Prefer i in d over d.has_key(i)

contrib/churn.py

@@ -1,204 +1,204 b''
 # churn.py - create a graph showing who changed the most lines
 #
 # Copyright 2006 Josef "Jeff" Sipek <[e-mail]>
 #
 # This software may be used and distributed according to the terms
 # of the GNU General Public License, incorporated herein by reference.
 #
 #
 # Aliases map file format is simple one alias per line in the following
 # format:
 #
 # <alias email> <actual email>
 
 from mercurial.i18n import gettext as _
 from mercurial import hg, mdiff, cmdutil, ui, util, templater, node
 import os, sys
 
 def get_tty_width():
     if 'COLUMNS' in os.environ:
         try:
             return int(os.environ['COLUMNS'])
         except ValueError:
             pass
     try:
         import termios, array, fcntl
         for dev in (sys.stdout, sys.stdin):
             try:
                 fd = dev.fileno()
                 if not os.isatty(fd):
                     continue
                 arri = fcntl.ioctl(fd, termios.TIOCGWINSZ, '\0' * 8)
                 return array.array('h', arri)[1]
             except ValueError:
                 pass
     except ImportError:
         pass
     return 80
 
 def __gather(ui, repo, node1, node2):
     def dirtywork(f, mmap1, mmap2):
         lines = 0
 
         to = mmap1 and repo.file(f).read(mmap1[f]) or None
         tn = mmap2 and repo.file(f).read(mmap2[f]) or None
 
         diff = mdiff.unidiff(to, "", tn, "", f, f).split("\n")
 
         for line in diff:
             if not line:
                 continue # skip EOF
             if line.startswith(" "):
                 continue # context line
             if line.startswith("--- ") or line.startswith("+++ "):
                 continue # begining of diff
             if line.startswith("@@ "):
                 continue # info line
 
             # changed lines
             lines += 1
 
         return lines
 
     ##
 
     lines = 0
 
     changes = repo.status(node1, node2, None, util.always)[:5]
 
     modified, added, removed, deleted, unknown = changes
 
     who = repo.changelog.read(node2)[1]
     who = templater.email(who) # get the email of the person
 
     mmap1 = repo.manifest.read(repo.changelog.read(node1)[0])
     mmap2 = repo.manifest.read(repo.changelog.read(node2)[0])
     for f in modified:
         lines += dirtywork(f, mmap1, mmap2)
 
     for f in added:
         lines += dirtywork(f, None, mmap2)
 
     for f in removed:
         lines += dirtywork(f, mmap1, None)
 
     for f in deleted:
         lines += dirtywork(f, mmap1, mmap2)
 
     for f in unknown:
         lines += dirtywork(f, mmap1, mmap2)
 
     return (who, lines)
 
 def gather_stats(ui, repo, amap, revs=None, progress=False):
     stats = {}
 
     cl    = repo.changelog
 
     if not revs:
         revs = range(0, cl.count())
 
     nr_revs = len(revs)
     cur_rev = 0
 
     for rev in revs:
         cur_rev += 1 # next revision
 
         node2    = cl.node(rev)
         node1    = cl.parents(node2)[0]
 
         if cl.parents(node2)[1] != node.nullid:
             ui.note(_('Revision %d is a merge, ignoring...\n') % (rev,))
             continue
 
         who, lines = __gather(ui, repo, node1, node2)
 
         # remap the owner if possible
-        if amap.has_key(who):
+        if who in amap:
             ui.note("using '%s' alias for '%s'\n" % (amap[who], who))
             who = amap[who]
 
-        if not stats.has_key(who):
+        if not who in stats:
             stats[who] = 0
         stats[who] += lines
 
         ui.note("rev %d: %d lines by %s\n" % (rev, lines, who))
 
         if progress:
             nr_revs = max(nr_revs, 1)
             if int(100.0*(cur_rev - 1)/nr_revs) < int(100.0*cur_rev/nr_revs):
                 ui.write("%d%%.." % (int(100.0*cur_rev/nr_revs),))
                 sys.stdout.flush()
 
     if progress:
         ui.write("done\n")
         sys.stdout.flush()
 
     return stats
 
 def churn(ui, repo, **opts):
     "Graphs the number of lines changed"
 
     def pad(s, l):
         if len(s) < l:
             return s + " " * (l-len(s))
         return s[0:l]
 
     def graph(n, maximum, width, char):
         maximum = max(1, maximum)
         n = int(n * width / float(maximum))
 
         return char * (n)
 
     def get_aliases(f):
         aliases = {}
 
         for l in f.readlines():
             l = l.strip()
             alias, actual = l.split(" ")
             aliases[alias] = actual
 
         return aliases
 
     amap = {}
     aliases = opts.get('aliases')
     if aliases:
         try:
             f = open(aliases,"r")
         except OSError, e:
             print "Error: " + e
             return
 
         amap = get_aliases(f)
         f.close()
 
     revs = [int(r) for r in cmdutil.revrange(repo, opts['rev'])]
     revs.sort()
     stats = gather_stats(ui, repo, amap, revs, opts.get('progress'))
 
     # make a list of tuples (name, lines) and sort it in descending order
     ordered = stats.items()
     ordered.sort(lambda x, y: cmp(y[1], x[1]))
 
     if not ordered:
         return
     maximum = ordered[0][1]
 
     width = get_tty_width()
     ui.note(_("assuming %i character terminal\n") % width)
     width -= 1
 
     for i in ordered:
         person = i[0]
         lines = i[1]
         print "%s %6d %s" % (pad(person, 20), lines,
                 graph(lines, maximum, width - 20 - 1 - 6 - 2 - 2, '*'))
 
 cmdtable = {
     "churn":
     (churn,
      [('r', 'rev', [], _('limit statistics to the specified revisions')),
       ('', 'aliases', '', _('file with email aliases')),
       ('', 'progress', None, _('show progress'))],
     'hg churn [-r revision range] [-a file] [--progress]'),
 }

hgext/keyword.py

@@ -1,521 +1,521 b''
 # keyword.py - $Keyword$ expansion for Mercurial
 #
 # Copyright 2007, 2008 Christian Ebert <[e-mail]>
 #
 # This software may be used and distributed according to the terms
 # of the GNU General Public License, incorporated herein by reference.
 #
 # $Id$
 #
 # Keyword expansion hack against the grain of a DSCM
 #
 # 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://www.selenic.com/mercurial/wiki/index.cgi/KeywordPlan>.
 #
 # Keyword expansion is based on Mercurial's changeset template mappings.
 #
 # Binary files are not touched.
 #
 # Setup in hgrc:
 #
 #   [extensions]
 #   # enable extension
 #   hgext.keyword =
 #
 # 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.
 
 '''keyword expansion in local repositories
 
 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.
 
 Configuration is done in the [keyword] and [keywordmaps] sections
 of hgrc files.
 
 Example:
 
     [keyword]
     # expand keywords in every python file except those matching "x*"
     **.py =
     x*    = ignore
 
 Note: the more specific you are in your filename patterns
       the less you lose speed in huge repos.
 
 For [keywordmaps] template mapping and expansion demonstration and
 control run "hg kwdemo".
 
 An additional date template filter {date|utcdate} is provided.
 
 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 config changes.
 
 Before changing/disabling active keywords, run "hg kwshrink" to avoid
 the risk of inadvertedly storing expanded keywords in the change history.
 
 To force expansion after enabling it, or a configuration change, run
 "hg kwexpand".
 
 Also, when committing with the record extension or using mq's qrecord, be aware
 that keywords cannot be updated. Again, run "hg kwexpand" on the files in
 question to update keyword expansions after all changes have been checked in.
 
 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, cmdutil, context, dispatch, filelog
 from mercurial import patch, localrepo, revlog, templater, util
 from mercurial.node import *
 from mercurial.i18n import _
 import re, shutil, sys, tempfile, time
 
 commands.optionalrepo += ' kwdemo'
 
 def utcdate(date):
     '''Returns hgdate in cvs-like UTC format.'''
     return time.strftime('%Y/%m/%d %H:%M:%S', time.gmtime(date[0]))
 
 def _kwrestrict(cmd):
     '''Returns True if cmd should trigger restricted expansion.
     Keywords will only expanded when writing to working dir.
     Crucial for mq as expanded keywords should not make it into patches.'''
     return cmd in ('diff1', 
                    'qimport', 'qnew', 'qpush', 'qrefresh', 'record', 'qrecord')
 
 
 _kwtemplater = None
 
 class kwtemplater(object):
     '''
     Sets up keyword templates, corresponding keyword regex, and
     provides keyword substitution functions.
     '''
     templates = {
         'Revision': '{node|short}',
         'Author': '{author|user}',
         'Date': '{date|utcdate}',
         'RCSFile': '{file|basename},v',
         'Source': '{root}/{file},v',
         'Id': '{file|basename},v {node|short} {date|utcdate} {author|user}',
         'Header': '{root}/{file},v {node|short} {date|utcdate} {author|user}',
     }
 
     def __init__(self, ui, repo, inc, exc, hgcmd):
         self.ui = ui
         self.repo = repo
         self.matcher = util.matcher(repo.root, inc=inc, exc=exc)[1]
         self.hgcmd = hgcmd
         self.commitnode = None
         self.path = ''
 
         kwmaps = self.ui.configitems('keywordmaps')
         if kwmaps: # override default templates
             kwmaps = [(k, templater.parsestring(v, quoted=False))
                       for (k, v) in kwmaps]
             self.templates = dict(kwmaps)
         escaped = map(re.escape, self.templates.keys())
         kwpat = r'\$(%s)(: [^$\n\r]*? )??\$' % '|'.join(escaped)
         self.re_kw = re.compile(kwpat)
 
         templater.common_filters['utcdate'] = utcdate
         self.ct = cmdutil.changeset_templater(self.ui, self.repo,
                                               False, '', False)
 
     def substitute(self, node, data, subfunc):
         '''Obtains file's changenode if commit node not given,
         and calls given substitution function.'''
         if self.commitnode:
             fnode = self.commitnode
         else:
             c = context.filectx(self.repo, self.path, fileid=node)
             fnode = c.node()
 
         def kwsub(mobj):
             '''Substitutes keyword using corresponding template.'''
             kw = mobj.group(1)
             self.ct.use_template(self.templates[kw])
             self.ui.pushbuffer()
             self.ct.show(changenode=fnode, root=self.repo.root, file=self.path)
             return '$%s: %s $' % (kw, templater.firstline(self.ui.popbuffer()))
 
         return subfunc(kwsub, data)
 
     def expand(self, node, data):
         '''Returns data with keywords expanded.'''
         if util.binary(data) or _kwrestrict(self.hgcmd):
             return data
         return self.substitute(node, data, self.re_kw.sub)
 
     def process(self, node, data, expand):
         '''Returns a tuple: data, count.
         Count is number of keywords/keyword substitutions,
         telling caller whether to act on file containing data.'''
         if util.binary(data):
             return data, None
         if expand:
             return self.substitute(node, data, self.re_kw.subn)
         return data, self.re_kw.search(data)
 
     def shrink(self, text):
         '''Returns text with all keyword substitutions removed.'''
         if util.binary(text):
             return text
         return self.re_kw.sub(r'$\1$', text)
 
 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, path):
         super(kwfilelog, self).__init__(opener, path)
         _kwtemplater.path = path
 
     def kwctread(self, node, expand):
         '''Reads expanding and counting keywords, called from _overwrite.'''
         data = super(kwfilelog, self).read(node)
         return _kwtemplater.process(node, data, expand)
 
     def read(self, node):
         '''Expands keywords when reading filelog.'''
         data = super(kwfilelog, self).read(node)
         return _kwtemplater.expand(node, data)
 
     def add(self, text, meta, tr, link, p1=None, p2=None):
         '''Removes keyword substitutions when adding to filelog.'''
         text = _kwtemplater.shrink(text)
         return super(kwfilelog, self).add(text, meta, tr, link, p1=p1, p2=p2)
 
     def cmp(self, node, text):
         '''Removes keyword substitutions for comparison.'''
         text = _kwtemplater.shrink(text)
         if self.renamed(node):
             t2 = super(kwfilelog, self).read(node)
             return t2 != text
         return revlog.revlog.cmp(self, node, text)
 
 
 # store original patch.patchfile.__init__
 _patchfile_init = patch.patchfile.__init__
 
 def _kwpatchfile_init(self, ui, fname, missing=False):
     '''Monkeypatch/wrap patch.patchfile.__init__ to avoid
     rejects or conflicts due to expanded keywords in working dir.'''
     _patchfile_init(self, ui, fname, missing=missing)
 
     if _kwtemplater.matcher(self.fname):
         # shrink keywords read from working dir
         kwshrunk = _kwtemplater.shrink(''.join(self.lines))
         self.lines = kwshrunk.splitlines(True)
 
 
 def _iskwfile(f, link):
     return not link(f) and _kwtemplater.matcher(f)
 
 def _status(ui, repo, *pats, **opts):
     '''Bails out if [keyword] configuration is not active.
     Returns status of working directory.'''
     if _kwtemplater:
         files, match, anypats = cmdutil.matchpats(repo, pats, opts)
         return repo.status(files=files, match=match, list_clean=True)
     if ui.configitems('keyword'):
         raise util.Abort(_('[keyword] patterns cannot match'))
     raise util.Abort(_('no [keyword] patterns configured'))
 
 def _overwrite(ui, repo, node=None, expand=True, files=None):
     '''Overwrites selected files expanding/shrinking keywords.'''
     ctx = repo.changectx(node)
     mf = ctx.manifest()
     if node is not None:   # commit
         _kwtemplater.commitnode = node
-        files = [f for f in ctx.files() if mf.has_key(f)]
+        files = [f for f in ctx.files() if f in mf]
         notify = ui.debug
     else:                  # kwexpand/kwshrink
         notify = ui.note
     candidates = [f for f in files if _iskwfile(f, mf.linkf)]
     if candidates:
         candidates.sort()
         action = expand and 'expanding' or 'shrinking'
         for f in candidates:
             fp = repo.file(f, kwmatch=True)
             data, kwfound = fp.kwctread(mf[f], expand)
             if kwfound:
                 notify(_('overwriting %s %s keywords\n') % (f, action))
                 repo.wwrite(f, data, mf.flags(f))
                 repo.dirstate.normal(f)
 
 def _kwfwrite(ui, repo, expand, *pats, **opts):
     '''Selects files and passes them to _overwrite.'''
     status = _status(ui, repo, *pats, **opts)
     modified, added, removed, deleted, unknown, ignored, clean = status
     if modified or added or removed or deleted:
         raise util.Abort(_('outstanding uncommitted changes in given files'))
     wlock = lock = None
     try:
         wlock = repo.wlock()
         lock = repo.lock()
         _overwrite(ui, repo, expand=expand, files=clean)
     finally:
         del wlock, lock
 
 
 def demo(ui, repo, *args, **opts):
     '''print [keywordmaps] configuration and an expansion example
 
     Show current, custom, or default keyword template maps
     and their expansion.
 
     Extend current configuration by specifying maps as arguments
     and optionally by reading from an additional hgrc file.
 
     Override current keyword template maps with "default" option.
     '''
     def demostatus(stat):
         ui.status(_('\n\t%s\n') % stat)
 
     def demoitems(section, items):
         ui.write('[%s]\n' % section)
         for k, v in items:
             ui.write('%s = %s\n' % (k, v))
 
     msg = 'hg keyword config and expansion example'
     kwstatus = 'current'
     fn = 'demo.txt'
     branchname = 'demobranch'
     tmpdir = tempfile.mkdtemp('', 'kwdemo.')
     ui.note(_('creating temporary repo at %s\n') % tmpdir)
     repo = localrepo.localrepository(ui, path=tmpdir, create=True)
     ui.setconfig('keyword', fn, '')
     if args or opts.get('rcfile'):
         kwstatus = 'custom'
     if opts.get('rcfile'):
         ui.readconfig(opts.get('rcfile'))
     if opts.get('default'):
         kwstatus = 'default'
         kwmaps = kwtemplater.templates
         if ui.configitems('keywordmaps'):
             # override maps from optional rcfile
             for k, v in kwmaps.items():
                 ui.setconfig('keywordmaps', k, v)
     elif 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'))
     if not opts.get('default'):
         kwmaps = dict(ui.configitems('keywordmaps')) or kwtemplater.templates
     reposetup(ui, repo)
     for k, v in ui.configitems('extensions'):
         if k.endswith('keyword'):
             extension = '%s = %s' % (k, v)
             break
     demostatus('config using %s keyword template maps' % kwstatus)
     ui.write('[extensions]\n%s\n' % extension)
     demoitems('keyword', ui.configitems('keyword'))
     demoitems('keywordmaps', kwmaps.items())
     keywords = '$' + '$\n$'.join(kwmaps.keys()) + '$\n'
     repo.wopener(fn, 'w').write(keywords)
     repo.add([fn])
     path = repo.wjoin(fn)
     ui.note(_('\n%s keywords written to %s:\n') % (kwstatus, path))
     ui.note(keywords)
     ui.note('\nhg -R "%s" branch "%s"\n' % (tmpdir, branchname))
     # silence branch command if not verbose
     quiet = ui.quiet
     ui.quiet = not ui.verbose
     commands.branch(ui, repo, branchname)
     ui.quiet = quiet
     for name, cmd in ui.configitems('hooks'):
         if name.split('.', 1)[0].find('commit') > -1:
             repo.ui.setconfig('hooks', name, '')
     ui.note(_('unhooked all commit hooks\n'))
     ui.note('hg -R "%s" ci -m "%s"\n' % (tmpdir, msg))
     repo.commit(text=msg)
     format = ui.verbose and ' in %s' % path or ''
     demostatus('%s keywords expanded%s' % (kwstatus, format))
     ui.write(repo.wread(fn))
     ui.debug(_('\nremoving temporary repo %s\n') % tmpdir)
     shutil.rmtree(tmpdir, ignore_errors=True)
 
 def expand(ui, repo, *pats, **opts):
     '''expand keywords in 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)
 
 def files(ui, repo, *pats, **opts):
     '''print files currently configured for keyword expansion
 
     Crosscheck which files in working directory are potential targets for
     keyword expansion.
     That is, files matched by [keyword] config patterns but not symlinks.
     '''
     status = _status(ui, repo, *pats, **opts)
     modified, added, removed, deleted, unknown, ignored, clean = status
     files = modified + added + clean
     if opts.get('untracked'):
         files += unknown
     files.sort()
     kwfiles = [f for f in files if _iskwfile(f, repo._link)]
     cwd = pats and repo.getcwd() or ''
     kwfstats = not opts.get('ignore') and (('K', kwfiles),) or ()
     if opts.get('all') or opts.get('ignore'):
         kwfstats += (('I', [f for f in files if f not in kwfiles]),)
     for char, filenames in kwfstats:
         format = (opts.get('all') or ui.verbose) and '%s %%s\n' % char or '%s\n'
         for f in filenames:
             ui.write(format % repo.pathto(f, cwd))
 
 def shrink(ui, repo, *pats, **opts):
     '''revert expanded keywords in working directory
 
     Run before changing/disabling active keywords
     or if you experience problems with "hg import" or "hg merge".
 
     kwshrink refuses to run if given files contain local changes.
     '''
     # 3rd argument sets expansion to False
     _kwfwrite(ui, repo, False, *pats, **opts)
 
 
 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.
     This is done for local repos only, and only if there are
     files configured at all for keyword substitution.'''
 
     if not repo.local():
         return
 
     nokwcommands = ('add', 'addremove', 'bundle', 'clone', 'copy',
                     'export', 'grep', 'identify', 'incoming', 'init',
                     'log', 'outgoing', 'push', 'remove', 'rename',
                     'rollback', 'tip',
                     'convert')
     hgcmd, func, args, opts, cmdopts = dispatch._parse(ui, sys.argv[1:])
     if hgcmd in nokwcommands:
         return
 
     if hgcmd == 'diff':
         # only expand if comparing against working dir
         node1, node2 = cmdutil.revpair(repo, cmdopts.get('rev'))
         if node2 is not None:
             return
         # shrink if rev is not current node
         if node1 is not None and node1 != repo.changectx().node():
             hgcmd = 'diff1'
 
     inc, exc = [], ['.hgtags']
     for pat, opt in ui.configitems('keyword'):
         if opt != 'ignore':
             inc.append(pat)
         else:
             exc.append(pat)
     if not inc:
         return
 
     global _kwtemplater
     _kwtemplater = kwtemplater(ui, repo, inc, exc, hgcmd)
 
     class kwrepo(repo.__class__):
         def file(self, f, kwmatch=False):
             if f[0] == '/':
                 f = f[1:]
             if kwmatch or _kwtemplater.matcher(f):
                 return kwfilelog(self.sopener, f)
             return filelog.filelog(self.sopener, f)
 
         def wread(self, filename):
             data = super(kwrepo, self).wread(filename)
             if _kwrestrict(hgcmd) and _kwtemplater.matcher(filename):
                 return _kwtemplater.shrink(data)
             return data
 
         def commit(self, files=None, text='', user=None, date=None,
                    match=util.always, force=False, force_editor=False,
                    p1=None, p2=None, extra={}):
             wlock = lock = None
             _p1 = _p2 = None
             try:
                 wlock = self.wlock()
                 lock = self.lock()
                 # store and postpone commit hooks
                 commithooks = []
                 for name, cmd in ui.configitems('hooks'):
                     if name.split('.', 1)[0] == 'commit':
                         commithooks.append((name, cmd))
                         ui.setconfig('hooks', name, None)
                 if commithooks:
                     # store parents for commit hook environment
                     if p1 is None:
                         _p1, _p2 = repo.dirstate.parents()
                     else:
                         _p1, _p2 = p1, p2 or nullid
                     _p1 = hex(_p1)
                     if _p2 == nullid:
                         _p2 = ''
                     else:
                         _p2 = hex(_p2)
 
                 node = super(kwrepo,
                              self).commit(files=files, text=text, user=user,
                                           date=date, match=match, force=force,
                                           force_editor=force_editor,
                                           p1=p1, p2=p2, extra=extra)
 
                 # restore commit hooks
                 for name, cmd in commithooks:
                     ui.setconfig('hooks', name, cmd)
                 if node is not None:
                     _overwrite(ui, self, node=node)
                     repo.hook('commit', node=node, parent1=_p1, parent2=_p2)
                 return node
             finally:
                 del wlock, lock
 
     repo.__class__ = kwrepo
     patch.patchfile.__init__ = _kwpatchfile_init
 
 
 cmdtable = {
     'kwdemo':
         (demo,
          [('d', 'default', None, _('show default keyword template maps')),
           ('f', 'rcfile', [], _('read maps from rcfile'))],
          _('hg kwdemo [-d] [-f RCFILE] [TEMPLATEMAP]...')),
     'kwexpand': (expand, commands.walkopts,
                  _('hg kwexpand [OPTION]... [FILE]...')),
     'kwfiles':
         (files,
          [('a', 'all', None, _('show keyword status flags of all files')),
           ('i', 'ignore', None, _('show files excluded from expansion')),
           ('u', 'untracked', None, _('additionally show untracked files')),
          ] + commands.walkopts,
          _('hg kwfiles [OPTION]... [FILE]...')),
     'kwshrink': (shrink, commands.walkopts,
                  _('hg kwshrink [OPTION]... [FILE]...')),
 }

hgext/patchbomb.py

@@ -1,467 +1,466 b''
 # Command for sending a collection of Mercurial changesets as a series
 # of patch emails.
 #
 # The series is started off with a "[PATCH 0 of N]" introduction,
 # which describes the series as a whole.
 #
 # Each patch email has a Subject line of "[PATCH M of N] ...", using
 # the first line of the changeset description as the subject text.
 # The message contains two or three body parts:
 #
 #   The remainder of the changeset description.
 #
 #   [Optional] If the diffstat program is installed, the result of
 #   running diffstat on the patch.
 #
 #   The patch itself, as generated by "hg export".
 #
 # Each message refers to all of its predecessors using the In-Reply-To
 # and References headers, so they will show up as a sequence in
 # threaded mail and news readers, and in mail archives.
 #
 # For each changeset, you will be prompted with a diffstat summary and
 # the changeset summary, so you can be sure you are sending the right
 # changes.
 #
 # To enable this extension:
 #
 #   [extensions]
 #   hgext.patchbomb =
 #
 # To configure other defaults, add a section like this to your hgrc
 # file:
 #
 #   [email]
 #   from = My Name <my@email>
 #   to = recipient1, recipient2, ...
 #   cc = cc1, cc2, ...
 #   bcc = bcc1, bcc2, ...
 #
 # Then you can use the "hg email" command to mail a series of changesets
 # as a patchbomb.
 #
 # To avoid sending patches prematurely, it is a good idea to first run
 # the "email" command with the "-n" option (test only).  You will be
 # prompted for an email recipient address, a subject an an introductory
 # message describing the patches of your patchbomb.  Then when all is
 # done, patchbomb messages are displayed. If PAGER environment variable
 # is set, your pager will be fired up once for each patchbomb message, so
 # you can verify everything is alright.
 #
 # The "-m" (mbox) option is also very useful.  Instead of previewing
 # each patchbomb message in a pager or sending the messages directly,
 # it will create a UNIX mailbox file with the patch emails.  This
 # mailbox file can be previewed with any mail user agent which supports
 # UNIX mbox files, i.e. with mutt:
 #
 #   % mutt -R -f mbox
 #
 # When you are previewing the patchbomb messages, you can use `formail'
 # (a utility that is commonly installed as part of the procmail package),
 # to send each message out:
 #
 #  % formail -s sendmail -bm -t < mbox
 #
 # That should be all.  Now your patchbomb is on its way out.
 
 import os, errno, socket, tempfile
 import email.MIMEMultipart, email.MIMEText, email.MIMEBase
 import email.Utils, email.Encoders
 from mercurial import cmdutil, commands, hg, mail, ui, patch, util
 from mercurial.i18n import _
 from mercurial.node import *
 
 def patchbomb(ui, repo, *revs, **opts):
     '''send changesets by email
 
     By default, diffs are sent in the format generated by hg export,
     one per message.  The series starts with a "[PATCH 0 of N]"
     introduction, which describes the series as a whole.
 
     Each patch email has a Subject line of "[PATCH M of N] ...", using
     the first line of the changeset description as the subject text.
     The message contains two or three body parts.  First, the rest of
     the changeset description.  Next, (optionally) if the diffstat
     program is installed, the result of running diffstat on the patch.
     Finally, the patch itself, as generated by "hg export".
 
     With --outgoing, emails will be generated for patches not
     found in the destination repository (or only those which are
     ancestors of the specified revisions if any are provided)
 
     With --bundle, changesets are selected as for --outgoing,
     but a single email containing a binary Mercurial bundle as an
     attachment will be sent.
 
     Examples:
 
     hg email -r 3000          # send patch 3000 only
     hg email -r 3000 -r 3001  # send patches 3000 and 3001
     hg email -r 3000:3005     # send patches 3000 through 3005
     hg email 3000             # send patch 3000 (deprecated)
 
     hg email -o               # send all patches not in default
     hg email -o DEST          # send all patches not in DEST
     hg email -o -r 3000       # send all ancestors of 3000 not in default
     hg email -o -r 3000 DEST  # send all ancestors of 3000 not in DEST
 
     hg email -b               # send bundle of all patches not in default
     hg email -b DEST          # send bundle of all patches not in DEST
     hg email -b -r 3000       # bundle of all ancestors of 3000 not in default
     hg email -b -r 3000 DEST  # bundle of all ancestors of 3000 not in DEST
 
     Before using this command, you will need to enable email in your hgrc.
     See the [email] section in hgrc(5) for details.
     '''
 
     def prompt(prompt, default = None, rest = ': ', empty_ok = False):
         if not ui.interactive:
             return default
         if default:
             prompt += ' [%s]' % default
         prompt += rest
         while True:
             r = ui.prompt(prompt, default=default)
             if r:
                 return r
             if default is not None:
                 return default
             if empty_ok:
                 return r
             ui.warn(_('Please enter a valid value.\n'))
 
     def confirm(s, denial):
         if not prompt(s, default = 'y', rest = '? ').lower().startswith('y'):
             raise util.Abort(denial)
 
     def cdiffstat(summary, patchlines):
         s = patch.diffstat(patchlines)
         if s:
             if summary:
                 ui.write(summary, '\n')
                 ui.write(s, '\n')
             confirm(_('Does the diffstat above look okay'),
                     _('diffstat rejected'))
         elif s is None:
             ui.warn(_('No diffstat information available.\n'))
             s = ''
         return s
 
     def makepatch(patch, idx, total):
         desc = []
         node = None
         body = ''
         for line in patch:
             if line.startswith('#'):
                 if line.startswith('# Node ID'):
                     node = line.split()[-1]
                 continue
             if line.startswith('diff -r') or line.startswith('diff --git'):
                 break
             desc.append(line)
         if not node:
             raise ValueError
 
         if opts['attach']:
              body = ('\n'.join(desc[1:]).strip() or
                    'Patch subject is complete summary.')
              body += '\n\n\n'
 
         if opts.get('plain'):
             while patch and patch[0].startswith('# '):
                 patch.pop(0)
             if patch:
                 patch.pop(0)
             while patch and not patch[0].strip():
                 patch.pop(0)
         if opts.get('diffstat'):
             body += cdiffstat('\n'.join(desc), patch) + '\n\n'
         if opts.get('attach') or opts.get('inline'):
             msg = email.MIMEMultipart.MIMEMultipart()
             if body:
                 msg.attach(email.MIMEText.MIMEText(body, 'plain'))
             p = email.MIMEText.MIMEText('\n'.join(patch), 'x-patch')
             binnode = bin(node)
             # if node is mq patch, it will have patch file name as tag
             patchname = [t for t in repo.nodetags(binnode)
                          if t.endswith('.patch') or t.endswith('.diff')]
             if patchname:
                 patchname = patchname[0]
             elif total > 1:
                 patchname = cmdutil.make_filename(repo, '%b-%n.patch',
                                                   binnode, idx, total)
             else:
                 patchname = cmdutil.make_filename(repo, '%b.patch', binnode)
             disposition = 'inline'
             if opts['attach']:
                 disposition = 'attachment'
             p['Content-Disposition'] = disposition + '; filename=' + patchname
             msg.attach(p)
         else:
             body += '\n'.join(patch)
             msg = email.MIMEText.MIMEText(body)
 
         subj = desc[0].strip().rstrip('. ')
         if total == 1:
             subj = '[PATCH] ' + (opts.get('subject') or subj)
         else:
             tlen = len(str(total))
             subj = '[PATCH %0*d of %d] %s' % (tlen, idx, total, subj)
         msg['Subject'] = subj
         msg['X-Mercurial-Node'] = node
         return msg
 
     def outgoing(dest, revs):
         '''Return the revisions present locally but not in dest'''
         dest = ui.expandpath(dest or 'default-push', dest or 'default')
         revs = [repo.lookup(rev) for rev in revs]
         other = hg.repository(ui, dest)
         ui.status(_('comparing with %s\n') % dest)
         o = repo.findoutgoing(other)
         if not o:
             ui.status(_("no changes found\n"))
             return []
         o = repo.changelog.nodesbetween(o, revs or None)[0]
         return [str(repo.changelog.rev(r)) for r in o]
 
     def getbundle(dest):
         tmpdir = tempfile.mkdtemp(prefix='hg-email-bundle-')
         tmpfn = os.path.join(tmpdir, 'bundle')
         try:
             commands.bundle(ui, repo, tmpfn, dest, **opts)
             return open(tmpfn, 'rb').read()
         finally:
             try:
                 os.unlink(tmpfn)
             except:
                 pass
             os.rmdir(tmpdir)
 
     if not (opts.get('test') or opts.get('mbox')):
         # really sending
         mail.validateconfig(ui)
 
     if not (revs or opts.get('rev')
             or opts.get('outgoing') or opts.get('bundle')):
         raise util.Abort(_('specify at least one changeset with -r or -o'))
 
     cmdutil.setremoteconfig(ui, opts)
     if opts.get('outgoing') and opts.get('bundle'):
         raise util.Abort(_("--outgoing mode always on with --bundle;"
                            " do not re-specify --outgoing"))
 
     if opts.get('outgoing') or opts.get('bundle'):
         if len(revs) > 1:
             raise util.Abort(_("too many destinations"))
         dest = revs and revs[0] or None
         revs = []
 
     if opts.get('rev'):
         if revs:
             raise util.Abort(_('use only one form to specify the revision'))
         revs = opts.get('rev')
 
     if opts.get('outgoing'):
         revs = outgoing(dest, opts.get('rev'))
     if opts.get('bundle'):
         opts['revs'] = revs
 
     # start
     if opts.get('date'):
         start_time = util.parsedate(opts.get('date'))
     else:
         start_time = util.makedate()
 
     def genmsgid(id):
         return '<%s.%s@%s>' % (id[:20], int(start_time[0]), socket.getfqdn())
 
     def getdescription(body, sender):
         if opts.get('desc'):
             body = open(opts.get('desc')).read()
         else:
             ui.write(_('\nWrite the introductory message for the '
                        'patch series.\n\n'))
             body = ui.edit(body, sender)
         return body
 
     def getexportmsgs():
         patches = []
 
         class exportee:
             def __init__(self, container):
                 self.lines = []
                 self.container = container
                 self.name = 'email'
 
             def write(self, data):
                 self.lines.append(data)
 
             def close(self):
                 self.container.append(''.join(self.lines).split('\n'))
                 self.lines = []
 
         commands.export(ui, repo, *revs, **{'output': exportee(patches),
                                             'switch_parent': False,
                                             'text': None,
                                             'git': opts.get('git')})
 
         jumbo = []
         msgs = []
 
         ui.write(_('This patch series consists of %d patches.\n\n')
                  % len(patches))
 
         for p, i in zip(patches, xrange(len(patches))):
             jumbo.extend(p)
             msgs.append(makepatch(p, i + 1, len(patches)))
 
         if len(patches) > 1:
             tlen = len(str(len(patches)))
 
             subj = '[PATCH %0*d of %d] %s' % (
                 tlen, 0, len(patches),
                 opts.get('subject') or
                 prompt('Subject:',
                        rest=' [PATCH %0*d of %d] ' % (tlen, 0, len(patches))))
 
             body = ''
             if opts.get('diffstat'):
                 d = cdiffstat(_('Final summary:\n'), jumbo)
                 if d:
                     body = '\n' + d
 
             body = getdescription(body, sender)
             msg = email.MIMEText.MIMEText(body)
             msg['Subject'] = subj
 
             msgs.insert(0, msg)
         return msgs
 
     def getbundlemsgs(bundle):
         subj = (opts.get('subject')
                 or prompt('Subject:', default='A bundle for your repository'))
 
         body = getdescription('', sender)
         msg = email.MIMEMultipart.MIMEMultipart()
         if body:
             msg.attach(email.MIMEText.MIMEText(body, 'plain'))
         datapart = email.MIMEBase.MIMEBase('application', 'x-mercurial-bundle')
         datapart.set_payload(bundle)
         datapart.add_header('Content-Disposition', 'attachment',
                             filename='bundle.hg')
         email.Encoders.encode_base64(datapart)
         msg.attach(datapart)
         msg['Subject'] = subj
         return [msg]
 
     sender = (opts.get('from') or ui.config('email', 'from') or
               ui.config('patchbomb', 'from') or
               prompt('From', ui.username()))
 
     if opts.get('bundle'):
         msgs = getbundlemsgs(getbundle(dest))
     else:
         msgs = getexportmsgs()
 
     def getaddrs(opt, prpt, default = None):
         addrs = opts.get(opt) or (ui.config('email', opt) or
                                   ui.config('patchbomb', opt) or
                                   prompt(prpt, default = default)).split(',')
         return [a.strip() for a in addrs if a.strip()]
 
     to = getaddrs('to', 'To')
     cc = getaddrs('cc', 'Cc', '')
 
     bcc = opts.get('bcc') or (ui.config('email', 'bcc') or
                           ui.config('patchbomb', 'bcc') or '').split(',')
     bcc = [a.strip() for a in bcc if a.strip()]
 
     ui.write('\n')
 
     parent = None
 
     sender_addr = email.Utils.parseaddr(sender)[1]
     sendmail = None
     for m in msgs:
         try:
             m['Message-Id'] = genmsgid(m['X-Mercurial-Node'])
         except TypeError:
             m['Message-Id'] = genmsgid('patchbomb')
         if parent:
             m['In-Reply-To'] = parent
         else:
             parent = m['Message-Id']
         m['Date'] = util.datestr(date=start_time,
                                  format="%a, %d %b %Y %H:%M:%S", timezone=True)
 
         start_time = (start_time[0] + 1, start_time[1])
         m['From'] = sender
         m['To'] = ', '.join(to)
         if cc:
             m['Cc']  = ', '.join(cc)
         if bcc:
             m['Bcc'] = ', '.join(bcc)
         if opts.get('test'):
             ui.status('Displaying ', m['Subject'], ' ...\n')
             ui.flush()
             if 'PAGER' in os.environ:
                 fp = os.popen(os.environ['PAGER'], 'w')
             else:
                 fp = ui
             try:
                 fp.write(m.as_string(0))
                 fp.write('\n')
             except IOError, inst:
                 if inst.errno != errno.EPIPE:
                     raise
             if fp is not ui:
                 fp.close()
         elif opts.get('mbox'):
             ui.status('Writing ', m['Subject'], ' ...\n')
-            fp = open(opts.get('mbox'),
-                      m.has_key('In-Reply-To') and 'ab+' or 'wb+')
+            fp = open(opts.get('mbox'), 'In-Reply-To' in m and 'ab+' or 'wb+')
             date = util.datestr(date=start_time,
                                 format='%a %b %d %H:%M:%S %Y', timezone=False)
             fp.write('From %s %s\n' % (sender_addr, date))
             fp.write(m.as_string(0))
             fp.write('\n\n')
             fp.close()
         else:
             if not sendmail:
                 sendmail = mail.connect(ui)
             ui.status('Sending ', m['Subject'], ' ...\n')
             # Exim does not remove the Bcc field
             del m['Bcc']
             sendmail(ui, sender, to + bcc + cc, m.as_string(0))
 
 cmdtable = {
     "email":
         (patchbomb,
          [('a', 'attach', None, _('send patches as attachments')),
           ('i', 'inline', None, _('send patches as inline attachments')),
           ('', 'bcc', [], _('email addresses of blind copy recipients')),
           ('c', 'cc', [], _('email addresses of copy recipients')),
           ('d', 'diffstat', None, _('add diffstat output to messages')),
           ('', 'date', '', _('use the given date as the sending date')),
           ('', 'desc', '', _('use the given file as the series description')),
           ('g', 'git', None, _('use git extended diff format')),
           ('f', 'from', '', _('email address of sender')),
           ('', 'plain', None, _('omit hg patch header')),
           ('n', 'test', None, _('print messages that would be sent')),
           ('m', 'mbox', '',
            _('write messages to mbox file instead of sending them')),
           ('o', 'outgoing', None,
            _('send changes not found in the target repository')),
           ('b', 'bundle', None,
            _('send changes not in target as a binary bundle')),
           ('r', 'rev', [], _('a revision to send')),
           ('s', 'subject', '',
            _('subject of first message (intro or single patch)')),
           ('t', 'to', [], _('email addresses of recipients')),
           ('', 'force', None,
            _('run even when remote repository is unrelated (with -b)')),
           ('', 'base', [],
            _('a base changeset to specify instead of a destination (with -b)')),
          ] + commands.remoteopts,
          _('hg email [OPTION]... [DEST]...'))
 }

mercurial/cmdutil.py

@@ -1,1159 +1,1159 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, incorporated herein by reference.
 
 from node import *
 from i18n import _
 import os, sys, bisect, stat
 import mdiff, bdiff, util, templater, patch, errno
 
 revrangesep = ':'
 
 class UnknownCommand(Exception):
     """Exception raised if command is not in the command table."""
 class AmbiguousCommand(Exception):
     """Exception raised if command shortcut matches more than one command."""
 
 def findpossible(ui, cmd, table):
     """
     Return cmd -> (aliases, command table entry)
     for each matching command.
     Return debug commands (or their aliases) only if no normal command matches.
     """
     choice = {}
     debugchoice = {}
     for e in table.keys():
         aliases = e.lstrip("^").split("|")
         found = None
         if cmd in aliases:
             found = cmd
         elif not ui.config("ui", "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(ui, cmd, table):
     """Return (aliases, command table entry) for command string."""
     choice = findpossible(ui, cmd, table)
 
-    if choice.has_key(cmd):
+    if cmd in choice:
         return choice[cmd]
 
     if len(choice) > 1:
         clist = choice.keys()
         clist.sort()
         raise AmbiguousCommand(cmd, clist)
 
     if choice:
         return choice.values()[0]
 
     raise UnknownCommand(cmd)
 
 def bail_if_changed(repo):
     if repo.dirstate.parents()[1] != 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(_("outstanding uncommitted changes"))
 
 def logmessage(opts):
     """ get the log message according to -m and -l option """
     message = opts['message']
     logfile = opts['logfile']
 
     if message and logfile:
         raise util.Abort(_('options --message and --logfile are mutually '
                            'exclusive'))
     if not message and logfile:
         try:
             if logfile == '-':
                 message = sys.stdin.read()
             else:
                 message = open(logfile).read()
         except IOError, inst:
             raise util.Abort(_("can't read commit message '%s': %s") %
                              (logfile, inst.strerror))
     return message
 
 def setremoteconfig(ui, opts):
     "copy remote options to ui tree"
     if opts.get('ssh'):
         ui.setconfig("ui", "ssh", opts['ssh'])
     if opts.get('remotecmd'):
         ui.setconfig("ui", "remotecmd", opts['remotecmd'])
 
 def revpair(repo, revs):
     '''return pair of nodes, given list of revisions. second item can
     be None, meaning use working dir.'''
 
     def revfix(repo, val, defval):
         if not val and val != 0 and defval is not None:
             val = defval
         return repo.lookup(val)
 
     if not revs:
         return repo.dirstate.parents()[0], None
     end = None
     if len(revs) == 1:
         if revrangesep in revs[0]:
             start, end = revs[0].split(revrangesep, 1)
             start = revfix(repo, start, 0)
             end = revfix(repo, end, repo.changelog.count() - 1)
         else:
             start = revfix(repo, revs[0], None)
     elif len(revs) == 2:
         if revrangesep in revs[0] or revrangesep in revs[1]:
             raise util.Abort(_('too many revisions specified'))
         start = revfix(repo, revs[0], None)
         end = revfix(repo, revs[1], None)
     else:
         raise util.Abort(_('too many revisions specified'))
     return start, end
 
 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.changelog.rev(repo.lookup(val))
 
     seen, l = {}, []
     for spec in revs:
         if revrangesep in spec:
             start, end = spec.split(revrangesep, 1)
             start = revfix(repo, start, 0)
             end = revfix(repo, end, repo.changelog.count() - 1)
             step = start > end and -1 or 1
             for rev in xrange(start, end+step, step):
                 if rev in seen:
                     continue
                 seen[rev] = 1
                 l.append(rev)
         else:
             rev = revfix(repo, spec, None)
             if rev in seen:
                 continue
             seen[rev] = 1
             l.append(rev)
 
     return l
 
 def make_filename(repo, pat, node,
                   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),
         }
     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 file name") %
                          inst.args[0])
 
 def make_file(repo, pat, node=None,
               total=None, seqno=None, revwidth=None, mode='wb', pathname=None):
     if not pat or pat == '-':
         return 'w' in mode and sys.stdout or sys.stdin
     if hasattr(pat, 'write') and 'w' in mode:
         return pat
     if hasattr(pat, 'read') and 'r' in mode:
         return pat
     return open(make_filename(repo, pat, node, total, seqno, revwidth,
                               pathname),
                 mode)
 
 def matchpats(repo, pats=[], opts={}, globbed=False, default=None):
     cwd = repo.getcwd()
     return util.cmdmatcher(repo.root, cwd, pats or [], opts.get('include'),
                            opts.get('exclude'), globbed=globbed,
                            default=default)
 
 def walk(repo, pats=[], opts={}, node=None, badmatch=None, globbed=False,
          default=None):
     files, matchfn, anypats = matchpats(repo, pats, opts, globbed=globbed,
                                         default=default)
     exact = dict.fromkeys(files)
     cwd = repo.getcwd()
     for src, fn in repo.walk(node=node, files=files, match=matchfn,
                              badmatch=badmatch):
         yield src, fn, repo.pathto(fn, cwd), fn in exact
 
 def findrenames(repo, added=None, removed=None, threshold=0.5):
     '''find renamed files -- yields (before, after, score) tuples'''
     if added is None or removed is None:
         added, removed = repo.status()[1:3]
     ctx = repo.changectx()
     for a in added:
         aa = repo.wread(a)
         bestname, bestscore = None, threshold
         for r in removed:
             rr = ctx.filectx(r).data()
 
             # bdiff.blocks() returns blocks of matching lines
             # count the number of bytes in each
             equal = 0
             alines = mdiff.splitnewlines(aa)
             matches = bdiff.blocks(aa, rr)
             for x1,x2,y1,y2 in matches:
                 for line in alines[x1:x2]:
                     equal += len(line)
 
             lengths = len(aa) + len(rr)
             if lengths:
                 myscore = equal*2.0 / lengths
                 if myscore >= bestscore:
                     bestname, bestscore = r, myscore
         if bestname:
             yield bestname, a, bestscore
 
 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)
     add, remove = [], []
     mapping = {}
     for src, abs, rel, exact in walk(repo, pats, opts):
         target = repo.wjoin(abs)
         if src == 'f' and abs not in repo.dirstate:
             add.append(abs)
             mapping[abs] = rel, exact
             if repo.ui.verbose or not exact:
                 repo.ui.status(_('adding %s\n') % ((pats and rel) or abs))
         if repo.dirstate[abs] != 'r' and (not util.lexists(target)
             or (os.path.isdir(target) and not os.path.islink(target))):
             remove.append(abs)
             mapping[abs] = rel, exact
             if repo.ui.verbose or not exact:
                 repo.ui.status(_('removing %s\n') % ((pats and rel) or abs))
     if not dry_run:
         repo.remove(remove)
         repo.add(add)
     if similarity > 0:
         for old, new, score in findrenames(repo, add, remove, similarity):
             oldrel, oldexact = mapping[old]
             newrel, newexact = mapping[new]
             if repo.ui.verbose or not oldexact or not newexact:
                 repo.ui.status(_('recording removal of %s as rename to %s '
                                  '(%d%% similar)\n') %
                                (oldrel, newrel, score * 100))
             if not dry_run:
                 repo.copy(old, new)
 
 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")
 
     def walkpat(pat):
         srcs = []
         for tag, abs, rel, exact in walk(repo, [pat], opts, globbed=True):
             state = repo.dirstate[abs]
             if state in '?r':
                 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 = util.canonpath(repo.root, cwd, otarget)
         reltarget = repo.pathto(abstarget, cwd)
         target = repo.wjoin(abstarget)
         src = repo.wjoin(abssrc)
         state = repo.dirstate[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.exists(target)
         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:
                 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)
                 util.copyfile(src, target)
             except IOError, inst:
                 if inst.errno == errno.ENOENT:
                     ui.warn(_('%s: deleted in working copy\n') % relsrc)
                 else:
                     ui.warn(_('%s: cannot copy - %s\n') %
                             (relsrc, inst.strerror))
                     return True # report a failure
 
         if ui.verbose or not exact:
             action = rename and "moving" or "copying"
             ui.status(_('%s %s to %s\n') % (action, relsrc, reltarget))
 
         targets[abstarget] = abssrc
 
         # fix up dirstate
         origsrc = repo.dirstate.copied(abssrc) or abssrc
         if abstarget == origsrc: # copying back a copy?
             if state not in 'mn' and not dryrun:
                 repo.dirstate.normallookup(abstarget)
         else:
             if repo.dirstate[origsrc] == 'a':
                 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), reltarget))
                 if abstarget not in repo.dirstate and not dryrun:
                     repo.add([abstarget])
             elif not dryrun:
                 repo.copy(origsrc, abstarget)
 
         if rename and not dryrun:
             repo.remove([abssrc], True)
 
     # 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 = util.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 util.patkind(pat, None)[0]:
             # a mercurial pattern
             res = lambda p: os.path.join(dest,
                                          os.path.basename(util.localpath(p)))
         else:
             abspfx = util.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.exists(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 = util.expand_glob(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)
     if not destdirexists:
         if len(pats) > 1 or util.patkind(pats[0], None)[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
 
 def service(opts, parentfn=None, initfn=None, runfn=None):
     '''Run a command as a service.'''
 
     if opts['daemon'] and not opts['daemon_pipefds']:
         rfd, wfd = os.pipe()
         args = sys.argv[:]
         args.append('--daemon-pipefds=%d,%d' % (rfd, wfd))
         # Don't pass --cwd to the child process, because we've already
         # changed directory.
         for i in xrange(1,len(args)):
             if args[i].startswith('--cwd='):
                 del args[i]
                 break
             elif args[i].startswith('--cwd'):
                 del args[i:i+2]
                 break
         pid = os.spawnvp(os.P_NOWAIT | getattr(os, 'P_DETACH', 0),
                          args[0], args)
         os.close(wfd)
         os.read(rfd, 1)
         if parentfn:
             return parentfn(pid)
         else:
             os._exit(0)
 
     if initfn:
         initfn()
 
     if opts['pid_file']:
         fp = open(opts['pid_file'], 'w')
         fp.write(str(os.getpid()) + '\n')
         fp.close()
 
     if opts['daemon_pipefds']:
         rfd, wfd = [int(x) for x in opts['daemon_pipefds'].split(',')]
         os.close(rfd)
         try:
             os.setsid()
         except AttributeError:
             pass
         os.write(wfd, 'y')
         os.close(wfd)
         sys.stdout.flush()
         sys.stderr.flush()
         fd = os.open(util.nulldev, os.O_RDWR)
         if fd != 0: os.dup2(fd, 0)
         if fd != 1: os.dup2(fd, 1)
         if fd != 2: os.dup2(fd, 2)
         if fd not in (0, 1, 2): os.close(fd)
 
     if runfn:
         return runfn()
 
 class changeset_printer(object):
     '''show changeset information when templating not requested.'''
 
     def __init__(self, ui, repo, patch, buffered):
         self.ui = ui
         self.repo = repo
         self.buffered = buffered
         self.patch = patch
         self.header = {}
         self.hunk = {}
         self.lastheader = 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 show(self, rev=0, changenode=None, copies=(), **props):
         if self.buffered:
             self.ui.pushbuffer()
             self._show(rev, changenode, copies, props)
             self.hunk[rev] = self.ui.popbuffer()
         else:
             self._show(rev, changenode, copies, props)
 
     def _show(self, rev, changenode, copies, props):
         '''show a single changeset or file revision'''
         log = self.repo.changelog
         if changenode is None:
             changenode = log.node(rev)
         elif not rev:
             rev = log.rev(changenode)
 
         if self.ui.quiet:
             self.ui.write("%d:%s\n" % (rev, short(changenode)))
             return
 
         changes = log.read(changenode)
         date = util.datestr(changes[2])
         extra = changes[5]
         branch = extra.get("branch")
 
         hexfunc = self.ui.debugflag and hex or short
 
         parents = [(p, hexfunc(log.node(p)))
                    for p in self._meaningful_parentrevs(log, rev)]
 
         self.ui.write(_("changeset:   %d:%s\n") % (rev, hexfunc(changenode)))
 
         # don't show the default branch name
         if branch != 'default':
             branch = util.tolocal(branch)
             self.ui.write(_("branch:      %s\n") % branch)
         for tag in self.repo.nodetags(changenode):
             self.ui.write(_("tag:         %s\n") % tag)
         for parent in parents:
             self.ui.write(_("parent:      %d:%s\n") % parent)
 
         if self.ui.debugflag:
             self.ui.write(_("manifest:    %d:%s\n") %
                           (self.repo.manifest.rev(changes[0]), hex(changes[0])))
         self.ui.write(_("user:        %s\n") % changes[1])
         self.ui.write(_("date:        %s\n") % date)
 
         if self.ui.debugflag:
             files = self.repo.status(log.parents(changenode)[0], changenode)[:3]
             for key, value in zip([_("files:"), _("files+:"), _("files-:")],
                                   files):
                 if value:
                     self.ui.write("%-12s %s\n" % (key, " ".join(value)))
         elif changes[3] and self.ui.verbose:
             self.ui.write(_("files:       %s\n") % " ".join(changes[3]))
         if copies and self.ui.verbose:
             copies = ['%s (%s)' % c for c in copies]
             self.ui.write(_("copies:      %s\n") % ' '.join(copies))
 
         if extra and self.ui.debugflag:
             extraitems = extra.items()
             extraitems.sort()
             for key, value in extraitems:
                 self.ui.write(_("extra:       %s=%s\n")
                               % (key, value.encode('string_escape')))
 
         description = changes[4].strip()
         if description:
             if self.ui.verbose:
                 self.ui.write(_("description:\n"))
                 self.ui.write(description)
                 self.ui.write("\n\n")
             else:
                 self.ui.write(_("summary:     %s\n") %
                               description.splitlines()[0])
         self.ui.write("\n")
 
         self.showpatch(changenode)
 
     def showpatch(self, node):
         if self.patch:
             prev = self.repo.changelog.parents(node)[0]
             patch.diff(self.repo, prev, node, match=self.patch, fp=self.ui,
                        opts=patch.diffopts(self.ui))
             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, mapfile, buffered):
         changeset_printer.__init__(self, ui, repo, patch, buffered)
         filters = templater.common_filters.copy()
         filters['formatnode'] = (ui.debugflag and (lambda x: x)
                                  or (lambda x: x[:12]))
         self.t = templater.templater(mapfile, filters,
                                      cache={
                                          'parent': '{rev}:{node|formatnode} ',
                                          'manifest': '{rev}:{node|formatnode}',
                                          'filecopy': '{name} ({source})'})
 
     def use_template(self, t):
         '''set template string to use'''
         self.t.cache['changeset'] = t
 
     def _show(self, rev, changenode, copies, props):
         '''show a single changeset or file revision'''
         log = self.repo.changelog
         if changenode is None:
             changenode = log.node(rev)
         elif not rev:
             rev = log.rev(changenode)
 
         changes = log.read(changenode)
 
         def showlist(name, values, plural=None, **args):
             '''expand set of values.
             name is name of key in template map.
             values is list of strings or dicts.
             plural is plural of name, if not simply name + 's'.
 
             expansion works like this, given name 'foo'.
 
             if values is empty, expand 'no_foos'.
 
             if 'foo' not in template map, return values as a string,
             joined by space.
 
             expand 'start_foos'.
 
             for each value, expand 'foo'. if 'last_foo' in template
             map, expand it instead of 'foo' for last key.
 
             expand 'end_foos'.
             '''
             if plural: names = plural
             else: names = name + 's'
             if not values:
                 noname = 'no_' + names
                 if noname in self.t:
                     yield self.t(noname, **args)
                 return
             if name not in self.t:
                 if isinstance(values[0], str):
                     yield ' '.join(values)
                 else:
                     for v in values:
                         yield dict(v, **args)
                 return
             startname = 'start_' + names
             if startname in self.t:
                 yield self.t(startname, **args)
             vargs = args.copy()
             def one(v, tag=name):
                 try:
                     vargs.update(v)
                 except (AttributeError, ValueError):
                     try:
                         for a, b in v:
                             vargs[a] = b
                     except ValueError:
                         vargs[name] = v
                 return self.t(tag, **vargs)
             lastname = 'last_' + name
             if lastname in self.t:
                 last = values.pop()
             else:
                 last = None
             for v in values:
                 yield one(v)
             if last is not None:
                 yield one(last, tag=lastname)
             endname = 'end_' + names
             if endname in self.t:
                 yield self.t(endname, **args)
 
         def showbranches(**args):
             branch = changes[5].get("branch")
             if branch != 'default':
                 branch = util.tolocal(branch)
                 return showlist('branch', [branch], plural='branches', **args)
 
         def showparents(**args):
             parents = [[('rev', p), ('node', hex(log.node(p)))]
                        for p in self._meaningful_parentrevs(log, rev)]
             return showlist('parent', parents, **args)
 
         def showtags(**args):
             return showlist('tag', self.repo.nodetags(changenode), **args)
 
         def showextras(**args):
             extras = changes[5].items()
             extras.sort()
             for key, value in extras:
                 args = args.copy()
                 args.update(dict(key=key, value=value))
                 yield self.t('extra', **args)
 
         def showcopies(**args):
             c = [{'name': x[0], 'source': x[1]} for x in copies]
             return showlist('file_copy', c, plural='file_copies', **args)
 
         files = []
         def getfiles():
             if not files:
                 files[:] = self.repo.status(
                     log.parents(changenode)[0], changenode)[:3]
             return files
         def showfiles(**args):
             return showlist('file', changes[3], **args)
         def showmods(**args):
             return showlist('file_mod', getfiles()[0], **args)
         def showadds(**args):
             return showlist('file_add', getfiles()[1], **args)
         def showdels(**args):
             return showlist('file_del', getfiles()[2], **args)
         def showmanifest(**args):
             args = args.copy()
             args.update(dict(rev=self.repo.manifest.rev(changes[0]),
                              node=hex(changes[0])))
             return self.t('manifest', **args)
 
         defprops = {
             'author': changes[1],
             'branches': showbranches,
             'date': changes[2],
             'desc': changes[4].strip(),
             'file_adds': showadds,
             'file_dels': showdels,
             'file_mods': showmods,
             'files': showfiles,
             'file_copies': showcopies,
             'manifest': showmanifest,
             'node': hex(changenode),
             'parents': showparents,
             'rev': rev,
             'tags': showtags,
             'extras': showextras,
             }
         props = props.copy()
         props.update(defprops)
 
         try:
             if self.ui.debugflag and 'header_debug' in self.t:
                 key = 'header_debug'
             elif self.ui.quiet and 'header_quiet' in self.t:
                 key = 'header_quiet'
             elif self.ui.verbose and 'header_verbose' in self.t:
                 key = 'header_verbose'
             elif 'header' in self.t:
                 key = 'header'
             else:
                 key = ''
             if key:
                 h = templater.stringify(self.t(key, **props))
                 if self.buffered:
                     self.header[rev] = h
                 else:
                     self.ui.write(h)
             if self.ui.debugflag and 'changeset_debug' in self.t:
                 key = 'changeset_debug'
             elif self.ui.quiet and 'changeset_quiet' in self.t:
                 key = 'changeset_quiet'
             elif self.ui.verbose and 'changeset_verbose' in self.t:
                 key = 'changeset_verbose'
             else:
                 key = 'changeset'
             self.ui.write(templater.stringify(self.t(key, **props)))
             self.showpatch(changenode)
         except KeyError, inst:
             raise util.Abort(_("%s: no key named '%s'") % (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, matchfn=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 = False
     if opts.get('patch'):
         patch = matchfn or util.always
 
     tmpl = opts.get('template')
     mapfile = None
     if tmpl:
         tmpl = templater.parsestring(tmpl, quoted=False)
     else:
         mapfile = opts.get('style')
         # ui settings
         if not mapfile:
             tmpl = ui.config('ui', 'logtemplate')
             if tmpl:
                 tmpl = templater.parsestring(tmpl)
             else:
                 mapfile = ui.config('ui', 'style')
 
     if tmpl or mapfile:
         if mapfile:
             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, mapfile, buffered)
         except SyntaxError, inst:
             raise util.Abort(inst.args[0])
         if tmpl: t.use_template(tmpl)
         return t
     return changeset_printer(ui, repo, patch, buffered)
 
 def finddate(ui, repo, date):
     """Find the tipmost changeset that matches the given date spec"""
     df = util.matchdate(date)
     get = util.cachefunc(lambda r: repo.changectx(r).changeset())
     changeiter, matchfn = walkchangerevs(ui, repo, [], get, {'rev':None})
     results = {}
     for st, rev, fns in changeiter:
         if st == 'add':
             d = get(rev)[2]
             if df(d[0]):
                 results[rev] = d
         elif st == 'iter':
             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 walkchangerevs(ui, repo, pats, change, opts):
     '''Iterate over files and the revs they changed in.
 
     Callers most commonly need to iterate backwards over the history
     it is interested in.  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, matchfn) tuple. The iterator
     yields 3-tuples. They will be of one of the following forms:
 
     "window", incrementing, lastrev: stepping through a window,
     positive if walking forwards through revs, last rev in the
     sequence iterated over - use to reset state for the current window
 
     "add", rev, fns: out-of-order traversal of the given file names
     fns, which changed during revision rev - use to gather data for
     possible display
 
     "iter", rev, None: in-order traversal of the revs earlier iterated
     over with "add" - use to display data'''
 
     def increasing_windows(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
 
     files, matchfn, anypats = matchpats(repo, pats, opts)
     follow = opts.get('follow') or opts.get('follow_first')
 
     if repo.changelog.count() == 0:
         return [], matchfn
 
     if follow:
         defrange = '%s:0' % repo.changectx().rev()
     else:
         defrange = 'tip:0'
     revs = revrange(repo, opts['rev'] or [defrange])
     wanted = {}
     slowpath = anypats or opts.get('removed')
     fncache = {}
 
     if not slowpath and not files:
         # No files, no patterns.  Display all revs.
         wanted = dict.fromkeys(revs)
     copies = []
     if not slowpath:
         # Only files, no patterns.  Check the history of each file.
         def filerevgen(filelog, node):
             cl_count = repo.changelog.count()
             if node is None:
                 last = filelog.count() - 1
             else:
                 last = filelog.rev(node)
             for i, window in increasing_windows(last, nullrev):
                 revs = []
                 for j in xrange(i - window, i + 1):
                     n = filelog.node(j)
                     revs.append((filelog.linkrev(n),
                                  follow and filelog.renamed(n)))
                 revs.reverse()
                 for rev in revs:
                     # only yield rev for which we have the changelog, it can
                     # happen while doing "hg log" during a pull or commit
                     if rev[0] < cl_count:
                         yield rev
         def iterfiles():
             for filename in files:
                 yield filename, None
             for filename_node in copies:
                 yield filename_node
         minrev, maxrev = min(revs), max(revs)
         for file_, node in iterfiles():
             filelog = repo.file(file_)
             # A zero count may be a directory or deleted file, so
             # try to find matching entries on the slow path.
             if filelog.count() == 0:
                 slowpath = True
                 break
             for rev, copied in filerevgen(filelog, node):
                 if rev <= maxrev:
                     if rev < minrev:
                         break
                     fncache.setdefault(rev, [])
                     fncache[rev].append(file_)
                     wanted[rev] = 1
                     if follow and copied:
                         copies.append(copied)
     if slowpath:
         if follow:
             raise util.Abort(_('can only follow copies/renames for explicit '
                                'file names'))
 
         # The slow path checks files modified in every changeset.
         def changerevgen():
             for i, window in increasing_windows(repo.changelog.count()-1,
                                                 nullrev):
                 for j in xrange(i - window, i + 1):
                     yield j, change(j)[3]
 
         for rev, changefiles in changerevgen():
             matches = filter(matchfn, changefiles)
             if matches:
                 fncache[rev] = matches
                 wanted[rev] = 1
 
     class followfilter:
         def __init__(self, onlyfirst=False):
             self.startrev = nullrev
             self.roots = []
             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.append(self.startrev)
                 for parent in realparents(rev):
                     if parent in self.roots:
                         self.roots.append(rev)
                         return True
             else:
                 # backwards: all parents
                 if not self.roots:
                     self.roots.extend(realparents(self.startrev))
                 if rev in self.roots:
                     self.roots.remove(rev)
                     self.roots.extend(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.changelog.rev(repo.lookup(rev))
         ff = followfilter()
         stop = min(revs[0], revs[-1])
         for x in xrange(rev, stop-1, -1):
             if ff.match(x) and x in wanted:
                 del wanted[x]
 
     def iterate():
         if follow and not files:
             ff = followfilter(onlyfirst=opts.get('follow_first'))
             def want(rev):
                 if ff.match(rev) and rev in wanted:
                     return True
                 return False
         else:
             def want(rev):
                 return rev in wanted
 
         for i, window in increasing_windows(0, len(revs)):
             yield 'window', revs[0] < revs[-1], revs[-1]
             nrevs = [rev for rev in revs[i:i+window] if want(rev)]
             srevs = list(nrevs)
             srevs.sort()
             for rev in srevs:
                 fns = fncache.get(rev)
                 if not fns:
                     def fns_generator():
                         for f in change(rev)[3]:
                             if matchfn(f):
                                 yield f
                     fns = fns_generator()
                 yield 'add', rev, fns
             for rev in nrevs:
                 yield 'iter', rev, None
     return iterate(), matchfn
 
 def commit(ui, repo, commitfunc, pats, opts):
     '''commit the specified files or all outstanding changes'''
     message = logmessage(opts)
 
     # extract addremove carefully -- this function can be called from a command
     # that doesn't support addremove
     if opts.get('addremove'):
         addremove(repo, pats, opts)
 
     fns, match, anypats = matchpats(repo, pats, opts)
     if pats:
         status = repo.status(files=fns, match=match)
         modified, added, removed, deleted, unknown = status[:5]
         files = modified + added + removed
         slist = None
         for f in fns:
             if f == '.':
                 continue
             if f not in files:
                 rf = repo.wjoin(f)
                 try:
                     mode = os.lstat(rf)[stat.ST_MODE]
                 except OSError:
                     raise util.Abort(_("file %s not found!") % rf)
                 if stat.S_ISDIR(mode):
                     name = f + '/'
                     if slist is None:
                         slist = list(files)
                         slist.sort()
                     i = bisect.bisect(slist, name)
                     if i >= len(slist) or not slist[i].startswith(name):
                         raise util.Abort(_("no match under directory %s!")
                                          % rf)
                 elif not (stat.S_ISREG(mode) or stat.S_ISLNK(mode)):
                     raise util.Abort(_("can't commit %s: "
                                        "unsupported file type!") % rf)
                 elif f not in repo.dirstate:
                     raise util.Abort(_("file %s not tracked!") % rf)
     else:
         files = []
     try:
         return commitfunc(ui, repo, files, message, match, opts)
     except ValueError, inst:
         raise util.Abort(str(inst))

mercurial/dirstate.py

@@ -1,582 +1,582 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, incorporated herein by reference.
 """
 
 from node import *
 from i18n import _
 import struct, os, time, bisect, stat, strutil, util, re, errno, ignore
 import cStringIO, osutil
 
 _unknown = ('?', 0, 0, 0)
 _format = ">cllll"
 
 class dirstate(object):
 
     def __init__(self, opener, ui, root):
         self._opener = opener
         self._root = root
         self._dirty = False
         self._dirtypl = False
         self._ui = ui
 
     def __getattr__(self, name):
         if name == '_map':
             self._read()
             return self._map
         elif name == '_copymap':
             self._read()
             return self._copymap
         elif name == '_branch':
             try:
                 self._branch = (self._opener("branch").read().strip()
                                 or "default")
             except IOError:
                 self._branch = "default"
             return self._branch
         elif name == '_pl':
             self._pl = [nullid, nullid]
             try:
                 st = self._opener("dirstate").read(40)
                 if len(st) == 40:
                     self._pl = st[:20], st[20:40]
             except IOError, err:
                 if err.errno != errno.ENOENT: raise
             return self._pl
         elif name == '_dirs':
             self._dirs = {}
             for f in self._map:
                 if self[f] != 'r':
                     self._incpath(f)
             return self._dirs
         elif name == '_ignore':
             files = [self._join('.hgignore')]
             for name, path in self._ui.configitems("ui"):
                 if name == 'ignore' or name.startswith('ignore.'):
                     files.append(os.path.expanduser(path))
             self._ignore = ignore.ignore(self._root, files, self._ui.warn)
             return self._ignore
         elif name == '_slash':
             self._slash = self._ui.configbool('ui', 'slash') and os.sep != '/'
             return self._slash
         else:
             raise AttributeError, name
 
     def _join(self, f):
         return os.path.join(self._root, f)
 
     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.normpath(path)
         return path
 
     def __getitem__(self, key):
         ''' current states:
         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):
         a = self._map.keys()
         a.sort()
         for x in a:
             yield x
 
     def parents(self):
         return self._pl
 
     def branch(self):
         return self._branch
 
     def setparents(self, p1, p2=nullid):
         self._dirty = self._dirtypl = True
         self._pl = p1, p2
 
     def setbranch(self, branch):
         self._branch = branch
         self._opener("branch", "w").write(branch + '\n')
 
     def _read(self):
         self._map = {}
         self._copymap = {}
         if not self._dirtypl:
             self._pl = [nullid, nullid]
         try:
             st = self._opener("dirstate").read()
         except IOError, err:
             if err.errno != errno.ENOENT: raise
             return
         if not st:
             return
 
         if not self._dirtypl:
             self._pl = [st[:20], st[20: 40]]
 
         # deref fields so they will be local in loop
         dmap = self._map
         copymap = self._copymap
         unpack = struct.unpack
         e_size = struct.calcsize(_format)
         pos1 = 40
         l = len(st)
 
         # the inner loop
         while pos1 < l:
             pos2 = pos1 + e_size
             e = unpack(">cllll", st[pos1:pos2]) # a literal here is faster
             pos1 = pos2 + e[4]
             f = st[pos2:pos1]
             if '\0' in f:
                 f, c = f.split('\0')
                 copymap[f] = c
             dmap[f] = e # we hold onto e[4] because making a subtuple is slow
 
     def invalidate(self):
         for a in "_map _copymap _branch _pl _dirs _ignore".split():
             if a in self.__dict__:
                 delattr(self, a)
         self._dirty = False
 
     def copy(self, source, dest):
         self._dirty = True
         self._copymap[dest] = source
 
     def copied(self, file):
         return self._copymap.get(file, None)
 
     def copies(self):
         return self._copymap
 
     def _incpath(self, path):
         c = path.rfind('/')
         if c >= 0:
             dirs = self._dirs
             base = path[:c]
             if base not in dirs:
                 self._incpath(base)
                 dirs[base] = 1
             else:
                 dirs[base] += 1
 
     def _decpath(self, path):
         c = path.rfind('/')
         if c >= 0:
             base = path[:c]
             dirs = self._dirs
             if dirs[base] == 1:
                 del dirs[base]
                 self._decpath(base)
             else:
                 dirs[base] -= 1
 
     def _incpathcheck(self, f):
         if '\r' in f or '\n' in f:
             raise util.Abort(_("'\\n' and '\\r' disallowed in filenames"))
         # shadows
         if f in self._dirs:
             raise util.Abort(_('directory %r already in dirstate') % f)
         for c in strutil.rfindall(f, '/'):
             d = f[:c]
             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))
         self._incpath(f)
 
     def _changepath(self, f, newstate, relaxed=False):
         # handle upcoming path changes
         oldstate = self[f]
         if oldstate not in "?r" and newstate in "?r":
             if "_dirs" in self.__dict__:
                 self._decpath(f)
             return
         if oldstate in "?r" and newstate not in "?r":
             if relaxed and oldstate == '?':
                 # XXX
                 # in relaxed mode we assume the caller knows
                 # what it is doing, workaround for updating
                 # dir-to-file revisions
                 if "_dirs" in self.__dict__:
                     self._incpath(f)
                 return
             self._incpathcheck(f)
             return
 
     def normal(self, f):
         'mark a file normal and clean'
         self._dirty = True
         self._changepath(f, 'n', True)
         s = os.lstat(self._join(f))
         self._map[f] = ('n', s.st_mode, s.st_size, s.st_mtime, 0)
-        if self._copymap.has_key(f):
+        if f in self._copymap:
             del self._copymap[f]
 
     def normallookup(self, f):
         'mark a file normal, but possibly dirty'
         self._dirty = True
         self._changepath(f, 'n', True)
         self._map[f] = ('n', 0, -1, -1, 0)
         if f in self._copymap:
             del self._copymap[f]
 
     def normaldirty(self, f):
         'mark a file normal, but dirty'
         self._dirty = True
         self._changepath(f, 'n', True)
         self._map[f] = ('n', 0, -2, -1, 0)
         if f in self._copymap:
             del self._copymap[f]
 
     def add(self, f):
         'mark a file added'
         self._dirty = True
         self._changepath(f, 'a')
         self._map[f] = ('a', 0, -1, -1, 0)
         if f in self._copymap:
             del self._copymap[f]
 
     def remove(self, f):
         'mark a file removed'
         self._dirty = True
         self._changepath(f, 'r')
         self._map[f] = ('r', 0, 0, 0, 0)
         if f in self._copymap:
             del self._copymap[f]
 
     def merge(self, f):
         'mark a file merged'
         self._dirty = True
         s = os.lstat(self._join(f))
         self._changepath(f, 'm', True)
         self._map[f] = ('m', s.st_mode, s.st_size, s.st_mtime, 0)
         if f in self._copymap:
             del self._copymap[f]
 
     def forget(self, f):
         'forget a file'
         self._dirty = True
         try:
             self._changepath(f, '?')
             del self._map[f]
         except KeyError:
             self._ui.warn(_("not in dirstate: %s!\n") % f)
 
     def clear(self):
         self._map = {}
         if "_dirs" in self.__dict__:
             delattr(self, "_dirs");
         self._copymap = {}
         self._pl = [nullid, nullid]
         self._dirty = True
 
     def rebuild(self, parent, files):
         self.clear()
         for f in files:
             if files.execf(f):
                 self._map[f] = ('n', 0777, -1, 0, 0)
             else:
                 self._map[f] = ('n', 0666, -1, 0, 0)
         self._pl = (parent, nullid)
         self._dirty = True
 
     def write(self):
         if not self._dirty:
             return
         cs = cStringIO.StringIO()
         copymap = self._copymap
         pack = struct.pack
         write = cs.write
         write("".join(self._pl))
         for f, e in self._map.iteritems():
             if f in copymap:
                 f = "%s\0%s" % (f, copymap[f])
             e = pack(_format, e[0], e[1], e[2], e[3], len(f))
             write(e)
             write(f)
         st = self._opener("dirstate", "w", atomictemp=True)
         st.write(cs.getvalue())
         st.rename()
         self._dirty = self._dirtypl = False
 
     def _filter(self, files):
         ret = {}
         unknown = []
 
         for x in files:
             if x == '.':
                 return self._map.copy()
             if x not in self._map:
                 unknown.append(x)
             else:
                 ret[x] = self._map[x]
 
         if not unknown:
             return ret
 
         b = self._map.keys()
         b.sort()
         blen = len(b)
 
         for x in unknown:
             bs = bisect.bisect(b, "%s%s" % (x, '/'))
             while bs < blen:
                 s = b[bs]
                 if len(s) > len(x) and s.startswith(x):
                     ret[s] = self._map[s]
                 else:
                     break
                 bs += 1
         return ret
 
     def _supported(self, f, mode, verbose=False):
         if stat.S_ISREG(mode) or stat.S_ISLNK(mode):
             return True
         if verbose:
             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')
             self._ui.warn(_('%s: unsupported file type (type is %s)\n')
                           % (self.pathto(f), kind))
         return False
 
     def walk(self, files=None, match=util.always, badmatch=None):
         # filter out the stat
         for src, f, st in self.statwalk(files, match, badmatch=badmatch):
             yield src, f
 
     def statwalk(self, files=None, match=util.always, ignored=False,
                  badmatch=None, directories=False):
         '''
         walk recursively through the directory tree, finding all files
         matched by the match function
 
         results are yielded in a tuple (src, filename, st), where src
         is one of:
         'f' the file was found in the directory tree
         'd' the file is a directory of the tree
         'm' the file was only in the dirstate and not in the tree
         'b' file was not found and matched badmatch
 
         and st is the stat result if the file was found in the directory.
         '''
 
         # walk all files by default
         if not files:
             files = ['.']
             dc = self._map.copy()
         else:
             files = util.unique(files)
             dc = self._filter(files)
 
         def imatch(file_):
             if file_ not in dc and self._ignore(file_):
                 return False
             return match(file_)
 
         ignore = self._ignore
         if ignored:
             imatch = match
             ignore = util.never
 
         # self._root may end with a path separator when self._root == '/'
         common_prefix_len = len(self._root)
         if not util.endswithsep(self._root):
             common_prefix_len += 1
 
         normpath = util.normpath
         listdir = osutil.listdir
         lstat = os.lstat
         bisect_left = bisect.bisect_left
         isdir = os.path.isdir
         pconvert = util.pconvert
         join = os.path.join
         s_isdir = stat.S_ISDIR
         supported = self._supported
         _join = self._join
         known = {'.hg': 1}
 
         # recursion free walker, faster than os.walk.
         def findfiles(s):
             work = [s]
             wadd = work.append
             found = []
             add = found.append
             if directories:
                 add((normpath(s[common_prefix_len:]), 'd', lstat(s)))
             while work:
                 top = work.pop()
                 entries = listdir(top, stat=True)
                 # nd is the top of the repository dir tree
                 nd = normpath(top[common_prefix_len:])
                 if nd == '.':
                     nd = ''
                 else:
                     # do not recurse into a repo contained in this
                     # one. use bisect to find .hg directory so speed
                     # is good on big directory.
                     names = [e[0] for e in entries]
                     hg = bisect_left(names, '.hg')
                     if hg < len(names) and names[hg] == '.hg':
                         if isdir(join(top, '.hg')):
                             continue
                 for f, kind, st in entries:
                     np = pconvert(join(nd, f))
                     if np in known:
                         continue
                     known[np] = 1
                     p = join(top, f)
                     # don't trip over symlinks
                     if kind == stat.S_IFDIR:
                         if not ignore(np):
                             wadd(p)
                             if directories:
                                 add((np, 'd', st))
                         if np in dc and match(np):
                             add((np, 'm', st))
                     elif imatch(np):
                         if supported(np, st.st_mode):
                             add((np, 'f', st))
                         elif np in dc:
                             add((np, 'm', st))
             found.sort()
             return found
 
         # step one, find all files that match our criteria
         files.sort()
         for ff in files:
             nf = normpath(ff)
             f = _join(ff)
             try:
                 st = lstat(f)
             except OSError, inst:
                 found = False
                 for fn in dc:
                     if nf == fn or (fn.startswith(nf) and fn[len(nf)] == '/'):
                         found = True
                         break
                 if not found:
                     if inst.errno != errno.ENOENT or not badmatch:
                         self._ui.warn('%s: %s\n' %
                                       (self.pathto(ff), inst.strerror))
                     elif badmatch and badmatch(ff) and imatch(nf):
                         yield 'b', ff, None
                 continue
             if s_isdir(st.st_mode):
                 for f, src, st in findfiles(f):
                     yield src, f, st
             else:
                 if nf in known:
                     continue
                 known[nf] = 1
                 if match(nf):
                     if supported(ff, st.st_mode, verbose=True):
                         yield 'f', nf, st
                     elif ff in dc:
                         yield 'm', nf, st
 
         # step two run through anything left in the dc hash and yield
         # if we haven't already seen it
         ks = dc.keys()
         ks.sort()
         for k in ks:
             if k in known:
                 continue
             known[k] = 1
             if imatch(k):
                 yield 'm', k, None
 
     def status(self, files, match, list_ignored, list_clean):
         lookup, modified, added, unknown, ignored = [], [], [], [], []
         removed, deleted, clean = [], [], []
 
         _join = self._join
         lstat = os.lstat
         cmap = self._copymap
         dmap = self._map
         ladd = lookup.append
         madd = modified.append
         aadd = added.append
         uadd = unknown.append
         iadd = ignored.append
         radd = removed.append
         dadd = deleted.append
         cadd = clean.append
 
         for src, fn, st in self.statwalk(files, match, ignored=list_ignored):
             if fn in dmap:
                 type_, mode, size, time, foo = dmap[fn]
             else:
                 if list_ignored and self._ignore(fn):
                     iadd(fn)
                 else:
                     uadd(fn)
                 continue
             if src == 'm':
                 nonexistent = True
                 if not st:
                     try:
                         st = lstat(_join(fn))
                     except OSError, inst:
                         if inst.errno not in (errno.ENOENT, errno.ENOTDIR):
                             raise
                         st = None
                     # We need to re-check that it is a valid file
                     if st and self._supported(fn, st.st_mode):
                         nonexistent = False
                 # XXX: what to do with file no longer present in the fs
                 # who are not removed in the dirstate ?
                 if nonexistent and type_ in "nm":
                     dadd(fn)
                     continue
             # check the common case first
             if type_ == 'n':
                 if not st:
                     st = lstat(_join(fn))
                 if (size >= 0 and (size != st.st_size
                                    or (mode ^ st.st_mode) & 0100)
                     or size == -2
                     or fn in self._copymap):
                     madd(fn)
                 elif time != int(st.st_mtime):
                     ladd(fn)
                 elif list_clean:
                     cadd(fn)
             elif type_ == 'm':
                 madd(fn)
             elif type_ == 'a':
                 aadd(fn)
             elif type_ == 'r':
                 radd(fn)
 
         return (lookup, modified, added, removed, deleted, unknown, ignored,
                 clean)

mercurial/filelog.py

@@ -1,83 +1,83 b''
 # filelog.py - file history 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, incorporated herein by reference.
 
 from revlog import *
 import os
 
 class filelog(revlog):
     def __init__(self, opener, path):
         revlog.__init__(self, opener,
                         "/".join(("data", self.encodedir(path + ".i"))))
 
     # This avoids a collision between a file named foo and a dir named
     # foo.i or foo.d
     def encodedir(self, path):
         return (path
                 .replace(".hg/", ".hg.hg/")
                 .replace(".i/", ".i.hg/")
                 .replace(".d/", ".d.hg/"))
 
     def decodedir(self, path):
         return (path
                 .replace(".d.hg/", ".d/")
                 .replace(".i.hg/", ".i/")
                 .replace(".hg.hg/", ".hg/"))
 
     def read(self, node):
         t = self.revision(node)
         if not t.startswith('\1\n'):
             return t
         s = t.index('\1\n', 2)
         return t[s+2:]
 
     def _readmeta(self, node):
         t = self.revision(node)
         if not t.startswith('\1\n'):
             return {}
         s = t.index('\1\n', 2)
         mt = t[2:s]
         m = {}
         for l in mt.splitlines():
             k, v = l.split(": ", 1)
             m[k] = v
         return m
 
     def add(self, text, meta, transaction, link, p1=None, p2=None):
         if meta or text.startswith('\1\n'):
             mt = ""
             if meta:
                 mt = [ "%s: %s\n" % (k, v) for k,v in meta.items() ]
             text = "\1\n%s\1\n%s" % ("".join(mt), text)
         return self.addrevision(text, transaction, link, p1, p2)
 
     def renamed(self, node):
         if self.parents(node)[0] != nullid:
             return False
         m = self._readmeta(node)
-        if m and m.has_key("copy"):
+        if m and "copy" in m:
             return (m["copy"], bin(m["copyrev"]))
         return False
 
     def size(self, rev):
         """return the size of a given revision"""
 
         # for revisions with renames, we have to go the slow way
         node = self.node(rev)
         if self.renamed(node):
             return len(self.read(node))
 
         return revlog.size(self, rev)
 
     def cmp(self, node, text):
         """compare text with a given file revision"""
 
         # for renames, we have to go the slow way
         if self.renamed(node):
             t2 = self.read(node)
             return t2 != text
 
         return revlog.cmp(self, node, text)

mercurial/hgweb/hgweb_mod.py

@@ -1,908 +1,908 b''
 # hgweb/hgweb_mod.py - Web interface for a repository.
 #
 # 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, incorporated herein by reference.
 
 import os, mimetypes, re, mimetools, cStringIO
 from mercurial.node import *
 from mercurial import mdiff, ui, hg, util, archival, patch, hook
 from mercurial import revlog, templater
 from common import ErrorResponse, get_mtime, style_map, paritygen, get_contact
 from request import wsgirequest
 import webcommands, protocol
 
 shortcuts = {
     'cl': [('cmd', ['changelog']), ('rev', None)],
     'sl': [('cmd', ['shortlog']), ('rev', None)],
     'cs': [('cmd', ['changeset']), ('node', None)],
     'f': [('cmd', ['file']), ('filenode', None)],
     'fl': [('cmd', ['filelog']), ('filenode', None)],
     'fd': [('cmd', ['filediff']), ('node', None)],
     'fa': [('cmd', ['annotate']), ('filenode', None)],
     'mf': [('cmd', ['manifest']), ('manifest', None)],
     'ca': [('cmd', ['archive']), ('node', None)],
     'tags': [('cmd', ['tags'])],
     'tip': [('cmd', ['changeset']), ('node', ['tip'])],
     'static': [('cmd', ['static']), ('file', None)]
 }
 
 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 revnavgen(pos, pagelen, limit, nodefunc):
     def seq(factor, limit=None):
         if limit:
             yield limit
             if limit >= 20 and limit <= 40:
                 yield 50
         else:
             yield 1 * factor
             yield 3 * factor
         for f in seq(factor * 10):
             yield f
 
     def nav(**map):
         l = []
         last = 0
         for f in seq(1, pagelen):
             if f < pagelen or f <= last:
                 continue
             if f > limit:
                 break
             last = f
             if pos + f < limit:
                 l.append(("+%d" % f, hex(nodefunc(pos + f).node())))
             if pos - f >= 0:
                 l.insert(0, ("-%d" % f, hex(nodefunc(pos - f).node())))
 
         try:
             yield {"label": "(0)", "node": hex(nodefunc('0').node())}
 
             for label, node in l:
                 yield {"label": label, "node": node}
 
             yield {"label": "tip", "node": "tip"}
         except hg.RepoError:
             pass
 
     return nav
 
 class hgweb(object):
     def __init__(self, repo, name=None):
         if isinstance(repo, str):
             parentui = ui.ui(report_untrusted=False, interactive=False)
             self.repo = hg.repository(parentui, repo)
         else:
             self.repo = repo
 
         hook.redirect(True)
         self.mtime = -1
         self.reponame = name
         self.archives = 'zip', 'gz', 'bz2'
         self.stripecount = 1
         # a repo owner may set web.templates in .hg/hgrc to get any file
         # readable by the user running the CGI script
         self.templatepath = self.config("web", "templates",
                                         templater.templatepath(),
                                         untrusted=False)
 
     # The CGI scripts are often run by a user different from the repo owner.
     # Trust the settings from the .hg/hgrc files by default.
     def config(self, section, name, default=None, untrusted=True):
         return self.repo.ui.config(section, name, default,
                                    untrusted=untrusted)
 
     def configbool(self, section, name, default=False, untrusted=True):
         return self.repo.ui.configbool(section, name, default,
                                        untrusted=untrusted)
 
     def configlist(self, section, name, default=None, untrusted=True):
         return self.repo.ui.configlist(section, name, default,
                                        untrusted=untrusted)
 
     def refresh(self):
         mtime = get_mtime(self.repo.root)
         if mtime != self.mtime:
             self.mtime = mtime
             self.repo = hg.repository(self.repo.ui, self.repo.root)
             self.maxchanges = int(self.config("web", "maxchanges", 10))
             self.stripecount = int(self.config("web", "stripes", 1))
             self.maxshortchanges = int(self.config("web", "maxshortchanges", 60))
             self.maxfiles = int(self.config("web", "maxfiles", 10))
             self.allowpull = self.configbool("web", "allowpull", True)
             self.encoding = self.config("web", "encoding", util._encoding)
 
     def run(self):
         if not os.environ.get('GATEWAY_INTERFACE', '').startswith("CGI/1."):
             raise RuntimeError("This function is only intended to be called while running as a CGI script.")
         import mercurial.hgweb.wsgicgi as wsgicgi
         wsgicgi.launch(self)
 
     def __call__(self, env, respond):
         req = wsgirequest(env, respond)
         self.run_wsgi(req)
         return req
 
     def run_wsgi(self, req):
 
         self.refresh()
 
         # expand form shortcuts
 
         for k in shortcuts.iterkeys():
             if k in req.form:
                 for name, value in shortcuts[k]:
                     if value is None:
                         value = req.form[k]
                     req.form[name] = value
                 del req.form[k]
 
         # work with CGI variables to create coherent structure
         # use SCRIPT_NAME, PATH_INFO and QUERY_STRING as well as our REPO_NAME
 
         req.url = req.env['SCRIPT_NAME']
         if not req.url.endswith('/'):
             req.url += '/'
-        if req.env.has_key('REPO_NAME'):
+        if 'REPO_NAME' in req.env:
             req.url += req.env['REPO_NAME'] + '/'
 
         if req.env.get('PATH_INFO'):
             parts = req.env.get('PATH_INFO').strip('/').split('/')
             repo_parts = req.env.get('REPO_NAME', '').split('/')
             if parts[:len(repo_parts)] == repo_parts:
                 parts = parts[len(repo_parts):]
             query = '/'.join(parts)
         else:
             query = req.env['QUERY_STRING'].split('&', 1)[0]
             query = query.split(';', 1)[0]
 
         # translate user-visible url structure to internal structure
 
         args = query.split('/', 2)
         if 'cmd' not in req.form and args and args[0]:
 
             cmd = args.pop(0)
             style = cmd.rfind('-')
             if style != -1:
                 req.form['style'] = [cmd[:style]]
                 cmd = cmd[style+1:]
 
             # avoid accepting e.g. style parameter as command
             if hasattr(webcommands, cmd) or hasattr(protocol, cmd):
                 req.form['cmd'] = [cmd]
 
             if args and args[0]:
                 node = args.pop(0)
                 req.form['node'] = [node]
             if args:
                 req.form['file'] = args
 
             if cmd == 'static':
                 req.form['file'] = req.form['node']
             elif cmd == 'archive':
                 fn = req.form['node'][0]
                 for type_, spec in self.archive_specs.iteritems():
                     ext = spec[2]
                     if fn.endswith(ext):
                         req.form['node'] = [fn[:-len(ext)]]
                         req.form['type'] = [type_]
 
         # actually process the request
 
         try:
 
             cmd = req.form.get('cmd', [''])[0]
             if hasattr(protocol, cmd):
                 method = getattr(protocol, cmd)
                 method(self, req)
             else:
 
                 tmpl = self.templater(req)
                 if cmd == '':
                     req.form['cmd'] = [tmpl.cache['default']]
                     cmd = req.form['cmd'][0]
 
                 if cmd == 'file' and 'raw' in req.form['style']:
                     webcommands.rawfile(self, req, tmpl)
                 else:
                     getattr(webcommands, cmd)(self, req, tmpl)
 
                 del tmpl
 
         except revlog.LookupError, err:
             req.respond(404, tmpl(
                         'error', error='revision not found: %s' % err.name))
         except (hg.RepoError, revlog.RevlogError), inst:
             req.respond('500 Internal Server Error',
                         tmpl('error', error=str(inst)))
         except ErrorResponse, inst:
             req.respond(inst.code, tmpl('error', error=inst.message))
         except AttributeError:
             req.respond(400, tmpl('error', error='No such method: ' + cmd))
 
     def templater(self, req):
 
         # determine scheme, port and server name
         # this is needed to create absolute urls
 
         proto = req.env.get('wsgi.url_scheme')
         if proto == 'https':
             proto = 'https'
             default_port = "443"
         else:
             proto = 'http'
             default_port = "80"
 
         port = req.env["SERVER_PORT"]
         port = port != default_port and (":" + port) or ""
         urlbase = '%s://%s%s' % (proto, req.env['SERVER_NAME'], port)
         staticurl = self.config("web", "staticurl") or req.url + 'static/'
         if not staticurl.endswith('/'):
             staticurl += '/'
 
         # some functions for the templater
 
         def header(**map):
             header_file = cStringIO.StringIO(
                 ''.join(tmpl("header", encoding=self.encoding, **map)))
             msg = mimetools.Message(header_file, 0)
             req.header(msg.items())
             yield header_file.read()
 
         def footer(**map):
             yield tmpl("footer", **map)
 
         def motd(**map):
             yield self.config("web", "motd", "")
 
         def sessionvars(**map):
             fields = []
-            if req.form.has_key('style'):
+            if 'style' in req.form:
                 style = req.form['style'][0]
                 if style != self.config('web', 'style', ''):
                     fields.append(('style', style))
 
             separator = req.url[-1] == '?' and ';' or '?'
             for name, value in fields:
                 yield dict(name=name, value=value, separator=separator)
                 separator = ';'
 
         # figure out which style to use
 
         style = self.config("web", "style", "")
-        if req.form.has_key('style'):
+        if 'style' in req.form:
             style = req.form['style'][0]
         mapfile = style_map(self.templatepath, style)
 
         if not self.reponame:
             self.reponame = (self.config("web", "name")
                              or req.env.get('REPO_NAME')
                              or req.url.strip('/') or self.repo.root)
 
         # create the templater
 
         tmpl = templater.templater(mapfile, templater.common_filters,
                                    defaults={"url": req.url,
                                              "staticurl": staticurl,
                                              "urlbase": urlbase,
                                              "repo": self.reponame,
                                              "header": header,
                                              "footer": footer,
                                              "motd": motd,
                                              "sessionvars": sessionvars
                                             })
         return tmpl
 
     def archivelist(self, nodeid):
         allowed = self.configlist("web", "allow_archive")
         for i, spec in self.archive_specs.iteritems():
             if i in allowed or self.configbool("web", "allow" + i):
                 yield {"type" : i, "extension" : spec[2], "node" : nodeid}
 
     def listfilediffs(self, tmpl, files, changeset):
         for f in files[:self.maxfiles]:
             yield tmpl("filedifflink", node=hex(changeset), file=f)
         if len(files) > self.maxfiles:
             yield tmpl("fileellipses")
 
     def siblings(self, siblings=[], hiderev=None, **args):
         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': hex(s.node()), 'rev': s.rev()}
             if hasattr(s, 'path'):
                 d['file'] = s.path()
             d.update(args)
             yield d
 
     def renamelink(self, fl, node):
         r = fl.renamed(node)
         if r:
             return [dict(file=r[0], node=hex(r[1]))]
         return []
 
     def nodetagsdict(self, node):
         return [{"name": i} for i in self.repo.nodetags(node)]
 
     def nodebranchdict(self, ctx):
         branches = []
         branch = ctx.branch()
         # If this is an empty repo, ctx.node() == nullid,
         # ctx.branch() == 'default', but branchtags() is
         # an empty dict. Using dict.get avoids a traceback.
         if self.repo.branchtags().get(branch) == ctx.node():
             branches.append({"name": branch})
         return branches
 
     def showtag(self, tmpl, t1, node=nullid, **args):
         for t in self.repo.nodetags(node):
             yield tmpl(t1, tag=t, **args)
 
     def diff(self, tmpl, node1, node2, files):
         def filterfiles(filters, files):
             l = [x for x in files if x in filters]
 
             for t in filters:
                 if t and t[-1] != os.sep:
                     t += os.sep
                 l += [x for x in files if x.startswith(t)]
             return l
 
         parity = paritygen(self.stripecount)
         def diffblock(diff, f, fn):
             yield tmpl("diffblock",
                        lines=prettyprintlines(diff),
                        parity=parity.next(),
                        file=f,
                        filenode=hex(fn or nullid))
 
         def prettyprintlines(diff):
             for l in diff.splitlines(1):
                 if l.startswith('+'):
                     yield tmpl("difflineplus", line=l)
                 elif l.startswith('-'):
                     yield tmpl("difflineminus", line=l)
                 elif l.startswith('@'):
                     yield tmpl("difflineat", line=l)
                 else:
                     yield tmpl("diffline", line=l)
 
         r = self.repo
         c1 = r.changectx(node1)
         c2 = r.changectx(node2)
         date1 = util.datestr(c1.date())
         date2 = util.datestr(c2.date())
 
         modified, added, removed, deleted, unknown = r.status(node1, node2)[:5]
         if files:
             modified, added, removed = map(lambda x: filterfiles(files, x),
                                            (modified, added, removed))
 
         diffopts = patch.diffopts(self.repo.ui, untrusted=True)
         for f in modified:
             to = c1.filectx(f).data()
             tn = c2.filectx(f).data()
             yield diffblock(mdiff.unidiff(to, date1, tn, date2, f, f,
                                           opts=diffopts), f, tn)
         for f in added:
             to = None
             tn = c2.filectx(f).data()
             yield diffblock(mdiff.unidiff(to, date1, tn, date2, f, f,
                                           opts=diffopts), f, tn)
         for f in removed:
             to = c1.filectx(f).data()
             tn = None
             yield diffblock(mdiff.unidiff(to, date1, tn, date2, f, f,
                                           opts=diffopts), f, tn)
 
     def changelog(self, tmpl, ctx, shortlog=False):
         def changelist(limit=0,**map):
             cl = self.repo.changelog
             l = [] # build a list in forward order for efficiency
             for i in xrange(start, end):
                 ctx = self.repo.changectx(i)
                 n = ctx.node()
 
                 l.insert(0, {"parity": parity.next(),
                              "author": ctx.user(),
                              "parent": self.siblings(ctx.parents(), i - 1),
                              "child": self.siblings(ctx.children(), i + 1),
                              "changelogtag": self.showtag("changelogtag",n),
                              "desc": ctx.description(),
                              "date": ctx.date(),
                              "files": self.listfilediffs(tmpl, ctx.files(), n),
                              "rev": i,
                              "node": hex(n),
                              "tags": self.nodetagsdict(n),
                              "branches": self.nodebranchdict(ctx)})
 
             if limit > 0:
                 l = l[:limit]
 
             for e in l:
                 yield e
 
         maxchanges = shortlog and self.maxshortchanges or self.maxchanges
         cl = self.repo.changelog
         count = cl.count()
         pos = ctx.rev()
         start = max(0, pos - maxchanges + 1)
         end = min(count, start + maxchanges)
         pos = end - 1
         parity = paritygen(self.stripecount, offset=start-end)
 
         changenav = revnavgen(pos, maxchanges, count, self.repo.changectx)
 
         return tmpl(shortlog and 'shortlog' or 'changelog',
                     changenav=changenav,
                     node=hex(cl.tip()),
                     rev=pos, changesets=count,
                     entries=lambda **x: changelist(limit=0,**x),
                     latestentry=lambda **x: changelist(limit=1,**x),
                     archives=self.archivelist("tip"))
 
     def search(self, tmpl, query):
 
         def changelist(**map):
             cl = self.repo.changelog
             count = 0
             qw = query.lower().split()
 
             def revgen():
                 for i in xrange(cl.count() - 1, 0, -100):
                     l = []
                     for j in xrange(max(0, i - 100), i):
                         ctx = self.repo.changectx(j)
                         l.append(ctx)
                     l.reverse()
                     for e in l:
                         yield e
 
             for ctx in revgen():
                 miss = 0
                 for q in qw:
                     if not (q in ctx.user().lower() or
                             q in ctx.description().lower() or
                             q in " ".join(ctx.files()).lower()):
                         miss = 1
                         break
                 if miss:
                     continue
 
                 count += 1
                 n = ctx.node()
 
                 yield tmpl('searchentry',
                            parity=parity.next(),
                            author=ctx.user(),
                            parent=self.siblings(ctx.parents()),
                            child=self.siblings(ctx.children()),
                            changelogtag=self.showtag("changelogtag",n),
                            desc=ctx.description(),
                            date=ctx.date(),
                            files=self.listfilediffs(tmpl, ctx.files(), n),
                            rev=ctx.rev(),
                            node=hex(n),
                            tags=self.nodetagsdict(n),
                            branches=self.nodebranchdict(ctx))
 
                 if count >= self.maxchanges:
                     break
 
         cl = self.repo.changelog
         parity = paritygen(self.stripecount)
 
         return tmpl('search',
                     query=query,
                     node=hex(cl.tip()),
                     entries=changelist,
                     archives=self.archivelist("tip"))
 
     def changeset(self, tmpl, ctx):
         n = ctx.node()
         parents = ctx.parents()
         p1 = parents[0].node()
 
         files = []
         parity = paritygen(self.stripecount)
         for f in ctx.files():
             files.append(tmpl("filenodelink",
                               node=hex(n), file=f,
                               parity=parity.next()))
 
         def diff(**map):
             yield self.diff(tmpl, p1, n, None)
 
         return tmpl('changeset',
                     diff=diff,
                     rev=ctx.rev(),
                     node=hex(n),
                     parent=self.siblings(parents),
                     child=self.siblings(ctx.children()),
                     changesettag=self.showtag("changesettag",n),
                     author=ctx.user(),
                     desc=ctx.description(),
                     date=ctx.date(),
                     files=files,
                     archives=self.archivelist(hex(n)),
                     tags=self.nodetagsdict(n),
                     branches=self.nodebranchdict(ctx))
 
     def filelog(self, tmpl, fctx):
         f = fctx.path()
         fl = fctx.filelog()
         count = fl.count()
         pagelen = self.maxshortchanges
         pos = fctx.filerev()
         start = max(0, pos - pagelen + 1)
         end = min(count, start + pagelen)
         pos = end - 1
         parity = paritygen(self.stripecount, offset=start-end)
 
         def entries(limit=0, **map):
             l = []
 
             for i in xrange(start, end):
                 ctx = fctx.filectx(i)
                 n = fl.node(i)
 
                 l.insert(0, {"parity": parity.next(),
                              "filerev": i,
                              "file": f,
                              "node": hex(ctx.node()),
                              "author": ctx.user(),
                              "date": ctx.date(),
                              "rename": self.renamelink(fl, n),
                              "parent": self.siblings(fctx.parents()),
                              "child": self.siblings(fctx.children()),
                              "desc": ctx.description()})
 
             if limit > 0:
                 l = l[:limit]
 
             for e in l:
                 yield e
 
         nodefunc = lambda x: fctx.filectx(fileid=x)
         nav = revnavgen(pos, pagelen, count, nodefunc)
         return tmpl("filelog", file=f, node=hex(fctx.node()), nav=nav,
                     entries=lambda **x: entries(limit=0, **x),
                     latestentry=lambda **x: entries(limit=1, **x))
 
     def filerevision(self, tmpl, fctx):
         f = fctx.path()
         text = fctx.data()
         fl = fctx.filelog()
         n = fctx.filenode()
         parity = paritygen(self.stripecount)
 
         mt = mimetypes.guess_type(f)[0]
         rawtext = text
         if util.binary(text):
             mt = mt or 'application/octet-stream'
             text = "(binary:%s)" % mt
         mt = mt or 'text/plain'
 
         def lines():
             for l, t in enumerate(text.splitlines(1)):
                 yield {"line": t,
                        "linenumber": "% 6d" % (l + 1),
                        "parity": parity.next()}
 
         return tmpl("filerevision",
                     file=f,
                     path=_up(f),
                     text=lines(),
                     raw=rawtext,
                     mimetype=mt,
                     rev=fctx.rev(),
                     node=hex(fctx.node()),
                     author=fctx.user(),
                     date=fctx.date(),
                     desc=fctx.description(),
                     parent=self.siblings(fctx.parents()),
                     child=self.siblings(fctx.children()),
                     rename=self.renamelink(fl, n),
                     permissions=fctx.manifest().flags(f))
 
     def fileannotate(self, tmpl, fctx):
         f = fctx.path()
         n = fctx.filenode()
         fl = fctx.filelog()
         parity = paritygen(self.stripecount)
 
         def annotate(**map):
             last = None
             for f, l in fctx.annotate(follow=True):
                 fnode = f.filenode()
                 name = self.repo.ui.shortuser(f.user())
 
                 if last != fnode:
                     last = fnode
 
                 yield {"parity": parity.next(),
                        "node": hex(f.node()),
                        "rev": f.rev(),
                        "author": name,
                        "file": f.path(),
                        "line": l}
 
         return tmpl("fileannotate",
                     file=f,
                     annotate=annotate,
                     path=_up(f),
                     rev=fctx.rev(),
                     node=hex(fctx.node()),
                     author=fctx.user(),
                     date=fctx.date(),
                     desc=fctx.description(),
                     rename=self.renamelink(fl, n),
                     parent=self.siblings(fctx.parents()),
                     child=self.siblings(fctx.children()),
                     permissions=fctx.manifest().flags(f))
 
     def manifest(self, tmpl, ctx, path):
         mf = ctx.manifest()
         node = ctx.node()
 
         files = {}
         parity = paritygen(self.stripecount)
 
         if path and path[-1] != "/":
             path += "/"
         l = len(path)
         abspath = "/" + path
 
         for f, n in mf.items():
             if f[:l] != path:
                 continue
             remain = f[l:]
             if "/" in remain:
                 short = remain[:remain.index("/") + 1] # bleah
                 files[short] = (f, None)
             else:
                 short = os.path.basename(remain)
                 files[short] = (f, n)
 
         if not files:
             raise ErrorResponse(404, 'Path not found: ' + path)
 
         def filelist(**map):
             fl = files.keys()
             fl.sort()
             for f in fl:
                 full, fnode = files[f]
                 if not fnode:
                     continue
 
                 fctx = ctx.filectx(full)
                 yield {"file": full,
                        "parity": parity.next(),
                        "basename": f,
                        "date": fctx.changectx().date(),
                        "size": fctx.size(),
                        "permissions": mf.flags(full)}
 
         def dirlist(**map):
             fl = files.keys()
             fl.sort()
             for f in fl:
                 full, fnode = files[f]
                 if fnode:
                     continue
 
                 yield {"parity": parity.next(),
                        "path": "%s%s" % (abspath, f),
                        "basename": f[:-1]}
 
         return tmpl("manifest",
                     rev=ctx.rev(),
                     node=hex(node),
                     path=abspath,
                     up=_up(abspath),
                     upparity=parity.next(),
                     fentries=filelist,
                     dentries=dirlist,
                     archives=self.archivelist(hex(node)),
                     tags=self.nodetagsdict(node),
                     branches=self.nodebranchdict(ctx))
 
     def tags(self, tmpl):
         i = self.repo.tagslist()
         i.reverse()
         parity = paritygen(self.stripecount)
 
         def entries(notip=False,limit=0, **map):
             count = 0
             for k, n in i:
                 if notip and k == "tip":
                     continue
                 if limit > 0 and count >= limit:
                     continue
                 count = count + 1
                 yield {"parity": parity.next(),
                        "tag": k,
                        "date": self.repo.changectx(n).date(),
                        "node": hex(n)}
 
         return tmpl("tags",
                     node=hex(self.repo.changelog.tip()),
                     entries=lambda **x: entries(False,0, **x),
                     entriesnotip=lambda **x: entries(True,0, **x),
                     latestentry=lambda **x: entries(True,1, **x))
 
     def summary(self, tmpl):
         i = self.repo.tagslist()
         i.reverse()
 
         def tagentries(**map):
             parity = paritygen(self.stripecount)
             count = 0
             for k, n in i:
                 if k == "tip": # skip tip
                     continue;
 
                 count += 1
                 if count > 10: # limit to 10 tags
                     break;
 
                 yield tmpl("tagentry",
                            parity=parity.next(),
                            tag=k,
                            node=hex(n),
                            date=self.repo.changectx(n).date())
 
 
         def branches(**map):
             parity = paritygen(self.stripecount)
 
             b = self.repo.branchtags()
             l = [(-self.repo.changelog.rev(n), n, t) for t, n in b.items()]
             l.sort()
 
             for r,n,t in l:
                 ctx = self.repo.changectx(n)
 
                 yield {'parity': parity.next(),
                        'branch': t,
                        'node': hex(n),
                        'date': ctx.date()}
 
         def changelist(**map):
             parity = paritygen(self.stripecount, offset=start-end)
             l = [] # build a list in forward order for efficiency
             for i in xrange(start, end):
                 ctx = self.repo.changectx(i)
                 n = ctx.node()
                 hn = hex(n)
 
                 l.insert(0, tmpl(
                    'shortlogentry',
                     parity=parity.next(),
                     author=ctx.user(),
                     desc=ctx.description(),
                     date=ctx.date(),
                     rev=i,
                     node=hn,
                     tags=self.nodetagsdict(n),
                     branches=self.nodebranchdict(ctx)))
 
             yield l
 
         cl = self.repo.changelog
         count = cl.count()
         start = max(0, count - self.maxchanges)
         end = min(count, start + self.maxchanges)
 
         return tmpl("summary",
                     desc=self.config("web", "description", "unknown"),
                     owner=get_contact(self.config) or "unknown",
                     lastchange=cl.read(cl.tip())[2],
                     tags=tagentries,
                     branches=branches,
                     shortlog=changelist,
                     node=hex(cl.tip()),
                     archives=self.archivelist("tip"))
 
     def filediff(self, tmpl, fctx):
         n = fctx.node()
         path = fctx.path()
         parents = fctx.parents()
         p1 = parents and parents[0].node() or nullid
 
         def diff(**map):
             yield self.diff(tmpl, p1, n, [path])
 
         return tmpl("filediff",
                     file=path,
                     node=hex(n),
                     rev=fctx.rev(),
                     parent=self.siblings(parents),
                     child=self.siblings(fctx.children()),
                     diff=diff)
 
     archive_specs = {
         'bz2': ('application/x-tar', 'tbz2', '.tar.bz2', None),
         'gz': ('application/x-tar', 'tgz', '.tar.gz', None),
         'zip': ('application/zip', 'zip', '.zip', None),
         }
 
     def archive(self, tmpl, req, key, type_):
         reponame = re.sub(r"\W+", "-", os.path.basename(self.reponame))
         cnode = self.repo.lookup(key)
         arch_version = key
         if cnode == key or key == 'tip':
             arch_version = short(cnode)
         name = "%s-%s" % (reponame, arch_version)
         mimetype, artype, extension, encoding = self.archive_specs[type_]
         headers = [('Content-type', mimetype),
                    ('Content-disposition', 'attachment; filename=%s%s' %
                     (name, extension))]
         if encoding:
             headers.append(('Content-encoding', encoding))
         req.header(headers)
         archival.archive(self.repo, req, cnode, artype, prefix=name)
 
     # add tags to things
     # tags -> list of changesets corresponding to tags
     # find tag, changeset, file
 
     def cleanpath(self, path):
         path = path.lstrip('/')
         return util.canonpath(self.repo.root, '', path)
 
     def changectx(self, req):
-        if req.form.has_key('node'):
+        if 'node' in req.form:
             changeid = req.form['node'][0]
-        elif req.form.has_key('manifest'):
+        elif 'manifest' in req.form:
             changeid = req.form['manifest'][0]
         else:
             changeid = self.repo.changelog.count() - 1
 
         try:
             ctx = self.repo.changectx(changeid)
         except hg.RepoError:
             man = self.repo.manifest
             mn = man.lookup(changeid)
             ctx = self.repo.changectx(man.linkrev(mn))
 
         return ctx
 
     def filectx(self, req):
         path = self.cleanpath(req.form['file'][0])
-        if req.form.has_key('node'):
+        if 'node' in req.form:
             changeid = req.form['node'][0]
         else:
             changeid = req.form['filenode'][0]
         try:
             ctx = self.repo.changectx(changeid)
             fctx = ctx.filectx(path)
         except hg.RepoError:
             fctx = self.repo.filectx(path, fileid=changeid)
 
         return fctx
 
     def check_perm(self, req, op, default):
         '''check permission for operation based on user auth.
         return true if op allowed, else false.
         default is policy to use if no config given.'''
 
         user = req.env.get('REMOTE_USER')
 
         deny = self.configlist('web', 'deny_' + op)
         if deny and (not user or deny == ['*'] or user in deny):
             return False
 
         allow = self.configlist('web', 'allow_' + op)
         return (allow and (allow == ['*'] or user in allow)) or default

mercurial/hgweb/hgwebdir_mod.py

@@ -1,276 +1,276 b''
 # hgweb/hgwebdir_mod.py - Web interface for a directory of repositories.
 #
 # Copyright 21 May 2005 - (c) 2005 Jake Edge <[e-mail]>
 # Copyright 2005, 2006 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms
 # of the GNU General Public License, incorporated herein by reference.
 
 import os, mimetools, cStringIO
 from mercurial.i18n import gettext as _
 from mercurial import ui, hg, util, templater
 from common import ErrorResponse, get_mtime, staticfile, style_map, paritygen, \
                    get_contact
 from hgweb_mod import hgweb
 from request import wsgirequest
 
 # This is a stopgap
 class hgwebdir(object):
     def __init__(self, config, parentui=None):
         def cleannames(items):
             return [(util.pconvert(name).strip('/'), path)
                     for name, path in items]
 
         self.parentui = parentui or ui.ui(report_untrusted=False,
                                           interactive = False)
         self.motd = None
         self.style = None
         self.stripecount = None
         self.repos_sorted = ('name', False)
         if isinstance(config, (list, tuple)):
             self.repos = cleannames(config)
             self.repos_sorted = ('', False)
         elif isinstance(config, dict):
             self.repos = cleannames(config.items())
             self.repos.sort()
         else:
             if isinstance(config, util.configparser):
                 cp = config
             else:
                 cp = util.configparser()
                 cp.read(config)
             self.repos = []
             if cp.has_section('web'):
                 if cp.has_option('web', 'motd'):
                     self.motd = cp.get('web', 'motd')
                 if cp.has_option('web', 'style'):
                     self.style = cp.get('web', 'style')
                 if cp.has_option('web', 'stripes'):
                     self.stripecount = int(cp.get('web', 'stripes'))
             if cp.has_section('paths'):
                 self.repos.extend(cleannames(cp.items('paths')))
             if cp.has_section('collections'):
                 for prefix, root in cp.items('collections'):
                     for path in util.walkrepos(root):
                         repo = os.path.normpath(path)
                         name = repo
                         if name.startswith(prefix):
                             name = name[len(prefix):]
                         self.repos.append((name.lstrip(os.sep), repo))
             self.repos.sort()
 
     def run(self):
         if not os.environ.get('GATEWAY_INTERFACE', '').startswith("CGI/1."):
             raise RuntimeError("This function is only intended to be called while running as a CGI script.")
         import mercurial.hgweb.wsgicgi as wsgicgi
         wsgicgi.launch(self)
 
     def __call__(self, env, respond):
         req = wsgirequest(env, respond)
         self.run_wsgi(req)
         return req
 
     def run_wsgi(self, req):
 
         try:
             try:
 
                 virtual = req.env.get("PATH_INFO", "").strip('/')
 
                 # a static file
                 if virtual.startswith('static/') or 'static' in req.form:
                     static = os.path.join(templater.templatepath(), 'static')
                     if virtual.startswith('static/'):
                         fname = virtual[7:]
                     else:
                         fname = req.form['static'][0]
                     req.write(staticfile(static, fname, req))
                     return
 
                 # top-level index
                 elif not virtual:
                     tmpl = self.templater(req)
                     self.makeindex(req, tmpl)
                     return
 
                 # nested indexes and hgwebs
                 repos = dict(self.repos)
                 while virtual:
                     real = repos.get(virtual)
                     if real:
                         req.env['REPO_NAME'] = virtual
                         try:
                             repo = hg.repository(self.parentui, real)
                             hgweb(repo).run_wsgi(req)
                             return
                         except IOError, inst:
                             raise ErrorResponse(500, inst.strerror)
                         except hg.RepoError, inst:
                             raise ErrorResponse(500, str(inst))
 
                     # browse subdirectories
                     subdir = virtual + '/'
                     if [r for r in repos if r.startswith(subdir)]:
                         tmpl = self.templater(req)
                         self.makeindex(req, tmpl, subdir)
                         return
 
                     up = virtual.rfind('/')
                     if up < 0:
                         break
                     virtual = virtual[:up]
 
                 # prefixes not found
                 tmpl = self.templater(req)
                 req.respond(404, tmpl("notfound", repo=virtual))
 
             except ErrorResponse, err:
                 tmpl = self.templater(req)
                 req.respond(err.code, tmpl('error', error=err.message or ''))
         finally:
             tmpl = None
 
     def makeindex(self, req, tmpl, subdir=""):
 
         def archivelist(ui, nodeid, url):
             allowed = ui.configlist("web", "allow_archive", untrusted=True)
             for i in [('zip', '.zip'), ('gz', '.tar.gz'), ('bz2', '.tar.bz2')]:
                 if i[0] in allowed or ui.configbool("web", "allow" + i[0],
                                                     untrusted=True):
                     yield {"type" : i[0], "extension": i[1],
                            "node": nodeid, "url": url}
 
         def entries(sortcolumn="", descending=False, subdir="", **map):
             def sessionvars(**map):
                 fields = []
-                if req.form.has_key('style'):
+                if 'style' in req.form:
                     style = req.form['style'][0]
                     if style != get('web', 'style', ''):
                         fields.append(('style', style))
 
                 separator = url[-1] == '?' and ';' or '?'
                 for name, value in fields:
                     yield dict(name=name, value=value, separator=separator)
                     separator = ';'
 
             rows = []
             parity = paritygen(self.stripecount)
             for name, path in self.repos:
                 if not name.startswith(subdir):
                     continue
                 name = name[len(subdir):]
 
                 u = ui.ui(parentui=self.parentui)
                 try:
                     u.readconfig(os.path.join(path, '.hg', 'hgrc'))
                 except Exception, e:
                     u.warn(_('error reading %s/.hg/hgrc: %s\n' % (path, e)))
                     continue
                 def get(section, name, default=None):
                     return u.config(section, name, default, untrusted=True)
 
                 if u.configbool("web", "hidden", untrusted=True):
                     continue
 
                 parts = [req.env['PATH_INFO'], name]
                 if req.env['SCRIPT_NAME']:
                     parts.insert(0, req.env['SCRIPT_NAME'])
                 url = ('/'.join(parts).replace("//", "/")) + '/'
 
                 # update time with local timezone
                 try:
                     d = (get_mtime(path), util.makedate()[1])
                 except OSError:
                     continue
 
                 contact = get_contact(get)
                 description = get("web", "description", "")
                 name = get("web", "name", name)
                 row = dict(contact=contact or "unknown",
                            contact_sort=contact.upper() or "unknown",
                            name=name,
                            name_sort=name,
                            url=url,
                            description=description or "unknown",
                            description_sort=description.upper() or "unknown",
                            lastchange=d,
                            lastchange_sort=d[1]-d[0],
                            sessionvars=sessionvars,
                            archives=archivelist(u, "tip", url))
                 if (not sortcolumn
                     or (sortcolumn, descending) == self.repos_sorted):
                     # fast path for unsorted output
                     row['parity'] = parity.next()
                     yield row
                 else:
                     rows.append((row["%s_sort" % sortcolumn], row))
             if rows:
                 rows.sort()
                 if descending:
                     rows.reverse()
                 for key, row in rows:
                     row['parity'] = parity.next()
                     yield row
 
         sortable = ["name", "description", "contact", "lastchange"]
         sortcolumn, descending = self.repos_sorted
-        if req.form.has_key('sort'):
+        if 'sort' in req.form:
             sortcolumn = req.form['sort'][0]
             descending = sortcolumn.startswith('-')
             if descending:
                 sortcolumn = sortcolumn[1:]
             if sortcolumn not in sortable:
                 sortcolumn = ""
 
         sort = [("sort_%s" % column,
                  "%s%s" % ((not descending and column == sortcolumn)
                             and "-" or "", column))
                 for column in sortable]
         req.write(tmpl("index", entries=entries, subdir=subdir,
                        sortcolumn=sortcolumn, descending=descending,
                        **dict(sort)))
 
     def templater(self, req):
 
         def header(**map):
             header_file = cStringIO.StringIO(
                 ''.join(tmpl("header", encoding=util._encoding, **map)))
             msg = mimetools.Message(header_file, 0)
             req.header(msg.items())
             yield header_file.read()
 
         def footer(**map):
             yield tmpl("footer", **map)
 
         def motd(**map):
             if self.motd is not None:
                 yield self.motd
             else:
                 yield config('web', 'motd', '')
 
         def config(section, name, default=None, untrusted=True):
             return self.parentui.config(section, name, default, untrusted)
 
         url = req.env.get('SCRIPT_NAME', '')
         if not url.endswith('/'):
             url += '/'
 
         staticurl = config('web', 'staticurl') or url + 'static/'
         if not staticurl.endswith('/'):
             staticurl += '/'
 
         style = self.style
         if style is None:
             style = config('web', 'style', '')
-        if req.form.has_key('style'):
+        if 'style' in req.form:
             style = req.form['style'][0]
         if self.stripecount is None:
             self.stripecount = int(config('web', 'stripes', 1))
         mapfile = style_map(templater.templatepath(), style)
         tmpl = templater.templater(mapfile, templater.common_filters,
                                    defaults={"header": header,
                                              "footer": footer,
                                              "motd": motd,
                                              "url": url,
                                              "staticurl": staticurl})
         return tmpl

mercurial/hgweb/protocol.py

@@ -1,237 +1,237 b''
 #
 # 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, incorporated herein by reference.
 
 import cStringIO, zlib, bz2, tempfile, errno, os, sys
 from mercurial import util, streamclone
 from mercurial.i18n import gettext as _
 from mercurial.node import *
 
 def lookup(web, req):
     try:
         r = hex(web.repo.lookup(req.form['key'][0]))
         success = 1
     except Exception,inst:
         r = str(inst)
         success = 0
     resp = "%s %s\n" % (success, r)
     req.httphdr("application/mercurial-0.1", length=len(resp))
     req.write(resp)
 
 def heads(web, req):
     resp = " ".join(map(hex, web.repo.heads())) + "\n"
     req.httphdr("application/mercurial-0.1", length=len(resp))
     req.write(resp)
 
 def branches(web, req):
     nodes = []
-    if req.form.has_key('nodes'):
+    if 'nodes' in req.form:
         nodes = map(bin, req.form['nodes'][0].split(" "))
     resp = cStringIO.StringIO()
     for b in web.repo.branches(nodes):
         resp.write(" ".join(map(hex, b)) + "\n")
     resp = resp.getvalue()
     req.httphdr("application/mercurial-0.1", length=len(resp))
     req.write(resp)
 
 def between(web, req):
-    if req.form.has_key('pairs'):
+    if 'pairs' in req.form:
         pairs = [map(bin, p.split("-"))
                  for p in req.form['pairs'][0].split(" ")]
     resp = cStringIO.StringIO()
     for b in web.repo.between(pairs):
         resp.write(" ".join(map(hex, b)) + "\n")
     resp = resp.getvalue()
     req.httphdr("application/mercurial-0.1", length=len(resp))
     req.write(resp)
 
 def changegroup(web, req):
     req.httphdr("application/mercurial-0.1")
     nodes = []
     if not web.allowpull:
         return
 
-    if req.form.has_key('roots'):
+    if 'roots' in req.form:
         nodes = map(bin, req.form['roots'][0].split(" "))
 
     z = zlib.compressobj()
     f = web.repo.changegroup(nodes, 'serve')
     while 1:
         chunk = f.read(4096)
         if not chunk:
             break
         req.write(z.compress(chunk))
 
     req.write(z.flush())
 
 def changegroupsubset(web, req):
     req.httphdr("application/mercurial-0.1")
     bases = []
     heads = []
     if not web.allowpull:
         return
 
-    if req.form.has_key('bases'):
+    if 'bases' in req.form:
         bases = [bin(x) for x in req.form['bases'][0].split(' ')]
-    if req.form.has_key('heads'):
+    if 'heads' in req.form:
         heads = [bin(x) for x in req.form['heads'][0].split(' ')]
 
     z = zlib.compressobj()
     f = web.repo.changegroupsubset(bases, heads, 'serve')
     while 1:
         chunk = f.read(4096)
         if not chunk:
             break
         req.write(z.compress(chunk))
 
     req.write(z.flush())
 
 def capabilities(web, req):
     caps = ['lookup', 'changegroupsubset']
     if web.configbool('server', 'uncompressed'):
         caps.append('stream=%d' % web.repo.changelog.version)
     # XXX: make configurable and/or share code with do_unbundle:
     unbundleversions = ['HG10GZ', 'HG10BZ', 'HG10UN']
     if unbundleversions:
         caps.append('unbundle=%s' % ','.join(unbundleversions))
     resp = ' '.join(caps)
     req.httphdr("application/mercurial-0.1", length=len(resp))
     req.write(resp)
 
 def unbundle(web, req):
     def bail(response, headers={}):
         length = int(req.env['CONTENT_LENGTH'])
         for s in util.filechunkiter(req, limit=length):
             # drain incoming bundle, else client will not see
             # response when run outside cgi script
             pass
         req.httphdr("application/mercurial-0.1", headers=headers)
         req.write('0\n')
         req.write(response)
 
     # require ssl by default, auth info cannot be sniffed and
     # replayed
     ssl_req = web.configbool('web', 'push_ssl', True)
     if ssl_req:
         if req.env.get('wsgi.url_scheme') != 'https':
             bail(_('ssl required\n'))
             return
         proto = 'https'
     else:
         proto = 'http'
 
     # do not allow push unless explicitly allowed
     if not web.check_perm(req, 'push', False):
         bail(_('push not authorized\n'),
              headers={'status': '401 Unauthorized'})
         return
 
     their_heads = req.form['heads'][0].split(' ')
 
     def check_heads():
         heads = map(hex, web.repo.heads())
         return their_heads == [hex('force')] or their_heads == heads
 
     # fail early if possible
     if not check_heads():
         bail(_('unsynced changes\n'))
         return
 
     req.httphdr("application/mercurial-0.1")
 
     # do not lock repo until all changegroup data is
     # streamed. save to temporary file.
 
     fd, tempname = tempfile.mkstemp(prefix='hg-unbundle-')
     fp = os.fdopen(fd, 'wb+')
     try:
         length = int(req.env['CONTENT_LENGTH'])
         for s in util.filechunkiter(req, limit=length):
             fp.write(s)
 
         try:
             lock = web.repo.lock()
             try:
                 if not check_heads():
                     req.write('0\n')
                     req.write(_('unsynced changes\n'))
                     return
 
                 fp.seek(0)
                 header = fp.read(6)
                 if not header.startswith("HG"):
                     # old client with uncompressed bundle
                     def generator(f):
                         yield header
                         for chunk in f:
                             yield chunk
                 elif not header.startswith("HG10"):
                     req.write("0\n")
                     req.write(_("unknown bundle version\n"))
                     return
                 elif header == "HG10GZ":
                     def generator(f):
                         zd = zlib.decompressobj()
                         for chunk in f:
                             yield zd.decompress(chunk)
                 elif header == "HG10BZ":
                     def generator(f):
                         zd = bz2.BZ2Decompressor()
                         zd.decompress("BZ")
                         for chunk in f:
                             yield zd.decompress(chunk)
                 elif header == "HG10UN":
                     def generator(f):
                         for chunk in f:
                             yield chunk
                 else:
                     req.write("0\n")
                     req.write(_("unknown bundle compression type\n"))
                     return
                 gen = generator(util.filechunkiter(fp, 4096))
 
                 # send addchangegroup output to client
 
                 old_stdout = sys.stdout
                 sys.stdout = cStringIO.StringIO()
 
                 try:
                     url = 'remote:%s:%s' % (proto,
                                             req.env.get('REMOTE_HOST', ''))
                     try:
                         ret = web.repo.addchangegroup(
                                     util.chunkbuffer(gen), 'serve', url)
                     except util.Abort, inst:
                         sys.stdout.write("abort: %s\n" % inst)
                         ret = 0
                 finally:
                     val = sys.stdout.getvalue()
                     sys.stdout = old_stdout
                 req.write('%d\n' % ret)
                 req.write(val)
             finally:
                 del lock
         except (OSError, IOError), inst:
             req.write('0\n')
             filename = getattr(inst, 'filename', '')
             # Don't send our filesystem layout to the client
             if filename.startswith(web.repo.root):
                 filename = filename[len(web.repo.root)+1:]
             else:
                 filename = ''
             error = getattr(inst, 'strerror', 'Unknown error')
             if inst.errno == errno.ENOENT:
                 code = 404
             else:
                 code = 500
             req.respond(code, '%s: %s\n' % (error, filename))
     finally:
         fp.close()
         os.unlink(tempname)
 
 def stream_out(web, req):
     req.httphdr("application/mercurial-0.1")
     streamclone.stream_out(web.repo, req, untrusted=True)

mercurial/hgweb/webcommands.py

@@ -1,113 +1,113 b''
 #
 # 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, incorporated herein by reference.
 
 import os, mimetypes
 from mercurial import revlog, util
 from common import staticfile
 
 def log(web, req, tmpl):
-    if req.form.has_key('file') and req.form['file'][0]:
+    if 'file' in req.form and req.form['file'][0]:
         filelog(web, req, tmpl)
     else:
         changelog(web, req, tmpl)
 
 def rawfile(web, req, tmpl):
     path = web.cleanpath(req.form.get('file', [''])[0])
     if not path:
         req.write(web.manifest(tmpl, web.changectx(req), path))
         return
 
     try:
         fctx = web.filectx(req)
     except revlog.LookupError:
         req.write(web.manifest(tmpl, web.changectx(req), path))
         return
 
     path = fctx.path()
     text = fctx.data()
     mt = mimetypes.guess_type(path)[0]
     if util.binary(text):
         mt = mt or 'application/octet-stream'
 
     req.httphdr(mt, path, len(text))
     req.write(text)
 
 def file(web, req, tmpl):
     path = web.cleanpath(req.form.get('file', [''])[0])
     if path:
         try:
             req.write(web.filerevision(tmpl, web.filectx(req)))
             return
         except revlog.LookupError:
             pass
 
     req.write(web.manifest(tmpl, web.changectx(req), path))
 
 def changelog(web, req, tmpl, shortlog = False):
-    if req.form.has_key('node'):
+    if 'node' in req.form:
         ctx = web.changectx(req)
     else:
-        if req.form.has_key('rev'):
+        if 'rev' in req.form:
             hi = req.form['rev'][0]
         else:
             hi = web.repo.changelog.count() - 1
         try:
             ctx = web.repo.changectx(hi)
         except hg.RepoError:
             req.write(web.search(tmpl, hi)) # XXX redirect to 404 page?
             return
 
     req.write(web.changelog(tmpl, ctx, shortlog = shortlog))
 
 def shortlog(web, req, tmpl):
     changelog(web, req, tmpl, shortlog = True)
 
 def changeset(web, req, tmpl):
     req.write(web.changeset(tmpl, web.changectx(req)))
 
 rev = changeset
 
 def manifest(web, req, tmpl):
     req.write(web.manifest(tmpl, web.changectx(req),
                            web.cleanpath(req.form['path'][0])))
 
 def tags(web, req, tmpl):
     req.write(web.tags(tmpl))
 
 def summary(web, req, tmpl):
     req.write(web.summary(tmpl))
 
 def filediff(web, req, tmpl):
     req.write(web.filediff(tmpl, web.filectx(req)))
 
 diff = filediff
 
 def annotate(web, req, tmpl):
     req.write(web.fileannotate(tmpl, web.filectx(req)))
 
 def filelog(web, req, tmpl):
     req.write(web.filelog(tmpl, web.filectx(req)))
 
 def archive(web, req, tmpl):
     type_ = req.form['type'][0]
     allowed = web.configlist("web", "allow_archive")
     if (type_ in web.archives and (type_ in allowed or
         web.configbool("web", "allow" + type_, False))):
         web.archive(tmpl, req, req.form['node'][0], type_)
         return
 
     req.respond(400, tmpl('error',
                            error='Unsupported archive type: %s' % type_))
 
 def static(web, req, tmpl):
     fname = req.form['file'][0]
     # a repo owner may set web.static in .hg/hgrc to get any file
     # readable by the user running the CGI script
     static = web.config("web", "static",
                         os.path.join(web.templatepath, "static"),
                         untrusted=False)
     req.write(staticfile(static, fname, req))

mercurial/httprepo.py

@@ -1,462 +1,462 b''
 # httprepo.py - HTTP repository proxy classes for mercurial
 #
 # Copyright 2005, 2006 Matt Mackall <[e-mail]>
 # Copyright 2006 Vadim Gelfer <[e-mail]>
 #
 # This software may be used and distributed according to the terms
 # of the GNU General Public License, incorporated herein by reference.
 
 from node import *
 from remoterepo import *
 from i18n import _
 import repo, os, urllib, urllib2, urlparse, zlib, util, httplib
 import errno, keepalive, tempfile, socket, changegroup
 
 class passwordmgr(urllib2.HTTPPasswordMgrWithDefaultRealm):
     def __init__(self, ui):
         urllib2.HTTPPasswordMgrWithDefaultRealm.__init__(self)
         self.ui = ui
 
     def find_user_password(self, realm, authuri):
         authinfo = urllib2.HTTPPasswordMgrWithDefaultRealm.find_user_password(
             self, realm, authuri)
         user, passwd = authinfo
         if user and passwd:
             return (user, passwd)
 
         if not self.ui.interactive:
             raise util.Abort(_('http authorization required'))
 
         self.ui.write(_("http authorization required\n"))
         self.ui.status(_("realm: %s\n") % realm)
         if user:
             self.ui.status(_("user: %s\n") % user)
         else:
             user = self.ui.prompt(_("user:"), default=None)
 
         if not passwd:
             passwd = self.ui.getpass()
 
         self.add_password(realm, authuri, user, passwd)
         return (user, passwd)
 
 def netlocsplit(netloc):
     '''split [user[:passwd]@]host[:port] into 4-tuple.'''
 
     a = netloc.find('@')
     if a == -1:
         user, passwd = None, None
     else:
         userpass, netloc = netloc[:a], netloc[a+1:]
         c = userpass.find(':')
         if c == -1:
             user, passwd = urllib.unquote(userpass), None
         else:
             user = urllib.unquote(userpass[:c])
             passwd = urllib.unquote(userpass[c+1:])
     c = netloc.find(':')
     if c == -1:
         host, port = netloc, None
     else:
         host, port = netloc[:c], netloc[c+1:]
     return host, port, user, passwd
 
 def netlocunsplit(host, port, user=None, passwd=None):
     '''turn host, port, user, passwd into [user[:passwd]@]host[:port].'''
     if port:
         hostport = host + ':' + port
     else:
         hostport = host
     if user:
         if passwd:
             userpass = urllib.quote(user) + ':' + urllib.quote(passwd)
         else:
             userpass = urllib.quote(user)
         return userpass + '@' + hostport
     return hostport
 
 # work around a bug in Python < 2.4.2
 # (it leaves a "\n" at the end of Proxy-authorization headers)
 class request(urllib2.Request):
     def add_header(self, key, val):
         if key.lower() == 'proxy-authorization':
             val = val.strip()
         return urllib2.Request.add_header(self, key, val)
 
 class httpsendfile(file):
     def __len__(self):
         return os.fstat(self.fileno()).st_size
 
 def _gen_sendfile(connection):
     def _sendfile(self, data):
         # send a file
         if isinstance(data, httpsendfile):
             # if auth required, some data sent twice, so rewind here
             data.seek(0)
             for chunk in util.filechunkiter(data):
                 connection.send(self, chunk)
         else:
             connection.send(self, data)
     return _sendfile
 
 class httpconnection(keepalive.HTTPConnection):
     # must be able to send big bundle as stream.
     send = _gen_sendfile(keepalive.HTTPConnection)
 
 class basehttphandler(keepalive.HTTPHandler):
     def http_open(self, req):
         return self.do_open(httpconnection, req)
 
 has_https = hasattr(urllib2, 'HTTPSHandler')
 if has_https:
     class httpsconnection(httplib.HTTPSConnection):
         response_class = keepalive.HTTPResponse
         # must be able to send big bundle as stream.
         send = _gen_sendfile(httplib.HTTPSConnection)
 
     class httphandler(basehttphandler, urllib2.HTTPSHandler):
         def https_open(self, req):
             return self.do_open(httpsconnection, req)
 else:
     class httphandler(basehttphandler):
         pass
 
 # In python < 2.5 AbstractDigestAuthHandler raises a ValueError if
 # it doesn't know about the auth type requested.  This can happen if
 # somebody is using BasicAuth and types a bad password.
 class httpdigestauthhandler(urllib2.HTTPDigestAuthHandler):
     def http_error_auth_reqed(self, auth_header, host, req, headers):
         try:
             return urllib2.HTTPDigestAuthHandler.http_error_auth_reqed(
                         self, auth_header, host, req, headers)
         except ValueError, inst:
             arg = inst.args[0]
             if arg.startswith("AbstractDigestAuthHandler doesn't know "):
                 return
             raise
 
 def zgenerator(f):
     zd = zlib.decompressobj()
     try:
         for chunk in util.filechunkiter(f):
             yield zd.decompress(chunk)
     except httplib.HTTPException, inst:
         raise IOError(None, _('connection ended unexpectedly'))
     yield zd.flush()
 
 _safe = ('abcdefghijklmnopqrstuvwxyz'
          'ABCDEFGHIJKLMNOPQRSTUVWXYZ'
          '0123456789' '_.-/')
 _safeset = None
 _hex = None
 def quotepath(path):
     '''quote the path part of a URL
 
     This is similar to urllib.quote, but it also tries to avoid
     quoting things twice (inspired by wget):
 
     >>> quotepath('abc def')
     'abc%20def'
     >>> quotepath('abc%20def')
     'abc%20def'
     >>> quotepath('abc%20 def')
     'abc%20%20def'
     >>> quotepath('abc def%20')
     'abc%20def%20'
     >>> quotepath('abc def%2')
     'abc%20def%252'
     >>> quotepath('abc def%')
     'abc%20def%25'
     '''
     global _safeset, _hex
     if _safeset is None:
         _safeset = util.set(_safe)
         _hex = util.set('abcdefABCDEF0123456789')
     l = list(path)
     for i in xrange(len(l)):
         c = l[i]
         if c == '%' and i + 2 < len(l) and (l[i+1] in _hex and l[i+2] in _hex):
             pass
         elif c not in _safeset:
             l[i] = '%%%02X' % ord(c)
     return ''.join(l)
 
 class httprepository(remoterepository):
     def __init__(self, ui, path):
         self.path = path
         self.caps = None
         self.handler = None
         scheme, netloc, urlpath, query, frag = urlparse.urlsplit(path)
         if query or frag:
             raise util.Abort(_('unsupported URL component: "%s"') %
                              (query or frag))
         if not urlpath:
             urlpath = '/'
         urlpath = quotepath(urlpath)
         host, port, user, passwd = netlocsplit(netloc)
 
         # urllib cannot handle URLs with embedded user or passwd
         self._url = urlparse.urlunsplit((scheme, netlocunsplit(host, port),
                                          urlpath, '', ''))
         self.ui = ui
         self.ui.debug(_('using %s\n') % self._url)
 
         proxyurl = ui.config("http_proxy", "host") or os.getenv('http_proxy')
         # XXX proxyauthinfo = None
         self.handler = httphandler()
         handlers = [self.handler]
 
         if proxyurl:
             # proxy can be proper url or host[:port]
             if not (proxyurl.startswith('http:') or
                     proxyurl.startswith('https:')):
                 proxyurl = 'http://' + proxyurl + '/'
             snpqf = urlparse.urlsplit(proxyurl)
             proxyscheme, proxynetloc, proxypath, proxyquery, proxyfrag = snpqf
             hpup = netlocsplit(proxynetloc)
 
             proxyhost, proxyport, proxyuser, proxypasswd = hpup
             if not proxyuser:
                 proxyuser = ui.config("http_proxy", "user")
                 proxypasswd = ui.config("http_proxy", "passwd")
 
             # see if we should use a proxy for this url
             no_list = [ "localhost", "127.0.0.1" ]
             no_list.extend([p.lower() for
                             p in ui.configlist("http_proxy", "no")])
             no_list.extend([p.strip().lower() for
                             p in os.getenv("no_proxy", '').split(',')
                             if p.strip()])
             # "http_proxy.always" config is for running tests on localhost
             if (not ui.configbool("http_proxy", "always") and
                 host.lower() in no_list):
                 # avoid auto-detection of proxy settings by appending
                 # a ProxyHandler with no proxies defined.
                 handlers.append(urllib2.ProxyHandler({}))
                 ui.debug(_('disabling proxy for %s\n') % host)
             else:
                 proxyurl = urlparse.urlunsplit((
                     proxyscheme, netlocunsplit(proxyhost, proxyport,
                                                proxyuser, proxypasswd or ''),
                     proxypath, proxyquery, proxyfrag))
                 handlers.append(urllib2.ProxyHandler({scheme: proxyurl}))
                 ui.debug(_('proxying through http://%s:%s\n') %
                           (proxyhost, proxyport))
 
         # urllib2 takes proxy values from the environment and those
         # will take precedence if found, so drop them
         for env in ["HTTP_PROXY", "http_proxy", "no_proxy"]:
             try:
-                if os.environ.has_key(env):
+                if env in os.environ:
                     del os.environ[env]
             except OSError:
                 pass
 
         passmgr = passwordmgr(ui)
         if user:
             ui.debug(_('http auth: user %s, password %s\n') %
                      (user, passwd and '*' * len(passwd) or 'not set'))
             netloc = host
             if port:
                 netloc += ':' + port
             # Python < 2.4.3 uses only the netloc to search for a password
             passmgr.add_password(None, (self._url, netloc), user, passwd or '')
 
         handlers.extend((urllib2.HTTPBasicAuthHandler(passmgr),
                          httpdigestauthhandler(passmgr)))
         opener = urllib2.build_opener(*handlers)
 
         # 1.0 here is the _protocol_ version
         opener.addheaders = [('User-agent', 'mercurial/proto-1.0')]
         urllib2.install_opener(opener)
 
     def __del__(self):
         if self.handler:
             self.handler.close_all()
             self.handler = None
 
     def url(self):
         return self.path
 
     # look up capabilities only when needed
 
     def get_caps(self):
         if self.caps is None:
             try:
                 self.caps = util.set(self.do_read('capabilities').split())
             except repo.RepoError:
                 self.caps = util.set()
             self.ui.debug(_('capabilities: %s\n') %
                           (' '.join(self.caps or ['none'])))
         return self.caps
 
     capabilities = property(get_caps)
 
     def lock(self):
         raise util.Abort(_('operation not supported over http'))
 
     def do_cmd(self, cmd, **args):
         data = args.pop('data', None)
         headers = args.pop('headers', {})
         self.ui.debug(_("sending %s command\n") % cmd)
         q = {"cmd": cmd}
         q.update(args)
         qs = '?%s' % urllib.urlencode(q)
         cu = "%s%s" % (self._url, qs)
         try:
             if data:
                 self.ui.debug(_("sending %s bytes\n") % len(data))
             resp = urllib2.urlopen(request(cu, data, headers))
         except urllib2.HTTPError, inst:
             if inst.code == 401:
                 raise util.Abort(_('authorization failed'))
             raise
         except httplib.HTTPException, inst:
             self.ui.debug(_('http error while sending %s command\n') % cmd)
             self.ui.print_exc()
             raise IOError(None, inst)
         except IndexError:
             # this only happens with Python 2.3, later versions raise URLError
             raise util.Abort(_('http error, possibly caused by proxy setting'))
         # record the url we got redirected to
         resp_url = resp.geturl()
         if resp_url.endswith(qs):
             resp_url = resp_url[:-len(qs)]
         if self._url != resp_url:
             self.ui.status(_('real URL is %s\n') % resp_url)
             self._url = resp_url
         try:
             proto = resp.getheader('content-type')
         except AttributeError:
             proto = resp.headers['content-type']
 
         # accept old "text/plain" and "application/hg-changegroup" for now
         if not (proto.startswith('application/mercurial-') or
                 proto.startswith('text/plain') or
                 proto.startswith('application/hg-changegroup')):
             self.ui.debug(_("Requested URL: '%s'\n") % cu)
             raise repo.RepoError(_("'%s' does not appear to be an hg repository")
                                % self._url)
 
         if proto.startswith('application/mercurial-'):
             try:
                 version = proto.split('-', 1)[1]
                 version_info = tuple([int(n) for n in version.split('.')])
             except ValueError:
                 raise repo.RepoError(_("'%s' sent a broken Content-type "
                                      "header (%s)") % (self._url, proto))
             if version_info > (0, 1):
                 raise repo.RepoError(_("'%s' uses newer protocol %s") %
                                    (self._url, version))
 
         return resp
 
     def do_read(self, cmd, **args):
         fp = self.do_cmd(cmd, **args)
         try:
             return fp.read()
         finally:
             # if using keepalive, allow connection to be reused
             fp.close()
 
     def lookup(self, key):
         self.requirecap('lookup', _('look up remote revision'))
         d = self.do_cmd("lookup", key = key).read()
         success, data = d[:-1].split(' ', 1)
         if int(success):
             return bin(data)
         raise repo.RepoError(data)
 
     def heads(self):
         d = self.do_read("heads")
         try:
             return map(bin, d[:-1].split(" "))
         except:
             raise util.UnexpectedOutput(_("unexpected response:"), d)
 
     def branches(self, nodes):
         n = " ".join(map(hex, nodes))
         d = self.do_read("branches", nodes=n)
         try:
             br = [ tuple(map(bin, b.split(" "))) for b in d.splitlines() ]
             return br
         except:
             raise util.UnexpectedOutput(_("unexpected response:"), d)
 
     def between(self, pairs):
         n = "\n".join(["-".join(map(hex, p)) for p in pairs])
         d = self.do_read("between", pairs=n)
         try:
             p = [ l and map(bin, l.split(" ")) or [] for l in d.splitlines() ]
             return p
         except:
             raise util.UnexpectedOutput(_("unexpected response:"), d)
 
     def changegroup(self, nodes, kind):
         n = " ".join(map(hex, nodes))
         f = self.do_cmd("changegroup", roots=n)
         return util.chunkbuffer(zgenerator(f))
 
     def changegroupsubset(self, bases, heads, source):
         self.requirecap('changegroupsubset', _('look up remote changes'))
         baselst = " ".join([hex(n) for n in bases])
         headlst = " ".join([hex(n) for n in heads])
         f = self.do_cmd("changegroupsubset", bases=baselst, heads=headlst)
         return util.chunkbuffer(zgenerator(f))
 
     def unbundle(self, cg, heads, source):
         # have to stream bundle to a temp file because we do not have
         # http 1.1 chunked transfer.
 
         type = ""
         types = self.capable('unbundle')
         # servers older than d1b16a746db6 will send 'unbundle' as a
         # boolean capability
         try:
             types = types.split(',')
         except AttributeError:
             types = [""]
         if types:
             for x in types:
                 if x in changegroup.bundletypes:
                     type = x
                     break
 
         tempname = changegroup.writebundle(cg, None, type)
         fp = httpsendfile(tempname, "rb")
         try:
             try:
                 rfp = self.do_cmd(
                     'unbundle', data=fp,
                     headers={'content-type': 'application/octet-stream'},
                     heads=' '.join(map(hex, heads)))
                 try:
                     ret = int(rfp.readline())
                     self.ui.write(rfp.read())
                     return ret
                 finally:
                     rfp.close()
             except socket.error, err:
                 if err[0] in (errno.ECONNRESET, errno.EPIPE):
                     raise util.Abort(_('push failed: %s') % err[1])
                 raise util.Abort(err[1])
         finally:
             fp.close()
             os.unlink(tempname)
 
     def stream_out(self):
         return self.do_cmd('stream_out')
 
 class httpsrepository(httprepository):
     def __init__(self, ui, path):
         if not has_https:
             raise util.Abort(_('Python support for SSL and HTTPS '
                                'is not installed'))
         httprepository.__init__(self, ui, path)
 
 def instance(ui, path, create):
     if create:
         raise util.Abort(_('cannot create new http repository'))
     if path.startswith('https:'):
         return httpsrepository(ui, path)
     return httprepository(ui, path)

mercurial/keepalive.py

@@ -1,579 +1,579 b''
 #   This library is free software; you can redistribute it and/or
 #   modify it under the terms of the GNU Lesser General Public
 #   License as published by the Free Software Foundation; either
 #   version 2.1 of the License, or (at your option) any later version.
 #
 #   This library is distributed in the hope that it will be useful,
 #   but WITHOUT ANY WARRANTY; without even the implied warranty of
 #   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 #   Lesser General Public License for more details.
 #
 #   You should have received a copy of the GNU Lesser General Public
 #   License along with this library; if not, write to the
 #      Free Software Foundation, Inc.,
 #      59 Temple Place, Suite 330,
 #      Boston, MA  02111-1307  USA
 
 # This file is part of urlgrabber, a high-level cross-protocol url-grabber
 # Copyright 2002-2004 Michael D. Stenner, Ryan Tomayko
 
 # Modified by Benoit Boissinot:
 #  - fix for digest auth (inspired from urllib2.py @ Python v2.4)
 
 """An HTTP handler for urllib2 that supports HTTP 1.1 and keepalive.
 
 >>> import urllib2
 >>> from keepalive import HTTPHandler
 >>> keepalive_handler = HTTPHandler()
 >>> opener = urllib2.build_opener(keepalive_handler)
 >>> urllib2.install_opener(opener)
 >>>
 >>> fo = urllib2.urlopen('http://www.python.org')
 
 If a connection to a given host is requested, and all of the existing
 connections are still in use, another connection will be opened.  If
 the handler tries to use an existing connection but it fails in some
 way, it will be closed and removed from the pool.
 
 To remove the handler, simply re-run build_opener with no arguments, and
 install that opener.
 
 You can explicitly close connections by using the close_connection()
 method of the returned file-like object (described below) or you can
 use the handler methods:
 
   close_connection(host)
   close_all()
   open_connections()
 
 NOTE: using the close_connection and close_all methods of the handler
 should be done with care when using multiple threads.
   * there is nothing that prevents another thread from creating new
     connections immediately after connections are closed
   * no checks are done to prevent in-use connections from being closed
 
 >>> keepalive_handler.close_all()
 
 EXTRA ATTRIBUTES AND METHODS
 
   Upon a status of 200, the object returned has a few additional
   attributes and methods, which should not be used if you want to
   remain consistent with the normal urllib2-returned objects:
 
     close_connection()  -  close the connection to the host
     readlines()         -  you know, readlines()
     status              -  the return status (ie 404)
     reason              -  english translation of status (ie 'File not found')
 
   If you want the best of both worlds, use this inside an
   AttributeError-catching try:
 
   >>> try: status = fo.status
   >>> except AttributeError: status = None
 
   Unfortunately, these are ONLY there if status == 200, so it's not
   easy to distinguish between non-200 responses.  The reason is that
   urllib2 tries to do clever things with error codes 301, 302, 401,
   and 407, and it wraps the object upon return.
 
   For python versions earlier than 2.4, you can avoid this fancy error
   handling by setting the module-level global HANDLE_ERRORS to zero.
   You see, prior to 2.4, it's the HTTP Handler's job to determine what
   to handle specially, and what to just pass up.  HANDLE_ERRORS == 0
   means "pass everything up".  In python 2.4, however, this job no
   longer belongs to the HTTP Handler and is now done by a NEW handler,
   HTTPErrorProcessor.  Here's the bottom line:
 
     python version < 2.4
         HANDLE_ERRORS == 1  (default) pass up 200, treat the rest as
                             errors
         HANDLE_ERRORS == 0  pass everything up, error processing is
                             left to the calling code
     python version >= 2.4
         HANDLE_ERRORS == 1  pass up 200, treat the rest as errors
         HANDLE_ERRORS == 0  (default) pass everything up, let the
                             other handlers (specifically,
                             HTTPErrorProcessor) decide what to do
 
   In practice, setting the variable either way makes little difference
   in python 2.4, so for the most consistent behavior across versions,
   you probably just want to use the defaults, which will give you
   exceptions on errors.
 
 """
 
 # $Id: keepalive.py,v 1.14 2006/04/04 21:00:32 mstenner Exp $
 
 import urllib2
 import httplib
 import socket
 import thread
 
 DEBUG = None
 
 import sys
 if sys.version_info < (2, 4): HANDLE_ERRORS = 1
 else: HANDLE_ERRORS = 0
 
 class ConnectionManager:
     """
     The connection manager must be able to:
       * keep track of all existing
       """
     def __init__(self):
         self._lock = thread.allocate_lock()
         self._hostmap = {} # map hosts to a list of connections
         self._connmap = {} # map connections to host
         self._readymap = {} # map connection to ready state
 
     def add(self, host, connection, ready):
         self._lock.acquire()
         try:
-            if not self._hostmap.has_key(host): self._hostmap[host] = []
+            if not host in self._hostmap: self._hostmap[host] = []
             self._hostmap[host].append(connection)
             self._connmap[connection] = host
             self._readymap[connection] = ready
         finally:
             self._lock.release()
 
     def remove(self, connection):
         self._lock.acquire()
         try:
             try:
                 host = self._connmap[connection]
             except KeyError:
                 pass
             else:
                 del self._connmap[connection]
                 del self._readymap[connection]
                 self._hostmap[host].remove(connection)
                 if not self._hostmap[host]: del self._hostmap[host]
         finally:
             self._lock.release()
 
     def set_ready(self, connection, ready):
         try: self._readymap[connection] = ready
         except KeyError: pass
 
     def get_ready_conn(self, host):
         conn = None
         self._lock.acquire()
         try:
-            if self._hostmap.has_key(host):
+            if host in self._hostmap:
                 for c in self._hostmap[host]:
                     if self._readymap[c]:
                         self._readymap[c] = 0
                         conn = c
                         break
         finally:
             self._lock.release()
         return conn
 
     def get_all(self, host=None):
         if host:
             return list(self._hostmap.get(host, []))
         else:
             return dict(self._hostmap)
 
 class HTTPHandler(urllib2.HTTPHandler):
     def __init__(self):
         self._cm = ConnectionManager()
 
     #### Connection Management
     def open_connections(self):
         """return a list of connected hosts and the number of connections
         to each.  [('foo.com:80', 2), ('bar.org', 1)]"""
         return [(host, len(li)) for (host, li) in self._cm.get_all().items()]
 
     def close_connection(self, host):
         """close connection(s) to <host>
         host is the host:port spec, as in 'www.cnn.com:8080' as passed in.
         no error occurs if there is no connection to that host."""
         for h in self._cm.get_all(host):
             self._cm.remove(h)
             h.close()
 
     def close_all(self):
         """close all open connections"""
         for host, conns in self._cm.get_all().items():
             for h in conns:
                 self._cm.remove(h)
                 h.close()
 
     def _request_closed(self, request, host, connection):
         """tells us that this request is now closed and the the
         connection is ready for another request"""
         self._cm.set_ready(connection, 1)
 
     def _remove_connection(self, host, connection, close=0):
         if close: connection.close()
         self._cm.remove(connection)
 
     #### Transaction Execution
     def http_open(self, req):
         return self.do_open(HTTPConnection, req)
 
     def do_open(self, http_class, req):
         host = req.get_host()
         if not host:
             raise urllib2.URLError('no host given')
 
         try:
             h = self._cm.get_ready_conn(host)
             while h:
                 r = self._reuse_connection(h, req, host)
 
                 # if this response is non-None, then it worked and we're
                 # done.  Break out, skipping the else block.
                 if r: break
 
                 # connection is bad - possibly closed by server
                 # discard it and ask for the next free connection
                 h.close()
                 self._cm.remove(h)
                 h = self._cm.get_ready_conn(host)
             else:
                 # no (working) free connections were found.  Create a new one.
                 h = http_class(host)
                 if DEBUG: DEBUG.info("creating new connection to %s (%d)",
                                      host, id(h))
                 self._cm.add(host, h, 0)
                 self._start_transaction(h, req)
                 r = h.getresponse()
         except (socket.error, httplib.HTTPException), err:
             raise urllib2.URLError(err)
 
         # if not a persistent connection, don't try to reuse it
         if r.will_close: self._cm.remove(h)
 
         if DEBUG: DEBUG.info("STATUS: %s, %s", r.status, r.reason)
         r._handler = self
         r._host = host
         r._url = req.get_full_url()
         r._connection = h
         r.code = r.status
         r.headers = r.msg
         r.msg = r.reason
 
         if r.status == 200 or not HANDLE_ERRORS:
             return r
         else:
             return self.parent.error('http', req, r,
                                      r.status, r.msg, r.headers)
 
     def _reuse_connection(self, h, req, host):
         """start the transaction with a re-used connection
         return a response object (r) upon success or None on failure.
         This DOES not close or remove bad connections in cases where
         it returns.  However, if an unexpected exception occurs, it
         will close and remove the connection before re-raising.
         """
         try:
             self._start_transaction(h, req)
             r = h.getresponse()
             # note: just because we got something back doesn't mean it
             # worked.  We'll check the version below, too.
         except (socket.error, httplib.HTTPException):
             r = None
         except:
             # adding this block just in case we've missed
             # something we will still raise the exception, but
             # lets try and close the connection and remove it
             # first.  We previously got into a nasty loop
             # where an exception was uncaught, and so the
             # connection stayed open.  On the next try, the
             # same exception was raised, etc.  The tradeoff is
             # that it's now possible this call will raise
             # a DIFFERENT exception
             if DEBUG: DEBUG.error("unexpected exception - closing " + \
                                   "connection to %s (%d)", host, id(h))
             self._cm.remove(h)
             h.close()
             raise
 
         if r is None or r.version == 9:
             # httplib falls back to assuming HTTP 0.9 if it gets a
             # bad header back.  This is most likely to happen if
             # the socket has been closed by the server since we
             # last used the connection.
             if DEBUG: DEBUG.info("failed to re-use connection to %s (%d)",
                                  host, id(h))
             r = None
         else:
             if DEBUG: DEBUG.info("re-using connection to %s (%d)", host, id(h))
 
         return r
 
     def _start_transaction(self, h, req):
         headers = req.headers.copy()
         body = req.data
         if sys.version_info >= (2, 4):
             headers.update(req.unredirected_hdrs)
         try:
             h.request(req.get_method(), req.get_selector(), body, headers)
         except socket.error, err: # XXX what error?
             raise urllib2.URLError(err)
 
 class HTTPResponse(httplib.HTTPResponse):
     # we need to subclass HTTPResponse in order to
     # 1) add readline() and readlines() methods
     # 2) add close_connection() methods
     # 3) add info() and geturl() methods
 
     # in order to add readline(), read must be modified to deal with a
     # buffer.  example: readline must read a buffer and then spit back
     # one line at a time.  The only real alternative is to read one
     # BYTE at a time (ick).  Once something has been read, it can't be
     # put back (ok, maybe it can, but that's even uglier than this),
     # so if you THEN do a normal read, you must first take stuff from
     # the buffer.
 
     # the read method wraps the original to accomodate buffering,
     # although read() never adds to the buffer.
     # Both readline and readlines have been stolen with almost no
     # modification from socket.py
 
 
     def __init__(self, sock, debuglevel=0, strict=0, method=None):
         if method: # the httplib in python 2.3 uses the method arg
             httplib.HTTPResponse.__init__(self, sock, debuglevel, method)
         else: # 2.2 doesn't
             httplib.HTTPResponse.__init__(self, sock, debuglevel)
         self.fileno = sock.fileno
         self.code = None
         self._rbuf = ''
         self._rbufsize = 8096
         self._handler = None # inserted by the handler later
         self._host = None    # (same)
         self._url = None     # (same)
         self._connection = None # (same)
 
     _raw_read = httplib.HTTPResponse.read
 
     def close(self):
         if self.fp:
             self.fp.close()
             self.fp = None
             if self._handler:
                 self._handler._request_closed(self, self._host,
                                               self._connection)
 
     def close_connection(self):
         self._handler._remove_connection(self._host, self._connection, close=1)
         self.close()
 
     def info(self):
         return self.headers
 
     def geturl(self):
         return self._url
 
     def read(self, amt=None):
         # the _rbuf test is only in this first if for speed.  It's not
         # logically necessary
         if self._rbuf and not amt is None:
             L = len(self._rbuf)
             if amt > L:
                 amt -= L
             else:
                 s = self._rbuf[:amt]
                 self._rbuf = self._rbuf[amt:]
                 return s
 
         s = self._rbuf + self._raw_read(amt)
         self._rbuf = ''
         return s
 
     def readline(self, limit=-1):
         data = ""
         i = self._rbuf.find('\n')
         while i < 0 and not (0 < limit <= len(self._rbuf)):
             new = self._raw_read(self._rbufsize)
             if not new: break
             i = new.find('\n')
             if i >= 0: i = i + len(self._rbuf)
             self._rbuf = self._rbuf + new
         if i < 0: i = len(self._rbuf)
         else: i = i+1
         if 0 <= limit < len(self._rbuf): i = limit
         data, self._rbuf = self._rbuf[:i], self._rbuf[i:]
         return data
 
     def readlines(self, sizehint = 0):
         total = 0
         list = []
         while 1:
             line = self.readline()
             if not line: break
             list.append(line)
             total += len(line)
             if sizehint and total >= sizehint:
                 break
         return list
 
 
 class HTTPConnection(httplib.HTTPConnection):
     # use the modified response class
     response_class = HTTPResponse
 
 #########################################################################
 #####   TEST FUNCTIONS
 #########################################################################
 
 def error_handler(url):
     global HANDLE_ERRORS
     orig = HANDLE_ERRORS
     keepalive_handler = HTTPHandler()
     opener = urllib2.build_opener(keepalive_handler)
     urllib2.install_opener(opener)
     pos = {0: 'off', 1: 'on'}
     for i in (0, 1):
         print "  fancy error handling %s (HANDLE_ERRORS = %i)" % (pos[i], i)
         HANDLE_ERRORS = i
         try:
             fo = urllib2.urlopen(url)
             foo = fo.read()
             fo.close()
             try: status, reason = fo.status, fo.reason
             except AttributeError: status, reason = None, None
         except IOError, e:
             print "  EXCEPTION: %s" % e
             raise
         else:
             print "  status = %s, reason = %s" % (status, reason)
     HANDLE_ERRORS = orig
     hosts = keepalive_handler.open_connections()
     print "open connections:", hosts
     keepalive_handler.close_all()
 
 def continuity(url):
     import md5
     format = '%25s: %s'
 
     # first fetch the file with the normal http handler
     opener = urllib2.build_opener()
     urllib2.install_opener(opener)
     fo = urllib2.urlopen(url)
     foo = fo.read()
     fo.close()
     m = md5.new(foo)
     print format % ('normal urllib', m.hexdigest())
 
     # now install the keepalive handler and try again
     opener = urllib2.build_opener(HTTPHandler())
     urllib2.install_opener(opener)
 
     fo = urllib2.urlopen(url)
     foo = fo.read()
     fo.close()
     m = md5.new(foo)
     print format % ('keepalive read', m.hexdigest())
 
     fo = urllib2.urlopen(url)
     foo = ''
     while 1:
         f = fo.readline()
         if f: foo = foo + f
         else: break
     fo.close()
     m = md5.new(foo)
     print format % ('keepalive readline', m.hexdigest())
 
 def comp(N, url):
     print '  making %i connections to:\n  %s' % (N, url)
 
     sys.stdout.write('  first using the normal urllib handlers')
     # first use normal opener
     opener = urllib2.build_opener()
     urllib2.install_opener(opener)
     t1 = fetch(N, url)
     print '  TIME: %.3f s' % t1
 
     sys.stdout.write('  now using the keepalive handler       ')
     # now install the keepalive handler and try again
     opener = urllib2.build_opener(HTTPHandler())
     urllib2.install_opener(opener)
     t2 = fetch(N, url)
     print '  TIME: %.3f s' % t2
     print '  improvement factor: %.2f' % (t1/t2, )
 
 def fetch(N, url, delay=0):
     import time
     lens = []
     starttime = time.time()
     for i in range(N):
         if delay and i > 0: time.sleep(delay)
         fo = urllib2.urlopen(url)
         foo = fo.read()
         fo.close()
         lens.append(len(foo))
     diff = time.time() - starttime
 
     j = 0
     for i in lens[1:]:
         j = j + 1
         if not i == lens[0]:
             print "WARNING: inconsistent length on read %i: %i" % (j, i)
 
     return diff
 
 def test_timeout(url):
     global DEBUG
     dbbackup = DEBUG
     class FakeLogger:
         def debug(self, msg, *args): print msg % args
         info = warning = error = debug
     DEBUG = FakeLogger()
     print "  fetching the file to establish a connection"
     fo = urllib2.urlopen(url)
     data1 = fo.read()
     fo.close()
 
     i = 20
     print "  waiting %i seconds for the server to close the connection" % i
     while i > 0:
         sys.stdout.write('\r  %2i' % i)
         sys.stdout.flush()
         time.sleep(1)
         i -= 1
     sys.stderr.write('\r')
 
     print "  fetching the file a second time"
     fo = urllib2.urlopen(url)
     data2 = fo.read()
     fo.close()
 
     if data1 == data2:
         print '  data are identical'
     else:
         print '  ERROR: DATA DIFFER'
 
     DEBUG = dbbackup
 
 
 def test(url, N=10):
     print "checking error hander (do this on a non-200)"
     try: error_handler(url)
     except IOError, e:
         print "exiting - exception will prevent further tests"
         sys.exit()
     print
     print "performing continuity test (making sure stuff isn't corrupted)"
     continuity(url)
     print
     print "performing speed comparison"
     comp(N, url)
     print
     print "performing dropped-connection check"
     test_timeout(url)
 
 if __name__ == '__main__':
     import time
     import sys
     try:
         N = int(sys.argv[1])
         url = sys.argv[2]
     except:
         print "%s <integer> <url>" % sys.argv[0]
     else:
         test(url, N)

mercurial/localrepo.py

@@ -1,2061 +1,2061 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, incorporated herein by reference.
 
 from node import *
 from i18n import _
 import repo, changegroup
 import changelog, dirstate, filelog, manifest, context, weakref
 import re, lock, transaction, tempfile, stat, errno, ui
 import os, revlog, time, util, extensions, hook
 
 class localrepository(repo.repository):
     capabilities = util.set(('lookup', 'changegroupsubset'))
     supported = ('revlogv1', 'store')
 
     def __init__(self, parentui, path=None, create=0):
         repo.repository.__init__(self)
         self.root = os.path.realpath(path)
         self.path = os.path.join(self.root, ".hg")
         self.origroot = path
         self.opener = util.opener(self.path)
         self.wopener = util.opener(self.root)
 
         if not os.path.isdir(self.path):
             if create:
                 if not os.path.exists(path):
                     os.mkdir(path)
                 os.mkdir(self.path)
                 requirements = ["revlogv1"]
                 if parentui.configbool('format', 'usestore', True):
                     os.mkdir(os.path.join(self.path, "store"))
                     requirements.append("store")
                     # create an invalid changelog
                     self.opener("00changelog.i", "a").write(
                         '\0\0\0\2' # represents revlogv2
                         ' dummy changelog to prevent using the old repo layout'
                     )
                 reqfile = self.opener("requires", "w")
                 for r in requirements:
                     reqfile.write("%s\n" % r)
                 reqfile.close()
             else:
                 raise repo.RepoError(_("repository %s not found") % path)
         elif create:
             raise repo.RepoError(_("repository %s already exists") % path)
         else:
             # find requirements
             try:
                 requirements = self.opener("requires").read().splitlines()
             except IOError, inst:
                 if inst.errno != errno.ENOENT:
                     raise
                 requirements = []
         # check them
         for r in requirements:
             if r not in self.supported:
                 raise repo.RepoError(_("requirement '%s' not supported") % r)
 
         # setup store
         if "store" in requirements:
             self.encodefn = util.encodefilename
             self.decodefn = util.decodefilename
             self.spath = os.path.join(self.path, "store")
         else:
             self.encodefn = lambda x: x
             self.decodefn = lambda x: x
             self.spath = self.path
         self.sopener = util.encodedopener(util.opener(self.spath),
                                           self.encodefn)
 
         self.ui = ui.ui(parentui=parentui)
         try:
             self.ui.readconfig(self.join("hgrc"), self.root)
             extensions.loadall(self.ui)
         except IOError:
             pass
 
         self.tagscache = None
         self._tagstypecache = None
         self.branchcache = None
         self.nodetagscache = None
         self.filterpats = {}
         self._transref = self._lockref = self._wlockref = None
 
     def __getattr__(self, name):
         if name == 'changelog':
             self.changelog = changelog.changelog(self.sopener)
             self.sopener.defversion = self.changelog.version
             return self.changelog
         if name == 'manifest':
             self.changelog
             self.manifest = manifest.manifest(self.sopener)
             return self.manifest
         if name == 'dirstate':
             self.dirstate = dirstate.dirstate(self.opener, self.ui, self.root)
             return self.dirstate
         else:
             raise AttributeError, name
 
     def url(self):
         return 'file:' + self.root
 
     def hook(self, name, throw=False, **args):
         return hook.hook(self.ui, self, name, throw, **args)
 
     tag_disallowed = ':\r\n'
 
     def _tag(self, name, node, message, local, user, date, parent=None,
              extra={}):
         use_dirstate = parent is None
 
         for c in self.tag_disallowed:
             if c in name:
                 raise util.Abort(_('%r cannot be used in a tag name') % c)
 
         self.hook('pretag', throw=True, node=hex(node), tag=name, local=local)
 
         def writetag(fp, name, munge, prevtags):
             if prevtags and prevtags[-1] != '\n':
                 fp.write('\n')
             fp.write('%s %s\n' % (hex(node), munge and munge(name) or name))
             fp.close()
 
         prevtags = ''
         if local:
             try:
                 fp = self.opener('localtags', 'r+')
             except IOError, err:
                 fp = self.opener('localtags', 'a')
             else:
                 prevtags = fp.read()
 
             # local tags are stored in the current charset
             writetag(fp, name, None, prevtags)
             self.hook('tag', node=hex(node), tag=name, local=local)
             return
 
         if use_dirstate:
             try:
                 fp = self.wfile('.hgtags', 'rb+')
             except IOError, err:
                 fp = self.wfile('.hgtags', 'ab')
             else:
                 prevtags = fp.read()
         else:
             try:
                 prevtags = self.filectx('.hgtags', parent).data()
             except revlog.LookupError:
                 pass
             fp = self.wfile('.hgtags', 'wb')
             if prevtags:
                 fp.write(prevtags)
 
         # committed tags are stored in UTF-8
         writetag(fp, name, util.fromlocal, prevtags)
 
         if use_dirstate and '.hgtags' not in self.dirstate:
             self.add(['.hgtags'])
 
         tagnode = self.commit(['.hgtags'], message, user, date, p1=parent,
                               extra=extra)
 
         self.hook('tag', node=hex(node), tag=name, local=local)
 
         return tagnode
 
     def tag(self, name, node, message, local, user, date):
         '''tag a revision with a symbolic name.
 
         if local is True, the tag is stored in a per-repository file.
         otherwise, it is stored in the .hgtags file, and a new
         changeset is committed with the change.
 
         keyword arguments:
 
         local: whether to store tag 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'''
 
         for x in self.status()[:5]:
             if '.hgtags' in x:
                 raise util.Abort(_('working copy of .hgtags is changed '
                                    '(please commit .hgtags manually)'))
 
 
         self._tag(name, node, message, local, user, date)
 
     def tags(self):
         '''return a mapping of tag to node'''
         if self.tagscache:
             return self.tagscache
 
         globaltags = {}
         tagtypes = {}
 
         def readtags(lines, fn, tagtype):
             filetags = {}
             count = 0
 
             def warn(msg):
                 self.ui.warn(_("%s, line %s: %s\n") % (fn, count, msg))
 
             for l in lines:
                 count += 1
                 if not l:
                     continue
                 s = l.split(" ", 1)
                 if len(s) != 2:
                     warn(_("cannot parse entry"))
                     continue
                 node, key = s
                 key = util.tolocal(key.strip()) # stored in UTF-8
                 try:
                     bin_n = bin(node)
                 except TypeError:
                     warn(_("node '%s' is not well formed") % node)
                     continue
                 if bin_n not in self.changelog.nodemap:
                     warn(_("tag '%s' refers to unknown node") % key)
                     continue
 
                 h = []
                 if key in filetags:
                     n, h = filetags[key]
                     h.append(n)
                 filetags[key] = (bin_n, h)
 
             for k, nh in filetags.items():
                 if k not in globaltags:
                     globaltags[k] = nh
                     tagtypes[k] = tagtype
                     continue
 
                 # we prefer the global tag if:
                 #  it supercedes us OR
                 #  mutual supercedes and it has a higher rank
                 # otherwise we win because we're tip-most
                 an, ah = nh
                 bn, bh = globaltags[k]
                 if (bn != an and an in bh and
                     (bn not in ah or len(bh) > len(ah))):
                     an = bn
                 ah.extend([n for n in bh if n not in ah])
                 globaltags[k] = an, ah
                 tagtypes[k] = tagtype
 
         # read the tags file from each head, ending with the tip
         f = None
         for rev, node, fnode in self._hgtagsnodes():
             f = (f and f.filectx(fnode) or
                  self.filectx('.hgtags', fileid=fnode))
             readtags(f.data().splitlines(), f, "global")
 
         try:
             data = util.fromlocal(self.opener("localtags").read())
             # localtags are stored in the local character set
             # while the internal tag table is stored in UTF-8
             readtags(data.splitlines(), "localtags", "local")
         except IOError:
             pass
 
         self.tagscache = {}
         self._tagstypecache = {}
         for k,nh in globaltags.items():
             n = nh[0]
             if n != nullid:
                 self.tagscache[k] = n
                 self._tagstypecache[k] = tagtypes[k]
         self.tagscache['tip'] = self.changelog.tip()
 
         return self.tagscache
 
     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
         '''
 
         self.tags()
 
         return self._tagstypecache.get(tagname)
 
     def _hgtagsnodes(self):
         heads = self.heads()
         heads.reverse()
         last = {}
         ret = []
         for node in heads:
             c = self.changectx(node)
             rev = c.rev()
             try:
                 fnode = c.filenode('.hgtags')
             except revlog.LookupError:
                 continue
             ret.append((rev, node, fnode))
             if fnode in last:
                 ret[last[fnode]] = None
             last[fnode] = len(ret) - 1
         return [item for item in ret if item]
 
     def tagslist(self):
         '''return a list of tags ordered by revision'''
         l = []
         for t, n in self.tags().items():
             try:
                 r = self.changelog.rev(n)
             except:
                 r = -2 # sort to the beginning of the list if unknown
             l.append((r, t, n))
         l.sort()
         return [(t, n) for r, t, n in l]
 
     def nodetags(self, node):
         '''return the tags associated with a node'''
         if not self.nodetagscache:
             self.nodetagscache = {}
             for t, n in self.tags().items():
                 self.nodetagscache.setdefault(n, []).append(t)
         return self.nodetagscache.get(node, [])
 
     def _branchtags(self):
         partial, last, lrev = self._readbranchcache()
 
         tiprev = self.changelog.count() - 1
         if lrev != tiprev:
             self._updatebranchcache(partial, lrev+1, tiprev+1)
             self._writebranchcache(partial, self.changelog.tip(), tiprev)
 
         return partial
 
     def branchtags(self):
         if self.branchcache is not None:
             return self.branchcache
 
         self.branchcache = {} # avoid recursion in changectx
         partial = self._branchtags()
 
         # the branch cache is stored on disk as UTF-8, but in the local
         # charset internally
         for k, v in partial.items():
             self.branchcache[util.tolocal(k)] = v
         return self.branchcache
 
     def _readbranchcache(self):
         partial = {}
         try:
             f = self.opener("branch.cache")
             lines = f.read().split('\n')
             f.close()
         except (IOError, OSError):
             return {}, nullid, nullrev
 
         try:
             last, lrev = lines.pop(0).split(" ", 1)
             last, lrev = bin(last), int(lrev)
             if not (lrev < self.changelog.count() and
                     self.changelog.node(lrev) == last): # sanity check
                 # invalidate the cache
                 raise ValueError('Invalid branch cache: unknown tip')
             for l in lines:
                 if not l: continue
                 node, label = l.split(" ", 1)
                 partial[label.strip()] = bin(node)
         except (KeyboardInterrupt, util.SignalInterrupt):
             raise
         except Exception, inst:
             if self.ui.debugflag:
                 self.ui.warn(str(inst), '\n')
             partial, last, lrev = {}, nullid, nullrev
         return partial, last, lrev
 
     def _writebranchcache(self, branches, tip, tiprev):
         try:
             f = self.opener("branch.cache", "w", atomictemp=True)
             f.write("%s %s\n" % (hex(tip), tiprev))
             for label, node in branches.iteritems():
                 f.write("%s %s\n" % (hex(node), label))
             f.rename()
         except (IOError, OSError):
             pass
 
     def _updatebranchcache(self, partial, start, end):
         for r in xrange(start, end):
             c = self.changectx(r)
             b = c.branch()
             partial[b] = c.node()
 
     def lookup(self, key):
         if key == '.':
             key, second = self.dirstate.parents()
             if key == nullid:
                 raise repo.RepoError(_("no revision checked out"))
             if second != nullid:
                 self.ui.warn(_("warning: working directory has two parents, "
                                "tag '.' uses the first\n"))
         elif key == 'null':
             return nullid
         n = self.changelog._match(key)
         if n:
             return n
         if key in self.tags():
             return self.tags()[key]
         if key in self.branchtags():
             return self.branchtags()[key]
         n = self.changelog._partialmatch(key)
         if n:
             return n
         try:
             if len(key) == 20:
                 key = hex(key)
         except:
             pass
         raise repo.RepoError(_("unknown revision '%s'") % key)
 
     def dev(self):
         return os.lstat(self.path).st_dev
 
     def local(self):
         return True
 
     def join(self, f):
         return os.path.join(self.path, f)
 
     def sjoin(self, f):
         f = self.encodefn(f)
         return os.path.join(self.spath, 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=None):
         return context.changectx(self, changeid)
 
     def workingctx(self):
         return context.workingctx(self)
 
     def parents(self, changeid=None):
         '''
         get list of changectxs for parents of changeid or working directory
         '''
         if changeid is None:
             pl = self.dirstate.parents()
         else:
             n = self.changelog.lookup(changeid)
             pl = self.changelog.parents(n)
         if pl[1] == nullid:
             return [self.changectx(pl[0])]
         return [self.changectx(pl[0]), self.changectx(pl[1])]
 
     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 os.path.islink(self.wjoin(f))
 
     def _filter(self, filter, filename, data):
         if filter not in self.filterpats:
             l = []
             for pat, cmd in self.ui.configitems(filter):
                 mf = util.matcher(self.root, "", [pat], [], [])[1]
                 l.append((mf, cmd))
             self.filterpats[filter] = l
 
         for mf, cmd in self.filterpats[filter]:
             if mf(filename):
                 self.ui.debug(_("filtering %s through %s\n") % (filename, cmd))
                 data = util.filter(data, cmd)
                 break
 
         return data
 
     def wread(self, filename):
         if self._link(filename):
             data = os.readlink(self.wjoin(filename))
         else:
             data = self.wopener(filename, 'r').read()
         return self._filter("encode", filename, data)
 
     def wwrite(self, filename, data, flags):
         data = self._filter("decode", filename, data)
         try:
             os.unlink(self.wjoin(filename))
         except OSError:
             pass
         self.wopener(filename, 'w').write(data)
         util.set_flags(self.wjoin(filename), flags)
 
     def wwritedata(self, filename, data):
         return self._filter("decode", filename, data)
 
     def transaction(self):
         if self._transref and self._transref():
             return self._transref().nest()
 
         # abort here if the journal already exists
         if os.path.exists(self.sjoin("journal")):
             raise repo.RepoError(_("journal already exists - run hg recover"))
 
         # save dirstate for rollback
         try:
             ds = self.opener("dirstate").read()
         except IOError:
             ds = ""
         self.opener("journal.dirstate", "w").write(ds)
         self.opener("journal.branch", "w").write(self.dirstate.branch())
 
         renames = [(self.sjoin("journal"), self.sjoin("undo")),
                    (self.join("journal.dirstate"), self.join("undo.dirstate")),
                    (self.join("journal.branch"), self.join("undo.branch"))]
         tr = transaction.transaction(self.ui.warn, self.sopener,
                                        self.sjoin("journal"),
                                        aftertrans(renames))
         self._transref = weakref.ref(tr)
         return tr
 
     def recover(self):
         l = self.lock()
         try:
             if os.path.exists(self.sjoin("journal")):
                 self.ui.status(_("rolling back interrupted transaction\n"))
                 transaction.rollback(self.sopener, self.sjoin("journal"))
                 self.invalidate()
                 return True
             else:
                 self.ui.warn(_("no interrupted transaction available\n"))
                 return False
         finally:
             del l
 
     def rollback(self):
         wlock = lock = None
         try:
             wlock = self.wlock()
             lock = self.lock()
             if os.path.exists(self.sjoin("undo")):
                 self.ui.status(_("rolling back last transaction\n"))
                 transaction.rollback(self.sopener, self.sjoin("undo"))
                 util.rename(self.join("undo.dirstate"), self.join("dirstate"))
                 branch = self.opener("undo.branch").read()
                 self.dirstate.setbranch(branch)
                 self.invalidate()
                 self.dirstate.invalidate()
             else:
                 self.ui.warn(_("no rollback information available\n"))
         finally:
             del lock, wlock
 
     def invalidate(self):
         for a in "changelog manifest".split():
             if hasattr(self, a):
                 self.__delattr__(a)
         self.tagscache = None
         self._tagstypecache = None
         self.nodetagscache = None
 
     def _lock(self, lockname, wait, releasefn, acquirefn, desc):
         try:
             l = lock.lock(lockname, 0, releasefn, desc=desc)
         except lock.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 lock(self, wait=True):
         if self._lockref and self._lockref():
             return self._lockref()
 
         l = self._lock(self.sjoin("lock"), wait, None, self.invalidate,
                        _('repository %s') % self.origroot)
         self._lockref = weakref.ref(l)
         return l
 
     def wlock(self, wait=True):
         if self._wlockref and self._wlockref():
             return self._wlockref()
 
         l = self._lock(self.join("wlock"), wait, self.dirstate.write,
                        self.dirstate.invalidate, _('working directory of %s') %
                        self.origroot)
         self._wlockref = weakref.ref(l)
         return l
 
     def filecommit(self, fn, manifest1, manifest2, linkrev, tr, changelist):
         """
         commit an individual file as part of a larger transaction
         """
 
         t = self.wread(fn)
         fl = self.file(fn)
         fp1 = manifest1.get(fn, nullid)
         fp2 = manifest2.get(fn, nullid)
 
         meta = {}
         cp = self.dirstate.copied(fn)
         if cp:
             # 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
             #
             meta["copy"] = cp
             if not manifest2: # not a branch merge
                 meta["copyrev"] = hex(manifest1.get(cp, nullid))
                 fp2 = nullid
             elif fp2 != nullid: # copied on remote side
                 meta["copyrev"] = hex(manifest1.get(cp, nullid))
             elif fp1 != nullid: # copied on local side, reversed
                 meta["copyrev"] = hex(manifest2.get(cp))
                 fp2 = fp1
             elif cp in manifest2: # directory rename on local side
                 meta["copyrev"] = hex(manifest2[cp])
             else: # directory rename on remote side
                 meta["copyrev"] = hex(manifest1.get(cp, nullid))
             self.ui.debug(_(" %s: copy %s:%s\n") %
                           (fn, cp, meta["copyrev"]))
             fp1 = nullid
         elif fp2 != nullid:
             # is one parent an ancestor of the other?
             fpa = fl.ancestor(fp1, fp2)
             if fpa == fp1:
                 fp1, fp2 = fp2, nullid
             elif fpa == fp2:
                 fp2 = nullid
 
         # is the file unmodified from the parent? report existing entry
         if fp2 == nullid and not fl.cmp(fp1, t) and not meta:
             return fp1
 
         changelist.append(fn)
         return fl.add(t, meta, tr, linkrev, fp1, fp2)
 
     def rawcommit(self, files, text, user, date, p1=None, p2=None, extra={}):
         if p1 is None:
             p1, p2 = self.dirstate.parents()
         return self.commit(files=files, text=text, user=user, date=date,
                            p1=p1, p2=p2, extra=extra, empty_ok=True)
 
     def commit(self, files=None, text="", user=None, date=None,
                match=util.always, force=False, force_editor=False,
                p1=None, p2=None, extra={}, empty_ok=False):
         wlock = lock = tr = None
         valid = 0 # don't save the dirstate if this isn't set
         if files:
             files = util.unique(files)
         try:
             commit = []
             remove = []
             changed = []
             use_dirstate = (p1 is None) # not rawcommit
             extra = extra.copy()
 
             if use_dirstate:
                 if files:
                     for f in files:
                         s = self.dirstate[f]
                         if s in 'nma':
                             commit.append(f)
                         elif s == 'r':
                             remove.append(f)
                         else:
                             self.ui.warn(_("%s not tracked!\n") % f)
                 else:
                     changes = self.status(match=match)[:5]
                     modified, added, removed, deleted, unknown = changes
                     commit = modified + added
                     remove = removed
             else:
                 commit = files
 
             if use_dirstate:
                 p1, p2 = self.dirstate.parents()
                 update_dirstate = True
             else:
                 p1, p2 = p1, p2 or nullid
                 update_dirstate = (self.dirstate.parents()[0] == p1)
 
             c1 = self.changelog.read(p1)
             c2 = self.changelog.read(p2)
             m1 = self.manifest.read(c1[0]).copy()
             m2 = self.manifest.read(c2[0])
 
             if use_dirstate:
                 branchname = self.workingctx().branch()
                 try:
                     branchname = branchname.decode('UTF-8').encode('UTF-8')
                 except UnicodeDecodeError:
                     raise util.Abort(_('branch name not in UTF-8!'))
             else:
                 branchname = ""
 
             if use_dirstate:
                 oldname = c1[5].get("branch") # stored in UTF-8
                 if (not commit and not remove and not force and p2 == nullid
                     and branchname == oldname):
                     self.ui.status(_("nothing changed\n"))
                     return None
 
             xp1 = hex(p1)
             if p2 == nullid: xp2 = ''
             else: xp2 = hex(p2)
 
             self.hook("precommit", throw=True, parent1=xp1, parent2=xp2)
 
             wlock = self.wlock()
             lock = self.lock()
             tr = self.transaction()
             trp = weakref.proxy(tr)
 
             # check in files
             new = {}
             linkrev = self.changelog.count()
             commit.sort()
             is_exec = util.execfunc(self.root, m1.execf)
             is_link = util.linkfunc(self.root, m1.linkf)
             for f in commit:
                 self.ui.note(f + "\n")
                 try:
                     new[f] = self.filecommit(f, m1, m2, linkrev, trp, changed)
                     new_exec = is_exec(f)
                     new_link = is_link(f)
                     if ((not changed or changed[-1] != f) and
                         m2.get(f) != new[f]):
                         # mention the file in the changelog if some
                         # flag changed, even if there was no content
                         # change.
                         old_exec = m1.execf(f)
                         old_link = m1.linkf(f)
                         if old_exec != new_exec or old_link != new_link:
                             changed.append(f)
                     m1.set(f, new_exec, new_link)
                     if use_dirstate:
                         self.dirstate.normal(f)
 
                 except (OSError, IOError):
                     if use_dirstate:
                         self.ui.warn(_("trouble committing %s!\n") % f)
                         raise
                     else:
                         remove.append(f)
 
             # update manifest
             m1.update(new)
             remove.sort()
             removed = []
 
             for f in remove:
                 if f in m1:
                     del m1[f]
                     removed.append(f)
                 elif f in m2:
                     removed.append(f)
             mn = self.manifest.add(m1, trp, linkrev, c1[0], c2[0],
                                    (new, removed))
 
             # add changeset
             new = new.keys()
             new.sort()
 
             user = user or self.ui.username()
             if (not empty_ok and not text) or force_editor:
                 edittext = []
                 if text:
                     edittext.append(text)
                 edittext.append("")
                 edittext.append(_("HG: Enter commit message."
                                   "  Lines beginning with 'HG:' are removed."))
                 edittext.append("HG: --")
                 edittext.append("HG: user: %s" % user)
                 if p2 != nullid:
                     edittext.append("HG: branch merge")
                 if branchname:
                     edittext.append("HG: branch '%s'" % util.tolocal(branchname))
                 edittext.extend(["HG: changed %s" % f for f in changed])
                 edittext.extend(["HG: removed %s" % f for f in removed])
                 if not changed and not remove:
                     edittext.append("HG: no files changed")
                 edittext.append("")
                 # run editor in the repository root
                 olddir = os.getcwd()
                 os.chdir(self.root)
                 text = self.ui.edit("\n".join(edittext), user)
                 os.chdir(olddir)
 
             if branchname:
                 extra["branch"] = branchname
 
             if use_dirstate:
                 lines = [line.rstrip() for line in text.rstrip().splitlines()]
                 while lines and not lines[0]:
                     del lines[0]
                 if not lines:
                     raise util.Abort(_("empty commit message"))
                 text = '\n'.join(lines)
 
             n = self.changelog.add(mn, changed + removed, text, trp, p1, p2,
                                    user, date, extra)
             self.hook('pretxncommit', throw=True, node=hex(n), parent1=xp1,
                       parent2=xp2)
             tr.close()
 
             if self.branchcache and "branch" in extra:
                 self.branchcache[util.tolocal(extra["branch"])] = n
 
             if use_dirstate or update_dirstate:
                 self.dirstate.setparents(n)
                 if use_dirstate:
                     for f in removed:
                         self.dirstate.forget(f)
             valid = 1 # our dirstate updates are complete
 
             self.hook("commit", node=hex(n), parent1=xp1, parent2=xp2)
             return n
         finally:
             if not valid: # don't save our updated dirstate
                 self.dirstate.invalidate()
             del tr, lock, wlock
 
     def walk(self, node=None, files=[], match=util.always, badmatch=None):
         '''
         walk recursively through the directory tree or a given
         changeset, finding all files matched by the match
         function
 
         results are yielded in a tuple (src, filename), where src
         is one of:
         'f' the file was found in the directory tree
         'm' the file was only in the dirstate and not in the tree
         'b' file was not found and matched badmatch
         '''
 
         if node:
             fdict = dict.fromkeys(files)
             # for dirstate.walk, files=['.'] means "walk the whole tree".
             # follow that here, too
             fdict.pop('.', None)
             mdict = self.manifest.read(self.changelog.read(node)[0])
             mfiles = mdict.keys()
             mfiles.sort()
             for fn in mfiles:
                 for ffn in fdict:
                     # match if the file is the exact name or a directory
                     if ffn == fn or fn.startswith("%s/" % ffn):
                         del fdict[ffn]
                         break
                 if match(fn):
                     yield 'm', fn
             ffiles = fdict.keys()
             ffiles.sort()
             for fn in ffiles:
                 if badmatch and badmatch(fn):
                     if match(fn):
                         yield 'b', fn
                 else:
                     self.ui.warn(_('%s: No such file in rev %s\n')
                                  % (self.pathto(fn), short(node)))
         else:
             for src, fn in self.dirstate.walk(files, match, badmatch=badmatch):
                 yield src, fn
 
     def status(self, node1=None, node2=None, files=[], match=util.always,
                list_ignored=False, list_clean=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 fcmp(fn, getnode):
             t1 = self.wread(fn)
             return self.file(fn).cmp(getnode(fn), t1)
 
         def mfmatches(node):
             change = self.changelog.read(node)
             mf = self.manifest.read(change[0]).copy()
             for fn in mf.keys():
                 if not match(fn):
                     del mf[fn]
             return mf
 
         modified, added, removed, deleted, unknown = [], [], [], [], []
         ignored, clean = [], []
 
         compareworking = False
         if not node1 or (not node2 and node1 == self.dirstate.parents()[0]):
             compareworking = True
 
         if not compareworking:
             # read the manifest from node1 before the manifest from node2,
             # so that we'll hit the manifest cache if we're going through
             # all the revisions in parent->child order.
             mf1 = mfmatches(node1)
 
         # are we comparing the working directory?
         if not node2:
             (lookup, modified, added, removed, deleted, unknown,
              ignored, clean) = self.dirstate.status(files, match,
                                                     list_ignored, list_clean)
 
             # are we comparing working dir against its parent?
             if compareworking:
                 if lookup:
                     fixup = []
                     # do a full compare of any files that might have changed
                     ctx = self.changectx()
                     for f in lookup:
                         if f not in ctx or ctx[f].cmp(self.wread(f)):
                             modified.append(f)
                         else:
                             fixup.append(f)
                             if list_clean:
                                 clean.append(f)
 
                     # update dirstate for files that are actually clean
                     if fixup:
                         wlock = None
                         try:
                             try:
                                 wlock = self.wlock(False)
                             except lock.LockException:
                                 pass
                             if wlock:
                                 for f in fixup:
                                     self.dirstate.normal(f)
                         finally:
                             del wlock
             else:
                 # we are comparing working dir against non-parent
                 # generate a pseudo-manifest for the working dir
                 # XXX: create it in dirstate.py ?
                 mf2 = mfmatches(self.dirstate.parents()[0])
                 is_exec = util.execfunc(self.root, mf2.execf)
                 is_link = util.linkfunc(self.root, mf2.linkf)
                 for f in lookup + modified + added:
                     mf2[f] = ""
                     mf2.set(f, is_exec(f), is_link(f))
                 for f in removed:
                     if f in mf2:
                         del mf2[f]
 
         else:
             # we are comparing two revisions
             mf2 = mfmatches(node2)
 
         if not compareworking:
             # flush lists from dirstate before comparing manifests
             modified, added, clean = [], [], []
 
             # make sure to sort the files so we talk to the disk in a
             # reasonable order
             mf2keys = mf2.keys()
             mf2keys.sort()
             getnode = lambda fn: mf1.get(fn, nullid)
             for fn in mf2keys:
-                if mf1.has_key(fn):
+                if fn in mf1:
                     if (mf1.flags(fn) != mf2.flags(fn) or
                         (mf1[fn] != mf2[fn] and
                          (mf2[fn] != "" or fcmp(fn, getnode)))):
                         modified.append(fn)
                     elif list_clean:
                         clean.append(fn)
                     del mf1[fn]
                 else:
                     added.append(fn)
 
             removed = mf1.keys()
 
         # sort and return results:
         for l in modified, added, removed, deleted, unknown, ignored, clean:
             l.sort()
         return (modified, added, removed, deleted, unknown, ignored, clean)
 
     def add(self, list):
         wlock = self.wlock()
         try:
             rejected = []
             for f in list:
                 p = self.wjoin(f)
                 try:
                     st = os.lstat(p)
                 except:
                     self.ui.warn(_("%s does not exist!\n") % f)
                     rejected.append(f)
                     continue
                 if st.st_size > 10000000:
                     self.ui.warn(_("%s: files over 10MB may cause memory and"
                                    " performance problems\n"
                                    "(use 'hg revert %s' to unadd the file)\n")
                                    % (f, f))
                 if not (stat.S_ISREG(st.st_mode) or stat.S_ISLNK(st.st_mode)):
                     self.ui.warn(_("%s not added: only files and symlinks "
                                    "supported currently\n") % f)
                     rejected.append(p)
                 elif self.dirstate[f] in 'amn':
                     self.ui.warn(_("%s already tracked!\n") % f)
                 elif self.dirstate[f] == 'r':
                     self.dirstate.normallookup(f)
                 else:
                     self.dirstate.add(f)
             return rejected
         finally:
             del wlock
 
     def forget(self, list):
         wlock = self.wlock()
         try:
             for f in list:
                 if self.dirstate[f] != 'a':
                     self.ui.warn(_("%s not added!\n") % f)
                 else:
                     self.dirstate.forget(f)
         finally:
             del wlock
 
     def remove(self, list, unlink=False):
         wlock = None
         try:
             if unlink:
                 for f in list:
                     try:
                         util.unlink(self.wjoin(f))
                     except OSError, inst:
                         if inst.errno != errno.ENOENT:
                             raise
             wlock = self.wlock()
             for f in list:
                 if unlink and os.path.exists(self.wjoin(f)):
                     self.ui.warn(_("%s still exists!\n") % f)
                 elif self.dirstate[f] == 'a':
                     self.dirstate.forget(f)
                 elif f not in self.dirstate:
                     self.ui.warn(_("%s not tracked!\n") % f)
                 else:
                     self.dirstate.remove(f)
         finally:
             del wlock
 
     def undelete(self, list):
         wlock = None
         try:
             manifests = [self.manifest.read(self.changelog.read(p)[0])
                          for p in self.dirstate.parents() if p != nullid]
             wlock = self.wlock()
             for f in list:
                 if self.dirstate[f] != 'r':
                     self.ui.warn("%s not removed!\n" % f)
                 else:
                     m = f in manifests[0] and manifests[0] or manifests[1]
                     t = self.file(f).read(m[f])
                     self.wwrite(f, t, m.flags(f))
                     self.dirstate.normal(f)
         finally:
             del wlock
 
     def copy(self, source, dest):
         wlock = None
         try:
             p = self.wjoin(dest)
             if not (os.path.exists(p) or os.path.islink(p)):
                 self.ui.warn(_("%s does not exist!\n") % dest)
             elif not (os.path.isfile(p) or os.path.islink(p)):
                 self.ui.warn(_("copy failed: %s is not a file or a "
                                "symbolic link\n") % dest)
             else:
                 wlock = self.wlock()
                 if dest not in self.dirstate:
                     self.dirstate.add(dest)
                 self.dirstate.copy(source, dest)
         finally:
             del wlock
 
     def heads(self, start=None):
         heads = self.changelog.heads(start)
         # sort the output in rev descending order
         heads = [(-self.changelog.rev(h), h) for h in heads]
         heads.sort()
         return [n for (r, n) in heads]
 
     def branchheads(self, branch, start=None):
         branches = self.branchtags()
         if branch not in branches:
             return []
         # The basic algorithm is this:
         #
         # Start from the branch tip since there are no later revisions that can
         # possibly be in this branch, and the tip is a guaranteed head.
         #
         # Remember the tip's parents as the first ancestors, since these by
         # definition are not heads.
         #
         # Step backwards from the brach tip through all the revisions. We are
         # guaranteed by the rules of Mercurial that we will now be visiting the
         # nodes in reverse topological order (children before parents).
         #
         # If a revision is one of the ancestors of a head then we can toss it
         # out of the ancestors set (we've already found it and won't be
         # visiting it again) and put its parents in the ancestors set.
         #
         # Otherwise, if a revision is in the branch it's another head, since it
         # wasn't in the ancestor list of an existing head.  So add it to the
         # head list, and add its parents to the ancestor list.
         #
         # If it is not in the branch ignore it.
         #
         # Once we have a list of heads, use nodesbetween to filter out all the
         # heads that cannot be reached from startrev.  There may be a more
         # efficient way to do this as part of the previous algorithm.
 
         set = util.set
         heads = [self.changelog.rev(branches[branch])]
         # Don't care if ancestors contains nullrev or not.
         ancestors = set(self.changelog.parentrevs(heads[0]))
         for rev in xrange(heads[0] - 1, nullrev, -1):
             if rev in ancestors:
                 ancestors.update(self.changelog.parentrevs(rev))
                 ancestors.remove(rev)
             elif self.changectx(rev).branch() == branch:
                 heads.append(rev)
                 ancestors.update(self.changelog.parentrevs(rev))
         heads = [self.changelog.node(rev) for rev in heads]
         if start is not None:
             heads = self.changelog.nodesbetween([start], heads)[2]
         return heads
 
     def branches(self, nodes):
         if not nodes:
             nodes = [self.changelog.tip()]
         b = []
         for n in nodes:
             t = n
             while 1:
                 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:
                 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 findincoming(self, remote, base=None, heads=None, force=False):
         """Return list of roots of the subsets of missing nodes from remote
 
         If base dict is specified, assume that these nodes and their parents
         exist on the remote side and that no child of a node of base exists
         in both remote and self.
         Furthermore base will be updated to include the nodes that exists
         in self and remote but no children exists in self and remote.
         If a list of heads is specified, return only nodes which are heads
         or ancestors of these heads.
 
         All the ancestors of base are in self and in remote.
         All the descendants of the list returned are missing in self.
         (and so we know that the rest of the nodes are missing in remote, see
         outgoing)
         """
         m = self.changelog.nodemap
         search = []
         fetch = {}
         seen = {}
         seenbranch = {}
         if base == None:
             base = {}
 
         if not heads:
             heads = remote.heads()
 
         if self.changelog.tip() == nullid:
             base[nullid] = 1
             if heads != [nullid]:
                 return [nullid]
             return []
 
         # assume we're closer to the tip than the root
         # and start by examining the heads
         self.ui.status(_("searching for changes\n"))
 
         unknown = []
         for h in heads:
             if h not in m:
                 unknown.append(h)
             else:
                 base[h] = 1
 
         if not unknown:
             return []
 
         req = dict.fromkeys(unknown)
         reqcnt = 0
 
         # search through remote branches
         # a 'branch' here is a linear segment of history, with four parts:
         # head, root, first parent, second parent
         # (a branch always has two parents (or none) by definition)
         unknown = remote.branches(unknown)
         while unknown:
             r = []
             while unknown:
                 n = unknown.pop(0)
                 if n[0] in seen:
                     continue
 
                 self.ui.debug(_("examining %s:%s\n")
                               % (short(n[0]), short(n[1])))
                 if n[0] == nullid: # found the end of the branch
                     pass
                 elif n in seenbranch:
                     self.ui.debug(_("branch already found\n"))
                     continue
                 elif n[1] and n[1] in m: # do we know the base?
                     self.ui.debug(_("found incomplete branch %s:%s\n")
                                   % (short(n[0]), short(n[1])))
                     search.append(n) # schedule branch range for scanning
                     seenbranch[n] = 1
                 else:
                     if n[1] not in seen and n[1] not in fetch:
                         if n[2] in m and n[3] in m:
                             self.ui.debug(_("found new changeset %s\n") %
                                           short(n[1]))
                             fetch[n[1]] = 1 # earliest unknown
                         for p in n[2:4]:
                             if p in m:
                                 base[p] = 1 # latest known
 
                     for p in n[2:4]:
                         if p not in req and p not in m:
                             r.append(p)
                             req[p] = 1
                 seen[n[0]] = 1
 
             if r:
                 reqcnt += 1
                 self.ui.debug(_("request %d: %s\n") %
                             (reqcnt, " ".join(map(short, r))))
                 for p in xrange(0, len(r), 10):
                     for b in remote.branches(r[p:p+10]):
                         self.ui.debug(_("received %s:%s\n") %
                                       (short(b[0]), short(b[1])))
                         unknown.append(b)
 
         # do binary search on the branches we found
         while search:
             n = search.pop(0)
             reqcnt += 1
             l = remote.between([(n[0], n[1])])[0]
             l.append(n[1])
             p = n[0]
             f = 1
             for i in l:
                 self.ui.debug(_("narrowing %d:%d %s\n") % (f, len(l), short(i)))
                 if i in m:
                     if f <= 2:
                         self.ui.debug(_("found new branch changeset %s\n") %
                                           short(p))
                         fetch[p] = 1
                         base[i] = 1
                     else:
                         self.ui.debug(_("narrowed branch search to %s:%s\n")
                                       % (short(p), short(i)))
                         search.append((p, i))
                     break
                 p, f = i, f * 2
 
         # sanity check our fetch list
         for f in fetch.keys():
             if f in m:
                 raise repo.RepoError(_("already have changeset ") + short(f[:4]))
 
         if base.keys() == [nullid]:
             if force:
                 self.ui.warn(_("warning: repository is unrelated\n"))
             else:
                 raise util.Abort(_("repository is unrelated"))
 
         self.ui.debug(_("found new changesets starting at ") +
                      " ".join([short(f) for f in fetch]) + "\n")
 
         self.ui.debug(_("%d total queries\n") % reqcnt)
 
         return fetch.keys()
 
     def findoutgoing(self, remote, base=None, heads=None, force=False):
         """Return list of nodes that are roots of subsets not in remote
 
         If base dict is specified, assume that these nodes and their parents
         exist on the remote side.
         If a list of heads is specified, return only nodes which are heads
         or ancestors of these heads, and return a second element which
         contains all remote heads which get new children.
         """
         if base == None:
             base = {}
             self.findincoming(remote, base, heads, force=force)
 
         self.ui.debug(_("common changesets up to ")
                       + " ".join(map(short, base.keys())) + "\n")
 
         remain = dict.fromkeys(self.changelog.nodemap)
 
         # prune everything remote has from the tree
         del remain[nullid]
         remove = base.keys()
         while remove:
             n = remove.pop(0)
             if n in remain:
                 del remain[n]
                 for p in self.changelog.parents(n):
                     remove.append(p)
 
         # find every node whose parents have been pruned
         subset = []
         # find every remote head that will get new children
         updated_heads = {}
         for n in remain:
             p1, p2 = self.changelog.parents(n)
             if p1 not in remain and p2 not in remain:
                 subset.append(n)
             if heads:
                 if p1 in heads:
                     updated_heads[p1] = True
                 if p2 in heads:
                     updated_heads[p2] = True
 
         # this is the set of all roots we have to push
         if heads:
             return subset, updated_heads.keys()
         else:
             return subset
 
     def pull(self, remote, heads=None, force=False):
         lock = self.lock()
         try:
             fetch = self.findincoming(remote, heads=heads, force=force)
             if fetch == [nullid]:
                 self.ui.status(_("requesting all changes\n"))
 
             if not fetch:
                 self.ui.status(_("no changes found\n"))
                 return 0
 
             if heads is None:
                 cg = remote.changegroup(fetch, 'pull')
             else:
                 if 'changegroupsubset' not in remote.capabilities:
                     raise util.Abort(_("Partial pull cannot be done because other repository doesn't support changegroupsubset."))
                 cg = remote.changegroupsubset(fetch, heads, 'pull')
             return self.addchangegroup(cg, 'pull', remote.url())
         finally:
             del lock
 
     def push(self, remote, force=False, revs=None):
         # 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 remote.capable('unbundle'):
             return self.push_unbundle(remote, force, revs)
         return self.push_addchangegroup(remote, force, revs)
 
     def prepush(self, remote, force, revs):
         base = {}
         remote_heads = remote.heads()
         inc = self.findincoming(remote, base, remote_heads, force=force)
 
         update, updated_heads = self.findoutgoing(remote, base, remote_heads)
         if revs is not None:
             msng_cl, bases, heads = self.changelog.nodesbetween(update, revs)
         else:
             bases, heads = update, self.changelog.heads()
 
         if not bases:
             self.ui.status(_("no changes found\n"))
             return None, 1
         elif not force:
             # check if we're creating new remote heads
             # to be a remote head after push, node must be either
             # - unknown locally
             # - a local outgoing head descended from update
             # - a remote head that's known locally and not
             #   ancestral to an outgoing head
 
             warn = 0
 
             if remote_heads == [nullid]:
                 warn = 0
             elif not revs and len(heads) > len(remote_heads):
                 warn = 1
             else:
                 newheads = list(heads)
                 for r in remote_heads:
                     if r in self.changelog.nodemap:
                         desc = self.changelog.heads(r, heads)
                         l = [h for h in heads if h in desc]
                         if not l:
                             newheads.append(r)
                     else:
                         newheads.append(r)
                 if len(newheads) > len(remote_heads):
                     warn = 1
 
             if warn:
                 self.ui.warn(_("abort: push creates new remote branches!\n"))
                 self.ui.status(_("(did you forget to merge?"
                                  " use push -f to force)\n"))
                 return None, 1
             elif inc:
                 self.ui.warn(_("note: unsynced remote changes!\n"))
 
 
         if revs is None:
             cg = self.changegroup(update, 'push')
         else:
             cg = self.changegroupsubset(update, revs, 'push')
         return cg, remote_heads
 
     def push_addchangegroup(self, remote, force, revs):
         lock = remote.lock()
         try:
             ret = self.prepush(remote, force, revs)
             if ret[0] is not None:
                 cg, remote_heads = ret
                 return remote.addchangegroup(cg, 'push', self.url())
             return ret[1]
         finally:
             del lock
 
     def push_unbundle(self, remote, force, revs):
         # 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.
 
         ret = self.prepush(remote, force, revs)
         if ret[0] is not None:
             cg, remote_heads = ret
             if force: remote_heads = ['force']
             return remote.unbundle(cg, remote_heads, 'push')
         return ret[1]
 
     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, extranodes=None):
         """This function generates a changegroup consisting of all the nodes
         that are descendents of any of the bases, and ancestors of any of
         the heads.
 
         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.
         
         The caller can specify some nodes that must be included in the
         changegroup using the extranodes argument.  It should be a dict
         where the keys are the filenames (or 1 for the manifest), and the
         values are lists of (node, linknode) tuples, where node is a wanted
         node and linknode is the changelog node that should be transmitted as
         the linkrev.
         """
 
         self.hook('preoutgoing', throw=True, source=source)
 
         # Set up some initial variables
         # Make it easy to refer to self.changelog
         cl = self.changelog
         # msng is short for missing - compute the list of changesets in this
         # changegroup.
         msng_cl_lst, bases, heads = cl.nodesbetween(bases, heads)
         self.changegroupinfo(msng_cl_lst, source)
         # Some bases may turn out to be superfluous, and some heads may be
         # too.  nodesbetween will return the minimal set of bases and heads
         # necessary to re-create the changegroup.
 
         # Known heads are the list of heads that it is assumed the recipient
         # of this changegroup will know about.
         knownheads = {}
         # We assume that all parents of bases are known heads.
         for n in bases:
             for p in cl.parents(n):
                 if p != nullid:
                     knownheads[p] = 1
         knownheads = knownheads.keys()
         if knownheads:
             # Now that we know what heads are known, we can compute which
             # changesets are known.  The recipient must know about all
             # changesets required to reach the known heads from the null
             # changeset.
             has_cl_set, junk, junk = cl.nodesbetween(None, knownheads)
             junk = None
             # Transform the list into an ersatz set.
             has_cl_set = dict.fromkeys(has_cl_set)
         else:
             # If there were no known heads, the recipient cannot be assumed to
             # know about any changesets.
             has_cl_set = {}
 
         # Make it easy to refer to self.manifest
         mnfst = self.manifest
         # We don't know which manifests are missing yet
         msng_mnfst_set = {}
         # Nor do we know which filenodes are missing.
         msng_filenode_set = {}
 
         junk = mnfst.index[mnfst.count() - 1] # Get around a bug in lazyindex
         junk = None
 
         # A changeset always belongs to itself, so the changenode lookup
         # function for a changenode is identity.
         def identity(x):
             return x
 
         # A function generating function.  Sets up an environment for the
         # inner function.
         def cmp_by_rev_func(revlog):
             # Compare two nodes by their revision number in the environment's
             # revision history.  Since the revision number both represents the
             # most efficient order to read the nodes in, and represents a
             # topological sorting of the nodes, this function is often useful.
             def cmp_by_rev(a, b):
                 return cmp(revlog.rev(a), revlog.rev(b))
             return cmp_by_rev
 
         # If we determine that a particular file or manifest node must be a
         # node that the recipient of the changegroup will already have, we can
         # also assume the recipient will have all the parents.  This function
         # prunes them from the set of missing nodes.
         def prune_parents(revlog, hasset, msngset):
             haslst = hasset.keys()
             haslst.sort(cmp_by_rev_func(revlog))
             for node in haslst:
                 parentlst = [p for p in revlog.parents(node) if p != nullid]
                 while parentlst:
                     n = parentlst.pop()
                     if n not in hasset:
                         hasset[n] = 1
                         p = [p for p in revlog.parents(n) if p != nullid]
                         parentlst.extend(p)
             for n in hasset:
                 msngset.pop(n, None)
 
         # This is a function generating function used to set up an environment
         # for the inner function to execute in.
         def manifest_and_file_collector(changedfileset):
             # This is an information gathering function that gathers
             # information from each changeset node that goes out as part of
             # the changegroup.  The information gathered is a list of which
             # manifest nodes are potentially required (the recipient may
             # already have them) and total list of all files which were
             # changed in any changeset in the changegroup.
             #
             # We also remember the first changenode we saw any manifest
             # referenced by so we can later determine which changenode 'owns'
             # the manifest.
             def collect_manifests_and_files(clnode):
                 c = cl.read(clnode)
                 for f in c[3]:
                     # This is to make sure we only have one instance of each
                     # filename string for each filename.
                     changedfileset.setdefault(f, f)
                 msng_mnfst_set.setdefault(c[0], clnode)
             return collect_manifests_and_files
 
         # Figure out which manifest nodes (of the ones we think might be part
         # of the changegroup) the recipient must know about and remove them
         # from the changegroup.
         def prune_manifests():
             has_mnfst_set = {}
             for n in msng_mnfst_set:
                 # If a 'missing' manifest thinks it belongs to a changenode
                 # the recipient is assumed to have, obviously the recipient
                 # must have that manifest.
                 linknode = cl.node(mnfst.linkrev(n))
                 if linknode in has_cl_set:
                     has_mnfst_set[n] = 1
             prune_parents(mnfst, has_mnfst_set, msng_mnfst_set)
 
         # Use the information collected in collect_manifests_and_files to say
         # which changenode any manifestnode belongs to.
         def lookup_manifest_link(mnfstnode):
             return msng_mnfst_set[mnfstnode]
 
         # A function generating function that sets up the initial environment
         # the inner function.
         def filenode_collector(changedfiles):
             next_rev = [0]
             # This gathers information from each manifestnode included in the
             # changegroup about which filenodes the manifest node references
             # so we can include those in the changegroup too.
             #
             # It also remembers which changenode each filenode belongs to.  It
             # does this by assuming the a filenode belongs to the changenode
             # the first manifest that references it belongs to.
             def collect_msng_filenodes(mnfstnode):
                 r = mnfst.rev(mnfstnode)
                 if r == next_rev[0]:
                     # If the last rev we looked at was the one just previous,
                     # we only need to see a diff.
                     deltamf = mnfst.readdelta(mnfstnode)
                     # For each line in the delta
                     for f, fnode in deltamf.items():
                         f = changedfiles.get(f, None)
                         # And if the file is in the list of files we care
                         # about.
                         if f is not None:
                             # Get the changenode this manifest belongs to
                             clnode = msng_mnfst_set[mnfstnode]
                             # Create the set of filenodes for the file if
                             # there isn't one already.
                             ndset = msng_filenode_set.setdefault(f, {})
                             # And set the filenode's changelog node to the
                             # manifest's if it hasn't been set already.
                             ndset.setdefault(fnode, clnode)
                 else:
                     # Otherwise we need a full manifest.
                     m = mnfst.read(mnfstnode)
                     # For every file in we care about.
                     for f in changedfiles:
                         fnode = m.get(f, None)
                         # If it's in the manifest
                         if fnode is not None:
                             # See comments above.
                             clnode = msng_mnfst_set[mnfstnode]
                             ndset = msng_filenode_set.setdefault(f, {})
                             ndset.setdefault(fnode, clnode)
                 # Remember the revision we hope to see next.
                 next_rev[0] = r + 1
             return collect_msng_filenodes
 
         # We have a list of filenodes we think we need for a file, lets remove
         # all those we now the recipient must have.
         def prune_filenodes(f, filerevlog):
             msngset = msng_filenode_set[f]
             hasset = {}
             # If a 'missing' filenode thinks it belongs to a changenode we
             # assume the recipient must have, then the recipient must have
             # that filenode.
             for n in msngset:
                 clnode = cl.node(filerevlog.linkrev(n))
                 if clnode in has_cl_set:
                     hasset[n] = 1
             prune_parents(filerevlog, hasset, msngset)
 
         # A function generator function that sets up the a context for the
         # inner function.
         def lookup_filenode_link_func(fname):
             msngset = msng_filenode_set[fname]
             # Lookup the changenode the filenode belongs to.
             def lookup_filenode_link(fnode):
                 return msngset[fnode]
             return lookup_filenode_link
 
         # Add the nodes that were explicitly requested.
         def add_extra_nodes(name, nodes):
             if not extranodes or name not in extranodes:
                 return
 
             for node, linknode in extranodes[name]:
                 if node not in nodes:
                     nodes[node] = linknode
 
         # Now that we have all theses utility functions to help out and
         # logically divide up the task, generate the group.
         def gengroup():
             # The set of changed files starts empty.
             changedfiles = {}
             # Create a changenode group generator that will call our functions
             # back to lookup the owning changenode and collect information.
             group = cl.group(msng_cl_lst, identity,
                              manifest_and_file_collector(changedfiles))
             for chnk in group:
                 yield chnk
 
             # The list of manifests has been collected by the generator
             # calling our functions back.
             prune_manifests()
             add_extra_nodes(1, msng_mnfst_set)
             msng_mnfst_lst = msng_mnfst_set.keys()
             # Sort the manifestnodes by revision number.
             msng_mnfst_lst.sort(cmp_by_rev_func(mnfst))
             # Create a generator for the manifestnodes that calls our lookup
             # and data collection functions back.
             group = mnfst.group(msng_mnfst_lst, lookup_manifest_link,
                                 filenode_collector(changedfiles))
             for chnk in group:
                 yield chnk
 
             # These are no longer needed, dereference and toss the memory for
             # them.
             msng_mnfst_lst = None
             msng_mnfst_set.clear()
 
             if extranodes:
                 for fname in extranodes:
                     if isinstance(fname, int):
                         continue
                     add_extra_nodes(fname,
                                     msng_filenode_set.setdefault(fname, {}))
                     changedfiles[fname] = 1
             changedfiles = changedfiles.keys()
             changedfiles.sort()
             # Go through all our files in order sorted by name.
             for fname in changedfiles:
                 filerevlog = self.file(fname)
                 if filerevlog.count() == 0:
                     raise util.Abort(_("empty or missing revlog for %s") % fname)
                 # Toss out the filenodes that the recipient isn't really
                 # missing.
-                if msng_filenode_set.has_key(fname):
+                if fname in msng_filenode_set:
                     prune_filenodes(fname, filerevlog)
                     msng_filenode_lst = msng_filenode_set[fname].keys()
                 else:
                     msng_filenode_lst = []
                 # If any filenodes are left, generate the group for them,
                 # otherwise don't bother.
                 if len(msng_filenode_lst) > 0:
                     yield changegroup.chunkheader(len(fname))
                     yield fname
                     # Sort the filenodes by their revision #
                     msng_filenode_lst.sort(cmp_by_rev_func(filerevlog))
                     # Create a group generator and only pass in a changenode
                     # lookup function as we need to collect no information
                     # from filenodes.
                     group = filerevlog.group(msng_filenode_lst,
                                              lookup_filenode_link_func(fname))
                     for chnk in group:
                         yield chnk
-                if msng_filenode_set.has_key(fname):
+                if fname in msng_filenode_set:
                     # Don't need this anymore, toss it to free memory.
                     del msng_filenode_set[fname]
             # Signal that no more groups are left.
             yield changegroup.closechunk()
 
             if msng_cl_lst:
                 self.hook('outgoing', node=hex(msng_cl_lst[0]), source=source)
 
         return util.chunkbuffer(gengroup())
 
     def changegroup(self, basenodes, source):
         """Generate a changegroup of all nodes that we have that a recipient
         doesn't.
 
         This is much easier than the previous function as we can assume that
         the recipient has any changenode we aren't sending them."""
 
         self.hook('preoutgoing', throw=True, source=source)
 
         cl = self.changelog
         nodes = cl.nodesbetween(basenodes, None)[0]
         revset = dict.fromkeys([cl.rev(n) for n in nodes])
         self.changegroupinfo(nodes, source)
 
         def identity(x):
             return x
 
         def gennodelst(revlog):
             for r in xrange(0, revlog.count()):
                 n = revlog.node(r)
                 if revlog.linkrev(n) in revset:
                     yield n
 
         def changed_file_collector(changedfileset):
             def collect_changed_files(clnode):
                 c = cl.read(clnode)
                 for fname in c[3]:
                     changedfileset[fname] = 1
             return collect_changed_files
 
         def lookuprevlink_func(revlog):
             def lookuprevlink(n):
                 return cl.node(revlog.linkrev(n))
             return lookuprevlink
 
         def gengroup():
             # construct a list of all changed files
             changedfiles = {}
 
             for chnk in cl.group(nodes, identity,
                                  changed_file_collector(changedfiles)):
                 yield chnk
             changedfiles = changedfiles.keys()
             changedfiles.sort()
 
             mnfst = self.manifest
             nodeiter = gennodelst(mnfst)
             for chnk in mnfst.group(nodeiter, lookuprevlink_func(mnfst)):
                 yield chnk
 
             for fname in changedfiles:
                 filerevlog = self.file(fname)
                 if filerevlog.count() == 0:
                     raise util.Abort(_("empty or missing revlog for %s") % fname)
                 nodeiter = gennodelst(filerevlog)
                 nodeiter = list(nodeiter)
                 if nodeiter:
                     yield changegroup.chunkheader(len(fname))
                     yield fname
                     lookup = lookuprevlink_func(filerevlog)
                     for chnk in filerevlog.group(nodeiter, lookup):
                         yield chnk
 
             yield changegroup.closechunk()
 
             if nodes:
                 self.hook('outgoing', node=hex(nodes[0]), source=source)
 
         return util.chunkbuffer(gengroup())
 
     def addchangegroup(self, source, srctype, url, emptyok=False):
         """add changegroup to repo.
 
         return values:
         - nothing changed or no source: 0
         - more heads than before: 1+added heads (2..n)
         - less 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 cl.count()
 
         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
 
         # write changelog data to temp files so concurrent readers will not see
         # inconsistent view
         cl = self.changelog
         cl.delayupdate()
         oldheads = len(cl.heads())
 
         tr = self.transaction()
         try:
             trp = weakref.proxy(tr)
             # pull off the changeset group
             self.ui.status(_("adding changesets\n"))
             cor = cl.count() - 1
             chunkiter = changegroup.chunkiter(source)
             if cl.addgroup(chunkiter, csmap, trp, 1) is None and not emptyok:
                 raise util.Abort(_("received changelog group is empty"))
             cnr = cl.count() - 1
             changesets = cnr - cor
 
             # pull off the manifest group
             self.ui.status(_("adding manifests\n"))
             chunkiter = changegroup.chunkiter(source)
             # 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
             self.manifest.addgroup(chunkiter, revmap, trp)
 
             # process the files
             self.ui.status(_("adding file changes\n"))
             while 1:
                 f = changegroup.getchunk(source)
                 if not f:
                     break
                 self.ui.debug(_("adding %s revisions\n") % f)
                 fl = self.file(f)
                 o = fl.count()
                 chunkiter = changegroup.chunkiter(source)
                 if fl.addgroup(chunkiter, revmap, trp) is None:
                     raise util.Abort(_("received file revlog group is empty"))
                 revisions += fl.count() - o
                 files += 1
 
             # make changelog see real files again
             cl.finalize(trp)
 
             newheads = len(self.changelog.heads())
             heads = ""
             if oldheads and newheads != oldheads:
                 heads = _(" (%+d heads)") % (newheads - oldheads)
 
             self.ui.status(_("added %d changesets"
                              " with %d changes to %d files%s\n")
                              % (changesets, revisions, files, heads))
 
             if changesets > 0:
                 self.hook('pretxnchangegroup', throw=True,
                           node=hex(self.changelog.node(cor+1)), source=srctype,
                           url=url)
 
             tr.close()
         finally:
             del tr
 
         if changesets > 0:
             self.hook("changegroup", node=hex(self.changelog.node(cor+1)),
                       source=srctype, url=url)
 
             for i in xrange(cor + 1, cnr + 1):
                 self.hook("incoming", node=hex(self.changelog.node(i)),
                           source=srctype, url=url)
 
         # never return 0 here:
         if newheads < oldheads:
             return newheads - oldheads - 1
         else:
             return newheads - oldheads + 1
 
 
     def stream_in(self, remote):
         fp = remote.stream_out()
         l = fp.readline()
         try:
             resp = int(l)
         except ValueError:
             raise util.UnexpectedOutput(
                 _('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 util.UnexpectedOutput(
                 _('Unexpected response from remote server:'), l)
         self.ui.status(_('%d files to transfer, %s of data\n') %
                        (total_files, util.bytecount(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 util.UnexpectedOutput(
                     _('Unexpected response from remote server:'), l)
             self.ui.debug('adding %s (%s)\n' % (name, util.bytecount(size)))
             ofp = self.sopener(name, 'w')
             for chunk in util.filechunkiter(fp, limit=size):
                 ofp.write(chunk)
             ofp.close()
         elapsed = time.time() - start
         if elapsed <= 0:
             elapsed = 0.001
         self.ui.status(_('transferred %s in %.1f seconds (%s/sec)\n') %
                        (util.bytecount(total_bytes), elapsed,
                         util.bytecount(total_bytes / elapsed)))
         self.invalidate()
         return len(self.heads()) + 1
 
     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 stream and not heads and remote.capable('stream'):
             return self.stream_in(remote)
         return self.pull(remote, heads)
 
 # used to avoid circular references so destructors work
 def aftertrans(files):
     renamefiles = [tuple(t) for t in files]
     def a():
         for src, dest in renamefiles:
             util.rename(src, dest)
     return a
 
 def instance(ui, path, create):
     return localrepository(ui, util.drop_scheme('file', path), create)
 
 def islocal(path):
     return True

mercurial/templater.py

@@ -1,298 +1,298 b''
 # templater.py - template expansion for output
 #
 # Copyright 2005, 2006 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms
 # of the GNU General Public License, incorporated herein by reference.
 
 from i18n import _
 from node import *
 import cgi, re, sys, os, time, urllib, util, textwrap
 
 def parsestring(s, quoted=True):
     '''parse a string using simple c-like syntax.
     string must be in quotes if quoted is True.'''
     if quoted:
         if len(s) < 2 or s[0] != s[-1]:
             raise SyntaxError(_('unmatched quotes'))
         return s[1:-1].decode('string_escape')
 
     return s.decode('string_escape')
 
 class templater(object):
     '''template expansion engine.
 
     template expansion works like this. a map file contains key=value
     pairs. if value is quoted, it is treated as string. otherwise, it
     is treated as name of template file.
 
     templater is asked to expand a key in map. it looks up key, and
     looks for strings like this: {foo}. it expands {foo} by looking up
     foo in map, and substituting it. expansion is recursive: it stops
     when there is no more {foo} to replace.
 
     expansion also allows formatting and filtering.
 
     format uses key to expand each item in list. syntax is
     {key%format}.
 
     filter uses function to transform value. syntax is
     {key|filter1|filter2|...}.'''
 
     template_re = re.compile(r"(?:(?:#(?=[\w\|%]+#))|(?:{(?=[\w\|%]+})))"
                              r"(\w+)(?:(?:%(\w+))|((?:\|\w+)*))[#}]")
 
     def __init__(self, mapfile, filters={}, defaults={}, cache={}):
         '''set up template engine.
         mapfile is name of file to read map definitions from.
         filters is dict of functions. each transforms a value into another.
         defaults is dict of default map definitions.'''
         self.mapfile = mapfile or 'template'
         self.cache = cache.copy()
         self.map = {}
         self.base = (mapfile and os.path.dirname(mapfile)) or ''
         self.filters = filters
         self.defaults = defaults
 
         if not mapfile:
             return
         i = 0
         for l in file(mapfile):
             l = l.strip()
             i += 1
             if not l or l[0] in '#;': continue
             m = re.match(r'([a-zA-Z_][a-zA-Z0-9_]*)\s*=\s*(.+)$', l)
             if m:
                 key, val = m.groups()
                 if val[0] in "'\"":
                     try:
                         self.cache[key] = parsestring(val)
                     except SyntaxError, inst:
                         raise SyntaxError('%s:%s: %s' %
                                           (mapfile, i, inst.args[0]))
                 else:
                     self.map[key] = os.path.join(self.base, val)
             else:
                 raise SyntaxError(_("%s:%s: parse error") % (mapfile, i))
 
     def __contains__(self, key):
         return key in self.cache or key in self.map
 
     def __call__(self, t, **map):
         '''perform expansion.
         t is name of map element to expand.
         map is added elements to use during expansion.'''
-        if not self.cache.has_key(t):
+        if not t in self.cache:
             try:
                 self.cache[t] = file(self.map[t]).read()
             except IOError, inst:
                 raise IOError(inst.args[0], _('template file %s: %s') %
                               (self.map[t], inst.args[1]))
         tmpl = self.cache[t]
 
         while tmpl:
             m = self.template_re.search(tmpl)
             if not m:
                 yield tmpl
                 break
 
             start, end = m.span(0)
             key, format, fl = m.groups()
 
             if start:
                 yield tmpl[:start]
             tmpl = tmpl[end:]
 
             if key in map:
                 v = map[key]
             else:
                 v = self.defaults.get(key, "")
             if callable(v):
                 v = v(**map)
             if format:
                 if not hasattr(v, '__iter__'):
                     raise SyntaxError(_("Error expanding '%s%s'")
                                       % (key, format))
                 lm = map.copy()
                 for i in v:
                     lm.update(i)
                     yield self(format, **lm)
             else:
                 if fl:
                     for f in fl.split("|")[1:]:
                         v = self.filters[f](v)
                 yield v
 
 agescales = [("second", 1),
              ("minute", 60),
              ("hour", 3600),
              ("day", 3600 * 24),
              ("week", 3600 * 24 * 7),
              ("month", 3600 * 24 * 30),
              ("year", 3600 * 24 * 365)]
 
 agescales.reverse()
 
 def age(date):
     '''turn a (timestamp, tzoff) tuple into an age string.'''
 
     def plural(t, c):
         if c == 1:
             return t
         return t + "s"
     def fmt(t, c):
         return "%d %s" % (c, plural(t, c))
 
     now = time.time()
     then = date[0]
     delta = max(1, int(now - then))
 
     for t, s in agescales:
         n = delta / s
         if n >= 2 or s == 1:
             return fmt(t, n)
 
 def stringify(thing):
     '''turn nested template iterator into string.'''
     if hasattr(thing, '__iter__'):
         return "".join([stringify(t) for t in thing if t is not None])
     return str(thing)
 
 para_re = None
 space_re = None
 
 def fill(text, width):
     '''fill many paragraphs.'''
     global para_re, space_re
     if para_re is None:
         para_re = re.compile('(\n\n|\n\\s*[-*]\\s*)', re.M)
         space_re = re.compile(r'  +')
 
     def findparas():
         start = 0
         while True:
             m = para_re.search(text, start)
             if not m:
                 w = len(text)
                 while w > start and text[w-1].isspace(): w -= 1
                 yield text[start:w], text[w:]
                 break
             yield text[start:m.start(0)], m.group(1)
             start = m.end(1)
 
     return "".join([space_re.sub(' ', textwrap.fill(para, width)) + rest
                     for para, rest in findparas()])
 
 def firstline(text):
     '''return the first line of text'''
     try:
         return text.splitlines(1)[0].rstrip('\r\n')
     except IndexError:
         return ''
 
 def isodate(date):
     '''turn a (timestamp, tzoff) tuple into an iso 8631 date and time.'''
     return util.datestr(date, format='%Y-%m-%d %H:%M')
 
 def hgdate(date):
     '''turn a (timestamp, tzoff) tuple into an hg cset timestamp.'''
     return "%d %d" % date
 
 def nl2br(text):
     '''replace raw newlines with xhtml line breaks.'''
     return text.replace('\n', '<br/>\n')
 
 def obfuscate(text):
     text = unicode(text, util._encoding, 'replace')
     return ''.join(['&#%d;' % ord(c) for c in text])
 
 def domain(author):
     '''get domain of author, or empty string if none.'''
     f = author.find('@')
     if f == -1: return ''
     author = author[f+1:]
     f = author.find('>')
     if f >= 0: author = author[:f]
     return author
 
 def email(author):
     '''get email of author.'''
     r = author.find('>')
     if r == -1: r = None
     return author[author.find('<')+1:r]
 
 def person(author):
     '''get name of author, or else username.'''
     f = author.find('<')
     if f == -1: return util.shortuser(author)
     return author[:f].rstrip()
 
 def shortdate(date):
     '''turn (timestamp, tzoff) tuple into iso 8631 date.'''
     return util.datestr(date, format='%Y-%m-%d', timezone=False)
 
 def indent(text, prefix):
     '''indent each non-empty line of text after first with prefix.'''
     lines = text.splitlines()
     num_lines = len(lines)
     def indenter():
         for i in xrange(num_lines):
             l = lines[i]
             if i and l.strip():
                 yield prefix
             yield l
             if i < num_lines - 1 or text.endswith('\n'):
                 yield '\n'
     return "".join(indenter())
 
 def permissions(flags):
     if "l" in flags:
         return "lrwxrwxrwx"
     if "x" in flags:
         return "-rwxr-xr-x"
     return "-rw-r--r--"
 
 common_filters = {
     "addbreaks": nl2br,
     "basename": os.path.basename,
     "age": age,
     "date": lambda x: util.datestr(x),
     "domain": domain,
     "email": email,
     "escape": lambda x: cgi.escape(x, True),
     "fill68": lambda x: fill(x, width=68),
     "fill76": lambda x: fill(x, width=76),
     "firstline": firstline,
     "tabindent": lambda x: indent(x, '\t'),
     "hgdate": hgdate,
     "isodate": isodate,
     "obfuscate": obfuscate,
     "permissions": permissions,
     "person": person,
     "rfc822date": lambda x: util.datestr(x, "%a, %d %b %Y %H:%M:%S"),
     "rfc3339date": lambda x: util.datestr(x, "%Y-%m-%dT%H:%M:%S", True, "%+03d:%02d"),
     "short": lambda x: x[:12],
     "shortdate": shortdate,
     "stringify": stringify,
     "strip": lambda x: x.strip(),
     "urlescape": lambda x: urllib.quote(x),
     "user": lambda x: util.shortuser(x),
     "stringescape": lambda x: x.encode('string_escape'),
     }
 
 def templatepath(name=None):
     '''return location of template file or directory (if no name).
     returns None if not found.'''
 
     # executable version (py2exe) doesn't support __file__
     if hasattr(sys, 'frozen'):
         module = sys.executable
     else:
         module = __file__
     for f in 'templates', '../templates':
         fl = f.split('/')
         if name: fl.append(name)
         p = os.path.join(os.path.dirname(module), *fl)
         if (name and os.path.exists(p)) or os.path.isdir(p):
             return os.path.normpath(p)
 

tests/coverage.py

@@ -1,1110 +1,1110 b''
 #!/usr/bin/env python
 #
 #             Perforce Defect Tracking Integration Project
 #              <http://www.ravenbrook.com/project/p4dti/>
 #
 #                   COVERAGE.PY -- COVERAGE TESTING
 #
 #             Gareth Rees, Ravenbrook Limited, 2001-12-04
 #                     Ned Batchelder, 2004-12-12
 #         http://nedbatchelder.com/code/modules/coverage.html
 #
 #
 # 1. INTRODUCTION
 #
 # This module provides coverage testing for Python code.
 #
 # The intended readership is all Python developers.
 #
 # This document is not confidential.
 #
 # See [GDR 2001-12-04a] for the command-line interface, programmatic
 # interface and limitations.  See [GDR 2001-12-04b] for requirements and
 # design.
 
 r"""Usage:
 
 coverage.py -x [-p] MODULE.py [ARG1 ARG2 ...]
     Execute module, passing the given command-line arguments, collecting
     coverage data. With the -p option, write to a temporary file containing
     the machine name and process ID.
 
 coverage.py -e
     Erase collected coverage data.
 
 coverage.py -c
     Collect data from multiple coverage files (as created by -p option above)
     and store it into a single file representing the union of the coverage.
 
 coverage.py -r [-m] [-o dir1,dir2,...] FILE1 FILE2 ...
     Report on the statement coverage for the given files.  With the -m
     option, show line numbers of the statements that weren't executed.
 
 coverage.py -a [-d dir] [-o dir1,dir2,...] FILE1 FILE2 ...
     Make annotated copies of the given files, marking statements that
     are executed with > and statements that are missed with !.  With
     the -d option, make the copies in that directory.  Without the -d
     option, make each copy in the same directory as the original.
 
 -o dir,dir2,...
   Omit reporting or annotating files when their filename path starts with
   a directory listed in the omit list.
   e.g. python coverage.py -i -r -o c:\python23,lib\enthought\traits
 
 Coverage data is saved in the file .coverage by default.  Set the
 COVERAGE_FILE environment variable to save it somewhere else."""
 
 __version__ = "2.77.20070729"    # see detailed history at the end of this file.
 
 import compiler
 import compiler.visitor
 import glob
 import os
 import re
 import string
 import symbol
 import sys
 import threading
 import token
 import types
 from socket import gethostname
 
 # Python version compatibility
 try:
     strclass = basestring   # new to 2.3
 except:
     strclass = str
 
 # 2. IMPLEMENTATION
 #
 # This uses the "singleton" pattern.
 #
 # The word "morf" means a module object (from which the source file can
 # be deduced by suitable manipulation of the __file__ attribute) or a
 # filename.
 #
 # When we generate a coverage report we have to canonicalize every
 # filename in the coverage dictionary just in case it refers to the
 # module we are reporting on.  It seems a shame to throw away this
 # information so the data in the coverage dictionary is transferred to
 # the 'cexecuted' dictionary under the canonical filenames.
 #
 # The coverage dictionary is called "c" and the trace function "t".  The
 # reason for these short names is that Python looks up variables by name
 # at runtime and so execution time depends on the length of variables!
 # In the bottleneck of this application it's appropriate to abbreviate
 # names to increase speed.
 
 class StatementFindingAstVisitor(compiler.visitor.ASTVisitor):
     """ A visitor for a parsed Abstract Syntax Tree which finds executable
         statements.
     """
     def __init__(self, statements, excluded, suite_spots):
         compiler.visitor.ASTVisitor.__init__(self)
         self.statements = statements
         self.excluded = excluded
         self.suite_spots = suite_spots
         self.excluding_suite = 0
 
     def doRecursive(self, node):
         for n in node.getChildNodes():
             self.dispatch(n)
 
     visitStmt = visitModule = doRecursive
 
     def doCode(self, node):
         if hasattr(node, 'decorators') and node.decorators:
             self.dispatch(node.decorators)
             self.recordAndDispatch(node.code)
         else:
             self.doSuite(node, node.code)
 
     visitFunction = visitClass = doCode
 
     def getFirstLine(self, node):
         # Find the first line in the tree node.
         lineno = node.lineno
         for n in node.getChildNodes():
             f = self.getFirstLine(n)
             if lineno and f:
                 lineno = min(lineno, f)
             else:
                 lineno = lineno or f
         return lineno
 
     def getLastLine(self, node):
         # Find the first line in the tree node.
         lineno = node.lineno
         for n in node.getChildNodes():
             lineno = max(lineno, self.getLastLine(n))
         return lineno
 
     def doStatement(self, node):
         self.recordLine(self.getFirstLine(node))
 
     visitAssert = visitAssign = visitAssTuple = visitPrint = \
         visitPrintnl = visitRaise = visitSubscript = visitDecorators = \
         doStatement
 
     def visitPass(self, node):
         # Pass statements have weird interactions with docstrings.  If this
         # pass statement is part of one of those pairs, claim that the statement
         # is on the later of the two lines.
         l = node.lineno
         if l:
             lines = self.suite_spots.get(l, [l,l])
             self.statements[lines[1]] = 1
 
     def visitDiscard(self, node):
         # Discard nodes are statements that execute an expression, but then
         # discard the results.  This includes function calls, so we can't
         # ignore them all.  But if the expression is a constant, the statement
         # won't be "executed", so don't count it now.
         if node.expr.__class__.__name__ != 'Const':
             self.doStatement(node)
 
     def recordNodeLine(self, node):
         # Stmt nodes often have None, but shouldn't claim the first line of
         # their children (because the first child might be an ignorable line
         # like "global a").
         if node.__class__.__name__ != 'Stmt':
             return self.recordLine(self.getFirstLine(node))
         else:
             return 0
 
     def recordLine(self, lineno):
         # Returns a bool, whether the line is included or excluded.
         if lineno:
             # Multi-line tests introducing suites have to get charged to their
             # keyword.
             if lineno in self.suite_spots:
                 lineno = self.suite_spots[lineno][0]
             # If we're inside an excluded suite, record that this line was
             # excluded.
             if self.excluding_suite:
                 self.excluded[lineno] = 1
                 return 0
             # If this line is excluded, or suite_spots maps this line to
             # another line that is exlcuded, then we're excluded.
-            elif self.excluded.has_key(lineno) or \
-                 self.suite_spots.has_key(lineno) and \
-                 self.excluded.has_key(self.suite_spots[lineno][1]):
+            elif lineno in self.excluded or \
+                 lineno in self.suite_spots and \
+                 self.suite_spots[lineno][1] in self.excluded:
                 return 0
             # Otherwise, this is an executable line.
             else:
                 self.statements[lineno] = 1
                 return 1
         return 0
 
     default = recordNodeLine
 
     def recordAndDispatch(self, node):
         self.recordNodeLine(node)
         self.dispatch(node)
 
     def doSuite(self, intro, body, exclude=0):
         exsuite = self.excluding_suite
         if exclude or (intro and not self.recordNodeLine(intro)):
             self.excluding_suite = 1
         self.recordAndDispatch(body)
         self.excluding_suite = exsuite
 
     def doPlainWordSuite(self, prevsuite, suite):
         # Finding the exclude lines for else's is tricky, because they aren't
         # present in the compiler parse tree.  Look at the previous suite,
         # and find its last line.  If any line between there and the else's
         # first line are excluded, then we exclude the else.
         lastprev = self.getLastLine(prevsuite)
         firstelse = self.getFirstLine(suite)
         for l in range(lastprev+1, firstelse):
-            if self.suite_spots.has_key(l):
-                self.doSuite(None, suite, exclude=self.excluded.has_key(l))
+            if l in self.suite_spots:
+                self.doSuite(None, suite, l in exclude=self.excluded)
                 break
         else:
             self.doSuite(None, suite)
 
     def doElse(self, prevsuite, node):
         if node.else_:
             self.doPlainWordSuite(prevsuite, node.else_)
 
     def visitFor(self, node):
         self.doSuite(node, node.body)
         self.doElse(node.body, node)
 
     visitWhile = visitFor
 
     def visitIf(self, node):
         # The first test has to be handled separately from the rest.
         # The first test is credited to the line with the "if", but the others
         # are credited to the line with the test for the elif.
         self.doSuite(node, node.tests[0][1])
         for t, n in node.tests[1:]:
             self.doSuite(t, n)
         self.doElse(node.tests[-1][1], node)
 
     def visitTryExcept(self, node):
         self.doSuite(node, node.body)
         for i in range(len(node.handlers)):
             a, b, h = node.handlers[i]
             if not a:
                 # It's a plain "except:".  Find the previous suite.
                 if i > 0:
                     prev = node.handlers[i-1][2]
                 else:
                     prev = node.body
                 self.doPlainWordSuite(prev, h)
             else:
                 self.doSuite(a, h)
         self.doElse(node.handlers[-1][2], node)
 
     def visitTryFinally(self, node):
         self.doSuite(node, node.body)
         self.doPlainWordSuite(node.body, node.final)
 
     def visitWith(self, node):
         self.doSuite(node, node.body)
 
     def visitGlobal(self, node):
         # "global" statements don't execute like others (they don't call the
         # trace function), so don't record their line numbers.
         pass
 
 the_coverage = None
 
 class CoverageException(Exception): pass
 
 class coverage:
     # Name of the cache file (unless environment variable is set).
     cache_default = ".coverage"
 
     # Environment variable naming the cache file.
     cache_env = "COVERAGE_FILE"
 
     # A dictionary with an entry for (Python source file name, line number
     # in that file) if that line has been executed.
     c = {}
 
     # A map from canonical Python source file name to a dictionary in
     # which there's an entry for each line number that has been
     # executed.
     cexecuted = {}
 
     # Cache of results of calling the analysis2() method, so that you can
     # specify both -r and -a without doing double work.
     analysis_cache = {}
 
     # Cache of results of calling the canonical_filename() method, to
     # avoid duplicating work.
     canonical_filename_cache = {}
 
     def __init__(self):
         global the_coverage
         if the_coverage:
             raise CoverageException, "Only one coverage object allowed."
         self.usecache = 1
         self.cache = None
         self.parallel_mode = False
         self.exclude_re = ''
         self.nesting = 0
         self.cstack = []
         self.xstack = []
         self.relative_dir = os.path.normcase(os.path.abspath(os.curdir)+os.sep)
         self.exclude('# *pragma[: ]*[nN][oO] *[cC][oO][vV][eE][rR]')
 
     # t(f, x, y).  This method is passed to sys.settrace as a trace function.
     # See [van Rossum 2001-07-20b, 9.2] for an explanation of sys.settrace and
     # the arguments and return value of the trace function.
     # See [van Rossum 2001-07-20a, 3.2] for a description of frame and code
     # objects.
 
     def t(self, f, w, unused):                                   #pragma: no cover
         if w == 'line':
             #print "Executing %s @ %d" % (f.f_code.co_filename, f.f_lineno)
             self.c[(f.f_code.co_filename, f.f_lineno)] = 1
             for c in self.cstack:
                 c[(f.f_code.co_filename, f.f_lineno)] = 1
         return self.t
 
     def help(self, error=None):     #pragma: no cover
         if error:
             print error
             print
         print __doc__
         sys.exit(1)
 
     def command_line(self, argv, help_fn=None):
         import getopt
         help_fn = help_fn or self.help
         settings = {}
         optmap = {
             '-a': 'annotate',
             '-c': 'collect',
             '-d:': 'directory=',
             '-e': 'erase',
             '-h': 'help',
             '-i': 'ignore-errors',
             '-m': 'show-missing',
             '-p': 'parallel-mode',
             '-r': 'report',
             '-x': 'execute',
             '-o:': 'omit=',
             }
         short_opts = string.join(map(lambda o: o[1:], optmap.keys()), '')
         long_opts = optmap.values()
         options, args = getopt.getopt(argv, short_opts, long_opts)
         for o, a in options:
-            if optmap.has_key(o):
+            if o in optmap:
                 settings[optmap[o]] = 1
-            elif optmap.has_key(o + ':'):
+            elif o + ':' in optmap:
                 settings[optmap[o + ':']] = a
             elif o[2:] in long_opts:
                 settings[o[2:]] = 1
             elif o[2:] + '=' in long_opts:
                 settings[o[2:]+'='] = a
             else:       #pragma: no cover
                 pass    # Can't get here, because getopt won't return anything unknown.
 
         if settings.get('help'):
             help_fn()
 
         for i in ['erase', 'execute']:
             for j in ['annotate', 'report', 'collect']:
                 if settings.get(i) and settings.get(j):
                     help_fn("You can't specify the '%s' and '%s' "
                               "options at the same time." % (i, j))
 
         args_needed = (settings.get('execute')
                        or settings.get('annotate')
                        or settings.get('report'))
         action = (settings.get('erase')
                   or settings.get('collect')
                   or args_needed)
         if not action:
             help_fn("You must specify at least one of -e, -x, -c, -r, or -a.")
         if not args_needed and args:
             help_fn("Unexpected arguments: %s" % " ".join(args))
 
         self.parallel_mode = settings.get('parallel-mode')
         self.get_ready()
 
         if settings.get('erase'):
             self.erase()
         if settings.get('execute'):
             if not args:
                 help_fn("Nothing to do.")
             sys.argv = args
             self.start()
             import __main__
             sys.path[0] = os.path.dirname(sys.argv[0])
             execfile(sys.argv[0], __main__.__dict__)
         if settings.get('collect'):
             self.collect()
         if not args:
             args = self.cexecuted.keys()
 
         ignore_errors = settings.get('ignore-errors')
         show_missing = settings.get('show-missing')
         directory = settings.get('directory=')
 
         omit = settings.get('omit=')
         if omit is not None:
             omit = omit.split(',')
         else:
             omit = []
 
         if settings.get('report'):
             self.report(args, show_missing, ignore_errors, omit_prefixes=omit)
         if settings.get('annotate'):
             self.annotate(args, directory, ignore_errors, omit_prefixes=omit)
 
     def use_cache(self, usecache, cache_file=None):
         self.usecache = usecache
         if cache_file and not self.cache:
             self.cache_default = cache_file
 
     def get_ready(self, parallel_mode=False):
         if self.usecache and not self.cache:
             self.cache = os.environ.get(self.cache_env, self.cache_default)
             if self.parallel_mode:
                 self.cache += "." + gethostname() + "." + str(os.getpid())
             self.restore()
         self.analysis_cache = {}
 
     def start(self, parallel_mode=False):
         self.get_ready()
         if self.nesting == 0:                               #pragma: no cover
             sys.settrace(self.t)
             if hasattr(threading, 'settrace'):
                 threading.settrace(self.t)
         self.nesting += 1
 
     def stop(self):
         self.nesting -= 1
         if self.nesting == 0:                               #pragma: no cover
             sys.settrace(None)
             if hasattr(threading, 'settrace'):
                 threading.settrace(None)
 
     def erase(self):
         self.get_ready()
         self.c = {}
         self.analysis_cache = {}
         self.cexecuted = {}
         if self.cache and os.path.exists(self.cache):
             os.remove(self.cache)
 
     def exclude(self, re):
         if self.exclude_re:
             self.exclude_re += "|"
         self.exclude_re += "(" + re + ")"
 
     def begin_recursive(self):
         self.cstack.append(self.c)
         self.xstack.append(self.exclude_re)
 
     def end_recursive(self):
         self.c = self.cstack.pop()
         self.exclude_re = self.xstack.pop()
 
     # save().  Save coverage data to the coverage cache.
 
     def save(self):
         if self.usecache and self.cache:
             self.canonicalize_filenames()
             cache = open(self.cache, 'wb')
             import marshal
             marshal.dump(self.cexecuted, cache)
             cache.close()
 
     # restore().  Restore coverage data from the coverage cache (if it exists).
 
     def restore(self):
         self.c = {}
         self.cexecuted = {}
         assert self.usecache
         if os.path.exists(self.cache):
             self.cexecuted = self.restore_file(self.cache)
 
     def restore_file(self, file_name):
         try:
             cache = open(file_name, 'rb')
             import marshal
             cexecuted = marshal.load(cache)
             cache.close()
             if isinstance(cexecuted, types.DictType):
                 return cexecuted
             else:
                 return {}
         except:
             return {}
 
     # collect(). Collect data in multiple files produced by parallel mode
 
     def collect(self):
         cache_dir, local = os.path.split(self.cache)
         for f in os.listdir(cache_dir or '.'):
             if not f.startswith(local):
                 continue
 
             full_path = os.path.join(cache_dir, f)
             cexecuted = self.restore_file(full_path)
             self.merge_data(cexecuted)
 
     def merge_data(self, new_data):
         for file_name, file_data in new_data.items():
-            if self.cexecuted.has_key(file_name):
+            if file_name in self.cexecuted:
                 self.merge_file_data(self.cexecuted[file_name], file_data)
             else:
                 self.cexecuted[file_name] = file_data
 
     def merge_file_data(self, cache_data, new_data):
         for line_number in new_data.keys():
-            if not cache_data.has_key(line_number):
+            if not line_number in cache_data:
                 cache_data[line_number] = new_data[line_number]
 
     # canonical_filename(filename).  Return a canonical filename for the
     # file (that is, an absolute path with no redundant components and
     # normalized case).  See [GDR 2001-12-04b, 3.3].
 
     def canonical_filename(self, filename):
-        if not self.canonical_filename_cache.has_key(filename):
+        if not filename in self.canonical_filename_cache:
             f = filename
             if os.path.isabs(f) and not os.path.exists(f):
                 f = os.path.basename(f)
             if not os.path.isabs(f):
                 for path in [os.curdir] + sys.path:
                     g = os.path.join(path, f)
                     if os.path.exists(g):
                         f = g
                         break
             cf = os.path.normcase(os.path.abspath(f))
             self.canonical_filename_cache[filename] = cf
         return self.canonical_filename_cache[filename]
 
     # canonicalize_filenames().  Copy results from "c" to "cexecuted",
     # canonicalizing filenames on the way.  Clear the "c" map.
 
     def canonicalize_filenames(self):
         for filename, lineno in self.c.keys():
             if filename == '<string>':
                 # Can't do anything useful with exec'd strings, so skip them.
                 continue
             f = self.canonical_filename(filename)
-            if not self.cexecuted.has_key(f):
+            if not f in self.cexecuted:
                 self.cexecuted[f] = {}
             self.cexecuted[f][lineno] = 1
         self.c = {}
 
     # morf_filename(morf).  Return the filename for a module or file.
 
     def morf_filename(self, morf):
         if isinstance(morf, types.ModuleType):
             if not hasattr(morf, '__file__'):
                 raise CoverageException, "Module has no __file__ attribute."
             f = morf.__file__
         else:
             f = morf
         return self.canonical_filename(f)
 
     # analyze_morf(morf).  Analyze the module or filename passed as
     # the argument.  If the source code can't be found, raise an error.
     # Otherwise, return a tuple of (1) the canonical filename of the
     # source code for the module, (2) a list of lines of statements
     # in the source code, (3) a list of lines of excluded statements,
     # and (4), a map of line numbers to multi-line line number ranges, for
     # statements that cross lines.
 
     def analyze_morf(self, morf):
-        if self.analysis_cache.has_key(morf):
+        if morf in self.analysis_cache:
             return self.analysis_cache[morf]
         filename = self.morf_filename(morf)
         ext = os.path.splitext(filename)[1]
         if ext == '.pyc':
             if not os.path.exists(filename[0:-1]):
                 raise CoverageException, ("No source for compiled code '%s'."
                                    % filename)
             filename = filename[0:-1]
         elif ext != '.py':
             raise CoverageException, "File '%s' not Python source." % filename
         source = open(filename, 'r')
         lines, excluded_lines, line_map = self.find_executable_statements(
             source.read(), exclude=self.exclude_re
             )
         source.close()
         result = filename, lines, excluded_lines, line_map
         self.analysis_cache[morf] = result
         return result
 
     def first_line_of_tree(self, tree):
         while True:
             if len(tree) == 3 and type(tree[2]) == type(1):
                 return tree[2]
             tree = tree[1]
 
     def last_line_of_tree(self, tree):
         while True:
             if len(tree) == 3 and type(tree[2]) == type(1):
                 return tree[2]
             tree = tree[-1]
 
     def find_docstring_pass_pair(self, tree, spots):
         for i in range(1, len(tree)):
             if self.is_string_constant(tree[i]) and self.is_pass_stmt(tree[i+1]):
                 first_line = self.first_line_of_tree(tree[i])
                 last_line = self.last_line_of_tree(tree[i+1])
                 self.record_multiline(spots, first_line, last_line)
 
     def is_string_constant(self, tree):
         try:
             return tree[0] == symbol.stmt and tree[1][1][1][0] == symbol.expr_stmt
         except:
             return False
 
     def is_pass_stmt(self, tree):
         try:
             return tree[0] == symbol.stmt and tree[1][1][1][0] == symbol.pass_stmt
         except:
             return False
 
     def record_multiline(self, spots, i, j):
         for l in range(i, j+1):
             spots[l] = (i, j)
 
     def get_suite_spots(self, tree, spots):
         """ Analyze a parse tree to find suite introducers which span a number
             of lines.
         """
         for i in range(1, len(tree)):
             if type(tree[i]) == type(()):
                 if tree[i][0] == symbol.suite:
                     # Found a suite, look back for the colon and keyword.
                     lineno_colon = lineno_word = None
                     for j in range(i-1, 0, -1):
                         if tree[j][0] == token.COLON:
                             # Colons are never executed themselves: we want the
                             # line number of the last token before the colon.
                             lineno_colon = self.last_line_of_tree(tree[j-1])
                         elif tree[j][0] == token.NAME:
                             if tree[j][1] == 'elif':
                                 # Find the line number of the first non-terminal
                                 # after the keyword.
                                 t = tree[j+1]
                                 while t and token.ISNONTERMINAL(t[0]):
                                     t = t[1]
                                 if t:
                                     lineno_word = t[2]
                             else:
                                 lineno_word = tree[j][2]
                             break
                         elif tree[j][0] == symbol.except_clause:
                             # "except" clauses look like:
                             # ('except_clause', ('NAME', 'except', lineno), ...)
                             if tree[j][1][0] == token.NAME:
                                 lineno_word = tree[j][1][2]
                                 break
                     if lineno_colon and lineno_word:
                         # Found colon and keyword, mark all the lines
                         # between the two with the two line numbers.
                         self.record_multiline(spots, lineno_word, lineno_colon)
 
                     # "pass" statements are tricky: different versions of Python
                     # treat them differently, especially in the common case of a
                     # function with a doc string and a single pass statement.
                     self.find_docstring_pass_pair(tree[i], spots)
 
                 elif tree[i][0] == symbol.simple_stmt:
                     first_line = self.first_line_of_tree(tree[i])
                     last_line = self.last_line_of_tree(tree[i])
                     if first_line != last_line:
                         self.record_multiline(spots, first_line, last_line)
                 self.get_suite_spots(tree[i], spots)
 
     def find_executable_statements(self, text, exclude=None):
         # Find lines which match an exclusion pattern.
         excluded = {}
         suite_spots = {}
         if exclude:
             reExclude = re.compile(exclude)
             lines = text.split('\n')
             for i in range(len(lines)):
                 if reExclude.search(lines[i]):
                     excluded[i+1] = 1
 
         # Parse the code and analyze the parse tree to find out which statements
         # are multiline, and where suites begin and end.
         import parser
         tree = parser.suite(text+'\n\n').totuple(1)
         self.get_suite_spots(tree, suite_spots)
         #print "Suite spots:", suite_spots
 
         # Use the compiler module to parse the text and find the executable
         # statements.  We add newlines to be impervious to final partial lines.
         statements = {}
         ast = compiler.parse(text+'\n\n')
         visitor = StatementFindingAstVisitor(statements, excluded, suite_spots)
         compiler.walk(ast, visitor, walker=visitor)
 
         lines = statements.keys()
         lines.sort()
         excluded_lines = excluded.keys()
         excluded_lines.sort()
         return lines, excluded_lines, suite_spots
 
     # format_lines(statements, lines).  Format a list of line numbers
     # for printing by coalescing groups of lines as long as the lines
     # represent consecutive statements.  This will coalesce even if
     # there are gaps between statements, so if statements =
     # [1,2,3,4,5,10,11,12,13,14] and lines = [1,2,5,10,11,13,14] then
     # format_lines will return "1-2, 5-11, 13-14".
 
     def format_lines(self, statements, lines):
         pairs = []
         i = 0
         j = 0
         start = None
         pairs = []
         while i < len(statements) and j < len(lines):
             if statements[i] == lines[j]:
                 if start == None:
                     start = lines[j]
                 end = lines[j]
                 j = j + 1
             elif start:
                 pairs.append((start, end))
                 start = None
             i = i + 1
         if start:
             pairs.append((start, end))
         def stringify(pair):
             start, end = pair
             if start == end:
                 return "%d" % start
             else:
                 return "%d-%d" % (start, end)
         ret = string.join(map(stringify, pairs), ", ")
         return ret
 
     # Backward compatibility with version 1.
     def analysis(self, morf):
         f, s, _, m, mf = self.analysis2(morf)
         return f, s, m, mf
 
     def analysis2(self, morf):
         filename, statements, excluded, line_map = self.analyze_morf(morf)
         self.canonicalize_filenames()
-        if not self.cexecuted.has_key(filename):
+        if not filename in self.cexecuted:
             self.cexecuted[filename] = {}
         missing = []
         for line in statements:
             lines = line_map.get(line, [line, line])
             for l in range(lines[0], lines[1]+1):
-                if self.cexecuted[filename].has_key(l):
+                if l in self.cexecuted[filename]:
                     break
             else:
                 missing.append(line)
         return (filename, statements, excluded, missing,
                 self.format_lines(statements, missing))
 
     def relative_filename(self, filename):
         """ Convert filename to relative filename from self.relative_dir.
         """
         return filename.replace(self.relative_dir, "")
 
     def morf_name(self, morf):
         """ Return the name of morf as used in report.
         """
         if isinstance(morf, types.ModuleType):
             return morf.__name__
         else:
             return self.relative_filename(os.path.splitext(morf)[0])
 
     def filter_by_prefix(self, morfs, omit_prefixes):
         """ Return list of morfs where the morf name does not begin
             with any one of the omit_prefixes.
         """
         filtered_morfs = []
         for morf in morfs:
             for prefix in omit_prefixes:
                 if self.morf_name(morf).startswith(prefix):
                     break
             else:
                 filtered_morfs.append(morf)
 
         return filtered_morfs
 
     def morf_name_compare(self, x, y):
         return cmp(self.morf_name(x), self.morf_name(y))
 
     def report(self, morfs, show_missing=1, ignore_errors=0, file=None, omit_prefixes=[]):
         if not isinstance(morfs, types.ListType):
             morfs = [morfs]
         # On windows, the shell doesn't expand wildcards.  Do it here.
         globbed = []
         for morf in morfs:
             if isinstance(morf, strclass):
                 globbed.extend(glob.glob(morf))
             else:
                 globbed.append(morf)
         morfs = globbed
 
         morfs = self.filter_by_prefix(morfs, omit_prefixes)
         morfs.sort(self.morf_name_compare)
 
         max_name = max([5,] + map(len, map(self.morf_name, morfs)))
         fmt_name = "%%- %ds  " % max_name
         fmt_err = fmt_name + "%s: %s"
         header = fmt_name % "Name" + " Stmts   Exec  Cover"
         fmt_coverage = fmt_name + "% 6d % 6d % 5d%%"
         if show_missing:
             header = header + "   Missing"
             fmt_coverage = fmt_coverage + "   %s"
         if not file:
             file = sys.stdout
         print >>file, header
         print >>file, "-" * len(header)
         total_statements = 0
         total_executed = 0
         for morf in morfs:
             name = self.morf_name(morf)
             try:
                 _, statements, _, missing, readable  = self.analysis2(morf)
                 n = len(statements)
                 m = n - len(missing)
                 if n > 0:
                     pc = 100.0 * m / n
                 else:
                     pc = 100.0
                 args = (name, n, m, pc)
                 if show_missing:
                     args = args + (readable,)
                 print >>file, fmt_coverage % args
                 total_statements = total_statements + n
                 total_executed = total_executed + m
             except KeyboardInterrupt:                       #pragma: no cover
                 raise
             except:
                 if not ignore_errors:
                     typ, msg = sys.exc_info()[0:2]
                     print >>file, fmt_err % (name, typ, msg)
         if len(morfs) > 1:
             print >>file, "-" * len(header)
             if total_statements > 0:
                 pc = 100.0 * total_executed / total_statements
             else:
                 pc = 100.0
             args = ("TOTAL", total_statements, total_executed, pc)
             if show_missing:
                 args = args + ("",)
             print >>file, fmt_coverage % args
 
     # annotate(morfs, ignore_errors).
 
     blank_re = re.compile(r"\s*(#|$)")
     else_re = re.compile(r"\s*else\s*:\s*(#|$)")
 
     def annotate(self, morfs, directory=None, ignore_errors=0, omit_prefixes=[]):
         morfs = self.filter_by_prefix(morfs, omit_prefixes)
         for morf in morfs:
             try:
                 filename, statements, excluded, missing, _ = self.analysis2(morf)
                 self.annotate_file(filename, statements, excluded, missing, directory)
             except KeyboardInterrupt:
                 raise
             except:
                 if not ignore_errors:
                     raise
 
     def annotate_file(self, filename, statements, excluded, missing, directory=None):
         source = open(filename, 'r')
         if directory:
             dest_file = os.path.join(directory,
                                      os.path.basename(filename)
                                      + ',cover')
         else:
             dest_file = filename + ',cover'
         dest = open(dest_file, 'w')
         lineno = 0
         i = 0
         j = 0
         covered = 1
         while 1:
             line = source.readline()
             if line == '':
                 break
             lineno = lineno + 1
             while i < len(statements) and statements[i] < lineno:
                 i = i + 1
             while j < len(missing) and missing[j] < lineno:
                 j = j + 1
             if i < len(statements) and statements[i] == lineno:
                 covered = j >= len(missing) or missing[j] > lineno
             if self.blank_re.match(line):
                 dest.write('  ')
             elif self.else_re.match(line):
                 # Special logic for lines containing only 'else:'.
                 # See [GDR 2001-12-04b, 3.2].
                 if i >= len(statements) and j >= len(missing):
                     dest.write('! ')
                 elif i >= len(statements) or j >= len(missing):
                     dest.write('> ')
                 elif statements[i] == missing[j]:
                     dest.write('! ')
                 else:
                     dest.write('> ')
             elif lineno in excluded:
                 dest.write('- ')
             elif covered:
                 dest.write('> ')
             else:
                 dest.write('! ')
             dest.write(line)
         source.close()
         dest.close()
 
 # Singleton object.
 the_coverage = coverage()
 
 # Module functions call methods in the singleton object.
 def use_cache(*args, **kw):
     return the_coverage.use_cache(*args, **kw)
 
 def start(*args, **kw):
     return the_coverage.start(*args, **kw)
 
 def stop(*args, **kw):
     return the_coverage.stop(*args, **kw)
 
 def erase(*args, **kw):
     return the_coverage.erase(*args, **kw)
 
 def begin_recursive(*args, **kw):
     return the_coverage.begin_recursive(*args, **kw)
 
 def end_recursive(*args, **kw):
     return the_coverage.end_recursive(*args, **kw)
 
 def exclude(*args, **kw):
     return the_coverage.exclude(*args, **kw)
 
 def analysis(*args, **kw):
     return the_coverage.analysis(*args, **kw)
 
 def analysis2(*args, **kw):
     return the_coverage.analysis2(*args, **kw)
 
 def report(*args, **kw):
     return the_coverage.report(*args, **kw)
 
 def annotate(*args, **kw):
     return the_coverage.annotate(*args, **kw)
 
 def annotate_file(*args, **kw):
     return the_coverage.annotate_file(*args, **kw)
 
 # Save coverage data when Python exits.  (The atexit module wasn't
 # introduced until Python 2.0, so use sys.exitfunc when it's not
 # available.)
 try:
     import atexit
     atexit.register(the_coverage.save)
 except ImportError:
     sys.exitfunc = the_coverage.save
 
 # Command-line interface.
 if __name__ == '__main__':
     the_coverage.command_line(sys.argv[1:])
 
 
 # A. REFERENCES
 #
 # [GDR 2001-12-04a] "Statement coverage for Python"; Gareth Rees;
 # Ravenbrook Limited; 2001-12-04;
 # <http://www.nedbatchelder.com/code/modules/rees-coverage.html>.
 #
 # [GDR 2001-12-04b] "Statement coverage for Python: design and
 # analysis"; Gareth Rees; Ravenbrook Limited; 2001-12-04;
 # <http://www.nedbatchelder.com/code/modules/rees-design.html>.
 #
 # [van Rossum 2001-07-20a] "Python Reference Manual (releae 2.1.1)";
 # Guide van Rossum; 2001-07-20;
 # <http://www.python.org/doc/2.1.1/ref/ref.html>.
 #
 # [van Rossum 2001-07-20b] "Python Library Reference"; Guido van Rossum;
 # 2001-07-20; <http://www.python.org/doc/2.1.1/lib/lib.html>.
 #
 #
 # B. DOCUMENT HISTORY
 #
 # 2001-12-04 GDR Created.
 #
 # 2001-12-06 GDR Added command-line interface and source code
 # annotation.
 #
 # 2001-12-09 GDR Moved design and interface to separate documents.
 #
 # 2001-12-10 GDR Open cache file as binary on Windows.  Allow
 # simultaneous -e and -x, or -a and -r.
 #
 # 2001-12-12 GDR Added command-line help.  Cache analysis so that it
 # only needs to be done once when you specify -a and -r.
 #
 # 2001-12-13 GDR Improved speed while recording.  Portable between
 # Python 1.5.2 and 2.1.1.
 #
 # 2002-01-03 GDR Module-level functions work correctly.
 #
 # 2002-01-07 GDR Update sys.path when running a file with the -x option,
 # so that it matches the value the program would get if it were run on
 # its own.
 #
 # 2004-12-12 NMB Significant code changes.
 # - Finding executable statements has been rewritten so that docstrings and
 #   other quirks of Python execution aren't mistakenly identified as missing
 #   lines.
 # - Lines can be excluded from consideration, even entire suites of lines.
 # - The filesystem cache of covered lines can be disabled programmatically.
 # - Modernized the code.
 #
 # 2004-12-14 NMB Minor tweaks.  Return 'analysis' to its original behavior
 # and add 'analysis2'.  Add a global for 'annotate', and factor it, adding
 # 'annotate_file'.
 #
 # 2004-12-31 NMB Allow for keyword arguments in the module global functions.
 # Thanks, Allen.
 #
 # 2005-12-02 NMB Call threading.settrace so that all threads are measured.
 # Thanks Martin Fuzzey. Add a file argument to report so that reports can be
 # captured to a different destination.
 #
 # 2005-12-03 NMB coverage.py can now measure itself.
 #
 # 2005-12-04 NMB Adapted Greg Rogers' patch for using relative filenames,
 # and sorting and omitting files to report on.
 #
 # 2006-07-23 NMB Applied Joseph Tate's patch for function decorators.
 #
 # 2006-08-21 NMB Applied Sigve Tjora and Mark van der Wal's fixes for argument
 # handling.
 #
 # 2006-08-22 NMB Applied Geoff Bache's parallel mode patch.
 #
 # 2006-08-23 NMB Refactorings to improve testability.  Fixes to command-line
 # logic for parallel mode and collect.
 #
 # 2006-08-25 NMB "#pragma: nocover" is excluded by default.
 #
 # 2006-09-10 NMB Properly ignore docstrings and other constant expressions that
 # appear in the middle of a function, a problem reported by Tim Leslie.
 # Minor changes to avoid lint warnings.
 #
 # 2006-09-17 NMB coverage.erase() shouldn't clobber the exclude regex.
 # Change how parallel mode is invoked, and fix erase() so that it erases the
 # cache when called programmatically.
 #
 # 2007-07-21 NMB In reports, ignore code executed from strings, since we can't
 # do anything useful with it anyway.
 # Better file handling on Linux, thanks Guillaume Chazarain.
 # Better shell support on Windows, thanks Noel O'Boyle.
 # Python 2.2 support maintained, thanks Catherine Proulx.
 #
 # 2007-07-22 NMB Python 2.5 now fully supported. The method of dealing with
 # multi-line statements is now less sensitive to the exact line that Python
 # reports during execution. Pass statements are handled specially so that their
 # disappearance during execution won't throw off the measurement.
 #
 # 2007-07-23 NMB Now Python 2.5 is *really* fully supported: the body of the
 # new with statement is counted as executable.
 #
 # 2007-07-29 NMB Better packaging.
 
 # C. COPYRIGHT AND LICENCE
 #
 # Copyright 2001 Gareth Rees.  All rights reserved.
 # Copyright 2004-2007 Ned Batchelder.  All rights reserved.
 #
 # Redistribution and use in source and binary forms, with or without
 # modification, are permitted provided that the following conditions are
 # met:
 #
 # 1. Redistributions of source code must retain the above copyright
 #    notice, this list of conditions and the following disclaimer.
 #
 # 2. Redistributions in binary form must reproduce the above copyright
 #    notice, this list of conditions and the following disclaimer in the
 #    documentation and/or other materials provided with the
 #    distribution.
 #
 # THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
 # "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
 # LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
 # A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
 # HOLDERS AND CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
 # INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
 # BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS
 # OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
 # ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR
 # TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE
 # USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH
 # DAMAGE.
 #
 # $Id: coverage.py 74 2007-07-29 22:28:35Z nedbat $