revset: add a predicate for finding converted changesets

This selects changesets added because of repo conversions.  For example

    hg log -r "converted()"      # all csets created by a convertion
    hg log -r "converted(rev)"   # the cset converted from rev in the src repo

The converted(rev) form is analogous to remote(id), where the remote repo is
the source of the conversion.  This can be useful for cross referencing an old
repository into the current one.

The source revision may be the short changeset hash or the full hash from the
source repository.  The local identifier isn't useful.  An interesting
ramification of this is if a short revision is specified, it may cause more
than one changeset to be selected.  (e.g. converted(6) matches changesets with
a convert_revision field of 6e..e and 67..0)

The convert.hg.saverev option must have been specified when converting the hg
source repository for this to work.  The other sources automatically embed the
converted marker.

mercurial/revset.py

@@ -1,1685 +1,1707 b''
 # revset.py - revision set queries for mercurial
 #
 # Copyright 2010 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 import re
 import parser, util, error, discovery, hbisect, phases
 import node
 import bookmarks as bookmarksmod
 import match as matchmod
 from i18n import _
 import encoding
 
 def _revancestors(repo, revs, followfirst):
     """Like revlog.ancestors(), but supports followfirst."""
     cut = followfirst and 1 or None
     cl = repo.changelog
     visit = util.deque(revs)
     seen = set([node.nullrev])
     while visit:
         for parent in cl.parentrevs(visit.popleft())[:cut]:
             if parent not in seen:
                 visit.append(parent)
                 seen.add(parent)
                 yield parent
 
 def _revdescendants(repo, revs, followfirst):
     """Like revlog.descendants() but supports followfirst."""
     cut = followfirst and 1 or None
     cl = repo.changelog
     first = min(revs)
     nullrev = node.nullrev
     if first == nullrev:
         # Are there nodes with a null first parent and a non-null
         # second one? Maybe. Do we care? Probably not.
         for i in cl:
             yield i
         return
 
     seen = set(revs)
     for i in xrange(first + 1, len(cl)):
         for x in cl.parentrevs(i)[:cut]:
             if x != nullrev and x in seen:
                 seen.add(i)
                 yield i
                 break
 
 def _revsbetween(repo, roots, heads):
     """Return all paths between roots and heads, inclusive of both endpoint
     sets."""
     if not roots:
         return []
     parentrevs = repo.changelog.parentrevs
     visit = heads[:]
     reachable = set()
     seen = {}
     minroot = min(roots)
     roots = set(roots)
     # open-code the post-order traversal due to the tiny size of
     # sys.getrecursionlimit()
     while visit:
         rev = visit.pop()
         if rev in roots:
             reachable.add(rev)
         parents = parentrevs(rev)
         seen[rev] = parents
         for parent in parents:
             if parent >= minroot and parent not in seen:
                 visit.append(parent)
     if not reachable:
         return []
     for rev in sorted(seen):
         for parent in seen[rev]:
             if parent in reachable:
                 reachable.add(rev)
     return sorted(reachable)
 
 elements = {
     "(": (20, ("group", 1, ")"), ("func", 1, ")")),
     "~": (18, None, ("ancestor", 18)),
     "^": (18, None, ("parent", 18), ("parentpost", 18)),
     "-": (5, ("negate", 19), ("minus", 5)),
     "::": (17, ("dagrangepre", 17), ("dagrange", 17),
            ("dagrangepost", 17)),
     "..": (17, ("dagrangepre", 17), ("dagrange", 17),
            ("dagrangepost", 17)),
     ":": (15, ("rangepre", 15), ("range", 15), ("rangepost", 15)),
     "not": (10, ("not", 10)),
     "!": (10, ("not", 10)),
     "and": (5, None, ("and", 5)),
     "&": (5, None, ("and", 5)),
     "or": (4, None, ("or", 4)),
     "|": (4, None, ("or", 4)),
     "+": (4, None, ("or", 4)),
     ",": (2, None, ("list", 2)),
     ")": (0, None, None),
     "symbol": (0, ("symbol",), None),
     "string": (0, ("string",), None),
     "end": (0, None, None),
 }
 
 keywords = set(['and', 'or', 'not'])
 
 def tokenize(program):
     pos, l = 0, len(program)
     while pos < l:
         c = program[pos]
         if c.isspace(): # skip inter-token whitespace
             pass
         elif c == ':' and program[pos:pos + 2] == '::': # look ahead carefully
             yield ('::', None, pos)
             pos += 1 # skip ahead
         elif c == '.' and program[pos:pos + 2] == '..': # look ahead carefully
             yield ('..', None, pos)
             pos += 1 # skip ahead
         elif c in "():,-|&+!~^": # handle simple operators
             yield (c, None, pos)
         elif (c in '"\'' or c == 'r' and
               program[pos:pos + 2] in ("r'", 'r"')): # handle quoted strings
             if c == 'r':
                 pos += 1
                 c = program[pos]
                 decode = lambda x: x
             else:
                 decode = lambda x: x.decode('string-escape')
             pos += 1
             s = pos
             while pos < l: # find closing quote
                 d = program[pos]
                 if d == '\\': # skip over escaped characters
                     pos += 2
                     continue
                 if d == c:
                     yield ('string', decode(program[s:pos]), s)
                     break
                 pos += 1
             else:
                 raise error.ParseError(_("unterminated string"), s)
         # gather up a symbol/keyword
         elif c.isalnum() or c in '._' or ord(c) > 127:
             s = pos
             pos += 1
             while pos < l: # find end of symbol
                 d = program[pos]
                 if not (d.isalnum() or d in "._/" or ord(d) > 127):
                     break
                 if d == '.' and program[pos - 1] == '.': # special case for ..
                     pos -= 1
                     break
                 pos += 1
             sym = program[s:pos]
             if sym in keywords: # operator keywords
                 yield (sym, None, s)
             else:
                 yield ('symbol', sym, s)
             pos -= 1
         else:
             raise error.ParseError(_("syntax error"), pos)
         pos += 1
     yield ('end', None, pos)
 
 # helpers
 
 def getstring(x, err):
     if x and (x[0] == 'string' or x[0] == 'symbol'):
         return x[1]
     raise error.ParseError(err)
 
 def getlist(x):
     if not x:
         return []
     if x[0] == 'list':
         return getlist(x[1]) + [x[2]]
     return [x]
 
 def getargs(x, min, max, err):
     l = getlist(x)
     if len(l) < min or (max >= 0 and len(l) > max):
         raise error.ParseError(err)
     return l
 
 def getset(repo, subset, x):
     if not x:
         raise error.ParseError(_("missing argument"))
     return methods[x[0]](repo, subset, *x[1:])
 
 # operator methods
 
 def stringset(repo, subset, x):
     x = repo[x].rev()
     if x == -1 and len(subset) == len(repo):
         return [-1]
     if len(subset) == len(repo) or x in subset:
         return [x]
     return []
 
 def symbolset(repo, subset, x):
     if x in symbols:
         raise error.ParseError(_("can't use %s here") % x)
     return stringset(repo, subset, x)
 
 def rangeset(repo, subset, x, y):
     m = getset(repo, subset, x)
     if not m:
         m = getset(repo, range(len(repo)), x)
 
     n = getset(repo, subset, y)
     if not n:
         n = getset(repo, range(len(repo)), y)
 
     if not m or not n:
         return []
     m, n = m[0], n[-1]
 
     if m < n:
         r = range(m, n + 1)
     else:
         r = range(m, n - 1, -1)
     s = set(subset)
     return [x for x in r if x in s]
 
 def dagrange(repo, subset, x, y):
     if subset:
         r = range(len(repo))
         xs = _revsbetween(repo, getset(repo, r, x), getset(repo, r, y))
         s = set(subset)
         return [r for r in xs if r in s]
     return []
 
 def andset(repo, subset, x, y):
     return getset(repo, getset(repo, subset, x), y)
 
 def orset(repo, subset, x, y):
     xl = getset(repo, subset, x)
     s = set(xl)
     yl = getset(repo, [r for r in subset if r not in s], y)
     return xl + yl
 
 def notset(repo, subset, x):
     s = set(getset(repo, subset, x))
     return [r for r in subset if r not in s]
 
 def listset(repo, subset, a, b):
     raise error.ParseError(_("can't use a list in this context"))
 
 def func(repo, subset, a, b):
     if a[0] == 'symbol' and a[1] in symbols:
         return symbols[a[1]](repo, subset, b)
     raise error.ParseError(_("not a function: %s") % a[1])
 
 # functions
 
 def adds(repo, subset, x):
     """``adds(pattern)``
     Changesets that add a file matching pattern.
     """
     # i18n: "adds" is a keyword
     pat = getstring(x, _("adds requires a pattern"))
     return checkstatus(repo, subset, pat, 1)
 
 def ancestor(repo, subset, x):
     """``ancestor(single, single)``
     Greatest common ancestor of the two changesets.
     """
     # i18n: "ancestor" is a keyword
     l = getargs(x, 2, 2, _("ancestor requires two arguments"))
     r = range(len(repo))
     a = getset(repo, r, l[0])
     b = getset(repo, r, l[1])
     if len(a) != 1 or len(b) != 1:
         # i18n: "ancestor" is a keyword
         raise error.ParseError(_("ancestor arguments must be single revisions"))
     an = [repo[a[0]].ancestor(repo[b[0]]).rev()]
 
     return [r for r in an if r in subset]
 
 def _ancestors(repo, subset, x, followfirst=False):
     args = getset(repo, range(len(repo)), x)
     if not args:
         return []
     s = set(_revancestors(repo, args, followfirst)) | set(args)
     return [r for r in subset if r in s]
 
 def ancestors(repo, subset, x):
     """``ancestors(set)``
     Changesets that are ancestors of a changeset in set.
     """
     return _ancestors(repo, subset, x)
 
 def _firstancestors(repo, subset, x):
     # ``_firstancestors(set)``
     # Like ``ancestors(set)`` but follows only the first parents.
     return _ancestors(repo, subset, x, followfirst=True)
 
 def ancestorspec(repo, subset, x, n):
     """``set~n``
     Changesets that are the Nth ancestor (first parents only) of a changeset
     in set.
     """
     try:
         n = int(n[1])
     except (TypeError, ValueError):
         raise error.ParseError(_("~ expects a number"))
     ps = set()
     cl = repo.changelog
     for r in getset(repo, subset, x):
         for i in range(n):
             r = cl.parentrevs(r)[0]
         ps.add(r)
     return [r for r in subset if r in ps]
 
 def author(repo, subset, x):
     """``author(string)``
     Alias for ``user(string)``.
     """
     # i18n: "author" is a keyword
     n = encoding.lower(getstring(x, _("author requires a string")))
     kind, pattern, matcher = _substringmatcher(n)
     return [r for r in subset if matcher(encoding.lower(repo[r].user()))]
 
 def bisect(repo, subset, x):
     """``bisect(string)``
     Changesets marked in the specified bisect status:
 
     - ``good``, ``bad``, ``skip``: csets explicitly marked as good/bad/skip
     - ``goods``, ``bads``      : csets topologicaly 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
     """
     status = getstring(x, _("bisect requires a string")).lower()
     state = set(hbisect.get(repo, status))
     return [r for r in subset if r in state]
 
 # Backward-compatibility
 # - no help entry so that we do not advertise it any more
 def bisected(repo, subset, x):
     return bisect(repo, subset, x)
 
 def bookmark(repo, subset, x):
     """``bookmark([name])``
     The named bookmark or all bookmarks.
 
     If `name` starts with `re:`, the remainder of the name is treated as
     a regular expression. To match a bookmark that actually starts with `re:`,
     use the prefix `literal:`.
     """
     # 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 = _stringmatcher(bm)
         if kind == 'literal':
             bmrev = bookmarksmod.listbookmarks(repo).get(bm, None)
             if not bmrev:
                 raise util.Abort(_("bookmark '%s' does not exist") % bm)
             bmrev = repo[bmrev].rev()
             return [r for r in subset if r == bmrev]
         else:
             matchrevs = set()
             for name, bmrev in bookmarksmod.listbookmarks(repo).iteritems():
                 if matcher(name):
                     matchrevs.add(bmrev)
             if not matchrevs:
                 raise util.Abort(_("no bookmarks exist that match '%s'")
                                  % pattern)
             bmrevs = set()
             for bmrev in matchrevs:
                 bmrevs.add(repo[bmrev].rev())
             return [r for r in subset if r in bmrevs]
 
     bms = set([repo[r].rev()
                for r in bookmarksmod.listbookmarks(repo).values()])
     return [r for r in subset if r in bms]
 
 def branch(repo, subset, x):
     """``branch(string or set)``
     All changesets belonging to the given branch or the branches of the given
     changesets.
 
     If `string` starts with `re:`, the remainder of the name is treated as
     a regular expression. To match a branch that actually starts with `re:`,
     use the prefix `literal:`.
     """
     try:
         b = getstring(x, '')
     except error.ParseError:
         # not a string, but another revspec, e.g. tip()
         pass
     else:
         kind, pattern, matcher = _stringmatcher(b)
         if kind == 'literal':
             # note: falls through to the revspec case if no branch with
             # this name exists
             if pattern in repo.branchmap():
                 return [r for r in subset if matcher(repo[r].branch())]
         else:
             return [r for r in subset if matcher(repo[r].branch())]
 
     s = getset(repo, range(len(repo)), x)
     b = set()
     for r in s:
         b.add(repo[r].branch())
     s = set(s)
     return [r for r in subset if r in s or repo[r].branch() in b]
 
 def checkstatus(repo, subset, pat, field):
     m = None
     s = []
     hasset = matchmod.patkind(pat) == 'set'
     fname = None
     for r in subset:
         c = repo[r]
         if not m or hasset:
             m = matchmod.match(repo.root, repo.getcwd(), [pat], ctx=c)
             if not m.anypats() and len(m.files()) == 1:
                 fname = m.files()[0]
         if fname is not None:
             if fname not in c.files():
                 continue
         else:
             for f in c.files():
                 if m(f):
                     break
             else:
                 continue
         files = repo.status(c.p1().node(), c.node())[field]
         if fname is not None:
             if fname in files:
                 s.append(r)
         else:
             for f in files:
                 if m(f):
                     s.append(r)
                     break
     return s
 
 def _children(repo, narrow, parentset):
     cs = set()
     pr = repo.changelog.parentrevs
     for r in narrow:
         for p in pr(r):
             if p in parentset:
                 cs.add(r)
     return cs
 
 def children(repo, subset, x):
     """``children(set)``
     Child changesets of changesets in set.
     """
     s = set(getset(repo, range(len(repo)), x))
     cs = _children(repo, subset, s)
     return [r for r in subset if r in cs]
 
 def closed(repo, subset, x):
     """``closed()``
     Changeset is closed.
     """
     # i18n: "closed" is a keyword
     getargs(x, 0, 0, _("closed takes no arguments"))
     return [r for r in subset if repo[r].closesbranch()]
 
 def contains(repo, subset, x):
     """``contains(pattern)``
     Revision contains a file matching pattern. See :hg:`help patterns`
     for information about file patterns.
     """
     # i18n: "contains" is a keyword
     pat = getstring(x, _("contains requires a pattern"))
     m = None
     s = []
     if not matchmod.patkind(pat):
         for r in subset:
             if pat in repo[r]:
                 s.append(r)
     else:
         for r in subset:
             c = repo[r]
             if not m or matchmod.patkind(pat) == 'set':
                 m = matchmod.match(repo.root, repo.getcwd(), [pat], ctx=c)
             for f in c.manifest():
                 if m(f):
                     s.append(r)
                     break
     return s
 
+def converted(repo, subset, x):
+    """``converted([id])``
+    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
+
+    # i18n: "converted" is a keyword
+    rev = None
+    l = getargs(x, 0, 1, _('converted takes one or no arguments'))
+    if l:
+        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 [r for r in subset if _matchvalue(r)]
+
 def date(repo, subset, x):
     """``date(interval)``
     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 [r for r in subset if dm(repo[r].date()[0])]
 
 def desc(repo, subset, x):
     """``desc(string)``
     Search commit message for string. The match is case-insensitive.
     """
     # i18n: "desc" is a keyword
     ds = encoding.lower(getstring(x, _("desc requires a string")))
     l = []
     for r in subset:
         c = repo[r]
         if ds in encoding.lower(c.description()):
             l.append(r)
     return l
 
 def _descendants(repo, subset, x, followfirst=False):
     args = getset(repo, range(len(repo)), x)
     if not args:
         return []
     s = set(_revdescendants(repo, args, followfirst)) | set(args)
     return [r for r in subset if r in s]
 
 def descendants(repo, subset, x):
     """``descendants(set)``
     Changesets which are descendants of changesets in set.
     """
     return _descendants(repo, subset, x)
 
 def _firstdescendants(repo, subset, x):
     # ``_firstdescendants(set)``
     # Like ``descendants(set)`` but follows only the first parents.
     return _descendants(repo, subset, x, followfirst=True)
 
 def draft(repo, subset, x):
     """``draft()``
     Changeset in draft phase."""
     getargs(x, 0, 0, _("draft takes no arguments"))
     pc = repo._phasecache
     return [r for r in subset if pc.phase(repo, r) == phases.draft]
 
 def extra(repo, subset, x):
     """``extra(label, [value])``
     Changesets with the given label in the extra metadata, with the given
     optional value.
 
     If `value` starts with `re:`, the remainder of the value is treated as
     a regular expression. To match a value that actually starts with `re:`,
     use the prefix `literal:`.
     """
 
     l = getargs(x, 1, 2, _('extra takes at least 1 and at most 2 arguments'))
     label = getstring(l[0], _('first argument to extra must be a string'))
     value = None
 
     if len(l) > 1:
         value = getstring(l[1], _('second argument to extra must be a string'))
         kind, value, matcher = _stringmatcher(value)
 
     def _matchvalue(r):
         extra = repo[r].extra()
         return label in extra and (value is None or matcher(extra[label]))
 
     return [r for r in subset if _matchvalue(r)]
 
 def filelog(repo, subset, x):
     """``filelog(pattern)``
     Changesets connected to the specified filelog.
     """
 
     pat = getstring(x, _("filelog requires a pattern"))
     m = matchmod.match(repo.root, repo.getcwd(), [pat], default='relpath',
                        ctx=repo[None])
     s = set()
 
     if not matchmod.patkind(pat):
         for f in m.files():
             fl = repo.file(f)
             for fr in fl:
                 s.add(fl.linkrev(fr))
     else:
         for f in repo[None]:
             if m(f):
                 fl = repo.file(f)
                 for fr in fl:
                     s.add(fl.linkrev(fr))
 
     return [r for r in subset if r in s]
 
 def first(repo, subset, x):
     """``first(set, [n])``
     An alias for limit().
     """
     return limit(repo, subset, x)
 
 def _follow(repo, subset, x, name, followfirst=False):
     l = getargs(x, 0, 1, _("%s takes no arguments or a filename") % name)
     c = repo['.']
     if l:
         x = getstring(l[0], _("%s expected a filename") % name)
         if x in c:
             cx = c[x]
             s = set(ctx.rev() for ctx in cx.ancestors(followfirst=followfirst))
             # include the revision responsible for the most recent version
             s.add(cx.linkrev())
         else:
             return []
     else:
         s = set(_revancestors(repo, [c.rev()], followfirst)) | set([c.rev()])
 
     return [r for r in subset if r in s]
 
 def follow(repo, subset, x):
     """``follow([file])``
     An alias for ``::.`` (ancestors of the working copy's first parent).
     If a filename is specified, the history of the given file is followed,
     including copies.
     """
     return _follow(repo, subset, x, 'follow')
 
 def _followfirst(repo, subset, x):
     # ``followfirst([file])``
     # Like ``follow([file])`` but follows only the first parent of
     # every revision or file revision.
     return _follow(repo, subset, x, '_followfirst', followfirst=True)
 
 def getall(repo, subset, x):
     """``all()``
     All changesets, the same as ``0:tip``.
     """
     # i18n: "all" is a keyword
     getargs(x, 0, 0, _("all takes no arguments"))
     return subset
 
 def grep(repo, subset, x):
     """``grep(regex)``
     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, e:
         raise error.ParseError(_('invalid match pattern: %s') % e)
     l = []
     for r in subset:
         c = repo[r]
         for e in c.files() + [c.user(), c.description()]:
             if gr.search(e):
                 l.append(r)
                 break
     return l
 
 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.
 
     # i18n: "_matchfiles" is a keyword
     l = getargs(x, 1, -1, _("_matchfiles requires at least one argument"))
     pats, inc, exc = [], [], []
     hasset = False
     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'))
             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 hasset and matchmod.patkind(value) == 'set':
             hasset = True
     if not default:
         default = 'glob'
     m = None
     s = []
     for r in subset:
         c = repo[r]
         if not m or (hasset and rev is None):
             ctx = c
             if rev is not None:
                 ctx = repo[rev or None]
             m = matchmod.match(repo.root, repo.getcwd(), pats, include=inc,
                                exclude=exc, ctx=ctx, default=default)
         for f in c.files():
             if m(f):
                 s.append(r)
                 break
     return s
 
 def hasfile(repo, subset, x):
     """``file(pattern)``
     Changesets affecting files matched by pattern.
     """
     # i18n: "file" is a keyword
     pat = getstring(x, _("file requires a pattern"))
     return _matchfiles(repo, subset, ('string', 'p:' + pat))
 
 def head(repo, subset, x):
     """``head()``
     Changeset is a named branch head.
     """
     # i18n: "head" is a keyword
     getargs(x, 0, 0, _("head takes no arguments"))
     hs = set()
     for b, ls in repo.branchmap().iteritems():
         hs.update(repo[h].rev() for h in ls)
     return [r for r in subset if r in hs]
 
 def heads(repo, subset, x):
     """``heads(set)``
     Members of set with no children in set.
     """
     s = getset(repo, subset, x)
     ps = set(parents(repo, subset, x))
     return [r for r in s if r not in ps]
 
 def keyword(repo, subset, x):
     """``keyword(string)``
     Search commit message, user name, and names of changed files for
     string. The match is case-insensitive.
     """
     # i18n: "keyword" is a keyword
     kw = encoding.lower(getstring(x, _("keyword requires a string")))
     l = []
     for r in subset:
         c = repo[r]
         t = " ".join(c.files() + [c.user(), c.description()])
         if kw in encoding.lower(t):
             l.append(r)
     return l
 
 def limit(repo, subset, x):
     """``limit(set, [n])``
     First n members of set, defaulting to 1.
     """
     # i18n: "limit" is a keyword
     l = getargs(x, 1, 2, _("limit requires one or two arguments"))
     try:
         lim = 1
         if len(l) == 2:
             # i18n: "limit" is a keyword
             lim = int(getstring(l[1], _("limit requires a number")))
     except (TypeError, ValueError):
         # i18n: "limit" is a keyword
         raise error.ParseError(_("limit expects a number"))
     ss = set(subset)
     os = getset(repo, range(len(repo)), l[0])[:lim]
     return [r for r in os if r in ss]
 
 def last(repo, subset, x):
     """``last(set, [n])``
     Last n members of set, defaulting to 1.
     """
     # i18n: "last" is a keyword
     l = getargs(x, 1, 2, _("last requires one or two arguments"))
     try:
         lim = 1
         if len(l) == 2:
             # i18n: "last" is a keyword
             lim = int(getstring(l[1], _("last requires a number")))
     except (TypeError, ValueError):
         # i18n: "last" is a keyword
         raise error.ParseError(_("last expects a number"))
     ss = set(subset)
     os = getset(repo, range(len(repo)), l[0])[-lim:]
     return [r for r in os if r in ss]
 
 def maxrev(repo, subset, x):
     """``max(set)``
     Changeset with highest revision number in set.
     """
     os = getset(repo, range(len(repo)), x)
     if os:
         m = max(os)
         if m in subset:
             return [m]
     return []
 
 def merge(repo, subset, x):
     """``merge()``
     Changeset is a merge changeset.
     """
     # i18n: "merge" is a keyword
     getargs(x, 0, 0, _("merge takes no arguments"))
     cl = repo.changelog
     return [r for r in subset if cl.parentrevs(r)[1] != -1]
 
 def minrev(repo, subset, x):
     """``min(set)``
     Changeset with lowest revision number in set.
     """
     os = getset(repo, range(len(repo)), x)
     if os:
         m = min(os)
         if m in subset:
             return [m]
     return []
 
 def modifies(repo, subset, x):
     """``modifies(pattern)``
     Changesets modifying files matched by pattern.
     """
     # i18n: "modifies" is a keyword
     pat = getstring(x, _("modifies requires a pattern"))
     return checkstatus(repo, subset, pat, 0)
 
 def node_(repo, subset, x):
     """``id(string)``
     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:
         rn = repo[n].rev()
     else:
         rn = None
         pm = repo.changelog._partialmatch(n)
         if pm is not None:
             rn = repo.changelog.rev(pm)
 
     return [r for r in subset if r == rn]
 
 def outgoing(repo, subset, x):
     """``outgoing([path])``
     Changesets not found in the specified destination repository, or the
     default push location.
     """
     import hg # avoid start-up nasties
     # 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 = set([cl.rev(r) for r in outgoing.missing])
     return [r for r in subset if r in o]
 
 def p1(repo, subset, x):
     """``p1([set])``
     First parent of changesets in set, or the working directory.
     """
     if x is None:
         p = repo[x].p1().rev()
         return [r for r in subset if r == p]
 
     ps = set()
     cl = repo.changelog
     for r in getset(repo, range(len(repo)), x):
         ps.add(cl.parentrevs(r)[0])
     return [r for r in subset if r in ps]
 
 def p2(repo, subset, x):
     """``p2([set])``
     Second parent of changesets in set, or the working directory.
     """
     if x is None:
         ps = repo[x].parents()
         try:
             p = ps[1].rev()
             return [r for r in subset if r == p]
         except IndexError:
             return []
 
     ps = set()
     cl = repo.changelog
     for r in getset(repo, range(len(repo)), x):
         ps.add(cl.parentrevs(r)[1])
     return [r for r in subset if r in ps]
 
 def parents(repo, subset, x):
     """``parents([set])``
     The set of all parents for all changesets in set, or the working directory.
     """
     if x is None:
         ps = tuple(p.rev() for p in repo[x].parents())
         return [r for r in subset if r in ps]
 
     ps = set()
     cl = repo.changelog
     for r in getset(repo, range(len(repo)), x):
         ps.update(cl.parentrevs(r))
     return [r for r in subset if r in ps]
 
 def parentspec(repo, subset, x, n):
     """``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, subset, x):
         if n == 0:
             ps.add(r)
         elif n == 1:
             ps.add(cl.parentrevs(r)[0])
         elif n == 2:
             parents = cl.parentrevs(r)
             if len(parents) > 1:
                 ps.add(parents[1])
     return [r for r in subset if r in ps]
 
 def present(repo, subset, x):
     """``present(set)``
     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)
     except error.RepoLookupError:
         return []
 
 def public(repo, subset, x):
     """``public()``
     Changeset in public phase."""
     getargs(x, 0, 0, _("public takes no arguments"))
     pc = repo._phasecache
     return [r for r in subset if pc.phase(repo, r) == phases.public]
 
 def remote(repo, subset, x):
     """``remote([id [,path]])``
     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.
     """
 
     import hg # avoid start-up nasties
     # i18n: "remote" is a keyword
     l = getargs(x, 0, 2, _("remote takes one, two or no 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 [r]
     return []
 
 def removes(repo, subset, x):
     """``removes(pattern)``
     Changesets which remove files matching pattern.
     """
     # i18n: "removes" is a keyword
     pat = getstring(x, _("removes requires a pattern"))
     return checkstatus(repo, subset, pat, 2)
 
 def rev(repo, subset, x):
     """``rev(number)``
     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"))
     return [r for r in subset if r == l]
 
 def matching(repo, subset, x):
     """``matching(revision [, field])``
     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`` and ``user``.
     Note that ``author`` and ``user`` are synonyms.
 
     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.
     """
     l = getargs(x, 1, 2, _("matching takes 1 or 2 arguments"))
 
     revs = getset(repo, xrange(len(repo)), l[0])
 
     fieldlist = ['metadata']
     if len(l) > 1:
             fieldlist = getstring(l[1],
                 _("matching requires a string "
                 "as its second argument")).split()
 
     # Make sure that there are no repeated fields, and expand the
     # 'special' 'metadata' field type
     fields = []
     for field in fieldlist:
         if field == 'metadata':
             fields += ['user', 'description', 'date']
         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']
     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],
     }
     for info in fields:
         getfield = _funcs.get(info, None)
         if getfield is None:
             raise error.ParseError(
                 _("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]
 
     matches = set()
     for rev in revs:
         target = getinfo(rev)
         for r in subset:
             match = True
             for n, f in enumerate(getfieldfuncs):
                 if target[n] != f(r):
                     match = False
                     break
             if match:
                 matches.add(r)
     return [r for r in subset if r in matches]
 
 def reverse(repo, subset, x):
     """``reverse(set)``
     Reverse order of set.
     """
     l = getset(repo, subset, x)
     l.reverse()
     return l
 
 def roots(repo, subset, x):
     """``roots(set)``
     Changesets in set with no parent changeset in set.
     """
     s = set(getset(repo, xrange(len(repo)), x))
     subset = [r for r in subset if r in s]
     cs = _children(repo, subset, s)
     return [r for r in subset if r not in cs]
 
 def secret(repo, subset, x):
     """``secret()``
     Changeset in secret phase."""
     getargs(x, 0, 0, _("secret takes no arguments"))
     pc = repo._phasecache
     return [r for r in subset if pc.phase(repo, r) == phases.secret]
 
 def sort(repo, subset, x):
     """``sort(set[, [-]key...])``
     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
     """
     # i18n: "sort" is a keyword
     l = getargs(x, 1, 2, _("sort requires one or two arguments"))
     keys = "rev"
     if len(l) == 2:
         keys = getstring(l[1], _("sort spec must be a string"))
 
     s = l[0]
     keys = keys.split()
     l = []
     def invert(s):
         return "".join(chr(255 - ord(c)) for c in s)
     for r in getset(repo, subset, s):
         c = repo[r]
         e = []
         for k in keys:
             if k == 'rev':
                 e.append(r)
             elif k == '-rev':
                 e.append(-r)
             elif k == 'branch':
                 e.append(c.branch())
             elif k == '-branch':
                 e.append(invert(c.branch()))
             elif k == 'desc':
                 e.append(c.description())
             elif k == '-desc':
                 e.append(invert(c.description()))
             elif k in 'user author':
                 e.append(c.user())
             elif k in '-user -author':
                 e.append(invert(c.user()))
             elif k == 'date':
                 e.append(c.date()[0])
             elif k == '-date':
                 e.append(-c.date()[0])
             else:
                 raise error.ParseError(_("unknown sort key %r") % k)
         e.append(r)
         l.append(e)
     l.sort()
     return [e[-1] for e in l]
 
 def _stringmatcher(pattern):
     """
     accepts a string, possibly starting with 're:' or 'literal:' prefix.
     returns the matcher name, pattern, and matcher function.
     missing or unknown prefixes are treated as literal matches.
 
     helper for tests:
     >>> def test(pattern, *tests):
     ...     kind, pattern, matcher = _stringmatcher(pattern)
     ...     return (kind, pattern, [bool(matcher(t)) for t in tests])
 
     exact matching (no prefix):
     >>> test('abcdefg', 'abc', 'def', 'abcdefg')
     ('literal', 'abcdefg', [False, False, True])
 
     regex matching ('re:' prefix)
     >>> test('re:a.+b', 'nomatch', 'fooadef', 'fooadefbar')
     ('re', 'a.+b', [False, False, True])
 
     force exact matches ('literal:' prefix)
     >>> test('literal:re:foobar', 'foobar', 're:foobar')
     ('literal', 're:foobar', [False, True])
 
     unknown prefixes are ignored and treated as literals
     >>> test('foo:bar', 'foo', 'bar', 'foo:bar')
     ('literal', 'foo:bar', [False, False, True])
     """
     if pattern.startswith('re:'):
         pattern = pattern[3:]
         try:
             regex = re.compile(pattern)
         except re.error, e:
             raise error.ParseError(_('invalid regular expression: %s')
                                    % e)
         return 're', pattern, regex.search
     elif pattern.startswith('literal:'):
         pattern = pattern[8:]
     return 'literal', pattern, pattern.__eq__
 
 def _substringmatcher(pattern):
     kind, pattern, matcher = _stringmatcher(pattern)
     if kind == 'literal':
         matcher = lambda s: pattern in s
     return kind, pattern, matcher
 
 def tag(repo, subset, x):
     """``tag([name])``
     The specified tag by name, or all tagged revisions if no name is given.
     """
     # 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 = _stringmatcher(pattern)
         if kind == 'literal':
             # avoid resolving all tags
             tn = repo._tagscache.tags.get(pattern, None)
             if tn is None:
                 raise util.Abort(_("tag '%s' does not exist") % pattern)
             s = set([repo[tn].rev()])
         else:
             s = set([cl.rev(n) for t, n in repo.tagslist() if matcher(t)])
             if not s:
                 raise util.Abort(_("no tags exist that match '%s'") % pattern)
     else:
         s = set([cl.rev(n) for t, n in repo.tagslist() if t != 'tip'])
     return [r for r in subset if r in s]
 
 def tagged(repo, subset, x):
     return tag(repo, subset, x)
 
 def user(repo, subset, x):
     """``user(string)``
     User name contains string. The match is case-insensitive.
 
     If `string` starts with `re:`, the remainder of the string is treated as
     a regular expression. To match a user that actually contains `re:`, use
     the prefix `literal:`.
     """
     return author(repo, subset, x)
 
 # for internal use
 def _list(repo, subset, x):
     s = getstring(x, "internal error")
     if not s:
         return []
     if not isinstance(subset, set):
         subset = set(subset)
     ls = [repo[r].rev() for r in s.split('\0')]
     return [r for r in ls if r in subset]
 
 symbols = {
     "adds": adds,
     "all": getall,
     "ancestor": ancestor,
     "ancestors": ancestors,
     "_firstancestors": _firstancestors,
     "author": author,
     "bisect": bisect,
     "bisected": bisected,
     "bookmark": bookmark,
     "branch": branch,
     "children": children,
     "closed": closed,
     "contains": contains,
+    "converted": converted,
     "date": date,
     "desc": desc,
     "descendants": descendants,
     "_firstdescendants": _firstdescendants,
     "draft": draft,
     "extra": extra,
     "file": hasfile,
     "filelog": filelog,
     "first": first,
     "follow": follow,
     "_followfirst": _followfirst,
     "grep": grep,
     "head": head,
     "heads": heads,
     "id": node_,
     "keyword": keyword,
     "last": last,
     "limit": limit,
     "_matchfiles": _matchfiles,
     "max": maxrev,
     "merge": merge,
     "min": minrev,
     "modifies": modifies,
     "outgoing": outgoing,
     "p1": p1,
     "p2": p2,
     "parents": parents,
     "present": present,
     "public": public,
     "remote": remote,
     "removes": removes,
     "rev": rev,
     "reverse": reverse,
     "roots": roots,
     "sort": sort,
     "secret": secret,
     "matching": matching,
     "tag": tag,
     "tagged": tagged,
     "user": user,
     "_list": _list,
 }
 
 methods = {
     "range": rangeset,
     "dagrange": dagrange,
     "string": stringset,
     "symbol": symbolset,
     "and": andset,
     "or": orset,
     "not": notset,
     "list": listset,
     "func": func,
     "ancestor": ancestorspec,
     "parent": parentspec,
     "parentpost": p1,
 }
 
 def optimize(x, small):
     if x is None:
         return 0, x
 
     smallbonus = 1
     if small:
         smallbonus = .5
 
     op = x[0]
     if op == 'minus':
         return optimize(('and', x[1], ('not', x[2])), small)
     elif op == 'dagrangepre':
         return optimize(('func', ('symbol', 'ancestors'), x[1]), small)
     elif op == 'dagrangepost':
         return optimize(('func', ('symbol', 'descendants'), x[1]), small)
     elif op == 'rangepre':
         return optimize(('range', ('string', '0'), x[1]), small)
     elif op == 'rangepost':
         return optimize(('range', x[1], ('string', 'tip')), small)
     elif op == 'negate':
         return optimize(('string',
                          '-' + getstring(x[1], _("can't negate that"))), small)
     elif op in 'string symbol negate':
         return smallbonus, x # single revisions are small
     elif op == 'and':
         wa, ta = optimize(x[1], True)
         wb, tb = optimize(x[2], True)
         w = min(wa, wb)
         if wa > wb:
             return w, (op, tb, ta)
         return w, (op, ta, tb)
     elif op == 'or':
         wa, ta = optimize(x[1], False)
         wb, tb = optimize(x[2], False)
         if wb < wa:
             wb, wa = wa, wb
         return max(wa, wb), (op, ta, tb)
     elif op == 'not':
         o = optimize(x[1], not small)
         return o[0], (op, o[1])
     elif op == 'parentpost':
         o = optimize(x[1], small)
         return o[0], (op, o[1])
     elif op == 'group':
         return optimize(x[1], small)
     elif op in 'dagrange range list parent ancestorspec':
         if op == 'parent':
             # x^:y means (x^) : y, not x ^ (:y)
             post = ('parentpost', x[1])
             if x[2][0] == 'dagrangepre':
                 return optimize(('dagrange', post, x[2][1]), small)
             elif x[2][0] == 'rangepre':
                 return optimize(('range', post, x[2][1]), small)
 
         wa, ta = optimize(x[1], small)
         wb, tb = optimize(x[2], small)
         return wa + wb, (op, ta, tb)
     elif op == 'func':
         f = getstring(x[1], _("not a symbol"))
         wa, ta = optimize(x[2], small)
         if f in ("author branch closed date desc file grep keyword "
                  "outgoing user"):
             w = 10 # slow
         elif f in "modifies adds removes":
             w = 30 # slower
         elif f == "contains":
             w = 100 # very slow
         elif f == "ancestor":
             w = 1 * smallbonus
         elif f in "reverse limit first":
             w = 0
         elif f in "sort":
             w = 10 # assume most sorts look at changelog
         else:
             w = 1
         return w + wa, (op, x[1], ta)
     return 1, x
 
 _aliasarg = ('func', ('symbol', '_aliasarg'))
 def _getaliasarg(tree):
     """If tree matches ('func', ('symbol', '_aliasarg'), ('string', X))
     return X, None otherwise.
     """
     if (len(tree) == 3 and tree[:2] == _aliasarg
         and tree[2][0] == 'string'):
         return tree[2][1]
     return None
 
 def _checkaliasarg(tree, known=None):
     """Check tree contains no _aliasarg construct or only ones which
     value is in known. Used to avoid alias placeholders injection.
     """
     if isinstance(tree, tuple):
         arg = _getaliasarg(tree)
         if arg is not None and (not known or arg not in known):
             raise error.ParseError(_("not a function: %s") % '_aliasarg')
         for t in tree:
             _checkaliasarg(t, known)
 
 class revsetalias(object):
     funcre = re.compile('^([^(]+)\(([^)]+)\)$')
     args = None
 
     def __init__(self, name, value):
         '''Aliases like:
 
         h = heads(default)
         b($1) = ancestors($1) - ancestors(default)
         '''
         m = self.funcre.search(name)
         if m:
             self.name = m.group(1)
             self.tree = ('func', ('symbol', m.group(1)))
             self.args = [x.strip() for x in m.group(2).split(',')]
             for arg in self.args:
                 # _aliasarg() is an unknown symbol only used separate
                 # alias argument placeholders from regular strings.
                 value = value.replace(arg, '_aliasarg(%r)' % (arg,))
         else:
             self.name = name
             self.tree = ('symbol', name)
 
         self.replacement, pos = parse(value)
         if pos != len(value):
             raise error.ParseError(_('invalid token'), pos)
         # Check for placeholder injection
         _checkaliasarg(self.replacement, self.args)
 
 def _getalias(aliases, tree):
     """If tree looks like an unexpanded alias, return it. Return None
     otherwise.
     """
     if isinstance(tree, tuple) and tree:
         if tree[0] == 'symbol' and len(tree) == 2:
             name = tree[1]
             alias = aliases.get(name)
             if alias and alias.args is None and alias.tree == tree:
                 return alias
         if tree[0] == 'func' and len(tree) > 1:
             if tree[1][0] == 'symbol' and len(tree[1]) == 2:
                 name = tree[1][1]
                 alias = aliases.get(name)
                 if alias and alias.args is not None and alias.tree == tree[:2]:
                     return alias
     return None
 
 def _expandargs(tree, args):
     """Replace _aliasarg instances with the substitution value of the
     same name in args, recursively.
     """
     if not tree or not isinstance(tree, tuple):
         return tree
     arg = _getaliasarg(tree)
     if arg is not None:
         return args[arg]
     return tuple(_expandargs(t, args) for t in tree)
 
 def _expandaliases(aliases, tree, expanding, cache):
     """Expand aliases in tree, recursively.
 
     'aliases' is a dictionary mapping user defined aliases to
     revsetalias objects.
     """
     if not isinstance(tree, tuple):
         # Do not expand raw strings
         return tree
     alias = _getalias(aliases, tree)
     if alias is not None:
         if alias in expanding:
             raise error.ParseError(_('infinite expansion of revset alias "%s" '
                                      'detected') % alias.name)
         expanding.append(alias)
         if alias.name not in cache:
             cache[alias.name] = _expandaliases(aliases, alias.replacement,
                                                expanding, cache)
         result = cache[alias.name]
         expanding.pop()
         if alias.args is not None:
             l = getlist(tree[2])
             if len(l) != len(alias.args):
                 raise error.ParseError(
                     _('invalid number of arguments: %s') % len(l))
             l = [_expandaliases(aliases, a, [], cache) for a in l]
             result = _expandargs(result, dict(zip(alias.args, l)))
     else:
         result = tuple(_expandaliases(aliases, t, expanding, cache)
                        for t in tree)
     return result
 
 def findaliases(ui, tree):
     _checkaliasarg(tree)
     aliases = {}
     for k, v in ui.configitems('revsetalias'):
         alias = revsetalias(k, v)
         aliases[alias.name] = alias
     return _expandaliases(aliases, tree, [], {})
 
 parse = parser.parser(tokenize, elements).parse
 
 def match(ui, spec):
     if not spec:
         raise error.ParseError(_("empty query"))
     tree, pos = parse(spec)
     if (pos != len(spec)):
         raise error.ParseError(_("invalid token"), pos)
     if ui:
         tree = findaliases(ui, tree)
     weight, tree = optimize(tree, True)
     def mfunc(repo, subset):
         return getset(repo, subset, tree)
     return mfunc
 
 def formatspec(expr, *args):
     '''
     This is a convenience function for using revsets internally, and
     escapes arguments appropriately. Aliases are intentionally ignored
     so that intended expression behavior isn't accidentally subverted.
 
     Supported arguments:
 
     %r = revset expression, parenthesized
     %d = int(arg), no quoting
     %s = string(arg), escaped and single-quoted
     %b = arg.branch(), escaped and single-quoted
     %n = hex(arg), single-quoted
     %% = a literal '%'
 
     Prefixing the type with 'l' specifies a parenthesized list of that type.
 
     >>> formatspec('%r:: and %lr', '10 or 11', ("this()", "that()"))
     '(10 or 11):: and ((this()) or (that()))'
     >>> formatspec('%d:: and not %d::', 10, 20)
     '10:: and not 20::'
     >>> formatspec('%ld or %ld', [], [1])
     "_list('') or 1"
     >>> formatspec('keyword(%s)', 'foo\\xe9')
     "keyword('foo\\\\xe9')"
     >>> b = lambda: 'default'
     >>> b.branch = b
     >>> formatspec('branch(%b)', b)
     "branch('default')"
     >>> formatspec('root(%ls)', ['a', 'b', 'c', 'd'])
     "root(_list('a\\x00b\\x00c\\x00d'))"
     '''
 
     def quote(s):
         return repr(str(s))
 
     def argtype(c, arg):
         if c == 'd':
             return str(int(arg))
         elif c == 's':
             return quote(arg)
         elif c == 'r':
             parse(arg) # make sure syntax errors are confined
             return '(%s)' % arg
         elif c == 'n':
             return quote(node.hex(arg))
         elif c == 'b':
             return quote(arg.branch())
 
     def listexp(s, t):
         l = len(s)
         if l == 0:
             return "_list('')"
         elif l == 1:
             return argtype(t, s[0])
         elif t == 'd':
             return "_list('%s')" % "\0".join(str(int(a)) for a in s)
         elif t == 's':
             return "_list('%s')" % "\0".join(s)
         elif t == 'n':
             return "_list('%s')" % "\0".join(node.hex(a) for a in s)
         elif t == 'b':
             return "_list('%s')" % "\0".join(a.branch() for a in s)
 
         m = l // 2
         return '(%s or %s)' % (listexp(s[:m], t), listexp(s[m:], t))
 
     ret = ''
     pos = 0
     arg = 0
     while pos < len(expr):
         c = expr[pos]
         if c == '%':
             pos += 1
             d = expr[pos]
             if d == '%':
                 ret += d
             elif d in 'dsnbr':
                 ret += argtype(d, args[arg])
                 arg += 1
             elif d == 'l':
                 # a list of some type
                 pos += 1
                 d = expr[pos]
                 ret += listexp(list(args[arg]), d)
                 arg += 1
             else:
                 raise util.Abort('unexpected revspec format character %s' % d)
         else:
             ret += c
         pos += 1
 
     return ret
 
 def prettyformat(tree):
     def _prettyformat(tree, level, lines):
         if not isinstance(tree, tuple) or tree[0] in ('string', 'symbol'):
             lines.append((level, str(tree)))
         else:
             lines.append((level, '(%s' % tree[0]))
             for s in tree[1:]:
                 _prettyformat(s, level + 1, lines)
             lines[-1:] = [(lines[-1][0], lines[-1][1] + ')')]
 
     lines = []
     _prettyformat(tree, 0, lines)
     output = '\n'.join(('  '*l + s) for l, s in lines)
     return output
 
 # tell hggettext to extract docstrings from these functions:
 i18nfunctions = symbols.values()

tests/test-convert.t

@@ -1,398 +1,447 b''
   $ cat >> $HGRCPATH <<EOF
   > [extensions]
   > convert=
   > [convert]
   > hg.saverev=False
   > EOF
   $ hg help convert
   hg convert [OPTION]... SOURCE [DEST [REVMAP]]
   
   convert a foreign SCM repository to a Mercurial one.
   
       Accepted source formats [identifiers]:
   
       - Mercurial [hg]
       - CVS [cvs]
       - Darcs [darcs]
       - git [git]
       - Subversion [svn]
       - Monotone [mtn]
       - GNU Arch [gnuarch]
       - Bazaar [bzr]
       - Perforce [p4]
   
       Accepted destination formats [identifiers]:
   
       - Mercurial [hg]
       - Subversion [svn] (history on branches is not preserved)
   
       If no revision is given, all revisions will be converted. Otherwise,
       convert will only import up to the named revision (given in a format
       understood by the source).
   
       If no destination directory name is specified, it defaults to the basename
       of the source with "-hg" appended. If the destination repository doesn't
       exist, it will be created.
   
       By default, all sources except Mercurial will use --branchsort. Mercurial
       uses --sourcesort to preserve original revision numbers order. Sort modes
       have the following effects:
   
       --branchsort  convert from parent to child revision when possible, which
                     means branches are usually converted one after the other.
                     It generates more compact repositories.
       --datesort    sort revisions by date. Converted repositories have good-
                     looking changelogs but are often an order of magnitude
                     larger than the same ones generated by --branchsort.
       --sourcesort  try to preserve source revisions order, only supported by
                     Mercurial sources.
   
       If "REVMAP" isn't given, it will be put in a default location
       ("<dest>/.hg/shamap" by default). The "REVMAP" is a simple text file that
       maps each source commit ID to the destination ID for that revision, like
       so:
   
         <source ID> <destination ID>
   
       If the file doesn't exist, it's automatically created. It's updated on
       each commit copied, so "hg convert" can be interrupted and can be run
       repeatedly to copy new commits.
   
       The authormap is a simple text file that maps each source commit author to
       a destination commit author. It is handy for source SCMs that use unix
       logins to identify authors (eg: CVS). One line per author mapping and the
       line format is:
   
         source author = destination author
   
       Empty lines and lines starting with a "#" are ignored.
   
       The filemap is a file that allows filtering and remapping of files and
       directories. Each line can contain one of the following directives:
   
         include path/to/file-or-dir
   
         exclude path/to/file-or-dir
   
         rename path/to/source path/to/destination
   
       Comment lines start with "#". A specified path matches if it equals the
       full relative name of a file or one of its parent directories. The
       "include" or "exclude" directive with the longest matching path applies,
       so line order does not matter.
   
       The "include" directive causes a file, or all files under a directory, to
       be included in the destination repository, and the exclusion of all other
       files and directories not explicitly included. The "exclude" directive
       causes files or directories to be omitted. The "rename" directive renames
       a file or directory if it is converted. To rename from a subdirectory into
       the root of the repository, use "." as the path to rename to.
   
       The splicemap is a file that allows insertion of synthetic history,
       letting you specify the parents of a revision. This is useful if you want
       to e.g. give a Subversion merge two parents, or graft two disconnected
       series of history together. Each entry contains a key, followed by a
       space, followed by one or two comma-separated values:
   
         key parent1, parent2
   
       The key is the revision ID in the source revision control system whose
       parents should be modified (same format as a key in .hg/shamap). The
       values are the revision IDs (in either the source or destination revision
       control system) that should be used as the new parents for that node. For
       example, if you have merged "release-1.0" into "trunk", then you should
       specify the revision on "trunk" as the first parent and the one on the
       "release-1.0" branch as the second.
   
       The branchmap is a file that allows you to rename a branch when it is
       being brought in from whatever external repository. When used in
       conjunction with a splicemap, it allows for a powerful combination to help
       fix even the most badly mismanaged repositories and turn them into nicely
       structured Mercurial repositories. The branchmap contains lines of the
       form:
   
         original_branch_name new_branch_name
   
       where "original_branch_name" is the name of the branch in the source
       repository, and "new_branch_name" is the name of the branch is the
       destination repository. No whitespace is allowed in the branch names. This
       can be used to (for instance) move code in one repository from "default"
       to a named branch.
   
       Mercurial Source
       ''''''''''''''''
   
       The Mercurial source recognizes the following configuration options, which
       you can set on the command line with "--config":
   
       convert.hg.ignoreerrors
                     ignore integrity errors when reading. Use it to fix
                     Mercurial repositories with missing revlogs, by converting
                     from and to Mercurial. Default is False.
       convert.hg.saverev
                     store original revision ID in changeset (forces target IDs
                     to change). It takes a boolean argument and defaults to
                     False.
       convert.hg.startrev
                     convert start revision and its descendants. It takes a hg
                     revision identifier and defaults to 0.
   
       CVS Source
       ''''''''''
   
       CVS source will use a sandbox (i.e. a checked-out copy) from CVS to
       indicate the starting point of what will be converted. Direct access to
       the repository files is not needed, unless of course the repository is
       ":local:". The conversion uses the top level directory in the sandbox to
       find the CVS repository, and then uses CVS rlog commands to find files to
       convert. This means that unless a filemap is given, all files under the
       starting directory will be converted, and that any directory
       reorganization in the CVS sandbox is ignored.
   
       The following options can be used with "--config":
   
       convert.cvsps.cache
                     Set to False to disable remote log caching, for testing and
                     debugging purposes. Default is True.
       convert.cvsps.fuzz
                     Specify the maximum time (in seconds) that is allowed
                     between commits with identical user and log message in a
                     single changeset. When very large files were checked in as
                     part of a changeset then the default may not be long enough.
                     The default is 60.
       convert.cvsps.mergeto
                     Specify a regular expression to which commit log messages
                     are matched. If a match occurs, then the conversion process
                     will insert a dummy revision merging the branch on which
                     this log message occurs to the branch indicated in the
                     regex. Default is "{{mergetobranch ([-\w]+)}}"
       convert.cvsps.mergefrom
                     Specify a regular expression to which commit log messages
                     are matched. If a match occurs, then the conversion process
                     will add the most recent revision on the branch indicated in
                     the regex as the second parent of the changeset. Default is
                     "{{mergefrombranch ([-\w]+)}}"
       hook.cvslog   Specify a Python function to be called at the end of
                     gathering the CVS log. The function is passed a list with
                     the log entries, and can modify the entries in-place, or add
                     or delete them.
       hook.cvschangesets
                     Specify a Python function to be called after the changesets
                     are calculated from the the CVS log. The function is passed
                     a list with the changeset entries, and can modify the
                     changesets in-place, or add or delete them.
   
       An additional "debugcvsps" Mercurial command allows the builtin changeset
       merging code to be run without doing a conversion. Its parameters and
       output are similar to that of cvsps 2.1. Please see the command help for
       more details.
   
       Subversion Source
       '''''''''''''''''
   
       Subversion source detects classical trunk/branches/tags layouts. By
       default, the supplied "svn://repo/path/" source URL is converted as a
       single branch. If "svn://repo/path/trunk" exists it replaces the default
       branch. If "svn://repo/path/branches" exists, its subdirectories are
       listed as possible branches. If "svn://repo/path/tags" exists, it is
       looked for tags referencing converted branches. Default "trunk",
       "branches" and "tags" values can be overridden with following options. Set
       them to paths relative to the source URL, or leave them blank to disable
       auto detection.
   
       The following options can be set with "--config":
   
       convert.svn.branches
                     specify the directory containing branches. The default is
                     "branches".
       convert.svn.tags
                     specify the directory containing tags. The default is
                     "tags".
       convert.svn.trunk
                     specify the name of the trunk branch. The default is
                     "trunk".
   
       Source history can be retrieved starting at a specific revision, instead
       of being integrally converted. Only single branch conversions are
       supported.
   
       convert.svn.startrev
                     specify start Subversion revision number. The default is 0.
   
       Perforce Source
       '''''''''''''''
   
       The Perforce (P4) importer can be given a p4 depot path or a client
       specification as source. It will convert all files in the source to a flat
       Mercurial repository, ignoring labels, branches and integrations. Note
       that when a depot path is given you then usually should specify a target
       directory, because otherwise the target may be named "...-hg".
   
       It is possible to limit the amount of source history to be converted by
       specifying an initial Perforce revision:
   
       convert.p4.startrev
                     specify initial Perforce revision (a Perforce changelist
                     number).
   
       Mercurial Destination
       '''''''''''''''''''''
   
       The following options are supported:
   
       convert.hg.clonebranches
                     dispatch source branches in separate clones. The default is
                     False.
       convert.hg.tagsbranch
                     branch name for tag revisions, defaults to "default".
       convert.hg.usebranchnames
                     preserve branch names. The default is True.
   
   options:
   
    -s --source-type TYPE source repository type
    -d --dest-type TYPE   destination repository type
    -r --rev REV          import up to target revision REV
    -A --authormap FILE   remap usernames using this file
       --filemap FILE     remap file names using contents of file
       --splicemap FILE   splice synthesized history into place
       --branchmap FILE   change branch names while converting
       --branchsort       try to sort changesets by branches
       --datesort         try to sort changesets by date
       --sourcesort       preserve source changesets order
   
   use "hg -v help convert" to show more info
   $ hg init a
   $ cd a
   $ echo a > a
   $ hg ci -d'0 0' -Ama
   adding a
   $ hg cp a b
   $ hg ci -d'1 0' -mb
   $ hg rm a
   $ hg ci -d'2 0' -mc
   $ hg mv b a
   $ hg ci -d'3 0' -md
   $ echo a >> a
   $ hg ci -d'4 0' -me
   $ cd ..
   $ hg convert a 2>&1 | grep -v 'subversion python bindings could not be loaded'
   assuming destination a-hg
   initializing destination a-hg repository
   scanning source...
   sorting...
   converting...
   4 a
   3 b
   2 c
   1 d
   0 e
   $ hg --cwd a-hg pull ../a
   pulling from ../a
   searching for changes
   no changes found
 
 conversion to existing file should fail
 
   $ touch bogusfile
   $ hg convert a bogusfile
   initializing destination bogusfile repository
   abort: cannot create new bundle repository
   [255]
 
 #if unix-permissions
 
 conversion to dir without permissions should fail
 
   $ mkdir bogusdir
   $ chmod 000 bogusdir
 
   $ hg convert a bogusdir
   abort: Permission denied: bogusdir
   [255]
 
 user permissions should succeed
 
   $ chmod 700 bogusdir
   $ hg convert a bogusdir
   initializing destination bogusdir repository
   scanning source...
   sorting...
   converting...
   4 a
   3 b
   2 c
   1 d
   0 e
 
 #endif
 
 test pre and post conversion actions
 
   $ echo 'include b' > filemap
   $ hg convert --debug --filemap filemap a partialb | \
   >     grep 'run hg'
   run hg source pre-conversion action
   run hg sink pre-conversion action
   run hg sink post-conversion action
   run hg source post-conversion action
 
 converting empty dir should fail "nicely
 
   $ mkdir emptydir
 
 override $PATH to ensure p4 not visible; use $PYTHON in case we're
 running from a devel copy, not a temp installation
 
   $ PATH="$BINDIR" $PYTHON "$BINDIR"/hg convert emptydir
   assuming destination emptydir-hg
   initializing destination emptydir-hg repository
   emptydir does not look like a CVS checkout
   emptydir does not look like a Git repository
   emptydir does not look like a Subversion repository
   emptydir is not a local Mercurial repository
   emptydir does not look like a darcs repository
   emptydir does not look like a monotone repository
   emptydir does not look like a GNU Arch repository
   emptydir does not look like a Bazaar repository
   cannot find required "p4" tool
   abort: emptydir: missing or unsupported repository
   [255]
 
 convert with imaginary source type
 
   $ hg convert --source-type foo a a-foo
   initializing destination a-foo repository
   abort: foo: invalid source repository type
   [255]
 
 convert with imaginary sink type
 
   $ hg convert --dest-type foo a a-foo
   abort: foo: invalid destination repository type
   [255]
 
 testing: convert must not produce duplicate entries in fncache
 
   $ hg convert a b
   initializing destination b repository
   scanning source...
   sorting...
   converting...
   4 a
   3 b
   2 c
   1 d
   0 e
 
 contents of fncache file:
 
   $ cat b/.hg/store/fncache | sort
   data/a.i
   data/b.i
 
 test bogus URL
 
   $ hg convert -q bzr+ssh://[e-mail]/baz baz
   abort: bzr+ssh://[e-mail]/baz: missing or unsupported repository
   [255]
+
+test revset converted() lookup
+
+  $ hg --config convert.hg.saverev=True convert a c  
+  initializing destination c repository
+  scanning source...
+  sorting...
+  converting...
+  4 a
+  3 b
+  2 c
+  1 d
+  0 e
+  $ echo f > c/f
+  $ hg -R c ci -d'0 0' -Amf
+  adding f
+  created new head
+  $ hg -R c log -r "converted(09d945a62ce6)"
+  changeset:   1:98c3dd46a874
+  user:        test
+  date:        Thu Jan 01 00:00:01 1970 +0000
+  summary:     b
+  
+  $ hg -R c log -r "converted()"
+  changeset:   0:31ed57b2037c
+  user:        test
+  date:        Thu Jan 01 00:00:00 1970 +0000
+  summary:     a
+  
+  changeset:   1:98c3dd46a874
+  user:        test
+  date:        Thu Jan 01 00:00:01 1970 +0000
+  summary:     b
+  
+  changeset:   2:3b9ca06ef716
+  user:        test
+  date:        Thu Jan 01 00:00:02 1970 +0000
+  summary:     c
+  
+  changeset:   3:4e0debd37cf2
+  user:        test
+  date:        Thu Jan 01 00:00:03 1970 +0000
+  summary:     d
+  
+  changeset:   4:9de3bc9349c5
+  user:        test
+  date:        Thu Jan 01 00:00:04 1970 +0000
+  summary:     e
+