revset: introduce basic parser

remoteui: move from cmdutil to hg

mq: better qqueue test for troublesome names

mq: prevent the creation of a queue whose name is already taken Each check is moved under the code handling the relevant option, and a new one is added for --create. This fixes duplicated entries being added to the queues list.

mq: fix naming issues for qqueue directories

win32text: mark this extension as deprecated

Merge with stable

shrink-revlog: preserve mode of the shrunken index and data file. Otherwise, the shrunken index file always has mode 0600 thanks to mkstemp(). This is annoying on a server, where multiple users may need to read/write the manifest. chmod()ing the data file is not strictly necessary, but it's nice for consistency.

Fixed a bashism with the use of $RANDOM in hgeditor. The variable $RANDOM is not POSIX so a portable /bin/sh may not define it. When creating a directory with a random name it's better to use mktemp, which, even though is not POSIX, exists in common Unixes including Linux, OpenBSD, FreeBSD and MacOS X.

churn: add possibility to include/exclude paths

churn: support spaces in aliases (issue2222)

Merge with stable

Merge with i18n

Added signature for changeset 24fe2629c6fd

Added tag 1.5.4 for changeset 24fe2629c6fd

Merge with i18n

merge with i18n stable

i18n-pt_BR: synchronized with 0bb67503ad4b

Merge with stable

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.

keyword: retrieve added and modified files from commitctx

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.

minirst: handle line breaks in hg role

extdiff: fix reST syntax in module docstring

Fixed a bashism with trap numbers in hgeditor. When using trap in a shell script, it's more portable to use signal names, instead of numbers. Signal names (INT, KILL,...) are defined in POSIX, whereas its corresponding numbers aren't.

Merge with stable

rebase: stress that only local changesets should be rebased

minirst: fix debug code

Merge with stable

tag: add -e/--edit option for modifying the commit message

extdiff: add labels, read diff arguments from [merge-tools] hgtk has been using these same configs since Feb. Users only have to name the tools they would like to use, ex: [extdiff] kdiff3 = meld =

patchbomb: respect HGPLAIN when piping --test output to PAGER It makes easy to use `hg email --test` from another tool.

pager: fork and exec pager as parent process With the pager as the child process instead of the parent process, the termination of the parent Mercurial process can cause the terminal to return before the pager exits. Inverting the relationship prevents that issue. Platforms without fork() will continue to use util.popen().

commit: fix complaint about branch merge creating new heads (issue2186)

Fix hg heads -r flag documentation The command arguments are "[-ac] [-r STARTREV] [REV]..."

Fix wording in hg pull documentation