hgext/convert/cvsps.py

6687:f8ef39206f6a

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

        # 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('/'):
            prefix+='/'

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

        # 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))

    cmd = ['cvs', '-q']
    if root:
        cmd.append('-d%s' % root)
        p = root.split(':')[-1]
        if not p.endswith('/'):
            p+='/'
        prefix = p+prefix
    cmd.append(['log', 'rlog'][rlog])
    if date:
        # no space between option and date string
        cmd.append('-d>%s' % date)
    cmd.append(directory)

            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))

            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):

                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(';')]

            e.tags = [scache(x) for x in tags.get(e.revision, [])]
            e.tags.sort()
            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 = {}

        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:

        # 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:
                ui.status(util.ellipsis('%d %s'%(len(changesets), repr(e.comment)[1:-1]), 80)+'\n')

        e.Changeset = c
        c.entries.append(e)
        files[e.file] = True
        c.date = e.date       # changeset date is date of latest commit in it

            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 = {}

                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

        i += 1

    # Number changesets

    for i, c in enumerate(changesets):
        c.id = i+1

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

    return changesets

6688:5cd7a8433cd4

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

        # 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('/'):
            prefix += '/'

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

        # 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))

    cmd = ['cvs', '-q']
    if root:
        cmd.append('-d%s' % root)
        p = root.split(':')[-1]
        if not p.endswith('/'):
            p += '/'
        prefix = p + prefix
    cmd.append(['log', 'rlog'][rlog])
    if date:
        # no space between option and date string
        cmd.append('-d>%s' % date)
    cmd.append(directory)

            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))

            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):

                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(';')]

            e.tags = [scache(x) for x in tags.get(e.revision, [])]
            e.tags.sort()
            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 = {}

        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:

        # 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')

        e.Changeset = c
        c.entries.append(e)
        files[e.file] = True
        c.date = e.date       # changeset date is date of latest commit in it

            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 = {}

                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

        i += 1

    # Number changesets

    for i, c in enumerate(changesets):
        c.id = i + 1

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

    return changesets