keyword: force dirstate normal when all changes in a file are recorded Before this bugfix a file whose changes were entirely recorded was still considered modified by "hg status". Note: the test must use hg record -l/--logfile, because this is not reproducible with hg record -m/--message.

clone: print number of linked/copied files on --debug

Merge with stable

eol: extension for managing file EOLs

Merge with stable

Merge with i18n

Merge with i18n

merge with i18n stable

i18n-pt_BR: added message from 1b8aa9ffa7dc

merge with i18n stable

i18n-pt_BR: synchronized with ed71cb07d7b2

Merge with stable

pager: exec pager using /bin/sh -c This mimics the behavior of popen() and ensures setting the pager to something like "LESS=FSRX less" will work.

hgweb: fix race in refreshing repo list (issue2188)

Merge with stable

record: check that we are not committing a merge before patch selection It might sound like a good idea to use record to filter changes when merging. If someone attemps this, it's better to tell her "no" right ahead, before the patch generation/line selection, so she does not spend time doing it just to receive a red light after that (sometimes rather long) process.

record: better way to find help in docstring This outputs only the lines in the verbatim block without relying on the translator to have translated the little 'y - record this change' string.

record: docstring typo

mq: mention qqueue in module docstring

clone: save hardlink state of util.copyfiles() When trying to do hardlink-cloning, the os_link() call of the first file tried already fails on Windows, if the source is on a UNC path. This change avoids calling os_link() for the rest of files, leaving us with a *single* failed os_link() call per clone operation, if the source can't do hardlinks.

util.copyfiles: don't try os_link() again if it failed before If the os_link() call on the first file in the directory fails [1], we switch mode to using shutil.copy() for all remaining files. [1] happens for example on Windows for every file when cloning from a UNC path without specifying --pull.

cmdutil: cleanup imports

make transactions work on non-refcounted python implementations

mq: support multiple patch queues using qqueue

Merge with stable

status: avoid performance regression when no .hgsub is present (introduced by 24ce8f0c0a39)

doc: document expansion of %include and ui.username

ui.username(): expand environment variables in username configuration value. note: expansion of config variables must be handled on a case-by-case basis because they can contain arbitrary data that may not be desirable to expand.

config: expand hgrc %include paths

rename: make --after work if source is already in R state I routinely want to use `hg addrem` and then fix up missed renames manually using `hg mv -A`. This patch allows me to record such renames from a source in state R to a target in state A.

Merge with stable

doc: clarify that sections can be split

doc: clarify that keys can be overridden

commands: document --new-branch flag for push

Merge with stable

commands: updates to push docstring. With contributions from mg, hstuart, timeless, and vsh.

mq: remove unneeded local variable in delete

pager: exec pager using /bin/sh -c This mimics the behavior of popen() and ensures setting the pager to something like "LESS=FSRX less" will work.

keyword: offer svn-like default keywordmaps svn-like default keywords can be set in a new configuration section called [keywordset] -- thanks to timeless for the name. Move setup of default keywordmaps into dedicated function used by kwtemplater.__init__ and demo. HeadURL/URL is not supported (by default).

keyword: add 2 svn-like date filters svnisodate yields the format the date in svn's Id keyword expands to. svnutcdate yields the format svn's Date/LastChangedDate expands to. http://svnbook.red-bean.com/en/1.5/svn.advanced.props.special.keywords.html

util: give appropriate default args to atomictempfile() mode='w+b' is the default of python's TemporaryFile().

push: add --new-branch option to allow intial push of new branches Compare this to --force which allows anything to be pushed. With --new-branch, only changesets to named branches not present on the and changesets not introducing additional heads on existing branches are allowed. Developed by Henrik Stuart <henrik.stuart@edlund.dk> Sune Foldager <cryo@cyanite.org>

check-code: add check for 'source'

Merge with stable

tests: fix bashism to load helpers.sh `source` isn't available at POSIX sh.

color: bring back colors with pager It's introduced by 3c368a1c962d, but missing in merge changeset at a890cc501501.

dispatch: include Python version in traceback

rebase: add error codes Suggested by Dirk Hasselbalch

rebase: improve --abort failure message

rebase: only show "rebase completed" message with -v

strip: hide unbundle messages by default Unbundling is an internal implementation detail for strip, only show them with --verbose.

Fix up rebase's handling of strip backups

strip: improve full backup message

strip: drop deprecated -b from synopsis

rebase: use helpers.sh in tests

strip: be quiet about temporary internal bundle

Merge with crew-stable

convert/svn: close gettags() log stream (issue2196)

convert/svn: remove useless try/catch While the try/catch was reintroduced in 2f0f9528e77b, it was made useless by the tags/ existence check in getheads().

Use our custom hg reStructuredText role some more I missed these occurrences on my first scan through the source.