transformers/tests/models/biogpt/test_tokenization_biogpt.py

# Copyright 2022 The HuggingFace Team. 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 json
import os
import shutil
import tempfile
import unittest

from transformers.models.biogpt.tokenization_biogpt import VOCAB_FILES_NAMES, BioGptTokenizer
from transformers.testing_utils import require_sacremoses, slow

from ...test_tokenization_common import TokenizerTesterMixin


@require_sacremoses
class BioGptTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
    from_pretrained_id = "microsoft/biogpt"
    tokenizer_class = BioGptTokenizer
    test_rust_tokenizer = False

    @classmethod
    def setUpClass(cls):
        super().setUpClass()

        # Adapted from Sennrich et al. 2015 and https://github.com/rsennrich/subword-nmt
        cls.vocab = [
            "l",
            "o",
            "w",
            "e",
            "r",
            "s",
            "t",
            "i",
            "d",
            "n",
            "w</w>",
            "r</w>",
            "t</w>",
            "lo",
            "low",
            "er</w>",
            "low</w>",
            "lowest</w>",
            "newer</w>",
            "wider</w>",
            "<unk>",
        ]
        cls.merges = ["l o 123", "lo w 1456", "e r</w> 1789", ""]

        cls.vocab_file = os.path.join(cls.tmpdirname, VOCAB_FILES_NAMES["vocab_file"])
        cls.merges_file = os.path.join(cls.tmpdirname, VOCAB_FILES_NAMES["merges_file"])

    def get_input_output_texts(self, tokenizer):
        input_text = "lower newer"
        output_text = "lower newer"
        return input_text, output_text

    def test_full_tokenizer(self):
        """Adapted from Sennrich et al. 2015 and https://github.com/rsennrich/subword-nmt"""

        vocab = [
            "l",
            "o",
            "w",
            "e",
            "r",
            "s",
            "t",
            "i",
            "d",
            "n",
            "w</w>",
            "r</w>",
            "t</w>",
            "lo",
            "low",
            "er</w>",
            "low</w>",
            "lowest</w>",
            "newer</w>",
            "wider</w>",
            "<unk>",
        ]
        vocab_tokens = dict(zip(vocab, range(len(vocab))))
        merges = ["l o 123", "lo w 1456", "e r</w> 1789", ""]

        with tempfile.TemporaryDirectory() as tmpdir:
            vocab_file = os.path.join(tmpdir, VOCAB_FILES_NAMES["vocab_file"])
            merges_file = os.path.join(tmpdir, VOCAB_FILES_NAMES["merges_file"])
            shutil.copy(self.vocab_file, vocab_file)
            shutil.copy(self.merges_file, merges_file)
            with open(vocab_file, "w") as fp:
                fp.write(json.dumps(vocab_tokens))
            with open(merges_file, "w") as fp:
                fp.write("\n".join(merges))
            tokenizer = BioGptTokenizer(vocab_file, merges_file)

        text = "lower"
        bpe_tokens = ["low", "er</w>"]
        tokens = tokenizer.tokenize(text)
        self.assertListEqual(tokens, bpe_tokens)

        input_tokens = tokens + ["<unk>"]
        input_bpe_tokens = [14, 15, 20]
        self.assertListEqual(tokenizer.convert_tokens_to_ids(input_tokens), input_bpe_tokens)

    @slow
    def test_sequence_builders(self):
        tokenizer = BioGptTokenizer.from_pretrained("microsoft/biogpt")

        text = tokenizer.encode("sequence builders", add_special_tokens=False)
        text_2 = tokenizer.encode("multi-sequence build", add_special_tokens=False)

        encoded_sentence = tokenizer.build_inputs_with_special_tokens(text)
        encoded_pair = tokenizer.build_inputs_with_special_tokens(text, text_2)

        self.assertTrue(encoded_sentence == [2] + text)
        self.assertTrue(encoded_pair == [2] + text + [2] + text_2)