match: add a subclass for dirstate normalizing of the matched patterns
This class is only needed on case insensitive filesystems, and only
for wdir context matches. It allows the user to not match the case of
the items in the filesystem- especially for naming directories, which
dirstate doesn't handle[1]. Making dirstate handle mismatched
directory cases is too expensive[2].
Since dirstate doesn't apply to committed csets, this is only created by
overriding basectx.match() in workingctx, and only on icasefs. The default
arguments have been dropped, because the ctx must be passed to the matcher in
order to function.
For operations that can apply to both wdir and some other context, this ends up
normalizing the filename to the case as it exists in the filesystem, and using
that case for the lookup in the other context. See the diff example in the
test.
Previously, given a directory with an inexact case:
- add worked as expected
- diff, forget and status would silently ignore the request
- files would exit with 1
- commit, revert and remove would fail (even when the commands leading up to
them worked):
$ hg ci -m "AbCDef" capsdir1/capsdir
abort: CapsDir1/CapsDir: no match under directory!
$ hg revert -r '.^' capsdir1/capsdir
capsdir1\capsdir: no such file in rev
64dae27060b7
$ hg remove capsdir1/capsdir
not removing capsdir1\capsdir: no tracked files
[1]
Globs are normalized, so that the -I and -X don't need to be specified with a
case match. Without that, the second last remove (with -X) removes the files,
leaving nothing for the last remove. However, specifying the files as
'glob:**.Txt' does not work. Perhaps this requires 're.IGNORECASE'?
There are only a handful of places that create matchers directly, instead of
being routed through the context.match() method. Some may benefit from changing
over to using ctx.match() as a factory function:
revset.checkstatus()
revset.contains()
revset.filelog()
revset._matchfiles()
localrepository._loadfilter()
ignore.ignore()
fileset.subrepo()
filemerge._picktool()
overrides.addlargefiles()
lfcommands.lfconvert()
kwtemplate.__init__()
eolfile.__init__()
eolfile.checkrev()
acl.buildmatch()
Currently, a toplevel subrepo can be named with an inexact case. However, the
path auditor gets in the way of naming _anything_ in the subrepo if the top
level case doesn't match. That is trickier to handle, because there's the user
provided case, the case in the filesystem, and the case stored in .hgsub. This
can be fixed next cycle.
--- a/tests/test-subrepo-deep-nested-change.t
+++ b/tests/test-subrepo-deep-nested-change.t
@@ -170,8 +170,15 @@
R sub1/sub2/test.txt
$ hg update -Cq
$ touch sub1/sub2/folder/bar
+#if icasefs
+ $ hg addremove Sub1/sub2
+ abort: path 'Sub1\sub2' is inside nested repo 'Sub1'
+ [255]
+ $ hg -q addremove sub1/sub2
+#else
$ hg addremove sub1/sub2
adding sub1/sub2/folder/bar (glob)
+#endif
$ hg status -S
A sub1/sub2/folder/bar
? foo/bar/abc
The narrowmatcher class may need to be tweaked when that is fixed.
[1] http://www.selenic.com/pipermail/mercurial-devel/2015-April/068183.html
[2] http://www.selenic.com/pipermail/mercurial-devel/2015-April/068191.html
# worker.py - master-slave parallelism support
#
# Copyright 2013 Facebook, Inc.
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
from i18n import _
import errno, os, signal, sys, threading
import util
def countcpus():
'''try to count the number of CPUs on the system'''
# posix
try:
n = int(os.sysconf('SC_NPROCESSORS_ONLN'))
if n > 0:
return n
except (AttributeError, ValueError):
pass
# windows
try:
n = int(os.environ['NUMBER_OF_PROCESSORS'])
if n > 0:
return n
except (KeyError, ValueError):
pass
return 1
def _numworkers(ui):
s = ui.config('worker', 'numcpus')
if s:
try:
n = int(s)
if n >= 1:
return n
except ValueError:
raise util.Abort(_('number of cpus must be an integer'))
return min(max(countcpus(), 4), 32)
if os.name == 'posix':
_startupcost = 0.01
else:
_startupcost = 1e30
def worthwhile(ui, costperop, nops):
'''try to determine whether the benefit of multiple processes can
outweigh the cost of starting them'''
linear = costperop * nops
workers = _numworkers(ui)
benefit = linear - (_startupcost * workers + linear / workers)
return benefit >= 0.15
def worker(ui, costperarg, func, staticargs, args):
'''run a function, possibly in parallel in multiple worker
processes.
returns a progress iterator
costperarg - cost of a single task
func - function to run
staticargs - arguments to pass to every invocation of the function
args - arguments to split into chunks, to pass to individual
workers
'''
if worthwhile(ui, costperarg, len(args)):
return _platformworker(ui, func, staticargs, args)
return func(*staticargs + (args,))
def _posixworker(ui, func, staticargs, args):
rfd, wfd = os.pipe()
workers = _numworkers(ui)
oldhandler = signal.getsignal(signal.SIGINT)
signal.signal(signal.SIGINT, signal.SIG_IGN)
pids, problem = [], [0]
for pargs in partition(args, workers):
pid = os.fork()
if pid == 0:
signal.signal(signal.SIGINT, oldhandler)
try:
os.close(rfd)
for i, item in func(*(staticargs + (pargs,))):
os.write(wfd, '%d %s\n' % (i, item))
os._exit(0)
except KeyboardInterrupt:
os._exit(255)
# other exceptions are allowed to propagate, we rely
# on lock.py's pid checks to avoid release callbacks
pids.append(pid)
pids.reverse()
os.close(wfd)
fp = os.fdopen(rfd, 'rb', 0)
def killworkers():
# if one worker bails, there's no good reason to wait for the rest
for p in pids:
try:
os.kill(p, signal.SIGTERM)
except OSError, err:
if err.errno != errno.ESRCH:
raise
def waitforworkers():
for _pid in pids:
st = _exitstatus(os.wait()[1])
if st and not problem[0]:
problem[0] = st
killworkers()
t = threading.Thread(target=waitforworkers)
t.start()
def cleanup():
signal.signal(signal.SIGINT, oldhandler)
t.join()
status = problem[0]
if status:
if status < 0:
os.kill(os.getpid(), -status)
sys.exit(status)
try:
for line in fp:
l = line.split(' ', 1)
yield int(l[0]), l[1][:-1]
except: # re-raises
killworkers()
cleanup()
raise
cleanup()
def _posixexitstatus(code):
'''convert a posix exit status into the same form returned by
os.spawnv
returns None if the process was stopped instead of exiting'''
if os.WIFEXITED(code):
return os.WEXITSTATUS(code)
elif os.WIFSIGNALED(code):
return -os.WTERMSIG(code)
if os.name != 'nt':
_platformworker = _posixworker
_exitstatus = _posixexitstatus
def partition(lst, nslices):
'''partition a list into N slices of equal size'''
n = len(lst)
chunk, slop = n / nslices, n % nslices
end = 0
for i in xrange(nslices):
start = end
end = start + chunk
if slop:
end += 1
slop -= 1
yield lst[start:end]