##// END OF EJS Templates
i18n: cache the result of every gettext call...
i18n: cache the result of every gettext call In looking at profiler output for 'hg log' on mozilla-central, I noticed we spent a _huge_ amount of time in gettext relative to what it's doing. Caching provides a roughly 15% performance improvement even on repositories as small as hg. == hg repo on linux == Before: % cumulative self time seconds seconds name 5.05 0.19 0.19 i18n.py:62:gettext 4.84 0.18 0.18 revlog.py:88:decompress 2.95 0.17 0.11 changelog.py:201:node 2.32 0.09 0.09 ui.py:577:write 2.11 0.08 0.08 i18n.py:72:gettext 2.11 0.08 0.08 obsolete.py:196:_fm0readmarkers 1.89 0.07 0.07 obsolete.py:569:_load 1.68 0.63 0.06 localrepo.py:29:__get__ real 0m4.026s user 0m3.993s sys 0m0.034s After: % cumulative self time seconds seconds name 8.05 0.26 0.26 revlog.py:88:decompress 2.68 0.22 0.09 color.py:395:write 2.20 0.07 0.07 obsolete.py:196:_fm0readmarkers 1.95 0.06 0.06 obsolete.py:174:_fm0readmarkers 1.95 0.06 0.06 ui.py:577:write 1.95 0.06 0.06 util.py:1228:datestr 1.71 0.06 0.06 utf_8.py:16:decode 1.71 0.06 0.06 revlog.py:273:__len__ real 0m3.519s user 0m3.447s sys 0m0.073s == mozilla-central repo on linux == Before: % cumulative self time seconds seconds name 7.72 2.35 2.35 revlog.py:88:decompress 4.46 1.36 1.36 i18n.py:62:gettext 2.22 0.67 0.67 i18n.py:72:gettext 2.19 1.14 0.67 changelog.py:201:node 2.16 0.66 0.66 ui.py:577:write 1.96 0.60 0.60 utf_8.py:16:decode 1.93 1.97 0.59 color.py:395:write 1.85 0.81 0.56 changelog.py:136:tip real 0m30.822s user 0m30.660s sys 0m0.149s After: % cumulative self time seconds seconds name 9.82 2.49 2.49 revlog.py:88:decompress 2.67 1.31 0.68 localrepo.py:29:__get__ 2.57 0.65 0.65 utf_8.py:16:decode 2.48 1.01 0.63 changelog.py:201:node 2.10 0.82 0.53 changelog.py:136:tip 2.01 0.51 0.51 ui.py:577:write 1.91 0.49 0.49 util.py:1232:datestr 1.85 1.65 0.47 color.py:395:write real 0m25.619s user 0m25.446s sys 0m0.166s == cpython repo on os x = Before: % cumulative self time seconds seconds name 5.05 1.35 1.35 cmdutil.py:982:_show 4.59 1.22 1.22 revlog.py:274:__len__ 3.98 1.06 1.06 i18n.py:62:gettext 3.91 1.04 1.04 revlog.py:1016:revision 3.68 0.98 0.98 revlog.py:337:parents 3.45 0.92 0.92 revlog.py:88:decompress 2.91 0.78 0.78 revlog.py:309:rev 2.62 0.70 0.70 revlog.py:1033:revision real 0m30.414s user 0m28.145s sys 0m0.541s After: % cumulative self time seconds seconds name 7.98 1.66 1.66 cmdutil.py:982:_show 6.83 1.42 1.42 changelog.py:46:decodeextra 5.18 1.08 1.08 revlog.py:274:__len__ 3.94 0.82 0.82 revlog.py:1016:revision 3.41 0.71 0.71 revlog.py:309:rev 3.32 0.69 0.69 revlog.py:88:decompress 2.99 0.63 0.62 revlog.py:1033:revision 2.69 0.56 0.56 revlog.py:341:start real 0m22.811s user 0m21.883s sys 0m0.397s

File last commit:

r21568:8dd17b19 stable
r23031:3c0983cc default
Show More
pathutil.py
166 lines | 5.8 KiB | text/x-python | PythonLexer
import os, errno, stat
import util
from i18n import _
class pathauditor(object):
'''ensure that a filesystem path contains no banned components.
the following properties of a path are checked:
- ends with a directory separator
- under top-level .hg
- starts at the root of a windows drive
- contains ".."
- traverses a symlink (e.g. a/symlink_here/b)
- inside a nested repository (a callback can be used to approve
some nested repositories, e.g., subrepositories)
'''
def __init__(self, root, callback=None):
self.audited = set()
self.auditeddir = set()
self.root = root
self.callback = callback
if os.path.lexists(root) and not util.checkcase(root):
self.normcase = util.normcase
else:
self.normcase = lambda x: x
def __call__(self, path):
'''Check the relative path.
path may contain a pattern (e.g. foodir/**.txt)'''
path = util.localpath(path)
normpath = self.normcase(path)
if normpath in self.audited:
return
# AIX ignores "/" at end of path, others raise EISDIR.
if util.endswithsep(path):
raise util.Abort(_("path ends in directory separator: %s") % path)
parts = util.splitpath(path)
if (os.path.splitdrive(path)[0]
or parts[0].lower() in ('.hg', '.hg.', '')
or os.pardir in parts):
raise util.Abort(_("path contains illegal component: %s") % path)
if '.hg' in path.lower():
lparts = [p.lower() for p in parts]
for p in '.hg', '.hg.':
if p in lparts[1:]:
pos = lparts.index(p)
base = os.path.join(*parts[:pos])
raise util.Abort(_("path '%s' is inside nested repo %r")
% (path, base))
normparts = util.splitpath(normpath)
assert len(parts) == len(normparts)
parts.pop()
normparts.pop()
prefixes = []
while parts:
prefix = os.sep.join(parts)
normprefix = os.sep.join(normparts)
if normprefix in self.auditeddir:
break
curpath = os.path.join(self.root, prefix)
try:
st = os.lstat(curpath)
except OSError, err:
# EINVAL can be raised as invalid path syntax under win32.
# They must be ignored for patterns can be checked too.
if err.errno not in (errno.ENOENT, errno.ENOTDIR, errno.EINVAL):
raise
else:
if stat.S_ISLNK(st.st_mode):
raise util.Abort(
_('path %r traverses symbolic link %r')
% (path, prefix))
elif (stat.S_ISDIR(st.st_mode) and
os.path.isdir(os.path.join(curpath, '.hg'))):
if not self.callback or not self.callback(curpath):
raise util.Abort(_("path '%s' is inside nested "
"repo %r")
% (path, prefix))
prefixes.append(normprefix)
parts.pop()
normparts.pop()
self.audited.add(normpath)
# only add prefixes to the cache after checking everything: we don't
# want to add "foo/bar/baz" before checking if there's a "foo/.hg"
self.auditeddir.update(prefixes)
def check(self, path):
try:
self(path)
return True
except (OSError, util.Abort):
return False
def canonpath(root, cwd, myname, auditor=None):
'''return the canonical path of myname, given cwd and root'''
if util.endswithsep(root):
rootsep = root
else:
rootsep = root + os.sep
name = myname
if not os.path.isabs(name):
name = os.path.join(root, cwd, name)
name = os.path.normpath(name)
if auditor is None:
auditor = pathauditor(root)
if name != rootsep and name.startswith(rootsep):
name = name[len(rootsep):]
auditor(name)
return util.pconvert(name)
elif name == root:
return ''
else:
# Determine whether `name' is in the hierarchy at or beneath `root',
# by iterating name=dirname(name) until that causes no change (can't
# check name == '/', because that doesn't work on windows). The list
# `rel' holds the reversed list of components making up the relative
# file name we want.
rel = []
while True:
try:
s = util.samefile(name, root)
except OSError:
s = False
if s:
if not rel:
# name was actually the same as root (maybe a symlink)
return ''
rel.reverse()
name = os.path.join(*rel)
auditor(name)
return util.pconvert(name)
dirname, basename = util.split(name)
rel.append(basename)
if dirname == name:
break
name = dirname
raise util.Abort(_("%s not under root '%s'") % (myname, root))
def normasprefix(path):
'''normalize the specified path as path prefix
Returned vaule can be used safely for "p.startswith(prefix)",
"p[len(prefix):]", and so on.
For efficiency, this expects "path" argument to be already
normalized by "os.path.normpath", "os.path.realpath", and so on.
See also issue3033 for detail about need of this function.
>>> normasprefix('/foo/bar').replace(os.sep, '/')
'/foo/bar/'
>>> normasprefix('/').replace(os.sep, '/')
'/'
'''
d, p = os.path.splitdrive(path)
if len(p) != len(os.sep):
return path + os.sep
else:
return path