comparison hgext/convert/cvsps.py @ 43076:2372284d9457

formatting: blacken the codebase

This is using my patch to black
(https://github.com/psf/black/pull/826) so we don't un-wrap collection
literals.

Done with:

  hg files 'set:**.py - mercurial/thirdparty/** - "contrib/python-zstandard/**"' | xargs black -S

# skip-blame mass-reformatting only

# no-check-commit reformats foo_bar functions

Differential Revision: https://phab.mercurial-scm.org/D6971

43075:57875cf423c9

    procutil,
    stringutil,
)

pickle = util.pickle

class logentry(object):
    '''Class logentry has the following attributes:
        .author    - author name as CVS knows it
        .branch    - name of branch this revision is on

        .synthetic - is this a synthetic "file ... added on ..." revision?
        .mergepoint - the branch that has been merged from (if present in
                      rlog output) or None
        .branchpoints - the branches that start at the current entry or empty
    '''
    def __init__(self, **entries):
        self.synthetic = False
        self.__dict__.update(entries)

    def __repr__(self):
        items = (r"%s=%r"%(k, self.__dict__[k]) for k in sorted(self.__dict__))
        return r"%s(%s)"%(type(self).__name__, r", ".join(items))

class logerror(Exception):
    pass

def getrepopath(cvspath):
    """Return the repository path from a CVS path.

    >>> getrepopath(b'/foo/bar')

    start = 0

    if atposition != -1:
        start = atposition

    repopath = parts[-1][parts[-1].find('/', start):]
    return repopath

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(b'RCS file: (.+)$')
    re_01 = re.compile(b'cvs \\[r?log aborted\\]: (.+)$')
    re_02 = re.compile(b'cvs (r?log|server): (.+)\n$')
    re_03 = re.compile(b"(Cannot access.+CVSROOT)|"
                       b"(can't create temporary directory.+)$")
    re_10 = re.compile(b'Working file: (.+)$')
    re_20 = re.compile(b'symbolic names:')
    re_30 = re.compile(b'\t(.+): ([\\d.]+)$')
    re_31 = re.compile(b'----------------------------$')
    re_32 = re.compile(b'======================================='
                       b'======================================$')
    re_50 = re.compile(br'revision ([\d.]+)(\s+locked by:\s+.+;)?$')
    re_60 = re.compile(br'date:\s+(.+);\s+author:\s+(.+);\s+state:\s+(.+?);'
                       br'(\s+lines:\s+(\+\d+)?\s+(-\d+)?;)?'
                       br'(\s+commitid:\s+([^;]+);)?'
                       br'(.*mergepoint:\s+([^;]+);)?')
    re_70 = re.compile(b'branches: (.+);$')

    file_added_re = re.compile(br'file [^/]+ was (initially )?added on branch')

    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

        if prefix and not prefix.endswith(pycompat.ossep):
            prefix += pycompat.ossep

        # Use the Root file in the sandbox, if it exists
        try:
            root = open(os.path.join('CVS','Root'), 'rb').read().strip()
        except IOError:
            pass

    if not root:
        root = encoding.environ.get('CVSROOT', '')

        # and
        #    /pserver/user/server/path
        # are mapped to different cache file names.
        cachefile = root.split(":") + [directory, "cache"]
        cachefile = ['-'.join(re.findall(br'\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(open(cachefile, 'rb'))
            for e in oldlog:
                if not (util.safehasattr(e, 'branchpoints') and
                        util.safehasattr(e, 'commitid') and
                        util.safehasattr(e, 'mergepoint')):
                    ui.status(_('ignoring old cache\n'))
                    oldlog = []
                    break

            ui.note(_('cache has %d log entries\n') % len(oldlog))
        except Exception as e:
            ui.note(_('error reading cache: %r\n') % e)

        if oldlog:
            date = oldlog[-1].date    # last commit date as a (time,tz) tuple
            date = dateutil.datestr(date, '%Y/%m/%d %H:%M:%S %1%2')

    # build the CVS commandline
    cmd = ['cvs', '-q']
    if root:

        # 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
    branchmap = {} # mapping between branch names and revision numbers
    rcsmap = {}
    state = 0
    store = False # set when a new record can be appended

    cmd = [procutil.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))

        if line == '':
            break
        peek = util.fromnativeeol(pfp.readline())
        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:

        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,
                         commitid=None,
                         mergepoint=None,
                         branchpoints=set())

            state = 6

        elif state == 6:
            # expecting date, author, state, lines changed

                d = '19' + d

            if len(d.split()) != 3:
                # cvs log dates always in GMT
                d = d + ' UTC'
            e.date = dateutil.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):

            elif match.group(6):
                e.lines = (0, int(match.group(6)))
            else:
                e.lines = None

            if match.group(7): # cvs 1.12 commitid
                e.commitid = match.group(8)

            if match.group(9): # cvsnt mergepoint
                myrev = match.group(10).split('.')
                if len(myrev) == 2: # head
                    e.mergepoint = 'HEAD'
                else:
                    myrev = '.'.join(myrev[:-2] + ['0', myrev[-2]])
                    branches = [b for b in branchmap if branchmap[b] == myrev]
                    assert len(branches) == 1, ('unknown branch: %s'
                                                % e.mergepoint)
                    e.mergepoint = branches[0]

            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) and re_50.match(peek):
                state = 5
                store = True
            elif re_32.match(line):

        # Likewise, if you merge such a file to a later branch B2 (one
        # that already existed when the file was added on B1), CVS
        # creates a synthetic dead revision 1.1.x.1 on B2.  Don't drop
        # these revisions now, but mark them synthetic so
        # createchangeset() can take care of them.
        if (store and
              e.dead and
              e.revision[-1] == 1 and      # 1.1 or 1.1.x.1
              len(e.comment) == 1 and
              file_added_re.match(e.comment[0])):
            ui.debug('found synthetic revision in %s: %r\n'
                     % (e.rcs, e.comment[0]))
            e.synthetic = True

        if store:
            # clean up the results and save in the log.
            store = False

            # find the branches starting from this revision
            branchpoints = set()
            for branch, revision in branchmap.iteritems():
                revparts = tuple([int(i) for i in revision.split('.')])
                if len(revparts) < 2: # bad tags
                    continue
                if revparts[-2] == 0 and revparts[-1] % 2 == 0:
                    # normal branch
                    if revparts[:-2] == e.revision:
                        branchpoints.add(branch)
                elif revparts == (1, 1, 1): # vendor branch
                    if revparts in e.branches:
                        branchpoints.add(branch)
            e.branchpoints = branchpoints

            log.append(e)

            rcsmap[e.rcs.replace('/Attic/', '/')] = e.rcs

            if len(log) % 100 == 0:
                ui.status(stringutil.ellipsis('%d %s' % (len(log), e.file), 80)
                          + '\n')

    log.sort(key=lambda x: (x.rcs, x.revision))

    # find parent revisions of individual files
    versions = {}

        if log:
            # join up the old and new logs
            log.sort(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)

    ui.status(_('%d log entries\n') % len(log))

    encodings = ui.configlist('convert', 'cvsps.logencoding')
    if encodings:
        def revstr(r):
            # this is needed, because logentry.revision is a tuple of "int"
            # (e.g. (1, 2) for "1.2")
            return '.'.join(pycompat.maplist(pycompat.bytestr, r))

        for entry in log:
            comment = entry.comment
            for e in encodings:
                try:
                    entry.comment = comment.decode(
                        pycompat.sysstr(e)).encode('utf-8')
                    if ui.debugflag:
                        ui.debug("transcoding by %s: %s of %s\n" %
                                 (e, revstr(entry.revision), entry.file))
                    break
                except UnicodeDecodeError:
                    pass # try next encoding
                except LookupError as inst: # unknown encoding, maybe
                    raise error.Abort(inst,
                                      hint=_('check convert.cvsps.logencoding'
                                             ' configuration'))
            else:
                raise error.Abort(_("no encoding can transcode"
                                    " CVS log message for %s of %s")
                                  % (revstr(entry.revision), entry.file),
                                  hint=_('check convert.cvsps.logencoding'
                                         ' configuration'))

    hook.hook(ui, None, "cvslog", True, log=log)

    return log

        .tags      - list of tags on this changeset
        .synthetic - from synthetic revision "file ... added on branch ..."
        .mergepoint- the branch that has been merged from or None
        .branchpoints- the branches that start at the current entry or empty
    '''
    def __init__(self, **entries):
        self.id = None
        self.synthetic = False
        self.__dict__.update(entries)

    def __repr__(self):
        items = ("%s=%r"%(k, self.__dict__[k]) for k in sorted(self.__dict__))
        return "%s(%s)"%(type(self).__name__, ", ".join(items))

def createchangeset(ui, log, fuzz=60, mergefrom=None, mergeto=None):
    '''Convert log into changesets.'''

    ui.status(_('creating changesets\n'))

                mindate[e.commitid] = e.date
            else:
                mindate[e.commitid] = min(e.date, mindate[e.commitid])

    # Merge changesets
    log.sort(key=lambda x: (mindate.get(x.commitid, (-1, 0)),
                            x.commitid or '', x.comment,
                            x.author, x.branch or '', x.date, x.branchpoints))

    changesets = []
    files = set()
    c = None
    for i, e in enumerate(log):

        # Here foo is part only of MYBRANCH, but not MYBRANCH2, e.g. a
        # later version of foo may be in MYBRANCH2, so foo should be the
        # first changeset and bar the next and MYBRANCH and MYBRANCH2
        # should both start off of the bar changeset. No provisions are
        # made to ensure that this is, in fact, what happens.
        if not (c and e.branchpoints == c.branchpoints and
                (# cvs commitids
                 (e.commitid is not None and e.commitid == c.commitid) or
                 (# no commitids, use fuzzy commit detection
                  (e.commitid is None or c.commitid is None) 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=[], mergepoint=e.mergepoint,
                          branchpoints=e.branchpoints, commitid=e.commitid)
            changesets.append(c)

            files = set()
            if len(changesets) % 100 == 0:
                t = '%d %s' % (len(changesets), repr(e.comment)[1:-1])
                ui.status(stringutil.ellipsis(t, 80) + '\n')

        c.entries.append(e)
        files.add(e.file)
        c.date = e.date       # changeset date is date of latest commit in it

    # Mark synthetic changesets

    for c in changesets:
        # Synthetic revisions always get their own changeset, because

        c.entries.sort(key=functools.cmp_to_key(entitycompare))

    # Sort changesets by date

    odd = set()
    def cscmp(l, r):
        d = sum(l.date) - sum(r.date)
        if d:
            return d

    if mergefrom is None:
        mergefrom = br'{{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]

        if p is not None:
            p = changesets[p]

            # Ensure no changeset has a synthetic changeset as a parent.
            while p.synthetic:
                assert len(p.parents) <= 1, (
                       _('synthetic changeset cannot have multiple parents'))
                if p.parents:
                    p = p.parents[0]
                else:
                    p = None
                    break

                if m == 'HEAD':
                    m = None
                try:
                    candidate = changesets[branches[m]]
                except KeyError:
                    ui.warn(_("warning: CVS commit message references "
                              "non-existent branch %r:\n%s\n")
                            % (pycompat.bytestr(m), c.comment))
                if m in branches and c.branch != m and not candidate.synthetic:
                    c.parents.append(candidate)

        if mergeto:
            m = mergeto.search(c.comment)

                if m.groups():
                    m = m.group(1)
                    if m == 'HEAD':
                        m = None
                else:
                    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

        c.id = i + 1

    if odd:
        for l, r in odd:
            if l.id is not None and r.id is not None:
                ui.warn(_('changeset %d is both before and after %d\n')
                        % (l.id, r.id))

    ui.status(_('%d changeset entries\n') % len(changesets))

    hook.hook(ui, None, "cvschangesets", True, changesets=changesets)

            for d in args:
                log += createlog(ui, d, root=opts["root"], cache=cache)
        else:
            log = createlog(ui, root=opts["root"], cache=cache)
    except logerror as 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' % dateutil.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 cs.branchpoints:
                ui.write(('Branchpoints: %s \n') %
                         ', '.join(sorted(cs.branchpoints)))
            if opts["parents"] and cs.parents:
                if len(cs.parents) > 1:
                    ui.write(('Parents: %s\n' %
                             (','.join([(b"%d" % p.id) for p in cs.parents]))))
                else:
                    ui.write(('Parent: %d\n' % cs.parents[0].id))

            if opts["ancestors"]:
                b = cs.branch

                    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([b"%d" % x for x in f.parent]) or 'INITIAL',
                        '.'.join([(b"%d" % 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] == (b"%d" % 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] == (b"%d" % cs.id) or
                revisions[1] in cs.tags):
                break

43076:2372284d9457

    procutil,
    stringutil,
)

pickle = util.pickle


class logentry(object):
    '''Class logentry has the following attributes:
        .author    - author name as CVS knows it
        .branch    - name of branch this revision is on

        .synthetic - is this a synthetic "file ... added on ..." revision?
        .mergepoint - the branch that has been merged from (if present in
                      rlog output) or None
        .branchpoints - the branches that start at the current entry or empty
    '''

    def __init__(self, **entries):
        self.synthetic = False
        self.__dict__.update(entries)

    def __repr__(self):
        items = (
            r"%s=%r" % (k, self.__dict__[k]) for k in sorted(self.__dict__)
        )
        return r"%s(%s)" % (type(self).__name__, r", ".join(items))


class logerror(Exception):
    pass


def getrepopath(cvspath):
    """Return the repository path from a CVS path.

    >>> getrepopath(b'/foo/bar')

    start = 0

    if atposition != -1:
        start = atposition

    repopath = parts[-1][parts[-1].find('/', start) :]
    return repopath


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(b'RCS file: (.+)$')
    re_01 = re.compile(b'cvs \\[r?log aborted\\]: (.+)$')
    re_02 = re.compile(b'cvs (r?log|server): (.+)\n$')
    re_03 = re.compile(
        b"(Cannot access.+CVSROOT)|" b"(can't create temporary directory.+)$"
    )
    re_10 = re.compile(b'Working file: (.+)$')
    re_20 = re.compile(b'symbolic names:')
    re_30 = re.compile(b'\t(.+): ([\\d.]+)$')
    re_31 = re.compile(b'----------------------------$')
    re_32 = re.compile(
        b'======================================='
        b'======================================$'
    )
    re_50 = re.compile(br'revision ([\d.]+)(\s+locked by:\s+.+;)?$')
    re_60 = re.compile(
        br'date:\s+(.+);\s+author:\s+(.+);\s+state:\s+(.+?);'
        br'(\s+lines:\s+(\+\d+)?\s+(-\d+)?;)?'
        br'(\s+commitid:\s+([^;]+);)?'
        br'(.*mergepoint:\s+([^;]+);)?'
    )
    re_70 = re.compile(b'branches: (.+);$')

    file_added_re = re.compile(br'file [^/]+ was (initially )?added on branch')

    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

        if prefix and not prefix.endswith(pycompat.ossep):
            prefix += pycompat.ossep

        # Use the Root file in the sandbox, if it exists
        try:
            root = open(os.path.join('CVS', 'Root'), 'rb').read().strip()
        except IOError:
            pass

    if not root:
        root = encoding.environ.get('CVSROOT', '')

        # and
        #    /pserver/user/server/path
        # are mapped to different cache file names.
        cachefile = root.split(":") + [directory, "cache"]
        cachefile = ['-'.join(re.findall(br'\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(open(cachefile, 'rb'))
            for e in oldlog:
                if not (
                    util.safehasattr(e, 'branchpoints')
                    and util.safehasattr(e, 'commitid')
                    and util.safehasattr(e, 'mergepoint')
                ):
                    ui.status(_('ignoring old cache\n'))
                    oldlog = []
                    break

            ui.note(_('cache has %d log entries\n') % len(oldlog))
        except Exception as e:
            ui.note(_('error reading cache: %r\n') % e)

        if oldlog:
            date = oldlog[-1].date  # last commit date as a (time,tz) tuple
            date = dateutil.datestr(date, '%Y/%m/%d %H:%M:%S %1%2')

    # build the CVS commandline
    cmd = ['cvs', '-q']
    if root:

        # 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
    branchmap = {}  # mapping between branch names and revision numbers
    rcsmap = {}
    state = 0
    store = False  # set when a new record can be appended

    cmd = [procutil.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))

        if line == '':
            break
        peek = util.fromnativeeol(pfp.readline())
        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:

        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,
                commitid=None,
                mergepoint=None,
                branchpoints=set(),
            )

            state = 6

        elif state == 6:
            # expecting date, author, state, lines changed

                d = '19' + d

            if len(d.split()) != 3:
                # cvs log dates always in GMT
                d = d + ' UTC'
            e.date = dateutil.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):

            elif match.group(6):
                e.lines = (0, int(match.group(6)))
            else:
                e.lines = None

            if match.group(7):  # cvs 1.12 commitid
                e.commitid = match.group(8)

            if match.group(9):  # cvsnt mergepoint
                myrev = match.group(10).split('.')
                if len(myrev) == 2:  # head
                    e.mergepoint = 'HEAD'
                else:
                    myrev = '.'.join(myrev[:-2] + ['0', myrev[-2]])
                    branches = [b for b in branchmap if branchmap[b] == myrev]
                    assert len(branches) == 1, (
                        'unknown branch: %s' % e.mergepoint
                    )
                    e.mergepoint = branches[0]

            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) and re_50.match(peek):
                state = 5
                store = True
            elif re_32.match(line):

        # Likewise, if you merge such a file to a later branch B2 (one
        # that already existed when the file was added on B1), CVS
        # creates a synthetic dead revision 1.1.x.1 on B2.  Don't drop
        # these revisions now, but mark them synthetic so
        # createchangeset() can take care of them.
        if (
            store
            and e.dead
            and e.revision[-1] == 1
            and len(e.comment) == 1  # 1.1 or 1.1.x.1
            and file_added_re.match(e.comment[0])
        ):
            ui.debug(
                'found synthetic revision in %s: %r\n' % (e.rcs, e.comment[0])
            )
            e.synthetic = True

        if store:
            # clean up the results and save in the log.
            store = False

            # find the branches starting from this revision
            branchpoints = set()
            for branch, revision in branchmap.iteritems():
                revparts = tuple([int(i) for i in revision.split('.')])
                if len(revparts) < 2:  # bad tags
                    continue
                if revparts[-2] == 0 and revparts[-1] % 2 == 0:
                    # normal branch
                    if revparts[:-2] == e.revision:
                        branchpoints.add(branch)
                elif revparts == (1, 1, 1):  # vendor branch
                    if revparts in e.branches:
                        branchpoints.add(branch)
            e.branchpoints = branchpoints

            log.append(e)

            rcsmap[e.rcs.replace('/Attic/', '/')] = e.rcs

            if len(log) % 100 == 0:
                ui.status(
                    stringutil.ellipsis('%d %s' % (len(log), e.file), 80) + '\n'
                )

    log.sort(key=lambda x: (x.rcs, x.revision))

    # find parent revisions of individual files
    versions = {}

        if log:
            # join up the old and new logs
            log.sort(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)

    ui.status(_('%d log entries\n') % len(log))

    encodings = ui.configlist('convert', 'cvsps.logencoding')
    if encodings:

        def revstr(r):
            # this is needed, because logentry.revision is a tuple of "int"
            # (e.g. (1, 2) for "1.2")
            return '.'.join(pycompat.maplist(pycompat.bytestr, r))

        for entry in log:
            comment = entry.comment
            for e in encodings:
                try:
                    entry.comment = comment.decode(pycompat.sysstr(e)).encode(
                        'utf-8'
                    )
                    if ui.debugflag:
                        ui.debug(
                            "transcoding by %s: %s of %s\n"
                            % (e, revstr(entry.revision), entry.file)
                        )
                    break
                except UnicodeDecodeError:
                    pass  # try next encoding
                except LookupError as inst:  # unknown encoding, maybe
                    raise error.Abort(
                        inst,
                        hint=_(
                            'check convert.cvsps.logencoding' ' configuration'
                        ),
                    )
            else:
                raise error.Abort(
                    _(
                        "no encoding can transcode"
                        " CVS log message for %s of %s"
                    )
                    % (revstr(entry.revision), entry.file),
                    hint=_('check convert.cvsps.logencoding' ' configuration'),
                )

    hook.hook(ui, None, "cvslog", True, log=log)

    return log

        .tags      - list of tags on this changeset
        .synthetic - from synthetic revision "file ... added on branch ..."
        .mergepoint- the branch that has been merged from or None
        .branchpoints- the branches that start at the current entry or empty
    '''

    def __init__(self, **entries):
        self.id = None
        self.synthetic = False
        self.__dict__.update(entries)

    def __repr__(self):
        items = ("%s=%r" % (k, self.__dict__[k]) for k in sorted(self.__dict__))
        return "%s(%s)" % (type(self).__name__, ", ".join(items))


def createchangeset(ui, log, fuzz=60, mergefrom=None, mergeto=None):
    '''Convert log into changesets.'''

    ui.status(_('creating changesets\n'))

                mindate[e.commitid] = e.date
            else:
                mindate[e.commitid] = min(e.date, mindate[e.commitid])

    # Merge changesets
    log.sort(
        key=lambda x: (
            mindate.get(x.commitid, (-1, 0)),
            x.commitid or '',
            x.comment,
            x.author,
            x.branch or '',
            x.date,
            x.branchpoints,
        )
    )

    changesets = []
    files = set()
    c = None
    for i, e in enumerate(log):

        # Here foo is part only of MYBRANCH, but not MYBRANCH2, e.g. a
        # later version of foo may be in MYBRANCH2, so foo should be the
        # first changeset and bar the next and MYBRANCH and MYBRANCH2
        # should both start off of the bar changeset. No provisions are
        # made to ensure that this is, in fact, what happens.
        if not (
            c
            and e.branchpoints == c.branchpoints
            and (  # cvs commitids
                (e.commitid is not None and e.commitid == c.commitid)
                or (  # no commitids, use fuzzy commit detection
                    (e.commitid is None or c.commitid is None)
                    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=[],
                mergepoint=e.mergepoint,
                branchpoints=e.branchpoints,
                commitid=e.commitid,
            )
            changesets.append(c)

            files = set()
            if len(changesets) % 100 == 0:
                t = '%d %s' % (len(changesets), repr(e.comment)[1:-1])
                ui.status(stringutil.ellipsis(t, 80) + '\n')

        c.entries.append(e)
        files.add(e.file)
        c.date = e.date  # changeset date is date of latest commit in it

    # Mark synthetic changesets

    for c in changesets:
        # Synthetic revisions always get their own changeset, because

        c.entries.sort(key=functools.cmp_to_key(entitycompare))

    # Sort changesets by date

    odd = set()

    def cscmp(l, r):
        d = sum(l.date) - sum(r.date)
        if d:
            return d

    if mergefrom is None:
        mergefrom = br'{{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]

        if p is not None:
            p = changesets[p]

            # Ensure no changeset has a synthetic changeset as a parent.
            while p.synthetic:
                assert len(p.parents) <= 1, _(
                    'synthetic changeset cannot have multiple parents'
                )
                if p.parents:
                    p = p.parents[0]
                else:
                    p = None
                    break

                if m == 'HEAD':
                    m = None
                try:
                    candidate = changesets[branches[m]]
                except KeyError:
                    ui.warn(
                        _(
                            "warning: CVS commit message references "
                            "non-existent branch %r:\n%s\n"
                        )
                        % (pycompat.bytestr(m), c.comment)
                    )
                if m in branches and c.branch != m and not candidate.synthetic:
                    c.parents.append(candidate)

        if mergeto:
            m = mergeto.search(c.comment)

                if m.groups():
                    m = m.group(1)
                    if m == 'HEAD':
                        m = None
                else:
                    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

        c.id = i + 1

    if odd:
        for l, r in odd:
            if l.id is not None and r.id is not None:
                ui.warn(
                    _('changeset %d is both before and after %d\n')
                    % (l.id, r.id)
                )

    ui.status(_('%d changeset entries\n') % len(changesets))

    hook.hook(ui, None, "cvschangesets", True, changesets=changesets)

            for d in args:
                log += createlog(ui, d, root=opts["root"], cache=cache)
        else:
            log = createlog(ui, root=opts["root"], cache=cache)
    except logerror as 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'
                    % dateutil.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 cs.branchpoints:
                ui.write(
                    'Branchpoints: %s \n' % ', '.join(sorted(cs.branchpoints))
                )
            if opts["parents"] and cs.parents:
                if len(cs.parents) > 1:
                    ui.write(
                        (
                            'Parents: %s\n'
                            % (','.join([(b"%d" % p.id) for p in cs.parents]))
                        )
                    )
                else:
                    ui.write(('Parent: %d\n' % cs.parents[0].id))

            if opts["ancestors"]:
                b = cs.branch

                    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([b"%d" % x for x in f.parent]) or 'INITIAL',
                        '.'.join([(b"%d" % 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] == (b"%d" % 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] == (b"%d" % cs.id) or revisions[1] in cs.tags:
                break