Add debugcvsps command, replacing cvsps script

hgext/convert/__init__.py

@@ -1,203 +1,233 b''
 # convert.py Foreign SCM converter
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms
 # of the GNU General Public License, incorporated herein by reference.
 '''converting foreign VCS repositories to Mercurial'''
 
 import convcmd
+import cvsps
 from mercurial import commands
 from mercurial.i18n import _
 
 # Commands definition was moved elsewhere to ease demandload job.
 
 def convert(ui, src, dest=None, revmapfile=None, **opts):
     """Convert a foreign SCM repository to a Mercurial one.
 
     Accepted source formats [identifiers]:
     - Mercurial [hg]
     - CVS [cvs]
     - Darcs [darcs]
     - git [git]
     - Subversion [svn]
     - Monotone [mtn]
     - GNU Arch [gnuarch]
     - Bazaar [bzr]
 
     Accepted destination formats [identifiers]:
     - Mercurial [hg]
     - Subversion [svn] (history on branches is not preserved)
 
     If no revision is given, all revisions will be converted. Otherwise,
     convert will only import up to the named revision (given in a format
     understood by the source).
 
     If no destination directory name is specified, it defaults to the
     basename of the source with '-hg' appended.  If the destination
     repository doesn't exist, it will be created.
 
     If <REVMAP> isn't given, it will be put in a default location
     (<dest>/.hg/shamap by default).  The <REVMAP> is a simple text
     file that maps each source commit ID to the destination ID for
     that revision, like so:
     <source ID> <destination ID>
 
     If the file doesn't exist, it's automatically created.  It's updated
     on each commit copied, so convert-repo can be interrupted and can
     be run repeatedly to copy new commits.
 
     The [username mapping] file is a simple text file that maps each source
     commit author to a destination commit author. It is handy for source SCMs
     that use unix logins to identify authors (eg: CVS). One line per author
     mapping and the line format is:
     srcauthor=whatever string you want
 
     The filemap is a file that allows filtering and remapping of files
     and directories.  Comment lines start with '#'.  Each line can
     contain one of the following directives:
 
       include path/to/file
 
       exclude path/to/file
 
       rename from/file to/file
 
     The 'include' directive causes a file, or all files under a
     directory, to be included in the destination repository, and the
     exclusion of all other files and dirs not explicitely included.
     The 'exclude' directive causes files or directories to be omitted.
     The 'rename' directive renames a file or directory.  To rename from a
     subdirectory into the root of the repository, use '.' as the path to
     rename to.
 
     The splicemap is a file that allows insertion of synthetic
     history, letting you specify the parents of a revision.  This is
     useful if you want to e.g. give a Subversion merge two parents, or
     graft two disconnected series of history together.  Each entry
     contains a key, followed by a space, followed by one or two
     values, separated by spaces.  The key is the revision ID in the
     source revision control system whose parents should be modified
     (same format as a key in .hg/shamap).  The values are the revision
     IDs (in either the source or destination revision control system)
     that should be used as the new parents for that node.
 
     Mercurial Source
     -----------------
 
     --config convert.hg.ignoreerrors=False (boolean)
         ignore integrity errors when reading. Use it to fix Mercurial
         repositories with missing revlogs, by converting from and to
         Mercurial.
     --config convert.hg.saverev=True          (boolean)
         allow target to preserve source revision ID
     --config convert.hg.startrev=0            (hg revision identifier)
         convert start revision and its descendants
 
     CVS Source
     ----------
 
     CVS source will use a sandbox (i.e. a checked-out copy) from CVS
     to indicate the starting point of what will be converted. Direct
     access to the repository files is not needed, unless of course
     the repository is :local:. The conversion uses the top level
     directory in the sandbox to find the CVS repository, and then uses
     CVS rlog commands to find files to convert. This means that unless
     a filemap is given, all files under the starting directory will be
     converted, and that any directory reorganisation in the CVS
     sandbox is ignored.
 
     Because CVS does not have changesets, it is necessary to collect
     individual commits to CVS and merge them into changesets. CVS
     source uses its internal changeset merging code by default but can
     be configured to call the external 'cvsps' program by setting:
         --config convert.cvsps='cvsps -A -u --cvs-direct -q'
     This is a legacy option and may be removed in future.
 
     The options shown are the defaults.
 
     Internal cvsps is selected by setting
         --config convert.cvsps=builtin
     and has a few more configurable options:
         --config convert.cvsps.fuzz=60   (integer)
             Specify the maximum time (in seconds) that is allowed between
             commits with identical user and log message in a single
             changeset. When very large files were checked in as part
             of a changeset then the default may not be long enough.
         --config convert.cvsps.mergeto='{{mergetobranch ([-\w]+)}}'
             Specify a regular expression to which commit log messages are
             matched. If a match occurs, then the conversion process will
             insert a dummy revision merging the branch on which this log
             message occurs to the branch indicated in the regex.
         --config convert.cvsps.mergefrom='{{mergefrombranch ([-\w]+)}}'
             Specify a regular expression to which commit log messages are
             matched. If a match occurs, then the conversion process will
             add the most recent revision on the branch indicated in the
             regex as the second parent of the changeset.
 
     The hgext/convert/cvsps wrapper script allows the builtin changeset
     merging code to be run without doing a conversion. Its parameters and
     output are similar to that of cvsps 2.1.
 
     Subversion Source
     -----------------
 
     Subversion source detects classical trunk/branches/tags layouts.
     By default, the supplied "svn://repo/path/" source URL is
     converted as a single branch. If "svn://repo/path/trunk" exists
     it replaces the default branch. If "svn://repo/path/branches"
     exists, its subdirectories are listed as possible branches. If
     "svn://repo/path/tags" exists, it is looked for tags referencing
     converted branches. Default "trunk", "branches" and "tags" values
     can be overriden with following options. Set them to paths
     relative to the source URL, or leave them blank to disable
     autodetection.
 
     --config convert.svn.branches=branches    (directory name)
         specify the directory containing branches
     --config convert.svn.tags=tags            (directory name)
         specify the directory containing tags
     --config convert.svn.trunk=trunk          (directory name)
         specify the name of the trunk branch
 
     Source history can be retrieved starting at a specific revision,
     instead of being integrally converted. Only single branch
     conversions are supported.
 
     --config convert.svn.startrev=0           (svn revision number)
         specify start Subversion revision.
 
     Mercurial Destination
     ---------------------
 
     --config convert.hg.clonebranches=False   (boolean)
         dispatch source branches in separate clones.
     --config convert.hg.tagsbranch=default    (branch name)
         tag revisions branch name
     --config convert.hg.usebranchnames=True   (boolean)
         preserve branch names
 
     """
     return convcmd.convert(ui, src, dest, revmapfile, **opts)
 
 def debugsvnlog(ui, **opts):
     return convcmd.debugsvnlog(ui, **opts)
 
-commands.norepo += " convert debugsvnlog"
+def debugcvsps(ui, *args, **opts):
+    '''Create changeset information from CVS
+
+    This command is intended as a debugging tool for the CVS to Mercurial
+    converter, and can be used as a direct replacement for cvsps.
+
+    Hg debugcvsps reads the CVS rlog for current directory (or any named
+    directory) in the CVS repository, and converts the log to a series of
+    changesets based on matching commit log entries and dates.'''
+    return cvsps.debugcvsps(ui, *args, **opts)
+
+commands.norepo += " convert debugsvnlog debugcvsps"
 
 cmdtable = {
     "convert":
         (convert,
          [('A', 'authors', '', _('username mapping filename')),
           ('d', 'dest-type', '', _('destination repository type')),
           ('', 'filemap', '', _('remap file names using contents of file')),
           ('r', 'rev', '', _('import up to target revision REV')),
           ('s', 'source-type', '', _('source repository type')),
           ('', 'splicemap', '', _('splice synthesized history into place')),
           ('', 'datesort', None, _('try to sort changesets by date'))],
          _('hg convert [OPTION]... SOURCE [DEST [REVMAP]]')),
     "debugsvnlog":
         (debugsvnlog,
          [],
          'hg debugsvnlog'),
+    "debugcvsps":
+        (debugcvsps,
+         [
+          # Main options shared with cvsps-2.1
+          ('b', 'branches', [], _('Only return changes on specified branches')),
+          ('p', 'prefix', '', _('Prefix to remove from file names')),
+          ('r', 'revisions', [], _('Only return changes after or between specified tags')),
+          ('u', 'update-cache', None, _("Update cvs log cache")),
+          ('x', 'new-cache', None, _("Create new cvs log cache")),
+          ('z', 'fuzz', 60, _('Set commit time fuzz in seconds')),
+          ('', 'root', '', _('Specify cvsroot')),
+          # Options specific to builtin cvsps
+          ('', 'parents', '', _('Show parent changesets')),
+          ('', 'ancestors', '', _('Show current changeset in ancestor branches')),
+          # Options that are ignored for compatibility with cvsps-2.1
+          ('A', 'cvs-direct', None, 'Ignored for compatibility'),
+         ],
+         'hg debugcvsps [OPTION]... [PATH]...'),
 }

hgext/convert/cvsps.py

@@ -1,586 +1,678 b''
 #
 # Mercurial built-in replacement for cvsps.
 #
 # Copyright 2008, Frank Kingswood <[e-mail]>
 #
 # This software may be used and distributed according to the terms
 # of the GNU General Public License, incorporated herein by reference.
 
 import os
 import re
 import cPickle as pickle
 from mercurial import util
 from mercurial.i18n import _
 
 def listsort(list, key):
     "helper to sort by key in Python 2.3"
     try:
         list.sort(key=key)
     except TypeError:
         list.sort(lambda l, r: cmp(key(l), key(r)))
 
 class logentry(object):
     '''Class logentry has the following attributes:
         .author    - author name as CVS knows it
         .branch    - name of branch this revision is on
         .branches  - revision tuple of branches starting at this revision
         .comment   - commit message
         .date      - the commit date as a (time, tz) tuple
         .dead      - true if file revision is dead
         .file      - Name of file
         .lines     - a tuple (+lines, -lines) or None
         .parent    - Previous revision of this entry
         .rcs       - name of file as returned from CVS
         .revision  - revision number as tuple
         .tags      - list of tags on the file
     '''
     def __init__(self, **entries):
         self.__dict__.update(entries)
 
 class logerror(Exception):
     pass
 
 def getrepopath(cvspath):
     """Return the repository path from a CVS path.
 
     >>> getrepopath('/foo/bar')
     '/foo/bar'
     >>> getrepopath('c:/foo/bar')
     'c:/foo/bar'
     >>> getrepopath(':pserver:10/foo/bar')
     '/foo/bar'
     >>> getrepopath(':pserver:10c:/foo/bar')
     '/foo/bar'
     >>> getrepopath(':pserver:/foo/bar')
     '/foo/bar'
     >>> getrepopath(':pserver:c:/foo/bar')
     'c:/foo/bar'
     >>> getrepopath(':pserver:[e-mail]:/foo/bar')
     '/foo/bar'
     >>> getrepopath(':pserver:[e-mail]:c:/foo/bar')
     'c:/foo/bar'
     """
     # According to CVS manual, CVS paths are expressed like:
     # [:method:][[user][:password]@]hostname[:[port]]/path/to/repository
     #
     # Unfortunately, Windows absolute paths start with a drive letter
     # like 'c:' making it harder to parse. Here we assume that drive
     # letters are only one character long and any CVS component before
     # the repository path is at least 2 characters long, and use this
     # to disambiguate.
     parts = cvspath.split(':')
     if len(parts) == 1:
         return parts[0]
     # Here there is an ambiguous case if we have a port number
     # immediately followed by a Windows driver letter. We assume this
     # never happens and decide it must be CVS path component,
     # therefore ignoring it.
     if len(parts[-2]) > 1:
         return parts[-1].lstrip('0123456789')
     return parts[-2] + ':' + parts[-1]
 
 def createlog(ui, directory=None, root="", rlog=True, cache=None):
     '''Collect the CVS rlog'''
 
     # Because we store many duplicate commit log messages, reusing strings
     # saves a lot of memory and pickle storage space.
     _scache = {}
     def scache(s):
         "return a shared version of a string"
         return _scache.setdefault(s, s)
 
     ui.status(_('collecting CVS rlog\n'))
 
     log = []      # list of logentry objects containing the CVS state
 
     # patterns to match in CVS (r)log output, by state of use
     re_00 = re.compile('RCS file: (.+)$')
     re_01 = re.compile('cvs \\[r?log aborted\\]: (.+)$')
     re_02 = re.compile('cvs (r?log|server): (.+)\n$')
     re_03 = re.compile("(Cannot access.+CVSROOT)|(can't create temporary directory.+)$")
     re_10 = re.compile('Working file: (.+)$')
     re_20 = re.compile('symbolic names:')
     re_30 = re.compile('\t(.+): ([\\d.]+)$')
     re_31 = re.compile('----------------------------$')
     re_32 = re.compile('=============================================================================$')
     re_50 = re.compile('revision ([\\d.]+)(\s+locked by:\s+.+;)?$')
     re_60 = re.compile(r'date:\s+(.+);\s+author:\s+(.+);\s+state:\s+(.+?);(\s+lines:\s+(\+\d+)?\s+(-\d+)?;)?')
     re_70 = re.compile('branches: (.+);$')
 
     prefix = ''   # leading path to strip of what we get from CVS
 
     if directory is None:
         # Current working directory
 
         # Get the real directory in the repository
         try:
             prefix = file(os.path.join('CVS','Repository')).read().strip()
             if prefix == ".":
                 prefix = ""
             directory = prefix
         except IOError:
             raise logerror('Not a CVS sandbox')
 
         if prefix and not prefix.endswith(os.sep):
             prefix += os.sep
 
         # Use the Root file in the sandbox, if it exists
         try:
             root = file(os.path.join('CVS','Root')).read().strip()
         except IOError:
             pass
 
     if not root:
         root = os.environ.get('CVSROOT', '')
 
     # read log cache if one exists
     oldlog = []
     date = None
 
     if cache:
         cachedir = os.path.expanduser('~/.hg.cvsps')
         if not os.path.exists(cachedir):
             os.mkdir(cachedir)
 
         # The cvsps cache pickle needs a uniquified name, based on the
         # repository location. The address may have all sort of nasties
         # in it, slashes, colons and such. So here we take just the
         # alphanumerics, concatenated in a way that does not mix up the
         # various components, so that
         #    :pserver:user@server:/path
         # and
         #    /pserver/user/server/path
         # are mapped to different cache file names.
         cachefile = root.split(":") + [directory, "cache"]
         cachefile = ['-'.join(re.findall(r'\w+', s)) for s in cachefile if s]
         cachefile = os.path.join(cachedir,
                                  '.'.join([s for s in cachefile if s]))
 
     if cache == 'update':
         try:
             ui.note(_('reading cvs log cache %s\n') % cachefile)
             oldlog = pickle.load(file(cachefile))
             ui.note(_('cache has %d log entries\n') % len(oldlog))
         except Exception, e:
             ui.note(_('error reading cache: %r\n') % e)
 
         if oldlog:
             date = oldlog[-1].date    # last commit date as a (time,tz) tuple
             date = util.datestr(date, '%Y/%m/%d %H:%M:%S %1%2')
 
     # build the CVS commandline
     cmd = ['cvs', '-q']
     if root:
         cmd.append('-d%s' % root)
         p = util.normpath(getrepopath(root))
         if not p.endswith('/'):
             p += '/'
         prefix = p + util.normpath(prefix)
     cmd.append(['log', 'rlog'][rlog])
     if date:
         # no space between option and date string
         cmd.append('-d>%s' % date)
     cmd.append(directory)
 
     # state machine begins here
     tags = {}     # dictionary of revisions on current file with their tags
     state = 0
     store = False # set when a new record can be appended
 
     cmd = [util.shellquote(arg) for arg in cmd]
     ui.note(_("running %s\n") % (' '.join(cmd)))
     ui.debug(_("prefix=%r directory=%r root=%r\n") % (prefix, directory, root))
 
     for line in util.popen(' '.join(cmd)):
         if line.endswith('\n'):
             line = line[:-1]
         #ui.debug('state=%d line=%r\n' % (state, line))
 
         if state == 0:
             # initial state, consume input until we see 'RCS file'
             match = re_00.match(line)
             if match:
                 rcs = match.group(1)
                 tags = {}
                 if rlog:
                     filename = util.normpath(rcs[:-2])
                     if filename.startswith(prefix):
                         filename = filename[len(prefix):]
                     if filename.startswith('/'):
                         filename = filename[1:]
                     if filename.startswith('Attic/'):
                         filename = filename[6:]
                     else:
                         filename = filename.replace('/Attic/', '/')
                     state = 2
                     continue
                 state = 1
                 continue
             match = re_01.match(line)
             if match:
                 raise Exception(match.group(1))
             match = re_02.match(line)
             if match:
                 raise Exception(match.group(2))
             if re_03.match(line):
                 raise Exception(line)
 
         elif state == 1:
             # expect 'Working file' (only when using log instead of rlog)
             match = re_10.match(line)
             assert match, _('RCS file must be followed by working file')
             filename = util.normpath(match.group(1))
             state = 2
 
         elif state == 2:
             # expect 'symbolic names'
             if re_20.match(line):
                 state = 3
 
         elif state == 3:
             # read the symbolic names and store as tags
             match = re_30.match(line)
             if match:
                 rev = [int(x) for x in match.group(2).split('.')]
 
                 # Convert magic branch number to an odd-numbered one
                 revn = len(rev)
                 if revn > 3 and (revn % 2) == 0 and rev[-2] == 0:
                     rev = rev[:-2] + rev[-1:]
                 rev = tuple(rev)
 
                 if rev not in tags:
                     tags[rev] = []
                 tags[rev].append(match.group(1))
 
             elif re_31.match(line):
                 state = 5
             elif re_32.match(line):
                 state = 0
 
         elif state == 4:
             # expecting '------' separator before first revision
             if re_31.match(line):
                 state = 5
             else:
                 assert not re_32.match(line), _('Must have at least some revisions')
 
         elif state == 5:
             # expecting revision number and possibly (ignored) lock indication
             # we create the logentry here from values stored in states 0 to 4,
             # as this state is re-entered for subsequent revisions of a file.
             match = re_50.match(line)
             assert match, _('expected revision number')
             e = logentry(rcs=scache(rcs), file=scache(filename),
                     revision=tuple([int(x) for x in match.group(1).split('.')]),
                     branches=[], parent=None)
             state = 6
 
         elif state == 6:
             # expecting date, author, state, lines changed
             match = re_60.match(line)
             assert match, _('revision must be followed by date line')
             d = match.group(1)
             if d[2] == '/':
                 # Y2K
                 d = '19' + d
 
             if len(d.split()) != 3:
                 # cvs log dates always in GMT
                 d = d + ' UTC'
             e.date = util.parsedate(d, ['%y/%m/%d %H:%M:%S', '%Y/%m/%d %H:%M:%S', '%Y-%m-%d %H:%M:%S'])
             e.author = scache(match.group(2))
             e.dead = match.group(3).lower() == 'dead'
 
             if match.group(5):
                 if match.group(6):
                     e.lines = (int(match.group(5)), int(match.group(6)))
                 else:
                     e.lines = (int(match.group(5)), 0)
             elif match.group(6):
                 e.lines = (0, int(match.group(6)))
             else:
                 e.lines = None
             e.comment = []
             state = 7
 
         elif state == 7:
             # read the revision numbers of branches that start at this revision
             # or store the commit log message otherwise
             m = re_70.match(line)
             if m:
                 e.branches = [tuple([int(y) for y in x.strip().split('.')])
                                 for x in m.group(1).split(';')]
                 state = 8
             elif re_31.match(line):
                 state = 5
                 store = True
             elif re_32.match(line):
                 state = 0
                 store = True
             else:
                 e.comment.append(line)
 
         elif state == 8:
             # store commit log message
             if re_31.match(line):
                 state = 5
                 store = True
             elif re_32.match(line):
                 state = 0
                 store = True
             else:
                 e.comment.append(line)
 
         if store:
             # clean up the results and save in the log.
             store = False
             e.tags = util.sort([scache(x) for x in tags.get(e.revision, [])])
             e.comment = scache('\n'.join(e.comment))
 
             revn = len(e.revision)
             if revn > 3 and (revn % 2) == 0:
                 e.branch = tags.get(e.revision[:-1], [None])[0]
             else:
                 e.branch = None
 
             log.append(e)
 
             if len(log) % 100 == 0:
                 ui.status(util.ellipsis('%d %s' % (len(log), e.file), 80)+'\n')
 
     listsort(log, key=lambda x:(x.rcs, x.revision))
 
     # find parent revisions of individual files
     versions = {}
     for e in log:
         branch = e.revision[:-1]
         p = versions.get((e.rcs, branch), None)
         if p is None:
             p = e.revision[:-2]
         e.parent = p
         versions[(e.rcs, branch)] = e.revision
 
     # update the log cache
     if cache:
         if log:
             # join up the old and new logs
             listsort(log, key=lambda x:x.date)
 
             if oldlog and oldlog[-1].date >= log[0].date:
                 raise logerror('Log cache overlaps with new log entries,'
                                ' re-run without cache.')
 
             log = oldlog + log
 
             # write the new cachefile
             ui.note(_('writing cvs log cache %s\n') % cachefile)
             pickle.dump(log, file(cachefile, 'w'))
         else:
             log = oldlog
 
     ui.status(_('%d log entries\n') % len(log))
 
     return log
 
 
 class changeset(object):
     '''Class changeset has the following attributes:
         .author    - author name as CVS knows it
         .branch    - name of branch this changeset is on, or None
         .comment   - commit message
         .date      - the commit date as a (time,tz) tuple
         .entries   - list of logentry objects in this changeset
         .parents   - list of one or two parent changesets
         .tags      - list of tags on this changeset
     '''
     def __init__(self, **entries):
         self.__dict__.update(entries)
 
 def createchangeset(ui, log, fuzz=60, mergefrom=None, mergeto=None):
     '''Convert log into changesets.'''
 
     ui.status(_('creating changesets\n'))
 
     # Merge changesets
 
     listsort(log, key=lambda x:(x.comment, x.author, x.branch, x.date))
 
     changesets = []
     files = {}
     c = None
     for i, e in enumerate(log):
 
         # Check if log entry belongs to the current changeset or not.
         if not (c and
                   e.comment == c.comment and
                   e.author == c.author and
                   e.branch == c.branch and
                   ((c.date[0] + c.date[1]) <=
                    (e.date[0] + e.date[1]) <=
                    (c.date[0] + c.date[1]) + fuzz) and
                   e.file not in files):
             c = changeset(comment=e.comment, author=e.author,
                           branch=e.branch, date=e.date, entries=[])
             changesets.append(c)
             files = {}
             if len(changesets) % 100 == 0:
                 t = '%d %s' % (len(changesets), repr(e.comment)[1:-1])
                 ui.status(util.ellipsis(t, 80) + '\n')
 
         c.entries.append(e)
         files[e.file] = True
         c.date = e.date       # changeset date is date of latest commit in it
 
     # Sort files in each changeset
 
     for c in changesets:
         def pathcompare(l, r):
             'Mimic cvsps sorting order'
             l = l.split('/')
             r = r.split('/')
             nl = len(l)
             nr = len(r)
             n = min(nl, nr)
             for i in range(n):
                 if i + 1 == nl and nl < nr:
                     return -1
                 elif i + 1 == nr and nl > nr:
                     return +1
                 elif l[i] < r[i]:
                     return -1
                 elif l[i] > r[i]:
                     return +1
             return 0
         def entitycompare(l, r):
             return pathcompare(l.file, r.file)
 
         c.entries.sort(entitycompare)
 
     # Sort changesets by date
 
     def cscmp(l, r):
         d = sum(l.date) - sum(r.date)
         if d:
             return d
 
         # detect vendor branches and initial commits on a branch
         le = {}
         for e in l.entries:
             le[e.rcs] = e.revision
         re = {}
         for e in r.entries:
             re[e.rcs] = e.revision
 
         d = 0
         for e in l.entries:
             if re.get(e.rcs, None) == e.parent:
                 assert not d
                 d = 1
                 break
 
         for e in r.entries:
             if le.get(e.rcs, None) == e.parent:
                 assert not d
                 d = -1
                 break
 
         return d
 
     changesets.sort(cscmp)
 
     # Collect tags
 
     globaltags = {}
     for c in changesets:
         tags = {}
         for e in c.entries:
             for tag in e.tags:
                 # remember which is the latest changeset to have this tag
                 globaltags[tag] = c
 
     for c in changesets:
         tags = {}
         for e in c.entries:
             for tag in e.tags:
                 tags[tag] = True
         # remember tags only if this is the latest changeset to have it
         c.tags = util.sort([tag for tag in tags if globaltags[tag] is c])
 
     # Find parent changesets, handle {{mergetobranch BRANCHNAME}}
     # by inserting dummy changesets with two parents, and handle
     # {{mergefrombranch BRANCHNAME}} by setting two parents.
 
     if mergeto is None:
         mergeto = r'{{mergetobranch ([-\w]+)}}'
     if mergeto:
         mergeto = re.compile(mergeto)
 
     if mergefrom is None:
         mergefrom = r'{{mergefrombranch ([-\w]+)}}'
     if mergefrom:
         mergefrom = re.compile(mergefrom)
 
     versions = {}    # changeset index where we saw any particular file version
     branches = {}    # changeset index where we saw a branch
     n = len(changesets)
     i = 0
     while i<n:
         c = changesets[i]
 
         for f in c.entries:
             versions[(f.rcs, f.revision)] = i
 
         p = None
         if c.branch in branches:
             p = branches[c.branch]
         else:
             for f in c.entries:
                 p = max(p, versions.get((f.rcs, f.parent), None))
 
         c.parents = []
         if p is not None:
             c.parents.append(changesets[p])
 
         if mergefrom:
             m = mergefrom.search(c.comment)
             if m:
                 m = m.group(1)
                 if m == 'HEAD':
                     m = None
                 if m in branches and c.branch != m:
                     c.parents.append(changesets[branches[m]])
 
         if mergeto:
             m = mergeto.search(c.comment)
             if m:
                 try:
                     m = m.group(1)
                     if m == 'HEAD':
                         m = None
                 except:
                     m = None   # if no group found then merge to HEAD
                 if m in branches and c.branch != m:
                     # insert empty changeset for merge
                     cc = changeset(author=c.author, branch=m, date=c.date,
                             comment='convert-repo: CVS merge from branch %s' % c.branch,
                             entries=[], tags=[], parents=[changesets[branches[m]], c])
                     changesets.insert(i + 1, cc)
                     branches[m] = i + 1
 
                     # adjust our loop counters now we have inserted a new entry
                     n += 1
                     i += 2
                     continue
 
         branches[c.branch] = i
         i += 1
 
     # Number changesets
 
     for i, c in enumerate(changesets):
         c.id = i + 1
 
     ui.status(_('%d changeset entries\n') % len(changesets))
 
     return changesets
+
+
+def debugcvsps(ui, *args, **opts):
+    '''Read CVS rlog for current directory or named path in repository, and 
+    convert the log to changesets based on matching commit log entries and dates.'''
+
+    if opts["new_cache"]:
+        cache = "write"
+    elif opts["update_cache"]:
+        cache = "update"
+    else:
+        cache = None
+
+    revisions = opts["revisions"]
+
+    try:
+        if args:
+            log = []
+            for d in args:
+                log += createlog(ui, d, root=opts["root"], cache=cache)
+        else:
+            log = createlog(ui, root=opts["root"], cache=cache)
+    except logerror, e:
+        ui.write("%r\n"%e)
+        return
+
+    changesets = createchangeset(ui, log, opts["fuzz"])
+    del log
+
+    # Print changesets (optionally filtered)
+
+    off = len(revisions)
+    branches = {}    # latest version number in each branch
+    ancestors = {}   # parent branch
+    for cs in changesets:
+
+        if opts["ancestors"]:
+            if cs.branch not in branches and cs.parents and cs.parents[0].id:
+                ancestors[cs.branch] = changesets[cs.parents[0].id-1].branch, cs.parents[0].id
+            branches[cs.branch] = cs.id
+
+        # limit by branches
+        if opts["branches"] and (cs.branch or 'HEAD') not in opts["branches"]:
+            continue
+
+        if not off:
+            # Note: trailing spaces on several lines here are needed to have
+            #       bug-for-bug compatibility with cvsps.
+            ui.write('---------------------\n')
+            ui.write('PatchSet %d \n' % cs.id)
+            ui.write('Date: %s\n' % util.datestr(cs.date, '%Y/%m/%d %H:%M:%S %1%2'))
+            ui.write('Author: %s\n' % cs.author)
+            ui.write('Branch: %s\n' % (cs.branch or 'HEAD'))
+            ui.write('Tag%s: %s \n' % (['', 's'][len(cs.tags)>1],
+                                  ','.join(cs.tags) or '(none)'))
+            if opts["parents"] and cs.parents:
+                if len(cs.parents)>1:
+                    ui.write('Parents: %s\n' % (','.join([str(p.id) for p in cs.parents])))
+                else:
+                    ui.write('Parent: %d\n' % cs.parents[0].id)
+
+            if opts["ancestors"]:
+                b = cs.branch
+                r = []
+                while b:
+                    b, c = ancestors[b]
+                    r.append('%s:%d:%d' % (b or "HEAD", c, branches[b]))
+                if r:
+                    ui.write('Ancestors: %s\n' % (','.join(r)))
+
+            ui.write('Log:\n')
+            ui.write('%s\n\n' % cs.comment)
+            ui.write('Members: \n')
+            for f in cs.entries:
+                fn = f.file
+                if fn.startswith(opts["prefix"]):
+                    fn = fn[len(opts["prefix"]):]
+                ui.write('\t%s:%s->%s%s \n' % (fn, '.'.join([str(x) for x in f.parent]) or 'INITIAL',
+                                          '.'.join([str(x) for x in f.revision]), ['', '(DEAD)'][f.dead]))
+            ui.write('\n')
+
+        # have we seen the start tag?
+        if revisions and off:
+            if revisions[0] == str(cs.id) or \
+                revisions[0] in cs.tags:
+                off = False
+
+        # see if we reached the end tag
+        if len(revisions)>1 and not off:
+            if revisions[1] == str(cs.id) or \
+                revisions[1] in cs.tags:
+                break