configitems: register the 'logtoprocess.command' config

configitems: register the 'logtoprocess.commandfinish' config

configitems: register the 'logtoprocess.commandexception' config

configitems: register the 'pager.pager' config

configitems: register the 'web.maxchanges' config

configitems: register the 'web.maxfiles' config

configitems: register the 'web.maxshortchanges' config

configitems: register the 'web.motd' config

configitems: register the 'web.name' config

configitems: register the 'web.push_ssl' config

configitems: register the 'web.view' config

configitems: fix registration for 'blackbox.track' config Default mutable values could be problematic. Use a lambda that returns the value instead. Thanks to martin for catching this bug.

status: copy-edit and improve --terse and --verbose help

templater: store revisions as ints so min/max won't compare them as strings Because a template value has no explicit type (like ancient PHP), ifcontains() has to coerce the type of the needle. Before, it was always converted to a string, which meant any container type should be a list/dict of strings. This no longer works since we've introduced min/max functions. In order to work around the untyped nature of templater, this patch adds a type specifier to hybrid dict/list. It isn't named as "valuetype" since the _hybrid class can also wrap a dict.

fsmonitor: update to match new dirstate refactor The dirstate was refactored so dirstate._map is now at dirstate._map._map. Same for _copymap, is not _map.copymap. It seems none of the mercurial tests cover this stuff, but it was caught by our Facebook extension tests. Differential Revision: https://phab.mercurial-scm.org/D945

doc: rename README to README.rst Many hosting services consider README without extension as plain text. By using .rst extension, we bring better formatting on many services (e.g. bitbucket).

test: use current user in the multi-user amend scenario The obsfate template keyword that will be introduced in a later patch distinguish between current user and other users when displaying the obsfate users. Update the test before for clarity.

test: cleanup verbosity variant from fatelog test Unlike the '{obsfate}' keyword defined in 'hg-evolve', the definition of hg fatelog in test-obsmarker-template.t is not verbosity dependent. Remove useless call to fatelog -v and fatelog -q.

test: rename obsfate template alias We will introduce an obsfate templatekw in the next patch that will conflict with the obsfate template in the test file, rename the one in test file to avoid this collision.

obsolete: add a devel.user.obsmarker In tests, we often want to use a different username in obs-markers without changing the default user. Add a 'devel.user.obsmarker'.

strip: factor out update target selection The same algorithm was used in two places: one to find out which commit shall become the parent of wdir, and the other to prepare the wdir when keeping changes. Factoring it out prevents inconsistent changes in either occurrence.

contrib: add check-code rule banning use of readlink readlink doesn't always exist, such as on Solaris-derived platforms. Differential Revision: https://phab.mercurial-scm.org/D1000

tests: use readlink.py instead of readlink The latter doesn't always exist, such as on Solaris-derived platforms. Differential Revision: https://phab.mercurial-scm.org/D999

tests: use readlink.py instead of readlink The latter doesn't always exist, such as on Solaris-derived platforms. Differential Revision: https://phab.mercurial-scm.org/D998

tests: use readlink.py instead of readlink The latter doesn't always exist, such as on Solaris-derived platforms. Differential Revision: https://phab.mercurial-scm.org/D997

tests: use readlink.py instead of readlink The latter doesn't always exist, such as on Solaris-derived platforms. Differential Revision: https://phab.mercurial-scm.org/D996

ui: recommend tweakdefaults in the default hgrc template Were I only slightly bolder, I'd make it on by default in the suggested user hgrc. Differential Revision: https://phab.mercurial-scm.org/D1001

tests: optimize test-copytrace-heuristics.t test-copytrace-heuristics.t tests the heuristics algorithm of copytracing. The test has a pattern of making a server repo first and then cloning into a local repo for each test to have public and draft commits. This is done because if we have all draft commits and we have very less commits, heuristics will fallback to full copytracing as that will be fast. To avoid creating the server repo, we set the commit limit to -1 so that everytime we perform the heuristics algorithm even when having full drafts and tweak the config setting when we need to test the ability to fallback to full copytracing. This optimizes this test by 3 seconds. Before: real 0m41.503s user 0m36.068s sys 0m3.900s After: real 0m38.826s user 0m33.884s sys 0m3.396s Differential Revision: https://phab.mercurial-scm.org/D991

patch: do not cache translated messages (API) Previously the code caches `i18n._` results in module variables. That causes issues after an encoding change. Instead of invalidating them manually, we now just recalculate the translated messages every time `filterpatch` gets called. This makes test-commit-interactive.t pass regardless of whether chg or demandimport is used or not. .. api: `patch.messages` now lives in `patch.getmessages()`. Extensions adding new messages should now wrap the `patch.getmessages` method instead of changing `patch.messages` directly. Differential Revision: https://phab.mercurial-scm.org/D959

fsmonitor: add new watchman notifications to fsmonitor extension The fsmonitor extension currently sends state-enter and state-leave notifications to watchman on the update operation. This commit creates additional notifications for the following events : - transaction creation and commit/abort. A state-enter notification will be sent when a transaction is created. It will provide the working copy parent's hash. A state-leave notification will be sent when the transaction is committed or aborted. It will provide the working copy parent's hash. - calls to set-parent will cause state-enter and state-leave notifications to be sent. The state-enter notification will be sent prior to the set-parent operation and the working copy parent's hash will be provided at this time. The state-leave notification will be sent after the set-parent operation completes providing the working copy parents hash. Test Plan: tested on dev server to check that necessary notifications were sent/received Differential Revision: https://phab.mercurial-scm.org/D989