mercurial: switch to util.timer for all interval timings

util.timer is now the best available interval timer, at the expense of not
having a known epoch. Let's use it whenever the epoch is irrelevant.

contrib/hgperf

@@ -1,100 +1,98
 #!/usr/bin/env python
 #
 # hgperf - measure performance of Mercurial commands
 #
 # Copyright 2014 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 '''measure performance of Mercurial commands
 
 Using ``hgperf`` instead of ``hg`` measures performance of the target
 Mercurial command. For example, the execution below measures
 performance of :hg:`heads --topo`::
 
     $ hgperf heads --topo
 
 All command output via ``ui`` is suppressed, and just measurement
 result is displayed: see also "perf" extension in "contrib".
 
 Costs of processing before dispatching to the command function like
 below are not measured::
 
     - parsing command line (e.g. option validity check)
     - reading configuration files in
 
 But ``pre-`` and ``post-`` hook invocation for the target command is
 measured, even though these are invoked before or after dispatching to
 the command function, because these may be required to repeat
 execution of the target command correctly.
 '''
 
 import os
 import sys
 
 libdir = '@LIBDIR@'
 
 if libdir != '@' 'LIBDIR' '@':
     if not os.path.isabs(libdir):
         libdir = os.path.join(os.path.dirname(os.path.realpath(__file__)),
                               libdir)
         libdir = os.path.abspath(libdir)
     sys.path.insert(0, libdir)
 
 # enable importing on demand to reduce startup time
 try:
     from mercurial import demandimport; demandimport.enable()
 except ImportError:
     import sys
     sys.stderr.write("abort: couldn't find mercurial libraries in [%s]\n" %
                      ' '.join(sys.path))
     sys.stderr.write("(check your install and PYTHONPATH)\n")
     sys.exit(-1)
 
 import mercurial.util
 import mercurial.dispatch
 
-import time
-
 def timer(func, title=None):
     results = []
-    begin = time.time()
+    begin = mercurial.util.timer()
     count = 0
     while True:
         ostart = os.times()
-        cstart = time.time()
+        cstart = mercurial.util.timer()
         r = func()
-        cstop = time.time()
+        cstop = mercurial.util.timer()
         ostop = os.times()
         count += 1
         a, b = ostart, ostop
         results.append((cstop - cstart, b[0] - a[0], b[1]-a[1]))
         if cstop - begin > 3 and count >= 100:
             break
         if cstop - begin > 10 and count >= 3:
             break
     if title:
         sys.stderr.write("! %s\n" % title)
     if r:
         sys.stderr.write("! result: %s\n" % r)
     m = min(results)
     sys.stderr.write("! wall %f comb %f user %f sys %f (best of %d)\n"
                      % (m[0], m[1] + m[2], m[1], m[2], count))
 
 orgruncommand = mercurial.dispatch.runcommand
 
 def runcommand(lui, repo, cmd, fullargs, ui, options, d, cmdpats, cmdoptions):
     ui.pushbuffer()
     lui.pushbuffer()
     timer(lambda : orgruncommand(lui, repo, cmd, fullargs, ui,
                                  options, d, cmdpats, cmdoptions))
     ui.popbuffer()
     lui.popbuffer()
 
 mercurial.dispatch.runcommand = runcommand
 
 for fp in (sys.stdin, sys.stdout, sys.stderr):
     mercurial.util.setbinary(fp)
 
 mercurial.dispatch.run()

contrib/perf.py

@@ -1,1285 +1,1285
 # perf.py - performance test routines
 '''helper extension to measure performance'''
 
 # "historical portability" policy of perf.py:
 #
 # We have to do:
 # - make perf.py "loadable" with as wide Mercurial version as possible
 #   This doesn't mean that perf commands work correctly with that Mercurial.
 #   BTW, perf.py itself has been available since 1.1 (or eb240755386d).
 # - make historical perf command work correctly with as wide Mercurial
 #   version as possible
 #
 # We have to do, if possible with reasonable cost:
 # - make recent perf command for historical feature work correctly
 #   with early Mercurial
 #
 # We don't have to do:
 # - make perf command for recent feature work correctly with early
 #   Mercurial
 
 from __future__ import absolute_import
 import functools
 import os
 import random
 import sys
 import time
 from mercurial import (
     bdiff,
     changegroup,
     cmdutil,
     commands,
     copies,
     error,
     extensions,
     mdiff,
     merge,
     util,
 )
 
 # for "historical portability":
 # try to import modules separately (in dict order), and ignore
 # failure, because these aren't available with early Mercurial
 try:
     from mercurial import branchmap # since 2.5 (or bcee63733aad)
 except ImportError:
     pass
 try:
     from mercurial import obsolete # since 2.3 (or ad0d6c2b3279)
 except ImportError:
     pass
 try:
     from mercurial import repoview # since 2.5 (or 3a6ddacb7198)
 except ImportError:
     pass
 try:
     from mercurial import scmutil # since 1.9 (or 8b252e826c68)
 except ImportError:
     pass
 
 # for "historical portability":
 # define util.safehasattr forcibly, because util.safehasattr has been
 # available since 1.9.3 (or 94b200a11cf7)
 _undefined = object()
 def safehasattr(thing, attr):
     return getattr(thing, attr, _undefined) is not _undefined
 setattr(util, 'safehasattr', safehasattr)
 
 # for "historical portability":
 # use locally defined empty option list, if formatteropts isn't
 # available, because commands.formatteropts has been available since
 # 3.2 (or 7a7eed5176a4), even though formatting itself has been
 # available since 2.2 (or ae5f92e154d3)
 formatteropts = getattr(commands, "formatteropts", [])
 
 # for "historical portability":
 # use locally defined option list, if debugrevlogopts isn't available,
 # because commands.debugrevlogopts has been available since 3.7 (or
 # 5606f7d0d063), even though cmdutil.openrevlog() has been available
 # since 1.9 (or a79fea6b3e77).
 revlogopts = getattr(commands, "debugrevlogopts", [
         ('c', 'changelog', False, ('open changelog')),
         ('m', 'manifest', False, ('open manifest')),
         ('', 'dir', False, ('open directory manifest')),
         ])
 
 cmdtable = {}
 
 # for "historical portability":
 # define parsealiases locally, because cmdutil.parsealiases has been
 # available since 1.5 (or 6252852b4332)
 def parsealiases(cmd):
     return cmd.lstrip("^").split("|")
 
 if safehasattr(cmdutil, 'command'):
     import inspect
     command = cmdutil.command(cmdtable)
     if 'norepo' not in inspect.getargspec(command)[0]:
         # for "historical portability":
         # wrap original cmdutil.command, because "norepo" option has
         # been available since 3.1 (or 75a96326cecb)
         _command = command
         def command(name, options=(), synopsis=None, norepo=False):
             if norepo:
                 commands.norepo += ' %s' % ' '.join(parsealiases(name))
             return _command(name, list(options), synopsis)
 else:
     # for "historical portability":
     # define "@command" annotation locally, because cmdutil.command
     # has been available since 1.9 (or 2daa5179e73f)
     def command(name, options=(), synopsis=None, norepo=False):
         def decorator(func):
             if synopsis:
                 cmdtable[name] = func, list(options), synopsis
             else:
                 cmdtable[name] = func, list(options)
             if norepo:
                 commands.norepo += ' %s' % ' '.join(parsealiases(name))
             return func
         return decorator
 
 def getlen(ui):
     if ui.configbool("perf", "stub"):
         return lambda x: 1
     return len
 
 def gettimer(ui, opts=None):
     """return a timer function and formatter: (timer, formatter)
 
     This function exists to gather the creation of formatter in a single
     place instead of duplicating it in all performance commands."""
 
     # enforce an idle period before execution to counteract power management
     # experimental config: perf.presleep
     time.sleep(getint(ui, "perf", "presleep", 1))
 
     if opts is None:
         opts = {}
     # redirect all to stderr unless buffer api is in use
     if not ui._buffers:
         ui = ui.copy()
         uifout = safeattrsetter(ui, 'fout', ignoremissing=True)
         if uifout:
             # for "historical portability":
             # ui.fout/ferr have been available since 1.9 (or 4e1ccd4c2b6d)
             uifout.set(ui.ferr)
 
     # get a formatter
     uiformatter = getattr(ui, 'formatter', None)
     if uiformatter:
         fm = uiformatter('perf', opts)
     else:
         # for "historical portability":
         # define formatter locally, because ui.formatter has been
         # available since 2.2 (or ae5f92e154d3)
         from mercurial import node
         class defaultformatter(object):
             """Minimized composition of baseformatter and plainformatter
             """
             def __init__(self, ui, topic, opts):
                 self._ui = ui
                 if ui.debugflag:
                     self.hexfunc = node.hex
                 else:
                     self.hexfunc = node.short
             def __nonzero__(self):
                 return False
             def startitem(self):
                 pass
             def data(self, **data):
                 pass
             def write(self, fields, deftext, *fielddata, **opts):
                 self._ui.write(deftext % fielddata, **opts)
             def condwrite(self, cond, fields, deftext, *fielddata, **opts):
                 if cond:
                     self._ui.write(deftext % fielddata, **opts)
             def plain(self, text, **opts):
                 self._ui.write(text, **opts)
             def end(self):
                 pass
         fm = defaultformatter(ui, 'perf', opts)
 
     # stub function, runs code only once instead of in a loop
     # experimental config: perf.stub
     if ui.configbool("perf", "stub"):
         return functools.partial(stub_timer, fm), fm
     return functools.partial(_timer, fm), fm
 
 def stub_timer(fm, func, title=None):
     func()
 
 def _timer(fm, func, title=None):
     results = []
-    begin = time.time()
+    begin = util.timer()
     count = 0
     while True:
         ostart = os.times()
-        cstart = time.time()
+        cstart = util.timer()
         r = func()
-        cstop = time.time()
+        cstop = util.timer()
         ostop = os.times()
         count += 1
         a, b = ostart, ostop
         results.append((cstop - cstart, b[0] - a[0], b[1]-a[1]))
         if cstop - begin > 3 and count >= 100:
             break
         if cstop - begin > 10 and count >= 3:
             break
 
     fm.startitem()
 
     if title:
         fm.write('title', '! %s\n', title)
     if r:
         fm.write('result', '! result: %s\n', r)
     m = min(results)
     fm.plain('!')
     fm.write('wall', ' wall %f', m[0])
     fm.write('comb', ' comb %f', m[1] + m[2])
     fm.write('user', ' user %f', m[1])
     fm.write('sys',  ' sys %f', m[2])
     fm.write('count',  ' (best of %d)', count)
     fm.plain('\n')
 
 # utilities for historical portability
 
 def getint(ui, section, name, default):
     # for "historical portability":
     # ui.configint has been available since 1.9 (or fa2b596db182)
     v = ui.config(section, name, None)
     if v is None:
         return default
     try:
         return int(v)
     except ValueError:
         raise error.ConfigError(("%s.%s is not an integer ('%s')")
                                 % (section, name, v))
 
 def safeattrsetter(obj, name, ignoremissing=False):
     """Ensure that 'obj' has 'name' attribute before subsequent setattr
 
     This function is aborted, if 'obj' doesn't have 'name' attribute
     at runtime. This avoids overlooking removal of an attribute, which
     breaks assumption of performance measurement, in the future.
 
     This function returns the object to (1) assign a new value, and
     (2) restore an original value to the attribute.
 
     If 'ignoremissing' is true, missing 'name' attribute doesn't cause
     abortion, and this function returns None. This is useful to
     examine an attribute, which isn't ensured in all Mercurial
     versions.
     """
     if not util.safehasattr(obj, name):
         if ignoremissing:
             return None
         raise error.Abort(("missing attribute %s of %s might break assumption"
                            " of performance measurement") % (name, obj))
 
     origvalue = getattr(obj, name)
     class attrutil(object):
         def set(self, newvalue):
             setattr(obj, name, newvalue)
         def restore(self):
             setattr(obj, name, origvalue)
 
     return attrutil()
 
 # utilities to examine each internal API changes
 
 def getbranchmapsubsettable():
     # for "historical portability":
     # subsettable is defined in:
     # - branchmap since 2.9 (or 175c6fd8cacc)
     # - repoview since 2.5 (or 59a9f18d4587)
     for mod in (branchmap, repoview):
         subsettable = getattr(mod, 'subsettable', None)
         if subsettable:
             return subsettable
 
     # bisecting in bcee63733aad::59a9f18d4587 can reach here (both
     # branchmap and repoview modules exist, but subsettable attribute
     # doesn't)
     raise error.Abort(("perfbranchmap not available with this Mercurial"),
                       hint="use 2.5 or later")
 
 def getsvfs(repo):
     """Return appropriate object to access files under .hg/store
     """
     # for "historical portability":
     # repo.svfs has been available since 2.3 (or 7034365089bf)
     svfs = getattr(repo, 'svfs', None)
     if svfs:
         return svfs
     else:
         return getattr(repo, 'sopener')
 
 def getvfs(repo):
     """Return appropriate object to access files under .hg
     """
     # for "historical portability":
     # repo.vfs has been available since 2.3 (or 7034365089bf)
     vfs = getattr(repo, 'vfs', None)
     if vfs:
         return vfs
     else:
         return getattr(repo, 'opener')
 
 def repocleartagscachefunc(repo):
     """Return the function to clear tags cache according to repo internal API
     """
     if util.safehasattr(repo, '_tagscache'): # since 2.0 (or 9dca7653b525)
         # in this case, setattr(repo, '_tagscache', None) or so isn't
         # correct way to clear tags cache, because existing code paths
         # expect _tagscache to be a structured object.
         def clearcache():
             # _tagscache has been filteredpropertycache since 2.5 (or
             # 98c867ac1330), and delattr() can't work in such case
             if '_tagscache' in vars(repo):
                 del repo.__dict__['_tagscache']
         return clearcache
 
     repotags = safeattrsetter(repo, '_tags', ignoremissing=True)
     if repotags: # since 1.4 (or 5614a628d173)
         return lambda : repotags.set(None)
 
     repotagscache = safeattrsetter(repo, 'tagscache', ignoremissing=True)
     if repotagscache: # since 0.6 (or d7df759d0e97)
         return lambda : repotagscache.set(None)
 
     # Mercurial earlier than 0.6 (or d7df759d0e97) logically reaches
     # this point, but it isn't so problematic, because:
     # - repo.tags of such Mercurial isn't "callable", and repo.tags()
     #   in perftags() causes failure soon
     # - perf.py itself has been available since 1.1 (or eb240755386d)
     raise error.Abort(("tags API of this hg command is unknown"))
 
 # perf commands
 
 @command('perfwalk', formatteropts)
 def perfwalk(ui, repo, *pats, **opts):
     timer, fm = gettimer(ui, opts)
     try:
         m = scmutil.match(repo[None], pats, {})
         timer(lambda: len(list(repo.dirstate.walk(m, [], True, False))))
     except Exception:
         try:
             m = scmutil.match(repo[None], pats, {})
             timer(lambda: len([b for a, b, c in repo.dirstate.statwalk([], m)]))
         except Exception:
             timer(lambda: len(list(cmdutil.walk(repo, pats, {}))))
     fm.end()
 
 @command('perfannotate', formatteropts)
 def perfannotate(ui, repo, f, **opts):
     timer, fm = gettimer(ui, opts)
     fc = repo['.'][f]
     timer(lambda: len(fc.annotate(True)))
     fm.end()
 
 @command('perfstatus',
          [('u', 'unknown', False,
            'ask status to look for unknown files')] + formatteropts)
 def perfstatus(ui, repo, **opts):
     #m = match.always(repo.root, repo.getcwd())
     #timer(lambda: sum(map(len, repo.dirstate.status(m, [], False, False,
     #                                                False))))
     timer, fm = gettimer(ui, opts)
     timer(lambda: sum(map(len, repo.status(unknown=opts['unknown']))))
     fm.end()
 
 @command('perfaddremove', formatteropts)
 def perfaddremove(ui, repo, **opts):
     timer, fm = gettimer(ui, opts)
     try:
         oldquiet = repo.ui.quiet
         repo.ui.quiet = True
         matcher = scmutil.match(repo[None])
         timer(lambda: scmutil.addremove(repo, matcher, "", dry_run=True))
     finally:
         repo.ui.quiet = oldquiet
         fm.end()
 
 def clearcaches(cl):
     # behave somewhat consistently across internal API changes
     if util.safehasattr(cl, 'clearcaches'):
         cl.clearcaches()
     elif util.safehasattr(cl, '_nodecache'):
         from mercurial.node import nullid, nullrev
         cl._nodecache = {nullid: nullrev}
         cl._nodepos = None
 
 @command('perfheads', formatteropts)
 def perfheads(ui, repo, **opts):
     timer, fm = gettimer(ui, opts)
     cl = repo.changelog
     def d():
         len(cl.headrevs())
         clearcaches(cl)
     timer(d)
     fm.end()
 
 @command('perftags', formatteropts)
 def perftags(ui, repo, **opts):
     import mercurial.changelog
     import mercurial.manifest
     timer, fm = gettimer(ui, opts)
     svfs = getsvfs(repo)
     repocleartagscache = repocleartagscachefunc(repo)
     def t():
         repo.changelog = mercurial.changelog.changelog(svfs)
         repo.manifestlog = mercurial.manifest.manifestlog(svfs, repo)
         repocleartagscache()
         return len(repo.tags())
     timer(t)
     fm.end()
 
 @command('perfancestors', formatteropts)
 def perfancestors(ui, repo, **opts):
     timer, fm = gettimer(ui, opts)
     heads = repo.changelog.headrevs()
     def d():
         for a in repo.changelog.ancestors(heads):
             pass
     timer(d)
     fm.end()
 
 @command('perfancestorset', formatteropts)
 def perfancestorset(ui, repo, revset, **opts):
     timer, fm = gettimer(ui, opts)
     revs = repo.revs(revset)
     heads = repo.changelog.headrevs()
     def d():
         s = repo.changelog.ancestors(heads)
         for rev in revs:
             rev in s
     timer(d)
     fm.end()
 
 @command('perfchangegroupchangelog', formatteropts +
          [('', 'version', '02', 'changegroup version'),
           ('r', 'rev', '', 'revisions to add to changegroup')])
 def perfchangegroupchangelog(ui, repo, version='02', rev=None, **opts):
     """Benchmark producing a changelog group for a changegroup.
 
     This measures the time spent processing the changelog during a
     bundle operation. This occurs during `hg bundle` and on a server
     processing a `getbundle` wire protocol request (handles clones
     and pull requests).
 
     By default, all revisions are added to the changegroup.
     """
     cl = repo.changelog
     revs = [cl.lookup(r) for r in repo.revs(rev or 'all()')]
     bundler = changegroup.getbundler(version, repo)
 
     def lookup(node):
         # The real bundler reads the revision in order to access the
         # manifest node and files list. Do that here.
         cl.read(node)
         return node
 
     def d():
         for chunk in bundler.group(revs, cl, lookup):
             pass
 
     timer, fm = gettimer(ui, opts)
     timer(d)
     fm.end()
 
 @command('perfdirs', formatteropts)
 def perfdirs(ui, repo, **opts):
     timer, fm = gettimer(ui, opts)
     dirstate = repo.dirstate
     'a' in dirstate
     def d():
         dirstate.dirs()
         del dirstate._dirs
     timer(d)
     fm.end()
 
 @command('perfdirstate', formatteropts)
 def perfdirstate(ui, repo, **opts):
     timer, fm = gettimer(ui, opts)
     "a" in repo.dirstate
     def d():
         repo.dirstate.invalidate()
         "a" in repo.dirstate
     timer(d)
     fm.end()
 
 @command('perfdirstatedirs', formatteropts)
 def perfdirstatedirs(ui, repo, **opts):
     timer, fm = gettimer(ui, opts)
     "a" in repo.dirstate
     def d():
         "a" in repo.dirstate._dirs
         del repo.dirstate._dirs
     timer(d)
     fm.end()
 
 @command('perfdirstatefoldmap', formatteropts)
 def perfdirstatefoldmap(ui, repo, **opts):
     timer, fm = gettimer(ui, opts)
     dirstate = repo.dirstate
     'a' in dirstate
     def d():
         dirstate._filefoldmap.get('a')
         del dirstate._filefoldmap
     timer(d)
     fm.end()
 
 @command('perfdirfoldmap', formatteropts)
 def perfdirfoldmap(ui, repo, **opts):
     timer, fm = gettimer(ui, opts)
     dirstate = repo.dirstate
     'a' in dirstate
     def d():
         dirstate._dirfoldmap.get('a')
         del dirstate._dirfoldmap
         del dirstate._dirs
     timer(d)
     fm.end()
 
 @command('perfdirstatewrite', formatteropts)
 def perfdirstatewrite(ui, repo, **opts):
     timer, fm = gettimer(ui, opts)
     ds = repo.dirstate
     "a" in ds
     def d():
         ds._dirty = True
         ds.write(repo.currenttransaction())
     timer(d)
     fm.end()
 
 @command('perfmergecalculate',
          [('r', 'rev', '.', 'rev to merge against')] + formatteropts)
 def perfmergecalculate(ui, repo, rev, **opts):
     timer, fm = gettimer(ui, opts)
     wctx = repo[None]
     rctx = scmutil.revsingle(repo, rev, rev)
     ancestor = wctx.ancestor(rctx)
     # we don't want working dir files to be stat'd in the benchmark, so prime
     # that cache
     wctx.dirty()
     def d():
         # acceptremote is True because we don't want prompts in the middle of
         # our benchmark
         merge.calculateupdates(repo, wctx, rctx, [ancestor], False, False,
                                acceptremote=True, followcopies=True)
     timer(d)
     fm.end()
 
 @command('perfpathcopies', [], "REV REV")
 def perfpathcopies(ui, repo, rev1, rev2, **opts):
     timer, fm = gettimer(ui, opts)
     ctx1 = scmutil.revsingle(repo, rev1, rev1)
     ctx2 = scmutil.revsingle(repo, rev2, rev2)
     def d():
         copies.pathcopies(ctx1, ctx2)
     timer(d)
     fm.end()
 
 @command('perfmanifest', [], 'REV')
 def perfmanifest(ui, repo, rev, **opts):
     timer, fm = gettimer(ui, opts)
     ctx = scmutil.revsingle(repo, rev, rev)
     t = ctx.manifestnode()
     def d():
         repo.manifestlog.clearcaches()
         repo.manifestlog[t].read()
     timer(d)
     fm.end()
 
 @command('perfchangeset', formatteropts)
 def perfchangeset(ui, repo, rev, **opts):
     timer, fm = gettimer(ui, opts)
     n = repo[rev].node()
     def d():
         repo.changelog.read(n)
         #repo.changelog._cache = None
     timer(d)
     fm.end()
 
 @command('perfindex', formatteropts)
 def perfindex(ui, repo, **opts):
     import mercurial.revlog
     timer, fm = gettimer(ui, opts)
     mercurial.revlog._prereadsize = 2**24 # disable lazy parser in old hg
     n = repo["tip"].node()
     svfs = getsvfs(repo)
     def d():
         cl = mercurial.revlog.revlog(svfs, "00changelog.i")
         cl.rev(n)
     timer(d)
     fm.end()
 
 @command('perfstartup', formatteropts)
 def perfstartup(ui, repo, **opts):
     timer, fm = gettimer(ui, opts)
     cmd = sys.argv[0]
     def d():
         if os.name != 'nt':
             os.system("HGRCPATH= %s version -q > /dev/null" % cmd)
         else:
             os.environ['HGRCPATH'] = ''
             os.system("%s version -q > NUL" % cmd)
     timer(d)
     fm.end()
 
 @command('perfparents', formatteropts)
 def perfparents(ui, repo, **opts):
     timer, fm = gettimer(ui, opts)
     # control the number of commits perfparents iterates over
     # experimental config: perf.parentscount
     count = getint(ui, "perf", "parentscount", 1000)
     if len(repo.changelog) < count:
         raise error.Abort("repo needs %d commits for this test" % count)
     repo = repo.unfiltered()
     nl = [repo.changelog.node(i) for i in xrange(count)]
     def d():
         for n in nl:
             repo.changelog.parents(n)
     timer(d)
     fm.end()
 
 @command('perfctxfiles', formatteropts)
 def perfctxfiles(ui, repo, x, **opts):
     x = int(x)
     timer, fm = gettimer(ui, opts)
     def d():
         len(repo[x].files())
     timer(d)
     fm.end()
 
 @command('perfrawfiles', formatteropts)
 def perfrawfiles(ui, repo, x, **opts):
     x = int(x)
     timer, fm = gettimer(ui, opts)
     cl = repo.changelog
     def d():
         len(cl.read(x)[3])
     timer(d)
     fm.end()
 
 @command('perflookup', formatteropts)
 def perflookup(ui, repo, rev, **opts):
     timer, fm = gettimer(ui, opts)
     timer(lambda: len(repo.lookup(rev)))
     fm.end()
 
 @command('perfrevrange', formatteropts)
 def perfrevrange(ui, repo, *specs, **opts):
     timer, fm = gettimer(ui, opts)
     revrange = scmutil.revrange
     timer(lambda: len(revrange(repo, specs)))
     fm.end()
 
 @command('perfnodelookup', formatteropts)
 def perfnodelookup(ui, repo, rev, **opts):
     timer, fm = gettimer(ui, opts)
     import mercurial.revlog
     mercurial.revlog._prereadsize = 2**24 # disable lazy parser in old hg
     n = repo[rev].node()
     cl = mercurial.revlog.revlog(getsvfs(repo), "00changelog.i")
     def d():
         cl.rev(n)
         clearcaches(cl)
     timer(d)
     fm.end()
 
 @command('perflog',
          [('', 'rename', False, 'ask log to follow renames')] + formatteropts)
 def perflog(ui, repo, rev=None, **opts):
     if rev is None:
         rev=[]
     timer, fm = gettimer(ui, opts)
     ui.pushbuffer()
     timer(lambda: commands.log(ui, repo, rev=rev, date='', user='',
                                copies=opts.get('rename')))
     ui.popbuffer()
     fm.end()
 
 @command('perfmoonwalk', formatteropts)
 def perfmoonwalk(ui, repo, **opts):
     """benchmark walking the changelog backwards
 
     This also loads the changelog data for each revision in the changelog.
     """
     timer, fm = gettimer(ui, opts)
     def moonwalk():
         for i in xrange(len(repo), -1, -1):
             ctx = repo[i]
             ctx.branch() # read changelog data (in addition to the index)
     timer(moonwalk)
     fm.end()
 
 @command('perftemplating', formatteropts)
 def perftemplating(ui, repo, rev=None, **opts):
     if rev is None:
         rev=[]
     timer, fm = gettimer(ui, opts)
     ui.pushbuffer()
     timer(lambda: commands.log(ui, repo, rev=rev, date='', user='',
                                template='{date|shortdate} [{rev}:{node|short}]'
                                ' {author|person}: {desc|firstline}\n'))
     ui.popbuffer()
     fm.end()
 
 @command('perfcca', formatteropts)
 def perfcca(ui, repo, **opts):
     timer, fm = gettimer(ui, opts)
     timer(lambda: scmutil.casecollisionauditor(ui, False, repo.dirstate))
     fm.end()
 
 @command('perffncacheload', formatteropts)
 def perffncacheload(ui, repo, **opts):
     timer, fm = gettimer(ui, opts)
     s = repo.store
     def d():
         s.fncache._load()
     timer(d)
     fm.end()
 
 @command('perffncachewrite', formatteropts)
 def perffncachewrite(ui, repo, **opts):
     timer, fm = gettimer(ui, opts)
     s = repo.store
     s.fncache._load()
     lock = repo.lock()
     tr = repo.transaction('perffncachewrite')
     def d():
         s.fncache._dirty = True
         s.fncache.write(tr)
     timer(d)
     tr.close()
     lock.release()
     fm.end()
 
 @command('perffncacheencode', formatteropts)
 def perffncacheencode(ui, repo, **opts):
     timer, fm = gettimer(ui, opts)
     s = repo.store
     s.fncache._load()
     def d():
         for p in s.fncache.entries:
             s.encode(p)
     timer(d)
     fm.end()
 
 @command('perfbdiff', revlogopts + formatteropts + [
     ('', 'count', 1, 'number of revisions to test (when using --startrev)'),
     ('', 'alldata', False, 'test bdiffs for all associated revisions')],
     '-c|-m|FILE REV')
 def perfbdiff(ui, repo, file_, rev=None, count=None, **opts):
     """benchmark a bdiff between revisions
 
     By default, benchmark a bdiff between its delta parent and itself.
 
     With ``--count``, benchmark bdiffs between delta parents and self for N
     revisions starting at the specified revision.
 
     With ``--alldata``, assume the requested revision is a changeset and
     measure bdiffs for all changes related to that changeset (manifest
     and filelogs).
     """
     if opts['alldata']:
         opts['changelog'] = True
 
     if opts.get('changelog') or opts.get('manifest'):
         file_, rev = None, file_
     elif rev is None:
         raise error.CommandError('perfbdiff', 'invalid arguments')
 
     textpairs = []
 
     r = cmdutil.openrevlog(repo, 'perfbdiff', file_, opts)
 
     startrev = r.rev(r.lookup(rev))
     for rev in range(startrev, min(startrev + count, len(r) - 1)):
         if opts['alldata']:
             # Load revisions associated with changeset.
             ctx = repo[rev]
             mtext = repo.manifestlog._revlog.revision(ctx.manifestnode())
             for pctx in ctx.parents():
                 pman = repo.manifestlog._revlog.revision(pctx.manifestnode())
                 textpairs.append((pman, mtext))
 
             # Load filelog revisions by iterating manifest delta.
             man = ctx.manifest()
             pman = ctx.p1().manifest()
             for filename, change in pman.diff(man).items():
                 fctx = repo.file(filename)
                 f1 = fctx.revision(change[0][0] or -1)
                 f2 = fctx.revision(change[1][0] or -1)
                 textpairs.append((f1, f2))
         else:
             dp = r.deltaparent(rev)
             textpairs.append((r.revision(dp), r.revision(rev)))
 
     def d():
         for pair in textpairs:
             bdiff.bdiff(*pair)
 
     timer, fm = gettimer(ui, opts)
     timer(d)
     fm.end()
 
 @command('perfdiffwd', formatteropts)
 def perfdiffwd(ui, repo, **opts):
     """Profile diff of working directory changes"""
     timer, fm = gettimer(ui, opts)
     options = {
         'w': 'ignore_all_space',
         'b': 'ignore_space_change',
         'B': 'ignore_blank_lines',
         }
 
     for diffopt in ('', 'w', 'b', 'B', 'wB'):
         opts = dict((options[c], '1') for c in diffopt)
         def d():
             ui.pushbuffer()
             commands.diff(ui, repo, **opts)
             ui.popbuffer()
         title = 'diffopts: %s' % (diffopt and ('-' + diffopt) or 'none')
         timer(d, title)
     fm.end()
 
 @command('perfrevlog', revlogopts + formatteropts +
          [('d', 'dist', 100, 'distance between the revisions'),
           ('s', 'startrev', 0, 'revision to start reading at'),
           ('', 'reverse', False, 'read in reverse')],
          '-c|-m|FILE')
 def perfrevlog(ui, repo, file_=None, startrev=0, reverse=False, **opts):
     """Benchmark reading a series of revisions from a revlog.
 
     By default, we read every ``-d/--dist`` revision from 0 to tip of
     the specified revlog.
 
     The start revision can be defined via ``-s/--startrev``.
     """
     timer, fm = gettimer(ui, opts)
     _len = getlen(ui)
 
     def d():
         r = cmdutil.openrevlog(repo, 'perfrevlog', file_, opts)
 
         startrev = 0
         endrev = _len(r)
         dist = opts['dist']
 
         if reverse:
             startrev, endrev = endrev, startrev
             dist = -1 * dist
 
         for x in xrange(startrev, endrev, dist):
             r.revision(r.node(x))
 
     timer(d)
     fm.end()
 
 @command('perfrevlogchunks', revlogopts + formatteropts +
          [('e', 'engines', '', 'compression engines to use'),
           ('s', 'startrev', 0, 'revision to start at')],
          '-c|-m|FILE')
 def perfrevlogchunks(ui, repo, file_=None, engines=None, startrev=0, **opts):
     """Benchmark operations on revlog chunks.
 
     Logically, each revlog is a collection of fulltext revisions. However,
     stored within each revlog are "chunks" of possibly compressed data. This
     data needs to be read and decompressed or compressed and written.
 
     This command measures the time it takes to read+decompress and recompress
     chunks in a revlog. It effectively isolates I/O and compression performance.
     For measurements of higher-level operations like resolving revisions,
     see ``perfrevlog`` and ``perfrevlogrevision``.
     """
     rl = cmdutil.openrevlog(repo, 'perfrevlogchunks', file_, opts)
 
     # Verify engines argument.
     if engines:
         engines = set(e.strip() for e in engines.split(','))
         for engine in engines:
             try:
                 util.compressionengines[engine]
             except KeyError:
                 raise error.Abort('unknown compression engine: %s' % engine)
     else:
         engines = []
         for e in util.compengines:
             engine = util.compengines[e]
             try:
                 if engine.available():
                     engine.revlogcompressor().compress('dummy')
                     engines.append(e)
             except NotImplementedError:
                 pass
 
     revs = list(rl.revs(startrev, len(rl) - 1))
 
     def rlfh(rl):
         if rl._inline:
             return getsvfs(repo)(rl.indexfile)
         else:
             return getsvfs(repo)(rl.datafile)
 
     def doread():
         rl.clearcaches()
         for rev in revs:
             rl._chunkraw(rev, rev)
 
     def doreadcachedfh():
         rl.clearcaches()
         fh = rlfh(rl)
         for rev in revs:
             rl._chunkraw(rev, rev, df=fh)
 
     def doreadbatch():
         rl.clearcaches()
         rl._chunkraw(revs[0], revs[-1])
 
     def doreadbatchcachedfh():
         rl.clearcaches()
         fh = rlfh(rl)
         rl._chunkraw(revs[0], revs[-1], df=fh)
 
     def dochunk():
         rl.clearcaches()
         fh = rlfh(rl)
         for rev in revs:
             rl._chunk(rev, df=fh)
 
     chunks = [None]
 
     def dochunkbatch():
         rl.clearcaches()
         fh = rlfh(rl)
         # Save chunks as a side-effect.
         chunks[0] = rl._chunks(revs, df=fh)
 
     def docompress(compressor):
         rl.clearcaches()
 
         try:
             # Swap in the requested compression engine.
             oldcompressor = rl._compressor
             rl._compressor = compressor
             for chunk in chunks[0]:
                 rl.compress(chunk)
         finally:
             rl._compressor = oldcompressor
 
     benches = [
         (lambda: doread(), 'read'),
         (lambda: doreadcachedfh(), 'read w/ reused fd'),
         (lambda: doreadbatch(), 'read batch'),
         (lambda: doreadbatchcachedfh(), 'read batch w/ reused fd'),
         (lambda: dochunk(), 'chunk'),
         (lambda: dochunkbatch(), 'chunk batch'),
     ]
 
     for engine in sorted(engines):
         compressor = util.compengines[engine].revlogcompressor()
         benches.append((functools.partial(docompress, compressor),
                         'compress w/ %s' % engine))
 
     for fn, title in benches:
         timer, fm = gettimer(ui, opts)
         timer(fn, title=title)
         fm.end()
 
 @command('perfrevlogrevision', revlogopts + formatteropts +
          [('', 'cache', False, 'use caches instead of clearing')],
          '-c|-m|FILE REV')
 def perfrevlogrevision(ui, repo, file_, rev=None, cache=None, **opts):
     """Benchmark obtaining a revlog revision.
 
     Obtaining a revlog revision consists of roughly the following steps:
 
     1. Compute the delta chain
     2. Obtain the raw chunks for that delta chain
     3. Decompress each raw chunk
     4. Apply binary patches to obtain fulltext
     5. Verify hash of fulltext
 
     This command measures the time spent in each of these phases.
     """
     if opts.get('changelog') or opts.get('manifest'):
         file_, rev = None, file_
     elif rev is None:
         raise error.CommandError('perfrevlogrevision', 'invalid arguments')
 
     r = cmdutil.openrevlog(repo, 'perfrevlogrevision', file_, opts)
     node = r.lookup(rev)
     rev = r.rev(node)
 
     def getrawchunks(data, chain):
         start = r.start
         length = r.length
         inline = r._inline
         iosize = r._io.size
         buffer = util.buffer
         offset = start(chain[0])
 
         chunks = []
         ladd = chunks.append
 
         for rev in chain:
             chunkstart = start(rev)
             if inline:
                 chunkstart += (rev + 1) * iosize
             chunklength = length(rev)
             ladd(buffer(data, chunkstart - offset, chunklength))
 
         return chunks
 
     def dodeltachain(rev):
         if not cache:
             r.clearcaches()
         r._deltachain(rev)
 
     def doread(chain):
         if not cache:
             r.clearcaches()
         r._chunkraw(chain[0], chain[-1])
 
     def dorawchunks(data, chain):
         if not cache:
             r.clearcaches()
         getrawchunks(data, chain)
 
     def dodecompress(chunks):
         decomp = r.decompress
         for chunk in chunks:
             decomp(chunk)
 
     def dopatch(text, bins):
         if not cache:
             r.clearcaches()
         mdiff.patches(text, bins)
 
     def dohash(text):
         if not cache:
             r.clearcaches()
         r.checkhash(text, node, rev=rev)
 
     def dorevision():
         if not cache:
             r.clearcaches()
         r.revision(node)
 
     chain = r._deltachain(rev)[0]
     data = r._chunkraw(chain[0], chain[-1])[1]
     rawchunks = getrawchunks(data, chain)
     bins = r._chunks(chain)
     text = str(bins[0])
     bins = bins[1:]
     text = mdiff.patches(text, bins)
 
     benches = [
         (lambda: dorevision(), 'full'),
         (lambda: dodeltachain(rev), 'deltachain'),
         (lambda: doread(chain), 'read'),
         (lambda: dorawchunks(data, chain), 'rawchunks'),
         (lambda: dodecompress(rawchunks), 'decompress'),
         (lambda: dopatch(text, bins), 'patch'),
         (lambda: dohash(text), 'hash'),
     ]
 
     for fn, title in benches:
         timer, fm = gettimer(ui, opts)
         timer(fn, title=title)
         fm.end()
 
 @command('perfrevset',
          [('C', 'clear', False, 'clear volatile cache between each call.'),
           ('', 'contexts', False, 'obtain changectx for each revision')]
          + formatteropts, "REVSET")
 def perfrevset(ui, repo, expr, clear=False, contexts=False, **opts):
     """benchmark the execution time of a revset
 
     Use the --clean option if need to evaluate the impact of build volatile
     revisions set cache on the revset execution. Volatile cache hold filtered
     and obsolete related cache."""
     timer, fm = gettimer(ui, opts)
     def d():
         if clear:
             repo.invalidatevolatilesets()
         if contexts:
             for ctx in repo.set(expr): pass
         else:
             for r in repo.revs(expr): pass
     timer(d)
     fm.end()
 
 @command('perfvolatilesets', formatteropts)
 def perfvolatilesets(ui, repo, *names, **opts):
     """benchmark the computation of various volatile set
 
     Volatile set computes element related to filtering and obsolescence."""
     timer, fm = gettimer(ui, opts)
     repo = repo.unfiltered()
 
     def getobs(name):
         def d():
             repo.invalidatevolatilesets()
             obsolete.getrevs(repo, name)
         return d
 
     allobs = sorted(obsolete.cachefuncs)
     if names:
         allobs = [n for n in allobs if n in names]
 
     for name in allobs:
         timer(getobs(name), title=name)
 
     def getfiltered(name):
         def d():
             repo.invalidatevolatilesets()
             repoview.filterrevs(repo, name)
         return d
 
     allfilter = sorted(repoview.filtertable)
     if names:
         allfilter = [n for n in allfilter if n in names]
 
     for name in allfilter:
         timer(getfiltered(name), title=name)
     fm.end()
 
 @command('perfbranchmap',
          [('f', 'full', False,
            'Includes build time of subset'),
          ] + formatteropts)
 def perfbranchmap(ui, repo, full=False, **opts):
     """benchmark the update of a branchmap
 
     This benchmarks the full repo.branchmap() call with read and write disabled
     """
     timer, fm = gettimer(ui, opts)
     def getbranchmap(filtername):
         """generate a benchmark function for the filtername"""
         if filtername is None:
             view = repo
         else:
             view = repo.filtered(filtername)
         def d():
             if full:
                 view._branchcaches.clear()
             else:
                 view._branchcaches.pop(filtername, None)
             view.branchmap()
         return d
     # add filter in smaller subset to bigger subset
     possiblefilters = set(repoview.filtertable)
     subsettable = getbranchmapsubsettable()
     allfilters = []
     while possiblefilters:
         for name in possiblefilters:
             subset = subsettable.get(name)
             if subset not in possiblefilters:
                 break
         else:
             assert False, 'subset cycle %s!' % possiblefilters
         allfilters.append(name)
         possiblefilters.remove(name)
 
     # warm the cache
     if not full:
         for name in allfilters:
             repo.filtered(name).branchmap()
     # add unfiltered
     allfilters.append(None)
 
     branchcacheread = safeattrsetter(branchmap, 'read')
     branchcachewrite = safeattrsetter(branchmap.branchcache, 'write')
     branchcacheread.set(lambda repo: None)
     branchcachewrite.set(lambda bc, repo: None)
     try:
         for name in allfilters:
             timer(getbranchmap(name), title=str(name))
     finally:
         branchcacheread.restore()
         branchcachewrite.restore()
     fm.end()
 
 @command('perfloadmarkers')
 def perfloadmarkers(ui, repo):
     """benchmark the time to parse the on-disk markers for a repo
 
     Result is the number of markers in the repo."""
     timer, fm = gettimer(ui)
     svfs = getsvfs(repo)
     timer(lambda: len(obsolete.obsstore(svfs)))
     fm.end()
 
 @command('perflrucachedict', formatteropts +
     [('', 'size', 4, 'size of cache'),
      ('', 'gets', 10000, 'number of key lookups'),
      ('', 'sets', 10000, 'number of key sets'),
      ('', 'mixed', 10000, 'number of mixed mode operations'),
      ('', 'mixedgetfreq', 50, 'frequency of get vs set ops in mixed mode')],
     norepo=True)
 def perflrucache(ui, size=4, gets=10000, sets=10000, mixed=10000,
                  mixedgetfreq=50, **opts):
     def doinit():
         for i in xrange(10000):
             util.lrucachedict(size)
 
     values = []
     for i in xrange(size):
         values.append(random.randint(0, sys.maxint))
 
     # Get mode fills the cache and tests raw lookup performance with no
     # eviction.
     getseq = []
     for i in xrange(gets):
         getseq.append(random.choice(values))
 
     def dogets():
         d = util.lrucachedict(size)
         for v in values:
             d[v] = v
         for key in getseq:
             value = d[key]
             value # silence pyflakes warning
 
     # Set mode tests insertion speed with cache eviction.
     setseq = []
     for i in xrange(sets):
         setseq.append(random.randint(0, sys.maxint))
 
     def dosets():
         d = util.lrucachedict(size)
         for v in setseq:
             d[v] = v
 
     # Mixed mode randomly performs gets and sets with eviction.
     mixedops = []
     for i in xrange(mixed):
         r = random.randint(0, 100)
         if r < mixedgetfreq:
             op = 0
         else:
             op = 1
 
         mixedops.append((op, random.randint(0, size * 2)))
 
     def domixed():
         d = util.lrucachedict(size)
 
         for op, v in mixedops:
             if op == 0:
                 try:
                     d[v]
                 except KeyError:
                     pass
             else:
                 d[v] = v
 
     benches = [
         (doinit, 'init'),
         (dogets, 'gets'),
         (dosets, 'sets'),
         (domixed, 'mixed')
     ]
 
     for fn, title in benches:
         timer, fm = gettimer(ui, opts)
         timer(fn, title=title)
         fm.end()
 
 def uisetup(ui):
     if (util.safehasattr(cmdutil, 'openrevlog') and
         not util.safehasattr(commands, 'debugrevlogopts')):
         # for "historical portability":
         # In this case, Mercurial should be 1.9 (or a79fea6b3e77) -
         # 3.7 (or 5606f7d0d063). Therefore, '--dir' option for
         # openrevlog() should cause failure, because it has been
         # available since 3.5 (or 49c583ca48c4).
         def openrevlog(orig, repo, cmd, file_, opts):
             if opts.get('dir') and not util.safehasattr(repo, 'dirlog'):
                 raise error.Abort("This version doesn't support --dir option",
                                   hint="use 3.5 or later")
             return orig(repo, cmd, file_, opts)
         extensions.wrapfunction(cmdutil, 'openrevlog', openrevlog)

mercurial/branchmap.py

@@ -1,522 +1,522
 # branchmap.py - logic to computes, maintain and stores branchmap for local repo
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import array
 import struct
-import time
 
 from .node import (
     bin,
     hex,
     nullid,
     nullrev,
 )
 from . import (
     encoding,
     error,
     scmutil,
+    util,
 )
 
 array = array.array
 calcsize = struct.calcsize
 pack = struct.pack
 unpack = struct.unpack
 
 def _filename(repo):
     """name of a branchcache file for a given repo or repoview"""
     filename = "cache/branch2"
     if repo.filtername:
         filename = '%s-%s' % (filename, repo.filtername)
     return filename
 
 def read(repo):
     try:
         f = repo.vfs(_filename(repo))
         lines = f.read().split('\n')
         f.close()
     except (IOError, OSError):
         return None
 
     try:
         cachekey = lines.pop(0).split(" ", 2)
         last, lrev = cachekey[:2]
         last, lrev = bin(last), int(lrev)
         filteredhash = None
         if len(cachekey) > 2:
             filteredhash = bin(cachekey[2])
         partial = branchcache(tipnode=last, tiprev=lrev,
                               filteredhash=filteredhash)
         if not partial.validfor(repo):
             # invalidate the cache
             raise ValueError('tip differs')
         cl = repo.changelog
         for l in lines:
             if not l:
                 continue
             node, state, label = l.split(" ", 2)
             if state not in 'oc':
                 raise ValueError('invalid branch state')
             label = encoding.tolocal(label.strip())
             node = bin(node)
             if not cl.hasnode(node):
                 raise ValueError('node %s does not exist' % hex(node))
             partial.setdefault(label, []).append(node)
             if state == 'c':
                 partial._closednodes.add(node)
     except KeyboardInterrupt:
         raise
     except Exception as inst:
         if repo.ui.debugflag:
             msg = 'invalid branchheads cache'
             if repo.filtername is not None:
                 msg += ' (%s)' % repo.filtername
             msg += ': %s\n'
             repo.ui.debug(msg % inst)
         partial = None
     return partial
 
 ### Nearest subset relation
 # Nearest subset of filter X is a filter Y so that:
 # * Y is included in X,
 # * X - Y is as small as possible.
 # This create and ordering used for branchmap purpose.
 # the ordering may be partial
 subsettable = {None: 'visible',
                'visible': 'served',
                'served': 'immutable',
                'immutable': 'base'}
 
 def updatecache(repo):
     cl = repo.changelog
     filtername = repo.filtername
     partial = repo._branchcaches.get(filtername)
 
     revs = []
     if partial is None or not partial.validfor(repo):
         partial = read(repo)
         if partial is None:
             subsetname = subsettable.get(filtername)
             if subsetname is None:
                 partial = branchcache()
             else:
                 subset = repo.filtered(subsetname)
                 partial = subset.branchmap().copy()
                 extrarevs = subset.changelog.filteredrevs - cl.filteredrevs
                 revs.extend(r for  r in extrarevs if r <= partial.tiprev)
     revs.extend(cl.revs(start=partial.tiprev + 1))
     if revs:
         partial.update(repo, revs)
         partial.write(repo)
 
     assert partial.validfor(repo), filtername
     repo._branchcaches[repo.filtername] = partial
 
 def replacecache(repo, bm):
     """Replace the branchmap cache for a repo with a branch mapping.
 
     This is likely only called during clone with a branch map from a remote.
     """
     rbheads = []
     closed = []
     for bheads in bm.itervalues():
         rbheads.extend(bheads)
         for h in bheads:
             r = repo.changelog.rev(h)
             b, c = repo.changelog.branchinfo(r)
             if c:
                 closed.append(h)
 
     if rbheads:
         rtiprev = max((int(repo.changelog.rev(node))
                 for node in rbheads))
         cache = branchcache(bm,
                             repo[rtiprev].node(),
                             rtiprev,
                             closednodes=closed)
 
         # Try to stick it as low as possible
         # filter above served are unlikely to be fetch from a clone
         for candidate in ('base', 'immutable', 'served'):
             rview = repo.filtered(candidate)
             if cache.validfor(rview):
                 repo._branchcaches[candidate] = cache
                 cache.write(rview)
                 break
 
 class branchcache(dict):
     """A dict like object that hold branches heads cache.
 
     This cache is used to avoid costly computations to determine all the
     branch heads of a repo.
 
     The cache is serialized on disk in the following format:
 
     <tip hex node> <tip rev number> [optional filtered repo hex hash]
     <branch head hex node> <open/closed state> <branch name>
     <branch head hex node> <open/closed state> <branch name>
     ...
 
     The first line is used to check if the cache is still valid. If the
     branch cache is for a filtered repo view, an optional third hash is
     included that hashes the hashes of all filtered revisions.
 
     The open/closed state is represented by a single letter 'o' or 'c'.
     This field can be used to avoid changelog reads when determining if a
     branch head closes a branch or not.
     """
 
     def __init__(self, entries=(), tipnode=nullid, tiprev=nullrev,
                  filteredhash=None, closednodes=None):
         super(branchcache, self).__init__(entries)
         self.tipnode = tipnode
         self.tiprev = tiprev
         self.filteredhash = filteredhash
         # closednodes is a set of nodes that close their branch. If the branch
         # cache has been updated, it may contain nodes that are no longer
         # heads.
         if closednodes is None:
             self._closednodes = set()
         else:
             self._closednodes = closednodes
 
     def validfor(self, repo):
         """Is the cache content valid regarding a repo
 
         - False when cached tipnode is unknown or if we detect a strip.
         - True when cache is up to date or a subset of current repo."""
         try:
             return ((self.tipnode == repo.changelog.node(self.tiprev))
                     and (self.filteredhash == \
                          scmutil.filteredhash(repo, self.tiprev)))
         except IndexError:
             return False
 
     def _branchtip(self, heads):
         '''Return tuple with last open head in heads and false,
         otherwise return last closed head and true.'''
         tip = heads[-1]
         closed = True
         for h in reversed(heads):
             if h not in self._closednodes:
                 tip = h
                 closed = False
                 break
         return tip, closed
 
     def branchtip(self, branch):
         '''Return the tipmost open head on branch head, otherwise return the
         tipmost closed head on branch.
         Raise KeyError for unknown branch.'''
         return self._branchtip(self[branch])[0]
 
     def branchheads(self, branch, closed=False):
         heads = self[branch]
         if not closed:
             heads = [h for h in heads if h not in self._closednodes]
         return heads
 
     def iterbranches(self):
         for bn, heads in self.iteritems():
             yield (bn, heads) + self._branchtip(heads)
 
     def copy(self):
         """return an deep copy of the branchcache object"""
         return branchcache(self, self.tipnode, self.tiprev, self.filteredhash,
                            self._closednodes)
 
     def write(self, repo):
         try:
             f = repo.vfs(_filename(repo), "w", atomictemp=True)
             cachekey = [hex(self.tipnode), str(self.tiprev)]
             if self.filteredhash is not None:
                 cachekey.append(hex(self.filteredhash))
             f.write(" ".join(cachekey) + '\n')
             nodecount = 0
             for label, nodes in sorted(self.iteritems()):
                 for node in nodes:
                     nodecount += 1
                     if node in self._closednodes:
                         state = 'c'
                     else:
                         state = 'o'
                     f.write("%s %s %s\n" % (hex(node), state,
                                             encoding.fromlocal(label)))
             f.close()
             repo.ui.log('branchcache',
                         'wrote %s branch cache with %d labels and %d nodes\n',
                         repo.filtername, len(self), nodecount)
         except (IOError, OSError, error.Abort) as inst:
             repo.ui.debug("couldn't write branch cache: %s\n" % inst)
             # Abort may be raise by read only opener
             pass
 
     def update(self, repo, revgen):
         """Given a branchhead cache, self, that may have extra nodes or be
         missing heads, and a generator of nodes that are strictly a superset of
         heads missing, this function updates self to be correct.
         """
-        starttime = time.time()
+        starttime = util.timer()
         cl = repo.changelog
         # collect new branch entries
         newbranches = {}
         getbranchinfo = repo.revbranchcache().branchinfo
         for r in revgen:
             branch, closesbranch = getbranchinfo(r)
             newbranches.setdefault(branch, []).append(r)
             if closesbranch:
                 self._closednodes.add(cl.node(r))
 
         # fetch current topological heads to speed up filtering
         topoheads = set(cl.headrevs())
 
         # if older branchheads are reachable from new ones, they aren't
         # really branchheads. Note checking parents is insufficient:
         # 1 (branch a) -> 2 (branch b) -> 3 (branch a)
         for branch, newheadrevs in newbranches.iteritems():
             bheads = self.setdefault(branch, [])
             bheadset = set(cl.rev(node) for node in bheads)
 
             # This have been tested True on all internal usage of this function.
             # run it again in case of doubt
             # assert not (set(bheadrevs) & set(newheadrevs))
             newheadrevs.sort()
             bheadset.update(newheadrevs)
 
             # This prunes out two kinds of heads - heads that are superseded by
             # a head in newheadrevs, and newheadrevs that are not heads because
             # an existing head is their descendant.
             uncertain = bheadset - topoheads
             if uncertain:
                 floorrev = min(uncertain)
                 ancestors = set(cl.ancestors(newheadrevs, floorrev))
                 bheadset -= ancestors
             bheadrevs = sorted(bheadset)
             self[branch] = [cl.node(rev) for rev in bheadrevs]
             tiprev = bheadrevs[-1]
             if tiprev > self.tiprev:
                 self.tipnode = cl.node(tiprev)
                 self.tiprev = tiprev
 
         if not self.validfor(repo):
             # cache key are not valid anymore
             self.tipnode = nullid
             self.tiprev = nullrev
             for heads in self.values():
                 tiprev = max(cl.rev(node) for node in heads)
                 if tiprev > self.tiprev:
                     self.tipnode = cl.node(tiprev)
                     self.tiprev = tiprev
         self.filteredhash = scmutil.filteredhash(repo, self.tiprev)
 
-        duration = time.time() - starttime
+        duration = util.timer() - starttime
         repo.ui.log('branchcache', 'updated %s branch cache in %.4f seconds\n',
                     repo.filtername, duration)
 
 # Revision branch info cache
 
 _rbcversion = '-v1'
 _rbcnames = 'cache/rbc-names' + _rbcversion
 _rbcrevs = 'cache/rbc-revs' + _rbcversion
 # [4 byte hash prefix][4 byte branch name number with sign bit indicating open]
 _rbcrecfmt = '>4sI'
 _rbcrecsize = calcsize(_rbcrecfmt)
 _rbcnodelen = 4
 _rbcbranchidxmask = 0x7fffffff
 _rbccloseflag = 0x80000000
 
 class revbranchcache(object):
     """Persistent cache, mapping from revision number to branch name and close.
     This is a low level cache, independent of filtering.
 
     Branch names are stored in rbc-names in internal encoding separated by 0.
     rbc-names is append-only, and each branch name is only stored once and will
     thus have a unique index.
 
     The branch info for each revision is stored in rbc-revs as constant size
     records. The whole file is read into memory, but it is only 'parsed' on
     demand. The file is usually append-only but will be truncated if repo
     modification is detected.
     The record for each revision contains the first 4 bytes of the
     corresponding node hash, and the record is only used if it still matches.
     Even a completely trashed rbc-revs fill thus still give the right result
     while converging towards full recovery ... assuming no incorrectly matching
     node hashes.
     The record also contains 4 bytes where 31 bits contains the index of the
     branch and the last bit indicate that it is a branch close commit.
     The usage pattern for rbc-revs is thus somewhat similar to 00changelog.i
     and will grow with it but be 1/8th of its size.
     """
 
     def __init__(self, repo, readonly=True):
         assert repo.filtername is None
         self._repo = repo
         self._names = [] # branch names in local encoding with static index
         self._rbcrevs = array('c') # structs of type _rbcrecfmt
         self._rbcsnameslen = 0 # length of names read at _rbcsnameslen
         try:
             bndata = repo.vfs.read(_rbcnames)
             self._rbcsnameslen = len(bndata) # for verification before writing
             self._names = [encoding.tolocal(bn) for bn in bndata.split('\0')]
         except (IOError, OSError):
             if readonly:
                 # don't try to use cache - fall back to the slow path
                 self.branchinfo = self._branchinfo
 
         if self._names:
             try:
                 data = repo.vfs.read(_rbcrevs)
                 self._rbcrevs.fromstring(data)
             except (IOError, OSError) as inst:
                 repo.ui.debug("couldn't read revision branch cache: %s\n" %
                               inst)
         # remember number of good records on disk
         self._rbcrevslen = min(len(self._rbcrevs) // _rbcrecsize,
                                len(repo.changelog))
         if self._rbcrevslen == 0:
             self._names = []
         self._rbcnamescount = len(self._names) # number of names read at
                                                # _rbcsnameslen
         self._namesreverse = dict((b, r) for r, b in enumerate(self._names))
 
     def _clear(self):
         self._rbcsnameslen = 0
         del self._names[:]
         self._rbcnamescount = 0
         self._namesreverse.clear()
         self._rbcrevslen = len(self._repo.changelog)
         self._rbcrevs = array('c')
         self._rbcrevs.fromstring('\0' * (self._rbcrevslen * _rbcrecsize))
 
     def branchinfo(self, rev):
         """Return branch name and close flag for rev, using and updating
         persistent cache."""
         changelog = self._repo.changelog
         rbcrevidx = rev * _rbcrecsize
 
         # avoid negative index, changelog.read(nullrev) is fast without cache
         if rev == nullrev:
             return changelog.branchinfo(rev)
 
         # if requested rev isn't allocated, grow and cache the rev info
         if len(self._rbcrevs) < rbcrevidx + _rbcrecsize:
             return self._branchinfo(rev)
 
         # fast path: extract data from cache, use it if node is matching
         reponode = changelog.node(rev)[:_rbcnodelen]
         cachenode, branchidx = unpack(
             _rbcrecfmt, buffer(self._rbcrevs, rbcrevidx, _rbcrecsize))
         close = bool(branchidx & _rbccloseflag)
         if close:
             branchidx &= _rbcbranchidxmask
         if cachenode == '\0\0\0\0':
             pass
         elif cachenode == reponode:
             try:
                 return self._names[branchidx], close
             except IndexError:
                 # recover from invalid reference to unknown branch
                 self._repo.ui.debug("referenced branch names not found"
                     " - rebuilding revision branch cache from scratch\n")
                 self._clear()
         else:
             # rev/node map has changed, invalidate the cache from here up
             self._repo.ui.debug("history modification detected - truncating "
                 "revision branch cache to revision %s\n" % rev)
             truncate = rbcrevidx + _rbcrecsize
             del self._rbcrevs[truncate:]
             self._rbcrevslen = min(self._rbcrevslen, truncate)
 
         # fall back to slow path and make sure it will be written to disk
         return self._branchinfo(rev)
 
     def _branchinfo(self, rev):
         """Retrieve branch info from changelog and update _rbcrevs"""
         changelog = self._repo.changelog
         b, close = changelog.branchinfo(rev)
         if b in self._namesreverse:
             branchidx = self._namesreverse[b]
         else:
             branchidx = len(self._names)
             self._names.append(b)
             self._namesreverse[b] = branchidx
         reponode = changelog.node(rev)
         if close:
             branchidx |= _rbccloseflag
         self._setcachedata(rev, reponode, branchidx)
         return b, close
 
     def _setcachedata(self, rev, node, branchidx):
         """Writes the node's branch data to the in-memory cache data."""
         rbcrevidx = rev * _rbcrecsize
         rec = array('c')
         rec.fromstring(pack(_rbcrecfmt, node, branchidx))
         if len(self._rbcrevs) < rbcrevidx + _rbcrecsize:
             self._rbcrevs.extend('\0' *
                                  (len(self._repo.changelog) * _rbcrecsize -
                                   len(self._rbcrevs)))
         self._rbcrevs[rbcrevidx:rbcrevidx + _rbcrecsize] = rec
         self._rbcrevslen = min(self._rbcrevslen, rev)
 
         tr = self._repo.currenttransaction()
         if tr:
             tr.addfinalize('write-revbranchcache', self.write)
 
     def write(self, tr=None):
         """Save branch cache if it is dirty."""
         repo = self._repo
         wlock = None
         step = ''
         try:
             if self._rbcnamescount < len(self._names):
                 step = ' names'
                 wlock = repo.wlock(wait=False)
                 if self._rbcnamescount != 0:
                     f = repo.vfs.open(_rbcnames, 'ab')
                     if f.tell() == self._rbcsnameslen:
                         f.write('\0')
                     else:
                         f.close()
                         repo.ui.debug("%s changed - rewriting it\n" % _rbcnames)
                         self._rbcnamescount = 0
                         self._rbcrevslen = 0
                 if self._rbcnamescount == 0:
                     # before rewriting names, make sure references are removed
                     repo.vfs.unlinkpath(_rbcrevs, ignoremissing=True)
                     f = repo.vfs.open(_rbcnames, 'wb')
                 f.write('\0'.join(encoding.fromlocal(b)
                                   for b in self._names[self._rbcnamescount:]))
                 self._rbcsnameslen = f.tell()
                 f.close()
                 self._rbcnamescount = len(self._names)
 
             start = self._rbcrevslen * _rbcrecsize
             if start != len(self._rbcrevs):
                 step = ''
                 if wlock is None:
                     wlock = repo.wlock(wait=False)
                 revs = min(len(repo.changelog),
                            len(self._rbcrevs) // _rbcrecsize)
                 f = repo.vfs.open(_rbcrevs, 'ab')
                 if f.tell() != start:
                     repo.ui.debug("truncating %s to %s\n" % (_rbcrevs, start))
                     f.seek(start)
                     if f.tell() != start:
                         start = 0
                         f.seek(start)
                     f.truncate()
                 end = revs * _rbcrecsize
                 f.write(self._rbcrevs[start:end])
                 f.close()
                 self._rbcrevslen = revs
         except (IOError, OSError, error.Abort, error.LockError) as inst:
             repo.ui.debug("couldn't write revision branch cache%s: %s\n"
                           % (step, inst))
         finally:
             if wlock is not None:
                 wlock.release()

mercurial/dispatch.py

@@ -1,889 +1,889
 # dispatch.py - command dispatching for mercurial
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import, print_function
 
 import atexit
 import difflib
 import errno
 import getopt
 import os
 import pdb
 import re
 import signal
 import sys
 import time
 import traceback
 
 
 from .i18n import _
 
 from . import (
     cmdutil,
     color,
     commands,
     debugcommands,
     demandimport,
     encoding,
     error,
     extensions,
     fancyopts,
     fileset,
     hg,
     hook,
     profiling,
     pycompat,
     revset,
     scmutil,
     templatefilters,
     templatekw,
     templater,
     ui as uimod,
     util,
 )
 
 class request(object):
     def __init__(self, args, ui=None, repo=None, fin=None, fout=None,
                  ferr=None):
         self.args = args
         self.ui = ui
         self.repo = repo
 
         # input/output/error streams
         self.fin = fin
         self.fout = fout
         self.ferr = ferr
 
 def run():
     "run the command in sys.argv"
     sys.exit((dispatch(request(pycompat.sysargv[1:])) or 0) & 255)
 
 def _getsimilar(symbols, value):
     sim = lambda x: difflib.SequenceMatcher(None, value, x).ratio()
     # The cutoff for similarity here is pretty arbitrary. It should
     # probably be investigated and tweaked.
     return [s for s in symbols if sim(s) > 0.6]
 
 def _reportsimilar(write, similar):
     if len(similar) == 1:
         write(_("(did you mean %s?)\n") % similar[0])
     elif similar:
         ss = ", ".join(sorted(similar))
         write(_("(did you mean one of %s?)\n") % ss)
 
 def _formatparse(write, inst):
     similar = []
     if isinstance(inst, error.UnknownIdentifier):
         # make sure to check fileset first, as revset can invoke fileset
         similar = _getsimilar(inst.symbols, inst.function)
     if len(inst.args) > 1:
         write(_("hg: parse error at %s: %s\n") %
                          (inst.args[1], inst.args[0]))
         if (inst.args[0][0] == ' '):
             write(_("unexpected leading whitespace\n"))
     else:
         write(_("hg: parse error: %s\n") % inst.args[0])
         _reportsimilar(write, similar)
     if inst.hint:
         write(_("(%s)\n") % inst.hint)
 
 def dispatch(req):
     "run the command specified in req.args"
     if req.ferr:
         ferr = req.ferr
     elif req.ui:
         ferr = req.ui.ferr
     else:
         ferr = util.stderr
 
     try:
         if not req.ui:
             req.ui = uimod.ui.load()
         if '--traceback' in req.args:
             req.ui.setconfig('ui', 'traceback', 'on', '--traceback')
 
         # set ui streams from the request
         if req.fin:
             req.ui.fin = req.fin
         if req.fout:
             req.ui.fout = req.fout
         if req.ferr:
             req.ui.ferr = req.ferr
     except error.Abort as inst:
         ferr.write(_("abort: %s\n") % inst)
         if inst.hint:
             ferr.write(_("(%s)\n") % inst.hint)
         return -1
     except error.ParseError as inst:
         _formatparse(ferr.write, inst)
         return -1
 
     msg = ' '.join(' ' in a and repr(a) or a for a in req.args)
-    starttime = time.time()
+    starttime = util.timer()
     ret = None
     try:
         ret = _runcatch(req)
     except KeyboardInterrupt:
         try:
             req.ui.warn(_("interrupted!\n"))
         except IOError as inst:
             if inst.errno != errno.EPIPE:
                 raise
         ret = -1
     finally:
-        duration = time.time() - starttime
+        duration = util.timer() - starttime
         req.ui.flush()
         req.ui.log("commandfinish", "%s exited %s after %0.2f seconds\n",
                    msg, ret or 0, duration)
     return ret
 
 def _runcatch(req):
     def catchterm(*args):
         raise error.SignalInterrupt
 
     ui = req.ui
     try:
         for name in 'SIGBREAK', 'SIGHUP', 'SIGTERM':
             num = getattr(signal, name, None)
             if num:
                 signal.signal(num, catchterm)
     except ValueError:
         pass # happens if called in a thread
 
     def _runcatchfunc():
         try:
             debugger = 'pdb'
             debugtrace = {
                 'pdb' : pdb.set_trace
             }
             debugmortem = {
                 'pdb' : pdb.post_mortem
             }
 
             # read --config before doing anything else
             # (e.g. to change trust settings for reading .hg/hgrc)
             cfgs = _parseconfig(req.ui, _earlygetopt(['--config'], req.args))
 
             if req.repo:
                 # copy configs that were passed on the cmdline (--config) to
                 # the repo ui
                 for sec, name, val in cfgs:
                     req.repo.ui.setconfig(sec, name, val, source='--config')
 
             # developer config: ui.debugger
             debugger = ui.config("ui", "debugger")
             debugmod = pdb
             if not debugger or ui.plain():
                 # if we are in HGPLAIN mode, then disable custom debugging
                 debugger = 'pdb'
             elif '--debugger' in req.args:
                 # This import can be slow for fancy debuggers, so only
                 # do it when absolutely necessary, i.e. when actual
                 # debugging has been requested
                 with demandimport.deactivated():
                     try:
                         debugmod = __import__(debugger)
                     except ImportError:
                         pass # Leave debugmod = pdb
 
             debugtrace[debugger] = debugmod.set_trace
             debugmortem[debugger] = debugmod.post_mortem
 
             # enter the debugger before command execution
             if '--debugger' in req.args:
                 ui.warn(_("entering debugger - "
                         "type c to continue starting hg or h for help\n"))
 
                 if (debugger != 'pdb' and
                     debugtrace[debugger] == debugtrace['pdb']):
                     ui.warn(_("%s debugger specified "
                               "but its module was not found\n") % debugger)
                 with demandimport.deactivated():
                     debugtrace[debugger]()
             try:
                 return _dispatch(req)
             finally:
                 ui.flush()
         except: # re-raises
             # enter the debugger when we hit an exception
             if '--debugger' in req.args:
                 traceback.print_exc()
                 debugmortem[debugger](sys.exc_info()[2])
             ui.traceback()
             raise
 
     return callcatch(ui, _runcatchfunc)
 
 def callcatch(ui, func):
     """like scmutil.callcatch but handles more high-level exceptions about
     config parsing and commands. besides, use handlecommandexception to handle
     uncaught exceptions.
     """
     try:
         return scmutil.callcatch(ui, func)
     except error.AmbiguousCommand as inst:
         ui.warn(_("hg: command '%s' is ambiguous:\n    %s\n") %
                 (inst.args[0], " ".join(inst.args[1])))
     except error.CommandError as inst:
         if inst.args[0]:
             ui.warn(_("hg %s: %s\n") % (inst.args[0], inst.args[1]))
             commands.help_(ui, inst.args[0], full=False, command=True)
         else:
             ui.warn(_("hg: %s\n") % inst.args[1])
             commands.help_(ui, 'shortlist')
     except error.ParseError as inst:
         _formatparse(ui.warn, inst)
         return -1
     except error.UnknownCommand as inst:
         ui.warn(_("hg: unknown command '%s'\n") % inst.args[0])
         try:
             # check if the command is in a disabled extension
             # (but don't check for extensions themselves)
             commands.help_(ui, inst.args[0], unknowncmd=True)
         except (error.UnknownCommand, error.Abort):
             suggested = False
             if len(inst.args) == 2:
                 sim = _getsimilar(inst.args[1], inst.args[0])
                 if sim:
                     _reportsimilar(ui.warn, sim)
                     suggested = True
             if not suggested:
                 commands.help_(ui, 'shortlist')
     except IOError:
         raise
     except KeyboardInterrupt:
         raise
     except:  # probably re-raises
         if not handlecommandexception(ui):
             raise
 
     return -1
 
 def aliasargs(fn, givenargs):
     args = getattr(fn, 'args', [])
     if args:
         cmd = ' '.join(map(util.shellquote, args))
 
         nums = []
         def replacer(m):
             num = int(m.group(1)) - 1
             nums.append(num)
             if num < len(givenargs):
                 return givenargs[num]
             raise error.Abort(_('too few arguments for command alias'))
         cmd = re.sub(r'\$(\d+|\$)', replacer, cmd)
         givenargs = [x for i, x in enumerate(givenargs)
                      if i not in nums]
         args = pycompat.shlexsplit(cmd)
     return args + givenargs
 
 def aliasinterpolate(name, args, cmd):
     '''interpolate args into cmd for shell aliases
 
     This also handles $0, $@ and "$@".
     '''
     # util.interpolate can't deal with "$@" (with quotes) because it's only
     # built to match prefix + patterns.
     replacemap = dict(('$%d' % (i + 1), arg) for i, arg in enumerate(args))
     replacemap['$0'] = name
     replacemap['$$'] = '$'
     replacemap['$@'] = ' '.join(args)
     # Typical Unix shells interpolate "$@" (with quotes) as all the positional
     # parameters, separated out into words. Emulate the same behavior here by
     # quoting the arguments individually. POSIX shells will then typically
     # tokenize each argument into exactly one word.
     replacemap['"$@"'] = ' '.join(util.shellquote(arg) for arg in args)
     # escape '\$' for regex
     regex = '|'.join(replacemap.keys()).replace('$', r'\$')
     r = re.compile(regex)
     return r.sub(lambda x: replacemap[x.group()], cmd)
 
 class cmdalias(object):
     def __init__(self, name, definition, cmdtable, source):
         self.name = self.cmd = name
         self.cmdname = ''
         self.definition = definition
         self.fn = None
         self.givenargs = []
         self.opts = []
         self.help = ''
         self.badalias = None
         self.unknowncmd = False
         self.source = source
 
         try:
             aliases, entry = cmdutil.findcmd(self.name, cmdtable)
             for alias, e in cmdtable.iteritems():
                 if e is entry:
                     self.cmd = alias
                     break
             self.shadows = True
         except error.UnknownCommand:
             self.shadows = False
 
         if not self.definition:
             self.badalias = _("no definition for alias '%s'") % self.name
             return
 
         if self.definition.startswith('!'):
             self.shell = True
             def fn(ui, *args):
                 env = {'HG_ARGS': ' '.join((self.name,) + args)}
                 def _checkvar(m):
                     if m.groups()[0] == '$':
                         return m.group()
                     elif int(m.groups()[0]) <= len(args):
                         return m.group()
                     else:
                         ui.debug("No argument found for substitution "
                                  "of %i variable in alias '%s' definition."
                                  % (int(m.groups()[0]), self.name))
                         return ''
                 cmd = re.sub(r'\$(\d+|\$)', _checkvar, self.definition[1:])
                 cmd = aliasinterpolate(self.name, args, cmd)
                 return ui.system(cmd, environ=env)
             self.fn = fn
             return
 
         try:
             args = pycompat.shlexsplit(self.definition)
         except ValueError as inst:
             self.badalias = (_("error in definition for alias '%s': %s")
                              % (self.name, inst))
             return
         self.cmdname = cmd = args.pop(0)
         self.givenargs = args
 
         for invalidarg in ("--cwd", "-R", "--repository", "--repo", "--config"):
             if _earlygetopt([invalidarg], args):
                 self.badalias = (_("error in definition for alias '%s': %s may "
                                    "only be given on the command line")
                                  % (self.name, invalidarg))
                 return
 
         try:
             tableentry = cmdutil.findcmd(cmd, cmdtable, False)[1]
             if len(tableentry) > 2:
                 self.fn, self.opts, self.help = tableentry
             else:
                 self.fn, self.opts = tableentry
 
             if self.help.startswith("hg " + cmd):
                 # drop prefix in old-style help lines so hg shows the alias
                 self.help = self.help[4 + len(cmd):]
             self.__doc__ = self.fn.__doc__
 
         except error.UnknownCommand:
             self.badalias = (_("alias '%s' resolves to unknown command '%s'")
                              % (self.name, cmd))
             self.unknowncmd = True
         except error.AmbiguousCommand:
             self.badalias = (_("alias '%s' resolves to ambiguous command '%s'")
                              % (self.name, cmd))
 
     @property
     def args(self):
         args = map(util.expandpath, self.givenargs)
         return aliasargs(self.fn, args)
 
     def __getattr__(self, name):
         adefaults = {'norepo': True, 'optionalrepo': False, 'inferrepo': False}
         if name not in adefaults:
             raise AttributeError(name)
         if self.badalias or util.safehasattr(self, 'shell'):
             return adefaults[name]
         return getattr(self.fn, name)
 
     def __call__(self, ui, *args, **opts):
         if self.badalias:
             hint = None
             if self.unknowncmd:
                 try:
                     # check if the command is in a disabled extension
                     cmd, ext = extensions.disabledcmd(ui, self.cmdname)[:2]
                     hint = _("'%s' is provided by '%s' extension") % (cmd, ext)
                 except error.UnknownCommand:
                     pass
             raise error.Abort(self.badalias, hint=hint)
         if self.shadows:
             ui.debug("alias '%s' shadows command '%s'\n" %
                      (self.name, self.cmdname))
 
         ui.log('commandalias', "alias '%s' expands to '%s'\n",
                self.name, self.definition)
         if util.safehasattr(self, 'shell'):
             return self.fn(ui, *args, **opts)
         else:
             try:
                 return util.checksignature(self.fn)(ui, *args, **opts)
             except error.SignatureError:
                 args = ' '.join([self.cmdname] + self.args)
                 ui.debug("alias '%s' expands to '%s'\n" % (self.name, args))
                 raise
 
 def addaliases(ui, cmdtable):
     # aliases are processed after extensions have been loaded, so they
     # may use extension commands. Aliases can also use other alias definitions,
     # but only if they have been defined prior to the current definition.
     for alias, definition in ui.configitems('alias'):
         source = ui.configsource('alias', alias)
         aliasdef = cmdalias(alias, definition, cmdtable, source)
 
         try:
             olddef = cmdtable[aliasdef.cmd][0]
             if olddef.definition == aliasdef.definition:
                 continue
         except (KeyError, AttributeError):
             # definition might not exist or it might not be a cmdalias
             pass
 
         cmdtable[aliasdef.name] = (aliasdef, aliasdef.opts, aliasdef.help)
 
 def _parse(ui, args):
     options = {}
     cmdoptions = {}
 
     try:
         args = fancyopts.fancyopts(args, commands.globalopts, options)
     except getopt.GetoptError as inst:
         raise error.CommandError(None, inst)
 
     if args:
         cmd, args = args[0], args[1:]
         aliases, entry = cmdutil.findcmd(cmd, commands.table,
                                          ui.configbool("ui", "strict"))
         cmd = aliases[0]
         args = aliasargs(entry[0], args)
         defaults = ui.config("defaults", cmd)
         if defaults:
             args = map(util.expandpath, pycompat.shlexsplit(defaults)) + args
         c = list(entry[1])
     else:
         cmd = None
         c = []
 
     # combine global options into local
     for o in commands.globalopts:
         c.append((o[0], o[1], options[o[1]], o[3]))
 
     try:
         args = fancyopts.fancyopts(args, c, cmdoptions, gnu=True)
     except getopt.GetoptError as inst:
         raise error.CommandError(cmd, inst)
 
     # separate global options back out
     for o in commands.globalopts:
         n = o[1]
         options[n] = cmdoptions[n]
         del cmdoptions[n]
 
     return (cmd, cmd and entry[0] or None, args, options, cmdoptions)
 
 def _parseconfig(ui, config):
     """parse the --config options from the command line"""
     configs = []
 
     for cfg in config:
         try:
             name, value = [cfgelem.strip()
                            for cfgelem in cfg.split('=', 1)]
             section, name = name.split('.', 1)
             if not section or not name:
                 raise IndexError
             ui.setconfig(section, name, value, '--config')
             configs.append((section, name, value))
         except (IndexError, ValueError):
             raise error.Abort(_('malformed --config option: %r '
                                '(use --config section.name=value)') % cfg)
 
     return configs
 
 def _earlygetopt(aliases, args):
     """Return list of values for an option (or aliases).
 
     The values are listed in the order they appear in args.
     The options and values are removed from args.
 
     >>> args = ['x', '--cwd', 'foo', 'y']
     >>> _earlygetopt(['--cwd'], args), args
     (['foo'], ['x', 'y'])
 
     >>> args = ['x', '--cwd=bar', 'y']
     >>> _earlygetopt(['--cwd'], args), args
     (['bar'], ['x', 'y'])
 
     >>> args = ['x', '-R', 'foo', 'y']
     >>> _earlygetopt(['-R'], args), args
     (['foo'], ['x', 'y'])
 
     >>> args = ['x', '-Rbar', 'y']
     >>> _earlygetopt(['-R'], args), args
     (['bar'], ['x', 'y'])
     """
     try:
         argcount = args.index("--")
     except ValueError:
         argcount = len(args)
     shortopts = [opt for opt in aliases if len(opt) == 2]
     values = []
     pos = 0
     while pos < argcount:
         fullarg = arg = args[pos]
         equals = arg.find('=')
         if equals > -1:
             arg = arg[:equals]
         if arg in aliases:
             del args[pos]
             if equals > -1:
                 values.append(fullarg[equals + 1:])
                 argcount -= 1
             else:
                 if pos + 1 >= argcount:
                     # ignore and let getopt report an error if there is no value
                     break
                 values.append(args.pop(pos))
                 argcount -= 2
         elif arg[:2] in shortopts:
             # short option can have no following space, e.g. hg log -Rfoo
             values.append(args.pop(pos)[2:])
             argcount -= 1
         else:
             pos += 1
     return values
 
 def runcommand(lui, repo, cmd, fullargs, ui, options, d, cmdpats, cmdoptions):
     # run pre-hook, and abort if it fails
     hook.hook(lui, repo, "pre-%s" % cmd, True, args=" ".join(fullargs),
               pats=cmdpats, opts=cmdoptions)
     try:
         ret = _runcommand(ui, options, cmd, d)
         # run post-hook, passing command result
         hook.hook(lui, repo, "post-%s" % cmd, False, args=" ".join(fullargs),
                   result=ret, pats=cmdpats, opts=cmdoptions)
     except Exception:
         # run failure hook and re-raise
         hook.hook(lui, repo, "fail-%s" % cmd, False, args=" ".join(fullargs),
                   pats=cmdpats, opts=cmdoptions)
         raise
     return ret
 
 def _getlocal(ui, rpath, wd=None):
     """Return (path, local ui object) for the given target path.
 
     Takes paths in [cwd]/.hg/hgrc into account."
     """
     if wd is None:
         try:
             wd = pycompat.getcwd()
         except OSError as e:
             raise error.Abort(_("error getting current working directory: %s") %
                               e.strerror)
     path = cmdutil.findrepo(wd) or ""
     if not path:
         lui = ui
     else:
         lui = ui.copy()
         lui.readconfig(os.path.join(path, ".hg", "hgrc"), path)
 
     if rpath and rpath[-1]:
         path = lui.expandpath(rpath[-1])
         lui = ui.copy()
         lui.readconfig(os.path.join(path, ".hg", "hgrc"), path)
 
     return path, lui
 
 def _checkshellalias(lui, ui, args):
     """Return the function to run the shell alias, if it is required"""
     options = {}
 
     try:
         args = fancyopts.fancyopts(args, commands.globalopts, options)
     except getopt.GetoptError:
         return
 
     if not args:
         return
 
     cmdtable = commands.table
 
     cmd = args[0]
     try:
         strict = ui.configbool("ui", "strict")
         aliases, entry = cmdutil.findcmd(cmd, cmdtable, strict)
     except (error.AmbiguousCommand, error.UnknownCommand):
         return
 
     cmd = aliases[0]
     fn = entry[0]
 
     if cmd and util.safehasattr(fn, 'shell'):
         d = lambda: fn(ui, *args[1:])
         return lambda: runcommand(lui, None, cmd, args[:1], ui, options, d,
                                   [], {})
 
 _loaded = set()
 
 # list of (objname, loadermod, loadername) tuple:
 # - objname is the name of an object in extension module, from which
 #   extra information is loaded
 # - loadermod is the module where loader is placed
 # - loadername is the name of the function, which takes (ui, extensionname,
 #   extraobj) arguments
 extraloaders = [
     ('cmdtable', commands, 'loadcmdtable'),
     ('colortable', color, 'loadcolortable'),
     ('filesetpredicate', fileset, 'loadpredicate'),
     ('revsetpredicate', revset, 'loadpredicate'),
     ('templatefilter', templatefilters, 'loadfilter'),
     ('templatefunc', templater, 'loadfunction'),
     ('templatekeyword', templatekw, 'loadkeyword'),
 ]
 
 def _dispatch(req):
     args = req.args
     ui = req.ui
 
     # check for cwd
     cwd = _earlygetopt(['--cwd'], args)
     if cwd:
         os.chdir(cwd[-1])
 
     rpath = _earlygetopt(["-R", "--repository", "--repo"], args)
     path, lui = _getlocal(ui, rpath)
 
     # Side-effect of accessing is debugcommands module is guaranteed to be
     # imported and commands.table is populated.
     debugcommands.command
 
     uis = set([ui, lui])
 
     if req.repo:
         uis.add(req.repo.ui)
 
     if '--profile' in args:
         for ui_ in uis:
             ui_.setconfig('profiling', 'enabled', 'true', '--profile')
 
     with profiling.maybeprofile(lui):
         # Configure extensions in phases: uisetup, extsetup, cmdtable, and
         # reposetup. Programs like TortoiseHg will call _dispatch several
         # times so we keep track of configured extensions in _loaded.
         extensions.loadall(lui)
         exts = [ext for ext in extensions.extensions() if ext[0] not in _loaded]
         # Propagate any changes to lui.__class__ by extensions
         ui.__class__ = lui.__class__
 
         # (uisetup and extsetup are handled in extensions.loadall)
 
         for name, module in exts:
             for objname, loadermod, loadername in extraloaders:
                 extraobj = getattr(module, objname, None)
                 if extraobj is not None:
                     getattr(loadermod, loadername)(ui, name, extraobj)
             _loaded.add(name)
 
         # (reposetup is handled in hg.repository)
 
         addaliases(lui, commands.table)
 
         # All aliases and commands are completely defined, now.
         # Check abbreviation/ambiguity of shell alias.
         shellaliasfn = _checkshellalias(lui, ui, args)
         if shellaliasfn:
             return shellaliasfn()
 
         # check for fallback encoding
         fallback = lui.config('ui', 'fallbackencoding')
         if fallback:
             encoding.fallbackencoding = fallback
 
         fullargs = args
         cmd, func, args, options, cmdoptions = _parse(lui, args)
 
         if options["config"]:
             raise error.Abort(_("option --config may not be abbreviated!"))
         if options["cwd"]:
             raise error.Abort(_("option --cwd may not be abbreviated!"))
         if options["repository"]:
             raise error.Abort(_(
                 "option -R has to be separated from other options (e.g. not "
                 "-qR) and --repository may only be abbreviated as --repo!"))
 
         if options["encoding"]:
             encoding.encoding = options["encoding"]
         if options["encodingmode"]:
             encoding.encodingmode = options["encodingmode"]
         if options["time"]:
             def get_times():
                 t = os.times()
                 if t[4] == 0.0:
                     # Windows leaves this as zero, so use time.clock()
                     t = (t[0], t[1], t[2], t[3], time.clock())
                 return t
             s = get_times()
             def print_time():
                 t = get_times()
                 ui.warn(
                     _("time: real %.3f secs (user %.3f+%.3f sys %.3f+%.3f)\n") %
                     (t[4]-s[4], t[0]-s[0], t[2]-s[2], t[1]-s[1], t[3]-s[3]))
             atexit.register(print_time)
 
         if options['verbose'] or options['debug'] or options['quiet']:
             for opt in ('verbose', 'debug', 'quiet'):
                 val = str(bool(options[opt]))
                 for ui_ in uis:
                     ui_.setconfig('ui', opt, val, '--' + opt)
 
         if options['traceback']:
             for ui_ in uis:
                 ui_.setconfig('ui', 'traceback', 'on', '--traceback')
 
         if options['noninteractive']:
             for ui_ in uis:
                 ui_.setconfig('ui', 'interactive', 'off', '-y')
 
         if cmdoptions.get('insecure', False):
             for ui_ in uis:
                 ui_.insecureconnections = True
 
         if options['version']:
             return commands.version_(ui)
         if options['help']:
             return commands.help_(ui, cmd, command=cmd is not None)
         elif not cmd:
             return commands.help_(ui, 'shortlist')
 
         repo = None
         cmdpats = args[:]
         if not func.norepo:
             # use the repo from the request only if we don't have -R
             if not rpath and not cwd:
                 repo = req.repo
 
             if repo:
                 # set the descriptors of the repo ui to those of ui
                 repo.ui.fin = ui.fin
                 repo.ui.fout = ui.fout
                 repo.ui.ferr = ui.ferr
             else:
                 try:
                     repo = hg.repository(ui, path=path)
                     if not repo.local():
                         raise error.Abort(_("repository '%s' is not local")
                                           % path)
                     repo.ui.setconfig("bundle", "mainreporoot", repo.root,
                                       'repo')
                 except error.RequirementError:
                     raise
                 except error.RepoError:
                     if rpath and rpath[-1]: # invalid -R path
                         raise
                     if not func.optionalrepo:
                         if func.inferrepo and args and not path:
                             # try to infer -R from command args
                             repos = map(cmdutil.findrepo, args)
                             guess = repos[0]
                             if guess and repos.count(guess) == len(repos):
                                 req.args = ['--repository', guess] + fullargs
                                 return _dispatch(req)
                         if not path:
                             raise error.RepoError(_("no repository found in"
                                                     " '%s' (.hg not found)")
                                                   % pycompat.getcwd())
                         raise
             if repo:
                 ui = repo.ui
                 if options['hidden']:
                     repo = repo.unfiltered()
             args.insert(0, repo)
         elif rpath:
             ui.warn(_("warning: --repository ignored\n"))
 
         msg = ' '.join(' ' in a and repr(a) or a for a in fullargs)
         ui.log("command", '%s\n', msg)
         strcmdopt = pycompat.strkwargs(cmdoptions)
         d = lambda: util.checksignature(func)(ui, *args, **strcmdopt)
         try:
             return runcommand(lui, repo, cmd, fullargs, ui, options, d,
                               cmdpats, cmdoptions)
         finally:
             if repo and repo != req.repo:
                 repo.close()
 
 def _runcommand(ui, options, cmd, cmdfunc):
     """Run a command function, possibly with profiling enabled."""
     try:
         return cmdfunc()
     except error.SignatureError:
         raise error.CommandError(cmd, _('invalid arguments'))
 
 def _exceptionwarning(ui):
     """Produce a warning message for the current active exception"""
 
     # For compatibility checking, we discard the portion of the hg
     # version after the + on the assumption that if a "normal
     # user" is running a build with a + in it the packager
     # probably built from fairly close to a tag and anyone with a
     # 'make local' copy of hg (where the version number can be out
     # of date) will be clueful enough to notice the implausible
     # version number and try updating.
     ct = util.versiontuple(n=2)
     worst = None, ct, ''
     if ui.config('ui', 'supportcontact', None) is None:
         for name, mod in extensions.extensions():
             testedwith = getattr(mod, 'testedwith', '')
             report = getattr(mod, 'buglink', _('the extension author.'))
             if not testedwith.strip():
                 # We found an untested extension. It's likely the culprit.
                 worst = name, 'unknown', report
                 break
 
             # Never blame on extensions bundled with Mercurial.
             if extensions.ismoduleinternal(mod):
                 continue
 
             tested = [util.versiontuple(t, 2) for t in testedwith.split()]
             if ct in tested:
                 continue
 
             lower = [t for t in tested if t < ct]
             nearest = max(lower or tested)
             if worst[0] is None or nearest < worst[1]:
                 worst = name, nearest, report
     if worst[0] is not None:
         name, testedwith, report = worst
         if not isinstance(testedwith, str):
             testedwith = '.'.join([str(c) for c in testedwith])
         warning = (_('** Unknown exception encountered with '
                      'possibly-broken third-party extension %s\n'
                      '** which supports versions %s of Mercurial.\n'
                      '** Please disable %s and try your action again.\n'
                      '** If that fixes the bug please report it to %s\n')
                    % (name, testedwith, name, report))
     else:
         bugtracker = ui.config('ui', 'supportcontact', None)
         if bugtracker is None:
             bugtracker = _("https://mercurial-scm.org/wiki/BugTracker")
         warning = (_("** unknown exception encountered, "
                      "please report by visiting\n** ") + bugtracker + '\n')
     warning += ((_("** Python %s\n") % sys.version.replace('\n', '')) +
                 (_("** Mercurial Distributed SCM (version %s)\n") %
                  util.version()) +
                 (_("** Extensions loaded: %s\n") %
                  ", ".join([x[0] for x in extensions.extensions()])))
     return warning
 
 def handlecommandexception(ui):
     """Produce a warning message for broken commands
 
     Called when handling an exception; the exception is reraised if
     this function returns False, ignored otherwise.
     """
     warning = _exceptionwarning(ui)
     ui.log("commandexception", "%s\n%s\n", warning, traceback.format_exc())
     ui.warn(warning)
     return False  # re-raise the exception

mercurial/hook.py

@@ -1,266 +1,265
 # hook.py - hook support for mercurial
 #
 # Copyright 2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import os
 import sys
-import time
 
 from .i18n import _
 from . import (
     demandimport,
     error,
     extensions,
     pycompat,
     util,
 )
 
 def _pythonhook(ui, repo, name, hname, funcname, args, throw):
     '''call python hook. hook is callable object, looked up as
     name in python module. if callable returns "true", hook
     fails, else passes. if hook raises exception, treated as
     hook failure. exception propagates if throw is "true".
 
     reason for "true" meaning "hook failed" is so that
     unmodified commands (e.g. mercurial.commands.update) can
     be run as hooks without wrappers to convert return values.'''
 
     if callable(funcname):
         obj = funcname
         funcname = obj.__module__ + "." + obj.__name__
     else:
         d = funcname.rfind('.')
         if d == -1:
             raise error.HookLoadError(
                 _('%s hook is invalid: "%s" not in a module')
                 % (hname, funcname))
         modname = funcname[:d]
         oldpaths = sys.path
         if util.mainfrozen():
             # binary installs require sys.path manipulation
             modpath, modfile = os.path.split(modname)
             if modpath and modfile:
                 sys.path = sys.path[:] + [modpath]
                 modname = modfile
         with demandimport.deactivated():
             try:
                 obj = __import__(modname)
             except (ImportError, SyntaxError):
                 e1 = sys.exc_info()
                 try:
                     # extensions are loaded with hgext_ prefix
                     obj = __import__("hgext_%s" % modname)
                 except (ImportError, SyntaxError):
                     e2 = sys.exc_info()
                     if ui.tracebackflag:
                         ui.warn(_('exception from first failed import '
                                   'attempt:\n'))
                     ui.traceback(e1)
                     if ui.tracebackflag:
                         ui.warn(_('exception from second failed import '
                                   'attempt:\n'))
                     ui.traceback(e2)
 
                     if not ui.tracebackflag:
                         tracebackhint = _(
                             'run with --traceback for stack trace')
                     else:
                         tracebackhint = None
                     raise error.HookLoadError(
                         _('%s hook is invalid: import of "%s" failed') %
                         (hname, modname), hint=tracebackhint)
         sys.path = oldpaths
         try:
             for p in funcname.split('.')[1:]:
                 obj = getattr(obj, p)
         except AttributeError:
             raise error.HookLoadError(
                 _('%s hook is invalid: "%s" is not defined')
                 % (hname, funcname))
         if not callable(obj):
             raise error.HookLoadError(
                 _('%s hook is invalid: "%s" is not callable')
                 % (hname, funcname))
 
     ui.note(_("calling hook %s: %s\n") % (hname, funcname))
-    starttime = time.time()
+    starttime = util.timer()
 
     try:
         r = obj(ui=ui, repo=repo, hooktype=name, **args)
     except Exception as exc:
         if isinstance(exc, error.Abort):
             ui.warn(_('error: %s hook failed: %s\n') %
                          (hname, exc.args[0]))
         else:
             ui.warn(_('error: %s hook raised an exception: '
                            '%s\n') % (hname, exc))
         if throw:
             raise
         if not ui.tracebackflag:
             ui.warn(_('(run with --traceback for stack trace)\n'))
         ui.traceback()
         return True, True
     finally:
-        duration = time.time() - starttime
+        duration = util.timer() - starttime
         ui.log('pythonhook', 'pythonhook-%s: %s finished in %0.2f seconds\n',
                name, funcname, duration)
     if r:
         if throw:
             raise error.HookAbort(_('%s hook failed') % hname)
         ui.warn(_('warning: %s hook failed\n') % hname)
     return r, False
 
 def _exthook(ui, repo, name, cmd, args, throw):
     ui.note(_("running hook %s: %s\n") % (name, cmd))
 
-    starttime = time.time()
+    starttime = util.timer()
     env = {}
 
     # make in-memory changes visible to external process
     if repo is not None:
         tr = repo.currenttransaction()
         repo.dirstate.write(tr)
         if tr and tr.writepending():
             env['HG_PENDING'] = repo.root
 
     for k, v in args.iteritems():
         if callable(v):
             v = v()
         if isinstance(v, dict):
             # make the dictionary element order stable across Python
             # implementations
             v = ('{' +
                  ', '.join('%r: %r' % i for i in sorted(v.iteritems())) +
                  '}')
         env['HG_' + k.upper()] = v
 
     if repo:
         cwd = repo.root
     else:
         cwd = pycompat.getcwd()
     r = ui.system(cmd, environ=env, cwd=cwd)
 
-    duration = time.time() - starttime
+    duration = util.timer() - starttime
     ui.log('exthook', 'exthook-%s: %s finished in %0.2f seconds\n',
            name, cmd, duration)
     if r:
         desc, r = util.explainexit(r)
         if throw:
             raise error.HookAbort(_('%s hook %s') % (name, desc))
         ui.warn(_('warning: %s hook %s\n') % (name, desc))
     return r
 
 # represent an untrusted hook command
 _fromuntrusted = object()
 
 def _allhooks(ui):
     """return a list of (hook-id, cmd) pairs sorted by priority"""
     hooks = _hookitems(ui)
     # Be careful in this section, propagating the real commands from untrusted
     # sources would create a security vulnerability, make sure anything altered
     # in that section uses "_fromuntrusted" as its command.
     untrustedhooks = _hookitems(ui, _untrusted=True)
     for name, value in untrustedhooks.items():
         trustedvalue = hooks.get(name, (None, None, name, _fromuntrusted))
         if value != trustedvalue:
             (lp, lo, lk, lv) = trustedvalue
             hooks[name] = (lp, lo, lk, _fromuntrusted)
     # (end of the security sensitive section)
     return [(k, v) for p, o, k, v in sorted(hooks.values())]
 
 def _hookitems(ui, _untrusted=False):
     """return all hooks items ready to be sorted"""
     hooks = {}
     for name, cmd in ui.configitems('hooks', untrusted=_untrusted):
         if not name.startswith('priority'):
             priority = ui.configint('hooks', 'priority.%s' % name, 0)
             hooks[name] = (-priority, len(hooks), name, cmd)
     return hooks
 
 _redirect = False
 def redirect(state):
     global _redirect
     _redirect = state
 
 def hook(ui, repo, name, throw=False, **args):
     if not ui.callhooks:
         return False
 
     hooks = []
     for hname, cmd in _allhooks(ui):
         if hname.split('.')[0] == name and cmd:
             hooks.append((hname, cmd))
 
     res = runhooks(ui, repo, name, hooks, throw=throw, **args)
     r = False
     for hname, cmd in hooks:
         r = res[hname][0] or r
     return r
 
 def runhooks(ui, repo, name, hooks, throw=False, **args):
     res = {}
     oldstdout = -1
 
     try:
         for hname, cmd in hooks:
             if oldstdout == -1 and _redirect:
                 try:
                     stdoutno = util.stdout.fileno()
                     stderrno = util.stderr.fileno()
                     # temporarily redirect stdout to stderr, if possible
                     if stdoutno >= 0 and stderrno >= 0:
                         util.stdout.flush()
                         oldstdout = os.dup(stdoutno)
                         os.dup2(stderrno, stdoutno)
                 except (OSError, AttributeError):
                     # files seem to be bogus, give up on redirecting (WSGI, etc)
                     pass
 
             if cmd is _fromuntrusted:
                 if throw:
                     raise error.HookAbort(
                         _('untrusted hook %s not executed') % name,
                         hint = _("see 'hg help config.trusted'"))
                 ui.warn(_('warning: untrusted hook %s not executed\n') % name)
                 r = 1
                 raised = False
             elif callable(cmd):
                 r, raised = _pythonhook(ui, repo, name, hname, cmd, args, throw)
             elif cmd.startswith('python:'):
                 if cmd.count(':') >= 2:
                     path, cmd = cmd[7:].rsplit(':', 1)
                     path = util.expandpath(path)
                     if repo:
                         path = os.path.join(repo.root, path)
                     try:
                         mod = extensions.loadpath(path, 'hghook.%s' % hname)
                     except Exception:
                         ui.write(_("loading %s hook failed:\n") % hname)
                         raise
                     hookfn = getattr(mod, cmd)
                 else:
                     hookfn = cmd[7:].strip()
                 r, raised = _pythonhook(ui, repo, name, hname, hookfn, args,
                                         throw)
             else:
                 r = _exthook(ui, repo, hname, cmd, args, throw)
                 raised = False
 
             res[hname] = r, raised
 
             # The stderr is fully buffered on Windows when connected to a pipe.
             # A forcible flush is required to make small stderr data in the
             # remote side available to the client immediately.
             util.stderr.flush()
     finally:
         if _redirect and oldstdout >= 0:
             util.stdout.flush()  # write hook output to stderr fd
             os.dup2(oldstdout, stdoutno)
             os.close(oldstdout)
 
     return res

mercurial/profiling.py

@@ -1,193 +1,192
 # profiling.py - profiling functions
 #
 # Copyright 2016 Gregory Szorc <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import, print_function
 
 import contextlib
-import time
 
 from .i18n import _
 from . import (
     encoding,
     error,
     util,
 )
 
 @contextlib.contextmanager
 def lsprofile(ui, fp):
     format = ui.config('profiling', 'format', default='text')
     field = ui.config('profiling', 'sort', default='inlinetime')
     limit = ui.configint('profiling', 'limit', default=30)
     climit = ui.configint('profiling', 'nested', default=0)
 
     if format not in ['text', 'kcachegrind']:
         ui.warn(_("unrecognized profiling format '%s'"
                     " - Ignored\n") % format)
         format = 'text'
 
     try:
         from . import lsprof
     except ImportError:
         raise error.Abort(_(
             'lsprof not available - install from '
             'http://codespeak.net/svn/user/arigo/hack/misc/lsprof/'))
     p = lsprof.Profiler()
     p.enable(subcalls=True)
     try:
         yield
     finally:
         p.disable()
 
         if format == 'kcachegrind':
             from . import lsprofcalltree
             calltree = lsprofcalltree.KCacheGrind(p)
             calltree.output(fp)
         else:
             # format == 'text'
             stats = lsprof.Stats(p.getstats())
             stats.sort(field)
             stats.pprint(limit=limit, file=fp, climit=climit)
 
 @contextlib.contextmanager
 def flameprofile(ui, fp):
     try:
         from flamegraph import flamegraph
     except ImportError:
         raise error.Abort(_(
             'flamegraph not available - install from '
             'https://github.com/evanhempel/python-flamegraph'))
     # developer config: profiling.freq
     freq = ui.configint('profiling', 'freq', default=1000)
     filter_ = None
     collapse_recursion = True
     thread = flamegraph.ProfileThread(fp, 1.0 / freq,
                                       filter_, collapse_recursion)
-    start_time = time.clock()
+    start_time = util.timer()
     try:
         thread.start()
         yield
     finally:
         thread.stop()
         thread.join()
         print('Collected %d stack frames (%d unique) in %2.2f seconds.' % (
-            time.clock() - start_time, thread.num_frames(),
+            util.timer() - start_time, thread.num_frames(),
             thread.num_frames(unique=True)))
 
 @contextlib.contextmanager
 def statprofile(ui, fp):
     from . import statprof
 
     freq = ui.configint('profiling', 'freq', default=1000)
     if freq > 0:
         # Cannot reset when profiler is already active. So silently no-op.
         if statprof.state.profile_level == 0:
             statprof.reset(freq)
     else:
         ui.warn(_("invalid sampling frequency '%s' - ignoring\n") % freq)
 
     statprof.start(mechanism='thread')
 
     try:
         yield
     finally:
         data = statprof.stop()
 
         profformat = ui.config('profiling', 'statformat', 'hotpath')
 
         formats = {
             'byline': statprof.DisplayFormats.ByLine,
             'bymethod': statprof.DisplayFormats.ByMethod,
             'hotpath': statprof.DisplayFormats.Hotpath,
             'json': statprof.DisplayFormats.Json,
             'chrome': statprof.DisplayFormats.Chrome,
         }
 
         if profformat in formats:
             displayformat = formats[profformat]
         else:
             ui.warn(_('unknown profiler output format: %s\n') % profformat)
             displayformat = statprof.DisplayFormats.Hotpath
 
         kwargs = {}
 
         def fraction(s):
             if s.endswith('%'):
                 v = float(s[:-1]) / 100
             else:
                 v = float(s)
             if 0 <= v <= 1:
                 return v
             raise ValueError(s)
 
         if profformat == 'chrome':
             showmin = ui.configwith(fraction, 'profiling', 'showmin', 0.005)
             showmax = ui.configwith(fraction, 'profiling', 'showmax', 0.999)
             kwargs.update(minthreshold=showmin, maxthreshold=showmax)
 
         statprof.display(fp, data=data, format=displayformat, **kwargs)
 
 @contextlib.contextmanager
 def profile(ui):
     """Start profiling.
 
     Profiling is active when the context manager is active. When the context
     manager exits, profiling results will be written to the configured output.
     """
     profiler = encoding.environ.get('HGPROF')
     if profiler is None:
         profiler = ui.config('profiling', 'type', default='stat')
     if profiler not in ('ls', 'stat', 'flame'):
         ui.warn(_("unrecognized profiler '%s' - ignored\n") % profiler)
         profiler = 'stat'
 
     output = ui.config('profiling', 'output')
 
     if output == 'blackbox':
         fp = util.stringio()
     elif output:
         path = ui.expandpath(output)
         fp = open(path, 'wb')
     else:
         fp = ui.ferr
 
     try:
         if profiler == 'ls':
             proffn = lsprofile
         elif profiler == 'flame':
             proffn = flameprofile
         else:
             proffn = statprofile
 
         with proffn(ui, fp):
             yield
 
     finally:
         if output:
             if output == 'blackbox':
                 val = 'Profile:\n%s' % fp.getvalue()
                 # ui.log treats the input as a format string,
                 # so we need to escape any % signs.
                 val = val.replace('%', '%%')
                 ui.log('profile', val)
             fp.close()
 
 @contextlib.contextmanager
 def maybeprofile(ui):
     """Profile if enabled, else do nothing.
 
     This context manager can be used to optionally profile if profiling
     is enabled. Otherwise, it does nothing.
 
     The purpose of this context manager is to make calling code simpler:
     just use a single code path for calling into code you may want to profile
     and this function determines whether to start profiling.
     """
     if ui.configbool('profiling', 'enabled'):
         with profile(ui):
             yield
     else:
         yield

mercurial/repair.py

@@ -1,1102 +1,1101
 # repair.py - functions for repository repair for mercurial
 #
 # Copyright 2005, 2006 Chris Mason <[e-mail]>
 # Copyright 2007 Matt Mackall
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import errno
 import hashlib
 import stat
 import tempfile
-import time
 
 from .i18n import _
 from .node import short
 from . import (
     bundle2,
     changegroup,
     changelog,
     error,
     exchange,
     manifest,
     obsolete,
     revlog,
     scmutil,
     util,
 )
 
 def _bundle(repo, bases, heads, node, suffix, compress=True):
     """create a bundle with the specified revisions as a backup"""
     cgversion = changegroup.safeversion(repo)
 
     cg = changegroup.changegroupsubset(repo, bases, heads, 'strip',
                                        version=cgversion)
     backupdir = "strip-backup"
     vfs = repo.vfs
     if not vfs.isdir(backupdir):
         vfs.mkdir(backupdir)
 
     # Include a hash of all the nodes in the filename for uniqueness
     allcommits = repo.set('%ln::%ln', bases, heads)
     allhashes = sorted(c.hex() for c in allcommits)
     totalhash = hashlib.sha1(''.join(allhashes)).hexdigest()
     name = "%s/%s-%s-%s.hg" % (backupdir, short(node), totalhash[:8], suffix)
 
     comp = None
     if cgversion != '01':
         bundletype = "HG20"
         if compress:
             comp = 'BZ'
     elif compress:
         bundletype = "HG10BZ"
     else:
         bundletype = "HG10UN"
     return bundle2.writebundle(repo.ui, cg, name, bundletype, vfs,
                                    compression=comp)
 
 def _collectfiles(repo, striprev):
     """find out the filelogs affected by the strip"""
     files = set()
 
     for x in xrange(striprev, len(repo)):
         files.update(repo[x].files())
 
     return sorted(files)
 
 def _collectbrokencsets(repo, files, striprev):
     """return the changesets which will be broken by the truncation"""
     s = set()
     def collectone(revlog):
         _, brokenset = revlog.getstrippoint(striprev)
         s.update([revlog.linkrev(r) for r in brokenset])
 
     collectone(repo.manifestlog._revlog)
     for fname in files:
         collectone(repo.file(fname))
 
     return s
 
 def strip(ui, repo, nodelist, backup=True, topic='backup'):
     # This function operates within a transaction of its own, but does
     # not take any lock on the repo.
     # Simple way to maintain backwards compatibility for this
     # argument.
     if backup in ['none', 'strip']:
         backup = False
 
     repo = repo.unfiltered()
     repo.destroying()
 
     cl = repo.changelog
     # TODO handle undo of merge sets
     if isinstance(nodelist, str):
         nodelist = [nodelist]
     striplist = [cl.rev(node) for node in nodelist]
     striprev = min(striplist)
 
     files = _collectfiles(repo, striprev)
     saverevs = _collectbrokencsets(repo, files, striprev)
 
     # Some revisions with rev > striprev may not be descendants of striprev.
     # We have to find these revisions and put them in a bundle, so that
     # we can restore them after the truncations.
     # To create the bundle we use repo.changegroupsubset which requires
     # the list of heads and bases of the set of interesting revisions.
     # (head = revision in the set that has no descendant in the set;
     #  base = revision in the set that has no ancestor in the set)
     tostrip = set(striplist)
     saveheads = set(saverevs)
     for r in cl.revs(start=striprev + 1):
         if any(p in tostrip for p in cl.parentrevs(r)):
             tostrip.add(r)
 
         if r not in tostrip:
             saverevs.add(r)
             saveheads.difference_update(cl.parentrevs(r))
             saveheads.add(r)
     saveheads = [cl.node(r) for r in saveheads]
 
     # compute base nodes
     if saverevs:
         descendants = set(cl.descendants(saverevs))
         saverevs.difference_update(descendants)
     savebases = [cl.node(r) for r in saverevs]
     stripbases = [cl.node(r) for r in tostrip]
 
     # For a set s, max(parents(s) - s) is the same as max(heads(::s - s)), but
     # is much faster
     newbmtarget = repo.revs('max(parents(%ld) - (%ld))', tostrip, tostrip)
     if newbmtarget:
         newbmtarget = repo[newbmtarget.first()].node()
     else:
         newbmtarget = '.'
 
     bm = repo._bookmarks
     updatebm = []
     for m in bm:
         rev = repo[bm[m]].rev()
         if rev in tostrip:
             updatebm.append(m)
 
     # create a changegroup for all the branches we need to keep
     backupfile = None
     vfs = repo.vfs
     node = nodelist[-1]
     if backup:
         backupfile = _bundle(repo, stripbases, cl.heads(), node, topic)
         repo.ui.status(_("saved backup bundle to %s\n") %
                        vfs.join(backupfile))
         repo.ui.log("backupbundle", "saved backup bundle to %s\n",
                     vfs.join(backupfile))
     tmpbundlefile = None
     if saveheads:
         # do not compress temporary bundle if we remove it from disk later
         tmpbundlefile = _bundle(repo, savebases, saveheads, node, 'temp',
                             compress=False)
 
     mfst = repo.manifestlog._revlog
 
     curtr = repo.currenttransaction()
     if curtr is not None:
         del curtr  # avoid carrying reference to transaction for nothing
         msg = _('programming error: cannot strip from inside a transaction')
         raise error.Abort(msg, hint=_('contact your extension maintainer'))
 
     try:
         with repo.transaction("strip") as tr:
             offset = len(tr.entries)
 
             tr.startgroup()
             cl.strip(striprev, tr)
             mfst.strip(striprev, tr)
             if 'treemanifest' in repo.requirements: # safe but unnecessary
                                                     # otherwise
                 for unencoded, encoded, size in repo.store.datafiles():
                     if (unencoded.startswith('meta/') and
                         unencoded.endswith('00manifest.i')):
                         dir = unencoded[5:-12]
                         repo.manifestlog._revlog.dirlog(dir).strip(striprev, tr)
             for fn in files:
                 repo.file(fn).strip(striprev, tr)
             tr.endgroup()
 
             for i in xrange(offset, len(tr.entries)):
                 file, troffset, ignore = tr.entries[i]
                 with repo.svfs(file, 'a', checkambig=True) as fp:
                     fp.truncate(troffset)
                 if troffset == 0:
                     repo.store.markremoved(file)
 
         if tmpbundlefile:
             ui.note(_("adding branch\n"))
             f = vfs.open(tmpbundlefile, "rb")
             gen = exchange.readbundle(ui, f, tmpbundlefile, vfs)
             if not repo.ui.verbose:
                 # silence internal shuffling chatter
                 repo.ui.pushbuffer()
             if isinstance(gen, bundle2.unbundle20):
                 with repo.transaction('strip') as tr:
                     tr.hookargs = {'source': 'strip',
                                    'url': 'bundle:' + vfs.join(tmpbundlefile)}
                     bundle2.applybundle(repo, gen, tr, source='strip',
                                         url='bundle:' + vfs.join(tmpbundlefile))
             else:
                 gen.apply(repo, 'strip', 'bundle:' + vfs.join(tmpbundlefile),
                           True)
             if not repo.ui.verbose:
                 repo.ui.popbuffer()
             f.close()
         repo._phasecache.invalidate()
 
         for m in updatebm:
             bm[m] = repo[newbmtarget].node()
         lock = tr = None
         try:
             lock = repo.lock()
             tr = repo.transaction('repair')
             bm.recordchange(tr)
             tr.close()
         finally:
             tr.release()
             lock.release()
 
         # remove undo files
         for undovfs, undofile in repo.undofiles():
             try:
                 undovfs.unlink(undofile)
             except OSError as e:
                 if e.errno != errno.ENOENT:
                     ui.warn(_('error removing %s: %s\n') %
                             (undovfs.join(undofile), str(e)))
 
     except: # re-raises
         if backupfile:
             ui.warn(_("strip failed, backup bundle stored in '%s'\n")
                     % vfs.join(backupfile))
         if tmpbundlefile:
             ui.warn(_("strip failed, unrecovered changes stored in '%s'\n")
                     % vfs.join(tmpbundlefile))
             ui.warn(_("(fix the problem, then recover the changesets with "
                       "\"hg unbundle '%s'\")\n") % vfs.join(tmpbundlefile))
         raise
     else:
         if tmpbundlefile:
             # Remove temporary bundle only if there were no exceptions
             vfs.unlink(tmpbundlefile)
 
     repo.destroyed()
     # return the backup file path (or None if 'backup' was False) so
     # extensions can use it
     return backupfile
 
 def rebuildfncache(ui, repo):
     """Rebuilds the fncache file from repo history.
 
     Missing entries will be added. Extra entries will be removed.
     """
     repo = repo.unfiltered()
 
     if 'fncache' not in repo.requirements:
         ui.warn(_('(not rebuilding fncache because repository does not '
                   'support fncache)\n'))
         return
 
     with repo.lock():
         fnc = repo.store.fncache
         # Trigger load of fncache.
         if 'irrelevant' in fnc:
             pass
 
         oldentries = set(fnc.entries)
         newentries = set()
         seenfiles = set()
 
         repolen = len(repo)
         for rev in repo:
             ui.progress(_('rebuilding'), rev, total=repolen,
                         unit=_('changesets'))
 
             ctx = repo[rev]
             for f in ctx.files():
                 # This is to minimize I/O.
                 if f in seenfiles:
                     continue
                 seenfiles.add(f)
 
                 i = 'data/%s.i' % f
                 d = 'data/%s.d' % f
 
                 if repo.store._exists(i):
                     newentries.add(i)
                 if repo.store._exists(d):
                     newentries.add(d)
 
         ui.progress(_('rebuilding'), None)
 
         if 'treemanifest' in repo.requirements: # safe but unnecessary otherwise
             for dir in util.dirs(seenfiles):
                 i = 'meta/%s/00manifest.i' % dir
                 d = 'meta/%s/00manifest.d' % dir
 
                 if repo.store._exists(i):
                     newentries.add(i)
                 if repo.store._exists(d):
                     newentries.add(d)
 
         addcount = len(newentries - oldentries)
         removecount = len(oldentries - newentries)
         for p in sorted(oldentries - newentries):
             ui.write(_('removing %s\n') % p)
         for p in sorted(newentries - oldentries):
             ui.write(_('adding %s\n') % p)
 
         if addcount or removecount:
             ui.write(_('%d items added, %d removed from fncache\n') %
                      (addcount, removecount))
             fnc.entries = newentries
             fnc._dirty = True
 
             with repo.transaction('fncache') as tr:
                 fnc.write(tr)
         else:
             ui.write(_('fncache already up to date\n'))
 
 def stripbmrevset(repo, mark):
     """
     The revset to strip when strip is called with -B mark
 
     Needs to live here so extensions can use it and wrap it even when strip is
     not enabled or not present on a box.
     """
     return repo.revs("ancestors(bookmark(%s)) - "
                      "ancestors(head() and not bookmark(%s)) - "
                      "ancestors(bookmark() and not bookmark(%s))",
                      mark, mark, mark)
 
 def deleteobsmarkers(obsstore, indices):
     """Delete some obsmarkers from obsstore and return how many were deleted
 
     'indices' is a list of ints which are the indices
     of the markers to be deleted.
 
     Every invocation of this function completely rewrites the obsstore file,
     skipping the markers we want to be removed. The new temporary file is
     created, remaining markers are written there and on .close() this file
     gets atomically renamed to obsstore, thus guaranteeing consistency."""
     if not indices:
         # we don't want to rewrite the obsstore with the same content
         return
 
     left = []
     current = obsstore._all
     n = 0
     for i, m in enumerate(current):
         if i in indices:
             n += 1
             continue
         left.append(m)
 
     newobsstorefile = obsstore.svfs('obsstore', 'w', atomictemp=True)
     for bytes in obsolete.encodemarkers(left, True, obsstore._version):
         newobsstorefile.write(bytes)
     newobsstorefile.close()
     return n
 
 def upgraderequiredsourcerequirements(repo):
     """Obtain requirements required to be present to upgrade a repo.
 
     An upgrade will not be allowed if the repository doesn't have the
     requirements returned by this function.
     """
     return set([
         # Introduced in Mercurial 0.9.2.
         'revlogv1',
         # Introduced in Mercurial 0.9.2.
         'store',
     ])
 
 def upgradeblocksourcerequirements(repo):
     """Obtain requirements that will prevent an upgrade from occurring.
 
     An upgrade cannot be performed if the source repository contains a
     requirements in the returned set.
     """
     return set([
         # The upgrade code does not yet support these experimental features.
         # This is an artificial limitation.
         'manifestv2',
         'treemanifest',
         # This was a precursor to generaldelta and was never enabled by default.
         # It should (hopefully) not exist in the wild.
         'parentdelta',
         # Upgrade should operate on the actual store, not the shared link.
         'shared',
     ])
 
 def upgradesupportremovedrequirements(repo):
     """Obtain requirements that can be removed during an upgrade.
 
     If an upgrade were to create a repository that dropped a requirement,
     the dropped requirement must appear in the returned set for the upgrade
     to be allowed.
     """
     return set()
 
 def upgradesupporteddestrequirements(repo):
     """Obtain requirements that upgrade supports in the destination.
 
     If the result of the upgrade would create requirements not in this set,
     the upgrade is disallowed.
 
     Extensions should monkeypatch this to add their custom requirements.
     """
     return set([
         'dotencode',
         'fncache',
         'generaldelta',
         'revlogv1',
         'store',
     ])
 
 def upgradeallowednewrequirements(repo):
     """Obtain requirements that can be added to a repository during upgrade.
 
     This is used to disallow proposed requirements from being added when
     they weren't present before.
 
     We use a list of allowed requirement additions instead of a list of known
     bad additions because the whitelist approach is safer and will prevent
     future, unknown requirements from accidentally being added.
     """
     return set([
         'dotencode',
         'fncache',
         'generaldelta',
     ])
 
 deficiency = 'deficiency'
 optimisation = 'optimization'
 
 class upgradeimprovement(object):
     """Represents an improvement that can be made as part of an upgrade.
 
     The following attributes are defined on each instance:
 
     name
        Machine-readable string uniquely identifying this improvement. It
        will be mapped to an action later in the upgrade process.
 
     type
        Either ``deficiency`` or ``optimisation``. A deficiency is an obvious
        problem. An optimization is an action (sometimes optional) that
        can be taken to further improve the state of the repository.
 
     description
        Message intended for humans explaining the improvement in more detail,
        including the implications of it. For ``deficiency`` types, should be
        worded in the present tense. For ``optimisation`` types, should be
        worded in the future tense.
 
     upgrademessage
        Message intended for humans explaining what an upgrade addressing this
        issue will do. Should be worded in the future tense.
 
     fromdefault (``deficiency`` types only)
        Boolean indicating whether the current (deficient) state deviates
        from Mercurial's default configuration.
 
     fromconfig (``deficiency`` types only)
        Boolean indicating whether the current (deficient) state deviates
        from the current Mercurial configuration.
     """
     def __init__(self, name, type, description, upgrademessage, **kwargs):
         self.name = name
         self.type = type
         self.description = description
         self.upgrademessage = upgrademessage
 
         for k, v in kwargs.items():
             setattr(self, k, v)
 
 def upgradefindimprovements(repo):
     """Determine improvements that can be made to the repo during upgrade.
 
     Returns a list of ``upgradeimprovement`` describing repository deficiencies
     and optimizations.
     """
     # Avoid cycle: cmdutil -> repair -> localrepo -> cmdutil
     from . import localrepo
 
     newreporeqs = localrepo.newreporequirements(repo)
 
     improvements = []
 
     # We could detect lack of revlogv1 and store here, but they were added
     # in 0.9.2 and we don't support upgrading repos without these
     # requirements, so let's not bother.
 
     if 'fncache' not in repo.requirements:
         improvements.append(upgradeimprovement(
             name='fncache',
             type=deficiency,
             description=_('long and reserved filenames may not work correctly; '
                           'repository performance is sub-optimal'),
             upgrademessage=_('repository will be more resilient to storing '
                              'certain paths and performance of certain '
                              'operations should be improved'),
             fromdefault=True,
             fromconfig='fncache' in newreporeqs))
 
     if 'dotencode' not in repo.requirements:
         improvements.append(upgradeimprovement(
             name='dotencode',
             type=deficiency,
             description=_('storage of filenames beginning with a period or '
                           'space may not work correctly'),
             upgrademessage=_('repository will be better able to store files '
                              'beginning with a space or period'),
             fromdefault=True,
             fromconfig='dotencode' in newreporeqs))
 
     if 'generaldelta' not in repo.requirements:
         improvements.append(upgradeimprovement(
             name='generaldelta',
             type=deficiency,
             description=_('deltas within internal storage are unable to '
                           'choose optimal revisions; repository is larger and '
                           'slower than it could be; interaction with other '
                           'repositories may require extra network and CPU '
                           'resources, making "hg push" and "hg pull" slower'),
             upgrademessage=_('repository storage will be able to create '
                              'optimal deltas; new repository data will be '
                              'smaller and read times should decrease; '
                              'interacting with other repositories using this '
                              'storage model should require less network and '
                              'CPU resources, making "hg push" and "hg pull" '
                              'faster'),
             fromdefault=True,
             fromconfig='generaldelta' in newreporeqs))
 
     # Mercurial 4.0 changed changelogs to not use delta chains. Search for
     # changelogs with deltas.
     cl = repo.changelog
     for rev in cl:
         chainbase = cl.chainbase(rev)
         if chainbase != rev:
             improvements.append(upgradeimprovement(
                 name='removecldeltachain',
                 type=deficiency,
                 description=_('changelog storage is using deltas instead of '
                               'raw entries; changelog reading and any '
                               'operation relying on changelog data are slower '
                               'than they could be'),
                 upgrademessage=_('changelog storage will be reformated to '
                                  'store raw entries; changelog reading will be '
                                  'faster; changelog size may be reduced'),
                 fromdefault=True,
                 fromconfig=True))
             break
 
     # Now for the optimizations.
 
     # These are unconditionally added. There is logic later that figures out
     # which ones to apply.
 
     improvements.append(upgradeimprovement(
         name='redeltaparent',
         type=optimisation,
         description=_('deltas within internal storage will be recalculated to '
                       'choose an optimal base revision where this was not '
                       'already done; the size of the repository may shrink and '
                       'various operations may become faster; the first time '
                       'this optimization is performed could slow down upgrade '
                       'execution considerably; subsequent invocations should '
                       'not run noticeably slower'),
         upgrademessage=_('deltas within internal storage will choose a new '
                          'base revision if needed')))
 
     improvements.append(upgradeimprovement(
         name='redeltamultibase',
         type=optimisation,
         description=_('deltas within internal storage will be recalculated '
                       'against multiple base revision and the smallest '
                       'difference will be used; the size of the repository may '
                       'shrink significantly when there are many merges; this '
                       'optimization will slow down execution in proportion to '
                       'the number of merges in the repository and the amount '
                       'of files in the repository; this slow down should not '
                       'be significant unless there are tens of thousands of '
                       'files and thousands of merges'),
         upgrademessage=_('deltas within internal storage will choose an '
                          'optimal delta by computing deltas against multiple '
                          'parents; may slow down execution time '
                          'significantly')))
 
     improvements.append(upgradeimprovement(
         name='redeltaall',
         type=optimisation,
         description=_('deltas within internal storage will always be '
                       'recalculated without reusing prior deltas; this will '
                       'likely make execution run several times slower; this '
                       'optimization is typically not needed'),
         upgrademessage=_('deltas within internal storage will be fully '
                          'recomputed; this will likely drastically slow down '
                          'execution time')))
 
     return improvements
 
 def upgradedetermineactions(repo, improvements, sourcereqs, destreqs,
                             optimize):
     """Determine upgrade actions that will be performed.
 
     Given a list of improvements as returned by ``upgradefindimprovements``,
     determine the list of upgrade actions that will be performed.
 
     The role of this function is to filter improvements if needed, apply
     recommended optimizations from the improvements list that make sense,
     etc.
 
     Returns a list of action names.
     """
     newactions = []
 
     knownreqs = upgradesupporteddestrequirements(repo)
 
     for i in improvements:
         name = i.name
 
         # If the action is a requirement that doesn't show up in the
         # destination requirements, prune the action.
         if name in knownreqs and name not in destreqs:
             continue
 
         if i.type == deficiency:
             newactions.append(name)
 
     newactions.extend(o for o in sorted(optimize) if o not in newactions)
 
     # FUTURE consider adding some optimizations here for certain transitions.
     # e.g. adding generaldelta could schedule parent redeltas.
 
     return newactions
 
 def _revlogfrompath(repo, path):
     """Obtain a revlog from a repo path.
 
     An instance of the appropriate class is returned.
     """
     if path == '00changelog.i':
         return changelog.changelog(repo.svfs)
     elif path.endswith('00manifest.i'):
         mandir = path[:-len('00manifest.i')]
         return manifest.manifestrevlog(repo.svfs, dir=mandir)
     else:
         # Filelogs don't do anything special with settings. So we can use a
         # vanilla revlog.
         return revlog.revlog(repo.svfs, path)
 
 def _copyrevlogs(ui, srcrepo, dstrepo, tr, deltareuse, aggressivemergedeltas):
     """Copy revlogs between 2 repos."""
     revcount = 0
     srcsize = 0
     srcrawsize = 0
     dstsize = 0
     fcount = 0
     frevcount = 0
     fsrcsize = 0
     frawsize = 0
     fdstsize = 0
     mcount = 0
     mrevcount = 0
     msrcsize = 0
     mrawsize = 0
     mdstsize = 0
     crevcount = 0
     csrcsize = 0
     crawsize = 0
     cdstsize = 0
 
     # Perform a pass to collect metadata. This validates we can open all
     # source files and allows a unified progress bar to be displayed.
     for unencoded, encoded, size in srcrepo.store.walk():
         if unencoded.endswith('.d'):
             continue
 
         rl = _revlogfrompath(srcrepo, unencoded)
         revcount += len(rl)
 
         datasize = 0
         rawsize = 0
         idx = rl.index
         for rev in rl:
             e = idx[rev]
             datasize += e[1]
             rawsize += e[2]
 
         srcsize += datasize
         srcrawsize += rawsize
 
         # This is for the separate progress bars.
         if isinstance(rl, changelog.changelog):
             crevcount += len(rl)
             csrcsize += datasize
             crawsize += rawsize
         elif isinstance(rl, manifest.manifestrevlog):
             mcount += 1
             mrevcount += len(rl)
             msrcsize += datasize
             mrawsize += rawsize
         elif isinstance(rl, revlog.revlog):
             fcount += 1
             frevcount += len(rl)
             fsrcsize += datasize
             frawsize += rawsize
 
     if not revcount:
         return
 
     ui.write(_('migrating %d total revisions (%d in filelogs, %d in manifests, '
                '%d in changelog)\n') %
              (revcount, frevcount, mrevcount, crevcount))
     ui.write(_('migrating %s in store; %s tracked data\n') % (
              (util.bytecount(srcsize), util.bytecount(srcrawsize))))
 
     # Used to keep track of progress.
     progress = []
     def oncopiedrevision(rl, rev, node):
         progress[1] += 1
         srcrepo.ui.progress(progress[0], progress[1], total=progress[2])
 
     # Do the actual copying.
     # FUTURE this operation can be farmed off to worker processes.
     seen = set()
     for unencoded, encoded, size in srcrepo.store.walk():
         if unencoded.endswith('.d'):
             continue
 
         oldrl = _revlogfrompath(srcrepo, unencoded)
         newrl = _revlogfrompath(dstrepo, unencoded)
 
         if isinstance(oldrl, changelog.changelog) and 'c' not in seen:
             ui.write(_('finished migrating %d manifest revisions across %d '
                        'manifests; change in size: %s\n') %
                      (mrevcount, mcount, util.bytecount(mdstsize - msrcsize)))
 
             ui.write(_('migrating changelog containing %d revisions '
                        '(%s in store; %s tracked data)\n') %
                      (crevcount, util.bytecount(csrcsize),
                       util.bytecount(crawsize)))
             seen.add('c')
             progress[:] = [_('changelog revisions'), 0, crevcount]
         elif isinstance(oldrl, manifest.manifestrevlog) and 'm' not in seen:
             ui.write(_('finished migrating %d filelog revisions across %d '
                        'filelogs; change in size: %s\n') %
                      (frevcount, fcount, util.bytecount(fdstsize - fsrcsize)))
 
             ui.write(_('migrating %d manifests containing %d revisions '
                        '(%s in store; %s tracked data)\n') %
                      (mcount, mrevcount, util.bytecount(msrcsize),
                       util.bytecount(mrawsize)))
             seen.add('m')
             progress[:] = [_('manifest revisions'), 0, mrevcount]
         elif 'f' not in seen:
             ui.write(_('migrating %d filelogs containing %d revisions '
                        '(%s in store; %s tracked data)\n') %
                      (fcount, frevcount, util.bytecount(fsrcsize),
                       util.bytecount(frawsize)))
             seen.add('f')
             progress[:] = [_('file revisions'), 0, frevcount]
 
         ui.progress(progress[0], progress[1], total=progress[2])
 
         ui.note(_('cloning %d revisions from %s\n') % (len(oldrl), unencoded))
         oldrl.clone(tr, newrl, addrevisioncb=oncopiedrevision,
                     deltareuse=deltareuse,
                     aggressivemergedeltas=aggressivemergedeltas)
 
         datasize = 0
         idx = newrl.index
         for rev in newrl:
             datasize += idx[rev][1]
 
         dstsize += datasize
 
         if isinstance(newrl, changelog.changelog):
             cdstsize += datasize
         elif isinstance(newrl, manifest.manifestrevlog):
             mdstsize += datasize
         else:
             fdstsize += datasize
 
     ui.progress(progress[0], None)
 
     ui.write(_('finished migrating %d changelog revisions; change in size: '
                '%s\n') % (crevcount, util.bytecount(cdstsize - csrcsize)))
 
     ui.write(_('finished migrating %d total revisions; total change in store '
                'size: %s\n') % (revcount, util.bytecount(dstsize - srcsize)))
 
 def _upgradefilterstorefile(srcrepo, dstrepo, requirements, path, mode, st):
     """Determine whether to copy a store file during upgrade.
 
     This function is called when migrating store files from ``srcrepo`` to
     ``dstrepo`` as part of upgrading a repository.
 
     Args:
       srcrepo: repo we are copying from
       dstrepo: repo we are copying to
       requirements: set of requirements for ``dstrepo``
       path: store file being examined
       mode: the ``ST_MODE`` file type of ``path``
       st: ``stat`` data structure for ``path``
 
     Function should return ``True`` if the file is to be copied.
     """
     # Skip revlogs.
     if path.endswith(('.i', '.d')):
         return False
     # Skip transaction related files.
     if path.startswith('undo'):
         return False
     # Only copy regular files.
     if mode != stat.S_IFREG:
         return False
     # Skip other skipped files.
     if path in ('lock', 'fncache'):
         return False
 
     return True
 
 def _upgradefinishdatamigration(ui, srcrepo, dstrepo, requirements):
     """Hook point for extensions to perform additional actions during upgrade.
 
     This function is called after revlogs and store files have been copied but
     before the new store is swapped into the original location.
     """
 
 def _upgraderepo(ui, srcrepo, dstrepo, requirements, actions):
     """Do the low-level work of upgrading a repository.
 
     The upgrade is effectively performed as a copy between a source
     repository and a temporary destination repository.
 
     The source repository is unmodified for as long as possible so the
     upgrade can abort at any time without causing loss of service for
     readers and without corrupting the source repository.
     """
     assert srcrepo.currentwlock()
     assert dstrepo.currentwlock()
 
     ui.write(_('(it is safe to interrupt this process any time before '
                'data migration completes)\n'))
 
     if 'redeltaall' in actions:
         deltareuse = revlog.revlog.DELTAREUSENEVER
     elif 'redeltaparent' in actions:
         deltareuse = revlog.revlog.DELTAREUSESAMEREVS
     elif 'redeltamultibase' in actions:
         deltareuse = revlog.revlog.DELTAREUSESAMEREVS
     else:
         deltareuse = revlog.revlog.DELTAREUSEALWAYS
 
     with dstrepo.transaction('upgrade') as tr:
         _copyrevlogs(ui, srcrepo, dstrepo, tr, deltareuse,
                      'redeltamultibase' in actions)
 
     # Now copy other files in the store directory.
     for p, kind, st in srcrepo.store.vfs.readdir('', stat=True):
         if not _upgradefilterstorefile(srcrepo, dstrepo, requirements,
                                        p, kind, st):
             continue
 
         srcrepo.ui.write(_('copying %s\n') % p)
         src = srcrepo.store.vfs.join(p)
         dst = dstrepo.store.vfs.join(p)
         util.copyfile(src, dst, copystat=True)
 
     _upgradefinishdatamigration(ui, srcrepo, dstrepo, requirements)
 
     ui.write(_('data fully migrated to temporary repository\n'))
 
     backuppath = tempfile.mkdtemp(prefix='upgradebackup.', dir=srcrepo.path)
     backupvfs = scmutil.vfs(backuppath)
 
     # Make a backup of requires file first, as it is the first to be modified.
     util.copyfile(srcrepo.join('requires'), backupvfs.join('requires'))
 
     # We install an arbitrary requirement that clients must not support
     # as a mechanism to lock out new clients during the data swap. This is
     # better than allowing a client to continue while the repository is in
     # an inconsistent state.
     ui.write(_('marking source repository as being upgraded; clients will be '
                'unable to read from repository\n'))
     scmutil.writerequires(srcrepo.vfs,
                           srcrepo.requirements | set(['upgradeinprogress']))
 
     ui.write(_('starting in-place swap of repository data\n'))
     ui.write(_('replaced files will be backed up at %s\n') %
              backuppath)
 
     # Now swap in the new store directory. Doing it as a rename should make
     # the operation nearly instantaneous and atomic (at least in well-behaved
     # environments).
     ui.write(_('replacing store...\n'))
-    tstart = time.time()
+    tstart = util.timer()
     util.rename(srcrepo.spath, backupvfs.join('store'))
     util.rename(dstrepo.spath, srcrepo.spath)
-    elapsed = time.time() - tstart
+    elapsed = util.timer() - tstart
     ui.write(_('store replacement complete; repository was inconsistent for '
                '%0.1fs\n') % elapsed)
 
     # We first write the requirements file. Any new requirements will lock
     # out legacy clients.
     ui.write(_('finalizing requirements file and making repository readable '
                'again\n'))
     scmutil.writerequires(srcrepo.vfs, requirements)
 
     # The lock file from the old store won't be removed because nothing has a
     # reference to its new location. So clean it up manually. Alternatively, we
     # could update srcrepo.svfs and other variables to point to the new
     # location. This is simpler.
     backupvfs.unlink('store/lock')
 
     return backuppath
 
 def upgraderepo(ui, repo, run=False, optimize=None):
     """Upgrade a repository in place."""
     # Avoid cycle: cmdutil -> repair -> localrepo -> cmdutil
     from . import localrepo
 
     optimize = set(optimize or [])
     repo = repo.unfiltered()
 
     # Ensure the repository can be upgraded.
     missingreqs = upgraderequiredsourcerequirements(repo) - repo.requirements
     if missingreqs:
         raise error.Abort(_('cannot upgrade repository; requirement '
                             'missing: %s') % _(', ').join(sorted(missingreqs)))
 
     blockedreqs = upgradeblocksourcerequirements(repo) & repo.requirements
     if blockedreqs:
         raise error.Abort(_('cannot upgrade repository; unsupported source '
                             'requirement: %s') %
                           _(', ').join(sorted(blockedreqs)))
 
     # FUTURE there is potentially a need to control the wanted requirements via
     # command arguments or via an extension hook point.
     newreqs = localrepo.newreporequirements(repo)
 
     noremovereqs = (repo.requirements - newreqs -
                    upgradesupportremovedrequirements(repo))
     if noremovereqs:
         raise error.Abort(_('cannot upgrade repository; requirement would be '
                             'removed: %s') % _(', ').join(sorted(noremovereqs)))
 
     noaddreqs = (newreqs - repo.requirements -
                  upgradeallowednewrequirements(repo))
     if noaddreqs:
         raise error.Abort(_('cannot upgrade repository; do not support adding '
                             'requirement: %s') %
                           _(', ').join(sorted(noaddreqs)))
 
     unsupportedreqs = newreqs - upgradesupporteddestrequirements(repo)
     if unsupportedreqs:
         raise error.Abort(_('cannot upgrade repository; do not support '
                             'destination requirement: %s') %
                           _(', ').join(sorted(unsupportedreqs)))
 
     # Find and validate all improvements that can be made.
     improvements = upgradefindimprovements(repo)
     for i in improvements:
         if i.type not in (deficiency, optimisation):
             raise error.Abort(_('unexpected improvement type %s for %s') % (
                 i.type, i.name))
 
     # Validate arguments.
     unknownoptimize = optimize - set(i.name for i in improvements
                                      if i.type == optimisation)
     if unknownoptimize:
         raise error.Abort(_('unknown optimization action requested: %s') %
                           ', '.join(sorted(unknownoptimize)),
                           hint=_('run without arguments to see valid '
                                  'optimizations'))
 
     actions = upgradedetermineactions(repo, improvements, repo.requirements,
                                       newreqs, optimize)
 
     def printrequirements():
         ui.write(_('requirements\n'))
         ui.write(_('   preserved: %s\n') %
                  _(', ').join(sorted(newreqs & repo.requirements)))
 
         if repo.requirements - newreqs:
             ui.write(_('   removed: %s\n') %
                      _(', ').join(sorted(repo.requirements - newreqs)))
 
         if newreqs - repo.requirements:
             ui.write(_('   added: %s\n') %
                      _(', ').join(sorted(newreqs - repo.requirements)))
 
         ui.write('\n')
 
     def printupgradeactions():
         for action in actions:
             for i in improvements:
                 if i.name == action:
                     ui.write('%s\n   %s\n\n' %
                              (i.name, i.upgrademessage))
 
     if not run:
         fromdefault = []
         fromconfig = []
         optimizations = []
 
         for i in improvements:
             assert i.type in (deficiency, optimisation)
             if i.type == deficiency:
                 if i.fromdefault:
                     fromdefault.append(i)
                 if i.fromconfig:
                     fromconfig.append(i)
             else:
                 optimizations.append(i)
 
         if fromdefault or fromconfig:
             fromconfignames = set(x.name for x in fromconfig)
             onlydefault = [i for i in fromdefault
                            if i.name not in fromconfignames]
 
             if fromconfig:
                 ui.write(_('repository lacks features recommended by '
                            'current config options:\n\n'))
                 for i in fromconfig:
                     ui.write('%s\n   %s\n\n' % (i.name, i.description))
 
             if onlydefault:
                 ui.write(_('repository lacks features used by the default '
                            'config options:\n\n'))
                 for i in onlydefault:
                     ui.write('%s\n   %s\n\n' % (i.name, i.description))
 
             ui.write('\n')
         else:
             ui.write(_('(no feature deficiencies found in existing '
                        'repository)\n'))
 
         ui.write(_('performing an upgrade with "--run" will make the following '
                    'changes:\n\n'))
 
         printrequirements()
         printupgradeactions()
 
         unusedoptimize = [i for i in improvements
                           if i.name not in actions and i.type == optimisation]
         if unusedoptimize:
             ui.write(_('additional optimizations are available by specifying '
                      '"--optimize <name>":\n\n'))
             for i in unusedoptimize:
                 ui.write(_('%s\n   %s\n\n') % (i.name, i.description))
         return
 
     # Else we're in the run=true case.
     ui.write(_('upgrade will perform the following actions:\n\n'))
     printrequirements()
     printupgradeactions()
 
     ui.write(_('beginning upgrade...\n'))
     with repo.wlock():
         with repo.lock():
             ui.write(_('repository locked and read-only\n'))
             # Our strategy for upgrading the repository is to create a new,
             # temporary repository, write data to it, then do a swap of the
             # data. There are less heavyweight ways to do this, but it is easier
             # to create a new repo object than to instantiate all the components
             # (like the store) separately.
             tmppath = tempfile.mkdtemp(prefix='upgrade.', dir=repo.path)
             backuppath = None
             try:
                 ui.write(_('creating temporary repository to stage migrated '
                            'data: %s\n') % tmppath)
                 dstrepo = localrepo.localrepository(repo.baseui,
                                                     path=tmppath,
                                                     create=True)
 
                 with dstrepo.wlock():
                     with dstrepo.lock():
                         backuppath = _upgraderepo(ui, repo, dstrepo, newreqs,
                                                   actions)
 
             finally:
                 ui.write(_('removing temporary repository %s\n') % tmppath)
                 repo.vfs.rmtree(tmppath, forcibly=True)
 
                 if backuppath:
                     ui.warn(_('copy of old repository backed up at %s\n') %
                             backuppath)
                     ui.warn(_('the old repository will not be deleted; remove '
                               'it to free up disk space once the upgraded '
                               'repository is verified\n'))

mercurial/streamclone.py

@@ -1,398 +1,397
 # streamclone.py - producing and consuming streaming repository data
 #
 # Copyright 2015 Gregory Szorc <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import struct
-import time
 
 from .i18n import _
 from . import (
     branchmap,
     error,
     store,
     util,
 )
 
 def canperformstreamclone(pullop, bailifbundle2supported=False):
     """Whether it is possible to perform a streaming clone as part of pull.
 
     ``bailifbundle2supported`` will cause the function to return False if
     bundle2 stream clones are supported. It should only be called by the
     legacy stream clone code path.
 
     Returns a tuple of (supported, requirements). ``supported`` is True if
     streaming clone is supported and False otherwise. ``requirements`` is
     a set of repo requirements from the remote, or ``None`` if stream clone
     isn't supported.
     """
     repo = pullop.repo
     remote = pullop.remote
 
     bundle2supported = False
     if pullop.canusebundle2:
         if 'v1' in pullop.remotebundle2caps.get('stream', []):
             bundle2supported = True
         # else
             # Server doesn't support bundle2 stream clone or doesn't support
             # the versions we support. Fall back and possibly allow legacy.
 
     # Ensures legacy code path uses available bundle2.
     if bailifbundle2supported and bundle2supported:
         return False, None
     # Ensures bundle2 doesn't try to do a stream clone if it isn't supported.
     #elif not bailifbundle2supported and not bundle2supported:
     #    return False, None
 
     # Streaming clone only works on empty repositories.
     if len(repo):
         return False, None
 
     # Streaming clone only works if all data is being requested.
     if pullop.heads:
         return False, None
 
     streamrequested = pullop.streamclonerequested
 
     # If we don't have a preference, let the server decide for us. This
     # likely only comes into play in LANs.
     if streamrequested is None:
         # The server can advertise whether to prefer streaming clone.
         streamrequested = remote.capable('stream-preferred')
 
     if not streamrequested:
         return False, None
 
     # In order for stream clone to work, the client has to support all the
     # requirements advertised by the server.
     #
     # The server advertises its requirements via the "stream" and "streamreqs"
     # capability. "stream" (a value-less capability) is advertised if and only
     # if the only requirement is "revlogv1." Else, the "streamreqs" capability
     # is advertised and contains a comma-delimited list of requirements.
     requirements = set()
     if remote.capable('stream'):
         requirements.add('revlogv1')
     else:
         streamreqs = remote.capable('streamreqs')
         # This is weird and shouldn't happen with modern servers.
         if not streamreqs:
             return False, None
 
         streamreqs = set(streamreqs.split(','))
         # Server requires something we don't support. Bail.
         if streamreqs - repo.supportedformats:
             return False, None
         requirements = streamreqs
 
     return True, requirements
 
 def maybeperformlegacystreamclone(pullop):
     """Possibly perform a legacy stream clone operation.
 
     Legacy stream clones are performed as part of pull but before all other
     operations.
 
     A legacy stream clone will not be performed if a bundle2 stream clone is
     supported.
     """
     supported, requirements = canperformstreamclone(pullop)
 
     if not supported:
         return
 
     repo = pullop.repo
     remote = pullop.remote
 
     # Save remote branchmap. We will use it later to speed up branchcache
     # creation.
     rbranchmap = None
     if remote.capable('branchmap'):
         rbranchmap = remote.branchmap()
 
     repo.ui.status(_('streaming all changes\n'))
 
     fp = remote.stream_out()
     l = fp.readline()
     try:
         resp = int(l)
     except ValueError:
         raise error.ResponseError(
             _('unexpected response from remote server:'), l)
     if resp == 1:
         raise error.Abort(_('operation forbidden by server'))
     elif resp == 2:
         raise error.Abort(_('locking the remote repository failed'))
     elif resp != 0:
         raise error.Abort(_('the server sent an unknown error code'))
 
     l = fp.readline()
     try:
         filecount, bytecount = map(int, l.split(' ', 1))
     except (ValueError, TypeError):
         raise error.ResponseError(
             _('unexpected response from remote server:'), l)
 
     with repo.lock():
         consumev1(repo, fp, filecount, bytecount)
 
         # new requirements = old non-format requirements +
         #                    new format-related remote requirements
         # requirements from the streamed-in repository
         repo.requirements = requirements | (
                 repo.requirements - repo.supportedformats)
         repo._applyopenerreqs()
         repo._writerequirements()
 
         if rbranchmap:
             branchmap.replacecache(repo, rbranchmap)
 
         repo.invalidate()
 
 def allowservergeneration(ui):
     """Whether streaming clones are allowed from the server."""
     return ui.configbool('server', 'uncompressed', True, untrusted=True)
 
 # This is it's own function so extensions can override it.
 def _walkstreamfiles(repo):
     return repo.store.walk()
 
 def generatev1(repo):
     """Emit content for version 1 of a streaming clone.
 
     This returns a 3-tuple of (file count, byte size, data iterator).
 
     The data iterator consists of N entries for each file being transferred.
     Each file entry starts as a line with the file name and integer size
     delimited by a null byte.
 
     The raw file data follows. Following the raw file data is the next file
     entry, or EOF.
 
     When used on the wire protocol, an additional line indicating protocol
     success will be prepended to the stream. This function is not responsible
     for adding it.
 
     This function will obtain a repository lock to ensure a consistent view of
     the store is captured. It therefore may raise LockError.
     """
     entries = []
     total_bytes = 0
     # Get consistent snapshot of repo, lock during scan.
     with repo.lock():
         repo.ui.debug('scanning\n')
         for name, ename, size in _walkstreamfiles(repo):
             if size:
                 entries.append((name, size))
                 total_bytes += size
 
     repo.ui.debug('%d files, %d bytes to transfer\n' %
                   (len(entries), total_bytes))
 
     svfs = repo.svfs
     oldaudit = svfs.mustaudit
     debugflag = repo.ui.debugflag
     svfs.mustaudit = False
 
     def emitrevlogdata():
         try:
             for name, size in entries:
                 if debugflag:
                     repo.ui.debug('sending %s (%d bytes)\n' % (name, size))
                 # partially encode name over the wire for backwards compat
                 yield '%s\0%d\n' % (store.encodedir(name), size)
                 if size <= 65536:
                     with svfs(name, 'rb') as fp:
                         yield fp.read(size)
                 else:
                     for chunk in util.filechunkiter(svfs(name), limit=size):
                         yield chunk
         finally:
             svfs.mustaudit = oldaudit
 
     return len(entries), total_bytes, emitrevlogdata()
 
 def generatev1wireproto(repo):
     """Emit content for version 1 of streaming clone suitable for the wire.
 
     This is the data output from ``generatev1()`` with a header line
     indicating file count and byte size.
     """
     filecount, bytecount, it = generatev1(repo)
     yield '%d %d\n' % (filecount, bytecount)
     for chunk in it:
         yield chunk
 
 def generatebundlev1(repo, compression='UN'):
     """Emit content for version 1 of a stream clone bundle.
 
     The first 4 bytes of the output ("HGS1") denote this as stream clone
     bundle version 1.
 
     The next 2 bytes indicate the compression type. Only "UN" is currently
     supported.
 
     The next 16 bytes are two 64-bit big endian unsigned integers indicating
     file count and byte count, respectively.
 
     The next 2 bytes is a 16-bit big endian unsigned short declaring the length
     of the requirements string, including a trailing \0. The following N bytes
     are the requirements string, which is ASCII containing a comma-delimited
     list of repo requirements that are needed to support the data.
 
     The remaining content is the output of ``generatev1()`` (which may be
     compressed in the future).
 
     Returns a tuple of (requirements, data generator).
     """
     if compression != 'UN':
         raise ValueError('we do not support the compression argument yet')
 
     requirements = repo.requirements & repo.supportedformats
     requires = ','.join(sorted(requirements))
 
     def gen():
         yield 'HGS1'
         yield compression
 
         filecount, bytecount, it = generatev1(repo)
         repo.ui.status(_('writing %d bytes for %d files\n') %
                          (bytecount, filecount))
 
         yield struct.pack('>QQ', filecount, bytecount)
         yield struct.pack('>H', len(requires) + 1)
         yield requires + '\0'
 
         # This is where we'll add compression in the future.
         assert compression == 'UN'
 
         seen = 0
         repo.ui.progress(_('bundle'), 0, total=bytecount, unit=_('bytes'))
 
         for chunk in it:
             seen += len(chunk)
             repo.ui.progress(_('bundle'), seen, total=bytecount,
                              unit=_('bytes'))
             yield chunk
 
         repo.ui.progress(_('bundle'), None)
 
     return requirements, gen()
 
 def consumev1(repo, fp, filecount, bytecount):
     """Apply the contents from version 1 of a streaming clone file handle.
 
     This takes the output from "stream_out" and applies it to the specified
     repository.
 
     Like "stream_out," the status line added by the wire protocol is not
     handled by this function.
     """
     with repo.lock():
         repo.ui.status(_('%d files to transfer, %s of data\n') %
                        (filecount, util.bytecount(bytecount)))
         handled_bytes = 0
         repo.ui.progress(_('clone'), 0, total=bytecount, unit=_('bytes'))
-        start = time.time()
+        start = util.timer()
 
         # TODO: get rid of (potential) inconsistency
         #
         # If transaction is started and any @filecache property is
         # changed at this point, it causes inconsistency between
         # in-memory cached property and streamclone-ed file on the
         # disk. Nested transaction prevents transaction scope "clone"
         # below from writing in-memory changes out at the end of it,
         # even though in-memory changes are discarded at the end of it
         # regardless of transaction nesting.
         #
         # But transaction nesting can't be simply prohibited, because
         # nesting occurs also in ordinary case (e.g. enabling
         # clonebundles).
 
         with repo.transaction('clone'):
             with repo.svfs.backgroundclosing(repo.ui, expectedcount=filecount):
                 for i in xrange(filecount):
                     # XXX doesn't support '\n' or '\r' in filenames
                     l = fp.readline()
                     try:
                         name, size = l.split('\0', 1)
                         size = int(size)
                     except (ValueError, TypeError):
                         raise error.ResponseError(
                             _('unexpected response from remote server:'), l)
                     if repo.ui.debugflag:
                         repo.ui.debug('adding %s (%s)\n' %
                                       (name, util.bytecount(size)))
                     # for backwards compat, name was partially encoded
                     path = store.decodedir(name)
                     with repo.svfs(path, 'w', backgroundclose=True) as ofp:
                         for chunk in util.filechunkiter(fp, limit=size):
                             handled_bytes += len(chunk)
                             repo.ui.progress(_('clone'), handled_bytes,
                                              total=bytecount, unit=_('bytes'))
                             ofp.write(chunk)
 
             # force @filecache properties to be reloaded from
             # streamclone-ed file at next access
             repo.invalidate(clearfilecache=True)
 
-        elapsed = time.time() - start
+        elapsed = util.timer() - start
         if elapsed <= 0:
             elapsed = 0.001
         repo.ui.progress(_('clone'), None)
         repo.ui.status(_('transferred %s in %.1f seconds (%s/sec)\n') %
                        (util.bytecount(bytecount), elapsed,
                         util.bytecount(bytecount / elapsed)))
 
 def readbundle1header(fp):
     compression = fp.read(2)
     if compression != 'UN':
         raise error.Abort(_('only uncompressed stream clone bundles are '
             'supported; got %s') % compression)
 
     filecount, bytecount = struct.unpack('>QQ', fp.read(16))
     requireslen = struct.unpack('>H', fp.read(2))[0]
     requires = fp.read(requireslen)
 
     if not requires.endswith('\0'):
         raise error.Abort(_('malformed stream clone bundle: '
                             'requirements not properly encoded'))
 
     requirements = set(requires.rstrip('\0').split(','))
 
     return filecount, bytecount, requirements
 
 def applybundlev1(repo, fp):
     """Apply the content from a stream clone bundle version 1.
 
     We assume the 4 byte header has been read and validated and the file handle
     is at the 2 byte compression identifier.
     """
     if len(repo):
         raise error.Abort(_('cannot apply stream clone bundle on non-empty '
                             'repo'))
 
     filecount, bytecount, requirements = readbundle1header(fp)
     missingreqs = requirements - repo.supportedformats
     if missingreqs:
         raise error.Abort(_('unable to apply stream clone: '
                             'unsupported format: %s') %
                             ', '.join(sorted(missingreqs)))
 
     consumev1(repo, fp, filecount, bytecount)
 
 class streamcloneapplier(object):
     """Class to manage applying streaming clone bundles.
 
     We need to wrap ``applybundlev1()`` in a dedicated type to enable bundle
     readers to perform bundle type-specific functionality.
     """
     def __init__(self, fh):
         self._fh = fh
 
     def apply(self, repo):
         return applybundlev1(repo, self._fh)

mercurial/tags.py

@@ -1,571 +1,570
 # tags.py - read tag info from local repository
 #
 # Copyright 2009 Matt Mackall <[e-mail]>
 # Copyright 2009 Greg Ward <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 # Currently this module only deals with reading and caching tags.
 # Eventually, it could take care of updating (adding/removing/moving)
 # tags too.
 
 from __future__ import absolute_import
 
 import array
 import errno
-import time
 
 from .node import (
     bin,
     hex,
     nullid,
     short,
 )
 from . import (
     encoding,
     error,
     util,
 )
 
 array = array.array
 
 # Tags computation can be expensive and caches exist to make it fast in
 # the common case.
 #
 # The "hgtagsfnodes1" cache file caches the .hgtags filenode values for
 # each revision in the repository. The file is effectively an array of
 # fixed length records. Read the docs for "hgtagsfnodescache" for technical
 # details.
 #
 # The .hgtags filenode cache grows in proportion to the length of the
 # changelog. The file is truncated when the # changelog is stripped.
 #
 # The purpose of the filenode cache is to avoid the most expensive part
 # of finding global tags, which is looking up the .hgtags filenode in the
 # manifest for each head. This can take dozens or over 100ms for
 # repositories with very large manifests. Multiplied by dozens or even
 # hundreds of heads and there is a significant performance concern.
 #
 # There also exist a separate cache file for each repository filter.
 # These "tags-*" files store information about the history of tags.
 #
 # The tags cache files consists of a cache validation line followed by
 # a history of tags.
 #
 # The cache validation line has the format:
 #
 #   <tiprev> <tipnode> [<filteredhash>]
 #
 # <tiprev> is an integer revision and <tipnode> is a 40 character hex
 # node for that changeset. These redundantly identify the repository
 # tip from the time the cache was written. In addition, <filteredhash>,
 # if present, is a 40 character hex hash of the contents of the filtered
 # revisions for this filter. If the set of filtered revs changes, the
 # hash will change and invalidate the cache.
 #
 # The history part of the tags cache consists of lines of the form:
 #
 #   <node> <tag>
 #
 # (This format is identical to that of .hgtags files.)
 #
 # <tag> is the tag name and <node> is the 40 character hex changeset
 # the tag is associated with.
 #
 # Tags are written sorted by tag name.
 #
 # Tags associated with multiple changesets have an entry for each changeset.
 # The most recent changeset (in terms of revlog ordering for the head
 # setting it) for each tag is last.
 
 def findglobaltags(ui, repo, alltags, tagtypes):
     '''Find global tags in a repo.
 
     "alltags" maps tag name to (node, hist) 2-tuples.
 
     "tagtypes" maps tag name to tag type. Global tags always have the
     "global" tag type.
 
     The "alltags" and "tagtypes" dicts are updated in place. Empty dicts
     should be passed in.
 
     The tags cache is read and updated as a side-effect of calling.
     '''
     # This is so we can be lazy and assume alltags contains only global
     # tags when we pass it to _writetagcache().
     assert len(alltags) == len(tagtypes) == 0, \
            "findglobaltags() should be called first"
 
     (heads, tagfnode, valid, cachetags, shouldwrite) = _readtagcache(ui, repo)
     if cachetags is not None:
         assert not shouldwrite
         # XXX is this really 100% correct?  are there oddball special
         # cases where a global tag should outrank a local tag but won't,
         # because cachetags does not contain rank info?
         _updatetags(cachetags, 'global', alltags, tagtypes)
         return
 
     seen = set()  # set of fnode
     fctx = None
     for head in reversed(heads):  # oldest to newest
         assert head in repo.changelog.nodemap, \
                "tag cache returned bogus head %s" % short(head)
 
         fnode = tagfnode.get(head)
         if fnode and fnode not in seen:
             seen.add(fnode)
             if not fctx:
                 fctx = repo.filectx('.hgtags', fileid=fnode)
             else:
                 fctx = fctx.filectx(fnode)
 
             filetags = _readtags(ui, repo, fctx.data().splitlines(), fctx)
             _updatetags(filetags, 'global', alltags, tagtypes)
 
     # and update the cache (if necessary)
     if shouldwrite:
         _writetagcache(ui, repo, valid, alltags)
 
 def readlocaltags(ui, repo, alltags, tagtypes):
     '''Read local tags in repo. Update alltags and tagtypes.'''
     try:
         data = repo.vfs.read("localtags")
     except IOError as inst:
         if inst.errno != errno.ENOENT:
             raise
         return
 
     # localtags is in the local encoding; re-encode to UTF-8 on
     # input for consistency with the rest of this module.
     filetags = _readtags(
         ui, repo, data.splitlines(), "localtags",
         recode=encoding.fromlocal)
 
     # remove tags pointing to invalid nodes
     cl = repo.changelog
     for t in filetags.keys():
         try:
             cl.rev(filetags[t][0])
         except (LookupError, ValueError):
             del filetags[t]
 
     _updatetags(filetags, "local", alltags, tagtypes)
 
 def _readtaghist(ui, repo, lines, fn, recode=None, calcnodelines=False):
     '''Read tag definitions from a file (or any source of lines).
 
     This function returns two sortdicts with similar information:
 
     - the first dict, bintaghist, contains the tag information as expected by
       the _readtags function, i.e. a mapping from tag name to (node, hist):
         - node is the node id from the last line read for that name,
         - hist is the list of node ids previously associated with it (in file
           order). All node ids are binary, not hex.
 
     - the second dict, hextaglines, is a mapping from tag name to a list of
       [hexnode, line number] pairs, ordered from the oldest to the newest node.
 
     When calcnodelines is False the hextaglines dict is not calculated (an
     empty dict is returned). This is done to improve this function's
     performance in cases where the line numbers are not needed.
     '''
 
     bintaghist = util.sortdict()
     hextaglines = util.sortdict()
     count = 0
 
     def dbg(msg):
         ui.debug("%s, line %s: %s\n" % (fn, count, msg))
 
     for nline, line in enumerate(lines):
         count += 1
         if not line:
             continue
         try:
             (nodehex, name) = line.split(" ", 1)
         except ValueError:
             dbg("cannot parse entry")
             continue
         name = name.strip()
         if recode:
             name = recode(name)
         try:
             nodebin = bin(nodehex)
         except TypeError:
             dbg("node '%s' is not well formed" % nodehex)
             continue
 
         # update filetags
         if calcnodelines:
             # map tag name to a list of line numbers
             if name not in hextaglines:
                 hextaglines[name] = []
             hextaglines[name].append([nodehex, nline])
             continue
         # map tag name to (node, hist)
         if name not in bintaghist:
             bintaghist[name] = []
         bintaghist[name].append(nodebin)
     return bintaghist, hextaglines
 
 def _readtags(ui, repo, lines, fn, recode=None, calcnodelines=False):
     '''Read tag definitions from a file (or any source of lines).
 
     Returns a mapping from tag name to (node, hist).
 
     "node" is the node id from the last line read for that name. "hist"
     is the list of node ids previously associated with it (in file order).
     All node ids are binary, not hex.
     '''
     filetags, nodelines = _readtaghist(ui, repo, lines, fn, recode=recode,
                                        calcnodelines=calcnodelines)
     # util.sortdict().__setitem__ is much slower at replacing then inserting
     # new entries. The difference can matter if there are thousands of tags.
     # Create a new sortdict to avoid the performance penalty.
     newtags = util.sortdict()
     for tag, taghist in filetags.items():
         newtags[tag] = (taghist[-1], taghist[:-1])
     return newtags
 
 def _updatetags(filetags, tagtype, alltags, tagtypes):
     '''Incorporate the tag info read from one file into the two
     dictionaries, alltags and tagtypes, that contain all tag
     info (global across all heads plus local).'''
 
     for name, nodehist in filetags.iteritems():
         if name not in alltags:
             alltags[name] = nodehist
             tagtypes[name] = tagtype
             continue
 
         # we prefer alltags[name] if:
         #  it supersedes us OR
         #  mutual supersedes and it has a higher rank
         # otherwise we win because we're tip-most
         anode, ahist = nodehist
         bnode, bhist = alltags[name]
         if (bnode != anode and anode in bhist and
             (bnode not in ahist or len(bhist) > len(ahist))):
             anode = bnode
         else:
             tagtypes[name] = tagtype
         ahist.extend([n for n in bhist if n not in ahist])
         alltags[name] = anode, ahist
 
 def _filename(repo):
     """name of a tagcache file for a given repo or repoview"""
     filename = 'cache/tags2'
     if repo.filtername:
         filename = '%s-%s' % (filename, repo.filtername)
     return filename
 
 def _readtagcache(ui, repo):
     '''Read the tag cache.
 
     Returns a tuple (heads, fnodes, validinfo, cachetags, shouldwrite).
 
     If the cache is completely up-to-date, "cachetags" is a dict of the
     form returned by _readtags() and "heads", "fnodes", and "validinfo" are
     None and "shouldwrite" is False.
 
     If the cache is not up to date, "cachetags" is None. "heads" is a list
     of all heads currently in the repository, ordered from tip to oldest.
     "validinfo" is a tuple describing cache validation info. This is used
     when writing the tags cache. "fnodes" is a mapping from head to .hgtags
     filenode. "shouldwrite" is True.
 
     If the cache is not up to date, the caller is responsible for reading tag
     info from each returned head. (See findglobaltags().)
     '''
     from . import scmutil  # avoid cycle
 
     try:
         cachefile = repo.vfs(_filename(repo), 'r')
         # force reading the file for static-http
         cachelines = iter(cachefile)
     except IOError:
         cachefile = None
 
     cacherev = None
     cachenode = None
     cachehash = None
     if cachefile:
         try:
             validline = next(cachelines)
             validline = validline.split()
             cacherev = int(validline[0])
             cachenode = bin(validline[1])
             if len(validline) > 2:
                 cachehash = bin(validline[2])
         except Exception:
             # corruption of the cache, just recompute it.
             pass
 
     tipnode = repo.changelog.tip()
     tiprev = len(repo.changelog) - 1
 
     # Case 1 (common): tip is the same, so nothing has changed.
     # (Unchanged tip trivially means no changesets have been added.
     # But, thanks to localrepository.destroyed(), it also means none
     # have been destroyed by strip or rollback.)
     if (cacherev == tiprev
             and cachenode == tipnode
             and cachehash == scmutil.filteredhash(repo, tiprev)):
         tags = _readtags(ui, repo, cachelines, cachefile.name)
         cachefile.close()
         return (None, None, None, tags, False)
     if cachefile:
         cachefile.close()               # ignore rest of file
 
     valid = (tiprev, tipnode, scmutil.filteredhash(repo, tiprev))
 
     repoheads = repo.heads()
     # Case 2 (uncommon): empty repo; get out quickly and don't bother
     # writing an empty cache.
     if repoheads == [nullid]:
         return ([], {}, valid, {}, False)
 
     # Case 3 (uncommon): cache file missing or empty.
 
     # Case 4 (uncommon): tip rev decreased.  This should only happen
     # when we're called from localrepository.destroyed().  Refresh the
     # cache so future invocations will not see disappeared heads in the
     # cache.
 
     # Case 5 (common): tip has changed, so we've added/replaced heads.
 
     # As it happens, the code to handle cases 3, 4, 5 is the same.
 
     # N.B. in case 4 (nodes destroyed), "new head" really means "newly
     # exposed".
     if not len(repo.file('.hgtags')):
         # No tags have ever been committed, so we can avoid a
         # potentially expensive search.
         return ([], {}, valid, None, True)
 
-    starttime = time.time()
+    starttime = util.timer()
 
     # Now we have to lookup the .hgtags filenode for every new head.
     # This is the most expensive part of finding tags, so performance
     # depends primarily on the size of newheads.  Worst case: no cache
     # file, so newheads == repoheads.
     fnodescache = hgtagsfnodescache(repo.unfiltered())
     cachefnode = {}
     for head in reversed(repoheads):
         fnode = fnodescache.getfnode(head)
         if fnode != nullid:
             cachefnode[head] = fnode
 
     fnodescache.write()
 
-    duration = time.time() - starttime
+    duration = util.timer() - starttime
     ui.log('tagscache',
            '%d/%d cache hits/lookups in %0.4f '
            'seconds\n',
            fnodescache.hitcount, fnodescache.lookupcount, duration)
 
     # Caller has to iterate over all heads, but can use the filenodes in
     # cachefnode to get to each .hgtags revision quickly.
     return (repoheads, cachefnode, valid, None, True)
 
 def _writetagcache(ui, repo, valid, cachetags):
     filename = _filename(repo)
     try:
         cachefile = repo.vfs(filename, 'w', atomictemp=True)
     except (OSError, IOError):
         return
 
     ui.log('tagscache', 'writing .hg/%s with %d tags\n',
            filename, len(cachetags))
 
     if valid[2]:
         cachefile.write('%d %s %s\n' % (valid[0], hex(valid[1]), hex(valid[2])))
     else:
         cachefile.write('%d %s\n' % (valid[0], hex(valid[1])))
 
     # Tag names in the cache are in UTF-8 -- which is the whole reason
     # we keep them in UTF-8 throughout this module.  If we converted
     # them local encoding on input, we would lose info writing them to
     # the cache.
     for (name, (node, hist)) in sorted(cachetags.iteritems()):
         for n in hist:
             cachefile.write("%s %s\n" % (hex(n), name))
         cachefile.write("%s %s\n" % (hex(node), name))
 
     try:
         cachefile.close()
     except (OSError, IOError):
         pass
 
 _fnodescachefile = 'cache/hgtagsfnodes1'
 _fnodesrecsize = 4 + 20 # changeset fragment + filenode
 _fnodesmissingrec = '\xff' * 24
 
 class hgtagsfnodescache(object):
     """Persistent cache mapping revisions to .hgtags filenodes.
 
     The cache is an array of records. Each item in the array corresponds to
     a changelog revision. Values in the array contain the first 4 bytes of
     the node hash and the 20 bytes .hgtags filenode for that revision.
 
     The first 4 bytes are present as a form of verification. Repository
     stripping and rewriting may change the node at a numeric revision in the
     changelog. The changeset fragment serves as a verifier to detect
     rewriting. This logic is shared with the rev branch cache (see
     branchmap.py).
 
     The instance holds in memory the full cache content but entries are
     only parsed on read.
 
     Instances behave like lists. ``c[i]`` works where i is a rev or
     changeset node. Missing indexes are populated automatically on access.
     """
     def __init__(self, repo):
         assert repo.filtername is None
 
         self._repo = repo
 
         # Only for reporting purposes.
         self.lookupcount = 0
         self.hitcount = 0
 
         self._raw = array('c')
 
         try:
             data = repo.vfs.read(_fnodescachefile)
         except (OSError, IOError):
             data = ""
         self._raw.fromstring(data)
 
         # The end state of self._raw is an array that is of the exact length
         # required to hold a record for every revision in the repository.
         # We truncate or extend the array as necessary. self._dirtyoffset is
         # defined to be the start offset at which we need to write the output
         # file. This offset is also adjusted when new entries are calculated
         # for array members.
         cllen = len(repo.changelog)
         wantedlen = cllen * _fnodesrecsize
         rawlen = len(self._raw)
 
         self._dirtyoffset = None
 
         if rawlen < wantedlen:
             self._dirtyoffset = rawlen
             self._raw.extend('\xff' * (wantedlen - rawlen))
         elif rawlen > wantedlen:
             # There's no easy way to truncate array instances. This seems
             # slightly less evil than copying a potentially large array slice.
             for i in range(rawlen - wantedlen):
                 self._raw.pop()
             self._dirtyoffset = len(self._raw)
 
     def getfnode(self, node, computemissing=True):
         """Obtain the filenode of the .hgtags file at a specified revision.
 
         If the value is in the cache, the entry will be validated and returned.
         Otherwise, the filenode will be computed and returned unless
         "computemissing" is False, in which case None will be returned without
         any potentially expensive computation being performed.
 
         If an .hgtags does not exist at the specified revision, nullid is
         returned.
         """
         ctx = self._repo[node]
         rev = ctx.rev()
 
         self.lookupcount += 1
 
         offset = rev * _fnodesrecsize
         record = self._raw[offset:offset + _fnodesrecsize].tostring()
         properprefix = node[0:4]
 
         # Validate and return existing entry.
         if record != _fnodesmissingrec:
             fileprefix = record[0:4]
 
             if fileprefix == properprefix:
                 self.hitcount += 1
                 return record[4:]
 
             # Fall through.
 
         # If we get here, the entry is either missing or invalid.
 
         if not computemissing:
             return None
 
         # Populate missing entry.
         try:
             fnode = ctx.filenode('.hgtags')
         except error.LookupError:
             # No .hgtags file on this revision.
             fnode = nullid
 
         self._writeentry(offset, properprefix, fnode)
         return fnode
 
     def setfnode(self, node, fnode):
         """Set the .hgtags filenode for a given changeset."""
         assert len(fnode) == 20
         ctx = self._repo[node]
 
         # Do a lookup first to avoid writing if nothing has changed.
         if self.getfnode(ctx.node(), computemissing=False) == fnode:
             return
 
         self._writeentry(ctx.rev() * _fnodesrecsize, node[0:4], fnode)
 
     def _writeentry(self, offset, prefix, fnode):
         # Slices on array instances only accept other array.
         entry = array('c', prefix + fnode)
         self._raw[offset:offset + _fnodesrecsize] = entry
         # self._dirtyoffset could be None.
         self._dirtyoffset = min(self._dirtyoffset, offset) or 0
 
     def write(self):
         """Perform all necessary writes to cache file.
 
         This may no-op if no writes are needed or if a write lock could
         not be obtained.
         """
         if self._dirtyoffset is None:
             return
 
         data = self._raw[self._dirtyoffset:]
         if not data:
             return
 
         repo = self._repo
 
         try:
             lock = repo.wlock(wait=False)
         except error.LockError:
             repo.ui.log('tagscache',
                         'not writing .hg/%s because lock cannot be acquired\n' %
                         (_fnodescachefile))
             return
 
         try:
             f = repo.vfs.open(_fnodescachefile, 'ab')
             try:
                 # if the file has been truncated
                 actualoffset = f.tell()
                 if actualoffset < self._dirtyoffset:
                     self._dirtyoffset = actualoffset
                     data = self._raw[self._dirtyoffset:]
                 f.seek(self._dirtyoffset)
                 f.truncate()
                 repo.ui.log('tagscache',
                             'writing %d bytes to %s\n' % (
                             len(data), _fnodescachefile))
                 f.write(data)
                 self._dirtyoffset = None
             finally:
                 f.close()
         except (IOError, OSError) as inst:
             repo.ui.log('tagscache',
                         "couldn't write %s: %s\n" % (
                         _fnodescachefile, inst))
         finally:
             lock.release()

mercurial/util.py

@@ -1,3556 +1,3556
 # util.py - Mercurial utility functions and platform specific implementations
 #
 #  Copyright 2005 K. Thananchayan <[e-mail]>
 #  Copyright 2005-2007 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 version 2 or any later version.
 
 """Mercurial utility functions and platform specific implementations.
 
 This contains helper routines that are independent of the SCM core and
 hide platform-specific details from the core.
 """
 
 from __future__ import absolute_import
 
 import bz2
 import calendar
 import collections
 import datetime
 import errno
 import gc
 import hashlib
 import imp
 import os
 import platform as pyplatform
 import re as remod
 import shutil
 import signal
 import socket
 import stat
 import string
 import subprocess
 import sys
 import tempfile
 import textwrap
 import time
 import traceback
 import zlib
 
 from . import (
     encoding,
     error,
     i18n,
     osutil,
     parsers,
     pycompat,
 )
 
 empty = pycompat.empty
 httplib = pycompat.httplib
 httpserver = pycompat.httpserver
 pickle = pycompat.pickle
 queue = pycompat.queue
 socketserver = pycompat.socketserver
 stderr = pycompat.stderr
 stdin = pycompat.stdin
 stdout = pycompat.stdout
 stringio = pycompat.stringio
 urlerr = pycompat.urlerr
 urlparse = pycompat.urlparse
 urlreq = pycompat.urlreq
 xmlrpclib = pycompat.xmlrpclib
 
 def isatty(fp):
     try:
         return fp.isatty()
     except AttributeError:
         return False
 
 # glibc determines buffering on first write to stdout - if we replace a TTY
 # destined stdout with a pipe destined stdout (e.g. pager), we want line
 # buffering
 if isatty(stdout):
     stdout = os.fdopen(stdout.fileno(), 'wb', 1)
 
 if pycompat.osname == 'nt':
     from . import windows as platform
     stdout = platform.winstdout(stdout)
 else:
     from . import posix as platform
 
 _ = i18n._
 
 bindunixsocket = platform.bindunixsocket
 cachestat = platform.cachestat
 checkexec = platform.checkexec
 checklink = platform.checklink
 copymode = platform.copymode
 executablepath = platform.executablepath
 expandglobs = platform.expandglobs
 explainexit = platform.explainexit
 findexe = platform.findexe
 gethgcmd = platform.gethgcmd
 getuser = platform.getuser
 getpid = os.getpid
 groupmembers = platform.groupmembers
 groupname = platform.groupname
 hidewindow = platform.hidewindow
 isexec = platform.isexec
 isowner = platform.isowner
 localpath = platform.localpath
 lookupreg = platform.lookupreg
 makedir = platform.makedir
 nlinks = platform.nlinks
 normpath = platform.normpath
 normcase = platform.normcase
 normcasespec = platform.normcasespec
 normcasefallback = platform.normcasefallback
 openhardlinks = platform.openhardlinks
 oslink = platform.oslink
 parsepatchoutput = platform.parsepatchoutput
 pconvert = platform.pconvert
 poll = platform.poll
 popen = platform.popen
 posixfile = platform.posixfile
 quotecommand = platform.quotecommand
 readpipe = platform.readpipe
 rename = platform.rename
 removedirs = platform.removedirs
 samedevice = platform.samedevice
 samefile = platform.samefile
 samestat = platform.samestat
 setbinary = platform.setbinary
 setflags = platform.setflags
 setsignalhandler = platform.setsignalhandler
 shellquote = platform.shellquote
 spawndetached = platform.spawndetached
 split = platform.split
 sshargs = platform.sshargs
 statfiles = getattr(osutil, 'statfiles', platform.statfiles)
 statisexec = platform.statisexec
 statislink = platform.statislink
 testpid = platform.testpid
 umask = platform.umask
 unlink = platform.unlink
 unlinkpath = platform.unlinkpath
 username = platform.username
 
 # Python compatibility
 
 _notset = object()
 
 # disable Python's problematic floating point timestamps (issue4836)
 # (Python hypocritically says you shouldn't change this behavior in
 # libraries, and sure enough Mercurial is not a library.)
 os.stat_float_times(False)
 
 def safehasattr(thing, attr):
     return getattr(thing, attr, _notset) is not _notset
 
 def bitsfrom(container):
     bits = 0
     for bit in container:
         bits |= bit
     return bits
 
 DIGESTS = {
     'md5': hashlib.md5,
     'sha1': hashlib.sha1,
     'sha512': hashlib.sha512,
 }
 # List of digest types from strongest to weakest
 DIGESTS_BY_STRENGTH = ['sha512', 'sha1', 'md5']
 
 for k in DIGESTS_BY_STRENGTH:
     assert k in DIGESTS
 
 class digester(object):
     """helper to compute digests.
 
     This helper can be used to compute one or more digests given their name.
 
     >>> d = digester(['md5', 'sha1'])
     >>> d.update('foo')
     >>> [k for k in sorted(d)]
     ['md5', 'sha1']
     >>> d['md5']
     'acbd18db4cc2f85cedef654fccc4a4d8'
     >>> d['sha1']
     '0beec7b5ea3f0fdbc95d0dd47f3c5bc275da8a33'
     >>> digester.preferred(['md5', 'sha1'])
     'sha1'
     """
 
     def __init__(self, digests, s=''):
         self._hashes = {}
         for k in digests:
             if k not in DIGESTS:
                 raise Abort(_('unknown digest type: %s') % k)
             self._hashes[k] = DIGESTS[k]()
         if s:
             self.update(s)
 
     def update(self, data):
         for h in self._hashes.values():
             h.update(data)
 
     def __getitem__(self, key):
         if key not in DIGESTS:
             raise Abort(_('unknown digest type: %s') % k)
         return self._hashes[key].hexdigest()
 
     def __iter__(self):
         return iter(self._hashes)
 
     @staticmethod
     def preferred(supported):
         """returns the strongest digest type in both supported and DIGESTS."""
 
         for k in DIGESTS_BY_STRENGTH:
             if k in supported:
                 return k
         return None
 
 class digestchecker(object):
     """file handle wrapper that additionally checks content against a given
     size and digests.
 
         d = digestchecker(fh, size, {'md5': '...'})
 
     When multiple digests are given, all of them are validated.
     """
 
     def __init__(self, fh, size, digests):
         self._fh = fh
         self._size = size
         self._got = 0
         self._digests = dict(digests)
         self._digester = digester(self._digests.keys())
 
     def read(self, length=-1):
         content = self._fh.read(length)
         self._digester.update(content)
         self._got += len(content)
         return content
 
     def validate(self):
         if self._size != self._got:
             raise Abort(_('size mismatch: expected %d, got %d') %
                 (self._size, self._got))
         for k, v in self._digests.items():
             if v != self._digester[k]:
                 # i18n: first parameter is a digest name
                 raise Abort(_('%s mismatch: expected %s, got %s') %
                     (k, v, self._digester[k]))
 
 try:
     buffer = buffer
 except NameError:
     if not pycompat.ispy3:
         def buffer(sliceable, offset=0, length=None):
             if length is not None:
                 return sliceable[offset:offset + length]
             return sliceable[offset:]
     else:
         def buffer(sliceable, offset=0, length=None):
             if length is not None:
                 return memoryview(sliceable)[offset:offset + length]
             return memoryview(sliceable)[offset:]
 
 closefds = pycompat.osname == 'posix'
 
 _chunksize = 4096
 
 class bufferedinputpipe(object):
     """a manually buffered input pipe
 
     Python will not let us use buffered IO and lazy reading with 'polling' at
     the same time. We cannot probe the buffer state and select will not detect
     that data are ready to read if they are already buffered.
 
     This class let us work around that by implementing its own buffering
     (allowing efficient readline) while offering a way to know if the buffer is
     empty from the output (allowing collaboration of the buffer with polling).
 
     This class lives in the 'util' module because it makes use of the 'os'
     module from the python stdlib.
     """
 
     def __init__(self, input):
         self._input = input
         self._buffer = []
         self._eof = False
         self._lenbuf = 0
 
     @property
     def hasbuffer(self):
         """True is any data is currently buffered
 
         This will be used externally a pre-step for polling IO. If there is
         already data then no polling should be set in place."""
         return bool(self._buffer)
 
     @property
     def closed(self):
         return self._input.closed
 
     def fileno(self):
         return self._input.fileno()
 
     def close(self):
         return self._input.close()
 
     def read(self, size):
         while (not self._eof) and (self._lenbuf < size):
             self._fillbuffer()
         return self._frombuffer(size)
 
     def readline(self, *args, **kwargs):
         if 1 < len(self._buffer):
             # this should not happen because both read and readline end with a
             # _frombuffer call that collapse it.
             self._buffer = [''.join(self._buffer)]
             self._lenbuf = len(self._buffer[0])
         lfi = -1
         if self._buffer:
             lfi = self._buffer[-1].find('\n')
         while (not self._eof) and lfi < 0:
             self._fillbuffer()
             if self._buffer:
                 lfi = self._buffer[-1].find('\n')
         size = lfi + 1
         if lfi < 0: # end of file
             size = self._lenbuf
         elif 1 < len(self._buffer):
             # we need to take previous chunks into account
             size += self._lenbuf - len(self._buffer[-1])
         return self._frombuffer(size)
 
     def _frombuffer(self, size):
         """return at most 'size' data from the buffer
 
         The data are removed from the buffer."""
         if size == 0 or not self._buffer:
             return ''
         buf = self._buffer[0]
         if 1 < len(self._buffer):
             buf = ''.join(self._buffer)
 
         data = buf[:size]
         buf = buf[len(data):]
         if buf:
             self._buffer = [buf]
             self._lenbuf = len(buf)
         else:
             self._buffer = []
             self._lenbuf = 0
         return data
 
     def _fillbuffer(self):
         """read data to the buffer"""
         data = os.read(self._input.fileno(), _chunksize)
         if not data:
             self._eof = True
         else:
             self._lenbuf += len(data)
             self._buffer.append(data)
 
 def popen2(cmd, env=None, newlines=False):
     # Setting bufsize to -1 lets the system decide the buffer size.
     # The default for bufsize is 0, meaning unbuffered. This leads to
     # poor performance on Mac OS X: http://bugs.python.org/issue4194
     p = subprocess.Popen(cmd, shell=True, bufsize=-1,
                          close_fds=closefds,
                          stdin=subprocess.PIPE, stdout=subprocess.PIPE,
                          universal_newlines=newlines,
                          env=env)
     return p.stdin, p.stdout
 
 def popen3(cmd, env=None, newlines=False):
     stdin, stdout, stderr, p = popen4(cmd, env, newlines)
     return stdin, stdout, stderr
 
 def popen4(cmd, env=None, newlines=False, bufsize=-1):
     p = subprocess.Popen(cmd, shell=True, bufsize=bufsize,
                          close_fds=closefds,
                          stdin=subprocess.PIPE, stdout=subprocess.PIPE,
                          stderr=subprocess.PIPE,
                          universal_newlines=newlines,
                          env=env)
     return p.stdin, p.stdout, p.stderr, p
 
 def version():
     """Return version information if available."""
     try:
         from . import __version__
         return __version__.version
     except ImportError:
         return 'unknown'
 
 def versiontuple(v=None, n=4):
     """Parses a Mercurial version string into an N-tuple.
 
     The version string to be parsed is specified with the ``v`` argument.
     If it isn't defined, the current Mercurial version string will be parsed.
 
     ``n`` can be 2, 3, or 4. Here is how some version strings map to
     returned values:
 
     >>> v = '3.6.1+190-df9b73d2d444'
     >>> versiontuple(v, 2)
     (3, 6)
     >>> versiontuple(v, 3)
     (3, 6, 1)
     >>> versiontuple(v, 4)
     (3, 6, 1, '190-df9b73d2d444')
 
     >>> versiontuple('3.6.1+190-df9b73d2d444+20151118')
     (3, 6, 1, '190-df9b73d2d444+20151118')
 
     >>> v = '3.6'
     >>> versiontuple(v, 2)
     (3, 6)
     >>> versiontuple(v, 3)
     (3, 6, None)
     >>> versiontuple(v, 4)
     (3, 6, None, None)
 
     >>> v = '3.9-rc'
     >>> versiontuple(v, 2)
     (3, 9)
     >>> versiontuple(v, 3)
     (3, 9, None)
     >>> versiontuple(v, 4)
     (3, 9, None, 'rc')
 
     >>> v = '3.9-rc+2-02a8fea4289b'
     >>> versiontuple(v, 2)
     (3, 9)
     >>> versiontuple(v, 3)
     (3, 9, None)
     >>> versiontuple(v, 4)
     (3, 9, None, 'rc+2-02a8fea4289b')
     """
     if not v:
         v = version()
     parts = remod.split('[\+-]', v, 1)
     if len(parts) == 1:
         vparts, extra = parts[0], None
     else:
         vparts, extra = parts
 
     vints = []
     for i in vparts.split('.'):
         try:
             vints.append(int(i))
         except ValueError:
             break
     # (3, 6) -> (3, 6, None)
     while len(vints) < 3:
         vints.append(None)
 
     if n == 2:
         return (vints[0], vints[1])
     if n == 3:
         return (vints[0], vints[1], vints[2])
     if n == 4:
         return (vints[0], vints[1], vints[2], extra)
 
 # used by parsedate
 defaultdateformats = (
     '%Y-%m-%dT%H:%M:%S', # the 'real' ISO8601
     '%Y-%m-%dT%H:%M',    #   without seconds
     '%Y-%m-%dT%H%M%S',   # another awful but legal variant without :
     '%Y-%m-%dT%H%M',     #   without seconds
     '%Y-%m-%d %H:%M:%S', # our common legal variant
     '%Y-%m-%d %H:%M',    #   without seconds
     '%Y-%m-%d %H%M%S',   # without :
     '%Y-%m-%d %H%M',     #   without seconds
     '%Y-%m-%d %I:%M:%S%p',
     '%Y-%m-%d %H:%M',
     '%Y-%m-%d %I:%M%p',
     '%Y-%m-%d',
     '%m-%d',
     '%m/%d',
     '%m/%d/%y',
     '%m/%d/%Y',
     '%a %b %d %H:%M:%S %Y',
     '%a %b %d %I:%M:%S%p %Y',
     '%a, %d %b %Y %H:%M:%S',        #  GNU coreutils "/bin/date --rfc-2822"
     '%b %d %H:%M:%S %Y',
     '%b %d %I:%M:%S%p %Y',
     '%b %d %H:%M:%S',
     '%b %d %I:%M:%S%p',
     '%b %d %H:%M',
     '%b %d %I:%M%p',
     '%b %d %Y',
     '%b %d',
     '%H:%M:%S',
     '%I:%M:%S%p',
     '%H:%M',
     '%I:%M%p',
 )
 
 extendeddateformats = defaultdateformats + (
     "%Y",
     "%Y-%m",
     "%b",
     "%b %Y",
     )
 
 def cachefunc(func):
     '''cache the result of function calls'''
     # XXX doesn't handle keywords args
     if func.__code__.co_argcount == 0:
         cache = []
         def f():
             if len(cache) == 0:
                 cache.append(func())
             return cache[0]
         return f
     cache = {}
     if func.__code__.co_argcount == 1:
         # we gain a small amount of time because
         # we don't need to pack/unpack the list
         def f(arg):
             if arg not in cache:
                 cache[arg] = func(arg)
             return cache[arg]
     else:
         def f(*args):
             if args not in cache:
                 cache[args] = func(*args)
             return cache[args]
 
     return f
 
 class sortdict(dict):
     '''a simple sorted dictionary'''
     def __init__(self, data=None):
         self._list = []
         if data:
             self.update(data)
     def copy(self):
         return sortdict(self)
     def __setitem__(self, key, val):
         if key in self:
             self._list.remove(key)
         self._list.append(key)
         dict.__setitem__(self, key, val)
     def __iter__(self):
         return self._list.__iter__()
     def update(self, src):
         if isinstance(src, dict):
             src = src.iteritems()
         for k, v in src:
             self[k] = v
     def clear(self):
         dict.clear(self)
         self._list = []
     def items(self):
         return [(k, self[k]) for k in self._list]
     def __delitem__(self, key):
         dict.__delitem__(self, key)
         self._list.remove(key)
     def pop(self, key, *args, **kwargs):
         dict.pop(self, key, *args, **kwargs)
         try:
             self._list.remove(key)
         except ValueError:
             pass
     def keys(self):
         return self._list[:]
     def iterkeys(self):
         return self._list.__iter__()
     def iteritems(self):
         for k in self._list:
             yield k, self[k]
     def insert(self, index, key, val):
         self._list.insert(index, key)
         dict.__setitem__(self, key, val)
     def __repr__(self):
         if not self:
             return '%s()' % self.__class__.__name__
         return '%s(%r)' % (self.__class__.__name__, self.items())
 
 class _lrucachenode(object):
     """A node in a doubly linked list.
 
     Holds a reference to nodes on either side as well as a key-value
     pair for the dictionary entry.
     """
     __slots__ = (u'next', u'prev', u'key', u'value')
 
     def __init__(self):
         self.next = None
         self.prev = None
 
         self.key = _notset
         self.value = None
 
     def markempty(self):
         """Mark the node as emptied."""
         self.key = _notset
 
 class lrucachedict(object):
     """Dict that caches most recent accesses and sets.
 
     The dict consists of an actual backing dict - indexed by original
     key - and a doubly linked circular list defining the order of entries in
     the cache.
 
     The head node is the newest entry in the cache. If the cache is full,
     we recycle head.prev and make it the new head. Cache accesses result in
     the node being moved to before the existing head and being marked as the
     new head node.
     """
     def __init__(self, max):
         self._cache = {}
 
         self._head = head = _lrucachenode()
         head.prev = head
         head.next = head
         self._size = 1
         self._capacity = max
 
     def __len__(self):
         return len(self._cache)
 
     def __contains__(self, k):
         return k in self._cache
 
     def __iter__(self):
         # We don't have to iterate in cache order, but why not.
         n = self._head
         for i in range(len(self._cache)):
             yield n.key
             n = n.next
 
     def __getitem__(self, k):
         node = self._cache[k]
         self._movetohead(node)
         return node.value
 
     def __setitem__(self, k, v):
         node = self._cache.get(k)
         # Replace existing value and mark as newest.
         if node is not None:
             node.value = v
             self._movetohead(node)
             return
 
         if self._size < self._capacity:
             node = self._addcapacity()
         else:
             # Grab the last/oldest item.
             node = self._head.prev
 
         # At capacity. Kill the old entry.
         if node.key is not _notset:
             del self._cache[node.key]
 
         node.key = k
         node.value = v
         self._cache[k] = node
         # And mark it as newest entry. No need to adjust order since it
         # is already self._head.prev.
         self._head = node
 
     def __delitem__(self, k):
         node = self._cache.pop(k)
         node.markempty()
 
         # Temporarily mark as newest item before re-adjusting head to make
         # this node the oldest item.
         self._movetohead(node)
         self._head = node.next
 
     # Additional dict methods.
 
     def get(self, k, default=None):
         try:
             return self._cache[k].value
         except KeyError:
             return default
 
     def clear(self):
         n = self._head
         while n.key is not _notset:
             n.markempty()
             n = n.next
 
         self._cache.clear()
 
     def copy(self):
         result = lrucachedict(self._capacity)
         n = self._head.prev
         # Iterate in oldest-to-newest order, so the copy has the right ordering
         for i in range(len(self._cache)):
             result[n.key] = n.value
             n = n.prev
         return result
 
     def _movetohead(self, node):
         """Mark a node as the newest, making it the new head.
 
         When a node is accessed, it becomes the freshest entry in the LRU
         list, which is denoted by self._head.
 
         Visually, let's make ``N`` the new head node (* denotes head):
 
             previous/oldest <-> head <-> next/next newest
 
             ----<->--- A* ---<->-----
             |                       |
             E <-> D <-> N <-> C <-> B
 
         To:
 
             ----<->--- N* ---<->-----
             |                       |
             E <-> D <-> C <-> B <-> A
 
         This requires the following moves:
 
            C.next = D  (node.prev.next = node.next)
            D.prev = C  (node.next.prev = node.prev)
            E.next = N  (head.prev.next = node)
            N.prev = E  (node.prev = head.prev)
            N.next = A  (node.next = head)
            A.prev = N  (head.prev = node)
         """
         head = self._head
         # C.next = D
         node.prev.next = node.next
         # D.prev = C
         node.next.prev = node.prev
         # N.prev = E
         node.prev = head.prev
         # N.next = A
         # It is tempting to do just "head" here, however if node is
         # adjacent to head, this will do bad things.
         node.next = head.prev.next
         # E.next = N
         node.next.prev = node
         # A.prev = N
         node.prev.next = node
 
         self._head = node
 
     def _addcapacity(self):
         """Add a node to the circular linked list.
 
         The new node is inserted before the head node.
         """
         head = self._head
         node = _lrucachenode()
         head.prev.next = node
         node.prev = head.prev
         node.next = head
         head.prev = node
         self._size += 1
         return node
 
 def lrucachefunc(func):
     '''cache most recent results of function calls'''
     cache = {}
     order = collections.deque()
     if func.__code__.co_argcount == 1:
         def f(arg):
             if arg not in cache:
                 if len(cache) > 20:
                     del cache[order.popleft()]
                 cache[arg] = func(arg)
             else:
                 order.remove(arg)
             order.append(arg)
             return cache[arg]
     else:
         def f(*args):
             if args not in cache:
                 if len(cache) > 20:
                     del cache[order.popleft()]
                 cache[args] = func(*args)
             else:
                 order.remove(args)
             order.append(args)
             return cache[args]
 
     return f
 
 class propertycache(object):
     def __init__(self, func):
         self.func = func
         self.name = func.__name__
     def __get__(self, obj, type=None):
         result = self.func(obj)
         self.cachevalue(obj, result)
         return result
 
     def cachevalue(self, obj, value):
         # __dict__ assignment required to bypass __setattr__ (eg: repoview)
         obj.__dict__[self.name] = value
 
 def pipefilter(s, cmd):
     '''filter string S through command CMD, returning its output'''
     p = subprocess.Popen(cmd, shell=True, close_fds=closefds,
                          stdin=subprocess.PIPE, stdout=subprocess.PIPE)
     pout, perr = p.communicate(s)
     return pout
 
 def tempfilter(s, cmd):
     '''filter string S through a pair of temporary files with CMD.
     CMD is used as a template to create the real command to be run,
     with the strings INFILE and OUTFILE replaced by the real names of
     the temporary files generated.'''
     inname, outname = None, None
     try:
         infd, inname = tempfile.mkstemp(prefix='hg-filter-in-')
         fp = os.fdopen(infd, pycompat.sysstr('wb'))
         fp.write(s)
         fp.close()
         outfd, outname = tempfile.mkstemp(prefix='hg-filter-out-')
         os.close(outfd)
         cmd = cmd.replace('INFILE', inname)
         cmd = cmd.replace('OUTFILE', outname)
         code = os.system(cmd)
         if pycompat.sysplatform == 'OpenVMS' and code & 1:
             code = 0
         if code:
             raise Abort(_("command '%s' failed: %s") %
                         (cmd, explainexit(code)))
         return readfile(outname)
     finally:
         try:
             if inname:
                 os.unlink(inname)
         except OSError:
             pass
         try:
             if outname:
                 os.unlink(outname)
         except OSError:
             pass
 
 filtertable = {
     'tempfile:': tempfilter,
     'pipe:': pipefilter,
     }
 
 def filter(s, cmd):
     "filter a string through a command that transforms its input to its output"
     for name, fn in filtertable.iteritems():
         if cmd.startswith(name):
             return fn(s, cmd[len(name):].lstrip())
     return pipefilter(s, cmd)
 
 def binary(s):
     """return true if a string is binary data"""
     return bool(s and '\0' in s)
 
 def increasingchunks(source, min=1024, max=65536):
     '''return no less than min bytes per chunk while data remains,
     doubling min after each chunk until it reaches max'''
     def log2(x):
         if not x:
             return 0
         i = 0
         while x:
             x >>= 1
             i += 1
         return i - 1
 
     buf = []
     blen = 0
     for chunk in source:
         buf.append(chunk)
         blen += len(chunk)
         if blen >= min:
             if min < max:
                 min = min << 1
                 nmin = 1 << log2(blen)
                 if nmin > min:
                     min = nmin
                 if min > max:
                     min = max
             yield ''.join(buf)
             blen = 0
             buf = []
     if buf:
         yield ''.join(buf)
 
 Abort = error.Abort
 
 def always(fn):
     return True
 
 def never(fn):
     return False
 
 def nogc(func):
     """disable garbage collector
 
     Python's garbage collector triggers a GC each time a certain number of
     container objects (the number being defined by gc.get_threshold()) are
     allocated even when marked not to be tracked by the collector. Tracking has
     no effect on when GCs are triggered, only on what objects the GC looks
     into. As a workaround, disable GC while building complex (huge)
     containers.
 
     This garbage collector issue have been fixed in 2.7.
     """
     if sys.version_info >= (2, 7):
         return func
     def wrapper(*args, **kwargs):
         gcenabled = gc.isenabled()
         gc.disable()
         try:
             return func(*args, **kwargs)
         finally:
             if gcenabled:
                 gc.enable()
     return wrapper
 
 def pathto(root, n1, n2):
     '''return the relative path from one place to another.
     root should use os.sep to separate directories
     n1 should use os.sep to separate directories
     n2 should use "/" to separate directories
     returns an os.sep-separated path.
 
     If n1 is a relative path, it's assumed it's
     relative to root.
     n2 should always be relative to root.
     '''
     if not n1:
         return localpath(n2)
     if os.path.isabs(n1):
         if os.path.splitdrive(root)[0] != os.path.splitdrive(n1)[0]:
             return os.path.join(root, localpath(n2))
         n2 = '/'.join((pconvert(root), n2))
     a, b = splitpath(n1), n2.split('/')
     a.reverse()
     b.reverse()
     while a and b and a[-1] == b[-1]:
         a.pop()
         b.pop()
     b.reverse()
     return pycompat.ossep.join((['..'] * len(a)) + b) or '.'
 
 def mainfrozen():
     """return True if we are a frozen executable.
 
     The code supports py2exe (most common, Windows only) and tools/freeze
     (portable, not much used).
     """
     return (safehasattr(sys, "frozen") or # new py2exe
             safehasattr(sys, "importers") or # old py2exe
             imp.is_frozen(u"__main__")) # tools/freeze
 
 # the location of data files matching the source code
 if mainfrozen() and getattr(sys, 'frozen', None) != 'macosx_app':
     # executable version (py2exe) doesn't support __file__
     datapath = os.path.dirname(pycompat.sysexecutable)
 else:
     datapath = os.path.dirname(__file__)
 
 if not isinstance(datapath, bytes):
     datapath = pycompat.fsencode(datapath)
 
 i18n.setdatapath(datapath)
 
 _hgexecutable = None
 
 def hgexecutable():
     """return location of the 'hg' executable.
 
     Defaults to $HG or 'hg' in the search path.
     """
     if _hgexecutable is None:
         hg = encoding.environ.get('HG')
         mainmod = sys.modules['__main__']
         if hg:
             _sethgexecutable(hg)
         elif mainfrozen():
             if getattr(sys, 'frozen', None) == 'macosx_app':
                 # Env variable set by py2app
                 _sethgexecutable(encoding.environ['EXECUTABLEPATH'])
             else:
                 _sethgexecutable(pycompat.sysexecutable)
         elif os.path.basename(getattr(mainmod, '__file__', '')) == 'hg':
             _sethgexecutable(mainmod.__file__)
         else:
             exe = findexe('hg') or os.path.basename(sys.argv[0])
             _sethgexecutable(exe)
     return _hgexecutable
 
 def _sethgexecutable(path):
     """set location of the 'hg' executable"""
     global _hgexecutable
     _hgexecutable = path
 
 def _isstdout(f):
     fileno = getattr(f, 'fileno', None)
     return fileno and fileno() == sys.__stdout__.fileno()
 
 def shellenviron(environ=None):
     """return environ with optional override, useful for shelling out"""
     def py2shell(val):
         'convert python object into string that is useful to shell'
         if val is None or val is False:
             return '0'
         if val is True:
             return '1'
         return str(val)
     env = dict(encoding.environ)
     if environ:
         env.update((k, py2shell(v)) for k, v in environ.iteritems())
     env['HG'] = hgexecutable()
     return env
 
 def system(cmd, environ=None, cwd=None, onerr=None, errprefix=None, out=None):
     '''enhanced shell command execution.
     run with environment maybe modified, maybe in different dir.
 
     if command fails and onerr is None, return status, else raise onerr
     object as exception.
 
     if out is specified, it is assumed to be a file-like object that has a
     write() method. stdout and stderr will be redirected to out.'''
     try:
         stdout.flush()
     except Exception:
         pass
     origcmd = cmd
     cmd = quotecommand(cmd)
     if pycompat.sysplatform == 'plan9' and (sys.version_info[0] == 2
                                     and sys.version_info[1] < 7):
         # subprocess kludge to work around issues in half-baked Python
         # ports, notably bichued/python:
         if not cwd is None:
             os.chdir(cwd)
         rc = os.system(cmd)
     else:
         env = shellenviron(environ)
         if out is None or _isstdout(out):
             rc = subprocess.call(cmd, shell=True, close_fds=closefds,
                                  env=env, cwd=cwd)
         else:
             proc = subprocess.Popen(cmd, shell=True, close_fds=closefds,
                                     env=env, cwd=cwd, stdout=subprocess.PIPE,
                                     stderr=subprocess.STDOUT)
             for line in iter(proc.stdout.readline, ''):
                 out.write(line)
             proc.wait()
             rc = proc.returncode
         if pycompat.sysplatform == 'OpenVMS' and rc & 1:
             rc = 0
     if rc and onerr:
         errmsg = '%s %s' % (os.path.basename(origcmd.split(None, 1)[0]),
                             explainexit(rc)[0])
         if errprefix:
             errmsg = '%s: %s' % (errprefix, errmsg)
         raise onerr(errmsg)
     return rc
 
 def checksignature(func):
     '''wrap a function with code to check for calling errors'''
     def check(*args, **kwargs):
         try:
             return func(*args, **kwargs)
         except TypeError:
             if len(traceback.extract_tb(sys.exc_info()[2])) == 1:
                 raise error.SignatureError
             raise
 
     return check
 
 def copyfile(src, dest, hardlink=False, copystat=False, checkambig=False):
     '''copy a file, preserving mode and optionally other stat info like
     atime/mtime
 
     checkambig argument is used with filestat, and is useful only if
     destination file is guarded by any lock (e.g. repo.lock or
     repo.wlock).
 
     copystat and checkambig should be exclusive.
     '''
     assert not (copystat and checkambig)
     oldstat = None
     if os.path.lexists(dest):
         if checkambig:
             oldstat = checkambig and filestat(dest)
         unlink(dest)
     # hardlinks are problematic on CIFS, quietly ignore this flag
     # until we find a way to work around it cleanly (issue4546)
     if False and hardlink:
         try:
             oslink(src, dest)
             return
         except (IOError, OSError):
             pass # fall back to normal copy
     if os.path.islink(src):
         os.symlink(os.readlink(src), dest)
         # copytime is ignored for symlinks, but in general copytime isn't needed
         # for them anyway
     else:
         try:
             shutil.copyfile(src, dest)
             if copystat:
                 # copystat also copies mode
                 shutil.copystat(src, dest)
             else:
                 shutil.copymode(src, dest)
                 if oldstat and oldstat.stat:
                     newstat = filestat(dest)
                     if newstat.isambig(oldstat):
                         # stat of copied file is ambiguous to original one
                         advanced = (oldstat.stat.st_mtime + 1) & 0x7fffffff
                         os.utime(dest, (advanced, advanced))
         except shutil.Error as inst:
             raise Abort(str(inst))
 
 def copyfiles(src, dst, hardlink=None, progress=lambda t, pos: None):
     """Copy a directory tree using hardlinks if possible."""
     num = 0
 
     if hardlink is None:
         hardlink = (os.stat(src).st_dev ==
                     os.stat(os.path.dirname(dst)).st_dev)
     if hardlink:
         topic = _('linking')
     else:
         topic = _('copying')
 
     if os.path.isdir(src):
         os.mkdir(dst)
         for name, kind in osutil.listdir(src):
             srcname = os.path.join(src, name)
             dstname = os.path.join(dst, name)
             def nprog(t, pos):
                 if pos is not None:
                     return progress(t, pos + num)
             hardlink, n = copyfiles(srcname, dstname, hardlink, progress=nprog)
             num += n
     else:
         if hardlink:
             try:
                 oslink(src, dst)
             except (IOError, OSError):
                 hardlink = False
                 shutil.copy(src, dst)
         else:
             shutil.copy(src, dst)
         num += 1
         progress(topic, num)
     progress(topic, None)
 
     return hardlink, num
 
 _winreservednames = '''con prn aux nul
     com1 com2 com3 com4 com5 com6 com7 com8 com9
     lpt1 lpt2 lpt3 lpt4 lpt5 lpt6 lpt7 lpt8 lpt9'''.split()
 _winreservedchars = ':*?"<>|'
 def checkwinfilename(path):
     r'''Check that the base-relative path is a valid filename on Windows.
     Returns None if the path is ok, or a UI string describing the problem.
 
     >>> checkwinfilename("just/a/normal/path")
     >>> checkwinfilename("foo/bar/con.xml")
     "filename contains 'con', which is reserved on Windows"
     >>> checkwinfilename("foo/con.xml/bar")
     "filename contains 'con', which is reserved on Windows"
     >>> checkwinfilename("foo/bar/xml.con")
     >>> checkwinfilename("foo/bar/AUX/bla.txt")
     "filename contains 'AUX', which is reserved on Windows"
     >>> checkwinfilename("foo/bar/bla:.txt")
     "filename contains ':', which is reserved on Windows"
     >>> checkwinfilename("foo/bar/b\07la.txt")
     "filename contains '\\x07', which is invalid on Windows"
     >>> checkwinfilename("foo/bar/bla ")
     "filename ends with ' ', which is not allowed on Windows"
     >>> checkwinfilename("../bar")
     >>> checkwinfilename("foo\\")
     "filename ends with '\\', which is invalid on Windows"
     >>> checkwinfilename("foo\\/bar")
     "directory name ends with '\\', which is invalid on Windows"
     '''
     if path.endswith('\\'):
         return _("filename ends with '\\', which is invalid on Windows")
     if '\\/' in path:
         return _("directory name ends with '\\', which is invalid on Windows")
     for n in path.replace('\\', '/').split('/'):
         if not n:
             continue
         for c in n:
             if c in _winreservedchars:
                 return _("filename contains '%s', which is reserved "
                          "on Windows") % c
             if ord(c) <= 31:
                 return _("filename contains %r, which is invalid "
                          "on Windows") % c
         base = n.split('.')[0]
         if base and base.lower() in _winreservednames:
             return _("filename contains '%s', which is reserved "
                      "on Windows") % base
         t = n[-1]
         if t in '. ' and n not in '..':
             return _("filename ends with '%s', which is not allowed "
                      "on Windows") % t
 
 if pycompat.osname == 'nt':
     checkosfilename = checkwinfilename
     timer = time.clock
 else:
     checkosfilename = platform.checkosfilename
     timer = time.time
 
 if safehasattr(time, "perf_counter"):
     timer = time.perf_counter
 
 def makelock(info, pathname):
     try:
         return os.symlink(info, pathname)
     except OSError as why:
         if why.errno == errno.EEXIST:
             raise
     except AttributeError: # no symlink in os
         pass
 
     ld = os.open(pathname, os.O_CREAT | os.O_WRONLY | os.O_EXCL)
     os.write(ld, info)
     os.close(ld)
 
 def readlock(pathname):
     try:
         return os.readlink(pathname)
     except OSError as why:
         if why.errno not in (errno.EINVAL, errno.ENOSYS):
             raise
     except AttributeError: # no symlink in os
         pass
     fp = posixfile(pathname)
     r = fp.read()
     fp.close()
     return r
 
 def fstat(fp):
     '''stat file object that may not have fileno method.'''
     try:
         return os.fstat(fp.fileno())
     except AttributeError:
         return os.stat(fp.name)
 
 # File system features
 
 def fscasesensitive(path):
     """
     Return true if the given path is on a case-sensitive filesystem
 
     Requires a path (like /foo/.hg) ending with a foldable final
     directory component.
     """
     s1 = os.lstat(path)
     d, b = os.path.split(path)
     b2 = b.upper()
     if b == b2:
         b2 = b.lower()
         if b == b2:
             return True # no evidence against case sensitivity
     p2 = os.path.join(d, b2)
     try:
         s2 = os.lstat(p2)
         if s2 == s1:
             return False
         return True
     except OSError:
         return True
 
 try:
     import re2
     _re2 = None
 except ImportError:
     _re2 = False
 
 class _re(object):
     def _checkre2(self):
         global _re2
         try:
             # check if match works, see issue3964
             _re2 = bool(re2.match(r'\[([^\[]+)\]', '[ui]'))
         except ImportError:
             _re2 = False
 
     def compile(self, pat, flags=0):
         '''Compile a regular expression, using re2 if possible
 
         For best performance, use only re2-compatible regexp features. The
         only flags from the re module that are re2-compatible are
         IGNORECASE and MULTILINE.'''
         if _re2 is None:
             self._checkre2()
         if _re2 and (flags & ~(remod.IGNORECASE | remod.MULTILINE)) == 0:
             if flags & remod.IGNORECASE:
                 pat = '(?i)' + pat
             if flags & remod.MULTILINE:
                 pat = '(?m)' + pat
             try:
                 return re2.compile(pat)
             except re2.error:
                 pass
         return remod.compile(pat, flags)
 
     @propertycache
     def escape(self):
         '''Return the version of escape corresponding to self.compile.
 
         This is imperfect because whether re2 or re is used for a particular
         function depends on the flags, etc, but it's the best we can do.
         '''
         global _re2
         if _re2 is None:
             self._checkre2()
         if _re2:
             return re2.escape
         else:
             return remod.escape
 
 re = _re()
 
 _fspathcache = {}
 def fspath(name, root):
     '''Get name in the case stored in the filesystem
 
     The name should be relative to root, and be normcase-ed for efficiency.
 
     Note that this function is unnecessary, and should not be
     called, for case-sensitive filesystems (simply because it's expensive).
 
     The root should be normcase-ed, too.
     '''
     def _makefspathcacheentry(dir):
         return dict((normcase(n), n) for n in os.listdir(dir))
 
     seps = pycompat.ossep
     if pycompat.osaltsep:
         seps = seps + pycompat.osaltsep
     # Protect backslashes. This gets silly very quickly.
     seps.replace('\\','\\\\')
     pattern = remod.compile(r'([^%s]+)|([%s]+)' % (seps, seps))
     dir = os.path.normpath(root)
     result = []
     for part, sep in pattern.findall(name):
         if sep:
             result.append(sep)
             continue
 
         if dir not in _fspathcache:
             _fspathcache[dir] = _makefspathcacheentry(dir)
         contents = _fspathcache[dir]
 
         found = contents.get(part)
         if not found:
             # retry "once per directory" per "dirstate.walk" which
             # may take place for each patches of "hg qpush", for example
             _fspathcache[dir] = contents = _makefspathcacheentry(dir)
             found = contents.get(part)
 
         result.append(found or part)
         dir = os.path.join(dir, part)
 
     return ''.join(result)
 
 def checknlink(testfile):
     '''check whether hardlink count reporting works properly'''
 
     # testfile may be open, so we need a separate file for checking to
     # work around issue2543 (or testfile may get lost on Samba shares)
     f1 = testfile + ".hgtmp1"
     if os.path.lexists(f1):
         return False
     try:
         posixfile(f1, 'w').close()
     except IOError:
         try:
             os.unlink(f1)
         except OSError:
             pass
         return False
 
     f2 = testfile + ".hgtmp2"
     fd = None
     try:
         oslink(f1, f2)
         # nlinks() may behave differently for files on Windows shares if
         # the file is open.
         fd = posixfile(f2)
         return nlinks(f2) > 1
     except OSError:
         return False
     finally:
         if fd is not None:
             fd.close()
         for f in (f1, f2):
             try:
                 os.unlink(f)
             except OSError:
                 pass
 
 def endswithsep(path):
     '''Check path ends with os.sep or os.altsep.'''
     return (path.endswith(pycompat.ossep)
             or pycompat.osaltsep and path.endswith(pycompat.osaltsep))
 
 def splitpath(path):
     '''Split path by os.sep.
     Note that this function does not use os.altsep because this is
     an alternative of simple "xxx.split(os.sep)".
     It is recommended to use os.path.normpath() before using this
     function if need.'''
     return path.split(pycompat.ossep)
 
 def gui():
     '''Are we running in a GUI?'''
     if pycompat.sysplatform == 'darwin':
         if 'SSH_CONNECTION' in encoding.environ:
             # handle SSH access to a box where the user is logged in
             return False
         elif getattr(osutil, 'isgui', None):
             # check if a CoreGraphics session is available
             return osutil.isgui()
         else:
             # pure build; use a safe default
             return True
     else:
         return pycompat.osname == "nt" or encoding.environ.get("DISPLAY")
 
 def mktempcopy(name, emptyok=False, createmode=None):
     """Create a temporary file with the same contents from name
 
     The permission bits are copied from the original file.
 
     If the temporary file is going to be truncated immediately, you
     can use emptyok=True as an optimization.
 
     Returns the name of the temporary file.
     """
     d, fn = os.path.split(name)
     fd, temp = tempfile.mkstemp(prefix='.%s-' % fn, dir=d)
     os.close(fd)
     # Temporary files are created with mode 0600, which is usually not
     # what we want.  If the original file already exists, just copy
     # its mode.  Otherwise, manually obey umask.
     copymode(name, temp, createmode)
     if emptyok:
         return temp
     try:
         try:
             ifp = posixfile(name, "rb")
         except IOError as inst:
             if inst.errno == errno.ENOENT:
                 return temp
             if not getattr(inst, 'filename', None):
                 inst.filename = name
             raise
         ofp = posixfile(temp, "wb")
         for chunk in filechunkiter(ifp):
             ofp.write(chunk)
         ifp.close()
         ofp.close()
     except: # re-raises
         try: os.unlink(temp)
         except OSError: pass
         raise
     return temp
 
 class filestat(object):
     """help to exactly detect change of a file
 
     'stat' attribute is result of 'os.stat()' if specified 'path'
     exists. Otherwise, it is None. This can avoid preparative
     'exists()' examination on client side of this class.
     """
     def __init__(self, path):
         try:
             self.stat = os.stat(path)
         except OSError as err:
             if err.errno != errno.ENOENT:
                 raise
             self.stat = None
 
     __hash__ = object.__hash__
 
     def __eq__(self, old):
         try:
             # if ambiguity between stat of new and old file is
             # avoided, comparison of size, ctime and mtime is enough
             # to exactly detect change of a file regardless of platform
             return (self.stat.st_size == old.stat.st_size and
                     self.stat.st_ctime == old.stat.st_ctime and
                     self.stat.st_mtime == old.stat.st_mtime)
         except AttributeError:
             return False
 
     def isambig(self, old):
         """Examine whether new (= self) stat is ambiguous against old one
 
         "S[N]" below means stat of a file at N-th change:
 
         - S[n-1].ctime  < S[n].ctime: can detect change of a file
         - S[n-1].ctime == S[n].ctime
           - S[n-1].ctime  < S[n].mtime: means natural advancing (*1)
           - S[n-1].ctime == S[n].mtime: is ambiguous (*2)
           - S[n-1].ctime  > S[n].mtime: never occurs naturally (don't care)
         - S[n-1].ctime  > S[n].ctime: never occurs naturally (don't care)
 
         Case (*2) above means that a file was changed twice or more at
         same time in sec (= S[n-1].ctime), and comparison of timestamp
         is ambiguous.
 
         Base idea to avoid such ambiguity is "advance mtime 1 sec, if
         timestamp is ambiguous".
 
         But advancing mtime only in case (*2) doesn't work as
         expected, because naturally advanced S[n].mtime in case (*1)
         might be equal to manually advanced S[n-1 or earlier].mtime.
 
         Therefore, all "S[n-1].ctime == S[n].ctime" cases should be
         treated as ambiguous regardless of mtime, to avoid overlooking
         by confliction between such mtime.
 
         Advancing mtime "if isambig(oldstat)" ensures "S[n-1].mtime !=
         S[n].mtime", even if size of a file isn't changed.
         """
         try:
             return (self.stat.st_ctime == old.stat.st_ctime)
         except AttributeError:
             return False
 
     def avoidambig(self, path, old):
         """Change file stat of specified path to avoid ambiguity
 
         'old' should be previous filestat of 'path'.
 
         This skips avoiding ambiguity, if a process doesn't have
         appropriate privileges for 'path'.
         """
         advanced = (old.stat.st_mtime + 1) & 0x7fffffff
         try:
             os.utime(path, (advanced, advanced))
         except OSError as inst:
             if inst.errno == errno.EPERM:
                 # utime() on the file created by another user causes EPERM,
                 # if a process doesn't have appropriate privileges
                 return
             raise
 
     def __ne__(self, other):
         return not self == other
 
 class atomictempfile(object):
     '''writable file object that atomically updates a file
 
     All writes will go to a temporary copy of the original file. Call
     close() when you are done writing, and atomictempfile will rename
     the temporary copy to the original name, making the changes
     visible. If the object is destroyed without being closed, all your
     writes are discarded.
 
     checkambig argument of constructor is used with filestat, and is
     useful only if target file is guarded by any lock (e.g. repo.lock
     or repo.wlock).
     '''
     def __init__(self, name, mode='w+b', createmode=None, checkambig=False):
         self.__name = name      # permanent name
         self._tempname = mktempcopy(name, emptyok=('w' in mode),
                                     createmode=createmode)
         self._fp = posixfile(self._tempname, mode)
         self._checkambig = checkambig
 
         # delegated methods
         self.read = self._fp.read
         self.write = self._fp.write
         self.seek = self._fp.seek
         self.tell = self._fp.tell
         self.fileno = self._fp.fileno
 
     def close(self):
         if not self._fp.closed:
             self._fp.close()
             filename = localpath(self.__name)
             oldstat = self._checkambig and filestat(filename)
             if oldstat and oldstat.stat:
                 rename(self._tempname, filename)
                 newstat = filestat(filename)
                 if newstat.isambig(oldstat):
                     # stat of changed file is ambiguous to original one
                     advanced = (oldstat.stat.st_mtime + 1) & 0x7fffffff
                     os.utime(filename, (advanced, advanced))
             else:
                 rename(self._tempname, filename)
 
     def discard(self):
         if not self._fp.closed:
             try:
                 os.unlink(self._tempname)
             except OSError:
                 pass
             self._fp.close()
 
     def __del__(self):
         if safehasattr(self, '_fp'): # constructor actually did something
             self.discard()
 
     def __enter__(self):
         return self
 
     def __exit__(self, exctype, excvalue, traceback):
         if exctype is not None:
             self.discard()
         else:
             self.close()
 
 def makedirs(name, mode=None, notindexed=False):
     """recursive directory creation with parent mode inheritance
 
     Newly created directories are marked as "not to be indexed by
     the content indexing service", if ``notindexed`` is specified
     for "write" mode access.
     """
     try:
         makedir(name, notindexed)
     except OSError as err:
         if err.errno == errno.EEXIST:
             return
         if err.errno != errno.ENOENT or not name:
             raise
         parent = os.path.dirname(os.path.abspath(name))
         if parent == name:
             raise
         makedirs(parent, mode, notindexed)
         try:
             makedir(name, notindexed)
         except OSError as err:
             # Catch EEXIST to handle races
             if err.errno == errno.EEXIST:
                 return
             raise
     if mode is not None:
         os.chmod(name, mode)
 
 def readfile(path):
     with open(path, 'rb') as fp:
         return fp.read()
 
 def writefile(path, text):
     with open(path, 'wb') as fp:
         fp.write(text)
 
 def appendfile(path, text):
     with open(path, 'ab') as fp:
         fp.write(text)
 
 class chunkbuffer(object):
     """Allow arbitrary sized chunks of data to be efficiently read from an
     iterator over chunks of arbitrary size."""
 
     def __init__(self, in_iter):
         """in_iter is the iterator that's iterating over the input chunks.
         targetsize is how big a buffer to try to maintain."""
         def splitbig(chunks):
             for chunk in chunks:
                 if len(chunk) > 2**20:
                     pos = 0
                     while pos < len(chunk):
                         end = pos + 2 ** 18
                         yield chunk[pos:end]
                         pos = end
                 else:
                     yield chunk
         self.iter = splitbig(in_iter)
         self._queue = collections.deque()
         self._chunkoffset = 0
 
     def read(self, l=None):
         """Read L bytes of data from the iterator of chunks of data.
         Returns less than L bytes if the iterator runs dry.
 
         If size parameter is omitted, read everything"""
         if l is None:
             return ''.join(self.iter)
 
         left = l
         buf = []
         queue = self._queue
         while left > 0:
             # refill the queue
             if not queue:
                 target = 2**18
                 for chunk in self.iter:
                     queue.append(chunk)
                     target -= len(chunk)
                     if target <= 0:
                         break
                 if not queue:
                     break
 
             # The easy way to do this would be to queue.popleft(), modify the
             # chunk (if necessary), then queue.appendleft(). However, for cases
             # where we read partial chunk content, this incurs 2 dequeue
             # mutations and creates a new str for the remaining chunk in the
             # queue. Our code below avoids this overhead.
 
             chunk = queue[0]
             chunkl = len(chunk)
             offset = self._chunkoffset
 
             # Use full chunk.
             if offset == 0 and left >= chunkl:
                 left -= chunkl
                 queue.popleft()
                 buf.append(chunk)
                 # self._chunkoffset remains at 0.
                 continue
 
             chunkremaining = chunkl - offset
 
             # Use all of unconsumed part of chunk.
             if left >= chunkremaining:
                 left -= chunkremaining
                 queue.popleft()
                 # offset == 0 is enabled by block above, so this won't merely
                 # copy via ``chunk[0:]``.
                 buf.append(chunk[offset:])
                 self._chunkoffset = 0
 
             # Partial chunk needed.
             else:
                 buf.append(chunk[offset:offset + left])
                 self._chunkoffset += left
                 left -= chunkremaining
 
         return ''.join(buf)
 
 def filechunkiter(f, size=131072, limit=None):
     """Create a generator that produces the data in the file size
     (default 131072) bytes at a time, up to optional limit (default is
     to read all data).  Chunks may be less than size bytes if the
     chunk is the last chunk in the file, or the file is a socket or
     some other type of file that sometimes reads less data than is
     requested."""
     assert size >= 0
     assert limit is None or limit >= 0
     while True:
         if limit is None:
             nbytes = size
         else:
             nbytes = min(limit, size)
         s = nbytes and f.read(nbytes)
         if not s:
             break
         if limit:
             limit -= len(s)
         yield s
 
 def makedate(timestamp=None):
     '''Return a unix timestamp (or the current time) as a (unixtime,
     offset) tuple based off the local timezone.'''
     if timestamp is None:
         timestamp = time.time()
     if timestamp < 0:
         hint = _("check your clock")
         raise Abort(_("negative timestamp: %d") % timestamp, hint=hint)
     delta = (datetime.datetime.utcfromtimestamp(timestamp) -
              datetime.datetime.fromtimestamp(timestamp))
     tz = delta.days * 86400 + delta.seconds
     return timestamp, tz
 
 def datestr(date=None, format='%a %b %d %H:%M:%S %Y %1%2'):
     """represent a (unixtime, offset) tuple as a localized time.
     unixtime is seconds since the epoch, and offset is the time zone's
     number of seconds away from UTC.
 
     >>> datestr((0, 0))
     'Thu Jan 01 00:00:00 1970 +0000'
     >>> datestr((42, 0))
     'Thu Jan 01 00:00:42 1970 +0000'
     >>> datestr((-42, 0))
     'Wed Dec 31 23:59:18 1969 +0000'
     >>> datestr((0x7fffffff, 0))
     'Tue Jan 19 03:14:07 2038 +0000'
     >>> datestr((-0x80000000, 0))
     'Fri Dec 13 20:45:52 1901 +0000'
     """
     t, tz = date or makedate()
     if "%1" in format or "%2" in format or "%z" in format:
         sign = (tz > 0) and "-" or "+"
         minutes = abs(tz) // 60
         q, r = divmod(minutes, 60)
         format = format.replace("%z", "%1%2")
         format = format.replace("%1", "%c%02d" % (sign, q))
         format = format.replace("%2", "%02d" % r)
     d = t - tz
     if d > 0x7fffffff:
         d = 0x7fffffff
     elif d < -0x80000000:
         d = -0x80000000
     # Never use time.gmtime() and datetime.datetime.fromtimestamp()
     # because they use the gmtime() system call which is buggy on Windows
     # for negative values.
     t = datetime.datetime(1970, 1, 1) + datetime.timedelta(seconds=d)
     s = t.strftime(format)
     return s
 
 def shortdate(date=None):
     """turn (timestamp, tzoff) tuple into iso 8631 date."""
     return datestr(date, format='%Y-%m-%d')
 
 def parsetimezone(s):
     """find a trailing timezone, if any, in string, and return a
        (offset, remainder) pair"""
 
     if s.endswith("GMT") or s.endswith("UTC"):
         return 0, s[:-3].rstrip()
 
     # Unix-style timezones [+-]hhmm
     if len(s) >= 5 and s[-5] in "+-" and s[-4:].isdigit():
         sign = (s[-5] == "+") and 1 or -1
         hours = int(s[-4:-2])
         minutes = int(s[-2:])
         return -sign * (hours * 60 + minutes) * 60, s[:-5].rstrip()
 
     # ISO8601 trailing Z
     if s.endswith("Z") and s[-2:-1].isdigit():
         return 0, s[:-1]
 
     # ISO8601-style [+-]hh:mm
     if (len(s) >= 6 and s[-6] in "+-" and s[-3] == ":" and
         s[-5:-3].isdigit() and s[-2:].isdigit()):
         sign = (s[-6] == "+") and 1 or -1
         hours = int(s[-5:-3])
         minutes = int(s[-2:])
         return -sign * (hours * 60 + minutes) * 60, s[:-6]
 
     return None, s
 
 def strdate(string, format, defaults=[]):
     """parse a localized time string and return a (unixtime, offset) tuple.
     if the string cannot be parsed, ValueError is raised."""
     # NOTE: unixtime = localunixtime + offset
     offset, date = parsetimezone(string)
 
     # add missing elements from defaults
     usenow = False # default to using biased defaults
     for part in ("S", "M", "HI", "d", "mb", "yY"): # decreasing specificity
         found = [True for p in part if ("%"+p) in format]
         if not found:
             date += "@" + defaults[part][usenow]
             format += "@%" + part[0]
         else:
             # We've found a specific time element, less specific time
             # elements are relative to today
             usenow = True
 
     timetuple = time.strptime(date, format)
     localunixtime = int(calendar.timegm(timetuple))
     if offset is None:
         # local timezone
         unixtime = int(time.mktime(timetuple))
         offset = unixtime - localunixtime
     else:
         unixtime = localunixtime + offset
     return unixtime, offset
 
 def parsedate(date, formats=None, bias=None):
     """parse a localized date/time and return a (unixtime, offset) tuple.
 
     The date may be a "unixtime offset" string or in one of the specified
     formats. If the date already is a (unixtime, offset) tuple, it is returned.
 
     >>> parsedate(' today ') == parsedate(\
                                   datetime.date.today().strftime('%b %d'))
     True
     >>> parsedate( 'yesterday ') == parsedate((datetime.date.today() -\
                                                datetime.timedelta(days=1)\
                                               ).strftime('%b %d'))
     True
     >>> now, tz = makedate()
     >>> strnow, strtz = parsedate('now')
     >>> (strnow - now) < 1
     True
     >>> tz == strtz
     True
     """
     if bias is None:
         bias = {}
     if not date:
         return 0, 0
     if isinstance(date, tuple) and len(date) == 2:
         return date
     if not formats:
         formats = defaultdateformats
     date = date.strip()
 
     if date == 'now' or date == _('now'):
         return makedate()
     if date == 'today' or date == _('today'):
         date = datetime.date.today().strftime('%b %d')
     elif date == 'yesterday' or date == _('yesterday'):
         date = (datetime.date.today() -
                 datetime.timedelta(days=1)).strftime('%b %d')
 
     try:
         when, offset = map(int, date.split(' '))
     except ValueError:
         # fill out defaults
         now = makedate()
         defaults = {}
         for part in ("d", "mb", "yY", "HI", "M", "S"):
             # this piece is for rounding the specific end of unknowns
             b = bias.get(part)
             if b is None:
                 if part[0] in "HMS":
                     b = "00"
                 else:
                     b = "0"
 
             # this piece is for matching the generic end to today's date
             n = datestr(now, "%" + part[0])
 
             defaults[part] = (b, n)
 
         for format in formats:
             try:
                 when, offset = strdate(date, format, defaults)
             except (ValueError, OverflowError):
                 pass
             else:
                 break
         else:
             raise Abort(_('invalid date: %r') % date)
     # validate explicit (probably user-specified) date and
     # time zone offset. values must fit in signed 32 bits for
     # current 32-bit linux runtimes. timezones go from UTC-12
     # to UTC+14
     if when < -0x80000000 or when > 0x7fffffff:
         raise Abort(_('date exceeds 32 bits: %d') % when)
     if offset < -50400 or offset > 43200:
         raise Abort(_('impossible time zone offset: %d') % offset)
     return when, offset
 
 def matchdate(date):
     """Return a function that matches a given date match specifier
 
     Formats include:
 
     '{date}' match a given date to the accuracy provided
 
     '<{date}' on or before a given date
 
     '>{date}' on or after a given date
 
     >>> p1 = parsedate("10:29:59")
     >>> p2 = parsedate("10:30:00")
     >>> p3 = parsedate("10:30:59")
     >>> p4 = parsedate("10:31:00")
     >>> p5 = parsedate("Sep 15 10:30:00 1999")
     >>> f = matchdate("10:30")
     >>> f(p1[0])
     False
     >>> f(p2[0])
     True
     >>> f(p3[0])
     True
     >>> f(p4[0])
     False
     >>> f(p5[0])
     False
     """
 
     def lower(date):
         d = {'mb': "1", 'd': "1"}
         return parsedate(date, extendeddateformats, d)[0]
 
     def upper(date):
         d = {'mb': "12", 'HI': "23", 'M': "59", 'S': "59"}
         for days in ("31", "30", "29"):
             try:
                 d["d"] = days
                 return parsedate(date, extendeddateformats, d)[0]
             except Abort:
                 pass
         d["d"] = "28"
         return parsedate(date, extendeddateformats, d)[0]
 
     date = date.strip()
 
     if not date:
         raise Abort(_("dates cannot consist entirely of whitespace"))
     elif date[0] == "<":
         if not date[1:]:
             raise Abort(_("invalid day spec, use '<DATE'"))
         when = upper(date[1:])
         return lambda x: x <= when
     elif date[0] == ">":
         if not date[1:]:
             raise Abort(_("invalid day spec, use '>DATE'"))
         when = lower(date[1:])
         return lambda x: x >= when
     elif date[0] == "-":
         try:
             days = int(date[1:])
         except ValueError:
             raise Abort(_("invalid day spec: %s") % date[1:])
         if days < 0:
             raise Abort(_("%s must be nonnegative (see 'hg help dates')")
                 % date[1:])
         when = makedate()[0] - days * 3600 * 24
         return lambda x: x >= when
     elif " to " in date:
         a, b = date.split(" to ")
         start, stop = lower(a), upper(b)
         return lambda x: x >= start and x <= stop
     else:
         start, stop = lower(date), upper(date)
         return lambda x: x >= start and x <= stop
 
 def stringmatcher(pattern, casesensitive=True):
     """
     accepts a string, possibly starting with 're:' or 'literal:' prefix.
     returns the matcher name, pattern, and matcher function.
     missing or unknown prefixes are treated as literal matches.
 
     helper for tests:
     >>> def test(pattern, *tests):
     ...     kind, pattern, matcher = stringmatcher(pattern)
     ...     return (kind, pattern, [bool(matcher(t)) for t in tests])
     >>> def itest(pattern, *tests):
     ...     kind, pattern, matcher = stringmatcher(pattern, casesensitive=False)
     ...     return (kind, pattern, [bool(matcher(t)) for t in tests])
 
     exact matching (no prefix):
     >>> test('abcdefg', 'abc', 'def', 'abcdefg')
     ('literal', 'abcdefg', [False, False, True])
 
     regex matching ('re:' prefix)
     >>> test('re:a.+b', 'nomatch', 'fooadef', 'fooadefbar')
     ('re', 'a.+b', [False, False, True])
 
     force exact matches ('literal:' prefix)
     >>> test('literal:re:foobar', 'foobar', 're:foobar')
     ('literal', 're:foobar', [False, True])
 
     unknown prefixes are ignored and treated as literals
     >>> test('foo:bar', 'foo', 'bar', 'foo:bar')
     ('literal', 'foo:bar', [False, False, True])
 
     case insensitive regex matches
     >>> itest('re:A.+b', 'nomatch', 'fooadef', 'fooadefBar')
     ('re', 'A.+b', [False, False, True])
 
     case insensitive literal matches
     >>> itest('ABCDEFG', 'abc', 'def', 'abcdefg')
     ('literal', 'ABCDEFG', [False, False, True])
     """
     if pattern.startswith('re:'):
         pattern = pattern[3:]
         try:
             flags = 0
             if not casesensitive:
                 flags = remod.I
             regex = remod.compile(pattern, flags)
         except remod.error as e:
             raise error.ParseError(_('invalid regular expression: %s')
                                    % e)
         return 're', pattern, regex.search
     elif pattern.startswith('literal:'):
         pattern = pattern[8:]
 
     match = pattern.__eq__
 
     if not casesensitive:
         ipat = encoding.lower(pattern)
         match = lambda s: ipat == encoding.lower(s)
     return 'literal', pattern, match
 
 def shortuser(user):
     """Return a short representation of a user name or email address."""
     f = user.find('@')
     if f >= 0:
         user = user[:f]
     f = user.find('<')
     if f >= 0:
         user = user[f + 1:]
     f = user.find(' ')
     if f >= 0:
         user = user[:f]
     f = user.find('.')
     if f >= 0:
         user = user[:f]
     return user
 
 def emailuser(user):
     """Return the user portion of an email address."""
     f = user.find('@')
     if f >= 0:
         user = user[:f]
     f = user.find('<')
     if f >= 0:
         user = user[f + 1:]
     return user
 
 def email(author):
     '''get email of author.'''
     r = author.find('>')
     if r == -1:
         r = None
     return author[author.find('<') + 1:r]
 
 def ellipsis(text, maxlength=400):
     """Trim string to at most maxlength (default: 400) columns in display."""
     return encoding.trim(text, maxlength, ellipsis='...')
 
 def unitcountfn(*unittable):
     '''return a function that renders a readable count of some quantity'''
 
     def go(count):
         for multiplier, divisor, format in unittable:
             if count >= divisor * multiplier:
                 return format % (count / float(divisor))
         return unittable[-1][2] % count
 
     return go
 
 bytecount = unitcountfn(
     (100, 1 << 30, _('%.0f GB')),
     (10, 1 << 30, _('%.1f GB')),
     (1, 1 << 30, _('%.2f GB')),
     (100, 1 << 20, _('%.0f MB')),
     (10, 1 << 20, _('%.1f MB')),
     (1, 1 << 20, _('%.2f MB')),
     (100, 1 << 10, _('%.0f KB')),
     (10, 1 << 10, _('%.1f KB')),
     (1, 1 << 10, _('%.2f KB')),
     (1, 1, _('%.0f bytes')),
     )
 
 def uirepr(s):
     # Avoid double backslash in Windows path repr()
     return repr(s).replace('\\\\', '\\')
 
 # delay import of textwrap
 def MBTextWrapper(**kwargs):
     class tw(textwrap.TextWrapper):
         """
         Extend TextWrapper for width-awareness.
 
         Neither number of 'bytes' in any encoding nor 'characters' is
         appropriate to calculate terminal columns for specified string.
 
         Original TextWrapper implementation uses built-in 'len()' directly,
         so overriding is needed to use width information of each characters.
 
         In addition, characters classified into 'ambiguous' width are
         treated as wide in East Asian area, but as narrow in other.
 
         This requires use decision to determine width of such characters.
         """
         def _cutdown(self, ucstr, space_left):
             l = 0
             colwidth = encoding.ucolwidth
             for i in xrange(len(ucstr)):
                 l += colwidth(ucstr[i])
                 if space_left < l:
                     return (ucstr[:i], ucstr[i:])
             return ucstr, ''
 
         # overriding of base class
         def _handle_long_word(self, reversed_chunks, cur_line, cur_len, width):
             space_left = max(width - cur_len, 1)
 
             if self.break_long_words:
                 cut, res = self._cutdown(reversed_chunks[-1], space_left)
                 cur_line.append(cut)
                 reversed_chunks[-1] = res
             elif not cur_line:
                 cur_line.append(reversed_chunks.pop())
 
         # this overriding code is imported from TextWrapper of Python 2.6
         # to calculate columns of string by 'encoding.ucolwidth()'
         def _wrap_chunks(self, chunks):
             colwidth = encoding.ucolwidth
 
             lines = []
             if self.width <= 0:
                 raise ValueError("invalid width %r (must be > 0)" % self.width)
 
             # Arrange in reverse order so items can be efficiently popped
             # from a stack of chucks.
             chunks.reverse()
 
             while chunks:
 
                 # Start the list of chunks that will make up the current line.
                 # cur_len is just the length of all the chunks in cur_line.
                 cur_line = []
                 cur_len = 0
 
                 # Figure out which static string will prefix this line.
                 if lines:
                     indent = self.subsequent_indent
                 else:
                     indent = self.initial_indent
 
                 # Maximum width for this line.
                 width = self.width - len(indent)
 
                 # First chunk on line is whitespace -- drop it, unless this
                 # is the very beginning of the text (i.e. no lines started yet).
                 if self.drop_whitespace and chunks[-1].strip() == '' and lines:
                     del chunks[-1]
 
                 while chunks:
                     l = colwidth(chunks[-1])
 
                     # Can at least squeeze this chunk onto the current line.
                     if cur_len + l <= width:
                         cur_line.append(chunks.pop())
                         cur_len += l
 
                     # Nope, this line is full.
                     else:
                         break
 
                 # The current line is full, and the next chunk is too big to
                 # fit on *any* line (not just this one).
                 if chunks and colwidth(chunks[-1]) > width:
                     self._handle_long_word(chunks, cur_line, cur_len, width)
 
                 # If the last chunk on this line is all whitespace, drop it.
                 if (self.drop_whitespace and
                     cur_line and cur_line[-1].strip() == ''):
                     del cur_line[-1]
 
                 # Convert current line back to a string and store it in list
                 # of all lines (return value).
                 if cur_line:
                     lines.append(indent + ''.join(cur_line))
 
             return lines
 
     global MBTextWrapper
     MBTextWrapper = tw
     return tw(**kwargs)
 
 def wrap(line, width, initindent='', hangindent=''):
     maxindent = max(len(hangindent), len(initindent))
     if width <= maxindent:
         # adjust for weird terminal size
         width = max(78, maxindent + 1)
     line = line.decode(encoding.encoding, encoding.encodingmode)
     initindent = initindent.decode(encoding.encoding, encoding.encodingmode)
     hangindent = hangindent.decode(encoding.encoding, encoding.encodingmode)
     wrapper = MBTextWrapper(width=width,
                             initial_indent=initindent,
                             subsequent_indent=hangindent)
     return wrapper.fill(line).encode(encoding.encoding)
 
 if (pyplatform.python_implementation() == 'CPython' and
     sys.version_info < (3, 0)):
     # There is an issue in CPython that some IO methods do not handle EINTR
     # correctly. The following table shows what CPython version (and functions)
     # are affected (buggy: has the EINTR bug, okay: otherwise):
     #
     #                | < 2.7.4 | 2.7.4 to 2.7.12 | >= 3.0
     #   --------------------------------------------------
     #    fp.__iter__ | buggy   | buggy           | okay
     #    fp.read*    | buggy   | okay [1]        | okay
     #
     # [1]: fixed by changeset 67dc99a989cd in the cpython hg repo.
     #
     # Here we workaround the EINTR issue for fileobj.__iter__. Other methods
     # like "read*" are ignored for now, as Python < 2.7.4 is a minority.
     #
     # Although we can workaround the EINTR issue for fp.__iter__, it is slower:
     # "for x in fp" is 4x faster than "for x in iter(fp.readline, '')" in
     # CPython 2, because CPython 2 maintains an internal readahead buffer for
     # fp.__iter__ but not other fp.read* methods.
     #
     # On modern systems like Linux, the "read" syscall cannot be interrupted
     # when reading "fast" files like on-disk files. So the EINTR issue only
     # affects things like pipes, sockets, ttys etc. We treat "normal" (S_ISREG)
     # files approximately as "fast" files and use the fast (unsafe) code path,
     # to minimize the performance impact.
     if sys.version_info >= (2, 7, 4):
         # fp.readline deals with EINTR correctly, use it as a workaround.
         def _safeiterfile(fp):
             return iter(fp.readline, '')
     else:
         # fp.read* are broken too, manually deal with EINTR in a stupid way.
         # note: this may block longer than necessary because of bufsize.
         def _safeiterfile(fp, bufsize=4096):
             fd = fp.fileno()
             line = ''
             while True:
                 try:
                     buf = os.read(fd, bufsize)
                 except OSError as ex:
                     # os.read only raises EINTR before any data is read
                     if ex.errno == errno.EINTR:
                         continue
                     else:
                         raise
                 line += buf
                 if '\n' in buf:
                     splitted = line.splitlines(True)
                     line = ''
                     for l in splitted:
                         if l[-1] == '\n':
                             yield l
                         else:
                             line = l
                 if not buf:
                     break
             if line:
                 yield line
 
     def iterfile(fp):
         fastpath = True
         if type(fp) is file:
             fastpath = stat.S_ISREG(os.fstat(fp.fileno()).st_mode)
         if fastpath:
             return fp
         else:
             return _safeiterfile(fp)
 else:
     # PyPy and CPython 3 do not have the EINTR issue thus no workaround needed.
     def iterfile(fp):
         return fp
 
 def iterlines(iterator):
     for chunk in iterator:
         for line in chunk.splitlines():
             yield line
 
 def expandpath(path):
     return os.path.expanduser(os.path.expandvars(path))
 
 def hgcmd():
     """Return the command used to execute current hg
 
     This is different from hgexecutable() because on Windows we want
     to avoid things opening new shell windows like batch files, so we
     get either the python call or current executable.
     """
     if mainfrozen():
         if getattr(sys, 'frozen', None) == 'macosx_app':
             # Env variable set by py2app
             return [encoding.environ['EXECUTABLEPATH']]
         else:
             return [pycompat.sysexecutable]
     return gethgcmd()
 
 def rundetached(args, condfn):
     """Execute the argument list in a detached process.
 
     condfn is a callable which is called repeatedly and should return
     True once the child process is known to have started successfully.
     At this point, the child process PID is returned. If the child
     process fails to start or finishes before condfn() evaluates to
     True, return -1.
     """
     # Windows case is easier because the child process is either
     # successfully starting and validating the condition or exiting
     # on failure. We just poll on its PID. On Unix, if the child
     # process fails to start, it will be left in a zombie state until
     # the parent wait on it, which we cannot do since we expect a long
     # running process on success. Instead we listen for SIGCHLD telling
     # us our child process terminated.
     terminated = set()
     def handler(signum, frame):
         terminated.add(os.wait())
     prevhandler = None
     SIGCHLD = getattr(signal, 'SIGCHLD', None)
     if SIGCHLD is not None:
         prevhandler = signal.signal(SIGCHLD, handler)
     try:
         pid = spawndetached(args)
         while not condfn():
             if ((pid in terminated or not testpid(pid))
                 and not condfn()):
                 return -1
             time.sleep(0.1)
         return pid
     finally:
         if prevhandler is not None:
             signal.signal(signal.SIGCHLD, prevhandler)
 
 def interpolate(prefix, mapping, s, fn=None, escape_prefix=False):
     """Return the result of interpolating items in the mapping into string s.
 
     prefix is a single character string, or a two character string with
     a backslash as the first character if the prefix needs to be escaped in
     a regular expression.
 
     fn is an optional function that will be applied to the replacement text
     just before replacement.
 
     escape_prefix is an optional flag that allows using doubled prefix for
     its escaping.
     """
     fn = fn or (lambda s: s)
     patterns = '|'.join(mapping.keys())
     if escape_prefix:
         patterns += '|' + prefix
         if len(prefix) > 1:
             prefix_char = prefix[1:]
         else:
             prefix_char = prefix
         mapping[prefix_char] = prefix_char
     r = remod.compile(r'%s(%s)' % (prefix, patterns))
     return r.sub(lambda x: fn(mapping[x.group()[1:]]), s)
 
 def getport(port):
     """Return the port for a given network service.
 
     If port is an integer, it's returned as is. If it's a string, it's
     looked up using socket.getservbyname(). If there's no matching
     service, error.Abort is raised.
     """
     try:
         return int(port)
     except ValueError:
         pass
 
     try:
         return socket.getservbyname(port)
     except socket.error:
         raise Abort(_("no port number associated with service '%s'") % port)
 
 _booleans = {'1': True, 'yes': True, 'true': True, 'on': True, 'always': True,
              '0': False, 'no': False, 'false': False, 'off': False,
              'never': False}
 
 def parsebool(s):
     """Parse s into a boolean.
 
     If s is not a valid boolean, returns None.
     """
     return _booleans.get(s.lower(), None)
 
 _hextochr = dict((a + b, chr(int(a + b, 16)))
                  for a in string.hexdigits for b in string.hexdigits)
 
 class url(object):
     r"""Reliable URL parser.
 
     This parses URLs and provides attributes for the following
     components:
 
     <scheme>://<user>:<passwd>@<host>:<port>/<path>?<query>#<fragment>
 
     Missing components are set to None. The only exception is
     fragment, which is set to '' if present but empty.
 
     If parsefragment is False, fragment is included in query. If
     parsequery is False, query is included in path. If both are
     False, both fragment and query are included in path.
 
     See http://www.ietf.org/rfc/rfc2396.txt for more information.
 
     Note that for backward compatibility reasons, bundle URLs do not
     take host names. That means 'bundle://../' has a path of '../'.
 
     Examples:
 
     >>> url('http://www.ietf.org/rfc/rfc2396.txt')
     <url scheme: 'http', host: 'www.ietf.org', path: 'rfc/rfc2396.txt'>
     >>> url('ssh://[::1]:2200//home/joe/repo')
     <url scheme: 'ssh', host: '[::1]', port: '2200', path: '/home/joe/repo'>
     >>> url('file:///home/joe/repo')
     <url scheme: 'file', path: '/home/joe/repo'>
     >>> url('file:///c:/temp/foo/')
     <url scheme: 'file', path: 'c:/temp/foo/'>
     >>> url('bundle:foo')
     <url scheme: 'bundle', path: 'foo'>
     >>> url('bundle://../foo')
     <url scheme: 'bundle', path: '../foo'>
     >>> url(r'c:\foo\bar')
     <url path: 'c:\\foo\\bar'>
     >>> url(r'\\blah\blah\blah')
     <url path: '\\\\blah\\blah\\blah'>
     >>> url(r'\\blah\blah\blah#baz')
     <url path: '\\\\blah\\blah\\blah', fragment: 'baz'>
     >>> url(r'file:///C:\users\me')
     <url scheme: 'file', path: 'C:\\users\\me'>
 
     Authentication credentials:
 
     >>> url('ssh://joe:xyz@x/repo')
     <url scheme: 'ssh', user: 'joe', passwd: 'xyz', host: 'x', path: 'repo'>
     >>> url('ssh://joe@x/repo')
     <url scheme: 'ssh', user: 'joe', host: 'x', path: 'repo'>
 
     Query strings and fragments:
 
     >>> url('http://host/a?b#c')
     <url scheme: 'http', host: 'host', path: 'a', query: 'b', fragment: 'c'>
     >>> url('http://host/a?b#c', parsequery=False, parsefragment=False)
     <url scheme: 'http', host: 'host', path: 'a?b#c'>
 
     Empty path:
 
     >>> url('')
     <url path: ''>
     >>> url('#a')
     <url path: '', fragment: 'a'>
     >>> url('http://host/')
     <url scheme: 'http', host: 'host', path: ''>
     >>> url('http://host/#a')
     <url scheme: 'http', host: 'host', path: '', fragment: 'a'>
 
     Only scheme:
 
     >>> url('http:')
     <url scheme: 'http'>
     """
 
     _safechars = "!~*'()+"
     _safepchars = "/!~*'()+:\\"
     _matchscheme = remod.compile('^[a-zA-Z0-9+.\\-]+:').match
 
     def __init__(self, path, parsequery=True, parsefragment=True):
         # We slowly chomp away at path until we have only the path left
         self.scheme = self.user = self.passwd = self.host = None
         self.port = self.path = self.query = self.fragment = None
         self._localpath = True
         self._hostport = ''
         self._origpath = path
 
         if parsefragment and '#' in path:
             path, self.fragment = path.split('#', 1)
 
         # special case for Windows drive letters and UNC paths
         if hasdriveletter(path) or path.startswith('\\\\'):
             self.path = path
             return
 
         # For compatibility reasons, we can't handle bundle paths as
         # normal URLS
         if path.startswith('bundle:'):
             self.scheme = 'bundle'
             path = path[7:]
             if path.startswith('//'):
                 path = path[2:]
             self.path = path
             return
 
         if self._matchscheme(path):
             parts = path.split(':', 1)
             if parts[0]:
                 self.scheme, path = parts
                 self._localpath = False
 
         if not path:
             path = None
             if self._localpath:
                 self.path = ''
                 return
         else:
             if self._localpath:
                 self.path = path
                 return
 
             if parsequery and '?' in path:
                 path, self.query = path.split('?', 1)
                 if not path:
                     path = None
                 if not self.query:
                     self.query = None
 
             # // is required to specify a host/authority
             if path and path.startswith('//'):
                 parts = path[2:].split('/', 1)
                 if len(parts) > 1:
                     self.host, path = parts
                 else:
                     self.host = parts[0]
                     path = None
                 if not self.host:
                     self.host = None
                     # path of file:///d is /d
                     # path of file:///d:/ is d:/, not /d:/
                     if path and not hasdriveletter(path):
                         path = '/' + path
 
             if self.host and '@' in self.host:
                 self.user, self.host = self.host.rsplit('@', 1)
                 if ':' in self.user:
                     self.user, self.passwd = self.user.split(':', 1)
                 if not self.host:
                     self.host = None
 
             # Don't split on colons in IPv6 addresses without ports
             if (self.host and ':' in self.host and
                 not (self.host.startswith('[') and self.host.endswith(']'))):
                 self._hostport = self.host
                 self.host, self.port = self.host.rsplit(':', 1)
                 if not self.host:
                     self.host = None
 
             if (self.host and self.scheme == 'file' and
                 self.host not in ('localhost', '127.0.0.1', '[::1]')):
                 raise Abort(_('file:// URLs can only refer to localhost'))
 
         self.path = path
 
         # leave the query string escaped
         for a in ('user', 'passwd', 'host', 'port',
                   'path', 'fragment'):
             v = getattr(self, a)
             if v is not None:
                 setattr(self, a, pycompat.urlunquote(v))
 
     def __repr__(self):
         attrs = []
         for a in ('scheme', 'user', 'passwd', 'host', 'port', 'path',
                   'query', 'fragment'):
             v = getattr(self, a)
             if v is not None:
                 attrs.append('%s: %r' % (a, v))
         return '<url %s>' % ', '.join(attrs)
 
     def __str__(self):
         r"""Join the URL's components back into a URL string.
 
         Examples:
 
         >>> str(url('http://user:pw@host:80/c:/bob?fo:oo#ba:ar'))
         'http://user:pw@host:80/c:/bob?fo:oo#ba:ar'
         >>> str(url('http://user:pw@host:80/?foo=bar&baz=42'))
         'http://user:pw@host:80/?foo=bar&baz=42'
         >>> str(url('http://user:pw@host:80/?foo=bar%3dbaz'))
         'http://user:pw@host:80/?foo=bar%3dbaz'
         >>> str(url('ssh://user:pw@[::1]:2200//home/joe#'))
         'ssh://user:pw@[::1]:2200//home/joe#'
         >>> str(url('http://localhost:80//'))
         'http://localhost:80//'
         >>> str(url('http://localhost:80/'))
         'http://localhost:80/'
         >>> str(url('http://localhost:80'))
         'http://localhost:80/'
         >>> str(url('bundle:foo'))
         'bundle:foo'
         >>> str(url('bundle://../foo'))
         'bundle:../foo'
         >>> str(url('path'))
         'path'
         >>> str(url('file:///tmp/foo/bar'))
         'file:///tmp/foo/bar'
         >>> str(url('file:///c:/tmp/foo/bar'))
         'file:///c:/tmp/foo/bar'
         >>> print url(r'bundle:foo\bar')
         bundle:foo\bar
         >>> print url(r'file:///D:\data\hg')
         file:///D:\data\hg
         """
         if self._localpath:
             s = self.path
             if self.scheme == 'bundle':
                 s = 'bundle:' + s
             if self.fragment:
                 s += '#' + self.fragment
             return s
 
         s = self.scheme + ':'
         if self.user or self.passwd or self.host:
             s += '//'
         elif self.scheme and (not self.path or self.path.startswith('/')
                               or hasdriveletter(self.path)):
             s += '//'
             if hasdriveletter(self.path):
                 s += '/'
         if self.user:
             s += urlreq.quote(self.user, safe=self._safechars)
         if self.passwd:
             s += ':' + urlreq.quote(self.passwd, safe=self._safechars)
         if self.user or self.passwd:
             s += '@'
         if self.host:
             if not (self.host.startswith('[') and self.host.endswith(']')):
                 s += urlreq.quote(self.host)
             else:
                 s += self.host
         if self.port:
             s += ':' + urlreq.quote(self.port)
         if self.host:
             s += '/'
         if self.path:
             # TODO: similar to the query string, we should not unescape the
             # path when we store it, the path might contain '%2f' = '/',
             # which we should *not* escape.
             s += urlreq.quote(self.path, safe=self._safepchars)
         if self.query:
             # we store the query in escaped form.
             s += '?' + self.query
         if self.fragment is not None:
             s += '#' + urlreq.quote(self.fragment, safe=self._safepchars)
         return s
 
     def authinfo(self):
         user, passwd = self.user, self.passwd
         try:
             self.user, self.passwd = None, None
             s = str(self)
         finally:
             self.user, self.passwd = user, passwd
         if not self.user:
             return (s, None)
         # authinfo[1] is passed to urllib2 password manager, and its
         # URIs must not contain credentials. The host is passed in the
         # URIs list because Python < 2.4.3 uses only that to search for
         # a password.
         return (s, (None, (s, self.host),
                     self.user, self.passwd or ''))
 
     def isabs(self):
         if self.scheme and self.scheme != 'file':
             return True # remote URL
         if hasdriveletter(self.path):
             return True # absolute for our purposes - can't be joined()
         if self.path.startswith(r'\\'):
             return True # Windows UNC path
         if self.path.startswith('/'):
             return True # POSIX-style
         return False
 
     def localpath(self):
         if self.scheme == 'file' or self.scheme == 'bundle':
             path = self.path or '/'
             # For Windows, we need to promote hosts containing drive
             # letters to paths with drive letters.
             if hasdriveletter(self._hostport):
                 path = self._hostport + '/' + self.path
             elif (self.host is not None and self.path
                   and not hasdriveletter(path)):
                 path = '/' + path
             return path
         return self._origpath
 
     def islocal(self):
         '''whether localpath will return something that posixfile can open'''
         return (not self.scheme or self.scheme == 'file'
                 or self.scheme == 'bundle')
 
 def hasscheme(path):
     return bool(url(path).scheme)
 
 def hasdriveletter(path):
     return path and path[1:2] == ':' and path[0:1].isalpha()
 
 def urllocalpath(path):
     return url(path, parsequery=False, parsefragment=False).localpath()
 
 def hidepassword(u):
     '''hide user credential in a url string'''
     u = url(u)
     if u.passwd:
         u.passwd = '***'
     return str(u)
 
 def removeauth(u):
     '''remove all authentication information from a url string'''
     u = url(u)
     u.user = u.passwd = None
     return str(u)
 
 timecount = unitcountfn(
     (1, 1e3, _('%.0f s')),
     (100, 1, _('%.1f s')),
     (10, 1, _('%.2f s')),
     (1, 1, _('%.3f s')),
     (100, 0.001, _('%.1f ms')),
     (10, 0.001, _('%.2f ms')),
     (1, 0.001, _('%.3f ms')),
     (100, 0.000001, _('%.1f us')),
     (10, 0.000001, _('%.2f us')),
     (1, 0.000001, _('%.3f us')),
     (100, 0.000000001, _('%.1f ns')),
     (10, 0.000000001, _('%.2f ns')),
     (1, 0.000000001, _('%.3f ns')),
     )
 
 _timenesting = [0]
 
 def timed(func):
     '''Report the execution time of a function call to stderr.
 
     During development, use as a decorator when you need to measure
     the cost of a function, e.g. as follows:
 
     @util.timed
     def foo(a, b, c):
         pass
     '''
 
     def wrapper(*args, **kwargs):
-        start = time.time()
+        start = timer()
         indent = 2
         _timenesting[0] += indent
         try:
             return func(*args, **kwargs)
         finally:
-            elapsed = time.time() - start
+            elapsed = timer() - start
             _timenesting[0] -= indent
             stderr.write('%s%s: %s\n' %
                          (' ' * _timenesting[0], func.__name__,
                           timecount(elapsed)))
     return wrapper
 
 _sizeunits = (('m', 2**20), ('k', 2**10), ('g', 2**30),
               ('kb', 2**10), ('mb', 2**20), ('gb', 2**30), ('b', 1))
 
 def sizetoint(s):
     '''Convert a space specifier to a byte count.
 
     >>> sizetoint('30')
     30
     >>> sizetoint('2.2kb')
     2252
     >>> sizetoint('6M')
     6291456
     '''
     t = s.strip().lower()
     try:
         for k, u in _sizeunits:
             if t.endswith(k):
                 return int(float(t[:-len(k)]) * u)
         return int(t)
     except ValueError:
         raise error.ParseError(_("couldn't parse size: %s") % s)
 
 class hooks(object):
     '''A collection of hook functions that can be used to extend a
     function's behavior. Hooks are called in lexicographic order,
     based on the names of their sources.'''
 
     def __init__(self):
         self._hooks = []
 
     def add(self, source, hook):
         self._hooks.append((source, hook))
 
     def __call__(self, *args):
         self._hooks.sort(key=lambda x: x[0])
         results = []
         for source, hook in self._hooks:
             results.append(hook(*args))
         return results
 
 def getstackframes(skip=0, line=' %-*s in %s\n', fileline='%s:%s'):
     '''Yields lines for a nicely formatted stacktrace.
     Skips the 'skip' last entries.
     Each file+linenumber is formatted according to fileline.
     Each line is formatted according to line.
     If line is None, it yields:
       length of longest filepath+line number,
       filepath+linenumber,
       function
 
     Not be used in production code but very convenient while developing.
     '''
     entries = [(fileline % (fn, ln), func)
         for fn, ln, func, _text in traceback.extract_stack()[:-skip - 1]]
     if entries:
         fnmax = max(len(entry[0]) for entry in entries)
         for fnln, func in entries:
             if line is None:
                 yield (fnmax, fnln, func)
             else:
                 yield line % (fnmax, fnln, func)
 
 def debugstacktrace(msg='stacktrace', skip=0, f=stderr, otherf=stdout):
     '''Writes a message to f (stderr) with a nicely formatted stacktrace.
     Skips the 'skip' last entries. By default it will flush stdout first.
     It can be used everywhere and intentionally does not require an ui object.
     Not be used in production code but very convenient while developing.
     '''
     if otherf:
         otherf.flush()
     f.write('%s at:\n' % msg)
     for line in getstackframes(skip + 1):
         f.write(line)
     f.flush()
 
 class dirs(object):
     '''a multiset of directory names from a dirstate or manifest'''
 
     def __init__(self, map, skip=None):
         self._dirs = {}
         addpath = self.addpath
         if safehasattr(map, 'iteritems') and skip is not None:
             for f, s in map.iteritems():
                 if s[0] != skip:
                     addpath(f)
         else:
             for f in map:
                 addpath(f)
 
     def addpath(self, path):
         dirs = self._dirs
         for base in finddirs(path):
             if base in dirs:
                 dirs[base] += 1
                 return
             dirs[base] = 1
 
     def delpath(self, path):
         dirs = self._dirs
         for base in finddirs(path):
             if dirs[base] > 1:
                 dirs[base] -= 1
                 return
             del dirs[base]
 
     def __iter__(self):
         return self._dirs.iterkeys()
 
     def __contains__(self, d):
         return d in self._dirs
 
 if safehasattr(parsers, 'dirs'):
     dirs = parsers.dirs
 
 def finddirs(path):
     pos = path.rfind('/')
     while pos != -1:
         yield path[:pos]
         pos = path.rfind('/', 0, pos)
 
 class ctxmanager(object):
     '''A context manager for use in 'with' blocks to allow multiple
     contexts to be entered at once.  This is both safer and more
     flexible than contextlib.nested.
 
     Once Mercurial supports Python 2.7+, this will become mostly
     unnecessary.
     '''
 
     def __init__(self, *args):
         '''Accepts a list of no-argument functions that return context
         managers.  These will be invoked at __call__ time.'''
         self._pending = args
         self._atexit = []
 
     def __enter__(self):
         return self
 
     def enter(self):
         '''Create and enter context managers in the order in which they were
         passed to the constructor.'''
         values = []
         for func in self._pending:
             obj = func()
             values.append(obj.__enter__())
             self._atexit.append(obj.__exit__)
         del self._pending
         return values
 
     def atexit(self, func, *args, **kwargs):
         '''Add a function to call when this context manager exits.  The
         ordering of multiple atexit calls is unspecified, save that
         they will happen before any __exit__ functions.'''
         def wrapper(exc_type, exc_val, exc_tb):
             func(*args, **kwargs)
         self._atexit.append(wrapper)
         return func
 
     def __exit__(self, exc_type, exc_val, exc_tb):
         '''Context managers are exited in the reverse order from which
         they were created.'''
         received = exc_type is not None
         suppressed = False
         pending = None
         self._atexit.reverse()
         for exitfunc in self._atexit:
             try:
                 if exitfunc(exc_type, exc_val, exc_tb):
                     suppressed = True
                     exc_type = None
                     exc_val = None
                     exc_tb = None
             except BaseException:
                 pending = sys.exc_info()
                 exc_type, exc_val, exc_tb = pending = sys.exc_info()
         del self._atexit
         if pending:
             raise exc_val
         return received and suppressed
 
 # compression code
 
 SERVERROLE = 'server'
 CLIENTROLE = 'client'
 
 compewireprotosupport = collections.namedtuple(u'compenginewireprotosupport',
                                                (u'name', u'serverpriority',
                                                 u'clientpriority'))
 
 class compressormanager(object):
     """Holds registrations of various compression engines.
 
     This class essentially abstracts the differences between compression
     engines to allow new compression formats to be added easily, possibly from
     extensions.
 
     Compressors are registered against the global instance by calling its
     ``register()`` method.
     """
     def __init__(self):
         self._engines = {}
         # Bundle spec human name to engine name.
         self._bundlenames = {}
         # Internal bundle identifier to engine name.
         self._bundletypes = {}
         # Revlog header to engine name.
         self._revlogheaders = {}
         # Wire proto identifier to engine name.
         self._wiretypes = {}
 
     def __getitem__(self, key):
         return self._engines[key]
 
     def __contains__(self, key):
         return key in self._engines
 
     def __iter__(self):
         return iter(self._engines.keys())
 
     def register(self, engine):
         """Register a compression engine with the manager.
 
         The argument must be a ``compressionengine`` instance.
         """
         if not isinstance(engine, compressionengine):
             raise ValueError(_('argument must be a compressionengine'))
 
         name = engine.name()
 
         if name in self._engines:
             raise error.Abort(_('compression engine %s already registered') %
                               name)
 
         bundleinfo = engine.bundletype()
         if bundleinfo:
             bundlename, bundletype = bundleinfo
 
             if bundlename in self._bundlenames:
                 raise error.Abort(_('bundle name %s already registered') %
                                   bundlename)
             if bundletype in self._bundletypes:
                 raise error.Abort(_('bundle type %s already registered by %s') %
                                   (bundletype, self._bundletypes[bundletype]))
 
             # No external facing name declared.
             if bundlename:
                 self._bundlenames[bundlename] = name
 
             self._bundletypes[bundletype] = name
 
         wiresupport = engine.wireprotosupport()
         if wiresupport:
             wiretype = wiresupport.name
             if wiretype in self._wiretypes:
                 raise error.Abort(_('wire protocol compression %s already '
                                     'registered by %s') %
                                   (wiretype, self._wiretypes[wiretype]))
 
             self._wiretypes[wiretype] = name
 
         revlogheader = engine.revlogheader()
         if revlogheader and revlogheader in self._revlogheaders:
             raise error.Abort(_('revlog header %s already registered by %s') %
                               (revlogheader, self._revlogheaders[revlogheader]))
 
         if revlogheader:
             self._revlogheaders[revlogheader] = name
 
         self._engines[name] = engine
 
     @property
     def supportedbundlenames(self):
         return set(self._bundlenames.keys())
 
     @property
     def supportedbundletypes(self):
         return set(self._bundletypes.keys())
 
     def forbundlename(self, bundlename):
         """Obtain a compression engine registered to a bundle name.
 
         Will raise KeyError if the bundle type isn't registered.
 
         Will abort if the engine is known but not available.
         """
         engine = self._engines[self._bundlenames[bundlename]]
         if not engine.available():
             raise error.Abort(_('compression engine %s could not be loaded') %
                               engine.name())
         return engine
 
     def forbundletype(self, bundletype):
         """Obtain a compression engine registered to a bundle type.
 
         Will raise KeyError if the bundle type isn't registered.
 
         Will abort if the engine is known but not available.
         """
         engine = self._engines[self._bundletypes[bundletype]]
         if not engine.available():
             raise error.Abort(_('compression engine %s could not be loaded') %
                               engine.name())
         return engine
 
     def supportedwireengines(self, role, onlyavailable=True):
         """Obtain compression engines that support the wire protocol.
 
         Returns a list of engines in prioritized order, most desired first.
 
         If ``onlyavailable`` is set, filter out engines that can't be
         loaded.
         """
         assert role in (SERVERROLE, CLIENTROLE)
 
         attr = 'serverpriority' if role == SERVERROLE else 'clientpriority'
 
         engines = [self._engines[e] for e in self._wiretypes.values()]
         if onlyavailable:
             engines = [e for e in engines if e.available()]
 
         def getkey(e):
             # Sort first by priority, highest first. In case of tie, sort
             # alphabetically. This is arbitrary, but ensures output is
             # stable.
             w = e.wireprotosupport()
             return -1 * getattr(w, attr), w.name
 
         return list(sorted(engines, key=getkey))
 
     def forwiretype(self, wiretype):
         engine = self._engines[self._wiretypes[wiretype]]
         if not engine.available():
             raise error.Abort(_('compression engine %s could not be loaded') %
                               engine.name())
         return engine
 
     def forrevlogheader(self, header):
         """Obtain a compression engine registered to a revlog header.
 
         Will raise KeyError if the revlog header value isn't registered.
         """
         return self._engines[self._revlogheaders[header]]
 
 compengines = compressormanager()
 
 class compressionengine(object):
     """Base class for compression engines.
 
     Compression engines must implement the interface defined by this class.
     """
     def name(self):
         """Returns the name of the compression engine.
 
         This is the key the engine is registered under.
 
         This method must be implemented.
         """
         raise NotImplementedError()
 
     def available(self):
         """Whether the compression engine is available.
 
         The intent of this method is to allow optional compression engines
         that may not be available in all installations (such as engines relying
         on C extensions that may not be present).
         """
         return True
 
     def bundletype(self):
         """Describes bundle identifiers for this engine.
 
         If this compression engine isn't supported for bundles, returns None.
 
         If this engine can be used for bundles, returns a 2-tuple of strings of
         the user-facing "bundle spec" compression name and an internal
         identifier used to denote the compression format within bundles. To
         exclude the name from external usage, set the first element to ``None``.
 
         If bundle compression is supported, the class must also implement
         ``compressstream`` and `decompressorreader``.
         """
         return None
 
     def wireprotosupport(self):
         """Declare support for this compression format on the wire protocol.
 
         If this compression engine isn't supported for compressing wire
         protocol payloads, returns None.
 
         Otherwise, returns ``compenginewireprotosupport`` with the following
         fields:
 
         * String format identifier
         * Integer priority for the server
         * Integer priority for the client
 
         The integer priorities are used to order the advertisement of format
         support by server and client. The highest integer is advertised
         first. Integers with non-positive values aren't advertised.
 
         The priority values are somewhat arbitrary and only used for default
         ordering. The relative order can be changed via config options.
 
         If wire protocol compression is supported, the class must also implement
         ``compressstream`` and ``decompressorreader``.
         """
         return None
 
     def revlogheader(self):
         """Header added to revlog chunks that identifies this engine.
 
         If this engine can be used to compress revlogs, this method should
         return the bytes used to identify chunks compressed with this engine.
         Else, the method should return ``None`` to indicate it does not
         participate in revlog compression.
         """
         return None
 
     def compressstream(self, it, opts=None):
         """Compress an iterator of chunks.
 
         The method receives an iterator (ideally a generator) of chunks of
         bytes to be compressed. It returns an iterator (ideally a generator)
         of bytes of chunks representing the compressed output.
 
         Optionally accepts an argument defining how to perform compression.
         Each engine treats this argument differently.
         """
         raise NotImplementedError()
 
     def decompressorreader(self, fh):
         """Perform decompression on a file object.
 
         Argument is an object with a ``read(size)`` method that returns
         compressed data. Return value is an object with a ``read(size)`` that
         returns uncompressed data.
         """
         raise NotImplementedError()
 
     def revlogcompressor(self, opts=None):
         """Obtain an object that can be used to compress revlog entries.
 
         The object has a ``compress(data)`` method that compresses binary
         data. This method returns compressed binary data or ``None`` if
         the data could not be compressed (too small, not compressible, etc).
         The returned data should have a header uniquely identifying this
         compression format so decompression can be routed to this engine.
         This header should be identified by the ``revlogheader()`` return
         value.
 
         The object has a ``decompress(data)`` method that decompresses
         data. The method will only be called if ``data`` begins with
         ``revlogheader()``. The method should return the raw, uncompressed
         data or raise a ``RevlogError``.
 
         The object is reusable but is not thread safe.
         """
         raise NotImplementedError()
 
 class _zlibengine(compressionengine):
     def name(self):
         return 'zlib'
 
     def bundletype(self):
         return 'gzip', 'GZ'
 
     def wireprotosupport(self):
         return compewireprotosupport('zlib', 20, 20)
 
     def revlogheader(self):
         return 'x'
 
     def compressstream(self, it, opts=None):
         opts = opts or {}
 
         z = zlib.compressobj(opts.get('level', -1))
         for chunk in it:
             data = z.compress(chunk)
             # Not all calls to compress emit data. It is cheaper to inspect
             # here than to feed empty chunks through generator.
             if data:
                 yield data
 
         yield z.flush()
 
     def decompressorreader(self, fh):
         def gen():
             d = zlib.decompressobj()
             for chunk in filechunkiter(fh):
                 while chunk:
                     # Limit output size to limit memory.
                     yield d.decompress(chunk, 2 ** 18)
                     chunk = d.unconsumed_tail
 
         return chunkbuffer(gen())
 
     class zlibrevlogcompressor(object):
         def compress(self, data):
             insize = len(data)
             # Caller handles empty input case.
             assert insize > 0
 
             if insize < 44:
                 return None
 
             elif insize <= 1000000:
                 compressed = zlib.compress(data)
                 if len(compressed) < insize:
                     return compressed
                 return None
 
             # zlib makes an internal copy of the input buffer, doubling
             # memory usage for large inputs. So do streaming compression
             # on large inputs.
             else:
                 z = zlib.compressobj()
                 parts = []
                 pos = 0
                 while pos < insize:
                     pos2 = pos + 2**20
                     parts.append(z.compress(data[pos:pos2]))
                     pos = pos2
                 parts.append(z.flush())
 
                 if sum(map(len, parts)) < insize:
                     return ''.join(parts)
                 return None
 
         def decompress(self, data):
             try:
                 return zlib.decompress(data)
             except zlib.error as e:
                 raise error.RevlogError(_('revlog decompress error: %s') %
                                         str(e))
 
     def revlogcompressor(self, opts=None):
         return self.zlibrevlogcompressor()
 
 compengines.register(_zlibengine())
 
 class _bz2engine(compressionengine):
     def name(self):
         return 'bz2'
 
     def bundletype(self):
         return 'bzip2', 'BZ'
 
     # We declare a protocol name but don't advertise by default because
     # it is slow.
     def wireprotosupport(self):
         return compewireprotosupport('bzip2', 0, 0)
 
     def compressstream(self, it, opts=None):
         opts = opts or {}
         z = bz2.BZ2Compressor(opts.get('level', 9))
         for chunk in it:
             data = z.compress(chunk)
             if data:
                 yield data
 
         yield z.flush()
 
     def decompressorreader(self, fh):
         def gen():
             d = bz2.BZ2Decompressor()
             for chunk in filechunkiter(fh):
                 yield d.decompress(chunk)
 
         return chunkbuffer(gen())
 
 compengines.register(_bz2engine())
 
 class _truncatedbz2engine(compressionengine):
     def name(self):
         return 'bz2truncated'
 
     def bundletype(self):
         return None, '_truncatedBZ'
 
     # We don't implement compressstream because it is hackily handled elsewhere.
 
     def decompressorreader(self, fh):
         def gen():
             # The input stream doesn't have the 'BZ' header. So add it back.
             d = bz2.BZ2Decompressor()
             d.decompress('BZ')
             for chunk in filechunkiter(fh):
                 yield d.decompress(chunk)
 
         return chunkbuffer(gen())
 
 compengines.register(_truncatedbz2engine())
 
 class _noopengine(compressionengine):
     def name(self):
         return 'none'
 
     def bundletype(self):
         return 'none', 'UN'
 
     # Clients always support uncompressed payloads. Servers don't because
     # unless you are on a fast network, uncompressed payloads can easily
     # saturate your network pipe.
     def wireprotosupport(self):
         return compewireprotosupport('none', 0, 10)
 
     # We don't implement revlogheader because it is handled specially
     # in the revlog class.
 
     def compressstream(self, it, opts=None):
         return it
 
     def decompressorreader(self, fh):
         return fh
 
     class nooprevlogcompressor(object):
         def compress(self, data):
             return None
 
     def revlogcompressor(self, opts=None):
         return self.nooprevlogcompressor()
 
 compengines.register(_noopengine())
 
 class _zstdengine(compressionengine):
     def name(self):
         return 'zstd'
 
     @propertycache
     def _module(self):
         # Not all installs have the zstd module available. So defer importing
         # until first access.
         try:
             from . import zstd
             # Force delayed import.
             zstd.__version__
             return zstd
         except ImportError:
             return None
 
     def available(self):
         return bool(self._module)
 
     def bundletype(self):
         return 'zstd', 'ZS'
 
     def wireprotosupport(self):
         return compewireprotosupport('zstd', 50, 50)
 
     def revlogheader(self):
         return '\x28'
 
     def compressstream(self, it, opts=None):
         opts = opts or {}
         # zstd level 3 is almost always significantly faster than zlib
         # while providing no worse compression. It strikes a good balance
         # between speed and compression.
         level = opts.get('level', 3)
 
         zstd = self._module
         z = zstd.ZstdCompressor(level=level).compressobj()
         for chunk in it:
             data = z.compress(chunk)
             if data:
                 yield data
 
         yield z.flush()
 
     def decompressorreader(self, fh):
         zstd = self._module
         dctx = zstd.ZstdDecompressor()
         return chunkbuffer(dctx.read_from(fh))
 
     class zstdrevlogcompressor(object):
         def __init__(self, zstd, level=3):
             # Writing the content size adds a few bytes to the output. However,
             # it allows decompression to be more optimal since we can
             # pre-allocate a buffer to hold the result.
             self._cctx = zstd.ZstdCompressor(level=level,
                                              write_content_size=True)
             self._dctx = zstd.ZstdDecompressor()
             self._compinsize = zstd.COMPRESSION_RECOMMENDED_INPUT_SIZE
             self._decompinsize = zstd.DECOMPRESSION_RECOMMENDED_INPUT_SIZE
 
         def compress(self, data):
             insize = len(data)
             # Caller handles empty input case.
             assert insize > 0
 
             if insize < 50:
                 return None
 
             elif insize <= 1000000:
                 compressed = self._cctx.compress(data)
                 if len(compressed) < insize:
                     return compressed
                 return None
             else:
                 z = self._cctx.compressobj()
                 chunks = []
                 pos = 0
                 while pos < insize:
                     pos2 = pos + self._compinsize
                     chunk = z.compress(data[pos:pos2])
                     if chunk:
                         chunks.append(chunk)
                     pos = pos2
                 chunks.append(z.flush())
 
                 if sum(map(len, chunks)) < insize:
                     return ''.join(chunks)
                 return None
 
         def decompress(self, data):
             insize = len(data)
 
             try:
                 # This was measured to be faster than other streaming
                 # decompressors.
                 dobj = self._dctx.decompressobj()
                 chunks = []
                 pos = 0
                 while pos < insize:
                     pos2 = pos + self._decompinsize
                     chunk = dobj.decompress(data[pos:pos2])
                     if chunk:
                         chunks.append(chunk)
                     pos = pos2
                 # Frame should be exhausted, so no finish() API.
 
                 return ''.join(chunks)
             except Exception as e:
                 raise error.RevlogError(_('revlog decompress error: %s') %
                                         str(e))
 
     def revlogcompressor(self, opts=None):
         opts = opts or {}
         return self.zstdrevlogcompressor(self._module,
                                          level=opts.get('level', 3))
 
 compengines.register(_zstdengine())
 
 # convenient shortcut
 dst = debugstacktrace