europarl.py 文件源码

def __iter__(self) -> Iterator[Tuple[str, str]]:
        with EuroparlCache() as europarl_cache:
            europarl_cache.download(name='europarl-v7.tgz', url=_v7_url)

            # peak in tarball
            filepath = europarl_cache.filepath('europarl-v7.tgz')
            source_filepath, target_filepath = self._files()
            with tar_extract_file(filepath, source_filepath) as source_file, \
                    tar_extract_file(filepath, target_filepath) as target_file:

                observations = 0
                for source, target in zip(source_file, target_file):
                    source, target = (source.rstrip(), target.rstrip())
                    if self._length_checker(source, target):
                        yield (source, target)
                        observations += 1

                        if self._max_observations is not None and \
                           observations >= self._max_observations:
                            break