revset: extract a parsefollowlinespattern helper function

We'll need the same logic in forthcoming changeset to handle --line-range
option in 'hg log' command.
The function lives in scmutil.py (rather than util.py) as it uses match and
pathutil modules.

mercurial/revset.py

@@ -1,2232 +1,2225
 # 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,
     registrar,
     repoview,
     revsetlang,
     scmutil,
     smartset,
     util,
 )
 
 # 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
 
 # operator methods
 
 def stringset(repo, subset, x, order):
     x = scmutil.intrev(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, len(repo) - 1, 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(), len(repo) - 1, 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, len(repo) - 1, 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 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, **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.
     """
     # i18n: "ancestor" is a keyword
     l = getlist(x)
     rl = fullreposet(repo)
     anc = None
 
     # (getset(repo, rl, i) for i in l) generates a list of lists
     for revs in (getset(repo, rl, i) for i in l):
         for r in revs:
             if anc is None:
                 anc = repo[r]
             else:
                 anc = anc.ancestor(repo[r])
 
     if anc is not None and anc.rev() in subset:
         return baseset([anc.rev()])
     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 = util.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 = util.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>' % sorted(b))
 
 @predicate('bumped()', safe=True)
 def bumped(repo, subset, x):
     msg = ("'bumped()' is deprecated, "
            "use 'phasedivergent()'")
     repo.ui.deprecwarn(msg, '4.4')
 
     return phasedivergent(repo, subset, x)
 
 @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 = util.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>' % sorted(dests))
 
 @predicate('divergent()', safe=True)
 def divergent(repo, subset, x):
     msg = ("'divergent()' is deprecated, "
            "use 'contentdivergent()'")
     repo.ui.deprecwarn(msg, '4.4')
 
     return contentdivergent(repo, subset, x)
 
 @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 = util.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):
     l = getargs(x, 0, 2, _("%s takes no arguments or a pattern "
                            "and an optional revset") % name)
     c = repo['.']
     if l:
         x = getstring(l[0], _("%s expected a pattern") % name)
         rev = None
         if len(l) >= 2:
             revs = getset(repo, fullreposet(repo), l[1])
             if len(revs) != 1:
                 raise error.RepoLookupError(
                         _("%s expected one starting revision") % name)
             rev = revs.last()
             c = repo[rev]
         matcher = matchmod.match(repo.root, repo.getcwd(), [x],
                                  ctx=repo[rev], default='path')
 
         files = c.manifest().walk(matcher)
 
         s = set()
         for fname in files:
             fctx = c[fname]
             s = s.union(set(c.rev() for c in fctx.ancestors(followfirst)))
             # include the revision responsible for the most recent version
             s.add(fctx.introrev())
     else:
         s = dagop.revancestors(repo, baseset([c.rev()]), followfirst)
 
     return subset & s
 
 @predicate('follow([pattern[, startrev]])', safe=True)
 def follow(repo, subset, x):
     """
     An alias for ``::.`` (ancestors of the working directory's first parent).
     If 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([pattern[, startrev]])``
     # Like ``follow([pattern[, 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"))
-    if not matchmod.patkind(pat):
-        fname = pathutil.canonpath(repo.root, repo.getcwd(), pat)
-    else:
-        m = matchmod.match(repo.root, repo.getcwd(), [pat], ctx=repo[rev])
-        files = [f for f in repo[rev] if m(f)]
-        if len(files) != 1:
-            # i18n: "followlines" is a keyword
-            raise error.ParseError(_("followlines expects exactly one file"))
-        fname = files[0]
-
+    # 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') % 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; leave rev as None
                 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'
 
     m = matchmod.match(repo.root, repo.getcwd(), pats, include=inc,
                        exclude=exc, ctx=repo[rev], default=default)
 
     # 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)
         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)
 def heads(repo, subset, x):
     """Members of set with no children in set.
     """
     s = getset(repo, subset, x)
     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 = util.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 = repo.changelog._partialmatch(n)
             if pm is not None:
                 rn = repo.changelog.rev(pm)
         except error.WdirUnsupported:
             rn = node.wdirrev
 
     if rn is None:
         return baseset()
     result = baseset([rn])
     return result & subset
 
 @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 ''
     dest = repo.ui.expandpath(dest or 'default-push', 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)
     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"""
     s = repo._phasecache.getrevset(repo, targets)
     return subset & s
 
 @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)
 
 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"))
     phase = repo._phasecache.phase
     target = phases.public
     condition = lambda r: phase(repo, r) == target
     return subset.filter(condition, condrepr=('<phase %r>', target),
                          cache=False)
 
 @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(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[0] == '-')
         if reverse:
             k = k[1:]
         if k not in _sortkeyfuncs and k != 'topo':
             raise error.ParseError(_("unknown sort key %r") % 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 = util.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 = util.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 = util.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('unstable()', safe=True)
 def unstable(repo, subset, x):
     msg = ("'unstable()' is deprecated, "
            "use 'orphan()'")
     repo.ui.deprecwarn(msg, '4.4')
 
     return orphan(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 str(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 posttreebuilthook(tree, repo):
     # hook for extensions to execute code on the optimized tree
     pass
 
 def match(ui, spec, repo=None):
     """Create a matcher for a single revision spec"""
     return matchany(ui, [spec], repo=repo)
 
 def matchany(ui, specs, repo=None, localalias=None):
     """Create a matcher that will include any revisions matching one of the
     given specs
 
     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"))
     lookup = None
     if repo:
         lookup = repo.__contains__
     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)
     posttreebuilthook(tree, repo)
     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/scmutil.py

@@ -1,1259 +1,1273
 # scmutil.py - Mercurial core utility functions
 #
 #  Copyright Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import errno
 import glob
 import hashlib
 import os
 import re
 import socket
 import subprocess
 import weakref
 
 from .i18n import _
 from .node import (
     hex,
     nullid,
     short,
     wdirid,
     wdirrev,
 )
 
 from . import (
     encoding,
     error,
     match as matchmod,
     obsolete,
     obsutil,
     pathutil,
     phases,
     pycompat,
     revsetlang,
     similar,
     url,
     util,
     vfs,
 )
 
 if pycompat.iswindows:
     from . import scmwindows as scmplatform
 else:
     from . import scmposix as scmplatform
 
 termsize = scmplatform.termsize
 
 class status(tuple):
     '''Named tuple with a list of files per status. The 'deleted', 'unknown'
        and 'ignored' properties are only relevant to the working copy.
     '''
 
     __slots__ = ()
 
     def __new__(cls, modified, added, removed, deleted, unknown, ignored,
                 clean):
         return tuple.__new__(cls, (modified, added, removed, deleted, unknown,
                                    ignored, clean))
 
     @property
     def modified(self):
         '''files that have been modified'''
         return self[0]
 
     @property
     def added(self):
         '''files that have been added'''
         return self[1]
 
     @property
     def removed(self):
         '''files that have been removed'''
         return self[2]
 
     @property
     def deleted(self):
         '''files that are in the dirstate, but have been deleted from the
            working copy (aka "missing")
         '''
         return self[3]
 
     @property
     def unknown(self):
         '''files not in the dirstate that are not ignored'''
         return self[4]
 
     @property
     def ignored(self):
         '''files not in the dirstate that are ignored (by _dirignore())'''
         return self[5]
 
     @property
     def clean(self):
         '''files that have not been modified'''
         return self[6]
 
     def __repr__(self, *args, **kwargs):
         return (('<status modified=%r, added=%r, removed=%r, deleted=%r, '
                  'unknown=%r, ignored=%r, clean=%r>') % self)
 
 def itersubrepos(ctx1, ctx2):
     """find subrepos in ctx1 or ctx2"""
     # Create a (subpath, ctx) mapping where we prefer subpaths from
     # ctx1. The subpaths from ctx2 are important when the .hgsub file
     # has been modified (in ctx2) but not yet committed (in ctx1).
     subpaths = dict.fromkeys(ctx2.substate, ctx2)
     subpaths.update(dict.fromkeys(ctx1.substate, ctx1))
 
     missing = set()
 
     for subpath in ctx2.substate:
         if subpath not in ctx1.substate:
             del subpaths[subpath]
             missing.add(subpath)
 
     for subpath, ctx in sorted(subpaths.iteritems()):
         yield subpath, ctx.sub(subpath)
 
     # Yield an empty subrepo based on ctx1 for anything only in ctx2.  That way,
     # status and diff will have an accurate result when it does
     # 'sub.{status|diff}(rev2)'.  Otherwise, the ctx2 subrepo is compared
     # against itself.
     for subpath in missing:
         yield subpath, ctx2.nullsub(subpath, ctx1)
 
 def nochangesfound(ui, repo, excluded=None):
     '''Report no changes for push/pull, excluded is None or a list of
     nodes excluded from the push/pull.
     '''
     secretlist = []
     if excluded:
         for n in excluded:
             ctx = repo[n]
             if ctx.phase() >= phases.secret and not ctx.extinct():
                 secretlist.append(n)
 
     if secretlist:
         ui.status(_("no changes found (ignored %d secret changesets)\n")
                   % len(secretlist))
     else:
         ui.status(_("no changes found\n"))
 
 def callcatch(ui, func):
     """call func() with global exception handling
 
     return func() if no exception happens. otherwise do some error handling
     and return an exit code accordingly. does not handle all exceptions.
     """
     try:
         try:
             return func()
         except: # re-raises
             ui.traceback()
             raise
     # Global exception handling, alphabetically
     # Mercurial-specific first, followed by built-in and library exceptions
     except error.LockHeld as inst:
         if inst.errno == errno.ETIMEDOUT:
             reason = _('timed out waiting for lock held by %r') % inst.locker
         else:
             reason = _('lock held by %r') % inst.locker
         ui.warn(_("abort: %s: %s\n") % (inst.desc or inst.filename, reason))
         if not inst.locker:
             ui.warn(_("(lock might be very busy)\n"))
     except error.LockUnavailable as inst:
         ui.warn(_("abort: could not lock %s: %s\n") %
                (inst.desc or inst.filename,
                 encoding.strtolocal(inst.strerror)))
     except error.OutOfBandError as inst:
         if inst.args:
             msg = _("abort: remote error:\n")
         else:
             msg = _("abort: remote error\n")
         ui.warn(msg)
         if inst.args:
             ui.warn(''.join(inst.args))
         if inst.hint:
             ui.warn('(%s)\n' % inst.hint)
     except error.RepoError as inst:
         ui.warn(_("abort: %s!\n") % inst)
         if inst.hint:
             ui.warn(_("(%s)\n") % inst.hint)
     except error.ResponseError as inst:
         ui.warn(_("abort: %s") % inst.args[0])
         if not isinstance(inst.args[1], basestring):
             ui.warn(" %r\n" % (inst.args[1],))
         elif not inst.args[1]:
             ui.warn(_(" empty string\n"))
         else:
             ui.warn("\n%r\n" % util.ellipsis(inst.args[1]))
     except error.CensoredNodeError as inst:
         ui.warn(_("abort: file censored %s!\n") % inst)
     except error.RevlogError as inst:
         ui.warn(_("abort: %s!\n") % inst)
     except error.InterventionRequired as inst:
         ui.warn("%s\n" % inst)
         if inst.hint:
             ui.warn(_("(%s)\n") % inst.hint)
         return 1
     except error.WdirUnsupported:
         ui.warn(_("abort: working directory revision cannot be specified\n"))
     except error.Abort as inst:
         ui.warn(_("abort: %s\n") % inst)
         if inst.hint:
             ui.warn(_("(%s)\n") % inst.hint)
     except ImportError as inst:
         ui.warn(_("abort: %s!\n") % inst)
         m = str(inst).split()[-1]
         if m in "mpatch bdiff".split():
             ui.warn(_("(did you forget to compile extensions?)\n"))
         elif m in "zlib".split():
             ui.warn(_("(is your Python install correct?)\n"))
     except IOError as inst:
         if util.safehasattr(inst, "code"):
             ui.warn(_("abort: %s\n") % inst)
         elif util.safehasattr(inst, "reason"):
             try: # usually it is in the form (errno, strerror)
                 reason = inst.reason.args[1]
             except (AttributeError, IndexError):
                 # it might be anything, for example a string
                 reason = inst.reason
             if isinstance(reason, unicode):
                 # SSLError of Python 2.7.9 contains a unicode
                 reason = encoding.unitolocal(reason)
             ui.warn(_("abort: error: %s\n") % reason)
         elif (util.safehasattr(inst, "args")
               and inst.args and inst.args[0] == errno.EPIPE):
             pass
         elif getattr(inst, "strerror", None):
             if getattr(inst, "filename", None):
                 ui.warn(_("abort: %s: %s\n") % (
                     encoding.strtolocal(inst.strerror), inst.filename))
             else:
                 ui.warn(_("abort: %s\n") % encoding.strtolocal(inst.strerror))
         else:
             raise
     except OSError as inst:
         if getattr(inst, "filename", None) is not None:
             ui.warn(_("abort: %s: '%s'\n") % (
                 encoding.strtolocal(inst.strerror), inst.filename))
         else:
             ui.warn(_("abort: %s\n") % encoding.strtolocal(inst.strerror))
     except MemoryError:
         ui.warn(_("abort: out of memory\n"))
     except SystemExit as inst:
         # Commands shouldn't sys.exit directly, but give a return code.
         # Just in case catch this and and pass exit code to caller.
         return inst.code
     except socket.error as inst:
         ui.warn(_("abort: %s\n") % inst.args[-1])
 
     return -1
 
 def checknewlabel(repo, lbl, kind):
     # Do not use the "kind" parameter in ui output.
     # It makes strings difficult to translate.
     if lbl in ['tip', '.', 'null']:
         raise error.Abort(_("the name '%s' is reserved") % lbl)
     for c in (':', '\0', '\n', '\r'):
         if c in lbl:
             raise error.Abort(_("%r cannot be used in a name") % c)
     try:
         int(lbl)
         raise error.Abort(_("cannot use an integer as a name"))
     except ValueError:
         pass
 
 def checkfilename(f):
     '''Check that the filename f is an acceptable filename for a tracked file'''
     if '\r' in f or '\n' in f:
         raise error.Abort(_("'\\n' and '\\r' disallowed in filenames: %r") % f)
 
 def checkportable(ui, f):
     '''Check if filename f is portable and warn or abort depending on config'''
     checkfilename(f)
     abort, warn = checkportabilityalert(ui)
     if abort or warn:
         msg = util.checkwinfilename(f)
         if msg:
             msg = "%s: %s" % (msg, util.shellquote(f))
             if abort:
                 raise error.Abort(msg)
             ui.warn(_("warning: %s\n") % msg)
 
 def checkportabilityalert(ui):
     '''check if the user's config requests nothing, a warning, or abort for
     non-portable filenames'''
     val = ui.config('ui', 'portablefilenames')
     lval = val.lower()
     bval = util.parsebool(val)
     abort = pycompat.iswindows or lval == 'abort'
     warn = bval or lval == 'warn'
     if bval is None and not (warn or abort or lval == 'ignore'):
         raise error.ConfigError(
             _("ui.portablefilenames value is invalid ('%s')") % val)
     return abort, warn
 
 class casecollisionauditor(object):
     def __init__(self, ui, abort, dirstate):
         self._ui = ui
         self._abort = abort
         allfiles = '\0'.join(dirstate._map)
         self._loweredfiles = set(encoding.lower(allfiles).split('\0'))
         self._dirstate = dirstate
         # The purpose of _newfiles is so that we don't complain about
         # case collisions if someone were to call this object with the
         # same filename twice.
         self._newfiles = set()
 
     def __call__(self, f):
         if f in self._newfiles:
             return
         fl = encoding.lower(f)
         if fl in self._loweredfiles and f not in self._dirstate:
             msg = _('possible case-folding collision for %s') % f
             if self._abort:
                 raise error.Abort(msg)
             self._ui.warn(_("warning: %s\n") % msg)
         self._loweredfiles.add(fl)
         self._newfiles.add(f)
 
 def filteredhash(repo, maxrev):
     """build hash of filtered revisions in the current repoview.
 
     Multiple caches perform up-to-date validation by checking that the
     tiprev and tipnode stored in the cache file match the current repository.
     However, this is not sufficient for validating repoviews because the set
     of revisions in the view may change without the repository tiprev and
     tipnode changing.
 
     This function hashes all the revs filtered from the view and returns
     that SHA-1 digest.
     """
     cl = repo.changelog
     if not cl.filteredrevs:
         return None
     key = None
     revs = sorted(r for r in cl.filteredrevs if r <= maxrev)
     if revs:
         s = hashlib.sha1()
         for rev in revs:
             s.update('%d;' % rev)
         key = s.digest()
     return key
 
 def walkrepos(path, followsym=False, seen_dirs=None, recurse=False):
     '''yield every hg repository under path, always recursively.
     The recurse flag will only control recursion into repo working dirs'''
     def errhandler(err):
         if err.filename == path:
             raise err
     samestat = getattr(os.path, 'samestat', None)
     if followsym and samestat is not None:
         def adddir(dirlst, dirname):
             match = False
             dirstat = os.stat(dirname)
             for lstdirstat in dirlst:
                 if samestat(dirstat, lstdirstat):
                     match = True
                     break
             if not match:
                 dirlst.append(dirstat)
             return not match
     else:
         followsym = False
 
     if (seen_dirs is None) and followsym:
         seen_dirs = []
         adddir(seen_dirs, path)
     for root, dirs, files in os.walk(path, topdown=True, onerror=errhandler):
         dirs.sort()
         if '.hg' in dirs:
             yield root # found a repository
             qroot = os.path.join(root, '.hg', 'patches')
             if os.path.isdir(os.path.join(qroot, '.hg')):
                 yield qroot # we have a patch queue repo here
             if recurse:
                 # avoid recursing inside the .hg directory
                 dirs.remove('.hg')
             else:
                 dirs[:] = [] # don't descend further
         elif followsym:
             newdirs = []
             for d in dirs:
                 fname = os.path.join(root, d)
                 if adddir(seen_dirs, fname):
                     if os.path.islink(fname):
                         for hgname in walkrepos(fname, True, seen_dirs):
                             yield hgname
                     else:
                         newdirs.append(d)
             dirs[:] = newdirs
 
 def binnode(ctx):
     """Return binary node id for a given basectx"""
     node = ctx.node()
     if node is None:
         return wdirid
     return node
 
 def intrev(ctx):
     """Return integer for a given basectx that can be used in comparison or
     arithmetic operation"""
     rev = ctx.rev()
     if rev is None:
         return wdirrev
     return rev
 
 def formatchangeid(ctx):
     """Format changectx as '{rev}:{node|formatnode}', which is the default
     template provided by cmdutil.changeset_templater"""
     repo = ctx.repo()
     return formatrevnode(repo.ui, intrev(ctx), binnode(ctx))
 
 def formatrevnode(ui, rev, node):
     """Format given revision and node depending on the current verbosity"""
     if ui.debugflag:
         hexfunc = hex
     else:
         hexfunc = short
     return '%d:%s' % (rev, hexfunc(node))
 
 def revsingle(repo, revspec, default='.', localalias=None):
     if not revspec and revspec != 0:
         return repo[default]
 
     l = revrange(repo, [revspec], localalias=localalias)
     if not l:
         raise error.Abort(_('empty revision set'))
     return repo[l.last()]
 
 def _pairspec(revspec):
     tree = revsetlang.parse(revspec)
     return tree and tree[0] in ('range', 'rangepre', 'rangepost', 'rangeall')
 
 def revpair(repo, revs):
     if not revs:
         return repo.dirstate.p1(), None
 
     l = revrange(repo, revs)
 
     if not l:
         first = second = None
     elif l.isascending():
         first = l.min()
         second = l.max()
     elif l.isdescending():
         first = l.max()
         second = l.min()
     else:
         first = l.first()
         second = l.last()
 
     if first is None:
         raise error.Abort(_('empty revision range'))
     if (first == second and len(revs) >= 2
         and not all(revrange(repo, [r]) for r in revs)):
         raise error.Abort(_('empty revision on one side of range'))
 
     # if top-level is range expression, the result must always be a pair
     if first == second and len(revs) == 1 and not _pairspec(revs[0]):
         return repo.lookup(first), None
 
     return repo.lookup(first), repo.lookup(second)
 
 def revrange(repo, specs, localalias=None):
     """Execute 1 to many revsets and return the union.
 
     This is the preferred mechanism for executing revsets using user-specified
     config options, such as revset aliases.
 
     The revsets specified by ``specs`` will be executed via a chained ``OR``
     expression. If ``specs`` is empty, an empty result is returned.
 
     ``specs`` can contain integers, in which case they are assumed to be
     revision numbers.
 
     It is assumed the revsets are already formatted. If you have arguments
     that need to be expanded in the revset, call ``revsetlang.formatspec()``
     and pass the result as an element of ``specs``.
 
     Specifying a single revset is allowed.
 
     Returns a ``revset.abstractsmartset`` which is a list-like interface over
     integer revisions.
     """
     allspecs = []
     for spec in specs:
         if isinstance(spec, int):
             spec = revsetlang.formatspec('rev(%d)', spec)
         allspecs.append(spec)
     return repo.anyrevs(allspecs, user=True, localalias=localalias)
 
 def meaningfulparents(repo, ctx):
     """Return list of meaningful (or all if debug) parentrevs for rev.
 
     For merges (two non-nullrev revisions) both parents are meaningful.
     Otherwise the first parent revision is considered meaningful if it
     is not the preceding revision.
     """
     parents = ctx.parents()
     if len(parents) > 1:
         return parents
     if repo.ui.debugflag:
         return [parents[0], repo['null']]
     if parents[0].rev() >= intrev(ctx) - 1:
         return []
     return parents
 
 def expandpats(pats):
     '''Expand bare globs when running on windows.
     On posix we assume it already has already been done by sh.'''
     if not util.expandglobs:
         return list(pats)
     ret = []
     for kindpat in pats:
         kind, pat = matchmod._patsplit(kindpat, None)
         if kind is None:
             try:
                 globbed = glob.glob(pat)
             except re.error:
                 globbed = [pat]
             if globbed:
                 ret.extend(globbed)
                 continue
         ret.append(kindpat)
     return ret
 
 def matchandpats(ctx, pats=(), opts=None, globbed=False, default='relpath',
                  badfn=None):
     '''Return a matcher and the patterns that were used.
     The matcher will warn about bad matches, unless an alternate badfn callback
     is provided.'''
     if pats == ("",):
         pats = []
     if opts is None:
         opts = {}
     if not globbed and default == 'relpath':
         pats = expandpats(pats or [])
 
     def bad(f, msg):
         ctx.repo().ui.warn("%s: %s\n" % (m.rel(f), msg))
 
     if badfn is None:
         badfn = bad
 
     m = ctx.match(pats, opts.get('include'), opts.get('exclude'),
                   default, listsubrepos=opts.get('subrepos'), badfn=badfn)
 
     if m.always():
         pats = []
     return m, pats
 
 def match(ctx, pats=(), opts=None, globbed=False, default='relpath',
           badfn=None):
     '''Return a matcher that will warn about bad matches.'''
     return matchandpats(ctx, pats, opts, globbed, default, badfn=badfn)[0]
 
 def matchall(repo):
     '''Return a matcher that will efficiently match everything.'''
     return matchmod.always(repo.root, repo.getcwd())
 
 def matchfiles(repo, files, badfn=None):
     '''Return a matcher that will efficiently match exactly these files.'''
     return matchmod.exact(repo.root, repo.getcwd(), files, badfn=badfn)
 
+def parsefollowlinespattern(repo, rev, pat, msg):
+    """Return a file name from `pat` pattern suitable for usage in followlines
+    logic.
+    """
+    if not matchmod.patkind(pat):
+        return pathutil.canonpath(repo.root, repo.getcwd(), pat)
+    else:
+        ctx = repo[rev]
+        m = matchmod.match(repo.root, repo.getcwd(), [pat], ctx=ctx)
+        files = [f for f in ctx if m(f)]
+        if len(files) != 1:
+            raise error.ParseError(msg)
+        return files[0]
+
 def origpath(ui, repo, filepath):
     '''customize where .orig files are created
 
     Fetch user defined path from config file: [ui] origbackuppath = <path>
     Fall back to default (filepath with .orig suffix) if not specified
     '''
     origbackuppath = ui.config('ui', 'origbackuppath')
     if not origbackuppath:
         return filepath + ".orig"
 
     # Convert filepath from an absolute path into a path inside the repo.
     filepathfromroot = util.normpath(os.path.relpath(filepath,
                                                      start=repo.root))
 
     origvfs = vfs.vfs(repo.wjoin(origbackuppath))
     origbackupdir = origvfs.dirname(filepathfromroot)
     if not origvfs.isdir(origbackupdir) or origvfs.islink(origbackupdir):
         ui.note(_('creating directory: %s\n') % origvfs.join(origbackupdir))
 
         # Remove any files that conflict with the backup file's path
         for f in reversed(list(util.finddirs(filepathfromroot))):
             if origvfs.isfileorlink(f):
                 ui.note(_('removing conflicting file: %s\n')
                         % origvfs.join(f))
                 origvfs.unlink(f)
                 break
 
         origvfs.makedirs(origbackupdir)
 
     if origvfs.isdir(filepathfromroot):
         ui.note(_('removing conflicting directory: %s\n')
                 % origvfs.join(filepathfromroot))
         origvfs.rmtree(filepathfromroot, forcibly=True)
 
     return origvfs.join(filepathfromroot)
 
 class _containsnode(object):
     """proxy __contains__(node) to container.__contains__ which accepts revs"""
 
     def __init__(self, repo, revcontainer):
         self._torev = repo.changelog.rev
         self._revcontains = revcontainer.__contains__
 
     def __contains__(self, node):
         return self._revcontains(self._torev(node))
 
 def cleanupnodes(repo, replacements, operation, moves=None, metadata=None):
     """do common cleanups when old nodes are replaced by new nodes
 
     That includes writing obsmarkers or stripping nodes, and moving bookmarks.
     (we might also want to move working directory parent in the future)
 
     By default, bookmark moves are calculated automatically from 'replacements',
     but 'moves' can be used to override that. Also, 'moves' may include
     additional bookmark moves that should not have associated obsmarkers.
 
     replacements is {oldnode: [newnode]} or a iterable of nodes if they do not
     have replacements. operation is a string, like "rebase".
 
     metadata is dictionary containing metadata to be stored in obsmarker if
     obsolescence is enabled.
     """
     if not replacements and not moves:
         return
 
     # translate mapping's other forms
     if not util.safehasattr(replacements, 'items'):
         replacements = {n: () for n in replacements}
 
     # Calculate bookmark movements
     if moves is None:
         moves = {}
     # Unfiltered repo is needed since nodes in replacements might be hidden.
     unfi = repo.unfiltered()
     for oldnode, newnodes in replacements.items():
         if oldnode in moves:
             continue
         if len(newnodes) > 1:
             # usually a split, take the one with biggest rev number
             newnode = next(unfi.set('max(%ln)', newnodes)).node()
         elif len(newnodes) == 0:
             # move bookmark backwards
             roots = list(unfi.set('max((::%n) - %ln)', oldnode,
                                   list(replacements)))
             if roots:
                 newnode = roots[0].node()
             else:
                 newnode = nullid
         else:
             newnode = newnodes[0]
         moves[oldnode] = newnode
 
     with repo.transaction('cleanup') as tr:
         # Move bookmarks
         bmarks = repo._bookmarks
         bmarkchanges = []
         allnewnodes = [n for ns in replacements.values() for n in ns]
         for oldnode, newnode in moves.items():
             oldbmarks = repo.nodebookmarks(oldnode)
             if not oldbmarks:
                 continue
             from . import bookmarks # avoid import cycle
             repo.ui.debug('moving bookmarks %r from %s to %s\n' %
                           (oldbmarks, hex(oldnode), hex(newnode)))
             # Delete divergent bookmarks being parents of related newnodes
             deleterevs = repo.revs('parents(roots(%ln & (::%n))) - parents(%n)',
                                    allnewnodes, newnode, oldnode)
             deletenodes = _containsnode(repo, deleterevs)
             for name in oldbmarks:
                 bmarkchanges.append((name, newnode))
                 for b in bookmarks.divergent2delete(repo, deletenodes, name):
                     bmarkchanges.append((b, None))
 
         if bmarkchanges:
             bmarks.applychanges(repo, tr, bmarkchanges)
 
         # Obsolete or strip nodes
         if obsolete.isenabled(repo, obsolete.createmarkersopt):
             # If a node is already obsoleted, and we want to obsolete it
             # without a successor, skip that obssolete request since it's
             # unnecessary. That's the "if s or not isobs(n)" check below.
             # Also sort the node in topology order, that might be useful for
             # some obsstore logic.
             # NOTE: the filtering and sorting might belong to createmarkers.
             isobs = unfi.obsstore.successors.__contains__
             torev = unfi.changelog.rev
             sortfunc = lambda ns: torev(ns[0])
             rels = [(unfi[n], tuple(unfi[m] for m in s))
                     for n, s in sorted(replacements.items(), key=sortfunc)
                     if s or not isobs(n)]
             if rels:
                 obsolete.createmarkers(repo, rels, operation=operation,
                                        metadata=metadata)
         else:
             from . import repair # avoid import cycle
             tostrip = list(replacements)
             if tostrip:
                 repair.delayedstrip(repo.ui, repo, tostrip, operation)
 
 def addremove(repo, matcher, prefix, opts=None, dry_run=None, similarity=None):
     if opts is None:
         opts = {}
     m = matcher
     if dry_run is None:
         dry_run = opts.get('dry_run')
     if similarity is None:
         similarity = float(opts.get('similarity') or 0)
 
     ret = 0
     join = lambda f: os.path.join(prefix, f)
 
     wctx = repo[None]
     for subpath in sorted(wctx.substate):
         submatch = matchmod.subdirmatcher(subpath, m)
         if opts.get('subrepos') or m.exact(subpath) or any(submatch.files()):
             sub = wctx.sub(subpath)
             try:
                 if sub.addremove(submatch, prefix, opts, dry_run, similarity):
                     ret = 1
             except error.LookupError:
                 repo.ui.status(_("skipping missing subrepository: %s\n")
                                  % join(subpath))
 
     rejected = []
     def badfn(f, msg):
         if f in m.files():
             m.bad(f, msg)
         rejected.append(f)
 
     badmatch = matchmod.badmatch(m, badfn)
     added, unknown, deleted, removed, forgotten = _interestingfiles(repo,
                                                                     badmatch)
 
     unknownset = set(unknown + forgotten)
     toprint = unknownset.copy()
     toprint.update(deleted)
     for abs in sorted(toprint):
         if repo.ui.verbose or not m.exact(abs):
             if abs in unknownset:
                 status = _('adding %s\n') % m.uipath(abs)
             else:
                 status = _('removing %s\n') % m.uipath(abs)
             repo.ui.status(status)
 
     renames = _findrenames(repo, m, added + unknown, removed + deleted,
                            similarity)
 
     if not dry_run:
         _markchanges(repo, unknown + forgotten, deleted, renames)
 
     for f in rejected:
         if f in m.files():
             return 1
     return ret
 
 def marktouched(repo, files, similarity=0.0):
     '''Assert that files have somehow been operated upon. files are relative to
     the repo root.'''
     m = matchfiles(repo, files, badfn=lambda x, y: rejected.append(x))
     rejected = []
 
     added, unknown, deleted, removed, forgotten = _interestingfiles(repo, m)
 
     if repo.ui.verbose:
         unknownset = set(unknown + forgotten)
         toprint = unknownset.copy()
         toprint.update(deleted)
         for abs in sorted(toprint):
             if abs in unknownset:
                 status = _('adding %s\n') % abs
             else:
                 status = _('removing %s\n') % abs
             repo.ui.status(status)
 
     renames = _findrenames(repo, m, added + unknown, removed + deleted,
                            similarity)
 
     _markchanges(repo, unknown + forgotten, deleted, renames)
 
     for f in rejected:
         if f in m.files():
             return 1
     return 0
 
 def _interestingfiles(repo, matcher):
     '''Walk dirstate with matcher, looking for files that addremove would care
     about.
 
     This is different from dirstate.status because it doesn't care about
     whether files are modified or clean.'''
     added, unknown, deleted, removed, forgotten = [], [], [], [], []
     audit_path = pathutil.pathauditor(repo.root, cached=True)
 
     ctx = repo[None]
     dirstate = repo.dirstate
     walkresults = dirstate.walk(matcher, subrepos=sorted(ctx.substate),
                                 unknown=True, ignored=False, full=False)
     for abs, st in walkresults.iteritems():
         dstate = dirstate[abs]
         if dstate == '?' and audit_path.check(abs):
             unknown.append(abs)
         elif dstate != 'r' and not st:
             deleted.append(abs)
         elif dstate == 'r' and st:
             forgotten.append(abs)
         # for finding renames
         elif dstate == 'r' and not st:
             removed.append(abs)
         elif dstate == 'a':
             added.append(abs)
 
     return added, unknown, deleted, removed, forgotten
 
 def _findrenames(repo, matcher, added, removed, similarity):
     '''Find renames from removed files to added ones.'''
     renames = {}
     if similarity > 0:
         for old, new, score in similar.findrenames(repo, added, removed,
                                                    similarity):
             if (repo.ui.verbose or not matcher.exact(old)
                 or not matcher.exact(new)):
                 repo.ui.status(_('recording removal of %s as rename to %s '
                                  '(%d%% similar)\n') %
                                (matcher.rel(old), matcher.rel(new),
                                 score * 100))
             renames[new] = old
     return renames
 
 def _markchanges(repo, unknown, deleted, renames):
     '''Marks the files in unknown as added, the files in deleted as removed,
     and the files in renames as copied.'''
     wctx = repo[None]
     with repo.wlock():
         wctx.forget(deleted)
         wctx.add(unknown)
         for new, old in renames.iteritems():
             wctx.copy(old, new)
 
 def dirstatecopy(ui, repo, wctx, src, dst, dryrun=False, cwd=None):
     """Update the dirstate to reflect the intent of copying src to dst. For
     different reasons it might not end with dst being marked as copied from src.
     """
     origsrc = repo.dirstate.copied(src) or src
     if dst == origsrc: # copying back a copy?
         if repo.dirstate[dst] not in 'mn' and not dryrun:
             repo.dirstate.normallookup(dst)
     else:
         if repo.dirstate[origsrc] == 'a' and origsrc == src:
             if not ui.quiet:
                 ui.warn(_("%s has not been committed yet, so no copy "
                           "data will be stored for %s.\n")
                         % (repo.pathto(origsrc, cwd), repo.pathto(dst, cwd)))
             if repo.dirstate[dst] in '?r' and not dryrun:
                 wctx.add([dst])
         elif not dryrun:
             wctx.copy(origsrc, dst)
 
 def readrequires(opener, supported):
     '''Reads and parses .hg/requires and checks if all entries found
     are in the list of supported features.'''
     requirements = set(opener.read("requires").splitlines())
     missings = []
     for r in requirements:
         if r not in supported:
             if not r or not r[0].isalnum():
                 raise error.RequirementError(_(".hg/requires file is corrupt"))
             missings.append(r)
     missings.sort()
     if missings:
         raise error.RequirementError(
             _("repository requires features unknown to this Mercurial: %s")
             % " ".join(missings),
             hint=_("see https://mercurial-scm.org/wiki/MissingRequirement"
                    " for more information"))
     return requirements
 
 def writerequires(opener, requirements):
     with opener('requires', 'w') as fp:
         for r in sorted(requirements):
             fp.write("%s\n" % r)
 
 class filecachesubentry(object):
     def __init__(self, path, stat):
         self.path = path
         self.cachestat = None
         self._cacheable = None
 
         if stat:
             self.cachestat = filecachesubentry.stat(self.path)
 
             if self.cachestat:
                 self._cacheable = self.cachestat.cacheable()
             else:
                 # None means we don't know yet
                 self._cacheable = None
 
     def refresh(self):
         if self.cacheable():
             self.cachestat = filecachesubentry.stat(self.path)
 
     def cacheable(self):
         if self._cacheable is not None:
             return self._cacheable
 
         # we don't know yet, assume it is for now
         return True
 
     def changed(self):
         # no point in going further if we can't cache it
         if not self.cacheable():
             return True
 
         newstat = filecachesubentry.stat(self.path)
 
         # we may not know if it's cacheable yet, check again now
         if newstat and self._cacheable is None:
             self._cacheable = newstat.cacheable()
 
             # check again
             if not self._cacheable:
                 return True
 
         if self.cachestat != newstat:
             self.cachestat = newstat
             return True
         else:
             return False
 
     @staticmethod
     def stat(path):
         try:
             return util.cachestat(path)
         except OSError as e:
             if e.errno != errno.ENOENT:
                 raise
 
 class filecacheentry(object):
     def __init__(self, paths, stat=True):
         self._entries = []
         for path in paths:
             self._entries.append(filecachesubentry(path, stat))
 
     def changed(self):
         '''true if any entry has changed'''
         for entry in self._entries:
             if entry.changed():
                 return True
         return False
 
     def refresh(self):
         for entry in self._entries:
             entry.refresh()
 
 class filecache(object):
     '''A property like decorator that tracks files under .hg/ for updates.
 
     Records stat info when called in _filecache.
 
     On subsequent calls, compares old stat info with new info, and recreates the
     object when any of the files changes, updating the new stat info in
     _filecache.
 
     Mercurial either atomic renames or appends for files under .hg,
     so to ensure the cache is reliable we need the filesystem to be able
     to tell us if a file has been replaced. If it can't, we fallback to
     recreating the object on every call (essentially the same behavior as
     propertycache).
 
     '''
     def __init__(self, *paths):
         self.paths = paths
 
     def join(self, obj, fname):
         """Used to compute the runtime path of a cached file.
 
         Users should subclass filecache and provide their own version of this
         function to call the appropriate join function on 'obj' (an instance
         of the class that its member function was decorated).
         """
         raise NotImplementedError
 
     def __call__(self, func):
         self.func = func
         self.name = func.__name__.encode('ascii')
         return self
 
     def __get__(self, obj, type=None):
         # if accessed on the class, return the descriptor itself.
         if obj is None:
             return self
         # do we need to check if the file changed?
         if self.name in obj.__dict__:
             assert self.name in obj._filecache, self.name
             return obj.__dict__[self.name]
 
         entry = obj._filecache.get(self.name)
 
         if entry:
             if entry.changed():
                 entry.obj = self.func(obj)
         else:
             paths = [self.join(obj, path) for path in self.paths]
 
             # We stat -before- creating the object so our cache doesn't lie if
             # a writer modified between the time we read and stat
             entry = filecacheentry(paths, True)
             entry.obj = self.func(obj)
 
             obj._filecache[self.name] = entry
 
         obj.__dict__[self.name] = entry.obj
         return entry.obj
 
     def __set__(self, obj, value):
         if self.name not in obj._filecache:
             # we add an entry for the missing value because X in __dict__
             # implies X in _filecache
             paths = [self.join(obj, path) for path in self.paths]
             ce = filecacheentry(paths, False)
             obj._filecache[self.name] = ce
         else:
             ce = obj._filecache[self.name]
 
         ce.obj = value # update cached copy
         obj.__dict__[self.name] = value # update copy returned by obj.x
 
     def __delete__(self, obj):
         try:
             del obj.__dict__[self.name]
         except KeyError:
             raise AttributeError(self.name)
 
 def extdatasource(repo, source):
     """Gather a map of rev -> value dict from the specified source
 
     A source spec is treated as a URL, with a special case shell: type
     for parsing the output from a shell command.
 
     The data is parsed as a series of newline-separated records where
     each record is a revision specifier optionally followed by a space
     and a freeform string value. If the revision is known locally, it
     is converted to a rev, otherwise the record is skipped.
 
     Note that both key and value are treated as UTF-8 and converted to
     the local encoding. This allows uniformity between local and
     remote data sources.
     """
 
     spec = repo.ui.config("extdata", source)
     if not spec:
         raise error.Abort(_("unknown extdata source '%s'") % source)
 
     data = {}
     src = proc = None
     try:
         if spec.startswith("shell:"):
             # external commands should be run relative to the repo root
             cmd = spec[6:]
             proc = subprocess.Popen(cmd, shell=True, bufsize=-1,
                                     close_fds=util.closefds,
                                     stdout=subprocess.PIPE, cwd=repo.root)
             src = proc.stdout
         else:
             # treat as a URL or file
             src = url.open(repo.ui, spec)
         for l in src:
             if " " in l:
                 k, v = l.strip().split(" ", 1)
             else:
                 k, v = l.strip(), ""
 
             k = encoding.tolocal(k)
             try:
                 data[repo[k].rev()] = encoding.tolocal(v)
             except (error.LookupError, error.RepoLookupError):
                 pass # we ignore data for nodes that don't exist locally
     finally:
         if proc:
             proc.communicate()
             if proc.returncode != 0:
                 # not an error so 'cmd | grep' can be empty
                 repo.ui.debug("extdata command '%s' %s\n"
                               % (cmd, util.explainexit(proc.returncode)[0]))
         if src:
             src.close()
 
     return data
 
 def _locksub(repo, lock, envvar, cmd, environ=None, *args, **kwargs):
     if lock is None:
         raise error.LockInheritanceContractViolation(
             'lock can only be inherited while held')
     if environ is None:
         environ = {}
     with lock.inherit() as locker:
         environ[envvar] = locker
         return repo.ui.system(cmd, environ=environ, *args, **kwargs)
 
 def wlocksub(repo, cmd, *args, **kwargs):
     """run cmd as a subprocess that allows inheriting repo's wlock
 
     This can only be called while the wlock is held. This takes all the
     arguments that ui.system does, and returns the exit code of the
     subprocess."""
     return _locksub(repo, repo.currentwlock(), 'HG_WLOCK_LOCKER', cmd, *args,
                     **kwargs)
 
 def gdinitconfig(ui):
     """helper function to know if a repo should be created as general delta
     """
     # experimental config: format.generaldelta
     return (ui.configbool('format', 'generaldelta')
             or ui.configbool('format', 'usegeneraldelta'))
 
 def gddeltaconfig(ui):
     """helper function to know if incoming delta should be optimised
     """
     # experimental config: format.generaldelta
     return ui.configbool('format', 'generaldelta')
 
 class simplekeyvaluefile(object):
     """A simple file with key=value lines
 
     Keys must be alphanumerics and start with a letter, values must not
     contain '\n' characters"""
     firstlinekey = '__firstline'
 
     def __init__(self, vfs, path, keys=None):
         self.vfs = vfs
         self.path = path
 
     def read(self, firstlinenonkeyval=False):
         """Read the contents of a simple key-value file
 
         'firstlinenonkeyval' indicates whether the first line of file should
         be treated as a key-value pair or reuturned fully under the
         __firstline key."""
         lines = self.vfs.readlines(self.path)
         d = {}
         if firstlinenonkeyval:
             if not lines:
                 e = _("empty simplekeyvalue file")
                 raise error.CorruptedState(e)
             # we don't want to include '\n' in the __firstline
             d[self.firstlinekey] = lines[0][:-1]
             del lines[0]
 
         try:
             # the 'if line.strip()' part prevents us from failing on empty
             # lines which only contain '\n' therefore are not skipped
             # by 'if line'
             updatedict = dict(line[:-1].split('=', 1) for line in lines
                                                       if line.strip())
             if self.firstlinekey in updatedict:
                 e = _("%r can't be used as a key")
                 raise error.CorruptedState(e % self.firstlinekey)
             d.update(updatedict)
         except ValueError as e:
             raise error.CorruptedState(str(e))
         return d
 
     def write(self, data, firstline=None):
         """Write key=>value mapping to a file
         data is a dict. Keys must be alphanumerical and start with a letter.
         Values must not contain newline characters.
 
         If 'firstline' is not None, it is written to file before
         everything else, as it is, not in a key=value form"""
         lines = []
         if firstline is not None:
             lines.append('%s\n' % firstline)
 
         for k, v in data.items():
             if k == self.firstlinekey:
                 e = "key name '%s' is reserved" % self.firstlinekey
                 raise error.ProgrammingError(e)
             if not k[0].isalpha():
                 e = "keys must start with a letter in a key-value file"
                 raise error.ProgrammingError(e)
             if not k.isalnum():
                 e = "invalid key name in a simple key-value file"
                 raise error.ProgrammingError(e)
             if '\n' in v:
                 e = "invalid value in a simple key-value file"
                 raise error.ProgrammingError(e)
             lines.append("%s=%s\n" % (k, v))
         with self.vfs(self.path, mode='wb', atomictemp=True) as fp:
             fp.write(''.join(lines))
 
 _reportobsoletedsource = [
     'debugobsolete',
     'pull',
     'push',
     'serve',
     'unbundle',
 ]
 
 _reportnewcssource = [
     'pull',
     'unbundle',
 ]
 
 def registersummarycallback(repo, otr, txnname=''):
     """register a callback to issue a summary after the transaction is closed
     """
     def txmatch(sources):
         return any(txnname.startswith(source) for source in sources)
 
     categories = []
 
     def reportsummary(func):
         """decorator for report callbacks."""
         reporef = weakref.ref(repo)
         def wrapped(tr):
             repo = reporef()
             func(repo, tr)
         newcat = '%2i-txnreport' % len(categories)
         otr.addpostclose(newcat, wrapped)
         categories.append(newcat)
         return wrapped
 
     if txmatch(_reportobsoletedsource):
         @reportsummary
         def reportobsoleted(repo, tr):
             obsoleted = obsutil.getobsoleted(repo, tr)
             if obsoleted:
                 repo.ui.status(_('obsoleted %i changesets\n')
                                % len(obsoleted))
 
     if txmatch(_reportnewcssource):
         @reportsummary
         def reportnewcs(repo, tr):
             """Report the range of new revisions pulled/unbundled."""
             newrevs = list(tr.changes.get('revs', set()))
             if not newrevs:
                 return
 
             # Compute the bounds of new revisions' range, excluding obsoletes.
             unfi = repo.unfiltered()
             revs = unfi.revs('%ld and not obsolete()', newrevs)
             if not revs:
                 # Got only obsoletes.
                 return
             minrev, maxrev = repo[revs.min()], repo[revs.max()]
 
             if minrev == maxrev:
                 revrange = minrev
             else:
                 revrange = '%s:%s' % (minrev, maxrev)
             repo.ui.status(_('new changesets %s\n') % revrange)