bundle: get rid of chunkiter

contrib/shrink-revlog.py

@@ -1,288 +1,288 b''
 #!/usr/bin/env python
 
 """\
 reorder a revlog (the manifest by default) to save space
 
 Specifically, this topologically sorts the revisions in the revlog so that
 revisions on the same branch are adjacent as much as possible. This is a
 workaround for the fact that Mercurial computes deltas relative to the
 previous revision rather than relative to a parent revision.
 
 This is *not* safe to run on a changelog.
 """
 
 # Originally written by Benoit Boissinot <benoit.boissinot at ens-lyon.org>
 # as a patch to rewrite-log. Cleaned up, refactored, documented, and
 # renamed by Greg Ward <greg at gerg.ca>.
 
 # XXX would be nice to have a way to verify the repository after shrinking,
 # e.g. by comparing "before" and "after" states of random changesets
 # (maybe: export before, shrink, export after, diff).
 
 import os, tempfile, errno
 from mercurial import revlog, transaction, node, util
 from mercurial import changegroup
 from mercurial.i18n import _
 
 
 def postorder(start, edges):
     result = []
     visit = list(start)
     finished = set()
 
     while visit:
         cur = visit[-1]
         for p in edges[cur]:
             if p not in finished:
                 visit.append(p)
                 break
         else:
             result.append(cur)
             finished.add(cur)
             visit.pop()
 
     return result
 
 def toposort_reversepostorder(ui, rl):
     # postorder of the reverse directed graph
 
     # map rev to list of parent revs (p2 first)
     parents = {}
     heads = set()
     ui.status(_('reading revs\n'))
     try:
         for rev in rl:
             ui.progress(_('reading'), rev, total=len(rl))
             (p1, p2) = rl.parentrevs(rev)
             if p1 == p2 == node.nullrev:
                 parents[rev] = ()       # root node
             elif p1 == p2 or p2 == node.nullrev:
                 parents[rev] = (p1,)    # normal node
             else:
                 parents[rev] = (p2, p1) # merge node
             heads.add(rev)
             for p in parents[rev]:
                 heads.discard(p)
     finally:
         ui.progress(_('reading'), None)
 
     heads = list(heads)
     heads.sort(reverse=True)
 
     ui.status(_('sorting revs\n'))
     return postorder(heads, parents)
 
 def toposort_postorderreverse(ui, rl):
     # reverse-postorder of the reverse directed graph
 
     children = {}
     roots = set()
     ui.status(_('reading revs\n'))
     try:
         for rev in rl:
             ui.progress(_('reading'), rev, total=len(rl))
             (p1, p2) = rl.parentrevs(rev)
             if p1 == p2 == node.nullrev:
                 roots.add(rev)
             children[rev] = []
             if p1 != node.nullrev:
                 children[p1].append(rev)
             if p2 != node.nullrev:
                 children[p2].append(rev)
     finally:
         ui.progress(_('reading'), None)
 
     roots = list(roots)
     roots.sort()
 
     ui.status(_('sorting revs\n'))
     result = postorder(roots, children)
     result.reverse()
     return result
 
 def writerevs(ui, r1, r2, order, tr):
 
     ui.status(_('writing revs\n'))
 
     count = [0]
     def progress(*args):
         ui.progress(_('writing'), count[0], total=len(order))
         count[0] += 1
 
     order = [r1.node(r) for r in order]
 
     # this is a bit ugly, but it works
     lookup = lambda x: "%020d" % r1.linkrev(r1.rev(x))
     unlookup = lambda x: int(x, 10)
 
     try:
         group = util.chunkbuffer(r1.group(order, lookup, progress))
-        r2.addgroup(group.chunks(), unlookup, tr)
+        r2.addgroup(group, unlookup, tr)
     finally:
         ui.progress(_('writing'), None)
 
 def report(ui, r1, r2):
     def getsize(r):
         s = 0
         for fn in (r.indexfile, r.datafile):
             try:
                 s += os.stat(fn).st_size
             except OSError, inst:
                 if inst.errno != errno.ENOENT:
                     raise
         return s
 
     oldsize = float(getsize(r1))
     newsize = float(getsize(r2))
 
     # argh: have to pass an int to %d, because a float >= 2^32
     # blows up under Python 2.5 or earlier
     ui.write(_('old file size: %12d bytes (%6.1f MiB)\n')
              % (int(oldsize), oldsize / 1024 / 1024))
     ui.write(_('new file size: %12d bytes (%6.1f MiB)\n')
              % (int(newsize), newsize / 1024 / 1024))
 
     shrink_percent = (oldsize - newsize) / oldsize * 100
     shrink_factor = oldsize / newsize
     ui.write(_('shrinkage: %.1f%% (%.1fx)\n')
              % (shrink_percent, shrink_factor))
 
 def shrink(ui, repo, **opts):
     """shrink a revlog by reordering revisions
 
     Rewrites all the entries in some revlog of the current repository
     (by default, the manifest log) to save space.
 
     Different sort algorithms have different performance
     characteristics.  Use ``--sort`` to select a sort algorithm so you
     can determine which works best for your data.
     """
 
     if not repo.local():
         raise util.Abort(_('not a local repository: %s') % repo.root)
 
     fn = opts.get('revlog')
     if not fn:
         indexfn = repo.sjoin('00manifest.i')
     else:
         if not fn.endswith('.i'):
             raise util.Abort(_('--revlog option must specify the revlog index '
                                'file (*.i), not %s') % opts.get('revlog'))
 
         indexfn = os.path.realpath(fn)
         store = repo.sjoin('')
         if not indexfn.startswith(store):
             raise util.Abort(_('--revlog option must specify a revlog in %s, '
                                'not %s') % (store, indexfn))
 
     sortname = opts['sort']
     try:
         toposort = globals()['toposort_' + sortname]
     except KeyError:
         raise util.Abort(_('no such toposort algorithm: %s') % sortname)
 
     if not os.path.exists(indexfn):
         raise util.Abort(_('no such file: %s') % indexfn)
     if '00changelog' in indexfn:
         raise util.Abort(_('shrinking the changelog '
                            'will corrupt your repository'))
 
     ui.write(_('shrinking %s\n') % indexfn)
     prefix = os.path.basename(indexfn)[:-1]
     tmpindexfn = util.mktempcopy(indexfn, emptyok=True)
 
     r1 = revlog.revlog(util.opener(os.getcwd(), audit=False), indexfn)
     r2 = revlog.revlog(util.opener(os.getcwd(), audit=False), tmpindexfn)
 
     datafn, tmpdatafn = r1.datafile, r2.datafile
 
     oldindexfn = indexfn + '.old'
     olddatafn = datafn + '.old'
     if os.path.exists(oldindexfn) or os.path.exists(olddatafn):
         raise util.Abort(_('one or both of\n'
                            '  %s\n'
                            '  %s\n'
                            'exists from a previous run; please clean up '
                            'before running again') % (oldindexfn, olddatafn))
 
     # Don't use repo.transaction(), because then things get hairy with
     # paths: some need to be relative to .hg, and some need to be
     # absolute. Doing it this way keeps things simple: everything is an
     # absolute path.
     lock = repo.lock(wait=False)
     tr = transaction.transaction(ui.warn,
                                  open,
                                  repo.sjoin('journal'))
 
     def ignoremissing(func):
         def f(*args, **kw):
             try:
                 return func(*args, **kw)
             except OSError, inst:
                 if inst.errno != errno.ENOENT:
                     raise
         return f
 
     try:
         try:
             order = toposort(ui, r1)
 
             suboptimal = 0
             for i in xrange(1, len(order)):
                 parents = [p for p in r1.parentrevs(order[i])
                            if p != node.nullrev]
                 if parents and order[i - 1] not in parents:
                     suboptimal += 1
             ui.note(_('%d suboptimal nodes\n') % suboptimal)
 
             writerevs(ui, r1, r2, order, tr)
             report(ui, r1, r2)
             tr.close()
         except:
             # Abort transaction first, so we truncate the files before
             # deleting them.
             tr.abort()
             for fn in (tmpindexfn, tmpdatafn):
                 ignoremissing(os.unlink)(fn)
             raise
         if not opts.get('dry_run'):
             # racy, both files cannot be renamed atomically
             # copy files
             util.os_link(indexfn, oldindexfn)
             ignoremissing(util.os_link)(datafn, olddatafn)
 
             # rename
             util.rename(tmpindexfn, indexfn)
             try:
                 os.chmod(tmpdatafn, os.stat(datafn).st_mode)
                 util.rename(tmpdatafn, datafn)
             except OSError, inst:
                 if inst.errno != errno.ENOENT:
                     raise
                 ignoremissing(os.unlink)(datafn)
         else:
             for fn in (tmpindexfn, tmpdatafn):
                 ignoremissing(os.unlink)(fn)
     finally:
         lock.release()
 
     if not opts.get('dry_run'):
         ui.write(_('note: old revlog saved in:\n'
                    '  %s\n'
                    '  %s\n'
                    '(You can delete those files when you are satisfied that your\n'
                    'repository is still sane.  '
                    'Running \'hg verify\' is strongly recommended.)\n')
                  % (oldindexfn, olddatafn))
 
 cmdtable = {
     'shrink': (shrink,
                [('', 'revlog', '', _('index (.i) file of the revlog to shrink')),
                 ('n', 'dry-run', None, _('do not shrink, simulate only')),
                 ('', 'sort', 'reversepostorder', 'name of sort algorithm to use'),
                 ],
                _('hg shrink [--revlog PATH]'))
 }
 
 if __name__ == "__main__":
     print "shrink-revlog.py is now an extension (see hg help extensions)"

mercurial/bundlerepo.py

@@ -1,282 +1,287 b''
 # bundlerepo.py - repository class for viewing uncompressed bundles
 #
 # Copyright 2006, 2007 Benoit Boissinot <[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.
 
 """Repository class for viewing uncompressed bundles.
 
 This provides a read-only repository interface to bundles as if they
 were part of the actual repository.
 """
 
 from node import nullid
 from i18n import _
 import os, struct, tempfile, shutil
 import changegroup, util, mdiff
 import localrepo, changelog, manifest, filelog, revlog, error
 
 class bundlerevlog(revlog.revlog):
     def __init__(self, opener, indexfile, bundle,
                  linkmapper=None):
         # How it works:
         # to retrieve a revision, we need to know the offset of
         # the revision in the bundle (an unbundle object).
         #
         # We store this offset in the index (start), to differentiate a
         # rev in the bundle and from a rev in the revlog, we check
         # len(index[r]). If the tuple is bigger than 7, it is a bundle
         # (it is bigger since we store the node to which the delta is)
         #
         revlog.revlog.__init__(self, opener, indexfile)
         self.bundle = bundle
         self.basemap = {}
         def chunkpositer():
-            for chunk in bundle.chunks():
+            while 1:
+                chunk = bundle.chunk()
+                if not chunk:
+                    break
                 pos = bundle.tell()
                 yield chunk, pos - len(chunk)
         n = len(self)
         prev = None
         for chunk, start in chunkpositer():
             size = len(chunk)
             if size < 80:
                 raise util.Abort(_("invalid changegroup"))
             start += 80
             size -= 80
             node, p1, p2, cs = struct.unpack("20s20s20s20s", chunk[:80])
             if node in self.nodemap:
                 prev = node
                 continue
             for p in (p1, p2):
                 if not p in self.nodemap:
                     raise error.LookupError(p, self.indexfile,
                                             _("unknown parent"))
             if linkmapper is None:
                 link = n
             else:
                 link = linkmapper(cs)
 
             if not prev:
                 prev = p1
             # start, size, full unc. size, base (unused), link, p1, p2, node
             e = (revlog.offset_type(start, 0), size, -1, -1, link,
                  self.rev(p1), self.rev(p2), node)
             self.basemap[n] = prev
             self.index.insert(-1, e)
             self.nodemap[node] = n
             prev = node
             n += 1
 
     def inbundle(self, rev):
         """is rev from the bundle"""
         if rev < 0:
             return False
         return rev in self.basemap
     def bundlebase(self, rev):
         return self.basemap[rev]
     def _chunk(self, rev):
         # Warning: in case of bundle, the diff is against bundlebase,
         # not against rev - 1
         # XXX: could use some caching
         if not self.inbundle(rev):
             return revlog.revlog._chunk(self, rev)
         self.bundle.seek(self.start(rev))
         return self.bundle.read(self.length(rev))
 
     def revdiff(self, rev1, rev2):
         """return or calculate a delta between two revisions"""
         if self.inbundle(rev1) and self.inbundle(rev2):
             # hot path for bundle
             revb = self.rev(self.bundlebase(rev2))
             if revb == rev1:
                 return self._chunk(rev2)
         elif not self.inbundle(rev1) and not self.inbundle(rev2):
             return revlog.revlog.revdiff(self, rev1, rev2)
 
         return mdiff.textdiff(self.revision(self.node(rev1)),
                          self.revision(self.node(rev2)))
 
     def revision(self, node):
         """return an uncompressed revision of a given"""
         if node == nullid:
             return ""
 
         text = None
         chain = []
         iter_node = node
         rev = self.rev(iter_node)
         # reconstruct the revision if it is from a changegroup
         while self.inbundle(rev):
             if self._cache and self._cache[0] == iter_node:
                 text = self._cache[2]
                 break
             chain.append(rev)
             iter_node = self.bundlebase(rev)
             rev = self.rev(iter_node)
         if text is None:
             text = revlog.revlog.revision(self, iter_node)
 
         while chain:
             delta = self._chunk(chain.pop())
             text = mdiff.patches(text, [delta])
 
         p1, p2 = self.parents(node)
         if node != revlog.hash(text, p1, p2):
             raise error.RevlogError(_("integrity check failed on %s:%d")
                                      % (self.datafile, self.rev(node)))
 
         self._cache = (node, self.rev(node), text)
         return text
 
     def addrevision(self, text, transaction, link, p1=None, p2=None, d=None):
         raise NotImplementedError
     def addgroup(self, revs, linkmapper, transaction):
         raise NotImplementedError
     def strip(self, rev, minlink):
         raise NotImplementedError
     def checksize(self):
         raise NotImplementedError
 
 class bundlechangelog(bundlerevlog, changelog.changelog):
     def __init__(self, opener, bundle):
         changelog.changelog.__init__(self, opener)
         bundlerevlog.__init__(self, opener, self.indexfile, bundle)
 
 class bundlemanifest(bundlerevlog, manifest.manifest):
     def __init__(self, opener, bundle, linkmapper):
         manifest.manifest.__init__(self, opener)
         bundlerevlog.__init__(self, opener, self.indexfile, bundle,
                               linkmapper)
 
 class bundlefilelog(bundlerevlog, filelog.filelog):
     def __init__(self, opener, path, bundle, linkmapper):
         filelog.filelog.__init__(self, opener, path)
         bundlerevlog.__init__(self, opener, self.indexfile, bundle,
                               linkmapper)
 
 class bundlerepository(localrepo.localrepository):
     def __init__(self, ui, path, bundlename):
         self._tempparent = None
         try:
             localrepo.localrepository.__init__(self, ui, path)
         except error.RepoError:
             self._tempparent = tempfile.mkdtemp()
             localrepo.instance(ui, self._tempparent, 1)
             localrepo.localrepository.__init__(self, ui, self._tempparent)
 
         if path:
             self._url = 'bundle:' + util.expandpath(path) + '+' + bundlename
         else:
             self._url = 'bundle:' + bundlename
 
         self.tempfile = None
         f = open(bundlename, "rb")
         self.bundle = changegroup.readbundle(f, bundlename)
         if self.bundle.compressed():
             # we need a seekable, decompressed bundle
             fdtemp, temp = tempfile.mkstemp(prefix="hg-bundle-",
                                             suffix=".hg10un", dir=self.path)
             self.tempfile = temp
             fptemp = os.fdopen(fdtemp, 'wb')
 
             try:
                 fptemp.write("HG10UN")
                 while 1:
                     chunk = self.bundle.read(2**18)
                     if not chunk:
                         break
                     fptemp.write(chunk)
             finally:
                 fptemp.close()
 
             f = open(self.tempfile, "rb")
             self.bundle = changegroup.readbundle(f, bundlename)
 
         # dict with the mapping 'filename' -> position in the bundle
         self.bundlefilespos = {}
 
     @util.propertycache
     def changelog(self):
         c = bundlechangelog(self.sopener, self.bundle)
         self.manstart = self.bundle.tell()
         return c
 
     @util.propertycache
     def manifest(self):
         self.bundle.seek(self.manstart)
         m = bundlemanifest(self.sopener, self.bundle, self.changelog.rev)
         self.filestart = self.bundle.tell()
         return m
 
     @util.propertycache
     def manstart(self):
         self.changelog
         return self.manstart
 
     @util.propertycache
     def filestart(self):
         self.manifest
         return self.filestart
 
     def url(self):
         return self._url
 
     def file(self, f):
         if not self.bundlefilespos:
             self.bundle.seek(self.filestart)
             while 1:
                 chunk = self.bundle.chunk()
                 if not chunk:
                     break
                 self.bundlefilespos[chunk] = self.bundle.tell()
-                for c in self.bundle.chunks():
-                    pass
+                while 1:
+                    c = self.bundle.chunk()
+                    if not c:
+                        break
 
         if f[0] == '/':
             f = f[1:]
         if f in self.bundlefilespos:
             self.bundle.seek(self.bundlefilespos[f])
             return bundlefilelog(self.sopener, f, self.bundle,
                                  self.changelog.rev)
         else:
             return filelog.filelog(self.sopener, f)
 
     def __del__(self):
         del self.bundle
         if tempfile is not None:
             os.unlink(tempfile)
         if self._tempparent:
             shutil.rmtree(self._tempparent, True)
 
     def cancopy(self):
         return False
 
     def getcwd(self):
         return os.getcwd() # always outside the repo
 
 def instance(ui, path, create):
     if create:
         raise util.Abort(_('cannot create new bundle repository'))
     parentpath = ui.config("bundle", "mainreporoot", "")
     if parentpath:
         # Try to make the full path relative so we get a nice, short URL.
         # In particular, we don't want temp dir names in test outputs.
         cwd = os.getcwd()
         if parentpath == cwd:
             parentpath = ''
         else:
             cwd = os.path.join(cwd,'')
             if parentpath.startswith(cwd):
                 parentpath = parentpath[len(cwd):]
     path = util.drop_scheme('file', path)
     if path.startswith('bundle:'):
         path = util.drop_scheme('bundle', path)
         s = path.split("+", 1)
         if len(s) == 1:
             repopath, bundlename = parentpath, s[0]
         else:
             repopath, bundlename = s
     else:
         repopath, bundlename = parentpath, path
     return bundlerepository(ui, repopath, bundlename)

mercurial/changegroup.py

@@ -1,208 +1,193 b''
 # changegroup.py - Mercurial changegroup manipulation functions
 #
 #  Copyright 2006 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from i18n import _
 import util
 import struct, os, bz2, zlib, tempfile
 
 def getchunk(source):
     """return the next chunk from changegroup 'source' as a string"""
     d = source.read(4)
     if not d:
         return ""
     l = struct.unpack(">l", d)[0]
     if l <= 4:
         return ""
     d = source.read(l - 4)
     if len(d) < l - 4:
         raise util.Abort(_("premature EOF reading chunk"
                            " (got %d bytes, expected %d)")
                           % (len(d), l - 4))
     return d
 
-def chunkiter(source, progress=None):
-    """iterate through the chunks in source, yielding a sequence of chunks
-    (strings)"""
-    while 1:
-        c = getchunk(source)
-        if not c:
-            break
-        elif progress is not None:
-            progress()
-        yield c
-
 def chunkheader(length):
     """return a changegroup chunk header (string)"""
     return struct.pack(">l", length + 4)
 
 def closechunk():
     """return a changegroup chunk header (string) for a zero-length chunk"""
     return struct.pack(">l", 0)
 
 class nocompress(object):
     def compress(self, x):
         return x
     def flush(self):
         return ""
 
 bundletypes = {
     "": ("", nocompress),
     "HG10UN": ("HG10UN", nocompress),
     "HG10BZ": ("HG10", lambda: bz2.BZ2Compressor()),
     "HG10GZ": ("HG10GZ", lambda: zlib.compressobj()),
 }
 
 def collector(cl, mmfs, files):
     # Gather information about changeset nodes going out in a bundle.
     # We want to gather manifests needed and filelogs affected.
     def collect(node):
         c = cl.read(node)
         files.update(c[3])
         mmfs.setdefault(c[0], node)
     return collect
 
 # hgweb uses this list to communicate its preferred type
 bundlepriority = ['HG10GZ', 'HG10BZ', 'HG10UN']
 
 def writebundle(cg, filename, bundletype):
     """Write a bundle file and return its filename.
 
     Existing files will not be overwritten.
     If no filename is specified, a temporary file is created.
     bz2 compression can be turned off.
     The bundle file will be deleted in case of errors.
     """
 
     fh = None
     cleanup = None
     try:
         if filename:
             fh = open(filename, "wb")
         else:
             fd, filename = tempfile.mkstemp(prefix="hg-bundle-", suffix=".hg")
             fh = os.fdopen(fd, "wb")
         cleanup = filename
 
         header, compressor = bundletypes[bundletype]
         fh.write(header)
         z = compressor()
 
         # parse the changegroup data, otherwise we will block
         # in case of sshrepo because we don't know the end of the stream
 
-        # an empty chunkiter is the end of the changegroup
-        # a changegroup has at least 2 chunkiters (changelog and manifest).
-        # after that, an empty chunkiter is the end of the changegroup
+        # an empty chunkgroup is the end of the changegroup
+        # a changegroup has at least 2 chunkgroups (changelog and manifest).
+        # after that, an empty chunkgroup is the end of the changegroup
         empty = False
         count = 0
         while not empty or count <= 2:
             empty = True
             count += 1
-            for chunk in chunkiter(cg):
+            while 1:
+                chunk = getchunk(cg)
+                if not chunk:
+                    break
                 empty = False
                 fh.write(z.compress(chunkheader(len(chunk))))
                 pos = 0
                 while pos < len(chunk):
                     next = pos + 2**20
                     fh.write(z.compress(chunk[pos:next]))
                     pos = next
             fh.write(z.compress(closechunk()))
         fh.write(z.flush())
         cleanup = None
         return filename
     finally:
         if fh is not None:
             fh.close()
         if cleanup is not None:
             os.unlink(cleanup)
 
 def decompressor(fh, alg):
     if alg == 'UN':
         return fh
     elif alg == 'GZ':
         def generator(f):
             zd = zlib.decompressobj()
             for chunk in f:
                 yield zd.decompress(chunk)
     elif alg == 'BZ':
         def generator(f):
             zd = bz2.BZ2Decompressor()
             zd.decompress("BZ")
             for chunk in util.filechunkiter(f, 4096):
                 yield zd.decompress(chunk)
     else:
         raise util.Abort("unknown bundle compression '%s'" % alg)
     return util.chunkbuffer(generator(fh))
 
 class unbundle10(object):
     def __init__(self, fh, alg):
         self._stream = decompressor(fh, alg)
         self._type = alg
         self.callback = None
     def compressed(self):
         return self._type != 'UN'
     def read(self, l):
         return self._stream.read(l)
     def seek(self, pos):
         return self._stream.seek(pos)
     def tell(self):
         return self._stream.tell()
 
     def chunklength(self):
         d = self.read(4)
         if not d:
             return 0
         l = max(0, struct.unpack(">l", d)[0] - 4)
         if l and self.callback:
             self.callback()
         return l
 
     def chunk(self):
         """return the next chunk from changegroup 'source' as a string"""
         l = self.chunklength()
         d = self.read(l)
         if len(d) < l:
             raise util.Abort(_("premature EOF reading chunk"
                                " (got %d bytes, expected %d)")
                              % (len(d), l))
         return d
 
-    def chunks(self):
-        while 1:
-            c = self.chunk()
-            if not c:
-                break
-            yield c
-
 class headerlessfixup(object):
     def __init__(self, fh, h):
         self._h = h
         self._fh = fh
     def read(self, n):
         if self._h:
             d, self._h = self._h[:n], self._h[n:]
             if len(d) < n:
                 d += self._fh.read(n - len(d))
             return d
         return self._fh.read(n)
 
 def readbundle(fh, fname):
     header = fh.read(6)
 
     if not fname:
         fname = "stream"
         if not header.startswith('HG') and header.startswith('\0'):
             fh = headerlessfixup(fh, header)
             header = "HG10UN"
 
     magic, version, alg = header[0:2], header[2:4], header[4:6]
 
     if magic != 'HG':
         raise util.Abort(_('%s: not a Mercurial bundle') % fname)
     if version != '10':
         raise util.Abort(_('%s: unknown bundle version %s') % (fname, version))
     return unbundle10(fh, alg)

mercurial/localrepo.py

@@ -1,1893 +1,1893 b''
 # localrepo.py - read/write repository class for mercurial
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from node import bin, hex, nullid, nullrev, short
 from i18n import _
 import repo, changegroup, subrepo, discovery, pushkey
 import changelog, dirstate, filelog, manifest, context
 import lock, transaction, store, encoding
 import util, extensions, hook, error
 import match as matchmod
 import merge as mergemod
 import tags as tagsmod
 import url as urlmod
 from lock import release
 import weakref, errno, os, time, inspect
 propertycache = util.propertycache
 
 class localrepository(repo.repository):
     capabilities = set(('lookup', 'changegroupsubset', 'branchmap', 'pushkey'))
     supportedformats = set(('revlogv1', 'parentdelta'))
     supported = supportedformats | set(('store', 'fncache', 'shared'))
 
     def __init__(self, baseui, path=None, create=0):
         repo.repository.__init__(self)
         self.root = os.path.realpath(util.expandpath(path))
         self.path = os.path.join(self.root, ".hg")
         self.origroot = path
         self.auditor = util.path_auditor(self.root, self._checknested)
         self.opener = util.opener(self.path)
         self.wopener = util.opener(self.root)
         self.baseui = baseui
         self.ui = baseui.copy()
 
         try:
             self.ui.readconfig(self.join("hgrc"), self.root)
             extensions.loadall(self.ui)
         except IOError:
             pass
 
         if not os.path.isdir(self.path):
             if create:
                 if not os.path.exists(path):
                     util.makedirs(path)
                 os.mkdir(self.path)
                 requirements = ["revlogv1"]
                 if self.ui.configbool('format', 'usestore', True):
                     os.mkdir(os.path.join(self.path, "store"))
                     requirements.append("store")
                     if self.ui.configbool('format', 'usefncache', True):
                         requirements.append("fncache")
                     # create an invalid changelog
                     self.opener("00changelog.i", "a").write(
                         '\0\0\0\2' # represents revlogv2
                         ' dummy changelog to prevent using the old repo layout'
                     )
                 if self.ui.configbool('format', 'parentdelta', False):
                     requirements.append("parentdelta")
             else:
                 raise error.RepoError(_("repository %s not found") % path)
         elif create:
             raise error.RepoError(_("repository %s already exists") % path)
         else:
             # find requirements
             requirements = set()
             try:
                 requirements = set(self.opener("requires").read().splitlines())
             except IOError, inst:
                 if inst.errno != errno.ENOENT:
                     raise
             for r in requirements - self.supported:
                 raise error.RepoError(_("requirement '%s' not supported") % r)
 
         self.sharedpath = self.path
         try:
             s = os.path.realpath(self.opener("sharedpath").read())
             if not os.path.exists(s):
                 raise error.RepoError(
                     _('.hg/sharedpath points to nonexistent directory %s') % s)
             self.sharedpath = s
         except IOError, inst:
             if inst.errno != errno.ENOENT:
                 raise
 
         self.store = store.store(requirements, self.sharedpath, util.opener)
         self.spath = self.store.path
         self.sopener = self.store.opener
         self.sjoin = self.store.join
         self.opener.createmode = self.store.createmode
         self._applyrequirements(requirements)
         if create:
             self._writerequirements()
 
         # These two define the set of tags for this repository.  _tags
         # maps tag name to node; _tagtypes maps tag name to 'global' or
         # 'local'.  (Global tags are defined by .hgtags across all
         # heads, and local tags are defined in .hg/localtags.)  They
         # constitute the in-memory cache of tags.
         self._tags = None
         self._tagtypes = None
 
         self._branchcache = None  # in UTF-8
         self._branchcachetip = None
         self.nodetagscache = None
         self.filterpats = {}
         self._datafilters = {}
         self._transref = self._lockref = self._wlockref = None
 
     def _applyrequirements(self, requirements):
         self.requirements = requirements
         self.sopener.options = {}
         if 'parentdelta' in requirements:
             self.sopener.options['parentdelta'] = 1
 
     def _writerequirements(self):
         reqfile = self.opener("requires", "w")
         for r in self.requirements:
             reqfile.write("%s\n" % r)
         reqfile.close()
 
     def _checknested(self, path):
         """Determine if path is a legal nested repository."""
         if not path.startswith(self.root):
             return False
         subpath = path[len(self.root) + 1:]
 
         # XXX: Checking against the current working copy is wrong in
         # the sense that it can reject things like
         #
         #   $ hg cat -r 10 sub/x.txt
         #
         # if sub/ is no longer a subrepository in the working copy
         # parent revision.
         #
         # However, it can of course also allow things that would have
         # been rejected before, such as the above cat command if sub/
         # is a subrepository now, but was a normal directory before.
         # The old path auditor would have rejected by mistake since it
         # panics when it sees sub/.hg/.
         #
         # All in all, checking against the working copy seems sensible
         # since we want to prevent access to nested repositories on
         # the filesystem *now*.
         ctx = self[None]
         parts = util.splitpath(subpath)
         while parts:
             prefix = os.sep.join(parts)
             if prefix in ctx.substate:
                 if prefix == subpath:
                     return True
                 else:
                     sub = ctx.sub(prefix)
                     return sub.checknested(subpath[len(prefix) + 1:])
             else:
                 parts.pop()
         return False
 
 
     @propertycache
     def changelog(self):
         c = changelog.changelog(self.sopener)
         if 'HG_PENDING' in os.environ:
             p = os.environ['HG_PENDING']
             if p.startswith(self.root):
                 c.readpending('00changelog.i.a')
         self.sopener.options['defversion'] = c.version
         return c
 
     @propertycache
     def manifest(self):
         return manifest.manifest(self.sopener)
 
     @propertycache
     def dirstate(self):
         return dirstate.dirstate(self.opener, self.ui, self.root)
 
     def __getitem__(self, changeid):
         if changeid is None:
             return context.workingctx(self)
         return context.changectx(self, changeid)
 
     def __contains__(self, changeid):
         try:
             return bool(self.lookup(changeid))
         except error.RepoLookupError:
             return False
 
     def __nonzero__(self):
         return True
 
     def __len__(self):
         return len(self.changelog)
 
     def __iter__(self):
         for i in xrange(len(self)):
             yield i
 
     def url(self):
         return 'file:' + self.root
 
     def hook(self, name, throw=False, **args):
         return hook.hook(self.ui, self, name, throw, **args)
 
     tag_disallowed = ':\r\n'
 
     def _tag(self, names, node, message, local, user, date, extra={}):
         if isinstance(names, str):
             allchars = names
             names = (names,)
         else:
             allchars = ''.join(names)
         for c in self.tag_disallowed:
             if c in allchars:
                 raise util.Abort(_('%r cannot be used in a tag name') % c)
 
         branches = self.branchmap()
         for name in names:
             self.hook('pretag', throw=True, node=hex(node), tag=name,
                       local=local)
             if name in branches:
                 self.ui.warn(_("warning: tag %s conflicts with existing"
                 " branch name\n") % name)
 
         def writetags(fp, names, munge, prevtags):
             fp.seek(0, 2)
             if prevtags and prevtags[-1] != '\n':
                 fp.write('\n')
             for name in names:
                 m = munge and munge(name) or name
                 if self._tagtypes and name in self._tagtypes:
                     old = self._tags.get(name, nullid)
                     fp.write('%s %s\n' % (hex(old), m))
                 fp.write('%s %s\n' % (hex(node), m))
             fp.close()
 
         prevtags = ''
         if local:
             try:
                 fp = self.opener('localtags', 'r+')
             except IOError:
                 fp = self.opener('localtags', 'a')
             else:
                 prevtags = fp.read()
 
             # local tags are stored in the current charset
             writetags(fp, names, None, prevtags)
             for name in names:
                 self.hook('tag', node=hex(node), tag=name, local=local)
             return
 
         try:
             fp = self.wfile('.hgtags', 'rb+')
         except IOError:
             fp = self.wfile('.hgtags', 'ab')
         else:
             prevtags = fp.read()
 
         # committed tags are stored in UTF-8
         writetags(fp, names, encoding.fromlocal, prevtags)
 
         if '.hgtags' not in self.dirstate:
             self[None].add(['.hgtags'])
 
         m = matchmod.exact(self.root, '', ['.hgtags'])
         tagnode = self.commit(message, user, date, extra=extra, match=m)
 
         for name in names:
             self.hook('tag', node=hex(node), tag=name, local=local)
 
         return tagnode
 
     def tag(self, names, node, message, local, user, date):
         '''tag a revision with one or more symbolic names.
 
         names is a list of strings or, when adding a single tag, names may be a
         string.
 
         if local is True, the tags are stored in a per-repository file.
         otherwise, they are stored in the .hgtags file, and a new
         changeset is committed with the change.
 
         keyword arguments:
 
         local: whether to store tags in non-version-controlled file
         (default False)
 
         message: commit message to use if committing
 
         user: name of user to use if committing
 
         date: date tuple to use if committing'''
 
         for x in self.status()[:5]:
             if '.hgtags' in x:
                 raise util.Abort(_('working copy of .hgtags is changed '
                                    '(please commit .hgtags manually)'))
 
         self.tags() # instantiate the cache
         self._tag(names, node, message, local, user, date)
 
     def tags(self):
         '''return a mapping of tag to node'''
         if self._tags is None:
             (self._tags, self._tagtypes) = self._findtags()
 
         return self._tags
 
     def _findtags(self):
         '''Do the hard work of finding tags.  Return a pair of dicts
         (tags, tagtypes) where tags maps tag name to node, and tagtypes
         maps tag name to a string like \'global\' or \'local\'.
         Subclasses or extensions are free to add their own tags, but
         should be aware that the returned dicts will be retained for the
         duration of the localrepo object.'''
 
         # XXX what tagtype should subclasses/extensions use?  Currently
         # mq and bookmarks add tags, but do not set the tagtype at all.
         # Should each extension invent its own tag type?  Should there
         # be one tagtype for all such "virtual" tags?  Or is the status
         # quo fine?
 
         alltags = {}                    # map tag name to (node, hist)
         tagtypes = {}
 
         tagsmod.findglobaltags(self.ui, self, alltags, tagtypes)
         tagsmod.readlocaltags(self.ui, self, alltags, tagtypes)
 
         # Build the return dicts.  Have to re-encode tag names because
         # the tags module always uses UTF-8 (in order not to lose info
         # writing to the cache), but the rest of Mercurial wants them in
         # local encoding.
         tags = {}
         for (name, (node, hist)) in alltags.iteritems():
             if node != nullid:
                 tags[encoding.tolocal(name)] = node
         tags['tip'] = self.changelog.tip()
         tagtypes = dict([(encoding.tolocal(name), value)
                          for (name, value) in tagtypes.iteritems()])
         return (tags, tagtypes)
 
     def tagtype(self, tagname):
         '''
         return the type of the given tag. result can be:
 
         'local'  : a local tag
         'global' : a global tag
         None     : tag does not exist
         '''
 
         self.tags()
 
         return self._tagtypes.get(tagname)
 
     def tagslist(self):
         '''return a list of tags ordered by revision'''
         l = []
         for t, n in self.tags().iteritems():
             try:
                 r = self.changelog.rev(n)
             except:
                 r = -2 # sort to the beginning of the list if unknown
             l.append((r, t, n))
         return [(t, n) for r, t, n in sorted(l)]
 
     def nodetags(self, node):
         '''return the tags associated with a node'''
         if not self.nodetagscache:
             self.nodetagscache = {}
             for t, n in self.tags().iteritems():
                 self.nodetagscache.setdefault(n, []).append(t)
             for tags in self.nodetagscache.itervalues():
                 tags.sort()
         return self.nodetagscache.get(node, [])
 
     def _branchtags(self, partial, lrev):
         # TODO: rename this function?
         tiprev = len(self) - 1
         if lrev != tiprev:
             ctxgen = (self[r] for r in xrange(lrev + 1, tiprev + 1))
             self._updatebranchcache(partial, ctxgen)
             self._writebranchcache(partial, self.changelog.tip(), tiprev)
 
         return partial
 
     def updatebranchcache(self):
         tip = self.changelog.tip()
         if self._branchcache is not None and self._branchcachetip == tip:
             return self._branchcache
 
         oldtip = self._branchcachetip
         self._branchcachetip = tip
         if oldtip is None or oldtip not in self.changelog.nodemap:
             partial, last, lrev = self._readbranchcache()
         else:
             lrev = self.changelog.rev(oldtip)
             partial = self._branchcache
 
         self._branchtags(partial, lrev)
         # this private cache holds all heads (not just tips)
         self._branchcache = partial
 
     def branchmap(self):
         '''returns a dictionary {branch: [branchheads]}'''
         self.updatebranchcache()
         return self._branchcache
 
     def branchtags(self):
         '''return a dict where branch names map to the tipmost head of
         the branch, open heads come before closed'''
         bt = {}
         for bn, heads in self.branchmap().iteritems():
             tip = heads[-1]
             for h in reversed(heads):
                 if 'close' not in self.changelog.read(h)[5]:
                     tip = h
                     break
             bt[bn] = tip
         return bt
 
 
     def _readbranchcache(self):
         partial = {}
         try:
             f = self.opener("branchheads.cache")
             lines = f.read().split('\n')
             f.close()
         except (IOError, OSError):
             return {}, nullid, nullrev
 
         try:
             last, lrev = lines.pop(0).split(" ", 1)
             last, lrev = bin(last), int(lrev)
             if lrev >= len(self) or self[lrev].node() != last:
                 # invalidate the cache
                 raise ValueError('invalidating branch cache (tip differs)')
             for l in lines:
                 if not l:
                     continue
                 node, label = l.split(" ", 1)
                 partial.setdefault(label.strip(), []).append(bin(node))
         except KeyboardInterrupt:
             raise
         except Exception, inst:
             if self.ui.debugflag:
                 self.ui.warn(str(inst), '\n')
             partial, last, lrev = {}, nullid, nullrev
         return partial, last, lrev
 
     def _writebranchcache(self, branches, tip, tiprev):
         try:
             f = self.opener("branchheads.cache", "w", atomictemp=True)
             f.write("%s %s\n" % (hex(tip), tiprev))
             for label, nodes in branches.iteritems():
                 for node in nodes:
                     f.write("%s %s\n" % (hex(node), label))
             f.rename()
         except (IOError, OSError):
             pass
 
     def _updatebranchcache(self, partial, ctxgen):
         # collect new branch entries
         newbranches = {}
         for c in ctxgen:
             newbranches.setdefault(c.branch(), []).append(c.node())
         # if older branchheads are reachable from new ones, they aren't
         # really branchheads. Note checking parents is insufficient:
         # 1 (branch a) -> 2 (branch b) -> 3 (branch a)
         for branch, newnodes in newbranches.iteritems():
             bheads = partial.setdefault(branch, [])
             bheads.extend(newnodes)
             if len(bheads) <= 1:
                 continue
             # starting from tip means fewer passes over reachable
             while newnodes:
                 latest = newnodes.pop()
                 if latest not in bheads:
                     continue
                 minbhrev = self[min([self[bh].rev() for bh in bheads])].node()
                 reachable = self.changelog.reachable(latest, minbhrev)
                 reachable.remove(latest)
                 bheads = [b for b in bheads if b not in reachable]
             partial[branch] = bheads
 
     def lookup(self, key):
         if isinstance(key, int):
             return self.changelog.node(key)
         elif key == '.':
             return self.dirstate.parents()[0]
         elif key == 'null':
             return nullid
         elif key == 'tip':
             return self.changelog.tip()
         n = self.changelog._match(key)
         if n:
             return n
         if key in self.tags():
             return self.tags()[key]
         if key in self.branchtags():
             return self.branchtags()[key]
         n = self.changelog._partialmatch(key)
         if n:
             return n
 
         # can't find key, check if it might have come from damaged dirstate
         if key in self.dirstate.parents():
             raise error.Abort(_("working directory has unknown parent '%s'!")
                               % short(key))
         try:
             if len(key) == 20:
                 key = hex(key)
         except:
             pass
         raise error.RepoLookupError(_("unknown revision '%s'") % key)
 
     def lookupbranch(self, key, remote=None):
         repo = remote or self
         if key in repo.branchmap():
             return key
 
         repo = (remote and remote.local()) and remote or self
         return repo[key].branch()
 
     def local(self):
         return True
 
     def join(self, f):
         return os.path.join(self.path, f)
 
     def wjoin(self, f):
         return os.path.join(self.root, f)
 
     def file(self, f):
         if f[0] == '/':
             f = f[1:]
         return filelog.filelog(self.sopener, f)
 
     def changectx(self, changeid):
         return self[changeid]
 
     def parents(self, changeid=None):
         '''get list of changectxs for parents of changeid'''
         return self[changeid].parents()
 
     def filectx(self, path, changeid=None, fileid=None):
         """changeid can be a changeset revision, node, or tag.
            fileid can be a file revision or node."""
         return context.filectx(self, path, changeid, fileid)
 
     def getcwd(self):
         return self.dirstate.getcwd()
 
     def pathto(self, f, cwd=None):
         return self.dirstate.pathto(f, cwd)
 
     def wfile(self, f, mode='r'):
         return self.wopener(f, mode)
 
     def _link(self, f):
         return os.path.islink(self.wjoin(f))
 
     def _loadfilter(self, filter):
         if filter not in self.filterpats:
             l = []
             for pat, cmd in self.ui.configitems(filter):
                 if cmd == '!':
                     continue
                 mf = matchmod.match(self.root, '', [pat])
                 fn = None
                 params = cmd
                 for name, filterfn in self._datafilters.iteritems():
                     if cmd.startswith(name):
                         fn = filterfn
                         params = cmd[len(name):].lstrip()
                         break
                 if not fn:
                     fn = lambda s, c, **kwargs: util.filter(s, c)
                 # Wrap old filters not supporting keyword arguments
                 if not inspect.getargspec(fn)[2]:
                     oldfn = fn
                     fn = lambda s, c, **kwargs: oldfn(s, c)
                 l.append((mf, fn, params))
             self.filterpats[filter] = l
 
     def _filter(self, filter, filename, data):
         self._loadfilter(filter)
 
         for mf, fn, cmd in self.filterpats[filter]:
             if mf(filename):
                 self.ui.debug("filtering %s through %s\n" % (filename, cmd))
                 data = fn(data, cmd, ui=self.ui, repo=self, filename=filename)
                 break
 
         return data
 
     def adddatafilter(self, name, filter):
         self._datafilters[name] = filter
 
     def wread(self, filename):
         if self._link(filename):
             data = os.readlink(self.wjoin(filename))
         else:
             data = self.wopener(filename, 'r').read()
         return self._filter("encode", filename, data)
 
     def wwrite(self, filename, data, flags):
         data = self._filter("decode", filename, data)
         try:
             os.unlink(self.wjoin(filename))
         except OSError:
             pass
         if 'l' in flags:
             self.wopener.symlink(data, filename)
         else:
             self.wopener(filename, 'w').write(data)
             if 'x' in flags:
                 util.set_flags(self.wjoin(filename), False, True)
 
     def wwritedata(self, filename, data):
         return self._filter("decode", filename, data)
 
     def transaction(self, desc):
         tr = self._transref and self._transref() or None
         if tr and tr.running():
             return tr.nest()
 
         # abort here if the journal already exists
         if os.path.exists(self.sjoin("journal")):
             raise error.RepoError(
                 _("abandoned transaction found - run hg recover"))
 
         # save dirstate for rollback
         try:
             ds = self.opener("dirstate").read()
         except IOError:
             ds = ""
         self.opener("journal.dirstate", "w").write(ds)
         self.opener("journal.branch", "w").write(self.dirstate.branch())
         self.opener("journal.desc", "w").write("%d\n%s\n" % (len(self), desc))
 
         renames = [(self.sjoin("journal"), self.sjoin("undo")),
                    (self.join("journal.dirstate"), self.join("undo.dirstate")),
                    (self.join("journal.branch"), self.join("undo.branch")),
                    (self.join("journal.desc"), self.join("undo.desc"))]
         tr = transaction.transaction(self.ui.warn, self.sopener,
                                      self.sjoin("journal"),
                                      aftertrans(renames),
                                      self.store.createmode)
         self._transref = weakref.ref(tr)
         return tr
 
     def recover(self):
         lock = self.lock()
         try:
             if os.path.exists(self.sjoin("journal")):
                 self.ui.status(_("rolling back interrupted transaction\n"))
                 transaction.rollback(self.sopener, self.sjoin("journal"),
                                      self.ui.warn)
                 self.invalidate()
                 return True
             else:
                 self.ui.warn(_("no interrupted transaction available\n"))
                 return False
         finally:
             lock.release()
 
     def rollback(self, dryrun=False):
         wlock = lock = None
         try:
             wlock = self.wlock()
             lock = self.lock()
             if os.path.exists(self.sjoin("undo")):
                 try:
                     args = self.opener("undo.desc", "r").read().splitlines()
                     if len(args) >= 3 and self.ui.verbose:
                         desc = _("rolling back to revision %s"
                                  " (undo %s: %s)\n") % (
                                  int(args[0]) - 1, args[1], args[2])
                     elif len(args) >= 2:
                         desc = _("rolling back to revision %s (undo %s)\n") % (
                                  int(args[0]) - 1, args[1])
                 except IOError:
                     desc = _("rolling back unknown transaction\n")
                 self.ui.status(desc)
                 if dryrun:
                     return
                 transaction.rollback(self.sopener, self.sjoin("undo"),
                                      self.ui.warn)
                 util.rename(self.join("undo.dirstate"), self.join("dirstate"))
                 try:
                     branch = self.opener("undo.branch").read()
                     self.dirstate.setbranch(branch)
                 except IOError:
                     self.ui.warn(_("Named branch could not be reset, "
                                    "current branch still is: %s\n")
                                  % encoding.tolocal(self.dirstate.branch()))
                 self.invalidate()
                 self.dirstate.invalidate()
                 self.destroyed()
             else:
                 self.ui.warn(_("no rollback information available\n"))
                 return 1
         finally:
             release(lock, wlock)
 
     def invalidatecaches(self):
         self._tags = None
         self._tagtypes = None
         self.nodetagscache = None
         self._branchcache = None # in UTF-8
         self._branchcachetip = None
 
     def invalidate(self):
         for a in "changelog manifest".split():
             if a in self.__dict__:
                 delattr(self, a)
         self.invalidatecaches()
 
     def _lock(self, lockname, wait, releasefn, acquirefn, desc):
         try:
             l = lock.lock(lockname, 0, releasefn, desc=desc)
         except error.LockHeld, inst:
             if not wait:
                 raise
             self.ui.warn(_("waiting for lock on %s held by %r\n") %
                          (desc, inst.locker))
             # default to 600 seconds timeout
             l = lock.lock(lockname, int(self.ui.config("ui", "timeout", "600")),
                           releasefn, desc=desc)
         if acquirefn:
             acquirefn()
         return l
 
     def lock(self, wait=True):
         '''Lock the repository store (.hg/store) and return a weak reference
         to the lock. Use this before modifying the store (e.g. committing or
         stripping). If you are opening a transaction, get a lock as well.)'''
         l = self._lockref and self._lockref()
         if l is not None and l.held:
             l.lock()
             return l
 
         l = self._lock(self.sjoin("lock"), wait, None, self.invalidate,
                        _('repository %s') % self.origroot)
         self._lockref = weakref.ref(l)
         return l
 
     def wlock(self, wait=True):
         '''Lock the non-store parts of the repository (everything under
         .hg except .hg/store) and return a weak reference to the lock.
         Use this before modifying files in .hg.'''
         l = self._wlockref and self._wlockref()
         if l is not None and l.held:
             l.lock()
             return l
 
         l = self._lock(self.join("wlock"), wait, self.dirstate.write,
                        self.dirstate.invalidate, _('working directory of %s') %
                        self.origroot)
         self._wlockref = weakref.ref(l)
         return l
 
     def _filecommit(self, fctx, manifest1, manifest2, linkrev, tr, changelist):
         """
         commit an individual file as part of a larger transaction
         """
 
         fname = fctx.path()
         text = fctx.data()
         flog = self.file(fname)
         fparent1 = manifest1.get(fname, nullid)
         fparent2 = fparent2o = manifest2.get(fname, nullid)
 
         meta = {}
         copy = fctx.renamed()
         if copy and copy[0] != fname:
             # Mark the new revision of this file as a copy of another
             # file.  This copy data will effectively act as a parent
             # of this new revision.  If this is a merge, the first
             # parent will be the nullid (meaning "look up the copy data")
             # and the second one will be the other parent.  For example:
             #
             # 0 --- 1 --- 3   rev1 changes file foo
             #   \       /     rev2 renames foo to bar and changes it
             #    \- 2 -/      rev3 should have bar with all changes and
             #                      should record that bar descends from
             #                      bar in rev2 and foo in rev1
             #
             # this allows this merge to succeed:
             #
             # 0 --- 1 --- 3   rev4 reverts the content change from rev2
             #   \       /     merging rev3 and rev4 should use bar@rev2
             #    \- 2 --- 4        as the merge base
             #
 
             cfname = copy[0]
             crev = manifest1.get(cfname)
             newfparent = fparent2
 
             if manifest2: # branch merge
                 if fparent2 == nullid or crev is None: # copied on remote side
                     if cfname in manifest2:
                         crev = manifest2[cfname]
                         newfparent = fparent1
 
             # find source in nearest ancestor if we've lost track
             if not crev:
                 self.ui.debug(" %s: searching for copy revision for %s\n" %
                               (fname, cfname))
                 for ancestor in self['.'].ancestors():
                     if cfname in ancestor:
                         crev = ancestor[cfname].filenode()
                         break
 
             self.ui.debug(" %s: copy %s:%s\n" % (fname, cfname, hex(crev)))
             meta["copy"] = cfname
             meta["copyrev"] = hex(crev)
             fparent1, fparent2 = nullid, newfparent
         elif fparent2 != nullid:
             # is one parent an ancestor of the other?
             fparentancestor = flog.ancestor(fparent1, fparent2)
             if fparentancestor == fparent1:
                 fparent1, fparent2 = fparent2, nullid
             elif fparentancestor == fparent2:
                 fparent2 = nullid
 
         # is the file changed?
         if fparent2 != nullid or flog.cmp(fparent1, text) or meta:
             changelist.append(fname)
             return flog.add(text, meta, tr, linkrev, fparent1, fparent2)
 
         # are just the flags changed during merge?
         if fparent1 != fparent2o and manifest1.flags(fname) != fctx.flags():
             changelist.append(fname)
 
         return fparent1
 
     def commit(self, text="", user=None, date=None, match=None, force=False,
                editor=False, extra={}):
         """Add a new revision to current repository.
 
         Revision information is gathered from the working directory,
         match can be used to filter the committed files. If editor is
         supplied, it is called to get a commit message.
         """
 
         def fail(f, msg):
             raise util.Abort('%s: %s' % (f, msg))
 
         if not match:
             match = matchmod.always(self.root, '')
 
         if not force:
             vdirs = []
             match.dir = vdirs.append
             match.bad = fail
 
         wlock = self.wlock()
         try:
             wctx = self[None]
             merge = len(wctx.parents()) > 1
 
             if (not force and merge and match and
                 (match.files() or match.anypats())):
                 raise util.Abort(_('cannot partially commit a merge '
                                    '(do not specify files or patterns)'))
 
             changes = self.status(match=match, clean=force)
             if force:
                 changes[0].extend(changes[6]) # mq may commit unchanged files
 
             # check subrepos
             subs = []
             removedsubs = set()
             for p in wctx.parents():
                 removedsubs.update(s for s in p.substate if match(s))
             for s in wctx.substate:
                 removedsubs.discard(s)
                 if match(s) and wctx.sub(s).dirty():
                     subs.append(s)
             if (subs or removedsubs):
                 if (not match('.hgsub') and
                     '.hgsub' in (wctx.modified() + wctx.added())):
                     raise util.Abort(_("can't commit subrepos without .hgsub"))
                 if '.hgsubstate' not in changes[0]:
                     changes[0].insert(0, '.hgsubstate')
 
             # make sure all explicit patterns are matched
             if not force and match.files():
                 matched = set(changes[0] + changes[1] + changes[2])
 
                 for f in match.files():
                     if f == '.' or f in matched or f in wctx.substate:
                         continue
                     if f in changes[3]: # missing
                         fail(f, _('file not found!'))
                     if f in vdirs: # visited directory
                         d = f + '/'
                         for mf in matched:
                             if mf.startswith(d):
                                 break
                         else:
                             fail(f, _("no match under directory!"))
                     elif f not in self.dirstate:
                         fail(f, _("file not tracked!"))
 
             if (not force and not extra.get("close") and not merge
                 and not (changes[0] or changes[1] or changes[2])
                 and wctx.branch() == wctx.p1().branch()):
                 return None
 
             ms = mergemod.mergestate(self)
             for f in changes[0]:
                 if f in ms and ms[f] == 'u':
                     raise util.Abort(_("unresolved merge conflicts "
                                                     "(see hg resolve)"))
 
             cctx = context.workingctx(self, text, user, date, extra, changes)
             if editor:
                 cctx._text = editor(self, cctx, subs)
             edited = (text != cctx._text)
 
             # commit subs
             if subs or removedsubs:
                 state = wctx.substate.copy()
                 for s in sorted(subs):
                     sub = wctx.sub(s)
                     self.ui.status(_('committing subrepository %s\n') %
                         subrepo.relpath(sub))
                     sr = sub.commit(cctx._text, user, date)
                     state[s] = (state[s][0], sr)
                 subrepo.writestate(self, state)
 
             # Save commit message in case this transaction gets rolled back
             # (e.g. by a pretxncommit hook).  Leave the content alone on
             # the assumption that the user will use the same editor again.
             msgfile = self.opener('last-message.txt', 'wb')
             msgfile.write(cctx._text)
             msgfile.close()
 
             p1, p2 = self.dirstate.parents()
             hookp1, hookp2 = hex(p1), (p2 != nullid and hex(p2) or '')
             try:
                 self.hook("precommit", throw=True, parent1=hookp1, parent2=hookp2)
                 ret = self.commitctx(cctx, True)
             except:
                 if edited:
                     msgfn = self.pathto(msgfile.name[len(self.root)+1:])
                     self.ui.write(
                         _('note: commit message saved in %s\n') % msgfn)
                 raise
 
             # update dirstate and mergestate
             for f in changes[0] + changes[1]:
                 self.dirstate.normal(f)
             for f in changes[2]:
                 self.dirstate.forget(f)
             self.dirstate.setparents(ret)
             ms.reset()
         finally:
             wlock.release()
 
         self.hook("commit", node=hex(ret), parent1=hookp1, parent2=hookp2)
         return ret
 
     def commitctx(self, ctx, error=False):
         """Add a new revision to current repository.
         Revision information is passed via the context argument.
         """
 
         tr = lock = None
         removed = ctx.removed()
         p1, p2 = ctx.p1(), ctx.p2()
         m1 = p1.manifest().copy()
         m2 = p2.manifest()
         user = ctx.user()
 
         lock = self.lock()
         try:
             tr = self.transaction("commit")
             trp = weakref.proxy(tr)
 
             # check in files
             new = {}
             changed = []
             linkrev = len(self)
             for f in sorted(ctx.modified() + ctx.added()):
                 self.ui.note(f + "\n")
                 try:
                     fctx = ctx[f]
                     new[f] = self._filecommit(fctx, m1, m2, linkrev, trp,
                                               changed)
                     m1.set(f, fctx.flags())
                 except OSError, inst:
                     self.ui.warn(_("trouble committing %s!\n") % f)
                     raise
                 except IOError, inst:
                     errcode = getattr(inst, 'errno', errno.ENOENT)
                     if error or errcode and errcode != errno.ENOENT:
                         self.ui.warn(_("trouble committing %s!\n") % f)
                         raise
                     else:
                         removed.append(f)
 
             # update manifest
             m1.update(new)
             removed = [f for f in sorted(removed) if f in m1 or f in m2]
             drop = [f for f in removed if f in m1]
             for f in drop:
                 del m1[f]
             mn = self.manifest.add(m1, trp, linkrev, p1.manifestnode(),
                                    p2.manifestnode(), (new, drop))
 
             # update changelog
             self.changelog.delayupdate()
             n = self.changelog.add(mn, changed + removed, ctx.description(),
                                    trp, p1.node(), p2.node(),
                                    user, ctx.date(), ctx.extra().copy())
             p = lambda: self.changelog.writepending() and self.root or ""
             xp1, xp2 = p1.hex(), p2 and p2.hex() or ''
             self.hook('pretxncommit', throw=True, node=hex(n), parent1=xp1,
                       parent2=xp2, pending=p)
             self.changelog.finalize(trp)
             tr.close()
 
             if self._branchcache:
                 self.updatebranchcache()
             return n
         finally:
             if tr:
                 tr.release()
             lock.release()
 
     def destroyed(self):
         '''Inform the repository that nodes have been destroyed.
         Intended for use by strip and rollback, so there's a common
         place for anything that has to be done after destroying history.'''
         # XXX it might be nice if we could take the list of destroyed
         # nodes, but I don't see an easy way for rollback() to do that
 
         # Ensure the persistent tag cache is updated.  Doing it now
         # means that the tag cache only has to worry about destroyed
         # heads immediately after a strip/rollback.  That in turn
         # guarantees that "cachetip == currenttip" (comparing both rev
         # and node) always means no nodes have been added or destroyed.
 
         # XXX this is suboptimal when qrefresh'ing: we strip the current
         # head, refresh the tag cache, then immediately add a new head.
         # But I think doing it this way is necessary for the "instant
         # tag cache retrieval" case to work.
         self.invalidatecaches()
 
     def walk(self, match, node=None):
         '''
         walk recursively through the directory tree or a given
         changeset, finding all files matched by the match
         function
         '''
         return self[node].walk(match)
 
     def status(self, node1='.', node2=None, match=None,
                ignored=False, clean=False, unknown=False,
                listsubrepos=False):
         """return status of files between two nodes or node and working directory
 
         If node1 is None, use the first dirstate parent instead.
         If node2 is None, compare node1 with working directory.
         """
 
         def mfmatches(ctx):
             mf = ctx.manifest().copy()
             for fn in mf.keys():
                 if not match(fn):
                     del mf[fn]
             return mf
 
         if isinstance(node1, context.changectx):
             ctx1 = node1
         else:
             ctx1 = self[node1]
         if isinstance(node2, context.changectx):
             ctx2 = node2
         else:
             ctx2 = self[node2]
 
         working = ctx2.rev() is None
         parentworking = working and ctx1 == self['.']
         match = match or matchmod.always(self.root, self.getcwd())
         listignored, listclean, listunknown = ignored, clean, unknown
 
         # load earliest manifest first for caching reasons
         if not working and ctx2.rev() < ctx1.rev():
             ctx2.manifest()
 
         if not parentworking:
             def bad(f, msg):
                 if f not in ctx1:
                     self.ui.warn('%s: %s\n' % (self.dirstate.pathto(f), msg))
             match.bad = bad
 
         if working: # we need to scan the working dir
             subrepos = []
             if '.hgsub' in self.dirstate:
                 subrepos = ctx1.substate.keys()
             s = self.dirstate.status(match, subrepos, listignored,
                                      listclean, listunknown)
             cmp, modified, added, removed, deleted, unknown, ignored, clean = s
 
             # check for any possibly clean files
             if parentworking and cmp:
                 fixup = []
                 # do a full compare of any files that might have changed
                 for f in sorted(cmp):
                     if (f not in ctx1 or ctx2.flags(f) != ctx1.flags(f)
                         or ctx1[f].cmp(ctx2[f])):
                         modified.append(f)
                     else:
                         fixup.append(f)
 
                 # update dirstate for files that are actually clean
                 if fixup:
                     if listclean:
                         clean += fixup
 
                     try:
                         # updating the dirstate is optional
                         # so we don't wait on the lock
                         wlock = self.wlock(False)
                         try:
                             for f in fixup:
                                 self.dirstate.normal(f)
                         finally:
                             wlock.release()
                     except error.LockError:
                         pass
 
         if not parentworking:
             mf1 = mfmatches(ctx1)
             if working:
                 # we are comparing working dir against non-parent
                 # generate a pseudo-manifest for the working dir
                 mf2 = mfmatches(self['.'])
                 for f in cmp + modified + added:
                     mf2[f] = None
                     mf2.set(f, ctx2.flags(f))
                 for f in removed:
                     if f in mf2:
                         del mf2[f]
             else:
                 # we are comparing two revisions
                 deleted, unknown, ignored = [], [], []
                 mf2 = mfmatches(ctx2)
 
             modified, added, clean = [], [], []
             for fn in mf2:
                 if fn in mf1:
                     if (mf1.flags(fn) != mf2.flags(fn) or
                         (mf1[fn] != mf2[fn] and
                          (mf2[fn] or ctx1[fn].cmp(ctx2[fn])))):
                         modified.append(fn)
                     elif listclean:
                         clean.append(fn)
                     del mf1[fn]
                 else:
                     added.append(fn)
             removed = mf1.keys()
 
         r = modified, added, removed, deleted, unknown, ignored, clean
 
         if listsubrepos:
             for subpath, sub in subrepo.itersubrepos(ctx1, ctx2):
                 if working:
                     rev2 = None
                 else:
                     rev2 = ctx2.substate[subpath][1]
                 try:
                     submatch = matchmod.narrowmatcher(subpath, match)
                     s = sub.status(rev2, match=submatch, ignored=listignored,
                                    clean=listclean, unknown=listunknown,
                                    listsubrepos=True)
                     for rfiles, sfiles in zip(r, s):
                         rfiles.extend("%s/%s" % (subpath, f) for f in sfiles)
                 except error.LookupError:
                     self.ui.status(_("skipping missing subrepository: %s\n")
                                    % subpath)
 
         [l.sort() for l in r]
         return r
 
     def heads(self, start=None):
         heads = self.changelog.heads(start)
         # sort the output in rev descending order
         heads = [(-self.changelog.rev(h), h) for h in heads]
         return [n for (r, n) in sorted(heads)]
 
     def branchheads(self, branch=None, start=None, closed=False):
         '''return a (possibly filtered) list of heads for the given branch
 
         Heads are returned in topological order, from newest to oldest.
         If branch is None, use the dirstate branch.
         If start is not None, return only heads reachable from start.
         If closed is True, return heads that are marked as closed as well.
         '''
         if branch is None:
             branch = self[None].branch()
         branches = self.branchmap()
         if branch not in branches:
             return []
         # the cache returns heads ordered lowest to highest
         bheads = list(reversed(branches[branch]))
         if start is not None:
             # filter out the heads that cannot be reached from startrev
             fbheads = set(self.changelog.nodesbetween([start], bheads)[2])
             bheads = [h for h in bheads if h in fbheads]
         if not closed:
             bheads = [h for h in bheads if
                       ('close' not in self.changelog.read(h)[5])]
         return bheads
 
     def branches(self, nodes):
         if not nodes:
             nodes = [self.changelog.tip()]
         b = []
         for n in nodes:
             t = n
             while 1:
                 p = self.changelog.parents(n)
                 if p[1] != nullid or p[0] == nullid:
                     b.append((t, n, p[0], p[1]))
                     break
                 n = p[0]
         return b
 
     def between(self, pairs):
         r = []
 
         for top, bottom in pairs:
             n, l, i = top, [], 0
             f = 1
 
             while n != bottom and n != nullid:
                 p = self.changelog.parents(n)[0]
                 if i == f:
                     l.append(n)
                     f = f * 2
                 n = p
                 i += 1
 
             r.append(l)
 
         return r
 
     def pull(self, remote, heads=None, force=False):
         lock = self.lock()
         try:
             tmp = discovery.findcommonincoming(self, remote, heads=heads,
                                                force=force)
             common, fetch, rheads = tmp
             if not fetch:
                 self.ui.status(_("no changes found\n"))
                 return 0
 
             if fetch == [nullid]:
                 self.ui.status(_("requesting all changes\n"))
             elif heads is None and remote.capable('changegroupsubset'):
                 # issue1320, avoid a race if remote changed after discovery
                 heads = rheads
 
             if heads is None:
                 cg = remote.changegroup(fetch, 'pull')
             else:
                 if not remote.capable('changegroupsubset'):
                     raise util.Abort(_("partial pull cannot be done because "
                                        "other repository doesn't support "
                                        "changegroupsubset."))
                 cg = remote.changegroupsubset(fetch, heads, 'pull')
             return self.addchangegroup(cg, 'pull', remote.url(), lock=lock)
         finally:
             lock.release()
 
     def push(self, remote, force=False, revs=None, newbranch=False):
         '''Push outgoing changesets (limited by revs) from the current
         repository to remote. Return an integer:
           - 0 means HTTP error *or* nothing to push
           - 1 means we pushed and remote head count is unchanged *or*
             we have outgoing changesets but refused to push
           - other values as described by addchangegroup()
         '''
         # there are two ways to push to remote repo:
         #
         # addchangegroup assumes local user can lock remote
         # repo (local filesystem, old ssh servers).
         #
         # unbundle assumes local user cannot lock remote repo (new ssh
         # servers, http servers).
 
         lock = None
         unbundle = remote.capable('unbundle')
         if not unbundle:
             lock = remote.lock()
         try:
             ret = discovery.prepush(self, remote, force, revs, newbranch)
             if ret[0] is None:
                 # and here we return 0 for "nothing to push" or 1 for
                 # "something to push but I refuse"
                 return ret[1]
 
             cg, remote_heads = ret
             if unbundle:
                 # local repo finds heads on server, finds out what revs it must
                 # push.  once revs transferred, if server finds it has
                 # different heads (someone else won commit/push race), server
                 # aborts.
                 if force:
                     remote_heads = ['force']
                 # ssh: return remote's addchangegroup()
                 # http: return remote's addchangegroup() or 0 for error
                 return remote.unbundle(cg, remote_heads, 'push')
             else:
                 # we return an integer indicating remote head count change
                 return remote.addchangegroup(cg, 'push', self.url(), lock=lock)
         finally:
             if lock is not None:
                 lock.release()
 
     def changegroupinfo(self, nodes, source):
         if self.ui.verbose or source == 'bundle':
             self.ui.status(_("%d changesets found\n") % len(nodes))
         if self.ui.debugflag:
             self.ui.debug("list of changesets:\n")
             for node in nodes:
                 self.ui.debug("%s\n" % hex(node))
 
     def changegroupsubset(self, bases, heads, source, extranodes=None):
         """Compute a changegroup consisting of all the nodes that are
         descendents of any of the bases and ancestors of any of the heads.
         Return a chunkbuffer object whose read() method will return
         successive changegroup chunks.
 
         It is fairly complex as determining which filenodes and which
         manifest nodes need to be included for the changeset to be complete
         is non-trivial.
 
         Another wrinkle is doing the reverse, figuring out which changeset in
         the changegroup a particular filenode or manifestnode belongs to.
 
         The caller can specify some nodes that must be included in the
         changegroup using the extranodes argument.  It should be a dict
         where the keys are the filenames (or 1 for the manifest), and the
         values are lists of (node, linknode) tuples, where node is a wanted
         node and linknode is the changelog node that should be transmitted as
         the linkrev.
         """
 
         # Set up some initial variables
         # Make it easy to refer to self.changelog
         cl = self.changelog
         # Compute the list of changesets in this changegroup.
         # Some bases may turn out to be superfluous, and some heads may be
         # too.  nodesbetween will return the minimal set of bases and heads
         # necessary to re-create the changegroup.
         if not bases:
             bases = [nullid]
         msng_cl_lst, bases, heads = cl.nodesbetween(bases, heads)
 
         if extranodes is None:
             # can we go through the fast path ?
             heads.sort()
             allheads = self.heads()
             allheads.sort()
             if heads == allheads:
                 return self._changegroup(msng_cl_lst, source)
 
         # slow path
         self.hook('preoutgoing', throw=True, source=source)
 
         self.changegroupinfo(msng_cl_lst, source)
 
         # We assume that all ancestors of bases are known
         commonrevs = set(cl.ancestors(*[cl.rev(n) for n in bases]))
 
         # Make it easy to refer to self.manifest
         mnfst = self.manifest
         # We don't know which manifests are missing yet
         msng_mnfst_set = {}
         # Nor do we know which filenodes are missing.
         msng_filenode_set = {}
 
         junk = mnfst.index[len(mnfst) - 1] # Get around a bug in lazyindex
         junk = None
 
         # A changeset always belongs to itself, so the changenode lookup
         # function for a changenode is identity.
         def identity(x):
             return x
 
         # A function generating function that sets up the initial environment
         # the inner function.
         def filenode_collector(changedfiles):
             # This gathers information from each manifestnode included in the
             # changegroup about which filenodes the manifest node references
             # so we can include those in the changegroup too.
             #
             # It also remembers which changenode each filenode belongs to.  It
             # does this by assuming the a filenode belongs to the changenode
             # the first manifest that references it belongs to.
             def collect_msng_filenodes(mnfstnode):
                 r = mnfst.rev(mnfstnode)
                 if r - 1 in mnfst.parentrevs(r):
                     # If the previous rev is one of the parents,
                     # we only need to see a diff.
                     deltamf = mnfst.readdelta(mnfstnode)
                     # For each line in the delta
                     for f, fnode in deltamf.iteritems():
                         # And if the file is in the list of files we care
                         # about.
                         if f in changedfiles:
                             # Get the changenode this manifest belongs to
                             clnode = msng_mnfst_set[mnfstnode]
                             # Create the set of filenodes for the file if
                             # there isn't one already.
                             ndset = msng_filenode_set.setdefault(f, {})
                             # And set the filenode's changelog node to the
                             # manifest's if it hasn't been set already.
                             ndset.setdefault(fnode, clnode)
                 else:
                     # Otherwise we need a full manifest.
                     m = mnfst.read(mnfstnode)
                     # For every file in we care about.
                     for f in changedfiles:
                         fnode = m.get(f, None)
                         # If it's in the manifest
                         if fnode is not None:
                             # See comments above.
                             clnode = msng_mnfst_set[mnfstnode]
                             ndset = msng_filenode_set.setdefault(f, {})
                             ndset.setdefault(fnode, clnode)
             return collect_msng_filenodes
 
         # If we determine that a particular file or manifest node must be a
         # node that the recipient of the changegroup will already have, we can
         # also assume the recipient will have all the parents.  This function
         # prunes them from the set of missing nodes.
         def prune(revlog, missingnodes):
             hasset = set()
             # If a 'missing' filenode thinks it belongs to a changenode we
             # assume the recipient must have, then the recipient must have
             # that filenode.
             for n in missingnodes:
                 clrev = revlog.linkrev(revlog.rev(n))
                 if clrev in commonrevs:
                     hasset.add(n)
             for n in hasset:
                 missingnodes.pop(n, None)
             for r in revlog.ancestors(*[revlog.rev(n) for n in hasset]):
                 missingnodes.pop(revlog.node(r), None)
 
         # Add the nodes that were explicitly requested.
         def add_extra_nodes(name, nodes):
             if not extranodes or name not in extranodes:
                 return
 
             for node, linknode in extranodes[name]:
                 if node not in nodes:
                     nodes[node] = linknode
 
         # Now that we have all theses utility functions to help out and
         # logically divide up the task, generate the group.
         def gengroup():
             # The set of changed files starts empty.
             changedfiles = set()
             collect = changegroup.collector(cl, msng_mnfst_set, changedfiles)
 
             # Create a changenode group generator that will call our functions
             # back to lookup the owning changenode and collect information.
             group = cl.group(msng_cl_lst, identity, collect)
             for cnt, chnk in enumerate(group):
                 yield chnk
                 self.ui.progress(_('bundling changes'), cnt, unit=_('chunks'))
             self.ui.progress(_('bundling changes'), None)
 
             prune(mnfst, msng_mnfst_set)
             add_extra_nodes(1, msng_mnfst_set)
             msng_mnfst_lst = msng_mnfst_set.keys()
             # Sort the manifestnodes by revision number.
             msng_mnfst_lst.sort(key=mnfst.rev)
             # Create a generator for the manifestnodes that calls our lookup
             # and data collection functions back.
             group = mnfst.group(msng_mnfst_lst,
                                 lambda mnode: msng_mnfst_set[mnode],
                                 filenode_collector(changedfiles))
             for cnt, chnk in enumerate(group):
                 yield chnk
                 self.ui.progress(_('bundling manifests'), cnt, unit=_('chunks'))
             self.ui.progress(_('bundling manifests'), None)
 
             # These are no longer needed, dereference and toss the memory for
             # them.
             msng_mnfst_lst = None
             msng_mnfst_set.clear()
 
             if extranodes:
                 for fname in extranodes:
                     if isinstance(fname, int):
                         continue
                     msng_filenode_set.setdefault(fname, {})
                     changedfiles.add(fname)
             # Go through all our files in order sorted by name.
             cnt = 0
             for fname in sorted(changedfiles):
                 filerevlog = self.file(fname)
                 if not len(filerevlog):
                     raise util.Abort(_("empty or missing revlog for %s") % fname)
                 # Toss out the filenodes that the recipient isn't really
                 # missing.
                 missingfnodes = msng_filenode_set.pop(fname, {})
                 prune(filerevlog, missingfnodes)
                 add_extra_nodes(fname, missingfnodes)
                 # If any filenodes are left, generate the group for them,
                 # otherwise don't bother.
                 if missingfnodes:
                     yield changegroup.chunkheader(len(fname))
                     yield fname
                     # Sort the filenodes by their revision # (topological order)
                     nodeiter = list(missingfnodes)
                     nodeiter.sort(key=filerevlog.rev)
                     # Create a group generator and only pass in a changenode
                     # lookup function as we need to collect no information
                     # from filenodes.
                     group = filerevlog.group(nodeiter,
                                              lambda fnode: missingfnodes[fnode])
                     for chnk in group:
                         self.ui.progress(
                             _('bundling files'), cnt, item=fname, unit=_('chunks'))
                         cnt += 1
                         yield chnk
             # Signal that no more groups are left.
             yield changegroup.closechunk()
             self.ui.progress(_('bundling files'), None)
 
             if msng_cl_lst:
                 self.hook('outgoing', node=hex(msng_cl_lst[0]), source=source)
 
         return util.chunkbuffer(gengroup())
 
     def changegroup(self, basenodes, source):
         # to avoid a race we use changegroupsubset() (issue1320)
         return self.changegroupsubset(basenodes, self.heads(), source)
 
     def _changegroup(self, nodes, source):
         """Compute the changegroup of all nodes that we have that a recipient
         doesn't.  Return a chunkbuffer object whose read() method will return
         successive changegroup chunks.
 
         This is much easier than the previous function as we can assume that
         the recipient has any changenode we aren't sending them.
 
         nodes is the set of nodes to send"""
 
         self.hook('preoutgoing', throw=True, source=source)
 
         cl = self.changelog
         revset = set([cl.rev(n) for n in nodes])
         self.changegroupinfo(nodes, source)
 
         def identity(x):
             return x
 
         def gennodelst(log):
             for r in log:
                 if log.linkrev(r) in revset:
                     yield log.node(r)
 
         def lookuplinkrev_func(revlog):
             def lookuplinkrev(n):
                 return cl.node(revlog.linkrev(revlog.rev(n)))
             return lookuplinkrev
 
         def gengroup():
             '''yield a sequence of changegroup chunks (strings)'''
             # construct a list of all changed files
             changedfiles = set()
             mmfs = {}
             collect = changegroup.collector(cl, mmfs, changedfiles)
 
             for cnt, chnk in enumerate(cl.group(nodes, identity, collect)):
                 self.ui.progress(_('bundling changes'), cnt, unit=_('chunks'))
                 yield chnk
             self.ui.progress(_('bundling changes'), None)
 
             mnfst = self.manifest
             nodeiter = gennodelst(mnfst)
             for cnt, chnk in enumerate(mnfst.group(nodeiter,
                                                    lookuplinkrev_func(mnfst))):
                 self.ui.progress(_('bundling manifests'), cnt, unit=_('chunks'))
                 yield chnk
             self.ui.progress(_('bundling manifests'), None)
 
             cnt = 0
             for fname in sorted(changedfiles):
                 filerevlog = self.file(fname)
                 if not len(filerevlog):
                     raise util.Abort(_("empty or missing revlog for %s") % fname)
                 nodeiter = gennodelst(filerevlog)
                 nodeiter = list(nodeiter)
                 if nodeiter:
                     yield changegroup.chunkheader(len(fname))
                     yield fname
                     lookup = lookuplinkrev_func(filerevlog)
                     for chnk in filerevlog.group(nodeiter, lookup):
                         self.ui.progress(
                             _('bundling files'), cnt, item=fname, unit=_('chunks'))
                         cnt += 1
                         yield chnk
             self.ui.progress(_('bundling files'), None)
 
             yield changegroup.closechunk()
 
             if nodes:
                 self.hook('outgoing', node=hex(nodes[0]), source=source)
 
         return util.chunkbuffer(gengroup())
 
     def addchangegroup(self, source, srctype, url, emptyok=False, lock=None):
         """Add the changegroup returned by source.read() to this repo.
         srctype is a string like 'push', 'pull', or 'unbundle'.  url is
         the URL of the repo where this changegroup is coming from.
 
         Return an integer summarizing the change to this repo:
         - nothing changed or no source: 0
         - more heads than before: 1+added heads (2..n)
         - fewer heads than before: -1-removed heads (-2..-n)
         - number of heads stays the same: 1
         """
         def csmap(x):
             self.ui.debug("add changeset %s\n" % short(x))
             return len(cl)
 
         def revmap(x):
             return cl.rev(x)
 
         if not source:
             return 0
 
         if not hasattr(source, 'chunk'):
             source = changegroup.unbundle10(source, 'UN')
 
         self.hook('prechangegroup', throw=True, source=srctype, url=url)
 
         changesets = files = revisions = 0
         efiles = set()
 
         # write changelog data to temp files so concurrent readers will not see
         # inconsistent view
         cl = self.changelog
         cl.delayupdate()
         oldheads = len(cl.heads())
 
         tr = self.transaction("\n".join([srctype, urlmod.hidepassword(url)]))
         try:
             trp = weakref.proxy(tr)
             # pull off the changeset group
             self.ui.status(_("adding changesets\n"))
             clstart = len(cl)
             class prog(object):
                 step = _('changesets')
                 count = 1
                 ui = self.ui
                 total = None
                 def __call__(self):
                     self.ui.progress(self.step, self.count, unit=_('chunks'),
                                      total=self.total)
                     self.count += 1
             pr = prog()
             source.callback = pr
 
-            if (cl.addgroup(source.chunks(), csmap, trp) is None
+            if (cl.addgroup(source, csmap, trp) is None
                 and not emptyok):
                 raise util.Abort(_("received changelog group is empty"))
             clend = len(cl)
             changesets = clend - clstart
             for c in xrange(clstart, clend):
                 efiles.update(self[c].files())
             efiles = len(efiles)
             self.ui.progress(_('changesets'), None)
 
             # pull off the manifest group
             self.ui.status(_("adding manifests\n"))
             pr.step = _('manifests')
             pr.count = 1
             pr.total = changesets # manifests <= changesets
             # no need to check for empty manifest group here:
             # if the result of the merge of 1 and 2 is the same in 3 and 4,
             # no new manifest will be created and the manifest group will
             # be empty during the pull
-            self.manifest.addgroup(source.chunks(), revmap, trp)
+            self.manifest.addgroup(source, revmap, trp)
             self.ui.progress(_('manifests'), None)
 
             needfiles = {}
             if self.ui.configbool('server', 'validate', default=False):
                 # validate incoming csets have their manifests
                 for cset in xrange(clstart, clend):
                     mfest = self.changelog.read(self.changelog.node(cset))[0]
                     mfest = self.manifest.readdelta(mfest)
                     # store file nodes we must see
                     for f, n in mfest.iteritems():
                         needfiles.setdefault(f, set()).add(n)
 
             # process the files
             self.ui.status(_("adding file changes\n"))
             pr.step = 'files'
             pr.count = 1
             pr.total = efiles
             source.callback = None
 
             while 1:
                 f = source.chunk()
                 if not f:
                     break
                 self.ui.debug("adding %s revisions\n" % f)
                 pr()
                 fl = self.file(f)
                 o = len(fl)
-                if fl.addgroup(source.chunks(), revmap, trp) is None:
+                if fl.addgroup(source, revmap, trp) is None:
                     raise util.Abort(_("received file revlog group is empty"))
                 revisions += len(fl) - o
                 files += 1
                 if f in needfiles:
                     needs = needfiles[f]
                     for new in xrange(o, len(fl)):
                         n = fl.node(new)
                         if n in needs:
                             needs.remove(n)
                     if not needs:
                         del needfiles[f]
             self.ui.progress(_('files'), None)
 
             for f, needs in needfiles.iteritems():
                 fl = self.file(f)
                 for n in needs:
                     try:
                         fl.rev(n)
                     except error.LookupError:
                         raise util.Abort(
                             _('missing file data for %s:%s - run hg verify') %
                             (f, hex(n)))
 
             newheads = len(cl.heads())
             heads = ""
             if oldheads and newheads != oldheads:
                 heads = _(" (%+d heads)") % (newheads - oldheads)
 
             self.ui.status(_("added %d changesets"
                              " with %d changes to %d files%s\n")
                              % (changesets, revisions, files, heads))
 
             if changesets > 0:
                 p = lambda: cl.writepending() and self.root or ""
                 self.hook('pretxnchangegroup', throw=True,
                           node=hex(cl.node(clstart)), source=srctype,
                           url=url, pending=p)
 
             # make changelog see real files again
             cl.finalize(trp)
 
             tr.close()
         finally:
             tr.release()
             if lock:
                 lock.release()
 
         if changesets > 0:
             # forcefully update the on-disk branch cache
             self.ui.debug("updating the branch cache\n")
             self.updatebranchcache()
             self.hook("changegroup", node=hex(cl.node(clstart)),
                       source=srctype, url=url)
 
             for i in xrange(clstart, clend):
                 self.hook("incoming", node=hex(cl.node(i)),
                           source=srctype, url=url)
 
         # never return 0 here:
         if newheads < oldheads:
             return newheads - oldheads - 1
         else:
             return newheads - oldheads + 1
 
 
     def stream_in(self, remote, requirements):
         fp = remote.stream_out()
         l = fp.readline()
         try:
             resp = int(l)
         except ValueError:
             raise error.ResponseError(
                 _('Unexpected response from remote server:'), l)
         if resp == 1:
             raise util.Abort(_('operation forbidden by server'))
         elif resp == 2:
             raise util.Abort(_('locking the remote repository failed'))
         elif resp != 0:
             raise util.Abort(_('the server sent an unknown error code'))
         self.ui.status(_('streaming all changes\n'))
         l = fp.readline()
         try:
             total_files, total_bytes = map(int, l.split(' ', 1))
         except (ValueError, TypeError):
             raise error.ResponseError(
                 _('Unexpected response from remote server:'), l)
         self.ui.status(_('%d files to transfer, %s of data\n') %
                        (total_files, util.bytecount(total_bytes)))
         start = time.time()
         for i in xrange(total_files):
             # XXX doesn't support '\n' or '\r' in filenames
             l = fp.readline()
             try:
                 name, size = l.split('\0', 1)
                 size = int(size)
             except (ValueError, TypeError):
                 raise error.ResponseError(
                     _('Unexpected response from remote server:'), l)
             self.ui.debug('adding %s (%s)\n' % (name, util.bytecount(size)))
             # for backwards compat, name was partially encoded
             ofp = self.sopener(store.decodedir(name), 'w')
             for chunk in util.filechunkiter(fp, limit=size):
                 ofp.write(chunk)
             ofp.close()
         elapsed = time.time() - start
         if elapsed <= 0:
             elapsed = 0.001
         self.ui.status(_('transferred %s in %.1f seconds (%s/sec)\n') %
                        (util.bytecount(total_bytes), elapsed,
                         util.bytecount(total_bytes / elapsed)))
 
         # new requirements = old non-format requirements + new format-related
         # requirements from the streamed-in repository
         requirements.update(set(self.requirements) - self.supportedformats)
         self._applyrequirements(requirements)
         self._writerequirements()
 
         self.invalidate()
         return len(self.heads()) + 1
 
     def clone(self, remote, heads=[], stream=False):
         '''clone remote repository.
 
         keyword arguments:
         heads: list of revs to clone (forces use of pull)
         stream: use streaming clone if possible'''
 
         # now, all clients that can request uncompressed clones can
         # read repo formats supported by all servers that can serve
         # them.
 
         # if revlog format changes, client will have to check version
         # and format flags on "stream" capability, and use
         # uncompressed only if compatible.
 
         if stream and not heads:
             # 'stream' means remote revlog format is revlogv1 only
             if remote.capable('stream'):
                 return self.stream_in(remote, set(('revlogv1',)))
             # otherwise, 'streamreqs' contains the remote revlog format
             streamreqs = remote.capable('streamreqs')
             if streamreqs:
                 streamreqs = set(streamreqs.split(','))
                 # if we support it, stream in and adjust our requirements
                 if not streamreqs - self.supportedformats:
                     return self.stream_in(remote, streamreqs)
         return self.pull(remote, heads)
 
     def pushkey(self, namespace, key, old, new):
         return pushkey.push(self, namespace, key, old, new)
 
     def listkeys(self, namespace):
         return pushkey.list(self, namespace)
 
 # used to avoid circular references so destructors work
 def aftertrans(files):
     renamefiles = [tuple(t) for t in files]
     def a():
         for src, dest in renamefiles:
             util.rename(src, dest)
     return a
 
 def instance(ui, path, create):
     return localrepository(ui, util.drop_scheme('file', path), create)
 
 def islocal(path):
     return True

mercurial/revlog.py

@@ -1,1481 +1,1484 b''
 # revlog.py - storage back-end for mercurial
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 """Storage back-end for Mercurial.
 
 This provides efficient delta storage with O(1) retrieve and append
 and O(changes) merge between branches.
 """
 
 # import stuff from node for others to import from revlog
 from node import bin, hex, nullid, nullrev, short #@UnusedImport
 from i18n import _
 import changegroup, ancestor, mdiff, parsers, error, util
 import struct, zlib, errno
 
 _pack = struct.pack
 _unpack = struct.unpack
 _compress = zlib.compress
 _decompress = zlib.decompress
 _sha = util.sha1
 
 # revlog header flags
 REVLOGV0 = 0
 REVLOGNG = 1
 REVLOGNGINLINEDATA = (1 << 16)
 REVLOGSHALLOW = (1 << 17)
 REVLOG_DEFAULT_FLAGS = REVLOGNGINLINEDATA
 REVLOG_DEFAULT_FORMAT = REVLOGNG
 REVLOG_DEFAULT_VERSION = REVLOG_DEFAULT_FORMAT | REVLOG_DEFAULT_FLAGS
 REVLOGNG_FLAGS = REVLOGNGINLINEDATA | REVLOGSHALLOW
 
 # revlog index flags
 REVIDX_PARENTDELTA  = 1
 REVIDX_PUNCHED_FLAG = 2
 REVIDX_KNOWN_FLAGS = REVIDX_PUNCHED_FLAG | REVIDX_PARENTDELTA
 
 # amount of data read unconditionally, should be >= 4
 # when not inline: threshold for using lazy index
 _prereadsize = 1048576
 # max size of revlog with inline data
 _maxinline = 131072
 
 RevlogError = error.RevlogError
 LookupError = error.LookupError
 
 def getoffset(q):
     return int(q >> 16)
 
 def gettype(q):
     return int(q & 0xFFFF)
 
 def offset_type(offset, type):
     return long(long(offset) << 16 | type)
 
 nullhash = _sha(nullid)
 
 def hash(text, p1, p2):
     """generate a hash from the given text and its parent hashes
 
     This hash combines both the current file contents and its history
     in a manner that makes it easy to distinguish nodes with the same
     content in the revision graph.
     """
     # As of now, if one of the parent node is null, p2 is null
     if p2 == nullid:
         # deep copy of a hash is faster than creating one
         s = nullhash.copy()
         s.update(p1)
     else:
         # none of the parent nodes are nullid
         l = [p1, p2]
         l.sort()
         s = _sha(l[0])
         s.update(l[1])
     s.update(text)
     return s.digest()
 
 def compress(text):
     """ generate a possibly-compressed representation of text """
     if not text:
         return ("", text)
     l = len(text)
     bin = None
     if l < 44:
         pass
     elif l > 1000000:
         # zlib makes an internal copy, thus doubling memory usage for
         # large files, so lets do this in pieces
         z = zlib.compressobj()
         p = []
         pos = 0
         while pos < l:
             pos2 = pos + 2**20
             p.append(z.compress(text[pos:pos2]))
             pos = pos2
         p.append(z.flush())
         if sum(map(len, p)) < l:
             bin = "".join(p)
     else:
         bin = _compress(text)
     if bin is None or len(bin) > l:
         if text[0] == '\0':
             return ("", text)
         return ('u', text)
     return ("", bin)
 
 def decompress(bin):
     """ decompress the given input """
     if not bin:
         return bin
     t = bin[0]
     if t == '\0':
         return bin
     if t == 'x':
         return _decompress(bin)
     if t == 'u':
         return bin[1:]
     raise RevlogError(_("unknown compression type %r") % t)
 
 class lazyparser(object):
     """
     this class avoids the need to parse the entirety of large indices
     """
 
     # lazyparser is not safe to use on windows if win32 extensions not
     # available. it keeps file handle open, which make it not possible
     # to break hardlinks on local cloned repos.
 
     def __init__(self, dataf):
         try:
             size = util.fstat(dataf).st_size
         except AttributeError:
             size = 0
         self.dataf = dataf
         self.s = struct.calcsize(indexformatng)
         self.datasize = size
         self.l = size // self.s
         self.index = [None] * self.l
         self.map = {nullid: nullrev}
         self.allmap = 0
         self.all = 0
         self.mapfind_count = 0
 
     def loadmap(self):
         """
         during a commit, we need to make sure the rev being added is
         not a duplicate.  This requires loading the entire index,
         which is fairly slow.  loadmap can load up just the node map,
         which takes much less time.
         """
         if self.allmap:
             return
         end = self.datasize
         self.allmap = 1
         cur = 0
         count = 0
         blocksize = self.s * 256
         self.dataf.seek(0)
         while cur < end:
             data = self.dataf.read(blocksize)
             off = 0
             for x in xrange(256):
                 n = data[off + ngshaoffset:off + ngshaoffset + 20]
                 self.map[n] = count
                 count += 1
                 if count >= self.l:
                     break
                 off += self.s
             cur += blocksize
 
     def loadblock(self, blockstart, blocksize, data=None):
         if self.all:
             return
         if data is None:
             self.dataf.seek(blockstart)
             if blockstart + blocksize > self.datasize:
                 # the revlog may have grown since we've started running,
                 # but we don't have space in self.index for more entries.
                 # limit blocksize so that we don't get too much data.
                 blocksize = max(self.datasize - blockstart, 0)
             data = self.dataf.read(blocksize)
         lend = len(data) // self.s
         i = blockstart // self.s
         off = 0
         # lazyindex supports __delitem__
         if lend > len(self.index) - i:
             lend = len(self.index) - i
         for x in xrange(lend):
             if self.index[i + x] is None:
                 b = data[off : off + self.s]
                 self.index[i + x] = b
                 n = b[ngshaoffset:ngshaoffset + 20]
                 self.map[n] = i + x
             off += self.s
 
     def findnode(self, node):
         """search backwards through the index file for a specific node"""
         if self.allmap:
             return None
 
         # hg log will cause many many searches for the manifest
         # nodes.  After we get called a few times, just load the whole
         # thing.
         if self.mapfind_count > 8:
             self.loadmap()
             if node in self.map:
                 return node
             return None
         self.mapfind_count += 1
         last = self.l - 1
         while self.index[last] != None:
             if last == 0:
                 self.all = 1
                 self.allmap = 1
                 return None
             last -= 1
         end = (last + 1) * self.s
         blocksize = self.s * 256
         while end >= 0:
             start = max(end - blocksize, 0)
             self.dataf.seek(start)
             data = self.dataf.read(end - start)
             findend = end - start
             while True:
                 # we're searching backwards, so we have to make sure
                 # we don't find a changeset where this node is a parent
                 off = data.find(node, 0, findend)
                 findend = off
                 if off >= 0:
                     i = off / self.s
                     off = i * self.s
                     n = data[off + ngshaoffset:off + ngshaoffset + 20]
                     if n == node:
                         self.map[n] = i + start / self.s
                         return node
                 else:
                     break
             end -= blocksize
         return None
 
     def loadindex(self, i=None, end=None):
         if self.all:
             return
         all = False
         if i is None:
             blockstart = 0
             blocksize = (65536 / self.s) * self.s
             end = self.datasize
             all = True
         else:
             if end:
                 blockstart = i * self.s
                 end = end * self.s
                 blocksize = end - blockstart
             else:
                 blockstart = (i & ~1023) * self.s
                 blocksize = self.s * 1024
                 end = blockstart + blocksize
         while blockstart < end:
             self.loadblock(blockstart, blocksize)
             blockstart += blocksize
         if all:
             self.all = True
 
 class lazyindex(object):
     """a lazy version of the index array"""
     def __init__(self, parser):
         self.p = parser
     def __len__(self):
         return len(self.p.index)
     def load(self, pos):
         if pos < 0:
             pos += len(self.p.index)
         self.p.loadindex(pos)
         return self.p.index[pos]
     def __getitem__(self, pos):
         return _unpack(indexformatng, self.p.index[pos] or self.load(pos))
     def __setitem__(self, pos, item):
         self.p.index[pos] = _pack(indexformatng, *item)
     def __delitem__(self, pos):
         del self.p.index[pos]
     def insert(self, pos, e):
         self.p.index.insert(pos, _pack(indexformatng, *e))
     def append(self, e):
         self.p.index.append(_pack(indexformatng, *e))
 
 class lazymap(object):
     """a lazy version of the node map"""
     def __init__(self, parser):
         self.p = parser
     def load(self, key):
         n = self.p.findnode(key)
         if n is None:
             raise KeyError(key)
     def __contains__(self, key):
         if key in self.p.map:
             return True
         self.p.loadmap()
         return key in self.p.map
     def __iter__(self):
         yield nullid
         for i, ret in enumerate(self.p.index):
             if not ret:
                 self.p.loadindex(i)
                 ret = self.p.index[i]
             if isinstance(ret, str):
                 ret = _unpack(indexformatng, ret)
             yield ret[7]
     def __getitem__(self, key):
         try:
             return self.p.map[key]
         except KeyError:
             try:
                 self.load(key)
                 return self.p.map[key]
             except KeyError:
                 raise KeyError("node " + hex(key))
     def __setitem__(self, key, val):
         self.p.map[key] = val
     def __delitem__(self, key):
         del self.p.map[key]
 
 indexformatv0 = ">4l20s20s20s"
 v0shaoffset = 56
 
 class revlogoldio(object):
     def __init__(self):
         self.size = struct.calcsize(indexformatv0)
 
     def parseindex(self, fp, data, inline):
         s = self.size
         index = []
         nodemap =  {nullid: nullrev}
         n = off = 0
         if len(data) == _prereadsize:
             data += fp.read() # read the rest
         l = len(data)
         while off + s <= l:
             cur = data[off:off + s]
             off += s
             e = _unpack(indexformatv0, cur)
             # transform to revlogv1 format
             e2 = (offset_type(e[0], 0), e[1], -1, e[2], e[3],
                   nodemap.get(e[4], nullrev), nodemap.get(e[5], nullrev), e[6])
             index.append(e2)
             nodemap[e[6]] = n
             n += 1
 
         return index, nodemap, None
 
     def packentry(self, entry, node, version, rev):
         if gettype(entry[0]):
             raise RevlogError(_("index entry flags need RevlogNG"))
         e2 = (getoffset(entry[0]), entry[1], entry[3], entry[4],
               node(entry[5]), node(entry[6]), entry[7])
         return _pack(indexformatv0, *e2)
 
 # index ng:
 #  6 bytes: offset
 #  2 bytes: flags
 #  4 bytes: compressed length
 #  4 bytes: uncompressed length
 #  4 bytes: base rev
 #  4 bytes: link rev
 #  4 bytes: parent 1 rev
 #  4 bytes: parent 2 rev
 # 32 bytes: nodeid
 indexformatng = ">Qiiiiii20s12x"
 ngshaoffset = 32
 versionformat = ">I"
 
 class revlogio(object):
     def __init__(self):
         self.size = struct.calcsize(indexformatng)
 
     def parseindex(self, fp, data, inline):
         if len(data) == _prereadsize:
             if util.openhardlinks() and not inline:
                 # big index, let's parse it on demand
                 parser = lazyparser(fp)
                 index = lazyindex(parser)
                 nodemap = lazymap(parser)
                 e = list(index[0])
                 type = gettype(e[0])
                 e[0] = offset_type(0, type)
                 index[0] = e
                 return index, nodemap, None
             else:
                 data += fp.read()
 
         # call the C implementation to parse the index data
         index, nodemap, cache = parsers.parse_index(data, inline)
         return index, nodemap, cache
 
     def packentry(self, entry, node, version, rev):
         p = _pack(indexformatng, *entry)
         if rev == 0:
             p = _pack(versionformat, version) + p[4:]
         return p
 
 class revlog(object):
     """
     the underlying revision storage object
 
     A revlog consists of two parts, an index and the revision data.
 
     The index is a file with a fixed record size containing
     information on each revision, including its nodeid (hash), the
     nodeids of its parents, the position and offset of its data within
     the data file, and the revision it's based on. Finally, each entry
     contains a linkrev entry that can serve as a pointer to external
     data.
 
     The revision data itself is a linear collection of data chunks.
     Each chunk represents a revision and is usually represented as a
     delta against the previous chunk. To bound lookup time, runs of
     deltas are limited to about 2 times the length of the original
     version data. This makes retrieval of a version proportional to
     its size, or O(1) relative to the number of revisions.
 
     Both pieces of the revlog are written to in an append-only
     fashion, which means we never need to rewrite a file to insert or
     remove data, and can use some simple techniques to avoid the need
     for locking while reading.
     """
     def __init__(self, opener, indexfile, shallowroot=None):
         """
         create a revlog object
 
         opener is a function that abstracts the file opening operation
         and can be used to implement COW semantics or the like.
         """
         self.indexfile = indexfile
         self.datafile = indexfile[:-2] + ".d"
         self.opener = opener
         self._cache = None
         self._chunkcache = (0, '')
         self.nodemap = {nullid: nullrev}
         self.index = []
         self._shallowroot = shallowroot
         self._parentdelta = 0
 
         v = REVLOG_DEFAULT_VERSION
         if hasattr(opener, 'options') and 'defversion' in opener.options:
             v = opener.options['defversion']
             if v & REVLOGNG:
                 v |= REVLOGNGINLINEDATA
             if v & REVLOGNG and 'parentdelta' in opener.options:
                 self._parentdelta = 1
 
         if shallowroot:
             v |= REVLOGSHALLOW
 
         i = ''
         try:
             f = self.opener(self.indexfile)
             if "nonlazy" in getattr(self.opener, 'options', {}):
                 i = f.read()
             else:
                 i = f.read(_prereadsize)
             if len(i) > 0:
                 v = struct.unpack(versionformat, i[:4])[0]
         except IOError, inst:
             if inst.errno != errno.ENOENT:
                 raise
 
         self.version = v
         self._inline = v & REVLOGNGINLINEDATA
         self._shallow = v & REVLOGSHALLOW
         flags = v & ~0xFFFF
         fmt = v & 0xFFFF
         if fmt == REVLOGV0 and flags:
             raise RevlogError(_("index %s unknown flags %#04x for format v0")
                               % (self.indexfile, flags >> 16))
         elif fmt == REVLOGNG and flags & ~REVLOGNG_FLAGS:
             raise RevlogError(_("index %s unknown flags %#04x for revlogng")
                               % (self.indexfile, flags >> 16))
         elif fmt > REVLOGNG:
             raise RevlogError(_("index %s unknown format %d")
                               % (self.indexfile, fmt))
 
         self._io = revlogio()
         if self.version == REVLOGV0:
             self._io = revlogoldio()
         if i:
             try:
                 d = self._io.parseindex(f, i, self._inline)
             except (ValueError, IndexError):
                 raise RevlogError(_("index %s is corrupted") % (self.indexfile))
             self.index, self.nodemap, self._chunkcache = d
             if not self._chunkcache:
                 self._chunkclear()
 
         # add the magic null revision at -1 (if it hasn't been done already)
         if (self.index == [] or isinstance(self.index, lazyindex) or
             self.index[-1][7] != nullid) :
             self.index.append((0, 0, 0, -1, -1, -1, -1, nullid))
 
     def _loadindex(self, start, end):
         """load a block of indexes all at once from the lazy parser"""
         if isinstance(self.index, lazyindex):
             self.index.p.loadindex(start, end)
 
     def _loadindexmap(self):
         """loads both the map and the index from the lazy parser"""
         if isinstance(self.index, lazyindex):
             p = self.index.p
             p.loadindex()
             self.nodemap = p.map
 
     def _loadmap(self):
         """loads the map from the lazy parser"""
         if isinstance(self.nodemap, lazymap):
             self.nodemap.p.loadmap()
             self.nodemap = self.nodemap.p.map
 
     def tip(self):
         return self.node(len(self.index) - 2)
     def __len__(self):
         return len(self.index) - 1
     def __iter__(self):
         for i in xrange(len(self)):
             yield i
     def rev(self, node):
         try:
             return self.nodemap[node]
         except KeyError:
             raise LookupError(node, self.indexfile, _('no node'))
     def node(self, rev):
         return self.index[rev][7]
     def linkrev(self, rev):
         return self.index[rev][4]
     def parents(self, node):
         i = self.index
         d = i[self.rev(node)]
         return i[d[5]][7], i[d[6]][7] # map revisions to nodes inline
     def parentrevs(self, rev):
         return self.index[rev][5:7]
     def start(self, rev):
         return int(self.index[rev][0] >> 16)
     def end(self, rev):
         return self.start(rev) + self.length(rev)
     def length(self, rev):
         return self.index[rev][1]
     def base(self, rev):
         return self.index[rev][3]
     def flags(self, rev):
         return self.index[rev][0] & 0xFFFF
     def rawsize(self, rev):
         """return the length of the uncompressed text for a given revision"""
         l = self.index[rev][2]
         if l >= 0:
             return l
 
         t = self.revision(self.node(rev))
         return len(t)
     size = rawsize
 
     def reachable(self, node, stop=None):
         """return the set of all nodes ancestral to a given node, including
          the node itself, stopping when stop is matched"""
         reachable = set((node,))
         visit = [node]
         if stop:
             stopn = self.rev(stop)
         else:
             stopn = 0
         while visit:
             n = visit.pop(0)
             if n == stop:
                 continue
             if n == nullid:
                 continue
             for p in self.parents(n):
                 if self.rev(p) < stopn:
                     continue
                 if p not in reachable:
                     reachable.add(p)
                     visit.append(p)
         return reachable
 
     def ancestors(self, *revs):
         """Generate the ancestors of 'revs' in reverse topological order.
 
         Yield a sequence of revision numbers starting with the parents
         of each revision in revs, i.e., each revision is *not* considered
         an ancestor of itself.  Results are in breadth-first order:
         parents of each rev in revs, then parents of those, etc.  Result
         does not include the null revision."""
         visit = list(revs)
         seen = set([nullrev])
         while visit:
             for parent in self.parentrevs(visit.pop(0)):
                 if parent not in seen:
                     visit.append(parent)
                     seen.add(parent)
                     yield parent
 
     def descendants(self, *revs):
         """Generate the descendants of 'revs' in revision order.
 
         Yield a sequence of revision numbers starting with a child of
         some rev in revs, i.e., each revision is *not* considered a
         descendant of itself.  Results are ordered by revision number (a
         topological sort)."""
         seen = set(revs)
         for i in xrange(min(revs) + 1, len(self)):
             for x in self.parentrevs(i):
                 if x != nullrev and x in seen:
                     seen.add(i)
                     yield i
                     break
 
     def findmissing(self, common=None, heads=None):
         """Return the ancestors of heads that are not ancestors of common.
 
         More specifically, return a list of nodes N such that every N
         satisfies the following constraints:
 
           1. N is an ancestor of some node in 'heads'
           2. N is not an ancestor of any node in 'common'
 
         The list is sorted by revision number, meaning it is
         topologically sorted.
 
         'heads' and 'common' are both lists of node IDs.  If heads is
         not supplied, uses all of the revlog's heads.  If common is not
         supplied, uses nullid."""
         if common is None:
             common = [nullid]
         if heads is None:
             heads = self.heads()
 
         common = [self.rev(n) for n in common]
         heads = [self.rev(n) for n in heads]
 
         # we want the ancestors, but inclusive
         has = set(self.ancestors(*common))
         has.add(nullrev)
         has.update(common)
 
         # take all ancestors from heads that aren't in has
         missing = set()
         visit = [r for r in heads if r not in has]
         while visit:
             r = visit.pop(0)
             if r in missing:
                 continue
             else:
                 missing.add(r)
                 for p in self.parentrevs(r):
                     if p not in has:
                         visit.append(p)
         missing = list(missing)
         missing.sort()
         return [self.node(r) for r in missing]
 
     def nodesbetween(self, roots=None, heads=None):
         """Return a topological path from 'roots' to 'heads'.
 
         Return a tuple (nodes, outroots, outheads) where 'nodes' is a
         topologically sorted list of all nodes N that satisfy both of
         these constraints:
 
           1. N is a descendant of some node in 'roots'
           2. N is an ancestor of some node in 'heads'
 
         Every node is considered to be both a descendant and an ancestor
         of itself, so every reachable node in 'roots' and 'heads' will be
         included in 'nodes'.
 
         'outroots' is the list of reachable nodes in 'roots', i.e., the
         subset of 'roots' that is returned in 'nodes'.  Likewise,
         'outheads' is the subset of 'heads' that is also in 'nodes'.
 
         'roots' and 'heads' are both lists of node IDs.  If 'roots' is
         unspecified, uses nullid as the only root.  If 'heads' is
         unspecified, uses list of all of the revlog's heads."""
         nonodes = ([], [], [])
         if roots is not None:
             roots = list(roots)
             if not roots:
                 return nonodes
             lowestrev = min([self.rev(n) for n in roots])
         else:
             roots = [nullid] # Everybody's a descendent of nullid
             lowestrev = nullrev
         if (lowestrev == nullrev) and (heads is None):
             # We want _all_ the nodes!
             return ([self.node(r) for r in self], [nullid], list(self.heads()))
         if heads is None:
             # All nodes are ancestors, so the latest ancestor is the last
             # node.
             highestrev = len(self) - 1
             # Set ancestors to None to signal that every node is an ancestor.
             ancestors = None
             # Set heads to an empty dictionary for later discovery of heads
             heads = {}
         else:
             heads = list(heads)
             if not heads:
                 return nonodes
             ancestors = set()
             # Turn heads into a dictionary so we can remove 'fake' heads.
             # Also, later we will be using it to filter out the heads we can't
             # find from roots.
             heads = dict.fromkeys(heads, 0)
             # Start at the top and keep marking parents until we're done.
             nodestotag = set(heads)
             # Remember where the top was so we can use it as a limit later.
             highestrev = max([self.rev(n) for n in nodestotag])
             while nodestotag:
                 # grab a node to tag
                 n = nodestotag.pop()
                 # Never tag nullid
                 if n == nullid:
                     continue
                 # A node's revision number represents its place in a
                 # topologically sorted list of nodes.
                 r = self.rev(n)
                 if r >= lowestrev:
                     if n not in ancestors:
                         # If we are possibly a descendent of one of the roots
                         # and we haven't already been marked as an ancestor
                         ancestors.add(n) # Mark as ancestor
                         # Add non-nullid parents to list of nodes to tag.
                         nodestotag.update([p for p in self.parents(n) if
                                            p != nullid])
                     elif n in heads: # We've seen it before, is it a fake head?
                         # So it is, real heads should not be the ancestors of
                         # any other heads.
                         heads.pop(n)
             if not ancestors:
                 return nonodes
             # Now that we have our set of ancestors, we want to remove any
             # roots that are not ancestors.
 
             # If one of the roots was nullid, everything is included anyway.
             if lowestrev > nullrev:
                 # But, since we weren't, let's recompute the lowest rev to not
                 # include roots that aren't ancestors.
 
                 # Filter out roots that aren't ancestors of heads
                 roots = [n for n in roots if n in ancestors]
                 # Recompute the lowest revision
                 if roots:
                     lowestrev = min([self.rev(n) for n in roots])
                 else:
                     # No more roots?  Return empty list
                     return nonodes
             else:
                 # We are descending from nullid, and don't need to care about
                 # any other roots.
                 lowestrev = nullrev
                 roots = [nullid]
         # Transform our roots list into a set.
         descendents = set(roots)
         # Also, keep the original roots so we can filter out roots that aren't
         # 'real' roots (i.e. are descended from other roots).
         roots = descendents.copy()
         # Our topologically sorted list of output nodes.
         orderedout = []
         # Don't start at nullid since we don't want nullid in our output list,
         # and if nullid shows up in descedents, empty parents will look like
         # they're descendents.
         for r in xrange(max(lowestrev, 0), highestrev + 1):
             n = self.node(r)
             isdescendent = False
             if lowestrev == nullrev:  # Everybody is a descendent of nullid
                 isdescendent = True
             elif n in descendents:
                 # n is already a descendent
                 isdescendent = True
                 # This check only needs to be done here because all the roots
                 # will start being marked is descendents before the loop.
                 if n in roots:
                     # If n was a root, check if it's a 'real' root.
                     p = tuple(self.parents(n))
                     # If any of its parents are descendents, it's not a root.
                     if (p[0] in descendents) or (p[1] in descendents):
                         roots.remove(n)
             else:
                 p = tuple(self.parents(n))
                 # A node is a descendent if either of its parents are
                 # descendents.  (We seeded the dependents list with the roots
                 # up there, remember?)
                 if (p[0] in descendents) or (p[1] in descendents):
                     descendents.add(n)
                     isdescendent = True
             if isdescendent and ((ancestors is None) or (n in ancestors)):
                 # Only include nodes that are both descendents and ancestors.
                 orderedout.append(n)
                 if (ancestors is not None) and (n in heads):
                     # We're trying to figure out which heads are reachable
                     # from roots.
                     # Mark this head as having been reached
                     heads[n] = 1
                 elif ancestors is None:
                     # Otherwise, we're trying to discover the heads.
                     # Assume this is a head because if it isn't, the next step
                     # will eventually remove it.
                     heads[n] = 1
                     # But, obviously its parents aren't.
                     for p in self.parents(n):
                         heads.pop(p, None)
         heads = [n for n in heads.iterkeys() if heads[n] != 0]
         roots = list(roots)
         assert orderedout
         assert roots
         assert heads
         return (orderedout, roots, heads)
 
     def heads(self, start=None, stop=None):
         """return the list of all nodes that have no children
 
         if start is specified, only heads that are descendants of
         start will be returned
         if stop is specified, it will consider all the revs from stop
         as if they had no children
         """
         if start is None and stop is None:
             count = len(self)
             if not count:
                 return [nullid]
             ishead = [1] * (count + 1)
             index = self.index
             for r in xrange(count):
                 e = index[r]
                 ishead[e[5]] = ishead[e[6]] = 0
             return [self.node(r) for r in xrange(count) if ishead[r]]
 
         if start is None:
             start = nullid
         if stop is None:
             stop = []
         stoprevs = set([self.rev(n) for n in stop])
         startrev = self.rev(start)
         reachable = set((startrev,))
         heads = set((startrev,))
 
         parentrevs = self.parentrevs
         for r in xrange(startrev + 1, len(self)):
             for p in parentrevs(r):
                 if p in reachable:
                     if r not in stoprevs:
                         reachable.add(r)
                     heads.add(r)
                 if p in heads and p not in stoprevs:
                     heads.remove(p)
 
         return [self.node(r) for r in heads]
 
     def children(self, node):
         """find the children of a given node"""
         c = []
         p = self.rev(node)
         for r in range(p + 1, len(self)):
             prevs = [pr for pr in self.parentrevs(r) if pr != nullrev]
             if prevs:
                 for pr in prevs:
                     if pr == p:
                         c.append(self.node(r))
             elif p == nullrev:
                 c.append(self.node(r))
         return c
 
     def descendant(self, start, end):
         for i in self.descendants(start):
             if i == end:
                 return True
             elif i > end:
                 break
         return False
 
     def ancestor(self, a, b):
         """calculate the least common ancestor of nodes a and b"""
 
         # fast path, check if it is a descendant
         a, b = self.rev(a), self.rev(b)
         start, end = sorted((a, b))
         if self.descendant(start, end):
             return self.node(start)
 
         def parents(rev):
             return [p for p in self.parentrevs(rev) if p != nullrev]
 
         c = ancestor.ancestor(a, b, parents)
         if c is None:
             return nullid
 
         return self.node(c)
 
     def _match(self, id):
         if isinstance(id, (long, int)):
             # rev
             return self.node(id)
         if len(id) == 20:
             # possibly a binary node
             # odds of a binary node being all hex in ASCII are 1 in 10**25
             try:
                 node = id
                 self.rev(node) # quick search the index
                 return node
             except LookupError:
                 pass # may be partial hex id
         try:
             # str(rev)
             rev = int(id)
             if str(rev) != id:
                 raise ValueError
             if rev < 0:
                 rev = len(self) + rev
             if rev < 0 or rev >= len(self):
                 raise ValueError
             return self.node(rev)
         except (ValueError, OverflowError):
             pass
         if len(id) == 40:
             try:
                 # a full hex nodeid?
                 node = bin(id)
                 self.rev(node)
                 return node
             except (TypeError, LookupError):
                 pass
 
     def _partialmatch(self, id):
         if len(id) < 40:
             try:
                 # hex(node)[:...]
                 l = len(id) // 2  # grab an even number of digits
                 bin_id = bin(id[:l * 2])
                 nl = [n for n in self.nodemap if n[:l] == bin_id]
                 nl = [n for n in nl if hex(n).startswith(id)]
                 if len(nl) > 0:
                     if len(nl) == 1:
                         return nl[0]
                     raise LookupError(id, self.indexfile,
                                       _('ambiguous identifier'))
                 return None
             except TypeError:
                 pass
 
     def lookup(self, id):
         """locate a node based on:
             - revision number or str(revision number)
             - nodeid or subset of hex nodeid
         """
         n = self._match(id)
         if n is not None:
             return n
         n = self._partialmatch(id)
         if n:
             return n
 
         raise LookupError(id, self.indexfile, _('no match found'))
 
     def cmp(self, node, text):
         """compare text with a given file revision
 
         returns True if text is different than what is stored.
         """
         p1, p2 = self.parents(node)
         return hash(text, p1, p2) != node
 
     def _addchunk(self, offset, data):
         o, d = self._chunkcache
         # try to add to existing cache
         if o + len(d) == offset and len(d) + len(data) < _prereadsize:
             self._chunkcache = o, d + data
         else:
             self._chunkcache = offset, data
 
     def _loadchunk(self, offset, length):
         if self._inline:
             df = self.opener(self.indexfile)
         else:
             df = self.opener(self.datafile)
 
         readahead = max(65536, length)
         df.seek(offset)
         d = df.read(readahead)
         self._addchunk(offset, d)
         if readahead > length:
             return d[:length]
         return d
 
     def _getchunk(self, offset, length):
         o, d = self._chunkcache
         l = len(d)
 
         # is it in the cache?
         cachestart = offset - o
         cacheend = cachestart + length
         if cachestart >= 0 and cacheend <= l:
             if cachestart == 0 and cacheend == l:
                 return d # avoid a copy
             return d[cachestart:cacheend]
 
         return self._loadchunk(offset, length)
 
     def _chunkraw(self, startrev, endrev):
         start = self.start(startrev)
         length = self.end(endrev) - start
         if self._inline:
             start += (startrev + 1) * self._io.size
         return self._getchunk(start, length)
 
     def _chunk(self, rev):
         return decompress(self._chunkraw(rev, rev))
 
     def _chunkclear(self):
         self._chunkcache = (0, '')
 
     def deltaparent(self, rev):
         """return previous revision or parentrev according to flags"""
         if self.flags(rev) & REVIDX_PARENTDELTA:
             return self.parentrevs(rev)[0]
         else:
             return rev - 1
 
     def revdiff(self, rev1, rev2):
         """return or calculate a delta between two revisions"""
         if self.base(rev2) != rev2 and self.deltaparent(rev2) == rev1:
             return self._chunk(rev2)
 
         return mdiff.textdiff(self.revision(self.node(rev1)),
                               self.revision(self.node(rev2)))
 
     def revision(self, node):
         """return an uncompressed revision of a given node"""
         cachedrev = None
         if node == nullid:
             return ""
         if self._cache:
             if self._cache[0] == node:
                 return self._cache[2]
             cachedrev = self._cache[1]
 
         # look up what we need to read
         text = None
         rev = self.rev(node)
         base = self.base(rev)
 
         # check rev flags
         if self.flags(rev) & ~REVIDX_KNOWN_FLAGS:
             raise RevlogError(_('incompatible revision flag %x') %
                               (self.flags(rev) & ~REVIDX_KNOWN_FLAGS))
 
         # build delta chain
         self._loadindex(base, rev + 1)
         chain = []
         index = self.index # for performance
         iterrev = rev
         e = index[iterrev]
         while iterrev != base and iterrev != cachedrev:
             chain.append(iterrev)
             if e[0] & REVIDX_PARENTDELTA:
                 iterrev = e[5]
             else:
                 iterrev -= 1
             e = index[iterrev]
         chain.reverse()
         base = iterrev
 
         if iterrev == cachedrev:
             # cache hit
             text = self._cache[2]
 
         # drop cache to save memory
         self._cache = None
 
         self._chunkraw(base, rev)
         if text is None:
             text = self._chunk(base)
 
         bins = [self._chunk(r) for r in chain]
         text = mdiff.patches(text, bins)
         p1, p2 = self.parents(node)
         if (node != hash(text, p1, p2) and
             not (self.flags(rev) & REVIDX_PUNCHED_FLAG)):
             raise RevlogError(_("integrity check failed on %s:%d")
                               % (self.indexfile, rev))
 
         self._cache = (node, rev, text)
         return text
 
     def checkinlinesize(self, tr, fp=None):
         if not self._inline or (self.start(-2) + self.length(-2)) < _maxinline:
             return
 
         trinfo = tr.find(self.indexfile)
         if trinfo is None:
             raise RevlogError(_("%s not found in the transaction")
                               % self.indexfile)
 
         trindex = trinfo[2]
         dataoff = self.start(trindex)
 
         tr.add(self.datafile, dataoff)
 
         if fp:
             fp.flush()
             fp.close()
 
         df = self.opener(self.datafile, 'w')
         try:
             for r in self:
                 df.write(self._chunkraw(r, r))
         finally:
             df.close()
 
         fp = self.opener(self.indexfile, 'w', atomictemp=True)
         self.version &= ~(REVLOGNGINLINEDATA)
         self._inline = False
         for i in self:
             e = self._io.packentry(self.index[i], self.node, self.version, i)
             fp.write(e)
 
         # if we don't call rename, the temp file will never replace the
         # real index
         fp.rename()
 
         tr.replace(self.indexfile, trindex * self._io.size)
         self._chunkclear()
 
     def addrevision(self, text, transaction, link, p1, p2, cachedelta=None):
         """add a revision to the log
 
         text - the revision data to add
         transaction - the transaction object used for rollback
         link - the linkrev data to add
         p1, p2 - the parent nodeids of the revision
         cachedelta - an optional precomputed delta
         """
         node = hash(text, p1, p2)
         if (node in self.nodemap and
             (not self.flags(self.rev(node)) & REVIDX_PUNCHED_FLAG)):
             return node
 
         dfh = None
         if not self._inline:
             dfh = self.opener(self.datafile, "a")
         ifh = self.opener(self.indexfile, "a+")
         try:
             return self._addrevision(node, text, transaction, link, p1, p2,
                                      cachedelta, ifh, dfh)
         finally:
             if dfh:
                 dfh.close()
             ifh.close()
 
     def _addrevision(self, node, text, transaction, link, p1, p2,
                      cachedelta, ifh, dfh):
         curr = len(self)
         prev = curr - 1
         base = curr
         offset = self.end(prev)
         flags = 0
         d = None
 
         if self._parentdelta:
             deltarev, deltanode = self.rev(p1), p1
             flags = REVIDX_PARENTDELTA
         else:
             deltarev, deltanode = prev, self.node(prev)
 
         # should we try to build a delta?
         if deltarev != nullrev:
             # can we use the cached delta?
             if cachedelta:
                 cacherev, d = cachedelta
                 if cacherev != deltarev:
                     d = None
             if d is None:
                 ptext = self.revision(deltanode)
                 d = mdiff.textdiff(ptext, text)
             data = compress(d)
             l = len(data[1]) + len(data[0])
             base = self.base(deltarev)
             dist = l + offset - self.start(base)
 
         # full versions are inserted when the needed deltas
         # become comparable to the uncompressed text
         # or the base revision is punched
         if (d is None or dist > len(text) * 2 or
             (self.flags(base) & REVIDX_PUNCHED_FLAG)):
             data = compress(text)
             l = len(data[1]) + len(data[0])
             base = curr
 
         e = (offset_type(offset, flags), l, len(text),
              base, link, self.rev(p1), self.rev(p2), node)
         self.index.insert(-1, e)
         self.nodemap[node] = curr
 
         entry = self._io.packentry(e, self.node, self.version, curr)
         if not self._inline:
             transaction.add(self.datafile, offset)
             transaction.add(self.indexfile, curr * len(entry))
             if data[0]:
                 dfh.write(data[0])
             dfh.write(data[1])
             dfh.flush()
             ifh.write(entry)
         else:
             offset += curr * self._io.size
             transaction.add(self.indexfile, offset, curr)
             ifh.write(entry)
             ifh.write(data[0])
             ifh.write(data[1])
             self.checkinlinesize(transaction, ifh)
 
         if type(text) == str: # only accept immutable objects
             self._cache = (node, curr, text)
         return node
 
     def group(self, nodelist, lookup, infocollect=None, fullrev=False):
         """Calculate a delta group, yielding a sequence of changegroup chunks
         (strings).
 
         Given a list of changeset revs, return a set of deltas and
         metadata corresponding to nodes. The first delta is
         first parent(nodelist[0]) -> nodelist[0], the receiver is
         guaranteed to have this parent as it has all history before
         these changesets. In the case firstparent is nullrev the
         changegroup starts with a full revision.
         fullrev forces the insertion of the full revision, necessary
         in the case of shallow clones where the first parent might
         not exist at the reciever.
         """
 
         revs = [self.rev(n) for n in nodelist]
 
         # if we don't have any revisions touched by these changesets, bail
         if not revs:
             yield changegroup.closechunk()
             return
 
         # add the parent of the first rev
         p = self.parentrevs(revs[0])[0]
         revs.insert(0, p)
         if p == nullrev:
             fullrev = True
 
         # build deltas
         for d in xrange(len(revs) - 1):
             a, b = revs[d], revs[d + 1]
             nb = self.node(b)
 
             if infocollect is not None:
                 infocollect(nb)
 
             p = self.parents(nb)
             meta = nb + p[0] + p[1] + lookup(nb)
             if fullrev:
                 d = self.revision(nb)
                 meta += mdiff.trivialdiffheader(len(d))
                 fullrev = False
             else:
                 d = self.revdiff(a, b)
             yield changegroup.chunkheader(len(meta) + len(d))
             yield meta
             yield d
 
         yield changegroup.closechunk()
 
-    def addgroup(self, revs, linkmapper, transaction):
+    def addgroup(self, bundle, linkmapper, transaction):
         """
         add a delta group
 
         given a set of deltas, add them to the revision log. the
         first delta is against its parent, which should be in our
         log, the rest are against the previous delta.
         """
 
         #track the base of the current delta log
         r = len(self)
         t = r - 1
         node = None
 
         base = prev = nullrev
         start = end = textlen = 0
         if r:
             end = self.end(t)
 
         ifh = self.opener(self.indexfile, "a+")
         isize = r * self._io.size
         if self._inline:
             transaction.add(self.indexfile, end + isize, r)
             dfh = None
         else:
             transaction.add(self.indexfile, isize, r)
             transaction.add(self.datafile, end)
             dfh = self.opener(self.datafile, "a")
 
         try:
             # loop through our set of deltas
             chain = None
-            for chunk in revs:
+            while 1:
+                chunk = bundle.chunk()
+                if not chunk:
+                    break
                 node, p1, p2, cs = struct.unpack("20s20s20s20s", chunk[:80])
                 link = linkmapper(cs)
                 if (node in self.nodemap and
                     (not self.flags(self.rev(node)) & REVIDX_PUNCHED_FLAG)):
                     # this can happen if two branches make the same change
                     chain = node
                     continue
                 delta = buffer(chunk, 80)
                 del chunk
 
                 for p in (p1, p2):
                     if not p in self.nodemap:
                         if self._shallow:
                             # add null entries for missing parents
                             if base == nullrev:
                                 base = len(self)
                             e = (offset_type(end, REVIDX_PUNCHED_FLAG),
                                  0, 0, base, nullrev, nullrev, nullrev, p)
                             self.index.insert(-1, e)
                             self.nodemap[p] = r
                             entry = self._io.packentry(e, self.node,
                                                        self.version, r)
                             ifh.write(entry)
                             t, r = r, r + 1
                         else:
                             raise LookupError(p, self.indexfile,
                                               _('unknown parent'))
 
                 if not chain:
                     # retrieve the parent revision of the delta chain
                     chain = p1
                     if not chain in self.nodemap:
                         raise LookupError(chain, self.indexfile, _('unknown base'))
 
                 # full versions are inserted when the needed deltas become
                 # comparable to the uncompressed text or when the previous
                 # version is not the one we have a delta against. We use
                 # the size of the previous full rev as a proxy for the
                 # current size.
 
                 if chain == prev:
                     cdelta = compress(delta)
                     cdeltalen = len(cdelta[0]) + len(cdelta[1])
                     textlen = mdiff.patchedsize(textlen, delta)
 
                 if chain != prev or (end - start + cdeltalen) > textlen * 2:
                     # flush our writes here so we can read it in revision
                     if dfh:
                         dfh.flush()
                     ifh.flush()
                     text = self.revision(chain)
                     text = mdiff.patch(text, delta)
                     del delta
                     chk = self._addrevision(node, text, transaction, link,
                                             p1, p2, None, ifh, dfh)
                     if not dfh and not self._inline:
                         # addrevision switched from inline to conventional
                         # reopen the index
                         dfh = self.opener(self.datafile, "a")
                         ifh = self.opener(self.indexfile, "a")
                     if chk != node:
                         raise RevlogError(_("consistency error adding group"))
                     textlen = len(text)
                 else:
                     e = (offset_type(end, 0), cdeltalen, textlen, base,
                          link, self.rev(p1), self.rev(p2), node)
                     self.index.insert(-1, e)
                     self.nodemap[node] = r
                     entry = self._io.packentry(e, self.node, self.version, r)
                     if self._inline:
                         ifh.write(entry)
                         ifh.write(cdelta[0])
                         ifh.write(cdelta[1])
                         self.checkinlinesize(transaction, ifh)
                         if not self._inline:
                             dfh = self.opener(self.datafile, "a")
                             ifh = self.opener(self.indexfile, "a")
                     else:
                         dfh.write(cdelta[0])
                         dfh.write(cdelta[1])
                         ifh.write(entry)
 
                 t, r, chain, prev = r, r + 1, node, node
                 base = self.base(t)
                 start = self.start(base)
                 end = self.end(t)
         finally:
             if dfh:
                 dfh.close()
             ifh.close()
 
         return node
 
     def strip(self, minlink, transaction):
         """truncate the revlog on the first revision with a linkrev >= minlink
 
         This function is called when we're stripping revision minlink and
         its descendants from the repository.
 
         We have to remove all revisions with linkrev >= minlink, because
         the equivalent changelog revisions will be renumbered after the
         strip.
 
         So we truncate the revlog on the first of these revisions, and
         trust that the caller has saved the revisions that shouldn't be
         removed and that it'll readd them after this truncation.
         """
         if len(self) == 0:
             return
 
         if isinstance(self.index, lazyindex):
             self._loadindexmap()
 
         for rev in self:
             if self.index[rev][4] >= minlink:
                 break
         else:
             return
 
         # first truncate the files on disk
         end = self.start(rev)
         if not self._inline:
             transaction.add(self.datafile, end)
             end = rev * self._io.size
         else:
             end += rev * self._io.size
 
         transaction.add(self.indexfile, end)
 
         # then reset internal state in memory to forget those revisions
         self._cache = None
         self._chunkclear()
         for x in xrange(rev, len(self)):
             del self.nodemap[self.node(x)]
 
         del self.index[rev:-1]
 
     def checksize(self):
         expected = 0
         if len(self):
             expected = max(0, self.end(len(self) - 1))
 
         try:
             f = self.opener(self.datafile)
             f.seek(0, 2)
             actual = f.tell()
             dd = actual - expected
         except IOError, inst:
             if inst.errno != errno.ENOENT:
                 raise
             dd = 0
 
         try:
             f = self.opener(self.indexfile)
             f.seek(0, 2)
             actual = f.tell()
             s = self._io.size
             i = max(0, actual // s)
             di = actual - (i * s)
             if self._inline:
                 databytes = 0
                 for r in self:
                     databytes += max(0, self.length(r))
                 dd = 0
                 di = actual - len(self) * s - databytes
         except IOError, inst:
             if inst.errno != errno.ENOENT:
                 raise
             di = 0
 
         return (dd, di)
 
     def files(self):
         res = [self.indexfile]
         if not self._inline:
             res.append(self.datafile)
         return res