langid.py 文件源码

def set_languages(self, langs=None):
    logger.debug("restricting languages to: %s", langs)

    # Unpack the full original model. This is needed in case the language set
    # has been previously trimmed, and the new set is not a subset of the current
    # set.
    nb_ptc, nb_pc, nb_classes = self.__full_model

    if langs is None:
      self.nb_classes = nb_classes 
      self.nb_ptc = nb_ptc
      self.nb_pc = nb_pc

    else:
      # We were passed a restricted set of languages. Trim the arrays accordingly
      # to speed up processing.
      for lang in langs:
        if lang not in nb_classes:
          raise ValueError("Unknown language code %s" % lang)

      subset_mask = np.fromiter((l in langs for l in nb_classes), dtype=bool)
      self.nb_classes = [ c for c in nb_classes if c in langs ]
      self.nb_ptc = nb_ptc[:,subset_mask]
      self.nb_pc = nb_pc[subset_mask]