def __init__(self, basedir, doctype, encoding='utf-8', indexstyle=None, threshold=100, verbose=False): self.basedir = basedir self.threshold = threshold self.verbose = verbose self._corpus = self.GzipTarDBCorpusWithLabel(os.path.join( basedir, 'src'), doctype, encoding, indexstyle=indexstyle) self._artdb = FixedDB(os.path.join(basedir, 'articles')) self._indexdb = IndexDB(os.path.join(basedir, 'idx'), 'idx') self._loctoindex = None self._mode = None return