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