bdiff: proxy through mdiff module

See the previous commit for why.

mdiff seems a good place to host bdiff functions. bdiff.bdiff was already
aliased as textdiff, so we use it.

contrib/bdiff-torture.py

@@ -1,100 +1,100
 # Randomized torture test generation for bdiff
 
 from __future__ import absolute_import, print_function
 import random
 import sys
 
 from mercurial import (
-    bdiff,
+    mdiff,
     mpatch,
 )
 
 def reducetest(a, b):
     tries = 0
     reductions = 0
     print("reducing...")
     while tries < 1000:
         a2 = "\n".join(l for l in a.splitlines()
                        if random.randint(0, 100) > 0) + "\n"
         b2 = "\n".join(l for l in b.splitlines()
                        if random.randint(0, 100) > 0) + "\n"
         if a2 == a and b2 == b:
             continue
         if a2 == b2:
             continue
         tries += 1
 
         try:
             test1(a, b)
         except Exception as inst:
             reductions += 1
             tries = 0
             a = a2
             b = b2
 
     print("reduced:", reductions, len(a) + len(b),
           repr(a), repr(b))
     try:
         test1(a, b)
     except Exception as inst:
         print("failed:", inst)
 
     sys.exit(0)
 
 def test1(a, b):
-    d = bdiff.bdiff(a, b)
+    d = mdiff.textdiff(a, b)
     if not d:
         raise ValueError("empty")
     c = mpatch.patches(a, [d])
     if c != b:
         raise ValueError("bad")
 
 def testwrap(a, b):
     try:
         test1(a, b)
         return
     except Exception as inst:
         pass
     print("exception:", inst)
     reducetest(a, b)
 
 def test(a, b):
     testwrap(a, b)
     testwrap(b, a)
 
 def rndtest(size, noise):
     a = []
     src = "                aaaaaaaabbbbccd"
     for x in xrange(size):
         a.append(src[random.randint(0, len(src) - 1)])
 
     while True:
         b = [c for c in a if random.randint(0, 99) > noise]
         b2 = []
         for c in b:
             b2.append(c)
             while random.randint(0, 99) < noise:
                 b2.append(src[random.randint(0, len(src) - 1)])
         if b2 != a:
             break
 
     a = "\n".join(a) + "\n"
     b = "\n".join(b2) + "\n"
 
     test(a, b)
 
 maxvol = 10000
 startsize = 2
 while True:
     size = startsize
     count = 0
     while size < maxvol:
         print(size)
         volume = 0
         while volume < maxvol:
             rndtest(size, 2)
             volume += size
             count += 2
         size *= 2
     maxvol *= 4
     startsize *= 4

contrib/perf.py

@@ -1,1309 +1,1308
 # 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 gc
 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":
 # define util.timer forcibly, because util.timer has been available
 # since ae5d60bb70c9
 if safehasattr(time, 'perf_counter'):
     util.timer = time.perf_counter
 elif os.name == 'nt':
     util.timer = time.clock
 else:
     util.timer = time.time
 
 # 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
             __bool__ = __nonzero__
             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):
     gc.collect()
     results = []
     begin = util.timer()
     count = 0
     while True:
         ostart = os.times()
         cstart = util.timer()
         r = func()
         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)
+            mdiff.textdiff(*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()
 
 @command('perfwrite', formatteropts)
 def perfwrite(ui, repo, **opts):
     """microbenchmark ui.write
     """
     timer, fm = gettimer(ui, opts)
     def write():
         for i in range(100000):
             ui.write(('Testing write performance\n'))
     timer(write)
     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/mdiff.py

@@ -1,483 +1,485
 # mdiff.py - diff and patch routines for mercurial
 #
 # Copyright 2005, 2006 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 re
 import struct
 import zlib
 
 from .i18n import _
 from . import (
     bdiff,
     error,
     mpatch,
     pycompat,
     util,
 )
 
+blocks = bdiff.blocks
+fixws = bdiff.fixws
 patches = mpatch.patches
 patchedsize = mpatch.patchedsize
 textdiff = bdiff.bdiff
 
 def splitnewlines(text):
     '''like str.splitlines, but only split on newlines.'''
     lines = [l + '\n' for l in text.split('\n')]
     if lines:
         if lines[-1] == '\n':
             lines.pop()
         else:
             lines[-1] = lines[-1][:-1]
     return lines
 
 class diffopts(object):
     '''context is the number of context lines
     text treats all files as text
     showfunc enables diff -p output
     git enables the git extended patch format
     nodates removes dates from diff headers
     nobinary ignores binary files
     noprefix disables the 'a/' and 'b/' prefixes (ignored in plain mode)
     ignorews ignores all whitespace changes in the diff
     ignorewsamount ignores changes in the amount of whitespace
     ignoreblanklines ignores changes whose lines are all blank
     upgrade generates git diffs to avoid data loss
     '''
 
     defaults = {
         'context': 3,
         'text': False,
         'showfunc': False,
         'git': False,
         'nodates': False,
         'nobinary': False,
         'noprefix': False,
         'index': 0,
         'ignorews': False,
         'ignorewsamount': False,
         'ignoreblanklines': False,
         'upgrade': False,
         'showsimilarity': False,
         }
 
     def __init__(self, **opts):
         opts = pycompat.byteskwargs(opts)
         for k in self.defaults.keys():
             v = opts.get(k)
             if v is None:
                 v = self.defaults[k]
             setattr(self, k, v)
 
         try:
             self.context = int(self.context)
         except ValueError:
             raise error.Abort(_('diff context lines count must be '
                                'an integer, not %r') % self.context)
 
     def copy(self, **kwargs):
         opts = dict((k, getattr(self, k)) for k in self.defaults)
         opts.update(kwargs)
         return diffopts(**opts)
 
 defaultopts = diffopts()
 
 def wsclean(opts, text, blank=True):
     if opts.ignorews:
         text = bdiff.fixws(text, 1)
     elif opts.ignorewsamount:
         text = bdiff.fixws(text, 0)
     if blank and opts.ignoreblanklines:
         text = re.sub('\n+', '\n', text).strip('\n')
     return text
 
 def splitblock(base1, lines1, base2, lines2, opts):
     # The input lines matches except for interwoven blank lines. We
     # transform it into a sequence of matching blocks and blank blocks.
     lines1 = [(wsclean(opts, l) and 1 or 0) for l in lines1]
     lines2 = [(wsclean(opts, l) and 1 or 0) for l in lines2]
     s1, e1 = 0, len(lines1)
     s2, e2 = 0, len(lines2)
     while s1 < e1 or s2 < e2:
         i1, i2, btype = s1, s2, '='
         if (i1 >= e1 or lines1[i1] == 0
             or i2 >= e2 or lines2[i2] == 0):
             # Consume the block of blank lines
             btype = '~'
             while i1 < e1 and lines1[i1] == 0:
                 i1 += 1
             while i2 < e2 and lines2[i2] == 0:
                 i2 += 1
         else:
             # Consume the matching lines
             while i1 < e1 and lines1[i1] == 1 and lines2[i2] == 1:
                 i1 += 1
                 i2 += 1
         yield [base1 + s1, base1 + i1, base2 + s2, base2 + i2], btype
         s1 = i1
         s2 = i2
 
 def hunkinrange(hunk, linerange):
     """Return True if `hunk` defined as (start, length) is in `linerange`
     defined as (lowerbound, upperbound).
 
     >>> hunkinrange((5, 10), (2, 7))
     True
     >>> hunkinrange((5, 10), (6, 12))
     True
     >>> hunkinrange((5, 10), (13, 17))
     True
     >>> hunkinrange((5, 10), (3, 17))
     True
     >>> hunkinrange((5, 10), (1, 3))
     False
     >>> hunkinrange((5, 10), (18, 20))
     False
     >>> hunkinrange((5, 10), (1, 5))
     False
     >>> hunkinrange((5, 10), (15, 27))
     False
     """
     start, length = hunk
     lowerbound, upperbound = linerange
     return lowerbound < start + length and start < upperbound
 
 def blocksinrange(blocks, rangeb):
     """filter `blocks` like (a1, a2, b1, b2) from items outside line range
     `rangeb` from ``(b1, b2)`` point of view.
 
     Return `filteredblocks, rangea` where:
 
     * `filteredblocks` is list of ``block = (a1, a2, b1, b2), stype`` items of
       `blocks` that are inside `rangeb` from ``(b1, b2)`` point of view; a
       block ``(b1, b2)`` being inside `rangeb` if
       ``rangeb[0] < b2 and b1 < rangeb[1]``;
     * `rangea` is the line range w.r.t. to ``(a1, a2)`` parts of `blocks`.
     """
     lbb, ubb = rangeb
     lba, uba = None, None
     filteredblocks = []
     for block in blocks:
         (a1, a2, b1, b2), stype = block
         if lbb >= b1 and ubb <= b2 and stype == '=':
             # rangeb is within a single "=" hunk, restrict back linerange1
             # by offsetting rangeb
             lba = lbb - b1 + a1
             uba = ubb - b1 + a1
         else:
             if b1 <= lbb < b2:
                 if stype == '=':
                     lba = a2 - (b2 - lbb)
                 else:
                     lba = a1
             if b1 < ubb <= b2:
                 if stype == '=':
                     uba = a1 + (ubb - b1)
                 else:
                     uba = a2
         if hunkinrange((b1, (b2 - b1)), rangeb):
             filteredblocks.append(block)
     if lba is None or uba is None or uba < lba:
         raise error.Abort(_('line range exceeds file size'))
     return filteredblocks, (lba, uba)
 
 def allblocks(text1, text2, opts=None, lines1=None, lines2=None):
     """Return (block, type) tuples, where block is an mdiff.blocks
     line entry. type is '=' for blocks matching exactly one another
     (bdiff blocks), '!' for non-matching blocks and '~' for blocks
     matching only after having filtered blank lines.
     line1 and line2 are text1 and text2 split with splitnewlines() if
     they are already available.
     """
     if opts is None:
         opts = defaultopts
     if opts.ignorews or opts.ignorewsamount:
         text1 = wsclean(opts, text1, False)
         text2 = wsclean(opts, text2, False)
     diff = bdiff.blocks(text1, text2)
     for i, s1 in enumerate(diff):
         # The first match is special.
         # we've either found a match starting at line 0 or a match later
         # in the file.  If it starts later, old and new below will both be
         # empty and we'll continue to the next match.
         if i > 0:
             s = diff[i - 1]
         else:
             s = [0, 0, 0, 0]
         s = [s[1], s1[0], s[3], s1[2]]
 
         # bdiff sometimes gives huge matches past eof, this check eats them,
         # and deals with the special first match case described above
         if s[0] != s[1] or s[2] != s[3]:
             type = '!'
             if opts.ignoreblanklines:
                 if lines1 is None:
                     lines1 = splitnewlines(text1)
                 if lines2 is None:
                     lines2 = splitnewlines(text2)
                 old = wsclean(opts, "".join(lines1[s[0]:s[1]]))
                 new = wsclean(opts, "".join(lines2[s[2]:s[3]]))
                 if old == new:
                     type = '~'
             yield s, type
         yield s1, '='
 
 def unidiff(a, ad, b, bd, fn1, fn2, opts=defaultopts):
     """Return a unified diff as a (headers, hunks) tuple.
 
     If the diff is not null, `headers` is a list with unified diff header
     lines "--- <original>" and "+++ <new>" and `hunks` is a generator yielding
     (hunkrange, hunklines) coming from _unidiff().
     Otherwise, `headers` and `hunks` are empty.
     """
     def datetag(date, fn=None):
         if not opts.git and not opts.nodates:
             return '\t%s' % date
         if fn and ' ' in fn:
             return '\t'
         return ''
 
     sentinel = [], ()
     if not a and not b:
         return sentinel
 
     if opts.noprefix:
         aprefix = bprefix = ''
     else:
         aprefix = 'a/'
         bprefix = 'b/'
 
     epoch = util.datestr((0, 0))
 
     fn1 = util.pconvert(fn1)
     fn2 = util.pconvert(fn2)
 
     def checknonewline(lines):
         for text in lines:
             if text[-1:] != '\n':
                 text += "\n\ No newline at end of file\n"
             yield text
 
     if not opts.text and (util.binary(a) or util.binary(b)):
         if a and b and len(a) == len(b) and a == b:
             return sentinel
         headerlines = []
         hunks = (None, ['Binary file %s has changed\n' % fn1]),
     elif not a:
         b = splitnewlines(b)
         if a is None:
             l1 = '--- /dev/null%s' % datetag(epoch)
         else:
             l1 = "--- %s%s%s" % (aprefix, fn1, datetag(ad, fn1))
         l2 = "+++ %s%s" % (bprefix + fn2, datetag(bd, fn2))
         headerlines = [l1, l2]
         size = len(b)
         hunkrange = (0, 0, 1, size)
         hunklines = ["@@ -0,0 +1,%d @@\n" % size] + ["+" + e for e in b]
         hunks = (hunkrange, checknonewline(hunklines)),
     elif not b:
         a = splitnewlines(a)
         l1 = "--- %s%s%s" % (aprefix, fn1, datetag(ad, fn1))
         if b is None:
             l2 = '+++ /dev/null%s' % datetag(epoch)
         else:
             l2 = "+++ %s%s%s" % (bprefix, fn2, datetag(bd, fn2))
         headerlines = [l1, l2]
         size = len(a)
         hunkrange = (1, size, 0, 0)
         hunklines = ["@@ -1,%d +0,0 @@\n" % size] + ["-" + e for e in a]
         hunks = (hunkrange, checknonewline(hunklines)),
     else:
         diffhunks = _unidiff(a, b, opts=opts)
         try:
             hunkrange, hunklines = next(diffhunks)
         except StopIteration:
             return sentinel
 
         headerlines = [
             "--- %s%s%s" % (aprefix, fn1, datetag(ad, fn1)),
             "+++ %s%s%s" % (bprefix, fn2, datetag(bd, fn2)),
         ]
         def rewindhunks():
             yield hunkrange, checknonewline(hunklines)
             for hr, hl in diffhunks:
                 yield hr, checknonewline(hl)
 
         hunks = rewindhunks()
 
     return headerlines, hunks
 
 def _unidiff(t1, t2, opts=defaultopts):
     """Yield hunks of a headerless unified diff from t1 and t2 texts.
 
     Each hunk consists of a (hunkrange, hunklines) tuple where `hunkrange` is a
     tuple (s1, l1, s2, l2) representing the range information of the hunk to
     form the '@@ -s1,l1 +s2,l2 @@' header and `hunklines` is a list of lines
     of the hunk combining said header followed by line additions and
     deletions.
     """
     l1 = splitnewlines(t1)
     l2 = splitnewlines(t2)
     def contextend(l, len):
         ret = l + opts.context
         if ret > len:
             ret = len
         return ret
 
     def contextstart(l):
         ret = l - opts.context
         if ret < 0:
             return 0
         return ret
 
     lastfunc = [0, '']
     def yieldhunk(hunk):
         (astart, a2, bstart, b2, delta) = hunk
         aend = contextend(a2, len(l1))
         alen = aend - astart
         blen = b2 - bstart + aend - a2
 
         func = ""
         if opts.showfunc:
             lastpos, func = lastfunc
             # walk backwards from the start of the context up to the start of
             # the previous hunk context until we find a line starting with an
             # alphanumeric char.
             for i in xrange(astart - 1, lastpos - 1, -1):
                 if l1[i][0].isalnum():
                     func = ' ' + l1[i].rstrip()[:40]
                     lastfunc[1] = func
                     break
             # by recording this hunk's starting point as the next place to
             # start looking for function lines, we avoid reading any line in
             # the file more than once.
             lastfunc[0] = astart
 
         # zero-length hunk ranges report their start line as one less
         if alen:
             astart += 1
         if blen:
             bstart += 1
 
         hunkrange = astart, alen, bstart, blen
         hunklines = (
             ["@@ -%d,%d +%d,%d @@%s\n" % (hunkrange + (func,))]
             + delta
             + [' ' + l1[x] for x in xrange(a2, aend)]
         )
         yield hunkrange, hunklines
 
     # bdiff.blocks gives us the matching sequences in the files.  The loop
     # below finds the spaces between those matching sequences and translates
     # them into diff output.
     #
     hunk = None
     ignoredlines = 0
     for s, stype in allblocks(t1, t2, opts, l1, l2):
         a1, a2, b1, b2 = s
         if stype != '!':
             if stype == '~':
                 # The diff context lines are based on t1 content. When
                 # blank lines are ignored, the new lines offsets must
                 # be adjusted as if equivalent blocks ('~') had the
                 # same sizes on both sides.
                 ignoredlines += (b2 - b1) - (a2 - a1)
             continue
         delta = []
         old = l1[a1:a2]
         new = l2[b1:b2]
 
         b1 -= ignoredlines
         b2 -= ignoredlines
         astart = contextstart(a1)
         bstart = contextstart(b1)
         prev = None
         if hunk:
             # join with the previous hunk if it falls inside the context
             if astart < hunk[1] + opts.context + 1:
                 prev = hunk
                 astart = hunk[1]
                 bstart = hunk[3]
             else:
                 for x in yieldhunk(hunk):
                     yield x
         if prev:
             # we've joined the previous hunk, record the new ending points.
             hunk[1] = a2
             hunk[3] = b2
             delta = hunk[4]
         else:
             # create a new hunk
             hunk = [astart, a2, bstart, b2, delta]
 
         delta[len(delta):] = [' ' + x for x in l1[astart:a1]]
         delta[len(delta):] = ['-' + x for x in old]
         delta[len(delta):] = ['+' + x for x in new]
 
     if hunk:
         for x in yieldhunk(hunk):
             yield x
 
 def b85diff(to, tn):
     '''print base85-encoded binary diff'''
     def fmtline(line):
         l = len(line)
         if l <= 26:
             l = chr(ord('A') + l - 1)
         else:
             l = chr(l - 26 + ord('a') - 1)
         return '%c%s\n' % (l, util.b85encode(line, True))
 
     def chunk(text, csize=52):
         l = len(text)
         i = 0
         while i < l:
             yield text[i:i + csize]
             i += csize
 
     if to is None:
         to = ''
     if tn is None:
         tn = ''
 
     if to == tn:
         return ''
 
     # TODO: deltas
     ret = []
     ret.append('GIT binary patch\n')
     ret.append('literal %s\n' % len(tn))
     for l in chunk(zlib.compress(tn)):
         ret.append(fmtline(l))
     ret.append('\n')
 
     return ''.join(ret)
 
 def patchtext(bin):
     pos = 0
     t = []
     while pos < len(bin):
         p1, p2, l = struct.unpack(">lll", bin[pos:pos + 12])
         pos += 12
         t.append(bin[pos:pos + l])
         pos += l
     return "".join(t)
 
 def patch(a, bin):
     if len(a) == 0:
         # skip over trivial delta header
         return util.buffer(bin, 12)
     return mpatch.patches(a, [bin])
 
 # similar to difflib.SequenceMatcher.get_matching_blocks
 def get_matching_blocks(a, b):
     return [(d[0], d[2], d[1] - d[0]) for d in bdiff.blocks(a, b)]
 
 def trivialdiffheader(length):
     return struct.pack(">lll", 0, 0, length) if length else ''
 
 def replacediffheader(oldlen, newlen):
     return struct.pack(">lll", 0, oldlen, newlen)

mercurial/similar.py

@@ -1,123 +1,122
 # similar.py - mechanisms for finding similar files
 #
 # 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
 
 from .i18n import _
 from . import (
-    bdiff,
     mdiff,
 )
 
 def _findexactmatches(repo, added, removed):
     '''find renamed files that have no changes
 
     Takes a list of new filectxs and a list of removed filectxs, and yields
     (before, after) tuples of exact matches.
     '''
     numfiles = len(added) + len(removed)
 
     # Build table of removed files: {hash(fctx.data()): [fctx, ...]}.
     # We use hash() to discard fctx.data() from memory.
     hashes = {}
     for i, fctx in enumerate(removed):
         repo.ui.progress(_('searching for exact renames'), i, total=numfiles,
                          unit=_('files'))
         h = hash(fctx.data())
         if h not in hashes:
             hashes[h] = [fctx]
         else:
             hashes[h].append(fctx)
 
     # For each added file, see if it corresponds to a removed file.
     for i, fctx in enumerate(added):
         repo.ui.progress(_('searching for exact renames'), i + len(removed),
                 total=numfiles, unit=_('files'))
         adata = fctx.data()
         h = hash(adata)
         for rfctx in hashes.get(h, []):
             # compare between actual file contents for exact identity
             if adata == rfctx.data():
                 yield (rfctx, fctx)
                 break
 
     # Done
     repo.ui.progress(_('searching for exact renames'), None)
 
 def _ctxdata(fctx):
     # lazily load text
     orig = fctx.data()
     return orig, mdiff.splitnewlines(orig)
 
 def _score(fctx, otherdata):
     orig, lines = otherdata
     text = fctx.data()
-    # bdiff.blocks() returns blocks of matching lines
+    # mdiff.blocks() returns blocks of matching lines
     # count the number of bytes in each
     equal = 0
-    matches = bdiff.blocks(text, orig)
+    matches = mdiff.blocks(text, orig)
     for x1, x2, y1, y2 in matches:
         for line in lines[y1:y2]:
             equal += len(line)
 
     lengths = len(text) + len(orig)
     return equal * 2.0 / lengths
 
 def score(fctx1, fctx2):
     return _score(fctx1, _ctxdata(fctx2))
 
 def _findsimilarmatches(repo, added, removed, threshold):
     '''find potentially renamed files based on similar file content
 
     Takes a list of new filectxs and a list of removed filectxs, and yields
     (before, after, score) tuples of partial matches.
     '''
     copies = {}
     for i, r in enumerate(removed):
         repo.ui.progress(_('searching for similar files'), i,
                          total=len(removed), unit=_('files'))
 
         data = None
         for a in added:
             bestscore = copies.get(a, (None, threshold))[1]
             if data is None:
                 data = _ctxdata(r)
             myscore = _score(a, data)
             if myscore > bestscore:
                 copies[a] = (r, myscore)
     repo.ui.progress(_('searching'), None)
 
     for dest, v in copies.iteritems():
         source, bscore = v
         yield source, dest, bscore
 
 def _dropempty(fctxs):
     return [x for x in fctxs if x.size() > 0]
 
 def findrenames(repo, added, removed, threshold):
     '''find renamed files -- yields (before, after, score) tuples'''
     wctx = repo[None]
     pctx = wctx.p1()
 
     # Zero length files will be frequently unrelated to each other, and
     # tracking the deletion/addition of such a file will probably cause more
     # harm than good. We strip them out here to avoid matching them later on.
     addedfiles = _dropempty(wctx[fp] for fp in sorted(added))
     removedfiles = _dropempty(pctx[fp] for fp in sorted(removed) if fp in pctx)
 
     # Find exact matches.
     matchedfiles = set()
     for (a, b) in _findexactmatches(repo, addedfiles, removedfiles):
         matchedfiles.add(b)
         yield (a.path(), b.path(), 1.0)
 
     # If the user requested similar files to be matched, search for them also.
     if threshold < 1.0:
         addedfiles = [x for x in addedfiles if x not in matchedfiles]
         for (a, b, score) in _findsimilarmatches(repo, addedfiles,
                                                  removedfiles, threshold):
             yield (a.path(), b.path(), score)

tests/test-bdiff.py

@@ -1,150 +1,150
 from __future__ import absolute_import, print_function
 import collections
 import struct
 import unittest
 
 from mercurial import (
-    bdiff,
+    mdiff,
     mpatch,
 )
 
 class diffreplace(
     collections.namedtuple('diffreplace', 'start end from_ to')):
     def __repr__(self):
         return 'diffreplace(%r, %r, %r, %r)' % self
 
 class BdiffTests(unittest.TestCase):
 
     def assert_bdiff_applies(self, a, b):
-        d = bdiff.bdiff(a, b)
+        d = mdiff.textdiff(a, b)
         c = a
         if d:
             c = mpatch.patches(a, [d])
         self.assertEqual(
             c, b, ("bad diff+patch result from\n  %r to\n  "
                    "%r: \nbdiff: %r\npatched: %r" % (a, b, d, c[:200])))
 
     def assert_bdiff(self, a, b):
         self.assert_bdiff_applies(a, b)
         self.assert_bdiff_applies(b, a)
 
     def test_bdiff_basic(self):
         cases = [
             ("a\nc\n\n\n\n", "a\nb\n\n\n"),
             ("a\nb\nc\n", "a\nc\n"),
             ("", ""),
             ("a\nb\nc", "a\nb\nc"),
             ("a\nb\nc\nd\n", "a\nd\n"),
             ("a\nb\nc\nd\n", "a\nc\ne\n"),
             ("a\nb\nc\n", "a\nc\n"),
             ("a\n", "c\na\nb\n"),
             ("a\n", ""),
             ("a\n", "b\nc\n"),
             ("a\n", "c\na\n"),
             ("", "adjfkjdjksdhfksj"),
             ("", "ab"),
             ("", "abc"),
             ("a", "a"),
             ("ab", "ab"),
             ("abc", "abc"),
             ("a\n", "a\n"),
             ("a\nb", "a\nb"),
         ]
         for a, b in cases:
             self.assert_bdiff(a, b)
 
     def showdiff(self, a, b):
-        bin = bdiff.bdiff(a, b)
+        bin = mdiff.textdiff(a, b)
         pos = 0
         q = 0
         actions = []
         while pos < len(bin):
             p1, p2, l = struct.unpack(">lll", bin[pos:pos + 12])
             pos += 12
             if p1:
                 actions.append(a[q:p1])
             actions.append(diffreplace(p1, p2, a[p1:p2], bin[pos:pos + l]))
             pos += l
             q = p2
         if q < len(a):
             actions.append(a[q:])
         return actions
 
     def test_issue1295(self):
         cases = [
             ("x\n\nx\n\nx\n\nx\n\nz\n", "x\n\nx\n\ny\n\nx\n\nx\n\nz\n",
              ['x\n\nx\n\n', diffreplace(6, 6, '', 'y\n\n'), 'x\n\nx\n\nz\n']),
             ("x\n\nx\n\nx\n\nx\n\nz\n", "x\n\nx\n\ny\n\nx\n\ny\n\nx\n\nz\n",
              ['x\n\nx\n\n',
               diffreplace(6, 6, '', 'y\n\n'),
               'x\n\n',
               diffreplace(9, 9, '', 'y\n\n'),
               'x\n\nz\n']),
         ]
         for old, new, want in cases:
             self.assertEqual(self.showdiff(old, new), want)
 
     def test_issue1295_varies_on_pure(self):
             # we should pick up abbbc. rather than bc.de as the longest match
         got = self.showdiff("a\nb\nb\nb\nc\n.\nd\ne\n.\nf\n",
                             "a\nb\nb\na\nb\nb\nb\nc\n.\nb\nc\n.\nd\ne\nf\n")
         want_c = ['a\nb\nb\n',
                   diffreplace(6, 6, '', 'a\nb\nb\nb\nc\n.\n'),
                   'b\nc\n.\nd\ne\n',
                   diffreplace(16, 18, '.\n', ''),
                   'f\n']
         want_pure = [diffreplace(0, 0, '', 'a\nb\nb\n'),
                      'a\nb\nb\nb\nc\n.\n',
                      diffreplace(12, 12, '', 'b\nc\n.\n'),
                      'd\ne\n',
                      diffreplace(16, 18, '.\n', ''), 'f\n']
         self.assert_(got in (want_c, want_pure),
                      'got: %r, wanted either %r or %r' % (
                          got, want_c, want_pure))
 
     def test_fixws(self):
         cases = [
             (" \ta\r b\t\n", "ab\n", 1),
             (" \ta\r b\t\n", " a b\n", 0),
             ("", "", 1),
             ("", "", 0),
         ]
         for a, b, allws in cases:
-            c = bdiff.fixws(a, allws)
+            c = mdiff.fixws(a, allws)
             self.assertEqual(
                 c, b, 'fixws(%r) want %r got %r (allws=%r)' % (a, b, c, allws))
 
     def test_nice_diff_for_trivial_change(self):
         self.assertEqual(self.showdiff(
             ''.join('<%s\n-\n' % i for i in range(5)),
             ''.join('>%s\n-\n' % i for i in range(5))),
                          [diffreplace(0, 3, '<0\n', '>0\n'),
                           '-\n',
                           diffreplace(5, 8, '<1\n', '>1\n'),
                           '-\n',
                           diffreplace(10, 13, '<2\n', '>2\n'),
                           '-\n',
                           diffreplace(15, 18, '<3\n', '>3\n'),
                           '-\n',
                           diffreplace(20, 23, '<4\n', '>4\n'),
                           '-\n'])
 
     def test_prefer_appending(self):
         # 1 line to 3 lines
         self.assertEqual(self.showdiff('a\n', 'a\n' * 3),
                          ['a\n', diffreplace(2, 2, '', 'a\na\n')])
         # 1 line to 5 lines
         self.assertEqual(self.showdiff('a\n', 'a\n' * 5),
                          ['a\n', diffreplace(2, 2, '', 'a\na\na\na\n')])
 
     def test_prefer_removing_trailing(self):
         # 3 lines to 1 line
         self.assertEqual(self.showdiff('a\n' * 3, 'a\n'),
                          ['a\n', diffreplace(2, 6, 'a\na\n', '')])
         # 5 lines to 1 line
         self.assertEqual(self.showdiff('a\n' * 5, 'a\n'),
                          ['a\n', diffreplace(2, 10, 'a\na\na\na\n', '')])
 
 if __name__ == '__main__':
     import silenttestrunner
     silenttestrunner.main(__name__)

tests/test-check-code.t

@@ -1,53 +1,53
 #require test-repo
 
   $ . "$TESTDIR/helpers-testrepo.sh"
   $ check_code="$TESTDIR"/../contrib/check-code.py
   $ cd "$TESTDIR"/..
 
 New errors are not allowed. Warnings are strongly discouraged.
 (The writing "no-che?k-code" is for not skipping this file when checking.)
 
   $ hg locate -X contrib/python-zstandard -X hgext/fsmonitor/pywatchman |
   > sed 's-\\-/-g' | "$check_code" --warnings --per-file=0 - || false
-  contrib/perf.py:869:
+  contrib/perf.py:868:
    >             r.revision(r.node(x))
    don't convert rev to node before passing to revision(nodeorrev)
   Skipping i18n/polib.py it has no-che?k-code (glob)
   Skipping mercurial/httpclient/__init__.py it has no-che?k-code (glob)
   Skipping mercurial/httpclient/_readers.py it has no-che?k-code (glob)
   Skipping mercurial/statprof.py it has no-che?k-code (glob)
   Skipping tests/badserverext.py it has no-che?k-code (glob)
   [1]
 
 @commands in debugcommands.py should be in alphabetical order.
 
   >>> import re
   >>> commands = []
   >>> with open('mercurial/debugcommands.py', 'rb') as fh:
   ...     for line in fh:
   ...         m = re.match("^@command\('([a-z]+)", line)
   ...         if m:
   ...             commands.append(m.group(1))
   >>> scommands = list(sorted(commands))
   >>> for i, command in enumerate(scommands):
   ...     if command != commands[i]:
   ...         print('commands in debugcommands.py not sorted; first differing '
   ...               'command is %s; expected %s' % (commands[i], command))
   ...         break
 
 Prevent adding new files in the root directory accidentally.
 
   $ hg files 'glob:*'
   .editorconfig
   .hgignore
   .hgsigs
   .hgtags
   CONTRIBUTING
   CONTRIBUTORS
   COPYING
   Makefile
   README
   hg
   hgeditor
   hgweb.cgi
   setup.py

tests/test-contrib-perf.t

@@ -1,171 +1,171
 #require test-repo
 
 Set vars:
 
   $ . "$TESTDIR/helpers-testrepo.sh"
   $ CONTRIBDIR="$TESTDIR/../contrib"
 
 Prepare repo:
 
   $ hg init
 
   $ echo this is file a > a
   $ hg add a
   $ hg commit -m first
 
   $ echo adding to file a >> a
   $ hg commit -m second
 
   $ echo adding more to file a >> a
   $ hg commit -m third
 
   $ hg up -r 0
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ echo merge-this >> a
   $ hg commit -m merge-able
   created new head
 
   $ hg up -r 2
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
 perfstatus
 
   $ cat >> $HGRCPATH << EOF
   > [extensions]
   > perfstatusext=$CONTRIBDIR/perf.py
   > [perf]
   > presleep=0
   > stub=on
   > parentscount=1
   > EOF
   $ hg help perfstatusext
   perfstatusext extension - helper extension to measure performance
   
   list of commands:
   
    perfaddremove
                  (no help text available)
    perfancestors
                  (no help text available)
    perfancestorset
                  (no help text available)
    perfannotate  (no help text available)
    perfbdiff     benchmark a bdiff between revisions
    perfbranchmap
                  benchmark the update of a branchmap
    perfcca       (no help text available)
    perfchangegroupchangelog
                  Benchmark producing a changelog group for a changegroup.
    perfchangeset
                  (no help text available)
    perfctxfiles  (no help text available)
    perfdiffwd    Profile diff of working directory changes
    perfdirfoldmap
                  (no help text available)
    perfdirs      (no help text available)
    perfdirstate  (no help text available)
    perfdirstatedirs
                  (no help text available)
    perfdirstatefoldmap
                  (no help text available)
    perfdirstatewrite
                  (no help text available)
    perffncacheencode
                  (no help text available)
    perffncacheload
                  (no help text available)
    perffncachewrite
                  (no help text available)
    perfheads     (no help text available)
    perfindex     (no help text available)
    perfloadmarkers
                  benchmark the time to parse the on-disk markers for a repo
    perflog       (no help text available)
    perflookup    (no help text available)
    perflrucachedict
                  (no help text available)
    perfmanifest  (no help text available)
    perfmergecalculate
                  (no help text available)
    perfmoonwalk  benchmark walking the changelog backwards
    perfnodelookup
                  (no help text available)
    perfparents   (no help text available)
    perfpathcopies
                  (no help text available)
    perfrawfiles  (no help text available)
    perfrevlog    Benchmark reading a series of revisions from a revlog.
    perfrevlogchunks
                  Benchmark operations on revlog chunks.
    perfrevlogrevision
                  Benchmark obtaining a revlog revision.
    perfrevrange  (no help text available)
    perfrevset    benchmark the execution time of a revset
    perfstartup   (no help text available)
    perfstatus    (no help text available)
    perftags      (no help text available)
    perftemplating
                  (no help text available)
    perfvolatilesets
                  benchmark the computation of various volatile set
    perfwalk      (no help text available)
    perfwrite     microbenchmark ui.write
   
   (use 'hg help -v perfstatusext' to show built-in aliases and global options)
   $ hg perfaddremove
   $ hg perfancestors
   $ hg perfancestorset 2
   $ hg perfannotate a
   $ hg perfbdiff -c 1
   $ hg perfbdiff --alldata 1
   $ hg perfbranchmap
   $ hg perfcca
   $ hg perfchangegroupchangelog
   $ hg perfchangeset 2
   $ hg perfctxfiles 2
   $ hg perfdiffwd
   $ hg perfdirfoldmap
   $ hg perfdirs
   $ hg perfdirstate
   $ hg perfdirstatedirs
   $ hg perfdirstatefoldmap
   $ hg perfdirstatewrite
   $ hg perffncacheencode
   $ hg perffncacheload
   $ hg perffncachewrite
   $ hg perfheads
   $ hg perfindex
   $ hg perfloadmarkers
   $ hg perflog
   $ hg perflookup 2
   $ hg perflrucache
   $ hg perfmanifest 2
   $ hg perfmergecalculate -r 3
   $ hg perfmoonwalk
   $ hg perfnodelookup 2
   $ hg perfpathcopies 1 2
   $ hg perfrawfiles 2
   $ hg perfrevlog .hg/store/data/a.i
   $ hg perfrevlogrevision -m 0
   $ hg perfrevlogchunks -c
   $ hg perfrevrange
   $ hg perfrevset 'all()'
   $ hg perfstartup
   $ hg perfstatus
   $ hg perftags
   $ hg perftemplating
   $ hg perfvolatilesets
   $ hg perfwalk
   $ hg perfparents
 
 Check perf.py for historical portability
 
   $ cd "$TESTDIR/.."
 
   $ (hg files -r 1.2 glob:mercurial/*.c glob:mercurial/*.py;
   >  hg files -r tip glob:mercurial/*.c glob:mercurial/*.py) |
   > "$TESTDIR"/check-perf-code.py contrib/perf.py
-  contrib/perf.py:869:
+  contrib/perf.py:868:
    >             r.revision(r.node(x))
    don't convert rev to node before passing to revision(nodeorrev)
   [1]