py3: drop unused aliases to array.array which are replaced with bytearray

mercurial/branchmap.py

@@ -1,520 +1,518 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), '%d' % 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 = 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[:] = 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 = 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, util.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 = 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/tags.py

@@ -1,568 +1,565 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
 
 
         try:
             data = repo.vfs.read(_fnodescachefile)
         except (OSError, IOError):
             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 = '%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 = 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()