view mercurial/pathutil.py @ 21424:d13b4ecdb680

test: split test-largefile.t in multiple file The `test-largefiles.t` unified test is significantly longer (about 30%) than any other tests in the mercurial test suite. As a result, its is alway the last test my test runner is waiting for at the end of a run. In practice, this means that `test-largefile.t` is wasting half a minute of my life every times I'm running the mercurial test suites. This probably mean more a few cumulated day by now. I've finally decided to split it up in multiple smaller tests to bring it back in reasonable length. This changeset extracts independent test cases in two files. One dedicated to wire protocole testing, and another one dedicated to all other tests that could be independently extracted. No test case were haltered in the making of this changeset. Various timing available below. All timing have been done on a with 90 jobs on a 64 cores machine. Similar result are shown on firefly (20 jobs on 12 core). General timing of the whole run -------------------------------- We see a 25% real time improvement for no significant cpu time impact. Before split: real 2m1.149s user 58m4.662s sys 11m28.563s After split: real 1m31.977s user 57m45.993s sys 11m33.634s Last test to finish (using run-test.py --time) ---------------------------------------------- test-largefile.t is now finishing at the same time than other slow tests. Before split: Time Test 119.280 test-largefiles.t 93.995 test-mq.t 89.897 test-subrepo.t 86.920 test-glog.t 85.508 test-rename-merge2.t 83.594 test-revset.t 79.824 test-keyword.t 78.077 test-mq-header-date.t After split: Time Test 90.414 test-mq.t 88.594 test-largefiles.t 85.363 test-subrepo.t 81.059 test-glog.t 78.927 test-rename-merge2.t 78.021 test-revset.t 77.777 test-command-template.t Timing of largefile test themself ----------------------------------- Running only tests prefixed with "test-largefiles". No significant change in cumulated time. Before: Time Test 58.673 test-largefiles.t 2.931 test-largefiles-cache.t 0.583 test-largefiles-small-disk.t After: Time Test 31.754 test-largefiles.t 17.460 test-largefiles-misc.t 8.888 test-largefiles-wireproto.t 2.864 test-largefiles-cache.t 0.580 test-largefiles-small-disk.t
author Pierre-Yves David <pierre-yves.david@fb.com>
date Fri, 16 May 2014 13:18:57 -0700
parents f962870712da
children 8dd17b19e722
line wrap: on
line source

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))