merge: backup conflicting directories when getting files During batchget, if a target file conflicts with a directory, or if the directory a target file is in conflicts with a file, backup and remove the conflicting file or directory before performing the get. Differential Revision: https://phab.mercurial-scm.org/D778

merge: add merge action 'pr' to rename files during update Add a new merge action to handle a path conflict by renaming the conflicting file to a safe name. The rename is just to avoid problems on the filesystem. The conflict is still considered unresolved until the user marks the original path as resolved. Differential Revision: https://phab.mercurial-scm.org/D777

merge: add merge action 'p' to record path conflicts during update Add a new merge action to record path conflicts. A status message is printed, and the path conflict is added to the merge state. Differential Revision: https://phab.mercurial-scm.org/D776

commands: update the resolve command to handle path conflicts The resolve command must support displaying path conflicts and marking them as resolved or unresolved. Differential Revision: https://phab.mercurial-scm.org/D775

merge: add pathconflict merge state Path conflicts that occur during merges are represented by 'pu' (unresolved) and 'pr' (resolved) records in the merge state. These are stored on disk in 'P' records. Differential Revision: https://phab.mercurial-scm.org/D774

tests: add a test demonstrating basic path conflict failures Differential Revision: https://phab.mercurial-scm.org/D773

scmutil: handle conflicting files and dirs in origbackuppath When ui.origbackuppath is set, .orig files are stored outside of the working copy. However conflicts can occur when files or directories end up having the same name. These conflicts cause Mercurial to abort, even if they've been created as a result of different backups. Make sure we always replace files or directories in the origbackuppath if they conflict with another file or directory. Test Plan: Add new unit test for conflicting paths. Differential Revision: https://phab.mercurial-scm.org/D680

extdata: show debug message if external command exits with non-zero status This isn't fatal because it's quite common for grep to exit with 1. Thanks to Foozy for spotting this.

templatekw: allow accessing to nested namespace item by its template name Since we have the dot operator, it makes more sense to write {namespaces.tags % "{tag}"} instead of {namespaces.tags % "{name}"}

templatekw: get rid of temporary dicts from shownamespaces()

templatekw: rename peerpaths to peerurls per naming convention (BC) Since each element is called as "url", the template keyword should be named as "<whatever>urls". {peerurls} is now stabilized.

templatekw: make experimental {peerpaths} return a single-level dict (BC) This was planned as in c0d8de2724ce, "{peerpaths.default.pushurl} will be translated to peerpaths['default'].makemap()['pushurl'], which means {peerpaths} should be a single-level dict and sub-options should be makemap()-ed."

templatekw: fix scope of peerpath url bound to generator I had to explicitly bind 'd' to the generator. Otherwise, the last 'd' would be used.

templater: extend dot operator as a short for get(dict, key)

templater: add dot operator to easily access a sub item This and the next patch will allow us to access a deeply-nested item by foo.bar.baz syntax.

templater: wrap get/min/max result so map operation can apply to element See the test for usage example. wraphybridvalue() takes a key/value pair because a hybrid dict passes a key to its makemap() function. Since makemap() of showmanifest() doesn't need a key, it's set to None.

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

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