test_tokenization_t5.py

# coding=utf-8
# Copyright 2021 The OneFlow Authors. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.


import os
import shutil
import tempfile
import unittest

from libai.tokenizer.tokenization_t5 import T5Tokenizer
from tests.fixtures.utils import get_fixtures
from tests.tokenizer.test_tokenization_common import TokenizerTesterMixin

SPIECE_UNDERLINE = "▁"

SAMPLE_VOCAB = os.path.join(
    os.path.dirname(os.path.abspath(__file__)), "../fixtures/test_sentencepiece.model"
)


class T5TokenizationTest(TokenizerTesterMixin, unittest.TestCase):

    tokenizer_class = T5Tokenizer

    def setUp(self):
        super().setUp()

        # We have a SentencePiece fixture for testing
        get_fixtures(SAMPLE_VOCAB)
        tokenizer = T5Tokenizer(SAMPLE_VOCAB)
        tokenizer.save_pretrained(self.tmpdirname)

    def test_convert_token_and_id(self):
        """Test ``_convert_token_to_id`` and ``_convert_id_to_token``."""
        token = "<s>"
        token_id = 1

        self.assertEqual(self.get_tokenizer()._convert_token_to_id(token), token_id)
        self.assertEqual(self.get_tokenizer()._convert_id_to_token(token_id), token)

    def test_get_vocab(self):
        vocab_keys = list(self.get_tokenizer().get_vocab().keys())

        self.assertEqual(vocab_keys[0], "<unk>")
        self.assertEqual(vocab_keys[1], "<s>")
        self.assertEqual(vocab_keys[-1], "<pad>")
        self.assertEqual(len(vocab_keys), 1_101)

    def test_vocab_size(self):
        self.assertEqual(self.get_tokenizer().vocab_size, 1_100)

    def test_full_tokenizer(self):
        tokenizer = T5Tokenizer(SAMPLE_VOCAB)

        tokens = tokenizer.tokenize("This is a test")
        self.assertListEqual(tokens, ["▁This", "▁is", "▁a", "▁t", "est"])

        self.assertListEqual(tokenizer.convert_tokens_to_ids(tokens), [285, 46, 10, 170, 382])

        tokens = tokenizer.tokenize("I was born in 92000, and this is falsé.")
        self.assertListEqual(
            tokens,
            [
                SPIECE_UNDERLINE + "I",
                SPIECE_UNDERLINE + "was",
                SPIECE_UNDERLINE + "b",
                "or",
                "n",
                SPIECE_UNDERLINE + "in",
                SPIECE_UNDERLINE + "",
                "9",
                "2",
                "0",
                "0",
                "0",
                ",",
                SPIECE_UNDERLINE + "and",
                SPIECE_UNDERLINE + "this",
                SPIECE_UNDERLINE + "is",
                SPIECE_UNDERLINE + "f",
                "al",
                "s",
                "é",
                ".",
            ],
        )
        ids = tokenizer.convert_tokens_to_ids(tokens)
        self.assertListEqual(
            ids, [8, 21, 84, 55, 24, 19, 7, 0, 602, 347, 347, 347, 3, 12, 66, 46, 72, 80, 6, 0, 4]
        )

        back_tokens = tokenizer.convert_ids_to_tokens(ids)
        self.assertListEqual(
            back_tokens,
            [
                SPIECE_UNDERLINE + "I",
                SPIECE_UNDERLINE + "was",
                SPIECE_UNDERLINE + "b",
                "or",
                "n",
                SPIECE_UNDERLINE + "in",
                SPIECE_UNDERLINE + "",
                "<unk>",
                "2",
                "0",
                "0",
                "0",
                ",",
                SPIECE_UNDERLINE + "and",
                SPIECE_UNDERLINE + "this",
                SPIECE_UNDERLINE + "is",
                SPIECE_UNDERLINE + "f",
                "al",
                "s",
                "<unk>",
                ".",
            ],
        )

    def test_save_and_load_tokenizer(self):
        # Now let's start the test
        tokenizers = self.get_tokenizers()
        for tokenizer in tokenizers:
            with self.subTest(f"{tokenizer.__class__.__name__}"):
                # Isolate this from the other tests because we save additional tokens/etc
                tmpdirname = tempfile.mkdtemp()

                sample_text = " He is very happy, UNwant\u00E9d,running"
                before_tokens = tokenizer.encode(sample_text)
                before_vocab = tokenizer.get_vocab()
                tokenizer.save_pretrained(tmpdirname)

                after_tokenizer = tokenizer.__class__.from_pretrained(tmpdirname)
                after_tokens = after_tokenizer.encode(sample_text)
                after_vocab = after_tokenizer.get_vocab()
                self.assertListEqual(before_tokens, after_tokens)
                self.assertDictEqual(before_vocab, after_vocab)

                shutil.rmtree(tmpdirname)


if __name__ == "__main__":
    unittest.main()