diffutil: remove diffopts() in favor of diffallopts()

patch.diffopts() exists only for backward compatibility. We don't need it
in new module.

contrib/synthrepo.py

@@ -1,521 +1,521 b''
 # synthrepo.py - repo synthesis
 #
 # Copyright 2012 Facebook
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 '''synthesize structurally interesting change history
 
 This extension is useful for creating a repository with properties
 that are statistically similar to an existing repository. During
 analysis, a simple probability table is constructed from the history
 of an existing repository.  During synthesis, these properties are
 reconstructed.
 
 Properties that are analyzed and synthesized include the following:
 
 - Lines added or removed when an existing file is modified
 - Number and sizes of files added
 - Number of files removed
 - Line lengths
 - Topological distance to parent changeset(s)
 - Probability of a commit being a merge
 - Probability of a newly added file being added to a new directory
 - Interarrival time, and time zone, of commits
 - Number of files in each directory
 
 A few obvious properties that are not currently handled realistically:
 
 - Merges are treated as regular commits with two parents, which is not
   realistic
 - Modifications are not treated as operations on hunks of lines, but
   as insertions and deletions of randomly chosen single lines
 - Committer ID (always random)
 - Executability of files
 - Symlinks and binary files are ignored
 '''
 
 from __future__ import absolute_import
 import bisect
 import collections
 import itertools
 import json
 import os
 import random
 import sys
 import time
 
 from mercurial.i18n import _
 from mercurial.node import (
     nullid,
     nullrev,
     short,
 )
 from mercurial import (
     context,
     error,
     hg,
     patch,
     registrar,
     scmutil,
 )
 from mercurial.utils import (
     dateutil,
     diffutil,
 )
 
 # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
 testedwith = 'ships-with-hg-core'
 
 cmdtable = {}
 command = registrar.command(cmdtable)
 
 newfile = {'new fi', 'rename', 'copy f', 'copy t'}
 
 def zerodict():
     return collections.defaultdict(lambda: 0)
 
 def roundto(x, k):
     if x > k * 2:
         return int(round(x / float(k)) * k)
     return int(round(x))
 
 def parsegitdiff(lines):
     filename, mar, lineadd, lineremove = None, None, zerodict(), 0
     binary = False
     for line in lines:
         start = line[:6]
         if start == 'diff -':
             if filename:
                 yield filename, mar, lineadd, lineremove, binary
             mar, lineadd, lineremove, binary = 'm', zerodict(), 0, False
             filename = patch.gitre.match(line).group(1)
         elif start in newfile:
             mar = 'a'
         elif start == 'GIT bi':
             binary = True
         elif start == 'delete':
             mar = 'r'
         elif start:
             s = start[0]
             if s == '-' and not line.startswith('--- '):
                 lineremove += 1
             elif s == '+' and not line.startswith('+++ '):
                 lineadd[roundto(len(line) - 1, 5)] += 1
     if filename:
         yield filename, mar, lineadd, lineremove, binary
 
 @command('analyze',
          [('o', 'output', '', _('write output to given file'), _('FILE')),
           ('r', 'rev', [], _('analyze specified revisions'), _('REV'))],
          _('hg analyze'), optionalrepo=True)
 def analyze(ui, repo, *revs, **opts):
     '''create a simple model of a repository to use for later synthesis
 
     This command examines every changeset in the given range (or all
     of history if none are specified) and creates a simple statistical
     model of the history of the repository. It also measures the directory
     structure of the repository as checked out.
 
     The model is written out to a JSON file, and can be used by
     :hg:`synthesize` to create or augment a repository with synthetic
     commits that have a structure that is statistically similar to the
     analyzed repository.
     '''
     root = repo.root
     if not root.endswith(os.path.sep):
         root += os.path.sep
 
     revs = list(revs)
     revs.extend(opts['rev'])
     if not revs:
         revs = [':']
 
     output = opts['output']
     if not output:
         output = os.path.basename(root) + '.json'
 
     if output == '-':
         fp = sys.stdout
     else:
         fp = open(output, 'w')
 
     # Always obtain file counts of each directory in the given root directory.
     def onerror(e):
         ui.warn(_('error walking directory structure: %s\n') % e)
 
     dirs = {}
     rootprefixlen = len(root)
     for dirpath, dirnames, filenames in os.walk(root, onerror=onerror):
         dirpathfromroot = dirpath[rootprefixlen:]
         dirs[dirpathfromroot] = len(filenames)
         if '.hg' in dirnames:
             dirnames.remove('.hg')
 
     lineschanged = zerodict()
     children = zerodict()
     p1distance = zerodict()
     p2distance = zerodict()
     linesinfilesadded = zerodict()
     fileschanged = zerodict()
     filesadded = zerodict()
     filesremoved = zerodict()
     linelengths = zerodict()
     interarrival = zerodict()
     parents = zerodict()
     dirsadded = zerodict()
     tzoffset = zerodict()
 
     # If a mercurial repo is available, also model the commit history.
     if repo:
         revs = scmutil.revrange(repo, revs)
         revs.sort()
 
         progress = ui.makeprogress(_('analyzing'), unit=_('changesets'),
                                    total=len(revs))
         for i, rev in enumerate(revs):
             progress.update(i)
             ctx = repo[rev]
             pl = ctx.parents()
             pctx = pl[0]
             prev = pctx.rev()
             children[prev] += 1
             p1distance[rev - prev] += 1
             parents[len(pl)] += 1
             tzoffset[ctx.date()[1]] += 1
             if len(pl) > 1:
                 p2distance[rev - pl[1].rev()] += 1
             if prev == rev - 1:
                 lastctx = pctx
             else:
                 lastctx = repo[rev - 1]
             if lastctx.rev() != nullrev:
                 timedelta = ctx.date()[0] - lastctx.date()[0]
                 interarrival[roundto(timedelta, 300)] += 1
-            diffopts = diffutil.diffopts(ui, {'git': True})
+            diffopts = diffutil.diffallopts(ui, {'git': True})
             diff = sum((d.splitlines()
                        for d in ctx.diff(pctx, opts=diffopts)), [])
             fileadds, diradds, fileremoves, filechanges = 0, 0, 0, 0
             for filename, mar, lineadd, lineremove, isbin in parsegitdiff(diff):
                 if isbin:
                     continue
                 added = sum(lineadd.itervalues(), 0)
                 if mar == 'm':
                     if added and lineremove:
                         lineschanged[roundto(added, 5),
                                      roundto(lineremove, 5)] += 1
                         filechanges += 1
                 elif mar == 'a':
                     fileadds += 1
                     if '/' in filename:
                         filedir = filename.rsplit('/', 1)[0]
                         if filedir not in pctx.dirs():
                             diradds += 1
                     linesinfilesadded[roundto(added, 5)] += 1
                 elif mar == 'r':
                     fileremoves += 1
                 for length, count in lineadd.iteritems():
                     linelengths[length] += count
             fileschanged[filechanges] += 1
             filesadded[fileadds] += 1
             dirsadded[diradds] += 1
             filesremoved[fileremoves] += 1
         progress.complete()
 
     invchildren = zerodict()
 
     for rev, count in children.iteritems():
         invchildren[count] += 1
 
     if output != '-':
         ui.status(_('writing output to %s\n') % output)
 
     def pronk(d):
         return sorted(d.iteritems(), key=lambda x: x[1], reverse=True)
 
     json.dump({'revs': len(revs),
                'initdirs': pronk(dirs),
                'lineschanged': pronk(lineschanged),
                'children': pronk(invchildren),
                'fileschanged': pronk(fileschanged),
                'filesadded': pronk(filesadded),
                'linesinfilesadded': pronk(linesinfilesadded),
                'dirsadded': pronk(dirsadded),
                'filesremoved': pronk(filesremoved),
                'linelengths': pronk(linelengths),
                'parents': pronk(parents),
                'p1distance': pronk(p1distance),
                'p2distance': pronk(p2distance),
                'interarrival': pronk(interarrival),
                'tzoffset': pronk(tzoffset),
                },
               fp)
     fp.close()
 
 @command('synthesize',
          [('c', 'count', 0, _('create given number of commits'), _('COUNT')),
           ('', 'dict', '', _('path to a dictionary of words'), _('FILE')),
           ('', 'initfiles', 0, _('initial file count to create'), _('COUNT'))],
          _('hg synthesize [OPTION].. DESCFILE'))
 def synthesize(ui, repo, descpath, **opts):
     '''synthesize commits based on a model of an existing repository
 
     The model must have been generated by :hg:`analyze`. Commits will
     be generated randomly according to the probabilities described in
     the model. If --initfiles is set, the repository will be seeded with
     the given number files following the modeled repository's directory
     structure.
 
     When synthesizing new content, commit descriptions, and user
     names, words will be chosen randomly from a dictionary that is
     presumed to contain one word per line. Use --dict to specify the
     path to an alternate dictionary to use.
     '''
     try:
         fp = hg.openpath(ui, descpath)
     except Exception as err:
         raise error.Abort('%s: %s' % (descpath, err[0].strerror))
     desc = json.load(fp)
     fp.close()
 
     def cdf(l):
         if not l:
             return [], []
         vals, probs = zip(*sorted(l, key=lambda x: x[1], reverse=True))
         t = float(sum(probs, 0))
         s, cdfs = 0, []
         for v in probs:
             s += v
             cdfs.append(s / t)
         return vals, cdfs
 
     lineschanged = cdf(desc['lineschanged'])
     fileschanged = cdf(desc['fileschanged'])
     filesadded = cdf(desc['filesadded'])
     dirsadded = cdf(desc['dirsadded'])
     filesremoved = cdf(desc['filesremoved'])
     linelengths = cdf(desc['linelengths'])
     parents = cdf(desc['parents'])
     p1distance = cdf(desc['p1distance'])
     p2distance = cdf(desc['p2distance'])
     interarrival = cdf(desc['interarrival'])
     linesinfilesadded = cdf(desc['linesinfilesadded'])
     tzoffset = cdf(desc['tzoffset'])
 
     dictfile = opts.get('dict') or '/usr/share/dict/words'
     try:
         fp = open(dictfile, 'rU')
     except IOError as err:
         raise error.Abort('%s: %s' % (dictfile, err.strerror))
     words = fp.read().splitlines()
     fp.close()
 
     initdirs = {}
     if desc['initdirs']:
         for k, v in desc['initdirs']:
             initdirs[k.encode('utf-8').replace('.hg', '_hg')] = v
         initdirs = renamedirs(initdirs, words)
     initdirscdf = cdf(initdirs)
 
     def pick(cdf):
         return cdf[0][bisect.bisect_left(cdf[1], random.random())]
 
     def pickpath():
         return os.path.join(pick(initdirscdf), random.choice(words))
 
     def makeline(minimum=0):
         total = max(minimum, pick(linelengths))
         c, l = 0, []
         while c < total:
             w = random.choice(words)
             c += len(w) + 1
             l.append(w)
         return ' '.join(l)
 
     wlock = repo.wlock()
     lock = repo.lock()
 
     nevertouch = {'.hgsub', '.hgignore', '.hgtags'}
 
     _synthesizing = _('synthesizing')
     _files = _('initial files')
     _changesets = _('changesets')
 
     # Synthesize a single initial revision adding files to the repo according
     # to the modeled directory structure.
     initcount = int(opts['initfiles'])
     if initcount and initdirs:
         pctx = repo[None].parents()[0]
         dirs = set(pctx.dirs())
         files = {}
 
         def validpath(path):
             # Don't pick filenames which are already directory names.
             if path in dirs:
                 return False
             # Don't pick directories which were used as file names.
             while path:
                 if path in files:
                     return False
                 path = os.path.dirname(path)
             return True
 
         progress = ui.makeprogress(_synthesizing, unit=_files, total=initcount)
         for i in xrange(0, initcount):
             progress.update(i)
 
             path = pickpath()
             while not validpath(path):
                 path = pickpath()
             data = '%s contents\n' % path
             files[path] = data
             dir = os.path.dirname(path)
             while dir and dir not in dirs:
                 dirs.add(dir)
                 dir = os.path.dirname(dir)
 
         def filectxfn(repo, memctx, path):
             return context.memfilectx(repo, memctx, path, files[path])
 
         progress.complete()
         message = 'synthesized wide repo with %d files' % (len(files),)
         mc = context.memctx(repo, [pctx.node(), nullid], message,
                             files, filectxfn, ui.username(),
                             '%d %d' % dateutil.makedate())
         initnode = mc.commit()
         if ui.debugflag:
             hexfn = hex
         else:
             hexfn = short
         ui.status(_('added commit %s with %d files\n')
                   % (hexfn(initnode), len(files)))
 
     # Synthesize incremental revisions to the repository, adding repo depth.
     count = int(opts['count'])
     heads = set(map(repo.changelog.rev, repo.heads()))
     progress = ui.makeprogress(_synthesizing, unit=_changesets, total=count)
     for i in xrange(count):
         progress.update(i)
 
         node = repo.changelog.node
         revs = len(repo)
 
         def pickhead(heads, distance):
             if heads:
                 lheads = sorted(heads)
                 rev = revs - min(pick(distance), revs)
                 if rev < lheads[-1]:
                     rev = lheads[bisect.bisect_left(lheads, rev)]
                 else:
                     rev = lheads[-1]
                 return rev, node(rev)
             return nullrev, nullid
 
         r1 = revs - min(pick(p1distance), revs)
         p1 = node(r1)
 
         # the number of heads will grow without bound if we use a pure
         # model, so artificially constrain their proliferation
         toomanyheads = len(heads) > random.randint(1, 20)
         if p2distance[0] and (pick(parents) == 2 or toomanyheads):
             r2, p2 = pickhead(heads.difference([r1]), p2distance)
         else:
             r2, p2 = nullrev, nullid
 
         pl = [p1, p2]
         pctx = repo[r1]
         mf = pctx.manifest()
         mfk = mf.keys()
         changes = {}
         if mfk:
             for __ in xrange(pick(fileschanged)):
                 for __ in xrange(10):
                     fctx = pctx.filectx(random.choice(mfk))
                     path = fctx.path()
                     if not (path in nevertouch or fctx.isbinary() or
                             'l' in fctx.flags()):
                         break
                 lines = fctx.data().splitlines()
                 add, remove = pick(lineschanged)
                 for __ in xrange(remove):
                     if not lines:
                         break
                     del lines[random.randrange(0, len(lines))]
                 for __ in xrange(add):
                     lines.insert(random.randint(0, len(lines)), makeline())
                 path = fctx.path()
                 changes[path] = '\n'.join(lines) + '\n'
             for __ in xrange(pick(filesremoved)):
                 path = random.choice(mfk)
                 for __ in xrange(10):
                     path = random.choice(mfk)
                     if path not in changes:
                         break
         if filesadded:
             dirs = list(pctx.dirs())
             dirs.insert(0, '')
         for __ in xrange(pick(filesadded)):
             pathstr = ''
             while pathstr in dirs:
                 path = [random.choice(dirs)]
                 if pick(dirsadded):
                     path.append(random.choice(words))
                 path.append(random.choice(words))
                 pathstr = '/'.join(filter(None, path))
             data = '\n'.join(makeline()
                              for __ in xrange(pick(linesinfilesadded))) + '\n'
             changes[pathstr] = data
         def filectxfn(repo, memctx, path):
             if path not in changes:
                 return None
             return context.memfilectx(repo, memctx, path, changes[path])
         if not changes:
             continue
         if revs:
             date = repo['tip'].date()[0] + pick(interarrival)
         else:
             date = time.time() - (86400 * count)
         # dates in mercurial must be positive, fit in 32-bit signed integers.
         date = min(0x7fffffff, max(0, date))
         user = random.choice(words) + '@' + random.choice(words)
         mc = context.memctx(repo, pl, makeline(minimum=2),
                             sorted(changes),
                             filectxfn, user, '%d %d' % (date, pick(tzoffset)))
         newnode = mc.commit()
         heads.add(repo.changelog.rev(newnode))
         heads.discard(r1)
         heads.discard(r2)
     progress.complete()
 
     lock.release()
     wlock.release()
 
 def renamedirs(dirs, words):
     '''Randomly rename the directory names in the per-dir file count dict.'''
     wordgen = itertools.cycle(words)
     replacements = {'': ''}
     def rename(dirpath):
         '''Recursively rename the directory and all path prefixes.
 
         The mapping from path to renamed path is stored for all path prefixes
         as in dynamic programming, ensuring linear runtime and consistent
         renaming regardless of iteration order through the model.
         '''
         if dirpath in replacements:
             return replacements[dirpath]
         head, _ = os.path.split(dirpath)
         if head:
             head = rename(head)
         else:
             head = ''
         renamed = os.path.join(head, next(wordgen))
         replacements[dirpath] = renamed
         return renamed
     result = []
     for dirpath, count in dirs.iteritems():
         result.append([rename(dirpath.lstrip(os.sep)), count])
     return result

mercurial/obsutil.py

@@ -1,980 +1,980 b''
 # obsutil.py - utility functions for obsolescence
 #
 # Copyright 2017 Boris Feld <[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
 
 from .i18n import _
 from . import (
     node as nodemod,
     phases,
     util,
 )
 from .utils import (
     dateutil,
     diffutil,
 )
 
 ### obsolescence marker flag
 
 ## bumpedfix flag
 #
 # When a changeset A' succeed to a changeset A which became public, we call A'
 # "bumped" because it's a successors of a public changesets
 #
 # o    A' (bumped)
 # |`:
 # | o  A
 # |/
 # o    Z
 #
 # The way to solve this situation is to create a new changeset Ad as children
 # of A. This changeset have the same content than A'. So the diff from A to A'
 # is the same than the diff from A to Ad. Ad is marked as a successors of A'
 #
 # o   Ad
 # |`:
 # | x A'
 # |'|
 # o | A
 # |/
 # o Z
 #
 # But by transitivity Ad is also a successors of A. To avoid having Ad marked
 # as bumped too, we add the `bumpedfix` flag to the marker. <A', (Ad,)>.
 # This flag mean that the successors express the changes between the public and
 # bumped version and fix the situation, breaking the transitivity of
 # "bumped" here.
 bumpedfix = 1
 usingsha256 = 2
 
 class marker(object):
     """Wrap obsolete marker raw data"""
 
     def __init__(self, repo, data):
         # the repo argument will be used to create changectx in later version
         self._repo = repo
         self._data = data
         self._decodedmeta = None
 
     def __hash__(self):
         return hash(self._data)
 
     def __eq__(self, other):
         if type(other) != type(self):
             return False
         return self._data == other._data
 
     def prednode(self):
         """Predecessor changeset node identifier"""
         return self._data[0]
 
     def succnodes(self):
         """List of successor changesets node identifiers"""
         return self._data[1]
 
     def parentnodes(self):
         """Parents of the predecessors (None if not recorded)"""
         return self._data[5]
 
     def metadata(self):
         """Decoded metadata dictionary"""
         return dict(self._data[3])
 
     def date(self):
         """Creation date as (unixtime, offset)"""
         return self._data[4]
 
     def flags(self):
         """The flags field of the marker"""
         return self._data[2]
 
 def getmarkers(repo, nodes=None, exclusive=False):
     """returns markers known in a repository
 
     If <nodes> is specified, only markers "relevant" to those nodes are are
     returned"""
     if nodes is None:
         rawmarkers = repo.obsstore
     elif exclusive:
         rawmarkers = exclusivemarkers(repo, nodes)
     else:
         rawmarkers = repo.obsstore.relevantmarkers(nodes)
 
     for markerdata in rawmarkers:
         yield marker(repo, markerdata)
 
 def closestpredecessors(repo, nodeid):
     """yield the list of next predecessors pointing on visible changectx nodes
 
     This function respect the repoview filtering, filtered revision will be
     considered missing.
     """
 
     precursors = repo.obsstore.predecessors
     stack = [nodeid]
     seen = set(stack)
 
     while stack:
         current = stack.pop()
         currentpreccs = precursors.get(current, ())
 
         for prec in currentpreccs:
             precnodeid = prec[0]
 
             # Basic cycle protection
             if precnodeid in seen:
                 continue
             seen.add(precnodeid)
 
             if precnodeid in repo:
                 yield precnodeid
             else:
                 stack.append(precnodeid)
 
 def allpredecessors(obsstore, nodes, ignoreflags=0):
     """Yield node for every precursors of <nodes>.
 
     Some precursors may be unknown locally.
 
     This is a linear yield unsuited to detecting folded changesets. It includes
     initial nodes too."""
 
     remaining = set(nodes)
     seen = set(remaining)
     while remaining:
         current = remaining.pop()
         yield current
         for mark in obsstore.predecessors.get(current, ()):
             # ignore marker flagged with specified flag
             if mark[2] & ignoreflags:
                 continue
             suc = mark[0]
             if suc not in seen:
                 seen.add(suc)
                 remaining.add(suc)
 
 def allsuccessors(obsstore, nodes, ignoreflags=0):
     """Yield node for every successor of <nodes>.
 
     Some successors may be unknown locally.
 
     This is a linear yield unsuited to detecting split changesets. It includes
     initial nodes too."""
     remaining = set(nodes)
     seen = set(remaining)
     while remaining:
         current = remaining.pop()
         yield current
         for mark in obsstore.successors.get(current, ()):
             # ignore marker flagged with specified flag
             if mark[2] & ignoreflags:
                 continue
             for suc in mark[1]:
                 if suc not in seen:
                     seen.add(suc)
                     remaining.add(suc)
 
 def _filterprunes(markers):
     """return a set with no prune markers"""
     return set(m for m in markers if m[1])
 
 def exclusivemarkers(repo, nodes):
     """set of markers relevant to "nodes" but no other locally-known nodes
 
     This function compute the set of markers "exclusive" to a locally-known
     node. This means we walk the markers starting from <nodes> until we reach a
     locally-known precursors outside of <nodes>. Element of <nodes> with
     locally-known successors outside of <nodes> are ignored (since their
     precursors markers are also relevant to these successors).
 
     For example:
 
         # (A0 rewritten as A1)
         #
         # A0 <-1- A1 # Marker "1" is exclusive to A1
 
         or
 
         # (A0 rewritten as AX; AX rewritten as A1; AX is unkown locally)
         #
         # <-1- A0 <-2- AX <-3- A1 # Marker "2,3" are exclusive to A1
 
         or
 
         # (A0 has unknown precursors, A0 rewritten as A1 and A2 (divergence))
         #
         #          <-2- A1 # Marker "2" is exclusive to A0,A1
         #        /
         # <-1- A0
         #        \
         #         <-3- A2 # Marker "3" is exclusive to A0,A2
         #
         # in addition:
         #
         #  Markers "2,3" are exclusive to A1,A2
         #  Markers "1,2,3" are exclusive to A0,A1,A2
 
         See test/test-obsolete-bundle-strip.t for more examples.
 
     An example usage is strip. When stripping a changeset, we also want to
     strip the markers exclusive to this changeset. Otherwise we would have
     "dangling"" obsolescence markers from its precursors: Obsolescence markers
     marking a node as obsolete without any successors available locally.
 
     As for relevant markers, the prune markers for children will be followed.
     Of course, they will only be followed if the pruned children is
     locally-known. Since the prune markers are relevant to the pruned node.
     However, while prune markers are considered relevant to the parent of the
     pruned changesets, prune markers for locally-known changeset (with no
     successors) are considered exclusive to the pruned nodes. This allows
     to strip the prune markers (with the rest of the exclusive chain) alongside
     the pruned changesets.
     """
     # running on a filtered repository would be dangerous as markers could be
     # reported as exclusive when they are relevant for other filtered nodes.
     unfi = repo.unfiltered()
 
     # shortcut to various useful item
     nm = unfi.changelog.nodemap
     precursorsmarkers = unfi.obsstore.predecessors
     successormarkers = unfi.obsstore.successors
     childrenmarkers = unfi.obsstore.children
 
     # exclusive markers (return of the function)
     exclmarkers = set()
     # we need fast membership testing
     nodes = set(nodes)
     # looking for head in the obshistory
     #
     # XXX we are ignoring all issues in regard with cycle for now.
     stack = [n for n in nodes if not _filterprunes(successormarkers.get(n, ()))]
     stack.sort()
     # nodes already stacked
     seennodes = set(stack)
     while stack:
         current = stack.pop()
         # fetch precursors markers
         markers = list(precursorsmarkers.get(current, ()))
         # extend the list with prune markers
         for mark in successormarkers.get(current, ()):
             if not mark[1]:
                 markers.append(mark)
         # and markers from children (looking for prune)
         for mark in childrenmarkers.get(current, ()):
             if not mark[1]:
                 markers.append(mark)
         # traverse the markers
         for mark in markers:
             if mark in exclmarkers:
                 # markers already selected
                 continue
 
             # If the markers is about the current node, select it
             #
             # (this delay the addition of markers from children)
             if mark[1] or mark[0] == current:
                 exclmarkers.add(mark)
 
             # should we keep traversing through the precursors?
             prec = mark[0]
 
             # nodes in the stack or already processed
             if prec in seennodes:
                 continue
 
             # is this a locally known node ?
             known = prec in nm
             # if locally-known and not in the <nodes> set the traversal
             # stop here.
             if known and prec not in nodes:
                 continue
 
             # do not keep going if there are unselected markers pointing to this
             # nodes. If we end up traversing these unselected markers later the
             # node will be taken care of at that point.
             precmarkers = _filterprunes(successormarkers.get(prec))
             if precmarkers.issubset(exclmarkers):
                 seennodes.add(prec)
                 stack.append(prec)
 
     return exclmarkers
 
 def foreground(repo, nodes):
     """return all nodes in the "foreground" of other node
 
     The foreground of a revision is anything reachable using parent -> children
     or precursor -> successor relation. It is very similar to "descendant" but
     augmented with obsolescence information.
 
     Beware that possible obsolescence cycle may result if complex situation.
     """
     repo = repo.unfiltered()
     foreground = set(repo.set('%ln::', nodes))
     if repo.obsstore:
         # We only need this complicated logic if there is obsolescence
         # XXX will probably deserve an optimised revset.
         nm = repo.changelog.nodemap
         plen = -1
         # compute the whole set of successors or descendants
         while len(foreground) != plen:
             plen = len(foreground)
             succs = set(c.node() for c in foreground)
             mutable = [c.node() for c in foreground if c.mutable()]
             succs.update(allsuccessors(repo.obsstore, mutable))
             known = (n for n in succs if n in nm)
             foreground = set(repo.set('%ln::', known))
     return set(c.node() for c in foreground)
 
 # effectflag field
 #
 # Effect-flag is a 1-byte bit field used to store what changed between a
 # changeset and its successor(s).
 #
 # The effect flag is stored in obs-markers metadata while we iterate on the
 # information design. That's why we have the EFFECTFLAGFIELD. If we come up
 # with an incompatible design for effect flag, we can store a new design under
 # another field name so we don't break readers. We plan to extend the existing
 # obsmarkers bit-field when the effect flag design will be stabilized.
 #
 # The effect-flag is placed behind an experimental flag
 # `effect-flags` set to off by default.
 #
 
 EFFECTFLAGFIELD = "ef1"
 
 DESCCHANGED = 1 << 0 # action changed the description
 METACHANGED = 1 << 1 # action change the meta
 DIFFCHANGED = 1 << 3 # action change diff introduced by the changeset
 PARENTCHANGED = 1 << 2 # action change the parent
 USERCHANGED = 1 << 4 # the user changed
 DATECHANGED = 1 << 5 # the date changed
 BRANCHCHANGED = 1 << 6 # the branch changed
 
 METABLACKLIST = [
     re.compile('^branch$'),
     re.compile('^.*-source$'),
     re.compile('^.*_source$'),
     re.compile('^source$'),
 ]
 
 def metanotblacklisted(metaitem):
     """ Check that the key of a meta item (extrakey, extravalue) does not
     match at least one of the blacklist pattern
     """
     metakey = metaitem[0]
 
     return not any(pattern.match(metakey) for pattern in METABLACKLIST)
 
 def _prepare_hunk(hunk):
     """Drop all information but the username and patch"""
     cleanhunk = []
     for line in hunk.splitlines():
         if line.startswith(b'# User') or not line.startswith(b'#'):
             if line.startswith(b'@@'):
                 line = b'@@\n'
             cleanhunk.append(line)
     return cleanhunk
 
 def _getdifflines(iterdiff):
     """return a cleaned up lines"""
     lines = next(iterdiff, None)
 
     if lines is None:
         return lines
 
     return _prepare_hunk(lines)
 
 def _cmpdiff(leftctx, rightctx):
     """return True if both ctx introduce the "same diff"
 
     This is a first and basic implementation, with many shortcoming.
     """
-    diffopts = diffutil.diffopts(leftctx.repo().ui, {'git': True})
+    diffopts = diffutil.diffallopts(leftctx.repo().ui, {'git': True})
     # Leftctx or right ctx might be filtered, so we need to use the contexts
     # with an unfiltered repository to safely compute the diff
     leftunfi = leftctx._repo.unfiltered()[leftctx.rev()]
     leftdiff = leftunfi.diff(opts=diffopts)
     rightunfi = rightctx._repo.unfiltered()[rightctx.rev()]
     rightdiff = rightunfi.diff(opts=diffopts)
 
     left, right = (0, 0)
     while None not in (left, right):
         left = _getdifflines(leftdiff)
         right = _getdifflines(rightdiff)
 
         if left != right:
             return False
     return True
 
 def geteffectflag(relation):
     """ From an obs-marker relation, compute what changed between the
     predecessor and the successor.
     """
     effects = 0
 
     source = relation[0]
 
     for changectx in relation[1]:
         # Check if description has changed
         if changectx.description() != source.description():
             effects |= DESCCHANGED
 
         # Check if user has changed
         if changectx.user() != source.user():
             effects |= USERCHANGED
 
         # Check if date has changed
         if changectx.date() != source.date():
             effects |= DATECHANGED
 
         # Check if branch has changed
         if changectx.branch() != source.branch():
             effects |= BRANCHCHANGED
 
         # Check if at least one of the parent has changed
         if changectx.parents() != source.parents():
             effects |= PARENTCHANGED
 
         # Check if other meta has changed
         changeextra = changectx.extra().items()
         ctxmeta = list(filter(metanotblacklisted, changeextra))
 
         sourceextra = source.extra().items()
         srcmeta = list(filter(metanotblacklisted, sourceextra))
 
         if ctxmeta != srcmeta:
             effects |= METACHANGED
 
         # Check if the diff has changed
         if not _cmpdiff(source, changectx):
             effects |= DIFFCHANGED
 
     return effects
 
 def getobsoleted(repo, tr):
     """return the set of pre-existing revisions obsoleted by a transaction"""
     torev = repo.unfiltered().changelog.nodemap.get
     phase = repo._phasecache.phase
     succsmarkers = repo.obsstore.successors.get
     public = phases.public
     addedmarkers = tr.changes.get('obsmarkers')
     addedrevs = tr.changes.get('revs')
     seenrevs = set()
     obsoleted = set()
     for mark in addedmarkers:
         node = mark[0]
         rev = torev(node)
         if rev is None or rev in seenrevs or rev in addedrevs:
             continue
         seenrevs.add(rev)
         if phase(repo, rev) == public:
             continue
         if set(succsmarkers(node) or []).issubset(addedmarkers):
             obsoleted.add(rev)
     return obsoleted
 
 class _succs(list):
     """small class to represent a successors with some metadata about it"""
 
     def __init__(self, *args, **kwargs):
         super(_succs, self).__init__(*args, **kwargs)
         self.markers = set()
 
     def copy(self):
         new = _succs(self)
         new.markers = self.markers.copy()
         return new
 
     @util.propertycache
     def _set(self):
         # immutable
         return set(self)
 
     def canmerge(self, other):
         return self._set.issubset(other._set)
 
 def successorssets(repo, initialnode, closest=False, cache=None):
     """Return set of all latest successors of initial nodes
 
     The successors set of a changeset A are the group of revisions that succeed
     A. It succeeds A as a consistent whole, each revision being only a partial
     replacement. By default, the successors set contains non-obsolete
     changesets only, walking the obsolescence graph until reaching a leaf. If
     'closest' is set to True, closest successors-sets are return (the
     obsolescence walk stops on known changesets).
 
     This function returns the full list of successor sets which is why it
     returns a list of tuples and not just a single tuple. Each tuple is a valid
     successors set. Note that (A,) may be a valid successors set for changeset A
     (see below).
 
     In most cases, a changeset A will have a single element (e.g. the changeset
     A is replaced by A') in its successors set. Though, it is also common for a
     changeset A to have no elements in its successor set (e.g. the changeset
     has been pruned). Therefore, the returned list of successors sets will be
     [(A',)] or [], respectively.
 
     When a changeset A is split into A' and B', however, it will result in a
     successors set containing more than a single element, i.e. [(A',B')].
     Divergent changesets will result in multiple successors sets, i.e. [(A',),
     (A'')].
 
     If a changeset A is not obsolete, then it will conceptually have no
     successors set. To distinguish this from a pruned changeset, the successor
     set will contain itself only, i.e. [(A,)].
 
     Finally, final successors unknown locally are considered to be pruned
     (pruned: obsoleted without any successors). (Final: successors not affected
     by markers).
 
     The 'closest' mode respect the repoview filtering. For example, without
     filter it will stop at the first locally known changeset, with 'visible'
     filter it will stop on visible changesets).
 
     The optional `cache` parameter is a dictionary that may contains
     precomputed successors sets. It is meant to reuse the computation of a
     previous call to `successorssets` when multiple calls are made at the same
     time. The cache dictionary is updated in place. The caller is responsible
     for its life span. Code that makes multiple calls to `successorssets`
     *should* use this cache mechanism or risk a performance hit.
 
     Since results are different depending of the 'closest' most, the same cache
     cannot be reused for both mode.
     """
 
     succmarkers = repo.obsstore.successors
 
     # Stack of nodes we search successors sets for
     toproceed = [initialnode]
     # set version of above list for fast loop detection
     # element added to "toproceed" must be added here
     stackedset = set(toproceed)
     if cache is None:
         cache = {}
 
     # This while loop is the flattened version of a recursive search for
     # successors sets
     #
     # def successorssets(x):
     #    successors = directsuccessors(x)
     #    ss = [[]]
     #    for succ in directsuccessors(x):
     #        # product as in itertools cartesian product
     #        ss = product(ss, successorssets(succ))
     #    return ss
     #
     # But we can not use plain recursive calls here:
     # - that would blow the python call stack
     # - obsolescence markers may have cycles, we need to handle them.
     #
     # The `toproceed` list act as our call stack. Every node we search
     # successors set for are stacked there.
     #
     # The `stackedset` is set version of this stack used to check if a node is
     # already stacked. This check is used to detect cycles and prevent infinite
     # loop.
     #
     # successors set of all nodes are stored in the `cache` dictionary.
     #
     # After this while loop ends we use the cache to return the successors sets
     # for the node requested by the caller.
     while toproceed:
         # Every iteration tries to compute the successors sets of the topmost
         # node of the stack: CURRENT.
         #
         # There are four possible outcomes:
         #
         # 1) We already know the successors sets of CURRENT:
         #    -> mission accomplished, pop it from the stack.
         # 2) Stop the walk:
         #    default case: Node is not obsolete
         #    closest case: Node is known at this repo filter level
         #      -> the node is its own successors sets. Add it to the cache.
         # 3) We do not know successors set of direct successors of CURRENT:
         #    -> We add those successors to the stack.
         # 4) We know successors sets of all direct successors of CURRENT:
         #    -> We can compute CURRENT successors set and add it to the
         #       cache.
         #
         current = toproceed[-1]
 
         # case 2 condition is a bit hairy because of closest,
         # we compute it on its own
         case2condition =  ((current not in succmarkers)
                            or (closest and current != initialnode
                                and current in repo))
 
         if current in cache:
             # case (1): We already know the successors sets
             stackedset.remove(toproceed.pop())
         elif case2condition:
             # case (2): end of walk.
             if current in repo:
                 # We have a valid successors.
                 cache[current] = [_succs((current,))]
             else:
                 # Final obsolete version is unknown locally.
                 # Do not count that as a valid successors
                 cache[current] = []
         else:
             # cases (3) and (4)
             #
             # We proceed in two phases. Phase 1 aims to distinguish case (3)
             # from case (4):
             #
             #     For each direct successors of CURRENT, we check whether its
             #     successors sets are known. If they are not, we stack the
             #     unknown node and proceed to the next iteration of the while
             #     loop. (case 3)
             #
             #     During this step, we may detect obsolescence cycles: a node
             #     with unknown successors sets but already in the call stack.
             #     In such a situation, we arbitrary set the successors sets of
             #     the node to nothing (node pruned) to break the cycle.
             #
             #     If no break was encountered we proceed to phase 2.
             #
             # Phase 2 computes successors sets of CURRENT (case 4); see details
             # in phase 2 itself.
             #
             # Note the two levels of iteration in each phase.
             # - The first one handles obsolescence markers using CURRENT as
             #   precursor (successors markers of CURRENT).
             #
             #   Having multiple entry here means divergence.
             #
             # - The second one handles successors defined in each marker.
             #
             #   Having none means pruned node, multiple successors means split,
             #   single successors are standard replacement.
             #
             for mark in sorted(succmarkers[current]):
                 for suc in mark[1]:
                     if suc not in cache:
                         if suc in stackedset:
                             # cycle breaking
                             cache[suc] = []
                         else:
                             # case (3) If we have not computed successors sets
                             # of one of those successors we add it to the
                             # `toproceed` stack and stop all work for this
                             # iteration.
                             toproceed.append(suc)
                             stackedset.add(suc)
                             break
                 else:
                     continue
                 break
             else:
                 # case (4): we know all successors sets of all direct
                 # successors
                 #
                 # Successors set contributed by each marker depends on the
                 # successors sets of all its "successors" node.
                 #
                 # Each different marker is a divergence in the obsolescence
                 # history. It contributes successors sets distinct from other
                 # markers.
                 #
                 # Within a marker, a successor may have divergent successors
                 # sets. In such a case, the marker will contribute multiple
                 # divergent successors sets. If multiple successors have
                 # divergent successors sets, a Cartesian product is used.
                 #
                 # At the end we post-process successors sets to remove
                 # duplicated entry and successors set that are strict subset of
                 # another one.
                 succssets = []
                 for mark in sorted(succmarkers[current]):
                     # successors sets contributed by this marker
                     base = _succs()
                     base.markers.add(mark)
                     markss = [base]
                     for suc in mark[1]:
                         # cardinal product with previous successors
                         productresult = []
                         for prefix in markss:
                             for suffix in cache[suc]:
                                 newss = prefix.copy()
                                 newss.markers.update(suffix.markers)
                                 for part in suffix:
                                     # do not duplicated entry in successors set
                                     # first entry wins.
                                     if part not in newss:
                                         newss.append(part)
                                 productresult.append(newss)
                         markss = productresult
                     succssets.extend(markss)
                 # remove duplicated and subset
                 seen = []
                 final = []
                 candidates = sorted((s for s in succssets if s),
                                     key=len, reverse=True)
                 for cand in candidates:
                     for seensuccs in seen:
                         if cand.canmerge(seensuccs):
                             seensuccs.markers.update(cand.markers)
                             break
                     else:
                         final.append(cand)
                         seen.append(cand)
                 final.reverse() # put small successors set first
                 cache[current] = final
     return cache[initialnode]
 
 def successorsandmarkers(repo, ctx):
     """compute the raw data needed for computing obsfate
     Returns a list of dict, one dict per successors set
     """
     if not ctx.obsolete():
         return None
 
     ssets = successorssets(repo, ctx.node(), closest=True)
 
     # closestsuccessors returns an empty list for pruned revisions, remap it
     # into a list containing an empty list for future processing
     if ssets == []:
         ssets = [[]]
 
     # Try to recover pruned markers
     succsmap = repo.obsstore.successors
     fullsuccessorsets = [] # successor set + markers
     for sset in ssets:
         if sset:
             fullsuccessorsets.append(sset)
         else:
             # successorsset return an empty set() when ctx or one of its
             # successors is pruned.
             # In this case, walk the obs-markers tree again starting with ctx
             # and find the relevant pruning obs-makers, the ones without
             # successors.
             # Having these markers allow us to compute some information about
             # its fate, like who pruned this changeset and when.
 
             # XXX we do not catch all prune markers (eg rewritten then pruned)
             # (fix me later)
             foundany = False
             for mark in succsmap.get(ctx.node(), ()):
                 if not mark[1]:
                     foundany = True
                     sset = _succs()
                     sset.markers.add(mark)
                     fullsuccessorsets.append(sset)
             if not foundany:
                 fullsuccessorsets.append(_succs())
 
     values = []
     for sset in fullsuccessorsets:
         values.append({'successors': sset, 'markers': sset.markers})
 
     return values
 
 def _getobsfate(successorssets):
     """ Compute a changeset obsolescence fate based on its successorssets.
     Successors can be the tipmost ones or the immediate ones. This function
     return values are not meant to be shown directly to users, it is meant to
     be used by internal functions only.
     Returns one fate from the following values:
     - pruned
     - diverged
     - superseded
     - superseded_split
     """
 
     if len(successorssets) == 0:
         # The commit has been pruned
         return 'pruned'
     elif len(successorssets) > 1:
         return 'diverged'
     else:
         # No divergence, only one set of successors
         successors = successorssets[0]
 
         if len(successors) == 1:
             return 'superseded'
         else:
             return 'superseded_split'
 
 def obsfateverb(successorset, markers):
     """ Return the verb summarizing the successorset and potentially using
     information from the markers
     """
     if not successorset:
         verb = 'pruned'
     elif len(successorset) == 1:
         verb = 'rewritten'
     else:
         verb = 'split'
     return verb
 
 def markersdates(markers):
     """returns the list of dates for a list of markers
     """
     return [m[4] for m in markers]
 
 def markersusers(markers):
     """ Returns a sorted list of markers users without duplicates
     """
     markersmeta = [dict(m[3]) for m in markers]
     users = set(meta.get('user') for meta in markersmeta if meta.get('user'))
 
     return sorted(users)
 
 def markersoperations(markers):
     """ Returns a sorted list of markers operations without duplicates
     """
     markersmeta = [dict(m[3]) for m in markers]
     operations = set(meta.get('operation') for meta in markersmeta
                      if meta.get('operation'))
 
     return sorted(operations)
 
 def obsfateprinter(ui, repo, successors, markers, formatctx):
     """ Build a obsfate string for a single successorset using all obsfate
     related function defined in obsutil
     """
     quiet = ui.quiet
     verbose = ui.verbose
     normal = not verbose and not quiet
 
     line = []
 
     # Verb
     line.append(obsfateverb(successors, markers))
 
     # Operations
     operations = markersoperations(markers)
     if operations:
         line.append(" using %s" % ", ".join(operations))
 
     # Successors
     if successors:
         fmtsuccessors = [formatctx(repo[succ]) for succ in successors]
         line.append(" as %s" % ", ".join(fmtsuccessors))
 
     # Users
     users = markersusers(markers)
     # Filter out current user in not verbose mode to reduce amount of
     # information
     if not verbose:
         currentuser = ui.username(acceptempty=True)
         if len(users) == 1 and currentuser in users:
             users = None
 
     if (verbose or normal) and users:
         line.append(" by %s" % ", ".join(users))
 
     # Date
     dates = markersdates(markers)
 
     if dates and verbose:
         min_date = min(dates)
         max_date = max(dates)
 
         if min_date == max_date:
             fmtmin_date = dateutil.datestr(min_date, '%Y-%m-%d %H:%M %1%2')
             line.append(" (at %s)" % fmtmin_date)
         else:
             fmtmin_date = dateutil.datestr(min_date, '%Y-%m-%d %H:%M %1%2')
             fmtmax_date = dateutil.datestr(max_date, '%Y-%m-%d %H:%M %1%2')
             line.append(" (between %s and %s)" % (fmtmin_date, fmtmax_date))
 
     return "".join(line)
 
 
 filteredmsgtable = {
     "pruned": _("hidden revision '%s' is pruned"),
     "diverged": _("hidden revision '%s' has diverged"),
     "superseded": _("hidden revision '%s' was rewritten as: %s"),
     "superseded_split": _("hidden revision '%s' was split as: %s"),
     "superseded_split_several": _("hidden revision '%s' was split as: %s and "
                                   "%d more"),
 }
 
 def _getfilteredreason(repo, changeid, ctx):
     """return a human-friendly string on why a obsolete changeset is hidden
     """
     successors = successorssets(repo, ctx.node())
     fate = _getobsfate(successors)
 
     # Be more precise in case the revision is superseded
     if fate == 'pruned':
         return filteredmsgtable['pruned'] % changeid
     elif fate == 'diverged':
         return filteredmsgtable['diverged'] % changeid
     elif fate == 'superseded':
         single_successor = nodemod.short(successors[0][0])
         return filteredmsgtable['superseded'] % (changeid, single_successor)
     elif fate == 'superseded_split':
 
         succs = []
         for node_id in successors[0]:
             succs.append(nodemod.short(node_id))
 
         if len(succs) <= 2:
             fmtsuccs = ', '.join(succs)
             return filteredmsgtable['superseded_split'] % (changeid, fmtsuccs)
         else:
             firstsuccessors = ', '.join(succs[:2])
             remainingnumber = len(succs) - 2
 
             args = (changeid, firstsuccessors, remainingnumber)
             return filteredmsgtable['superseded_split_several'] % args
 
 def divergentsets(repo, ctx):
     """Compute sets of commits divergent with a given one"""
     cache = {}
     base = {}
     for n in allpredecessors(repo.obsstore, [ctx.node()]):
         if n == ctx.node():
             # a node can't be a base for divergence with itself
             continue
         nsuccsets = successorssets(repo, n, cache)
         for nsuccset in nsuccsets:
             if ctx.node() in nsuccset:
                 # we are only interested in *other* successor sets
                 continue
             if tuple(nsuccset) in base:
                 # we already know the latest base for this divergency
                 continue
             base[tuple(nsuccset)] = n
     return [{'divergentnodes': divset, 'commonpredecessor': b}
             for divset, b in base.iteritems()]
 
 def whyunstable(repo, ctx):
     result = []
     if ctx.orphan():
         for parent in ctx.parents():
             kind = None
             if parent.orphan():
                 kind = 'orphan'
             elif parent.obsolete():
                 kind = 'obsolete'
             if kind is not None:
                 result.append({'instability': 'orphan',
                                'reason': '%s parent' % kind,
                                'node': parent.hex()})
     if ctx.phasedivergent():
         predecessors = allpredecessors(repo.obsstore, [ctx.node()],
                                        ignoreflags=bumpedfix)
         immutable = [repo[p] for p in predecessors
                      if p in repo and not repo[p].mutable()]
         for predecessor in immutable:
             result.append({'instability': 'phase-divergent',
                            'reason': 'immutable predecessor',
                            'node': predecessor.hex()})
     if ctx.contentdivergent():
         dsets = divergentsets(repo, ctx)
         for dset in dsets:
             divnodes = [repo[n] for n in dset['divergentnodes']]
             result.append({'instability': 'content-divergent',
                            'divergentnodes': divnodes,
                            'reason': 'predecessor',
                            'node': nodemod.hex(dset['commonpredecessor'])})
     return result

mercurial/patch.py

@@ -1,2866 +1,2866 b''
 # patch.py - patch file parsing routines
 #
 # Copyright 2006 Brendan Cully <[e-mail]>
 # Copyright 2007 Chris Mason <[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 collections
 import contextlib
 import copy
 import email
 import errno
 import hashlib
 import os
 import posixpath
 import re
 import shutil
 import zlib
 
 from .i18n import _
 from .node import (
     hex,
     short,
 )
 from . import (
     copies,
     diffhelper,
     encoding,
     error,
     mail,
     mdiff,
     pathutil,
     pycompat,
     scmutil,
     similar,
     util,
     vfs as vfsmod,
 )
 from .utils import (
     dateutil,
     diffutil,
     procutil,
     stringutil,
 )
 
 stringio = util.stringio
 
 gitre = re.compile(br'diff --git a/(.*) b/(.*)')
 tabsplitter = re.compile(br'(\t+|[^\t]+)')
 wordsplitter = re.compile(br'(\t+| +|[a-zA-Z0-9_\x80-\xff]+|'
                           b'[^ \ta-zA-Z0-9_\x80-\xff])')
 
 PatchError = error.PatchError
 
 # public functions
 
 def split(stream):
     '''return an iterator of individual patches from a stream'''
     def isheader(line, inheader):
         if inheader and line.startswith((' ', '\t')):
             # continuation
             return True
         if line.startswith((' ', '-', '+')):
             # diff line - don't check for header pattern in there
             return False
         l = line.split(': ', 1)
         return len(l) == 2 and ' ' not in l[0]
 
     def chunk(lines):
         return stringio(''.join(lines))
 
     def hgsplit(stream, cur):
         inheader = True
 
         for line in stream:
             if not line.strip():
                 inheader = False
             if not inheader and line.startswith('# HG changeset patch'):
                 yield chunk(cur)
                 cur = []
                 inheader = True
 
             cur.append(line)
 
         if cur:
             yield chunk(cur)
 
     def mboxsplit(stream, cur):
         for line in stream:
             if line.startswith('From '):
                 for c in split(chunk(cur[1:])):
                     yield c
                 cur = []
 
             cur.append(line)
 
         if cur:
             for c in split(chunk(cur[1:])):
                 yield c
 
     def mimesplit(stream, cur):
         def msgfp(m):
             fp = stringio()
             g = email.Generator.Generator(fp, mangle_from_=False)
             g.flatten(m)
             fp.seek(0)
             return fp
 
         for line in stream:
             cur.append(line)
         c = chunk(cur)
 
         m = mail.parse(c)
         if not m.is_multipart():
             yield msgfp(m)
         else:
             ok_types = ('text/plain', 'text/x-diff', 'text/x-patch')
             for part in m.walk():
                 ct = part.get_content_type()
                 if ct not in ok_types:
                     continue
                 yield msgfp(part)
 
     def headersplit(stream, cur):
         inheader = False
 
         for line in stream:
             if not inheader and isheader(line, inheader):
                 yield chunk(cur)
                 cur = []
                 inheader = True
             if inheader and not isheader(line, inheader):
                 inheader = False
 
             cur.append(line)
 
         if cur:
             yield chunk(cur)
 
     def remainder(cur):
         yield chunk(cur)
 
     class fiter(object):
         def __init__(self, fp):
             self.fp = fp
 
         def __iter__(self):
             return self
 
         def next(self):
             l = self.fp.readline()
             if not l:
                 raise StopIteration
             return l
 
         __next__ = next
 
     inheader = False
     cur = []
 
     mimeheaders = ['content-type']
 
     if not util.safehasattr(stream, 'next'):
         # http responses, for example, have readline but not next
         stream = fiter(stream)
 
     for line in stream:
         cur.append(line)
         if line.startswith('# HG changeset patch'):
             return hgsplit(stream, cur)
         elif line.startswith('From '):
             return mboxsplit(stream, cur)
         elif isheader(line, inheader):
             inheader = True
             if line.split(':', 1)[0].lower() in mimeheaders:
                 # let email parser handle this
                 return mimesplit(stream, cur)
         elif line.startswith('--- ') and inheader:
             # No evil headers seen by diff start, split by hand
             return headersplit(stream, cur)
         # Not enough info, keep reading
 
     # if we are here, we have a very plain patch
     return remainder(cur)
 
 ## Some facility for extensible patch parsing:
 # list of pairs ("header to match", "data key")
 patchheadermap = [('Date', 'date'),
                   ('Branch', 'branch'),
                   ('Node ID', 'nodeid'),
                  ]
 
 @contextlib.contextmanager
 def extract(ui, fileobj):
     '''extract patch from data read from fileobj.
 
     patch can be a normal patch or contained in an email message.
 
     return a dictionary. Standard keys are:
       - filename,
       - message,
       - user,
       - date,
       - branch,
       - node,
       - p1,
       - p2.
     Any item can be missing from the dictionary. If filename is missing,
     fileobj did not contain a patch. Caller must unlink filename when done.'''
 
     fd, tmpname = pycompat.mkstemp(prefix='hg-patch-')
     tmpfp = os.fdopen(fd, r'wb')
     try:
         yield _extract(ui, fileobj, tmpname, tmpfp)
     finally:
         tmpfp.close()
         os.unlink(tmpname)
 
 def _extract(ui, fileobj, tmpname, tmpfp):
 
     # attempt to detect the start of a patch
     # (this heuristic is borrowed from quilt)
     diffre = re.compile(br'^(?:Index:[ \t]|diff[ \t]-|RCS file: |'
                         br'retrieving revision [0-9]+(\.[0-9]+)*$|'
                         br'---[ \t].*?^\+\+\+[ \t]|'
                         br'\*\*\*[ \t].*?^---[ \t])',
                         re.MULTILINE | re.DOTALL)
 
     data = {}
 
     msg = mail.parse(fileobj)
 
     subject = msg[r'Subject'] and mail.headdecode(msg[r'Subject'])
     data['user'] = msg[r'From'] and mail.headdecode(msg[r'From'])
     if not subject and not data['user']:
         # Not an email, restore parsed headers if any
         subject = '\n'.join(': '.join(map(encoding.strtolocal, h))
                             for h in msg.items()) + '\n'
 
     # should try to parse msg['Date']
     parents = []
 
     if subject:
         if subject.startswith('[PATCH'):
             pend = subject.find(']')
             if pend >= 0:
                 subject = subject[pend + 1:].lstrip()
         subject = re.sub(br'\n[ \t]+', ' ', subject)
         ui.debug('Subject: %s\n' % subject)
     if data['user']:
         ui.debug('From: %s\n' % data['user'])
     diffs_seen = 0
     ok_types = ('text/plain', 'text/x-diff', 'text/x-patch')
     message = ''
     for part in msg.walk():
         content_type = pycompat.bytestr(part.get_content_type())
         ui.debug('Content-Type: %s\n' % content_type)
         if content_type not in ok_types:
             continue
         payload = part.get_payload(decode=True)
         m = diffre.search(payload)
         if m:
             hgpatch = False
             hgpatchheader = False
             ignoretext = False
 
             ui.debug('found patch at byte %d\n' % m.start(0))
             diffs_seen += 1
             cfp = stringio()
             for line in payload[:m.start(0)].splitlines():
                 if line.startswith('# HG changeset patch') and not hgpatch:
                     ui.debug('patch generated by hg export\n')
                     hgpatch = True
                     hgpatchheader = True
                     # drop earlier commit message content
                     cfp.seek(0)
                     cfp.truncate()
                     subject = None
                 elif hgpatchheader:
                     if line.startswith('# User '):
                         data['user'] = line[7:]
                         ui.debug('From: %s\n' % data['user'])
                     elif line.startswith("# Parent "):
                         parents.append(line[9:].lstrip())
                     elif line.startswith("# "):
                         for header, key in patchheadermap:
                             prefix = '# %s ' % header
                             if line.startswith(prefix):
                                 data[key] = line[len(prefix):]
                     else:
                         hgpatchheader = False
                 elif line == '---':
                     ignoretext = True
                 if not hgpatchheader and not ignoretext:
                     cfp.write(line)
                     cfp.write('\n')
             message = cfp.getvalue()
             if tmpfp:
                 tmpfp.write(payload)
                 if not payload.endswith('\n'):
                     tmpfp.write('\n')
         elif not diffs_seen and message and content_type == 'text/plain':
             message += '\n' + payload
 
     if subject and not message.startswith(subject):
         message = '%s\n%s' % (subject, message)
     data['message'] = message
     tmpfp.close()
     if parents:
         data['p1'] = parents.pop(0)
         if parents:
             data['p2'] = parents.pop(0)
 
     if diffs_seen:
         data['filename'] = tmpname
 
     return data
 
 class patchmeta(object):
     """Patched file metadata
 
     'op' is the performed operation within ADD, DELETE, RENAME, MODIFY
     or COPY.  'path' is patched file path. 'oldpath' is set to the
     origin file when 'op' is either COPY or RENAME, None otherwise. If
     file mode is changed, 'mode' is a tuple (islink, isexec) where
     'islink' is True if the file is a symlink and 'isexec' is True if
     the file is executable. Otherwise, 'mode' is None.
     """
     def __init__(self, path):
         self.path = path
         self.oldpath = None
         self.mode = None
         self.op = 'MODIFY'
         self.binary = False
 
     def setmode(self, mode):
         islink = mode & 0o20000
         isexec = mode & 0o100
         self.mode = (islink, isexec)
 
     def copy(self):
         other = patchmeta(self.path)
         other.oldpath = self.oldpath
         other.mode = self.mode
         other.op = self.op
         other.binary = self.binary
         return other
 
     def _ispatchinga(self, afile):
         if afile == '/dev/null':
             return self.op == 'ADD'
         return afile == 'a/' + (self.oldpath or self.path)
 
     def _ispatchingb(self, bfile):
         if bfile == '/dev/null':
             return self.op == 'DELETE'
         return bfile == 'b/' + self.path
 
     def ispatching(self, afile, bfile):
         return self._ispatchinga(afile) and self._ispatchingb(bfile)
 
     def __repr__(self):
         return "<patchmeta %s %r>" % (self.op, self.path)
 
 def readgitpatch(lr):
     """extract git-style metadata about patches from <patchname>"""
 
     # Filter patch for git information
     gp = None
     gitpatches = []
     for line in lr:
         line = line.rstrip(' \r\n')
         if line.startswith('diff --git a/'):
             m = gitre.match(line)
             if m:
                 if gp:
                     gitpatches.append(gp)
                 dst = m.group(2)
                 gp = patchmeta(dst)
         elif gp:
             if line.startswith('--- '):
                 gitpatches.append(gp)
                 gp = None
                 continue
             if line.startswith('rename from '):
                 gp.op = 'RENAME'
                 gp.oldpath = line[12:]
             elif line.startswith('rename to '):
                 gp.path = line[10:]
             elif line.startswith('copy from '):
                 gp.op = 'COPY'
                 gp.oldpath = line[10:]
             elif line.startswith('copy to '):
                 gp.path = line[8:]
             elif line.startswith('deleted file'):
                 gp.op = 'DELETE'
             elif line.startswith('new file mode '):
                 gp.op = 'ADD'
                 gp.setmode(int(line[-6:], 8))
             elif line.startswith('new mode '):
                 gp.setmode(int(line[-6:], 8))
             elif line.startswith('GIT binary patch'):
                 gp.binary = True
     if gp:
         gitpatches.append(gp)
 
     return gitpatches
 
 class linereader(object):
     # simple class to allow pushing lines back into the input stream
     def __init__(self, fp):
         self.fp = fp
         self.buf = []
 
     def push(self, line):
         if line is not None:
             self.buf.append(line)
 
     def readline(self):
         if self.buf:
             l = self.buf[0]
             del self.buf[0]
             return l
         return self.fp.readline()
 
     def __iter__(self):
         return iter(self.readline, '')
 
 class abstractbackend(object):
     def __init__(self, ui):
         self.ui = ui
 
     def getfile(self, fname):
         """Return target file data and flags as a (data, (islink,
         isexec)) tuple. Data is None if file is missing/deleted.
         """
         raise NotImplementedError
 
     def setfile(self, fname, data, mode, copysource):
         """Write data to target file fname and set its mode. mode is a
         (islink, isexec) tuple. If data is None, the file content should
         be left unchanged. If the file is modified after being copied,
         copysource is set to the original file name.
         """
         raise NotImplementedError
 
     def unlink(self, fname):
         """Unlink target file."""
         raise NotImplementedError
 
     def writerej(self, fname, failed, total, lines):
         """Write rejected lines for fname. total is the number of hunks
         which failed to apply and total the total number of hunks for this
         files.
         """
 
     def exists(self, fname):
         raise NotImplementedError
 
     def close(self):
         raise NotImplementedError
 
 class fsbackend(abstractbackend):
     def __init__(self, ui, basedir):
         super(fsbackend, self).__init__(ui)
         self.opener = vfsmod.vfs(basedir)
 
     def getfile(self, fname):
         if self.opener.islink(fname):
             return (self.opener.readlink(fname), (True, False))
 
         isexec = False
         try:
             isexec = self.opener.lstat(fname).st_mode & 0o100 != 0
         except OSError as e:
             if e.errno != errno.ENOENT:
                 raise
         try:
             return (self.opener.read(fname), (False, isexec))
         except IOError as e:
             if e.errno != errno.ENOENT:
                 raise
             return None, None
 
     def setfile(self, fname, data, mode, copysource):
         islink, isexec = mode
         if data is None:
             self.opener.setflags(fname, islink, isexec)
             return
         if islink:
             self.opener.symlink(data, fname)
         else:
             self.opener.write(fname, data)
             if isexec:
                 self.opener.setflags(fname, False, True)
 
     def unlink(self, fname):
         rmdir = self.ui.configbool('experimental', 'removeemptydirs')
         self.opener.unlinkpath(fname, ignoremissing=True, rmdir=rmdir)
 
     def writerej(self, fname, failed, total, lines):
         fname = fname + ".rej"
         self.ui.warn(
             _("%d out of %d hunks FAILED -- saving rejects to file %s\n") %
             (failed, total, fname))
         fp = self.opener(fname, 'w')
         fp.writelines(lines)
         fp.close()
 
     def exists(self, fname):
         return self.opener.lexists(fname)
 
 class workingbackend(fsbackend):
     def __init__(self, ui, repo, similarity):
         super(workingbackend, self).__init__(ui, repo.root)
         self.repo = repo
         self.similarity = similarity
         self.removed = set()
         self.changed = set()
         self.copied = []
 
     def _checkknown(self, fname):
         if self.repo.dirstate[fname] == '?' and self.exists(fname):
             raise PatchError(_('cannot patch %s: file is not tracked') % fname)
 
     def setfile(self, fname, data, mode, copysource):
         self._checkknown(fname)
         super(workingbackend, self).setfile(fname, data, mode, copysource)
         if copysource is not None:
             self.copied.append((copysource, fname))
         self.changed.add(fname)
 
     def unlink(self, fname):
         self._checkknown(fname)
         super(workingbackend, self).unlink(fname)
         self.removed.add(fname)
         self.changed.add(fname)
 
     def close(self):
         wctx = self.repo[None]
         changed = set(self.changed)
         for src, dst in self.copied:
             scmutil.dirstatecopy(self.ui, self.repo, wctx, src, dst)
         if self.removed:
             wctx.forget(sorted(self.removed))
             for f in self.removed:
                 if f not in self.repo.dirstate:
                     # File was deleted and no longer belongs to the
                     # dirstate, it was probably marked added then
                     # deleted, and should not be considered by
                     # marktouched().
                     changed.discard(f)
         if changed:
             scmutil.marktouched(self.repo, changed, self.similarity)
         return sorted(self.changed)
 
 class filestore(object):
     def __init__(self, maxsize=None):
         self.opener = None
         self.files = {}
         self.created = 0
         self.maxsize = maxsize
         if self.maxsize is None:
             self.maxsize = 4*(2**20)
         self.size = 0
         self.data = {}
 
     def setfile(self, fname, data, mode, copied=None):
         if self.maxsize < 0 or (len(data) + self.size) <= self.maxsize:
             self.data[fname] = (data, mode, copied)
             self.size += len(data)
         else:
             if self.opener is None:
                 root = pycompat.mkdtemp(prefix='hg-patch-')
                 self.opener = vfsmod.vfs(root)
             # Avoid filename issues with these simple names
             fn = '%d' % self.created
             self.opener.write(fn, data)
             self.created += 1
             self.files[fname] = (fn, mode, copied)
 
     def getfile(self, fname):
         if fname in self.data:
             return self.data[fname]
         if not self.opener or fname not in self.files:
             return None, None, None
         fn, mode, copied = self.files[fname]
         return self.opener.read(fn), mode, copied
 
     def close(self):
         if self.opener:
             shutil.rmtree(self.opener.base)
 
 class repobackend(abstractbackend):
     def __init__(self, ui, repo, ctx, store):
         super(repobackend, self).__init__(ui)
         self.repo = repo
         self.ctx = ctx
         self.store = store
         self.changed = set()
         self.removed = set()
         self.copied = {}
 
     def _checkknown(self, fname):
         if fname not in self.ctx:
             raise PatchError(_('cannot patch %s: file is not tracked') % fname)
 
     def getfile(self, fname):
         try:
             fctx = self.ctx[fname]
         except error.LookupError:
             return None, None
         flags = fctx.flags()
         return fctx.data(), ('l' in flags, 'x' in flags)
 
     def setfile(self, fname, data, mode, copysource):
         if copysource:
             self._checkknown(copysource)
         if data is None:
             data = self.ctx[fname].data()
         self.store.setfile(fname, data, mode, copysource)
         self.changed.add(fname)
         if copysource:
             self.copied[fname] = copysource
 
     def unlink(self, fname):
         self._checkknown(fname)
         self.removed.add(fname)
 
     def exists(self, fname):
         return fname in self.ctx
 
     def close(self):
         return self.changed | self.removed
 
 # @@ -start,len +start,len @@ or @@ -start +start @@ if len is 1
 unidesc = re.compile('@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@')
 contextdesc = re.compile('(?:---|\*\*\*) (\d+)(?:,(\d+))? (?:---|\*\*\*)')
 eolmodes = ['strict', 'crlf', 'lf', 'auto']
 
 class patchfile(object):
     def __init__(self, ui, gp, backend, store, eolmode='strict'):
         self.fname = gp.path
         self.eolmode = eolmode
         self.eol = None
         self.backend = backend
         self.ui = ui
         self.lines = []
         self.exists = False
         self.missing = True
         self.mode = gp.mode
         self.copysource = gp.oldpath
         self.create = gp.op in ('ADD', 'COPY', 'RENAME')
         self.remove = gp.op == 'DELETE'
         if self.copysource is None:
             data, mode = backend.getfile(self.fname)
         else:
             data, mode = store.getfile(self.copysource)[:2]
         if data is not None:
             self.exists = self.copysource is None or backend.exists(self.fname)
             self.missing = False
             if data:
                 self.lines = mdiff.splitnewlines(data)
             if self.mode is None:
                 self.mode = mode
             if self.lines:
                 # Normalize line endings
                 if self.lines[0].endswith('\r\n'):
                     self.eol = '\r\n'
                 elif self.lines[0].endswith('\n'):
                     self.eol = '\n'
                 if eolmode != 'strict':
                     nlines = []
                     for l in self.lines:
                         if l.endswith('\r\n'):
                             l = l[:-2] + '\n'
                         nlines.append(l)
                     self.lines = nlines
         else:
             if self.create:
                 self.missing = False
             if self.mode is None:
                 self.mode = (False, False)
         if self.missing:
             self.ui.warn(_("unable to find '%s' for patching\n") % self.fname)
             self.ui.warn(_("(use '--prefix' to apply patch relative to the "
                            "current directory)\n"))
 
         self.hash = {}
         self.dirty = 0
         self.offset = 0
         self.skew = 0
         self.rej = []
         self.fileprinted = False
         self.printfile(False)
         self.hunks = 0
 
     def writelines(self, fname, lines, mode):
         if self.eolmode == 'auto':
             eol = self.eol
         elif self.eolmode == 'crlf':
             eol = '\r\n'
         else:
             eol = '\n'
 
         if self.eolmode != 'strict' and eol and eol != '\n':
             rawlines = []
             for l in lines:
                 if l and l.endswith('\n'):
                     l = l[:-1] + eol
                 rawlines.append(l)
             lines = rawlines
 
         self.backend.setfile(fname, ''.join(lines), mode, self.copysource)
 
     def printfile(self, warn):
         if self.fileprinted:
             return
         if warn or self.ui.verbose:
             self.fileprinted = True
         s = _("patching file %s\n") % self.fname
         if warn:
             self.ui.warn(s)
         else:
             self.ui.note(s)
 
 
     def findlines(self, l, linenum):
         # looks through the hash and finds candidate lines.  The
         # result is a list of line numbers sorted based on distance
         # from linenum
 
         cand = self.hash.get(l, [])
         if len(cand) > 1:
             # resort our list of potentials forward then back.
             cand.sort(key=lambda x: abs(x - linenum))
         return cand
 
     def write_rej(self):
         # our rejects are a little different from patch(1).  This always
         # creates rejects in the same form as the original patch.  A file
         # header is inserted so that you can run the reject through patch again
         # without having to type the filename.
         if not self.rej:
             return
         base = os.path.basename(self.fname)
         lines = ["--- %s\n+++ %s\n" % (base, base)]
         for x in self.rej:
             for l in x.hunk:
                 lines.append(l)
                 if l[-1:] != '\n':
                     lines.append("\n\ No newline at end of file\n")
         self.backend.writerej(self.fname, len(self.rej), self.hunks, lines)
 
     def apply(self, h):
         if not h.complete():
             raise PatchError(_("bad hunk #%d %s (%d %d %d %d)") %
                             (h.number, h.desc, len(h.a), h.lena, len(h.b),
                             h.lenb))
 
         self.hunks += 1
 
         if self.missing:
             self.rej.append(h)
             return -1
 
         if self.exists and self.create:
             if self.copysource:
                 self.ui.warn(_("cannot create %s: destination already "
                                "exists\n") % self.fname)
             else:
                 self.ui.warn(_("file %s already exists\n") % self.fname)
             self.rej.append(h)
             return -1
 
         if isinstance(h, binhunk):
             if self.remove:
                 self.backend.unlink(self.fname)
             else:
                 l = h.new(self.lines)
                 self.lines[:] = l
                 self.offset += len(l)
                 self.dirty = True
             return 0
 
         horig = h
         if (self.eolmode in ('crlf', 'lf')
             or self.eolmode == 'auto' and self.eol):
             # If new eols are going to be normalized, then normalize
             # hunk data before patching. Otherwise, preserve input
             # line-endings.
             h = h.getnormalized()
 
         # fast case first, no offsets, no fuzz
         old, oldstart, new, newstart = h.fuzzit(0, False)
         oldstart += self.offset
         orig_start = oldstart
         # if there's skew we want to emit the "(offset %d lines)" even
         # when the hunk cleanly applies at start + skew, so skip the
         # fast case code
         if self.skew == 0 and diffhelper.testhunk(old, self.lines, oldstart):
             if self.remove:
                 self.backend.unlink(self.fname)
             else:
                 self.lines[oldstart:oldstart + len(old)] = new
                 self.offset += len(new) - len(old)
                 self.dirty = True
             return 0
 
         # ok, we couldn't match the hunk. Lets look for offsets and fuzz it
         self.hash = {}
         for x, s in enumerate(self.lines):
             self.hash.setdefault(s, []).append(x)
 
         for fuzzlen in xrange(self.ui.configint("patch", "fuzz") + 1):
             for toponly in [True, False]:
                 old, oldstart, new, newstart = h.fuzzit(fuzzlen, toponly)
                 oldstart = oldstart + self.offset + self.skew
                 oldstart = min(oldstart, len(self.lines))
                 if old:
                     cand = self.findlines(old[0][1:], oldstart)
                 else:
                     # Only adding lines with no or fuzzed context, just
                     # take the skew in account
                     cand = [oldstart]
 
                 for l in cand:
                     if not old or diffhelper.testhunk(old, self.lines, l):
                         self.lines[l : l + len(old)] = new
                         self.offset += len(new) - len(old)
                         self.skew = l - orig_start
                         self.dirty = True
                         offset = l - orig_start - fuzzlen
                         if fuzzlen:
                             msg = _("Hunk #%d succeeded at %d "
                                     "with fuzz %d "
                                     "(offset %d lines).\n")
                             self.printfile(True)
                             self.ui.warn(msg %
                                 (h.number, l + 1, fuzzlen, offset))
                         else:
                             msg = _("Hunk #%d succeeded at %d "
                                     "(offset %d lines).\n")
                             self.ui.note(msg % (h.number, l + 1, offset))
                         return fuzzlen
         self.printfile(True)
         self.ui.warn(_("Hunk #%d FAILED at %d\n") % (h.number, orig_start))
         self.rej.append(horig)
         return -1
 
     def close(self):
         if self.dirty:
             self.writelines(self.fname, self.lines, self.mode)
         self.write_rej()
         return len(self.rej)
 
 class header(object):
     """patch header
     """
     diffgit_re = re.compile('diff --git a/(.*) b/(.*)$')
     diff_re = re.compile('diff -r .* (.*)$')
     allhunks_re = re.compile('(?:index|deleted file) ')
     pretty_re = re.compile('(?:new file|deleted file) ')
     special_re = re.compile('(?:index|deleted|copy|rename) ')
     newfile_re = re.compile('(?:new file)')
 
     def __init__(self, header):
         self.header = header
         self.hunks = []
 
     def binary(self):
         return any(h.startswith('index ') for h in self.header)
 
     def pretty(self, fp):
         for h in self.header:
             if h.startswith('index '):
                 fp.write(_('this modifies a binary file (all or nothing)\n'))
                 break
             if self.pretty_re.match(h):
                 fp.write(h)
                 if self.binary():
                     fp.write(_('this is a binary file\n'))
                 break
             if h.startswith('---'):
                 fp.write(_('%d hunks, %d lines changed\n') %
                          (len(self.hunks),
                           sum([max(h.added, h.removed) for h in self.hunks])))
                 break
             fp.write(h)
 
     def write(self, fp):
         fp.write(''.join(self.header))
 
     def allhunks(self):
         return any(self.allhunks_re.match(h) for h in self.header)
 
     def files(self):
         match = self.diffgit_re.match(self.header[0])
         if match:
             fromfile, tofile = match.groups()
             if fromfile == tofile:
                 return [fromfile]
             return [fromfile, tofile]
         else:
             return self.diff_re.match(self.header[0]).groups()
 
     def filename(self):
         return self.files()[-1]
 
     def __repr__(self):
         return '<header %s>' % (' '.join(map(repr, self.files())))
 
     def isnewfile(self):
         return any(self.newfile_re.match(h) for h in self.header)
 
     def special(self):
         # Special files are shown only at the header level and not at the hunk
         # level for example a file that has been deleted is a special file.
         # The user cannot change the content of the operation, in the case of
         # the deleted file he has to take the deletion or not take it, he
         # cannot take some of it.
         # Newly added files are special if they are empty, they are not special
         # if they have some content as we want to be able to change it
         nocontent = len(self.header) == 2
         emptynewfile = self.isnewfile() and nocontent
         return emptynewfile or \
                 any(self.special_re.match(h) for h in self.header)
 
 class recordhunk(object):
     """patch hunk
 
     XXX shouldn't we merge this with the other hunk class?
     """
 
     def __init__(self, header, fromline, toline, proc, before, hunk, after,
                  maxcontext=None):
         def trimcontext(lines, reverse=False):
             if maxcontext is not None:
                 delta = len(lines) - maxcontext
                 if delta > 0:
                     if reverse:
                         return delta, lines[delta:]
                     else:
                         return delta, lines[:maxcontext]
             return 0, lines
 
         self.header = header
         trimedbefore, self.before = trimcontext(before, True)
         self.fromline = fromline + trimedbefore
         self.toline = toline + trimedbefore
         _trimedafter, self.after = trimcontext(after, False)
         self.proc = proc
         self.hunk = hunk
         self.added, self.removed = self.countchanges(self.hunk)
 
     def __eq__(self, v):
         if not isinstance(v, recordhunk):
             return False
 
         return ((v.hunk == self.hunk) and
                 (v.proc == self.proc) and
                 (self.fromline == v.fromline) and
                 (self.header.files() == v.header.files()))
 
     def __hash__(self):
         return hash((tuple(self.hunk),
             tuple(self.header.files()),
             self.fromline,
             self.proc))
 
     def countchanges(self, hunk):
         """hunk -> (n+,n-)"""
         add = len([h for h in hunk if h.startswith('+')])
         rem = len([h for h in hunk if h.startswith('-')])
         return add, rem
 
     def reversehunk(self):
         """return another recordhunk which is the reverse of the hunk
 
         If this hunk is diff(A, B), the returned hunk is diff(B, A). To do
         that, swap fromline/toline and +/- signs while keep other things
         unchanged.
         """
         m = {'+': '-', '-': '+', '\\': '\\'}
         hunk = ['%s%s' % (m[l[0:1]], l[1:]) for l in self.hunk]
         return recordhunk(self.header, self.toline, self.fromline, self.proc,
                           self.before, hunk, self.after)
 
     def write(self, fp):
         delta = len(self.before) + len(self.after)
         if self.after and self.after[-1] == '\\ No newline at end of file\n':
             delta -= 1
         fromlen = delta + self.removed
         tolen = delta + self.added
         fp.write('@@ -%d,%d +%d,%d @@%s\n' %
                  (self.fromline, fromlen, self.toline, tolen,
                   self.proc and (' ' + self.proc)))
         fp.write(''.join(self.before + self.hunk + self.after))
 
     pretty = write
 
     def filename(self):
         return self.header.filename()
 
     def __repr__(self):
         return '<hunk %r@%d>' % (self.filename(), self.fromline)
 
 def getmessages():
     return {
         'multiple': {
             'apply': _("apply change %d/%d to '%s'?"),
             'discard': _("discard change %d/%d to '%s'?"),
             'record': _("record change %d/%d to '%s'?"),
         },
         'single': {
             'apply': _("apply this change to '%s'?"),
             'discard': _("discard this change to '%s'?"),
             'record': _("record this change to '%s'?"),
         },
         'help': {
             'apply': _('[Ynesfdaq?]'
                          '$$ &Yes, apply this change'
                          '$$ &No, skip this change'
                          '$$ &Edit this change manually'
                          '$$ &Skip remaining changes to this file'
                          '$$ Apply remaining changes to this &file'
                          '$$ &Done, skip remaining changes and files'
                          '$$ Apply &all changes to all remaining files'
                          '$$ &Quit, applying no changes'
                          '$$ &? (display help)'),
             'discard': _('[Ynesfdaq?]'
                          '$$ &Yes, discard this change'
                          '$$ &No, skip this change'
                          '$$ &Edit this change manually'
                          '$$ &Skip remaining changes to this file'
                          '$$ Discard remaining changes to this &file'
                          '$$ &Done, skip remaining changes and files'
                          '$$ Discard &all changes to all remaining files'
                          '$$ &Quit, discarding no changes'
                          '$$ &? (display help)'),
             'record': _('[Ynesfdaq?]'
                         '$$ &Yes, record this change'
                         '$$ &No, skip this change'
                         '$$ &Edit this change manually'
                         '$$ &Skip remaining changes to this file'
                         '$$ Record remaining changes to this &file'
                         '$$ &Done, skip remaining changes and files'
                         '$$ Record &all changes to all remaining files'
                         '$$ &Quit, recording no changes'
                         '$$ &? (display help)'),
         }
     }
 
 def filterpatch(ui, headers, operation=None):
     """Interactively filter patch chunks into applied-only chunks"""
     messages = getmessages()
 
     if operation is None:
         operation = 'record'
 
     def prompt(skipfile, skipall, query, chunk):
         """prompt query, and process base inputs
 
         - y/n for the rest of file
         - y/n for the rest
         - ? (help)
         - q (quit)
 
         Return True/False and possibly updated skipfile and skipall.
         """
         newpatches = None
         if skipall is not None:
             return skipall, skipfile, skipall, newpatches
         if skipfile is not None:
             return skipfile, skipfile, skipall, newpatches
         while True:
             resps = messages['help'][operation]
             r = ui.promptchoice("%s %s" % (query, resps))
             ui.write("\n")
             if r == 8: # ?
                 for c, t in ui.extractchoices(resps)[1]:
                     ui.write('%s - %s\n' % (c, encoding.lower(t)))
                 continue
             elif r == 0: # yes
                 ret = True
             elif r == 1: # no
                 ret = False
             elif r == 2: # Edit patch
                 if chunk is None:
                     ui.write(_('cannot edit patch for whole file'))
                     ui.write("\n")
                     continue
                 if chunk.header.binary():
                     ui.write(_('cannot edit patch for binary file'))
                     ui.write("\n")
                     continue
                 # Patch comment based on the Git one (based on comment at end of
                 # https://mercurial-scm.org/wiki/RecordExtension)
                 phelp = '---' + _("""
 To remove '-' lines, make them ' ' lines (context).
 To remove '+' lines, delete them.
 Lines starting with # will be removed from the patch.
 
 If the patch applies cleanly, the edited hunk will immediately be
 added to the record list. If it does not apply cleanly, a rejects
 file will be generated: you can use that when you try again. If
 all lines of the hunk are removed, then the edit is aborted and
 the hunk is left unchanged.
 """)
                 (patchfd, patchfn) = pycompat.mkstemp(prefix="hg-editor-",
                                                       suffix=".diff")
                 ncpatchfp = None
                 try:
                     # Write the initial patch
                     f = util.nativeeolwriter(os.fdopen(patchfd, r'wb'))
                     chunk.header.write(f)
                     chunk.write(f)
                     f.write('\n'.join(['# ' + i for i in phelp.splitlines()]))
                     f.close()
                     # Start the editor and wait for it to complete
                     editor = ui.geteditor()
                     ret = ui.system("%s \"%s\"" % (editor, patchfn),
                                     environ={'HGUSER': ui.username()},
                                     blockedtag='filterpatch')
                     if ret != 0:
                         ui.warn(_("editor exited with exit code %d\n") % ret)
                         continue
                     # Remove comment lines
                     patchfp = open(patchfn, r'rb')
                     ncpatchfp = stringio()
                     for line in util.iterfile(patchfp):
                         line = util.fromnativeeol(line)
                         if not line.startswith('#'):
                             ncpatchfp.write(line)
                     patchfp.close()
                     ncpatchfp.seek(0)
                     newpatches = parsepatch(ncpatchfp)
                 finally:
                     os.unlink(patchfn)
                     del ncpatchfp
                 # Signal that the chunk shouldn't be applied as-is, but
                 # provide the new patch to be used instead.
                 ret = False
             elif r == 3: # Skip
                 ret = skipfile = False
             elif r == 4: # file (Record remaining)
                 ret = skipfile = True
             elif r == 5: # done, skip remaining
                 ret = skipall = False
             elif r == 6: # all
                 ret = skipall = True
             elif r == 7: # quit
                 raise error.Abort(_('user quit'))
             return ret, skipfile, skipall, newpatches
 
     seen = set()
     applied = {}        # 'filename' -> [] of chunks
     skipfile, skipall = None, None
     pos, total = 1, sum(len(h.hunks) for h in headers)
     for h in headers:
         pos += len(h.hunks)
         skipfile = None
         fixoffset = 0
         hdr = ''.join(h.header)
         if hdr in seen:
             continue
         seen.add(hdr)
         if skipall is None:
             h.pretty(ui)
         msg = (_('examine changes to %s?') %
                _(' and ').join("'%s'" % f for f in h.files()))
         r, skipfile, skipall, np = prompt(skipfile, skipall, msg, None)
         if not r:
             continue
         applied[h.filename()] = [h]
         if h.allhunks():
             applied[h.filename()] += h.hunks
             continue
         for i, chunk in enumerate(h.hunks):
             if skipfile is None and skipall is None:
                 chunk.pretty(ui)
             if total == 1:
                 msg = messages['single'][operation] % chunk.filename()
             else:
                 idx = pos - len(h.hunks) + i
                 msg = messages['multiple'][operation] % (idx, total,
                                                          chunk.filename())
             r, skipfile, skipall, newpatches = prompt(skipfile,
                     skipall, msg, chunk)
             if r:
                 if fixoffset:
                     chunk = copy.copy(chunk)
                     chunk.toline += fixoffset
                 applied[chunk.filename()].append(chunk)
             elif newpatches is not None:
                 for newpatch in newpatches:
                     for newhunk in newpatch.hunks:
                         if fixoffset:
                             newhunk.toline += fixoffset
                         applied[newhunk.filename()].append(newhunk)
             else:
                 fixoffset += chunk.removed - chunk.added
     return (sum([h for h in applied.itervalues()
                if h[0].special() or len(h) > 1], []), {})
 class hunk(object):
     def __init__(self, desc, num, lr, context):
         self.number = num
         self.desc = desc
         self.hunk = [desc]
         self.a = []
         self.b = []
         self.starta = self.lena = None
         self.startb = self.lenb = None
         if lr is not None:
             if context:
                 self.read_context_hunk(lr)
             else:
                 self.read_unified_hunk(lr)
 
     def getnormalized(self):
         """Return a copy with line endings normalized to LF."""
 
         def normalize(lines):
             nlines = []
             for line in lines:
                 if line.endswith('\r\n'):
                     line = line[:-2] + '\n'
                 nlines.append(line)
             return nlines
 
         # Dummy object, it is rebuilt manually
         nh = hunk(self.desc, self.number, None, None)
         nh.number = self.number
         nh.desc = self.desc
         nh.hunk = self.hunk
         nh.a = normalize(self.a)
         nh.b = normalize(self.b)
         nh.starta = self.starta
         nh.startb = self.startb
         nh.lena = self.lena
         nh.lenb = self.lenb
         return nh
 
     def read_unified_hunk(self, lr):
         m = unidesc.match(self.desc)
         if not m:
             raise PatchError(_("bad hunk #%d") % self.number)
         self.starta, self.lena, self.startb, self.lenb = m.groups()
         if self.lena is None:
             self.lena = 1
         else:
             self.lena = int(self.lena)
         if self.lenb is None:
             self.lenb = 1
         else:
             self.lenb = int(self.lenb)
         self.starta = int(self.starta)
         self.startb = int(self.startb)
         try:
             diffhelper.addlines(lr, self.hunk, self.lena, self.lenb,
                                 self.a, self.b)
         except error.ParseError as e:
             raise PatchError(_("bad hunk #%d: %s") % (self.number, e))
         # if we hit eof before finishing out the hunk, the last line will
         # be zero length.  Lets try to fix it up.
         while len(self.hunk[-1]) == 0:
             del self.hunk[-1]
             del self.a[-1]
             del self.b[-1]
             self.lena -= 1
             self.lenb -= 1
         self._fixnewline(lr)
 
     def read_context_hunk(self, lr):
         self.desc = lr.readline()
         m = contextdesc.match(self.desc)
         if not m:
             raise PatchError(_("bad hunk #%d") % self.number)
         self.starta, aend = m.groups()
         self.starta = int(self.starta)
         if aend is None:
             aend = self.starta
         self.lena = int(aend) - self.starta
         if self.starta:
             self.lena += 1
         for x in xrange(self.lena):
             l = lr.readline()
             if l.startswith('---'):
                 # lines addition, old block is empty
                 lr.push(l)
                 break
             s = l[2:]
             if l.startswith('- ') or l.startswith('! '):
                 u = '-' + s
             elif l.startswith('  '):
                 u = ' ' + s
             else:
                 raise PatchError(_("bad hunk #%d old text line %d") %
                                  (self.number, x))
             self.a.append(u)
             self.hunk.append(u)
 
         l = lr.readline()
         if l.startswith('\ '):
             s = self.a[-1][:-1]
             self.a[-1] = s
             self.hunk[-1] = s
             l = lr.readline()
         m = contextdesc.match(l)
         if not m:
             raise PatchError(_("bad hunk #%d") % self.number)
         self.startb, bend = m.groups()
         self.startb = int(self.startb)
         if bend is None:
             bend = self.startb
         self.lenb = int(bend) - self.startb
         if self.startb:
             self.lenb += 1
         hunki = 1
         for x in xrange(self.lenb):
             l = lr.readline()
             if l.startswith('\ '):
                 # XXX: the only way to hit this is with an invalid line range.
                 # The no-eol marker is not counted in the line range, but I
                 # guess there are diff(1) out there which behave differently.
                 s = self.b[-1][:-1]
                 self.b[-1] = s
                 self.hunk[hunki - 1] = s
                 continue
             if not l:
                 # line deletions, new block is empty and we hit EOF
                 lr.push(l)
                 break
             s = l[2:]
             if l.startswith('+ ') or l.startswith('! '):
                 u = '+' + s
             elif l.startswith('  '):
                 u = ' ' + s
             elif len(self.b) == 0:
                 # line deletions, new block is empty
                 lr.push(l)
                 break
             else:
                 raise PatchError(_("bad hunk #%d old text line %d") %
                                  (self.number, x))
             self.b.append(s)
             while True:
                 if hunki >= len(self.hunk):
                     h = ""
                 else:
                     h = self.hunk[hunki]
                 hunki += 1
                 if h == u:
                     break
                 elif h.startswith('-'):
                     continue
                 else:
                     self.hunk.insert(hunki - 1, u)
                     break
 
         if not self.a:
             # this happens when lines were only added to the hunk
             for x in self.hunk:
                 if x.startswith('-') or x.startswith(' '):
                     self.a.append(x)
         if not self.b:
             # this happens when lines were only deleted from the hunk
             for x in self.hunk:
                 if x.startswith('+') or x.startswith(' '):
                     self.b.append(x[1:])
         # @@ -start,len +start,len @@
         self.desc = "@@ -%d,%d +%d,%d @@\n" % (self.starta, self.lena,
                                              self.startb, self.lenb)
         self.hunk[0] = self.desc
         self._fixnewline(lr)
 
     def _fixnewline(self, lr):
         l = lr.readline()
         if l.startswith('\ '):
             diffhelper.fixnewline(self.hunk, self.a, self.b)
         else:
             lr.push(l)
 
     def complete(self):
         return len(self.a) == self.lena and len(self.b) == self.lenb
 
     def _fuzzit(self, old, new, fuzz, toponly):
         # this removes context lines from the top and bottom of list 'l'.  It
         # checks the hunk to make sure only context lines are removed, and then
         # returns a new shortened list of lines.
         fuzz = min(fuzz, len(old))
         if fuzz:
             top = 0
             bot = 0
             hlen = len(self.hunk)
             for x in xrange(hlen - 1):
                 # the hunk starts with the @@ line, so use x+1
                 if self.hunk[x + 1].startswith(' '):
                     top += 1
                 else:
                     break
             if not toponly:
                 for x in xrange(hlen - 1):
                     if self.hunk[hlen - bot - 1].startswith(' '):
                         bot += 1
                     else:
                         break
 
             bot = min(fuzz, bot)
             top = min(fuzz, top)
             return old[top:len(old) - bot], new[top:len(new) - bot], top
         return old, new, 0
 
     def fuzzit(self, fuzz, toponly):
         old, new, top = self._fuzzit(self.a, self.b, fuzz, toponly)
         oldstart = self.starta + top
         newstart = self.startb + top
         # zero length hunk ranges already have their start decremented
         if self.lena and oldstart > 0:
             oldstart -= 1
         if self.lenb and newstart > 0:
             newstart -= 1
         return old, oldstart, new, newstart
 
 class binhunk(object):
     'A binary patch file.'
     def __init__(self, lr, fname):
         self.text = None
         self.delta = False
         self.hunk = ['GIT binary patch\n']
         self._fname = fname
         self._read(lr)
 
     def complete(self):
         return self.text is not None
 
     def new(self, lines):
         if self.delta:
             return [applybindelta(self.text, ''.join(lines))]
         return [self.text]
 
     def _read(self, lr):
         def getline(lr, hunk):
             l = lr.readline()
             hunk.append(l)
             return l.rstrip('\r\n')
 
         size = 0
         while True:
             line = getline(lr, self.hunk)
             if not line:
                 raise PatchError(_('could not extract "%s" binary data')
                                  % self._fname)
             if line.startswith('literal '):
                 size = int(line[8:].rstrip())
                 break
             if line.startswith('delta '):
                 size = int(line[6:].rstrip())
                 self.delta = True
                 break
         dec = []
         line = getline(lr, self.hunk)
         while len(line) > 1:
             l = line[0:1]
             if l <= 'Z' and l >= 'A':
                 l = ord(l) - ord('A') + 1
             else:
                 l = ord(l) - ord('a') + 27
             try:
                 dec.append(util.b85decode(line[1:])[:l])
             except ValueError as e:
                 raise PatchError(_('could not decode "%s" binary patch: %s')
                                  % (self._fname, stringutil.forcebytestr(e)))
             line = getline(lr, self.hunk)
         text = zlib.decompress(''.join(dec))
         if len(text) != size:
             raise PatchError(_('"%s" length is %d bytes, should be %d')
                              % (self._fname, len(text), size))
         self.text = text
 
 def parsefilename(str):
     # --- filename \t|space stuff
     s = str[4:].rstrip('\r\n')
     i = s.find('\t')
     if i < 0:
         i = s.find(' ')
         if i < 0:
             return s
     return s[:i]
 
 def reversehunks(hunks):
     '''reverse the signs in the hunks given as argument
 
     This function operates on hunks coming out of patch.filterpatch, that is
     a list of the form: [header1, hunk1, hunk2, header2...]. Example usage:
 
     >>> rawpatch = b"""diff --git a/folder1/g b/folder1/g
     ... --- a/folder1/g
     ... +++ b/folder1/g
     ... @@ -1,7 +1,7 @@
     ... +firstline
     ...  c
     ...  1
     ...  2
     ... + 3
     ... -4
     ...  5
     ...  d
     ... +lastline"""
     >>> hunks = parsepatch([rawpatch])
     >>> hunkscomingfromfilterpatch = []
     >>> for h in hunks:
     ...     hunkscomingfromfilterpatch.append(h)
     ...     hunkscomingfromfilterpatch.extend(h.hunks)
 
     >>> reversedhunks = reversehunks(hunkscomingfromfilterpatch)
     >>> from . import util
     >>> fp = util.stringio()
     >>> for c in reversedhunks:
     ...      c.write(fp)
     >>> fp.seek(0) or None
     >>> reversedpatch = fp.read()
     >>> print(pycompat.sysstr(reversedpatch))
     diff --git a/folder1/g b/folder1/g
     --- a/folder1/g
     +++ b/folder1/g
     @@ -1,4 +1,3 @@
     -firstline
      c
      1
      2
     @@ -2,6 +1,6 @@
      c
      1
      2
     - 3
     +4
      5
      d
     @@ -6,3 +5,2 @@
      5
      d
     -lastline
 
     '''
 
     newhunks = []
     for c in hunks:
         if util.safehasattr(c, 'reversehunk'):
             c = c.reversehunk()
         newhunks.append(c)
     return newhunks
 
 def parsepatch(originalchunks, maxcontext=None):
     """patch -> [] of headers -> [] of hunks
 
     If maxcontext is not None, trim context lines if necessary.
 
     >>> rawpatch = b'''diff --git a/folder1/g b/folder1/g
     ... --- a/folder1/g
     ... +++ b/folder1/g
     ... @@ -1,8 +1,10 @@
     ...  1
     ...  2
     ... -3
     ...  4
     ...  5
     ...  6
     ... +6.1
     ... +6.2
     ...  7
     ...  8
     ... +9'''
     >>> out = util.stringio()
     >>> headers = parsepatch([rawpatch], maxcontext=1)
     >>> for header in headers:
     ...     header.write(out)
     ...     for hunk in header.hunks:
     ...         hunk.write(out)
     >>> print(pycompat.sysstr(out.getvalue()))
     diff --git a/folder1/g b/folder1/g
     --- a/folder1/g
     +++ b/folder1/g
     @@ -2,3 +2,2 @@
      2
     -3
      4
     @@ -6,2 +5,4 @@
      6
     +6.1
     +6.2
      7
     @@ -8,1 +9,2 @@
      8
     +9
     """
     class parser(object):
         """patch parsing state machine"""
         def __init__(self):
             self.fromline = 0
             self.toline = 0
             self.proc = ''
             self.header = None
             self.context = []
             self.before = []
             self.hunk = []
             self.headers = []
 
         def addrange(self, limits):
             fromstart, fromend, tostart, toend, proc = limits
             self.fromline = int(fromstart)
             self.toline = int(tostart)
             self.proc = proc
 
         def addcontext(self, context):
             if self.hunk:
                 h = recordhunk(self.header, self.fromline, self.toline,
                         self.proc, self.before, self.hunk, context, maxcontext)
                 self.header.hunks.append(h)
                 self.fromline += len(self.before) + h.removed
                 self.toline += len(self.before) + h.added
                 self.before = []
                 self.hunk = []
             self.context = context
 
         def addhunk(self, hunk):
             if self.context:
                 self.before = self.context
                 self.context = []
             self.hunk = hunk
 
         def newfile(self, hdr):
             self.addcontext([])
             h = header(hdr)
             self.headers.append(h)
             self.header = h
 
         def addother(self, line):
             pass # 'other' lines are ignored
 
         def finished(self):
             self.addcontext([])
             return self.headers
 
         transitions = {
             'file': {'context': addcontext,
                      'file': newfile,
                      'hunk': addhunk,
                      'range': addrange},
             'context': {'file': newfile,
                         'hunk': addhunk,
                         'range': addrange,
                         'other': addother},
             'hunk': {'context': addcontext,
                      'file': newfile,
                      'range': addrange},
             'range': {'context': addcontext,
                       'hunk': addhunk},
             'other': {'other': addother},
             }
 
     p = parser()
     fp = stringio()
     fp.write(''.join(originalchunks))
     fp.seek(0)
 
     state = 'context'
     for newstate, data in scanpatch(fp):
         try:
             p.transitions[state][newstate](p, data)
         except KeyError:
             raise PatchError('unhandled transition: %s -> %s' %
                                    (state, newstate))
         state = newstate
     del fp
     return p.finished()
 
 def pathtransform(path, strip, prefix):
     '''turn a path from a patch into a path suitable for the repository
 
     prefix, if not empty, is expected to be normalized with a / at the end.
 
     Returns (stripped components, path in repository).
 
     >>> pathtransform(b'a/b/c', 0, b'')
     ('', 'a/b/c')
     >>> pathtransform(b'   a/b/c   ', 0, b'')
     ('', '   a/b/c')
     >>> pathtransform(b'   a/b/c   ', 2, b'')
     ('a/b/', 'c')
     >>> pathtransform(b'a/b/c', 0, b'd/e/')
     ('', 'd/e/a/b/c')
     >>> pathtransform(b'   a//b/c   ', 2, b'd/e/')
     ('a//b/', 'd/e/c')
     >>> pathtransform(b'a/b/c', 3, b'')
     Traceback (most recent call last):
     PatchError: unable to strip away 1 of 3 dirs from a/b/c
     '''
     pathlen = len(path)
     i = 0
     if strip == 0:
         return '', prefix + path.rstrip()
     count = strip
     while count > 0:
         i = path.find('/', i)
         if i == -1:
             raise PatchError(_("unable to strip away %d of %d dirs from %s") %
                              (count, strip, path))
         i += 1
         # consume '//' in the path
         while i < pathlen - 1 and path[i:i + 1] == '/':
             i += 1
         count -= 1
     return path[:i].lstrip(), prefix + path[i:].rstrip()
 
 def makepatchmeta(backend, afile_orig, bfile_orig, hunk, strip, prefix):
     nulla = afile_orig == "/dev/null"
     nullb = bfile_orig == "/dev/null"
     create = nulla and hunk.starta == 0 and hunk.lena == 0
     remove = nullb and hunk.startb == 0 and hunk.lenb == 0
     abase, afile = pathtransform(afile_orig, strip, prefix)
     gooda = not nulla and backend.exists(afile)
     bbase, bfile = pathtransform(bfile_orig, strip, prefix)
     if afile == bfile:
         goodb = gooda
     else:
         goodb = not nullb and backend.exists(bfile)
     missing = not goodb and not gooda and not create
 
     # some diff programs apparently produce patches where the afile is
     # not /dev/null, but afile starts with bfile
     abasedir = afile[:afile.rfind('/') + 1]
     bbasedir = bfile[:bfile.rfind('/') + 1]
     if (missing and abasedir == bbasedir and afile.startswith(bfile)
         and hunk.starta == 0 and hunk.lena == 0):
         create = True
         missing = False
 
     # If afile is "a/b/foo" and bfile is "a/b/foo.orig" we assume the
     # diff is between a file and its backup. In this case, the original
     # file should be patched (see original mpatch code).
     isbackup = (abase == bbase and bfile.startswith(afile))
     fname = None
     if not missing:
         if gooda and goodb:
             if isbackup:
                 fname = afile
             else:
                 fname = bfile
         elif gooda:
             fname = afile
 
     if not fname:
         if not nullb:
             if isbackup:
                 fname = afile
             else:
                 fname = bfile
         elif not nulla:
             fname = afile
         else:
             raise PatchError(_("undefined source and destination files"))
 
     gp = patchmeta(fname)
     if create:
         gp.op = 'ADD'
     elif remove:
         gp.op = 'DELETE'
     return gp
 
 def scanpatch(fp):
     """like patch.iterhunks, but yield different events
 
     - ('file',    [header_lines + fromfile + tofile])
     - ('context', [context_lines])
     - ('hunk',    [hunk_lines])
     - ('range',   (-start,len, +start,len, proc))
     """
     lines_re = re.compile(br'@@ -(\d+),(\d+) \+(\d+),(\d+) @@\s*(.*)')
     lr = linereader(fp)
 
     def scanwhile(first, p):
         """scan lr while predicate holds"""
         lines = [first]
         for line in iter(lr.readline, ''):
             if p(line):
                 lines.append(line)
             else:
                 lr.push(line)
                 break
         return lines
 
     for line in iter(lr.readline, ''):
         if line.startswith('diff --git a/') or line.startswith('diff -r '):
             def notheader(line):
                 s = line.split(None, 1)
                 return not s or s[0] not in ('---', 'diff')
             header = scanwhile(line, notheader)
             fromfile = lr.readline()
             if fromfile.startswith('---'):
                 tofile = lr.readline()
                 header += [fromfile, tofile]
             else:
                 lr.push(fromfile)
             yield 'file', header
         elif line.startswith(' '):
             cs = (' ', '\\')
             yield 'context', scanwhile(line, lambda l: l.startswith(cs))
         elif line.startswith(('-', '+')):
             cs = ('-', '+', '\\')
             yield 'hunk', scanwhile(line, lambda l: l.startswith(cs))
         else:
             m = lines_re.match(line)
             if m:
                 yield 'range', m.groups()
             else:
                 yield 'other', line
 
 def scangitpatch(lr, firstline):
     """
     Git patches can emit:
     - rename a to b
     - change b
     - copy a to c
     - change c
 
     We cannot apply this sequence as-is, the renamed 'a' could not be
     found for it would have been renamed already. And we cannot copy
     from 'b' instead because 'b' would have been changed already. So
     we scan the git patch for copy and rename commands so we can
     perform the copies ahead of time.
     """
     pos = 0
     try:
         pos = lr.fp.tell()
         fp = lr.fp
     except IOError:
         fp = stringio(lr.fp.read())
     gitlr = linereader(fp)
     gitlr.push(firstline)
     gitpatches = readgitpatch(gitlr)
     fp.seek(pos)
     return gitpatches
 
 def iterhunks(fp):
     """Read a patch and yield the following events:
     - ("file", afile, bfile, firsthunk): select a new target file.
     - ("hunk", hunk): a new hunk is ready to be applied, follows a
     "file" event.
     - ("git", gitchanges): current diff is in git format, gitchanges
     maps filenames to gitpatch records. Unique event.
     """
     afile = ""
     bfile = ""
     state = None
     hunknum = 0
     emitfile = newfile = False
     gitpatches = None
 
     # our states
     BFILE = 1
     context = None
     lr = linereader(fp)
 
     for x in iter(lr.readline, ''):
         if state == BFILE and (
             (not context and x.startswith('@'))
             or (context is not False and x.startswith('***************'))
             or x.startswith('GIT binary patch')):
             gp = None
             if (gitpatches and
                 gitpatches[-1].ispatching(afile, bfile)):
                 gp = gitpatches.pop()
             if x.startswith('GIT binary patch'):
                 h = binhunk(lr, gp.path)
             else:
                 if context is None and x.startswith('***************'):
                     context = True
                 h = hunk(x, hunknum + 1, lr, context)
             hunknum += 1
             if emitfile:
                 emitfile = False
                 yield 'file', (afile, bfile, h, gp and gp.copy() or None)
             yield 'hunk', h
         elif x.startswith('diff --git a/'):
             m = gitre.match(x.rstrip(' \r\n'))
             if not m:
                 continue
             if gitpatches is None:
                 # scan whole input for git metadata
                 gitpatches = scangitpatch(lr, x)
                 yield 'git', [g.copy() for g in gitpatches
                               if g.op in ('COPY', 'RENAME')]
                 gitpatches.reverse()
             afile = 'a/' + m.group(1)
             bfile = 'b/' + m.group(2)
             while gitpatches and not gitpatches[-1].ispatching(afile, bfile):
                 gp = gitpatches.pop()
                 yield 'file', ('a/' + gp.path, 'b/' + gp.path, None, gp.copy())
             if not gitpatches:
                 raise PatchError(_('failed to synchronize metadata for "%s"')
                                  % afile[2:])
             gp = gitpatches[-1]
             newfile = True
         elif x.startswith('---'):
             # check for a unified diff
             l2 = lr.readline()
             if not l2.startswith('+++'):
                 lr.push(l2)
                 continue
             newfile = True
             context = False
             afile = parsefilename(x)
             bfile = parsefilename(l2)
         elif x.startswith('***'):
             # check for a context diff
             l2 = lr.readline()
             if not l2.startswith('---'):
                 lr.push(l2)
                 continue
             l3 = lr.readline()
             lr.push(l3)
             if not l3.startswith("***************"):
                 lr.push(l2)
                 continue
             newfile = True
             context = True
             afile = parsefilename(x)
             bfile = parsefilename(l2)
 
         if newfile:
             newfile = False
             emitfile = True
             state = BFILE
             hunknum = 0
 
     while gitpatches:
         gp = gitpatches.pop()
         yield 'file', ('a/' + gp.path, 'b/' + gp.path, None, gp.copy())
 
 def applybindelta(binchunk, data):
     """Apply a binary delta hunk
     The algorithm used is the algorithm from git's patch-delta.c
     """
     def deltahead(binchunk):
         i = 0
         for c in pycompat.bytestr(binchunk):
             i += 1
             if not (ord(c) & 0x80):
                 return i
         return i
     out = ""
     s = deltahead(binchunk)
     binchunk = binchunk[s:]
     s = deltahead(binchunk)
     binchunk = binchunk[s:]
     i = 0
     while i < len(binchunk):
         cmd = ord(binchunk[i:i + 1])
         i += 1
         if (cmd & 0x80):
             offset = 0
             size = 0
             if (cmd & 0x01):
                 offset = ord(binchunk[i:i + 1])
                 i += 1
             if (cmd & 0x02):
                 offset |= ord(binchunk[i:i + 1]) << 8
                 i += 1
             if (cmd & 0x04):
                 offset |= ord(binchunk[i:i + 1]) << 16
                 i += 1
             if (cmd & 0x08):
                 offset |= ord(binchunk[i:i + 1]) << 24
                 i += 1
             if (cmd & 0x10):
                 size = ord(binchunk[i:i + 1])
                 i += 1
             if (cmd & 0x20):
                 size |= ord(binchunk[i:i + 1]) << 8
                 i += 1
             if (cmd & 0x40):
                 size |= ord(binchunk[i:i + 1]) << 16
                 i += 1
             if size == 0:
                 size = 0x10000
             offset_end = offset + size
             out += data[offset:offset_end]
         elif cmd != 0:
             offset_end = i + cmd
             out += binchunk[i:offset_end]
             i += cmd
         else:
             raise PatchError(_('unexpected delta opcode 0'))
     return out
 
 def applydiff(ui, fp, backend, store, strip=1, prefix='', eolmode='strict'):
     """Reads a patch from fp and tries to apply it.
 
     Returns 0 for a clean patch, -1 if any rejects were found and 1 if
     there was any fuzz.
 
     If 'eolmode' is 'strict', the patch content and patched file are
     read in binary mode. Otherwise, line endings are ignored when
     patching then normalized according to 'eolmode'.
     """
     return _applydiff(ui, fp, patchfile, backend, store, strip=strip,
                       prefix=prefix, eolmode=eolmode)
 
 def _canonprefix(repo, prefix):
     if prefix:
         prefix = pathutil.canonpath(repo.root, repo.getcwd(), prefix)
         if prefix != '':
             prefix += '/'
     return prefix
 
 def _applydiff(ui, fp, patcher, backend, store, strip=1, prefix='',
                eolmode='strict'):
     prefix = _canonprefix(backend.repo, prefix)
     def pstrip(p):
         return pathtransform(p, strip - 1, prefix)[1]
 
     rejects = 0
     err = 0
     current_file = None
 
     for state, values in iterhunks(fp):
         if state == 'hunk':
             if not current_file:
                 continue
             ret = current_file.apply(values)
             if ret > 0:
                 err = 1
         elif state == 'file':
             if current_file:
                 rejects += current_file.close()
                 current_file = None
             afile, bfile, first_hunk, gp = values
             if gp:
                 gp.path = pstrip(gp.path)
                 if gp.oldpath:
                     gp.oldpath = pstrip(gp.oldpath)
             else:
                 gp = makepatchmeta(backend, afile, bfile, first_hunk, strip,
                                    prefix)
             if gp.op == 'RENAME':
                 backend.unlink(gp.oldpath)
             if not first_hunk:
                 if gp.op == 'DELETE':
                     backend.unlink(gp.path)
                     continue
                 data, mode = None, None
                 if gp.op in ('RENAME', 'COPY'):
                     data, mode = store.getfile(gp.oldpath)[:2]
                     if data is None:
                         # This means that the old path does not exist
                         raise PatchError(_("source file '%s' does not exist")
                                            % gp.oldpath)
                 if gp.mode:
                     mode = gp.mode
                     if gp.op == 'ADD':
                         # Added files without content have no hunk and
                         # must be created
                         data = ''
                 if data or mode:
                     if (gp.op in ('ADD', 'RENAME', 'COPY')
                         and backend.exists(gp.path)):
                         raise PatchError(_("cannot create %s: destination "
                                            "already exists") % gp.path)
                     backend.setfile(gp.path, data, mode, gp.oldpath)
                 continue
             try:
                 current_file = patcher(ui, gp, backend, store,
                                        eolmode=eolmode)
             except PatchError as inst:
                 ui.warn(str(inst) + '\n')
                 current_file = None
                 rejects += 1
                 continue
         elif state == 'git':
             for gp in values:
                 path = pstrip(gp.oldpath)
                 data, mode = backend.getfile(path)
                 if data is None:
                     # The error ignored here will trigger a getfile()
                     # error in a place more appropriate for error
                     # handling, and will not interrupt the patching
                     # process.
                     pass
                 else:
                     store.setfile(path, data, mode)
         else:
             raise error.Abort(_('unsupported parser state: %s') % state)
 
     if current_file:
         rejects += current_file.close()
 
     if rejects:
         return -1
     return err
 
 def _externalpatch(ui, repo, patcher, patchname, strip, files,
                    similarity):
     """use <patcher> to apply <patchname> to the working directory.
     returns whether patch was applied with fuzz factor."""
 
     fuzz = False
     args = []
     cwd = repo.root
     if cwd:
         args.append('-d %s' % procutil.shellquote(cwd))
     cmd = ('%s %s -p%d < %s'
            % (patcher, ' '.join(args), strip, procutil.shellquote(patchname)))
     ui.debug('Using external patch tool: %s\n' % cmd)
     fp = procutil.popen(cmd, 'rb')
     try:
         for line in util.iterfile(fp):
             line = line.rstrip()
             ui.note(line + '\n')
             if line.startswith('patching file '):
                 pf = util.parsepatchoutput(line)
                 printed_file = False
                 files.add(pf)
             elif line.find('with fuzz') >= 0:
                 fuzz = True
                 if not printed_file:
                     ui.warn(pf + '\n')
                     printed_file = True
                 ui.warn(line + '\n')
             elif line.find('saving rejects to file') >= 0:
                 ui.warn(line + '\n')
             elif line.find('FAILED') >= 0:
                 if not printed_file:
                     ui.warn(pf + '\n')
                     printed_file = True
                 ui.warn(line + '\n')
     finally:
         if files:
             scmutil.marktouched(repo, files, similarity)
     code = fp.close()
     if code:
         raise PatchError(_("patch command failed: %s") %
                          procutil.explainexit(code))
     return fuzz
 
 def patchbackend(ui, backend, patchobj, strip, prefix, files=None,
                  eolmode='strict'):
     if files is None:
         files = set()
     if eolmode is None:
         eolmode = ui.config('patch', 'eol')
     if eolmode.lower() not in eolmodes:
         raise error.Abort(_('unsupported line endings type: %s') % eolmode)
     eolmode = eolmode.lower()
 
     store = filestore()
     try:
         fp = open(patchobj, 'rb')
     except TypeError:
         fp = patchobj
     try:
         ret = applydiff(ui, fp, backend, store, strip=strip, prefix=prefix,
                         eolmode=eolmode)
     finally:
         if fp != patchobj:
             fp.close()
         files.update(backend.close())
         store.close()
     if ret < 0:
         raise PatchError(_('patch failed to apply'))
     return ret > 0
 
 def internalpatch(ui, repo, patchobj, strip, prefix='', files=None,
                   eolmode='strict', similarity=0):
     """use builtin patch to apply <patchobj> to the working directory.
     returns whether patch was applied with fuzz factor."""
     backend = workingbackend(ui, repo, similarity)
     return patchbackend(ui, backend, patchobj, strip, prefix, files, eolmode)
 
 def patchrepo(ui, repo, ctx, store, patchobj, strip, prefix, files=None,
               eolmode='strict'):
     backend = repobackend(ui, repo, ctx, store)
     return patchbackend(ui, backend, patchobj, strip, prefix, files, eolmode)
 
 def patch(ui, repo, patchname, strip=1, prefix='', files=None, eolmode='strict',
           similarity=0):
     """Apply <patchname> to the working directory.
 
     'eolmode' specifies how end of lines should be handled. It can be:
     - 'strict': inputs are read in binary mode, EOLs are preserved
     - 'crlf': EOLs are ignored when patching and reset to CRLF
     - 'lf': EOLs are ignored when patching and reset to LF
     - None: get it from user settings, default to 'strict'
     'eolmode' is ignored when using an external patcher program.
 
     Returns whether patch was applied with fuzz factor.
     """
     patcher = ui.config('ui', 'patch')
     if files is None:
         files = set()
     if patcher:
         return _externalpatch(ui, repo, patcher, patchname, strip,
                               files, similarity)
     return internalpatch(ui, repo, patchname, strip, prefix, files, eolmode,
                          similarity)
 
 def changedfiles(ui, repo, patchpath, strip=1, prefix=''):
     backend = fsbackend(ui, repo.root)
     prefix = _canonprefix(repo, prefix)
     with open(patchpath, 'rb') as fp:
         changed = set()
         for state, values in iterhunks(fp):
             if state == 'file':
                 afile, bfile, first_hunk, gp = values
                 if gp:
                     gp.path = pathtransform(gp.path, strip - 1, prefix)[1]
                     if gp.oldpath:
                         gp.oldpath = pathtransform(gp.oldpath, strip - 1,
                                                    prefix)[1]
                 else:
                     gp = makepatchmeta(backend, afile, bfile, first_hunk, strip,
                                        prefix)
                 changed.add(gp.path)
                 if gp.op == 'RENAME':
                     changed.add(gp.oldpath)
             elif state not in ('hunk', 'git'):
                 raise error.Abort(_('unsupported parser state: %s') % state)
         return changed
 
 class GitDiffRequired(Exception):
     pass
 
-diffopts = diffutil.diffopts
+diffopts = diffutil.diffallopts
 diffallopts = diffutil.diffallopts
 difffeatureopts = diffutil.difffeatureopts
 
 def diff(repo, node1=None, node2=None, match=None, changes=None,
          opts=None, losedatafn=None, prefix='', relroot='', copy=None,
          hunksfilterfn=None):
     '''yields diff of changes to files between two nodes, or node and
     working directory.
 
     if node1 is None, use first dirstate parent instead.
     if node2 is None, compare node1 with working directory.
 
     losedatafn(**kwarg) is a callable run when opts.upgrade=True and
     every time some change cannot be represented with the current
     patch format. Return False to upgrade to git patch format, True to
     accept the loss or raise an exception to abort the diff. It is
     called with the name of current file being diffed as 'fn'. If set
     to None, patches will always be upgraded to git format when
     necessary.
 
     prefix is a filename prefix that is prepended to all filenames on
     display (used for subrepos).
 
     relroot, if not empty, must be normalized with a trailing /. Any match
     patterns that fall outside it will be ignored.
 
     copy, if not empty, should contain mappings {dst@y: src@x} of copy
     information.
 
     hunksfilterfn, if not None, should be a function taking a filectx and
     hunks generator that may yield filtered hunks.
     '''
     for fctx1, fctx2, hdr, hunks in diffhunks(
             repo, node1=node1, node2=node2,
             match=match, changes=changes, opts=opts,
             losedatafn=losedatafn, prefix=prefix, relroot=relroot, copy=copy,
     ):
         if hunksfilterfn is not None:
             # If the file has been removed, fctx2 is None; but this should
             # not occur here since we catch removed files early in
             # logcmdutil.getlinerangerevs() for 'hg log -L'.
             assert fctx2 is not None, \
                 'fctx2 unexpectly None in diff hunks filtering'
             hunks = hunksfilterfn(fctx2, hunks)
         text = ''.join(sum((list(hlines) for hrange, hlines in hunks), []))
         if hdr and (text or len(hdr) > 1):
             yield '\n'.join(hdr) + '\n'
         if text:
             yield text
 
 def diffhunks(repo, node1=None, node2=None, match=None, changes=None,
               opts=None, losedatafn=None, prefix='', relroot='', copy=None):
     """Yield diff of changes to files in the form of (`header`, `hunks`) tuples
     where `header` is a list of diff headers and `hunks` is an iterable of
     (`hunkrange`, `hunklines`) tuples.
 
     See diff() for the meaning of parameters.
     """
 
     if opts is None:
         opts = mdiff.defaultopts
 
     if not node1 and not node2:
         node1 = repo.dirstate.p1()
 
     def lrugetfilectx():
         cache = {}
         order = collections.deque()
         def getfilectx(f, ctx):
             fctx = ctx.filectx(f, filelog=cache.get(f))
             if f not in cache:
                 if len(cache) > 20:
                     del cache[order.popleft()]
                 cache[f] = fctx.filelog()
             else:
                 order.remove(f)
             order.append(f)
             return fctx
         return getfilectx
     getfilectx = lrugetfilectx()
 
     ctx1 = repo[node1]
     ctx2 = repo[node2]
 
     relfiltered = False
     if relroot != '' and match.always():
         # as a special case, create a new matcher with just the relroot
         pats = [relroot]
         match = scmutil.match(ctx2, pats, default='path')
         relfiltered = True
 
     if not changes:
         changes = repo.status(ctx1, ctx2, match=match)
     modified, added, removed = changes[:3]
 
     if not modified and not added and not removed:
         return []
 
     if repo.ui.debugflag:
         hexfunc = hex
     else:
         hexfunc = short
     revs = [hexfunc(node) for node in [ctx1.node(), ctx2.node()] if node]
 
     if copy is None:
         copy = {}
         if opts.git or opts.upgrade:
             copy = copies.pathcopies(ctx1, ctx2, match=match)
 
     if relroot is not None:
         if not relfiltered:
             # XXX this would ideally be done in the matcher, but that is
             # generally meant to 'or' patterns, not 'and' them. In this case we
             # need to 'and' all the patterns from the matcher with relroot.
             def filterrel(l):
                 return [f for f in l if f.startswith(relroot)]
             modified = filterrel(modified)
             added = filterrel(added)
             removed = filterrel(removed)
             relfiltered = True
         # filter out copies where either side isn't inside the relative root
         copy = dict(((dst, src) for (dst, src) in copy.iteritems()
                      if dst.startswith(relroot)
                      and src.startswith(relroot)))
 
     modifiedset = set(modified)
     addedset = set(added)
     removedset = set(removed)
     for f in modified:
         if f not in ctx1:
             # Fix up added, since merged-in additions appear as
             # modifications during merges
             modifiedset.remove(f)
             addedset.add(f)
     for f in removed:
         if f not in ctx1:
             # Merged-in additions that are then removed are reported as removed.
             # They are not in ctx1, so We don't want to show them in the diff.
             removedset.remove(f)
     modified = sorted(modifiedset)
     added = sorted(addedset)
     removed = sorted(removedset)
     for dst, src in list(copy.items()):
         if src not in ctx1:
             # Files merged in during a merge and then copied/renamed are
             # reported as copies. We want to show them in the diff as additions.
             del copy[dst]
 
     prefetchmatch = scmutil.matchfiles(
         repo, list(modifiedset | addedset | removedset))
     scmutil.prefetchfiles(repo, [ctx1.rev(), ctx2.rev()], prefetchmatch)
 
     def difffn(opts, losedata):
         return trydiff(repo, revs, ctx1, ctx2, modified, added, removed,
                        copy, getfilectx, opts, losedata, prefix, relroot)
     if opts.upgrade and not opts.git:
         try:
             def losedata(fn):
                 if not losedatafn or not losedatafn(fn=fn):
                     raise GitDiffRequired
             # Buffer the whole output until we are sure it can be generated
             return list(difffn(opts.copy(git=False), losedata))
         except GitDiffRequired:
             return difffn(opts.copy(git=True), None)
     else:
         return difffn(opts, None)
 
 def diffsinglehunk(hunklines):
     """yield tokens for a list of lines in a single hunk"""
     for line in hunklines:
         # chomp
         chompline = line.rstrip('\n')
         # highlight tabs and trailing whitespace
         stripline = chompline.rstrip()
         if line.startswith('-'):
             label = 'diff.deleted'
         elif line.startswith('+'):
             label = 'diff.inserted'
         else:
             raise error.ProgrammingError('unexpected hunk line: %s' % line)
         for token in tabsplitter.findall(stripline):
             if token.startswith('\t'):
                 yield (token, 'diff.tab')
             else:
                 yield (token, label)
 
         if chompline != stripline:
             yield (chompline[len(stripline):], 'diff.trailingwhitespace')
         if chompline != line:
             yield (line[len(chompline):], '')
 
 def diffsinglehunkinline(hunklines):
     """yield tokens for a list of lines in a single hunk, with inline colors"""
     # prepare deleted, and inserted content
     a = ''
     b = ''
     for line in hunklines:
         if line[0] == '-':
             a += line[1:]
         elif line[0] == '+':
             b += line[1:]
         else:
             raise error.ProgrammingError('unexpected hunk line: %s' % line)
     # fast path: if either side is empty, use diffsinglehunk
     if not a or not b:
         for t in diffsinglehunk(hunklines):
             yield t
         return
     # re-split the content into words
     al = wordsplitter.findall(a)
     bl = wordsplitter.findall(b)
     # re-arrange the words to lines since the diff algorithm is line-based
     aln = [s if s == '\n' else s + '\n' for s in al]
     bln = [s if s == '\n' else s + '\n' for s in bl]
     an = ''.join(aln)
     bn = ''.join(bln)
     # run the diff algorithm, prepare atokens and btokens
     atokens = []
     btokens = []
     blocks = mdiff.allblocks(an, bn, lines1=aln, lines2=bln)
     for (a1, a2, b1, b2), btype in blocks:
         changed = btype == '!'
         for token in mdiff.splitnewlines(''.join(al[a1:a2])):
             atokens.append((changed, token))
         for token in mdiff.splitnewlines(''.join(bl[b1:b2])):
             btokens.append((changed, token))
 
     # yield deleted tokens, then inserted ones
     for prefix, label, tokens in [('-', 'diff.deleted', atokens),
                                   ('+', 'diff.inserted', btokens)]:
         nextisnewline = True
         for changed, token in tokens:
             if nextisnewline:
                 yield (prefix, label)
                 nextisnewline = False
             # special handling line end
             isendofline = token.endswith('\n')
             if isendofline:
                 chomp = token[:-1] # chomp
                 token = chomp.rstrip() # detect spaces at the end
                 endspaces = chomp[len(token):]
             # scan tabs
             for maybetab in tabsplitter.findall(token):
                 if '\t' == maybetab[0]:
                     currentlabel = 'diff.tab'
                 else:
                     if changed:
                         currentlabel = label + '.changed'
                     else:
                         currentlabel = label + '.unchanged'
                 yield (maybetab, currentlabel)
             if isendofline:
                 if endspaces:
                     yield (endspaces, 'diff.trailingwhitespace')
                 yield ('\n', '')
                 nextisnewline = True
 
 def difflabel(func, *args, **kw):
     '''yields 2-tuples of (output, label) based on the output of func()'''
     if kw.get(r'opts') and kw[r'opts'].worddiff:
         dodiffhunk = diffsinglehunkinline
     else:
         dodiffhunk = diffsinglehunk
     headprefixes = [('diff', 'diff.diffline'),
                     ('copy', 'diff.extended'),
                     ('rename', 'diff.extended'),
                     ('old', 'diff.extended'),
                     ('new', 'diff.extended'),
                     ('deleted', 'diff.extended'),
                     ('index', 'diff.extended'),
                     ('similarity', 'diff.extended'),
                     ('---', 'diff.file_a'),
                     ('+++', 'diff.file_b')]
     textprefixes = [('@', 'diff.hunk'),
                     # - and + are handled by diffsinglehunk
                    ]
     head = False
 
     # buffers a hunk, i.e. adjacent "-", "+" lines without other changes.
     hunkbuffer = []
     def consumehunkbuffer():
         if hunkbuffer:
             for token in dodiffhunk(hunkbuffer):
                 yield token
             hunkbuffer[:] = []
 
     for chunk in func(*args, **kw):
         lines = chunk.split('\n')
         linecount = len(lines)
         for i, line in enumerate(lines):
             if head:
                 if line.startswith('@'):
                     head = False
             else:
                 if line and not line.startswith((' ', '+', '-', '@', '\\')):
                     head = True
             diffline = False
             if not head and line and line.startswith(('+', '-')):
                 diffline = True
 
             prefixes = textprefixes
             if head:
                 prefixes = headprefixes
             if diffline:
                 # buffered
                 bufferedline = line
                 if i + 1 < linecount:
                     bufferedline += "\n"
                 hunkbuffer.append(bufferedline)
             else:
                 # unbuffered
                 for token in consumehunkbuffer():
                     yield token
                 stripline = line.rstrip()
                 for prefix, label in prefixes:
                     if stripline.startswith(prefix):
                         yield (stripline, label)
                         if line != stripline:
                             yield (line[len(stripline):],
                                    'diff.trailingwhitespace')
                         break
                 else:
                     yield (line, '')
                 if i + 1 < linecount:
                     yield ('\n', '')
         for token in consumehunkbuffer():
             yield token
 
 def diffui(*args, **kw):
     '''like diff(), but yields 2-tuples of (output, label) for ui.write()'''
     return difflabel(diff, *args, **kw)
 
 def _filepairs(modified, added, removed, copy, opts):
     '''generates tuples (f1, f2, copyop), where f1 is the name of the file
     before and f2 is the the name after. For added files, f1 will be None,
     and for removed files, f2 will be None. copyop may be set to None, 'copy'
     or 'rename' (the latter two only if opts.git is set).'''
     gone = set()
 
     copyto = dict([(v, k) for k, v in copy.items()])
 
     addedset, removedset = set(added), set(removed)
 
     for f in sorted(modified + added + removed):
         copyop = None
         f1, f2 = f, f
         if f in addedset:
             f1 = None
             if f in copy:
                 if opts.git:
                     f1 = copy[f]
                     if f1 in removedset and f1 not in gone:
                         copyop = 'rename'
                         gone.add(f1)
                     else:
                         copyop = 'copy'
         elif f in removedset:
             f2 = None
             if opts.git:
                 # have we already reported a copy above?
                 if (f in copyto and copyto[f] in addedset
                     and copy[copyto[f]] == f):
                     continue
         yield f1, f2, copyop
 
 def trydiff(repo, revs, ctx1, ctx2, modified, added, removed,
             copy, getfilectx, opts, losedatafn, prefix, relroot):
     '''given input data, generate a diff and yield it in blocks
 
     If generating a diff would lose data like flags or binary data and
     losedatafn is not None, it will be called.
 
     relroot is removed and prefix is added to every path in the diff output.
 
     If relroot is not empty, this function expects every path in modified,
     added, removed and copy to start with it.'''
 
     def gitindex(text):
         if not text:
             text = ""
         l = len(text)
         s = hashlib.sha1('blob %d\0' % l)
         s.update(text)
         return hex(s.digest())
 
     if opts.noprefix:
         aprefix = bprefix = ''
     else:
         aprefix = 'a/'
         bprefix = 'b/'
 
     def diffline(f, revs):
         revinfo = ' '.join(["-r %s" % rev for rev in revs])
         return 'diff %s %s' % (revinfo, f)
 
     def isempty(fctx):
         return fctx is None or fctx.size() == 0
 
     date1 = dateutil.datestr(ctx1.date())
     date2 = dateutil.datestr(ctx2.date())
 
     gitmode = {'l': '120000', 'x': '100755', '': '100644'}
 
     if relroot != '' and (repo.ui.configbool('devel', 'all-warnings')
                           or repo.ui.configbool('devel', 'check-relroot')):
         for f in modified + added + removed + list(copy) + list(copy.values()):
             if f is not None and not f.startswith(relroot):
                 raise AssertionError(
                     "file %s doesn't start with relroot %s" % (f, relroot))
 
     for f1, f2, copyop in _filepairs(modified, added, removed, copy, opts):
         content1 = None
         content2 = None
         fctx1 = None
         fctx2 = None
         flag1 = None
         flag2 = None
         if f1:
             fctx1 = getfilectx(f1, ctx1)
             if opts.git or losedatafn:
                 flag1 = ctx1.flags(f1)
         if f2:
             fctx2 = getfilectx(f2, ctx2)
             if opts.git or losedatafn:
                 flag2 = ctx2.flags(f2)
         # if binary is True, output "summary" or "base85", but not "text diff"
         if opts.text:
             binary = False
         else:
             binary = any(f.isbinary() for f in [fctx1, fctx2] if f is not None)
 
         if losedatafn and not opts.git:
             if (binary or
                 # copy/rename
                 f2 in copy or
                 # empty file creation
                 (not f1 and isempty(fctx2)) or
                 # empty file deletion
                 (isempty(fctx1) and not f2) or
                 # create with flags
                 (not f1 and flag2) or
                 # change flags
                 (f1 and f2 and flag1 != flag2)):
                 losedatafn(f2 or f1)
 
         path1 = f1 or f2
         path2 = f2 or f1
         path1 = posixpath.join(prefix, path1[len(relroot):])
         path2 = posixpath.join(prefix, path2[len(relroot):])
         header = []
         if opts.git:
             header.append('diff --git %s%s %s%s' %
                           (aprefix, path1, bprefix, path2))
             if not f1: # added
                 header.append('new file mode %s' % gitmode[flag2])
             elif not f2: # removed
                 header.append('deleted file mode %s' % gitmode[flag1])
             else:  # modified/copied/renamed
                 mode1, mode2 = gitmode[flag1], gitmode[flag2]
                 if mode1 != mode2:
                     header.append('old mode %s' % mode1)
                     header.append('new mode %s' % mode2)
                 if copyop is not None:
                     if opts.showsimilarity:
                         sim = similar.score(ctx1[path1], ctx2[path2]) * 100
                         header.append('similarity index %d%%' % sim)
                     header.append('%s from %s' % (copyop, path1))
                     header.append('%s to %s' % (copyop, path2))
         elif revs and not repo.ui.quiet:
             header.append(diffline(path1, revs))
 
         #  fctx.is  | diffopts                | what to   | is fctx.data()
         #  binary() | text nobinary git index | output?   | outputted?
         # ------------------------------------|----------------------------
         #  yes      | no   no       no  *     | summary   | no
         #  yes      | no   no       yes *     | base85    | yes
         #  yes      | no   yes      no  *     | summary   | no
         #  yes      | no   yes      yes 0     | summary   | no
         #  yes      | no   yes      yes >0    | summary   | semi [1]
         #  yes      | yes  *        *   *     | text diff | yes
         #  no       | *    *        *   *     | text diff | yes
         # [1]: hash(fctx.data()) is outputted. so fctx.data() cannot be faked
         if binary and (not opts.git or (opts.git and opts.nobinary and not
                                         opts.index)):
             # fast path: no binary content will be displayed, content1 and
             # content2 are only used for equivalent test. cmp() could have a
             # fast path.
             if fctx1 is not None:
                 content1 = b'\0'
             if fctx2 is not None:
                 if fctx1 is not None and not fctx1.cmp(fctx2):
                     content2 = b'\0' # not different
                 else:
                     content2 = b'\0\0'
         else:
             # normal path: load contents
             if fctx1 is not None:
                 content1 = fctx1.data()
             if fctx2 is not None:
                 content2 = fctx2.data()
 
         if binary and opts.git and not opts.nobinary:
             text = mdiff.b85diff(content1, content2)
             if text:
                 header.append('index %s..%s' %
                               (gitindex(content1), gitindex(content2)))
             hunks = (None, [text]),
         else:
             if opts.git and opts.index > 0:
                 flag = flag1
                 if flag is None:
                     flag = flag2
                 header.append('index %s..%s %s' %
                               (gitindex(content1)[0:opts.index],
                                gitindex(content2)[0:opts.index],
                                gitmode[flag]))
 
             uheaders, hunks = mdiff.unidiff(content1, date1,
                                             content2, date2,
                                             path1, path2,
                                             binary=binary, opts=opts)
             header.extend(uheaders)
         yield fctx1, fctx2, header, hunks
 
 def diffstatsum(stats):
     maxfile, maxtotal, addtotal, removetotal, binary = 0, 0, 0, 0, False
     for f, a, r, b in stats:
         maxfile = max(maxfile, encoding.colwidth(f))
         maxtotal = max(maxtotal, a + r)
         addtotal += a
         removetotal += r
         binary = binary or b
 
     return maxfile, maxtotal, addtotal, removetotal, binary
 
 def diffstatdata(lines):
     diffre = re.compile('^diff .*-r [a-z0-9]+\s(.*)$')
 
     results = []
     filename, adds, removes, isbinary = None, 0, 0, False
 
     def addresult():
         if filename:
             results.append((filename, adds, removes, isbinary))
 
     # inheader is used to track if a line is in the
     # header portion of the diff.  This helps properly account
     # for lines that start with '--' or '++'
     inheader = False
 
     for line in lines:
         if line.startswith('diff'):
             addresult()
             # starting a new file diff
             # set numbers to 0 and reset inheader
             inheader = True
             adds, removes, isbinary = 0, 0, False
             if line.startswith('diff --git a/'):
                 filename = gitre.search(line).group(2)
             elif line.startswith('diff -r'):
                 # format: "diff -r ... -r ... filename"
                 filename = diffre.search(line).group(1)
         elif line.startswith('@@'):
             inheader = False
         elif line.startswith('+') and not inheader:
             adds += 1
         elif line.startswith('-') and not inheader:
             removes += 1
         elif (line.startswith('GIT binary patch') or
               line.startswith('Binary file')):
             isbinary = True
     addresult()
     return results
 
 def diffstat(lines, width=80):
     output = []
     stats = diffstatdata(lines)
     maxname, maxtotal, totaladds, totalremoves, hasbinary = diffstatsum(stats)
 
     countwidth = len(str(maxtotal))
     if hasbinary and countwidth < 3:
         countwidth = 3
     graphwidth = width - countwidth - maxname - 6
     if graphwidth < 10:
         graphwidth = 10
 
     def scale(i):
         if maxtotal <= graphwidth:
             return i
         # If diffstat runs out of room it doesn't print anything,
         # which isn't very useful, so always print at least one + or -
         # if there were at least some changes.
         return max(i * graphwidth // maxtotal, int(bool(i)))
 
     for filename, adds, removes, isbinary in stats:
         if isbinary:
             count = 'Bin'
         else:
             count = '%d' % (adds + removes)
         pluses = '+' * scale(adds)
         minuses = '-' * scale(removes)
         output.append(' %s%s |  %*s %s%s\n' %
                       (filename, ' ' * (maxname - encoding.colwidth(filename)),
                        countwidth, count, pluses, minuses))
 
     if stats:
         output.append(_(' %d files changed, %d insertions(+), '
                         '%d deletions(-)\n')
                       % (len(stats), totaladds, totalremoves))
 
     return ''.join(output)
 
 def diffstatui(*args, **kw):
     '''like diffstat(), but yields 2-tuples of (output, label) for
     ui.write()
     '''
 
     for line in diffstat(*args, **kw).splitlines():
         if line and line[-1] in '+-':
             name, graph = line.rsplit(' ', 1)
             yield (name + ' ', '')
             m = re.search(br'\++', graph)
             if m:
                 yield (m.group(0), 'diffstat.inserted')
             m = re.search(br'-+', graph)
             if m:
                 yield (m.group(0), 'diffstat.deleted')
         else:
             yield (line, '')
         yield ('\n', '')

mercurial/revset.py

@@ -1,2250 +1,2250 b''
 # revset.py - revision set queries for mercurial
 #
 # Copyright 2010 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import re
 
 from .i18n import _
 from . import (
     dagop,
     destutil,
     encoding,
     error,
     hbisect,
     match as matchmod,
     node,
     obsolete as obsmod,
     obsutil,
     pathutil,
     phases,
     pycompat,
     registrar,
     repoview,
     revsetlang,
     scmutil,
     smartset,
     stack as stackmod,
     util,
 )
 from .utils import (
     dateutil,
     diffutil,
     stringutil,
 )
 
 # helpers for processing parsed tree
 getsymbol = revsetlang.getsymbol
 getstring = revsetlang.getstring
 getinteger = revsetlang.getinteger
 getboolean = revsetlang.getboolean
 getlist = revsetlang.getlist
 getrange = revsetlang.getrange
 getargs = revsetlang.getargs
 getargsdict = revsetlang.getargsdict
 
 baseset = smartset.baseset
 generatorset = smartset.generatorset
 spanset = smartset.spanset
 fullreposet = smartset.fullreposet
 
 # Constants for ordering requirement, used in getset():
 #
 # If 'define', any nested functions and operations MAY change the ordering of
 # the entries in the set (but if changes the ordering, it MUST ALWAYS change
 # it). If 'follow', any nested functions and operations MUST take the ordering
 # specified by the first operand to the '&' operator.
 #
 # For instance,
 #
 #   X & (Y | Z)
 #   ^   ^^^^^^^
 #   |   follow
 #   define
 #
 # will be evaluated as 'or(y(x()), z(x()))', where 'x()' can change the order
 # of the entries in the set, but 'y()', 'z()' and 'or()' shouldn't.
 #
 # 'any' means the order doesn't matter. For instance,
 #
 #   (X & !Y) | ancestors(Z)
 #         ^              ^
 #         any            any
 #
 # For 'X & !Y', 'X' decides the order and 'Y' is subtracted from 'X', so the
 # order of 'Y' does not matter. For 'ancestors(Z)', Z's order does not matter
 # since 'ancestors' does not care about the order of its argument.
 #
 # Currently, most revsets do not care about the order, so 'define' is
 # equivalent to 'follow' for them, and the resulting order is based on the
 # 'subset' parameter passed down to them:
 #
 #   m = revset.match(...)
 #   m(repo, subset, order=defineorder)
 #           ^^^^^^
 #      For most revsets, 'define' means using the order this subset provides
 #
 # There are a few revsets that always redefine the order if 'define' is
 # specified: 'sort(X)', 'reverse(X)', 'x:y'.
 anyorder = 'any'        # don't care the order, could be even random-shuffled
 defineorder = 'define'  # ALWAYS redefine, or ALWAYS follow the current order
 followorder = 'follow'  # MUST follow the current order
 
 # helpers
 
 def getset(repo, subset, x, order=defineorder):
     if not x:
         raise error.ParseError(_("missing argument"))
     return methods[x[0]](repo, subset, *x[1:], order=order)
 
 def _getrevsource(repo, r):
     extra = repo[r].extra()
     for label in ('source', 'transplant_source', 'rebase_source'):
         if label in extra:
             try:
                 return repo[extra[label]].rev()
             except error.RepoLookupError:
                 pass
     return None
 
 def _sortedb(xs):
     return sorted(pycompat.rapply(pycompat.maybebytestr, xs))
 
 # operator methods
 
 def stringset(repo, subset, x, order):
     if not x:
         raise error.ParseError(_("empty string is not a valid revision"))
     x = scmutil.intrev(scmutil.revsymbol(repo, x))
     if (x in subset
         or x == node.nullrev and isinstance(subset, fullreposet)):
         return baseset([x])
     return baseset()
 
 def rangeset(repo, subset, x, y, order):
     m = getset(repo, fullreposet(repo), x)
     n = getset(repo, fullreposet(repo), y)
 
     if not m or not n:
         return baseset()
     return _makerangeset(repo, subset, m.first(), n.last(), order)
 
 def rangeall(repo, subset, x, order):
     assert x is None
     return _makerangeset(repo, subset, 0, repo.changelog.tiprev(), order)
 
 def rangepre(repo, subset, y, order):
     # ':y' can't be rewritten to '0:y' since '0' may be hidden
     n = getset(repo, fullreposet(repo), y)
     if not n:
         return baseset()
     return _makerangeset(repo, subset, 0, n.last(), order)
 
 def rangepost(repo, subset, x, order):
     m = getset(repo, fullreposet(repo), x)
     if not m:
         return baseset()
     return _makerangeset(repo, subset, m.first(), repo.changelog.tiprev(),
                          order)
 
 def _makerangeset(repo, subset, m, n, order):
     if m == n:
         r = baseset([m])
     elif n == node.wdirrev:
         r = spanset(repo, m, len(repo)) + baseset([n])
     elif m == node.wdirrev:
         r = baseset([m]) + spanset(repo, repo.changelog.tiprev(), n - 1)
     elif m < n:
         r = spanset(repo, m, n + 1)
     else:
         r = spanset(repo, m, n - 1)
 
     if order == defineorder:
         return r & subset
     else:
         # carrying the sorting over when possible would be more efficient
         return subset & r
 
 def dagrange(repo, subset, x, y, order):
     r = fullreposet(repo)
     xs = dagop.reachableroots(repo, getset(repo, r, x), getset(repo, r, y),
                               includepath=True)
     return subset & xs
 
 def andset(repo, subset, x, y, order):
     if order == anyorder:
         yorder = anyorder
     else:
         yorder = followorder
     return getset(repo, getset(repo, subset, x, order), y, yorder)
 
 def andsmallyset(repo, subset, x, y, order):
     # 'andsmally(x, y)' is equivalent to 'and(x, y)', but faster when y is small
     if order == anyorder:
         yorder = anyorder
     else:
         yorder = followorder
     return getset(repo, getset(repo, subset, y, yorder), x, order)
 
 def differenceset(repo, subset, x, y, order):
     return getset(repo, subset, x, order) - getset(repo, subset, y, anyorder)
 
 def _orsetlist(repo, subset, xs, order):
     assert xs
     if len(xs) == 1:
         return getset(repo, subset, xs[0], order)
     p = len(xs) // 2
     a = _orsetlist(repo, subset, xs[:p], order)
     b = _orsetlist(repo, subset, xs[p:], order)
     return a + b
 
 def orset(repo, subset, x, order):
     xs = getlist(x)
     if not xs:
         return baseset()
     if order == followorder:
         # slow path to take the subset order
         return subset & _orsetlist(repo, fullreposet(repo), xs, anyorder)
     else:
         return _orsetlist(repo, subset, xs, order)
 
 def notset(repo, subset, x, order):
     return subset - getset(repo, subset, x, anyorder)
 
 def relationset(repo, subset, x, y, order):
     raise error.ParseError(_("can't use a relation in this context"))
 
 def relsubscriptset(repo, subset, x, y, z, order):
     # this is pretty basic implementation of 'x#y[z]' operator, still
     # experimental so undocumented. see the wiki for further ideas.
     # https://www.mercurial-scm.org/wiki/RevsetOperatorPlan
     rel = getsymbol(y)
     n = getinteger(z, _("relation subscript must be an integer"))
 
     # TODO: perhaps this should be a table of relation functions
     if rel in ('g', 'generations'):
         # TODO: support range, rewrite tests, and drop startdepth argument
         # from ancestors() and descendants() predicates
         if n <= 0:
             n = -n
             return _ancestors(repo, subset, x, startdepth=n, stopdepth=n + 1)
         else:
             return _descendants(repo, subset, x, startdepth=n, stopdepth=n + 1)
 
     raise error.UnknownIdentifier(rel, ['generations'])
 
 def subscriptset(repo, subset, x, y, order):
     raise error.ParseError(_("can't use a subscript in this context"))
 
 def listset(repo, subset, *xs, **opts):
     raise error.ParseError(_("can't use a list in this context"),
                            hint=_('see hg help "revsets.x or y"'))
 
 def keyvaluepair(repo, subset, k, v, order):
     raise error.ParseError(_("can't use a key-value pair in this context"))
 
 def func(repo, subset, a, b, order):
     f = getsymbol(a)
     if f in symbols:
         func = symbols[f]
         if getattr(func, '_takeorder', False):
             return func(repo, subset, b, order)
         return func(repo, subset, b)
 
     keep = lambda fn: getattr(fn, '__doc__', None) is not None
 
     syms = [s for (s, fn) in symbols.items() if keep(fn)]
     raise error.UnknownIdentifier(f, syms)
 
 # functions
 
 # symbols are callables like:
 #   fn(repo, subset, x)
 # with:
 #   repo - current repository instance
 #   subset - of revisions to be examined
 #   x - argument in tree form
 symbols = revsetlang.symbols
 
 # symbols which can't be used for a DoS attack for any given input
 # (e.g. those which accept regexes as plain strings shouldn't be included)
 # functions that just return a lot of changesets (like all) don't count here
 safesymbols = set()
 
 predicate = registrar.revsetpredicate()
 
 @predicate('_destupdate')
 def _destupdate(repo, subset, x):
     # experimental revset for update destination
     args = getargsdict(x, 'limit', 'clean')
     return subset & baseset([destutil.destupdate(repo,
                             **pycompat.strkwargs(args))[0]])
 
 @predicate('_destmerge')
 def _destmerge(repo, subset, x):
     # experimental revset for merge destination
     sourceset = None
     if x is not None:
         sourceset = getset(repo, fullreposet(repo), x)
     return subset & baseset([destutil.destmerge(repo, sourceset=sourceset)])
 
 @predicate('adds(pattern)', safe=True, weight=30)
 def adds(repo, subset, x):
     """Changesets that add a file matching pattern.
 
     The pattern without explicit kind like ``glob:`` is expected to be
     relative to the current directory and match against a file or a
     directory.
     """
     # i18n: "adds" is a keyword
     pat = getstring(x, _("adds requires a pattern"))
     return checkstatus(repo, subset, pat, 1)
 
 @predicate('ancestor(*changeset)', safe=True, weight=0.5)
 def ancestor(repo, subset, x):
     """A greatest common ancestor of the changesets.
 
     Accepts 0 or more changesets.
     Will return empty list when passed no args.
     Greatest common ancestor of a single changeset is that changeset.
     """
     reviter = iter(orset(repo, fullreposet(repo), x, order=anyorder))
     try:
         anc = repo[next(reviter)]
     except StopIteration:
         return baseset()
     for r in reviter:
         anc = anc.ancestor(repo[r])
 
     r = scmutil.intrev(anc)
     if r in subset:
         return baseset([r])
     return baseset()
 
 def _ancestors(repo, subset, x, followfirst=False, startdepth=None,
                stopdepth=None):
     heads = getset(repo, fullreposet(repo), x)
     if not heads:
         return baseset()
     s = dagop.revancestors(repo, heads, followfirst, startdepth, stopdepth)
     return subset & s
 
 @predicate('ancestors(set[, depth])', safe=True)
 def ancestors(repo, subset, x):
     """Changesets that are ancestors of changesets in set, including the
     given changesets themselves.
 
     If depth is specified, the result only includes changesets up to
     the specified generation.
     """
     # startdepth is for internal use only until we can decide the UI
     args = getargsdict(x, 'ancestors', 'set depth startdepth')
     if 'set' not in args:
         # i18n: "ancestors" is a keyword
         raise error.ParseError(_('ancestors takes at least 1 argument'))
     startdepth = stopdepth = None
     if 'startdepth' in args:
         n = getinteger(args['startdepth'],
                        "ancestors expects an integer startdepth")
         if n < 0:
             raise error.ParseError("negative startdepth")
         startdepth = n
     if 'depth' in args:
         # i18n: "ancestors" is a keyword
         n = getinteger(args['depth'], _("ancestors expects an integer depth"))
         if n < 0:
             raise error.ParseError(_("negative depth"))
         stopdepth = n + 1
     return _ancestors(repo, subset, args['set'],
                       startdepth=startdepth, stopdepth=stopdepth)
 
 @predicate('_firstancestors', safe=True)
 def _firstancestors(repo, subset, x):
     # ``_firstancestors(set)``
     # Like ``ancestors(set)`` but follows only the first parents.
     return _ancestors(repo, subset, x, followfirst=True)
 
 def _childrenspec(repo, subset, x, n, order):
     """Changesets that are the Nth child of a changeset
     in set.
     """
     cs = set()
     for r in getset(repo, fullreposet(repo), x):
         for i in range(n):
             c = repo[r].children()
             if len(c) == 0:
                 break
             if len(c) > 1:
                 raise error.RepoLookupError(
                     _("revision in set has more than one child"))
             r = c[0].rev()
         else:
             cs.add(r)
     return subset & cs
 
 def ancestorspec(repo, subset, x, n, order):
     """``set~n``
     Changesets that are the Nth ancestor (first parents only) of a changeset
     in set.
     """
     n = getinteger(n, _("~ expects a number"))
     if n < 0:
         # children lookup
         return _childrenspec(repo, subset, x, -n, order)
     ps = set()
     cl = repo.changelog
     for r in getset(repo, fullreposet(repo), x):
         for i in range(n):
             try:
                 r = cl.parentrevs(r)[0]
             except error.WdirUnsupported:
                 r = repo[r].parents()[0].rev()
         ps.add(r)
     return subset & ps
 
 @predicate('author(string)', safe=True, weight=10)
 def author(repo, subset, x):
     """Alias for ``user(string)``.
     """
     # i18n: "author" is a keyword
     n = getstring(x, _("author requires a string"))
     kind, pattern, matcher = _substringmatcher(n, casesensitive=False)
     return subset.filter(lambda x: matcher(repo[x].user()),
                          condrepr=('<user %r>', n))
 
 @predicate('bisect(string)', safe=True)
 def bisect(repo, subset, x):
     """Changesets marked in the specified bisect status:
 
     - ``good``, ``bad``, ``skip``: csets explicitly marked as good/bad/skip
     - ``goods``, ``bads``      : csets topologically good/bad
     - ``range``              : csets taking part in the bisection
     - ``pruned``             : csets that are goods, bads or skipped
     - ``untested``           : csets whose fate is yet unknown
     - ``ignored``            : csets ignored due to DAG topology
     - ``current``            : the cset currently being bisected
     """
     # i18n: "bisect" is a keyword
     status = getstring(x, _("bisect requires a string")).lower()
     state = set(hbisect.get(repo, status))
     return subset & state
 
 # Backward-compatibility
 # - no help entry so that we do not advertise it any more
 @predicate('bisected', safe=True)
 def bisected(repo, subset, x):
     return bisect(repo, subset, x)
 
 @predicate('bookmark([name])', safe=True)
 def bookmark(repo, subset, x):
     """The named bookmark or all bookmarks.
 
     Pattern matching is supported for `name`. See :hg:`help revisions.patterns`.
     """
     # i18n: "bookmark" is a keyword
     args = getargs(x, 0, 1, _('bookmark takes one or no arguments'))
     if args:
         bm = getstring(args[0],
                        # i18n: "bookmark" is a keyword
                        _('the argument to bookmark must be a string'))
         kind, pattern, matcher = stringutil.stringmatcher(bm)
         bms = set()
         if kind == 'literal':
             bmrev = repo._bookmarks.get(pattern, None)
             if not bmrev:
                 raise error.RepoLookupError(_("bookmark '%s' does not exist")
                                             % pattern)
             bms.add(repo[bmrev].rev())
         else:
             matchrevs = set()
             for name, bmrev in repo._bookmarks.iteritems():
                 if matcher(name):
                     matchrevs.add(bmrev)
             if not matchrevs:
                 raise error.RepoLookupError(_("no bookmarks exist"
                                               " that match '%s'") % pattern)
             for bmrev in matchrevs:
                 bms.add(repo[bmrev].rev())
     else:
         bms = {repo[r].rev() for r in repo._bookmarks.values()}
     bms -= {node.nullrev}
     return subset & bms
 
 @predicate('branch(string or set)', safe=True, weight=10)
 def branch(repo, subset, x):
     """
     All changesets belonging to the given branch or the branches of the given
     changesets.
 
     Pattern matching is supported for `string`. See
     :hg:`help revisions.patterns`.
     """
     getbi = repo.revbranchcache().branchinfo
     def getbranch(r):
         try:
             return getbi(r)[0]
         except error.WdirUnsupported:
             return repo[r].branch()
 
     try:
         b = getstring(x, '')
     except error.ParseError:
         # not a string, but another revspec, e.g. tip()
         pass
     else:
         kind, pattern, matcher = stringutil.stringmatcher(b)
         if kind == 'literal':
             # note: falls through to the revspec case if no branch with
             # this name exists and pattern kind is not specified explicitly
             if pattern in repo.branchmap():
                 return subset.filter(lambda r: matcher(getbranch(r)),
                                      condrepr=('<branch %r>', b))
             if b.startswith('literal:'):
                 raise error.RepoLookupError(_("branch '%s' does not exist")
                                             % pattern)
         else:
             return subset.filter(lambda r: matcher(getbranch(r)),
                                  condrepr=('<branch %r>', b))
 
     s = getset(repo, fullreposet(repo), x)
     b = set()
     for r in s:
         b.add(getbranch(r))
     c = s.__contains__
     return subset.filter(lambda r: c(r) or getbranch(r) in b,
                          condrepr=lambda: '<branch %r>' % _sortedb(b))
 
 @predicate('phasedivergent()', safe=True)
 def phasedivergent(repo, subset, x):
     """Mutable changesets marked as successors of public changesets.
 
     Only non-public and non-obsolete changesets can be `phasedivergent`.
     (EXPERIMENTAL)
     """
     # i18n: "phasedivergent" is a keyword
     getargs(x, 0, 0, _("phasedivergent takes no arguments"))
     phasedivergent = obsmod.getrevs(repo, 'phasedivergent')
     return subset & phasedivergent
 
 @predicate('bundle()', safe=True)
 def bundle(repo, subset, x):
     """Changesets in the bundle.
 
     Bundle must be specified by the -R option."""
 
     try:
         bundlerevs = repo.changelog.bundlerevs
     except AttributeError:
         raise error.Abort(_("no bundle provided - specify with -R"))
     return subset & bundlerevs
 
 def checkstatus(repo, subset, pat, field):
     hasset = matchmod.patkind(pat) == 'set'
 
     mcache = [None]
     def matches(x):
         c = repo[x]
         if not mcache[0] or hasset:
             mcache[0] = matchmod.match(repo.root, repo.getcwd(), [pat], ctx=c)
         m = mcache[0]
         fname = None
         if not m.anypats() and len(m.files()) == 1:
             fname = m.files()[0]
         if fname is not None:
             if fname not in c.files():
                 return False
         else:
             for f in c.files():
                 if m(f):
                     break
             else:
                 return False
         files = repo.status(c.p1().node(), c.node())[field]
         if fname is not None:
             if fname in files:
                 return True
         else:
             for f in files:
                 if m(f):
                     return True
 
     return subset.filter(matches, condrepr=('<status[%r] %r>', field, pat))
 
 def _children(repo, subset, parentset):
     if not parentset:
         return baseset()
     cs = set()
     pr = repo.changelog.parentrevs
     minrev = parentset.min()
     nullrev = node.nullrev
     for r in subset:
         if r <= minrev:
             continue
         p1, p2 = pr(r)
         if p1 in parentset:
             cs.add(r)
         if p2 != nullrev and p2 in parentset:
             cs.add(r)
     return baseset(cs)
 
 @predicate('children(set)', safe=True)
 def children(repo, subset, x):
     """Child changesets of changesets in set.
     """
     s = getset(repo, fullreposet(repo), x)
     cs = _children(repo, subset, s)
     return subset & cs
 
 @predicate('closed()', safe=True, weight=10)
 def closed(repo, subset, x):
     """Changeset is closed.
     """
     # i18n: "closed" is a keyword
     getargs(x, 0, 0, _("closed takes no arguments"))
     return subset.filter(lambda r: repo[r].closesbranch(),
                          condrepr='<branch closed>')
 
 @predicate('contains(pattern)', weight=100)
 def contains(repo, subset, x):
     """The revision's manifest contains a file matching pattern (but might not
     modify it). See :hg:`help patterns` for information about file patterns.
 
     The pattern without explicit kind like ``glob:`` is expected to be
     relative to the current directory and match against a file exactly
     for efficiency.
     """
     # i18n: "contains" is a keyword
     pat = getstring(x, _("contains requires a pattern"))
 
     def matches(x):
         if not matchmod.patkind(pat):
             pats = pathutil.canonpath(repo.root, repo.getcwd(), pat)
             if pats in repo[x]:
                 return True
         else:
             c = repo[x]
             m = matchmod.match(repo.root, repo.getcwd(), [pat], ctx=c)
             for f in c.manifest():
                 if m(f):
                     return True
         return False
 
     return subset.filter(matches, condrepr=('<contains %r>', pat))
 
 @predicate('converted([id])', safe=True)
 def converted(repo, subset, x):
     """Changesets converted from the given identifier in the old repository if
     present, or all converted changesets if no identifier is specified.
     """
 
     # There is exactly no chance of resolving the revision, so do a simple
     # string compare and hope for the best
 
     rev = None
     # i18n: "converted" is a keyword
     l = getargs(x, 0, 1, _('converted takes one or no arguments'))
     if l:
         # i18n: "converted" is a keyword
         rev = getstring(l[0], _('converted requires a revision'))
 
     def _matchvalue(r):
         source = repo[r].extra().get('convert_revision', None)
         return source is not None and (rev is None or source.startswith(rev))
 
     return subset.filter(lambda r: _matchvalue(r),
                          condrepr=('<converted %r>', rev))
 
 @predicate('date(interval)', safe=True, weight=10)
 def date(repo, subset, x):
     """Changesets within the interval, see :hg:`help dates`.
     """
     # i18n: "date" is a keyword
     ds = getstring(x, _("date requires a string"))
     dm = dateutil.matchdate(ds)
     return subset.filter(lambda x: dm(repo[x].date()[0]),
                          condrepr=('<date %r>', ds))
 
 @predicate('desc(string)', safe=True, weight=10)
 def desc(repo, subset, x):
     """Search commit message for string. The match is case-insensitive.
 
     Pattern matching is supported for `string`. See
     :hg:`help revisions.patterns`.
     """
     # i18n: "desc" is a keyword
     ds = getstring(x, _("desc requires a string"))
 
     kind, pattern, matcher = _substringmatcher(ds, casesensitive=False)
 
     return subset.filter(lambda r: matcher(repo[r].description()),
                          condrepr=('<desc %r>', ds))
 
 def _descendants(repo, subset, x, followfirst=False, startdepth=None,
                  stopdepth=None):
     roots = getset(repo, fullreposet(repo), x)
     if not roots:
         return baseset()
     s = dagop.revdescendants(repo, roots, followfirst, startdepth, stopdepth)
     return subset & s
 
 @predicate('descendants(set[, depth])', safe=True)
 def descendants(repo, subset, x):
     """Changesets which are descendants of changesets in set, including the
     given changesets themselves.
 
     If depth is specified, the result only includes changesets up to
     the specified generation.
     """
     # startdepth is for internal use only until we can decide the UI
     args = getargsdict(x, 'descendants', 'set depth startdepth')
     if 'set' not in args:
         # i18n: "descendants" is a keyword
         raise error.ParseError(_('descendants takes at least 1 argument'))
     startdepth = stopdepth = None
     if 'startdepth' in args:
         n = getinteger(args['startdepth'],
                        "descendants expects an integer startdepth")
         if n < 0:
             raise error.ParseError("negative startdepth")
         startdepth = n
     if 'depth' in args:
         # i18n: "descendants" is a keyword
         n = getinteger(args['depth'], _("descendants expects an integer depth"))
         if n < 0:
             raise error.ParseError(_("negative depth"))
         stopdepth = n + 1
     return _descendants(repo, subset, args['set'],
                         startdepth=startdepth, stopdepth=stopdepth)
 
 @predicate('_firstdescendants', safe=True)
 def _firstdescendants(repo, subset, x):
     # ``_firstdescendants(set)``
     # Like ``descendants(set)`` but follows only the first parents.
     return _descendants(repo, subset, x, followfirst=True)
 
 @predicate('destination([set])', safe=True, weight=10)
 def destination(repo, subset, x):
     """Changesets that were created by a graft, transplant or rebase operation,
     with the given revisions specified as the source.  Omitting the optional set
     is the same as passing all().
     """
     if x is not None:
         sources = getset(repo, fullreposet(repo), x)
     else:
         sources = fullreposet(repo)
 
     dests = set()
 
     # subset contains all of the possible destinations that can be returned, so
     # iterate over them and see if their source(s) were provided in the arg set.
     # Even if the immediate src of r is not in the arg set, src's source (or
     # further back) may be.  Scanning back further than the immediate src allows
     # transitive transplants and rebases to yield the same results as transitive
     # grafts.
     for r in subset:
         src = _getrevsource(repo, r)
         lineage = None
 
         while src is not None:
             if lineage is None:
                 lineage = list()
 
             lineage.append(r)
 
             # The visited lineage is a match if the current source is in the arg
             # set.  Since every candidate dest is visited by way of iterating
             # subset, any dests further back in the lineage will be tested by a
             # different iteration over subset.  Likewise, if the src was already
             # selected, the current lineage can be selected without going back
             # further.
             if src in sources or src in dests:
                 dests.update(lineage)
                 break
 
             r = src
             src = _getrevsource(repo, r)
 
     return subset.filter(dests.__contains__,
                          condrepr=lambda: '<destination %r>' % _sortedb(dests))
 
 @predicate('contentdivergent()', safe=True)
 def contentdivergent(repo, subset, x):
     """
     Final successors of changesets with an alternative set of final
     successors. (EXPERIMENTAL)
     """
     # i18n: "contentdivergent" is a keyword
     getargs(x, 0, 0, _("contentdivergent takes no arguments"))
     contentdivergent = obsmod.getrevs(repo, 'contentdivergent')
     return subset & contentdivergent
 
 @predicate('extdata(source)', safe=False, weight=100)
 def extdata(repo, subset, x):
     """Changesets in the specified extdata source. (EXPERIMENTAL)"""
     # i18n: "extdata" is a keyword
     args = getargsdict(x, 'extdata', 'source')
     source = getstring(args.get('source'),
                        # i18n: "extdata" is a keyword
                        _('extdata takes at least 1 string argument'))
     data = scmutil.extdatasource(repo, source)
     return subset & baseset(data)
 
 @predicate('extinct()', safe=True)
 def extinct(repo, subset, x):
     """Obsolete changesets with obsolete descendants only.
     """
     # i18n: "extinct" is a keyword
     getargs(x, 0, 0, _("extinct takes no arguments"))
     extincts = obsmod.getrevs(repo, 'extinct')
     return subset & extincts
 
 @predicate('extra(label, [value])', safe=True)
 def extra(repo, subset, x):
     """Changesets with the given label in the extra metadata, with the given
     optional value.
 
     Pattern matching is supported for `value`. See
     :hg:`help revisions.patterns`.
     """
     args = getargsdict(x, 'extra', 'label value')
     if 'label' not in args:
         # i18n: "extra" is a keyword
         raise error.ParseError(_('extra takes at least 1 argument'))
     # i18n: "extra" is a keyword
     label = getstring(args['label'], _('first argument to extra must be '
                                        'a string'))
     value = None
 
     if 'value' in args:
         # i18n: "extra" is a keyword
         value = getstring(args['value'], _('second argument to extra must be '
                                            'a string'))
         kind, value, matcher = stringutil.stringmatcher(value)
 
     def _matchvalue(r):
         extra = repo[r].extra()
         return label in extra and (value is None or matcher(extra[label]))
 
     return subset.filter(lambda r: _matchvalue(r),
                          condrepr=('<extra[%r] %r>', label, value))
 
 @predicate('filelog(pattern)', safe=True)
 def filelog(repo, subset, x):
     """Changesets connected to the specified filelog.
 
     For performance reasons, visits only revisions mentioned in the file-level
     filelog, rather than filtering through all changesets (much faster, but
     doesn't include deletes or duplicate changes). For a slower, more accurate
     result, use ``file()``.
 
     The pattern without explicit kind like ``glob:`` is expected to be
     relative to the current directory and match against a file exactly
     for efficiency.
 
     If some linkrev points to revisions filtered by the current repoview, we'll
     work around it to return a non-filtered value.
     """
 
     # i18n: "filelog" is a keyword
     pat = getstring(x, _("filelog requires a pattern"))
     s = set()
     cl = repo.changelog
 
     if not matchmod.patkind(pat):
         f = pathutil.canonpath(repo.root, repo.getcwd(), pat)
         files = [f]
     else:
         m = matchmod.match(repo.root, repo.getcwd(), [pat], ctx=repo[None])
         files = (f for f in repo[None] if m(f))
 
     for f in files:
         fl = repo.file(f)
         known = {}
         scanpos = 0
         for fr in list(fl):
             fn = fl.node(fr)
             if fn in known:
                 s.add(known[fn])
                 continue
 
             lr = fl.linkrev(fr)
             if lr in cl:
                 s.add(lr)
             elif scanpos is not None:
                 # lowest matching changeset is filtered, scan further
                 # ahead in changelog
                 start = max(lr, scanpos) + 1
                 scanpos = None
                 for r in cl.revs(start):
                     # minimize parsing of non-matching entries
                     if f in cl.revision(r) and f in cl.readfiles(r):
                         try:
                             # try to use manifest delta fastpath
                             n = repo[r].filenode(f)
                             if n not in known:
                                 if n == fn:
                                     s.add(r)
                                     scanpos = r
                                     break
                                 else:
                                     known[n] = r
                         except error.ManifestLookupError:
                             # deletion in changelog
                             continue
 
     return subset & s
 
 @predicate('first(set, [n])', safe=True, takeorder=True, weight=0)
 def first(repo, subset, x, order):
     """An alias for limit().
     """
     return limit(repo, subset, x, order)
 
 def _follow(repo, subset, x, name, followfirst=False):
     args = getargsdict(x, name, 'file startrev')
     revs = None
     if 'startrev' in args:
         revs = getset(repo, fullreposet(repo), args['startrev'])
     if 'file' in args:
         x = getstring(args['file'], _("%s expected a pattern") % name)
         if revs is None:
             revs = [None]
         fctxs = []
         for r in revs:
             ctx = mctx = repo[r]
             if r is None:
                 ctx = repo['.']
             m = matchmod.match(repo.root, repo.getcwd(), [x],
                                ctx=mctx, default='path')
             fctxs.extend(ctx[f].introfilectx() for f in ctx.manifest().walk(m))
         s = dagop.filerevancestors(fctxs, followfirst)
     else:
         if revs is None:
             revs = baseset([repo['.'].rev()])
         s = dagop.revancestors(repo, revs, followfirst)
 
     return subset & s
 
 @predicate('follow([file[, startrev]])', safe=True)
 def follow(repo, subset, x):
     """
     An alias for ``::.`` (ancestors of the working directory's first parent).
     If file pattern is specified, the histories of files matching given
     pattern in the revision given by startrev are followed, including copies.
     """
     return _follow(repo, subset, x, 'follow')
 
 @predicate('_followfirst', safe=True)
 def _followfirst(repo, subset, x):
     # ``followfirst([file[, startrev]])``
     # Like ``follow([file[, startrev]])`` but follows only the first parent
     # of every revisions or files revisions.
     return _follow(repo, subset, x, '_followfirst', followfirst=True)
 
 @predicate('followlines(file, fromline:toline[, startrev=., descend=False])',
            safe=True)
 def followlines(repo, subset, x):
     """Changesets modifying `file` in line range ('fromline', 'toline').
 
     Line range corresponds to 'file' content at 'startrev' and should hence be
     consistent with file size. If startrev is not specified, working directory's
     parent is used.
 
     By default, ancestors of 'startrev' are returned. If 'descend' is True,
     descendants of 'startrev' are returned though renames are (currently) not
     followed in this direction.
     """
     args = getargsdict(x, 'followlines', 'file *lines startrev descend')
     if len(args['lines']) != 1:
         raise error.ParseError(_("followlines requires a line range"))
 
     rev = '.'
     if 'startrev' in args:
         revs = getset(repo, fullreposet(repo), args['startrev'])
         if len(revs) != 1:
             raise error.ParseError(
                 # i18n: "followlines" is a keyword
                 _("followlines expects exactly one revision"))
         rev = revs.last()
 
     pat = getstring(args['file'], _("followlines requires a pattern"))
     # i18n: "followlines" is a keyword
     msg = _("followlines expects exactly one file")
     fname = scmutil.parsefollowlinespattern(repo, rev, pat, msg)
     # i18n: "followlines" is a keyword
     lr = getrange(args['lines'][0], _("followlines expects a line range"))
     fromline, toline = [getinteger(a, _("line range bounds must be integers"))
                         for a in lr]
     fromline, toline = util.processlinerange(fromline, toline)
 
     fctx = repo[rev].filectx(fname)
     descend = False
     if 'descend' in args:
         descend = getboolean(args['descend'],
                              # i18n: "descend" is a keyword
                              _("descend argument must be a boolean"))
     if descend:
         rs = generatorset(
             (c.rev() for c, _linerange
              in dagop.blockdescendants(fctx, fromline, toline)),
             iterasc=True)
     else:
         rs = generatorset(
             (c.rev() for c, _linerange
              in dagop.blockancestors(fctx, fromline, toline)),
             iterasc=False)
     return subset & rs
 
 @predicate('all()', safe=True)
 def getall(repo, subset, x):
     """All changesets, the same as ``0:tip``.
     """
     # i18n: "all" is a keyword
     getargs(x, 0, 0, _("all takes no arguments"))
     return subset & spanset(repo)  # drop "null" if any
 
 @predicate('grep(regex)', weight=10)
 def grep(repo, subset, x):
     """Like ``keyword(string)`` but accepts a regex. Use ``grep(r'...')``
     to ensure special escape characters are handled correctly. Unlike
     ``keyword(string)``, the match is case-sensitive.
     """
     try:
         # i18n: "grep" is a keyword
         gr = re.compile(getstring(x, _("grep requires a string")))
     except re.error as e:
         raise error.ParseError(
             _('invalid match pattern: %s') % stringutil.forcebytestr(e))
 
     def matches(x):
         c = repo[x]
         for e in c.files() + [c.user(), c.description()]:
             if gr.search(e):
                 return True
         return False
 
     return subset.filter(matches, condrepr=('<grep %r>', gr.pattern))
 
 @predicate('_matchfiles', safe=True)
 def _matchfiles(repo, subset, x):
     # _matchfiles takes a revset list of prefixed arguments:
     #
     #   [p:foo, i:bar, x:baz]
     #
     # builds a match object from them and filters subset. Allowed
     # prefixes are 'p:' for regular patterns, 'i:' for include
     # patterns and 'x:' for exclude patterns. Use 'r:' prefix to pass
     # a revision identifier, or the empty string to reference the
     # working directory, from which the match object is
     # initialized. Use 'd:' to set the default matching mode, default
     # to 'glob'. At most one 'r:' and 'd:' argument can be passed.
 
     l = getargs(x, 1, -1, "_matchfiles requires at least one argument")
     pats, inc, exc = [], [], []
     rev, default = None, None
     for arg in l:
         s = getstring(arg, "_matchfiles requires string arguments")
         prefix, value = s[:2], s[2:]
         if prefix == 'p:':
             pats.append(value)
         elif prefix == 'i:':
             inc.append(value)
         elif prefix == 'x:':
             exc.append(value)
         elif prefix == 'r:':
             if rev is not None:
                 raise error.ParseError('_matchfiles expected at most one '
                                        'revision')
             if value == '': # empty means working directory
                 rev = node.wdirrev
             else:
                 rev = value
         elif prefix == 'd:':
             if default is not None:
                 raise error.ParseError('_matchfiles expected at most one '
                                        'default mode')
             default = value
         else:
             raise error.ParseError('invalid _matchfiles prefix: %s' % prefix)
     if not default:
         default = 'glob'
     hasset = any(matchmod.patkind(p) == 'set' for p in pats + inc + exc)
 
     mcache = [None]
 
     # This directly read the changelog data as creating changectx for all
     # revisions is quite expensive.
     getfiles = repo.changelog.readfiles
     wdirrev = node.wdirrev
     def matches(x):
         if x == wdirrev:
             files = repo[x].files()
         else:
             files = getfiles(x)
 
         if not mcache[0] or (hasset and rev is None):
             r = x if rev is None else rev
             mcache[0] = matchmod.match(repo.root, repo.getcwd(), pats,
                                        include=inc, exclude=exc, ctx=repo[r],
                                        default=default)
         m = mcache[0]
 
         for f in files:
             if m(f):
                 return True
         return False
 
     return subset.filter(matches,
                          condrepr=('<matchfiles patterns=%r, include=%r '
                                    'exclude=%r, default=%r, rev=%r>',
                                    pats, inc, exc, default, rev))
 
 @predicate('file(pattern)', safe=True, weight=10)
 def hasfile(repo, subset, x):
     """Changesets affecting files matched by pattern.
 
     For a faster but less accurate result, consider using ``filelog()``
     instead.
 
     This predicate uses ``glob:`` as the default kind of pattern.
     """
     # i18n: "file" is a keyword
     pat = getstring(x, _("file requires a pattern"))
     return _matchfiles(repo, subset, ('string', 'p:' + pat))
 
 @predicate('head()', safe=True)
 def head(repo, subset, x):
     """Changeset is a named branch head.
     """
     # i18n: "head" is a keyword
     getargs(x, 0, 0, _("head takes no arguments"))
     hs = set()
     cl = repo.changelog
     for ls in repo.branchmap().itervalues():
         hs.update(cl.rev(h) for h in ls)
     return subset & baseset(hs)
 
 @predicate('heads(set)', safe=True, takeorder=True)
 def heads(repo, subset, x, order):
     """Members of set with no children in set.
     """
     # argument set should never define order
     if order == defineorder:
         order = followorder
     s = getset(repo, subset, x, order=order)
     ps = parents(repo, subset, x)
     return s - ps
 
 @predicate('hidden()', safe=True)
 def hidden(repo, subset, x):
     """Hidden changesets.
     """
     # i18n: "hidden" is a keyword
     getargs(x, 0, 0, _("hidden takes no arguments"))
     hiddenrevs = repoview.filterrevs(repo, 'visible')
     return subset & hiddenrevs
 
 @predicate('keyword(string)', safe=True, weight=10)
 def keyword(repo, subset, x):
     """Search commit message, user name, and names of changed files for
     string. The match is case-insensitive.
 
     For a regular expression or case sensitive search of these fields, use
     ``grep(regex)``.
     """
     # i18n: "keyword" is a keyword
     kw = encoding.lower(getstring(x, _("keyword requires a string")))
 
     def matches(r):
         c = repo[r]
         return any(kw in encoding.lower(t)
                    for t in c.files() + [c.user(), c.description()])
 
     return subset.filter(matches, condrepr=('<keyword %r>', kw))
 
 @predicate('limit(set[, n[, offset]])', safe=True, takeorder=True, weight=0)
 def limit(repo, subset, x, order):
     """First n members of set, defaulting to 1, starting from offset.
     """
     args = getargsdict(x, 'limit', 'set n offset')
     if 'set' not in args:
         # i18n: "limit" is a keyword
         raise error.ParseError(_("limit requires one to three arguments"))
     # i18n: "limit" is a keyword
     lim = getinteger(args.get('n'), _("limit expects a number"), default=1)
     if lim < 0:
         raise error.ParseError(_("negative number to select"))
     # i18n: "limit" is a keyword
     ofs = getinteger(args.get('offset'), _("limit expects a number"), default=0)
     if ofs < 0:
         raise error.ParseError(_("negative offset"))
     os = getset(repo, fullreposet(repo), args['set'])
     ls = os.slice(ofs, ofs + lim)
     if order == followorder and lim > 1:
         return subset & ls
     return ls & subset
 
 @predicate('last(set, [n])', safe=True, takeorder=True)
 def last(repo, subset, x, order):
     """Last n members of set, defaulting to 1.
     """
     # i18n: "last" is a keyword
     l = getargs(x, 1, 2, _("last requires one or two arguments"))
     lim = 1
     if len(l) == 2:
         # i18n: "last" is a keyword
         lim = getinteger(l[1], _("last expects a number"))
     if lim < 0:
         raise error.ParseError(_("negative number to select"))
     os = getset(repo, fullreposet(repo), l[0])
     os.reverse()
     ls = os.slice(0, lim)
     if order == followorder and lim > 1:
         return subset & ls
     ls.reverse()
     return ls & subset
 
 @predicate('max(set)', safe=True)
 def maxrev(repo, subset, x):
     """Changeset with highest revision number in set.
     """
     os = getset(repo, fullreposet(repo), x)
     try:
         m = os.max()
         if m in subset:
             return baseset([m], datarepr=('<max %r, %r>', subset, os))
     except ValueError:
         # os.max() throws a ValueError when the collection is empty.
         # Same as python's max().
         pass
     return baseset(datarepr=('<max %r, %r>', subset, os))
 
 @predicate('merge()', safe=True)
 def merge(repo, subset, x):
     """Changeset is a merge changeset.
     """
     # i18n: "merge" is a keyword
     getargs(x, 0, 0, _("merge takes no arguments"))
     cl = repo.changelog
     return subset.filter(lambda r: cl.parentrevs(r)[1] != -1,
                          condrepr='<merge>')
 
 @predicate('branchpoint()', safe=True)
 def branchpoint(repo, subset, x):
     """Changesets with more than one child.
     """
     # i18n: "branchpoint" is a keyword
     getargs(x, 0, 0, _("branchpoint takes no arguments"))
     cl = repo.changelog
     if not subset:
         return baseset()
     # XXX this should be 'parentset.min()' assuming 'parentset' is a smartset
     # (and if it is not, it should.)
     baserev = min(subset)
     parentscount = [0]*(len(repo) - baserev)
     for r in cl.revs(start=baserev + 1):
         for p in cl.parentrevs(r):
             if p >= baserev:
                 parentscount[p - baserev] += 1
     return subset.filter(lambda r: parentscount[r - baserev] > 1,
                          condrepr='<branchpoint>')
 
 @predicate('min(set)', safe=True)
 def minrev(repo, subset, x):
     """Changeset with lowest revision number in set.
     """
     os = getset(repo, fullreposet(repo), x)
     try:
         m = os.min()
         if m in subset:
             return baseset([m], datarepr=('<min %r, %r>', subset, os))
     except ValueError:
         # os.min() throws a ValueError when the collection is empty.
         # Same as python's min().
         pass
     return baseset(datarepr=('<min %r, %r>', subset, os))
 
 @predicate('modifies(pattern)', safe=True, weight=30)
 def modifies(repo, subset, x):
     """Changesets modifying files matched by pattern.
 
     The pattern without explicit kind like ``glob:`` is expected to be
     relative to the current directory and match against a file or a
     directory.
     """
     # i18n: "modifies" is a keyword
     pat = getstring(x, _("modifies requires a pattern"))
     return checkstatus(repo, subset, pat, 0)
 
 @predicate('named(namespace)')
 def named(repo, subset, x):
     """The changesets in a given namespace.
 
     Pattern matching is supported for `namespace`. See
     :hg:`help revisions.patterns`.
     """
     # i18n: "named" is a keyword
     args = getargs(x, 1, 1, _('named requires a namespace argument'))
 
     ns = getstring(args[0],
                    # i18n: "named" is a keyword
                    _('the argument to named must be a string'))
     kind, pattern, matcher = stringutil.stringmatcher(ns)
     namespaces = set()
     if kind == 'literal':
         if pattern not in repo.names:
             raise error.RepoLookupError(_("namespace '%s' does not exist")
                                         % ns)
         namespaces.add(repo.names[pattern])
     else:
         for name, ns in repo.names.iteritems():
             if matcher(name):
                 namespaces.add(ns)
         if not namespaces:
             raise error.RepoLookupError(_("no namespace exists"
                                           " that match '%s'") % pattern)
 
     names = set()
     for ns in namespaces:
         for name in ns.listnames(repo):
             if name not in ns.deprecated:
                 names.update(repo[n].rev() for n in ns.nodes(repo, name))
 
     names -= {node.nullrev}
     return subset & names
 
 @predicate('id(string)', safe=True)
 def node_(repo, subset, x):
     """Revision non-ambiguously specified by the given hex string prefix.
     """
     # i18n: "id" is a keyword
     l = getargs(x, 1, 1, _("id requires one argument"))
     # i18n: "id" is a keyword
     n = getstring(l[0], _("id requires a string"))
     if len(n) == 40:
         try:
             rn = repo.changelog.rev(node.bin(n))
         except error.WdirUnsupported:
             rn = node.wdirrev
         except (LookupError, TypeError):
             rn = None
     else:
         rn = None
         try:
             pm = scmutil.resolvehexnodeidprefix(repo, n)
             if pm is not None:
                 rn = repo.changelog.rev(pm)
         except LookupError:
             pass
         except error.WdirUnsupported:
             rn = node.wdirrev
 
     if rn is None:
         return baseset()
     result = baseset([rn])
     return result & subset
 
 @predicate('none()', safe=True)
 def none(repo, subset, x):
     """No changesets.
     """
     # i18n: "none" is a keyword
     getargs(x, 0, 0, _("none takes no arguments"))
     return baseset()
 
 @predicate('obsolete()', safe=True)
 def obsolete(repo, subset, x):
     """Mutable changeset with a newer version."""
     # i18n: "obsolete" is a keyword
     getargs(x, 0, 0, _("obsolete takes no arguments"))
     obsoletes = obsmod.getrevs(repo, 'obsolete')
     return subset & obsoletes
 
 @predicate('only(set, [set])', safe=True)
 def only(repo, subset, x):
     """Changesets that are ancestors of the first set that are not ancestors
     of any other head in the repo. If a second set is specified, the result
     is ancestors of the first set that are not ancestors of the second set
     (i.e. ::<set1> - ::<set2>).
     """
     cl = repo.changelog
     # i18n: "only" is a keyword
     args = getargs(x, 1, 2, _('only takes one or two arguments'))
     include = getset(repo, fullreposet(repo), args[0])
     if len(args) == 1:
         if not include:
             return baseset()
 
         descendants = set(dagop.revdescendants(repo, include, False))
         exclude = [rev for rev in cl.headrevs()
             if not rev in descendants and not rev in include]
     else:
         exclude = getset(repo, fullreposet(repo), args[1])
 
     results = set(cl.findmissingrevs(common=exclude, heads=include))
     # XXX we should turn this into a baseset instead of a set, smartset may do
     # some optimizations from the fact this is a baseset.
     return subset & results
 
 @predicate('origin([set])', safe=True)
 def origin(repo, subset, x):
     """
     Changesets that were specified as a source for the grafts, transplants or
     rebases that created the given revisions.  Omitting the optional set is the
     same as passing all().  If a changeset created by these operations is itself
     specified as a source for one of these operations, only the source changeset
     for the first operation is selected.
     """
     if x is not None:
         dests = getset(repo, fullreposet(repo), x)
     else:
         dests = fullreposet(repo)
 
     def _firstsrc(rev):
         src = _getrevsource(repo, rev)
         if src is None:
             return None
 
         while True:
             prev = _getrevsource(repo, src)
 
             if prev is None:
                 return src
             src = prev
 
     o = {_firstsrc(r) for r in dests}
     o -= {None}
     # XXX we should turn this into a baseset instead of a set, smartset may do
     # some optimizations from the fact this is a baseset.
     return subset & o
 
 @predicate('outgoing([path])', safe=False, weight=10)
 def outgoing(repo, subset, x):
     """Changesets not found in the specified destination repository, or the
     default push location.
     """
     # Avoid cycles.
     from . import (
         discovery,
         hg,
     )
     # i18n: "outgoing" is a keyword
     l = getargs(x, 0, 1, _("outgoing takes one or no arguments"))
     # i18n: "outgoing" is a keyword
     dest = l and getstring(l[0], _("outgoing requires a repository path")) or ''
     if not dest:
         # ui.paths.getpath() explicitly tests for None, not just a boolean
         dest = None
     path = repo.ui.paths.getpath(dest, default=('default-push', 'default'))
     if not path:
         raise error.Abort(_('default repository not configured!'),
                 hint=_("see 'hg help config.paths'"))
     dest = path.pushloc or path.loc
     branches = path.branch, []
 
     revs, checkout = hg.addbranchrevs(repo, repo, branches, [])
     if revs:
         revs = [repo.lookup(rev) for rev in revs]
     other = hg.peer(repo, {}, dest)
     repo.ui.pushbuffer()
     outgoing = discovery.findcommonoutgoing(repo, other, onlyheads=revs)
     repo.ui.popbuffer()
     cl = repo.changelog
     o = {cl.rev(r) for r in outgoing.missing}
     return subset & o
 
 @predicate('p1([set])', safe=True)
 def p1(repo, subset, x):
     """First parent of changesets in set, or the working directory.
     """
     if x is None:
         p = repo[x].p1().rev()
         if p >= 0:
             return subset & baseset([p])
         return baseset()
 
     ps = set()
     cl = repo.changelog
     for r in getset(repo, fullreposet(repo), x):
         try:
             ps.add(cl.parentrevs(r)[0])
         except error.WdirUnsupported:
             ps.add(repo[r].parents()[0].rev())
     ps -= {node.nullrev}
     # XXX we should turn this into a baseset instead of a set, smartset may do
     # some optimizations from the fact this is a baseset.
     return subset & ps
 
 @predicate('p2([set])', safe=True)
 def p2(repo, subset, x):
     """Second parent of changesets in set, or the working directory.
     """
     if x is None:
         ps = repo[x].parents()
         try:
             p = ps[1].rev()
             if p >= 0:
                 return subset & baseset([p])
             return baseset()
         except IndexError:
             return baseset()
 
     ps = set()
     cl = repo.changelog
     for r in getset(repo, fullreposet(repo), x):
         try:
             ps.add(cl.parentrevs(r)[1])
         except error.WdirUnsupported:
             parents = repo[r].parents()
             if len(parents) == 2:
                 ps.add(parents[1])
     ps -= {node.nullrev}
     # XXX we should turn this into a baseset instead of a set, smartset may do
     # some optimizations from the fact this is a baseset.
     return subset & ps
 
 def parentpost(repo, subset, x, order):
     return p1(repo, subset, x)
 
 @predicate('parents([set])', safe=True)
 def parents(repo, subset, x):
     """
     The set of all parents for all changesets in set, or the working directory.
     """
     if x is None:
         ps = set(p.rev() for p in repo[x].parents())
     else:
         ps = set()
         cl = repo.changelog
         up = ps.update
         parentrevs = cl.parentrevs
         for r in getset(repo, fullreposet(repo), x):
             try:
                 up(parentrevs(r))
             except error.WdirUnsupported:
                 up(p.rev() for p in repo[r].parents())
     ps -= {node.nullrev}
     return subset & ps
 
 def _phase(repo, subset, *targets):
     """helper to select all rev in <targets> phases"""
     return repo._phasecache.getrevset(repo, targets, subset)
 
 @predicate('draft()', safe=True)
 def draft(repo, subset, x):
     """Changeset in draft phase."""
     # i18n: "draft" is a keyword
     getargs(x, 0, 0, _("draft takes no arguments"))
     target = phases.draft
     return _phase(repo, subset, target)
 
 @predicate('secret()', safe=True)
 def secret(repo, subset, x):
     """Changeset in secret phase."""
     # i18n: "secret" is a keyword
     getargs(x, 0, 0, _("secret takes no arguments"))
     target = phases.secret
     return _phase(repo, subset, target)
 
 @predicate('stack([revs])', safe=True)
 def stack(repo, subset, x):
     """Experimental revset for the stack of changesets or working directory
     parent. (EXPERIMENTAL)
     """
     if x is None:
         stacks = stackmod.getstack(repo, x)
     else:
         stacks = smartset.baseset([])
         for revision in getset(repo, fullreposet(repo), x):
             currentstack = stackmod.getstack(repo, revision)
             stacks = stacks + currentstack
 
     return subset & stacks
 
 def parentspec(repo, subset, x, n, order):
     """``set^0``
     The set.
     ``set^1`` (or ``set^``), ``set^2``
     First or second parent, respectively, of all changesets in set.
     """
     try:
         n = int(n[1])
         if n not in (0, 1, 2):
             raise ValueError
     except (TypeError, ValueError):
         raise error.ParseError(_("^ expects a number 0, 1, or 2"))
     ps = set()
     cl = repo.changelog
     for r in getset(repo, fullreposet(repo), x):
         if n == 0:
             ps.add(r)
         elif n == 1:
             try:
                 ps.add(cl.parentrevs(r)[0])
             except error.WdirUnsupported:
                 ps.add(repo[r].parents()[0].rev())
         else:
             try:
                 parents = cl.parentrevs(r)
                 if parents[1] != node.nullrev:
                     ps.add(parents[1])
             except error.WdirUnsupported:
                 parents = repo[r].parents()
                 if len(parents) == 2:
                     ps.add(parents[1].rev())
     return subset & ps
 
 @predicate('present(set)', safe=True, takeorder=True)
 def present(repo, subset, x, order):
     """An empty set, if any revision in set isn't found; otherwise,
     all revisions in set.
 
     If any of specified revisions is not present in the local repository,
     the query is normally aborted. But this predicate allows the query
     to continue even in such cases.
     """
     try:
         return getset(repo, subset, x, order)
     except error.RepoLookupError:
         return baseset()
 
 # for internal use
 @predicate('_notpublic', safe=True)
 def _notpublic(repo, subset, x):
     getargs(x, 0, 0, "_notpublic takes no arguments")
     return _phase(repo, subset, phases.draft, phases.secret)
 
 # for internal use
 @predicate('_phaseandancestors(phasename, set)', safe=True)
 def _phaseandancestors(repo, subset, x):
     # equivalent to (phasename() & ancestors(set)) but more efficient
     # phasename could be one of 'draft', 'secret', or '_notpublic'
     args = getargs(x, 2, 2, "_phaseandancestors requires two arguments")
     phasename = getsymbol(args[0])
     s = getset(repo, fullreposet(repo), args[1])
 
     draft = phases.draft
     secret = phases.secret
     phasenamemap = {
         '_notpublic': draft,
         'draft': draft, # follow secret's ancestors
         'secret': secret,
     }
     if phasename not in phasenamemap:
         raise error.ParseError('%r is not a valid phasename' % phasename)
 
     minimalphase = phasenamemap[phasename]
     getphase = repo._phasecache.phase
 
     def cutfunc(rev):
         return getphase(repo, rev) < minimalphase
 
     revs = dagop.revancestors(repo, s, cutfunc=cutfunc)
 
     if phasename == 'draft': # need to remove secret changesets
         revs = revs.filter(lambda r: getphase(repo, r) == draft)
     return subset & revs
 
 @predicate('public()', safe=True)
 def public(repo, subset, x):
     """Changeset in public phase."""
     # i18n: "public" is a keyword
     getargs(x, 0, 0, _("public takes no arguments"))
     return _phase(repo, subset, phases.public)
 
 @predicate('remote([id [,path]])', safe=False)
 def remote(repo, subset, x):
     """Local revision that corresponds to the given identifier in a
     remote repository, if present. Here, the '.' identifier is a
     synonym for the current local branch.
     """
 
     from . import hg # avoid start-up nasties
     # i18n: "remote" is a keyword
     l = getargs(x, 0, 2, _("remote takes zero, one, or two arguments"))
 
     q = '.'
     if len(l) > 0:
     # i18n: "remote" is a keyword
         q = getstring(l[0], _("remote requires a string id"))
     if q == '.':
         q = repo['.'].branch()
 
     dest = ''
     if len(l) > 1:
         # i18n: "remote" is a keyword
         dest = getstring(l[1], _("remote requires a repository path"))
     dest = repo.ui.expandpath(dest or 'default')
     dest, branches = hg.parseurl(dest)
     revs, checkout = hg.addbranchrevs(repo, repo, branches, [])
     if revs:
         revs = [repo.lookup(rev) for rev in revs]
     other = hg.peer(repo, {}, dest)
     n = other.lookup(q)
     if n in repo:
         r = repo[n].rev()
         if r in subset:
             return baseset([r])
     return baseset()
 
 @predicate('removes(pattern)', safe=True, weight=30)
 def removes(repo, subset, x):
     """Changesets which remove files matching pattern.
 
     The pattern without explicit kind like ``glob:`` is expected to be
     relative to the current directory and match against a file or a
     directory.
     """
     # i18n: "removes" is a keyword
     pat = getstring(x, _("removes requires a pattern"))
     return checkstatus(repo, subset, pat, 2)
 
 @predicate('rev(number)', safe=True)
 def rev(repo, subset, x):
     """Revision with the given numeric identifier.
     """
     # i18n: "rev" is a keyword
     l = getargs(x, 1, 1, _("rev requires one argument"))
     try:
         # i18n: "rev" is a keyword
         l = int(getstring(l[0], _("rev requires a number")))
     except (TypeError, ValueError):
         # i18n: "rev" is a keyword
         raise error.ParseError(_("rev expects a number"))
     if l not in repo.changelog and l not in (node.nullrev, node.wdirrev):
         return baseset()
     return subset & baseset([l])
 
 @predicate('matching(revision [, field])', safe=True)
 def matching(repo, subset, x):
     """Changesets in which a given set of fields match the set of fields in the
     selected revision or set.
 
     To match more than one field pass the list of fields to match separated
     by spaces (e.g. ``author description``).
 
     Valid fields are most regular revision fields and some special fields.
 
     Regular revision fields are ``description``, ``author``, ``branch``,
     ``date``, ``files``, ``phase``, ``parents``, ``substate``, ``user``
     and ``diff``.
     Note that ``author`` and ``user`` are synonyms. ``diff`` refers to the
     contents of the revision. Two revisions matching their ``diff`` will
     also match their ``files``.
 
     Special fields are ``summary`` and ``metadata``:
     ``summary`` matches the first line of the description.
     ``metadata`` is equivalent to matching ``description user date``
     (i.e. it matches the main metadata fields).
 
     ``metadata`` is the default field which is used when no fields are
     specified. You can match more than one field at a time.
     """
     # i18n: "matching" is a keyword
     l = getargs(x, 1, 2, _("matching takes 1 or 2 arguments"))
 
     revs = getset(repo, fullreposet(repo), l[0])
 
     fieldlist = ['metadata']
     if len(l) > 1:
             fieldlist = getstring(l[1],
                 # i18n: "matching" is a keyword
                 _("matching requires a string "
                 "as its second argument")).split()
 
     # Make sure that there are no repeated fields,
     # expand the 'special' 'metadata' field type
     # and check the 'files' whenever we check the 'diff'
     fields = []
     for field in fieldlist:
         if field == 'metadata':
             fields += ['user', 'description', 'date']
         elif field == 'diff':
             # a revision matching the diff must also match the files
             # since matching the diff is very costly, make sure to
             # also match the files first
             fields += ['files', 'diff']
         else:
             if field == 'author':
                 field = 'user'
             fields.append(field)
     fields = set(fields)
     if 'summary' in fields and 'description' in fields:
         # If a revision matches its description it also matches its summary
         fields.discard('summary')
 
     # We may want to match more than one field
     # Not all fields take the same amount of time to be matched
     # Sort the selected fields in order of increasing matching cost
     fieldorder = ['phase', 'parents', 'user', 'date', 'branch', 'summary',
         'files', 'description', 'substate', 'diff']
     def fieldkeyfunc(f):
         try:
             return fieldorder.index(f)
         except ValueError:
             # assume an unknown field is very costly
             return len(fieldorder)
     fields = list(fields)
     fields.sort(key=fieldkeyfunc)
 
     # Each field will be matched with its own "getfield" function
     # which will be added to the getfieldfuncs array of functions
     getfieldfuncs = []
     _funcs = {
         'user': lambda r: repo[r].user(),
         'branch': lambda r: repo[r].branch(),
         'date': lambda r: repo[r].date(),
         'description': lambda r: repo[r].description(),
         'files': lambda r: repo[r].files(),
         'parents': lambda r: repo[r].parents(),
         'phase': lambda r: repo[r].phase(),
         'substate': lambda r: repo[r].substate,
         'summary': lambda r: repo[r].description().splitlines()[0],
         'diff': lambda r: list(repo[r].diff(
-            opts=diffutil.diffopts(repo.ui, {'git': True}))),
+            opts=diffutil.diffallopts(repo.ui, {'git': True}))),
     }
     for info in fields:
         getfield = _funcs.get(info, None)
         if getfield is None:
             raise error.ParseError(
                 # i18n: "matching" is a keyword
                 _("unexpected field name passed to matching: %s") % info)
         getfieldfuncs.append(getfield)
     # convert the getfield array of functions into a "getinfo" function
     # which returns an array of field values (or a single value if there
     # is only one field to match)
     getinfo = lambda r: [f(r) for f in getfieldfuncs]
 
     def matches(x):
         for rev in revs:
             target = getinfo(rev)
             match = True
             for n, f in enumerate(getfieldfuncs):
                 if target[n] != f(x):
                     match = False
             if match:
                 return True
         return False
 
     return subset.filter(matches, condrepr=('<matching%r %r>', fields, revs))
 
 @predicate('reverse(set)', safe=True, takeorder=True, weight=0)
 def reverse(repo, subset, x, order):
     """Reverse order of set.
     """
     l = getset(repo, subset, x, order)
     if order == defineorder:
         l.reverse()
     return l
 
 @predicate('roots(set)', safe=True)
 def roots(repo, subset, x):
     """Changesets in set with no parent changeset in set.
     """
     s = getset(repo, fullreposet(repo), x)
     parents = repo.changelog.parentrevs
     def filter(r):
         for p in parents(r):
             if 0 <= p and p in s:
                 return False
         return True
     return subset & s.filter(filter, condrepr='<roots>')
 
 _sortkeyfuncs = {
     'rev': lambda c: c.rev(),
     'branch': lambda c: c.branch(),
     'desc': lambda c: c.description(),
     'user': lambda c: c.user(),
     'author': lambda c: c.user(),
     'date': lambda c: c.date()[0],
 }
 
 def _getsortargs(x):
     """Parse sort options into (set, [(key, reverse)], opts)"""
     args = getargsdict(x, 'sort', 'set keys topo.firstbranch')
     if 'set' not in args:
         # i18n: "sort" is a keyword
         raise error.ParseError(_('sort requires one or two arguments'))
     keys = "rev"
     if 'keys' in args:
         # i18n: "sort" is a keyword
         keys = getstring(args['keys'], _("sort spec must be a string"))
 
     keyflags = []
     for k in keys.split():
         fk = k
         reverse = (k.startswith('-'))
         if reverse:
             k = k[1:]
         if k not in _sortkeyfuncs and k != 'topo':
             raise error.ParseError(
                 _("unknown sort key %r") % pycompat.bytestr(fk))
         keyflags.append((k, reverse))
 
     if len(keyflags) > 1 and any(k == 'topo' for k, reverse in keyflags):
         # i18n: "topo" is a keyword
         raise error.ParseError(_('topo sort order cannot be combined '
                                  'with other sort keys'))
 
     opts = {}
     if 'topo.firstbranch' in args:
         if any(k == 'topo' for k, reverse in keyflags):
             opts['topo.firstbranch'] = args['topo.firstbranch']
         else:
             # i18n: "topo" and "topo.firstbranch" are keywords
             raise error.ParseError(_('topo.firstbranch can only be used '
                                      'when using the topo sort key'))
 
     return args['set'], keyflags, opts
 
 @predicate('sort(set[, [-]key... [, ...]])', safe=True, takeorder=True,
            weight=10)
 def sort(repo, subset, x, order):
     """Sort set by keys. The default sort order is ascending, specify a key
     as ``-key`` to sort in descending order.
 
     The keys can be:
 
     - ``rev`` for the revision number,
     - ``branch`` for the branch name,
     - ``desc`` for the commit message (description),
     - ``user`` for user name (``author`` can be used as an alias),
     - ``date`` for the commit date
     - ``topo`` for a reverse topographical sort
 
     The ``topo`` sort order cannot be combined with other sort keys. This sort
     takes one optional argument, ``topo.firstbranch``, which takes a revset that
     specifies what topographical branches to prioritize in the sort.
 
     """
     s, keyflags, opts = _getsortargs(x)
     revs = getset(repo, subset, s, order)
 
     if not keyflags or order != defineorder:
         return revs
     if len(keyflags) == 1 and keyflags[0][0] == "rev":
         revs.sort(reverse=keyflags[0][1])
         return revs
     elif keyflags[0][0] == "topo":
         firstbranch = ()
         if 'topo.firstbranch' in opts:
             firstbranch = getset(repo, subset, opts['topo.firstbranch'])
         revs = baseset(dagop.toposort(revs, repo.changelog.parentrevs,
                                       firstbranch),
                        istopo=True)
         if keyflags[0][1]:
             revs.reverse()
         return revs
 
     # sort() is guaranteed to be stable
     ctxs = [repo[r] for r in revs]
     for k, reverse in reversed(keyflags):
         ctxs.sort(key=_sortkeyfuncs[k], reverse=reverse)
     return baseset([c.rev() for c in ctxs])
 
 @predicate('subrepo([pattern])')
 def subrepo(repo, subset, x):
     """Changesets that add, modify or remove the given subrepo.  If no subrepo
     pattern is named, any subrepo changes are returned.
     """
     # i18n: "subrepo" is a keyword
     args = getargs(x, 0, 1, _('subrepo takes at most one argument'))
     pat = None
     if len(args) != 0:
         pat = getstring(args[0], _("subrepo requires a pattern"))
 
     m = matchmod.exact(repo.root, repo.root, ['.hgsubstate'])
 
     def submatches(names):
         k, p, m = stringutil.stringmatcher(pat)
         for name in names:
             if m(name):
                 yield name
 
     def matches(x):
         c = repo[x]
         s = repo.status(c.p1().node(), c.node(), match=m)
 
         if pat is None:
             return s.added or s.modified or s.removed
 
         if s.added:
             return any(submatches(c.substate.keys()))
 
         if s.modified:
             subs = set(c.p1().substate.keys())
             subs.update(c.substate.keys())
 
             for path in submatches(subs):
                 if c.p1().substate.get(path) != c.substate.get(path):
                     return True
 
         if s.removed:
             return any(submatches(c.p1().substate.keys()))
 
         return False
 
     return subset.filter(matches, condrepr=('<subrepo %r>', pat))
 
 def _mapbynodefunc(repo, s, f):
     """(repo, smartset, [node] -> [node]) -> smartset
 
     Helper method to map a smartset to another smartset given a function only
     talking about nodes. Handles converting between rev numbers and nodes, and
     filtering.
     """
     cl = repo.unfiltered().changelog
     torev = cl.rev
     tonode = cl.node
     nodemap = cl.nodemap
     result = set(torev(n) for n in f(tonode(r) for r in s) if n in nodemap)
     return smartset.baseset(result - repo.changelog.filteredrevs)
 
 @predicate('successors(set)', safe=True)
 def successors(repo, subset, x):
     """All successors for set, including the given set themselves"""
     s = getset(repo, fullreposet(repo), x)
     f = lambda nodes: obsutil.allsuccessors(repo.obsstore, nodes)
     d = _mapbynodefunc(repo, s, f)
     return subset & d
 
 def _substringmatcher(pattern, casesensitive=True):
     kind, pattern, matcher = stringutil.stringmatcher(
         pattern, casesensitive=casesensitive)
     if kind == 'literal':
         if not casesensitive:
             pattern = encoding.lower(pattern)
             matcher = lambda s: pattern in encoding.lower(s)
         else:
             matcher = lambda s: pattern in s
     return kind, pattern, matcher
 
 @predicate('tag([name])', safe=True)
 def tag(repo, subset, x):
     """The specified tag by name, or all tagged revisions if no name is given.
 
     Pattern matching is supported for `name`. See
     :hg:`help revisions.patterns`.
     """
     # i18n: "tag" is a keyword
     args = getargs(x, 0, 1, _("tag takes one or no arguments"))
     cl = repo.changelog
     if args:
         pattern = getstring(args[0],
                             # i18n: "tag" is a keyword
                             _('the argument to tag must be a string'))
         kind, pattern, matcher = stringutil.stringmatcher(pattern)
         if kind == 'literal':
             # avoid resolving all tags
             tn = repo._tagscache.tags.get(pattern, None)
             if tn is None:
                 raise error.RepoLookupError(_("tag '%s' does not exist")
                                             % pattern)
             s = {repo[tn].rev()}
         else:
             s = {cl.rev(n) for t, n in repo.tagslist() if matcher(t)}
     else:
         s = {cl.rev(n) for t, n in repo.tagslist() if t != 'tip'}
     return subset & s
 
 @predicate('tagged', safe=True)
 def tagged(repo, subset, x):
     return tag(repo, subset, x)
 
 @predicate('orphan()', safe=True)
 def orphan(repo, subset, x):
     """Non-obsolete changesets with obsolete ancestors. (EXPERIMENTAL)
     """
     # i18n: "orphan" is a keyword
     getargs(x, 0, 0, _("orphan takes no arguments"))
     orphan = obsmod.getrevs(repo, 'orphan')
     return subset & orphan
 
 
 @predicate('user(string)', safe=True, weight=10)
 def user(repo, subset, x):
     """User name contains string. The match is case-insensitive.
 
     Pattern matching is supported for `string`. See
     :hg:`help revisions.patterns`.
     """
     return author(repo, subset, x)
 
 @predicate('wdir()', safe=True, weight=0)
 def wdir(repo, subset, x):
     """Working directory. (EXPERIMENTAL)"""
     # i18n: "wdir" is a keyword
     getargs(x, 0, 0, _("wdir takes no arguments"))
     if node.wdirrev in subset or isinstance(subset, fullreposet):
         return baseset([node.wdirrev])
     return baseset()
 
 def _orderedlist(repo, subset, x):
     s = getstring(x, "internal error")
     if not s:
         return baseset()
     # remove duplicates here. it's difficult for caller to deduplicate sets
     # because different symbols can point to the same rev.
     cl = repo.changelog
     ls = []
     seen = set()
     for t in s.split('\0'):
         try:
             # fast path for integer revision
             r = int(t)
             if ('%d' % r) != t or r not in cl:
                 raise ValueError
             revs = [r]
         except ValueError:
             revs = stringset(repo, subset, t, defineorder)
 
         for r in revs:
             if r in seen:
                 continue
             if (r in subset
                 or r == node.nullrev and isinstance(subset, fullreposet)):
                 ls.append(r)
             seen.add(r)
     return baseset(ls)
 
 # for internal use
 @predicate('_list', safe=True, takeorder=True)
 def _list(repo, subset, x, order):
     if order == followorder:
         # slow path to take the subset order
         return subset & _orderedlist(repo, fullreposet(repo), x)
     else:
         return _orderedlist(repo, subset, x)
 
 def _orderedintlist(repo, subset, x):
     s = getstring(x, "internal error")
     if not s:
         return baseset()
     ls = [int(r) for r in s.split('\0')]
     s = subset
     return baseset([r for r in ls if r in s])
 
 # for internal use
 @predicate('_intlist', safe=True, takeorder=True, weight=0)
 def _intlist(repo, subset, x, order):
     if order == followorder:
         # slow path to take the subset order
         return subset & _orderedintlist(repo, fullreposet(repo), x)
     else:
         return _orderedintlist(repo, subset, x)
 
 def _orderedhexlist(repo, subset, x):
     s = getstring(x, "internal error")
     if not s:
         return baseset()
     cl = repo.changelog
     ls = [cl.rev(node.bin(r)) for r in s.split('\0')]
     s = subset
     return baseset([r for r in ls if r in s])
 
 # for internal use
 @predicate('_hexlist', safe=True, takeorder=True)
 def _hexlist(repo, subset, x, order):
     if order == followorder:
         # slow path to take the subset order
         return subset & _orderedhexlist(repo, fullreposet(repo), x)
     else:
         return _orderedhexlist(repo, subset, x)
 
 methods = {
     "range": rangeset,
     "rangeall": rangeall,
     "rangepre": rangepre,
     "rangepost": rangepost,
     "dagrange": dagrange,
     "string": stringset,
     "symbol": stringset,
     "and": andset,
     "andsmally": andsmallyset,
     "or": orset,
     "not": notset,
     "difference": differenceset,
     "relation": relationset,
     "relsubscript": relsubscriptset,
     "subscript": subscriptset,
     "list": listset,
     "keyvalue": keyvaluepair,
     "func": func,
     "ancestor": ancestorspec,
     "parent": parentspec,
     "parentpost": parentpost,
 }
 
 def lookupfn(repo):
     return lambda symbol: scmutil.isrevsymbol(repo, symbol)
 
 def match(ui, spec, lookup=None):
     """Create a matcher for a single revision spec"""
     return matchany(ui, [spec], lookup=lookup)
 
 def matchany(ui, specs, lookup=None, localalias=None):
     """Create a matcher that will include any revisions matching one of the
     given specs
 
     If lookup function is not None, the parser will first attempt to handle
     old-style ranges, which may contain operator characters.
 
     If localalias is not None, it is a dict {name: definitionstring}. It takes
     precedence over [revsetalias] config section.
     """
     if not specs:
         def mfunc(repo, subset=None):
             return baseset()
         return mfunc
     if not all(specs):
         raise error.ParseError(_("empty query"))
     if len(specs) == 1:
         tree = revsetlang.parse(specs[0], lookup)
     else:
         tree = ('or',
                 ('list',) + tuple(revsetlang.parse(s, lookup) for s in specs))
 
     aliases = []
     warn = None
     if ui:
         aliases.extend(ui.configitems('revsetalias'))
         warn = ui.warn
     if localalias:
         aliases.extend(localalias.items())
     if aliases:
         tree = revsetlang.expandaliases(tree, aliases, warn=warn)
     tree = revsetlang.foldconcat(tree)
     tree = revsetlang.analyze(tree)
     tree = revsetlang.optimize(tree)
     return makematcher(tree)
 
 def makematcher(tree):
     """Create a matcher from an evaluatable tree"""
     def mfunc(repo, subset=None, order=None):
         if order is None:
             if subset is None:
                 order = defineorder  # 'x'
             else:
                 order = followorder  # 'subset & x'
         if subset is None:
             subset = fullreposet(repo)
         return getset(repo, subset, tree, order)
     return mfunc
 
 def loadpredicate(ui, extname, registrarobj):
     """Load revset predicates from specified registrarobj
     """
     for name, func in registrarobj._table.iteritems():
         symbols[name] = func
         if func._safe:
             safesymbols.add(name)
 
 # load built-in predicates explicitly to setup safesymbols
 loadpredicate(None, None, predicate)
 
 # tell hggettext to extract docstrings from these functions:
 i18nfunctions = symbols.values()

mercurial/templatekw.py

@@ -1,816 +1,816 b''
 # templatekw.py - common changeset template keywords
 #
 # Copyright 2005-2009 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 .node import (
     hex,
     nullid,
 )
 
 from . import (
     encoding,
     error,
     hbisect,
     i18n,
     obsutil,
     patch,
     pycompat,
     registrar,
     scmutil,
     templateutil,
     util,
 )
 from .utils import (
     diffutil,
     stringutil,
 )
 
 _hybrid = templateutil.hybrid
 hybriddict = templateutil.hybriddict
 hybridlist = templateutil.hybridlist
 compatdict = templateutil.compatdict
 compatlist = templateutil.compatlist
 _showcompatlist = templateutil._showcompatlist
 
 def getlatesttags(context, mapping, pattern=None):
     '''return date, distance and name for the latest tag of rev'''
     repo = context.resource(mapping, 'repo')
     ctx = context.resource(mapping, 'ctx')
     cache = context.resource(mapping, 'cache')
 
     cachename = 'latesttags'
     if pattern is not None:
         cachename += '-' + pattern
         match = stringutil.stringmatcher(pattern)[2]
     else:
         match = util.always
 
     if cachename not in cache:
         # Cache mapping from rev to a tuple with tag date, tag
         # distance and tag name
         cache[cachename] = {-1: (0, 0, ['null'])}
     latesttags = cache[cachename]
 
     rev = ctx.rev()
     todo = [rev]
     while todo:
         rev = todo.pop()
         if rev in latesttags:
             continue
         ctx = repo[rev]
         tags = [t for t in ctx.tags()
                 if (repo.tagtype(t) and repo.tagtype(t) != 'local'
                     and match(t))]
         if tags:
             latesttags[rev] = ctx.date()[0], 0, [t for t in sorted(tags)]
             continue
         try:
             ptags = [latesttags[p.rev()] for p in ctx.parents()]
             if len(ptags) > 1:
                 if ptags[0][2] == ptags[1][2]:
                     # The tuples are laid out so the right one can be found by
                     # comparison in this case.
                     pdate, pdist, ptag = max(ptags)
                 else:
                     def key(x):
                         changessincetag = len(repo.revs('only(%d, %s)',
                                                         ctx.rev(), x[2][0]))
                         # Smallest number of changes since tag wins. Date is
                         # used as tiebreaker.
                         return [-changessincetag, x[0]]
                     pdate, pdist, ptag = max(ptags, key=key)
             else:
                 pdate, pdist, ptag = ptags[0]
         except KeyError:
             # Cache miss - recurse
             todo.append(rev)
             todo.extend(p.rev() for p in ctx.parents())
             continue
         latesttags[rev] = pdate, pdist + 1, ptag
     return latesttags[rev]
 
 def getrenamedfn(repo, endrev=None):
     rcache = {}
     if endrev is None:
         endrev = len(repo)
 
     def getrenamed(fn, rev):
         '''looks up all renames for a file (up to endrev) the first
         time the file is given. It indexes on the changerev and only
         parses the manifest if linkrev != changerev.
         Returns rename info for fn at changerev rev.'''
         if fn not in rcache:
             rcache[fn] = {}
             fl = repo.file(fn)
             for i in fl:
                 lr = fl.linkrev(i)
                 renamed = fl.renamed(fl.node(i))
                 rcache[fn][lr] = renamed and renamed[0]
                 if lr >= endrev:
                     break
         if rev in rcache[fn]:
             return rcache[fn][rev]
 
         # If linkrev != rev (i.e. rev not found in rcache) fallback to
         # filectx logic.
         try:
             renamed = repo[rev][fn].renamed()
             return renamed and renamed[0]
         except error.LookupError:
             return None
 
     return getrenamed
 
 def getlogcolumns():
     """Return a dict of log column labels"""
     _ = pycompat.identity  # temporarily disable gettext
     # i18n: column positioning for "hg log"
     columns = _('bookmark:    %s\n'
                 'branch:      %s\n'
                 'changeset:   %s\n'
                 'copies:      %s\n'
                 'date:        %s\n'
                 'extra:       %s=%s\n'
                 'files+:      %s\n'
                 'files-:      %s\n'
                 'files:       %s\n'
                 'instability: %s\n'
                 'manifest:    %s\n'
                 'obsolete:    %s\n'
                 'parent:      %s\n'
                 'phase:       %s\n'
                 'summary:     %s\n'
                 'tag:         %s\n'
                 'user:        %s\n')
     return dict(zip([s.split(':', 1)[0] for s in columns.splitlines()],
                     i18n._(columns).splitlines(True)))
 
 # default templates internally used for rendering of lists
 defaulttempl = {
     'parent': '{rev}:{node|formatnode} ',
     'manifest': '{rev}:{node|formatnode}',
     'file_copy': '{name} ({source})',
     'envvar': '{key}={value}',
     'extra': '{key}={value|stringescape}'
 }
 # filecopy is preserved for compatibility reasons
 defaulttempl['filecopy'] = defaulttempl['file_copy']
 
 # keywords are callables (see registrar.templatekeyword for details)
 keywords = {}
 templatekeyword = registrar.templatekeyword(keywords)
 
 @templatekeyword('author', requires={'ctx'})
 def showauthor(context, mapping):
     """String. The unmodified author of the changeset."""
     ctx = context.resource(mapping, 'ctx')
     return ctx.user()
 
 @templatekeyword('bisect', requires={'repo', 'ctx'})
 def showbisect(context, mapping):
     """String. The changeset bisection status."""
     repo = context.resource(mapping, 'repo')
     ctx = context.resource(mapping, 'ctx')
     return hbisect.label(repo, ctx.node())
 
 @templatekeyword('branch', requires={'ctx'})
 def showbranch(context, mapping):
     """String. The name of the branch on which the changeset was
     committed.
     """
     ctx = context.resource(mapping, 'ctx')
     return ctx.branch()
 
 @templatekeyword('branches', requires={'ctx'})
 def showbranches(context, mapping):
     """List of strings. The name of the branch on which the
     changeset was committed. Will be empty if the branch name was
     default. (DEPRECATED)
     """
     ctx = context.resource(mapping, 'ctx')
     branch = ctx.branch()
     if branch != 'default':
         return compatlist(context, mapping, 'branch', [branch],
                           plural='branches')
     return compatlist(context, mapping, 'branch', [], plural='branches')
 
 @templatekeyword('bookmarks', requires={'repo', 'ctx'})
 def showbookmarks(context, mapping):
     """List of strings. Any bookmarks associated with the
     changeset. Also sets 'active', the name of the active bookmark.
     """
     repo = context.resource(mapping, 'repo')
     ctx = context.resource(mapping, 'ctx')
     bookmarks = ctx.bookmarks()
     active = repo._activebookmark
     makemap = lambda v: {'bookmark': v, 'active': active, 'current': active}
     f = _showcompatlist(context, mapping, 'bookmark', bookmarks)
     return _hybrid(f, bookmarks, makemap, pycompat.identity)
 
 @templatekeyword('children', requires={'ctx'})
 def showchildren(context, mapping):
     """List of strings. The children of the changeset."""
     ctx = context.resource(mapping, 'ctx')
     childrevs = ['%d:%s' % (cctx.rev(), cctx) for cctx in ctx.children()]
     return compatlist(context, mapping, 'children', childrevs, element='child')
 
 # Deprecated, but kept alive for help generation a purpose.
 @templatekeyword('currentbookmark', requires={'repo', 'ctx'})
 def showcurrentbookmark(context, mapping):
     """String. The active bookmark, if it is associated with the changeset.
     (DEPRECATED)"""
     return showactivebookmark(context, mapping)
 
 @templatekeyword('activebookmark', requires={'repo', 'ctx'})
 def showactivebookmark(context, mapping):
     """String. The active bookmark, if it is associated with the changeset."""
     repo = context.resource(mapping, 'repo')
     ctx = context.resource(mapping, 'ctx')
     active = repo._activebookmark
     if active and active in ctx.bookmarks():
         return active
     return ''
 
 @templatekeyword('date', requires={'ctx'})
 def showdate(context, mapping):
     """Date information. The date when the changeset was committed."""
     ctx = context.resource(mapping, 'ctx')
     # the default string format is '<float(unixtime)><tzoffset>' because
     # python-hglib splits date at decimal separator.
     return templateutil.date(ctx.date(), showfmt='%d.0%d')
 
 @templatekeyword('desc', requires={'ctx'})
 def showdescription(context, mapping):
     """String. The text of the changeset description."""
     ctx = context.resource(mapping, 'ctx')
     s = ctx.description()
     if isinstance(s, encoding.localstr):
         # try hard to preserve utf-8 bytes
         return encoding.tolocal(encoding.fromlocal(s).strip())
     elif isinstance(s, encoding.safelocalstr):
         return encoding.safelocalstr(s.strip())
     else:
         return s.strip()
 
 @templatekeyword('diffstat', requires={'ui', 'ctx'})
 def showdiffstat(context, mapping):
     """String. Statistics of changes with the following format:
     "modified files: +added/-removed lines"
     """
     ui = context.resource(mapping, 'ui')
     ctx = context.resource(mapping, 'ctx')
-    diffopts = diffutil.diffopts(ui, {'noprefix': False})
+    diffopts = diffutil.diffallopts(ui, {'noprefix': False})
     diff = ctx.diff(opts=diffopts)
     stats = patch.diffstatdata(util.iterlines(diff))
     maxname, maxtotal, adds, removes, binary = patch.diffstatsum(stats)
     return '%d: +%d/-%d' % (len(stats), adds, removes)
 
 @templatekeyword('envvars', requires={'ui'})
 def showenvvars(context, mapping):
     """A dictionary of environment variables. (EXPERIMENTAL)"""
     ui = context.resource(mapping, 'ui')
     env = ui.exportableenviron()
     env = util.sortdict((k, env[k]) for k in sorted(env))
     return compatdict(context, mapping, 'envvar', env, plural='envvars')
 
 @templatekeyword('extras', requires={'ctx'})
 def showextras(context, mapping):
     """List of dicts with key, value entries of the 'extras'
     field of this changeset."""
     ctx = context.resource(mapping, 'ctx')
     extras = ctx.extra()
     extras = util.sortdict((k, extras[k]) for k in sorted(extras))
     makemap = lambda k: {'key': k, 'value': extras[k]}
     c = [makemap(k) for k in extras]
     f = _showcompatlist(context, mapping, 'extra', c, plural='extras')
     return _hybrid(f, extras, makemap,
                    lambda k: '%s=%s' % (k, stringutil.escapestr(extras[k])))
 
 def _showfilesbystat(context, mapping, name, index):
     repo = context.resource(mapping, 'repo')
     ctx = context.resource(mapping, 'ctx')
     revcache = context.resource(mapping, 'revcache')
     if 'files' not in revcache:
         revcache['files'] = repo.status(ctx.p1(), ctx)[:3]
     files = revcache['files'][index]
     return compatlist(context, mapping, name, files, element='file')
 
 @templatekeyword('file_adds', requires={'repo', 'ctx', 'revcache'})
 def showfileadds(context, mapping):
     """List of strings. Files added by this changeset."""
     return _showfilesbystat(context, mapping, 'file_add', 1)
 
 @templatekeyword('file_copies',
                  requires={'repo', 'ctx', 'cache', 'revcache'})
 def showfilecopies(context, mapping):
     """List of strings. Files copied in this changeset with
     their sources.
     """
     repo = context.resource(mapping, 'repo')
     ctx = context.resource(mapping, 'ctx')
     cache = context.resource(mapping, 'cache')
     copies = context.resource(mapping, 'revcache').get('copies')
     if copies is None:
         if 'getrenamed' not in cache:
             cache['getrenamed'] = getrenamedfn(repo)
         copies = []
         getrenamed = cache['getrenamed']
         for fn in ctx.files():
             rename = getrenamed(fn, ctx.rev())
             if rename:
                 copies.append((fn, rename))
 
     copies = util.sortdict(copies)
     return compatdict(context, mapping, 'file_copy', copies,
                       key='name', value='source', fmt='%s (%s)',
                       plural='file_copies')
 
 # showfilecopiesswitch() displays file copies only if copy records are
 # provided before calling the templater, usually with a --copies
 # command line switch.
 @templatekeyword('file_copies_switch', requires={'revcache'})
 def showfilecopiesswitch(context, mapping):
     """List of strings. Like "file_copies" but displayed
     only if the --copied switch is set.
     """
     copies = context.resource(mapping, 'revcache').get('copies') or []
     copies = util.sortdict(copies)
     return compatdict(context, mapping, 'file_copy', copies,
                       key='name', value='source', fmt='%s (%s)',
                       plural='file_copies')
 
 @templatekeyword('file_dels', requires={'repo', 'ctx', 'revcache'})
 def showfiledels(context, mapping):
     """List of strings. Files removed by this changeset."""
     return _showfilesbystat(context, mapping, 'file_del', 2)
 
 @templatekeyword('file_mods', requires={'repo', 'ctx', 'revcache'})
 def showfilemods(context, mapping):
     """List of strings. Files modified by this changeset."""
     return _showfilesbystat(context, mapping, 'file_mod', 0)
 
 @templatekeyword('files', requires={'ctx'})
 def showfiles(context, mapping):
     """List of strings. All files modified, added, or removed by this
     changeset.
     """
     ctx = context.resource(mapping, 'ctx')
     return compatlist(context, mapping, 'file', ctx.files())
 
 @templatekeyword('graphnode', requires={'repo', 'ctx'})
 def showgraphnode(context, mapping):
     """String. The character representing the changeset node in an ASCII
     revision graph."""
     repo = context.resource(mapping, 'repo')
     ctx = context.resource(mapping, 'ctx')
     return getgraphnode(repo, ctx)
 
 def getgraphnode(repo, ctx):
     return getgraphnodecurrent(repo, ctx) or getgraphnodesymbol(ctx)
 
 def getgraphnodecurrent(repo, ctx):
     wpnodes = repo.dirstate.parents()
     if wpnodes[1] == nullid:
         wpnodes = wpnodes[:1]
     if ctx.node() in wpnodes:
         return '@'
     else:
         return ''
 
 def getgraphnodesymbol(ctx):
     if ctx.obsolete():
         return 'x'
     elif ctx.isunstable():
         return '*'
     elif ctx.closesbranch():
         return '_'
     else:
         return 'o'
 
 @templatekeyword('graphwidth', requires=())
 def showgraphwidth(context, mapping):
     """Integer. The width of the graph drawn by 'log --graph' or zero."""
     # just hosts documentation; should be overridden by template mapping
     return 0
 
 @templatekeyword('index', requires=())
 def showindex(context, mapping):
     """Integer. The current iteration of the loop. (0 indexed)"""
     # just hosts documentation; should be overridden by template mapping
     raise error.Abort(_("can't use index in this context"))
 
 @templatekeyword('latesttag', requires={'repo', 'ctx', 'cache'})
 def showlatesttag(context, mapping):
     """List of strings. The global tags on the most recent globally
     tagged ancestor of this changeset.  If no such tags exist, the list
     consists of the single string "null".
     """
     return showlatesttags(context, mapping, None)
 
 def showlatesttags(context, mapping, pattern):
     """helper method for the latesttag keyword and function"""
     latesttags = getlatesttags(context, mapping, pattern)
 
     # latesttag[0] is an implementation detail for sorting csets on different
     # branches in a stable manner- it is the date the tagged cset was created,
     # not the date the tag was created.  Therefore it isn't made visible here.
     makemap = lambda v: {
         'changes': _showchangessincetag,
         'distance': latesttags[1],
         'latesttag': v,   # BC with {latesttag % '{latesttag}'}
         'tag': v
     }
 
     tags = latesttags[2]
     f = _showcompatlist(context, mapping, 'latesttag', tags, separator=':')
     return _hybrid(f, tags, makemap, pycompat.identity)
 
 @templatekeyword('latesttagdistance', requires={'repo', 'ctx', 'cache'})
 def showlatesttagdistance(context, mapping):
     """Integer. Longest path to the latest tag."""
     return getlatesttags(context, mapping)[1]
 
 @templatekeyword('changessincelatesttag', requires={'repo', 'ctx', 'cache'})
 def showchangessincelatesttag(context, mapping):
     """Integer. All ancestors not in the latest tag."""
     tag = getlatesttags(context, mapping)[2][0]
     mapping = context.overlaymap(mapping, {'tag': tag})
     return _showchangessincetag(context, mapping)
 
 def _showchangessincetag(context, mapping):
     repo = context.resource(mapping, 'repo')
     ctx = context.resource(mapping, 'ctx')
     offset = 0
     revs = [ctx.rev()]
     tag = context.symbol(mapping, 'tag')
 
     # The only() revset doesn't currently support wdir()
     if ctx.rev() is None:
         offset = 1
         revs = [p.rev() for p in ctx.parents()]
 
     return len(repo.revs('only(%ld, %s)', revs, tag)) + offset
 
 # teach templater latesttags.changes is switched to (context, mapping) API
 _showchangessincetag._requires = {'repo', 'ctx'}
 
 @templatekeyword('manifest', requires={'repo', 'ctx'})
 def showmanifest(context, mapping):
     repo = context.resource(mapping, 'repo')
     ctx = context.resource(mapping, 'ctx')
     mnode = ctx.manifestnode()
     if mnode is None:
         # just avoid crash, we might want to use the 'ff...' hash in future
         return
     mrev = repo.manifestlog.rev(mnode)
     mhex = hex(mnode)
     mapping = context.overlaymap(mapping, {'rev': mrev, 'node': mhex})
     f = context.process('manifest', mapping)
     # TODO: perhaps 'ctx' should be dropped from mapping because manifest
     # rev and node are completely different from changeset's.
     return templateutil.hybriditem(f, None, f,
                                    lambda x: {'rev': mrev, 'node': mhex})
 
 @templatekeyword('obsfate', requires={'ui', 'repo', 'ctx'})
 def showobsfate(context, mapping):
     # this function returns a list containing pre-formatted obsfate strings.
     #
     # This function will be replaced by templates fragments when we will have
     # the verbosity templatekw available.
     succsandmarkers = showsuccsandmarkers(context, mapping)
 
     ui = context.resource(mapping, 'ui')
     repo = context.resource(mapping, 'repo')
     values = []
 
     for x in succsandmarkers.tovalue(context, mapping):
         v = obsutil.obsfateprinter(ui, repo, x['successors'], x['markers'],
                                    scmutil.formatchangeid)
         values.append(v)
 
     return compatlist(context, mapping, "fate", values)
 
 def shownames(context, mapping, namespace):
     """helper method to generate a template keyword for a namespace"""
     repo = context.resource(mapping, 'repo')
     ctx = context.resource(mapping, 'ctx')
     ns = repo.names[namespace]
     names = ns.names(repo, ctx.node())
     return compatlist(context, mapping, ns.templatename, names,
                       plural=namespace)
 
 @templatekeyword('namespaces', requires={'repo', 'ctx'})
 def shownamespaces(context, mapping):
     """Dict of lists. Names attached to this changeset per
     namespace."""
     repo = context.resource(mapping, 'repo')
     ctx = context.resource(mapping, 'ctx')
 
     namespaces = util.sortdict()
     def makensmapfn(ns):
         # 'name' for iterating over namespaces, templatename for local reference
         return lambda v: {'name': v, ns.templatename: v}
 
     for k, ns in repo.names.iteritems():
         names = ns.names(repo, ctx.node())
         f = _showcompatlist(context, mapping, 'name', names)
         namespaces[k] = _hybrid(f, names, makensmapfn(ns), pycompat.identity)
 
     f = _showcompatlist(context, mapping, 'namespace', list(namespaces))
 
     def makemap(ns):
         return {
             'namespace': ns,
             'names': namespaces[ns],
             'builtin': repo.names[ns].builtin,
             'colorname': repo.names[ns].colorname,
         }
 
     return _hybrid(f, namespaces, makemap, pycompat.identity)
 
 @templatekeyword('node', requires={'ctx'})
 def shownode(context, mapping):
     """String. The changeset identification hash, as a 40 hexadecimal
     digit string.
     """
     ctx = context.resource(mapping, 'ctx')
     return ctx.hex()
 
 @templatekeyword('obsolete', requires={'ctx'})
 def showobsolete(context, mapping):
     """String. Whether the changeset is obsolete. (EXPERIMENTAL)"""
     ctx = context.resource(mapping, 'ctx')
     if ctx.obsolete():
         return 'obsolete'
     return ''
 
 @templatekeyword('peerurls', requires={'repo'})
 def showpeerurls(context, mapping):
     """A dictionary of repository locations defined in the [paths] section
     of your configuration file."""
     repo = context.resource(mapping, 'repo')
     # see commands.paths() for naming of dictionary keys
     paths = repo.ui.paths
     urls = util.sortdict((k, p.rawloc) for k, p in sorted(paths.iteritems()))
     def makemap(k):
         p = paths[k]
         d = {'name': k, 'url': p.rawloc}
         d.update((o, v) for o, v in sorted(p.suboptions.iteritems()))
         return d
     return _hybrid(None, urls, makemap, lambda k: '%s=%s' % (k, urls[k]))
 
 @templatekeyword("predecessors", requires={'repo', 'ctx'})
 def showpredecessors(context, mapping):
     """Returns the list if the closest visible successors. (EXPERIMENTAL)"""
     repo = context.resource(mapping, 'repo')
     ctx = context.resource(mapping, 'ctx')
     predecessors = sorted(obsutil.closestpredecessors(repo, ctx.node()))
     predecessors = pycompat.maplist(hex, predecessors)
 
     return _hybrid(None, predecessors,
                    lambda x: {'ctx': repo[x]},
                    lambda x: scmutil.formatchangeid(repo[x]))
 
 @templatekeyword('reporoot', requires={'repo'})
 def showreporoot(context, mapping):
     """String. The root directory of the current repository."""
     repo = context.resource(mapping, 'repo')
     return repo.root
 
 @templatekeyword("successorssets", requires={'repo', 'ctx'})
 def showsuccessorssets(context, mapping):
     """Returns a string of sets of successors for a changectx. Format used
     is: [ctx1, ctx2], [ctx3] if ctx has been splitted into ctx1 and ctx2
     while also diverged into ctx3. (EXPERIMENTAL)"""
     repo = context.resource(mapping, 'repo')
     ctx = context.resource(mapping, 'ctx')
     if not ctx.obsolete():
         return ''
 
     ssets = obsutil.successorssets(repo, ctx.node(), closest=True)
     ssets = [[hex(n) for n in ss] for ss in ssets]
 
     data = []
     for ss in ssets:
         h = _hybrid(None, ss, lambda x: {'ctx': repo[x]},
                     lambda x: scmutil.formatchangeid(repo[x]))
         data.append(h)
 
     # Format the successorssets
     def render(d):
         return templateutil.stringify(context, mapping, d)
 
     def gen(data):
         yield "; ".join(render(d) for d in data)
 
     return _hybrid(gen(data), data, lambda x: {'successorset': x},
                    pycompat.identity)
 
 @templatekeyword("succsandmarkers", requires={'repo', 'ctx'})
 def showsuccsandmarkers(context, mapping):
     """Returns a list of dict for each final successor of ctx. The dict
     contains successors node id in "successors" keys and the list of
     obs-markers from ctx to the set of successors in "markers".
     (EXPERIMENTAL)
     """
     repo = context.resource(mapping, 'repo')
     ctx = context.resource(mapping, 'ctx')
 
     values = obsutil.successorsandmarkers(repo, ctx)
 
     if values is None:
         values = []
 
     # Format successors and markers to avoid exposing binary to templates
     data = []
     for i in values:
         # Format successors
         successors = i['successors']
 
         successors = [hex(n) for n in successors]
         successors = _hybrid(None, successors,
                              lambda x: {'ctx': repo[x]},
                              lambda x: scmutil.formatchangeid(repo[x]))
 
         # Format markers
         finalmarkers = []
         for m in i['markers']:
             hexprec = hex(m[0])
             hexsucs = tuple(hex(n) for n in m[1])
             hexparents = None
             if m[5] is not None:
                 hexparents = tuple(hex(n) for n in m[5])
             newmarker = (hexprec, hexsucs) + m[2:5] + (hexparents,) + m[6:]
             finalmarkers.append(newmarker)
 
         data.append({'successors': successors, 'markers': finalmarkers})
 
     return templateutil.mappinglist(data)
 
 @templatekeyword('p1rev', requires={'ctx'})
 def showp1rev(context, mapping):
     """Integer. The repository-local revision number of the changeset's
     first parent, or -1 if the changeset has no parents."""
     ctx = context.resource(mapping, 'ctx')
     return ctx.p1().rev()
 
 @templatekeyword('p2rev', requires={'ctx'})
 def showp2rev(context, mapping):
     """Integer. The repository-local revision number of the changeset's
     second parent, or -1 if the changeset has no second parent."""
     ctx = context.resource(mapping, 'ctx')
     return ctx.p2().rev()
 
 @templatekeyword('p1node', requires={'ctx'})
 def showp1node(context, mapping):
     """String. The identification hash of the changeset's first parent,
     as a 40 digit hexadecimal string. If the changeset has no parents, all
     digits are 0."""
     ctx = context.resource(mapping, 'ctx')
     return ctx.p1().hex()
 
 @templatekeyword('p2node', requires={'ctx'})
 def showp2node(context, mapping):
     """String. The identification hash of the changeset's second
     parent, as a 40 digit hexadecimal string. If the changeset has no second
     parent, all digits are 0."""
     ctx = context.resource(mapping, 'ctx')
     return ctx.p2().hex()
 
 @templatekeyword('parents', requires={'repo', 'ctx'})
 def showparents(context, mapping):
     """List of strings. The parents of the changeset in "rev:node"
     format. If the changeset has only one "natural" parent (the predecessor
     revision) nothing is shown."""
     repo = context.resource(mapping, 'repo')
     ctx = context.resource(mapping, 'ctx')
     pctxs = scmutil.meaningfulparents(repo, ctx)
     prevs = [p.rev() for p in pctxs]
     parents = [[('rev', p.rev()),
                 ('node', p.hex()),
                 ('phase', p.phasestr())]
                for p in pctxs]
     f = _showcompatlist(context, mapping, 'parent', parents)
     return _hybrid(f, prevs, lambda x: {'ctx': repo[x]},
                    lambda x: scmutil.formatchangeid(repo[x]), keytype=int)
 
 @templatekeyword('phase', requires={'ctx'})
 def showphase(context, mapping):
     """String. The changeset phase name."""
     ctx = context.resource(mapping, 'ctx')
     return ctx.phasestr()
 
 @templatekeyword('phaseidx', requires={'ctx'})
 def showphaseidx(context, mapping):
     """Integer. The changeset phase index. (ADVANCED)"""
     ctx = context.resource(mapping, 'ctx')
     return ctx.phase()
 
 @templatekeyword('rev', requires={'ctx'})
 def showrev(context, mapping):
     """Integer. The repository-local changeset revision number."""
     ctx = context.resource(mapping, 'ctx')
     return scmutil.intrev(ctx)
 
 def showrevslist(context, mapping, name, revs):
     """helper to generate a list of revisions in which a mapped template will
     be evaluated"""
     repo = context.resource(mapping, 'repo')
     f = _showcompatlist(context, mapping, name, ['%d' % r for r in revs])
     return _hybrid(f, revs,
                    lambda x: {name: x, 'ctx': repo[x]},
                    pycompat.identity, keytype=int)
 
 @templatekeyword('subrepos', requires={'ctx'})
 def showsubrepos(context, mapping):
     """List of strings. Updated subrepositories in the changeset."""
     ctx = context.resource(mapping, 'ctx')
     substate = ctx.substate
     if not substate:
         return compatlist(context, mapping, 'subrepo', [])
     psubstate = ctx.parents()[0].substate or {}
     subrepos = []
     for sub in substate:
         if sub not in psubstate or substate[sub] != psubstate[sub]:
             subrepos.append(sub) # modified or newly added in ctx
     for sub in psubstate:
         if sub not in substate:
             subrepos.append(sub) # removed in ctx
     return compatlist(context, mapping, 'subrepo', sorted(subrepos))
 
 # don't remove "showtags" definition, even though namespaces will put
 # a helper function for "tags" keyword into "keywords" map automatically,
 # because online help text is built without namespaces initialization
 @templatekeyword('tags', requires={'repo', 'ctx'})
 def showtags(context, mapping):
     """List of strings. Any tags associated with the changeset."""
     return shownames(context, mapping, 'tags')
 
 @templatekeyword('termwidth', requires={'ui'})
 def showtermwidth(context, mapping):
     """Integer. The width of the current terminal."""
     ui = context.resource(mapping, 'ui')
     return ui.termwidth()
 
 @templatekeyword('instabilities', requires={'ctx'})
 def showinstabilities(context, mapping):
     """List of strings. Evolution instabilities affecting the changeset.
     (EXPERIMENTAL)
     """
     ctx = context.resource(mapping, 'ctx')
     return compatlist(context, mapping, 'instability', ctx.instabilities(),
                       plural='instabilities')
 
 @templatekeyword('verbosity', requires={'ui'})
 def showverbosity(context, mapping):
     """String. The current output verbosity in 'debug', 'quiet', 'verbose',
     or ''."""
     ui = context.resource(mapping, 'ui')
     # see logcmdutil.changesettemplater for priority of these flags
     if ui.debugflag:
         return 'debug'
     elif ui.quiet:
         return 'quiet'
     elif ui.verbose:
         return 'verbose'
     return ''
 
 @templatekeyword('whyunstable', requires={'repo', 'ctx'})
 def showwhyunstable(context, mapping):
     """List of dicts explaining all instabilities of a changeset.
     (EXPERIMENTAL)
     """
     repo = context.resource(mapping, 'repo')
     ctx = context.resource(mapping, 'ctx')
 
     def formatnode(ctx):
         return '%s (%s)' % (scmutil.formatchangeid(ctx), ctx.phasestr())
 
     entries = obsutil.whyunstable(repo, ctx)
 
     for entry in entries:
         if entry.get('divergentnodes'):
             dnodes = entry['divergentnodes']
             dnhybrid = _hybrid(None, [dnode.hex() for dnode in dnodes],
                                lambda x: {'ctx': repo[x]},
                                lambda x: formatnode(repo[x]))
             entry['divergentnodes'] = dnhybrid
 
     tmpl = ('{instability}:{if(divergentnodes, " ")}{divergentnodes} '
             '{reason} {node|short}')
     return templateutil.mappinglist(entries, tmpl=tmpl, sep='\n')
 
 def loadkeyword(ui, extname, registrarobj):
     """Load template keyword from specified registrarobj
     """
     for name, func in registrarobj._table.iteritems():
         keywords[name] = func
 
 # tell hggettext to extract docstrings from these functions:
 i18nfunctions = keywords.values()

mercurial/utils/diffutil.py

@@ -1,107 +1,105 b''
 # diffutil.py - utility functions related to diff and patch
 #
 # Copyright 2006 Brendan Cully <[e-mail]>
 # Copyright 2007 Chris Mason <[e-mail]>
 # Copyright 2018 Octobus <[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 (
     mdiff,
     pycompat,
 )
 
 def diffallopts(ui, opts=None, untrusted=False, section='diff'):
     '''return diffopts with all features supported and parsed'''
     return difffeatureopts(ui, opts=opts, untrusted=untrusted, section=section,
                            git=True, whitespace=True, formatchanging=True)
 
-diffopts = diffallopts
-
 def difffeatureopts(ui, opts=None, untrusted=False, section='diff', git=False,
                     whitespace=False, formatchanging=False):
     '''return diffopts with only opted-in features parsed
 
     Features:
     - git: git-style diffs
     - whitespace: whitespace options like ignoreblanklines and ignorews
     - formatchanging: options that will likely break or cause correctness issues
       with most diff parsers
     '''
     def get(key, name=None, getter=ui.configbool, forceplain=None):
         if opts:
             v = opts.get(key)
             # diffopts flags are either None-default (which is passed
             # through unchanged, so we can identify unset values), or
             # some other falsey default (eg --unified, which defaults
             # to an empty string). We only want to override the config
             # entries from hgrc with command line values if they
             # appear to have been set, which is any truthy value,
             # True, or False.
             if v or isinstance(v, bool):
                 return v
         if forceplain is not None and ui.plain():
             return forceplain
         return getter(section, name or key, untrusted=untrusted)
 
     # core options, expected to be understood by every diff parser
     buildopts = {
         'nodates': get('nodates'),
         'showfunc': get('show_function', 'showfunc'),
         'context': get('unified', getter=ui.config),
     }
     buildopts['worddiff'] = ui.configbool('experimental', 'worddiff')
     buildopts['xdiff'] = ui.configbool('experimental', 'xdiff')
 
     if git:
         buildopts['git'] = get('git')
 
         # since this is in the experimental section, we need to call
         # ui.configbool directory
         buildopts['showsimilarity'] = ui.configbool('experimental',
                                                     'extendedheader.similarity')
 
         # need to inspect the ui object instead of using get() since we want to
         # test for an int
         hconf = ui.config('experimental', 'extendedheader.index')
         if hconf is not None:
             hlen = None
             try:
                 # the hash config could be an integer (for length of hash) or a
                 # word (e.g. short, full, none)
                 hlen = int(hconf)
                 if hlen < 0 or hlen > 40:
                     msg = _("invalid length for extendedheader.index: '%d'\n")
                     ui.warn(msg % hlen)
             except ValueError:
                 # default value
                 if hconf == 'short' or hconf == '':
                     hlen = 12
                 elif hconf == 'full':
                     hlen = 40
                 elif hconf != 'none':
                     msg = _("invalid value for extendedheader.index: '%s'\n")
                     ui.warn(msg % hconf)
             finally:
                 buildopts['index'] = hlen
 
     if whitespace:
         buildopts['ignorews'] = get('ignore_all_space', 'ignorews')
         buildopts['ignorewsamount'] = get('ignore_space_change',
                                           'ignorewsamount')
         buildopts['ignoreblanklines'] = get('ignore_blank_lines',
                                             'ignoreblanklines')
         buildopts['ignorewseol'] = get('ignore_space_at_eol', 'ignorewseol')
     if formatchanging:
         buildopts['text'] = opts and opts.get('text')
         binary = None if opts is None else opts.get('binary')
         buildopts['nobinary'] = (not binary if binary is not None
                                  else get('nobinary', forceplain=False))
         buildopts['noprefix'] = get('noprefix', forceplain=False)
 
     return mdiff.diffopts(**pycompat.strkwargs(buildopts))

tests/test-context.py

@@ -1,211 +1,211 b''
 from __future__ import absolute_import, print_function
 import os
 import stat
 import sys
 from mercurial.node import hex
 from mercurial import (
     context,
     encoding,
     hg,
     scmutil,
     ui as uimod,
 )
 from mercurial.utils import diffutil
 
 print_ = print
 def print(*args, **kwargs):
     """print() wrapper that flushes stdout buffers to avoid py3 buffer issues
 
     We could also just write directly to sys.stdout.buffer the way the
     ui object will, but this was easier for porting the test.
     """
     print_(*args, **kwargs)
     sys.stdout.flush()
 
 def printb(data, end=b'\n'):
     out = getattr(sys.stdout, 'buffer', sys.stdout)
     out.write(data + end)
     out.flush()
 
 u = uimod.ui.load()
 
 repo = hg.repository(u, b'test1', create=1)
 os.chdir('test1')
 
 # create 'foo' with fixed time stamp
 f = open('foo', 'wb')
 f.write(b'foo\n')
 f.close()
 os.utime('foo', (1000, 1000))
 
 # add+commit 'foo'
 repo[None].add([b'foo'])
 repo.commit(text=b'commit1', date=b"0 0")
 
 d = repo[None][b'foo'].date()
 if os.name == 'nt':
     d = d[:2]
 print("workingfilectx.date = (%d, %d)" % d)
 
 # test memctx with non-ASCII commit message
 
 def filectxfn(repo, memctx, path):
     return context.memfilectx(repo, memctx, b"foo", b"")
 
 ctx = context.memctx(repo, [b'tip', None],
                      encoding.tolocal(b"Gr\xc3\xbcezi!"),
                      [b"foo"], filectxfn)
 ctx.commit()
 for enc in "ASCII", "Latin-1", "UTF-8":
     encoding.encoding = enc
     printb(b"%-8s: %s" % (enc.encode('ascii'), repo[b"tip"].description()))
 
 # test performing a status
 
 def getfilectx(repo, memctx, f):
     fctx = memctx.parents()[0][f]
     data, flags = fctx.data(), fctx.flags()
     if f == b'foo':
         data += b'bar\n'
     return context.memfilectx(
         repo, memctx, f, data, b'l' in flags, b'x' in flags)
 
 ctxa = repo[0]
 ctxb = context.memctx(repo, [ctxa.node(), None], b"test diff", [b"foo"],
                       getfilectx, ctxa.user(), ctxa.date())
 
 print(ctxb.status(ctxa))
 
 # test performing a diff on a memctx
-diffopts = diffutil.diffopts(repo.ui, {'git': True})
+diffopts = diffutil.diffallopts(repo.ui, {'git': True})
 for d in ctxb.diff(ctxa, opts=diffopts):
     printb(d, end=b'')
 
 # test safeness and correctness of "ctx.status()"
 print('= checking context.status():')
 
 # ancestor "wcctx ~ 2"
 actx2 = repo[b'.']
 
 repo.wwrite(b'bar-m', b'bar-m\n', b'')
 repo.wwrite(b'bar-r', b'bar-r\n', b'')
 repo[None].add([b'bar-m', b'bar-r'])
 repo.commit(text=b'add bar-m, bar-r', date=b"0 0")
 
 # ancestor "wcctx ~ 1"
 actx1 = repo[b'.']
 
 repo.wwrite(b'bar-m', b'bar-m bar-m\n', b'')
 repo.wwrite(b'bar-a', b'bar-a\n', b'')
 repo[None].add([b'bar-a'])
 repo[None].forget([b'bar-r'])
 
 # status at this point:
 #   M bar-m
 #   A bar-a
 #   R bar-r
 #   C foo
 
 from mercurial import scmutil
 
 print('== checking workingctx.status:')
 
 wctx = repo[None]
 print('wctx._status=%s' % (str(wctx._status)))
 
 print('=== with "pattern match":')
 print(actx1.status(other=wctx,
                    match=scmutil.matchfiles(repo, [b'bar-m', b'foo'])))
 print('wctx._status=%s' % (str(wctx._status)))
 print(actx2.status(other=wctx,
                    match=scmutil.matchfiles(repo, [b'bar-m', b'foo'])))
 print('wctx._status=%s' % (str(wctx._status)))
 
 print('=== with "always match" and "listclean=True":')
 print(actx1.status(other=wctx, listclean=True))
 print('wctx._status=%s' % (str(wctx._status)))
 print(actx2.status(other=wctx, listclean=True))
 print('wctx._status=%s' % (str(wctx._status)))
 
 print("== checking workingcommitctx.status:")
 
 wcctx = context.workingcommitctx(repo,
                                  scmutil.status([b'bar-m'],
                                                 [b'bar-a'],
                                                 [],
                                                 [], [], [], []),
                                  text=b'', date=b'0 0')
 print('wcctx._status=%s' % (str(wcctx._status)))
 
 print('=== with "always match":')
 print(actx1.status(other=wcctx))
 print('wcctx._status=%s' % (str(wcctx._status)))
 print(actx2.status(other=wcctx))
 print('wcctx._status=%s' % (str(wcctx._status)))
 
 print('=== with "always match" and "listclean=True":')
 print(actx1.status(other=wcctx, listclean=True))
 print('wcctx._status=%s' % (str(wcctx._status)))
 print(actx2.status(other=wcctx, listclean=True))
 print('wcctx._status=%s' % (str(wcctx._status)))
 
 print('=== with "pattern match":')
 print(actx1.status(other=wcctx,
                    match=scmutil.matchfiles(repo, [b'bar-m', b'foo'])))
 print('wcctx._status=%s' % (str(wcctx._status)))
 print(actx2.status(other=wcctx,
                    match=scmutil.matchfiles(repo, [b'bar-m', b'foo'])))
 print('wcctx._status=%s' % (str(wcctx._status)))
 
 print('=== with "pattern match" and "listclean=True":')
 print(actx1.status(other=wcctx,
                    match=scmutil.matchfiles(repo, [b'bar-r', b'foo']),
                    listclean=True))
 print('wcctx._status=%s' % (str(wcctx._status)))
 print(actx2.status(other=wcctx,
                    match=scmutil.matchfiles(repo, [b'bar-r', b'foo']),
                    listclean=True))
 print('wcctx._status=%s' % (str(wcctx._status)))
 
 os.chdir('..')
 
 # test manifestlog being changed
 print('== commit with manifestlog invalidated')
 
 repo = hg.repository(u, b'test2', create=1)
 os.chdir('test2')
 
 # make some commits
 for i in [b'1', b'2', b'3']:
     with open(i, 'wb') as f:
         f.write(i)
     status = scmutil.status([], [i], [], [], [], [], [])
     ctx = context.workingcommitctx(repo, status, text=i, user=b'[e-mail]',
                                    date=(0, 0))
     ctx.p1().manifest() # side effect: cache manifestctx
     n = repo.commitctx(ctx)
     printb(b'commit %s: %s' % (i, hex(n)))
 
     # touch 00manifest.i mtime so storecache could expire.
     # repo.__dict__['manifestlog'] is deleted by transaction releasefn.
     st = repo.svfs.stat(b'00manifest.i')
     repo.svfs.utime(b'00manifest.i',
                     (st[stat.ST_MTIME] + 1, st[stat.ST_MTIME] + 1))
 
     # read the file just committed
     try:
         if repo[n][i].data() != i:
             print('data mismatch')
     except Exception as ex:
         print('cannot read data: %r' % ex)
 
 with repo.wlock(), repo.lock(), repo.transaction(b'test'):
     with open(b'4', 'wb') as f:
         f.write(b'4')
     repo.dirstate.normal(b'4')
     repo.commit(b'4')
     revsbefore = len(repo.changelog)
     repo.invalidate(clearfilecache=True)
     revsafter = len(repo.changelog)
     if revsbefore != revsafter:
         print('changeset lost by repo.invalidate()')