitems: register the 'devel.warn-config-default' config

configitems: register the 'devel.warn-config' config

configitems: register 'merge.checkunknown' and 'merge.checkignored' They both use the same function defining a default, so we need to update them at the same time.

configitems: register the 'diff.*' config All the config were already using a unified function with a forced default, so, registering them all at once seems safe.

configitems: register the 'experimental.mmapindexthreshold' config

configitems: register the 'experimental.maxdeltachainspan' config

configitems: register the 'commands.show.aliasprefix' config

configitems: register the 'blackbox.track' config

copies: add docs for config `experimental.copytrace.sourcecommitlimit` This patch adds documentation for the config option. The config name does not convey much and hence documentation was required. Differential Revision: https://phab.mercurial-scm.org/D986

hgweb: extract function for loading style from request context Also make it work on Python 3. Differential Revision: https://phab.mercurial-scm.org/D970

request: coerce content-type to native str Again, required by WSGI. Differential Revision: https://phab.mercurial-scm.org/D969

request: use trivial iterator over dictionary keys Differential Revision: https://phab.mercurial-scm.org/D968

hgweb: when constructing or adding to a wsgi environ dict, use native strs That's what's required of us to work with the WSGI API on Python 3. Differential Revision: https://phab.mercurial-scm.org/D967

hgweb: produce native string for etag value Also use %d since we know mtime is numeric. Differential Revision: https://phab.mercurial-scm.org/D966

hgweb: in protocol adapter, look for bytes instances, not str Differential Revision: https://phab.mercurial-scm.org/D963

hgweb: in protocol adapter, avoid control reaching end of non-void function This greatly confounded some Python 3 porting work, once it was managing to get this far. Differential Revision: https://phab.mercurial-scm.org/D962

test-check-code: fail new commits which use 'atexit' instead of 'ui.atexit' Callbacks registered with 'atexit' are sometimes not called (like when hg aborts and calls os._exit). On the other hand, callbacks registered with 'ui.atexit' are called in most cases. Therefore, encouraging the use of 'ui.atexit' by failing the test 'test-check-code.t' appropriately. Test Plan: Ran the test 'test-check-code.t' after importing 'atexit' in one of the py files and confirmed that the test fails. Differential Revision: https://phab.mercurial-scm.org/D961

test-push-race: use 'ui.atexit' instead of python's 'atexit' Callbacks registered with 'atexit' are sometimes not called (like when a process is killed by the SIGTERM signal). Therefore, this commit replaces it with 'ui.atexit' which ensures that the callbacks are always called. This also makes the test compatible with chg. Test Plan: Ran the test 'test-push-race.t' with and without the '--chg' option. Differential Revision: https://phab.mercurial-scm.org/D957

py3: use '%d' for integers instead of '%s' Differential Revision: https://phab.mercurial-scm.org/D973

py3: fix keyword arguments handling in mq This patch fixes the handling of keyword arguments to functions on Python 3. On python3, the keys of keyword arguments need to str which is unicode. So any keyword argument will get will have str keys and any dictionary we pass as kwargs must have all the keys as str. This patch uses pycompat.(strkwargs|byteskwargs) to do so conversion between bytes keys and str keys and use r'' if there are very less uses and conversion can be prevented. Differential Revision: https://phab.mercurial-scm.org/D972

test-rebase-base: clarify it is about the "--base" flag It happened several times that people use `test-rebase-base.t` as a general purposed test file for rebase. But it is intended to be only related to the `--base` flag. This patch split, renamed the test, and added a note to clarify. Differential Revision: https://phab.mercurial-scm.org/D975