pathutil: tease out a new library to break an import cycle from canonpath use

mercurial/pathutil.py

@@ -0,0 +1,144 b''
+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))

hgext/keyword.py

@@ -1,732 +1,732 b''
 # keyword.py - $Keyword$ expansion for Mercurial
 #
 # Copyright 2007-2012 Christian Ebert <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 #
 # $Id$
 #
 # Keyword expansion hack against the grain of a Distributed SCM
 #
 # There are many good reasons why this is not needed in a distributed
 # SCM, still it may be useful in very small projects based on single
 # files (like LaTeX packages), that are mostly addressed to an
 # audience not running a version control system.
 #
 # For in-depth discussion refer to
 # <http://mercurial.selenic.com/wiki/KeywordPlan>.
 #
 # Keyword expansion is based on Mercurial's changeset template mappings.
 #
 # Binary files are not touched.
 #
 # Files to act upon/ignore are specified in the [keyword] section.
 # Customized keyword template mappings in the [keywordmaps] section.
 #
 # Run "hg help keyword" and "hg kwdemo" to get info on configuration.
 
 '''expand keywords in tracked files
 
 This extension expands RCS/CVS-like or self-customized $Keywords$ in
 tracked text files selected by your configuration.
 
 Keywords are only expanded in local repositories and not stored in the
 change history. The mechanism can be regarded as a convenience for the
 current user or for archive distribution.
 
 Keywords expand to the changeset data pertaining to the latest change
 relative to the working directory parent of each file.
 
 Configuration is done in the [keyword], [keywordset] and [keywordmaps]
 sections of hgrc files.
 
 Example::
 
     [keyword]
     # expand keywords in every python file except those matching "x*"
     **.py =
     x*    = ignore
 
     [keywordset]
     # prefer svn- over cvs-like default keywordmaps
     svn = True
 
 .. note::
 
    The more specific you are in your filename patterns the less you
    lose speed in huge repositories.
 
 For [keywordmaps] template mapping and expansion demonstration and
 control run :hg:`kwdemo`. See :hg:`help templates` for a list of
 available templates and filters.
 
 Three additional date template filters are provided:
 
 :``utcdate``:    "2006/09/18 15:13:13"
 :``svnutcdate``: "2006-09-18 15:13:13Z"
 :``svnisodate``: "2006-09-18 08:13:13 -700 (Mon, 18 Sep 2006)"
 
 The default template mappings (view with :hg:`kwdemo -d`) can be
 replaced with customized keywords and templates. Again, run
 :hg:`kwdemo` to control the results of your configuration changes.
 
 Before changing/disabling active keywords, you must run :hg:`kwshrink`
 to avoid storing expanded keywords in the change history.
 
 To force expansion after enabling it, or a configuration change, run
 :hg:`kwexpand`.
 
 Expansions spanning more than one line and incremental expansions,
 like CVS' $Log$, are not supported. A keyword template map "Log =
 {desc}" expands to the first line of the changeset description.
 '''
 
 from mercurial import commands, context, cmdutil, dispatch, filelog, extensions
 from mercurial import localrepo, match, patch, templatefilters, templater, util
-from mercurial import scmutil
+from mercurial import scmutil, pathutil
 from mercurial.hgweb import webcommands
 from mercurial.i18n import _
 import os, re, shutil, tempfile
 
 commands.optionalrepo += ' kwdemo'
 commands.inferrepo += ' kwexpand kwfiles kwshrink'
 
 cmdtable = {}
 command = cmdutil.command(cmdtable)
 testedwith = 'internal'
 
 # hg commands that do not act on keywords
 nokwcommands = ('add addremove annotate bundle export grep incoming init log'
                 ' outgoing push tip verify convert email glog')
 
 # hg commands that trigger expansion only when writing to working dir,
 # not when reading filelog, and unexpand when reading from working dir
 restricted = 'merge kwexpand kwshrink record qrecord resolve transplant'
 
 # names of extensions using dorecord
 recordextensions = 'record'
 
 colortable = {
     'kwfiles.enabled': 'green bold',
     'kwfiles.deleted': 'cyan bold underline',
     'kwfiles.enabledunknown': 'green',
     'kwfiles.ignored': 'bold',
     'kwfiles.ignoredunknown': 'none'
 }
 
 # date like in cvs' $Date
 def utcdate(text):
     ''':utcdate: Date. Returns a UTC-date in this format: "2009/08/18 11:00:13".
     '''
     return util.datestr((util.parsedate(text)[0], 0), '%Y/%m/%d %H:%M:%S')
 # date like in svn's $Date
 def svnisodate(text):
     ''':svnisodate: Date. Returns a date in this format: "2009-08-18 13:00:13
     +0200 (Tue, 18 Aug 2009)".
     '''
     return util.datestr(text, '%Y-%m-%d %H:%M:%S %1%2 (%a, %d %b %Y)')
 # date like in svn's $Id
 def svnutcdate(text):
     ''':svnutcdate: Date. Returns a UTC-date in this format: "2009-08-18
     11:00:13Z".
     '''
     return util.datestr((util.parsedate(text)[0], 0), '%Y-%m-%d %H:%M:%SZ')
 
 templatefilters.filters.update({'utcdate': utcdate,
                                 'svnisodate': svnisodate,
                                 'svnutcdate': svnutcdate})
 
 # make keyword tools accessible
 kwtools = {'templater': None, 'hgcmd': ''}
 
 def _defaultkwmaps(ui):
     '''Returns default keywordmaps according to keywordset configuration.'''
     templates = {
         'Revision': '{node|short}',
         'Author': '{author|user}',
     }
     kwsets = ({
         'Date': '{date|utcdate}',
         'RCSfile': '{file|basename},v',
         'RCSFile': '{file|basename},v', # kept for backwards compatibility
                                         # with hg-keyword
         'Source': '{root}/{file},v',
         'Id': '{file|basename},v {node|short} {date|utcdate} {author|user}',
         'Header': '{root}/{file},v {node|short} {date|utcdate} {author|user}',
     }, {
         'Date': '{date|svnisodate}',
         'Id': '{file|basename},v {node|short} {date|svnutcdate} {author|user}',
         'LastChangedRevision': '{node|short}',
         'LastChangedBy': '{author|user}',
         'LastChangedDate': '{date|svnisodate}',
     })
     templates.update(kwsets[ui.configbool('keywordset', 'svn')])
     return templates
 
 def _shrinktext(text, subfunc):
     '''Helper for keyword expansion removal in text.
     Depending on subfunc also returns number of substitutions.'''
     return subfunc(r'$\1$', text)
 
 def _preselect(wstatus, changed):
     '''Retrieves modified and added files from a working directory state
     and returns the subset of each contained in given changed files
     retrieved from a change context.'''
     modified, added = wstatus[:2]
     modified = [f for f in modified if f in changed]
     added = [f for f in added if f in changed]
     return modified, added
 
 
 class kwtemplater(object):
     '''
     Sets up keyword templates, corresponding keyword regex, and
     provides keyword substitution functions.
     '''
 
     def __init__(self, ui, repo, inc, exc):
         self.ui = ui
         self.repo = repo
         self.match = match.match(repo.root, '', [], inc, exc)
         self.restrict = kwtools['hgcmd'] in restricted.split()
         self.postcommit = False
 
         kwmaps = self.ui.configitems('keywordmaps')
         if kwmaps: # override default templates
             self.templates = dict((k, templater.parsestring(v, False))
                                   for k, v in kwmaps)
         else:
             self.templates = _defaultkwmaps(self.ui)
 
     @util.propertycache
     def escape(self):
         '''Returns bar-separated and escaped keywords.'''
         return '|'.join(map(re.escape, self.templates.keys()))
 
     @util.propertycache
     def rekw(self):
         '''Returns regex for unexpanded keywords.'''
         return re.compile(r'\$(%s)\$' % self.escape)
 
     @util.propertycache
     def rekwexp(self):
         '''Returns regex for expanded keywords.'''
         return re.compile(r'\$(%s): [^$\n\r]*? \$' % self.escape)
 
     def substitute(self, data, path, ctx, subfunc):
         '''Replaces keywords in data with expanded template.'''
         def kwsub(mobj):
             kw = mobj.group(1)
             ct = cmdutil.changeset_templater(self.ui, self.repo,
                                              False, None, '', False)
             ct.use_template(self.templates[kw])
             self.ui.pushbuffer()
             ct.show(ctx, root=self.repo.root, file=path)
             ekw = templatefilters.firstline(self.ui.popbuffer())
             return '$%s: %s $' % (kw, ekw)
         return subfunc(kwsub, data)
 
     def linkctx(self, path, fileid):
         '''Similar to filelog.linkrev, but returns a changectx.'''
         return self.repo.filectx(path, fileid=fileid).changectx()
 
     def expand(self, path, node, data):
         '''Returns data with keywords expanded.'''
         if not self.restrict and self.match(path) and not util.binary(data):
             ctx = self.linkctx(path, node)
             return self.substitute(data, path, ctx, self.rekw.sub)
         return data
 
     def iskwfile(self, cand, ctx):
         '''Returns subset of candidates which are configured for keyword
         expansion but are not symbolic links.'''
         return [f for f in cand if self.match(f) and 'l' not in ctx.flags(f)]
 
     def overwrite(self, ctx, candidates, lookup, expand, rekw=False):
         '''Overwrites selected files expanding/shrinking keywords.'''
         if self.restrict or lookup or self.postcommit: # exclude kw_copy
             candidates = self.iskwfile(candidates, ctx)
         if not candidates:
             return
         kwcmd = self.restrict and lookup # kwexpand/kwshrink
         if self.restrict or expand and lookup:
             mf = ctx.manifest()
         if self.restrict or rekw:
             re_kw = self.rekw
         else:
             re_kw = self.rekwexp
         if expand:
             msg = _('overwriting %s expanding keywords\n')
         else:
             msg = _('overwriting %s shrinking keywords\n')
         for f in candidates:
             if self.restrict:
                 data = self.repo.file(f).read(mf[f])
             else:
                 data = self.repo.wread(f)
             if util.binary(data):
                 continue
             if expand:
                 if lookup:
                     ctx = self.linkctx(f, mf[f])
                 data, found = self.substitute(data, f, ctx, re_kw.subn)
             elif self.restrict:
                 found = re_kw.search(data)
             else:
                 data, found = _shrinktext(data, re_kw.subn)
             if found:
                 self.ui.note(msg % f)
                 fp = self.repo.wopener(f, "wb", atomictemp=True)
                 fp.write(data)
                 fp.close()
                 if kwcmd:
                     self.repo.dirstate.normal(f)
                 elif self.postcommit:
                     self.repo.dirstate.normallookup(f)
 
     def shrink(self, fname, text):
         '''Returns text with all keyword substitutions removed.'''
         if self.match(fname) and not util.binary(text):
             return _shrinktext(text, self.rekwexp.sub)
         return text
 
     def shrinklines(self, fname, lines):
         '''Returns lines with keyword substitutions removed.'''
         if self.match(fname):
             text = ''.join(lines)
             if not util.binary(text):
                 return _shrinktext(text, self.rekwexp.sub).splitlines(True)
         return lines
 
     def wread(self, fname, data):
         '''If in restricted mode returns data read from wdir with
         keyword substitutions removed.'''
         if self.restrict:
             return self.shrink(fname, data)
         return data
 
 class kwfilelog(filelog.filelog):
     '''
     Subclass of filelog to hook into its read, add, cmp methods.
     Keywords are "stored" unexpanded, and processed on reading.
     '''
     def __init__(self, opener, kwt, path):
         super(kwfilelog, self).__init__(opener, path)
         self.kwt = kwt
         self.path = path
 
     def read(self, node):
         '''Expands keywords when reading filelog.'''
         data = super(kwfilelog, self).read(node)
         if self.renamed(node):
             return data
         return self.kwt.expand(self.path, node, data)
 
     def add(self, text, meta, tr, link, p1=None, p2=None):
         '''Removes keyword substitutions when adding to filelog.'''
         text = self.kwt.shrink(self.path, text)
         return super(kwfilelog, self).add(text, meta, tr, link, p1, p2)
 
     def cmp(self, node, text):
         '''Removes keyword substitutions for comparison.'''
         text = self.kwt.shrink(self.path, text)
         return super(kwfilelog, self).cmp(node, text)
 
 def _status(ui, repo, wctx, kwt, *pats, **opts):
     '''Bails out if [keyword] configuration is not active.
     Returns status of working directory.'''
     if kwt:
         return repo.status(match=scmutil.match(wctx, pats, opts), clean=True,
                            unknown=opts.get('unknown') or opts.get('all'))
     if ui.configitems('keyword'):
         raise util.Abort(_('[keyword] patterns cannot match'))
     raise util.Abort(_('no [keyword] patterns configured'))
 
 def _kwfwrite(ui, repo, expand, *pats, **opts):
     '''Selects files and passes them to kwtemplater.overwrite.'''
     wctx = repo[None]
     if len(wctx.parents()) > 1:
         raise util.Abort(_('outstanding uncommitted merge'))
     kwt = kwtools['templater']
     wlock = repo.wlock()
     try:
         status = _status(ui, repo, wctx, kwt, *pats, **opts)
         modified, added, removed, deleted, unknown, ignored, clean = status
         if modified or added or removed or deleted:
             raise util.Abort(_('outstanding uncommitted changes'))
         kwt.overwrite(wctx, clean, True, expand)
     finally:
         wlock.release()
 
 @command('kwdemo',
          [('d', 'default', None, _('show default keyword template maps')),
           ('f', 'rcfile', '',
            _('read maps from rcfile'), _('FILE'))],
          _('hg kwdemo [-d] [-f RCFILE] [TEMPLATEMAP]...'))
 def demo(ui, repo, *args, **opts):
     '''print [keywordmaps] configuration and an expansion example
 
     Show current, custom, or default keyword template maps and their
     expansions.
 
     Extend the current configuration by specifying maps as arguments
     and using -f/--rcfile to source an external hgrc file.
 
     Use -d/--default to disable current configuration.
 
     See :hg:`help templates` for information on templates and filters.
     '''
     def demoitems(section, items):
         ui.write('[%s]\n' % section)
         for k, v in sorted(items):
             ui.write('%s = %s\n' % (k, v))
 
     fn = 'demo.txt'
     tmpdir = tempfile.mkdtemp('', 'kwdemo.')
     ui.note(_('creating temporary repository at %s\n') % tmpdir)
     repo = localrepo.localrepository(repo.baseui, tmpdir, True)
     ui.setconfig('keyword', fn, '')
     svn = ui.configbool('keywordset', 'svn')
     # explicitly set keywordset for demo output
     ui.setconfig('keywordset', 'svn', svn)
 
     uikwmaps = ui.configitems('keywordmaps')
     if args or opts.get('rcfile'):
         ui.status(_('\n\tconfiguration using custom keyword template maps\n'))
         if uikwmaps:
             ui.status(_('\textending current template maps\n'))
         if opts.get('default') or not uikwmaps:
             if svn:
                 ui.status(_('\toverriding default svn keywordset\n'))
             else:
                 ui.status(_('\toverriding default cvs keywordset\n'))
         if opts.get('rcfile'):
             ui.readconfig(opts.get('rcfile'))
         if args:
             # simulate hgrc parsing
             rcmaps = ['[keywordmaps]\n'] + [a + '\n' for a in args]
             fp = repo.opener('hgrc', 'w')
             fp.writelines(rcmaps)
             fp.close()
             ui.readconfig(repo.join('hgrc'))
         kwmaps = dict(ui.configitems('keywordmaps'))
     elif opts.get('default'):
         if svn:
             ui.status(_('\n\tconfiguration using default svn keywordset\n'))
         else:
             ui.status(_('\n\tconfiguration using default cvs keywordset\n'))
         kwmaps = _defaultkwmaps(ui)
         if uikwmaps:
             ui.status(_('\tdisabling current template maps\n'))
             for k, v in kwmaps.iteritems():
                 ui.setconfig('keywordmaps', k, v)
     else:
         ui.status(_('\n\tconfiguration using current keyword template maps\n'))
         if uikwmaps:
             kwmaps = dict(uikwmaps)
         else:
             kwmaps = _defaultkwmaps(ui)
 
     uisetup(ui)
     reposetup(ui, repo)
     ui.write('[extensions]\nkeyword =\n')
     demoitems('keyword', ui.configitems('keyword'))
     demoitems('keywordset', ui.configitems('keywordset'))
     demoitems('keywordmaps', kwmaps.iteritems())
     keywords = '$' + '$\n$'.join(sorted(kwmaps.keys())) + '$\n'
     repo.wopener.write(fn, keywords)
     repo[None].add([fn])
     ui.note(_('\nkeywords written to %s:\n') % fn)
     ui.note(keywords)
     repo.dirstate.setbranch('demobranch')
     for name, cmd in ui.configitems('hooks'):
         if name.split('.', 1)[0].find('commit') > -1:
             repo.ui.setconfig('hooks', name, '')
     msg = _('hg keyword configuration and expansion example')
     ui.note("hg ci -m '%s'\n" % msg) # check-code-ignore
     repo.commit(text=msg)
     ui.status(_('\n\tkeywords expanded\n'))
     ui.write(repo.wread(fn))
     shutil.rmtree(tmpdir, ignore_errors=True)
 
 @command('kwexpand', commands.walkopts, _('hg kwexpand [OPTION]... [FILE]...'))
 def expand(ui, repo, *pats, **opts):
     '''expand keywords in the working directory
 
     Run after (re)enabling keyword expansion.
 
     kwexpand refuses to run if given files contain local changes.
     '''
     # 3rd argument sets expansion to True
     _kwfwrite(ui, repo, True, *pats, **opts)
 
 @command('kwfiles',
          [('A', 'all', None, _('show keyword status flags of all files')),
           ('i', 'ignore', None, _('show files excluded from expansion')),
           ('u', 'unknown', None, _('only show unknown (not tracked) files')),
          ] + commands.walkopts,
          _('hg kwfiles [OPTION]... [FILE]...'))
 def files(ui, repo, *pats, **opts):
     '''show files configured for keyword expansion
 
     List which files in the working directory are matched by the
     [keyword] configuration patterns.
 
     Useful to prevent inadvertent keyword expansion and to speed up
     execution by including only files that are actual candidates for
     expansion.
 
     See :hg:`help keyword` on how to construct patterns both for
     inclusion and exclusion of files.
 
     With -A/--all and -v/--verbose the codes used to show the status
     of files are::
 
       K = keyword expansion candidate
       k = keyword expansion candidate (not tracked)
       I = ignored
       i = ignored (not tracked)
     '''
     kwt = kwtools['templater']
     wctx = repo[None]
     status = _status(ui, repo, wctx, kwt, *pats, **opts)
     cwd = pats and repo.getcwd() or ''
     modified, added, removed, deleted, unknown, ignored, clean = status
     files = []
     if not opts.get('unknown') or opts.get('all'):
         files = sorted(modified + added + clean)
     kwfiles = kwt.iskwfile(files, wctx)
     kwdeleted = kwt.iskwfile(deleted, wctx)
     kwunknown = kwt.iskwfile(unknown, wctx)
     if not opts.get('ignore') or opts.get('all'):
         showfiles = kwfiles, kwdeleted, kwunknown
     else:
         showfiles = [], [], []
     if opts.get('all') or opts.get('ignore'):
         showfiles += ([f for f in files if f not in kwfiles],
                       [f for f in unknown if f not in kwunknown])
     kwlabels = 'enabled deleted enabledunknown ignored ignoredunknown'.split()
     kwstates = zip(kwlabels, 'K!kIi', showfiles)
     fm = ui.formatter('kwfiles', opts)
     fmt = '%.0s%s\n'
     if opts.get('all') or ui.verbose:
         fmt = '%s %s\n'
     for kwstate, char, filenames in kwstates:
         label = 'kwfiles.' + kwstate
         for f in filenames:
             fm.startitem()
             fm.write('kwstatus path', fmt, char,
                      repo.pathto(f, cwd), label=label)
     fm.end()
 
 @command('kwshrink', commands.walkopts, _('hg kwshrink [OPTION]... [FILE]...'))
 def shrink(ui, repo, *pats, **opts):
     '''revert expanded keywords in the working directory
 
     Must be run before changing/disabling active keywords.
 
     kwshrink refuses to run if given files contain local changes.
     '''
     # 3rd argument sets expansion to False
     _kwfwrite(ui, repo, False, *pats, **opts)
 
 
 def uisetup(ui):
     ''' Monkeypatches dispatch._parse to retrieve user command.'''
 
     def kwdispatch_parse(orig, ui, args):
         '''Monkeypatch dispatch._parse to obtain running hg command.'''
         cmd, func, args, options, cmdoptions = orig(ui, args)
         kwtools['hgcmd'] = cmd
         return cmd, func, args, options, cmdoptions
 
     extensions.wrapfunction(dispatch, '_parse', kwdispatch_parse)
 
 def reposetup(ui, repo):
     '''Sets up repo as kwrepo for keyword substitution.
     Overrides file method to return kwfilelog instead of filelog
     if file matches user configuration.
     Wraps commit to overwrite configured files with updated
     keyword substitutions.
     Monkeypatches patch and webcommands.'''
 
     try:
         if (not repo.local() or kwtools['hgcmd'] in nokwcommands.split()
             or '.hg' in util.splitpath(repo.root)
             or repo._url.startswith('bundle:')):
             return
     except AttributeError:
         pass
 
     inc, exc = [], ['.hg*']
     for pat, opt in ui.configitems('keyword'):
         if opt != 'ignore':
             inc.append(pat)
         else:
             exc.append(pat)
     if not inc:
         return
 
     kwtools['templater'] = kwt = kwtemplater(ui, repo, inc, exc)
 
     class kwrepo(repo.__class__):
         def file(self, f):
             if f[0] == '/':
                 f = f[1:]
             return kwfilelog(self.sopener, kwt, f)
 
         def wread(self, filename):
             data = super(kwrepo, self).wread(filename)
             return kwt.wread(filename, data)
 
         def commit(self, *args, **opts):
             # use custom commitctx for user commands
             # other extensions can still wrap repo.commitctx directly
             self.commitctx = self.kwcommitctx
             try:
                 return super(kwrepo, self).commit(*args, **opts)
             finally:
                 del self.commitctx
 
         def kwcommitctx(self, ctx, error=False):
             n = super(kwrepo, self).commitctx(ctx, error)
             # no lock needed, only called from repo.commit() which already locks
             if not kwt.postcommit:
                 restrict = kwt.restrict
                 kwt.restrict = True
                 kwt.overwrite(self[n], sorted(ctx.added() + ctx.modified()),
                               False, True)
                 kwt.restrict = restrict
             return n
 
         def rollback(self, dryrun=False, force=False):
             wlock = self.wlock()
             try:
                 if not dryrun:
                     changed = self['.'].files()
                 ret = super(kwrepo, self).rollback(dryrun, force)
                 if not dryrun:
                     ctx = self['.']
                     modified, added = _preselect(self[None].status(), changed)
                     kwt.overwrite(ctx, modified, True, True)
                     kwt.overwrite(ctx, added, True, False)
                 return ret
             finally:
                 wlock.release()
 
     # monkeypatches
     def kwpatchfile_init(orig, self, ui, gp, backend, store, eolmode=None):
         '''Monkeypatch/wrap patch.patchfile.__init__ to avoid
         rejects or conflicts due to expanded keywords in working dir.'''
         orig(self, ui, gp, backend, store, eolmode)
         # shrink keywords read from working dir
         self.lines = kwt.shrinklines(self.fname, self.lines)
 
     def kw_diff(orig, repo, node1=None, node2=None, match=None, changes=None,
                 opts=None, prefix=''):
         '''Monkeypatch patch.diff to avoid expansion.'''
         kwt.restrict = True
         return orig(repo, node1, node2, match, changes, opts, prefix)
 
     def kwweb_skip(orig, web, req, tmpl):
         '''Wraps webcommands.x turning off keyword expansion.'''
         kwt.match = util.never
         return orig(web, req, tmpl)
 
     def kw_amend(orig, ui, repo, commitfunc, old, extra, pats, opts):
         '''Wraps cmdutil.amend expanding keywords after amend.'''
         wlock = repo.wlock()
         try:
             kwt.postcommit = True
             newid = orig(ui, repo, commitfunc, old, extra, pats, opts)
             if newid != old.node():
                 ctx = repo[newid]
                 kwt.restrict = True
                 kwt.overwrite(ctx, ctx.files(), False, True)
                 kwt.restrict = False
             return newid
         finally:
             wlock.release()
 
     def kw_copy(orig, ui, repo, pats, opts, rename=False):
         '''Wraps cmdutil.copy so that copy/rename destinations do not
         contain expanded keywords.
         Note that the source of a regular file destination may also be a
         symlink:
         hg cp sym x                -> x is symlink
         cp sym x; hg cp -A sym x   -> x is file (maybe expanded keywords)
         For the latter we have to follow the symlink to find out whether its
         target is configured for expansion and we therefore must unexpand the
         keywords in the destination.'''
         wlock = repo.wlock()
         try:
             orig(ui, repo, pats, opts, rename)
             if opts.get('dry_run'):
                 return
             wctx = repo[None]
             cwd = repo.getcwd()
 
             def haskwsource(dest):
                 '''Returns true if dest is a regular file and configured for
                 expansion or a symlink which points to a file configured for
                 expansion. '''
                 source = repo.dirstate.copied(dest)
                 if 'l' in wctx.flags(source):
-                    source = scmutil.canonpath(repo.root, cwd,
+                    source = pathutil.canonpath(repo.root, cwd,
                                                os.path.realpath(source))
                 return kwt.match(source)
 
             candidates = [f for f in repo.dirstate.copies() if
                           'l' not in wctx.flags(f) and haskwsource(f)]
             kwt.overwrite(wctx, candidates, False, False)
         finally:
             wlock.release()
 
     def kw_dorecord(orig, ui, repo, commitfunc, *pats, **opts):
         '''Wraps record.dorecord expanding keywords after recording.'''
         wlock = repo.wlock()
         try:
             # record returns 0 even when nothing has changed
             # therefore compare nodes before and after
             kwt.postcommit = True
             ctx = repo['.']
             wstatus = repo[None].status()
             ret = orig(ui, repo, commitfunc, *pats, **opts)
             recctx = repo['.']
             if ctx != recctx:
                 modified, added = _preselect(wstatus, recctx.files())
                 kwt.restrict = False
                 kwt.overwrite(recctx, modified, False, True)
                 kwt.overwrite(recctx, added, False, True, True)
                 kwt.restrict = True
             return ret
         finally:
             wlock.release()
 
     def kwfilectx_cmp(orig, self, fctx):
         # keyword affects data size, comparing wdir and filelog size does
         # not make sense
         if (fctx._filerev is None and
             (self._repo._encodefilterpats or
              kwt.match(fctx.path()) and 'l' not in fctx.flags() or
              self.size() - 4 == fctx.size()) or
             self.size() == fctx.size()):
             return self._filelog.cmp(self._filenode, fctx.data())
         return True
 
     extensions.wrapfunction(context.filectx, 'cmp', kwfilectx_cmp)
     extensions.wrapfunction(patch.patchfile, '__init__', kwpatchfile_init)
     extensions.wrapfunction(patch, 'diff', kw_diff)
     extensions.wrapfunction(cmdutil, 'amend', kw_amend)
     extensions.wrapfunction(cmdutil, 'copy', kw_copy)
     for c in 'annotate changeset rev filediff diff'.split():
         extensions.wrapfunction(webcommands, c, kwweb_skip)
     for name in recordextensions.split():
         try:
             record = extensions.find(name)
             extensions.wrapfunction(record, 'dorecord', kw_dorecord)
         except KeyError:
             pass
 
     repo.__class__ = kwrepo

hgext/largefiles/overrides.py

@@ -1,1218 +1,1218 b''
 # Copyright 2009-2010 Gregory P. Ward
 # Copyright 2009-2010 Intelerad Medical Systems Incorporated
 # Copyright 2010-2011 Fog Creek Software
 # Copyright 2010-2011 Unity Technologies
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 '''Overridden Mercurial commands and functions for the largefiles extension'''
 
 import os
 import copy
 
 from mercurial import hg, commands, util, cmdutil, scmutil, match as match_, \
-    node, archival, error, merge, discovery
+    node, archival, error, merge, discovery, pathutil
 from mercurial.i18n import _
 from mercurial.node import hex
 from hgext import rebase
 
 import lfutil
 import lfcommands
 import basestore
 
 # -- Utility functions: commonly/repeatedly needed functionality ---------------
 
 def installnormalfilesmatchfn(manifest):
     '''overrides scmutil.match so that the matcher it returns will ignore all
     largefiles'''
     oldmatch = None # for the closure
     def overridematch(ctx, pats=[], opts={}, globbed=False,
             default='relpath'):
         match = oldmatch(ctx, pats, opts, globbed, default)
         m = copy.copy(match)
         notlfile = lambda f: not (lfutil.isstandin(f) or lfutil.standin(f) in
                 manifest)
         m._files = filter(notlfile, m._files)
         m._fmap = set(m._files)
         m._always = False
         origmatchfn = m.matchfn
         m.matchfn = lambda f: notlfile(f) and origmatchfn(f) or None
         return m
     oldmatch = installmatchfn(overridematch)
 
 def installmatchfn(f):
     oldmatch = scmutil.match
     setattr(f, 'oldmatch', oldmatch)
     scmutil.match = f
     return oldmatch
 
 def restorematchfn():
     '''restores scmutil.match to what it was before installnormalfilesmatchfn
     was called.  no-op if scmutil.match is its original function.
 
     Note that n calls to installnormalfilesmatchfn will require n calls to
     restore matchfn to reverse'''
     scmutil.match = getattr(scmutil.match, 'oldmatch', scmutil.match)
 
 def addlargefiles(ui, repo, *pats, **opts):
     large = opts.pop('large', None)
     lfsize = lfutil.getminsize(
         ui, lfutil.islfilesrepo(repo), opts.pop('lfsize', None))
 
     lfmatcher = None
     if lfutil.islfilesrepo(repo):
         lfpats = ui.configlist(lfutil.longname, 'patterns', default=[])
         if lfpats:
             lfmatcher = match_.match(repo.root, '', list(lfpats))
 
     lfnames = []
     m = scmutil.match(repo[None], pats, opts)
     m.bad = lambda x, y: None
     wctx = repo[None]
     for f in repo.walk(m):
         exact = m.exact(f)
         lfile = lfutil.standin(f) in wctx
         nfile = f in wctx
         exists = lfile or nfile
 
         # Don't warn the user when they attempt to add a normal tracked file.
         # The normal add code will do that for us.
         if exact and exists:
             if lfile:
                 ui.warn(_('%s already a largefile\n') % f)
             continue
 
         if (exact or not exists) and not lfutil.isstandin(f):
             wfile = repo.wjoin(f)
 
             # In case the file was removed previously, but not committed
             # (issue3507)
             if not os.path.exists(wfile):
                 continue
 
             abovemin = (lfsize and
                         os.lstat(wfile).st_size >= lfsize * 1024 * 1024)
             if large or abovemin or (lfmatcher and lfmatcher(f)):
                 lfnames.append(f)
                 if ui.verbose or not exact:
                     ui.status(_('adding %s as a largefile\n') % m.rel(f))
 
     bad = []
     standins = []
 
     # Need to lock, otherwise there could be a race condition between
     # when standins are created and added to the repo.
     wlock = repo.wlock()
     try:
         if not opts.get('dry_run'):
             lfdirstate = lfutil.openlfdirstate(ui, repo)
             for f in lfnames:
                 standinname = lfutil.standin(f)
                 lfutil.writestandin(repo, standinname, hash='',
                     executable=lfutil.getexecutable(repo.wjoin(f)))
                 standins.append(standinname)
                 if lfdirstate[f] == 'r':
                     lfdirstate.normallookup(f)
                 else:
                     lfdirstate.add(f)
             lfdirstate.write()
             bad += [lfutil.splitstandin(f)
                     for f in repo[None].add(standins)
                     if f in m.files()]
     finally:
         wlock.release()
     return bad
 
 def removelargefiles(ui, repo, *pats, **opts):
     after = opts.get('after')
     if not pats and not after:
         raise util.Abort(_('no files specified'))
     m = scmutil.match(repo[None], pats, opts)
     try:
         repo.lfstatus = True
         s = repo.status(match=m, clean=True)
     finally:
         repo.lfstatus = False
     manifest = repo[None].manifest()
     modified, added, deleted, clean = [[f for f in list
                                         if lfutil.standin(f) in manifest]
                                        for list in [s[0], s[1], s[3], s[6]]]
 
     def warn(files, msg):
         for f in files:
             ui.warn(msg % m.rel(f))
         return int(len(files) > 0)
 
     result = 0
 
     if after:
         remove, forget = deleted, []
         result = warn(modified + added + clean,
                       _('not removing %s: file still exists\n'))
     else:
         remove, forget = deleted + clean, []
         result = warn(modified, _('not removing %s: file is modified (use -f'
                                   ' to force removal)\n'))
         result = warn(added, _('not removing %s: file has been marked for add'
                                ' (use forget to undo)\n')) or result
 
     for f in sorted(remove + forget):
         if ui.verbose or not m.exact(f):
             ui.status(_('removing %s\n') % m.rel(f))
 
     # Need to lock because standin files are deleted then removed from the
     # repository and we could race in-between.
     wlock = repo.wlock()
     try:
         lfdirstate = lfutil.openlfdirstate(ui, repo)
         for f in remove:
             if not after:
                 # If this is being called by addremove, notify the user that we
                 # are removing the file.
                 if getattr(repo, "_isaddremove", False):
                     ui.status(_('removing %s\n') % f)
                 util.unlinkpath(repo.wjoin(f), ignoremissing=True)
             lfdirstate.remove(f)
         lfdirstate.write()
         forget = [lfutil.standin(f) for f in forget]
         remove = [lfutil.standin(f) for f in remove]
         repo[None].forget(forget)
         # If this is being called by addremove, let the original addremove
         # function handle this.
         if not getattr(repo, "_isaddremove", False):
             for f in remove:
                 util.unlinkpath(repo.wjoin(f), ignoremissing=True)
         repo[None].forget(remove)
     finally:
         wlock.release()
 
     return result
 
 # For overriding mercurial.hgweb.webcommands so that largefiles will
 # appear at their right place in the manifests.
 def decodepath(orig, path):
     return lfutil.splitstandin(path) or path
 
 # -- Wrappers: modify existing commands --------------------------------
 
 # Add works by going through the files that the user wanted to add and
 # checking if they should be added as largefiles. Then it makes a new
 # matcher which matches only the normal files and runs the original
 # version of add.
 def overrideadd(orig, ui, repo, *pats, **opts):
     normal = opts.pop('normal')
     if normal:
         if opts.get('large'):
             raise util.Abort(_('--normal cannot be used with --large'))
         return orig(ui, repo, *pats, **opts)
     bad = addlargefiles(ui, repo, *pats, **opts)
     installnormalfilesmatchfn(repo[None].manifest())
     result = orig(ui, repo, *pats, **opts)
     restorematchfn()
 
     return (result == 1 or bad) and 1 or 0
 
 def overrideremove(orig, ui, repo, *pats, **opts):
     installnormalfilesmatchfn(repo[None].manifest())
     result = orig(ui, repo, *pats, **opts)
     restorematchfn()
     return removelargefiles(ui, repo, *pats, **opts) or result
 
 def overridestatusfn(orig, repo, rev2, **opts):
     try:
         repo._repo.lfstatus = True
         return orig(repo, rev2, **opts)
     finally:
         repo._repo.lfstatus = False
 
 def overridestatus(orig, ui, repo, *pats, **opts):
     try:
         repo.lfstatus = True
         return orig(ui, repo, *pats, **opts)
     finally:
         repo.lfstatus = False
 
 def overridedirty(orig, repo, ignoreupdate=False):
     try:
         repo._repo.lfstatus = True
         return orig(repo, ignoreupdate)
     finally:
         repo._repo.lfstatus = False
 
 def overridelog(orig, ui, repo, *pats, **opts):
     def overridematch(ctx, pats=[], opts={}, globbed=False,
             default='relpath'):
         """Matcher that merges root directory with .hglf, suitable for log.
         It is still possible to match .hglf directly.
         For any listed files run log on the standin too.
         matchfn tries both the given filename and with .hglf stripped.
         """
         match = oldmatch(ctx, pats, opts, globbed, default)
         m = copy.copy(match)
         for i in range(0, len(m._files)):
             standin = lfutil.standin(m._files[i])
             if standin in repo[ctx.node()]:
                 m._files[i] = standin
         m._fmap = set(m._files)
         m._always = False
         origmatchfn = m.matchfn
         def lfmatchfn(f):
             lf = lfutil.splitstandin(f)
             if lf is not None and origmatchfn(lf):
                 return True
             r = origmatchfn(f)
             return r
         m.matchfn = lfmatchfn
         return m
     oldmatch = installmatchfn(overridematch)
     try:
         repo.lfstatus = True
         return orig(ui, repo, *pats, **opts)
     finally:
         repo.lfstatus = False
         restorematchfn()
 
 def overrideverify(orig, ui, repo, *pats, **opts):
     large = opts.pop('large', False)
     all = opts.pop('lfa', False)
     contents = opts.pop('lfc', False)
 
     result = orig(ui, repo, *pats, **opts)
     if large or all or contents:
         result = result or lfcommands.verifylfiles(ui, repo, all, contents)
     return result
 
 def overridedebugstate(orig, ui, repo, *pats, **opts):
     large = opts.pop('large', False)
     if large:
         lfcommands.debugdirstate(ui, repo)
     else:
         orig(ui, repo, *pats, **opts)
 
 # Override needs to refresh standins so that update's normal merge
 # will go through properly. Then the other update hook (overriding repo.update)
 # will get the new files. Filemerge is also overridden so that the merge
 # will merge standins correctly.
 def overrideupdate(orig, ui, repo, *pats, **opts):
     lfdirstate = lfutil.openlfdirstate(ui, repo)
     s = lfdirstate.status(match_.always(repo.root, repo.getcwd()), [], False,
         False, False)
     (unsure, modified, added, removed, missing, unknown, ignored, clean) = s
 
     # Need to lock between the standins getting updated and their
     # largefiles getting updated
     wlock = repo.wlock()
     try:
         if opts['check']:
             mod = len(modified) > 0
             for lfile in unsure:
                 standin = lfutil.standin(lfile)
                 if repo['.'][standin].data().strip() != \
                         lfutil.hashfile(repo.wjoin(lfile)):
                     mod = True
                 else:
                     lfdirstate.normal(lfile)
             lfdirstate.write()
             if mod:
                 raise util.Abort(_('uncommitted changes'))
         # XXX handle removed differently
         if not opts['clean']:
             for lfile in unsure + modified + added:
                 lfutil.updatestandin(repo, lfutil.standin(lfile))
     finally:
         wlock.release()
     return orig(ui, repo, *pats, **opts)
 
 # Before starting the manifest merge, merge.updates will call
 # _checkunknown to check if there are any files in the merged-in
 # changeset that collide with unknown files in the working copy.
 #
 # The largefiles are seen as unknown, so this prevents us from merging
 # in a file 'foo' if we already have a largefile with the same name.
 #
 # The overridden function filters the unknown files by removing any
 # largefiles. This makes the merge proceed and we can then handle this
 # case further in the overridden manifestmerge function below.
 def overridecheckunknownfile(origfn, repo, wctx, mctx, f):
     if lfutil.standin(repo.dirstate.normalize(f)) in wctx:
         return False
     return origfn(repo, wctx, mctx, f)
 
 # The manifest merge handles conflicts on the manifest level. We want
 # to handle changes in largefile-ness of files at this level too.
 #
 # The strategy is to run the original manifestmerge and then process
 # the action list it outputs. There are two cases we need to deal with:
 #
 # 1. Normal file in p1, largefile in p2. Here the largefile is
 #    detected via its standin file, which will enter the working copy
 #    with a "get" action. It is not "merge" since the standin is all
 #    Mercurial is concerned with at this level -- the link to the
 #    existing normal file is not relevant here.
 #
 # 2. Largefile in p1, normal file in p2. Here we get a "merge" action
 #    since the largefile will be present in the working copy and
 #    different from the normal file in p2. Mercurial therefore
 #    triggers a merge action.
 #
 # In both cases, we prompt the user and emit new actions to either
 # remove the standin (if the normal file was kept) or to remove the
 # normal file and get the standin (if the largefile was kept). The
 # default prompt answer is to use the largefile version since it was
 # presumably changed on purpose.
 #
 # Finally, the merge.applyupdates function will then take care of
 # writing the files into the working copy and lfcommands.updatelfiles
 # will update the largefiles.
 def overridemanifestmerge(origfn, repo, p1, p2, pa, branchmerge, force,
                           partial, acceptremote=False):
     overwrite = force and not branchmerge
     actions = origfn(repo, p1, p2, pa, branchmerge, force, partial,
                      acceptremote)
 
     if overwrite:
         return actions
 
     removes = set(a[0] for a in actions if a[1] == 'r')
     processed = []
 
     for action in actions:
         f, m, args, msg = action
 
         splitstandin = lfutil.splitstandin(f)
         if (m == "g" and splitstandin is not None and
             splitstandin in p1 and splitstandin not in removes):
             # Case 1: normal file in the working copy, largefile in
             # the second parent
             lfile = splitstandin
             standin = f
             msg = _('remote turned local normal file %s into a largefile\n'
                     'use (l)argefile or keep (n)ormal file?'
                     '$$ &Largefile $$ &Normal file') % lfile
             if repo.ui.promptchoice(msg, 0) == 0:
                 processed.append((lfile, "r", None, msg))
                 processed.append((standin, "g", (p2.flags(standin),), msg))
             else:
                 processed.append((standin, "r", None, msg))
         elif (m == "g" and
             lfutil.standin(f) in p1 and lfutil.standin(f) not in removes):
             # Case 2: largefile in the working copy, normal file in
             # the second parent
             standin = lfutil.standin(f)
             lfile = f
             msg = _('remote turned local largefile %s into a normal file\n'
                     'keep (l)argefile or use (n)ormal file?'
                     '$$ &Largefile $$ &Normal file') % lfile
             if repo.ui.promptchoice(msg, 0) == 0:
                 processed.append((lfile, "r", None, msg))
             else:
                 processed.append((standin, "r", None, msg))
                 processed.append((lfile, "g", (p2.flags(lfile),), msg))
         else:
             processed.append(action)
 
     return processed
 
 # Override filemerge to prompt the user about how they wish to merge
 # largefiles. This will handle identical edits, and copy/rename +
 # edit without prompting the user.
 def overridefilemerge(origfn, repo, mynode, orig, fcd, fco, fca):
     # Use better variable names here. Because this is a wrapper we cannot
     # change the variable names in the function declaration.
     fcdest, fcother, fcancestor = fcd, fco, fca
     if not lfutil.isstandin(orig):
         return origfn(repo, mynode, orig, fcdest, fcother, fcancestor)
     else:
         if not fcother.cmp(fcdest): # files identical?
             return None
 
         # backwards, use working dir parent as ancestor
         if fcancestor == fcother:
             fcancestor = fcdest.parents()[0]
 
         if orig != fcother.path():
             repo.ui.status(_('merging %s and %s to %s\n')
                            % (lfutil.splitstandin(orig),
                               lfutil.splitstandin(fcother.path()),
                               lfutil.splitstandin(fcdest.path())))
         else:
             repo.ui.status(_('merging %s\n')
                            % lfutil.splitstandin(fcdest.path()))
 
         if fcancestor.path() != fcother.path() and fcother.data() == \
                 fcancestor.data():
             return 0
         if fcancestor.path() != fcdest.path() and fcdest.data() == \
                 fcancestor.data():
             repo.wwrite(fcdest.path(), fcother.data(), fcother.flags())
             return 0
 
         if repo.ui.promptchoice(_('largefile %s has a merge conflict\n'
                                   'keep (l)ocal or take (o)ther?'
                                   '$$ &Local $$ &Other') %
                                 lfutil.splitstandin(orig), 0) == 0:
             return 0
         else:
             repo.wwrite(fcdest.path(), fcother.data(), fcother.flags())
             return 0
 
 # Copy first changes the matchers to match standins instead of
 # largefiles.  Then it overrides util.copyfile in that function it
 # checks if the destination largefile already exists. It also keeps a
 # list of copied files so that the largefiles can be copied and the
 # dirstate updated.
 def overridecopy(orig, ui, repo, pats, opts, rename=False):
     # doesn't remove largefile on rename
     if len(pats) < 2:
         # this isn't legal, let the original function deal with it
         return orig(ui, repo, pats, opts, rename)
 
     def makestandin(relpath):
-        path = scmutil.canonpath(repo.root, repo.getcwd(), relpath)
+        path = pathutil.canonpath(repo.root, repo.getcwd(), relpath)
         return os.path.join(repo.wjoin(lfutil.standin(path)))
 
     fullpats = scmutil.expandpats(pats)
     dest = fullpats[-1]
 
     if os.path.isdir(dest):
         if not os.path.isdir(makestandin(dest)):
             os.makedirs(makestandin(dest))
     # This could copy both lfiles and normal files in one command,
     # but we don't want to do that. First replace their matcher to
     # only match normal files and run it, then replace it to just
     # match largefiles and run it again.
     nonormalfiles = False
     nolfiles = False
     try:
         try:
             installnormalfilesmatchfn(repo[None].manifest())
             result = orig(ui, repo, pats, opts, rename)
         except util.Abort, e:
             if str(e) != _('no files to copy'):
                 raise e
             else:
                 nonormalfiles = True
             result = 0
     finally:
         restorematchfn()
 
     # The first rename can cause our current working directory to be removed.
     # In that case there is nothing left to copy/rename so just quit.
     try:
         repo.getcwd()
     except OSError:
         return result
 
     try:
         try:
             # When we call orig below it creates the standins but we don't add
             # them to the dir state until later so lock during that time.
             wlock = repo.wlock()
 
             manifest = repo[None].manifest()
             oldmatch = None # for the closure
             def overridematch(ctx, pats=[], opts={}, globbed=False,
                     default='relpath'):
                 newpats = []
                 # The patterns were previously mangled to add the standin
                 # directory; we need to remove that now
                 for pat in pats:
                     if match_.patkind(pat) is None and lfutil.shortname in pat:
                         newpats.append(pat.replace(lfutil.shortname, ''))
                     else:
                         newpats.append(pat)
                 match = oldmatch(ctx, newpats, opts, globbed, default)
                 m = copy.copy(match)
                 lfile = lambda f: lfutil.standin(f) in manifest
                 m._files = [lfutil.standin(f) for f in m._files if lfile(f)]
                 m._fmap = set(m._files)
                 m._always = False
                 origmatchfn = m.matchfn
                 m.matchfn = lambda f: (lfutil.isstandin(f) and
                                     (f in manifest) and
                                     origmatchfn(lfutil.splitstandin(f)) or
                                     None)
                 return m
             oldmatch = installmatchfn(overridematch)
             listpats = []
             for pat in pats:
                 if match_.patkind(pat) is not None:
                     listpats.append(pat)
                 else:
                     listpats.append(makestandin(pat))
 
             try:
                 origcopyfile = util.copyfile
                 copiedfiles = []
                 def overridecopyfile(src, dest):
                     if (lfutil.shortname in src and
                         dest.startswith(repo.wjoin(lfutil.shortname))):
                         destlfile = dest.replace(lfutil.shortname, '')
                         if not opts['force'] and os.path.exists(destlfile):
                             raise IOError('',
                                 _('destination largefile already exists'))
                     copiedfiles.append((src, dest))
                     origcopyfile(src, dest)
 
                 util.copyfile = overridecopyfile
                 result += orig(ui, repo, listpats, opts, rename)
             finally:
                 util.copyfile = origcopyfile
 
             lfdirstate = lfutil.openlfdirstate(ui, repo)
             for (src, dest) in copiedfiles:
                 if (lfutil.shortname in src and
                     dest.startswith(repo.wjoin(lfutil.shortname))):
                     srclfile = src.replace(repo.wjoin(lfutil.standin('')), '')
                     destlfile = dest.replace(repo.wjoin(lfutil.standin('')), '')
                     destlfiledir = os.path.dirname(repo.wjoin(destlfile)) or '.'
                     if not os.path.isdir(destlfiledir):
                         os.makedirs(destlfiledir)
                     if rename:
                         os.rename(repo.wjoin(srclfile), repo.wjoin(destlfile))
                         lfdirstate.remove(srclfile)
                     else:
                         util.copyfile(repo.wjoin(srclfile),
                                       repo.wjoin(destlfile))
 
                     lfdirstate.add(destlfile)
             lfdirstate.write()
         except util.Abort, e:
             if str(e) != _('no files to copy'):
                 raise e
             else:
                 nolfiles = True
     finally:
         restorematchfn()
         wlock.release()
 
     if nolfiles and nonormalfiles:
         raise util.Abort(_('no files to copy'))
 
     return result
 
 # When the user calls revert, we have to be careful to not revert any
 # changes to other largefiles accidentally. This means we have to keep
 # track of the largefiles that are being reverted so we only pull down
 # the necessary largefiles.
 #
 # Standins are only updated (to match the hash of largefiles) before
 # commits. Update the standins then run the original revert, changing
 # the matcher to hit standins instead of largefiles. Based on the
 # resulting standins update the largefiles. Then return the standins
 # to their proper state
 def overriderevert(orig, ui, repo, *pats, **opts):
     # Because we put the standins in a bad state (by updating them)
     # and then return them to a correct state we need to lock to
     # prevent others from changing them in their incorrect state.
     wlock = repo.wlock()
     try:
         lfdirstate = lfutil.openlfdirstate(ui, repo)
         (modified, added, removed, missing, unknown, ignored, clean) = \
             lfutil.lfdirstatestatus(lfdirstate, repo, repo['.'].rev())
         lfdirstate.write()
         for lfile in modified:
             lfutil.updatestandin(repo, lfutil.standin(lfile))
         for lfile in missing:
             if (os.path.exists(repo.wjoin(lfutil.standin(lfile)))):
                 os.unlink(repo.wjoin(lfutil.standin(lfile)))
 
         try:
             ctx = scmutil.revsingle(repo, opts.get('rev'))
             oldmatch = None # for the closure
             def overridematch(ctx, pats=[], opts={}, globbed=False,
                     default='relpath'):
                 match = oldmatch(ctx, pats, opts, globbed, default)
                 m = copy.copy(match)
                 def tostandin(f):
                     if lfutil.standin(f) in ctx:
                         return lfutil.standin(f)
                     elif lfutil.standin(f) in repo[None]:
                         return None
                     return f
                 m._files = [tostandin(f) for f in m._files]
                 m._files = [f for f in m._files if f is not None]
                 m._fmap = set(m._files)
                 m._always = False
                 origmatchfn = m.matchfn
                 def matchfn(f):
                     if lfutil.isstandin(f):
                         # We need to keep track of what largefiles are being
                         # matched so we know which ones to update later --
                         # otherwise we accidentally revert changes to other
                         # largefiles. This is repo-specific, so duckpunch the
                         # repo object to keep the list of largefiles for us
                         # later.
                         if origmatchfn(lfutil.splitstandin(f)) and \
                                 (f in repo[None] or f in ctx):
                             lfileslist = getattr(repo, '_lfilestoupdate', [])
                             lfileslist.append(lfutil.splitstandin(f))
                             repo._lfilestoupdate = lfileslist
                             return True
                         else:
                             return False
                     return origmatchfn(f)
                 m.matchfn = matchfn
                 return m
             oldmatch = installmatchfn(overridematch)
             scmutil.match
             matches = overridematch(repo[None], pats, opts)
             orig(ui, repo, *pats, **opts)
         finally:
             restorematchfn()
         lfileslist = getattr(repo, '_lfilestoupdate', [])
         lfcommands.updatelfiles(ui, repo, filelist=lfileslist,
                                 printmessage=False)
 
         # empty out the largefiles list so we start fresh next time
         repo._lfilestoupdate = []
         for lfile in modified:
             if lfile in lfileslist:
                 if os.path.exists(repo.wjoin(lfutil.standin(lfile))) and lfile\
                         in repo['.']:
                     lfutil.writestandin(repo, lfutil.standin(lfile),
                         repo['.'][lfile].data().strip(),
                         'x' in repo['.'][lfile].flags())
         lfdirstate = lfutil.openlfdirstate(ui, repo)
         for lfile in added:
             standin = lfutil.standin(lfile)
             if standin not in ctx and (standin in matches or opts.get('all')):
                 if lfile in lfdirstate:
                     lfdirstate.drop(lfile)
                 util.unlinkpath(repo.wjoin(standin))
         lfdirstate.write()
     finally:
         wlock.release()
 
 def hgupdaterepo(orig, repo, node, overwrite):
     if not overwrite:
         # Only call updatelfiles on the standins that have changed to save time
         oldstandins = lfutil.getstandinsstate(repo)
 
     result = orig(repo, node, overwrite)
 
     filelist = None
     if not overwrite:
         newstandins = lfutil.getstandinsstate(repo)
         filelist = lfutil.getlfilestoupdate(oldstandins, newstandins)
     lfcommands.updatelfiles(repo.ui, repo, filelist=filelist)
     return result
 
 def hgmerge(orig, repo, node, force=None, remind=True):
     result = orig(repo, node, force, remind)
     lfcommands.updatelfiles(repo.ui, repo)
     return result
 
 # When we rebase a repository with remotely changed largefiles, we need to
 # take some extra care so that the largefiles are correctly updated in the
 # working copy
 def overridepull(orig, ui, repo, source=None, **opts):
     revsprepull = len(repo)
     if not source:
         source = 'default'
     repo.lfpullsource = source
     if opts.get('rebase', False):
         repo._isrebasing = True
         try:
             if opts.get('update'):
                 del opts['update']
                 ui.debug('--update and --rebase are not compatible, ignoring '
                          'the update flag\n')
             del opts['rebase']
             origpostincoming = commands.postincoming
             def _dummy(*args, **kwargs):
                 pass
             commands.postincoming = _dummy
             try:
                 result = commands.pull(ui, repo, source, **opts)
             finally:
                 commands.postincoming = origpostincoming
             revspostpull = len(repo)
             if revspostpull > revsprepull:
                 result = result or rebase.rebase(ui, repo)
         finally:
             repo._isrebasing = False
     else:
         result = orig(ui, repo, source, **opts)
     revspostpull = len(repo)
     lfrevs = opts.get('lfrev', [])
     if opts.get('all_largefiles'):
         lfrevs.append('pulled()')
     if lfrevs and revspostpull > revsprepull:
         numcached = 0
         repo.firstpulled = revsprepull # for pulled() revset expression
         try:
             for rev in scmutil.revrange(repo, lfrevs):
                 ui.note(_('pulling largefiles for revision %s\n') % rev)
                 (cached, missing) = lfcommands.cachelfiles(ui, repo, rev)
                 numcached += len(cached)
         finally:
             del repo.firstpulled
         ui.status(_("%d largefiles cached\n") % numcached)
     return result
 
 def pulledrevsetsymbol(repo, subset, x):
     """``pulled()``
     Changesets that just has been pulled.
 
     Only available with largefiles from pull --lfrev expressions.
 
     .. container:: verbose
 
       Some examples:
 
       - pull largefiles for all new changesets::
 
           hg pull -lfrev "pulled()"
 
       - pull largefiles for all new branch heads::
 
           hg pull -lfrev "head(pulled()) and not closed()"
 
     """
 
     try:
         firstpulled = repo.firstpulled
     except AttributeError:
         raise util.Abort(_("pulled() only available in --lfrev"))
     return [r for r in subset if r >= firstpulled]
 
 def overrideclone(orig, ui, source, dest=None, **opts):
     d = dest
     if d is None:
         d = hg.defaultdest(source)
     if opts.get('all_largefiles') and not hg.islocal(d):
             raise util.Abort(_(
             '--all-largefiles is incompatible with non-local destination %s' %
             d))
 
     return orig(ui, source, dest, **opts)
 
 def hgclone(orig, ui, opts, *args, **kwargs):
     result = orig(ui, opts, *args, **kwargs)
 
     if result is not None:
         sourcerepo, destrepo = result
         repo = destrepo.local()
 
         # Caching is implicitly limited to 'rev' option, since the dest repo was
         # truncated at that point.  The user may expect a download count with
         # this option, so attempt whether or not this is a largefile repo.
         if opts.get('all_largefiles'):
             success, missing = lfcommands.downloadlfiles(ui, repo, None)
 
             if missing != 0:
                 return None
 
     return result
 
 def overriderebase(orig, ui, repo, **opts):
     repo._isrebasing = True
     try:
         return orig(ui, repo, **opts)
     finally:
         repo._isrebasing = False
 
 def overridearchive(orig, repo, dest, node, kind, decode=True, matchfn=None,
             prefix=None, mtime=None, subrepos=None):
     # No need to lock because we are only reading history and
     # largefile caches, neither of which are modified.
     lfcommands.cachelfiles(repo.ui, repo, node)
 
     if kind not in archival.archivers:
         raise util.Abort(_("unknown archive type '%s'") % kind)
 
     ctx = repo[node]
 
     if kind == 'files':
         if prefix:
             raise util.Abort(
                 _('cannot give prefix when archiving to files'))
     else:
         prefix = archival.tidyprefix(dest, kind, prefix)
 
     def write(name, mode, islink, getdata):
         if matchfn and not matchfn(name):
             return
         data = getdata()
         if decode:
             data = repo.wwritedata(name, data)
         archiver.addfile(prefix + name, mode, islink, data)
 
     archiver = archival.archivers[kind](dest, mtime or ctx.date()[0])
 
     if repo.ui.configbool("ui", "archivemeta", True):
         def metadata():
             base = 'repo: %s\nnode: %s\nbranch: %s\n' % (
                 hex(repo.changelog.node(0)), hex(node), ctx.branch())
 
             tags = ''.join('tag: %s\n' % t for t in ctx.tags()
                            if repo.tagtype(t) == 'global')
             if not tags:
                 repo.ui.pushbuffer()
                 opts = {'template': '{latesttag}\n{latesttagdistance}',
                         'style': '', 'patch': None, 'git': None}
                 cmdutil.show_changeset(repo.ui, repo, opts).show(ctx)
                 ltags, dist = repo.ui.popbuffer().split('\n')
                 tags = ''.join('latesttag: %s\n' % t for t in ltags.split(':'))
                 tags += 'latesttagdistance: %s\n' % dist
 
             return base + tags
 
         write('.hg_archival.txt', 0644, False, metadata)
 
     for f in ctx:
         ff = ctx.flags(f)
         getdata = ctx[f].data
         if lfutil.isstandin(f):
             path = lfutil.findfile(repo, getdata().strip())
             if path is None:
                 raise util.Abort(
                     _('largefile %s not found in repo store or system cache')
                     % lfutil.splitstandin(f))
             f = lfutil.splitstandin(f)
 
             def getdatafn():
                 fd = None
                 try:
                     fd = open(path, 'rb')
                     return fd.read()
                 finally:
                     if fd:
                         fd.close()
 
             getdata = getdatafn
         write(f, 'x' in ff and 0755 or 0644, 'l' in ff, getdata)
 
     if subrepos:
         for subpath in sorted(ctx.substate):
             sub = ctx.sub(subpath)
             submatch = match_.narrowmatcher(subpath, matchfn)
             sub.archive(repo.ui, archiver, prefix, submatch)
 
     archiver.done()
 
 def hgsubrepoarchive(orig, repo, ui, archiver, prefix, match=None):
     repo._get(repo._state + ('hg',))
     rev = repo._state[1]
     ctx = repo._repo[rev]
 
     lfcommands.cachelfiles(ui, repo._repo, ctx.node())
 
     def write(name, mode, islink, getdata):
         # At this point, the standin has been replaced with the largefile name,
         # so the normal matcher works here without the lfutil variants.
         if match and not match(f):
             return
         data = getdata()
 
         archiver.addfile(prefix + repo._path + '/' + name, mode, islink, data)
 
     for f in ctx:
         ff = ctx.flags(f)
         getdata = ctx[f].data
         if lfutil.isstandin(f):
             path = lfutil.findfile(repo._repo, getdata().strip())
             if path is None:
                 raise util.Abort(
                     _('largefile %s not found in repo store or system cache')
                     % lfutil.splitstandin(f))
             f = lfutil.splitstandin(f)
 
             def getdatafn():
                 fd = None
                 try:
                     fd = open(os.path.join(prefix, path), 'rb')
                     return fd.read()
                 finally:
                     if fd:
                         fd.close()
 
             getdata = getdatafn
 
         write(f, 'x' in ff and 0755 or 0644, 'l' in ff, getdata)
 
     for subpath in sorted(ctx.substate):
         sub = ctx.sub(subpath)
         submatch = match_.narrowmatcher(subpath, match)
         sub.archive(ui, archiver, os.path.join(prefix, repo._path) + '/',
                     submatch)
 
 # If a largefile is modified, the change is not reflected in its
 # standin until a commit. cmdutil.bailifchanged() raises an exception
 # if the repo has uncommitted changes. Wrap it to also check if
 # largefiles were changed. This is used by bisect and backout.
 def overridebailifchanged(orig, repo):
     orig(repo)
     repo.lfstatus = True
     modified, added, removed, deleted = repo.status()[:4]
     repo.lfstatus = False
     if modified or added or removed or deleted:
         raise util.Abort(_('uncommitted changes'))
 
 # Fetch doesn't use cmdutil.bailifchanged so override it to add the check
 def overridefetch(orig, ui, repo, *pats, **opts):
     repo.lfstatus = True
     modified, added, removed, deleted = repo.status()[:4]
     repo.lfstatus = False
     if modified or added or removed or deleted:
         raise util.Abort(_('uncommitted changes'))
     return orig(ui, repo, *pats, **opts)
 
 def overrideforget(orig, ui, repo, *pats, **opts):
     installnormalfilesmatchfn(repo[None].manifest())
     result = orig(ui, repo, *pats, **opts)
     restorematchfn()
     m = scmutil.match(repo[None], pats, opts)
 
     try:
         repo.lfstatus = True
         s = repo.status(match=m, clean=True)
     finally:
         repo.lfstatus = False
     forget = sorted(s[0] + s[1] + s[3] + s[6])
     forget = [f for f in forget if lfutil.standin(f) in repo[None].manifest()]
 
     for f in forget:
         if lfutil.standin(f) not in repo.dirstate and not \
                 os.path.isdir(m.rel(lfutil.standin(f))):
             ui.warn(_('not removing %s: file is already untracked\n')
                     % m.rel(f))
             result = 1
 
     for f in forget:
         if ui.verbose or not m.exact(f):
             ui.status(_('removing %s\n') % m.rel(f))
 
     # Need to lock because standin files are deleted then removed from the
     # repository and we could race in-between.
     wlock = repo.wlock()
     try:
         lfdirstate = lfutil.openlfdirstate(ui, repo)
         for f in forget:
             if lfdirstate[f] == 'a':
                 lfdirstate.drop(f)
             else:
                 lfdirstate.remove(f)
         lfdirstate.write()
         standins = [lfutil.standin(f) for f in forget]
         for f in standins:
             util.unlinkpath(repo.wjoin(f), ignoremissing=True)
         repo[None].forget(standins)
     finally:
         wlock.release()
 
     return result
 
 def getoutgoinglfiles(ui, repo, dest=None, **opts):
     dest = ui.expandpath(dest or 'default-push', dest or 'default')
     dest, branches = hg.parseurl(dest, opts.get('branch'))
     revs, checkout = hg.addbranchrevs(repo, repo, branches, opts.get('rev'))
     if revs:
         revs = [repo.lookup(rev) for rev in scmutil.revrange(repo, revs)]
 
     try:
         remote = hg.peer(repo, opts, dest)
     except error.RepoError:
         return None
     outgoing = discovery.findcommonoutgoing(repo, remote.peer(), force=False)
     if not outgoing.missing:
         return outgoing.missing
     o = repo.changelog.nodesbetween(outgoing.missing, revs)[0]
     if opts.get('newest_first'):
         o.reverse()
 
     toupload = set()
     for n in o:
         parents = [p for p in repo.changelog.parents(n) if p != node.nullid]
         ctx = repo[n]
         files = set(ctx.files())
         if len(parents) == 2:
             mc = ctx.manifest()
             mp1 = ctx.parents()[0].manifest()
             mp2 = ctx.parents()[1].manifest()
             for f in mp1:
                 if f not in mc:
                         files.add(f)
             for f in mp2:
                 if f not in mc:
                     files.add(f)
             for f in mc:
                 if mc[f] != mp1.get(f, None) or mc[f] != mp2.get(f, None):
                     files.add(f)
         toupload = toupload.union(
             set([f for f in files if lfutil.isstandin(f) and f in ctx]))
     return sorted(toupload)
 
 def overrideoutgoing(orig, ui, repo, dest=None, **opts):
     result = orig(ui, repo, dest, **opts)
 
     if opts.pop('large', None):
         toupload = getoutgoinglfiles(ui, repo, dest, **opts)
         if toupload is None:
             ui.status(_('largefiles: No remote repo\n'))
         elif not toupload:
             ui.status(_('largefiles: no files to upload\n'))
         else:
             ui.status(_('largefiles to upload:\n'))
             for file in toupload:
                 ui.status(lfutil.splitstandin(file) + '\n')
             ui.status('\n')
 
     return result
 
 def overridesummary(orig, ui, repo, *pats, **opts):
     try:
         repo.lfstatus = True
         orig(ui, repo, *pats, **opts)
     finally:
         repo.lfstatus = False
 
     if opts.pop('large', None):
         toupload = getoutgoinglfiles(ui, repo, None, **opts)
         if toupload is None:
             # i18n: column positioning for "hg summary"
             ui.status(_('largefiles: (no remote repo)\n'))
         elif not toupload:
             # i18n: column positioning for "hg summary"
             ui.status(_('largefiles: (no files to upload)\n'))
         else:
             # i18n: column positioning for "hg summary"
             ui.status(_('largefiles: %d to upload\n') % len(toupload))
 
 def scmutiladdremove(orig, repo, pats=[], opts={}, dry_run=None,
                      similarity=None):
     if not lfutil.islfilesrepo(repo):
         return orig(repo, pats, opts, dry_run, similarity)
     # Get the list of missing largefiles so we can remove them
     lfdirstate = lfutil.openlfdirstate(repo.ui, repo)
     s = lfdirstate.status(match_.always(repo.root, repo.getcwd()), [], False,
         False, False)
     (unsure, modified, added, removed, missing, unknown, ignored, clean) = s
 
     # Call into the normal remove code, but the removing of the standin, we want
     # to have handled by original addremove.  Monkey patching here makes sure
     # we don't remove the standin in the largefiles code, preventing a very
     # confused state later.
     if missing:
         m = [repo.wjoin(f) for f in missing]
         repo._isaddremove = True
         removelargefiles(repo.ui, repo, *m, **opts)
         repo._isaddremove = False
     # Call into the normal add code, and any files that *should* be added as
     # largefiles will be
     addlargefiles(repo.ui, repo, *pats, **opts)
     # Now that we've handled largefiles, hand off to the original addremove
     # function to take care of the rest.  Make sure it doesn't do anything with
     # largefiles by installing a matcher that will ignore them.
     installnormalfilesmatchfn(repo[None].manifest())
     result = orig(repo, pats, opts, dry_run, similarity)
     restorematchfn()
     return result
 
 # Calling purge with --all will cause the largefiles to be deleted.
 # Override repo.status to prevent this from happening.
 def overridepurge(orig, ui, repo, *dirs, **opts):
     # XXX large file status is buggy when used on repo proxy.
     # XXX this needs to be investigate.
     repo = repo.unfiltered()
     oldstatus = repo.status
     def overridestatus(node1='.', node2=None, match=None, ignored=False,
                         clean=False, unknown=False, listsubrepos=False):
         r = oldstatus(node1, node2, match, ignored, clean, unknown,
                       listsubrepos)
         lfdirstate = lfutil.openlfdirstate(ui, repo)
         modified, added, removed, deleted, unknown, ignored, clean = r
         unknown = [f for f in unknown if lfdirstate[f] == '?']
         ignored = [f for f in ignored if lfdirstate[f] == '?']
         return modified, added, removed, deleted, unknown, ignored, clean
     repo.status = overridestatus
     orig(ui, repo, *dirs, **opts)
     repo.status = oldstatus
 
 def overriderollback(orig, ui, repo, **opts):
     result = orig(ui, repo, **opts)
     merge.update(repo, node=None, branchmerge=False, force=True,
         partial=lfutil.isstandin)
     wlock = repo.wlock()
     try:
         lfdirstate = lfutil.openlfdirstate(ui, repo)
         lfiles = lfutil.listlfiles(repo)
         oldlfiles = lfutil.listlfiles(repo, repo[None].parents()[0].rev())
         for file in lfiles:
             if file in oldlfiles:
                 lfdirstate.normallookup(file)
             else:
                 lfdirstate.add(file)
         lfdirstate.write()
     finally:
         wlock.release()
     return result
 
 def overridetransplant(orig, ui, repo, *revs, **opts):
     try:
         oldstandins = lfutil.getstandinsstate(repo)
         repo._istransplanting = True
         result = orig(ui, repo, *revs, **opts)
         newstandins = lfutil.getstandinsstate(repo)
         filelist = lfutil.getlfilestoupdate(oldstandins, newstandins)
         lfcommands.updatelfiles(repo.ui, repo, filelist=filelist,
                                 printmessage=True)
     finally:
         repo._istransplanting = False
     return result
 
 def overridecat(orig, ui, repo, file1, *pats, **opts):
     ctx = scmutil.revsingle(repo, opts.get('rev'))
     err = 1
     notbad = set()
     m = scmutil.match(ctx, (file1,) + pats, opts)
     origmatchfn = m.matchfn
     def lfmatchfn(f):
         lf = lfutil.splitstandin(f)
         if lf is None:
             return origmatchfn(f)
         notbad.add(lf)
         return origmatchfn(lf)
     m.matchfn = lfmatchfn
     origbadfn = m.bad
     def lfbadfn(f, msg):
         if not f in notbad:
             return origbadfn(f, msg)
     m.bad = lfbadfn
     for f in ctx.walk(m):
         fp = cmdutil.makefileobj(repo, opts.get('output'), ctx.node(),
                                  pathname=f)
         lf = lfutil.splitstandin(f)
         if lf is None:
             # duplicating unreachable code from commands.cat
             data = ctx[f].data()
             if opts.get('decode'):
                 data = repo.wwritedata(f, data)
             fp.write(data)
         else:
             hash = lfutil.readstandin(repo, lf, ctx.rev())
             if not lfutil.inusercache(repo.ui, hash):
                 store = basestore._openstore(repo)
                 success, missing = store.get([(lf, hash)])
                 if len(success) != 1:
                     raise util.Abort(
                         _('largefile %s is not in cache and could not be '
                           'downloaded')  % lf)
             path = lfutil.usercachepath(repo.ui, hash)
             fpin = open(path, "rb")
             for chunk in util.filechunkiter(fpin, 128 * 1024):
                 fp.write(chunk)
             fpin.close()
         fp.close()
         err = 0
     return err
 
 def mercurialsinkbefore(orig, sink):
     sink.repo._isconverting = True
     orig(sink)
 
 def mercurialsinkafter(orig, sink):
     sink.repo._isconverting = False
     orig(sink)

mercurial/cmdutil.py

@@ -1,2167 +1,2167 b''
 # cmdutil.py - help for command processing in mercurial
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from node import hex, nullid, nullrev, short
 from i18n import _
 import os, sys, errno, re, tempfile
 import util, scmutil, templater, patch, error, templatekw, revlog, copies
 import match as matchmod
-import subrepo, context, repair, graphmod, revset, phases, obsolete
+import subrepo, context, repair, graphmod, revset, phases, obsolete, pathutil
 import changelog
 import bookmarks
 import lock as lockmod
 
 def parsealiases(cmd):
     return cmd.lstrip("^").split("|")
 
 def findpossible(cmd, table, strict=False):
     """
     Return cmd -> (aliases, command table entry)
     for each matching command.
     Return debug commands (or their aliases) only if no normal command matches.
     """
     choice = {}
     debugchoice = {}
 
     if cmd in table:
         # short-circuit exact matches, "log" alias beats "^log|history"
         keys = [cmd]
     else:
         keys = table.keys()
 
     for e in keys:
         aliases = parsealiases(e)
         found = None
         if cmd in aliases:
             found = cmd
         elif not strict:
             for a in aliases:
                 if a.startswith(cmd):
                     found = a
                     break
         if found is not None:
             if aliases[0].startswith("debug") or found.startswith("debug"):
                 debugchoice[found] = (aliases, table[e])
             else:
                 choice[found] = (aliases, table[e])
 
     if not choice and debugchoice:
         choice = debugchoice
 
     return choice
 
 def findcmd(cmd, table, strict=True):
     """Return (aliases, command table entry) for command string."""
     choice = findpossible(cmd, table, strict)
 
     if cmd in choice:
         return choice[cmd]
 
     if len(choice) > 1:
         clist = choice.keys()
         clist.sort()
         raise error.AmbiguousCommand(cmd, clist)
 
     if choice:
         return choice.values()[0]
 
     raise error.UnknownCommand(cmd)
 
 def findrepo(p):
     while not os.path.isdir(os.path.join(p, ".hg")):
         oldp, p = p, os.path.dirname(p)
         if p == oldp:
             return None
 
     return p
 
 def bailifchanged(repo):
     if repo.dirstate.p2() != nullid:
         raise util.Abort(_('outstanding uncommitted merge'))
     modified, added, removed, deleted = repo.status()[:4]
     if modified or added or removed or deleted:
         raise util.Abort(_('uncommitted changes'))
     ctx = repo[None]
     for s in sorted(ctx.substate):
         if ctx.sub(s).dirty():
             raise util.Abort(_("uncommitted changes in subrepo %s") % s)
 
 def logmessage(ui, opts):
     """ get the log message according to -m and -l option """
     message = opts.get('message')
     logfile = opts.get('logfile')
 
     if message and logfile:
         raise util.Abort(_('options --message and --logfile are mutually '
                            'exclusive'))
     if not message and logfile:
         try:
             if logfile == '-':
                 message = ui.fin.read()
             else:
                 message = '\n'.join(util.readfile(logfile).splitlines())
         except IOError, inst:
             raise util.Abort(_("can't read commit message '%s': %s") %
                              (logfile, inst.strerror))
     return message
 
 def loglimit(opts):
     """get the log limit according to option -l/--limit"""
     limit = opts.get('limit')
     if limit:
         try:
             limit = int(limit)
         except ValueError:
             raise util.Abort(_('limit must be a positive integer'))
         if limit <= 0:
             raise util.Abort(_('limit must be positive'))
     else:
         limit = None
     return limit
 
 def makefilename(repo, pat, node, desc=None,
                   total=None, seqno=None, revwidth=None, pathname=None):
     node_expander = {
         'H': lambda: hex(node),
         'R': lambda: str(repo.changelog.rev(node)),
         'h': lambda: short(node),
         'm': lambda: re.sub('[^\w]', '_', str(desc))
         }
     expander = {
         '%': lambda: '%',
         'b': lambda: os.path.basename(repo.root),
         }
 
     try:
         if node:
             expander.update(node_expander)
         if node:
             expander['r'] = (lambda:
                     str(repo.changelog.rev(node)).zfill(revwidth or 0))
         if total is not None:
             expander['N'] = lambda: str(total)
         if seqno is not None:
             expander['n'] = lambda: str(seqno)
         if total is not None and seqno is not None:
             expander['n'] = lambda: str(seqno).zfill(len(str(total)))
         if pathname is not None:
             expander['s'] = lambda: os.path.basename(pathname)
             expander['d'] = lambda: os.path.dirname(pathname) or '.'
             expander['p'] = lambda: pathname
 
         newname = []
         patlen = len(pat)
         i = 0
         while i < patlen:
             c = pat[i]
             if c == '%':
                 i += 1
                 c = pat[i]
                 c = expander[c]()
             newname.append(c)
             i += 1
         return ''.join(newname)
     except KeyError, inst:
         raise util.Abort(_("invalid format spec '%%%s' in output filename") %
                          inst.args[0])
 
 def makefileobj(repo, pat, node=None, desc=None, total=None,
                 seqno=None, revwidth=None, mode='wb', modemap=None,
                 pathname=None):
 
     writable = mode not in ('r', 'rb')
 
     if not pat or pat == '-':
         fp = writable and repo.ui.fout or repo.ui.fin
         if util.safehasattr(fp, 'fileno'):
             return os.fdopen(os.dup(fp.fileno()), mode)
         else:
             # if this fp can't be duped properly, return
             # a dummy object that can be closed
             class wrappedfileobj(object):
                 noop = lambda x: None
                 def __init__(self, f):
                     self.f = f
                 def __getattr__(self, attr):
                     if attr == 'close':
                         return self.noop
                     else:
                         return getattr(self.f, attr)
 
             return wrappedfileobj(fp)
     if util.safehasattr(pat, 'write') and writable:
         return pat
     if util.safehasattr(pat, 'read') and 'r' in mode:
         return pat
     fn = makefilename(repo, pat, node, desc, total, seqno, revwidth, pathname)
     if modemap is not None:
         mode = modemap.get(fn, mode)
         if mode == 'wb':
             modemap[fn] = 'ab'
     return open(fn, mode)
 
 def openrevlog(repo, cmd, file_, opts):
     """opens the changelog, manifest, a filelog or a given revlog"""
     cl = opts['changelog']
     mf = opts['manifest']
     msg = None
     if cl and mf:
         msg = _('cannot specify --changelog and --manifest at the same time')
     elif cl or mf:
         if file_:
             msg = _('cannot specify filename with --changelog or --manifest')
         elif not repo:
             msg = _('cannot specify --changelog or --manifest '
                     'without a repository')
     if msg:
         raise util.Abort(msg)
 
     r = None
     if repo:
         if cl:
             r = repo.changelog
         elif mf:
             r = repo.manifest
         elif file_:
             filelog = repo.file(file_)
             if len(filelog):
                 r = filelog
     if not r:
         if not file_:
             raise error.CommandError(cmd, _('invalid arguments'))
         if not os.path.isfile(file_):
             raise util.Abort(_("revlog '%s' not found") % file_)
         r = revlog.revlog(scmutil.opener(os.getcwd(), audit=False),
                           file_[:-2] + ".i")
     return r
 
 def copy(ui, repo, pats, opts, rename=False):
     # called with the repo lock held
     #
     # hgsep => pathname that uses "/" to separate directories
     # ossep => pathname that uses os.sep to separate directories
     cwd = repo.getcwd()
     targets = {}
     after = opts.get("after")
     dryrun = opts.get("dry_run")
     wctx = repo[None]
 
     def walkpat(pat):
         srcs = []
         badstates = after and '?' or '?r'
         m = scmutil.match(repo[None], [pat], opts, globbed=True)
         for abs in repo.walk(m):
             state = repo.dirstate[abs]
             rel = m.rel(abs)
             exact = m.exact(abs)
             if state in badstates:
                 if exact and state == '?':
                     ui.warn(_('%s: not copying - file is not managed\n') % rel)
                 if exact and state == 'r':
                     ui.warn(_('%s: not copying - file has been marked for'
                               ' remove\n') % rel)
                 continue
             # abs: hgsep
             # rel: ossep
             srcs.append((abs, rel, exact))
         return srcs
 
     # abssrc: hgsep
     # relsrc: ossep
     # otarget: ossep
     def copyfile(abssrc, relsrc, otarget, exact):
-        abstarget = scmutil.canonpath(repo.root, cwd, otarget)
+        abstarget = pathutil.canonpath(repo.root, cwd, otarget)
         if '/' in abstarget:
             # We cannot normalize abstarget itself, this would prevent
             # case only renames, like a => A.
             abspath, absname = abstarget.rsplit('/', 1)
             abstarget = repo.dirstate.normalize(abspath) + '/' + absname
         reltarget = repo.pathto(abstarget, cwd)
         target = repo.wjoin(abstarget)
         src = repo.wjoin(abssrc)
         state = repo.dirstate[abstarget]
 
         scmutil.checkportable(ui, abstarget)
 
         # check for collisions
         prevsrc = targets.get(abstarget)
         if prevsrc is not None:
             ui.warn(_('%s: not overwriting - %s collides with %s\n') %
                     (reltarget, repo.pathto(abssrc, cwd),
                      repo.pathto(prevsrc, cwd)))
             return
 
         # check for overwrites
         exists = os.path.lexists(target)
         samefile = False
         if exists and abssrc != abstarget:
             if (repo.dirstate.normalize(abssrc) ==
                 repo.dirstate.normalize(abstarget)):
                 if not rename:
                     ui.warn(_("%s: can't copy - same file\n") % reltarget)
                     return
                 exists = False
                 samefile = True
 
         if not after and exists or after and state in 'mn':
             if not opts['force']:
                 ui.warn(_('%s: not overwriting - file exists\n') %
                         reltarget)
                 return
 
         if after:
             if not exists:
                 if rename:
                     ui.warn(_('%s: not recording move - %s does not exist\n') %
                             (relsrc, reltarget))
                 else:
                     ui.warn(_('%s: not recording copy - %s does not exist\n') %
                             (relsrc, reltarget))
                 return
         elif not dryrun:
             try:
                 if exists:
                     os.unlink(target)
                 targetdir = os.path.dirname(target) or '.'
                 if not os.path.isdir(targetdir):
                     os.makedirs(targetdir)
                 if samefile:
                     tmp = target + "~hgrename"
                     os.rename(src, tmp)
                     os.rename(tmp, target)
                 else:
                     util.copyfile(src, target)
                 srcexists = True
             except IOError, inst:
                 if inst.errno == errno.ENOENT:
                     ui.warn(_('%s: deleted in working copy\n') % relsrc)
                     srcexists = False
                 else:
                     ui.warn(_('%s: cannot copy - %s\n') %
                             (relsrc, inst.strerror))
                     return True # report a failure
 
         if ui.verbose or not exact:
             if rename:
                 ui.status(_('moving %s to %s\n') % (relsrc, reltarget))
             else:
                 ui.status(_('copying %s to %s\n') % (relsrc, reltarget))
 
         targets[abstarget] = abssrc
 
         # fix up dirstate
         scmutil.dirstatecopy(ui, repo, wctx, abssrc, abstarget,
                              dryrun=dryrun, cwd=cwd)
         if rename and not dryrun:
             if not after and srcexists and not samefile:
                 util.unlinkpath(repo.wjoin(abssrc))
             wctx.forget([abssrc])
 
     # pat: ossep
     # dest ossep
     # srcs: list of (hgsep, hgsep, ossep, bool)
     # return: function that takes hgsep and returns ossep
     def targetpathfn(pat, dest, srcs):
         if os.path.isdir(pat):
-            abspfx = scmutil.canonpath(repo.root, cwd, pat)
+            abspfx = pathutil.canonpath(repo.root, cwd, pat)
             abspfx = util.localpath(abspfx)
             if destdirexists:
                 striplen = len(os.path.split(abspfx)[0])
             else:
                 striplen = len(abspfx)
             if striplen:
                 striplen += len(os.sep)
             res = lambda p: os.path.join(dest, util.localpath(p)[striplen:])
         elif destdirexists:
             res = lambda p: os.path.join(dest,
                                          os.path.basename(util.localpath(p)))
         else:
             res = lambda p: dest
         return res
 
     # pat: ossep
     # dest ossep
     # srcs: list of (hgsep, hgsep, ossep, bool)
     # return: function that takes hgsep and returns ossep
     def targetpathafterfn(pat, dest, srcs):
         if matchmod.patkind(pat):
             # a mercurial pattern
             res = lambda p: os.path.join(dest,
                                          os.path.basename(util.localpath(p)))
         else:
-            abspfx = scmutil.canonpath(repo.root, cwd, pat)
+            abspfx = pathutil.canonpath(repo.root, cwd, pat)
             if len(abspfx) < len(srcs[0][0]):
                 # A directory. Either the target path contains the last
                 # component of the source path or it does not.
                 def evalpath(striplen):
                     score = 0
                     for s in srcs:
                         t = os.path.join(dest, util.localpath(s[0])[striplen:])
                         if os.path.lexists(t):
                             score += 1
                     return score
 
                 abspfx = util.localpath(abspfx)
                 striplen = len(abspfx)
                 if striplen:
                     striplen += len(os.sep)
                 if os.path.isdir(os.path.join(dest, os.path.split(abspfx)[1])):
                     score = evalpath(striplen)
                     striplen1 = len(os.path.split(abspfx)[0])
                     if striplen1:
                         striplen1 += len(os.sep)
                     if evalpath(striplen1) > score:
                         striplen = striplen1
                 res = lambda p: os.path.join(dest,
                                              util.localpath(p)[striplen:])
             else:
                 # a file
                 if destdirexists:
                     res = lambda p: os.path.join(dest,
                                         os.path.basename(util.localpath(p)))
                 else:
                     res = lambda p: dest
         return res
 
 
     pats = scmutil.expandpats(pats)
     if not pats:
         raise util.Abort(_('no source or destination specified'))
     if len(pats) == 1:
         raise util.Abort(_('no destination specified'))
     dest = pats.pop()
     destdirexists = os.path.isdir(dest) and not os.path.islink(dest)
     if not destdirexists:
         if len(pats) > 1 or matchmod.patkind(pats[0]):
             raise util.Abort(_('with multiple sources, destination must be an '
                                'existing directory'))
         if util.endswithsep(dest):
             raise util.Abort(_('destination %s is not a directory') % dest)
 
     tfn = targetpathfn
     if after:
         tfn = targetpathafterfn
     copylist = []
     for pat in pats:
         srcs = walkpat(pat)
         if not srcs:
             continue
         copylist.append((tfn(pat, dest, srcs), srcs))
     if not copylist:
         raise util.Abort(_('no files to copy'))
 
     errors = 0
     for targetpath, srcs in copylist:
         for abssrc, relsrc, exact in srcs:
             if copyfile(abssrc, relsrc, targetpath(abssrc), exact):
                 errors += 1
 
     if errors:
         ui.warn(_('(consider using --after)\n'))
 
     return errors != 0
 
 def service(opts, parentfn=None, initfn=None, runfn=None, logfile=None,
     runargs=None, appendpid=False):
     '''Run a command as a service.'''
 
     def writepid(pid):
         if opts['pid_file']:
             mode = appendpid and 'a' or 'w'
             fp = open(opts['pid_file'], mode)
             fp.write(str(pid) + '\n')
             fp.close()
 
     if opts['daemon'] and not opts['daemon_pipefds']:
         # Signal child process startup with file removal
         lockfd, lockpath = tempfile.mkstemp(prefix='hg-service-')
         os.close(lockfd)
         try:
             if not runargs:
                 runargs = util.hgcmd() + sys.argv[1:]
             runargs.append('--daemon-pipefds=%s' % lockpath)
             # Don't pass --cwd to the child process, because we've already
             # changed directory.
             for i in xrange(1, len(runargs)):
                 if runargs[i].startswith('--cwd='):
                     del runargs[i]
                     break
                 elif runargs[i].startswith('--cwd'):
                     del runargs[i:i + 2]
                     break
             def condfn():
                 return not os.path.exists(lockpath)
             pid = util.rundetached(runargs, condfn)
             if pid < 0:
                 raise util.Abort(_('child process failed to start'))
             writepid(pid)
         finally:
             try:
                 os.unlink(lockpath)
             except OSError, e:
                 if e.errno != errno.ENOENT:
                     raise
         if parentfn:
             return parentfn(pid)
         else:
             return
 
     if initfn:
         initfn()
 
     if not opts['daemon']:
         writepid(os.getpid())
 
     if opts['daemon_pipefds']:
         lockpath = opts['daemon_pipefds']
         try:
             os.setsid()
         except AttributeError:
             pass
         os.unlink(lockpath)
         util.hidewindow()
         sys.stdout.flush()
         sys.stderr.flush()
 
         nullfd = os.open(os.devnull, os.O_RDWR)
         logfilefd = nullfd
         if logfile:
             logfilefd = os.open(logfile, os.O_RDWR | os.O_CREAT | os.O_APPEND)
         os.dup2(nullfd, 0)
         os.dup2(logfilefd, 1)
         os.dup2(logfilefd, 2)
         if nullfd not in (0, 1, 2):
             os.close(nullfd)
         if logfile and logfilefd not in (0, 1, 2):
             os.close(logfilefd)
 
     if runfn:
         return runfn()
 
 def export(repo, revs, template='hg-%h.patch', fp=None, switch_parent=False,
            opts=None):
     '''export changesets as hg patches.'''
 
     total = len(revs)
     revwidth = max([len(str(rev)) for rev in revs])
     filemode = {}
 
     def single(rev, seqno, fp):
         ctx = repo[rev]
         node = ctx.node()
         parents = [p.node() for p in ctx.parents() if p]
         branch = ctx.branch()
         if switch_parent:
             parents.reverse()
         prev = (parents and parents[0]) or nullid
 
         shouldclose = False
         if not fp and len(template) > 0:
             desc_lines = ctx.description().rstrip().split('\n')
             desc = desc_lines[0]    #Commit always has a first line.
             fp = makefileobj(repo, template, node, desc=desc, total=total,
                              seqno=seqno, revwidth=revwidth, mode='wb',
                              modemap=filemode)
             if fp != template:
                 shouldclose = True
         if fp and fp != sys.stdout and util.safehasattr(fp, 'name'):
             repo.ui.note("%s\n" % fp.name)
 
         if not fp:
             write = repo.ui.write
         else:
             def write(s, **kw):
                 fp.write(s)
 
 
         write("# HG changeset patch\n")
         write("# User %s\n" % ctx.user())
         write("# Date %d %d\n" % ctx.date())
         write("#      %s\n" % util.datestr(ctx.date()))
         if branch and branch != 'default':
             write("# Branch %s\n" % branch)
         write("# Node ID %s\n" % hex(node))
         write("# Parent  %s\n" % hex(prev))
         if len(parents) > 1:
             write("# Parent  %s\n" % hex(parents[1]))
         write(ctx.description().rstrip())
         write("\n\n")
 
         for chunk, label in patch.diffui(repo, prev, node, opts=opts):
             write(chunk, label=label)
 
         if shouldclose:
             fp.close()
 
     for seqno, rev in enumerate(revs):
         single(rev, seqno + 1, fp)
 
 def diffordiffstat(ui, repo, diffopts, node1, node2, match,
                    changes=None, stat=False, fp=None, prefix='',
                    listsubrepos=False):
     '''show diff or diffstat.'''
     if fp is None:
         write = ui.write
     else:
         def write(s, **kw):
             fp.write(s)
 
     if stat:
         diffopts = diffopts.copy(context=0)
         width = 80
         if not ui.plain():
             width = ui.termwidth()
         chunks = patch.diff(repo, node1, node2, match, changes, diffopts,
                             prefix=prefix)
         for chunk, label in patch.diffstatui(util.iterlines(chunks),
                                              width=width,
                                              git=diffopts.git):
             write(chunk, label=label)
     else:
         for chunk, label in patch.diffui(repo, node1, node2, match,
                                          changes, diffopts, prefix=prefix):
             write(chunk, label=label)
 
     if listsubrepos:
         ctx1 = repo[node1]
         ctx2 = repo[node2]
         for subpath, sub in subrepo.itersubrepos(ctx1, ctx2):
             tempnode2 = node2
             try:
                 if node2 is not None:
                     tempnode2 = ctx2.substate[subpath][1]
             except KeyError:
                 # A subrepo that existed in node1 was deleted between node1 and
                 # node2 (inclusive). Thus, ctx2's substate won't contain that
                 # subpath. The best we can do is to ignore it.
                 tempnode2 = None
             submatch = matchmod.narrowmatcher(subpath, match)
             sub.diff(ui, diffopts, tempnode2, submatch, changes=changes,
                      stat=stat, fp=fp, prefix=prefix)
 
 class changeset_printer(object):
     '''show changeset information when templating not requested.'''
 
     def __init__(self, ui, repo, patch, diffopts, buffered):
         self.ui = ui
         self.repo = repo
         self.buffered = buffered
         self.patch = patch
         self.diffopts = diffopts
         self.header = {}
         self.hunk = {}
         self.lastheader = None
         self.footer = None
 
     def flush(self, rev):
         if rev in self.header:
             h = self.header[rev]
             if h != self.lastheader:
                 self.lastheader = h
                 self.ui.write(h)
             del self.header[rev]
         if rev in self.hunk:
             self.ui.write(self.hunk[rev])
             del self.hunk[rev]
             return 1
         return 0
 
     def close(self):
         if self.footer:
             self.ui.write(self.footer)
 
     def show(self, ctx, copies=None, matchfn=None, **props):
         if self.buffered:
             self.ui.pushbuffer()
             self._show(ctx, copies, matchfn, props)
             self.hunk[ctx.rev()] = self.ui.popbuffer(labeled=True)
         else:
             self._show(ctx, copies, matchfn, props)
 
     def _show(self, ctx, copies, matchfn, props):
         '''show a single changeset or file revision'''
         changenode = ctx.node()
         rev = ctx.rev()
 
         if self.ui.quiet:
             self.ui.write("%d:%s\n" % (rev, short(changenode)),
                           label='log.node')
             return
 
         log = self.repo.changelog
         date = util.datestr(ctx.date())
 
         hexfunc = self.ui.debugflag and hex or short
 
         parents = [(p, hexfunc(log.node(p)))
                    for p in self._meaningful_parentrevs(log, rev)]
 
         # i18n: column positioning for "hg log"
         self.ui.write(_("changeset:   %d:%s\n") % (rev, hexfunc(changenode)),
                       label='log.changeset changeset.%s' % ctx.phasestr())
 
         branch = ctx.branch()
         # don't show the default branch name
         if branch != 'default':
             # i18n: column positioning for "hg log"
             self.ui.write(_("branch:      %s\n") % branch,
                           label='log.branch')
         for bookmark in self.repo.nodebookmarks(changenode):
             # i18n: column positioning for "hg log"
             self.ui.write(_("bookmark:    %s\n") % bookmark,
                     label='log.bookmark')
         for tag in self.repo.nodetags(changenode):
             # i18n: column positioning for "hg log"
             self.ui.write(_("tag:         %s\n") % tag,
                           label='log.tag')
         if self.ui.debugflag and ctx.phase():
             # i18n: column positioning for "hg log"
             self.ui.write(_("phase:       %s\n") % _(ctx.phasestr()),
                           label='log.phase')
         for parent in parents:
             # i18n: column positioning for "hg log"
             self.ui.write(_("parent:      %d:%s\n") % parent,
                           label='log.parent changeset.%s' % ctx.phasestr())
 
         if self.ui.debugflag:
             mnode = ctx.manifestnode()
             # i18n: column positioning for "hg log"
             self.ui.write(_("manifest:    %d:%s\n") %
                           (self.repo.manifest.rev(mnode), hex(mnode)),
                           label='ui.debug log.manifest')
         # i18n: column positioning for "hg log"
         self.ui.write(_("user:        %s\n") % ctx.user(),
                       label='log.user')
         # i18n: column positioning for "hg log"
         self.ui.write(_("date:        %s\n") % date,
                       label='log.date')
 
         if self.ui.debugflag:
             files = self.repo.status(log.parents(changenode)[0], changenode)[:3]
             for key, value in zip([# i18n: column positioning for "hg log"
                                    _("files:"),
                                    # i18n: column positioning for "hg log"
                                    _("files+:"),
                                    # i18n: column positioning for "hg log"
                                    _("files-:")], files):
                 if value:
                     self.ui.write("%-12s %s\n" % (key, " ".join(value)),
                                   label='ui.debug log.files')
         elif ctx.files() and self.ui.verbose:
             # i18n: column positioning for "hg log"
             self.ui.write(_("files:       %s\n") % " ".join(ctx.files()),
                           label='ui.note log.files')
         if copies and self.ui.verbose:
             copies = ['%s (%s)' % c for c in copies]
             # i18n: column positioning for "hg log"
             self.ui.write(_("copies:      %s\n") % ' '.join(copies),
                           label='ui.note log.copies')
 
         extra = ctx.extra()
         if extra and self.ui.debugflag:
             for key, value in sorted(extra.items()):
                 # i18n: column positioning for "hg log"
                 self.ui.write(_("extra:       %s=%s\n")
                               % (key, value.encode('string_escape')),
                               label='ui.debug log.extra')
 
         description = ctx.description().strip()
         if description:
             if self.ui.verbose:
                 self.ui.write(_("description:\n"),
                               label='ui.note log.description')
                 self.ui.write(description,
                               label='ui.note log.description')
                 self.ui.write("\n\n")
             else:
                 # i18n: column positioning for "hg log"
                 self.ui.write(_("summary:     %s\n") %
                               description.splitlines()[0],
                               label='log.summary')
         self.ui.write("\n")
 
         self.showpatch(changenode, matchfn)
 
     def showpatch(self, node, matchfn):
         if not matchfn:
             matchfn = self.patch
         if matchfn:
             stat = self.diffopts.get('stat')
             diff = self.diffopts.get('patch')
             diffopts = patch.diffopts(self.ui, self.diffopts)
             prev = self.repo.changelog.parents(node)[0]
             if stat:
                 diffordiffstat(self.ui, self.repo, diffopts, prev, node,
                                match=matchfn, stat=True)
             if diff:
                 if stat:
                     self.ui.write("\n")
                 diffordiffstat(self.ui, self.repo, diffopts, prev, node,
                                match=matchfn, stat=False)
             self.ui.write("\n")
 
     def _meaningful_parentrevs(self, log, rev):
         """Return list of meaningful (or all if debug) parentrevs for rev.
 
         For merges (two non-nullrev revisions) both parents are meaningful.
         Otherwise the first parent revision is considered meaningful if it
         is not the preceding revision.
         """
         parents = log.parentrevs(rev)
         if not self.ui.debugflag and parents[1] == nullrev:
             if parents[0] >= rev - 1:
                 parents = []
             else:
                 parents = [parents[0]]
         return parents
 
 
 class changeset_templater(changeset_printer):
     '''format changeset information.'''
 
     def __init__(self, ui, repo, patch, diffopts, mapfile, buffered):
         changeset_printer.__init__(self, ui, repo, patch, diffopts, buffered)
         formatnode = ui.debugflag and (lambda x: x) or (lambda x: x[:12])
         defaulttempl = {
             'parent': '{rev}:{node|formatnode} ',
             'manifest': '{rev}:{node|formatnode}',
             'file_copy': '{name} ({source})',
             'extra': '{key}={value|stringescape}'
             }
         # filecopy is preserved for compatibility reasons
         defaulttempl['filecopy'] = defaulttempl['file_copy']
         self.t = templater.templater(mapfile, {'formatnode': formatnode},
                                      cache=defaulttempl)
         self.cache = {}
 
     def use_template(self, t):
         '''set template string to use'''
         self.t.cache['changeset'] = t
 
     def _meaningful_parentrevs(self, ctx):
         """Return list of meaningful (or all if debug) parentrevs for rev.
         """
         parents = ctx.parents()
         if len(parents) > 1:
             return parents
         if self.ui.debugflag:
             return [parents[0], self.repo['null']]
         if parents[0].rev() >= ctx.rev() - 1:
             return []
         return parents
 
     def _show(self, ctx, copies, matchfn, props):
         '''show a single changeset or file revision'''
 
         showlist = templatekw.showlist
 
         # showparents() behaviour depends on ui trace level which
         # causes unexpected behaviours at templating level and makes
         # it harder to extract it in a standalone function. Its
         # behaviour cannot be changed so leave it here for now.
         def showparents(**args):
             ctx = args['ctx']
             parents = [[('rev', p.rev()), ('node', p.hex())]
                        for p in self._meaningful_parentrevs(ctx)]
             return showlist('parent', parents, **args)
 
         props = props.copy()
         props.update(templatekw.keywords)
         props['parents'] = showparents
         props['templ'] = self.t
         props['ctx'] = ctx
         props['repo'] = self.repo
         props['revcache'] = {'copies': copies}
         props['cache'] = self.cache
 
         # find correct templates for current mode
 
         tmplmodes = [
             (True, None),
             (self.ui.verbose, 'verbose'),
             (self.ui.quiet, 'quiet'),
             (self.ui.debugflag, 'debug'),
         ]
 
         types = {'header': '', 'footer':'', 'changeset': 'changeset'}
         for mode, postfix  in tmplmodes:
             for type in types:
                 cur = postfix and ('%s_%s' % (type, postfix)) or type
                 if mode and cur in self.t:
                     types[type] = cur
 
         try:
 
             # write header
             if types['header']:
                 h = templater.stringify(self.t(types['header'], **props))
                 if self.buffered:
                     self.header[ctx.rev()] = h
                 else:
                     if self.lastheader != h:
                         self.lastheader = h
                         self.ui.write(h)
 
             # write changeset metadata, then patch if requested
             key = types['changeset']
             self.ui.write(templater.stringify(self.t(key, **props)))
             self.showpatch(ctx.node(), matchfn)
 
             if types['footer']:
                 if not self.footer:
                     self.footer = templater.stringify(self.t(types['footer'],
                                                       **props))
 
         except KeyError, inst:
             msg = _("%s: no key named '%s'")
             raise util.Abort(msg % (self.t.mapfile, inst.args[0]))
         except SyntaxError, inst:
             raise util.Abort('%s: %s' % (self.t.mapfile, inst.args[0]))
 
 def show_changeset(ui, repo, opts, buffered=False):
     """show one changeset using template or regular display.
 
     Display format will be the first non-empty hit of:
     1. option 'template'
     2. option 'style'
     3. [ui] setting 'logtemplate'
     4. [ui] setting 'style'
     If all of these values are either the unset or the empty string,
     regular display via changeset_printer() is done.
     """
     # options
     patch = None
     if opts.get('patch') or opts.get('stat'):
         patch = scmutil.matchall(repo)
 
     tmpl = opts.get('template')
     style = None
     if tmpl:
         tmpl = templater.parsestring(tmpl, quoted=False)
     else:
         style = opts.get('style')
 
     # ui settings
     if not (tmpl or style):
         tmpl = ui.config('ui', 'logtemplate')
         if tmpl:
             try:
                 tmpl = templater.parsestring(tmpl)
             except SyntaxError:
                 tmpl = templater.parsestring(tmpl, quoted=False)
         else:
             style = util.expandpath(ui.config('ui', 'style', ''))
 
     if not (tmpl or style):
         return changeset_printer(ui, repo, patch, opts, buffered)
 
     mapfile = None
     if style and not tmpl:
         mapfile = style
         if not os.path.split(mapfile)[0]:
             mapname = (templater.templatepath('map-cmdline.' + mapfile)
                        or templater.templatepath(mapfile))
             if mapname:
                 mapfile = mapname
 
     try:
         t = changeset_templater(ui, repo, patch, opts, mapfile, buffered)
     except SyntaxError, inst:
         raise util.Abort(inst.args[0])
     if tmpl:
         t.use_template(tmpl)
     return t
 
 def finddate(ui, repo, date):
     """Find the tipmost changeset that matches the given date spec"""
 
     df = util.matchdate(date)
     m = scmutil.matchall(repo)
     results = {}
 
     def prep(ctx, fns):
         d = ctx.date()
         if df(d[0]):
             results[ctx.rev()] = d
 
     for ctx in walkchangerevs(repo, m, {'rev': None}, prep):
         rev = ctx.rev()
         if rev in results:
             ui.status(_("found revision %s from %s\n") %
                       (rev, util.datestr(results[rev])))
             return str(rev)
 
     raise util.Abort(_("revision matching date not found"))
 
 def increasingwindows(start, end, windowsize=8, sizelimit=512):
     if start < end:
         while start < end:
             yield start, min(windowsize, end - start)
             start += windowsize
             if windowsize < sizelimit:
                 windowsize *= 2
     else:
         while start > end:
             yield start, min(windowsize, start - end - 1)
             start -= windowsize
             if windowsize < sizelimit:
                 windowsize *= 2
 
 class FileWalkError(Exception):
     pass
 
 def walkfilerevs(repo, match, follow, revs, fncache):
     '''Walks the file history for the matched files.
 
     Returns the changeset revs that are involved in the file history.
 
     Throws FileWalkError if the file history can't be walked using
     filelogs alone.
     '''
     wanted = set()
     copies = []
     minrev, maxrev = min(revs), max(revs)
     def filerevgen(filelog, last):
         """
         Only files, no patterns.  Check the history of each file.
 
         Examines filelog entries within minrev, maxrev linkrev range
         Returns an iterator yielding (linkrev, parentlinkrevs, copied)
         tuples in backwards order
         """
         cl_count = len(repo)
         revs = []
         for j in xrange(0, last + 1):
             linkrev = filelog.linkrev(j)
             if linkrev < minrev:
                 continue
             # only yield rev for which we have the changelog, it can
             # happen while doing "hg log" during a pull or commit
             if linkrev >= cl_count:
                 break
 
             parentlinkrevs = []
             for p in filelog.parentrevs(j):
                 if p != nullrev:
                     parentlinkrevs.append(filelog.linkrev(p))
             n = filelog.node(j)
             revs.append((linkrev, parentlinkrevs,
                          follow and filelog.renamed(n)))
 
         return reversed(revs)
     def iterfiles():
         pctx = repo['.']
         for filename in match.files():
             if follow:
                 if filename not in pctx:
                     raise util.Abort(_('cannot follow file not in parent '
                                        'revision: "%s"') % filename)
                 yield filename, pctx[filename].filenode()
             else:
                 yield filename, None
         for filename_node in copies:
             yield filename_node
 
     for file_, node in iterfiles():
         filelog = repo.file(file_)
         if not len(filelog):
             if node is None:
                 # A zero count may be a directory or deleted file, so
                 # try to find matching entries on the slow path.
                 if follow:
                     raise util.Abort(
                         _('cannot follow nonexistent file: "%s"') % file_)
                 raise FileWalkError("Cannot walk via filelog")
             else:
                 continue
 
         if node is None:
             last = len(filelog) - 1
         else:
             last = filelog.rev(node)
 
 
         # keep track of all ancestors of the file
         ancestors = set([filelog.linkrev(last)])
 
         # iterate from latest to oldest revision
         for rev, flparentlinkrevs, copied in filerevgen(filelog, last):
             if not follow:
                 if rev > maxrev:
                     continue
             else:
                 # Note that last might not be the first interesting
                 # rev to us:
                 # if the file has been changed after maxrev, we'll
                 # have linkrev(last) > maxrev, and we still need
                 # to explore the file graph
                 if rev not in ancestors:
                     continue
                 # XXX insert 1327 fix here
                 if flparentlinkrevs:
                     ancestors.update(flparentlinkrevs)
 
             fncache.setdefault(rev, []).append(file_)
             wanted.add(rev)
             if copied:
                 copies.append(copied)
 
     return wanted
 
 def walkchangerevs(repo, match, opts, prepare):
     '''Iterate over files and the revs in which they changed.
 
     Callers most commonly need to iterate backwards over the history
     in which they are interested. Doing so has awful (quadratic-looking)
     performance, so we use iterators in a "windowed" way.
 
     We walk a window of revisions in the desired order.  Within the
     window, we first walk forwards to gather data, then in the desired
     order (usually backwards) to display it.
 
     This function returns an iterator yielding contexts. Before
     yielding each context, the iterator will first call the prepare
     function on each context in the window in forward order.'''
 
     follow = opts.get('follow') or opts.get('follow_first')
 
     if opts.get('rev'):
         revs = scmutil.revrange(repo, opts.get('rev'))
     elif follow:
         revs = repo.revs('reverse(:.)')
     else:
         revs = list(repo)
         revs.reverse()
     if not revs:
         return []
     wanted = set()
     slowpath = match.anypats() or (match.files() and opts.get('removed'))
     fncache = {}
     change = repo.changectx
 
     # First step is to fill wanted, the set of revisions that we want to yield.
     # When it does not induce extra cost, we also fill fncache for revisions in
     # wanted: a cache of filenames that were changed (ctx.files()) and that
     # match the file filtering conditions.
 
     if not slowpath and not match.files():
         # No files, no patterns.  Display all revs.
         wanted = set(revs)
 
     if not slowpath and match.files():
         # We only have to read through the filelog to find wanted revisions
 
         try:
             wanted = walkfilerevs(repo, match, follow, revs, fncache)
         except FileWalkError:
             slowpath = True
 
             # We decided to fall back to the slowpath because at least one
             # of the paths was not a file. Check to see if at least one of them
             # existed in history, otherwise simply return
             for path in match.files():
                 if path == '.' or path in repo.store:
                     break
             else:
                 return []
 
     if slowpath:
         # We have to read the changelog to match filenames against
         # changed files
 
         if follow:
             raise util.Abort(_('can only follow copies/renames for explicit '
                                'filenames'))
 
         # The slow path checks files modified in every changeset.
         # This is really slow on large repos, so compute the set lazily.
         class lazywantedset(object):
             def __init__(self):
                 self.set = set()
                 self.revs = set(revs)
 
             # No need to worry about locality here because it will be accessed
             # in the same order as the increasing window below.
             def __contains__(self, value):
                 if value in self.set:
                     return True
                 elif not value in self.revs:
                     return False
                 else:
                     self.revs.discard(value)
                     ctx = change(value)
                     matches = filter(match, ctx.files())
                     if matches:
                         fncache[value] = matches
                         self.set.add(value)
                         return True
                     return False
 
             def discard(self, value):
                 self.revs.discard(value)
                 self.set.discard(value)
 
         wanted = lazywantedset()
 
     class followfilter(object):
         def __init__(self, onlyfirst=False):
             self.startrev = nullrev
             self.roots = set()
             self.onlyfirst = onlyfirst
 
         def match(self, rev):
             def realparents(rev):
                 if self.onlyfirst:
                     return repo.changelog.parentrevs(rev)[0:1]
                 else:
                     return filter(lambda x: x != nullrev,
                                   repo.changelog.parentrevs(rev))
 
             if self.startrev == nullrev:
                 self.startrev = rev
                 return True
 
             if rev > self.startrev:
                 # forward: all descendants
                 if not self.roots:
                     self.roots.add(self.startrev)
                 for parent in realparents(rev):
                     if parent in self.roots:
                         self.roots.add(rev)
                         return True
             else:
                 # backwards: all parents
                 if not self.roots:
                     self.roots.update(realparents(self.startrev))
                 if rev in self.roots:
                     self.roots.remove(rev)
                     self.roots.update(realparents(rev))
                     return True
 
             return False
 
     # it might be worthwhile to do this in the iterator if the rev range
     # is descending and the prune args are all within that range
     for rev in opts.get('prune', ()):
         rev = repo[rev].rev()
         ff = followfilter()
         stop = min(revs[0], revs[-1])
         for x in xrange(rev, stop - 1, -1):
             if ff.match(x):
                 wanted.discard(x)
 
     # Choose a small initial window if we will probably only visit a
     # few commits.
     limit = loglimit(opts)
     windowsize = 8
     if limit:
         windowsize = min(limit, windowsize)
 
     # Now that wanted is correctly initialized, we can iterate over the
     # revision range, yielding only revisions in wanted.
     def iterate():
         if follow and not match.files():
             ff = followfilter(onlyfirst=opts.get('follow_first'))
             def want(rev):
                 return ff.match(rev) and rev in wanted
         else:
             def want(rev):
                 return rev in wanted
 
         for i, window in increasingwindows(0, len(revs), windowsize):
             nrevs = [rev for rev in revs[i:i + window] if want(rev)]
             for rev in sorted(nrevs):
                 fns = fncache.get(rev)
                 ctx = change(rev)
                 if not fns:
                     def fns_generator():
                         for f in ctx.files():
                             if match(f):
                                 yield f
                     fns = fns_generator()
                 prepare(ctx, fns)
             for rev in nrevs:
                 yield change(rev)
     return iterate()
 
 def _makegraphfilematcher(repo, pats, followfirst):
     # When displaying a revision with --patch --follow FILE, we have
     # to know which file of the revision must be diffed. With
     # --follow, we want the names of the ancestors of FILE in the
     # revision, stored in "fcache". "fcache" is populated by
     # reproducing the graph traversal already done by --follow revset
     # and relating linkrevs to file names (which is not "correct" but
     # good enough).
     fcache = {}
     fcacheready = [False]
     pctx = repo['.']
     wctx = repo[None]
 
     def populate():
         for fn in pats:
             for i in ((pctx[fn],), pctx[fn].ancestors(followfirst=followfirst)):
                 for c in i:
                     fcache.setdefault(c.linkrev(), set()).add(c.path())
 
     def filematcher(rev):
         if not fcacheready[0]:
             # Lazy initialization
             fcacheready[0] = True
             populate()
         return scmutil.match(wctx, fcache.get(rev, []), default='path')
 
     return filematcher
 
 def _makegraphlogrevset(repo, pats, opts, revs):
     """Return (expr, filematcher) where expr is a revset string built
     from log options and file patterns or None. If --stat or --patch
     are not passed filematcher is None. Otherwise it is a callable
     taking a revision number and returning a match objects filtering
     the files to be detailed when displaying the revision.
     """
     opt2revset = {
         'no_merges':        ('not merge()', None),
         'only_merges':      ('merge()', None),
         '_ancestors':       ('ancestors(%(val)s)', None),
         '_fancestors':      ('_firstancestors(%(val)s)', None),
         '_descendants':     ('descendants(%(val)s)', None),
         '_fdescendants':    ('_firstdescendants(%(val)s)', None),
         '_matchfiles':      ('_matchfiles(%(val)s)', None),
         'date':             ('date(%(val)r)', None),
         'branch':           ('branch(%(val)r)', ' or '),
         '_patslog':         ('filelog(%(val)r)', ' or '),
         '_patsfollow':      ('follow(%(val)r)', ' or '),
         '_patsfollowfirst': ('_followfirst(%(val)r)', ' or '),
         'keyword':          ('keyword(%(val)r)', ' or '),
         'prune':            ('not (%(val)r or ancestors(%(val)r))', ' and '),
         'user':             ('user(%(val)r)', ' or '),
         }
 
     opts = dict(opts)
     # follow or not follow?
     follow = opts.get('follow') or opts.get('follow_first')
     followfirst = opts.get('follow_first') and 1 or 0
     # --follow with FILE behaviour depends on revs...
     startrev = revs[0]
     followdescendants = (len(revs) > 1 and revs[0] < revs[1]) and 1 or 0
 
     # branch and only_branch are really aliases and must be handled at
     # the same time
     opts['branch'] = opts.get('branch', []) + opts.get('only_branch', [])
     opts['branch'] = [repo.lookupbranch(b) for b in opts['branch']]
     # pats/include/exclude are passed to match.match() directly in
     # _matchfiles() revset but walkchangerevs() builds its matcher with
     # scmutil.match(). The difference is input pats are globbed on
     # platforms without shell expansion (windows).
     pctx = repo[None]
     match, pats = scmutil.matchandpats(pctx, pats, opts)
     slowpath = match.anypats() or (match.files() and opts.get('removed'))
     if not slowpath:
         for f in match.files():
             if follow and f not in pctx:
                 raise util.Abort(_('cannot follow file not in parent '
                                    'revision: "%s"') % f)
             filelog = repo.file(f)
             if not filelog:
                 # A zero count may be a directory or deleted file, so
                 # try to find matching entries on the slow path.
                 if follow:
                     raise util.Abort(
                         _('cannot follow nonexistent file: "%s"') % f)
                 slowpath = True
 
         # We decided to fall back to the slowpath because at least one
         # of the paths was not a file. Check to see if at least one of them
         # existed in history - in that case, we'll continue down the
         # slowpath; otherwise, we can turn off the slowpath
         if slowpath:
             for path in match.files():
                 if path == '.' or path in repo.store:
                     break
             else:
                 slowpath = False
 
     if slowpath:
         # See walkchangerevs() slow path.
         #
         if follow:
             raise util.Abort(_('can only follow copies/renames for explicit '
                                'filenames'))
         # pats/include/exclude cannot be represented as separate
         # revset expressions as their filtering logic applies at file
         # level. For instance "-I a -X a" matches a revision touching
         # "a" and "b" while "file(a) and not file(b)" does
         # not. Besides, filesets are evaluated against the working
         # directory.
         matchargs = ['r:', 'd:relpath']
         for p in pats:
             matchargs.append('p:' + p)
         for p in opts.get('include', []):
             matchargs.append('i:' + p)
         for p in opts.get('exclude', []):
             matchargs.append('x:' + p)
         matchargs = ','.join(('%r' % p) for p in matchargs)
         opts['_matchfiles'] = matchargs
     else:
         if follow:
             fpats = ('_patsfollow', '_patsfollowfirst')
             fnopats = (('_ancestors', '_fancestors'),
                        ('_descendants', '_fdescendants'))
             if pats:
                 # follow() revset interprets its file argument as a
                 # manifest entry, so use match.files(), not pats.
                 opts[fpats[followfirst]] = list(match.files())
             else:
                 opts[fnopats[followdescendants][followfirst]] = str(startrev)
         else:
             opts['_patslog'] = list(pats)
 
     filematcher = None
     if opts.get('patch') or opts.get('stat'):
         if follow:
             filematcher = _makegraphfilematcher(repo, pats, followfirst)
         else:
             filematcher = lambda rev: match
 
     expr = []
     for op, val in opts.iteritems():
         if not val:
             continue
         if op not in opt2revset:
             continue
         revop, andor = opt2revset[op]
         if '%(val)' not in revop:
             expr.append(revop)
         else:
             if not isinstance(val, list):
                 e = revop % {'val': val}
             else:
                 e = '(' + andor.join((revop % {'val': v}) for v in val) + ')'
             expr.append(e)
 
     if expr:
         expr = '(' + ' and '.join(expr) + ')'
     else:
         expr = None
     return expr, filematcher
 
 def getgraphlogrevs(repo, pats, opts):
     """Return (revs, expr, filematcher) where revs is an iterable of
     revision numbers, expr is a revset string built from log options
     and file patterns or None, and used to filter 'revs'. If --stat or
     --patch are not passed filematcher is None. Otherwise it is a
     callable taking a revision number and returning a match objects
     filtering the files to be detailed when displaying the revision.
     """
     if not len(repo):
         return [], None, None
     limit = loglimit(opts)
     # Default --rev value depends on --follow but --follow behaviour
     # depends on revisions resolved from --rev...
     follow = opts.get('follow') or opts.get('follow_first')
     possiblyunsorted = False # whether revs might need sorting
     if opts.get('rev'):
         revs = scmutil.revrange(repo, opts['rev'])
         # Don't sort here because _makegraphlogrevset might depend on the
         # order of revs
         possiblyunsorted = True
     else:
         if follow and len(repo) > 0:
             revs = repo.revs('reverse(:.)')
         else:
             revs = list(repo.changelog)
             revs.reverse()
     if not revs:
         return [], None, None
     expr, filematcher = _makegraphlogrevset(repo, pats, opts, revs)
     if possiblyunsorted:
         revs.sort(reverse=True)
     if expr:
         # Revset matchers often operate faster on revisions in changelog
         # order, because most filters deal with the changelog.
         revs.reverse()
         matcher = revset.match(repo.ui, expr)
         # Revset matches can reorder revisions. "A or B" typically returns
         # returns the revision matching A then the revision matching B. Sort
         # again to fix that.
         revs = matcher(repo, revs)
         revs.sort(reverse=True)
     if limit is not None:
         revs = revs[:limit]
 
     return revs, expr, filematcher
 
 def displaygraph(ui, dag, displayer, showparents, edgefn, getrenamed=None,
                  filematcher=None):
     seen, state = [], graphmod.asciistate()
     for rev, type, ctx, parents in dag:
         char = 'o'
         if ctx.node() in showparents:
             char = '@'
         elif ctx.obsolete():
             char = 'x'
         copies = None
         if getrenamed and ctx.rev():
             copies = []
             for fn in ctx.files():
                 rename = getrenamed(fn, ctx.rev())
                 if rename:
                     copies.append((fn, rename[0]))
         revmatchfn = None
         if filematcher is not None:
             revmatchfn = filematcher(ctx.rev())
         displayer.show(ctx, copies=copies, matchfn=revmatchfn)
         lines = displayer.hunk.pop(rev).split('\n')
         if not lines[-1]:
             del lines[-1]
         displayer.flush(rev)
         edges = edgefn(type, char, lines, seen, rev, parents)
         for type, char, lines, coldata in edges:
             graphmod.ascii(ui, state, type, char, lines, coldata)
     displayer.close()
 
 def graphlog(ui, repo, *pats, **opts):
     # Parameters are identical to log command ones
     revs, expr, filematcher = getgraphlogrevs(repo, pats, opts)
     revdag = graphmod.dagwalker(repo, revs)
 
     getrenamed = None
     if opts.get('copies'):
         endrev = None
         if opts.get('rev'):
             endrev = max(scmutil.revrange(repo, opts.get('rev'))) + 1
         getrenamed = templatekw.getrenamedfn(repo, endrev=endrev)
     displayer = show_changeset(ui, repo, opts, buffered=True)
     showparents = [ctx.node() for ctx in repo[None].parents()]
     displaygraph(ui, revdag, displayer, showparents,
                  graphmod.asciiedges, getrenamed, filematcher)
 
 def checkunsupportedgraphflags(pats, opts):
     for op in ["newest_first"]:
         if op in opts and opts[op]:
             raise util.Abort(_("-G/--graph option is incompatible with --%s")
                              % op.replace("_", "-"))
 
 def graphrevs(repo, nodes, opts):
     limit = loglimit(opts)
     nodes.reverse()
     if limit is not None:
         nodes = nodes[:limit]
     return graphmod.nodes(repo, nodes)
 
 def add(ui, repo, match, dryrun, listsubrepos, prefix, explicitonly):
     join = lambda f: os.path.join(prefix, f)
     bad = []
     oldbad = match.bad
     match.bad = lambda x, y: bad.append(x) or oldbad(x, y)
     names = []
     wctx = repo[None]
     cca = None
     abort, warn = scmutil.checkportabilityalert(ui)
     if abort or warn:
         cca = scmutil.casecollisionauditor(ui, abort, repo.dirstate)
     for f in repo.walk(match):
         exact = match.exact(f)
         if exact or not explicitonly and f not in repo.dirstate:
             if cca:
                 cca(f)
             names.append(f)
             if ui.verbose or not exact:
                 ui.status(_('adding %s\n') % match.rel(join(f)))
 
     for subpath in sorted(wctx.substate):
         sub = wctx.sub(subpath)
         try:
             submatch = matchmod.narrowmatcher(subpath, match)
             if listsubrepos:
                 bad.extend(sub.add(ui, submatch, dryrun, listsubrepos, prefix,
                                    False))
             else:
                 bad.extend(sub.add(ui, submatch, dryrun, listsubrepos, prefix,
                                    True))
         except error.LookupError:
             ui.status(_("skipping missing subrepository: %s\n")
                            % join(subpath))
 
     if not dryrun:
         rejected = wctx.add(names, prefix)
         bad.extend(f for f in rejected if f in match.files())
     return bad
 
 def forget(ui, repo, match, prefix, explicitonly):
     join = lambda f: os.path.join(prefix, f)
     bad = []
     oldbad = match.bad
     match.bad = lambda x, y: bad.append(x) or oldbad(x, y)
     wctx = repo[None]
     forgot = []
     s = repo.status(match=match, clean=True)
     forget = sorted(s[0] + s[1] + s[3] + s[6])
     if explicitonly:
         forget = [f for f in forget if match.exact(f)]
 
     for subpath in sorted(wctx.substate):
         sub = wctx.sub(subpath)
         try:
             submatch = matchmod.narrowmatcher(subpath, match)
             subbad, subforgot = sub.forget(ui, submatch, prefix)
             bad.extend([subpath + '/' + f for f in subbad])
             forgot.extend([subpath + '/' + f for f in subforgot])
         except error.LookupError:
             ui.status(_("skipping missing subrepository: %s\n")
                            % join(subpath))
 
     if not explicitonly:
         for f in match.files():
             if f not in repo.dirstate and not os.path.isdir(match.rel(join(f))):
                 if f not in forgot:
                     if os.path.exists(match.rel(join(f))):
                         ui.warn(_('not removing %s: '
                                   'file is already untracked\n')
                                 % match.rel(join(f)))
                     bad.append(f)
 
     for f in forget:
         if ui.verbose or not match.exact(f):
             ui.status(_('removing %s\n') % match.rel(join(f)))
 
     rejected = wctx.forget(forget, prefix)
     bad.extend(f for f in rejected if f in match.files())
     forgot.extend(forget)
     return bad, forgot
 
 def duplicatecopies(repo, rev, fromrev):
     '''reproduce copies from fromrev to rev in the dirstate'''
     for dst, src in copies.pathcopies(repo[fromrev], repo[rev]).iteritems():
         # copies.pathcopies returns backward renames, so dst might not
         # actually be in the dirstate
         if repo.dirstate[dst] in "nma":
             repo.dirstate.copy(src, dst)
 
 def commit(ui, repo, commitfunc, pats, opts):
     '''commit the specified files or all outstanding changes'''
     date = opts.get('date')
     if date:
         opts['date'] = util.parsedate(date)
     message = logmessage(ui, opts)
 
     # extract addremove carefully -- this function can be called from a command
     # that doesn't support addremove
     if opts.get('addremove'):
         scmutil.addremove(repo, pats, opts)
 
     return commitfunc(ui, repo, message,
                       scmutil.match(repo[None], pats, opts), opts)
 
 def amend(ui, repo, commitfunc, old, extra, pats, opts):
     ui.note(_('amending changeset %s\n') % old)
     base = old.p1()
 
     wlock = lock = newid = None
     try:
         wlock = repo.wlock()
         lock = repo.lock()
         tr = repo.transaction('amend')
         try:
             # See if we got a message from -m or -l, if not, open the editor
             # with the message of the changeset to amend
             message = logmessage(ui, opts)
             # ensure logfile does not conflict with later enforcement of the
             # message. potential logfile content has been processed by
             # `logmessage` anyway.
             opts.pop('logfile')
             # First, do a regular commit to record all changes in the working
             # directory (if there are any)
             ui.callhooks = False
             currentbookmark = repo._bookmarkcurrent
             try:
                 repo._bookmarkcurrent = None
                 opts['message'] = 'temporary amend commit for %s' % old
                 node = commit(ui, repo, commitfunc, pats, opts)
             finally:
                 repo._bookmarkcurrent = currentbookmark
                 ui.callhooks = True
             ctx = repo[node]
 
             # Participating changesets:
             #
             # node/ctx o - new (intermediate) commit that contains changes
             #          |   from working dir to go into amending commit
             #          |   (or a workingctx if there were no changes)
             #          |
             # old      o - changeset to amend
             #          |
             # base     o - parent of amending changeset
 
             # Update extra dict from amended commit (e.g. to preserve graft
             # source)
             extra.update(old.extra())
 
             # Also update it from the intermediate commit or from the wctx
             extra.update(ctx.extra())
 
             if len(old.parents()) > 1:
                 # ctx.files() isn't reliable for merges, so fall back to the
                 # slower repo.status() method
                 files = set([fn for st in repo.status(base, old)[:3]
                              for fn in st])
             else:
                 files = set(old.files())
 
             # Second, we use either the commit we just did, or if there were no
             # changes the parent of the working directory as the version of the
             # files in the final amend commit
             if node:
                 ui.note(_('copying changeset %s to %s\n') % (ctx, base))
 
                 user = ctx.user()
                 date = ctx.date()
                 # Recompute copies (avoid recording a -> b -> a)
                 copied = copies.pathcopies(base, ctx)
 
                 # Prune files which were reverted by the updates: if old
                 # introduced file X and our intermediate commit, node,
                 # renamed that file, then those two files are the same and
                 # we can discard X from our list of files. Likewise if X
                 # was deleted, it's no longer relevant
                 files.update(ctx.files())
 
                 def samefile(f):
                     if f in ctx.manifest():
                         a = ctx.filectx(f)
                         if f in base.manifest():
                             b = base.filectx(f)
                             return (not a.cmp(b)
                                     and a.flags() == b.flags())
                         else:
                             return False
                     else:
                         return f not in base.manifest()
                 files = [f for f in files if not samefile(f)]
 
                 def filectxfn(repo, ctx_, path):
                     try:
                         fctx = ctx[path]
                         flags = fctx.flags()
                         mctx = context.memfilectx(fctx.path(), fctx.data(),
                                                   islink='l' in flags,
                                                   isexec='x' in flags,
                                                   copied=copied.get(path))
                         return mctx
                     except KeyError:
                         raise IOError
             else:
                 ui.note(_('copying changeset %s to %s\n') % (old, base))
 
                 # Use version of files as in the old cset
                 def filectxfn(repo, ctx_, path):
                     try:
                         return old.filectx(path)
                     except KeyError:
                         raise IOError
 
                 user = opts.get('user') or old.user()
                 date = opts.get('date') or old.date()
             editmsg = False
             if not message:
                 editmsg = True
                 message = old.description()
 
             pureextra = extra.copy()
             extra['amend_source'] = old.hex()
 
             new = context.memctx(repo,
                                  parents=[base.node(), old.p2().node()],
                                  text=message,
                                  files=files,
                                  filectxfn=filectxfn,
                                  user=user,
                                  date=date,
                                  extra=extra)
             if editmsg:
                 new._text = commitforceeditor(repo, new, [])
 
             newdesc =  changelog.stripdesc(new.description())
             if ((not node)
                 and newdesc == old.description()
                 and user == old.user()
                 and date == old.date()
                 and pureextra == old.extra()):
                 # nothing changed. continuing here would create a new node
                 # anyway because of the amend_source noise.
                 #
                 # This not what we expect from amend.
                 return old.node()
 
             ph = repo.ui.config('phases', 'new-commit', phases.draft)
             try:
                 repo.ui.setconfig('phases', 'new-commit', old.phase())
                 newid = repo.commitctx(new)
             finally:
                 repo.ui.setconfig('phases', 'new-commit', ph)
             if newid != old.node():
                 # Reroute the working copy parent to the new changeset
                 repo.setparents(newid, nullid)
 
                 # Move bookmarks from old parent to amend commit
                 bms = repo.nodebookmarks(old.node())
                 if bms:
                     marks = repo._bookmarks
                     for bm in bms:
                         marks[bm] = newid
                     marks.write()
             #commit the whole amend process
             if obsolete._enabled and newid != old.node():
                 # mark the new changeset as successor of the rewritten one
                 new = repo[newid]
                 obs = [(old, (new,))]
                 if node:
                     obs.append((ctx, ()))
 
                 obsolete.createmarkers(repo, obs)
             tr.close()
         finally:
             tr.release()
         if (not obsolete._enabled) and newid != old.node():
             # Strip the intermediate commit (if there was one) and the amended
             # commit
             if node:
                 ui.note(_('stripping intermediate changeset %s\n') % ctx)
             ui.note(_('stripping amended changeset %s\n') % old)
             repair.strip(ui, repo, old.node(), topic='amend-backup')
     finally:
         if newid is None:
             repo.dirstate.invalidate()
         lockmod.release(lock, wlock)
     return newid
 
 def commiteditor(repo, ctx, subs):
     if ctx.description():
         return ctx.description()
     return commitforceeditor(repo, ctx, subs)
 
 def commitforceeditor(repo, ctx, subs):
     edittext = []
     modified, added, removed = ctx.modified(), ctx.added(), ctx.removed()
     if ctx.description():
         edittext.append(ctx.description())
     edittext.append("")
     edittext.append("") # Empty line between message and comments.
     edittext.append(_("HG: Enter commit message."
                       "  Lines beginning with 'HG:' are removed."))
     edittext.append(_("HG: Leave message empty to abort commit."))
     edittext.append("HG: --")
     edittext.append(_("HG: user: %s") % ctx.user())
     if ctx.p2():
         edittext.append(_("HG: branch merge"))
     if ctx.branch():
         edittext.append(_("HG: branch '%s'") % ctx.branch())
     if bookmarks.iscurrent(repo):
         edittext.append(_("HG: bookmark '%s'") % repo._bookmarkcurrent)
     edittext.extend([_("HG: subrepo %s") % s for s in subs])
     edittext.extend([_("HG: added %s") % f for f in added])
     edittext.extend([_("HG: changed %s") % f for f in modified])
     edittext.extend([_("HG: removed %s") % f for f in removed])
     if not added and not modified and not removed:
         edittext.append(_("HG: no files changed"))
     edittext.append("")
     # run editor in the repository root
     olddir = os.getcwd()
     os.chdir(repo.root)
     text = repo.ui.edit("\n".join(edittext), ctx.user())
     text = re.sub("(?m)^HG:.*(\n|$)", "", text)
     os.chdir(olddir)
 
     if not text.strip():
         raise util.Abort(_("empty commit message"))
 
     return text
 
 def commitstatus(repo, node, branch, bheads=None, opts={}):
     ctx = repo[node]
     parents = ctx.parents()
 
     if (not opts.get('amend') and bheads and node not in bheads and not
         [x for x in parents if x.node() in bheads and x.branch() == branch]):
         repo.ui.status(_('created new head\n'))
         # The message is not printed for initial roots. For the other
         # changesets, it is printed in the following situations:
         #
         # Par column: for the 2 parents with ...
         #   N: null or no parent
         #   B: parent is on another named branch
         #   C: parent is a regular non head changeset
         #   H: parent was a branch head of the current branch
         # Msg column: whether we print "created new head" message
         # In the following, it is assumed that there already exists some
         # initial branch heads of the current branch, otherwise nothing is
         # printed anyway.
         #
         # Par Msg Comment
         # N N  y  additional topo root
         #
         # B N  y  additional branch root
         # C N  y  additional topo head
         # H N  n  usual case
         #
         # B B  y  weird additional branch root
         # C B  y  branch merge
         # H B  n  merge with named branch
         #
         # C C  y  additional head from merge
         # C H  n  merge with a head
         #
         # H H  n  head merge: head count decreases
 
     if not opts.get('close_branch'):
         for r in parents:
             if r.closesbranch() and r.branch() == branch:
                 repo.ui.status(_('reopening closed branch head %d\n') % r)
 
     if repo.ui.debugflag:
         repo.ui.write(_('committed changeset %d:%s\n') % (int(ctx), ctx.hex()))
     elif repo.ui.verbose:
         repo.ui.write(_('committed changeset %d:%s\n') % (int(ctx), ctx))
 
 def revert(ui, repo, ctx, parents, *pats, **opts):
     parent, p2 = parents
     node = ctx.node()
 
     mf = ctx.manifest()
     if node == parent:
         pmf = mf
     else:
         pmf = None
 
     # need all matching names in dirstate and manifest of target rev,
     # so have to walk both. do not print errors if files exist in one
     # but not other.
 
     names = {}
 
     wlock = repo.wlock()
     try:
         # walk dirstate.
 
         m = scmutil.match(repo[None], pats, opts)
         m.bad = lambda x, y: False
         for abs in repo.walk(m):
             names[abs] = m.rel(abs), m.exact(abs)
 
         # walk target manifest.
 
         def badfn(path, msg):
             if path in names:
                 return
             if path in ctx.substate:
                 return
             path_ = path + '/'
             for f in names:
                 if f.startswith(path_):
                     return
             ui.warn("%s: %s\n" % (m.rel(path), msg))
 
         m = scmutil.match(ctx, pats, opts)
         m.bad = badfn
         for abs in ctx.walk(m):
             if abs not in names:
                 names[abs] = m.rel(abs), m.exact(abs)
 
         # get the list of subrepos that must be reverted
         targetsubs = sorted(s for s in ctx.substate if m(s))
         m = scmutil.matchfiles(repo, names)
         changes = repo.status(match=m)[:4]
         modified, added, removed, deleted = map(set, changes)
 
         # if f is a rename, also revert the source
         cwd = repo.getcwd()
         for f in added:
             src = repo.dirstate.copied(f)
             if src and src not in names and repo.dirstate[src] == 'r':
                 removed.add(src)
                 names[src] = (repo.pathto(src, cwd), True)
 
         def removeforget(abs):
             if repo.dirstate[abs] == 'a':
                 return _('forgetting %s\n')
             return _('removing %s\n')
 
         revert = ([], _('reverting %s\n'))
         add = ([], _('adding %s\n'))
         remove = ([], removeforget)
         undelete = ([], _('undeleting %s\n'))
 
         disptable = (
             # dispatch table:
             #   file state
             #   action if in target manifest
             #   action if not in target manifest
             #   make backup if in target manifest
             #   make backup if not in target manifest
             (modified, revert, remove, True, True),
             (added, revert, remove, True, False),
             (removed, undelete, None, True, False),
             (deleted, revert, remove, False, False),
             )
 
         for abs, (rel, exact) in sorted(names.items()):
             mfentry = mf.get(abs)
             target = repo.wjoin(abs)
             def handle(xlist, dobackup):
                 xlist[0].append(abs)
                 if (dobackup and not opts.get('no_backup') and
                     os.path.lexists(target) and
                     abs in ctx and repo[None][abs].cmp(ctx[abs])):
                     bakname = "%s.orig" % rel
                     ui.note(_('saving current version of %s as %s\n') %
                             (rel, bakname))
                     if not opts.get('dry_run'):
                         util.rename(target, bakname)
                 if ui.verbose or not exact:
                     msg = xlist[1]
                     if not isinstance(msg, basestring):
                         msg = msg(abs)
                     ui.status(msg % rel)
             for table, hitlist, misslist, backuphit, backupmiss in disptable:
                 if abs not in table:
                     continue
                 # file has changed in dirstate
                 if mfentry:
                     handle(hitlist, backuphit)
                 elif misslist is not None:
                     handle(misslist, backupmiss)
                 break
             else:
                 if abs not in repo.dirstate:
                     if mfentry:
                         handle(add, True)
                     elif exact:
                         ui.warn(_('file not managed: %s\n') % rel)
                     continue
                 # file has not changed in dirstate
                 if node == parent:
                     if exact:
                         ui.warn(_('no changes needed to %s\n') % rel)
                     continue
                 if pmf is None:
                     # only need parent manifest in this unlikely case,
                     # so do not read by default
                     pmf = repo[parent].manifest()
                 if abs in pmf and mfentry:
                     # if version of file is same in parent and target
                     # manifests, do nothing
                     if (pmf[abs] != mfentry or
                         pmf.flags(abs) != mf.flags(abs)):
                         handle(revert, False)
                 else:
                     handle(remove, False)
 
         if not opts.get('dry_run'):
             def checkout(f):
                 fc = ctx[f]
                 repo.wwrite(f, fc.data(), fc.flags())
 
-            audit_path = scmutil.pathauditor(repo.root)
+            audit_path = pathutil.pathauditor(repo.root)
             for f in remove[0]:
                 if repo.dirstate[f] == 'a':
                     repo.dirstate.drop(f)
                     continue
                 audit_path(f)
                 try:
                     util.unlinkpath(repo.wjoin(f))
                 except OSError:
                     pass
                 repo.dirstate.remove(f)
 
             normal = None
             if node == parent:
                 # We're reverting to our parent. If possible, we'd like status
                 # to report the file as clean. We have to use normallookup for
                 # merges to avoid losing information about merged/dirty files.
                 if p2 != nullid:
                     normal = repo.dirstate.normallookup
                 else:
                     normal = repo.dirstate.normal
             for f in revert[0]:
                 checkout(f)
                 if normal:
                     normal(f)
 
             for f in add[0]:
                 checkout(f)
                 repo.dirstate.add(f)
 
             normal = repo.dirstate.normallookup
             if node == parent and p2 == nullid:
                 normal = repo.dirstate.normal
             for f in undelete[0]:
                 checkout(f)
                 normal(f)
 
             copied = copies.pathcopies(repo[parent], ctx)
 
             for f in add[0] + undelete[0] + revert[0]:
                 if f in copied:
                     repo.dirstate.copy(copied[f], f)
 
             if targetsubs:
                 # Revert the subrepos on the revert list
                 for sub in targetsubs:
                     ctx.sub(sub).revert(ui, ctx.substate[sub], *pats, **opts)
     finally:
         wlock.release()
 
 def command(table):
     '''returns a function object bound to table which can be used as
     a decorator for populating table as a command table'''
 
     def cmd(name, options=(), synopsis=None):
         def decorator(func):
             if synopsis:
                 table[name] = func, list(options), synopsis
             else:
                 table[name] = func, list(options)
             return func
         return decorator
 
     return cmd
 
 # a list of (ui, repo) functions called by commands.summary
 summaryhooks = util.hooks()
 
 # A list of state files kept by multistep operations like graft.
 # Since graft cannot be aborted, it is considered 'clearable' by update.
 # note: bisect is intentionally excluded
 # (state file, clearable, allowcommit, error, hint)
 unfinishedstates = [
     ('graftstate', True, False, _('graft in progress'),
      _("use 'hg graft --continue' or 'hg update' to abort")),
     ('updatestate', True, False, _('last update was interrupted'),
      _("use 'hg update' to get a consistent checkout"))
     ]
 
 def checkunfinished(repo, commit=False):
     '''Look for an unfinished multistep operation, like graft, and abort
     if found. It's probably good to check this right before
     bailifchanged().
     '''
     for f, clearable, allowcommit, msg, hint in unfinishedstates:
         if commit and allowcommit:
             continue
         if repo.vfs.exists(f):
             raise util.Abort(msg, hint=hint)
 
 def clearunfinished(repo):
     '''Check for unfinished operations (as above), and clear the ones
     that are clearable.
     '''
     for f, clearable, allowcommit, msg, hint in unfinishedstates:
         if not clearable and repo.vfs.exists(f):
             raise util.Abort(msg, hint=hint)
     for f, clearable, allowcommit, msg, hint in unfinishedstates:
         if clearable and repo.vfs.exists(f):
             util.unlink(repo.join(f))

mercurial/dirstate.py

@@ -1,852 +1,852 b''
 # dirstate.py - working directory tracking for mercurial
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 import errno
 
 from node import nullid
 from i18n import _
-import scmutil, util, ignore, osutil, parsers, encoding
+import scmutil, util, ignore, osutil, parsers, encoding, pathutil
 import os, stat, errno, gc
 
 propertycache = util.propertycache
 filecache = scmutil.filecache
 _rangemask = 0x7fffffff
 
 class repocache(filecache):
     """filecache for files in .hg/"""
     def join(self, obj, fname):
         return obj._opener.join(fname)
 
 class rootcache(filecache):
     """filecache for files in the repository root"""
     def join(self, obj, fname):
         return obj._join(fname)
 
 class dirstate(object):
 
     def __init__(self, opener, ui, root, validate):
         '''Create a new dirstate object.
 
         opener is an open()-like callable that can be used to open the
         dirstate file; root is the root of the directory tracked by
         the dirstate.
         '''
         self._opener = opener
         self._validate = validate
         self._root = root
         self._rootdir = os.path.join(root, '')
         self._dirty = False
         self._dirtypl = False
         self._lastnormaltime = 0
         self._ui = ui
         self._filecache = {}
 
     @propertycache
     def _map(self):
         '''Return the dirstate contents as a map from filename to
         (state, mode, size, time).'''
         self._read()
         return self._map
 
     @propertycache
     def _copymap(self):
         self._read()
         return self._copymap
 
     @propertycache
     def _foldmap(self):
         f = {}
         for name, s in self._map.iteritems():
             if s[0] != 'r':
                 f[util.normcase(name)] = name
         for name in self._dirs:
             f[util.normcase(name)] = name
         f['.'] = '.' # prevents useless util.fspath() invocation
         return f
 
     @repocache('branch')
     def _branch(self):
         try:
             return self._opener.read("branch").strip() or "default"
         except IOError, inst:
             if inst.errno != errno.ENOENT:
                 raise
             return "default"
 
     @propertycache
     def _pl(self):
         try:
             fp = self._opener("dirstate")
             st = fp.read(40)
             fp.close()
             l = len(st)
             if l == 40:
                 return st[:20], st[20:40]
             elif l > 0 and l < 40:
                 raise util.Abort(_('working directory state appears damaged!'))
         except IOError, err:
             if err.errno != errno.ENOENT:
                 raise
         return [nullid, nullid]
 
     @propertycache
     def _dirs(self):
         return scmutil.dirs(self._map, 'r')
 
     def dirs(self):
         return self._dirs
 
     @rootcache('.hgignore')
     def _ignore(self):
         files = [self._join('.hgignore')]
         for name, path in self._ui.configitems("ui"):
             if name == 'ignore' or name.startswith('ignore.'):
                 files.append(util.expandpath(path))
         return ignore.ignore(self._root, files, self._ui.warn)
 
     @propertycache
     def _slash(self):
         return self._ui.configbool('ui', 'slash') and os.sep != '/'
 
     @propertycache
     def _checklink(self):
         return util.checklink(self._root)
 
     @propertycache
     def _checkexec(self):
         return util.checkexec(self._root)
 
     @propertycache
     def _checkcase(self):
         return not util.checkcase(self._join('.hg'))
 
     def _join(self, f):
         # much faster than os.path.join()
         # it's safe because f is always a relative path
         return self._rootdir + f
 
     def flagfunc(self, buildfallback):
         if self._checklink and self._checkexec:
             def f(x):
                 try:
                     st = os.lstat(self._join(x))
                     if util.statislink(st):
                         return 'l'
                     if util.statisexec(st):
                         return 'x'
                 except OSError:
                     pass
                 return ''
             return f
 
         fallback = buildfallback()
         if self._checklink:
             def f(x):
                 if os.path.islink(self._join(x)):
                     return 'l'
                 if 'x' in fallback(x):
                     return 'x'
                 return ''
             return f
         if self._checkexec:
             def f(x):
                 if 'l' in fallback(x):
                     return 'l'
                 if util.isexec(self._join(x)):
                     return 'x'
                 return ''
             return f
         else:
             return fallback
 
     def getcwd(self):
         cwd = os.getcwd()
         if cwd == self._root:
             return ''
         # self._root ends with a path separator if self._root is '/' or 'C:\'
         rootsep = self._root
         if not util.endswithsep(rootsep):
             rootsep += os.sep
         if cwd.startswith(rootsep):
             return cwd[len(rootsep):]
         else:
             # we're outside the repo. return an absolute path.
             return cwd
 
     def pathto(self, f, cwd=None):
         if cwd is None:
             cwd = self.getcwd()
         path = util.pathto(self._root, cwd, f)
         if self._slash:
             return util.pconvert(path)
         return path
 
     def __getitem__(self, key):
         '''Return the current state of key (a filename) in the dirstate.
 
         States are:
           n  normal
           m  needs merging
           r  marked for removal
           a  marked for addition
           ?  not tracked
         '''
         return self._map.get(key, ("?",))[0]
 
     def __contains__(self, key):
         return key in self._map
 
     def __iter__(self):
         for x in sorted(self._map):
             yield x
 
     def iteritems(self):
         return self._map.iteritems()
 
     def parents(self):
         return [self._validate(p) for p in self._pl]
 
     def p1(self):
         return self._validate(self._pl[0])
 
     def p2(self):
         return self._validate(self._pl[1])
 
     def branch(self):
         return encoding.tolocal(self._branch)
 
     def setparents(self, p1, p2=nullid):
         """Set dirstate parents to p1 and p2.
 
         When moving from two parents to one, 'm' merged entries a
         adjusted to normal and previous copy records discarded and
         returned by the call.
 
         See localrepo.setparents()
         """
         self._dirty = self._dirtypl = True
         oldp2 = self._pl[1]
         self._pl = p1, p2
         copies = {}
         if oldp2 != nullid and p2 == nullid:
             # Discard 'm' markers when moving away from a merge state
             for f, s in self._map.iteritems():
                 if s[0] == 'm':
                     if f in self._copymap:
                         copies[f] = self._copymap[f]
                     self.normallookup(f)
         return copies
 
     def setbranch(self, branch):
         self._branch = encoding.fromlocal(branch)
         f = self._opener('branch', 'w', atomictemp=True)
         try:
             f.write(self._branch + '\n')
             f.close()
 
             # make sure filecache has the correct stat info for _branch after
             # replacing the underlying file
             ce = self._filecache['_branch']
             if ce:
                 ce.refresh()
         except: # re-raises
             f.discard()
             raise
 
     def _read(self):
         self._map = {}
         self._copymap = {}
         try:
             st = self._opener.read("dirstate")
         except IOError, err:
             if err.errno != errno.ENOENT:
                 raise
             return
         if not st:
             return
 
         # Python's garbage collector triggers a GC each time a certain number
         # of container objects (the number being defined by
         # gc.get_threshold()) are allocated. parse_dirstate creates a tuple
         # for each file in the dirstate. The C version then immediately marks
         # them as not to be tracked by the collector. However, this has no
         # effect on when GCs are triggered, only on what objects the GC looks
         # into. This means that O(number of files) GCs are unavoidable.
         # Depending on when in the process's lifetime the dirstate is parsed,
         # this can get very expensive. As a workaround, disable GC while
         # parsing the dirstate.
         gcenabled = gc.isenabled()
         gc.disable()
         try:
             p = parsers.parse_dirstate(self._map, self._copymap, st)
         finally:
             if gcenabled:
                 gc.enable()
         if not self._dirtypl:
             self._pl = p
 
     def invalidate(self):
         for a in ("_map", "_copymap", "_foldmap", "_branch", "_pl", "_dirs",
                 "_ignore"):
             if a in self.__dict__:
                 delattr(self, a)
         self._lastnormaltime = 0
         self._dirty = False
 
     def copy(self, source, dest):
         """Mark dest as a copy of source. Unmark dest if source is None."""
         if source == dest:
             return
         self._dirty = True
         if source is not None:
             self._copymap[dest] = source
         elif dest in self._copymap:
             del self._copymap[dest]
 
     def copied(self, file):
         return self._copymap.get(file, None)
 
     def copies(self):
         return self._copymap
 
     def _droppath(self, f):
         if self[f] not in "?r" and "_dirs" in self.__dict__:
             self._dirs.delpath(f)
 
     def _addpath(self, f, state, mode, size, mtime):
         oldstate = self[f]
         if state == 'a' or oldstate == 'r':
             scmutil.checkfilename(f)
             if f in self._dirs:
                 raise util.Abort(_('directory %r already in dirstate') % f)
             # shadows
             for d in scmutil.finddirs(f):
                 if d in self._dirs:
                     break
                 if d in self._map and self[d] != 'r':
                     raise util.Abort(
                         _('file %r in dirstate clashes with %r') % (d, f))
         if oldstate in "?r" and "_dirs" in self.__dict__:
             self._dirs.addpath(f)
         self._dirty = True
         self._map[f] = (state, mode, size, mtime)
 
     def normal(self, f):
         '''Mark a file normal and clean.'''
         s = os.lstat(self._join(f))
         mtime = int(s.st_mtime)
         self._addpath(f, 'n', s.st_mode,
                       s.st_size & _rangemask, mtime & _rangemask)
         if f in self._copymap:
             del self._copymap[f]
         if mtime > self._lastnormaltime:
             # Remember the most recent modification timeslot for status(),
             # to make sure we won't miss future size-preserving file content
             # modifications that happen within the same timeslot.
             self._lastnormaltime = mtime
 
     def normallookup(self, f):
         '''Mark a file normal, but possibly dirty.'''
         if self._pl[1] != nullid and f in self._map:
             # if there is a merge going on and the file was either
             # in state 'm' (-1) or coming from other parent (-2) before
             # being removed, restore that state.
             entry = self._map[f]
             if entry[0] == 'r' and entry[2] in (-1, -2):
                 source = self._copymap.get(f)
                 if entry[2] == -1:
                     self.merge(f)
                 elif entry[2] == -2:
                     self.otherparent(f)
                 if source:
                     self.copy(source, f)
                 return
             if entry[0] == 'm' or entry[0] == 'n' and entry[2] == -2:
                 return
         self._addpath(f, 'n', 0, -1, -1)
         if f in self._copymap:
             del self._copymap[f]
 
     def otherparent(self, f):
         '''Mark as coming from the other parent, always dirty.'''
         if self._pl[1] == nullid:
             raise util.Abort(_("setting %r to other parent "
                                "only allowed in merges") % f)
         self._addpath(f, 'n', 0, -2, -1)
         if f in self._copymap:
             del self._copymap[f]
 
     def add(self, f):
         '''Mark a file added.'''
         self._addpath(f, 'a', 0, -1, -1)
         if f in self._copymap:
             del self._copymap[f]
 
     def remove(self, f):
         '''Mark a file removed.'''
         self._dirty = True
         self._droppath(f)
         size = 0
         if self._pl[1] != nullid and f in self._map:
             # backup the previous state
             entry = self._map[f]
             if entry[0] == 'm': # merge
                 size = -1
             elif entry[0] == 'n' and entry[2] == -2: # other parent
                 size = -2
         self._map[f] = ('r', 0, size, 0)
         if size == 0 and f in self._copymap:
             del self._copymap[f]
 
     def merge(self, f):
         '''Mark a file merged.'''
         if self._pl[1] == nullid:
             return self.normallookup(f)
         s = os.lstat(self._join(f))
         self._addpath(f, 'm', s.st_mode,
                       s.st_size & _rangemask, int(s.st_mtime) & _rangemask)
         if f in self._copymap:
             del self._copymap[f]
 
     def drop(self, f):
         '''Drop a file from the dirstate'''
         if f in self._map:
             self._dirty = True
             self._droppath(f)
             del self._map[f]
 
     def _normalize(self, path, isknown, ignoremissing=False, exists=None):
         normed = util.normcase(path)
         folded = self._foldmap.get(normed, None)
         if folded is None:
             if isknown:
                 folded = path
             else:
                 if exists is None:
                     exists = os.path.lexists(os.path.join(self._root, path))
                 if not exists:
                     # Maybe a path component exists
                     if not ignoremissing and '/' in path:
                         d, f = path.rsplit('/', 1)
                         d = self._normalize(d, isknown, ignoremissing, None)
                         folded = d + "/" + f
                     else:
                         # No path components, preserve original case
                         folded = path
                 else:
                     # recursively normalize leading directory components
                     # against dirstate
                     if '/' in normed:
                         d, f = normed.rsplit('/', 1)
                         d = self._normalize(d, isknown, ignoremissing, True)
                         r = self._root + "/" + d
                         folded = d + "/" + util.fspath(f, r)
                     else:
                         folded = util.fspath(normed, self._root)
                     self._foldmap[normed] = folded
 
         return folded
 
     def normalize(self, path, isknown=False, ignoremissing=False):
         '''
         normalize the case of a pathname when on a casefolding filesystem
 
         isknown specifies whether the filename came from walking the
         disk, to avoid extra filesystem access.
 
         If ignoremissing is True, missing path are returned
         unchanged. Otherwise, we try harder to normalize possibly
         existing path components.
 
         The normalized case is determined based on the following precedence:
 
         - version of name already stored in the dirstate
         - version of name stored on disk
         - version provided via command arguments
         '''
 
         if self._checkcase:
             return self._normalize(path, isknown, ignoremissing)
         return path
 
     def clear(self):
         self._map = {}
         if "_dirs" in self.__dict__:
             delattr(self, "_dirs")
         self._copymap = {}
         self._pl = [nullid, nullid]
         self._lastnormaltime = 0
         self._dirty = True
 
     def rebuild(self, parent, allfiles, changedfiles=None):
         changedfiles = changedfiles or allfiles
         oldmap = self._map
         self.clear()
         for f in allfiles:
             if f not in changedfiles:
                 self._map[f] = oldmap[f]
             else:
                 if 'x' in allfiles.flags(f):
                     self._map[f] = ('n', 0777, -1, 0)
                 else:
                     self._map[f] = ('n', 0666, -1, 0)
         self._pl = (parent, nullid)
         self._dirty = True
 
     def write(self):
         if not self._dirty:
             return
         st = self._opener("dirstate", "w", atomictemp=True)
 
         def finish(s):
             st.write(s)
             st.close()
             self._lastnormaltime = 0
             self._dirty = self._dirtypl = False
 
         # use the modification time of the newly created temporary file as the
         # filesystem's notion of 'now'
         now = util.fstat(st).st_mtime
         finish(parsers.pack_dirstate(self._map, self._copymap, self._pl, now))
 
     def _dirignore(self, f):
         if f == '.':
             return False
         if self._ignore(f):
             return True
         for p in scmutil.finddirs(f):
             if self._ignore(p):
                 return True
         return False
 
     def _walkexplicit(self, match, subrepos):
         '''Get stat data about the files explicitly specified by match.
 
         Return a triple (results, dirsfound, dirsnotfound).
         - results is a mapping from filename to stat result. It also contains
           listings mapping subrepos and .hg to None.
         - dirsfound is a list of files found to be directories.
         - dirsnotfound is a list of files that the dirstate thinks are
           directories and that were not found.'''
 
         def badtype(mode):
             kind = _('unknown')
             if stat.S_ISCHR(mode):
                 kind = _('character device')
             elif stat.S_ISBLK(mode):
                 kind = _('block device')
             elif stat.S_ISFIFO(mode):
                 kind = _('fifo')
             elif stat.S_ISSOCK(mode):
                 kind = _('socket')
             elif stat.S_ISDIR(mode):
                 kind = _('directory')
             return _('unsupported file type (type is %s)') % kind
 
         matchedir = match.explicitdir
         badfn = match.bad
         dmap = self._map
         normpath = util.normpath
         lstat = os.lstat
         getkind = stat.S_IFMT
         dirkind = stat.S_IFDIR
         regkind = stat.S_IFREG
         lnkkind = stat.S_IFLNK
         join = self._join
         dirsfound = []
         foundadd = dirsfound.append
         dirsnotfound = []
         notfoundadd = dirsnotfound.append
 
         if match.matchfn != match.exact and self._checkcase:
             normalize = self._normalize
         else:
             normalize = None
 
         files = sorted(match.files())
         subrepos.sort()
         i, j = 0, 0
         while i < len(files) and j < len(subrepos):
             subpath = subrepos[j] + "/"
             if files[i] < subpath:
                 i += 1
                 continue
             while i < len(files) and files[i].startswith(subpath):
                 del files[i]
             j += 1
 
         if not files or '.' in files:
             files = ['']
         results = dict.fromkeys(subrepos)
         results['.hg'] = None
 
         for ff in files:
             if normalize:
                 nf = normalize(normpath(ff), False, True)
             else:
                 nf = normpath(ff)
             if nf in results:
                 continue
 
             try:
                 st = lstat(join(nf))
                 kind = getkind(st.st_mode)
                 if kind == dirkind:
                     if nf in dmap:
                         #file deleted on disk but still in dirstate
                         results[nf] = None
                     if matchedir:
                         matchedir(nf)
                     foundadd(nf)
                 elif kind == regkind or kind == lnkkind:
                     results[nf] = st
                 else:
                     badfn(ff, badtype(kind))
                     if nf in dmap:
                         results[nf] = None
             except OSError, inst:
                 if nf in dmap: # does it exactly match a file?
                     results[nf] = None
                 else: # does it match a directory?
                     prefix = nf + "/"
                     for fn in dmap:
                         if fn.startswith(prefix):
                             if matchedir:
                                 matchedir(nf)
                             notfoundadd(nf)
                             break
                     else:
                         badfn(ff, inst.strerror)
 
         return results, dirsfound, dirsnotfound
 
     def walk(self, match, subrepos, unknown, ignored, full=True):
         '''
         Walk recursively through the directory tree, finding all files
         matched by match.
 
         If full is False, maybe skip some known-clean files.
 
         Return a dict mapping filename to stat-like object (either
         mercurial.osutil.stat instance or return value of os.stat()).
 
         '''
         # full is a flag that extensions that hook into walk can use -- this
         # implementation doesn't use it at all. This satisfies the contract
         # because we only guarantee a "maybe".
 
         def fwarn(f, msg):
             self._ui.warn('%s: %s\n' % (self.pathto(f), msg))
             return False
 
         ignore = self._ignore
         dirignore = self._dirignore
         if ignored:
             ignore = util.never
             dirignore = util.never
         elif not unknown:
             # if unknown and ignored are False, skip step 2
             ignore = util.always
             dirignore = util.always
 
         matchfn = match.matchfn
         matchalways = match.always()
         matchtdir = match.traversedir
         dmap = self._map
         listdir = osutil.listdir
         lstat = os.lstat
         dirkind = stat.S_IFDIR
         regkind = stat.S_IFREG
         lnkkind = stat.S_IFLNK
         join = self._join
 
         exact = skipstep3 = False
         if matchfn == match.exact: # match.exact
             exact = True
             dirignore = util.always # skip step 2
         elif match.files() and not match.anypats(): # match.match, no patterns
             skipstep3 = True
 
         if not exact and self._checkcase:
             normalize = self._normalize
             skipstep3 = False
         else:
             normalize = None
 
         # step 1: find all explicit files
         results, work, dirsnotfound = self._walkexplicit(match, subrepos)
 
         skipstep3 = skipstep3 and not (work or dirsnotfound)
         work = [d for d in work if not dirignore(d)]
         wadd = work.append
 
         # step 2: visit subdirectories
         while work:
             nd = work.pop()
             skip = None
             if nd == '.':
                 nd = ''
             else:
                 skip = '.hg'
             try:
                 entries = listdir(join(nd), stat=True, skip=skip)
             except OSError, inst:
                 if inst.errno in (errno.EACCES, errno.ENOENT):
                     fwarn(nd, inst.strerror)
                     continue
                 raise
             for f, kind, st in entries:
                 if normalize:
                     nf = normalize(nd and (nd + "/" + f) or f, True, True)
                 else:
                     nf = nd and (nd + "/" + f) or f
                 if nf not in results:
                     if kind == dirkind:
                         if not ignore(nf):
                             if matchtdir:
                                 matchtdir(nf)
                             wadd(nf)
                         if nf in dmap and (matchalways or matchfn(nf)):
                             results[nf] = None
                     elif kind == regkind or kind == lnkkind:
                         if nf in dmap:
                             if matchalways or matchfn(nf):
                                 results[nf] = st
                         elif (matchalways or matchfn(nf)) and not ignore(nf):
                             results[nf] = st
                     elif nf in dmap and (matchalways or matchfn(nf)):
                         results[nf] = None
 
         for s in subrepos:
             del results[s]
         del results['.hg']
 
         # step 3: report unseen items in the dmap hash
         if not skipstep3 and not exact:
             if not results and matchalways:
                 visit = dmap.keys()
             else:
                 visit = [f for f in dmap if f not in results and matchfn(f)]
             visit.sort()
 
             if unknown:
                 # unknown == True means we walked the full directory tree above.
                 # So if a file is not seen it was either a) not matching matchfn
                 # b) ignored, c) missing, or d) under a symlink directory.
-                audit_path = scmutil.pathauditor(self._root)
+                audit_path = pathutil.pathauditor(self._root)
 
                 for nf in iter(visit):
                     # Report ignored items in the dmap as long as they are not
                     # under a symlink directory.
                     if audit_path.check(nf):
                         try:
                             results[nf] = lstat(join(nf))
                         except OSError:
                             # file doesn't exist
                             results[nf] = None
                     else:
                         # It's either missing or under a symlink directory
                         results[nf] = None
             else:
                 # We may not have walked the full directory tree above,
                 # so stat everything we missed.
                 nf = iter(visit).next
                 for st in util.statfiles([join(i) for i in visit]):
                     results[nf()] = st
         return results
 
     def status(self, match, subrepos, ignored, clean, unknown):
         '''Determine the status of the working copy relative to the
         dirstate and return a tuple of lists (unsure, modified, added,
         removed, deleted, unknown, ignored, clean), where:
 
           unsure:
             files that might have been modified since the dirstate was
             written, but need to be read to be sure (size is the same
             but mtime differs)
           modified:
             files that have definitely been modified since the dirstate
             was written (different size or mode)
           added:
             files that have been explicitly added with hg add
           removed:
             files that have been explicitly removed with hg remove
           deleted:
             files that have been deleted through other means ("missing")
           unknown:
             files not in the dirstate that are not ignored
           ignored:
             files not in the dirstate that are ignored
             (by _dirignore())
           clean:
             files that have definitely not been modified since the
             dirstate was written
         '''
         listignored, listclean, listunknown = ignored, clean, unknown
         lookup, modified, added, unknown, ignored = [], [], [], [], []
         removed, deleted, clean = [], [], []
 
         dmap = self._map
         ladd = lookup.append            # aka "unsure"
         madd = modified.append
         aadd = added.append
         uadd = unknown.append
         iadd = ignored.append
         radd = removed.append
         dadd = deleted.append
         cadd = clean.append
         mexact = match.exact
         dirignore = self._dirignore
         checkexec = self._checkexec
         copymap = self._copymap
         lastnormaltime = self._lastnormaltime
 
         # We need to do full walks when either
         # - we're listing all clean files, or
         # - match.traversedir does something, because match.traversedir should
         #   be called for every dir in the working dir
         full = listclean or match.traversedir is not None
         for fn, st in self.walk(match, subrepos, listunknown, listignored,
                                 full=full).iteritems():
             if fn not in dmap:
                 if (listignored or mexact(fn)) and dirignore(fn):
                     if listignored:
                         iadd(fn)
                 else:
                     uadd(fn)
                 continue
 
             state, mode, size, time = dmap[fn]
 
             if not st and state in "nma":
                 dadd(fn)
             elif state == 'n':
                 mtime = int(st.st_mtime)
                 if (size >= 0 and
                     ((size != st.st_size and size != st.st_size & _rangemask)
                      or ((mode ^ st.st_mode) & 0100 and checkexec))
                     or size == -2 # other parent
                     or fn in copymap):
                     madd(fn)
                 elif time != mtime and time != mtime & _rangemask:
                     ladd(fn)
                 elif mtime == lastnormaltime:
                     # fn may have been changed in the same timeslot without
                     # changing its size. This can happen if we quickly do
                     # multiple commits in a single transaction.
                     # Force lookup, so we don't miss such a racy file change.
                     ladd(fn)
                 elif listclean:
                     cadd(fn)
             elif state == 'm':
                 madd(fn)
             elif state == 'a':
                 aadd(fn)
             elif state == 'r':
                 radd(fn)
 
         return (lookup, modified, added, removed, deleted, unknown, ignored,
                 clean)

mercurial/hgweb/webutil.py

@@ -1,408 +1,408 b''
 # hgweb/webutil.py - utility library for the web interface.
 #
 # Copyright 21 May 2005 - (c) 2005 Jake Edge <[e-mail]>
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 import os, copy
-from mercurial import match, patch, scmutil, error, ui, util
+from mercurial import match, patch, error, ui, util, pathutil
 from mercurial.i18n import _
 from mercurial.node import hex, nullid
 from common import ErrorResponse
 from common import HTTP_NOT_FOUND
 import difflib
 
 def up(p):
     if p[0] != "/":
         p = "/" + p
     if p[-1] == "/":
         p = p[:-1]
     up = os.path.dirname(p)
     if up == "/":
         return "/"
     return up + "/"
 
 def _navseq(step, firststep=None):
     if firststep:
         yield firststep
         if firststep >= 20 and firststep <= 40:
             firststep = 50
             yield firststep
         assert step > 0
         assert firststep > 0
         while step <= firststep:
             step *= 10
     while True:
         yield 1 * step
         yield 3 * step
         step *= 10
 
 class revnav(object):
 
     def __init__(self, repo):
         """Navigation generation object
 
         :repo: repo object we generate nav for
         """
         # used for hex generation
         self._revlog = repo.changelog
 
     def __nonzero__(self):
         """return True if any revision to navigate over"""
         return self._first() is not None
 
     def _first(self):
         """return the minimum non-filtered changeset or None"""
         try:
             return iter(self._revlog).next()
         except StopIteration:
             return None
 
     def hex(self, rev):
         return hex(self._revlog.node(rev))
 
     def gen(self, pos, pagelen, limit):
         """computes label and revision id for navigation link
 
         :pos: is the revision relative to which we generate navigation.
         :pagelen: the size of each navigation page
         :limit: how far shall we link
 
         The return is:
             - a single element tuple
             - containing a dictionary with a `before` and `after` key
             - values are generator functions taking arbitrary number of kwargs
             - yield items are dictionaries with `label` and `node` keys
         """
         if not self:
             # empty repo
             return ({'before': (), 'after': ()},)
 
         targets = []
         for f in _navseq(1, pagelen):
             if f > limit:
                 break
             targets.append(pos + f)
             targets.append(pos - f)
         targets.sort()
 
         first = self._first()
         navbefore = [("(%i)" % first, self.hex(first))]
         navafter = []
         for rev in targets:
             if rev not in self._revlog:
                 continue
             if pos < rev < limit:
                 navafter.append(("+%d" % abs(rev - pos), self.hex(rev)))
             if 0 < rev < pos:
                 navbefore.append(("-%d" % abs(rev - pos), self.hex(rev)))
 
 
         navafter.append(("tip", "tip"))
 
         data = lambda i: {"label": i[0], "node": i[1]}
         return ({'before': lambda **map: (data(i) for i in navbefore),
                  'after':  lambda **map: (data(i) for i in navafter)},)
 
 class filerevnav(revnav):
 
     def __init__(self, repo, path):
         """Navigation generation object
 
         :repo: repo object we generate nav for
         :path: path of the file we generate nav for
         """
         # used for iteration
         self._changelog = repo.unfiltered().changelog
         # used for hex generation
         self._revlog = repo.file(path)
 
     def hex(self, rev):
         return hex(self._changelog.node(self._revlog.linkrev(rev)))
 
 
 def _siblings(siblings=[], hiderev=None):
     siblings = [s for s in siblings if s.node() != nullid]
     if len(siblings) == 1 and siblings[0].rev() == hiderev:
         return
     for s in siblings:
         d = {'node': s.hex(), 'rev': s.rev()}
         d['user'] = s.user()
         d['date'] = s.date()
         d['description'] = s.description()
         d['branch'] = s.branch()
         if util.safehasattr(s, 'path'):
             d['file'] = s.path()
         yield d
 
 def parents(ctx, hide=None):
     return _siblings(ctx.parents(), hide)
 
 def children(ctx, hide=None):
     return _siblings(ctx.children(), hide)
 
 def renamelink(fctx):
     r = fctx.renamed()
     if r:
         return [dict(file=r[0], node=hex(r[1]))]
     return []
 
 def nodetagsdict(repo, node):
     return [{"name": i} for i in repo.nodetags(node)]
 
 def nodebookmarksdict(repo, node):
     return [{"name": i} for i in repo.nodebookmarks(node)]
 
 def nodebranchdict(repo, ctx):
     branches = []
     branch = ctx.branch()
     # If this is an empty repo, ctx.node() == nullid,
     # ctx.branch() == 'default'.
     try:
         branchnode = repo.branchtip(branch)
     except error.RepoLookupError:
         branchnode = None
     if branchnode == ctx.node():
         branches.append({"name": branch})
     return branches
 
 def nodeinbranch(repo, ctx):
     branches = []
     branch = ctx.branch()
     try:
         branchnode = repo.branchtip(branch)
     except error.RepoLookupError:
         branchnode = None
     if branch != 'default' and branchnode != ctx.node():
         branches.append({"name": branch})
     return branches
 
 def nodebranchnodefault(ctx):
     branches = []
     branch = ctx.branch()
     if branch != 'default':
         branches.append({"name": branch})
     return branches
 
 def showtag(repo, tmpl, t1, node=nullid, **args):
     for t in repo.nodetags(node):
         yield tmpl(t1, tag=t, **args)
 
 def showbookmark(repo, tmpl, t1, node=nullid, **args):
     for t in repo.nodebookmarks(node):
         yield tmpl(t1, bookmark=t, **args)
 
 def cleanpath(repo, path):
     path = path.lstrip('/')
-    return scmutil.canonpath(repo.root, '', path)
+    return pathutil.canonpath(repo.root, '', path)
 
 def changeidctx (repo, changeid):
     try:
         ctx = repo[changeid]
     except error.RepoError:
         man = repo.manifest
         ctx = repo[man.linkrev(man.rev(man.lookup(changeid)))]
 
     return ctx
 
 def changectx (repo, req):
     changeid = "tip"
     if 'node' in req.form:
         changeid = req.form['node'][0]
         ipos=changeid.find(':')
         if ipos != -1:
             changeid = changeid[(ipos + 1):]
     elif 'manifest' in req.form:
         changeid = req.form['manifest'][0]
 
     return changeidctx(repo, changeid)
 
 def basechangectx(repo, req):
     if 'node' in req.form:
         changeid = req.form['node'][0]
         ipos=changeid.find(':')
         if ipos != -1:
             changeid = changeid[:ipos]
             return changeidctx(repo, changeid)
 
     return None
 
 def filectx(repo, req):
     if 'file' not in req.form:
         raise ErrorResponse(HTTP_NOT_FOUND, 'file not given')
     path = cleanpath(repo, req.form['file'][0])
     if 'node' in req.form:
         changeid = req.form['node'][0]
     elif 'filenode' in req.form:
         changeid = req.form['filenode'][0]
     else:
         raise ErrorResponse(HTTP_NOT_FOUND, 'node or filenode not given')
     try:
         fctx = repo[changeid][path]
     except error.RepoError:
         fctx = repo.filectx(path, fileid=changeid)
 
     return fctx
 
 def listfilediffs(tmpl, files, node, max):
     for f in files[:max]:
         yield tmpl('filedifflink', node=hex(node), file=f)
     if len(files) > max:
         yield tmpl('fileellipses')
 
 def diffs(repo, tmpl, ctx, basectx, files, parity, style):
 
     def countgen():
         start = 1
         while True:
             yield start
             start += 1
 
     blockcount = countgen()
     def prettyprintlines(diff, blockno):
         for lineno, l in enumerate(diff.splitlines(True)):
             lineno = "%d.%d" % (blockno, lineno + 1)
             if l.startswith('+'):
                 ltype = "difflineplus"
             elif l.startswith('-'):
                 ltype = "difflineminus"
             elif l.startswith('@'):
                 ltype = "difflineat"
             else:
                 ltype = "diffline"
             yield tmpl(ltype,
                        line=l,
                        lineid="l%s" % lineno,
                        linenumber="% 8s" % lineno)
 
     if files:
         m = match.exact(repo.root, repo.getcwd(), files)
     else:
         m = match.always(repo.root, repo.getcwd())
 
     diffopts = patch.diffopts(repo.ui, untrusted=True)
     if basectx is None:
         parents = ctx.parents()
         node1 = parents and parents[0].node() or nullid
     else:
         node1 = basectx.node()
     node2 = ctx.node()
 
     block = []
     for chunk in patch.diff(repo, node1, node2, m, opts=diffopts):
         if chunk.startswith('diff') and block:
             blockno = blockcount.next()
             yield tmpl('diffblock', parity=parity.next(), blockno=blockno,
                        lines=prettyprintlines(''.join(block), blockno))
             block = []
         if chunk.startswith('diff') and style != 'raw':
             chunk = ''.join(chunk.splitlines(True)[1:])
         block.append(chunk)
     blockno = blockcount.next()
     yield tmpl('diffblock', parity=parity.next(), blockno=blockno,
                lines=prettyprintlines(''.join(block), blockno))
 
 def compare(tmpl, context, leftlines, rightlines):
     '''Generator function that provides side-by-side comparison data.'''
 
     def compline(type, leftlineno, leftline, rightlineno, rightline):
         lineid = leftlineno and ("l%s" % leftlineno) or ''
         lineid += rightlineno and ("r%s" % rightlineno) or ''
         return tmpl('comparisonline',
                     type=type,
                     lineid=lineid,
                     leftlinenumber="% 6s" % (leftlineno or ''),
                     leftline=leftline or '',
                     rightlinenumber="% 6s" % (rightlineno or ''),
                     rightline=rightline or '')
 
     def getblock(opcodes):
         for type, llo, lhi, rlo, rhi in opcodes:
             len1 = lhi - llo
             len2 = rhi - rlo
             count = min(len1, len2)
             for i in xrange(count):
                 yield compline(type=type,
                                leftlineno=llo + i + 1,
                                leftline=leftlines[llo + i],
                                rightlineno=rlo + i + 1,
                                rightline=rightlines[rlo + i])
             if len1 > len2:
                 for i in xrange(llo + count, lhi):
                     yield compline(type=type,
                                    leftlineno=i + 1,
                                    leftline=leftlines[i],
                                    rightlineno=None,
                                    rightline=None)
             elif len2 > len1:
                 for i in xrange(rlo + count, rhi):
                     yield compline(type=type,
                                    leftlineno=None,
                                    leftline=None,
                                    rightlineno=i + 1,
                                    rightline=rightlines[i])
 
     s = difflib.SequenceMatcher(None, leftlines, rightlines)
     if context < 0:
         yield tmpl('comparisonblock', lines=getblock(s.get_opcodes()))
     else:
         for oc in s.get_grouped_opcodes(n=context):
             yield tmpl('comparisonblock', lines=getblock(oc))
 
 def diffstatgen(ctx, basectx):
     '''Generator function that provides the diffstat data.'''
 
     stats = patch.diffstatdata(util.iterlines(ctx.diff(basectx)))
     maxname, maxtotal, addtotal, removetotal, binary = patch.diffstatsum(stats)
     while True:
         yield stats, maxname, maxtotal, addtotal, removetotal, binary
 
 def diffsummary(statgen):
     '''Return a short summary of the diff.'''
 
     stats, maxname, maxtotal, addtotal, removetotal, binary = statgen.next()
     return _(' %d files changed, %d insertions(+), %d deletions(-)\n') % (
              len(stats), addtotal, removetotal)
 
 def diffstat(tmpl, ctx, statgen, parity):
     '''Return a diffstat template for each file in the diff.'''
 
     stats, maxname, maxtotal, addtotal, removetotal, binary = statgen.next()
     files = ctx.files()
 
     def pct(i):
         if maxtotal == 0:
             return 0
         return (float(i) / maxtotal) * 100
 
     fileno = 0
     for filename, adds, removes, isbinary in stats:
         template = filename in files and 'diffstatlink' or 'diffstatnolink'
         total = adds + removes
         fileno += 1
         yield tmpl(template, node=ctx.hex(), file=filename, fileno=fileno,
                    total=total, addpct=pct(adds), removepct=pct(removes),
                    parity=parity.next())
 
 class sessionvars(object):
     def __init__(self, vars, start='?'):
         self.start = start
         self.vars = vars
     def __getitem__(self, key):
         return self.vars[key]
     def __setitem__(self, key, value):
         self.vars[key] = value
     def __copy__(self):
         return sessionvars(copy.copy(self.vars), self.start)
     def __iter__(self):
         separator = self.start
         for key, value in sorted(self.vars.iteritems()):
             yield {'name': key, 'value': str(value), 'separator': separator}
             separator = '&'
 
 class wsgiui(ui.ui):
     # default termwidth breaks under mod_wsgi
     def termwidth(self):
         return 80

mercurial/localrepo.py

@@ -1,2461 +1,2461 b''
 # localrepo.py - read/write repository class for mercurial
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 from node import hex, nullid, short
 from i18n import _
 import peer, changegroup, subrepo, discovery, pushkey, obsolete, repoview
 import changelog, dirstate, filelog, manifest, context, bookmarks, phases
 import lock, transaction, store, encoding
 import scmutil, util, extensions, hook, error, revset
 import match as matchmod
 import merge as mergemod
 import tags as tagsmod
 from lock import release
 import weakref, errno, os, time, inspect
-import branchmap
+import branchmap, pathutil
 propertycache = util.propertycache
 filecache = scmutil.filecache
 
 class repofilecache(filecache):
     """All filecache usage on repo are done for logic that should be unfiltered
     """
 
     def __get__(self, repo, type=None):
         return super(repofilecache, self).__get__(repo.unfiltered(), type)
     def __set__(self, repo, value):
         return super(repofilecache, self).__set__(repo.unfiltered(), value)
     def __delete__(self, repo):
         return super(repofilecache, self).__delete__(repo.unfiltered())
 
 class storecache(repofilecache):
     """filecache for files in the store"""
     def join(self, obj, fname):
         return obj.sjoin(fname)
 
 class unfilteredpropertycache(propertycache):
     """propertycache that apply to unfiltered repo only"""
 
     def __get__(self, repo, type=None):
         unfi = repo.unfiltered()
         if unfi is repo:
             return super(unfilteredpropertycache, self).__get__(unfi)
         return getattr(unfi, self.name)
 
 class filteredpropertycache(propertycache):
     """propertycache that must take filtering in account"""
 
     def cachevalue(self, obj, value):
         object.__setattr__(obj, self.name, value)
 
 
 def hasunfilteredcache(repo, name):
     """check if a repo has an unfilteredpropertycache value for <name>"""
     return name in vars(repo.unfiltered())
 
 def unfilteredmethod(orig):
     """decorate method that always need to be run on unfiltered version"""
     def wrapper(repo, *args, **kwargs):
         return orig(repo.unfiltered(), *args, **kwargs)
     return wrapper
 
 MODERNCAPS = set(('lookup', 'branchmap', 'pushkey', 'known', 'getbundle'))
 LEGACYCAPS = MODERNCAPS.union(set(['changegroupsubset']))
 
 class localpeer(peer.peerrepository):
     '''peer for a local repo; reflects only the most recent API'''
 
     def __init__(self, repo, caps=MODERNCAPS):
         peer.peerrepository.__init__(self)
         self._repo = repo.filtered('served')
         self.ui = repo.ui
         self._caps = repo._restrictcapabilities(caps)
         self.requirements = repo.requirements
         self.supportedformats = repo.supportedformats
 
     def close(self):
         self._repo.close()
 
     def _capabilities(self):
         return self._caps
 
     def local(self):
         return self._repo
 
     def canpush(self):
         return True
 
     def url(self):
         return self._repo.url()
 
     def lookup(self, key):
         return self._repo.lookup(key)
 
     def branchmap(self):
         return self._repo.branchmap()
 
     def heads(self):
         return self._repo.heads()
 
     def known(self, nodes):
         return self._repo.known(nodes)
 
     def getbundle(self, source, heads=None, common=None, bundlecaps=None):
         return self._repo.getbundle(source, heads=heads, common=common,
                                     bundlecaps=None)
 
     # TODO We might want to move the next two calls into legacypeer and add
     # unbundle instead.
 
     def lock(self):
         return self._repo.lock()
 
     def addchangegroup(self, cg, source, url):
         return self._repo.addchangegroup(cg, source, url)
 
     def pushkey(self, namespace, key, old, new):
         return self._repo.pushkey(namespace, key, old, new)
 
     def listkeys(self, namespace):
         return self._repo.listkeys(namespace)
 
     def debugwireargs(self, one, two, three=None, four=None, five=None):
         '''used to test argument passing over the wire'''
         return "%s %s %s %s %s" % (one, two, three, four, five)
 
 class locallegacypeer(localpeer):
     '''peer extension which implements legacy methods too; used for tests with
     restricted capabilities'''
 
     def __init__(self, repo):
         localpeer.__init__(self, repo, caps=LEGACYCAPS)
 
     def branches(self, nodes):
         return self._repo.branches(nodes)
 
     def between(self, pairs):
         return self._repo.between(pairs)
 
     def changegroup(self, basenodes, source):
         return self._repo.changegroup(basenodes, source)
 
     def changegroupsubset(self, bases, heads, source):
         return self._repo.changegroupsubset(bases, heads, source)
 
 class localrepository(object):
 
     supportedformats = set(('revlogv1', 'generaldelta'))
     _basesupported = supportedformats | set(('store', 'fncache', 'shared',
                                              'dotencode'))
     openerreqs = set(('revlogv1', 'generaldelta'))
     requirements = ['revlogv1']
     filtername = None
 
     # a list of (ui, featureset) functions.
     # only functions defined in module of enabled extensions are invoked
     featuresetupfuncs = set()
 
     def _baserequirements(self, create):
         return self.requirements[:]
 
     def __init__(self, baseui, path=None, create=False):
         self.wvfs = scmutil.vfs(path, expandpath=True, realpath=True)
         self.wopener = self.wvfs
         self.root = self.wvfs.base
         self.path = self.wvfs.join(".hg")
         self.origroot = path
-        self.auditor = scmutil.pathauditor(self.root, self._checknested)
+        self.auditor = pathutil.pathauditor(self.root, self._checknested)
         self.vfs = scmutil.vfs(self.path)
         self.opener = self.vfs
         self.baseui = baseui
         self.ui = baseui.copy()
         # A list of callback to shape the phase if no data were found.
         # Callback are in the form: func(repo, roots) --> processed root.
         # This list it to be filled by extension during repo setup
         self._phasedefaults = []
         try:
             self.ui.readconfig(self.join("hgrc"), self.root)
             extensions.loadall(self.ui)
         except IOError:
             pass
 
         if self.featuresetupfuncs:
             self.supported = set(self._basesupported) # use private copy
             extmods = set(m.__name__ for n, m
                           in extensions.extensions(self.ui))
             for setupfunc in self.featuresetupfuncs:
                 if setupfunc.__module__ in extmods:
                     setupfunc(self.ui, self.supported)
         else:
             self.supported = self._basesupported
 
         if not self.vfs.isdir():
             if create:
                 if not self.wvfs.exists():
                     self.wvfs.makedirs()
                 self.vfs.makedir(notindexed=True)
                 requirements = self._baserequirements(create)
                 if self.ui.configbool('format', 'usestore', True):
                     self.vfs.mkdir("store")
                     requirements.append("store")
                     if self.ui.configbool('format', 'usefncache', True):
                         requirements.append("fncache")
                         if self.ui.configbool('format', 'dotencode', True):
                             requirements.append('dotencode')
                     # create an invalid changelog
                     self.vfs.append(
                         "00changelog.i",
                         '\0\0\0\2' # represents revlogv2
                         ' dummy changelog to prevent using the old repo layout'
                     )
                 if self.ui.configbool('format', 'generaldelta', False):
                     requirements.append("generaldelta")
                 requirements = set(requirements)
             else:
                 raise error.RepoError(_("repository %s not found") % path)
         elif create:
             raise error.RepoError(_("repository %s already exists") % path)
         else:
             try:
                 requirements = scmutil.readrequires(self.vfs, self.supported)
             except IOError, inst:
                 if inst.errno != errno.ENOENT:
                     raise
                 requirements = set()
 
         self.sharedpath = self.path
         try:
             vfs = scmutil.vfs(self.vfs.read("sharedpath").rstrip('\n'),
                               realpath=True)
             s = vfs.base
             if not vfs.exists():
                 raise error.RepoError(
                     _('.hg/sharedpath points to nonexistent directory %s') % s)
             self.sharedpath = s
         except IOError, inst:
             if inst.errno != errno.ENOENT:
                 raise
 
         self.store = store.store(requirements, self.sharedpath, scmutil.vfs)
         self.spath = self.store.path
         self.svfs = self.store.vfs
         self.sopener = self.svfs
         self.sjoin = self.store.join
         self.vfs.createmode = self.store.createmode
         self._applyrequirements(requirements)
         if create:
             self._writerequirements()
 
 
         self._branchcaches = {}
         self.filterpats = {}
         self._datafilters = {}
         self._transref = self._lockref = self._wlockref = None
 
         # A cache for various files under .hg/ that tracks file changes,
         # (used by the filecache decorator)
         #
         # Maps a property name to its util.filecacheentry
         self._filecache = {}
 
         # hold sets of revision to be filtered
         # should be cleared when something might have changed the filter value:
         # - new changesets,
         # - phase change,
         # - new obsolescence marker,
         # - working directory parent change,
         # - bookmark changes
         self.filteredrevcache = {}
 
     def close(self):
         pass
 
     def _restrictcapabilities(self, caps):
         return caps
 
     def _applyrequirements(self, requirements):
         self.requirements = requirements
         self.sopener.options = dict((r, 1) for r in requirements
                                            if r in self.openerreqs)
 
     def _writerequirements(self):
         reqfile = self.opener("requires", "w")
         for r in sorted(self.requirements):
             reqfile.write("%s\n" % r)
         reqfile.close()
 
     def _checknested(self, path):
         """Determine if path is a legal nested repository."""
         if not path.startswith(self.root):
             return False
         subpath = path[len(self.root) + 1:]
         normsubpath = util.pconvert(subpath)
 
         # XXX: Checking against the current working copy is wrong in
         # the sense that it can reject things like
         #
         #   $ hg cat -r 10 sub/x.txt
         #
         # if sub/ is no longer a subrepository in the working copy
         # parent revision.
         #
         # However, it can of course also allow things that would have
         # been rejected before, such as the above cat command if sub/
         # is a subrepository now, but was a normal directory before.
         # The old path auditor would have rejected by mistake since it
         # panics when it sees sub/.hg/.
         #
         # All in all, checking against the working copy seems sensible
         # since we want to prevent access to nested repositories on
         # the filesystem *now*.
         ctx = self[None]
         parts = util.splitpath(subpath)
         while parts:
             prefix = '/'.join(parts)
             if prefix in ctx.substate:
                 if prefix == normsubpath:
                     return True
                 else:
                     sub = ctx.sub(prefix)
                     return sub.checknested(subpath[len(prefix) + 1:])
             else:
                 parts.pop()
         return False
 
     def peer(self):
         return localpeer(self) # not cached to avoid reference cycle
 
     def unfiltered(self):
         """Return unfiltered version of the repository
 
         Intended to be overwritten by filtered repo."""
         return self
 
     def filtered(self, name):
         """Return a filtered version of a repository"""
         # build a new class with the mixin and the current class
         # (possibly subclass of the repo)
         class proxycls(repoview.repoview, self.unfiltered().__class__):
             pass
         return proxycls(self, name)
 
     @repofilecache('bookmarks')
     def _bookmarks(self):
         return bookmarks.bmstore(self)
 
     @repofilecache('bookmarks.current')
     def _bookmarkcurrent(self):
         return bookmarks.readcurrent(self)
 
     def bookmarkheads(self, bookmark):
         name = bookmark.split('@', 1)[0]
         heads = []
         for mark, n in self._bookmarks.iteritems():
             if mark.split('@', 1)[0] == name:
                 heads.append(n)
         return heads
 
     @storecache('phaseroots')
     def _phasecache(self):
         return phases.phasecache(self, self._phasedefaults)
 
     @storecache('obsstore')
     def obsstore(self):
         store = obsolete.obsstore(self.sopener)
         if store and not obsolete._enabled:
             # message is rare enough to not be translated
             msg = 'obsolete feature not enabled but %i markers found!\n'
             self.ui.warn(msg % len(list(store)))
         return store
 
     @storecache('00changelog.i')
     def changelog(self):
         c = changelog.changelog(self.sopener)
         if 'HG_PENDING' in os.environ:
             p = os.environ['HG_PENDING']
             if p.startswith(self.root):
                 c.readpending('00changelog.i.a')
         return c
 
     @storecache('00manifest.i')
     def manifest(self):
         return manifest.manifest(self.sopener)
 
     @repofilecache('dirstate')
     def dirstate(self):
         warned = [0]
         def validate(node):
             try:
                 self.changelog.rev(node)
                 return node
             except error.LookupError:
                 if not warned[0]:
                     warned[0] = True
                     self.ui.warn(_("warning: ignoring unknown"
                                    " working parent %s!\n") % short(node))
                 return nullid
 
         return dirstate.dirstate(self.opener, self.ui, self.root, validate)
 
     def __getitem__(self, changeid):
         if changeid is None:
             return context.workingctx(self)
         return context.changectx(self, changeid)
 
     def __contains__(self, changeid):
         try:
             return bool(self.lookup(changeid))
         except error.RepoLookupError:
             return False
 
     def __nonzero__(self):
         return True
 
     def __len__(self):
         return len(self.changelog)
 
     def __iter__(self):
         return iter(self.changelog)
 
     def revs(self, expr, *args):
         '''Return a list of revisions matching the given revset'''
         expr = revset.formatspec(expr, *args)
         m = revset.match(None, expr)
         return [r for r in m(self, list(self))]
 
     def set(self, expr, *args):
         '''
         Yield a context for each matching revision, after doing arg
         replacement via revset.formatspec
         '''
         for r in self.revs(expr, *args):
             yield self[r]
 
     def url(self):
         return 'file:' + self.root
 
     def hook(self, name, throw=False, **args):
         return hook.hook(self.ui, self, name, throw, **args)
 
     @unfilteredmethod
     def _tag(self, names, node, message, local, user, date, extra={}):
         if isinstance(names, str):
             names = (names,)
 
         branches = self.branchmap()
         for name in names:
             self.hook('pretag', throw=True, node=hex(node), tag=name,
                       local=local)
             if name in branches:
                 self.ui.warn(_("warning: tag %s conflicts with existing"
                 " branch name\n") % name)
 
         def writetags(fp, names, munge, prevtags):
             fp.seek(0, 2)
             if prevtags and prevtags[-1] != '\n':
                 fp.write('\n')
             for name in names:
                 m = munge and munge(name) or name
                 if (self._tagscache.tagtypes and
                     name in self._tagscache.tagtypes):
                     old = self.tags().get(name, nullid)
                     fp.write('%s %s\n' % (hex(old), m))
                 fp.write('%s %s\n' % (hex(node), m))
             fp.close()
 
         prevtags = ''
         if local:
             try:
                 fp = self.opener('localtags', 'r+')
             except IOError:
                 fp = self.opener('localtags', 'a')
             else:
                 prevtags = fp.read()
 
             # local tags are stored in the current charset
             writetags(fp, names, None, prevtags)
             for name in names:
                 self.hook('tag', node=hex(node), tag=name, local=local)
             return
 
         try:
             fp = self.wfile('.hgtags', 'rb+')
         except IOError, e:
             if e.errno != errno.ENOENT:
                 raise
             fp = self.wfile('.hgtags', 'ab')
         else:
             prevtags = fp.read()
 
         # committed tags are stored in UTF-8
         writetags(fp, names, encoding.fromlocal, prevtags)
 
         fp.close()
 
         self.invalidatecaches()
 
         if '.hgtags' not in self.dirstate:
             self[None].add(['.hgtags'])
 
         m = matchmod.exact(self.root, '', ['.hgtags'])
         tagnode = self.commit(message, user, date, extra=extra, match=m)
 
         for name in names:
             self.hook('tag', node=hex(node), tag=name, local=local)
 
         return tagnode
 
     def tag(self, names, node, message, local, user, date):
         '''tag a revision with one or more symbolic names.
 
         names is a list of strings or, when adding a single tag, names may be a
         string.
 
         if local is True, the tags are stored in a per-repository file.
         otherwise, they are stored in the .hgtags file, and a new
         changeset is committed with the change.
 
         keyword arguments:
 
         local: whether to store tags in non-version-controlled file
         (default False)
 
         message: commit message to use if committing
 
         user: name of user to use if committing
 
         date: date tuple to use if committing'''
 
         if not local:
             for x in self.status()[:5]:
                 if '.hgtags' in x:
                     raise util.Abort(_('working copy of .hgtags is changed '
                                        '(please commit .hgtags manually)'))
 
         self.tags() # instantiate the cache
         self._tag(names, node, message, local, user, date)
 
     @filteredpropertycache
     def _tagscache(self):
         '''Returns a tagscache object that contains various tags related
         caches.'''
 
         # This simplifies its cache management by having one decorated
         # function (this one) and the rest simply fetch things from it.
         class tagscache(object):
             def __init__(self):
                 # These two define the set of tags for this repository. tags
                 # maps tag name to node; tagtypes maps tag name to 'global' or
                 # 'local'. (Global tags are defined by .hgtags across all
                 # heads, and local tags are defined in .hg/localtags.)
                 # They constitute the in-memory cache of tags.
                 self.tags = self.tagtypes = None
 
                 self.nodetagscache = self.tagslist = None
 
         cache = tagscache()
         cache.tags, cache.tagtypes = self._findtags()
 
         return cache
 
     def tags(self):
         '''return a mapping of tag to node'''
         t = {}
         if self.changelog.filteredrevs:
             tags, tt = self._findtags()
         else:
             tags = self._tagscache.tags
         for k, v in tags.iteritems():
             try:
                 # ignore tags to unknown nodes
                 self.changelog.rev(v)
                 t[k] = v
             except (error.LookupError, ValueError):
                 pass
         return t
 
     def _findtags(self):
         '''Do the hard work of finding tags.  Return a pair of dicts
         (tags, tagtypes) where tags maps tag name to node, and tagtypes
         maps tag name to a string like \'global\' or \'local\'.
         Subclasses or extensions are free to add their own tags, but
         should be aware that the returned dicts will be retained for the
         duration of the localrepo object.'''
 
         # XXX what tagtype should subclasses/extensions use?  Currently
         # mq and bookmarks add tags, but do not set the tagtype at all.
         # Should each extension invent its own tag type?  Should there
         # be one tagtype for all such "virtual" tags?  Or is the status
         # quo fine?
 
         alltags = {}                    # map tag name to (node, hist)
         tagtypes = {}
 
         tagsmod.findglobaltags(self.ui, self, alltags, tagtypes)
         tagsmod.readlocaltags(self.ui, self, alltags, tagtypes)
 
         # Build the return dicts.  Have to re-encode tag names because
         # the tags module always uses UTF-8 (in order not to lose info
         # writing to the cache), but the rest of Mercurial wants them in
         # local encoding.
         tags = {}
         for (name, (node, hist)) in alltags.iteritems():
             if node != nullid:
                 tags[encoding.tolocal(name)] = node
         tags['tip'] = self.changelog.tip()
         tagtypes = dict([(encoding.tolocal(name), value)
                          for (name, value) in tagtypes.iteritems()])
         return (tags, tagtypes)
 
     def tagtype(self, tagname):
         '''
         return the type of the given tag. result can be:
 
         'local'  : a local tag
         'global' : a global tag
         None     : tag does not exist
         '''
 
         return self._tagscache.tagtypes.get(tagname)
 
     def tagslist(self):
         '''return a list of tags ordered by revision'''
         if not self._tagscache.tagslist:
             l = []
             for t, n in self.tags().iteritems():
                 r = self.changelog.rev(n)
                 l.append((r, t, n))
             self._tagscache.tagslist = [(t, n) for r, t, n in sorted(l)]
 
         return self._tagscache.tagslist
 
     def nodetags(self, node):
         '''return the tags associated with a node'''
         if not self._tagscache.nodetagscache:
             nodetagscache = {}
             for t, n in self._tagscache.tags.iteritems():
                 nodetagscache.setdefault(n, []).append(t)
             for tags in nodetagscache.itervalues():
                 tags.sort()
             self._tagscache.nodetagscache = nodetagscache
         return self._tagscache.nodetagscache.get(node, [])
 
     def nodebookmarks(self, node):
         marks = []
         for bookmark, n in self._bookmarks.iteritems():
             if n == node:
                 marks.append(bookmark)
         return sorted(marks)
 
     def branchmap(self):
         '''returns a dictionary {branch: [branchheads]}'''
         branchmap.updatecache(self)
         return self._branchcaches[self.filtername]
 
 
     def _branchtip(self, heads):
         '''return the tipmost branch head in heads'''
         tip = heads[-1]
         for h in reversed(heads):
             if not self[h].closesbranch():
                 tip = h
                 break
         return tip
 
     def branchtip(self, branch):
         '''return the tip node for a given branch'''
         if branch not in self.branchmap():
             raise error.RepoLookupError(_("unknown branch '%s'") % branch)
         return self._branchtip(self.branchmap()[branch])
 
     def branchtags(self):
         '''return a dict where branch names map to the tipmost head of
         the branch, open heads come before closed'''
         bt = {}
         for bn, heads in self.branchmap().iteritems():
             bt[bn] = self._branchtip(heads)
         return bt
 
     def lookup(self, key):
         return self[key].node()
 
     def lookupbranch(self, key, remote=None):
         repo = remote or self
         if key in repo.branchmap():
             return key
 
         repo = (remote and remote.local()) and remote or self
         return repo[key].branch()
 
     def known(self, nodes):
         nm = self.changelog.nodemap
         pc = self._phasecache
         result = []
         for n in nodes:
             r = nm.get(n)
             resp = not (r is None or pc.phase(self, r) >= phases.secret)
             result.append(resp)
         return result
 
     def local(self):
         return self
 
     def cancopy(self):
         return self.local() # so statichttprepo's override of local() works
 
     def join(self, f):
         return os.path.join(self.path, f)
 
     def wjoin(self, f):
         return os.path.join(self.root, f)
 
     def file(self, f):
         if f[0] == '/':
             f = f[1:]
         return filelog.filelog(self.sopener, f)
 
     def changectx(self, changeid):
         return self[changeid]
 
     def parents(self, changeid=None):
         '''get list of changectxs for parents of changeid'''
         return self[changeid].parents()
 
     def setparents(self, p1, p2=nullid):
         copies = self.dirstate.setparents(p1, p2)
         pctx = self[p1]
         if copies:
             # Adjust copy records, the dirstate cannot do it, it
             # requires access to parents manifests. Preserve them
             # only for entries added to first parent.
             for f in copies:
                 if f not in pctx and copies[f] in pctx:
                     self.dirstate.copy(copies[f], f)
         if p2 == nullid:
             for f, s in sorted(self.dirstate.copies().items()):
                 if f not in pctx and s not in pctx:
                     self.dirstate.copy(None, f)
 
     def filectx(self, path, changeid=None, fileid=None):
         """changeid can be a changeset revision, node, or tag.
            fileid can be a file revision or node."""
         return context.filectx(self, path, changeid, fileid)
 
     def getcwd(self):
         return self.dirstate.getcwd()
 
     def pathto(self, f, cwd=None):
         return self.dirstate.pathto(f, cwd)
 
     def wfile(self, f, mode='r'):
         return self.wopener(f, mode)
 
     def _link(self, f):
         return self.wvfs.islink(f)
 
     def _loadfilter(self, filter):
         if filter not in self.filterpats:
             l = []
             for pat, cmd in self.ui.configitems(filter):
                 if cmd == '!':
                     continue
                 mf = matchmod.match(self.root, '', [pat])
                 fn = None
                 params = cmd
                 for name, filterfn in self._datafilters.iteritems():
                     if cmd.startswith(name):
                         fn = filterfn
                         params = cmd[len(name):].lstrip()
                         break
                 if not fn:
                     fn = lambda s, c, **kwargs: util.filter(s, c)
                 # Wrap old filters not supporting keyword arguments
                 if not inspect.getargspec(fn)[2]:
                     oldfn = fn
                     fn = lambda s, c, **kwargs: oldfn(s, c)
                 l.append((mf, fn, params))
             self.filterpats[filter] = l
         return self.filterpats[filter]
 
     def _filter(self, filterpats, filename, data):
         for mf, fn, cmd in filterpats:
             if mf(filename):
                 self.ui.debug("filtering %s through %s\n" % (filename, cmd))
                 data = fn(data, cmd, ui=self.ui, repo=self, filename=filename)
                 break
 
         return data
 
     @unfilteredpropertycache
     def _encodefilterpats(self):
         return self._loadfilter('encode')
 
     @unfilteredpropertycache
     def _decodefilterpats(self):
         return self._loadfilter('decode')
 
     def adddatafilter(self, name, filter):
         self._datafilters[name] = filter
 
     def wread(self, filename):
         if self._link(filename):
             data = self.wvfs.readlink(filename)
         else:
             data = self.wopener.read(filename)
         return self._filter(self._encodefilterpats, filename, data)
 
     def wwrite(self, filename, data, flags):
         data = self._filter(self._decodefilterpats, filename, data)
         if 'l' in flags:
             self.wopener.symlink(data, filename)
         else:
             self.wopener.write(filename, data)
             if 'x' in flags:
                 self.wvfs.setflags(filename, False, True)
 
     def wwritedata(self, filename, data):
         return self._filter(self._decodefilterpats, filename, data)
 
     def transaction(self, desc, report=None):
         tr = self._transref and self._transref() or None
         if tr and tr.running():
             return tr.nest()
 
         # abort here if the journal already exists
         if self.svfs.exists("journal"):
             raise error.RepoError(
                 _("abandoned transaction found - run hg recover"))
 
         self._writejournal(desc)
         renames = [(vfs, x, undoname(x)) for vfs, x in self._journalfiles()]
         rp = report and report or self.ui.warn
         tr = transaction.transaction(rp, self.sopener,
                                      self.sjoin("journal"),
                                      aftertrans(renames),
                                      self.store.createmode)
         self._transref = weakref.ref(tr)
         return tr
 
     def _journalfiles(self):
         return ((self.svfs, 'journal'),
                 (self.vfs, 'journal.dirstate'),
                 (self.vfs, 'journal.branch'),
                 (self.vfs, 'journal.desc'),
                 (self.vfs, 'journal.bookmarks'),
                 (self.svfs, 'journal.phaseroots'))
 
     def undofiles(self):
         return [vfs.join(undoname(x)) for vfs, x in self._journalfiles()]
 
     def _writejournal(self, desc):
         self.opener.write("journal.dirstate",
                           self.opener.tryread("dirstate"))
         self.opener.write("journal.branch",
                           encoding.fromlocal(self.dirstate.branch()))
         self.opener.write("journal.desc",
                           "%d\n%s\n" % (len(self), desc))
         self.opener.write("journal.bookmarks",
                           self.opener.tryread("bookmarks"))
         self.sopener.write("journal.phaseroots",
                            self.sopener.tryread("phaseroots"))
 
     def recover(self):
         lock = self.lock()
         try:
             if self.svfs.exists("journal"):
                 self.ui.status(_("rolling back interrupted transaction\n"))
                 transaction.rollback(self.sopener, self.sjoin("journal"),
                                      self.ui.warn)
                 self.invalidate()
                 return True
             else:
                 self.ui.warn(_("no interrupted transaction available\n"))
                 return False
         finally:
             lock.release()
 
     def rollback(self, dryrun=False, force=False):
         wlock = lock = None
         try:
             wlock = self.wlock()
             lock = self.lock()
             if self.svfs.exists("undo"):
                 return self._rollback(dryrun, force)
             else:
                 self.ui.warn(_("no rollback information available\n"))
                 return 1
         finally:
             release(lock, wlock)
 
     @unfilteredmethod # Until we get smarter cache management
     def _rollback(self, dryrun, force):
         ui = self.ui
         try:
             args = self.opener.read('undo.desc').splitlines()
             (oldlen, desc, detail) = (int(args[0]), args[1], None)
             if len(args) >= 3:
                 detail = args[2]
             oldtip = oldlen - 1
 
             if detail and ui.verbose:
                 msg = (_('repository tip rolled back to revision %s'
                          ' (undo %s: %s)\n')
                        % (oldtip, desc, detail))
             else:
                 msg = (_('repository tip rolled back to revision %s'
                          ' (undo %s)\n')
                        % (oldtip, desc))
         except IOError:
             msg = _('rolling back unknown transaction\n')
             desc = None
 
         if not force and self['.'] != self['tip'] and desc == 'commit':
             raise util.Abort(
                 _('rollback of last commit while not checked out '
                   'may lose data'), hint=_('use -f to force'))
 
         ui.status(msg)
         if dryrun:
             return 0
 
         parents = self.dirstate.parents()
         self.destroying()
         transaction.rollback(self.sopener, self.sjoin('undo'), ui.warn)
         if self.vfs.exists('undo.bookmarks'):
             self.vfs.rename('undo.bookmarks', 'bookmarks')
         if self.svfs.exists('undo.phaseroots'):
             self.svfs.rename('undo.phaseroots', 'phaseroots')
         self.invalidate()
 
         parentgone = (parents[0] not in self.changelog.nodemap or
                       parents[1] not in self.changelog.nodemap)
         if parentgone:
             self.vfs.rename('undo.dirstate', 'dirstate')
             try:
                 branch = self.opener.read('undo.branch')
                 self.dirstate.setbranch(encoding.tolocal(branch))
             except IOError:
                 ui.warn(_('named branch could not be reset: '
                           'current branch is still \'%s\'\n')
                         % self.dirstate.branch())
 
             self.dirstate.invalidate()
             parents = tuple([p.rev() for p in self.parents()])
             if len(parents) > 1:
                 ui.status(_('working directory now based on '
                             'revisions %d and %d\n') % parents)
             else:
                 ui.status(_('working directory now based on '
                             'revision %d\n') % parents)
         # TODO: if we know which new heads may result from this rollback, pass
         # them to destroy(), which will prevent the branchhead cache from being
         # invalidated.
         self.destroyed()
         return 0
 
     def invalidatecaches(self):
 
         if '_tagscache' in vars(self):
             # can't use delattr on proxy
             del self.__dict__['_tagscache']
 
         self.unfiltered()._branchcaches.clear()
         self.invalidatevolatilesets()
 
     def invalidatevolatilesets(self):
         self.filteredrevcache.clear()
         obsolete.clearobscaches(self)
 
     def invalidatedirstate(self):
         '''Invalidates the dirstate, causing the next call to dirstate
         to check if it was modified since the last time it was read,
         rereading it if it has.
 
         This is different to dirstate.invalidate() that it doesn't always
         rereads the dirstate. Use dirstate.invalidate() if you want to
         explicitly read the dirstate again (i.e. restoring it to a previous
         known good state).'''
         if hasunfilteredcache(self, 'dirstate'):
             for k in self.dirstate._filecache:
                 try:
                     delattr(self.dirstate, k)
                 except AttributeError:
                     pass
             delattr(self.unfiltered(), 'dirstate')
 
     def invalidate(self):
         unfiltered = self.unfiltered() # all file caches are stored unfiltered
         for k in self._filecache:
             # dirstate is invalidated separately in invalidatedirstate()
             if k == 'dirstate':
                 continue
 
             try:
                 delattr(unfiltered, k)
             except AttributeError:
                 pass
         self.invalidatecaches()
 
     def _lock(self, lockname, wait, releasefn, acquirefn, desc):
         try:
             l = lock.lock(lockname, 0, releasefn, desc=desc)
         except error.LockHeld, inst:
             if not wait:
                 raise
             self.ui.warn(_("waiting for lock on %s held by %r\n") %
                          (desc, inst.locker))
             # default to 600 seconds timeout
             l = lock.lock(lockname, int(self.ui.config("ui", "timeout", "600")),
                           releasefn, desc=desc)
         if acquirefn:
             acquirefn()
         return l
 
     def _afterlock(self, callback):
         """add a callback to the current repository lock.
 
         The callback will be executed on lock release."""
         l = self._lockref and self._lockref()
         if l:
             l.postrelease.append(callback)
         else:
             callback()
 
     def lock(self, wait=True):
         '''Lock the repository store (.hg/store) and return a weak reference
         to the lock. Use this before modifying the store (e.g. committing or
         stripping). If you are opening a transaction, get a lock as well.)'''
         l = self._lockref and self._lockref()
         if l is not None and l.held:
             l.lock()
             return l
 
         def unlock():
             self.store.write()
             if hasunfilteredcache(self, '_phasecache'):
                 self._phasecache.write()
             for k, ce in self._filecache.items():
                 if k == 'dirstate' or k not in self.__dict__:
                     continue
                 ce.refresh()
 
         l = self._lock(self.sjoin("lock"), wait, unlock,
                        self.invalidate, _('repository %s') % self.origroot)
         self._lockref = weakref.ref(l)
         return l
 
     def wlock(self, wait=True):
         '''Lock the non-store parts of the repository (everything under
         .hg except .hg/store) and return a weak reference to the lock.
         Use this before modifying files in .hg.'''
         l = self._wlockref and self._wlockref()
         if l is not None and l.held:
             l.lock()
             return l
 
         def unlock():
             self.dirstate.write()
             self._filecache['dirstate'].refresh()
 
         l = self._lock(self.join("wlock"), wait, unlock,
                        self.invalidatedirstate, _('working directory of %s') %
                        self.origroot)
         self._wlockref = weakref.ref(l)
         return l
 
     def _filecommit(self, fctx, manifest1, manifest2, linkrev, tr, changelist):
         """
         commit an individual file as part of a larger transaction
         """
 
         fname = fctx.path()
         text = fctx.data()
         flog = self.file(fname)
         fparent1 = manifest1.get(fname, nullid)
         fparent2 = fparent2o = manifest2.get(fname, nullid)
 
         meta = {}
         copy = fctx.renamed()
         if copy and copy[0] != fname:
             # Mark the new revision of this file as a copy of another
             # file.  This copy data will effectively act as a parent
             # of this new revision.  If this is a merge, the first
             # parent will be the nullid (meaning "look up the copy data")
             # and the second one will be the other parent.  For example:
             #
             # 0 --- 1 --- 3   rev1 changes file foo
             #   \       /     rev2 renames foo to bar and changes it
             #    \- 2 -/      rev3 should have bar with all changes and
             #                      should record that bar descends from
             #                      bar in rev2 and foo in rev1
             #
             # this allows this merge to succeed:
             #
             # 0 --- 1 --- 3   rev4 reverts the content change from rev2
             #   \       /     merging rev3 and rev4 should use bar@rev2
             #    \- 2 --- 4        as the merge base
             #
 
             cfname = copy[0]
             crev = manifest1.get(cfname)
             newfparent = fparent2
 
             if manifest2: # branch merge
                 if fparent2 == nullid or crev is None: # copied on remote side
                     if cfname in manifest2:
                         crev = manifest2[cfname]
                         newfparent = fparent1
 
             # find source in nearest ancestor if we've lost track
             if not crev:
                 self.ui.debug(" %s: searching for copy revision for %s\n" %
                               (fname, cfname))
                 for ancestor in self[None].ancestors():
                     if cfname in ancestor:
                         crev = ancestor[cfname].filenode()
                         break
 
             if crev:
                 self.ui.debug(" %s: copy %s:%s\n" % (fname, cfname, hex(crev)))
                 meta["copy"] = cfname
                 meta["copyrev"] = hex(crev)
                 fparent1, fparent2 = nullid, newfparent
             else:
                 self.ui.warn(_("warning: can't find ancestor for '%s' "
                                "copied from '%s'!\n") % (fname, cfname))
 
         elif fparent2 != nullid:
             # is one parent an ancestor of the other?
             fparentancestor = flog.ancestor(fparent1, fparent2)
             if fparentancestor == fparent1:
                 fparent1, fparent2 = fparent2, nullid
             elif fparentancestor == fparent2:
                 fparent2 = nullid
 
         # is the file changed?
         if fparent2 != nullid or flog.cmp(fparent1, text) or meta:
             changelist.append(fname)
             return flog.add(text, meta, tr, linkrev, fparent1, fparent2)
 
         # are just the flags changed during merge?
         if fparent1 != fparent2o and manifest1.flags(fname) != fctx.flags():
             changelist.append(fname)
 
         return fparent1
 
     @unfilteredmethod
     def commit(self, text="", user=None, date=None, match=None, force=False,
                editor=False, extra={}):
         """Add a new revision to current repository.
 
         Revision information is gathered from the working directory,
         match can be used to filter the committed files. If editor is
         supplied, it is called to get a commit message.
         """
 
         def fail(f, msg):
             raise util.Abort('%s: %s' % (f, msg))
 
         if not match:
             match = matchmod.always(self.root, '')
 
         if not force:
             vdirs = []
             match.explicitdir = vdirs.append
             match.bad = fail
 
         wlock = self.wlock()
         try:
             wctx = self[None]
             merge = len(wctx.parents()) > 1
 
             if (not force and merge and match and
                 (match.files() or match.anypats())):
                 raise util.Abort(_('cannot partially commit a merge '
                                    '(do not specify files or patterns)'))
 
             changes = self.status(match=match, clean=force)
             if force:
                 changes[0].extend(changes[6]) # mq may commit unchanged files
 
             # check subrepos
             subs = []
             commitsubs = set()
             newstate = wctx.substate.copy()
             # only manage subrepos and .hgsubstate if .hgsub is present
             if '.hgsub' in wctx:
                 # we'll decide whether to track this ourselves, thanks
                 if '.hgsubstate' in changes[0]:
                     changes[0].remove('.hgsubstate')
                 if '.hgsubstate' in changes[2]:
                     changes[2].remove('.hgsubstate')
 
                 # compare current state to last committed state
                 # build new substate based on last committed state
                 oldstate = wctx.p1().substate
                 for s in sorted(newstate.keys()):
                     if not match(s):
                         # ignore working copy, use old state if present
                         if s in oldstate:
                             newstate[s] = oldstate[s]
                             continue
                         if not force:
                             raise util.Abort(
                                 _("commit with new subrepo %s excluded") % s)
                     if wctx.sub(s).dirty(True):
                         if not self.ui.configbool('ui', 'commitsubrepos'):
                             raise util.Abort(
                                 _("uncommitted changes in subrepo %s") % s,
                                 hint=_("use --subrepos for recursive commit"))
                         subs.append(s)
                         commitsubs.add(s)
                     else:
                         bs = wctx.sub(s).basestate()
                         newstate[s] = (newstate[s][0], bs, newstate[s][2])
                         if oldstate.get(s, (None, None, None))[1] != bs:
                             subs.append(s)
 
                 # check for removed subrepos
                 for p in wctx.parents():
                     r = [s for s in p.substate if s not in newstate]
                     subs += [s for s in r if match(s)]
                 if subs:
                     if (not match('.hgsub') and
                         '.hgsub' in (wctx.modified() + wctx.added())):
                         raise util.Abort(
                             _("can't commit subrepos without .hgsub"))
                     changes[0].insert(0, '.hgsubstate')
 
             elif '.hgsub' in changes[2]:
                 # clean up .hgsubstate when .hgsub is removed
                 if ('.hgsubstate' in wctx and
                     '.hgsubstate' not in changes[0] + changes[1] + changes[2]):
                     changes[2].insert(0, '.hgsubstate')
 
             # make sure all explicit patterns are matched
             if not force and match.files():
                 matched = set(changes[0] + changes[1] + changes[2])
 
                 for f in match.files():
                     f = self.dirstate.normalize(f)
                     if f == '.' or f in matched or f in wctx.substate:
                         continue
                     if f in changes[3]: # missing
                         fail(f, _('file not found!'))
                     if f in vdirs: # visited directory
                         d = f + '/'
                         for mf in matched:
                             if mf.startswith(d):
                                 break
                         else:
                             fail(f, _("no match under directory!"))
                     elif f not in self.dirstate:
                         fail(f, _("file not tracked!"))
 
             cctx = context.workingctx(self, text, user, date, extra, changes)
 
             if (not force and not extra.get("close") and not merge
                 and not cctx.files()
                 and wctx.branch() == wctx.p1().branch()):
                 return None
 
             if merge and cctx.deleted():
                 raise util.Abort(_("cannot commit merge with missing files"))
 
             ms = mergemod.mergestate(self)
             for f in changes[0]:
                 if f in ms and ms[f] == 'u':
                     raise util.Abort(_("unresolved merge conflicts "
                                        "(see hg help resolve)"))
 
             if editor:
                 cctx._text = editor(self, cctx, subs)
             edited = (text != cctx._text)
 
             # commit subs and write new state
             if subs:
                 for s in sorted(commitsubs):
                     sub = wctx.sub(s)
                     self.ui.status(_('committing subrepository %s\n') %
                         subrepo.subrelpath(sub))
                     sr = sub.commit(cctx._text, user, date)
                     newstate[s] = (newstate[s][0], sr)
                 subrepo.writestate(self, newstate)
 
             # Save commit message in case this transaction gets rolled back
             # (e.g. by a pretxncommit hook).  Leave the content alone on
             # the assumption that the user will use the same editor again.
             msgfn = self.savecommitmessage(cctx._text)
 
             p1, p2 = self.dirstate.parents()
             hookp1, hookp2 = hex(p1), (p2 != nullid and hex(p2) or '')
             try:
                 self.hook("precommit", throw=True, parent1=hookp1,
                           parent2=hookp2)
                 ret = self.commitctx(cctx, True)
             except: # re-raises
                 if edited:
                     self.ui.write(
                         _('note: commit message saved in %s\n') % msgfn)
                 raise
 
             # update bookmarks, dirstate and mergestate
             bookmarks.update(self, [p1, p2], ret)
             cctx.markcommitted(ret)
             ms.reset()
         finally:
             wlock.release()
 
         def commithook(node=hex(ret), parent1=hookp1, parent2=hookp2):
             self.hook("commit", node=node, parent1=parent1, parent2=parent2)
         self._afterlock(commithook)
         return ret
 
     @unfilteredmethod
     def commitctx(self, ctx, error=False):
         """Add a new revision to current repository.
         Revision information is passed via the context argument.
         """
 
         tr = lock = None
         removed = list(ctx.removed())
         p1, p2 = ctx.p1(), ctx.p2()
         user = ctx.user()
 
         lock = self.lock()
         try:
             tr = self.transaction("commit")
             trp = weakref.proxy(tr)
 
             if ctx.files():
                 m1 = p1.manifest().copy()
                 m2 = p2.manifest()
 
                 # check in files
                 new = {}
                 changed = []
                 linkrev = len(self)
                 for f in sorted(ctx.modified() + ctx.added()):
                     self.ui.note(f + "\n")
                     try:
                         fctx = ctx[f]
                         new[f] = self._filecommit(fctx, m1, m2, linkrev, trp,
                                                   changed)
                         m1.set(f, fctx.flags())
                     except OSError, inst:
                         self.ui.warn(_("trouble committing %s!\n") % f)
                         raise
                     except IOError, inst:
                         errcode = getattr(inst, 'errno', errno.ENOENT)
                         if error or errcode and errcode != errno.ENOENT:
                             self.ui.warn(_("trouble committing %s!\n") % f)
                             raise
                         else:
                             removed.append(f)
 
                 # update manifest
                 m1.update(new)
                 removed = [f for f in sorted(removed) if f in m1 or f in m2]
                 drop = [f for f in removed if f in m1]
                 for f in drop:
                     del m1[f]
                 mn = self.manifest.add(m1, trp, linkrev, p1.manifestnode(),
                                        p2.manifestnode(), (new, drop))
                 files = changed + removed
             else:
                 mn = p1.manifestnode()
                 files = []
 
             # update changelog
             self.changelog.delayupdate()
             n = self.changelog.add(mn, files, ctx.description(),
                                    trp, p1.node(), p2.node(),
                                    user, ctx.date(), ctx.extra().copy())
             p = lambda: self.changelog.writepending() and self.root or ""
             xp1, xp2 = p1.hex(), p2 and p2.hex() or ''
             self.hook('pretxncommit', throw=True, node=hex(n), parent1=xp1,
                       parent2=xp2, pending=p)
             self.changelog.finalize(trp)
             # set the new commit is proper phase
             targetphase = phases.newcommitphase(self.ui)
             if targetphase:
                 # retract boundary do not alter parent changeset.
                 # if a parent have higher the resulting phase will
                 # be compliant anyway
                 #
                 # if minimal phase was 0 we don't need to retract anything
                 phases.retractboundary(self, targetphase, [n])
             tr.close()
             branchmap.updatecache(self.filtered('served'))
             return n
         finally:
             if tr:
                 tr.release()
             lock.release()
 
     @unfilteredmethod
     def destroying(self):
         '''Inform the repository that nodes are about to be destroyed.
         Intended for use by strip and rollback, so there's a common
         place for anything that has to be done before destroying history.
 
         This is mostly useful for saving state that is in memory and waiting
         to be flushed when the current lock is released. Because a call to
         destroyed is imminent, the repo will be invalidated causing those
         changes to stay in memory (waiting for the next unlock), or vanish
         completely.
         '''
         # When using the same lock to commit and strip, the phasecache is left
         # dirty after committing. Then when we strip, the repo is invalidated,
         # causing those changes to disappear.
         if '_phasecache' in vars(self):
             self._phasecache.write()
 
     @unfilteredmethod
     def destroyed(self):
         '''Inform the repository that nodes have been destroyed.
         Intended for use by strip and rollback, so there's a common
         place for anything that has to be done after destroying history.
         '''
         # When one tries to:
         # 1) destroy nodes thus calling this method (e.g. strip)
         # 2) use phasecache somewhere (e.g. commit)
         #
         # then 2) will fail because the phasecache contains nodes that were
         # removed. We can either remove phasecache from the filecache,
         # causing it to reload next time it is accessed, or simply filter
         # the removed nodes now and write the updated cache.
         self._phasecache.filterunknown(self)
         self._phasecache.write()
 
         # update the 'served' branch cache to help read only server process
         # Thanks to branchcache collaboration this is done from the nearest
         # filtered subset and it is expected to be fast.
         branchmap.updatecache(self.filtered('served'))
 
         # Ensure the persistent tag cache is updated.  Doing it now
         # means that the tag cache only has to worry about destroyed
         # heads immediately after a strip/rollback.  That in turn
         # guarantees that "cachetip == currenttip" (comparing both rev
         # and node) always means no nodes have been added or destroyed.
 
         # XXX this is suboptimal when qrefresh'ing: we strip the current
         # head, refresh the tag cache, then immediately add a new head.
         # But I think doing it this way is necessary for the "instant
         # tag cache retrieval" case to work.
         self.invalidate()
 
     def walk(self, match, node=None):
         '''
         walk recursively through the directory tree or a given
         changeset, finding all files matched by the match
         function
         '''
         return self[node].walk(match)
 
     def status(self, node1='.', node2=None, match=None,
                ignored=False, clean=False, unknown=False,
                listsubrepos=False):
         """return status of files between two nodes or node and working
         directory.
 
         If node1 is None, use the first dirstate parent instead.
         If node2 is None, compare node1 with working directory.
         """
 
         def mfmatches(ctx):
             mf = ctx.manifest().copy()
             if match.always():
                 return mf
             for fn in mf.keys():
                 if not match(fn):
                     del mf[fn]
             return mf
 
         ctx1 = self[node1]
         ctx2 = self[node2]
 
         working = ctx2.rev() is None
         parentworking = working and ctx1 == self['.']
         match = match or matchmod.always(self.root, self.getcwd())
         listignored, listclean, listunknown = ignored, clean, unknown
 
         # load earliest manifest first for caching reasons
         if not working and ctx2.rev() < ctx1.rev():
             ctx2.manifest()
 
         if not parentworking:
             def bad(f, msg):
                 # 'f' may be a directory pattern from 'match.files()',
                 # so 'f not in ctx1' is not enough
                 if f not in ctx1 and f not in ctx1.dirs():
                     self.ui.warn('%s: %s\n' % (self.dirstate.pathto(f), msg))
             match.bad = bad
 
         if working: # we need to scan the working dir
             subrepos = []
             if '.hgsub' in self.dirstate:
                 subrepos = sorted(ctx2.substate)
             s = self.dirstate.status(match, subrepos, listignored,
                                      listclean, listunknown)
             cmp, modified, added, removed, deleted, unknown, ignored, clean = s
 
             # check for any possibly clean files
             if parentworking and cmp:
                 fixup = []
                 # do a full compare of any files that might have changed
                 for f in sorted(cmp):
                     if (f not in ctx1 or ctx2.flags(f) != ctx1.flags(f)
                         or ctx1[f].cmp(ctx2[f])):
                         modified.append(f)
                     else:
                         fixup.append(f)
 
                 # update dirstate for files that are actually clean
                 if fixup:
                     if listclean:
                         clean += fixup
 
                     try:
                         # updating the dirstate is optional
                         # so we don't wait on the lock
                         wlock = self.wlock(False)
                         try:
                             for f in fixup:
                                 self.dirstate.normal(f)
                         finally:
                             wlock.release()
                     except error.LockError:
                         pass
 
         if not parentworking:
             mf1 = mfmatches(ctx1)
             if working:
                 # we are comparing working dir against non-parent
                 # generate a pseudo-manifest for the working dir
                 mf2 = mfmatches(self['.'])
                 for f in cmp + modified + added:
                     mf2[f] = None
                     mf2.set(f, ctx2.flags(f))
                 for f in removed:
                     if f in mf2:
                         del mf2[f]
             else:
                 # we are comparing two revisions
                 deleted, unknown, ignored = [], [], []
                 mf2 = mfmatches(ctx2)
 
             modified, added, clean = [], [], []
             withflags = mf1.withflags() | mf2.withflags()
             for fn, mf2node in mf2.iteritems():
                 if fn in mf1:
                     if (fn not in deleted and
                         ((fn in withflags and mf1.flags(fn) != mf2.flags(fn)) or
                          (mf1[fn] != mf2node and
                           (mf2node or ctx1[fn].cmp(ctx2[fn]))))):
                         modified.append(fn)
                     elif listclean:
                         clean.append(fn)
                     del mf1[fn]
                 elif fn not in deleted:
                     added.append(fn)
             removed = mf1.keys()
 
         if working and modified and not self.dirstate._checklink:
             # Symlink placeholders may get non-symlink-like contents
             # via user error or dereferencing by NFS or Samba servers,
             # so we filter out any placeholders that don't look like a
             # symlink
             sane = []
             for f in modified:
                 if ctx2.flags(f) == 'l':
                     d = ctx2[f].data()
                     if d == '' or len(d) >= 1024 or '\n' in d or util.binary(d):
                         self.ui.debug('ignoring suspect symlink placeholder'
                                       ' "%s"\n' % f)
                         continue
                 sane.append(f)
             modified = sane
 
         r = modified, added, removed, deleted, unknown, ignored, clean
 
         if listsubrepos:
             for subpath, sub in subrepo.itersubrepos(ctx1, ctx2):
                 if working:
                     rev2 = None
                 else:
                     rev2 = ctx2.substate[subpath][1]
                 try:
                     submatch = matchmod.narrowmatcher(subpath, match)
                     s = sub.status(rev2, match=submatch, ignored=listignored,
                                    clean=listclean, unknown=listunknown,
                                    listsubrepos=True)
                     for rfiles, sfiles in zip(r, s):
                         rfiles.extend("%s/%s" % (subpath, f) for f in sfiles)
                 except error.LookupError:
                     self.ui.status(_("skipping missing subrepository: %s\n")
                                    % subpath)
 
         for l in r:
             l.sort()
         return r
 
     def heads(self, start=None):
         heads = self.changelog.heads(start)
         # sort the output in rev descending order
         return sorted(heads, key=self.changelog.rev, reverse=True)
 
     def branchheads(self, branch=None, start=None, closed=False):
         '''return a (possibly filtered) list of heads for the given branch
 
         Heads are returned in topological order, from newest to oldest.
         If branch is None, use the dirstate branch.
         If start is not None, return only heads reachable from start.
         If closed is True, return heads that are marked as closed as well.
         '''
         if branch is None:
             branch = self[None].branch()
         branches = self.branchmap()
         if branch not in branches:
             return []
         # the cache returns heads ordered lowest to highest
         bheads = list(reversed(branches[branch]))
         if start is not None:
             # filter out the heads that cannot be reached from startrev
             fbheads = set(self.changelog.nodesbetween([start], bheads)[2])
             bheads = [h for h in bheads if h in fbheads]
         if not closed:
             bheads = [h for h in bheads if not self[h].closesbranch()]
         return bheads
 
     def branches(self, nodes):
         if not nodes:
             nodes = [self.changelog.tip()]
         b = []
         for n in nodes:
             t = n
             while True:
                 p = self.changelog.parents(n)
                 if p[1] != nullid or p[0] == nullid:
                     b.append((t, n, p[0], p[1]))
                     break
                 n = p[0]
         return b
 
     def between(self, pairs):
         r = []
 
         for top, bottom in pairs:
             n, l, i = top, [], 0
             f = 1
 
             while n != bottom and n != nullid:
                 p = self.changelog.parents(n)[0]
                 if i == f:
                     l.append(n)
                     f = f * 2
                 n = p
                 i += 1
 
             r.append(l)
 
         return r
 
     def pull(self, remote, heads=None, force=False):
         if remote.local():
             missing = set(remote.requirements) - self.supported
             if missing:
                 msg = _("required features are not"
                         " supported in the destination:"
                         " %s") % (', '.join(sorted(missing)))
                 raise util.Abort(msg)
 
         # don't open transaction for nothing or you break future useful
         # rollback call
         tr = None
         trname = 'pull\n' + util.hidepassword(remote.url())
         lock = self.lock()
         try:
             tmp = discovery.findcommonincoming(self, remote, heads=heads,
                                                force=force)
             common, fetch, rheads = tmp
             if not fetch:
                 self.ui.status(_("no changes found\n"))
                 added = []
                 result = 0
             else:
                 tr = self.transaction(trname)
                 if heads is None and list(common) == [nullid]:
                     self.ui.status(_("requesting all changes\n"))
                 elif heads is None and remote.capable('changegroupsubset'):
                     # issue1320, avoid a race if remote changed after discovery
                     heads = rheads
 
                 if remote.capable('getbundle'):
                     # TODO: get bundlecaps from remote
                     cg = remote.getbundle('pull', common=common,
                                           heads=heads or rheads)
                 elif heads is None:
                     cg = remote.changegroup(fetch, 'pull')
                 elif not remote.capable('changegroupsubset'):
                     raise util.Abort(_("partial pull cannot be done because "
                                            "other repository doesn't support "
                                            "changegroupsubset."))
                 else:
                     cg = remote.changegroupsubset(fetch, heads, 'pull')
                 # we use unfiltered changelog here because hidden revision must
                 # be taken in account for phase synchronization. They may
                 # becomes public and becomes visible again.
                 cl = self.unfiltered().changelog
                 clstart = len(cl)
                 result = self.addchangegroup(cg, 'pull', remote.url())
                 clend = len(cl)
                 added = [cl.node(r) for r in xrange(clstart, clend)]
 
             # compute target subset
             if heads is None:
                 # We pulled every thing possible
                 # sync on everything common
                 subset = common + added
             else:
                 # We pulled a specific subset
                 # sync on this subset
                 subset = heads
 
             # Get remote phases data from remote
             remotephases = remote.listkeys('phases')
             publishing = bool(remotephases.get('publishing', False))
             if remotephases and not publishing:
                 # remote is new and unpublishing
                 pheads, _dr = phases.analyzeremotephases(self, subset,
                                                          remotephases)
                 phases.advanceboundary(self, phases.public, pheads)
                 phases.advanceboundary(self, phases.draft, subset)
             else:
                 # Remote is old or publishing all common changesets
                 # should be seen as public
                 phases.advanceboundary(self, phases.public, subset)
 
             def gettransaction():
                 if tr is None:
                     return self.transaction(trname)
                 return tr
 
             obstr = obsolete.syncpull(self, remote, gettransaction)
             if obstr is not None:
                 tr = obstr
 
             if tr is not None:
                 tr.close()
         finally:
             if tr is not None:
                 tr.release()
             lock.release()
 
         return result
 
     def checkpush(self, force, revs):
         """Extensions can override this function if additional checks have
         to be performed before pushing, or call it if they override push
         command.
         """
         pass
 
     def push(self, remote, force=False, revs=None, newbranch=False):
         '''Push outgoing changesets (limited by revs) from the current
         repository to remote. Return an integer:
           - None means nothing to push
           - 0 means HTTP error
           - 1 means we pushed and remote head count is unchanged *or*
             we have outgoing changesets but refused to push
           - other values as described by addchangegroup()
         '''
         if remote.local():
             missing = set(self.requirements) - remote.local().supported
             if missing:
                 msg = _("required features are not"
                         " supported in the destination:"
                         " %s") % (', '.join(sorted(missing)))
                 raise util.Abort(msg)
 
         # there are two ways to push to remote repo:
         #
         # addchangegroup assumes local user can lock remote
         # repo (local filesystem, old ssh servers).
         #
         # unbundle assumes local user cannot lock remote repo (new ssh
         # servers, http servers).
 
         if not remote.canpush():
             raise util.Abort(_("destination does not support push"))
         unfi = self.unfiltered()
         def localphasemove(nodes, phase=phases.public):
             """move <nodes> to <phase> in the local source repo"""
             if locallock is not None:
                 phases.advanceboundary(self, phase, nodes)
             else:
                 # repo is not locked, do not change any phases!
                 # Informs the user that phases should have been moved when
                 # applicable.
                 actualmoves = [n for n in nodes if phase < self[n].phase()]
                 phasestr = phases.phasenames[phase]
                 if actualmoves:
                     self.ui.status(_('cannot lock source repo, skipping local'
                                      ' %s phase update\n') % phasestr)
         # get local lock as we might write phase data
         locallock = None
         try:
             locallock = self.lock()
         except IOError, err:
             if err.errno != errno.EACCES:
                 raise
             # source repo cannot be locked.
             # We do not abort the push, but just disable the local phase
             # synchronisation.
             msg = 'cannot lock source repository: %s\n' % err
             self.ui.debug(msg)
         try:
             self.checkpush(force, revs)
             lock = None
             unbundle = remote.capable('unbundle')
             if not unbundle:
                 lock = remote.lock()
             try:
                 # discovery
                 fci = discovery.findcommonincoming
                 commoninc = fci(unfi, remote, force=force)
                 common, inc, remoteheads = commoninc
                 fco = discovery.findcommonoutgoing
                 outgoing = fco(unfi, remote, onlyheads=revs,
                                commoninc=commoninc, force=force)
 
 
                 if not outgoing.missing:
                     # nothing to push
                     scmutil.nochangesfound(unfi.ui, unfi, outgoing.excluded)
                     ret = None
                 else:
                     # something to push
                     if not force:
                         # if self.obsstore == False --> no obsolete
                         # then, save the iteration
                         if unfi.obsstore:
                             # this message are here for 80 char limit reason
                             mso = _("push includes obsolete changeset: %s!")
                             mst = "push includes %s changeset: %s!"
                             # plain versions for i18n tool to detect them
                             _("push includes unstable changeset: %s!")
                             _("push includes bumped changeset: %s!")
                             _("push includes divergent changeset: %s!")
                             # If we are to push if there is at least one
                             # obsolete or unstable changeset in missing, at
                             # least one of the missinghead will be obsolete or
                             # unstable. So checking heads only is ok
                             for node in outgoing.missingheads:
                                 ctx = unfi[node]
                                 if ctx.obsolete():
                                     raise util.Abort(mso % ctx)
                                 elif ctx.troubled():
                                     raise util.Abort(_(mst)
                                                      % (ctx.troubles()[0],
                                                         ctx))
                         discovery.checkheads(unfi, remote, outgoing,
                                              remoteheads, newbranch,
                                              bool(inc))
 
                     # TODO: get bundlecaps from remote
                     bundlecaps = None
                     # create a changegroup from local
                     if revs is None and not outgoing.excluded:
                         # push everything,
                         # use the fast path, no race possible on push
                         bundler = changegroup.bundle10(self, bundlecaps)
                         cg = self._changegroupsubset(outgoing,
                                                      bundler,
                                                      'push',
                                                      fastpath=True)
                     else:
                         cg = self.getlocalbundle('push', outgoing, bundlecaps)
 
                     # apply changegroup to remote
                     if unbundle:
                         # local repo finds heads on server, finds out what
                         # revs it must push. once revs transferred, if server
                         # finds it has different heads (someone else won
                         # commit/push race), server aborts.
                         if force:
                             remoteheads = ['force']
                         # ssh: return remote's addchangegroup()
                         # http: return remote's addchangegroup() or 0 for error
                         ret = remote.unbundle(cg, remoteheads, 'push')
                     else:
                         # we return an integer indicating remote head count
                         # change
                         ret = remote.addchangegroup(cg, 'push', self.url())
 
                 if ret:
                     # push succeed, synchronize target of the push
                     cheads = outgoing.missingheads
                 elif revs is None:
                     # All out push fails. synchronize all common
                     cheads = outgoing.commonheads
                 else:
                     # I want cheads = heads(::missingheads and ::commonheads)
                     # (missingheads is revs with secret changeset filtered out)
                     #
                     # This can be expressed as:
                     #     cheads = ( (missingheads and ::commonheads)
                     #              + (commonheads and ::missingheads))"
                     #              )
                     #
                     # while trying to push we already computed the following:
                     #     common = (::commonheads)
                     #     missing = ((commonheads::missingheads) - commonheads)
                     #
                     # We can pick:
                     # * missingheads part of common (::commonheads)
                     common = set(outgoing.common)
                     cheads = [node for node in revs if node in common]
                     # and
                     # * commonheads parents on missing
                     revset = unfi.set('%ln and parents(roots(%ln))',
                                      outgoing.commonheads,
                                      outgoing.missing)
                     cheads.extend(c.node() for c in revset)
                 # even when we don't push, exchanging phase data is useful
                 remotephases = remote.listkeys('phases')
                 if (self.ui.configbool('ui', '_usedassubrepo', False)
                     and remotephases    # server supports phases
                     and ret is None # nothing was pushed
                     and remotephases.get('publishing', False)):
                     # When:
                     # - this is a subrepo push
                     # - and remote support phase
                     # - and no changeset was pushed
                     # - and remote is publishing
                     # We may be in issue 3871 case!
                     # We drop the possible phase synchronisation done by
                     # courtesy to publish changesets possibly locally draft
                     # on the remote.
                     remotephases = {'publishing': 'True'}
                 if not remotephases: # old server or public only repo
                     localphasemove(cheads)
                     # don't push any phase data as there is nothing to push
                 else:
                     ana = phases.analyzeremotephases(self, cheads, remotephases)
                     pheads, droots = ana
                     ### Apply remote phase on local
                     if remotephases.get('publishing', False):
                         localphasemove(cheads)
                     else: # publish = False
                         localphasemove(pheads)
                         localphasemove(cheads, phases.draft)
                     ### Apply local phase on remote
 
                     # Get the list of all revs draft on remote by public here.
                     # XXX Beware that revset break if droots is not strictly
                     # XXX root we may want to ensure it is but it is costly
                     outdated =  unfi.set('heads((%ln::%ln) and public())',
                                          droots, cheads)
                     for newremotehead in outdated:
                         r = remote.pushkey('phases',
                                            newremotehead.hex(),
                                            str(phases.draft),
                                            str(phases.public))
                         if not r:
                             self.ui.warn(_('updating %s to public failed!\n')
                                             % newremotehead)
                 self.ui.debug('try to push obsolete markers to remote\n')
                 obsolete.syncpush(self, remote)
             finally:
                 if lock is not None:
                     lock.release()
         finally:
             if locallock is not None:
                 locallock.release()
 
         bookmarks.updateremote(self.ui, unfi, remote, revs)
         return ret
 
     def changegroupinfo(self, nodes, source):
         if self.ui.verbose or source == 'bundle':
             self.ui.status(_("%d changesets found\n") % len(nodes))
         if self.ui.debugflag:
             self.ui.debug("list of changesets:\n")
             for node in nodes:
                 self.ui.debug("%s\n" % hex(node))
 
     def changegroupsubset(self, bases, heads, source):
         """Compute a changegroup consisting of all the nodes that are
         descendants of any of the bases and ancestors of any of the heads.
         Return a chunkbuffer object whose read() method will return
         successive changegroup chunks.
 
         It is fairly complex as determining which filenodes and which
         manifest nodes need to be included for the changeset to be complete
         is non-trivial.
 
         Another wrinkle is doing the reverse, figuring out which changeset in
         the changegroup a particular filenode or manifestnode belongs to.
         """
         cl = self.changelog
         if not bases:
             bases = [nullid]
         # TODO: remove call to nodesbetween.
         csets, bases, heads = cl.nodesbetween(bases, heads)
         bases = [p for n in bases for p in cl.parents(n) if p != nullid]
         outgoing = discovery.outgoing(cl, bases, heads)
         bundler = changegroup.bundle10(self)
         return self._changegroupsubset(outgoing, bundler, source)
 
     def getlocalbundle(self, source, outgoing, bundlecaps=None):
         """Like getbundle, but taking a discovery.outgoing as an argument.
 
         This is only implemented for local repos and reuses potentially
         precomputed sets in outgoing."""
         if not outgoing.missing:
             return None
         bundler = changegroup.bundle10(self, bundlecaps)
         return self._changegroupsubset(outgoing, bundler, source)
 
     def getbundle(self, source, heads=None, common=None, bundlecaps=None):
         """Like changegroupsubset, but returns the set difference between the
         ancestors of heads and the ancestors common.
 
         If heads is None, use the local heads. If common is None, use [nullid].
 
         The nodes in common might not all be known locally due to the way the
         current discovery protocol works.
         """
         cl = self.changelog
         if common:
             hasnode = cl.hasnode
             common = [n for n in common if hasnode(n)]
         else:
             common = [nullid]
         if not heads:
             heads = cl.heads()
         return self.getlocalbundle(source,
                                    discovery.outgoing(cl, common, heads),
                                    bundlecaps=bundlecaps)
 
     @unfilteredmethod
     def _changegroupsubset(self, outgoing, bundler, source,
                            fastpath=False):
         commonrevs = outgoing.common
         csets = outgoing.missing
         heads = outgoing.missingheads
         # We go through the fast path if we get told to, or if all (unfiltered
         # heads have been requested (since we then know there all linkrevs will
         # be pulled by the client).
         heads.sort()
         fastpathlinkrev = fastpath or (
                 self.filtername is None and heads == sorted(self.heads()))
 
         self.hook('preoutgoing', throw=True, source=source)
         self.changegroupinfo(csets, source)
         gengroup = bundler.generate(commonrevs, csets, fastpathlinkrev, source)
         return changegroup.unbundle10(util.chunkbuffer(gengroup), 'UN')
 
     def changegroup(self, basenodes, source):
         # to avoid a race we use changegroupsubset() (issue1320)
         return self.changegroupsubset(basenodes, self.heads(), source)
 
     @unfilteredmethod
     def addchangegroup(self, source, srctype, url, emptyok=False):
         """Add the changegroup returned by source.read() to this repo.
         srctype is a string like 'push', 'pull', or 'unbundle'.  url is
         the URL of the repo where this changegroup is coming from.
 
         Return an integer summarizing the change to this repo:
         - nothing changed or no source: 0
         - more heads than before: 1+added heads (2..n)
         - fewer heads than before: -1-removed heads (-2..-n)
         - number of heads stays the same: 1
         """
         def csmap(x):
             self.ui.debug("add changeset %s\n" % short(x))
             return len(cl)
 
         def revmap(x):
             return cl.rev(x)
 
         if not source:
             return 0
 
         self.hook('prechangegroup', throw=True, source=srctype, url=url)
 
         changesets = files = revisions = 0
         efiles = set()
 
         # write changelog data to temp files so concurrent readers will not see
         # inconsistent view
         cl = self.changelog
         cl.delayupdate()
         oldheads = cl.heads()
 
         tr = self.transaction("\n".join([srctype, util.hidepassword(url)]))
         try:
             trp = weakref.proxy(tr)
             # pull off the changeset group
             self.ui.status(_("adding changesets\n"))
             clstart = len(cl)
             class prog(object):
                 step = _('changesets')
                 count = 1
                 ui = self.ui
                 total = None
                 def __call__(self):
                     self.ui.progress(self.step, self.count, unit=_('chunks'),
                                      total=self.total)
                     self.count += 1
             pr = prog()
             source.callback = pr
 
             source.changelogheader()
             srccontent = cl.addgroup(source, csmap, trp)
             if not (srccontent or emptyok):
                 raise util.Abort(_("received changelog group is empty"))
             clend = len(cl)
             changesets = clend - clstart
             for c in xrange(clstart, clend):
                 efiles.update(self[c].files())
             efiles = len(efiles)
             self.ui.progress(_('changesets'), None)
 
             # pull off the manifest group
             self.ui.status(_("adding manifests\n"))
             pr.step = _('manifests')
             pr.count = 1
             pr.total = changesets # manifests <= changesets
             # no need to check for empty manifest group here:
             # if the result of the merge of 1 and 2 is the same in 3 and 4,
             # no new manifest will be created and the manifest group will
             # be empty during the pull
             source.manifestheader()
             self.manifest.addgroup(source, revmap, trp)
             self.ui.progress(_('manifests'), None)
 
             needfiles = {}
             if self.ui.configbool('server', 'validate', default=False):
                 # validate incoming csets have their manifests
                 for cset in xrange(clstart, clend):
                     mfest = self.changelog.read(self.changelog.node(cset))[0]
                     mfest = self.manifest.readdelta(mfest)
                     # store file nodes we must see
                     for f, n in mfest.iteritems():
                         needfiles.setdefault(f, set()).add(n)
 
             # process the files
             self.ui.status(_("adding file changes\n"))
             pr.step = _('files')
             pr.count = 1
             pr.total = efiles
             source.callback = None
 
             newrevs, newfiles = self.addchangegroupfiles(source, revmap, trp,
                                                          pr, needfiles)
             revisions += newrevs
             files += newfiles
 
             dh = 0
             if oldheads:
                 heads = cl.heads()
                 dh = len(heads) - len(oldheads)
                 for h in heads:
                     if h not in oldheads and self[h].closesbranch():
                         dh -= 1
             htext = ""
             if dh:
                 htext = _(" (%+d heads)") % dh
 
             self.ui.status(_("added %d changesets"
                              " with %d changes to %d files%s\n")
                              % (changesets, revisions, files, htext))
             self.invalidatevolatilesets()
 
             if changesets > 0:
                 p = lambda: cl.writepending() and self.root or ""
                 self.hook('pretxnchangegroup', throw=True,
                           node=hex(cl.node(clstart)), source=srctype,
                           url=url, pending=p)
 
             added = [cl.node(r) for r in xrange(clstart, clend)]
             publishing = self.ui.configbool('phases', 'publish', True)
             if srctype == 'push':
                 # Old server can not push the boundary themself.
                 # New server won't push the boundary if changeset already
                 # existed locally as secrete
                 #
                 # We should not use added here but the list of all change in
                 # the bundle
                 if publishing:
                     phases.advanceboundary(self, phases.public, srccontent)
                 else:
                     phases.advanceboundary(self, phases.draft, srccontent)
                     phases.retractboundary(self, phases.draft, added)
             elif srctype != 'strip':
                 # publishing only alter behavior during push
                 #
                 # strip should not touch boundary at all
                 phases.retractboundary(self, phases.draft, added)
 
             # make changelog see real files again
             cl.finalize(trp)
 
             tr.close()
 
             if changesets > 0:
                 if srctype != 'strip':
                     # During strip, branchcache is invalid but coming call to
                     # `destroyed` will repair it.
                     # In other case we can safely update cache on disk.
                     branchmap.updatecache(self.filtered('served'))
                 def runhooks():
                     # These hooks run when the lock releases, not when the
                     # transaction closes. So it's possible for the changelog
                     # to have changed since we last saw it.
                     if clstart >= len(self):
                         return
 
                     # forcefully update the on-disk branch cache
                     self.ui.debug("updating the branch cache\n")
                     self.hook("changegroup", node=hex(cl.node(clstart)),
                               source=srctype, url=url)
 
                     for n in added:
                         self.hook("incoming", node=hex(n), source=srctype,
                                   url=url)
 
                     newheads = [h for h in self.heads() if h not in oldheads]
                     self.ui.log("incoming",
                                 "%s incoming changes - new heads: %s\n",
                                 len(added),
                                 ', '.join([hex(c[:6]) for c in newheads]))
                 self._afterlock(runhooks)
 
         finally:
             tr.release()
         # never return 0 here:
         if dh < 0:
             return dh - 1
         else:
             return dh + 1
 
     def addchangegroupfiles(self, source, revmap, trp, pr, needfiles):
         revisions = 0
         files = 0
         while True:
             chunkdata = source.filelogheader()
             if not chunkdata:
                 break
             f = chunkdata["filename"]
             self.ui.debug("adding %s revisions\n" % f)
             pr()
             fl = self.file(f)
             o = len(fl)
             if not fl.addgroup(source, revmap, trp):
                 raise util.Abort(_("received file revlog group is empty"))
             revisions += len(fl) - o
             files += 1
             if f in needfiles:
                 needs = needfiles[f]
                 for new in xrange(o, len(fl)):
                     n = fl.node(new)
                     if n in needs:
                         needs.remove(n)
                     else:
                         raise util.Abort(
                             _("received spurious file revlog entry"))
                 if not needs:
                     del needfiles[f]
         self.ui.progress(_('files'), None)
 
         for f, needs in needfiles.iteritems():
             fl = self.file(f)
             for n in needs:
                 try:
                     fl.rev(n)
                 except error.LookupError:
                     raise util.Abort(
                         _('missing file data for %s:%s - run hg verify') %
                         (f, hex(n)))
 
         return revisions, files
 
     def stream_in(self, remote, requirements):
         lock = self.lock()
         try:
             # Save remote branchmap. We will use it later
             # to speed up branchcache creation
             rbranchmap = None
             if remote.capable("branchmap"):
                 rbranchmap = remote.branchmap()
 
             fp = remote.stream_out()
             l = fp.readline()
             try:
                 resp = int(l)
             except ValueError:
                 raise error.ResponseError(
                     _('unexpected response from remote server:'), l)
             if resp == 1:
                 raise util.Abort(_('operation forbidden by server'))
             elif resp == 2:
                 raise util.Abort(_('locking the remote repository failed'))
             elif resp != 0:
                 raise util.Abort(_('the server sent an unknown error code'))
             self.ui.status(_('streaming all changes\n'))
             l = fp.readline()
             try:
                 total_files, total_bytes = map(int, l.split(' ', 1))
             except (ValueError, TypeError):
                 raise error.ResponseError(
                     _('unexpected response from remote server:'), l)
             self.ui.status(_('%d files to transfer, %s of data\n') %
                            (total_files, util.bytecount(total_bytes)))
             handled_bytes = 0
             self.ui.progress(_('clone'), 0, total=total_bytes)
             start = time.time()
             for i in xrange(total_files):
                 # XXX doesn't support '\n' or '\r' in filenames
                 l = fp.readline()
                 try:
                     name, size = l.split('\0', 1)
                     size = int(size)
                 except (ValueError, TypeError):
                     raise error.ResponseError(
                         _('unexpected response from remote server:'), l)
                 if self.ui.debugflag:
                     self.ui.debug('adding %s (%s)\n' %
                                   (name, util.bytecount(size)))
                 # for backwards compat, name was partially encoded
                 ofp = self.sopener(store.decodedir(name), 'w')
                 for chunk in util.filechunkiter(fp, limit=size):
                     handled_bytes += len(chunk)
                     self.ui.progress(_('clone'), handled_bytes,
                                      total=total_bytes)
                     ofp.write(chunk)
                 ofp.close()
             elapsed = time.time() - start
             if elapsed <= 0:
                 elapsed = 0.001
             self.ui.progress(_('clone'), None)
             self.ui.status(_('transferred %s in %.1f seconds (%s/sec)\n') %
                            (util.bytecount(total_bytes), elapsed,
                             util.bytecount(total_bytes / elapsed)))
 
             # new requirements = old non-format requirements +
             #                    new format-related
             # requirements from the streamed-in repository
             requirements.update(set(self.requirements) - self.supportedformats)
             self._applyrequirements(requirements)
             self._writerequirements()
 
             if rbranchmap:
                 rbheads = []
                 for bheads in rbranchmap.itervalues():
                     rbheads.extend(bheads)
 
                 if rbheads:
                     rtiprev = max((int(self.changelog.rev(node))
                             for node in rbheads))
                     cache = branchmap.branchcache(rbranchmap,
                                                   self[rtiprev].node(),
                                                   rtiprev)
                     # Try to stick it as low as possible
                     # filter above served are unlikely to be fetch from a clone
                     for candidate in ('base', 'immutable', 'served'):
                         rview = self.filtered(candidate)
                         if cache.validfor(rview):
                             self._branchcaches[candidate] = cache
                             cache.write(rview)
                             break
             self.invalidate()
             return len(self.heads()) + 1
         finally:
             lock.release()
 
     def clone(self, remote, heads=[], stream=False):
         '''clone remote repository.
 
         keyword arguments:
         heads: list of revs to clone (forces use of pull)
         stream: use streaming clone if possible'''
 
         # now, all clients that can request uncompressed clones can
         # read repo formats supported by all servers that can serve
         # them.
 
         # if revlog format changes, client will have to check version
         # and format flags on "stream" capability, and use
         # uncompressed only if compatible.
 
         if not stream:
             # if the server explicitly prefers to stream (for fast LANs)
             stream = remote.capable('stream-preferred')
 
         if stream and not heads:
             # 'stream' means remote revlog format is revlogv1 only
             if remote.capable('stream'):
                 return self.stream_in(remote, set(('revlogv1',)))
             # otherwise, 'streamreqs' contains the remote revlog format
             streamreqs = remote.capable('streamreqs')
             if streamreqs:
                 streamreqs = set(streamreqs.split(','))
                 # if we support it, stream in and adjust our requirements
                 if not streamreqs - self.supportedformats:
                     return self.stream_in(remote, streamreqs)
         return self.pull(remote, heads)
 
     def pushkey(self, namespace, key, old, new):
         self.hook('prepushkey', throw=True, namespace=namespace, key=key,
                   old=old, new=new)
         self.ui.debug('pushing key for "%s:%s"\n' % (namespace, key))
         ret = pushkey.push(self, namespace, key, old, new)
         self.hook('pushkey', namespace=namespace, key=key, old=old, new=new,
                   ret=ret)
         return ret
 
     def listkeys(self, namespace):
         self.hook('prelistkeys', throw=True, namespace=namespace)
         self.ui.debug('listing keys for "%s"\n' % namespace)
         values = pushkey.list(self, namespace)
         self.hook('listkeys', namespace=namespace, values=values)
         return values
 
     def debugwireargs(self, one, two, three=None, four=None, five=None):
         '''used to test argument passing over the wire'''
         return "%s %s %s %s %s" % (one, two, three, four, five)
 
     def savecommitmessage(self, text):
         fp = self.opener('last-message.txt', 'wb')
         try:
             fp.write(text)
         finally:
             fp.close()
         return self.pathto(fp.name[len(self.root) + 1:])
 
 # used to avoid circular references so destructors work
 def aftertrans(files):
     renamefiles = [tuple(t) for t in files]
     def a():
         for vfs, src, dest in renamefiles:
             try:
                 vfs.rename(src, dest)
             except OSError: # journal file does not yet exist
                 pass
     return a
 
 def undoname(fn):
     base, name = os.path.split(fn)
     assert name.startswith('journal')
     return os.path.join(base, name.replace('journal', 'undo', 1))
 
 def instance(ui, path, create):
     return localrepository(ui, util.urllocalpath(path), create)
 
 def islocal(path):
     return True

mercurial/match.py

@@ -1,358 +1,358 b''
 # match.py - filename matching
 #
 #  Copyright 2008, 2009 Matt Mackall <[e-mail]> and others
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 import re
-import scmutil, util, fileset
+import util, fileset, pathutil
 from i18n import _
 
 def _rematcher(pat):
     m = util.compilere(pat)
     try:
         # slightly faster, provided by facebook's re2 bindings
         return m.test_match
     except AttributeError:
         return m.match
 
 def _expandsets(pats, ctx):
     '''convert set: patterns into a list of files in the given context'''
     fset = set()
     other = []
 
     for kind, expr in pats:
         if kind == 'set':
             if not ctx:
                 raise util.Abort("fileset expression with no context")
             s = fileset.getfileset(ctx, expr)
             fset.update(s)
             continue
         other.append((kind, expr))
     return fset, other
 
 class match(object):
     def __init__(self, root, cwd, patterns, include=[], exclude=[],
                  default='glob', exact=False, auditor=None, ctx=None):
         """build an object to match a set of file patterns
 
         arguments:
         root - the canonical root of the tree you're matching against
         cwd - the current working directory, if relevant
         patterns - patterns to find
         include - patterns to include
         exclude - patterns to exclude
         default - if a pattern in names has no explicit type, assume this one
         exact - patterns are actually literals
 
         a pattern is one of:
         'glob:<glob>' - a glob relative to cwd
         're:<regexp>' - a regular expression
         'path:<path>' - a path relative to repository root
         'relglob:<glob>' - an unrooted glob (*.c matches C files in all dirs)
         'relpath:<path>' - a path relative to cwd
         'relre:<regexp>' - a regexp that needn't match the start of a name
         'set:<fileset>' - a fileset expression
         '<something>' - a pattern of the specified default type
         """
 
         self._root = root
         self._cwd = cwd
         self._files = []
         self._anypats = bool(include or exclude)
         self._ctx = ctx
         self._always = False
 
         if include:
             pats = _normalize(include, 'glob', root, cwd, auditor)
             self.includepat, im = _buildmatch(ctx, pats, '(?:/|$)')
         if exclude:
             pats = _normalize(exclude, 'glob', root, cwd, auditor)
             self.excludepat, em = _buildmatch(ctx, pats, '(?:/|$)')
         if exact:
             if isinstance(patterns, list):
                 self._files = patterns
             else:
                 self._files = list(patterns)
             pm = self.exact
         elif patterns:
             pats = _normalize(patterns, default, root, cwd, auditor)
             self._files = _roots(pats)
             self._anypats = self._anypats or _anypats(pats)
             self.patternspat, pm = _buildmatch(ctx, pats, '$')
 
         if patterns or exact:
             if include:
                 if exclude:
                     m = lambda f: im(f) and not em(f) and pm(f)
                 else:
                     m = lambda f: im(f) and pm(f)
             else:
                 if exclude:
                     m = lambda f: not em(f) and pm(f)
                 else:
                     m = pm
         else:
             if include:
                 if exclude:
                     m = lambda f: im(f) and not em(f)
                 else:
                     m = im
             else:
                 if exclude:
                     m = lambda f: not em(f)
                 else:
                     m = lambda f: True
                     self._always = True
 
         self.matchfn = m
         self._fmap = set(self._files)
 
     def __call__(self, fn):
         return self.matchfn(fn)
     def __iter__(self):
         for f in self._files:
             yield f
     def bad(self, f, msg):
         '''callback for each explicit file that can't be
         found/accessed, with an error message
         '''
         pass
     # If this is set, it will be called when an explicitly listed directory is
     # visited.
     explicitdir = None
     # If this is set, it will be called when a directory discovered by recursive
     # traversal is visited.
     traversedir = None
     def missing(self, f):
         pass
     def exact(self, f):
         return f in self._fmap
     def rel(self, f):
         return util.pathto(self._root, self._cwd, f)
     def files(self):
         return self._files
     def anypats(self):
         return self._anypats
     def always(self):
         return self._always
 
 class exact(match):
     def __init__(self, root, cwd, files):
         match.__init__(self, root, cwd, files, exact=True)
 
 class always(match):
     def __init__(self, root, cwd):
         match.__init__(self, root, cwd, [])
         self._always = True
 
 class narrowmatcher(match):
     """Adapt a matcher to work on a subdirectory only.
 
     The paths are remapped to remove/insert the path as needed:
 
     >>> m1 = match('root', '', ['a.txt', 'sub/b.txt'])
     >>> m2 = narrowmatcher('sub', m1)
     >>> bool(m2('a.txt'))
     False
     >>> bool(m2('b.txt'))
     True
     >>> bool(m2.matchfn('a.txt'))
     False
     >>> bool(m2.matchfn('b.txt'))
     True
     >>> m2.files()
     ['b.txt']
     >>> m2.exact('b.txt')
     True
     >>> m2.rel('b.txt')
     'b.txt'
     >>> def bad(f, msg):
     ...     print "%s: %s" % (f, msg)
     >>> m1.bad = bad
     >>> m2.bad('x.txt', 'No such file')
     sub/x.txt: No such file
     """
 
     def __init__(self, path, matcher):
         self._root = matcher._root
         self._cwd = matcher._cwd
         self._path = path
         self._matcher = matcher
         self._always = matcher._always
 
         self._files = [f[len(path) + 1:] for f in matcher._files
                        if f.startswith(path + "/")]
         self._anypats = matcher._anypats
         self.matchfn = lambda fn: matcher.matchfn(self._path + "/" + fn)
         self._fmap = set(self._files)
 
     def bad(self, f, msg):
         self._matcher.bad(self._path + "/" + f, msg)
 
 def patkind(pat):
     return _patsplit(pat, None)[0]
 
 def _patsplit(pat, default):
     """Split a string into an optional pattern kind prefix and the
     actual pattern."""
     if ':' in pat:
         kind, val = pat.split(':', 1)
         if kind in ('re', 'glob', 'path', 'relglob', 'relpath', 'relre',
                     'listfile', 'listfile0', 'set'):
             return kind, val
     return default, pat
 
 def _globre(pat):
     "convert a glob pattern into a regexp"
     i, n = 0, len(pat)
     res = ''
     group = 0
     escape = re.escape
     def peek():
         return i < n and pat[i]
     while i < n:
         c = pat[i]
         i += 1
         if c not in '*?[{},\\':
             res += escape(c)
         elif c == '*':
             if peek() == '*':
                 i += 1
                 res += '.*'
             else:
                 res += '[^/]*'
         elif c == '?':
             res += '.'
         elif c == '[':
             j = i
             if j < n and pat[j] in '!]':
                 j += 1
             while j < n and pat[j] != ']':
                 j += 1
             if j >= n:
                 res += '\\['
             else:
                 stuff = pat[i:j].replace('\\','\\\\')
                 i = j + 1
                 if stuff[0] == '!':
                     stuff = '^' + stuff[1:]
                 elif stuff[0] == '^':
                     stuff = '\\' + stuff
                 res = '%s[%s]' % (res, stuff)
         elif c == '{':
             group += 1
             res += '(?:'
         elif c == '}' and group:
             res += ')'
             group -= 1
         elif c == ',' and group:
             res += '|'
         elif c == '\\':
             p = peek()
             if p:
                 i += 1
                 res += escape(p)
             else:
                 res += escape(c)
         else:
             res += escape(c)
     return res
 
 def _regex(kind, name, tail):
     '''convert a pattern into a regular expression'''
     if not name:
         return ''
     if kind == 're':
         return name
     elif kind == 'path':
         return '^' + re.escape(name) + '(?:/|$)'
     elif kind == 'relglob':
         return '(?:|.*/)' + _globre(name) + tail
     elif kind == 'relpath':
         return re.escape(name) + '(?:/|$)'
     elif kind == 'relre':
         if name.startswith('^'):
             return name
         return '.*' + name
     return _globre(name) + tail
 
 def _buildmatch(ctx, pats, tail):
     fset, pats = _expandsets(pats, ctx)
     if not pats:
         return "", fset.__contains__
 
     pat, mf = _buildregexmatch(pats, tail)
     if fset:
         return pat, lambda f: f in fset or mf(f)
     return pat, mf
 
 def _buildregexmatch(pats, tail):
     """build a matching function from a set of patterns"""
     try:
         pat = '(?:%s)' % '|'.join([_regex(k, p, tail) for (k, p) in pats])
         if len(pat) > 20000:
             raise OverflowError
         return pat, _rematcher(pat)
     except OverflowError:
         # We're using a Python with a tiny regex engine and we
         # made it explode, so we'll divide the pattern list in two
         # until it works
         l = len(pats)
         if l < 2:
             raise
         pata, a = _buildregexmatch(pats[:l//2], tail)
         patb, b = _buildregexmatch(pats[l//2:], tail)
         return pat, lambda s: a(s) or b(s)
     except re.error:
         for k, p in pats:
             try:
                 _rematcher('(?:%s)' % _regex(k, p, tail))
             except re.error:
                 raise util.Abort(_("invalid pattern (%s): %s") % (k, p))
         raise util.Abort(_("invalid pattern"))
 
 def _normalize(names, default, root, cwd, auditor):
     pats = []
     for kind, name in [_patsplit(p, default) for p in names]:
         if kind in ('glob', 'relpath'):
-            name = scmutil.canonpath(root, cwd, name, auditor)
+            name = pathutil.canonpath(root, cwd, name, auditor)
         elif kind in ('relglob', 'path'):
             name = util.normpath(name)
         elif kind in ('listfile', 'listfile0'):
             try:
                 files = util.readfile(name)
                 if kind == 'listfile0':
                     files = files.split('\0')
                 else:
                     files = files.splitlines()
                 files = [f for f in files if f]
             except EnvironmentError:
                 raise util.Abort(_("unable to read file list (%s)") % name)
             pats += _normalize(files, default, root, cwd, auditor)
             continue
 
         pats.append((kind, name))
     return pats
 
 def _roots(patterns):
     r = []
     for kind, name in patterns:
         if kind == 'glob': # find the non-glob prefix
             root = []
             for p in name.split('/'):
                 if '[' in p or '{' in p or '*' in p or '?' in p:
                     break
                 root.append(p)
             r.append('/'.join(root) or '.')
         elif kind in ('relpath', 'path'):
             r.append(name or '.')
         else: # relglob, re, relre
             r.append('.')
     return r
 
 def _anypats(patterns):
     for kind, name in patterns:
         if kind in ('glob', 're', 'relglob', 'relre', 'set'):
             return True

mercurial/scmutil.py

@@ -1,1025 +1,886 b''
 # scmutil.py - Mercurial core utility functions
 #
 #  Copyright Matt Mackall <[e-mail]>
 #
 # 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 _
 from mercurial.node import nullrev
 import util, error, osutil, revset, similar, encoding, phases, parsers
+import pathutil
 import match as matchmod
-import os, errno, re, stat, glob
+import os, errno, re, glob
 
 if os.name == 'nt':
     import scmwindows as scmplatform
 else:
     import scmposix as scmplatform
 
 systemrcpath = scmplatform.systemrcpath
 userrcpath = scmplatform.userrcpath
 
 def nochangesfound(ui, repo, excluded=None):
     '''Report no changes for push/pull, excluded is None or a list of
     nodes excluded from the push/pull.
     '''
     secretlist = []
     if excluded:
         for n in excluded:
             if n not in repo:
                 # discovery should not have included the filtered revision,
                 # we have to explicitly exclude it until discovery is cleanup.
                 continue
             ctx = repo[n]
             if ctx.phase() >= phases.secret and not ctx.extinct():
                 secretlist.append(n)
 
     if secretlist:
         ui.status(_("no changes found (ignored %d secret changesets)\n")
                   % len(secretlist))
     else:
         ui.status(_("no changes found\n"))
 
 def checknewlabel(repo, lbl, kind):
     # Do not use the "kind" parameter in ui output.
     # It makes strings difficult to translate.
     if lbl in ['tip', '.', 'null']:
         raise util.Abort(_("the name '%s' is reserved") % lbl)
     for c in (':', '\0', '\n', '\r'):
         if c in lbl:
             raise util.Abort(_("%r cannot be used in a name") % c)
     try:
         int(lbl)
         raise util.Abort(_("cannot use an integer as a name"))
     except ValueError:
         pass
 
 def checkfilename(f):
     '''Check that the filename f is an acceptable filename for a tracked file'''
     if '\r' in f or '\n' in f:
         raise util.Abort(_("'\\n' and '\\r' disallowed in filenames: %r") % f)
 
 def checkportable(ui, f):
     '''Check if filename f is portable and warn or abort depending on config'''
     checkfilename(f)
     abort, warn = checkportabilityalert(ui)
     if abort or warn:
         msg = util.checkwinfilename(f)
         if msg:
             msg = "%s: %r" % (msg, f)
             if abort:
                 raise util.Abort(msg)
             ui.warn(_("warning: %s\n") % msg)
 
 def checkportabilityalert(ui):
     '''check if the user's config requests nothing, a warning, or abort for
     non-portable filenames'''
     val = ui.config('ui', 'portablefilenames', 'warn')
     lval = val.lower()
     bval = util.parsebool(val)
     abort = os.name == 'nt' or lval == 'abort'
     warn = bval or lval == 'warn'
     if bval is None and not (warn or abort or lval == 'ignore'):
         raise error.ConfigError(
             _("ui.portablefilenames value is invalid ('%s')") % val)
     return abort, warn
 
 class casecollisionauditor(object):
     def __init__(self, ui, abort, dirstate):
         self._ui = ui
         self._abort = abort
         allfiles = '\0'.join(dirstate._map)
         self._loweredfiles = set(encoding.lower(allfiles).split('\0'))
         self._dirstate = dirstate
         # The purpose of _newfiles is so that we don't complain about
         # case collisions if someone were to call this object with the
         # same filename twice.
         self._newfiles = set()
 
     def __call__(self, f):
         if f in self._newfiles:
             return
         fl = encoding.lower(f)
         if fl in self._loweredfiles and f not in self._dirstate:
             msg = _('possible case-folding collision for %s') % f
             if self._abort:
                 raise util.Abort(msg)
             self._ui.warn(_("warning: %s\n") % msg)
         self._loweredfiles.add(fl)
         self._newfiles.add(f)
 
-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
-
 class abstractvfs(object):
     """Abstract base class; cannot be instantiated"""
 
     def __init__(self, *args, **kwargs):
         '''Prevent instantiation; don't call this from subclasses.'''
         raise NotImplementedError('attempted instantiating ' + str(type(self)))
 
     def tryread(self, path):
         '''gracefully return an empty string for missing files'''
         try:
             return self.read(path)
         except IOError, inst:
             if inst.errno != errno.ENOENT:
                 raise
         return ""
 
     def open(self, path, mode="r", text=False, atomictemp=False):
         self.open = self.__call__
         return self.__call__(path, mode, text, atomictemp)
 
     def read(self, path):
         fp = self(path, 'rb')
         try:
             return fp.read()
         finally:
             fp.close()
 
     def write(self, path, data):
         fp = self(path, 'wb')
         try:
             return fp.write(data)
         finally:
             fp.close()
 
     def append(self, path, data):
         fp = self(path, 'ab')
         try:
             return fp.write(data)
         finally:
             fp.close()
 
     def exists(self, path=None):
         return os.path.exists(self.join(path))
 
     def fstat(self, fp):
         return util.fstat(fp)
 
     def isdir(self, path=None):
         return os.path.isdir(self.join(path))
 
     def islink(self, path=None):
         return os.path.islink(self.join(path))
 
     def lstat(self, path=None):
         return os.lstat(self.join(path))
 
     def makedir(self, path=None, notindexed=True):
         return util.makedir(self.join(path), notindexed)
 
     def makedirs(self, path=None, mode=None):
         return util.makedirs(self.join(path), mode)
 
     def mkdir(self, path=None):
         return os.mkdir(self.join(path))
 
     def readdir(self, path=None, stat=None, skip=None):
         return osutil.listdir(self.join(path), stat, skip)
 
     def rename(self, src, dst):
         return util.rename(self.join(src), self.join(dst))
 
     def readlink(self, path):
         return os.readlink(self.join(path))
 
     def setflags(self, path, l, x):
         return util.setflags(self.join(path), l, x)
 
     def stat(self, path=None):
         return os.stat(self.join(path))
 
     def unlink(self, path=None):
         return util.unlink(self.join(path))
 
     def utime(self, path=None, t=None):
         return os.utime(self.join(path), t)
 
 class vfs(abstractvfs):
     '''Operate files relative to a base directory
 
     This class is used to hide the details of COW semantics and
     remote file access from higher level code.
     '''
     def __init__(self, base, audit=True, expandpath=False, realpath=False):
         if expandpath:
             base = util.expandpath(base)
         if realpath:
             base = os.path.realpath(base)
         self.base = base
         self._setmustaudit(audit)
         self.createmode = None
         self._trustnlink = None
 
     def _getmustaudit(self):
         return self._audit
 
     def _setmustaudit(self, onoff):
         self._audit = onoff
         if onoff:
-            self.audit = pathauditor(self.base)
+            self.audit = pathutil.pathauditor(self.base)
         else:
             self.audit = util.always
 
     mustaudit = property(_getmustaudit, _setmustaudit)
 
     @util.propertycache
     def _cansymlink(self):
         return util.checklink(self.base)
 
     @util.propertycache
     def _chmod(self):
         return util.checkexec(self.base)
 
     def _fixfilemode(self, name):
         if self.createmode is None or not self._chmod:
             return
         os.chmod(name, self.createmode & 0666)
 
     def __call__(self, path, mode="r", text=False, atomictemp=False):
         if self._audit:
             r = util.checkosfilename(path)
             if r:
                 raise util.Abort("%s: %r" % (r, path))
         self.audit(path)
         f = self.join(path)
 
         if not text and "b" not in mode:
             mode += "b" # for that other OS
 
         nlink = -1
         if mode not in ('r', 'rb'):
             dirname, basename = util.split(f)
             # If basename is empty, then the path is malformed because it points
             # to a directory. Let the posixfile() call below raise IOError.
             if basename:
                 if atomictemp:
                     util.ensuredirs(dirname, self.createmode)
                     return util.atomictempfile(f, mode, self.createmode)
                 try:
                     if 'w' in mode:
                         util.unlink(f)
                         nlink = 0
                     else:
                         # nlinks() may behave differently for files on Windows
                         # shares if the file is open.
                         fd = util.posixfile(f)
                         nlink = util.nlinks(f)
                         if nlink < 1:
                             nlink = 2 # force mktempcopy (issue1922)
                         fd.close()
                 except (OSError, IOError), e:
                     if e.errno != errno.ENOENT:
                         raise
                     nlink = 0
                     util.ensuredirs(dirname, self.createmode)
                 if nlink > 0:
                     if self._trustnlink is None:
                         self._trustnlink = nlink > 1 or util.checknlink(f)
                     if nlink > 1 or not self._trustnlink:
                         util.rename(util.mktempcopy(f), f)
         fp = util.posixfile(f, mode)
         if nlink == 0:
             self._fixfilemode(f)
         return fp
 
     def symlink(self, src, dst):
         self.audit(dst)
         linkname = self.join(dst)
         try:
             os.unlink(linkname)
         except OSError:
             pass
 
         util.ensuredirs(os.path.dirname(linkname), self.createmode)
 
         if self._cansymlink:
             try:
                 os.symlink(src, linkname)
             except OSError, err:
                 raise OSError(err.errno, _('could not symlink to %r: %s') %
                               (src, err.strerror), linkname)
         else:
             self.write(dst, src)
 
     def join(self, path):
         if path:
             return os.path.join(self.base, path)
         else:
             return self.base
 
 opener = vfs
 
 class auditvfs(object):
     def __init__(self, vfs):
         self.vfs = vfs
 
     def _getmustaudit(self):
         return self.vfs.mustaudit
 
     def _setmustaudit(self, onoff):
         self.vfs.mustaudit = onoff
 
     mustaudit = property(_getmustaudit, _setmustaudit)
 
 class filtervfs(abstractvfs, auditvfs):
     '''Wrapper vfs for filtering filenames with a function.'''
 
     def __init__(self, vfs, filter):
         auditvfs.__init__(self, vfs)
         self._filter = filter
 
     def __call__(self, path, *args, **kwargs):
         return self.vfs(self._filter(path), *args, **kwargs)
 
     def join(self, path):
         if path:
             return self.vfs.join(self._filter(path))
         else:
             return self.vfs.join(path)
 
 filteropener = filtervfs
 
 class readonlyvfs(abstractvfs, auditvfs):
     '''Wrapper vfs preventing any writing.'''
 
     def __init__(self, vfs):
         auditvfs.__init__(self, vfs)
 
     def __call__(self, path, mode='r', *args, **kw):
         if mode not in ('r', 'rb'):
             raise util.Abort('this vfs is read only')
         return self.vfs(path, mode, *args, **kw)
 
 
-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 walkrepos(path, followsym=False, seen_dirs=None, recurse=False):
     '''yield every hg repository under path, always recursively.
     The recurse flag will only control recursion into repo working dirs'''
     def errhandler(err):
         if err.filename == path:
             raise err
     samestat = getattr(os.path, 'samestat', None)
     if followsym and samestat is not None:
         def adddir(dirlst, dirname):
             match = False
             dirstat = os.stat(dirname)
             for lstdirstat in dirlst:
                 if samestat(dirstat, lstdirstat):
                     match = True
                     break
             if not match:
                 dirlst.append(dirstat)
             return not match
     else:
         followsym = False
 
     if (seen_dirs is None) and followsym:
         seen_dirs = []
         adddir(seen_dirs, path)
     for root, dirs, files in os.walk(path, topdown=True, onerror=errhandler):
         dirs.sort()
         if '.hg' in dirs:
             yield root # found a repository
             qroot = os.path.join(root, '.hg', 'patches')
             if os.path.isdir(os.path.join(qroot, '.hg')):
                 yield qroot # we have a patch queue repo here
             if recurse:
                 # avoid recursing inside the .hg directory
                 dirs.remove('.hg')
             else:
                 dirs[:] = [] # don't descend further
         elif followsym:
             newdirs = []
             for d in dirs:
                 fname = os.path.join(root, d)
                 if adddir(seen_dirs, fname):
                     if os.path.islink(fname):
                         for hgname in walkrepos(fname, True, seen_dirs):
                             yield hgname
                     else:
                         newdirs.append(d)
             dirs[:] = newdirs
 
 def osrcpath():
     '''return default os-specific hgrc search path'''
     path = systemrcpath()
     path.extend(userrcpath())
     path = [os.path.normpath(f) for f in path]
     return path
 
 _rcpath = None
 
 def rcpath():
     '''return hgrc search path. if env var HGRCPATH is set, use it.
     for each item in path, if directory, use files ending in .rc,
     else use item.
     make HGRCPATH empty to only look in .hg/hgrc of current repo.
     if no HGRCPATH, use default os-specific path.'''
     global _rcpath
     if _rcpath is None:
         if 'HGRCPATH' in os.environ:
             _rcpath = []
             for p in os.environ['HGRCPATH'].split(os.pathsep):
                 if not p:
                     continue
                 p = util.expandpath(p)
                 if os.path.isdir(p):
                     for f, kind in osutil.listdir(p):
                         if f.endswith('.rc'):
                             _rcpath.append(os.path.join(p, f))
                 else:
                     _rcpath.append(p)
         else:
             _rcpath = osrcpath()
     return _rcpath
 
 def revsingle(repo, revspec, default='.'):
     if not revspec and revspec != 0:
         return repo[default]
 
     l = revrange(repo, [revspec])
     if len(l) < 1:
         raise util.Abort(_('empty revision set'))
     return repo[l[-1]]
 
 def revpair(repo, revs):
     if not revs:
         return repo.dirstate.p1(), None
 
     l = revrange(repo, revs)
 
     if len(l) == 0:
         if revs:
             raise util.Abort(_('empty revision range'))
         return repo.dirstate.p1(), None
 
     if len(l) == 1 and len(revs) == 1 and _revrangesep not in revs[0]:
         return repo.lookup(l[0]), None
 
     return repo.lookup(l[0]), repo.lookup(l[-1])
 
 _revrangesep = ':'
 
 def revrange(repo, revs):
     """Yield revision as strings from a list of revision specifications."""
 
     def revfix(repo, val, defval):
         if not val and val != 0 and defval is not None:
             return defval
         return repo[val].rev()
 
     seen, l = set(), []
     for spec in revs:
         if l and not seen:
             seen = set(l)
         # attempt to parse old-style ranges first to deal with
         # things like old-tag which contain query metacharacters
         try:
             if isinstance(spec, int):
                 seen.add(spec)
                 l.append(spec)
                 continue
 
             if _revrangesep in spec:
                 start, end = spec.split(_revrangesep, 1)
                 start = revfix(repo, start, 0)
                 end = revfix(repo, end, len(repo) - 1)
                 if end == nullrev and start <= 0:
                     start = nullrev
                 rangeiter = repo.changelog.revs(start, end)
                 if not seen and not l:
                     # by far the most common case: revs = ["-1:0"]
                     l = list(rangeiter)
                     # defer syncing seen until next iteration
                     continue
                 newrevs = set(rangeiter)
                 if seen:
                     newrevs.difference_update(seen)
                     seen.update(newrevs)
                 else:
                     seen = newrevs
                 l.extend(sorted(newrevs, reverse=start > end))
                 continue
             elif spec and spec in repo: # single unquoted rev
                 rev = revfix(repo, spec, None)
                 if rev in seen:
                     continue
                 seen.add(rev)
                 l.append(rev)
                 continue
         except error.RepoLookupError:
             pass
 
         # fall through to new-style queries if old-style fails
         m = revset.match(repo.ui, spec)
         dl = [r for r in m(repo, list(repo)) if r not in seen]
         l.extend(dl)
         seen.update(dl)
 
     return l
 
 def expandpats(pats):
     if not util.expandglobs:
         return list(pats)
     ret = []
     for p in pats:
         kind, name = matchmod._patsplit(p, None)
         if kind is None:
             try:
                 globbed = glob.glob(name)
             except re.error:
                 globbed = [name]
             if globbed:
                 ret.extend(globbed)
                 continue
         ret.append(p)
     return ret
 
 def matchandpats(ctx, pats=[], opts={}, globbed=False, default='relpath'):
     if pats == ("",):
         pats = []
     if not globbed and default == 'relpath':
         pats = expandpats(pats or [])
 
     m = ctx.match(pats, opts.get('include'), opts.get('exclude'),
                          default)
     def badfn(f, msg):
         ctx._repo.ui.warn("%s: %s\n" % (m.rel(f), msg))
     m.bad = badfn
     return m, pats
 
 def match(ctx, pats=[], opts={}, globbed=False, default='relpath'):
     return matchandpats(ctx, pats, opts, globbed, default)[0]
 
 def matchall(repo):
     return matchmod.always(repo.root, repo.getcwd())
 
 def matchfiles(repo, files):
     return matchmod.exact(repo.root, repo.getcwd(), files)
 
 def addremove(repo, pats=[], opts={}, dry_run=None, similarity=None):
     if dry_run is None:
         dry_run = opts.get('dry_run')
     if similarity is None:
         similarity = float(opts.get('similarity') or 0)
     # we'd use status here, except handling of symlinks and ignore is tricky
     m = match(repo[None], pats, opts)
     rejected = []
     m.bad = lambda x, y: rejected.append(x)
 
     added, unknown, deleted, removed = _interestingfiles(repo, m)
 
     unknownset = set(unknown)
     toprint = unknownset.copy()
     toprint.update(deleted)
     for abs in sorted(toprint):
         if repo.ui.verbose or not m.exact(abs):
             rel = m.rel(abs)
             if abs in unknownset:
                 status = _('adding %s\n') % ((pats and rel) or abs)
             else:
                 status = _('removing %s\n') % ((pats and rel) or abs)
             repo.ui.status(status)
 
     renames = _findrenames(repo, m, added + unknown, removed + deleted,
                            similarity)
 
     if not dry_run:
         _markchanges(repo, unknown, deleted, renames)
 
     for f in rejected:
         if f in m.files():
             return 1
     return 0
 
 def marktouched(repo, files, similarity=0.0):
     '''Assert that files have somehow been operated upon. files are relative to
     the repo root.'''
     m = matchfiles(repo, files)
     rejected = []
     m.bad = lambda x, y: rejected.append(x)
 
     added, unknown, deleted, removed = _interestingfiles(repo, m)
 
     if repo.ui.verbose:
         unknownset = set(unknown)
         toprint = unknownset.copy()
         toprint.update(deleted)
         for abs in sorted(toprint):
             if abs in unknownset:
                 status = _('adding %s\n') % abs
             else:
                 status = _('removing %s\n') % abs
             repo.ui.status(status)
 
     renames = _findrenames(repo, m, added + unknown, removed + deleted,
                            similarity)
 
     _markchanges(repo, unknown, deleted, renames)
 
     for f in rejected:
         if f in m.files():
             return 1
     return 0
 
 def _interestingfiles(repo, matcher):
     '''Walk dirstate with matcher, looking for files that addremove would care
     about.
 
     This is different from dirstate.status because it doesn't care about
     whether files are modified or clean.'''
     added, unknown, deleted, removed = [], [], [], []
-    audit_path = pathauditor(repo.root)
+    audit_path = pathutil.pathauditor(repo.root)
 
     ctx = repo[None]
     dirstate = repo.dirstate
     walkresults = dirstate.walk(matcher, sorted(ctx.substate), True, False,
                                 full=False)
     for abs, st in walkresults.iteritems():
         dstate = dirstate[abs]
         if dstate == '?' and audit_path.check(abs):
             unknown.append(abs)
         elif dstate != 'r' and not st:
             deleted.append(abs)
         # for finding renames
         elif dstate == 'r':
             removed.append(abs)
         elif dstate == 'a':
             added.append(abs)
 
     return added, unknown, deleted, removed
 
 def _findrenames(repo, matcher, added, removed, similarity):
     '''Find renames from removed files to added ones.'''
     renames = {}
     if similarity > 0:
         for old, new, score in similar.findrenames(repo, added, removed,
                                                    similarity):
             if (repo.ui.verbose or not matcher.exact(old)
                 or not matcher.exact(new)):
                 repo.ui.status(_('recording removal of %s as rename to %s '
                                  '(%d%% similar)\n') %
                                (matcher.rel(old), matcher.rel(new),
                                 score * 100))
             renames[new] = old
     return renames
 
 def _markchanges(repo, unknown, deleted, renames):
     '''Marks the files in unknown as added, the files in deleted as removed,
     and the files in renames as copied.'''
     wctx = repo[None]
     wlock = repo.wlock()
     try:
         wctx.forget(deleted)
         wctx.add(unknown)
         for new, old in renames.iteritems():
             wctx.copy(old, new)
     finally:
         wlock.release()
 
 def dirstatecopy(ui, repo, wctx, src, dst, dryrun=False, cwd=None):
     """Update the dirstate to reflect the intent of copying src to dst. For
     different reasons it might not end with dst being marked as copied from src.
     """
     origsrc = repo.dirstate.copied(src) or src
     if dst == origsrc: # copying back a copy?
         if repo.dirstate[dst] not in 'mn' and not dryrun:
             repo.dirstate.normallookup(dst)
     else:
         if repo.dirstate[origsrc] == 'a' and origsrc == src:
             if not ui.quiet:
                 ui.warn(_("%s has not been committed yet, so no copy "
                           "data will be stored for %s.\n")
                         % (repo.pathto(origsrc, cwd), repo.pathto(dst, cwd)))
             if repo.dirstate[dst] in '?r' and not dryrun:
                 wctx.add([dst])
         elif not dryrun:
             wctx.copy(origsrc, dst)
 
 def readrequires(opener, supported):
     '''Reads and parses .hg/requires and checks if all entries found
     are in the list of supported features.'''
     requirements = set(opener.read("requires").splitlines())
     missings = []
     for r in requirements:
         if r not in supported:
             if not r or not r[0].isalnum():
                 raise error.RequirementError(_(".hg/requires file is corrupt"))
             missings.append(r)
     missings.sort()
     if missings:
         raise error.RequirementError(
             _("unknown repository format: requires features '%s' (upgrade "
               "Mercurial)") % "', '".join(missings))
     return requirements
 
 class filecacheentry(object):
     def __init__(self, path, stat=True):
         self.path = path
         self.cachestat = None
         self._cacheable = None
 
         if stat:
             self.cachestat = filecacheentry.stat(self.path)
 
             if self.cachestat:
                 self._cacheable = self.cachestat.cacheable()
             else:
                 # None means we don't know yet
                 self._cacheable = None
 
     def refresh(self):
         if self.cacheable():
             self.cachestat = filecacheentry.stat(self.path)
 
     def cacheable(self):
         if self._cacheable is not None:
             return self._cacheable
 
         # we don't know yet, assume it is for now
         return True
 
     def changed(self):
         # no point in going further if we can't cache it
         if not self.cacheable():
             return True
 
         newstat = filecacheentry.stat(self.path)
 
         # we may not know if it's cacheable yet, check again now
         if newstat and self._cacheable is None:
             self._cacheable = newstat.cacheable()
 
             # check again
             if not self._cacheable:
                 return True
 
         if self.cachestat != newstat:
             self.cachestat = newstat
             return True
         else:
             return False
 
     @staticmethod
     def stat(path):
         try:
             return util.cachestat(path)
         except OSError, e:
             if e.errno != errno.ENOENT:
                 raise
 
 class filecache(object):
     '''A property like decorator that tracks a file under .hg/ for updates.
 
     Records stat info when called in _filecache.
 
     On subsequent calls, compares old stat info with new info, and recreates
     the object when needed, updating the new stat info in _filecache.
 
     Mercurial either atomic renames or appends for files under .hg,
     so to ensure the cache is reliable we need the filesystem to be able
     to tell us if a file has been replaced. If it can't, we fallback to
     recreating the object on every call (essentially the same behaviour as
     propertycache).'''
     def __init__(self, path):
         self.path = path
 
     def join(self, obj, fname):
         """Used to compute the runtime path of the cached file.
 
         Users should subclass filecache and provide their own version of this
         function to call the appropriate join function on 'obj' (an instance
         of the class that its member function was decorated).
         """
         return obj.join(fname)
 
     def __call__(self, func):
         self.func = func
         self.name = func.__name__
         return self
 
     def __get__(self, obj, type=None):
         # do we need to check if the file changed?
         if self.name in obj.__dict__:
             assert self.name in obj._filecache, self.name
             return obj.__dict__[self.name]
 
         entry = obj._filecache.get(self.name)
 
         if entry:
             if entry.changed():
                 entry.obj = self.func(obj)
         else:
             path = self.join(obj, self.path)
 
             # We stat -before- creating the object so our cache doesn't lie if
             # a writer modified between the time we read and stat
             entry = filecacheentry(path)
             entry.obj = self.func(obj)
 
             obj._filecache[self.name] = entry
 
         obj.__dict__[self.name] = entry.obj
         return entry.obj
 
     def __set__(self, obj, value):
         if self.name not in obj._filecache:
             # we add an entry for the missing value because X in __dict__
             # implies X in _filecache
             ce = filecacheentry(self.join(obj, self.path), False)
             obj._filecache[self.name] = ce
         else:
             ce = obj._filecache[self.name]
 
         ce.obj = value # update cached copy
         obj.__dict__[self.name] = value # update copy returned by obj.x
 
     def __delete__(self, obj):
         try:
             del obj.__dict__[self.name]
         except KeyError:
             raise AttributeError(self.name)
 
 class dirs(object):
     '''a multiset of directory names from a dirstate or manifest'''
 
     def __init__(self, map, skip=None):
         self._dirs = {}
         addpath = self.addpath
         if util.safehasattr(map, 'iteritems') and skip is not None:
             for f, s in map.iteritems():
                 if s[0] != skip:
                     addpath(f)
         else:
             for f in map:
                 addpath(f)
 
     def addpath(self, path):
         dirs = self._dirs
         for base in finddirs(path):
             if base in dirs:
                 dirs[base] += 1
                 return
             dirs[base] = 1
 
     def delpath(self, path):
         dirs = self._dirs
         for base in finddirs(path):
             if dirs[base] > 1:
                 dirs[base] -= 1
                 return
             del dirs[base]
 
     def __iter__(self):
         return self._dirs.iterkeys()
 
     def __contains__(self, d):
         return d in self._dirs
 
 if util.safehasattr(parsers, 'dirs'):
     dirs = parsers.dirs
 
 def finddirs(path):
     pos = path.rfind('/')
     while pos != -1:
         yield path[:pos]
         pos = path.rfind('/', 0, pos)

mercurial/subrepo.py

@@ -1,1469 +1,1470 b''
 # subrepo.py - sub-repository handling for Mercurial
 #
 # Copyright 2009-2010 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 import errno, os, re, shutil, posixpath, sys
 import xml.dom.minidom
 import stat, subprocess, tarfile
 from i18n import _
-import config, scmutil, util, node, error, cmdutil, bookmarks, match as matchmod
+import config, util, node, error, cmdutil, bookmarks, match as matchmod
+import pathutil
 hg = None
 propertycache = util.propertycache
 
 nullstate = ('', '', 'empty')
 
 def _expandedabspath(path):
     '''
     get a path or url and if it is a path expand it and return an absolute path
     '''
     expandedpath = util.urllocalpath(util.expandpath(path))
     u = util.url(expandedpath)
     if not u.scheme:
         path = util.normpath(os.path.abspath(u.path))
     return path
 
 def _getstorehashcachename(remotepath):
     '''get a unique filename for the store hash cache of a remote repository'''
     return util.sha1(_expandedabspath(remotepath)).hexdigest()[0:12]
 
 def _calcfilehash(filename):
     data = ''
     if os.path.exists(filename):
         fd = open(filename, 'rb')
         data = fd.read()
         fd.close()
     return util.sha1(data).hexdigest()
 
 class SubrepoAbort(error.Abort):
     """Exception class used to avoid handling a subrepo error more than once"""
     def __init__(self, *args, **kw):
         error.Abort.__init__(self, *args, **kw)
         self.subrepo = kw.get('subrepo')
         self.cause = kw.get('cause')
 
 def annotatesubrepoerror(func):
     def decoratedmethod(self, *args, **kargs):
         try:
             res = func(self, *args, **kargs)
         except SubrepoAbort, ex:
             # This exception has already been handled
             raise ex
         except error.Abort, ex:
             subrepo = subrelpath(self)
             errormsg = str(ex) + ' ' + _('(in subrepo %s)') % subrepo
             # avoid handling this exception by raising a SubrepoAbort exception
             raise SubrepoAbort(errormsg, hint=ex.hint, subrepo=subrepo,
                                cause=sys.exc_info())
         return res
     return decoratedmethod
 
 def state(ctx, ui):
     """return a state dict, mapping subrepo paths configured in .hgsub
     to tuple: (source from .hgsub, revision from .hgsubstate, kind
     (key in types dict))
     """
     p = config.config()
     def read(f, sections=None, remap=None):
         if f in ctx:
             try:
                 data = ctx[f].data()
             except IOError, err:
                 if err.errno != errno.ENOENT:
                     raise
                 # handle missing subrepo spec files as removed
                 ui.warn(_("warning: subrepo spec file %s not found\n") % f)
                 return
             p.parse(f, data, sections, remap, read)
         else:
             raise util.Abort(_("subrepo spec file %s not found") % f)
 
     if '.hgsub' in ctx:
         read('.hgsub')
 
     for path, src in ui.configitems('subpaths'):
         p.set('subpaths', path, src, ui.configsource('subpaths', path))
 
     rev = {}
     if '.hgsubstate' in ctx:
         try:
             for i, l in enumerate(ctx['.hgsubstate'].data().splitlines()):
                 l = l.lstrip()
                 if not l:
                     continue
                 try:
                     revision, path = l.split(" ", 1)
                 except ValueError:
                     raise util.Abort(_("invalid subrepository revision "
                                        "specifier in .hgsubstate line %d")
                                      % (i + 1))
                 rev[path] = revision
         except IOError, err:
             if err.errno != errno.ENOENT:
                 raise
 
     def remap(src):
         for pattern, repl in p.items('subpaths'):
             # Turn r'C:\foo\bar' into r'C:\\foo\\bar' since re.sub
             # does a string decode.
             repl = repl.encode('string-escape')
             # However, we still want to allow back references to go
             # through unharmed, so we turn r'\\1' into r'\1'. Again,
             # extra escapes are needed because re.sub string decodes.
             repl = re.sub(r'\\\\([0-9]+)', r'\\\1', repl)
             try:
                 src = re.sub(pattern, repl, src, 1)
             except re.error, e:
                 raise util.Abort(_("bad subrepository pattern in %s: %s")
                                  % (p.source('subpaths', pattern), e))
         return src
 
     state = {}
     for path, src in p[''].items():
         kind = 'hg'
         if src.startswith('['):
             if ']' not in src:
                 raise util.Abort(_('missing ] in subrepo source'))
             kind, src = src.split(']', 1)
             kind = kind[1:]
             src = src.lstrip() # strip any extra whitespace after ']'
 
         if not util.url(src).isabs():
             parent = _abssource(ctx._repo, abort=False)
             if parent:
                 parent = util.url(parent)
                 parent.path = posixpath.join(parent.path or '', src)
                 parent.path = posixpath.normpath(parent.path)
                 joined = str(parent)
                 # Remap the full joined path and use it if it changes,
                 # else remap the original source.
                 remapped = remap(joined)
                 if remapped == joined:
                     src = remap(src)
                 else:
                     src = remapped
 
         src = remap(src)
         state[util.pconvert(path)] = (src.strip(), rev.get(path, ''), kind)
 
     return state
 
 def writestate(repo, state):
     """rewrite .hgsubstate in (outer) repo with these subrepo states"""
     lines = ['%s %s\n' % (state[s][1], s) for s in sorted(state)]
     repo.wwrite('.hgsubstate', ''.join(lines), '')
 
 def submerge(repo, wctx, mctx, actx, overwrite):
     """delegated from merge.applyupdates: merging of .hgsubstate file
     in working context, merging context and ancestor context"""
     if mctx == actx: # backwards?
         actx = wctx.p1()
     s1 = wctx.substate
     s2 = mctx.substate
     sa = actx.substate
     sm = {}
 
     repo.ui.debug("subrepo merge %s %s %s\n" % (wctx, mctx, actx))
 
     def debug(s, msg, r=""):
         if r:
             r = "%s:%s:%s" % r
         repo.ui.debug("  subrepo %s: %s %s\n" % (s, msg, r))
 
     for s, l in sorted(s1.iteritems()):
         a = sa.get(s, nullstate)
         ld = l # local state with possible dirty flag for compares
         if wctx.sub(s).dirty():
             ld = (l[0], l[1] + "+")
         if wctx == actx: # overwrite
             a = ld
 
         if s in s2:
             r = s2[s]
             if ld == r or r == a: # no change or local is newer
                 sm[s] = l
                 continue
             elif ld == a: # other side changed
                 debug(s, "other changed, get", r)
                 wctx.sub(s).get(r, overwrite)
                 sm[s] = r
             elif ld[0] != r[0]: # sources differ
                 if repo.ui.promptchoice(
                     _(' subrepository sources for %s differ\n'
                       'use (l)ocal source (%s) or (r)emote source (%s)?'
                       '$$ &Local $$ &Remote') % (s, l[0], r[0]), 0):
                     debug(s, "prompt changed, get", r)
                     wctx.sub(s).get(r, overwrite)
                     sm[s] = r
             elif ld[1] == a[1]: # local side is unchanged
                 debug(s, "other side changed, get", r)
                 wctx.sub(s).get(r, overwrite)
                 sm[s] = r
             else:
                 debug(s, "both sides changed")
                 option = repo.ui.promptchoice(
                     _(' subrepository %s diverged (local revision: %s, '
                       'remote revision: %s)\n'
                       '(M)erge, keep (l)ocal or keep (r)emote?'
                       '$$ &Merge $$ &Local $$ &Remote')
                     % (s, l[1][:12], r[1][:12]), 0)
                 if option == 0:
                     wctx.sub(s).merge(r)
                     sm[s] = l
                     debug(s, "merge with", r)
                 elif option == 1:
                     sm[s] = l
                     debug(s, "keep local subrepo revision", l)
                 else:
                     wctx.sub(s).get(r, overwrite)
                     sm[s] = r
                     debug(s, "get remote subrepo revision", r)
         elif ld == a: # remote removed, local unchanged
             debug(s, "remote removed, remove")
             wctx.sub(s).remove()
         elif a == nullstate: # not present in remote or ancestor
             debug(s, "local added, keep")
             sm[s] = l
             continue
         else:
             if repo.ui.promptchoice(
                 _(' local changed subrepository %s which remote removed\n'
                   'use (c)hanged version or (d)elete?'
                   '$$ &Changed $$ &Delete') % s, 0):
                 debug(s, "prompt remove")
                 wctx.sub(s).remove()
 
     for s, r in sorted(s2.items()):
         if s in s1:
             continue
         elif s not in sa:
             debug(s, "remote added, get", r)
             mctx.sub(s).get(r)
             sm[s] = r
         elif r != sa[s]:
             if repo.ui.promptchoice(
                 _(' remote changed subrepository %s which local removed\n'
                   'use (c)hanged version or (d)elete?'
                   '$$ &Changed $$ &Delete') % s, 0) == 0:
                 debug(s, "prompt recreate", r)
                 wctx.sub(s).get(r)
                 sm[s] = r
 
     # record merged .hgsubstate
     writestate(repo, sm)
     return sm
 
 def _updateprompt(ui, sub, dirty, local, remote):
     if dirty:
         msg = (_(' subrepository sources for %s differ\n'
                  'use (l)ocal source (%s) or (r)emote source (%s)?\n'
                  '$$ &Local $$ &Remote')
                % (subrelpath(sub), local, remote))
     else:
         msg = (_(' subrepository sources for %s differ (in checked out '
                  'version)\n'
                  'use (l)ocal source (%s) or (r)emote source (%s)?\n'
                  '$$ &Local $$ &Remote')
                % (subrelpath(sub), local, remote))
     return ui.promptchoice(msg, 0)
 
 def reporelpath(repo):
     """return path to this (sub)repo as seen from outermost repo"""
     parent = repo
     while util.safehasattr(parent, '_subparent'):
         parent = parent._subparent
     p = parent.root.rstrip(os.sep)
     return repo.root[len(p) + 1:]
 
 def subrelpath(sub):
     """return path to this subrepo as seen from outermost repo"""
     if util.safehasattr(sub, '_relpath'):
         return sub._relpath
     if not util.safehasattr(sub, '_repo'):
         return sub._path
     return reporelpath(sub._repo)
 
 def _abssource(repo, push=False, abort=True):
     """return pull/push path of repo - either based on parent repo .hgsub info
     or on the top repo config. Abort or return None if no source found."""
     if util.safehasattr(repo, '_subparent'):
         source = util.url(repo._subsource)
         if source.isabs():
             return str(source)
         source.path = posixpath.normpath(source.path)
         parent = _abssource(repo._subparent, push, abort=False)
         if parent:
             parent = util.url(util.pconvert(parent))
             parent.path = posixpath.join(parent.path or '', source.path)
             parent.path = posixpath.normpath(parent.path)
             return str(parent)
     else: # recursion reached top repo
         if util.safehasattr(repo, '_subtoppath'):
             return repo._subtoppath
         if push and repo.ui.config('paths', 'default-push'):
             return repo.ui.config('paths', 'default-push')
         if repo.ui.config('paths', 'default'):
             return repo.ui.config('paths', 'default')
         if repo.sharedpath != repo.path:
             # chop off the .hg component to get the default path form
             return os.path.dirname(repo.sharedpath)
     if abort:
         raise util.Abort(_("default path for subrepository not found"))
 
 def itersubrepos(ctx1, ctx2):
     """find subrepos in ctx1 or ctx2"""
     # Create a (subpath, ctx) mapping where we prefer subpaths from
     # ctx1. The subpaths from ctx2 are important when the .hgsub file
     # has been modified (in ctx2) but not yet committed (in ctx1).
     subpaths = dict.fromkeys(ctx2.substate, ctx2)
     subpaths.update(dict.fromkeys(ctx1.substate, ctx1))
     for subpath, ctx in sorted(subpaths.iteritems()):
         yield subpath, ctx.sub(subpath)
 
 def subrepo(ctx, path):
     """return instance of the right subrepo class for subrepo in path"""
     # subrepo inherently violates our import layering rules
     # because it wants to make repo objects from deep inside the stack
     # so we manually delay the circular imports to not break
     # scripts that don't use our demand-loading
     global hg
     import hg as h
     hg = h
 
-    scmutil.pathauditor(ctx._repo.root)(path)
+    pathutil.pathauditor(ctx._repo.root)(path)
     state = ctx.substate[path]
     if state[2] not in types:
         raise util.Abort(_('unknown subrepo type %s') % state[2])
     return types[state[2]](ctx, path, state[:2])
 
 # subrepo classes need to implement the following abstract class:
 
 class abstractsubrepo(object):
 
     def storeclean(self, path):
         """
         returns true if the repository has not changed since it was last
         cloned from or pushed to a given repository.
         """
         return False
 
     def dirty(self, ignoreupdate=False):
         """returns true if the dirstate of the subrepo is dirty or does not
         match current stored state. If ignoreupdate is true, only check
         whether the subrepo has uncommitted changes in its dirstate.
         """
         raise NotImplementedError
 
     def basestate(self):
         """current working directory base state, disregarding .hgsubstate
         state and working directory modifications"""
         raise NotImplementedError
 
     def checknested(self, path):
         """check if path is a subrepository within this repository"""
         return False
 
     def commit(self, text, user, date):
         """commit the current changes to the subrepo with the given
         log message. Use given user and date if possible. Return the
         new state of the subrepo.
         """
         raise NotImplementedError
 
     def remove(self):
         """remove the subrepo
 
         (should verify the dirstate is not dirty first)
         """
         raise NotImplementedError
 
     def get(self, state, overwrite=False):
         """run whatever commands are needed to put the subrepo into
         this state
         """
         raise NotImplementedError
 
     def merge(self, state):
         """merge currently-saved state with the new state."""
         raise NotImplementedError
 
     def push(self, opts):
         """perform whatever action is analogous to 'hg push'
 
         This may be a no-op on some systems.
         """
         raise NotImplementedError
 
     def add(self, ui, match, dryrun, listsubrepos, prefix, explicitonly):
         return []
 
     def status(self, rev2, **opts):
         return [], [], [], [], [], [], []
 
     def diff(self, ui, diffopts, node2, match, prefix, **opts):
         pass
 
     def outgoing(self, ui, dest, opts):
         return 1
 
     def incoming(self, ui, source, opts):
         return 1
 
     def files(self):
         """return filename iterator"""
         raise NotImplementedError
 
     def filedata(self, name):
         """return file data"""
         raise NotImplementedError
 
     def fileflags(self, name):
         """return file flags"""
         return ''
 
     def archive(self, ui, archiver, prefix, match=None):
         if match is not None:
             files = [f for f in self.files() if match(f)]
         else:
             files = self.files()
         total = len(files)
         relpath = subrelpath(self)
         ui.progress(_('archiving (%s)') % relpath, 0,
                     unit=_('files'), total=total)
         for i, name in enumerate(files):
             flags = self.fileflags(name)
             mode = 'x' in flags and 0755 or 0644
             symlink = 'l' in flags
             archiver.addfile(os.path.join(prefix, self._path, name),
                              mode, symlink, self.filedata(name))
             ui.progress(_('archiving (%s)') % relpath, i + 1,
                         unit=_('files'), total=total)
         ui.progress(_('archiving (%s)') % relpath, None)
         return total
 
     def walk(self, match):
         '''
         walk recursively through the directory tree, finding all files
         matched by the match function
         '''
         pass
 
     def forget(self, ui, match, prefix):
         return ([], [])
 
     def revert(self, ui, substate, *pats, **opts):
         ui.warn('%s: reverting %s subrepos is unsupported\n' \
             % (substate[0], substate[2]))
         return []
 
 class hgsubrepo(abstractsubrepo):
     def __init__(self, ctx, path, state):
         self._path = path
         self._state = state
         r = ctx._repo
         root = r.wjoin(path)
         create = False
         if not os.path.exists(os.path.join(root, '.hg')):
             create = True
             util.makedirs(root)
         self._repo = hg.repository(r.baseui, root, create=create)
         for s, k in [('ui', 'commitsubrepos')]:
             v = r.ui.config(s, k)
             if v:
                 self._repo.ui.setconfig(s, k, v)
         self._repo.ui.setconfig('ui', '_usedassubrepo', 'True')
         self._initrepo(r, state[0], create)
 
     def storeclean(self, path):
         clean = True
         lock = self._repo.lock()
         itercache = self._calcstorehash(path)
         try:
             for filehash in self._readstorehashcache(path):
                 if filehash != itercache.next():
                     clean = False
                     break
         except StopIteration:
             # the cached and current pull states have a different size
             clean = False
         if clean:
             try:
                 itercache.next()
                 # the cached and current pull states have a different size
                 clean = False
             except StopIteration:
                 pass
         lock.release()
         return clean
 
     def _calcstorehash(self, remotepath):
         '''calculate a unique "store hash"
 
         This method is used to to detect when there are changes that may
         require a push to a given remote path.'''
         # sort the files that will be hashed in increasing (likely) file size
         filelist = ('bookmarks', 'store/phaseroots', 'store/00changelog.i')
         yield '# %s\n' % _expandedabspath(remotepath)
         for relname in filelist:
             absname = os.path.normpath(self._repo.join(relname))
             yield '%s = %s\n' % (relname, _calcfilehash(absname))
 
     def _getstorehashcachepath(self, remotepath):
         '''get a unique path for the store hash cache'''
         return self._repo.join(os.path.join(
             'cache', 'storehash', _getstorehashcachename(remotepath)))
 
     def _readstorehashcache(self, remotepath):
         '''read the store hash cache for a given remote repository'''
         cachefile = self._getstorehashcachepath(remotepath)
         if not os.path.exists(cachefile):
             return ''
         fd = open(cachefile, 'r')
         pullstate = fd.readlines()
         fd.close()
         return pullstate
 
     def _cachestorehash(self, remotepath):
         '''cache the current store hash
 
         Each remote repo requires its own store hash cache, because a subrepo
         store may be "clean" versus a given remote repo, but not versus another
         '''
         cachefile = self._getstorehashcachepath(remotepath)
         lock = self._repo.lock()
         storehash = list(self._calcstorehash(remotepath))
         cachedir = os.path.dirname(cachefile)
         if not os.path.exists(cachedir):
             util.makedirs(cachedir, notindexed=True)
         fd = open(cachefile, 'w')
         fd.writelines(storehash)
         fd.close()
         lock.release()
 
     @annotatesubrepoerror
     def _initrepo(self, parentrepo, source, create):
         self._repo._subparent = parentrepo
         self._repo._subsource = source
 
         if create:
             fp = self._repo.opener("hgrc", "w", text=True)
             fp.write('[paths]\n')
 
             def addpathconfig(key, value):
                 if value:
                     fp.write('%s = %s\n' % (key, value))
                     self._repo.ui.setconfig('paths', key, value)
 
             defpath = _abssource(self._repo, abort=False)
             defpushpath = _abssource(self._repo, True, abort=False)
             addpathconfig('default', defpath)
             if defpath != defpushpath:
                 addpathconfig('default-push', defpushpath)
             fp.close()
 
     @annotatesubrepoerror
     def add(self, ui, match, dryrun, listsubrepos, prefix, explicitonly):
         return cmdutil.add(ui, self._repo, match, dryrun, listsubrepos,
                            os.path.join(prefix, self._path), explicitonly)
 
     @annotatesubrepoerror
     def status(self, rev2, **opts):
         try:
             rev1 = self._state[1]
             ctx1 = self._repo[rev1]
             ctx2 = self._repo[rev2]
             return self._repo.status(ctx1, ctx2, **opts)
         except error.RepoLookupError, inst:
             self._repo.ui.warn(_('warning: error "%s" in subrepository "%s"\n')
                                % (inst, subrelpath(self)))
             return [], [], [], [], [], [], []
 
     @annotatesubrepoerror
     def diff(self, ui, diffopts, node2, match, prefix, **opts):
         try:
             node1 = node.bin(self._state[1])
             # We currently expect node2 to come from substate and be
             # in hex format
             if node2 is not None:
                 node2 = node.bin(node2)
             cmdutil.diffordiffstat(ui, self._repo, diffopts,
                                    node1, node2, match,
                                    prefix=posixpath.join(prefix, self._path),
                                    listsubrepos=True, **opts)
         except error.RepoLookupError, inst:
             self._repo.ui.warn(_('warning: error "%s" in subrepository "%s"\n')
                                % (inst, subrelpath(self)))
 
     @annotatesubrepoerror
     def archive(self, ui, archiver, prefix, match=None):
         self._get(self._state + ('hg',))
         total = abstractsubrepo.archive(self, ui, archiver, prefix, match)
         rev = self._state[1]
         ctx = self._repo[rev]
         for subpath in ctx.substate:
             s = subrepo(ctx, subpath)
             submatch = matchmod.narrowmatcher(subpath, match)
             total += s.archive(
                 ui, archiver, os.path.join(prefix, self._path), submatch)
         return total
 
     @annotatesubrepoerror
     def dirty(self, ignoreupdate=False):
         r = self._state[1]
         if r == '' and not ignoreupdate: # no state recorded
             return True
         w = self._repo[None]
         if r != w.p1().hex() and not ignoreupdate:
             # different version checked out
             return True
         return w.dirty() # working directory changed
 
     def basestate(self):
         return self._repo['.'].hex()
 
     def checknested(self, path):
         return self._repo._checknested(self._repo.wjoin(path))
 
     @annotatesubrepoerror
     def commit(self, text, user, date):
         # don't bother committing in the subrepo if it's only been
         # updated
         if not self.dirty(True):
             return self._repo['.'].hex()
         self._repo.ui.debug("committing subrepo %s\n" % subrelpath(self))
         n = self._repo.commit(text, user, date)
         if not n:
             return self._repo['.'].hex() # different version checked out
         return node.hex(n)
 
     @annotatesubrepoerror
     def remove(self):
         # we can't fully delete the repository as it may contain
         # local-only history
         self._repo.ui.note(_('removing subrepo %s\n') % subrelpath(self))
         hg.clean(self._repo, node.nullid, False)
 
     def _get(self, state):
         source, revision, kind = state
         if revision not in self._repo:
             self._repo._subsource = source
             srcurl = _abssource(self._repo)
             other = hg.peer(self._repo, {}, srcurl)
             if len(self._repo) == 0:
                 self._repo.ui.status(_('cloning subrepo %s from %s\n')
                                      % (subrelpath(self), srcurl))
                 parentrepo = self._repo._subparent
                 shutil.rmtree(self._repo.path)
                 other, cloned = hg.clone(self._repo._subparent.baseui, {},
                                          other, self._repo.root,
                                          update=False)
                 self._repo = cloned.local()
                 self._initrepo(parentrepo, source, create=True)
                 self._cachestorehash(srcurl)
             else:
                 self._repo.ui.status(_('pulling subrepo %s from %s\n')
                                      % (subrelpath(self), srcurl))
                 cleansub = self.storeclean(srcurl)
                 remotebookmarks = other.listkeys('bookmarks')
                 self._repo.pull(other)
                 bookmarks.updatefromremote(self._repo.ui, self._repo,
                                            remotebookmarks, srcurl)
                 if cleansub:
                     # keep the repo clean after pull
                     self._cachestorehash(srcurl)
 
     @annotatesubrepoerror
     def get(self, state, overwrite=False):
         self._get(state)
         source, revision, kind = state
         self._repo.ui.debug("getting subrepo %s\n" % self._path)
         hg.updaterepo(self._repo, revision, overwrite)
 
     @annotatesubrepoerror
     def merge(self, state):
         self._get(state)
         cur = self._repo['.']
         dst = self._repo[state[1]]
         anc = dst.ancestor(cur)
 
         def mergefunc():
             if anc == cur and dst.branch() == cur.branch():
                 self._repo.ui.debug("updating subrepo %s\n" % subrelpath(self))
                 hg.update(self._repo, state[1])
             elif anc == dst:
                 self._repo.ui.debug("skipping subrepo %s\n" % subrelpath(self))
             else:
                 self._repo.ui.debug("merging subrepo %s\n" % subrelpath(self))
                 hg.merge(self._repo, state[1], remind=False)
 
         wctx = self._repo[None]
         if self.dirty():
             if anc != dst:
                 if _updateprompt(self._repo.ui, self, wctx.dirty(), cur, dst):
                     mergefunc()
             else:
                 mergefunc()
         else:
             mergefunc()
 
     @annotatesubrepoerror
     def push(self, opts):
         force = opts.get('force')
         newbranch = opts.get('new_branch')
         ssh = opts.get('ssh')
 
         # push subrepos depth-first for coherent ordering
         c = self._repo['']
         subs = c.substate # only repos that are committed
         for s in sorted(subs):
             if c.sub(s).push(opts) == 0:
                 return False
 
         dsturl = _abssource(self._repo, True)
         if not force:
             if self.storeclean(dsturl):
                 self._repo.ui.status(
                     _('no changes made to subrepo %s since last push to %s\n')
                     % (subrelpath(self), dsturl))
                 return None
         self._repo.ui.status(_('pushing subrepo %s to %s\n') %
             (subrelpath(self), dsturl))
         other = hg.peer(self._repo, {'ssh': ssh}, dsturl)
         res = self._repo.push(other, force, newbranch=newbranch)
 
         # the repo is now clean
         self._cachestorehash(dsturl)
         return res
 
     @annotatesubrepoerror
     def outgoing(self, ui, dest, opts):
         return hg.outgoing(ui, self._repo, _abssource(self._repo, True), opts)
 
     @annotatesubrepoerror
     def incoming(self, ui, source, opts):
         return hg.incoming(ui, self._repo, _abssource(self._repo, False), opts)
 
     @annotatesubrepoerror
     def files(self):
         rev = self._state[1]
         ctx = self._repo[rev]
         return ctx.manifest()
 
     def filedata(self, name):
         rev = self._state[1]
         return self._repo[rev][name].data()
 
     def fileflags(self, name):
         rev = self._state[1]
         ctx = self._repo[rev]
         return ctx.flags(name)
 
     def walk(self, match):
         ctx = self._repo[None]
         return ctx.walk(match)
 
     @annotatesubrepoerror
     def forget(self, ui, match, prefix):
         return cmdutil.forget(ui, self._repo, match,
                               os.path.join(prefix, self._path), True)
 
     @annotatesubrepoerror
     def revert(self, ui, substate, *pats, **opts):
         # reverting a subrepo is a 2 step process:
         # 1. if the no_backup is not set, revert all modified
         #    files inside the subrepo
         # 2. update the subrepo to the revision specified in
         #    the corresponding substate dictionary
         ui.status(_('reverting subrepo %s\n') % substate[0])
         if not opts.get('no_backup'):
             # Revert all files on the subrepo, creating backups
             # Note that this will not recursively revert subrepos
             # We could do it if there was a set:subrepos() predicate
             opts = opts.copy()
             opts['date'] = None
             opts['rev'] = substate[1]
 
             pats = []
             if not opts.get('all'):
                 pats = ['set:modified()']
             self.filerevert(ui, *pats, **opts)
 
         # Update the repo to the revision specified in the given substate
         self.get(substate, overwrite=True)
 
     def filerevert(self, ui, *pats, **opts):
         ctx = self._repo[opts['rev']]
         parents = self._repo.dirstate.parents()
         if opts.get('all'):
             pats = ['set:modified()']
         else:
             pats = []
         cmdutil.revert(ui, self._repo, ctx, parents, *pats, **opts)
 
 class svnsubrepo(abstractsubrepo):
     def __init__(self, ctx, path, state):
         self._path = path
         self._state = state
         self._ctx = ctx
         self._ui = ctx._repo.ui
         self._exe = util.findexe('svn')
         if not self._exe:
             raise util.Abort(_("'svn' executable not found for subrepo '%s'")
                              % self._path)
 
     def _svncommand(self, commands, filename='', failok=False):
         cmd = [self._exe]
         extrakw = {}
         if not self._ui.interactive():
             # Making stdin be a pipe should prevent svn from behaving
             # interactively even if we can't pass --non-interactive.
             extrakw['stdin'] = subprocess.PIPE
             # Starting in svn 1.5 --non-interactive is a global flag
             # instead of being per-command, but we need to support 1.4 so
             # we have to be intelligent about what commands take
             # --non-interactive.
             if commands[0] in ('update', 'checkout', 'commit'):
                 cmd.append('--non-interactive')
         cmd.extend(commands)
         if filename is not None:
             path = os.path.join(self._ctx._repo.origroot, self._path, filename)
             cmd.append(path)
         env = dict(os.environ)
         # Avoid localized output, preserve current locale for everything else.
         lc_all = env.get('LC_ALL')
         if lc_all:
             env['LANG'] = lc_all
             del env['LC_ALL']
         env['LC_MESSAGES'] = 'C'
         p = subprocess.Popen(cmd, bufsize=-1, close_fds=util.closefds,
                              stdout=subprocess.PIPE, stderr=subprocess.PIPE,
                               universal_newlines=True, env=env, **extrakw)
         stdout, stderr = p.communicate()
         stderr = stderr.strip()
         if not failok:
             if p.returncode:
                 raise util.Abort(stderr or 'exited with code %d' % p.returncode)
             if stderr:
                 self._ui.warn(stderr + '\n')
         return stdout, stderr
 
     @propertycache
     def _svnversion(self):
         output, err = self._svncommand(['--version', '--quiet'], filename=None)
         m = re.search(r'^(\d+)\.(\d+)', output)
         if not m:
             raise util.Abort(_('cannot retrieve svn tool version'))
         return (int(m.group(1)), int(m.group(2)))
 
     def _wcrevs(self):
         # Get the working directory revision as well as the last
         # commit revision so we can compare the subrepo state with
         # both. We used to store the working directory one.
         output, err = self._svncommand(['info', '--xml'])
         doc = xml.dom.minidom.parseString(output)
         entries = doc.getElementsByTagName('entry')
         lastrev, rev = '0', '0'
         if entries:
             rev = str(entries[0].getAttribute('revision')) or '0'
             commits = entries[0].getElementsByTagName('commit')
             if commits:
                 lastrev = str(commits[0].getAttribute('revision')) or '0'
         return (lastrev, rev)
 
     def _wcrev(self):
         return self._wcrevs()[0]
 
     def _wcchanged(self):
         """Return (changes, extchanges, missing) where changes is True
         if the working directory was changed, extchanges is
         True if any of these changes concern an external entry and missing
         is True if any change is a missing entry.
         """
         output, err = self._svncommand(['status', '--xml'])
         externals, changes, missing = [], [], []
         doc = xml.dom.minidom.parseString(output)
         for e in doc.getElementsByTagName('entry'):
             s = e.getElementsByTagName('wc-status')
             if not s:
                 continue
             item = s[0].getAttribute('item')
             props = s[0].getAttribute('props')
             path = e.getAttribute('path')
             if item == 'external':
                 externals.append(path)
             elif item == 'missing':
                 missing.append(path)
             if (item not in ('', 'normal', 'unversioned', 'external')
                 or props not in ('', 'none', 'normal')):
                 changes.append(path)
         for path in changes:
             for ext in externals:
                 if path == ext or path.startswith(ext + os.sep):
                     return True, True, bool(missing)
         return bool(changes), False, bool(missing)
 
     def dirty(self, ignoreupdate=False):
         if not self._wcchanged()[0]:
             if self._state[1] in self._wcrevs() or ignoreupdate:
                 return False
         return True
 
     def basestate(self):
         lastrev, rev = self._wcrevs()
         if lastrev != rev:
             # Last committed rev is not the same than rev. We would
             # like to take lastrev but we do not know if the subrepo
             # URL exists at lastrev.  Test it and fallback to rev it
             # is not there.
             try:
                 self._svncommand(['list', '%s@%s' % (self._state[0], lastrev)])
                 return lastrev
             except error.Abort:
                 pass
         return rev
 
     @annotatesubrepoerror
     def commit(self, text, user, date):
         # user and date are out of our hands since svn is centralized
         changed, extchanged, missing = self._wcchanged()
         if not changed:
             return self.basestate()
         if extchanged:
             # Do not try to commit externals
             raise util.Abort(_('cannot commit svn externals'))
         if missing:
             # svn can commit with missing entries but aborting like hg
             # seems a better approach.
             raise util.Abort(_('cannot commit missing svn entries'))
         commitinfo, err = self._svncommand(['commit', '-m', text])
         self._ui.status(commitinfo)
         newrev = re.search('Committed revision ([0-9]+).', commitinfo)
         if not newrev:
             if not commitinfo.strip():
                 # Sometimes, our definition of "changed" differs from
                 # svn one. For instance, svn ignores missing files
                 # when committing. If there are only missing files, no
                 # commit is made, no output and no error code.
                 raise util.Abort(_('failed to commit svn changes'))
             raise util.Abort(commitinfo.splitlines()[-1])
         newrev = newrev.groups()[0]
         self._ui.status(self._svncommand(['update', '-r', newrev])[0])
         return newrev
 
     @annotatesubrepoerror
     def remove(self):
         if self.dirty():
             self._ui.warn(_('not removing repo %s because '
                             'it has changes.\n' % self._path))
             return
         self._ui.note(_('removing subrepo %s\n') % self._path)
 
         def onerror(function, path, excinfo):
             if function is not os.remove:
                 raise
             # read-only files cannot be unlinked under Windows
             s = os.stat(path)
             if (s.st_mode & stat.S_IWRITE) != 0:
                 raise
             os.chmod(path, stat.S_IMODE(s.st_mode) | stat.S_IWRITE)
             os.remove(path)
 
         path = self._ctx._repo.wjoin(self._path)
         shutil.rmtree(path, onerror=onerror)
         try:
             os.removedirs(os.path.dirname(path))
         except OSError:
             pass
 
     @annotatesubrepoerror
     def get(self, state, overwrite=False):
         if overwrite:
             self._svncommand(['revert', '--recursive'])
         args = ['checkout']
         if self._svnversion >= (1, 5):
             args.append('--force')
         # The revision must be specified at the end of the URL to properly
         # update to a directory which has since been deleted and recreated.
         args.append('%s@%s' % (state[0], state[1]))
         status, err = self._svncommand(args, failok=True)
         if not re.search('Checked out revision [0-9]+.', status):
             if ('is already a working copy for a different URL' in err
                 and (self._wcchanged()[:2] == (False, False))):
                 # obstructed but clean working copy, so just blow it away.
                 self.remove()
                 self.get(state, overwrite=False)
                 return
             raise util.Abort((status or err).splitlines()[-1])
         self._ui.status(status)
 
     @annotatesubrepoerror
     def merge(self, state):
         old = self._state[1]
         new = state[1]
         wcrev = self._wcrev()
         if new != wcrev:
             dirty = old == wcrev or self._wcchanged()[0]
             if _updateprompt(self._ui, self, dirty, wcrev, new):
                 self.get(state, False)
 
     def push(self, opts):
         # push is a no-op for SVN
         return True
 
     @annotatesubrepoerror
     def files(self):
         output = self._svncommand(['list', '--recursive', '--xml'])[0]
         doc = xml.dom.minidom.parseString(output)
         paths = []
         for e in doc.getElementsByTagName('entry'):
             kind = str(e.getAttribute('kind'))
             if kind != 'file':
                 continue
             name = ''.join(c.data for c
                            in e.getElementsByTagName('name')[0].childNodes
                            if c.nodeType == c.TEXT_NODE)
             paths.append(name.encode('utf-8'))
         return paths
 
     def filedata(self, name):
         return self._svncommand(['cat'], name)[0]
 
 
 class gitsubrepo(abstractsubrepo):
     def __init__(self, ctx, path, state):
         self._state = state
         self._ctx = ctx
         self._path = path
         self._relpath = os.path.join(reporelpath(ctx._repo), path)
         self._abspath = ctx._repo.wjoin(path)
         self._subparent = ctx._repo
         self._ui = ctx._repo.ui
         self._ensuregit()
 
     def _ensuregit(self):
         try:
             self._gitexecutable = 'git'
             out, err = self._gitnodir(['--version'])
         except OSError, e:
             if e.errno != 2 or os.name != 'nt':
                 raise
             self._gitexecutable = 'git.cmd'
             out, err = self._gitnodir(['--version'])
         m = re.search(r'^git version (\d+)\.(\d+)\.(\d+)', out)
         if not m:
             self._ui.warn(_('cannot retrieve git version'))
             return
         version = (int(m.group(1)), m.group(2), m.group(3))
         # git 1.4.0 can't work at all, but 1.5.X can in at least some cases,
         # despite the docstring comment.  For now, error on 1.4.0, warn on
         # 1.5.0 but attempt to continue.
         if version < (1, 5, 0):
             raise util.Abort(_('git subrepo requires at least 1.6.0 or later'))
         elif version < (1, 6, 0):
             self._ui.warn(_('git subrepo requires at least 1.6.0 or later'))
 
     def _gitcommand(self, commands, env=None, stream=False):
         return self._gitdir(commands, env=env, stream=stream)[0]
 
     def _gitdir(self, commands, env=None, stream=False):
         return self._gitnodir(commands, env=env, stream=stream,
                               cwd=self._abspath)
 
     def _gitnodir(self, commands, env=None, stream=False, cwd=None):
         """Calls the git command
 
         The methods tries to call the git command. versions prior to 1.6.0
         are not supported and very probably fail.
         """
         self._ui.debug('%s: git %s\n' % (self._relpath, ' '.join(commands)))
         # unless ui.quiet is set, print git's stderr,
         # which is mostly progress and useful info
         errpipe = None
         if self._ui.quiet:
             errpipe = open(os.devnull, 'w')
         p = subprocess.Popen([self._gitexecutable] + commands, bufsize=-1,
                              cwd=cwd, env=env, close_fds=util.closefds,
                              stdout=subprocess.PIPE, stderr=errpipe)
         if stream:
             return p.stdout, None
 
         retdata = p.stdout.read().strip()
         # wait for the child to exit to avoid race condition.
         p.wait()
 
         if p.returncode != 0 and p.returncode != 1:
             # there are certain error codes that are ok
             command = commands[0]
             if command in ('cat-file', 'symbolic-ref'):
                 return retdata, p.returncode
             # for all others, abort
             raise util.Abort('git %s error %d in %s' %
                              (command, p.returncode, self._relpath))
 
         return retdata, p.returncode
 
     def _gitmissing(self):
         return not os.path.exists(os.path.join(self._abspath, '.git'))
 
     def _gitstate(self):
         return self._gitcommand(['rev-parse', 'HEAD'])
 
     def _gitcurrentbranch(self):
         current, err = self._gitdir(['symbolic-ref', 'HEAD', '--quiet'])
         if err:
             current = None
         return current
 
     def _gitremote(self, remote):
         out = self._gitcommand(['remote', 'show', '-n', remote])
         line = out.split('\n')[1]
         i = line.index('URL: ') + len('URL: ')
         return line[i:]
 
     def _githavelocally(self, revision):
         out, code = self._gitdir(['cat-file', '-e', revision])
         return code == 0
 
     def _gitisancestor(self, r1, r2):
         base = self._gitcommand(['merge-base', r1, r2])
         return base == r1
 
     def _gitisbare(self):
         return self._gitcommand(['config', '--bool', 'core.bare']) == 'true'
 
     def _gitupdatestat(self):
         """This must be run before git diff-index.
         diff-index only looks at changes to file stat;
         this command looks at file contents and updates the stat."""
         self._gitcommand(['update-index', '-q', '--refresh'])
 
     def _gitbranchmap(self):
         '''returns 2 things:
         a map from git branch to revision
         a map from revision to branches'''
         branch2rev = {}
         rev2branch = {}
 
         out = self._gitcommand(['for-each-ref', '--format',
                                 '%(objectname) %(refname)'])
         for line in out.split('\n'):
             revision, ref = line.split(' ')
             if (not ref.startswith('refs/heads/') and
                 not ref.startswith('refs/remotes/')):
                 continue
             if ref.startswith('refs/remotes/') and ref.endswith('/HEAD'):
                 continue # ignore remote/HEAD redirects
             branch2rev[ref] = revision
             rev2branch.setdefault(revision, []).append(ref)
         return branch2rev, rev2branch
 
     def _gittracking(self, branches):
         'return map of remote branch to local tracking branch'
         # assumes no more than one local tracking branch for each remote
         tracking = {}
         for b in branches:
             if b.startswith('refs/remotes/'):
                 continue
             bname = b.split('/', 2)[2]
             remote = self._gitcommand(['config', 'branch.%s.remote' % bname])
             if remote:
                 ref = self._gitcommand(['config', 'branch.%s.merge' % bname])
                 tracking['refs/remotes/%s/%s' %
                          (remote, ref.split('/', 2)[2])] = b
         return tracking
 
     def _abssource(self, source):
         if '://' not in source:
             # recognize the scp syntax as an absolute source
             colon = source.find(':')
             if colon != -1 and '/' not in source[:colon]:
                 return source
         self._subsource = source
         return _abssource(self)
 
     def _fetch(self, source, revision):
         if self._gitmissing():
             source = self._abssource(source)
             self._ui.status(_('cloning subrepo %s from %s\n') %
                             (self._relpath, source))
             self._gitnodir(['clone', source, self._abspath])
         if self._githavelocally(revision):
             return
         self._ui.status(_('pulling subrepo %s from %s\n') %
                         (self._relpath, self._gitremote('origin')))
         # try only origin: the originally cloned repo
         self._gitcommand(['fetch'])
         if not self._githavelocally(revision):
             raise util.Abort(_("revision %s does not exist in subrepo %s\n") %
                                (revision, self._relpath))
 
     @annotatesubrepoerror
     def dirty(self, ignoreupdate=False):
         if self._gitmissing():
             return self._state[1] != ''
         if self._gitisbare():
             return True
         if not ignoreupdate and self._state[1] != self._gitstate():
             # different version checked out
             return True
         # check for staged changes or modified files; ignore untracked files
         self._gitupdatestat()
         out, code = self._gitdir(['diff-index', '--quiet', 'HEAD'])
         return code == 1
 
     def basestate(self):
         return self._gitstate()
 
     @annotatesubrepoerror
     def get(self, state, overwrite=False):
         source, revision, kind = state
         if not revision:
             self.remove()
             return
         self._fetch(source, revision)
         # if the repo was set to be bare, unbare it
         if self._gitisbare():
             self._gitcommand(['config', 'core.bare', 'false'])
             if self._gitstate() == revision:
                 self._gitcommand(['reset', '--hard', 'HEAD'])
                 return
         elif self._gitstate() == revision:
             if overwrite:
                 # first reset the index to unmark new files for commit, because
                 # reset --hard will otherwise throw away files added for commit,
                 # not just unmark them.
                 self._gitcommand(['reset', 'HEAD'])
                 self._gitcommand(['reset', '--hard', 'HEAD'])
             return
         branch2rev, rev2branch = self._gitbranchmap()
 
         def checkout(args):
             cmd = ['checkout']
             if overwrite:
                 # first reset the index to unmark new files for commit, because
                 # the -f option will otherwise throw away files added for
                 # commit, not just unmark them.
                 self._gitcommand(['reset', 'HEAD'])
                 cmd.append('-f')
             self._gitcommand(cmd + args)
 
         def rawcheckout():
             # no branch to checkout, check it out with no branch
             self._ui.warn(_('checking out detached HEAD in subrepo %s\n') %
                           self._relpath)
             self._ui.warn(_('check out a git branch if you intend '
                             'to make changes\n'))
             checkout(['-q', revision])
 
         if revision not in rev2branch:
             rawcheckout()
             return
         branches = rev2branch[revision]
         firstlocalbranch = None
         for b in branches:
             if b == 'refs/heads/master':
                 # master trumps all other branches
                 checkout(['refs/heads/master'])
                 return
             if not firstlocalbranch and not b.startswith('refs/remotes/'):
                 firstlocalbranch = b
         if firstlocalbranch:
             checkout([firstlocalbranch])
             return
 
         tracking = self._gittracking(branch2rev.keys())
         # choose a remote branch already tracked if possible
         remote = branches[0]
         if remote not in tracking:
             for b in branches:
                 if b in tracking:
                     remote = b
                     break
 
         if remote not in tracking:
             # create a new local tracking branch
             local = remote.split('/', 3)[3]
             checkout(['-b', local, remote])
         elif self._gitisancestor(branch2rev[tracking[remote]], remote):
             # When updating to a tracked remote branch,
             # if the local tracking branch is downstream of it,
             # a normal `git pull` would have performed a "fast-forward merge"
             # which is equivalent to updating the local branch to the remote.
             # Since we are only looking at branching at update, we need to
             # detect this situation and perform this action lazily.
             if tracking[remote] != self._gitcurrentbranch():
                 checkout([tracking[remote]])
             self._gitcommand(['merge', '--ff', remote])
         else:
             # a real merge would be required, just checkout the revision
             rawcheckout()
 
     @annotatesubrepoerror
     def commit(self, text, user, date):
         if self._gitmissing():
             raise util.Abort(_("subrepo %s is missing") % self._relpath)
         cmd = ['commit', '-a', '-m', text]
         env = os.environ.copy()
         if user:
             cmd += ['--author', user]
         if date:
             # git's date parser silently ignores when seconds < 1e9
             # convert to ISO8601
             env['GIT_AUTHOR_DATE'] = util.datestr(date,
                                                   '%Y-%m-%dT%H:%M:%S %1%2')
         self._gitcommand(cmd, env=env)
         # make sure commit works otherwise HEAD might not exist under certain
         # circumstances
         return self._gitstate()
 
     @annotatesubrepoerror
     def merge(self, state):
         source, revision, kind = state
         self._fetch(source, revision)
         base = self._gitcommand(['merge-base', revision, self._state[1]])
         self._gitupdatestat()
         out, code = self._gitdir(['diff-index', '--quiet', 'HEAD'])
 
         def mergefunc():
             if base == revision:
                 self.get(state) # fast forward merge
             elif base != self._state[1]:
                 self._gitcommand(['merge', '--no-commit', revision])
 
         if self.dirty():
             if self._gitstate() != revision:
                 dirty = self._gitstate() == self._state[1] or code != 0
                 if _updateprompt(self._ui, self, dirty,
                                  self._state[1][:7], revision[:7]):
                     mergefunc()
         else:
             mergefunc()
 
     @annotatesubrepoerror
     def push(self, opts):
         force = opts.get('force')
 
         if not self._state[1]:
             return True
         if self._gitmissing():
             raise util.Abort(_("subrepo %s is missing") % self._relpath)
         # if a branch in origin contains the revision, nothing to do
         branch2rev, rev2branch = self._gitbranchmap()
         if self._state[1] in rev2branch:
             for b in rev2branch[self._state[1]]:
                 if b.startswith('refs/remotes/origin/'):
                     return True
         for b, revision in branch2rev.iteritems():
             if b.startswith('refs/remotes/origin/'):
                 if self._gitisancestor(self._state[1], revision):
                     return True
         # otherwise, try to push the currently checked out branch
         cmd = ['push']
         if force:
             cmd.append('--force')
 
         current = self._gitcurrentbranch()
         if current:
             # determine if the current branch is even useful
             if not self._gitisancestor(self._state[1], current):
                 self._ui.warn(_('unrelated git branch checked out '
                                 'in subrepo %s\n') % self._relpath)
                 return False
             self._ui.status(_('pushing branch %s of subrepo %s\n') %
                             (current.split('/', 2)[2], self._relpath))
             self._gitcommand(cmd + ['origin', current])
             return True
         else:
             self._ui.warn(_('no branch checked out in subrepo %s\n'
                             'cannot push revision %s\n') %
                           (self._relpath, self._state[1]))
             return False
 
     @annotatesubrepoerror
     def remove(self):
         if self._gitmissing():
             return
         if self.dirty():
             self._ui.warn(_('not removing repo %s because '
                             'it has changes.\n') % self._relpath)
             return
         # we can't fully delete the repository as it may contain
         # local-only history
         self._ui.note(_('removing subrepo %s\n') % self._relpath)
         self._gitcommand(['config', 'core.bare', 'true'])
         for f in os.listdir(self._abspath):
             if f == '.git':
                 continue
             path = os.path.join(self._abspath, f)
             if os.path.isdir(path) and not os.path.islink(path):
                 shutil.rmtree(path)
             else:
                 os.remove(path)
 
     def archive(self, ui, archiver, prefix, match=None):
         total = 0
         source, revision = self._state
         if not revision:
             return total
         self._fetch(source, revision)
 
         # Parse git's native archive command.
         # This should be much faster than manually traversing the trees
         # and objects with many subprocess calls.
         tarstream = self._gitcommand(['archive', revision], stream=True)
         tar = tarfile.open(fileobj=tarstream, mode='r|')
         relpath = subrelpath(self)
         ui.progress(_('archiving (%s)') % relpath, 0, unit=_('files'))
         for i, info in enumerate(tar):
             if info.isdir():
                 continue
             if match and not match(info.name):
                 continue
             if info.issym():
                 data = info.linkname
             else:
                 data = tar.extractfile(info).read()
             archiver.addfile(os.path.join(prefix, self._path, info.name),
                              info.mode, info.issym(), data)
             total += 1
             ui.progress(_('archiving (%s)') % relpath, i + 1,
                         unit=_('files'))
         ui.progress(_('archiving (%s)') % relpath, None)
         return total
 
 
     @annotatesubrepoerror
     def status(self, rev2, **opts):
         rev1 = self._state[1]
         if self._gitmissing() or not rev1:
             # if the repo is missing, return no results
             return [], [], [], [], [], [], []
         modified, added, removed = [], [], []
         self._gitupdatestat()
         if rev2:
             command = ['diff-tree', rev1, rev2]
         else:
             command = ['diff-index', rev1]
         out = self._gitcommand(command)
         for line in out.split('\n'):
             tab = line.find('\t')
             if tab == -1:
                 continue
             status, f = line[tab - 1], line[tab + 1:]
             if status == 'M':
                 modified.append(f)
             elif status == 'A':
                 added.append(f)
             elif status == 'D':
                 removed.append(f)
 
         deleted = unknown = ignored = clean = []
         return modified, added, removed, deleted, unknown, ignored, clean
 
 types = {
     'hg': hgsubrepo,
     'svn': svnsubrepo,
     'git': gitsubrepo,
     }