treemanifest: optimize treemanifest._walk() to skip directories
This makes treemanifest.walk() not visit submanifests that are known not to
have any matching files. It does this by calling match.visitdir() on
submanifests as it walks.
This change also updates largefiles to be able to work with this new behavior
in treemanifests. It overrides match.visitdir(), the function that dictates
how walk() and matches() skip over directories.
The greatest speed improvements are seen with narrower scopes. For example,
this commit speeds up the following command on the Mozilla repo from 1.14s
to 1.02s:
hg files -r . dom/apps/
Whereas with a wider scope, dom/, the speed only improves from 1.21s to 1.13s.
As with similar a similar optimization to treemanifest.matches(), this change
will bring out even bigger performance improvements once treemanifests are
loaded lazily. Once that happens, we won't just skip over looking at
submanifests, but we'll skip even loading them.
# fixpax - fix ownership in bdist_mpkg output
#
# Copyright 2015 Matt Mackall <mpm@selenic.com>
#
# This software may be used and distributed according to the terms of the
# MIT license (http://opensource.org/licenses/MIT)
"""Set file ownership to 0 in an Archive.pax.gz.
Suitable for fixing files bdist_mpkg output:
*.mpkg/Contents/Packages/*.pkg/Contents/Archive.pax.gz
"""
import sys, os, gzip
def fixpax(iname, oname):
i = gzip.GzipFile(iname)
o = gzip.GzipFile(oname, "w")
while True:
magic = i.read(6)
dev = i.read(6)
ino = i.read(6)
mode = i.read(6)
i.read(6) # uid
i.read(6) # gid
nlink = i.read(6)
rdev = i.read(6)
mtime = i.read(11)
namesize = i.read(6)
filesize = i.read(11)
name = i.read(int(namesize, 8))
data = i.read(int(filesize, 8))
o.write(magic)
o.write(dev)
o.write(ino)
o.write(mode)
o.write("000000")
o.write("000000")
o.write(nlink)
o.write(rdev)
o.write(mtime)
o.write(namesize)
o.write(filesize)
o.write(name)
o.write(data)
if name.startswith("TRAILER!!!"):
o.write(i.read())
break
o.close()
i.close()
if __name__ == '__main__':
for iname in sys.argv[1:]:
print 'fixing file ownership in %s' % iname
oname = sys.argv[1] + '.tmp'
fixpax(iname, oname)
os.rename(oname, iname)