merge with stable

hgext/convert/git.py

@@ -1,385 +1,385 b''
 # git.py - git support for the convert extension
 #
 #  Copyright 2005-2009 Matt Mackall <[e-mail]> and others
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 import os
 import subprocess
 from mercurial import util, config
 from mercurial.node import hex, nullid
 from mercurial.i18n import _
 
 from common import NoRepo, commit, converter_source, checktool
 
 class submodule(object):
     def __init__(self, path, node, url):
         self.path = path
         self.node = node
         self.url = url
 
     def hgsub(self):
         return "%s = [git]%s" % (self.path, self.url)
 
     def hgsubstate(self):
         return "%s %s" % (self.node, self.path)
 
 class convert_git(converter_source):
     # Windows does not support GIT_DIR= construct while other systems
     # cannot remove environment variable. Just assume none have
     # both issues.
     if util.safehasattr(os, 'unsetenv'):
         def gitopen(self, s, err=None):
             prevgitdir = os.environ.get('GIT_DIR')
             os.environ['GIT_DIR'] = self.path
             try:
                 if err == subprocess.PIPE:
                     (stdin, stdout, stderr) = util.popen3(s)
                     return stdout
                 elif err == subprocess.STDOUT:
                     return self.popen_with_stderr(s)
                 else:
                     return util.popen(s, 'rb')
             finally:
                 if prevgitdir is None:
                     del os.environ['GIT_DIR']
                 else:
                     os.environ['GIT_DIR'] = prevgitdir
 
         def gitpipe(self, s):
             prevgitdir = os.environ.get('GIT_DIR')
             os.environ['GIT_DIR'] = self.path
             try:
                 return util.popen3(s)
             finally:
                 if prevgitdir is None:
                     del os.environ['GIT_DIR']
                 else:
                     os.environ['GIT_DIR'] = prevgitdir
 
     else:
         def gitopen(self, s, err=None):
             if err == subprocess.PIPE:
                 (sin, so, se) = util.popen3('GIT_DIR=%s %s' % (self.path, s))
                 return so
             elif err == subprocess.STDOUT:
                     return self.popen_with_stderr(s)
             else:
                 return util.popen('GIT_DIR=%s %s' % (self.path, s), 'rb')
 
         def gitpipe(self, s):
             return util.popen3('GIT_DIR=%s %s' % (self.path, s))
 
     def popen_with_stderr(self, s):
         p = subprocess.Popen(s, shell=True, bufsize=-1,
                              close_fds=util.closefds,
                              stdin=subprocess.PIPE,
                              stdout=subprocess.PIPE,
                              stderr=subprocess.STDOUT,
                              universal_newlines=False,
                              env=None)
         return p.stdout
 
     def gitread(self, s):
         fh = self.gitopen(s)
         data = fh.read()
         return data, fh.close()
 
     def __init__(self, ui, path, rev=None):
         super(convert_git, self).__init__(ui, path, rev=rev)
 
         if os.path.isdir(path + "/.git"):
             path += "/.git"
         if not os.path.exists(path + "/objects"):
             raise NoRepo(_("%s does not look like a Git repository") % path)
 
         # The default value (50) is based on the default for 'git diff'.
         similarity = ui.configint('convert', 'git.similarity', default=50)
         if similarity < 0 or similarity > 100:
             raise util.Abort(_('similarity must be between 0 and 100'))
         if similarity > 0:
-            self.simopt = '--find-copies=%d%%' % similarity
+            self.simopt = '-C%d%%' % similarity
             findcopiesharder = ui.configbool('convert', 'git.findcopiesharder',
                                              False)
             if findcopiesharder:
                 self.simopt += ' --find-copies-harder'
         else:
             self.simopt = ''
 
         checktool('git', 'git')
 
         self.path = path
         self.submodules = []
 
         self.catfilepipe = self.gitpipe('git cat-file --batch')
 
     def after(self):
         for f in self.catfilepipe:
             f.close()
 
     def getheads(self):
         if not self.rev:
             heads, ret = self.gitread('git rev-parse --branches --remotes')
             heads = heads.splitlines()
         else:
             heads, ret = self.gitread("git rev-parse --verify %s" % self.rev)
             heads = [heads[:-1]]
         if ret:
             raise util.Abort(_('cannot retrieve git heads'))
         return heads
 
     def catfile(self, rev, type):
         if rev == hex(nullid):
             raise IOError
         self.catfilepipe[0].write(rev+'\n')
         self.catfilepipe[0].flush()
         info = self.catfilepipe[1].readline().split()
         if info[1] != type:
             raise util.Abort(_('cannot read %r object at %s') % (type, rev))
         size = int(info[2])
         data = self.catfilepipe[1].read(size)
         if len(data) < size:
             raise util.Abort(_('cannot read %r object at %s: unexpected size')
                              % (type, rev))
         # read the trailing newline
         self.catfilepipe[1].read(1)
         return data
 
     def getfile(self, name, rev):
         if rev == hex(nullid):
             return None, None
         if name == '.hgsub':
             data = '\n'.join([m.hgsub() for m in self.submoditer()])
             mode = ''
         elif name == '.hgsubstate':
             data = '\n'.join([m.hgsubstate() for m in self.submoditer()])
             mode = ''
         else:
             data = self.catfile(rev, "blob")
             mode = self.modecache[(name, rev)]
         return data, mode
 
     def submoditer(self):
         null = hex(nullid)
         for m in sorted(self.submodules, key=lambda p: p.path):
             if m.node != null:
                 yield m
 
     def parsegitmodules(self, content):
         """Parse the formatted .gitmodules file, example file format:
         [submodule "sub"]\n
         \tpath = sub\n
         \turl = git://giturl\n
         """
         self.submodules = []
         c = config.config()
         # Each item in .gitmodules starts with \t that cant be parsed
         c.parse('.gitmodules', content.replace('\t',''))
         for sec in c.sections():
             s = c[sec]
             if 'url' in s and 'path' in s:
                 self.submodules.append(submodule(s['path'], '', s['url']))
 
     def retrievegitmodules(self, version):
         modules, ret = self.gitread("git show %s:%s" % (version, '.gitmodules'))
         if ret:
             raise util.Abort(_('cannot read submodules config file in %s') %
                              version)
         self.parsegitmodules(modules)
         for m in self.submodules:
             node, ret = self.gitread("git rev-parse %s:%s" % (version, m.path))
             if ret:
                 continue
             m.node = node.strip()
 
     def getchanges(self, version, full):
         if full:
             raise util.Abort(_("convert from git do not support --full"))
         self.modecache = {}
         fh = self.gitopen("git diff-tree -z --root -m -r %s %s" % (
             self.simopt, version))
         changes = []
         copies = {}
         seen = set()
         entry = None
         subexists = [False]
         subdeleted = [False]
         difftree = fh.read().split('\x00')
         lcount = len(difftree)
         i = 0
 
         def add(entry, f, isdest):
             seen.add(f)
             h = entry[3]
             p = (entry[1] == "100755")
             s = (entry[1] == "120000")
             renamesource = (not isdest and entry[4][0] == 'R')
 
             if f == '.gitmodules':
                 subexists[0] = True
                 if entry[4] == 'D' or renamesource:
                     subdeleted[0] = True
                     changes.append(('.hgsub', hex(nullid)))
                 else:
                     changes.append(('.hgsub', ''))
             elif entry[1] == '160000' or entry[0] == ':160000':
                 subexists[0] = True
             else:
                 if renamesource:
                     h = hex(nullid)
                 self.modecache[(f, h)] = (p and "x") or (s and "l") or ""
                 changes.append((f, h))
 
         while i < lcount:
             l = difftree[i]
             i += 1
             if not entry:
                 if not l.startswith(':'):
                     continue
                 entry = l.split()
                 continue
             f = l
             if f not in seen:
                 add(entry, f, False)
             # A file can be copied multiple times, or modified and copied
             # simultaneously. So f can be repeated even if fdest isn't.
             if entry[4][0] in 'RC':
                 # rename or copy: next line is the destination
                 fdest = difftree[i]
                 i += 1
                 if fdest not in seen:
                     add(entry, fdest, True)
                     # .gitmodules isn't imported at all, so it being copied to
                     # and fro doesn't really make sense
                     if f != '.gitmodules' and fdest != '.gitmodules':
                         copies[fdest] = f
             entry = None
         if fh.close():
             raise util.Abort(_('cannot read changes in %s') % version)
 
         if subexists[0]:
             if subdeleted[0]:
                 changes.append(('.hgsubstate', hex(nullid)))
             else:
                 self.retrievegitmodules(version)
                 changes.append(('.hgsubstate', ''))
         return (changes, copies)
 
     def getcommit(self, version):
         c = self.catfile(version, "commit") # read the commit hash
         end = c.find("\n\n")
         message = c[end + 2:]
         message = self.recode(message)
         l = c[:end].splitlines()
         parents = []
         author = committer = None
         for e in l[1:]:
             n, v = e.split(" ", 1)
             if n == "author":
                 p = v.split()
                 tm, tz = p[-2:]
                 author = " ".join(p[:-2])
                 if author[0] == "<": author = author[1:-1]
                 author = self.recode(author)
             if n == "committer":
                 p = v.split()
                 tm, tz = p[-2:]
                 committer = " ".join(p[:-2])
                 if committer[0] == "<": committer = committer[1:-1]
                 committer = self.recode(committer)
             if n == "parent":
                 parents.append(v)
 
         if committer and committer != author:
             message += "\ncommitter: %s\n" % committer
         tzs, tzh, tzm = tz[-5:-4] + "1", tz[-4:-2], tz[-2:]
         tz = -int(tzs) * (int(tzh) * 3600 + int(tzm))
         date = tm + " " + str(tz)
 
         c = commit(parents=parents, date=date, author=author, desc=message,
                    rev=version)
         return c
 
     def numcommits(self):
         return len([None for _ in self.gitopen('git rev-list --all')])
 
     def gettags(self):
         tags = {}
         alltags = {}
         fh = self.gitopen('git ls-remote --tags "%s"' % self.path,
                           err=subprocess.STDOUT)
         prefix = 'refs/tags/'
 
         # Build complete list of tags, both annotated and bare ones
         for line in fh:
             line = line.strip()
             if line.startswith("error:") or line.startswith("fatal:"):
                 raise util.Abort(_('cannot read tags from %s') % self.path)
             node, tag = line.split(None, 1)
             if not tag.startswith(prefix):
                 continue
             alltags[tag[len(prefix):]] = node
         if fh.close():
             raise util.Abort(_('cannot read tags from %s') % self.path)
 
         # Filter out tag objects for annotated tag refs
         for tag in alltags:
             if tag.endswith('^{}'):
                 tags[tag[:-3]] = alltags[tag]
             else:
                 if tag + '^{}' in alltags:
                     continue
                 else:
                     tags[tag] = alltags[tag]
 
         return tags
 
     def getchangedfiles(self, version, i):
         changes = []
         if i is None:
             fh = self.gitopen("git diff-tree --root -m -r %s" % version)
             for l in fh:
                 if "\t" not in l:
                     continue
                 m, f = l[:-1].split("\t")
                 changes.append(f)
         else:
             fh = self.gitopen('git diff-tree --name-only --root -r %s '
                               '"%s^%s" --' % (version, version, i + 1))
             changes = [f.rstrip('\n') for f in fh]
         if fh.close():
             raise util.Abort(_('cannot read changes in %s') % version)
 
         return changes
 
     def getbookmarks(self):
         bookmarks = {}
 
         # Interesting references in git are prefixed
         prefix = 'refs/heads/'
         prefixlen = len(prefix)
 
         # factor two commands
         gitcmd = { 'remote/': 'git ls-remote --heads origin',
                           '': 'git show-ref'}
 
         # Origin heads
         for reftype in gitcmd:
             try:
                 fh = self.gitopen(gitcmd[reftype], err=subprocess.PIPE)
                 for line in fh:
                     line = line.strip()
                     rev, name = line.split(None, 1)
                     if not name.startswith(prefix):
                         continue
                     name = '%s%s' % (reftype, name[prefixlen:])
                     bookmarks[name] = rev
             except Exception:
                 pass
 
         return bookmarks
 
     def checkrevformat(self, revstr, mapname='splicemap'):
         """ git revision string is a 40 byte hex """
         self.checkhexformat(revstr, mapname)

mercurial/changegroup.py

@@ -1,831 +1,829 b''
 # changegroup.py - Mercurial changegroup manipulation functions
 #
 #  Copyright 2006 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 import weakref
 from i18n import _
 from node import nullrev, nullid, hex, short
 import mdiff, util, dagutil
 import struct, os, bz2, zlib, tempfile
 import discovery, error, phases, branchmap
 
 _CHANGEGROUPV1_DELTA_HEADER = "20s20s20s20s"
 _CHANGEGROUPV2_DELTA_HEADER = "20s20s20s20s20s"
 
 def readexactly(stream, n):
     '''read n bytes from stream.read and abort if less was available'''
     s = stream.read(n)
     if len(s) < n:
         raise util.Abort(_("stream ended unexpectedly"
                            " (got %d bytes, expected %d)")
                           % (len(s), n))
     return s
 
 def getchunk(stream):
     """return the next chunk from stream as a string"""
     d = readexactly(stream, 4)
     l = struct.unpack(">l", d)[0]
     if l <= 4:
         if l:
             raise util.Abort(_("invalid chunk length %d") % l)
         return ""
     return readexactly(stream, l - 4)
 
 def chunkheader(length):
     """return a changegroup chunk header (string)"""
     return struct.pack(">l", length + 4)
 
 def closechunk():
     """return a changegroup chunk header (string) for a zero-length chunk"""
     return struct.pack(">l", 0)
 
 class nocompress(object):
     def compress(self, x):
         return x
     def flush(self):
         return ""
 
 bundletypes = {
     "": ("", nocompress), # only when using unbundle on ssh and old http servers
                           # since the unification ssh accepts a header but there
                           # is no capability signaling it.
     "HG10UN": ("HG10UN", nocompress),
     "HG10BZ": ("HG10", lambda: bz2.BZ2Compressor()),
     "HG10GZ": ("HG10GZ", lambda: zlib.compressobj()),
 }
 
 # hgweb uses this list to communicate its preferred type
 bundlepriority = ['HG10GZ', 'HG10BZ', 'HG10UN']
 
 def writebundle(cg, filename, bundletype, vfs=None):
     """Write a bundle file and return its filename.
 
     Existing files will not be overwritten.
     If no filename is specified, a temporary file is created.
     bz2 compression can be turned off.
     The bundle file will be deleted in case of errors.
     """
 
     fh = None
     cleanup = None
     try:
         if filename:
             if vfs:
                 fh = vfs.open(filename, "wb")
             else:
                 fh = open(filename, "wb")
         else:
             fd, filename = tempfile.mkstemp(prefix="hg-bundle-", suffix=".hg")
             fh = os.fdopen(fd, "wb")
         cleanup = filename
 
         header, compressor = bundletypes[bundletype]
         fh.write(header)
         z = compressor()
 
         # parse the changegroup data, otherwise we will block
         # in case of sshrepo because we don't know the end of the stream
 
         # an empty chunkgroup is the end of the changegroup
         # a changegroup has at least 2 chunkgroups (changelog and manifest).
         # after that, an empty chunkgroup is the end of the changegroup
         for chunk in cg.getchunks():
             fh.write(z.compress(chunk))
         fh.write(z.flush())
         cleanup = None
         return filename
     finally:
         if fh is not None:
             fh.close()
         if cleanup is not None:
             if filename and vfs:
                 vfs.unlink(cleanup)
             else:
                 os.unlink(cleanup)
 
 def decompressor(fh, alg):
     if alg == 'UN':
         return fh
     elif alg == 'GZ':
         def generator(f):
             zd = zlib.decompressobj()
             for chunk in util.filechunkiter(f):
                 yield zd.decompress(chunk)
     elif alg == 'BZ':
         def generator(f):
             zd = bz2.BZ2Decompressor()
             zd.decompress("BZ")
             for chunk in util.filechunkiter(f, 4096):
                 yield zd.decompress(chunk)
     else:
         raise util.Abort("unknown bundle compression '%s'" % alg)
     return util.chunkbuffer(generator(fh))
 
 class cg1unpacker(object):
     deltaheader = _CHANGEGROUPV1_DELTA_HEADER
     deltaheadersize = struct.calcsize(deltaheader)
     def __init__(self, fh, alg):
         self._stream = decompressor(fh, alg)
         self._type = alg
         self.callback = None
     def compressed(self):
         return self._type != 'UN'
     def read(self, l):
         return self._stream.read(l)
     def seek(self, pos):
         return self._stream.seek(pos)
     def tell(self):
         return self._stream.tell()
     def close(self):
         return self._stream.close()
 
     def chunklength(self):
         d = readexactly(self._stream, 4)
         l = struct.unpack(">l", d)[0]
         if l <= 4:
             if l:
                 raise util.Abort(_("invalid chunk length %d") % l)
             return 0
         if self.callback:
             self.callback()
         return l - 4
 
     def changelogheader(self):
         """v10 does not have a changelog header chunk"""
         return {}
 
     def manifestheader(self):
         """v10 does not have a manifest header chunk"""
         return {}
 
     def filelogheader(self):
         """return the header of the filelogs chunk, v10 only has the filename"""
         l = self.chunklength()
         if not l:
             return {}
         fname = readexactly(self._stream, l)
         return {'filename': fname}
 
     def _deltaheader(self, headertuple, prevnode):
         node, p1, p2, cs = headertuple
         if prevnode is None:
             deltabase = p1
         else:
             deltabase = prevnode
         return node, p1, p2, deltabase, cs
 
     def deltachunk(self, prevnode):
         l = self.chunklength()
         if not l:
             return {}
         headerdata = readexactly(self._stream, self.deltaheadersize)
         header = struct.unpack(self.deltaheader, headerdata)
         delta = readexactly(self._stream, l - self.deltaheadersize)
         node, p1, p2, deltabase, cs = self._deltaheader(header, prevnode)
         return {'node': node, 'p1': p1, 'p2': p2, 'cs': cs,
                 'deltabase': deltabase, 'delta': delta}
 
     def getchunks(self):
         """returns all the chunks contains in the bundle
 
         Used when you need to forward the binary stream to a file or another
         network API. To do so, it parse the changegroup data, otherwise it will
         block in case of sshrepo because it don't know the end of the stream.
         """
         # an empty chunkgroup is the end of the changegroup
         # a changegroup has at least 2 chunkgroups (changelog and manifest).
         # after that, an empty chunkgroup is the end of the changegroup
         empty = False
         count = 0
         while not empty or count <= 2:
             empty = True
             count += 1
             while True:
                 chunk = getchunk(self)
                 if not chunk:
                     break
                 empty = False
                 yield chunkheader(len(chunk))
                 pos = 0
                 while pos < len(chunk):
                     next = pos + 2**20
                     yield chunk[pos:next]
                     pos = next
             yield closechunk()
 
 class cg2unpacker(cg1unpacker):
     deltaheader = _CHANGEGROUPV2_DELTA_HEADER
     deltaheadersize = struct.calcsize(deltaheader)
 
     def _deltaheader(self, headertuple, prevnode):
         node, p1, p2, deltabase, cs = headertuple
         return node, p1, p2, deltabase, cs
 
 class headerlessfixup(object):
     def __init__(self, fh, h):
         self._h = h
         self._fh = fh
     def read(self, n):
         if self._h:
             d, self._h = self._h[:n], self._h[n:]
             if len(d) < n:
                 d += readexactly(self._fh, n - len(d))
             return d
         return readexactly(self._fh, n)
 
 class cg1packer(object):
     deltaheader = _CHANGEGROUPV1_DELTA_HEADER
     def __init__(self, repo, bundlecaps=None):
         """Given a source repo, construct a bundler.
 
         bundlecaps is optional and can be used to specify the set of
         capabilities which can be used to build the bundle.
         """
         # Set of capabilities we can use to build the bundle.
         if bundlecaps is None:
             bundlecaps = set()
         self._bundlecaps = bundlecaps
         self._changelog = repo.changelog
         self._manifest = repo.manifest
         reorder = repo.ui.config('bundle', 'reorder', 'auto')
         if reorder == 'auto':
             reorder = None
         else:
             reorder = util.parsebool(reorder)
         self._repo = repo
         self._reorder = reorder
         self._progress = repo.ui.progress
     def close(self):
         return closechunk()
 
     def fileheader(self, fname):
         return chunkheader(len(fname)) + fname
 
     def group(self, nodelist, revlog, lookup, units=None, reorder=None):
         """Calculate a delta group, yielding a sequence of changegroup chunks
         (strings).
 
         Given a list of changeset revs, return a set of deltas and
         metadata corresponding to nodes. The first delta is
         first parent(nodelist[0]) -> nodelist[0], the receiver is
         guaranteed to have this parent as it has all history before
         these changesets. In the case firstparent is nullrev the
         changegroup starts with a full revision.
 
         If units is not None, progress detail will be generated, units specifies
         the type of revlog that is touched (changelog, manifest, etc.).
         """
         # if we don't have any revisions touched by these changesets, bail
         if len(nodelist) == 0:
             yield self.close()
             return
 
         # for generaldelta revlogs, we linearize the revs; this will both be
         # much quicker and generate a much smaller bundle
         if (revlog._generaldelta and reorder is not False) or reorder:
             dag = dagutil.revlogdag(revlog)
             revs = set(revlog.rev(n) for n in nodelist)
             revs = dag.linearize(revs)
         else:
             revs = sorted([revlog.rev(n) for n in nodelist])
 
         # add the parent of the first rev
         p = revlog.parentrevs(revs[0])[0]
         revs.insert(0, p)
 
         # build deltas
         total = len(revs) - 1
         msgbundling = _('bundling')
         for r in xrange(len(revs) - 1):
             if units is not None:
                 self._progress(msgbundling, r + 1, unit=units, total=total)
             prev, curr = revs[r], revs[r + 1]
             linknode = lookup(revlog.node(curr))
             for c in self.revchunk(revlog, curr, prev, linknode):
                 yield c
 
         yield self.close()
 
     # filter any nodes that claim to be part of the known set
     def prune(self, revlog, missing, commonrevs, source):
         rr, rl = revlog.rev, revlog.linkrev
         return [n for n in missing if rl(rr(n)) not in commonrevs]
 
     def generate(self, commonrevs, clnodes, fastpathlinkrev, source):
         '''yield a sequence of changegroup chunks (strings)'''
         repo = self._repo
         cl = self._changelog
         mf = self._manifest
         reorder = self._reorder
         progress = self._progress
 
         # for progress output
         msgbundling = _('bundling')
 
         mfs = {} # needed manifests
         fnodes = {} # needed file nodes
         changedfiles = set()
 
         # Callback for the changelog, used to collect changed files and manifest
         # nodes.
         # Returns the linkrev node (identity in the changelog case).
         def lookupcl(x):
             c = cl.read(x)
             changedfiles.update(c[3])
             # record the first changeset introducing this manifest version
             mfs.setdefault(c[0], x)
             return x
 
+        for chunk in self.group(clnodes, cl, lookupcl, units=_('changesets'),
+                                reorder=reorder):
+            yield chunk
+        progress(msgbundling, None)
+
         # Callback for the manifest, used to collect linkrevs for filelog
         # revisions.
         # Returns the linkrev node (collected in lookupcl).
         def lookupmf(x):
             clnode = mfs[x]
             if not fastpathlinkrev:
                 mdata = mf.readfast(x)
                 for f, n in mdata.iteritems():
                     if f in changedfiles:
                         # record the first changeset introducing this filelog
                         # version
-                        fnodes[f].setdefault(n, clnode)
+                        fnodes.setdefault(f, {}).setdefault(n, clnode)
             return clnode
 
-        for chunk in self.group(clnodes, cl, lookupcl, units=_('changesets'),
-                                reorder=reorder):
-            yield chunk
-        progress(msgbundling, None)
-
-        for f in changedfiles:
-            fnodes[f] = {}
         mfnodes = self.prune(mf, mfs, commonrevs, source)
         for chunk in self.group(mfnodes, mf, lookupmf, units=_('manifests'),
                                 reorder=reorder):
             yield chunk
         progress(msgbundling, None)
 
         mfs.clear()
         needed = set(cl.rev(x) for x in clnodes)
 
         def linknodes(filerevlog, fname):
             if fastpathlinkrev:
                 llr = filerevlog.linkrev
                 def genfilenodes():
                     for r in filerevlog:
                         linkrev = llr(r)
                         if linkrev in needed:
                             yield filerevlog.node(r), cl.node(linkrev)
-                fnodes[fname] = dict(genfilenodes())
+                return dict(genfilenodes())
             return fnodes.get(fname, {})
 
         for chunk in self.generatefiles(changedfiles, linknodes, commonrevs,
                                         source):
             yield chunk
 
         yield self.close()
         progress(msgbundling, None)
 
         if clnodes:
             repo.hook('outgoing', node=hex(clnodes[0]), source=source)
 
     def generatefiles(self, changedfiles, linknodes, commonrevs, source):
         repo = self._repo
         progress = self._progress
         reorder = self._reorder
         msgbundling = _('bundling')
 
         total = len(changedfiles)
         # for progress output
         msgfiles = _('files')
         for i, fname in enumerate(sorted(changedfiles)):
             filerevlog = repo.file(fname)
             if not filerevlog:
                 raise util.Abort(_("empty or missing revlog for %s") % fname)
 
             linkrevnodes = linknodes(filerevlog, fname)
             # Lookup for filenodes, we collected the linkrev nodes above in the
             # fastpath case and with lookupmf in the slowpath case.
             def lookupfilelog(x):
                 return linkrevnodes[x]
 
             filenodes = self.prune(filerevlog, linkrevnodes, commonrevs, source)
             if filenodes:
                 progress(msgbundling, i + 1, item=fname, unit=msgfiles,
                          total=total)
                 yield self.fileheader(fname)
                 for chunk in self.group(filenodes, filerevlog, lookupfilelog,
                                         reorder=reorder):
                     yield chunk
 
     def deltaparent(self, revlog, rev, p1, p2, prev):
         return prev
 
     def revchunk(self, revlog, rev, prev, linknode):
         node = revlog.node(rev)
         p1, p2 = revlog.parentrevs(rev)
         base = self.deltaparent(revlog, rev, p1, p2, prev)
 
         prefix = ''
         if base == nullrev:
             delta = revlog.revision(node)
             prefix = mdiff.trivialdiffheader(len(delta))
         else:
             delta = revlog.revdiff(base, rev)
         p1n, p2n = revlog.parents(node)
         basenode = revlog.node(base)
         meta = self.builddeltaheader(node, p1n, p2n, basenode, linknode)
         meta += prefix
         l = len(meta) + len(delta)
         yield chunkheader(l)
         yield meta
         yield delta
     def builddeltaheader(self, node, p1n, p2n, basenode, linknode):
         # do nothing with basenode, it is implicitly the previous one in HG10
         return struct.pack(self.deltaheader, node, p1n, p2n, linknode)
 
 class cg2packer(cg1packer):
 
     deltaheader = _CHANGEGROUPV2_DELTA_HEADER
 
     def group(self, nodelist, revlog, lookup, units=None, reorder=None):
         if (revlog._generaldelta and reorder is not True):
             reorder = False
         return super(cg2packer, self).group(nodelist, revlog, lookup,
                                             units=units, reorder=reorder)
 
     def deltaparent(self, revlog, rev, p1, p2, prev):
         dp = revlog.deltaparent(rev)
         # avoid storing full revisions; pick prev in those cases
         # also pick prev when we can't be sure remote has dp
         if dp == nullrev or (dp != p1 and dp != p2 and dp != prev):
             return prev
         return dp
 
     def builddeltaheader(self, node, p1n, p2n, basenode, linknode):
         return struct.pack(self.deltaheader, node, p1n, p2n, basenode, linknode)
 
 packermap = {'01': (cg1packer, cg1unpacker),
              '02': (cg2packer, cg2unpacker)}
 
 def _changegroupinfo(repo, nodes, source):
     if repo.ui.verbose or source == 'bundle':
         repo.ui.status(_("%d changesets found\n") % len(nodes))
     if repo.ui.debugflag:
         repo.ui.debug("list of changesets:\n")
         for node in nodes:
             repo.ui.debug("%s\n" % hex(node))
 
 def getsubsetraw(repo, outgoing, bundler, source, fastpath=False):
     repo = repo.unfiltered()
     commonrevs = outgoing.common
     csets = outgoing.missing
     heads = outgoing.missingheads
     # We go through the fast path if we get told to, or if all (unfiltered
     # heads have been requested (since we then know there all linkrevs will
     # be pulled by the client).
     heads.sort()
     fastpathlinkrev = fastpath or (
             repo.filtername is None and heads == sorted(repo.heads()))
 
     repo.hook('preoutgoing', throw=True, source=source)
     _changegroupinfo(repo, csets, source)
     return bundler.generate(commonrevs, csets, fastpathlinkrev, source)
 
 def getsubset(repo, outgoing, bundler, source, fastpath=False):
     gengroup = getsubsetraw(repo, outgoing, bundler, source, fastpath)
     return cg1unpacker(util.chunkbuffer(gengroup), 'UN')
 
 def changegroupsubset(repo, roots, heads, source):
     """Compute a changegroup consisting of all the nodes that are
     descendants of any of the roots and ancestors of any of the heads.
     Return a chunkbuffer object whose read() method will return
     successive changegroup chunks.
 
     It is fairly complex as determining which filenodes and which
     manifest nodes need to be included for the changeset to be complete
     is non-trivial.
 
     Another wrinkle is doing the reverse, figuring out which changeset in
     the changegroup a particular filenode or manifestnode belongs to.
     """
     cl = repo.changelog
     if not roots:
         roots = [nullid]
     # TODO: remove call to nodesbetween.
     csets, roots, heads = cl.nodesbetween(roots, heads)
     discbases = []
     for n in roots:
         discbases.extend([p for p in cl.parents(n) if p != nullid])
     outgoing = discovery.outgoing(cl, discbases, heads)
     bundler = cg1packer(repo)
     return getsubset(repo, outgoing, bundler, source)
 
 def getlocalchangegroupraw(repo, source, outgoing, bundlecaps=None,
                            version='01'):
     """Like getbundle, but taking a discovery.outgoing as an argument.
 
     This is only implemented for local repos and reuses potentially
     precomputed sets in outgoing. Returns a raw changegroup generator."""
     if not outgoing.missing:
         return None
     bundler = packermap[version][0](repo, bundlecaps)
     return getsubsetraw(repo, outgoing, bundler, source)
 
 def getlocalchangegroup(repo, source, outgoing, bundlecaps=None):
     """Like getbundle, but taking a discovery.outgoing as an argument.
 
     This is only implemented for local repos and reuses potentially
     precomputed sets in outgoing."""
     if not outgoing.missing:
         return None
     bundler = cg1packer(repo, bundlecaps)
     return getsubset(repo, outgoing, bundler, source)
 
 def _computeoutgoing(repo, heads, common):
     """Computes which revs are outgoing given a set of common
     and a set of heads.
 
     This is a separate function so extensions can have access to
     the logic.
 
     Returns a discovery.outgoing object.
     """
     cl = repo.changelog
     if common:
         hasnode = cl.hasnode
         common = [n for n in common if hasnode(n)]
     else:
         common = [nullid]
     if not heads:
         heads = cl.heads()
     return discovery.outgoing(cl, common, heads)
 
 def getchangegroupraw(repo, source, heads=None, common=None, bundlecaps=None,
                       version='01'):
     """Like changegroupsubset, but returns the set difference between the
     ancestors of heads and the ancestors common.
 
     If heads is None, use the local heads. If common is None, use [nullid].
 
     If version is None, use a version '1' changegroup.
 
     The nodes in common might not all be known locally due to the way the
     current discovery protocol works. Returns a raw changegroup generator.
     """
     outgoing = _computeoutgoing(repo, heads, common)
     return getlocalchangegroupraw(repo, source, outgoing, bundlecaps=bundlecaps,
                                   version=version)
 
 def getchangegroup(repo, source, heads=None, common=None, bundlecaps=None):
     """Like changegroupsubset, but returns the set difference between the
     ancestors of heads and the ancestors common.
 
     If heads is None, use the local heads. If common is None, use [nullid].
 
     The nodes in common might not all be known locally due to the way the
     current discovery protocol works.
     """
     outgoing = _computeoutgoing(repo, heads, common)
     return getlocalchangegroup(repo, source, outgoing, bundlecaps=bundlecaps)
 
 def changegroup(repo, basenodes, source):
     # to avoid a race we use changegroupsubset() (issue1320)
     return changegroupsubset(repo, basenodes, repo.heads(), source)
 
 def addchangegroupfiles(repo, source, revmap, trp, pr, needfiles):
     revisions = 0
     files = 0
     while True:
         chunkdata = source.filelogheader()
         if not chunkdata:
             break
         f = chunkdata["filename"]
         repo.ui.debug("adding %s revisions\n" % f)
         pr()
         fl = repo.file(f)
         o = len(fl)
         if not fl.addgroup(source, revmap, trp):
             raise util.Abort(_("received file revlog group is empty"))
         revisions += len(fl) - o
         files += 1
         if f in needfiles:
             needs = needfiles[f]
             for new in xrange(o, len(fl)):
                 n = fl.node(new)
                 if n in needs:
                     needs.remove(n)
                 else:
                     raise util.Abort(
                         _("received spurious file revlog entry"))
             if not needs:
                 del needfiles[f]
     repo.ui.progress(_('files'), None)
 
     for f, needs in needfiles.iteritems():
         fl = repo.file(f)
         for n in needs:
             try:
                 fl.rev(n)
             except error.LookupError:
                 raise util.Abort(
                     _('missing file data for %s:%s - run hg verify') %
                     (f, hex(n)))
 
     return revisions, files
 
 def addchangegroup(repo, source, srctype, url, emptyok=False,
                    targetphase=phases.draft):
     """Add the changegroup returned by source.read() to this repo.
     srctype is a string like 'push', 'pull', or 'unbundle'.  url is
     the URL of the repo where this changegroup is coming from.
 
     Return an integer summarizing the change to this repo:
     - nothing changed or no source: 0
     - more heads than before: 1+added heads (2..n)
     - fewer heads than before: -1-removed heads (-2..-n)
     - number of heads stays the same: 1
     """
     repo = repo.unfiltered()
     def csmap(x):
         repo.ui.debug("add changeset %s\n" % short(x))
         return len(cl)
 
     def revmap(x):
         return cl.rev(x)
 
     if not source:
         return 0
 
     changesets = files = revisions = 0
     efiles = set()
 
     tr = repo.transaction("\n".join([srctype, util.hidepassword(url)]))
     # The transaction could have been created before and already carries source
     # information. In this case we use the top level data. We overwrite the
     # argument because we need to use the top level value (if they exist) in
     # this function.
     srctype = tr.hookargs.setdefault('source', srctype)
     url = tr.hookargs.setdefault('url', url)
 
     # write changelog data to temp files so concurrent readers will not see
     # inconsistent view
     cl = repo.changelog
     cl.delayupdate(tr)
     oldheads = cl.heads()
     try:
         repo.hook('prechangegroup', throw=True, **tr.hookargs)
 
         trp = weakref.proxy(tr)
         # pull off the changeset group
         repo.ui.status(_("adding changesets\n"))
         clstart = len(cl)
         class prog(object):
             step = _('changesets')
             count = 1
             ui = repo.ui
             total = None
             def __call__(repo):
                 repo.ui.progress(repo.step, repo.count, unit=_('chunks'),
                                  total=repo.total)
                 repo.count += 1
         pr = prog()
         source.callback = pr
 
         source.changelogheader()
         srccontent = cl.addgroup(source, csmap, trp)
         if not (srccontent or emptyok):
             raise util.Abort(_("received changelog group is empty"))
         clend = len(cl)
         changesets = clend - clstart
         for c in xrange(clstart, clend):
             efiles.update(repo[c].files())
         efiles = len(efiles)
         repo.ui.progress(_('changesets'), None)
 
         # pull off the manifest group
         repo.ui.status(_("adding manifests\n"))
         pr.step = _('manifests')
         pr.count = 1
         pr.total = changesets # manifests <= changesets
         # no need to check for empty manifest group here:
         # if the result of the merge of 1 and 2 is the same in 3 and 4,
         # no new manifest will be created and the manifest group will
         # be empty during the pull
         source.manifestheader()
         repo.manifest.addgroup(source, revmap, trp)
         repo.ui.progress(_('manifests'), None)
 
         needfiles = {}
         if repo.ui.configbool('server', 'validate', default=False):
             # validate incoming csets have their manifests
             for cset in xrange(clstart, clend):
                 mfest = repo.changelog.read(repo.changelog.node(cset))[0]
                 mfest = repo.manifest.readdelta(mfest)
                 # store file nodes we must see
                 for f, n in mfest.iteritems():
                     needfiles.setdefault(f, set()).add(n)
 
         # process the files
         repo.ui.status(_("adding file changes\n"))
         pr.step = _('files')
         pr.count = 1
         pr.total = efiles
         source.callback = None
 
         newrevs, newfiles = addchangegroupfiles(repo, source, revmap, trp, pr,
                                                 needfiles)
         revisions += newrevs
         files += newfiles
 
         dh = 0
         if oldheads:
             heads = cl.heads()
             dh = len(heads) - len(oldheads)
             for h in heads:
                 if h not in oldheads and repo[h].closesbranch():
                     dh -= 1
         htext = ""
         if dh:
             htext = _(" (%+d heads)") % dh
 
         repo.ui.status(_("added %d changesets"
                          " with %d changes to %d files%s\n")
                          % (changesets, revisions, files, htext))
         repo.invalidatevolatilesets()
 
         if changesets > 0:
             p = lambda: tr.writepending() and repo.root or ""
             if 'node' not in tr.hookargs:
                 tr.hookargs['node'] = hex(cl.node(clstart))
                 hookargs = dict(tr.hookargs)
             else:
                 hookargs = dict(tr.hookargs)
                 hookargs['node'] = hex(cl.node(clstart))
             repo.hook('pretxnchangegroup', throw=True, pending=p, **hookargs)
 
         added = [cl.node(r) for r in xrange(clstart, clend)]
         publishing = repo.ui.configbool('phases', 'publish', True)
         if srctype in ('push', 'serve'):
             # Old servers can not push the boundary themselves.
             # New servers won't push the boundary if changeset already
             # exists locally as secret
             #
             # We should not use added here but the list of all change in
             # the bundle
             if publishing:
                 phases.advanceboundary(repo, tr, phases.public, srccontent)
             else:
                 # Those changesets have been pushed from the outside, their
                 # phases are going to be pushed alongside. Therefor
                 # `targetphase` is ignored.
                 phases.advanceboundary(repo, tr, phases.draft, srccontent)
                 phases.retractboundary(repo, tr, phases.draft, added)
         elif srctype != 'strip':
             # publishing only alter behavior during push
             #
             # strip should not touch boundary at all
             phases.retractboundary(repo, tr, targetphase, added)
 
         if changesets > 0:
             if srctype != 'strip':
                 # During strip, branchcache is invalid but coming call to
                 # `destroyed` will repair it.
                 # In other case we can safely update cache on disk.
                 branchmap.updatecache(repo.filtered('served'))
 
             def runhooks():
                 # These hooks run when the lock releases, not when the
                 # transaction closes. So it's possible for the changelog
                 # to have changed since we last saw it.
                 if clstart >= len(repo):
                     return
 
                 # forcefully update the on-disk branch cache
                 repo.ui.debug("updating the branch cache\n")
                 repo.hook("changegroup", **hookargs)
 
                 for n in added:
                     args = hookargs.copy()
                     args['node'] = hex(n)
                     repo.hook("incoming", **args)
 
                 newheads = [h for h in repo.heads() if h not in oldheads]
                 repo.ui.log("incoming",
                             "%s incoming changes - new heads: %s\n",
                             len(added),
                             ', '.join([hex(c[:6]) for c in newheads]))
 
             tr.addpostclose('changegroup-runhooks-%020i' % clstart,
                             lambda: repo._afterlock(runhooks))
 
         tr.close()
 
     finally:
         tr.release()
     # never return 0 here:
     if dh < 0:
         return dh - 1
     else:
         return dh + 1

mercurial/hgweb/webcommands.py

@@ -1,1107 +1,1107 b''
 #
 # Copyright 21 May 2005 - (c) 2005 Jake Edge <[e-mail]>
 # 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.
 
 import os, mimetypes, re, cgi, copy
 import webutil
 from mercurial import error, encoding, archival, templater, templatefilters
 from mercurial.node import short, hex
 from mercurial import util
 from common import paritygen, staticfile, get_contact, ErrorResponse
 from common import HTTP_OK, HTTP_FORBIDDEN, HTTP_NOT_FOUND
 from mercurial import graphmod, patch
 from mercurial import help as helpmod
 from mercurial import scmutil
 from mercurial.i18n import _
 from mercurial.error import ParseError, RepoLookupError, Abort
 from mercurial import revset
 
 # __all__ is populated with the allowed commands. Be sure to add to it if
 # you're adding a new command, or the new command won't work.
 
 __all__ = [
    'log', 'rawfile', 'file', 'changelog', 'shortlog', 'changeset', 'rev',
    'manifest', 'tags', 'bookmarks', 'branches', 'summary', 'filediff', 'diff',
    'comparison', 'annotate', 'filelog', 'archive', 'static', 'graph', 'help',
 ]
 
 def log(web, req, tmpl):
     if 'file' in req.form and req.form['file'][0]:
         return filelog(web, req, tmpl)
     else:
         return changelog(web, req, tmpl)
 
 def rawfile(web, req, tmpl):
     guessmime = web.configbool('web', 'guessmime', False)
 
     path = webutil.cleanpath(web.repo, req.form.get('file', [''])[0])
     if not path:
         content = manifest(web, req, tmpl)
         req.respond(HTTP_OK, web.ctype)
         return content
 
     try:
         fctx = webutil.filectx(web.repo, req)
     except error.LookupError, inst:
         try:
             content = manifest(web, req, tmpl)
             req.respond(HTTP_OK, web.ctype)
             return content
         except ErrorResponse:
             raise inst
 
     path = fctx.path()
     text = fctx.data()
     mt = 'application/binary'
     if guessmime:
         mt = mimetypes.guess_type(path)[0]
         if mt is None:
             mt = util.binary(text) and 'application/binary' or 'text/plain'
     if mt.startswith('text/'):
         mt += '; charset="%s"' % encoding.encoding
 
     req.respond(HTTP_OK, mt, path, body=text)
     return []
 
 def _filerevision(web, tmpl, fctx):
     f = fctx.path()
     text = fctx.data()
     parity = paritygen(web.stripecount)
 
     if util.binary(text):
         mt = mimetypes.guess_type(f)[0] or 'application/octet-stream'
         text = '(binary:%s)' % mt
 
     def lines():
         for lineno, t in enumerate(text.splitlines(True)):
             yield {"line": t,
                    "lineid": "l%d" % (lineno + 1),
                    "linenumber": "% 6d" % (lineno + 1),
                    "parity": parity.next()}
 
     return tmpl("filerevision",
                 file=f,
                 path=webutil.up(f),
                 text=lines(),
                 rev=fctx.rev(),
                 node=fctx.hex(),
                 author=fctx.user(),
                 date=fctx.date(),
                 desc=fctx.description(),
                 extra=fctx.extra(),
                 branch=webutil.nodebranchnodefault(fctx),
                 parent=webutil.parents(fctx),
                 child=webutil.children(fctx),
                 rename=webutil.renamelink(fctx),
                 permissions=fctx.manifest().flags(f))
 
 def file(web, req, tmpl):
     path = webutil.cleanpath(web.repo, req.form.get('file', [''])[0])
     if not path:
         return manifest(web, req, tmpl)
     try:
         return _filerevision(web, tmpl, webutil.filectx(web.repo, req))
     except error.LookupError, inst:
         try:
             return manifest(web, req, tmpl)
         except ErrorResponse:
             raise inst
 
 def _search(web, req, tmpl):
     MODE_REVISION = 'rev'
     MODE_KEYWORD = 'keyword'
     MODE_REVSET = 'revset'
 
     def revsearch(ctx):
         yield ctx
 
     def keywordsearch(query):
         lower = encoding.lower
         qw = lower(query).split()
 
         def revgen():
             cl = web.repo.changelog
             for i in xrange(len(web.repo) - 1, 0, -100):
                 l = []
                 for j in cl.revs(max(0, i - 99), i):
                     ctx = web.repo[j]
                     l.append(ctx)
                 l.reverse()
                 for e in l:
                     yield e
 
         for ctx in revgen():
             miss = 0
             for q in qw:
                 if not (q in lower(ctx.user()) or
                         q in lower(ctx.description()) or
                         q in lower(" ".join(ctx.files()))):
                     miss = 1
                     break
             if miss:
                 continue
 
             yield ctx
 
     def revsetsearch(revs):
         for r in revs:
             yield web.repo[r]
 
     searchfuncs = {
         MODE_REVISION: (revsearch, 'exact revision search'),
         MODE_KEYWORD: (keywordsearch, 'literal keyword search'),
         MODE_REVSET: (revsetsearch, 'revset expression search'),
     }
 
     def getsearchmode(query):
         try:
             ctx = web.repo[query]
         except (error.RepoError, error.LookupError):
             # query is not an exact revision pointer, need to
             # decide if it's a revset expression or keywords
             pass
         else:
             return MODE_REVISION, ctx
 
         revdef = 'reverse(%s)' % query
         try:
             tree, pos = revset.parse(revdef)
         except ParseError:
             # can't parse to a revset tree
             return MODE_KEYWORD, query
 
         if revset.depth(tree) <= 2:
             # no revset syntax used
             return MODE_KEYWORD, query
 
         if util.any((token, (value or '')[:3]) == ('string', 're:')
                     for token, value, pos in revset.tokenize(revdef)):
             return MODE_KEYWORD, query
 
         funcsused = revset.funcsused(tree)
         if not funcsused.issubset(revset.safesymbols):
             return MODE_KEYWORD, query
 
         mfunc = revset.match(web.repo.ui, revdef)
         try:
             revs = mfunc(web.repo, revset.baseset(web.repo))
             return MODE_REVSET, revs
             # ParseError: wrongly placed tokens, wrongs arguments, etc
             # RepoLookupError: no such revision, e.g. in 'revision:'
             # Abort: bookmark/tag not exists
             # LookupError: ambiguous identifier, e.g. in '(bc)' on a large repo
         except (ParseError, RepoLookupError, Abort, LookupError):
             return MODE_KEYWORD, query
 
     def changelist(**map):
         count = 0
 
         for ctx in searchfunc[0](funcarg):
             count += 1
             n = ctx.node()
             showtags = webutil.showtag(web.repo, tmpl, 'changelogtag', n)
             files = webutil.listfilediffs(tmpl, ctx.files(), n, web.maxfiles)
 
             yield tmpl('searchentry',
                        parity=parity.next(),
                        author=ctx.user(),
                        parent=webutil.parents(ctx),
                        child=webutil.children(ctx),
                        changelogtag=showtags,
                        desc=ctx.description(),
                        extra=ctx.extra(),
                        date=ctx.date(),
                        files=files,
                        rev=ctx.rev(),
                        node=hex(n),
                        tags=webutil.nodetagsdict(web.repo, n),
                        bookmarks=webutil.nodebookmarksdict(web.repo, n),
                        inbranch=webutil.nodeinbranch(web.repo, ctx),
                        branches=webutil.nodebranchdict(web.repo, ctx))
 
             if count >= revcount:
                 break
 
     query = req.form['rev'][0]
     revcount = web.maxchanges
     if 'revcount' in req.form:
         try:
             revcount = int(req.form.get('revcount', [revcount])[0])
             revcount = max(revcount, 1)
             tmpl.defaults['sessionvars']['revcount'] = revcount
         except ValueError:
             pass
 
     lessvars = copy.copy(tmpl.defaults['sessionvars'])
     lessvars['revcount'] = max(revcount / 2, 1)
     lessvars['rev'] = query
     morevars = copy.copy(tmpl.defaults['sessionvars'])
     morevars['revcount'] = revcount * 2
     morevars['rev'] = query
 
     mode, funcarg = getsearchmode(query)
 
     if 'forcekw' in req.form:
         showforcekw = ''
         showunforcekw = searchfuncs[mode][1]
         mode = MODE_KEYWORD
         funcarg = query
     else:
         if mode != MODE_KEYWORD:
             showforcekw = searchfuncs[MODE_KEYWORD][1]
         else:
             showforcekw = ''
         showunforcekw = ''
 
     searchfunc = searchfuncs[mode]
 
     tip = web.repo['tip']
     parity = paritygen(web.stripecount)
 
     return tmpl('search', query=query, node=tip.hex(),
                 entries=changelist, archives=web.archivelist("tip"),
                 morevars=morevars, lessvars=lessvars,
                 modedesc=searchfunc[1],
                 showforcekw=showforcekw, showunforcekw=showunforcekw)
 
 def changelog(web, req, tmpl, shortlog=False):
 
     query = ''
     if 'node' in req.form:
         ctx = webutil.changectx(web.repo, req)
     elif 'rev' in req.form:
         return _search(web, req, tmpl)
     else:
         ctx = web.repo['tip']
 
     def changelist():
         revs = []
         if pos != -1:
             revs = web.repo.changelog.revs(pos, 0)
         curcount = 0
         for i in revs:
             ctx = web.repo[i]
             n = ctx.node()
             showtags = webutil.showtag(web.repo, tmpl, 'changelogtag', n)
             files = webutil.listfilediffs(tmpl, ctx.files(), n, web.maxfiles)
 
             curcount += 1
             if curcount > revcount + 1:
                 break
             yield {"parity": parity.next(),
                    "author": ctx.user(),
                    "parent": webutil.parents(ctx, i - 1),
                    "child": webutil.children(ctx, i + 1),
                    "changelogtag": showtags,
                    "desc": ctx.description(),
                    "extra": ctx.extra(),
                    "date": ctx.date(),
                    "files": files,
                    "rev": i,
                    "node": hex(n),
                    "tags": webutil.nodetagsdict(web.repo, n),
                    "bookmarks": webutil.nodebookmarksdict(web.repo, n),
                    "inbranch": webutil.nodeinbranch(web.repo, ctx),
                    "branches": webutil.nodebranchdict(web.repo, ctx)
             }
 
     revcount = shortlog and web.maxshortchanges or web.maxchanges
     if 'revcount' in req.form:
         try:
             revcount = int(req.form.get('revcount', [revcount])[0])
             revcount = max(revcount, 1)
             tmpl.defaults['sessionvars']['revcount'] = revcount
         except ValueError:
             pass
 
     lessvars = copy.copy(tmpl.defaults['sessionvars'])
     lessvars['revcount'] = max(revcount / 2, 1)
     morevars = copy.copy(tmpl.defaults['sessionvars'])
     morevars['revcount'] = revcount * 2
 
     count = len(web.repo)
     pos = ctx.rev()
     parity = paritygen(web.stripecount)
 
     changenav = webutil.revnav(web.repo).gen(pos, revcount, count)
 
     entries = list(changelist())
     latestentry = entries[:1]
     if len(entries) > revcount:
         nextentry = entries[-1:]
         entries = entries[:-1]
     else:
         nextentry = []
 
     return tmpl(shortlog and 'shortlog' or 'changelog', changenav=changenav,
                 node=ctx.hex(), rev=pos, changesets=count,
                 entries=entries,
                 latestentry=latestentry, nextentry=nextentry,
                 archives=web.archivelist("tip"), revcount=revcount,
                 morevars=morevars, lessvars=lessvars, query=query)
 
 def shortlog(web, req, tmpl):
     return changelog(web, req, tmpl, shortlog=True)
 
 def changeset(web, req, tmpl):
     ctx = webutil.changectx(web.repo, req)
     basectx = webutil.basechangectx(web.repo, req)
     if basectx is None:
         basectx = ctx.p1()
     showtags = webutil.showtag(web.repo, tmpl, 'changesettag', ctx.node())
     showbookmarks = webutil.showbookmark(web.repo, tmpl, 'changesetbookmark',
                                          ctx.node())
     showbranch = webutil.nodebranchnodefault(ctx)
 
     files = []
     parity = paritygen(web.stripecount)
     for blockno, f in enumerate(ctx.files()):
         template = f in ctx and 'filenodelink' or 'filenolink'
         files.append(tmpl(template,
                           node=ctx.hex(), file=f, blockno=blockno + 1,
                           parity=parity.next()))
 
     style = web.config('web', 'style', 'paper')
     if 'style' in req.form:
         style = req.form['style'][0]
 
     parity = paritygen(web.stripecount)
     diffs = webutil.diffs(web.repo, tmpl, ctx, basectx, None, parity, style)
 
     parity = paritygen(web.stripecount)
     diffstatgen = webutil.diffstatgen(ctx, basectx)
     diffstat = webutil.diffstat(tmpl, ctx, diffstatgen, parity)
 
     return tmpl('changeset',
                 diff=diffs,
                 rev=ctx.rev(),
                 node=ctx.hex(),
                 parent=webutil.parents(ctx),
                 child=webutil.children(ctx),
                 basenode=basectx.hex(),
                 changesettag=showtags,
                 changesetbookmark=showbookmarks,
                 changesetbranch=showbranch,
                 author=ctx.user(),
                 desc=ctx.description(),
                 extra=ctx.extra(),
                 date=ctx.date(),
                 files=files,
                 diffsummary=lambda **x: webutil.diffsummary(diffstatgen),
                 diffstat=diffstat,
                 archives=web.archivelist(ctx.hex()),
                 tags=webutil.nodetagsdict(web.repo, ctx.node()),
                 bookmarks=webutil.nodebookmarksdict(web.repo, ctx.node()),
                 branch=webutil.nodebranchnodefault(ctx),
                 inbranch=webutil.nodeinbranch(web.repo, ctx),
                 branches=webutil.nodebranchdict(web.repo, ctx))
 
 rev = changeset
 
 def decodepath(path):
     """Hook for mapping a path in the repository to a path in the
     working copy.
 
     Extensions (e.g., largefiles) can override this to remap files in
     the virtual file system presented by the manifest command below."""
     return path
 
 def manifest(web, req, tmpl):
     ctx = webutil.changectx(web.repo, req)
     path = webutil.cleanpath(web.repo, req.form.get('file', [''])[0])
     mf = ctx.manifest()
     node = ctx.node()
 
     files = {}
     dirs = {}
     parity = paritygen(web.stripecount)
 
     if path and path[-1] != "/":
         path += "/"
     l = len(path)
     abspath = "/" + path
 
     for full, n in mf.iteritems():
         # the virtual path (working copy path) used for the full
         # (repository) path
         f = decodepath(full)
 
         if f[:l] != path:
             continue
         remain = f[l:]
         elements = remain.split('/')
         if len(elements) == 1:
             files[remain] = full
         else:
             h = dirs # need to retain ref to dirs (root)
             for elem in elements[0:-1]:
                 if elem not in h:
                     h[elem] = {}
                 h = h[elem]
                 if len(h) > 1:
                     break
             h[None] = None # denotes files present
 
     if mf and not files and not dirs:
         raise ErrorResponse(HTTP_NOT_FOUND, 'path not found: ' + path)
 
     def filelist(**map):
         for f in sorted(files):
             full = files[f]
 
             fctx = ctx.filectx(full)
             yield {"file": full,
                    "parity": parity.next(),
                    "basename": f,
                    "date": fctx.date(),
                    "size": fctx.size(),
                    "permissions": mf.flags(full)}
 
     def dirlist(**map):
         for d in sorted(dirs):
 
             emptydirs = []
             h = dirs[d]
             while isinstance(h, dict) and len(h) == 1:
                 k, v = h.items()[0]
                 if v:
                     emptydirs.append(k)
                 h = v
 
             path = "%s%s" % (abspath, d)
             yield {"parity": parity.next(),
                    "path": path,
                    "emptydirs": "/".join(emptydirs),
                    "basename": d}
 
     return tmpl("manifest",
                 rev=ctx.rev(),
                 node=hex(node),
                 path=abspath,
                 up=webutil.up(abspath),
                 upparity=parity.next(),
                 fentries=filelist,
                 dentries=dirlist,
                 archives=web.archivelist(hex(node)),
                 tags=webutil.nodetagsdict(web.repo, node),
                 bookmarks=webutil.nodebookmarksdict(web.repo, node),
                 inbranch=webutil.nodeinbranch(web.repo, ctx),
                 branches=webutil.nodebranchdict(web.repo, ctx))
 
 def tags(web, req, tmpl):
     i = list(reversed(web.repo.tagslist()))
     parity = paritygen(web.stripecount)
 
     def entries(notip, latestonly, **map):
         t = i
         if notip:
             t = [(k, n) for k, n in i if k != "tip"]
         if latestonly:
             t = t[:1]
         for k, n in t:
             yield {"parity": parity.next(),
                    "tag": k,
                    "date": web.repo[n].date(),
                    "node": hex(n)}
 
     return tmpl("tags",
                 node=hex(web.repo.changelog.tip()),
                 entries=lambda **x: entries(False, False, **x),
                 entriesnotip=lambda **x: entries(True, False, **x),
                 latestentry=lambda **x: entries(True, True, **x))
 
 def bookmarks(web, req, tmpl):
     i = [b for b in web.repo._bookmarks.items() if b[1] in web.repo]
     parity = paritygen(web.stripecount)
 
     def entries(latestonly, **map):
         if latestonly:
             t = [min(i)]
         else:
             t = sorted(i)
         for k, n in t:
             yield {"parity": parity.next(),
                    "bookmark": k,
                    "date": web.repo[n].date(),
                    "node": hex(n)}
 
     return tmpl("bookmarks",
                 node=hex(web.repo.changelog.tip()),
                 entries=lambda **x: entries(latestonly=False, **x),
                 latestentry=lambda **x: entries(latestonly=True, **x))
 
 def branches(web, req, tmpl):
     tips = []
     heads = web.repo.heads()
     parity = paritygen(web.stripecount)
     sortkey = lambda item: (not item[1], item[0].rev())
 
     def entries(limit, **map):
         count = 0
         if not tips:
             for tag, hs, tip, closed in web.repo.branchmap().iterbranches():
                 tips.append((web.repo[tip], closed))
         for ctx, closed in sorted(tips, key=sortkey, reverse=True):
             if limit > 0 and count >= limit:
                 return
             count += 1
             if closed:
                 status = 'closed'
             elif ctx.node() not in heads:
                 status = 'inactive'
             else:
                 status = 'open'
             yield {'parity': parity.next(),
                    'branch': ctx.branch(),
                    'status': status,
                    'node': ctx.hex(),
                    'date': ctx.date()}
 
     return tmpl('branches', node=hex(web.repo.changelog.tip()),
                 entries=lambda **x: entries(0, **x),
                 latestentry=lambda **x: entries(1, **x))
 
 def summary(web, req, tmpl):
     i = reversed(web.repo.tagslist())
 
     def tagentries(**map):
         parity = paritygen(web.stripecount)
         count = 0
         for k, n in i:
             if k == "tip": # skip tip
                 continue
 
             count += 1
             if count > 10: # limit to 10 tags
                 break
 
             yield tmpl("tagentry",
                        parity=parity.next(),
                        tag=k,
                        node=hex(n),
                        date=web.repo[n].date())
 
     def bookmarks(**map):
         parity = paritygen(web.stripecount)
         marks = [b for b in web.repo._bookmarks.items() if b[1] in web.repo]
         for k, n in sorted(marks)[:10]:  # limit to 10 bookmarks
             yield {'parity': parity.next(),
                    'bookmark': k,
                    'date': web.repo[n].date(),
                    'node': hex(n)}
 
     def branches(**map):
         parity = paritygen(web.stripecount)
 
         b = web.repo.branchmap()
         l = [(-web.repo.changelog.rev(tip), tip, tag)
              for tag, heads, tip, closed in b.iterbranches()]
         for r, n, t in sorted(l):
             yield {'parity': parity.next(),
                    'branch': t,
                    'node': hex(n),
                    'date': web.repo[n].date()}
 
     def changelist(**map):
         parity = paritygen(web.stripecount, offset=start - end)
         l = [] # build a list in forward order for efficiency
         revs = []
         if start < end:
             revs = web.repo.changelog.revs(start, end - 1)
         for i in revs:
             ctx = web.repo[i]
             n = ctx.node()
             hn = hex(n)
 
             l.append(tmpl(
                'shortlogentry',
                 parity=parity.next(),
                 author=ctx.user(),
                 desc=ctx.description(),
                 extra=ctx.extra(),
                 date=ctx.date(),
                 rev=i,
                 node=hn,
                 tags=webutil.nodetagsdict(web.repo, n),
                 bookmarks=webutil.nodebookmarksdict(web.repo, n),
                 inbranch=webutil.nodeinbranch(web.repo, ctx),
                 branches=webutil.nodebranchdict(web.repo, ctx)))
 
         l.reverse()
         yield l
 
     tip = web.repo['tip']
     count = len(web.repo)
     start = max(0, count - web.maxchanges)
     end = min(count, start + web.maxchanges)
 
     return tmpl("summary",
                 desc=web.config("web", "description", "unknown"),
                 owner=get_contact(web.config) or "unknown",
                 lastchange=tip.date(),
                 tags=tagentries,
                 bookmarks=bookmarks,
                 branches=branches,
                 shortlog=changelist,
                 node=tip.hex(),
                 archives=web.archivelist("tip"))
 
 def filediff(web, req, tmpl):
     fctx, ctx = None, None
     try:
         fctx = webutil.filectx(web.repo, req)
     except LookupError:
         ctx = webutil.changectx(web.repo, req)
         path = webutil.cleanpath(web.repo, req.form['file'][0])
         if path not in ctx.files():
             raise
 
     if fctx is not None:
         n = fctx.node()
         path = fctx.path()
         ctx = fctx.changectx()
     else:
         n = ctx.node()
         # path already defined in except clause
 
     parity = paritygen(web.stripecount)
     style = web.config('web', 'style', 'paper')
     if 'style' in req.form:
         style = req.form['style'][0]
 
     diffs = webutil.diffs(web.repo, tmpl, ctx, None, [path], parity, style)
     rename = fctx and webutil.renamelink(fctx) or []
     ctx = fctx and fctx or ctx
     return tmpl("filediff",
                 file=path,
                 node=hex(n),
                 rev=ctx.rev(),
                 date=ctx.date(),
                 desc=ctx.description(),
                 extra=ctx.extra(),
                 author=ctx.user(),
                 rename=rename,
                 branch=webutil.nodebranchnodefault(ctx),
                 parent=webutil.parents(ctx),
                 child=webutil.children(ctx),
                 diff=diffs)
 
 diff = filediff
 
 def comparison(web, req, tmpl):
     ctx = webutil.changectx(web.repo, req)
     if 'file' not in req.form:
         raise ErrorResponse(HTTP_NOT_FOUND, 'file not given')
     path = webutil.cleanpath(web.repo, req.form['file'][0])
     rename = path in ctx and webutil.renamelink(ctx[path]) or []
 
     parsecontext = lambda v: v == 'full' and -1 or int(v)
     if 'context' in req.form:
         context = parsecontext(req.form['context'][0])
     else:
         context = parsecontext(web.config('web', 'comparisoncontext', '5'))
 
     def filelines(f):
         if util.binary(f.data()):
             mt = mimetypes.guess_type(f.path())[0]
             if not mt:
                 mt = 'application/octet-stream'
             return [_('(binary file %s, hash: %s)') % (mt, hex(f.filenode()))]
         return f.data().splitlines()
 
     parent = ctx.p1()
     leftrev = parent.rev()
     leftnode = parent.node()
     rightrev = ctx.rev()
     rightnode = ctx.node()
     if path in ctx:
         fctx = ctx[path]
         rightlines = filelines(fctx)
         if path not in parent:
             leftlines = ()
         else:
             pfctx = parent[path]
             leftlines = filelines(pfctx)
     else:
         rightlines = ()
         fctx = ctx.parents()[0][path]
         leftlines = filelines(fctx)
 
     comparison = webutil.compare(tmpl, context, leftlines, rightlines)
     return tmpl('filecomparison',
                 file=path,
                 node=hex(ctx.node()),
                 rev=ctx.rev(),
                 date=ctx.date(),
                 desc=ctx.description(),
                 extra=ctx.extra(),
                 author=ctx.user(),
                 rename=rename,
                 branch=webutil.nodebranchnodefault(ctx),
                 parent=webutil.parents(fctx),
                 child=webutil.children(fctx),
                 leftrev=leftrev,
                 leftnode=hex(leftnode),
                 rightrev=rightrev,
                 rightnode=hex(rightnode),
                 comparison=comparison)
 
 def annotate(web, req, tmpl):
     fctx = webutil.filectx(web.repo, req)
     f = fctx.path()
     parity = paritygen(web.stripecount)
     diffopts = patch.diffopts(web.repo.ui, untrusted=True, section='annotate')
 
     def annotate(**map):
         last = None
         if util.binary(fctx.data()):
             mt = (mimetypes.guess_type(fctx.path())[0]
                   or 'application/octet-stream')
             lines = enumerate([((fctx.filectx(fctx.filerev()), 1),
                                 '(binary:%s)' % mt)])
         else:
             lines = enumerate(fctx.annotate(follow=True, linenumber=True,
                                             diffopts=diffopts))
         for lineno, ((f, targetline), l) in lines:
             fnode = f.filenode()
 
             if last != fnode:
                 last = fnode
 
             yield {"parity": parity.next(),
                    "node": f.hex(),
                    "rev": f.rev(),
                    "author": f.user(),
                    "desc": f.description(),
                    "extra": f.extra(),
                    "file": f.path(),
                    "targetline": targetline,
                    "line": l,
                    "lineid": "l%d" % (lineno + 1),
                    "linenumber": "% 6d" % (lineno + 1),
                    "revdate": f.date()}
 
     return tmpl("fileannotate",
                 file=f,
                 annotate=annotate,
                 path=webutil.up(f),
                 rev=fctx.rev(),
                 node=fctx.hex(),
                 author=fctx.user(),
                 date=fctx.date(),
                 desc=fctx.description(),
                 extra=fctx.extra(),
                 rename=webutil.renamelink(fctx),
                 branch=webutil.nodebranchnodefault(fctx),
                 parent=webutil.parents(fctx),
                 child=webutil.children(fctx),
                 permissions=fctx.manifest().flags(f))
 
 def filelog(web, req, tmpl):
 
     try:
         fctx = webutil.filectx(web.repo, req)
         f = fctx.path()
         fl = fctx.filelog()
     except error.LookupError:
         f = webutil.cleanpath(web.repo, req.form['file'][0])
         fl = web.repo.file(f)
         numrevs = len(fl)
         if not numrevs: # file doesn't exist at all
             raise
         rev = webutil.changectx(web.repo, req).rev()
         first = fl.linkrev(0)
         if rev < first: # current rev is from before file existed
             raise
         frev = numrevs - 1
         while fl.linkrev(frev) > rev:
             frev -= 1
         fctx = web.repo.filectx(f, fl.linkrev(frev))
 
     revcount = web.maxshortchanges
     if 'revcount' in req.form:
         try:
             revcount = int(req.form.get('revcount', [revcount])[0])
             revcount = max(revcount, 1)
             tmpl.defaults['sessionvars']['revcount'] = revcount
         except ValueError:
             pass
 
     lessvars = copy.copy(tmpl.defaults['sessionvars'])
     lessvars['revcount'] = max(revcount / 2, 1)
     morevars = copy.copy(tmpl.defaults['sessionvars'])
     morevars['revcount'] = revcount * 2
 
     count = fctx.filerev() + 1
     start = max(0, fctx.filerev() - revcount + 1) # first rev on this page
     end = min(count, start + revcount) # last rev on this page
     parity = paritygen(web.stripecount, offset=start - end)
 
     def entries():
         l = []
 
         repo = web.repo
         revs = fctx.filelog().revs(start, end - 1)
         for i in revs:
             iterfctx = fctx.filectx(i)
 
             l.append({"parity": parity.next(),
                       "filerev": i,
                       "file": f,
                       "node": iterfctx.hex(),
                       "author": iterfctx.user(),
                       "date": iterfctx.date(),
                       "rename": webutil.renamelink(iterfctx),
                       "parent": webutil.parents(iterfctx),
                       "child": webutil.children(iterfctx),
                       "desc": iterfctx.description(),
                       "extra": iterfctx.extra(),
                       "tags": webutil.nodetagsdict(repo, iterfctx.node()),
                       "bookmarks": webutil.nodebookmarksdict(
                           repo, iterfctx.node()),
                       "branch": webutil.nodebranchnodefault(iterfctx),
                       "inbranch": webutil.nodeinbranch(repo, iterfctx),
                       "branches": webutil.nodebranchdict(repo, iterfctx)})
         for e in reversed(l):
             yield e
 
     entries = list(entries())
     latestentry = entries[:1]
 
     revnav = webutil.filerevnav(web.repo, fctx.path())
     nav = revnav.gen(end - 1, revcount, count)
     return tmpl("filelog", file=f, node=fctx.hex(), nav=nav,
                 entries=entries,
                 latestentry=latestentry,
                 revcount=revcount, morevars=morevars, lessvars=lessvars)
 
 def archive(web, req, tmpl):
     type_ = req.form.get('type', [None])[0]
     allowed = web.configlist("web", "allow_archive")
     key = req.form['node'][0]
 
     if type_ not in web.archives:
         msg = 'Unsupported archive type: %s' % type_
         raise ErrorResponse(HTTP_NOT_FOUND, msg)
 
     if not ((type_ in allowed or
         web.configbool("web", "allow" + type_, False))):
         msg = 'Archive type not allowed: %s' % type_
         raise ErrorResponse(HTTP_FORBIDDEN, msg)
 
     reponame = re.sub(r"\W+", "-", os.path.basename(web.reponame))
     cnode = web.repo.lookup(key)
     arch_version = key
     if cnode == key or key == 'tip':
         arch_version = short(cnode)
     name = "%s-%s" % (reponame, arch_version)
 
     ctx = webutil.changectx(web.repo, req)
     pats = []
-    matchfn = None
+    matchfn = scmutil.match(ctx, [])
     file = req.form.get('file', None)
     if file:
         pats = ['path:' + file[0]]
         matchfn = scmutil.match(ctx, pats, default='path')
         if pats:
             files = [f for f in ctx.manifest().keys() if matchfn(f)]
             if not files:
                 raise ErrorResponse(HTTP_NOT_FOUND,
                     'file(s) not found: %s' % file[0])
 
     mimetype, artype, extension, encoding = web.archive_specs[type_]
     headers = [
         ('Content-Disposition', 'attachment; filename=%s%s' % (name, extension))
         ]
     if encoding:
         headers.append(('Content-Encoding', encoding))
     req.headers.extend(headers)
     req.respond(HTTP_OK, mimetype)
 
     archival.archive(web.repo, req, cnode, artype, prefix=name,
                      matchfn=matchfn,
                      subrepos=web.configbool("web", "archivesubrepos"))
     return []
 
 
 def static(web, req, tmpl):
     fname = req.form['file'][0]
     # a repo owner may set web.static in .hg/hgrc to get any file
     # readable by the user running the CGI script
     static = web.config("web", "static", None, untrusted=False)
     if not static:
         tp = web.templatepath or templater.templatepaths()
         if isinstance(tp, str):
             tp = [tp]
         static = [os.path.join(p, 'static') for p in tp]
     staticfile(static, fname, req)
     return []
 
 def graph(web, req, tmpl):
 
     ctx = webutil.changectx(web.repo, req)
     rev = ctx.rev()
 
     bg_height = 39
     revcount = web.maxshortchanges
     if 'revcount' in req.form:
         try:
             revcount = int(req.form.get('revcount', [revcount])[0])
             revcount = max(revcount, 1)
             tmpl.defaults['sessionvars']['revcount'] = revcount
         except ValueError:
             pass
 
     lessvars = copy.copy(tmpl.defaults['sessionvars'])
     lessvars['revcount'] = max(revcount / 2, 1)
     morevars = copy.copy(tmpl.defaults['sessionvars'])
     morevars['revcount'] = revcount * 2
 
     count = len(web.repo)
     pos = rev
 
     uprev = min(max(0, count - 1), rev + revcount)
     downrev = max(0, rev - revcount)
     changenav = webutil.revnav(web.repo).gen(pos, revcount, count)
 
     tree = []
     if pos != -1:
         allrevs = web.repo.changelog.revs(pos, 0)
         revs = []
         for i in allrevs:
             revs.append(i)
             if len(revs) >= revcount:
                 break
 
         # We have to feed a baseset to dagwalker as it is expecting smartset
         # object. This does not have a big impact on hgweb performance itself
         # since hgweb graphing code is not itself lazy yet.
         dag = graphmod.dagwalker(web.repo, revset.baseset(revs))
         # As we said one line above... not lazy.
         tree = list(graphmod.colored(dag, web.repo))
 
     def getcolumns(tree):
         cols = 0
         for (id, type, ctx, vtx, edges) in tree:
             if type != graphmod.CHANGESET:
                 continue
             cols = max(cols, max([edge[0] for edge in edges] or [0]),
                              max([edge[1] for edge in edges] or [0]))
         return cols
 
     def graphdata(usetuples, **map):
         data = []
 
         row = 0
         for (id, type, ctx, vtx, edges) in tree:
             if type != graphmod.CHANGESET:
                 continue
             node = str(ctx)
             age = templatefilters.age(ctx.date())
             desc = templatefilters.firstline(ctx.description())
             desc = cgi.escape(templatefilters.nonempty(desc))
             user = cgi.escape(templatefilters.person(ctx.user()))
             branch = cgi.escape(ctx.branch())
             try:
                 branchnode = web.repo.branchtip(branch)
             except error.RepoLookupError:
                 branchnode = None
             branch = branch, branchnode == ctx.node()
 
             if usetuples:
                 data.append((node, vtx, edges, desc, user, age, branch,
                              [cgi.escape(x) for x in ctx.tags()],
                              [cgi.escape(x) for x in ctx.bookmarks()]))
             else:
                 edgedata = [{'col': edge[0], 'nextcol': edge[1],
                              'color': (edge[2] - 1) % 6 + 1,
                              'width': edge[3], 'bcolor': edge[4]}
                             for edge in edges]
 
                 data.append(
                     {'node': node,
                      'col': vtx[0],
                      'color': (vtx[1] - 1) % 6 + 1,
                      'edges': edgedata,
                      'row': row,
                      'nextrow': row + 1,
                      'desc': desc,
                      'user': user,
                      'age': age,
                      'bookmarks': webutil.nodebookmarksdict(
                          web.repo, ctx.node()),
                      'branches': webutil.nodebranchdict(web.repo, ctx),
                      'inbranch': webutil.nodeinbranch(web.repo, ctx),
                      'tags': webutil.nodetagsdict(web.repo, ctx.node())})
 
             row += 1
 
         return data
 
     cols = getcolumns(tree)
     rows = len(tree)
     canvasheight = (rows + 1) * bg_height - 27
 
     return tmpl('graph', rev=rev, revcount=revcount, uprev=uprev,
                 lessvars=lessvars, morevars=morevars, downrev=downrev,
                 cols=cols, rows=rows,
                 canvaswidth=(cols + 1) * bg_height,
                 truecanvasheight=rows * bg_height,
                 canvasheight=canvasheight, bg_height=bg_height,
                 jsdata=lambda **x: graphdata(True, **x),
                 nodes=lambda **x: graphdata(False, **x),
                 node=ctx.hex(), changenav=changenav)
 
 def _getdoc(e):
     doc = e[0].__doc__
     if doc:
         doc = _(doc).split('\n')[0]
     else:
         doc = _('(no help text available)')
     return doc
 
 def help(web, req, tmpl):
     from mercurial import commands # avoid cycle
 
     topicname = req.form.get('node', [None])[0]
     if not topicname:
         def topics(**map):
             for entries, summary, _doc in helpmod.helptable:
                 yield {'topic': entries[0], 'summary': summary}
 
         early, other = [], []
         primary = lambda s: s.split('|')[0]
         for c, e in commands.table.iteritems():
             doc = _getdoc(e)
             if 'DEPRECATED' in doc or c.startswith('debug'):
                 continue
             cmd = primary(c)
             if cmd.startswith('^'):
                 early.append((cmd[1:], doc))
             else:
                 other.append((cmd, doc))
 
         early.sort()
         other.sort()
 
         def earlycommands(**map):
             for c, doc in early:
                 yield {'topic': c, 'summary': doc}
 
         def othercommands(**map):
             for c, doc in other:
                 yield {'topic': c, 'summary': doc}
 
         return tmpl('helptopics', topics=topics, earlycommands=earlycommands,
                     othercommands=othercommands, title='Index')
 
     u = webutil.wsgiui()
     u.verbose = True
     try:
         doc = helpmod.help_(u, topicname)
     except error.UnknownCommand:
         raise ErrorResponse(HTTP_NOT_FOUND)
     return tmpl('help', topic=topicname, doc=doc)

mercurial/mail.py

@@ -1,330 +1,331 b''
 # mail.py - mail sending bits for mercurial
 #
 # Copyright 2006 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from i18n import _
 import util, encoding, sslutil
 import os, smtplib, socket, quopri, time, sys
 import email
 # On python2.4 you have to import these by name or they fail to
 # load. This was not a problem on Python 2.7.
 import email.Header
 import email.MIMEText
 
 _oldheaderinit = email.Header.Header.__init__
 def _unifiedheaderinit(self, *args, **kw):
     """
     Python 2.7 introduces a backwards incompatible change
     (Python issue1974, r70772) in email.Generator.Generator code:
     pre-2.7 code passed "continuation_ws='\t'" to the Header
     constructor, and 2.7 removed this parameter.
 
     Default argument is continuation_ws=' ', which means that the
     behaviour is different in <2.7 and 2.7
 
     We consider the 2.7 behaviour to be preferable, but need
     to have an unified behaviour for versions 2.4 to 2.7
     """
     # override continuation_ws
     kw['continuation_ws'] = ' '
     _oldheaderinit(self, *args, **kw)
 
 email.Header.Header.__dict__['__init__'] = _unifiedheaderinit
 
 class STARTTLS(smtplib.SMTP):
     '''Derived class to verify the peer certificate for STARTTLS.
 
     This class allows to pass any keyword arguments to SSL socket creation.
     '''
     def __init__(self, sslkwargs, **kwargs):
         smtplib.SMTP.__init__(self, **kwargs)
         self._sslkwargs = sslkwargs
 
     def starttls(self, keyfile=None, certfile=None):
         if not self.has_extn("starttls"):
             msg = "STARTTLS extension not supported by server"
             raise smtplib.SMTPException(msg)
         (resp, reply) = self.docmd("STARTTLS")
         if resp == 220:
             self.sock = sslutil.ssl_wrap_socket(self.sock, keyfile, certfile,
                                                 **self._sslkwargs)
             if not util.safehasattr(self.sock, "read"):
                 # using httplib.FakeSocket with Python 2.5.x or earlier
                 self.sock.read = self.sock.recv
             self.file = smtplib.SSLFakeFile(self.sock)
             self.helo_resp = None
             self.ehlo_resp = None
             self.esmtp_features = {}
             self.does_esmtp = 0
         return (resp, reply)
 
 if util.safehasattr(smtplib.SMTP, '_get_socket'):
     class SMTPS(smtplib.SMTP):
         '''Derived class to verify the peer certificate for SMTPS.
 
         This class allows to pass any keyword arguments to SSL socket creation.
         '''
         def __init__(self, sslkwargs, keyfile=None, certfile=None, **kwargs):
             self.keyfile = keyfile
             self.certfile = certfile
             smtplib.SMTP.__init__(self, **kwargs)
             self.default_port = smtplib.SMTP_SSL_PORT
             self._sslkwargs = sslkwargs
 
         def _get_socket(self, host, port, timeout):
             if self.debuglevel > 0:
                 print >> sys.stderr, 'connect:', (host, port)
             new_socket = socket.create_connection((host, port), timeout)
             new_socket = sslutil.ssl_wrap_socket(new_socket,
                                                  self.keyfile, self.certfile,
                                                  **self._sslkwargs)
             self.file = smtplib.SSLFakeFile(new_socket)
             return new_socket
 else:
     def SMTPS(sslkwargs, keyfile=None, certfile=None, **kwargs):
         raise util.Abort(_('SMTPS requires Python 2.6 or later'))
 
 def _smtp(ui):
     '''build an smtp connection and return a function to send mail'''
     local_hostname = ui.config('smtp', 'local_hostname')
     tls = ui.config('smtp', 'tls', 'none')
     # backward compatible: when tls = true, we use starttls.
     starttls = tls == 'starttls' or util.parsebool(tls)
     smtps = tls == 'smtps'
     if (starttls or smtps) and not util.safehasattr(socket, 'ssl'):
         raise util.Abort(_("can't use TLS: Python SSL support not installed"))
     mailhost = ui.config('smtp', 'host')
     if not mailhost:
         raise util.Abort(_('smtp.host not configured - cannot send mail'))
     verifycert = ui.config('smtp', 'verifycert', 'strict')
     if verifycert not in ['strict', 'loose']:
         if util.parsebool(verifycert) is not False:
             raise util.Abort(_('invalid smtp.verifycert configuration: %s')
                              % (verifycert))
+        verifycert = False
     if (starttls or smtps) and verifycert:
         sslkwargs = sslutil.sslkwargs(ui, mailhost)
     else:
         sslkwargs = {}
     if smtps:
         ui.note(_('(using smtps)\n'))
         s = SMTPS(sslkwargs, local_hostname=local_hostname)
     elif starttls:
         s = STARTTLS(sslkwargs, local_hostname=local_hostname)
     else:
         s = smtplib.SMTP(local_hostname=local_hostname)
     if smtps:
         defaultport = 465
     else:
         defaultport = 25
     mailport = util.getport(ui.config('smtp', 'port', defaultport))
     ui.note(_('sending mail: smtp host %s, port %s\n') %
             (mailhost, mailport))
     s.connect(host=mailhost, port=mailport)
     if starttls:
         ui.note(_('(using starttls)\n'))
         s.ehlo()
         s.starttls()
         s.ehlo()
     if (starttls or smtps) and verifycert:
         ui.note(_('(verifying remote certificate)\n'))
         sslutil.validator(ui, mailhost)(s.sock, verifycert == 'strict')
     username = ui.config('smtp', 'username')
     password = ui.config('smtp', 'password')
     if username and not password:
         password = ui.getpass()
     if username and password:
         ui.note(_('(authenticating to mail server as %s)\n') %
                   (username))
         try:
             s.login(username, password)
         except smtplib.SMTPException, inst:
             raise util.Abort(inst)
 
     def send(sender, recipients, msg):
         try:
             return s.sendmail(sender, recipients, msg)
         except smtplib.SMTPRecipientsRefused, inst:
             recipients = [r[1] for r in inst.recipients.values()]
             raise util.Abort('\n' + '\n'.join(recipients))
         except smtplib.SMTPException, inst:
             raise util.Abort(inst)
 
     return send
 
 def _sendmail(ui, sender, recipients, msg):
     '''send mail using sendmail.'''
     program = ui.config('email', 'method')
     cmdline = '%s -f %s %s' % (program, util.email(sender),
                                ' '.join(map(util.email, recipients)))
     ui.note(_('sending mail: %s\n') % cmdline)
     fp = util.popen(cmdline, 'w')
     fp.write(msg)
     ret = fp.close()
     if ret:
         raise util.Abort('%s %s' % (
             os.path.basename(program.split(None, 1)[0]),
             util.explainexit(ret)[0]))
 
 def _mbox(mbox, sender, recipients, msg):
     '''write mails to mbox'''
     fp = open(mbox, 'ab+')
     # Should be time.asctime(), but Windows prints 2-characters day
     # of month instead of one. Make them print the same thing.
     date = time.strftime('%a %b %d %H:%M:%S %Y', time.localtime())
     fp.write('From %s %s\n' % (sender, date))
     fp.write(msg)
     fp.write('\n\n')
     fp.close()
 
 def connect(ui, mbox=None):
     '''make a mail connection. return a function to send mail.
     call as sendmail(sender, list-of-recipients, msg).'''
     if mbox:
         open(mbox, 'wb').close()
         return lambda s, r, m: _mbox(mbox, s, r, m)
     if ui.config('email', 'method', 'smtp') == 'smtp':
         return _smtp(ui)
     return lambda s, r, m: _sendmail(ui, s, r, m)
 
 def sendmail(ui, sender, recipients, msg, mbox=None):
     send = connect(ui, mbox=mbox)
     return send(sender, recipients, msg)
 
 def validateconfig(ui):
     '''determine if we have enough config data to try sending email.'''
     method = ui.config('email', 'method', 'smtp')
     if method == 'smtp':
         if not ui.config('smtp', 'host'):
             raise util.Abort(_('smtp specified as email transport, '
                                'but no smtp host configured'))
     else:
         if not util.findexe(method):
             raise util.Abort(_('%r specified as email transport, '
                                'but not in PATH') % method)
 
 def mimetextpatch(s, subtype='plain', display=False):
     '''Return MIME message suitable for a patch.
     Charset will be detected as utf-8 or (possibly fake) us-ascii.
     Transfer encodings will be used if necessary.'''
 
     cs = 'us-ascii'
     if not display:
         try:
             s.decode('us-ascii')
         except UnicodeDecodeError:
             try:
                 s.decode('utf-8')
                 cs = 'utf-8'
             except UnicodeDecodeError:
                 # We'll go with us-ascii as a fallback.
                 pass
 
     return mimetextqp(s, subtype, cs)
 
 def mimetextqp(body, subtype, charset):
     '''Return MIME message.
     Quoted-printable transfer encoding will be used if necessary.
     '''
     enc = None
     for line in body.splitlines():
         if len(line) > 950:
             body = quopri.encodestring(body)
             enc = "quoted-printable"
             break
 
     msg = email.MIMEText.MIMEText(body, subtype, charset)
     if enc:
         del msg['Content-Transfer-Encoding']
         msg['Content-Transfer-Encoding'] = enc
     return msg
 
 def _charsets(ui):
     '''Obtains charsets to send mail parts not containing patches.'''
     charsets = [cs.lower() for cs in ui.configlist('email', 'charsets')]
     fallbacks = [encoding.fallbackencoding.lower(),
                  encoding.encoding.lower(), 'utf-8']
     for cs in fallbacks: # find unique charsets while keeping order
         if cs not in charsets:
             charsets.append(cs)
     return [cs for cs in charsets if not cs.endswith('ascii')]
 
 def _encode(ui, s, charsets):
     '''Returns (converted) string, charset tuple.
     Finds out best charset by cycling through sendcharsets in descending
     order. Tries both encoding and fallbackencoding for input. Only as
     last resort send as is in fake ascii.
     Caveat: Do not use for mail parts containing patches!'''
     try:
         s.decode('ascii')
     except UnicodeDecodeError:
         sendcharsets = charsets or _charsets(ui)
         for ics in (encoding.encoding, encoding.fallbackencoding):
             try:
                 u = s.decode(ics)
             except UnicodeDecodeError:
                 continue
             for ocs in sendcharsets:
                 try:
                     return u.encode(ocs), ocs
                 except UnicodeEncodeError:
                     pass
                 except LookupError:
                     ui.warn(_('ignoring invalid sendcharset: %s\n') % ocs)
     # if ascii, or all conversion attempts fail, send (broken) ascii
     return s, 'us-ascii'
 
 def headencode(ui, s, charsets=None, display=False):
     '''Returns RFC-2047 compliant header from given string.'''
     if not display:
         # split into words?
         s, cs = _encode(ui, s, charsets)
         return str(email.Header.Header(s, cs))
     return s
 
 def _addressencode(ui, name, addr, charsets=None):
     name = headencode(ui, name, charsets)
     try:
         acc, dom = addr.split('@')
         acc = acc.encode('ascii')
         dom = dom.decode(encoding.encoding).encode('idna')
         addr = '%s@%s' % (acc, dom)
     except UnicodeDecodeError:
         raise util.Abort(_('invalid email address: %s') % addr)
     except ValueError:
         try:
             # too strict?
             addr = addr.encode('ascii')
         except UnicodeDecodeError:
             raise util.Abort(_('invalid local address: %s') % addr)
     return email.Utils.formataddr((name, addr))
 
 def addressencode(ui, address, charsets=None, display=False):
     '''Turns address into RFC-2047 compliant header.'''
     if display or not address:
         return address or ''
     name, addr = email.Utils.parseaddr(address)
     return _addressencode(ui, name, addr, charsets)
 
 def addrlistencode(ui, addrs, charsets=None, display=False):
     '''Turns a list of addresses into a list of RFC-2047 compliant headers.
     A single element of input list may contain multiple addresses, but output
     always has one address per item'''
     if display:
         return [a.strip() for a in addrs if a.strip()]
 
     result = []
     for name, addr in email.Utils.getaddresses(addrs):
         if name or addr:
             result.append(_addressencode(ui, name, addr, charsets))
     return result
 
 def mimeencode(ui, s, charsets=None, display=False):
     '''creates mime text object, encodes it if needed, and sets
     charset and transfer-encoding accordingly.'''
     cs = 'us-ascii'
     if not display:
         s, cs = _encode(ui, s, charsets)
     return mimetextqp(s, 'plain', cs)

tests/test-archive.t

@@ -1,334 +1,368 b''
 #require serve
 
   $ hg init test
   $ cd test
   $ echo foo>foo
   $ hg commit -Am 1 -d '1 0'
   adding foo
   $ echo bar>bar
   $ hg commit -Am 2 -d '2 0'
   adding bar
   $ mkdir baz
   $ echo bletch>baz/bletch
   $ hg commit -Am 3 -d '1000000000 0'
   adding baz/bletch
+  $ hg init subrepo
+  $ touch subrepo/sub
+  $ hg -q -R subrepo ci -Am "init subrepo"
+  $ echo "subrepo = subrepo" > .hgsub
+  $ hg add .hgsub
+  $ hg ci -m "add subrepo"
   $ echo "[web]" >> .hg/hgrc
   $ echo "name = test-archive" >> .hg/hgrc
+  $ echo "archivesubrepos = True" >> .hg/hgrc
   $ cp .hg/hgrc .hg/hgrc-base
   > test_archtype() {
   >     echo "allow_archive = $1" >> .hg/hgrc
   >     hg serve -p $HGPORT -d --pid-file=hg.pid -E errors.log
   >     cat hg.pid >> $DAEMON_PIDS
   >     echo % $1 allowed should give 200
   >     "$TESTDIR/get-with-headers.py" localhost:$HGPORT "archive/tip.$2" | head -n 1
   >     echo % $3 and $4 disallowed should both give 403
   >     "$TESTDIR/get-with-headers.py" localhost:$HGPORT "archive/tip.$3" | head -n 1
   >     "$TESTDIR/get-with-headers.py" localhost:$HGPORT "archive/tip.$4" | head -n 1
   >     "$TESTDIR/killdaemons.py" $DAEMON_PIDS
   >     cat errors.log
   >     cp .hg/hgrc-base .hg/hgrc
   > }
 
 check http return codes
 
   $ test_archtype gz tar.gz tar.bz2 zip
   % gz allowed should give 200
   200 Script output follows
   % tar.bz2 and zip disallowed should both give 403
   403 Archive type not allowed: bz2
   403 Archive type not allowed: zip
   $ test_archtype bz2 tar.bz2 zip tar.gz
   % bz2 allowed should give 200
   200 Script output follows
   % zip and tar.gz disallowed should both give 403
   403 Archive type not allowed: zip
   403 Archive type not allowed: gz
   $ test_archtype zip zip tar.gz tar.bz2
   % zip allowed should give 200
   200 Script output follows
   % tar.gz and tar.bz2 disallowed should both give 403
   403 Archive type not allowed: gz
   403 Archive type not allowed: bz2
 
   $ echo "allow_archive = gz bz2 zip" >> .hg/hgrc
   $ hg serve -p $HGPORT -d --pid-file=hg.pid -E errors.log
   $ cat hg.pid >> $DAEMON_PIDS
 
 invalid arch type should give 404
 
   $ "$TESTDIR/get-with-headers.py" localhost:$HGPORT "archive/tip.invalid" | head -n 1
   404 Unsupported archive type: None
 
   $ TIP=`hg id -v | cut -f1 -d' '`
   $ QTIP=`hg id -q`
   $ cat > getarchive.py <<EOF
   > import os, sys, urllib2
   > try:
   >     # Set stdout to binary mode for win32 platforms
   >     import msvcrt
   >     msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)
   > except ImportError:
   >     pass
   > if len(sys.argv) <= 3:
   >     node, archive = sys.argv[1:]
   >     requeststr = 'cmd=archive;node=%s;type=%s' % (node, archive)
   > else:
   >     node, archive, file = sys.argv[1:]
   >     requeststr = 'cmd=archive;node=%s;type=%s;file=%s' % (node, archive, file)
   > try:
   >     f = urllib2.urlopen('http://127.0.0.1:%s/?%s'
   >                     % (os.environ['HGPORT'], requeststr))
   >     sys.stdout.write(f.read())
   > except urllib2.HTTPError, e:
   >     sys.stderr.write(str(e) + '\n')
   > EOF
   $ python getarchive.py "$TIP" gz | gunzip | tar tf - 2>/dev/null
-  test-archive-2c0277f05ed4/.hg_archival.txt
-  test-archive-2c0277f05ed4/bar
-  test-archive-2c0277f05ed4/baz/bletch
-  test-archive-2c0277f05ed4/foo
+  test-archive-1701ef1f1510/.hg_archival.txt
+  test-archive-1701ef1f1510/.hgsub
+  test-archive-1701ef1f1510/.hgsubstate
+  test-archive-1701ef1f1510/bar
+  test-archive-1701ef1f1510/baz/bletch
+  test-archive-1701ef1f1510/foo
+  test-archive-1701ef1f1510/subrepo/sub
   $ python getarchive.py "$TIP" bz2 | bunzip2 | tar tf - 2>/dev/null
-  test-archive-2c0277f05ed4/.hg_archival.txt
-  test-archive-2c0277f05ed4/bar
-  test-archive-2c0277f05ed4/baz/bletch
-  test-archive-2c0277f05ed4/foo
+  test-archive-1701ef1f1510/.hg_archival.txt
+  test-archive-1701ef1f1510/.hgsub
+  test-archive-1701ef1f1510/.hgsubstate
+  test-archive-1701ef1f1510/bar
+  test-archive-1701ef1f1510/baz/bletch
+  test-archive-1701ef1f1510/foo
+  test-archive-1701ef1f1510/subrepo/sub
   $ python getarchive.py "$TIP" zip > archive.zip
   $ unzip -t archive.zip
   Archive:  archive.zip
-      testing: test-archive-2c0277f05ed4/.hg_archival.txt   OK
-      testing: test-archive-2c0277f05ed4/bar   OK
-      testing: test-archive-2c0277f05ed4/baz/bletch   OK
-      testing: test-archive-2c0277f05ed4/foo   OK
+      testing: test-archive-1701ef1f1510/.hg_archival.txt   OK
+      testing: test-archive-1701ef1f1510/.hgsub   OK
+      testing: test-archive-1701ef1f1510/.hgsubstate   OK
+      testing: test-archive-1701ef1f1510/bar   OK
+      testing: test-archive-1701ef1f1510/baz/bletch   OK
+      testing: test-archive-1701ef1f1510/foo   OK
+      testing: test-archive-1701ef1f1510/subrepo/sub   OK
   No errors detected in compressed data of archive.zip.
 
 test that we can download single directories and files
 
   $ python getarchive.py "$TIP" gz baz | gunzip | tar tf - 2>/dev/null
-  test-archive-2c0277f05ed4/baz/bletch
+  test-archive-1701ef1f1510/baz/bletch
   $ python getarchive.py "$TIP" gz foo | gunzip | tar tf - 2>/dev/null
-  test-archive-2c0277f05ed4/foo
+  test-archive-1701ef1f1510/foo
 
 test that we detect file patterns that match no files
 
   $ python getarchive.py "$TIP" gz foobar
   HTTP Error 404: file(s) not found: foobar
 
 test that we reject unsafe patterns
 
   $ python getarchive.py "$TIP" gz relre:baz
   HTTP Error 404: file(s) not found: relre:baz
 
   $ "$TESTDIR/killdaemons.py" $DAEMON_PIDS
 
   $ hg archive -t tar test.tar
   $ tar tf test.tar
   test/.hg_archival.txt
+  test/.hgsub
+  test/.hgsubstate
   test/bar
   test/baz/bletch
   test/foo
 
   $ hg archive --debug -t tbz2 -X baz test.tar.bz2
-  archiving: 0/2 files (0.00%)
-  archiving: bar 1/2 files (50.00%)
-  archiving: foo 2/2 files (100.00%)
+  archiving: 0/4 files (0.00%)
+  archiving: .hgsub 1/4 files (25.00%)
+  archiving: .hgsubstate 2/4 files (50.00%)
+  archiving: bar 3/4 files (75.00%)
+  archiving: foo 4/4 files (100.00%)
   $ bunzip2 -dc test.tar.bz2 | tar tf - 2>/dev/null
   test/.hg_archival.txt
+  test/.hgsub
+  test/.hgsubstate
   test/bar
   test/foo
 
   $ hg archive -t tgz -p %b-%h test-%h.tar.gz
   $ gzip -dc test-$QTIP.tar.gz | tar tf - 2>/dev/null
-  test-2c0277f05ed4/.hg_archival.txt
-  test-2c0277f05ed4/bar
-  test-2c0277f05ed4/baz/bletch
-  test-2c0277f05ed4/foo
+  test-1701ef1f1510/.hg_archival.txt
+  test-1701ef1f1510/.hgsub
+  test-1701ef1f1510/.hgsubstate
+  test-1701ef1f1510/bar
+  test-1701ef1f1510/baz/bletch
+  test-1701ef1f1510/foo
 
   $ hg archive autodetected_test.tar
   $ tar tf autodetected_test.tar
   autodetected_test/.hg_archival.txt
+  autodetected_test/.hgsub
+  autodetected_test/.hgsubstate
   autodetected_test/bar
   autodetected_test/baz/bletch
   autodetected_test/foo
 
 The '-t' should override autodetection
 
   $ hg archive -t tar autodetect_override_test.zip
   $ tar tf autodetect_override_test.zip
   autodetect_override_test.zip/.hg_archival.txt
+  autodetect_override_test.zip/.hgsub
+  autodetect_override_test.zip/.hgsubstate
   autodetect_override_test.zip/bar
   autodetect_override_test.zip/baz/bletch
   autodetect_override_test.zip/foo
 
   $ for ext in tar tar.gz tgz tar.bz2 tbz2 zip; do
   >     hg archive auto_test.$ext
   >     if [ -d auto_test.$ext ]; then
   >         echo "extension $ext was not autodetected."
   >     fi
   > done
 
   $ cat > md5comp.py <<EOF
   > try:
   >     from hashlib import md5
   > except ImportError:
   >     from md5 import md5
   > import sys
   > f1, f2 = sys.argv[1:3]
   > h1 = md5(file(f1, 'rb').read()).hexdigest()
   > h2 = md5(file(f2, 'rb').read()).hexdigest()
   > print h1 == h2 or "md5 differ: " + repr((h1, h2))
   > EOF
 
 archive name is stored in the archive, so create similar archives and
 rename them afterwards.
 
   $ hg archive -t tgz tip.tar.gz
   $ mv tip.tar.gz tip1.tar.gz
   $ sleep 1
   $ hg archive -t tgz tip.tar.gz
   $ mv tip.tar.gz tip2.tar.gz
   $ python md5comp.py tip1.tar.gz tip2.tar.gz
   True
 
   $ hg archive -t zip -p /illegal test.zip
   abort: archive prefix contains illegal components
   [255]
   $ hg archive -t zip -p very/../bad test.zip
 
   $ hg archive --config ui.archivemeta=false -t zip -r 2 test.zip
   $ unzip -t test.zip
   Archive:  test.zip
       testing: test/bar                 OK
       testing: test/baz/bletch          OK
       testing: test/foo                 OK
   No errors detected in compressed data of test.zip.
 
   $ hg archive -t tar - | tar tf - 2>/dev/null
-  test-2c0277f05ed4/.hg_archival.txt
-  test-2c0277f05ed4/bar
-  test-2c0277f05ed4/baz/bletch
-  test-2c0277f05ed4/foo
+  test-1701ef1f1510/.hg_archival.txt
+  test-1701ef1f1510/.hgsub
+  test-1701ef1f1510/.hgsubstate
+  test-1701ef1f1510/bar
+  test-1701ef1f1510/baz/bletch
+  test-1701ef1f1510/foo
 
   $ hg archive -r 0 -t tar rev-%r.tar
   $ [ -f rev-0.tar ]
 
 test .hg_archival.txt
 
   $ hg archive ../test-tags
   $ cat ../test-tags/.hg_archival.txt
   repo: daa7f7c60e0a224faa4ff77ca41b2760562af264
-  node: 2c0277f05ed49d1c8328fb9ba92fba7a5ebcb33e
+  node: 1701ef1f151069b8747038e93b5186bb43a47504
   branch: default
   latesttag: null
-  latesttagdistance: 3
+  latesttagdistance: 4
   $ hg tag -r 2 mytag
   $ hg tag -r 2 anothertag
   $ hg archive -r 2 ../test-lasttag
   $ cat ../test-lasttag/.hg_archival.txt
   repo: daa7f7c60e0a224faa4ff77ca41b2760562af264
   node: 2c0277f05ed49d1c8328fb9ba92fba7a5ebcb33e
   branch: default
   tag: anothertag
   tag: mytag
 
   $ hg archive -t bogus test.bogus
   abort: unknown archive type 'bogus'
   [255]
 
 enable progress extension:
 
   $ cp $HGRCPATH $HGRCPATH.no-progress
   $ cat >> $HGRCPATH <<EOF
   > [extensions]
   > progress =
   > [progress]
   > assume-tty = 1
   > format = topic bar number
   > delay = 0
   > refresh = 0
   > width = 60
   > EOF
 
   $ hg archive ../with-progress
   \r (no-eol) (esc)
-  archiving [                                           ] 0/4\r (no-eol) (esc)
-  archiving [                                           ] 0/4\r (no-eol) (esc)
-  archiving [=========>                                 ] 1/4\r (no-eol) (esc)
-  archiving [=========>                                 ] 1/4\r (no-eol) (esc)
-  archiving [====================>                      ] 2/4\r (no-eol) (esc)
-  archiving [====================>                      ] 2/4\r (no-eol) (esc)
-  archiving [===============================>           ] 3/4\r (no-eol) (esc)
-  archiving [===============================>           ] 3/4\r (no-eol) (esc)
-  archiving [==========================================>] 4/4\r (no-eol) (esc)
-  archiving [==========================================>] 4/4\r (no-eol) (esc)
+  archiving [                                           ] 0/6\r (no-eol) (esc)
+  archiving [                                           ] 0/6\r (no-eol) (esc)
+  archiving [======>                                    ] 1/6\r (no-eol) (esc)
+  archiving [======>                                    ] 1/6\r (no-eol) (esc)
+  archiving [=============>                             ] 2/6\r (no-eol) (esc)
+  archiving [=============>                             ] 2/6\r (no-eol) (esc)
+  archiving [====================>                      ] 3/6\r (no-eol) (esc)
+  archiving [====================>                      ] 3/6\r (no-eol) (esc)
+  archiving [===========================>               ] 4/6\r (no-eol) (esc)
+  archiving [===========================>               ] 4/6\r (no-eol) (esc)
+  archiving [==================================>        ] 5/6\r (no-eol) (esc)
+  archiving [==================================>        ] 5/6\r (no-eol) (esc)
+  archiving [==========================================>] 6/6\r (no-eol) (esc)
+  archiving [==========================================>] 6/6\r (no-eol) (esc)
                                                               \r (no-eol) (esc)
 
 cleanup after progress extension test:
 
   $ cp $HGRCPATH.no-progress $HGRCPATH
 
 server errors
 
   $ cat errors.log
 
 empty repo
 
   $ hg init ../empty
   $ cd ../empty
   $ hg archive ../test-empty
   abort: no working directory: please specify a revision
   [255]
 
 old file -- date clamped to 1980
 
   $ touch -t 197501010000 old
   $ hg add old
   $ hg commit -m old
   $ hg archive ../old.zip
   $ unzip -l ../old.zip
   Archive:  ../old.zip
   \s*Length.* (re)
   *-----* (glob)
   *147*80*00:00*old/.hg_archival.txt (glob)
   *0*80*00:00*old/old (glob)
   *-----* (glob)
   \s*147\s+2 files (re)
 
 show an error when a provided pattern matches no files
 
   $ hg archive -I file_that_does_not_exist.foo ../empty.zip
   abort: no files match the archive pattern
   [255]
 
   $ hg archive -X * ../empty.zip
   abort: no files match the archive pattern
   [255]
 
   $ cd ..
 
 issue3600: check whether "hg archive" can create archive files which
 are extracted with expected timestamp, even though TZ is not
 configured as GMT.
 
   $ mkdir issue3600
   $ cd issue3600
 
   $ hg init repo
   $ echo a > repo/a
   $ hg -R repo add repo/a
   $ hg -R repo commit -m '#0' -d '456789012 21600'
   $ cat > show_mtime.py <<EOF
   > import sys, os
   > print int(os.stat(sys.argv[1]).st_mtime)
   > EOF
 
   $ hg -R repo archive --prefix tar-extracted archive.tar
   $ (TZ=UTC-3; export TZ; tar xf archive.tar)
   $ python show_mtime.py tar-extracted/a
   456789012
 
   $ hg -R repo archive --prefix zip-extracted archive.zip
   $ (TZ=UTC-3; export TZ; unzip -q archive.zip)
   $ python show_mtime.py zip-extracted/a
   456789012
 
   $ cd ..