dispatch: when --pager=no is passed, also disable pager on req.repo.ui With a future chg change, `req.repo` could be set and currently it is unaffected by `--pager=on`. This patch makes it so. This could make one of the test cases in `test-pager.t` pass with future chg changes. Differential Revision: https://phab.mercurial-scm.org/D990

bundle2: immediate exit for ctrl+c (issue5692) 21c2df59a regressed bundle2 by catching all exceptions and trying to handle them. The old behavior was to allow KeyboardInterrupts to throw and not have graceful cleanup, which allowed it to exit immediately. Let's go back to that behavior. Differential Revision: https://phab.mercurial-scm.org/D960

exewrapper: format with clang-format A few *s move around, some spaces around parens, a couple of braces. Nothing remarkable. Differential Revision: https://phab.mercurial-scm.org/D1032

util: add clang-format control comment around struct and format macro clang-format is not a fan of PyObject_HEAD. Differential Revision: https://phab.mercurial-scm.org/D1031

mpatch: reflow two oddly formatted else blocks with clang-format Differential Revision: https://phab.mercurial-scm.org/D1029

mpatch: re-wrap wide line with clang-format Differential Revision: https://phab.mercurial-scm.org/D1027

bdiff: remove trailing newlines Differential Revision: https://phab.mercurial-scm.org/D1009

bdiff: rewrap function prototypes per clang-format Differential Revision: https://phab.mercurial-scm.org/D1008

bdiff: re-wrap lines per clang-format A few too-wide lines corrected, and some places where clang-format prefers to wrap after the binary operator instead of before. I don't feel strongly, so I'm leaving the auto-format result as "after the binary operator". Differential Revision: https://phab.mercurial-scm.org/D1007

bdiff: remove extra space after * per clang-format Differential Revision: https://phab.mercurial-scm.org/D1006

bdiff: fix misplaced comma in macro definition with clang-format Differential Revision: https://phab.mercurial-scm.org/D1005

bdiff: format header file with clang-format Differential Revision: https://phab.mercurial-scm.org/D1004

bdiff: sort includes using clang-format Differential Revision: https://phab.mercurial-scm.org/D1003

build: "make deb" failed when the base path contained spaces With these changes, all the commands triggered by "make deb" use proper quoting and succeed even when invoked from a directory containing spaces.

build: chg build was failing when the base directory contained spaces

build: initial version detection by make deb/rpm was missing quoting

build: make install in "/doc" failed if the destination dir contained spaces This and the following commits try to add the necessary quoting in the build scripts to make the process more robust. The target for now is rendering "make deb" successful even when the base directory contains spaces (eg. "/opt/mercu rial"). The build process should succeed without scattering files in spurious directories (eg.: "/opt/mercu/usr/bin/hg").

strip: take branch into account when selecting update target (issue5540) Test contributed by Matt Harbison Keep the same behavior in most cases (i.e. first parent of the first root of stripped changsets), but if the branch differs from wdir's, try to find another parent of stripped commits that is on the same branch.

scmutil: factor out building of transaction summary callback In registersummarycallback(), we extra generic bits of the existing "reportsummary" function into a decorator which will be used in forthcoming changesets to add new summary callbacks.

scmutil: factor out transaction name lookup in registersummarycallback() Add an inner txmatch function in registersummarycallback() factoring out the logic to determine if the transaction matches a particular sources set. We'll reuse this function to add some new report logic in the new changeset.

configitems: register the annotate diff options

configitems: register the 'convert.cvsps.logencoding' config

configitems: register the 'ui.interface.chunkselector' config

configitems: register the 'experimental.archivemetatemplate' config

configitems: register the 'rebase.singletransaction' config

configitems: register the 'server.bundle*' family of config All these config use the same function specifying a default value. We need to register them all at the same time.

configitems: register the 'web.logourl' config

configitems: register the 'web.logoimg' config

configitems: register the 'web.labels' config

configitems: register the 'web.hidden' config

configitems: register the 'web.guessmime' config

configitems: register the 'web.deny_push' config

configitems: register the 'web.contact' config

configitems: register the 'web.cache' config

configitems: register the 'web.allowzip' config

configitems: register the 'web.allow_push' config

configitems: register the 'web.allowpull' config

configitems: register the 'web.allowgz' config

configitems: register the 'web.allowbz2' config

configitems: register the 'email.reply-to' config

configitems: register the 'email.cc' config

configitems: register the 'email.bcc' config

configitems: register the 'logtoprocess.uiblocked' config

configitems: register the 'logtoprocess.develwarn' config

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

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.

mq: use the newcommitphase utility We use the official API instead of doing the operation manually. This will help storing the default value for phases properly in the next changeset.

patch: rename "header" variable into "hdr" in diff() The "header" variable was hiding the eponymous class, hence preventing its usage.

merge: improve comments in mergestate._makerecords Differential Revision: https://phab.mercurial-scm.org/D955

commands: tidy up merge state decoding in resolve Make the mapping from merge state to label and display key explicit, and move construction of the dict out of the loop. Differential Revision: https://phab.mercurial-scm.org/D861

tests: add test for path conflicts during merge Differential Revision: https://phab.mercurial-scm.org/D787

tests: add test for path conflicts during update Differential Revision: https://phab.mercurial-scm.org/D786

context: also consider path conflicts when clearing unknown files When clearing unknown files to remove path conflicts, also delete files that conflict with the target file's path. Differential Revision: https://phab.mercurial-scm.org/D785

merge: check for path conflicts when merging (issue5628) When merging, check for any path conflicts introduced by the manifest merge and rename the conflicting file to a safe name. Differential Revision: https://phab.mercurial-scm.org/D784

util: add safename function for generating safe names to rename to This function finds a name which does not clash with any other name in the manifest, and so can be used to safely rename a file. Differential Revision: https://phab.mercurial-scm.org/D783

merge: improve error messages for path conflicts during update Differential Revision: https://phab.mercurial-scm.org/D782

merge: check for path conflicts when updating (issue5628) When updating to a new revision, check for path conflicts caused by unknown files in the working directory, and handle these by backing up the file or directory and replacing it. Differential Revision: https://phab.mercurial-scm.org/D781

merge: rename conflicts to fileconflicts in _checkunknownfiles We will need to distinguish between file conflicts and path conflicts. Rename the conflicts variable so that it will be clearly distinct from pathconflicts, which will be introduced in a future commit. Differential Revision: https://phab.mercurial-scm.org/D780

merge: add _checkunknowndirs function for detecting path conflicts Add a new function which, given a file name, finds the shortest path for which there is a conflicting file or directory in the working directory. Differential Revision: https://phab.mercurial-scm.org/D779

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