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

fsmonitor: change the distance calculation Change the distance calculation in the fsmonitor extension. It is done in a method since anticipated changes will need to use this logic as well. Test Plan: Tested on development server. Differential Revision: https://phab.mercurial-scm.org/D988

configitems: update default value of 'phases.new-commit' Now that mq is cleaned up, we can rely on the config register for the default value. We switch the default from the integer to human readable value to help with future automatic documentation that could be generated from the config register.