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

configitems: register the 'convert.p4.encoding' config

configitems: register the 'gpg.key' config

configitems: register the 'gpg.cmd' config

configitems: register the 'keywordset.svn' config

configitems: register the 'hgk.path' config

configitems: register the 'share.poolnaming' config

configitems: register the 'share.pool' config

configitems: register the 'shelve.maxbackups' config

configitems: register the 'pager.attend' config

configitems: register the 'perf.stub' config

configitems: register the 'commands.rebase.requiredest' config

configitems: register the 'experimental.rebaseskipobsolete' config

configitems: register the 'experimental.nonnormalparanoidcheck' config

configitems: register the 'experimental.allowdivergence' config

histedit: removing the experimental config 'histeditng' This config has been around for about 2 years now. So, it can be assumed to be stable. Therefore, I am removing the config. This also makes the test 'test-histedit-base.t' compatible with chg. Test Plan: - Ran the test 'test-histedit-base.t' with and without '--chg' option. - Ran all the other tests without '--chg' option. - Checked the output of 'hg help histedit'. Differential Revision: https://phab.mercurial-scm.org/D942

convert: fix the RevisionSpec import in the bzr module This import was failing (because its invalid) which was resulting in the following tests failing with chg running: - test-convert-bzr.t - test-convert-bzr-directories.t - test-convert-bzr-ghosts.t - test-convert-bzr-treeroot.t - test-convert-bzr-114.t - test-convert-bzr-merges.t This commit fixes the import which in turn fixes the tests. Test Plan: Ran the aforementioned tests with and without '--chg' option. Differential Revision: https://phab.mercurial-scm.org/D936

test-annotate: fix up expected output for pure This is just a side effect of surfacing the "revisions were skipped" state in the blame output. Differential Revision: https://phab.mercurial-scm.org/D956

style: never use a space before a colon or comma Differential Revision: https://phab.mercurial-scm.org/D954

eol: make [eol] config section sensitive for chg confighash The eol extension may mangle the [eol] config section and that means chg is unable to detect config file change (because it re-applies setconfig changes). This makes test-eol.t pass with chg. Differential Revision: https://phab.mercurial-scm.org/D917

test-alias: make it compatible with chg ad1bdea (dispatch: defer environment variable resolution in alias commands (BC), 2016-05-06) made environment variables lazily resolved. But after D805 (alias: make alias command lazily resolved 2017-09-23), alias resolution happened after uisetup, which breaks the test for chg. `uisetup` is known to behave different in chg. Let's verify the feature without using `*setup`. Differential Revision: https://phab.mercurial-scm.org/D912

serve: make tests compatible with chg chg only supports 'hg serve' when the options to the serve command follow the 'hg serve'. For example, 'hg -R <repo> serve ..' is unsupported. This leads to issues with chg running for the following tests: - test-bundle2-exchange.t - test-clone-uncompressed.t - test-hgweb-csp.t - test-http-bad-server.t - test-http-bundle1.t - test-http-protocol.t - test-http.t There was an effort made earlier to fix this issue for chg and the tests were fixed to confirm to the compatible pattern. But the new tests did not take care of the same and hence, fail. Hopefully, there will be continuous build setup for chg after all tests are made compatible with chg so that we can avoid such issues. Test Plan: Ran the aforementioned tests with and without '--chg' option. Differential Revision: https://phab.mercurial-scm.org/D946

ui: convert to/from Optional[bytes] to Optional[str] in password manager This password manager proxy is roughly the right-looking layer to convert between strings and bytes. Many of these arguments can be None, so we have a helper method to make the conversion preserve Nones without exploding. Differential Revision: https://phab.mercurial-scm.org/D886

configitems: register the 'debug.dirstate.delaywrite' config

configitems: register the 'merge.preferancestor' config

configitems: register the 'email.from' config

configitems: register the 'smtp.port' config

configitems: register the 'phases.new-commit' config

configitems: register the 'experimental.histeditng' config

configitems: register the 'experimental.histedit.autoverb' config

configitems: register the 'histedit.singletransaction' config

configitems: register the 'histedit.linelen' config

configitems: register the 'histedit.dropmissing' config

configitems: register the 'histedit.defaultrev' config

configitems: register the 'transplant.log' config

configitems: register the 'transplant.filter' config

urllibcompat: move some adapters from pycompat to urllibcompat These are all the httpserver and urllib.* aliases. They seem to make more sense in the slightly-more-specific urllibcompat package than the general-purpose pycompat. Differential Revision: https://phab.mercurial-scm.org/D935

cleanup: use urllibcompat for renamed methods on urllib request objects Differential Revision: https://phab.mercurial-scm.org/D891

urllibcompat: new library to help abstract out some python3 urllib2 stuff Doing a new file instead of pycompat because I'm starting to feel like pycompat is getting a little enormous in terms of scope. Differential Revision: https://phab.mercurial-scm.org/D890

test-devel-warnings: make the test compatible with chg The test fails when run with the "--chg" option. Therefore, this commit makes it compatible with chg. Test Plan: Ran the test "test-devel-warnings.t' with and without the "--chg" option Differential Revision: https://phab.mercurial-scm.org/D915

fsmonitor: use configitem We might as well get this out of the way. Differential Revision: https://phab.mercurial-scm.org/D893

fsmonitor: access copymap in new location fsmonitor has been busted since 0865d25e8a8a due to moving self._copymap. Fix it. Differential Revision: https://phab.mercurial-scm.org/D892

extdata: use subprocess so we don't have to chdir() manually

extdata: just use iterator to read lines one by one

extdata: ignore ambiguous identifier as well