Matt Mackall <mpm@selenic.com> [Tue, 01 Jun 2010 10:12:07 -0500] rev 11256
Merge with stable
Adrian Buehlmann <adrian@cadifra.com> [Fri, 28 May 2010 17:28:34 +0200] rev 11255
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.
Adrian Buehlmann <adrian@cadifra.com> [Fri, 28 May 2010 17:28:34 +0200] rev 11254
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.
Christian Ebert <blacktrash@gmx.net> [Tue, 01 Jun 2010 03:45:10 +0200] rev 11253
keyword: retrieve added and modified files from commitctx
Christian Ebert <blacktrash@gmx.net> [Tue, 01 Jun 2010 01:05:45 +0200] rev 11252
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.
Adrian Buehlmann <adrian@cadifra.com> [Mon, 31 May 2010 13:47:51 +0200] rev 11251
clone: print number of linked/copied files on --debug
Martin Geisler <mg@lazybytes.net> [Mon, 31 May 2010 21:43:03 +0200] rev 11250
Merge with stable