comparison hgext/convert/cvsps.py @ 19145:0a12e5f3a979 stable

convert: fix bug of wrong CVS path parsing without port number (issue3678)

The cvsps.py:getrepopath suffers from a string parsing bug (it returns
"user@server/path/to/repository" if the CVSROOT is given like this:
":pserver:user@server/path/to/repository" ), which gives returnes the wrong
value becouse cvsps.py fails to strip the prefix from filenames.
With this patch for the same input we get the correct repo path that is:
"/path/to/repository"

19131:af3b651505e2

    """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

19145:0a12e5f3a979

    """Return the repository path from a CVS path.

    >>> getrepopath('/foo/bar')
    '/foo/bar'
    >>> getrepopath('c:/foo/bar')
    '/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')
    '/foo/bar'
    >>> getrepopath(':pserver:[e-mail]:/foo/bar')
    '/foo/bar'
    >>> getrepopath(':pserver:[e-mail]:c:/foo/bar')
    '/foo/bar'
    >>> getrepopath('user@server/path/to/repository')
    '/path/to/repository'
    """
    # According to CVS manual, CVS paths are expressed like:
    # [:method:][[user][:password]@]hostname[:[port]]/path/to/repository
    #
    # CVSpath is splitted into parts and then position of the first occurrence
    # of the '/' char after the '@' is located. The solution is the rest of the
    # string after that '/' sign including it

    parts = cvspath.split(':')
    atposition = parts[-1].find('@')
    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