def testSpaceTokenizer(self):
self._testTokenizer(tokenizers.SpaceTokenizer(),
["Hello world !", "How are you ?", "Good !"],
[["Hello", "world", "!"],
["How", "are", "you", "?"], ["Good", "!"]])
self._testDetokenizer(
tokenizers.SpaceTokenizer(),
[["Hello", "world", "!"], ["Test"], ["My", "name"]],
["Hello world !", "Test", "My name"])
def initialize(self, metadata, asset_dir=None, asset_prefix=""):
self.vocabulary_file = metadata[self.vocabulary_file_key]
self.vocabulary_size = count_lines(self.vocabulary_file) + self.num_oov_buckets
if self.tokenizer is None:
tokenizer_config = _get_field(metadata, "tokenization", prefix=asset_prefix)
if tokenizer_config:
if isinstance(tokenizer_config, six.string_types) and compat.gfile_exists(tokenizer_config):
with compat.gfile_open(tokenizer_config, mode="rb") as config_file:
tokenizer_config = yaml.load(config_file)
self.tokenizer = tokenizers.OpenNMTTokenizer(params=tokenizer_config)
else:
self.tokenizer = tokenizers.SpaceTokenizer()
self.tokenizer.initialize(metadata)
return super(TextInputter, self).initialize(
metadata, asset_dir=asset_dir, asset_prefix=asset_prefix)
