py3: use bytearray() instead of array('c', ...) constructions

Portable from 2.6-3.6.

mercurial/branchmap.py

@@ -1,522 +1,520 b''
 # branchmap.py - logic to computes, maintain and stores branchmap for local repo
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import array
 import struct
 
 from .node import (
     bin,
     hex,
     nullid,
     nullrev,
 )
 from . import (
     encoding,
     error,
     scmutil,
     util,
 )
 
 array = array.array
 calcsize = struct.calcsize
 pack = struct.pack
 unpack = struct.unpack
 
 def _filename(repo):
     """name of a branchcache file for a given repo or repoview"""
     filename = "cache/branch2"
     if repo.filtername:
         filename = '%s-%s' % (filename, repo.filtername)
     return filename
 
 def read(repo):
     try:
         f = repo.vfs(_filename(repo))
         lines = f.read().split('\n')
         f.close()
     except (IOError, OSError):
         return None
 
     try:
         cachekey = lines.pop(0).split(" ", 2)
         last, lrev = cachekey[:2]
         last, lrev = bin(last), int(lrev)
         filteredhash = None
         if len(cachekey) > 2:
             filteredhash = bin(cachekey[2])
         partial = branchcache(tipnode=last, tiprev=lrev,
                               filteredhash=filteredhash)
         if not partial.validfor(repo):
             # invalidate the cache
             raise ValueError('tip differs')
         cl = repo.changelog
         for l in lines:
             if not l:
                 continue
             node, state, label = l.split(" ", 2)
             if state not in 'oc':
                 raise ValueError('invalid branch state')
             label = encoding.tolocal(label.strip())
             node = bin(node)
             if not cl.hasnode(node):
                 raise ValueError('node %s does not exist' % hex(node))
             partial.setdefault(label, []).append(node)
             if state == 'c':
                 partial._closednodes.add(node)
     except KeyboardInterrupt:
         raise
     except Exception as inst:
         if repo.ui.debugflag:
             msg = 'invalid branchheads cache'
             if repo.filtername is not None:
                 msg += ' (%s)' % repo.filtername
             msg += ': %s\n'
             repo.ui.debug(msg % inst)
         partial = None
     return partial
 
 ### Nearest subset relation
 # Nearest subset of filter X is a filter Y so that:
 # * Y is included in X,
 # * X - Y is as small as possible.
 # This create and ordering used for branchmap purpose.
 # the ordering may be partial
 subsettable = {None: 'visible',
                'visible': 'served',
                'served': 'immutable',
                'immutable': 'base'}
 
 def updatecache(repo):
     cl = repo.changelog
     filtername = repo.filtername
     partial = repo._branchcaches.get(filtername)
 
     revs = []
     if partial is None or not partial.validfor(repo):
         partial = read(repo)
         if partial is None:
             subsetname = subsettable.get(filtername)
             if subsetname is None:
                 partial = branchcache()
             else:
                 subset = repo.filtered(subsetname)
                 partial = subset.branchmap().copy()
                 extrarevs = subset.changelog.filteredrevs - cl.filteredrevs
                 revs.extend(r for  r in extrarevs if r <= partial.tiprev)
     revs.extend(cl.revs(start=partial.tiprev + 1))
     if revs:
         partial.update(repo, revs)
         partial.write(repo)
 
     assert partial.validfor(repo), filtername
     repo._branchcaches[repo.filtername] = partial
 
 def replacecache(repo, bm):
     """Replace the branchmap cache for a repo with a branch mapping.
 
     This is likely only called during clone with a branch map from a remote.
     """
     rbheads = []
     closed = []
     for bheads in bm.itervalues():
         rbheads.extend(bheads)
         for h in bheads:
             r = repo.changelog.rev(h)
             b, c = repo.changelog.branchinfo(r)
             if c:
                 closed.append(h)
 
     if rbheads:
         rtiprev = max((int(repo.changelog.rev(node))
                 for node in rbheads))
         cache = branchcache(bm,
                             repo[rtiprev].node(),
                             rtiprev,
                             closednodes=closed)
 
         # Try to stick it as low as possible
         # filter above served are unlikely to be fetch from a clone
         for candidate in ('base', 'immutable', 'served'):
             rview = repo.filtered(candidate)
             if cache.validfor(rview):
                 repo._branchcaches[candidate] = cache
                 cache.write(rview)
                 break
 
 class branchcache(dict):
     """A dict like object that hold branches heads cache.
 
     This cache is used to avoid costly computations to determine all the
     branch heads of a repo.
 
     The cache is serialized on disk in the following format:
 
     <tip hex node> <tip rev number> [optional filtered repo hex hash]
     <branch head hex node> <open/closed state> <branch name>
     <branch head hex node> <open/closed state> <branch name>
     ...
 
     The first line is used to check if the cache is still valid. If the
     branch cache is for a filtered repo view, an optional third hash is
     included that hashes the hashes of all filtered revisions.
 
     The open/closed state is represented by a single letter 'o' or 'c'.
     This field can be used to avoid changelog reads when determining if a
     branch head closes a branch or not.
     """
 
     def __init__(self, entries=(), tipnode=nullid, tiprev=nullrev,
                  filteredhash=None, closednodes=None):
         super(branchcache, self).__init__(entries)
         self.tipnode = tipnode
         self.tiprev = tiprev
         self.filteredhash = filteredhash
         # closednodes is a set of nodes that close their branch. If the branch
         # cache has been updated, it may contain nodes that are no longer
         # heads.
         if closednodes is None:
             self._closednodes = set()
         else:
             self._closednodes = closednodes
 
     def validfor(self, repo):
         """Is the cache content valid regarding a repo
 
         - False when cached tipnode is unknown or if we detect a strip.
         - True when cache is up to date or a subset of current repo."""
         try:
             return ((self.tipnode == repo.changelog.node(self.tiprev))
                     and (self.filteredhash == \
                          scmutil.filteredhash(repo, self.tiprev)))
         except IndexError:
             return False
 
     def _branchtip(self, heads):
         '''Return tuple with last open head in heads and false,
         otherwise return last closed head and true.'''
         tip = heads[-1]
         closed = True
         for h in reversed(heads):
             if h not in self._closednodes:
                 tip = h
                 closed = False
                 break
         return tip, closed
 
     def branchtip(self, branch):
         '''Return the tipmost open head on branch head, otherwise return the
         tipmost closed head on branch.
         Raise KeyError for unknown branch.'''
         return self._branchtip(self[branch])[0]
 
     def branchheads(self, branch, closed=False):
         heads = self[branch]
         if not closed:
             heads = [h for h in heads if h not in self._closednodes]
         return heads
 
     def iterbranches(self):
         for bn, heads in self.iteritems():
             yield (bn, heads) + self._branchtip(heads)
 
     def copy(self):
         """return an deep copy of the branchcache object"""
         return branchcache(self, self.tipnode, self.tiprev, self.filteredhash,
                            self._closednodes)
 
     def write(self, repo):
         try:
             f = repo.vfs(_filename(repo), "w", atomictemp=True)
             cachekey = [hex(self.tipnode), str(self.tiprev)]
             if self.filteredhash is not None:
                 cachekey.append(hex(self.filteredhash))
             f.write(" ".join(cachekey) + '\n')
             nodecount = 0
             for label, nodes in sorted(self.iteritems()):
                 for node in nodes:
                     nodecount += 1
                     if node in self._closednodes:
                         state = 'c'
                     else:
                         state = 'o'
                     f.write("%s %s %s\n" % (hex(node), state,
                                             encoding.fromlocal(label)))
             f.close()
             repo.ui.log('branchcache',
                         'wrote %s branch cache with %d labels and %d nodes\n',
                         repo.filtername, len(self), nodecount)
         except (IOError, OSError, error.Abort) as inst:
             repo.ui.debug("couldn't write branch cache: %s\n" % inst)
             # Abort may be raise by read only opener
             pass
 
     def update(self, repo, revgen):
         """Given a branchhead cache, self, that may have extra nodes or be
         missing heads, and a generator of nodes that are strictly a superset of
         heads missing, this function updates self to be correct.
         """
         starttime = util.timer()
         cl = repo.changelog
         # collect new branch entries
         newbranches = {}
         getbranchinfo = repo.revbranchcache().branchinfo
         for r in revgen:
             branch, closesbranch = getbranchinfo(r)
             newbranches.setdefault(branch, []).append(r)
             if closesbranch:
                 self._closednodes.add(cl.node(r))
 
         # fetch current topological heads to speed up filtering
         topoheads = set(cl.headrevs())
 
         # 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, newheadrevs in newbranches.iteritems():
             bheads = self.setdefault(branch, [])
             bheadset = set(cl.rev(node) for node in bheads)
 
             # This have been tested True on all internal usage of this function.
             # run it again in case of doubt
             # assert not (set(bheadrevs) & set(newheadrevs))
             newheadrevs.sort()
             bheadset.update(newheadrevs)
 
             # This prunes out two kinds of heads - heads that are superseded by
             # a head in newheadrevs, and newheadrevs that are not heads because
             # an existing head is their descendant.
             uncertain = bheadset - topoheads
             if uncertain:
                 floorrev = min(uncertain)
                 ancestors = set(cl.ancestors(newheadrevs, floorrev))
                 bheadset -= ancestors
             bheadrevs = sorted(bheadset)
             self[branch] = [cl.node(rev) for rev in bheadrevs]
             tiprev = bheadrevs[-1]
             if tiprev > self.tiprev:
                 self.tipnode = cl.node(tiprev)
                 self.tiprev = tiprev
 
         if not self.validfor(repo):
             # cache key are not valid anymore
             self.tipnode = nullid
             self.tiprev = nullrev
             for heads in self.values():
                 tiprev = max(cl.rev(node) for node in heads)
                 if tiprev > self.tiprev:
                     self.tipnode = cl.node(tiprev)
                     self.tiprev = tiprev
         self.filteredhash = scmutil.filteredhash(repo, self.tiprev)
 
         duration = util.timer() - starttime
         repo.ui.log('branchcache', 'updated %s branch cache in %.4f seconds\n',
                     repo.filtername, duration)
 
 # Revision branch info cache
 
 _rbcversion = '-v1'
 _rbcnames = 'cache/rbc-names' + _rbcversion
 _rbcrevs = 'cache/rbc-revs' + _rbcversion
 # [4 byte hash prefix][4 byte branch name number with sign bit indicating open]
 _rbcrecfmt = '>4sI'
 _rbcrecsize = calcsize(_rbcrecfmt)
 _rbcnodelen = 4
 _rbcbranchidxmask = 0x7fffffff
 _rbccloseflag = 0x80000000
 
 class revbranchcache(object):
     """Persistent cache, mapping from revision number to branch name and close.
     This is a low level cache, independent of filtering.
 
     Branch names are stored in rbc-names in internal encoding separated by 0.
     rbc-names is append-only, and each branch name is only stored once and will
     thus have a unique index.
 
     The branch info for each revision is stored in rbc-revs as constant size
     records. The whole file is read into memory, but it is only 'parsed' on
     demand. The file is usually append-only but will be truncated if repo
     modification is detected.
     The record for each revision contains the first 4 bytes of the
     corresponding node hash, and the record is only used if it still matches.
     Even a completely trashed rbc-revs fill thus still give the right result
     while converging towards full recovery ... assuming no incorrectly matching
     node hashes.
     The record also contains 4 bytes where 31 bits contains the index of the
     branch and the last bit indicate that it is a branch close commit.
     The usage pattern for rbc-revs is thus somewhat similar to 00changelog.i
     and will grow with it but be 1/8th of its size.
     """
 
     def __init__(self, repo, readonly=True):
         assert repo.filtername is None
         self._repo = repo
         self._names = [] # branch names in local encoding with static index
-        self._rbcrevs = array('c') # structs of type _rbcrecfmt
+        self._rbcrevs = bytearray()
         self._rbcsnameslen = 0 # length of names read at _rbcsnameslen
         try:
             bndata = repo.vfs.read(_rbcnames)
             self._rbcsnameslen = len(bndata) # for verification before writing
             self._names = [encoding.tolocal(bn) for bn in bndata.split('\0')]
         except (IOError, OSError):
             if readonly:
                 # don't try to use cache - fall back to the slow path
                 self.branchinfo = self._branchinfo
 
         if self._names:
             try:
                 data = repo.vfs.read(_rbcrevs)
-                self._rbcrevs.fromstring(data)
+                self._rbcrevs[:] = data
             except (IOError, OSError) as inst:
                 repo.ui.debug("couldn't read revision branch cache: %s\n" %
                               inst)
         # remember number of good records on disk
         self._rbcrevslen = min(len(self._rbcrevs) // _rbcrecsize,
                                len(repo.changelog))
         if self._rbcrevslen == 0:
             self._names = []
         self._rbcnamescount = len(self._names) # number of names read at
                                                # _rbcsnameslen
         self._namesreverse = dict((b, r) for r, b in enumerate(self._names))
 
     def _clear(self):
         self._rbcsnameslen = 0
         del self._names[:]
         self._rbcnamescount = 0
         self._namesreverse.clear()
         self._rbcrevslen = len(self._repo.changelog)
-        self._rbcrevs = array('c')
-        self._rbcrevs.fromstring('\0' * (self._rbcrevslen * _rbcrecsize))
+        self._rbcrevs = bytearray(self._rbcrevslen * _rbcrecsize)
 
     def branchinfo(self, rev):
         """Return branch name and close flag for rev, using and updating
         persistent cache."""
         changelog = self._repo.changelog
         rbcrevidx = rev * _rbcrecsize
 
         # avoid negative index, changelog.read(nullrev) is fast without cache
         if rev == nullrev:
             return changelog.branchinfo(rev)
 
         # if requested rev isn't allocated, grow and cache the rev info
         if len(self._rbcrevs) < rbcrevidx + _rbcrecsize:
             return self._branchinfo(rev)
 
         # fast path: extract data from cache, use it if node is matching
         reponode = changelog.node(rev)[:_rbcnodelen]
         cachenode, branchidx = unpack(
             _rbcrecfmt, buffer(self._rbcrevs, rbcrevidx, _rbcrecsize))
         close = bool(branchidx & _rbccloseflag)
         if close:
             branchidx &= _rbcbranchidxmask
         if cachenode == '\0\0\0\0':
             pass
         elif cachenode == reponode:
             try:
                 return self._names[branchidx], close
             except IndexError:
                 # recover from invalid reference to unknown branch
                 self._repo.ui.debug("referenced branch names not found"
                     " - rebuilding revision branch cache from scratch\n")
                 self._clear()
         else:
             # rev/node map has changed, invalidate the cache from here up
             self._repo.ui.debug("history modification detected - truncating "
                 "revision branch cache to revision %s\n" % rev)
             truncate = rbcrevidx + _rbcrecsize
             del self._rbcrevs[truncate:]
             self._rbcrevslen = min(self._rbcrevslen, truncate)
 
         # fall back to slow path and make sure it will be written to disk
         return self._branchinfo(rev)
 
     def _branchinfo(self, rev):
         """Retrieve branch info from changelog and update _rbcrevs"""
         changelog = self._repo.changelog
         b, close = changelog.branchinfo(rev)
         if b in self._namesreverse:
             branchidx = self._namesreverse[b]
         else:
             branchidx = len(self._names)
             self._names.append(b)
             self._namesreverse[b] = branchidx
         reponode = changelog.node(rev)
         if close:
             branchidx |= _rbccloseflag
         self._setcachedata(rev, reponode, branchidx)
         return b, close
 
     def _setcachedata(self, rev, node, branchidx):
         """Writes the node's branch data to the in-memory cache data."""
         rbcrevidx = rev * _rbcrecsize
-        rec = array('c')
-        rec.fromstring(pack(_rbcrecfmt, node, branchidx))
+        rec = bytearray(pack(_rbcrecfmt, node, branchidx))
         if len(self._rbcrevs) < rbcrevidx + _rbcrecsize:
             self._rbcrevs.extend('\0' *
                                  (len(self._repo.changelog) * _rbcrecsize -
                                   len(self._rbcrevs)))
         self._rbcrevs[rbcrevidx:rbcrevidx + _rbcrecsize] = rec
         self._rbcrevslen = min(self._rbcrevslen, rev)
 
         tr = self._repo.currenttransaction()
         if tr:
             tr.addfinalize('write-revbranchcache', self.write)
 
     def write(self, tr=None):
         """Save branch cache if it is dirty."""
         repo = self._repo
         wlock = None
         step = ''
         try:
             if self._rbcnamescount < len(self._names):
                 step = ' names'
                 wlock = repo.wlock(wait=False)
                 if self._rbcnamescount != 0:
                     f = repo.vfs.open(_rbcnames, 'ab')
                     if f.tell() == self._rbcsnameslen:
                         f.write('\0')
                     else:
                         f.close()
                         repo.ui.debug("%s changed - rewriting it\n" % _rbcnames)
                         self._rbcnamescount = 0
                         self._rbcrevslen = 0
                 if self._rbcnamescount == 0:
                     # before rewriting names, make sure references are removed
                     repo.vfs.unlinkpath(_rbcrevs, ignoremissing=True)
                     f = repo.vfs.open(_rbcnames, 'wb')
                 f.write('\0'.join(encoding.fromlocal(b)
                                   for b in self._names[self._rbcnamescount:]))
                 self._rbcsnameslen = f.tell()
                 f.close()
                 self._rbcnamescount = len(self._names)
 
             start = self._rbcrevslen * _rbcrecsize
             if start != len(self._rbcrevs):
                 step = ''
                 if wlock is None:
                     wlock = repo.wlock(wait=False)
                 revs = min(len(repo.changelog),
                            len(self._rbcrevs) // _rbcrecsize)
                 f = repo.vfs.open(_rbcrevs, 'ab')
                 if f.tell() != start:
                     repo.ui.debug("truncating %s to %s\n" % (_rbcrevs, start))
                     f.seek(start)
                     if f.tell() != start:
                         start = 0
                         f.seek(start)
                     f.truncate()
                 end = revs * _rbcrecsize
                 f.write(self._rbcrevs[start:end])
                 f.close()
                 self._rbcrevslen = revs
         except (IOError, OSError, error.Abort, error.LockError) as inst:
             repo.ui.debug("couldn't write revision branch cache%s: %s\n"
                           % (step, inst))
         finally:
             if wlock is not None:
                 wlock.release()

mercurial/bundlerepo.py

@@ -1,557 +1,557 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 __future__ import absolute_import
 
 import os
 import shutil
 import tempfile
 
 from .i18n import _
 from .node import nullid
 
 from . import (
     bundle2,
     changegroup,
     changelog,
     cmdutil,
     discovery,
     error,
     exchange,
     filelog,
     localrepo,
     manifest,
     mdiff,
     node as nodemod,
     pathutil,
     phases,
     pycompat,
     revlog,
     util,
     vfs as vfsmod,
 )
 
 class bundlerevlog(revlog.revlog):
     def __init__(self, opener, indexfile, bundle, linkmapper):
         # 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). The base of the delta is stored in the base field.
         #
         # To differentiate a rev in the bundle from a rev in the revlog, we
         # check revision against repotiprev.
         opener = vfsmod.readonlyvfs(opener)
         revlog.revlog.__init__(self, opener, indexfile)
         self.bundle = bundle
         n = len(self)
         self.repotiprev = n - 1
         chain = None
         self.bundlerevs = set() # used by 'bundle()' revset expression
         getchunk = lambda: bundle.deltachunk(chain)
         for chunkdata in iter(getchunk, {}):
             node = chunkdata['node']
             p1 = chunkdata['p1']
             p2 = chunkdata['p2']
             cs = chunkdata['cs']
             deltabase = chunkdata['deltabase']
             delta = chunkdata['delta']
 
             size = len(delta)
             start = bundle.tell() - size
 
             link = linkmapper(cs)
             if node in self.nodemap:
                 # this can happen if two branches make the same change
                 chain = node
                 self.bundlerevs.add(self.nodemap[node])
                 continue
 
             for p in (p1, p2):
                 if p not in self.nodemap:
                     raise error.LookupError(p, self.indexfile,
                                             _("unknown parent"))
 
             if deltabase not in self.nodemap:
                 raise LookupError(deltabase, self.indexfile,
                                   _('unknown delta base'))
 
             baserev = self.rev(deltabase)
             # start, size, full unc. size, base (unused), link, p1, p2, node
             e = (revlog.offset_type(start, 0), size, -1, baserev, link,
                  self.rev(p1), self.rev(p2), node)
             self.index.insert(-1, e)
             self.nodemap[node] = n
             self.bundlerevs.add(n)
             chain = node
             n += 1
 
     def _chunk(self, rev):
         # Warning: in case of bundle, the diff is against what we stored as
         # delta base, not against rev - 1
         # XXX: could use some caching
         if rev <= self.repotiprev:
             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 rev1 > self.repotiprev and rev2 > self.repotiprev:
             # hot path for bundle
             revb = self.index[rev2][3]
             if revb == rev1:
                 return self._chunk(rev2)
         elif rev1 <= self.repotiprev and rev2 <= self.repotiprev:
             return revlog.revlog.revdiff(self, rev1, rev2)
 
         return mdiff.textdiff(self.revision(self.node(rev1)),
                               self.revision(self.node(rev2)))
 
     def revision(self, nodeorrev, raw=False):
         """return an uncompressed revision of a given node or revision
         number.
         """
         if isinstance(nodeorrev, int):
             rev = nodeorrev
             node = self.node(rev)
         else:
             node = nodeorrev
             rev = self.rev(node)
 
         if node == nullid:
             return ""
 
         text = None
         chain = []
         iterrev = rev
         # reconstruct the revision if it is from a changegroup
         while iterrev > self.repotiprev:
             if self._cache and self._cache[1] == iterrev:
                 text = self._cache[2]
                 break
             chain.append(iterrev)
             iterrev = self.index[iterrev][3]
         if text is None:
             text = self.baserevision(iterrev)
 
         while chain:
             delta = self._chunk(chain.pop())
             text = mdiff.patches(text, [delta])
 
         text, validatehash = self._processflags(text, self.flags(rev),
                                                 'read', raw=raw)
         if validatehash:
             self.checkhash(text, node, rev=rev)
         self._cache = (node, rev, text)
         return text
 
     def baserevision(self, nodeorrev):
         # Revlog subclasses may override 'revision' method to modify format of
         # content retrieved from revlog. To use bundlerevlog with such class one
         # needs to override 'baserevision' and make more specific call here.
         return revlog.revlog.revision(self, nodeorrev)
 
     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)
         linkmapper = lambda x: x
         bundlerevlog.__init__(self, opener, self.indexfile, bundle,
                               linkmapper)
 
     def baserevision(self, nodeorrev):
         # Although changelog doesn't override 'revision' method, some extensions
         # may replace this class with another that does. Same story with
         # manifest and filelog classes.
 
         # This bypasses filtering on changelog.node() and rev() because we need
         # revision text of the bundle base even if it is hidden.
         oldfilter = self.filteredrevs
         try:
             self.filteredrevs = ()
             return changelog.changelog.revision(self, nodeorrev)
         finally:
             self.filteredrevs = oldfilter
 
 class bundlemanifest(bundlerevlog, manifest.manifestrevlog):
     def __init__(self, opener, bundle, linkmapper, dirlogstarts=None, dir=''):
         manifest.manifestrevlog.__init__(self, opener, dir=dir)
         bundlerevlog.__init__(self, opener, self.indexfile, bundle,
                               linkmapper)
         if dirlogstarts is None:
             dirlogstarts = {}
             if self.bundle.version == "03":
                 dirlogstarts = _getfilestarts(self.bundle)
         self._dirlogstarts = dirlogstarts
         self._linkmapper = linkmapper
 
     def baserevision(self, nodeorrev):
         node = nodeorrev
         if isinstance(node, int):
             node = self.node(node)
 
         if node in self.fulltextcache:
-            result = self.fulltextcache[node].tostring()
+            result = '%s' % self.fulltextcache[node]
         else:
             result = manifest.manifestrevlog.revision(self, nodeorrev)
         return result
 
     def dirlog(self, d):
         if d in self._dirlogstarts:
             self.bundle.seek(self._dirlogstarts[d])
             return bundlemanifest(
                 self.opener, self.bundle, self._linkmapper,
                 self._dirlogstarts, dir=d)
         return super(bundlemanifest, self).dirlog(d)
 
 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)
 
     def baserevision(self, nodeorrev):
         return filelog.filelog.revision(self, nodeorrev)
 
 class bundlepeer(localrepo.localpeer):
     def canpush(self):
         return False
 
 class bundlephasecache(phases.phasecache):
     def __init__(self, *args, **kwargs):
         super(bundlephasecache, self).__init__(*args, **kwargs)
         if util.safehasattr(self, 'opener'):
             self.opener = vfsmod.readonlyvfs(self.opener)
 
     def write(self):
         raise NotImplementedError
 
     def _write(self, fp):
         raise NotImplementedError
 
     def _updateroots(self, phase, newroots, tr):
         self.phaseroots[phase] = newroots
         self.invalidate()
         self.dirty = True
 
 def _getfilestarts(bundle):
     bundlefilespos = {}
     for chunkdata in iter(bundle.filelogheader, {}):
         fname = chunkdata['filename']
         bundlefilespos[fname] = bundle.tell()
         for chunk in iter(lambda: bundle.deltachunk(None), {}):
             pass
     return bundlefilespos
 
 class bundlerepository(localrepo.localrepository):
     def __init__(self, ui, path, bundlename):
         def _writetempbundle(read, suffix, header=''):
             """Write a temporary file to disk
 
             This is closure because we need to make sure this tracked by
             self.tempfile for cleanup purposes."""
             fdtemp, temp = self.vfs.mkstemp(prefix="hg-bundle-",
                                             suffix=".hg10un")
             self.tempfile = temp
 
             with os.fdopen(fdtemp, pycompat.sysstr('wb')) as fptemp:
                 fptemp.write(header)
                 while True:
                     chunk = read(2**18)
                     if not chunk:
                         break
                     fptemp.write(chunk)
 
             return self.vfs.open(self.tempfile, mode="rb")
         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)
         self.ui.setconfig('phases', 'publish', False, 'bundlerepo')
 
         if path:
             self._url = 'bundle:' + util.expandpath(path) + '+' + bundlename
         else:
             self._url = 'bundle:' + bundlename
 
         self.tempfile = None
         f = util.posixfile(bundlename, "rb")
         self.bundlefile = self.bundle = exchange.readbundle(ui, f, bundlename)
 
         if isinstance(self.bundle, bundle2.unbundle20):
             cgstream = None
             for part in self.bundle.iterparts():
                 if part.type == 'changegroup':
                     if cgstream is not None:
                         raise NotImplementedError("can't process "
                                                   "multiple changegroups")
                     cgstream = part
                     version = part.params.get('version', '01')
                     legalcgvers = changegroup.supportedincomingversions(self)
                     if version not in legalcgvers:
                         msg = _('Unsupported changegroup version: %s')
                         raise error.Abort(msg % version)
                     if self.bundle.compressed():
                         cgstream = _writetempbundle(part.read,
                                                     ".cg%sun" % version)
 
             if cgstream is None:
                 raise error.Abort(_('No changegroups found'))
             cgstream.seek(0)
 
             self.bundle = changegroup.getunbundler(version, cgstream, 'UN')
 
         elif self.bundle.compressed():
             f = _writetempbundle(self.bundle.read, '.hg10un', header='HG10UN')
             self.bundlefile = self.bundle = exchange.readbundle(ui, f,
                                                                 bundlename,
                                                                 self.vfs)
 
         # dict with the mapping 'filename' -> position in the bundle
         self.bundlefilespos = {}
 
         self.firstnewrev = self.changelog.repotiprev + 1
         phases.retractboundary(self, None, phases.draft,
                                [ctx.node() for ctx in self[self.firstnewrev:]])
 
     @localrepo.unfilteredpropertycache
     def _phasecache(self):
         return bundlephasecache(self, self._phasedefaults)
 
     @localrepo.unfilteredpropertycache
     def changelog(self):
         # consume the header if it exists
         self.bundle.changelogheader()
         c = bundlechangelog(self.svfs, self.bundle)
         self.manstart = self.bundle.tell()
         return c
 
     def _constructmanifest(self):
         self.bundle.seek(self.manstart)
         # consume the header if it exists
         self.bundle.manifestheader()
         linkmapper = self.unfiltered().changelog.rev
         m = bundlemanifest(self.svfs, self.bundle, linkmapper)
         self.filestart = self.bundle.tell()
         return m
 
     @localrepo.unfilteredpropertycache
     def manstart(self):
         self.changelog
         return self.manstart
 
     @localrepo.unfilteredpropertycache
     def filestart(self):
         self.manifestlog
         return self.filestart
 
     def url(self):
         return self._url
 
     def file(self, f):
         if not self.bundlefilespos:
             self.bundle.seek(self.filestart)
             self.bundlefilespos = _getfilestarts(self.bundle)
 
         if f in self.bundlefilespos:
             self.bundle.seek(self.bundlefilespos[f])
             linkmapper = self.unfiltered().changelog.rev
             return bundlefilelog(self.svfs, f, self.bundle, linkmapper)
         else:
             return filelog.filelog(self.svfs, f)
 
     def close(self):
         """Close assigned bundle file immediately."""
         self.bundlefile.close()
         if self.tempfile is not None:
             self.vfs.unlink(self.tempfile)
         if self._tempparent:
             shutil.rmtree(self._tempparent, True)
 
     def cancopy(self):
         return False
 
     def peer(self):
         return bundlepeer(self)
 
     def getcwd(self):
         return pycompat.getcwd() # always outside the repo
 
     # Check if parents exist in localrepo before setting
     def setparents(self, p1, p2=nullid):
         p1rev = self.changelog.rev(p1)
         p2rev = self.changelog.rev(p2)
         msg = _("setting parent to node %s that only exists in the bundle\n")
         if self.changelog.repotiprev < p1rev:
             self.ui.warn(msg % nodemod.hex(p1))
         if self.changelog.repotiprev < p2rev:
             self.ui.warn(msg % nodemod.hex(p2))
         return super(bundlerepository, self).setparents(p1, p2)
 
 def instance(ui, path, create):
     if create:
         raise error.Abort(_('cannot create new bundle repository'))
     # internal config: bundle.mainreporoot
     parentpath = ui.config("bundle", "mainreporoot", "")
     if not parentpath:
         # try to find the correct path to the working directory repo
         parentpath = cmdutil.findrepo(pycompat.getcwd())
         if parentpath is None:
             parentpath = ''
     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 = pycompat.getcwd()
         if parentpath == cwd:
             parentpath = ''
         else:
             cwd = pathutil.normasprefix(cwd)
             if parentpath.startswith(cwd):
                 parentpath = parentpath[len(cwd):]
     u = util.url(path)
     path = u.localpath()
     if u.scheme == 'bundle':
         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)
 
 class bundletransactionmanager(object):
     def transaction(self):
         return None
 
     def close(self):
         raise NotImplementedError
 
     def release(self):
         raise NotImplementedError
 
 def getremotechanges(ui, repo, other, onlyheads=None, bundlename=None,
                      force=False):
     '''obtains a bundle of changes incoming from other
 
     "onlyheads" restricts the returned changes to those reachable from the
       specified heads.
     "bundlename", if given, stores the bundle to this file path permanently;
       otherwise it's stored to a temp file and gets deleted again when you call
       the returned "cleanupfn".
     "force" indicates whether to proceed on unrelated repos.
 
     Returns a tuple (local, csets, cleanupfn):
 
     "local" is a local repo from which to obtain the actual incoming
       changesets; it is a bundlerepo for the obtained bundle when the
       original "other" is remote.
     "csets" lists the incoming changeset node ids.
     "cleanupfn" must be called without arguments when you're done processing
       the changes; it closes both the original "other" and the one returned
       here.
     '''
     tmp = discovery.findcommonincoming(repo, other, heads=onlyheads,
                                        force=force)
     common, incoming, rheads = tmp
     if not incoming:
         try:
             if bundlename:
                 os.unlink(bundlename)
         except OSError:
             pass
         return repo, [], other.close
 
     commonset = set(common)
     rheads = [x for x in rheads if x not in commonset]
 
     bundle = None
     bundlerepo = None
     localrepo = other.local()
     if bundlename or not localrepo:
         # create a bundle (uncompressed if other repo is not local)
 
         # developer config: devel.legacy.exchange
         legexc = ui.configlist('devel', 'legacy.exchange')
         forcebundle1 = 'bundle2' not in legexc and 'bundle1' in legexc
         canbundle2 = (not forcebundle1
                       and other.capable('getbundle')
                       and other.capable('bundle2'))
         if canbundle2:
             kwargs = {}
             kwargs['common'] = common
             kwargs['heads'] = rheads
             kwargs['bundlecaps'] = exchange.caps20to10(repo)
             kwargs['cg'] = True
             b2 = other.getbundle('incoming', **kwargs)
             fname = bundle = changegroup.writechunks(ui, b2._forwardchunks(),
                                                      bundlename)
         else:
             if other.capable('getbundle'):
                 cg = other.getbundle('incoming', common=common, heads=rheads)
             elif onlyheads is None and not other.capable('changegroupsubset'):
                 # compat with older servers when pulling all remote heads
                 cg = other.changegroup(incoming, "incoming")
                 rheads = None
             else:
                 cg = other.changegroupsubset(incoming, rheads, 'incoming')
             if localrepo:
                 bundletype = "HG10BZ"
             else:
                 bundletype = "HG10UN"
             fname = bundle = bundle2.writebundle(ui, cg, bundlename,
                                                      bundletype)
         # keep written bundle?
         if bundlename:
             bundle = None
         if not localrepo:
             # use the created uncompressed bundlerepo
             localrepo = bundlerepo = bundlerepository(repo.baseui, repo.root,
                                                       fname)
             # this repo contains local and other now, so filter out local again
             common = repo.heads()
     if localrepo:
         # Part of common may be remotely filtered
         # So use an unfiltered version
         # The discovery process probably need cleanup to avoid that
         localrepo = localrepo.unfiltered()
 
     csets = localrepo.changelog.findmissing(common, rheads)
 
     if bundlerepo:
         reponodes = [ctx.node() for ctx in bundlerepo[bundlerepo.firstnewrev:]]
         remotephases = other.listkeys('phases')
 
         pullop = exchange.pulloperation(bundlerepo, other, heads=reponodes)
         pullop.trmanager = bundletransactionmanager()
         exchange._pullapplyphases(pullop, remotephases)
 
     def cleanup():
         if bundlerepo:
             bundlerepo.close()
         if bundle:
             os.unlink(bundle)
         other.close()
 
     return (localrepo, csets, cleanup)

mercurial/manifest.py

@@ -1,1603 +1,1603 b''
 # manifest.py - manifest revision 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 __future__ import absolute_import
 
-import array
 import heapq
 import os
 import struct
 
 from .i18n import _
 from . import (
     error,
     mdiff,
     parsers,
     revlog,
     util,
 )
 
 propertycache = util.propertycache
 
 def _parsev1(data):
     # This method does a little bit of excessive-looking
     # precondition checking. This is so that the behavior of this
     # class exactly matches its C counterpart to try and help
     # prevent surprise breakage for anyone that develops against
     # the pure version.
     if data and data[-1] != '\n':
         raise ValueError('Manifest did not end in a newline.')
     prev = None
     for l in data.splitlines():
         if prev is not None and prev > l:
             raise ValueError('Manifest lines not in sorted order.')
         prev = l
         f, n = l.split('\0')
         if len(n) > 40:
             yield f, revlog.bin(n[:40]), n[40:]
         else:
             yield f, revlog.bin(n), ''
 
 def _parsev2(data):
     metadataend = data.find('\n')
     # Just ignore metadata for now
     pos = metadataend + 1
     prevf = ''
     while pos < len(data):
         end = data.find('\n', pos + 1) # +1 to skip stem length byte
         if end == -1:
             raise ValueError('Manifest ended with incomplete file entry.')
         stemlen = ord(data[pos])
         items = data[pos + 1:end].split('\0')
         f = prevf[:stemlen] + items[0]
         if prevf > f:
             raise ValueError('Manifest entries not in sorted order.')
         fl = items[1]
         # Just ignore metadata (items[2:] for now)
         n = data[end + 1:end + 21]
         yield f, n, fl
         pos = end + 22
         prevf = f
 
 def _parse(data):
     """Generates (path, node, flags) tuples from a manifest text"""
     if data.startswith('\0'):
         return iter(_parsev2(data))
     else:
         return iter(_parsev1(data))
 
 def _text(it, usemanifestv2):
     """Given an iterator over (path, node, flags) tuples, returns a manifest
     text"""
     if usemanifestv2:
         return _textv2(it)
     else:
         return _textv1(it)
 
 def _textv1(it):
     files = []
     lines = []
     _hex = revlog.hex
     for f, n, fl in it:
         files.append(f)
         # if this is changed to support newlines in filenames,
         # be sure to check the templates/ dir again (especially *-raw.tmpl)
         lines.append("%s\0%s%s\n" % (f, _hex(n), fl))
 
     _checkforbidden(files)
     return ''.join(lines)
 
 def _textv2(it):
     files = []
     lines = ['\0\n']
     prevf = ''
     for f, n, fl in it:
         files.append(f)
         stem = os.path.commonprefix([prevf, f])
         stemlen = min(len(stem), 255)
         lines.append("%c%s\0%s\n%s\n" % (stemlen, f[stemlen:], fl, n))
         prevf = f
     _checkforbidden(files)
     return ''.join(lines)
 
 class lazymanifestiter(object):
     def __init__(self, lm):
         self.pos = 0
         self.lm = lm
 
     def __iter__(self):
         return self
 
     def next(self):
         try:
             data, pos = self.lm._get(self.pos)
         except IndexError:
             raise StopIteration
         if pos == -1:
             self.pos += 1
             return data[0]
         self.pos += 1
         zeropos = data.find('\x00', pos)
         return data[pos:zeropos]
 
 class lazymanifestiterentries(object):
     def __init__(self, lm):
         self.lm = lm
         self.pos = 0
 
     def __iter__(self):
         return self
 
     def next(self):
         try:
             data, pos = self.lm._get(self.pos)
         except IndexError:
             raise StopIteration
         if pos == -1:
             self.pos += 1
             return data
         zeropos = data.find('\x00', pos)
         hashval = unhexlify(data, self.lm.extrainfo[self.pos],
                             zeropos + 1, 40)
         flags = self.lm._getflags(data, self.pos, zeropos)
         self.pos += 1
         return (data[pos:zeropos], hashval, flags)
 
 def unhexlify(data, extra, pos, length):
     s = data[pos:pos + length].decode('hex')
     if extra:
         s += chr(extra & 0xff)
     return s
 
 def _cmp(a, b):
     return (a > b) - (a < b)
 
 class _lazymanifest(object):
     def __init__(self, data, positions=None, extrainfo=None, extradata=None):
         if positions is None:
             self.positions = self.findlines(data)
             self.extrainfo = [0] * len(self.positions)
             self.data = data
             self.extradata = []
         else:
             self.positions = positions[:]
             self.extrainfo = extrainfo[:]
             self.extradata = extradata[:]
             self.data = data
 
     def findlines(self, data):
         if not data:
             return []
         pos = data.find("\n")
         if pos == -1 or data[-1] != '\n':
             raise ValueError("Manifest did not end in a newline.")
         positions = [0]
         prev = data[:data.find('\x00')]
         while pos < len(data) - 1 and pos != -1:
             positions.append(pos + 1)
             nexts = data[pos + 1:data.find('\x00', pos + 1)]
             if nexts < prev:
                 raise ValueError("Manifest lines not in sorted order.")
             prev = nexts
             pos = data.find("\n", pos + 1)
         return positions
 
     def _get(self, index):
         # get the position encoded in pos:
         #   positive number is an index in 'data'
         #   negative number is in extrapieces
         pos = self.positions[index]
         if pos >= 0:
             return self.data, pos
         return self.extradata[-pos - 1], -1
 
     def _getkey(self, pos):
         if pos >= 0:
             return self.data[pos:self.data.find('\x00', pos + 1)]
         return self.extradata[-pos - 1][0]
 
     def bsearch(self, key):
         first = 0
         last = len(self.positions) - 1
 
         while first <= last:
             midpoint = (first + last)//2
             nextpos = self.positions[midpoint]
             candidate = self._getkey(nextpos)
             r = _cmp(key, candidate)
             if r == 0:
                 return midpoint
             else:
                 if r < 0:
                     last = midpoint - 1
                 else:
                     first = midpoint + 1
         return -1
 
     def bsearch2(self, key):
         # same as the above, but will always return the position
         # done for performance reasons
         first = 0
         last = len(self.positions) - 1
 
         while first <= last:
             midpoint = (first + last)//2
             nextpos = self.positions[midpoint]
             candidate = self._getkey(nextpos)
             r = _cmp(key, candidate)
             if r == 0:
                 return (midpoint, True)
             else:
                 if r < 0:
                     last = midpoint - 1
                 else:
                     first = midpoint + 1
         return (first, False)
 
     def __contains__(self, key):
         return self.bsearch(key) != -1
 
     def _getflags(self, data, needle, pos):
         start = pos + 41
         end = data.find("\n", start)
         if end == -1:
             end = len(data) - 1
         if start == end:
             return ''
         return self.data[start:end]
 
     def __getitem__(self, key):
         if not isinstance(key, str):
             raise TypeError("getitem: manifest keys must be a string.")
         needle = self.bsearch(key)
         if needle == -1:
             raise KeyError
         data, pos = self._get(needle)
         if pos == -1:
             return (data[1], data[2])
         zeropos = data.find('\x00', pos)
         assert 0 <= needle <= len(self.positions)
         assert len(self.extrainfo) == len(self.positions)
         hashval = unhexlify(data, self.extrainfo[needle], zeropos + 1, 40)
         flags = self._getflags(data, needle, zeropos)
         return (hashval, flags)
 
     def __delitem__(self, key):
         needle, found = self.bsearch2(key)
         if not found:
             raise KeyError
         cur = self.positions[needle]
         self.positions = self.positions[:needle] + self.positions[needle + 1:]
         self.extrainfo = self.extrainfo[:needle] + self.extrainfo[needle + 1:]
         if cur >= 0:
             self.data = self.data[:cur] + '\x00' + self.data[cur + 1:]
 
     def __setitem__(self, key, value):
         if not isinstance(key, str):
             raise TypeError("setitem: manifest keys must be a string.")
         if not isinstance(value, tuple) or len(value) != 2:
             raise TypeError("Manifest values must be a tuple of (node, flags).")
         hashval = value[0]
         if not isinstance(hashval, str) or not 20 <= len(hashval) <= 22:
             raise TypeError("node must be a 20-byte string")
         flags = value[1]
         if len(hashval) == 22:
             hashval = hashval[:-1]
         if not isinstance(flags, str) or len(flags) > 1:
             raise TypeError("flags must a 0 or 1 byte string, got %r", flags)
         needle, found = self.bsearch2(key)
         if found:
             # put the item
             pos = self.positions[needle]
             if pos < 0:
                 self.extradata[-pos - 1] = (key, hashval, value[1])
             else:
                 # just don't bother
                 self.extradata.append((key, hashval, value[1]))
                 self.positions[needle] = -len(self.extradata)
         else:
             # not found, put it in with extra positions
             self.extradata.append((key, hashval, value[1]))
             self.positions = (self.positions[:needle] + [-len(self.extradata)]
                               + self.positions[needle:])
             self.extrainfo = (self.extrainfo[:needle] + [0] +
                               self.extrainfo[needle:])
 
     def copy(self):
         # XXX call _compact like in C?
         return _lazymanifest(self.data, self.positions, self.extrainfo,
             self.extradata)
 
     def _compact(self):
         # hopefully not called TOO often
         if len(self.extradata) == 0:
             return
         l = []
         last_cut = 0
         i = 0
         offset = 0
         self.extrainfo = [0] * len(self.positions)
         while i < len(self.positions):
             if self.positions[i] >= 0:
                 cur = self.positions[i]
                 last_cut = cur
                 while True:
                     self.positions[i] = offset
                     i += 1
                     if i == len(self.positions) or self.positions[i] < 0:
                         break
                     offset += self.positions[i] - cur
                     cur = self.positions[i]
                 end_cut = self.data.find('\n', cur)
                 if end_cut != -1:
                     end_cut += 1
                 offset += end_cut - cur
                 l.append(self.data[last_cut:end_cut])
             else:
                 while i < len(self.positions) and self.positions[i] < 0:
                     cur = self.positions[i]
                     t = self.extradata[-cur - 1]
                     l.append(self._pack(t))
                     self.positions[i] = offset
                     if len(t[1]) > 20:
                         self.extrainfo[i] = ord(t[1][21])
                     offset += len(l[-1])
                     i += 1
         self.data = ''.join(l)
         self.extradata = []
 
     def _pack(self, d):
         return d[0] + '\x00' + d[1][:20].encode('hex') + d[2] + '\n'
 
     def text(self):
         self._compact()
         return self.data
 
     def diff(self, m2, clean=False):
         '''Finds changes between the current manifest and m2.'''
         # XXX think whether efficiency matters here
         diff = {}
 
         for fn, e1, flags in self.iterentries():
             if fn not in m2:
                 diff[fn] = (e1, flags), (None, '')
             else:
                 e2 = m2[fn]
                 if (e1, flags) != e2:
                     diff[fn] = (e1, flags), e2
                 elif clean:
                     diff[fn] = None
 
         for fn, e2, flags in m2.iterentries():
             if fn not in self:
                 diff[fn] = (None, ''), (e2, flags)
 
         return diff
 
     def iterentries(self):
         return lazymanifestiterentries(self)
 
     def iterkeys(self):
         return lazymanifestiter(self)
 
     def __iter__(self):
         return lazymanifestiter(self)
 
     def __len__(self):
         return len(self.positions)
 
     def filtercopy(self, filterfn):
         # XXX should be optimized
         c = _lazymanifest('')
         for f, n, fl in self.iterentries():
             if filterfn(f):
                 c[f] = n, fl
         return c
 
 try:
     _lazymanifest = parsers.lazymanifest
 except AttributeError:
     pass
 
 class manifestdict(object):
     def __init__(self, data=''):
         if data.startswith('\0'):
             #_lazymanifest can not parse v2
             self._lm = _lazymanifest('')
             for f, n, fl in _parsev2(data):
                 self._lm[f] = n, fl
         else:
             self._lm = _lazymanifest(data)
 
     def __getitem__(self, key):
         return self._lm[key][0]
 
     def find(self, key):
         return self._lm[key]
 
     def __len__(self):
         return len(self._lm)
 
     def __nonzero__(self):
         # nonzero is covered by the __len__ function, but implementing it here
         # makes it easier for extensions to override.
         return len(self._lm) != 0
 
     def __setitem__(self, key, node):
         self._lm[key] = node, self.flags(key, '')
 
     def __contains__(self, key):
         return key in self._lm
 
     def __delitem__(self, key):
         del self._lm[key]
 
     def __iter__(self):
         return self._lm.__iter__()
 
     def iterkeys(self):
         return self._lm.iterkeys()
 
     def keys(self):
         return list(self.iterkeys())
 
     def filesnotin(self, m2, match=None):
         '''Set of files in this manifest that are not in the other'''
         if match:
             m1 = self.matches(match)
             m2 = m2.matches(match)
             return m1.filesnotin(m2)
         diff = self.diff(m2)
         files = set(filepath
                     for filepath, hashflags in diff.iteritems()
                     if hashflags[1][0] is None)
         return files
 
     @propertycache
     def _dirs(self):
         return util.dirs(self)
 
     def dirs(self):
         return self._dirs
 
     def hasdir(self, dir):
         return dir in self._dirs
 
     def _filesfastpath(self, match):
         '''Checks whether we can correctly and quickly iterate over matcher
         files instead of over manifest files.'''
         files = match.files()
         return (len(files) < 100 and (match.isexact() or
             (match.prefix() and all(fn in self for fn in files))))
 
     def walk(self, match):
         '''Generates matching file names.
 
         Equivalent to manifest.matches(match).iterkeys(), but without creating
         an entirely new manifest.
 
         It also reports nonexistent files by marking them bad with match.bad().
         '''
         if match.always():
             for f in iter(self):
                 yield f
             return
 
         fset = set(match.files())
 
         # avoid the entire walk if we're only looking for specific files
         if self._filesfastpath(match):
             for fn in sorted(fset):
                 yield fn
             return
 
         for fn in self:
             if fn in fset:
                 # specified pattern is the exact name
                 fset.remove(fn)
             if match(fn):
                 yield fn
 
         # for dirstate.walk, files=['.'] means "walk the whole tree".
         # follow that here, too
         fset.discard('.')
 
         for fn in sorted(fset):
             if not self.hasdir(fn):
                 match.bad(fn, None)
 
     def matches(self, match):
         '''generate a new manifest filtered by the match argument'''
         if match.always():
             return self.copy()
 
         if self._filesfastpath(match):
             m = manifestdict()
             lm = self._lm
             for fn in match.files():
                 if fn in lm:
                     m._lm[fn] = lm[fn]
             return m
 
         m = manifestdict()
         m._lm = self._lm.filtercopy(match)
         return m
 
     def diff(self, m2, match=None, clean=False):
         '''Finds changes between the current manifest and m2.
 
         Args:
           m2: the manifest to which this manifest should be compared.
           clean: if true, include files unchanged between these manifests
                  with a None value in the returned dictionary.
 
         The result is returned as a dict with filename as key and
         values of the form ((n1,fl1),(n2,fl2)), where n1/n2 is the
         nodeid in the current/other manifest and fl1/fl2 is the flag
         in the current/other manifest. Where the file does not exist,
         the nodeid will be None and the flags will be the empty
         string.
         '''
         if match:
             m1 = self.matches(match)
             m2 = m2.matches(match)
             return m1.diff(m2, clean=clean)
         return self._lm.diff(m2._lm, clean)
 
     def setflag(self, key, flag):
         self._lm[key] = self[key], flag
 
     def get(self, key, default=None):
         try:
             return self._lm[key][0]
         except KeyError:
             return default
 
     def flags(self, key, default=''):
         try:
             return self._lm[key][1]
         except KeyError:
             return default
 
     def copy(self):
         c = manifestdict()
         c._lm = self._lm.copy()
         return c
 
     def iteritems(self):
         return (x[:2] for x in self._lm.iterentries())
 
     def iterentries(self):
         return self._lm.iterentries()
 
     def text(self, usemanifestv2=False):
         if usemanifestv2:
             return _textv2(self._lm.iterentries())
         else:
             # use (probably) native version for v1
             return self._lm.text()
 
     def fastdelta(self, base, changes):
         """Given a base manifest text as an array.array and a list of changes
         relative to that text, compute a delta that can be used by revlog.
         """
         delta = []
         dstart = None
         dend = None
         dline = [""]
         start = 0
         # zero copy representation of base as a buffer
         addbuf = util.buffer(base)
 
         changes = list(changes)
         if len(changes) < 1000:
             # start with a readonly loop that finds the offset of
             # each line and creates the deltas
             for f, todelete in changes:
                 # bs will either be the index of the item or the insert point
                 start, end = _msearch(addbuf, f, start)
                 if not todelete:
                     h, fl = self._lm[f]
                     l = "%s\0%s%s\n" % (f, revlog.hex(h), fl)
                 else:
                     if start == end:
                         # item we want to delete was not found, error out
                         raise AssertionError(
                                 _("failed to remove %s from manifest") % f)
                     l = ""
                 if dstart is not None and dstart <= start and dend >= start:
                     if dend < end:
                         dend = end
                     if l:
                         dline.append(l)
                 else:
                     if dstart is not None:
                         delta.append([dstart, dend, "".join(dline)])
                     dstart = start
                     dend = end
                     dline = [l]
 
             if dstart is not None:
                 delta.append([dstart, dend, "".join(dline)])
             # apply the delta to the base, and get a delta for addrevision
             deltatext, arraytext = _addlistdelta(base, delta)
         else:
             # For large changes, it's much cheaper to just build the text and
             # diff it.
-            arraytext = array.array('c', self.text())
-            deltatext = mdiff.textdiff(base, arraytext)
+            arraytext = bytearray(self.text())
+            deltatext = mdiff.textdiff(
+                util.buffer(base), util.buffer(arraytext))
 
         return arraytext, deltatext
 
 def _msearch(m, s, lo=0, hi=None):
     '''return a tuple (start, end) that says where to find s within m.
 
     If the string is found m[start:end] are the line containing
     that string.  If start == end the string was not found and
     they indicate the proper sorted insertion point.
 
     m should be a buffer or a string
     s is a string'''
     def advance(i, c):
         while i < lenm and m[i] != c:
             i += 1
         return i
     if not s:
         return (lo, lo)
     lenm = len(m)
     if not hi:
         hi = lenm
     while lo < hi:
         mid = (lo + hi) // 2
         start = mid
         while start > 0 and m[start - 1] != '\n':
             start -= 1
         end = advance(start, '\0')
         if m[start:end] < s:
             # we know that after the null there are 40 bytes of sha1
             # this translates to the bisect lo = mid + 1
             lo = advance(end + 40, '\n') + 1
         else:
             # this translates to the bisect hi = mid
             hi = start
     end = advance(lo, '\0')
     found = m[lo:end]
     if s == found:
         # we know that after the null there are 40 bytes of sha1
         end = advance(end + 40, '\n')
         return (lo, end + 1)
     else:
         return (lo, lo)
 
 def _checkforbidden(l):
     """Check filenames for illegal characters."""
     for f in l:
         if '\n' in f or '\r' in f:
             raise error.RevlogError(
                 _("'\\n' and '\\r' disallowed in filenames: %r") % f)
 
 
 # apply the changes collected during the bisect loop to our addlist
 # return a delta suitable for addrevision
 def _addlistdelta(addlist, x):
     # for large addlist arrays, building a new array is cheaper
     # than repeatedly modifying the existing one
     currentposition = 0
-    newaddlist = array.array('c')
+    newaddlist = bytearray()
 
     for start, end, content in x:
         newaddlist += addlist[currentposition:start]
         if content:
-            newaddlist += array.array('c', content)
+            newaddlist += bytearray(content)
 
         currentposition = end
 
     newaddlist += addlist[currentposition:]
 
     deltatext = "".join(struct.pack(">lll", start, end, len(content))
                    + content for start, end, content in x)
     return deltatext, newaddlist
 
 def _splittopdir(f):
     if '/' in f:
         dir, subpath = f.split('/', 1)
         return dir + '/', subpath
     else:
         return '', f
 
 _noop = lambda s: None
 
 class treemanifest(object):
     def __init__(self, dir='', text=''):
         self._dir = dir
         self._node = revlog.nullid
         self._loadfunc = _noop
         self._copyfunc = _noop
         self._dirty = False
         self._dirs = {}
         # Using _lazymanifest here is a little slower than plain old dicts
         self._files = {}
         self._flags = {}
         if text:
             def readsubtree(subdir, subm):
                 raise AssertionError('treemanifest constructor only accepts '
                                      'flat manifests')
             self.parse(text, readsubtree)
             self._dirty = True # Mark flat manifest dirty after parsing
 
     def _subpath(self, path):
         return self._dir + path
 
     def __len__(self):
         self._load()
         size = len(self._files)
         for m in self._dirs.values():
             size += m.__len__()
         return size
 
     def _isempty(self):
         self._load() # for consistency; already loaded by all callers
         return (not self._files and (not self._dirs or
                 all(m._isempty() for m in self._dirs.values())))
 
     def __repr__(self):
         return ('<treemanifest dir=%s, node=%s, loaded=%s, dirty=%s at 0x%x>' %
                 (self._dir, revlog.hex(self._node),
                  bool(self._loadfunc is _noop),
                  self._dirty, id(self)))
 
     def dir(self):
         '''The directory that this tree manifest represents, including a
         trailing '/'. Empty string for the repo root directory.'''
         return self._dir
 
     def node(self):
         '''This node of this instance. nullid for unsaved instances. Should
         be updated when the instance is read or written from a revlog.
         '''
         assert not self._dirty
         return self._node
 
     def setnode(self, node):
         self._node = node
         self._dirty = False
 
     def iterentries(self):
         self._load()
         for p, n in sorted(self._dirs.items() + self._files.items()):
             if p in self._files:
                 yield self._subpath(p), n, self._flags.get(p, '')
             else:
                 for x in n.iterentries():
                     yield x
 
     def iteritems(self):
         self._load()
         for p, n in sorted(self._dirs.items() + self._files.items()):
             if p in self._files:
                 yield self._subpath(p), n
             else:
                 for f, sn in n.iteritems():
                     yield f, sn
 
     def iterkeys(self):
         self._load()
         for p in sorted(self._dirs.keys() + self._files.keys()):
             if p in self._files:
                 yield self._subpath(p)
             else:
                 for f in self._dirs[p].iterkeys():
                     yield f
 
     def keys(self):
         return list(self.iterkeys())
 
     def __iter__(self):
         return self.iterkeys()
 
     def __contains__(self, f):
         if f is None:
             return False
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             if dir not in self._dirs:
                 return False
             return self._dirs[dir].__contains__(subpath)
         else:
             return f in self._files
 
     def get(self, f, default=None):
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             if dir not in self._dirs:
                 return default
             return self._dirs[dir].get(subpath, default)
         else:
             return self._files.get(f, default)
 
     def __getitem__(self, f):
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             return self._dirs[dir].__getitem__(subpath)
         else:
             return self._files[f]
 
     def flags(self, f):
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             if dir not in self._dirs:
                 return ''
             return self._dirs[dir].flags(subpath)
         else:
             if f in self._dirs:
                 return ''
             return self._flags.get(f, '')
 
     def find(self, f):
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             return self._dirs[dir].find(subpath)
         else:
             return self._files[f], self._flags.get(f, '')
 
     def __delitem__(self, f):
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             self._dirs[dir].__delitem__(subpath)
             # If the directory is now empty, remove it
             if self._dirs[dir]._isempty():
                 del self._dirs[dir]
         else:
             del self._files[f]
             if f in self._flags:
                 del self._flags[f]
         self._dirty = True
 
     def __setitem__(self, f, n):
         assert n is not None
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             if dir not in self._dirs:
                 self._dirs[dir] = treemanifest(self._subpath(dir))
             self._dirs[dir].__setitem__(subpath, n)
         else:
             self._files[f] = n[:21] # to match manifestdict's behavior
         self._dirty = True
 
     def _load(self):
         if self._loadfunc is not _noop:
             lf, self._loadfunc = self._loadfunc, _noop
             lf(self)
         elif self._copyfunc is not _noop:
             cf, self._copyfunc = self._copyfunc, _noop
             cf(self)
 
     def setflag(self, f, flags):
         """Set the flags (symlink, executable) for path f."""
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             if dir not in self._dirs:
                 self._dirs[dir] = treemanifest(self._subpath(dir))
             self._dirs[dir].setflag(subpath, flags)
         else:
             self._flags[f] = flags
         self._dirty = True
 
     def copy(self):
         copy = treemanifest(self._dir)
         copy._node = self._node
         copy._dirty = self._dirty
         if self._copyfunc is _noop:
             def _copyfunc(s):
                 self._load()
                 for d in self._dirs:
                     s._dirs[d] = self._dirs[d].copy()
                 s._files = dict.copy(self._files)
                 s._flags = dict.copy(self._flags)
             if self._loadfunc is _noop:
                 _copyfunc(copy)
             else:
                 copy._copyfunc = _copyfunc
         else:
             copy._copyfunc = self._copyfunc
         return copy
 
     def filesnotin(self, m2, match=None):
         '''Set of files in this manifest that are not in the other'''
         if match:
             m1 = self.matches(match)
             m2 = m2.matches(match)
             return m1.filesnotin(m2)
 
         files = set()
         def _filesnotin(t1, t2):
             if t1._node == t2._node and not t1._dirty and not t2._dirty:
                 return
             t1._load()
             t2._load()
             for d, m1 in t1._dirs.iteritems():
                 if d in t2._dirs:
                     m2 = t2._dirs[d]
                     _filesnotin(m1, m2)
                 else:
                     files.update(m1.iterkeys())
 
             for fn in t1._files.iterkeys():
                 if fn not in t2._files:
                     files.add(t1._subpath(fn))
 
         _filesnotin(self, m2)
         return files
 
     @propertycache
     def _alldirs(self):
         return util.dirs(self)
 
     def dirs(self):
         return self._alldirs
 
     def hasdir(self, dir):
         self._load()
         topdir, subdir = _splittopdir(dir)
         if topdir:
             if topdir in self._dirs:
                 return self._dirs[topdir].hasdir(subdir)
             return False
         return (dir + '/') in self._dirs
 
     def walk(self, match):
         '''Generates matching file names.
 
         Equivalent to manifest.matches(match).iterkeys(), but without creating
         an entirely new manifest.
 
         It also reports nonexistent files by marking them bad with match.bad().
         '''
         if match.always():
             for f in iter(self):
                 yield f
             return
 
         fset = set(match.files())
 
         for fn in self._walk(match):
             if fn in fset:
                 # specified pattern is the exact name
                 fset.remove(fn)
             yield fn
 
         # for dirstate.walk, files=['.'] means "walk the whole tree".
         # follow that here, too
         fset.discard('.')
 
         for fn in sorted(fset):
             if not self.hasdir(fn):
                 match.bad(fn, None)
 
     def _walk(self, match):
         '''Recursively generates matching file names for walk().'''
         if not match.visitdir(self._dir[:-1] or '.'):
             return
 
         # yield this dir's files and walk its submanifests
         self._load()
         for p in sorted(self._dirs.keys() + self._files.keys()):
             if p in self._files:
                 fullp = self._subpath(p)
                 if match(fullp):
                     yield fullp
             else:
                 for f in self._dirs[p]._walk(match):
                     yield f
 
     def matches(self, match):
         '''generate a new manifest filtered by the match argument'''
         if match.always():
             return self.copy()
 
         return self._matches(match)
 
     def _matches(self, match):
         '''recursively generate a new manifest filtered by the match argument.
         '''
 
         visit = match.visitdir(self._dir[:-1] or '.')
         if visit == 'all':
             return self.copy()
         ret = treemanifest(self._dir)
         if not visit:
             return ret
 
         self._load()
         for fn in self._files:
             fullp = self._subpath(fn)
             if not match(fullp):
                 continue
             ret._files[fn] = self._files[fn]
             if fn in self._flags:
                 ret._flags[fn] = self._flags[fn]
 
         for dir, subm in self._dirs.iteritems():
             m = subm._matches(match)
             if not m._isempty():
                 ret._dirs[dir] = m
 
         if not ret._isempty():
             ret._dirty = True
         return ret
 
     def diff(self, m2, match=None, clean=False):
         '''Finds changes between the current manifest and m2.
 
         Args:
           m2: the manifest to which this manifest should be compared.
           clean: if true, include files unchanged between these manifests
                  with a None value in the returned dictionary.
 
         The result is returned as a dict with filename as key and
         values of the form ((n1,fl1),(n2,fl2)), where n1/n2 is the
         nodeid in the current/other manifest and fl1/fl2 is the flag
         in the current/other manifest. Where the file does not exist,
         the nodeid will be None and the flags will be the empty
         string.
         '''
         if match:
             m1 = self.matches(match)
             m2 = m2.matches(match)
             return m1.diff(m2, clean=clean)
         result = {}
         emptytree = treemanifest()
         def _diff(t1, t2):
             if t1._node == t2._node and not t1._dirty and not t2._dirty:
                 return
             t1._load()
             t2._load()
             for d, m1 in t1._dirs.iteritems():
                 m2 = t2._dirs.get(d, emptytree)
                 _diff(m1, m2)
 
             for d, m2 in t2._dirs.iteritems():
                 if d not in t1._dirs:
                     _diff(emptytree, m2)
 
             for fn, n1 in t1._files.iteritems():
                 fl1 = t1._flags.get(fn, '')
                 n2 = t2._files.get(fn, None)
                 fl2 = t2._flags.get(fn, '')
                 if n1 != n2 or fl1 != fl2:
                     result[t1._subpath(fn)] = ((n1, fl1), (n2, fl2))
                 elif clean:
                     result[t1._subpath(fn)] = None
 
             for fn, n2 in t2._files.iteritems():
                 if fn not in t1._files:
                     fl2 = t2._flags.get(fn, '')
                     result[t2._subpath(fn)] = ((None, ''), (n2, fl2))
 
         _diff(self, m2)
         return result
 
     def unmodifiedsince(self, m2):
         return not self._dirty and not m2._dirty and self._node == m2._node
 
     def parse(self, text, readsubtree):
         for f, n, fl in _parse(text):
             if fl == 't':
                 f = f + '/'
                 self._dirs[f] = readsubtree(self._subpath(f), n)
             elif '/' in f:
                 # This is a flat manifest, so use __setitem__ and setflag rather
                 # than assigning directly to _files and _flags, so we can
                 # assign a path in a subdirectory, and to mark dirty (compared
                 # to nullid).
                 self[f] = n
                 if fl:
                     self.setflag(f, fl)
             else:
                 # Assigning to _files and _flags avoids marking as dirty,
                 # and should be a little faster.
                 self._files[f] = n
                 if fl:
                     self._flags[f] = fl
 
     def text(self, usemanifestv2=False):
         """Get the full data of this manifest as a bytestring."""
         self._load()
         return _text(self.iterentries(), usemanifestv2)
 
     def dirtext(self, usemanifestv2=False):
         """Get the full data of this directory as a bytestring. Make sure that
         any submanifests have been written first, so their nodeids are correct.
         """
         self._load()
         flags = self.flags
         dirs = [(d[:-1], self._dirs[d]._node, 't') for d in self._dirs]
         files = [(f, self._files[f], flags(f)) for f in self._files]
         return _text(sorted(dirs + files), usemanifestv2)
 
     def read(self, gettext, readsubtree):
         def _load_for_read(s):
             s.parse(gettext(), readsubtree)
             s._dirty = False
         self._loadfunc = _load_for_read
 
     def writesubtrees(self, m1, m2, writesubtree):
         self._load() # for consistency; should never have any effect here
         m1._load()
         m2._load()
         emptytree = treemanifest()
         for d, subm in self._dirs.iteritems():
             subp1 = m1._dirs.get(d, emptytree)._node
             subp2 = m2._dirs.get(d, emptytree)._node
             if subp1 == revlog.nullid:
                 subp1, subp2 = subp2, subp1
             writesubtree(subm, subp1, subp2)
 
 class manifestrevlog(revlog.revlog):
     '''A revlog that stores manifest texts. This is responsible for caching the
     full-text manifest contents.
     '''
     def __init__(self, opener, dir='', dirlogcache=None, indexfile=None):
         """Constructs a new manifest revlog
 
         `indexfile` - used by extensions to have two manifests at once, like
         when transitioning between flatmanifeset and treemanifests.
         """
         # During normal operations, we expect to deal with not more than four
         # revs at a time (such as during commit --amend). When rebasing large
         # stacks of commits, the number can go up, hence the config knob below.
         cachesize = 4
         usetreemanifest = False
         usemanifestv2 = False
         opts = getattr(opener, 'options', None)
         if opts is not None:
             cachesize = opts.get('manifestcachesize', cachesize)
             usetreemanifest = opts.get('treemanifest', usetreemanifest)
             usemanifestv2 = opts.get('manifestv2', usemanifestv2)
 
         self._treeondisk = usetreemanifest
         self._usemanifestv2 = usemanifestv2
 
         self._fulltextcache = util.lrucachedict(cachesize)
 
         if dir:
             assert self._treeondisk, 'opts is %r' % opts
             if not dir.endswith('/'):
                 dir = dir + '/'
 
         if indexfile is None:
             indexfile = '00manifest.i'
             if dir:
                 indexfile = "meta/" + dir + indexfile
 
         self._dir = dir
         # The dirlogcache is kept on the root manifest log
         if dir:
             self._dirlogcache = dirlogcache
         else:
             self._dirlogcache = {'': self}
 
         super(manifestrevlog, self).__init__(opener, indexfile,
                                              checkambig=bool(dir))
 
     @property
     def fulltextcache(self):
         return self._fulltextcache
 
     def clearcaches(self):
         super(manifestrevlog, self).clearcaches()
         self._fulltextcache.clear()
         self._dirlogcache = {'': self}
 
     def dirlog(self, dir):
         if dir:
             assert self._treeondisk
         if dir not in self._dirlogcache:
             self._dirlogcache[dir] = manifestrevlog(self.opener, dir,
                                                     self._dirlogcache)
         return self._dirlogcache[dir]
 
     def add(self, m, transaction, link, p1, p2, added, removed, readtree=None):
         if (p1 in self.fulltextcache and util.safehasattr(m, 'fastdelta')
             and not self._usemanifestv2):
             # If our first parent is in the manifest cache, we can
             # compute a delta here using properties we know about the
             # manifest up-front, which may save time later for the
             # revlog layer.
 
             _checkforbidden(added)
             # combine the changed lists into one sorted iterator
             work = heapq.merge([(x, False) for x in added],
                                [(x, True) for x in removed])
 
             arraytext, deltatext = m.fastdelta(self.fulltextcache[p1], work)
             cachedelta = self.rev(p1), deltatext
             text = util.buffer(arraytext)
             n = self.addrevision(text, transaction, link, p1, p2, cachedelta)
         else:
             # The first parent manifest isn't already loaded, so we'll
             # just encode a fulltext of the manifest and pass that
             # through to the revlog layer, and let it handle the delta
             # process.
             if self._treeondisk:
                 assert readtree, "readtree must be set for treemanifest writes"
                 m1 = readtree(self._dir, p1)
                 m2 = readtree(self._dir, p2)
                 n = self._addtree(m, transaction, link, m1, m2, readtree)
                 arraytext = None
             else:
                 text = m.text(self._usemanifestv2)
                 n = self.addrevision(text, transaction, link, p1, p2)
-                arraytext = array.array('c', text)
+                arraytext = bytearray(text)
 
         if arraytext is not None:
             self.fulltextcache[n] = arraytext
 
         return n
 
     def _addtree(self, m, transaction, link, m1, m2, readtree):
         # If the manifest is unchanged compared to one parent,
         # don't write a new revision
         if self._dir != '' and (m.unmodifiedsince(m1) or m.unmodifiedsince(m2)):
             return m.node()
         def writesubtree(subm, subp1, subp2):
             sublog = self.dirlog(subm.dir())
             sublog.add(subm, transaction, link, subp1, subp2, None, None,
                        readtree=readtree)
         m.writesubtrees(m1, m2, writesubtree)
         text = m.dirtext(self._usemanifestv2)
         n = None
         if self._dir != '':
             # Double-check whether contents are unchanged to one parent
             if text == m1.dirtext(self._usemanifestv2):
                 n = m1.node()
             elif text == m2.dirtext(self._usemanifestv2):
                 n = m2.node()
 
         if not n:
             n = self.addrevision(text, transaction, link, m1.node(), m2.node())
 
         # Save nodeid so parent manifest can calculate its nodeid
         m.setnode(n)
         return n
 
 class manifestlog(object):
     """A collection class representing the collection of manifest snapshots
     referenced by commits in the repository.
 
     In this situation, 'manifest' refers to the abstract concept of a snapshot
     of the list of files in the given commit. Consumers of the output of this
     class do not care about the implementation details of the actual manifests
     they receive (i.e. tree or flat or lazily loaded, etc)."""
     def __init__(self, opener, repo):
         usetreemanifest = False
         cachesize = 4
 
         opts = getattr(opener, 'options', None)
         if opts is not None:
             usetreemanifest = opts.get('treemanifest', usetreemanifest)
             cachesize = opts.get('manifestcachesize', cachesize)
         self._treeinmem = usetreemanifest
 
         self._oldmanifest = repo._constructmanifest()
         self._revlog = self._oldmanifest
 
         # A cache of the manifestctx or treemanifestctx for each directory
         self._dirmancache = {}
         self._dirmancache[''] = util.lrucachedict(cachesize)
 
         self.cachesize = cachesize
 
     def __getitem__(self, node):
         """Retrieves the manifest instance for the given node. Throws a
         LookupError if not found.
         """
         return self.get('', node)
 
     def get(self, dir, node, verify=True):
         """Retrieves the manifest instance for the given node. Throws a
         LookupError if not found.
 
         `verify` - if True an exception will be thrown if the node is not in
                    the revlog
         """
         if node in self._dirmancache.get(dir, ()):
             cachemf = self._dirmancache[dir][node]
             # The old manifest may put non-ctx manifests in the cache, so
             # skip those since they don't implement the full api.
             if (isinstance(cachemf, manifestctx) or
                 isinstance(cachemf, treemanifestctx)):
                 return cachemf
 
         if dir:
             if self._revlog._treeondisk:
                 if verify:
                     dirlog = self._revlog.dirlog(dir)
                     if node not in dirlog.nodemap:
                         raise LookupError(node, dirlog.indexfile,
                                           _('no node'))
                 m = treemanifestctx(self, dir, node)
             else:
                 raise error.Abort(
                         _("cannot ask for manifest directory '%s' in a flat "
                           "manifest") % dir)
         else:
             if verify:
                 if node not in self._revlog.nodemap:
                     raise LookupError(node, self._revlog.indexfile,
                                       _('no node'))
             if self._treeinmem:
                 m = treemanifestctx(self, '', node)
             else:
                 m = manifestctx(self, node)
 
         if node != revlog.nullid:
             mancache = self._dirmancache.get(dir)
             if not mancache:
                 mancache = util.lrucachedict(self.cachesize)
                 self._dirmancache[dir] = mancache
             mancache[node] = m
         return m
 
     def clearcaches(self):
         self._dirmancache.clear()
         self._revlog.clearcaches()
 
 class memmanifestctx(object):
     def __init__(self, manifestlog):
         self._manifestlog = manifestlog
         self._manifestdict = manifestdict()
 
     def _revlog(self):
         return self._manifestlog._revlog
 
     def new(self):
         return memmanifestctx(self._manifestlog)
 
     def copy(self):
         memmf = memmanifestctx(self._manifestlog)
         memmf._manifestdict = self.read().copy()
         return memmf
 
     def read(self):
         return self._manifestdict
 
     def write(self, transaction, link, p1, p2, added, removed):
         return self._revlog().add(self._manifestdict, transaction, link, p1, p2,
                                   added, removed)
 
 class manifestctx(object):
     """A class representing a single revision of a manifest, including its
     contents, its parent revs, and its linkrev.
     """
     def __init__(self, manifestlog, node):
         self._manifestlog = manifestlog
         self._data = None
 
         self._node = node
 
         # TODO: We eventually want p1, p2, and linkrev exposed on this class,
         # but let's add it later when something needs it and we can load it
         # lazily.
         #self.p1, self.p2 = revlog.parents(node)
         #rev = revlog.rev(node)
         #self.linkrev = revlog.linkrev(rev)
 
     def _revlog(self):
         return self._manifestlog._revlog
 
     def node(self):
         return self._node
 
     def new(self):
         return memmanifestctx(self._manifestlog)
 
     def copy(self):
         memmf = memmanifestctx(self._manifestlog)
         memmf._manifestdict = self.read().copy()
         return memmf
 
     @propertycache
     def parents(self):
         return self._revlog().parents(self._node)
 
     def read(self):
         if self._data is None:
             if self._node == revlog.nullid:
                 self._data = manifestdict()
             else:
                 rl = self._revlog()
                 text = rl.revision(self._node)
-                arraytext = array.array('c', text)
+                arraytext = bytearray(text)
                 rl._fulltextcache[self._node] = arraytext
                 self._data = manifestdict(text)
         return self._data
 
     def readfast(self, shallow=False):
         '''Calls either readdelta or read, based on which would be less work.
         readdelta is called if the delta is against the p1, and therefore can be
         read quickly.
 
         If `shallow` is True, nothing changes since this is a flat manifest.
         '''
         rl = self._revlog()
         r = rl.rev(self._node)
         deltaparent = rl.deltaparent(r)
         if deltaparent != revlog.nullrev and deltaparent in rl.parentrevs(r):
             return self.readdelta()
         return self.read()
 
     def readdelta(self, shallow=False):
         '''Returns a manifest containing just the entries that are present
         in this manifest, but not in its p1 manifest. This is efficient to read
         if the revlog delta is already p1.
 
         Changing the value of `shallow` has no effect on flat manifests.
         '''
         revlog = self._revlog()
         if revlog._usemanifestv2:
             # Need to perform a slow delta
             r0 = revlog.deltaparent(revlog.rev(self._node))
             m0 = self._manifestlog[revlog.node(r0)].read()
             m1 = self.read()
             md = manifestdict()
             for f, ((n0, fl0), (n1, fl1)) in m0.diff(m1).iteritems():
                 if n1:
                     md[f] = n1
                     if fl1:
                         md.setflag(f, fl1)
             return md
 
         r = revlog.rev(self._node)
         d = mdiff.patchtext(revlog.revdiff(revlog.deltaparent(r), r))
         return manifestdict(d)
 
     def find(self, key):
         return self.read().find(key)
 
 class memtreemanifestctx(object):
     def __init__(self, manifestlog, dir=''):
         self._manifestlog = manifestlog
         self._dir = dir
         self._treemanifest = treemanifest()
 
     def _revlog(self):
         return self._manifestlog._revlog
 
     def new(self, dir=''):
         return memtreemanifestctx(self._manifestlog, dir=dir)
 
     def copy(self):
         memmf = memtreemanifestctx(self._manifestlog, dir=self._dir)
         memmf._treemanifest = self._treemanifest.copy()
         return memmf
 
     def read(self):
         return self._treemanifest
 
     def write(self, transaction, link, p1, p2, added, removed):
         def readtree(dir, node):
             return self._manifestlog.get(dir, node).read()
         return self._revlog().add(self._treemanifest, transaction, link, p1, p2,
                                   added, removed, readtree=readtree)
 
 class treemanifestctx(object):
     def __init__(self, manifestlog, dir, node):
         self._manifestlog = manifestlog
         self._dir = dir
         self._data = None
 
         self._node = node
 
         # TODO: Load p1/p2/linkrev lazily. They need to be lazily loaded so that
         # we can instantiate treemanifestctx objects for directories we don't
         # have on disk.
         #self.p1, self.p2 = revlog.parents(node)
         #rev = revlog.rev(node)
         #self.linkrev = revlog.linkrev(rev)
 
     def _revlog(self):
         return self._manifestlog._revlog.dirlog(self._dir)
 
     def read(self):
         if self._data is None:
             rl = self._revlog()
             if self._node == revlog.nullid:
                 self._data = treemanifest()
             elif rl._treeondisk:
                 m = treemanifest(dir=self._dir)
                 def gettext():
                     return rl.revision(self._node)
                 def readsubtree(dir, subm):
                     # Set verify to False since we need to be able to create
                     # subtrees for trees that don't exist on disk.
                     return self._manifestlog.get(dir, subm, verify=False).read()
                 m.read(gettext, readsubtree)
                 m.setnode(self._node)
                 self._data = m
             else:
                 text = rl.revision(self._node)
-                arraytext = array.array('c', text)
+                arraytext = bytearray(text)
                 rl.fulltextcache[self._node] = arraytext
                 self._data = treemanifest(dir=self._dir, text=text)
 
         return self._data
 
     def node(self):
         return self._node
 
     def new(self, dir=''):
         return memtreemanifestctx(self._manifestlog, dir=dir)
 
     def copy(self):
         memmf = memtreemanifestctx(self._manifestlog, dir=self._dir)
         memmf._treemanifest = self.read().copy()
         return memmf
 
     @propertycache
     def parents(self):
         return self._revlog().parents(self._node)
 
     def readdelta(self, shallow=False):
         '''Returns a manifest containing just the entries that are present
         in this manifest, but not in its p1 manifest. This is efficient to read
         if the revlog delta is already p1.
 
         If `shallow` is True, this will read the delta for this directory,
         without recursively reading subdirectory manifests. Instead, any
         subdirectory entry will be reported as it appears in the manifest, i.e.
         the subdirectory will be reported among files and distinguished only by
         its 't' flag.
         '''
         revlog = self._revlog()
         if shallow and not revlog._usemanifestv2:
             r = revlog.rev(self._node)
             d = mdiff.patchtext(revlog.revdiff(revlog.deltaparent(r), r))
             return manifestdict(d)
         else:
             # Need to perform a slow delta
             r0 = revlog.deltaparent(revlog.rev(self._node))
             m0 = self._manifestlog.get(self._dir, revlog.node(r0)).read()
             m1 = self.read()
             md = treemanifest(dir=self._dir)
             for f, ((n0, fl0), (n1, fl1)) in m0.diff(m1).iteritems():
                 if n1:
                     md[f] = n1
                     if fl1:
                         md.setflag(f, fl1)
             return md
 
     def readfast(self, shallow=False):
         '''Calls either readdelta or read, based on which would be less work.
         readdelta is called if the delta is against the p1, and therefore can be
         read quickly.
 
         If `shallow` is True, it only returns the entries from this manifest,
         and not any submanifests.
         '''
         rl = self._revlog()
         r = rl.rev(self._node)
         deltaparent = rl.deltaparent(r)
         if (deltaparent != revlog.nullrev and
             deltaparent in rl.parentrevs(r)):
             return self.readdelta(shallow=shallow)
 
         if shallow:
             return manifestdict(rl.revision(self._node))
         else:
             return self.read()
 
     def find(self, key):
         return self.read().find(key)

mercurial/tags.py

@@ -1,569 +1,568 b''
 # tags.py - read tag info from local repository
 #
 # Copyright 2009 Matt Mackall <[e-mail]>
 # Copyright 2009 Greg Ward <[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.
 
 # Currently this module only deals with reading and caching tags.
 # Eventually, it could take care of updating (adding/removing/moving)
 # tags too.
 
 from __future__ import absolute_import
 
 import array
 import errno
 
 from .node import (
     bin,
     hex,
     nullid,
     short,
 )
 from . import (
     encoding,
     error,
     scmutil,
     util,
 )
 
 array = array.array
 
 # Tags computation can be expensive and caches exist to make it fast in
 # the common case.
 #
 # The "hgtagsfnodes1" cache file caches the .hgtags filenode values for
 # each revision in the repository. The file is effectively an array of
 # fixed length records. Read the docs for "hgtagsfnodescache" for technical
 # details.
 #
 # The .hgtags filenode cache grows in proportion to the length of the
 # changelog. The file is truncated when the # changelog is stripped.
 #
 # The purpose of the filenode cache is to avoid the most expensive part
 # of finding global tags, which is looking up the .hgtags filenode in the
 # manifest for each head. This can take dozens or over 100ms for
 # repositories with very large manifests. Multiplied by dozens or even
 # hundreds of heads and there is a significant performance concern.
 #
 # There also exist a separate cache file for each repository filter.
 # These "tags-*" files store information about the history of tags.
 #
 # The tags cache files consists of a cache validation line followed by
 # a history of tags.
 #
 # The cache validation line has the format:
 #
 #   <tiprev> <tipnode> [<filteredhash>]
 #
 # <tiprev> is an integer revision and <tipnode> is a 40 character hex
 # node for that changeset. These redundantly identify the repository
 # tip from the time the cache was written. In addition, <filteredhash>,
 # if present, is a 40 character hex hash of the contents of the filtered
 # revisions for this filter. If the set of filtered revs changes, the
 # hash will change and invalidate the cache.
 #
 # The history part of the tags cache consists of lines of the form:
 #
 #   <node> <tag>
 #
 # (This format is identical to that of .hgtags files.)
 #
 # <tag> is the tag name and <node> is the 40 character hex changeset
 # the tag is associated with.
 #
 # Tags are written sorted by tag name.
 #
 # Tags associated with multiple changesets have an entry for each changeset.
 # The most recent changeset (in terms of revlog ordering for the head
 # setting it) for each tag is last.
 
 def findglobaltags(ui, repo, alltags, tagtypes):
     '''Find global tags in a repo.
 
     "alltags" maps tag name to (node, hist) 2-tuples.
 
     "tagtypes" maps tag name to tag type. Global tags always have the
     "global" tag type.
 
     The "alltags" and "tagtypes" dicts are updated in place. Empty dicts
     should be passed in.
 
     The tags cache is read and updated as a side-effect of calling.
     '''
     # This is so we can be lazy and assume alltags contains only global
     # tags when we pass it to _writetagcache().
     assert len(alltags) == len(tagtypes) == 0, \
            "findglobaltags() should be called first"
 
     (heads, tagfnode, valid, cachetags, shouldwrite) = _readtagcache(ui, repo)
     if cachetags is not None:
         assert not shouldwrite
         # XXX is this really 100% correct?  are there oddball special
         # cases where a global tag should outrank a local tag but won't,
         # because cachetags does not contain rank info?
         _updatetags(cachetags, 'global', alltags, tagtypes)
         return
 
     seen = set()  # set of fnode
     fctx = None
     for head in reversed(heads):  # oldest to newest
         assert head in repo.changelog.nodemap, \
                "tag cache returned bogus head %s" % short(head)
 
         fnode = tagfnode.get(head)
         if fnode and fnode not in seen:
             seen.add(fnode)
             if not fctx:
                 fctx = repo.filectx('.hgtags', fileid=fnode)
             else:
                 fctx = fctx.filectx(fnode)
 
             filetags = _readtags(ui, repo, fctx.data().splitlines(), fctx)
             _updatetags(filetags, 'global', alltags, tagtypes)
 
     # and update the cache (if necessary)
     if shouldwrite:
         _writetagcache(ui, repo, valid, alltags)
 
 def readlocaltags(ui, repo, alltags, tagtypes):
     '''Read local tags in repo. Update alltags and tagtypes.'''
     try:
         data = repo.vfs.read("localtags")
     except IOError as inst:
         if inst.errno != errno.ENOENT:
             raise
         return
 
     # localtags is in the local encoding; re-encode to UTF-8 on
     # input for consistency with the rest of this module.
     filetags = _readtags(
         ui, repo, data.splitlines(), "localtags",
         recode=encoding.fromlocal)
 
     # remove tags pointing to invalid nodes
     cl = repo.changelog
     for t in filetags.keys():
         try:
             cl.rev(filetags[t][0])
         except (LookupError, ValueError):
             del filetags[t]
 
     _updatetags(filetags, "local", alltags, tagtypes)
 
 def _readtaghist(ui, repo, lines, fn, recode=None, calcnodelines=False):
     '''Read tag definitions from a file (or any source of lines).
 
     This function returns two sortdicts with similar information:
 
     - the first dict, bintaghist, contains the tag information as expected by
       the _readtags function, i.e. a mapping from tag name to (node, hist):
         - node is the node id from the last line read for that name,
         - hist is the list of node ids previously associated with it (in file
           order). All node ids are binary, not hex.
 
     - the second dict, hextaglines, is a mapping from tag name to a list of
       [hexnode, line number] pairs, ordered from the oldest to the newest node.
 
     When calcnodelines is False the hextaglines dict is not calculated (an
     empty dict is returned). This is done to improve this function's
     performance in cases where the line numbers are not needed.
     '''
 
     bintaghist = util.sortdict()
     hextaglines = util.sortdict()
     count = 0
 
     def dbg(msg):
         ui.debug("%s, line %s: %s\n" % (fn, count, msg))
 
     for nline, line in enumerate(lines):
         count += 1
         if not line:
             continue
         try:
             (nodehex, name) = line.split(" ", 1)
         except ValueError:
             dbg("cannot parse entry")
             continue
         name = name.strip()
         if recode:
             name = recode(name)
         try:
             nodebin = bin(nodehex)
         except TypeError:
             dbg("node '%s' is not well formed" % nodehex)
             continue
 
         # update filetags
         if calcnodelines:
             # map tag name to a list of line numbers
             if name not in hextaglines:
                 hextaglines[name] = []
             hextaglines[name].append([nodehex, nline])
             continue
         # map tag name to (node, hist)
         if name not in bintaghist:
             bintaghist[name] = []
         bintaghist[name].append(nodebin)
     return bintaghist, hextaglines
 
 def _readtags(ui, repo, lines, fn, recode=None, calcnodelines=False):
     '''Read tag definitions from a file (or any source of lines).
 
     Returns a mapping from tag name to (node, hist).
 
     "node" is the node id from the last line read for that name. "hist"
     is the list of node ids previously associated with it (in file order).
     All node ids are binary, not hex.
     '''
     filetags, nodelines = _readtaghist(ui, repo, lines, fn, recode=recode,
                                        calcnodelines=calcnodelines)
     # util.sortdict().__setitem__ is much slower at replacing then inserting
     # new entries. The difference can matter if there are thousands of tags.
     # Create a new sortdict to avoid the performance penalty.
     newtags = util.sortdict()
     for tag, taghist in filetags.items():
         newtags[tag] = (taghist[-1], taghist[:-1])
     return newtags
 
 def _updatetags(filetags, tagtype, alltags, tagtypes):
     '''Incorporate the tag info read from one file into the two
     dictionaries, alltags and tagtypes, that contain all tag
     info (global across all heads plus local).'''
 
     for name, nodehist in filetags.iteritems():
         if name not in alltags:
             alltags[name] = nodehist
             tagtypes[name] = tagtype
             continue
 
         # we prefer alltags[name] if:
         #  it supersedes us OR
         #  mutual supersedes and it has a higher rank
         # otherwise we win because we're tip-most
         anode, ahist = nodehist
         bnode, bhist = alltags[name]
         if (bnode != anode and anode in bhist and
             (bnode not in ahist or len(bhist) > len(ahist))):
             anode = bnode
         else:
             tagtypes[name] = tagtype
         ahist.extend([n for n in bhist if n not in ahist])
         alltags[name] = anode, ahist
 
 def _filename(repo):
     """name of a tagcache file for a given repo or repoview"""
     filename = 'cache/tags2'
     if repo.filtername:
         filename = '%s-%s' % (filename, repo.filtername)
     return filename
 
 def _readtagcache(ui, repo):
     '''Read the tag cache.
 
     Returns a tuple (heads, fnodes, validinfo, cachetags, shouldwrite).
 
     If the cache is completely up-to-date, "cachetags" is a dict of the
     form returned by _readtags() and "heads", "fnodes", and "validinfo" are
     None and "shouldwrite" is False.
 
     If the cache is not up to date, "cachetags" is None. "heads" is a list
     of all heads currently in the repository, ordered from tip to oldest.
     "validinfo" is a tuple describing cache validation info. This is used
     when writing the tags cache. "fnodes" is a mapping from head to .hgtags
     filenode. "shouldwrite" is True.
 
     If the cache is not up to date, the caller is responsible for reading tag
     info from each returned head. (See findglobaltags().)
     '''
     try:
         cachefile = repo.vfs(_filename(repo), 'r')
         # force reading the file for static-http
         cachelines = iter(cachefile)
     except IOError:
         cachefile = None
 
     cacherev = None
     cachenode = None
     cachehash = None
     if cachefile:
         try:
             validline = next(cachelines)
             validline = validline.split()
             cacherev = int(validline[0])
             cachenode = bin(validline[1])
             if len(validline) > 2:
                 cachehash = bin(validline[2])
         except Exception:
             # corruption of the cache, just recompute it.
             pass
 
     tipnode = repo.changelog.tip()
     tiprev = len(repo.changelog) - 1
 
     # Case 1 (common): tip is the same, so nothing has changed.
     # (Unchanged tip trivially means no changesets have been added.
     # But, thanks to localrepository.destroyed(), it also means none
     # have been destroyed by strip or rollback.)
     if (cacherev == tiprev
             and cachenode == tipnode
             and cachehash == scmutil.filteredhash(repo, tiprev)):
         tags = _readtags(ui, repo, cachelines, cachefile.name)
         cachefile.close()
         return (None, None, None, tags, False)
     if cachefile:
         cachefile.close()               # ignore rest of file
 
     valid = (tiprev, tipnode, scmutil.filteredhash(repo, tiprev))
 
     repoheads = repo.heads()
     # Case 2 (uncommon): empty repo; get out quickly and don't bother
     # writing an empty cache.
     if repoheads == [nullid]:
         return ([], {}, valid, {}, False)
 
     # Case 3 (uncommon): cache file missing or empty.
 
     # Case 4 (uncommon): tip rev decreased.  This should only happen
     # when we're called from localrepository.destroyed().  Refresh the
     # cache so future invocations will not see disappeared heads in the
     # cache.
 
     # Case 5 (common): tip has changed, so we've added/replaced heads.
 
     # As it happens, the code to handle cases 3, 4, 5 is the same.
 
     # N.B. in case 4 (nodes destroyed), "new head" really means "newly
     # exposed".
     if not len(repo.file('.hgtags')):
         # No tags have ever been committed, so we can avoid a
         # potentially expensive search.
         return ([], {}, valid, None, True)
 
     starttime = util.timer()
 
     # Now we have to lookup the .hgtags filenode for every new head.
     # This is the most expensive part of finding tags, so performance
     # depends primarily on the size of newheads.  Worst case: no cache
     # file, so newheads == repoheads.
     fnodescache = hgtagsfnodescache(repo.unfiltered())
     cachefnode = {}
     for head in reversed(repoheads):
         fnode = fnodescache.getfnode(head)
         if fnode != nullid:
             cachefnode[head] = fnode
 
     fnodescache.write()
 
     duration = util.timer() - starttime
     ui.log('tagscache',
            '%d/%d cache hits/lookups in %0.4f '
            'seconds\n',
            fnodescache.hitcount, fnodescache.lookupcount, duration)
 
     # Caller has to iterate over all heads, but can use the filenodes in
     # cachefnode to get to each .hgtags revision quickly.
     return (repoheads, cachefnode, valid, None, True)
 
 def _writetagcache(ui, repo, valid, cachetags):
     filename = _filename(repo)
     try:
         cachefile = repo.vfs(filename, 'w', atomictemp=True)
     except (OSError, IOError):
         return
 
     ui.log('tagscache', 'writing .hg/%s with %d tags\n',
            filename, len(cachetags))
 
     if valid[2]:
         cachefile.write('%d %s %s\n' % (valid[0], hex(valid[1]), hex(valid[2])))
     else:
         cachefile.write('%d %s\n' % (valid[0], hex(valid[1])))
 
     # Tag names in the cache are in UTF-8 -- which is the whole reason
     # we keep them in UTF-8 throughout this module.  If we converted
     # them local encoding on input, we would lose info writing them to
     # the cache.
     for (name, (node, hist)) in sorted(cachetags.iteritems()):
         for n in hist:
             cachefile.write("%s %s\n" % (hex(n), name))
         cachefile.write("%s %s\n" % (hex(node), name))
 
     try:
         cachefile.close()
     except (OSError, IOError):
         pass
 
 _fnodescachefile = 'cache/hgtagsfnodes1'
 _fnodesrecsize = 4 + 20 # changeset fragment + filenode
 _fnodesmissingrec = '\xff' * 24
 
 class hgtagsfnodescache(object):
     """Persistent cache mapping revisions to .hgtags filenodes.
 
     The cache is an array of records. Each item in the array corresponds to
     a changelog revision. Values in the array contain the first 4 bytes of
     the node hash and the 20 bytes .hgtags filenode for that revision.
 
     The first 4 bytes are present as a form of verification. Repository
     stripping and rewriting may change the node at a numeric revision in the
     changelog. The changeset fragment serves as a verifier to detect
     rewriting. This logic is shared with the rev branch cache (see
     branchmap.py).
 
     The instance holds in memory the full cache content but entries are
     only parsed on read.
 
     Instances behave like lists. ``c[i]`` works where i is a rev or
     changeset node. Missing indexes are populated automatically on access.
     """
     def __init__(self, repo):
         assert repo.filtername is None
 
         self._repo = repo
 
         # Only for reporting purposes.
         self.lookupcount = 0
         self.hitcount = 0
 
-        self._raw = array('c')
 
         try:
             data = repo.vfs.read(_fnodescachefile)
         except (OSError, IOError):
             data = ""
-        self._raw.fromstring(data)
+        self._raw = bytearray(data)
 
         # The end state of self._raw is an array that is of the exact length
         # required to hold a record for every revision in the repository.
         # We truncate or extend the array as necessary. self._dirtyoffset is
         # defined to be the start offset at which we need to write the output
         # file. This offset is also adjusted when new entries are calculated
         # for array members.
         cllen = len(repo.changelog)
         wantedlen = cllen * _fnodesrecsize
         rawlen = len(self._raw)
 
         self._dirtyoffset = None
 
         if rawlen < wantedlen:
             self._dirtyoffset = rawlen
             self._raw.extend('\xff' * (wantedlen - rawlen))
         elif rawlen > wantedlen:
             # There's no easy way to truncate array instances. This seems
             # slightly less evil than copying a potentially large array slice.
             for i in range(rawlen - wantedlen):
                 self._raw.pop()
             self._dirtyoffset = len(self._raw)
 
     def getfnode(self, node, computemissing=True):
         """Obtain the filenode of the .hgtags file at a specified revision.
 
         If the value is in the cache, the entry will be validated and returned.
         Otherwise, the filenode will be computed and returned unless
         "computemissing" is False, in which case None will be returned without
         any potentially expensive computation being performed.
 
         If an .hgtags does not exist at the specified revision, nullid is
         returned.
         """
         ctx = self._repo[node]
         rev = ctx.rev()
 
         self.lookupcount += 1
 
         offset = rev * _fnodesrecsize
-        record = self._raw[offset:offset + _fnodesrecsize].tostring()
+        record = '%s' % self._raw[offset:offset + _fnodesrecsize]
         properprefix = node[0:4]
 
         # Validate and return existing entry.
         if record != _fnodesmissingrec:
             fileprefix = record[0:4]
 
             if fileprefix == properprefix:
                 self.hitcount += 1
                 return record[4:]
 
             # Fall through.
 
         # If we get here, the entry is either missing or invalid.
 
         if not computemissing:
             return None
 
         # Populate missing entry.
         try:
             fnode = ctx.filenode('.hgtags')
         except error.LookupError:
             # No .hgtags file on this revision.
             fnode = nullid
 
         self._writeentry(offset, properprefix, fnode)
         return fnode
 
     def setfnode(self, node, fnode):
         """Set the .hgtags filenode for a given changeset."""
         assert len(fnode) == 20
         ctx = self._repo[node]
 
         # Do a lookup first to avoid writing if nothing has changed.
         if self.getfnode(ctx.node(), computemissing=False) == fnode:
             return
 
         self._writeentry(ctx.rev() * _fnodesrecsize, node[0:4], fnode)
 
     def _writeentry(self, offset, prefix, fnode):
         # Slices on array instances only accept other array.
-        entry = array('c', prefix + fnode)
+        entry = bytearray(prefix + fnode)
         self._raw[offset:offset + _fnodesrecsize] = entry
         # self._dirtyoffset could be None.
         self._dirtyoffset = min(self._dirtyoffset, offset) or 0
 
     def write(self):
         """Perform all necessary writes to cache file.
 
         This may no-op if no writes are needed or if a write lock could
         not be obtained.
         """
         if self._dirtyoffset is None:
             return
 
         data = self._raw[self._dirtyoffset:]
         if not data:
             return
 
         repo = self._repo
 
         try:
             lock = repo.wlock(wait=False)
         except error.LockError:
             repo.ui.log('tagscache',
                         'not writing .hg/%s because lock cannot be acquired\n' %
                         (_fnodescachefile))
             return
 
         try:
             f = repo.vfs.open(_fnodescachefile, 'ab')
             try:
                 # if the file has been truncated
                 actualoffset = f.tell()
                 if actualoffset < self._dirtyoffset:
                     self._dirtyoffset = actualoffset
                     data = self._raw[self._dirtyoffset:]
                 f.seek(self._dirtyoffset)
                 f.truncate()
                 repo.ui.log('tagscache',
                             'writing %d bytes to %s\n' % (
                             len(data), _fnodescachefile))
                 f.write(data)
                 self._dirtyoffset = None
             finally:
                 f.close()
         except (IOError, OSError) as inst:
             repo.ui.log('tagscache',
                         "couldn't write %s: %s\n" % (
                         _fnodescachefile, inst))
         finally:
             lock.release()