mirror of
https://github.com/huggingface/transformers.git
synced 2025-07-14 18:18:24 +06:00
9aeacb58ba
* [WIP] SP tokenizers * fixing tests for T5 * WIP tokenizers * serialization * update T5 * WIP T5 tokenization * slow to fast conversion script * Refactoring to move tokenzier implementations inside transformers * Adding gpt - refactoring - quality * WIP adding several tokenizers to the fast world * WIP Roberta - moving implementations * update to dev4 switch file loading to in-memory loading * Updating and fixing * advancing on the tokenizers - updating do_lower_case * style and quality * moving forward with tokenizers conversion and tests * MBart, T5 * dumping the fast version of transformer XL * Adding to autotokenizers + style/quality * update init and space_between_special_tokens * style and quality * bump up tokenizers version * add protobuf * fix pickle Bert JP with Mecab * fix newly added tokenizers * style and quality * fix bert japanese * fix funnel * limite tokenizer warning to one occurence * clean up file * fix new tokenizers * fast tokenizers deep tests * WIP adding all the special fast tests on the new fast tokenizers * quick fix * adding more fast tokenizers in the fast tests * all tokenizers in fast version tested * Adding BertGenerationFast * bump up setup.py for CI * remove BertGenerationFast (too early) * bump up tokenizers version * Clean old docstrings * Typo * Update following Lysandre comments Co-authored-by: Sylvain Gugger <sylvain.gugger@gmail.com>
181 lines
5.8 KiB
Python
181 lines
5.8 KiB
Python
# coding=utf-8
|
|
# Copyright 2018 The Google AI Language Team Authors.
|
|
#
|
|
# 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 unittest
|
|
|
|
from transformers.testing_utils import slow
|
|
from transformers.tokenization_xlnet import SPIECE_UNDERLINE, XLNetTokenizer, XLNetTokenizerFast
|
|
|
|
from .test_tokenization_common import TokenizerTesterMixin
|
|
|
|
|
|
SAMPLE_VOCAB = os.path.join(os.path.dirname(os.path.abspath(__file__)), "fixtures/test_sentencepiece.model")
|
|
|
|
|
|
class XLNetTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
|
|
|
|
tokenizer_class = XLNetTokenizer
|
|
rust_tokenizer_class = XLNetTokenizerFast
|
|
test_rust_tokenizer = True
|
|
|
|
def setUp(self):
|
|
super().setUp()
|
|
|
|
# We have a SentencePiece fixture for testing
|
|
tokenizer = XLNetTokenizer(SAMPLE_VOCAB, keep_accents=True)
|
|
tokenizer.sanitize_special_tokens()
|
|
tokenizer.save_pretrained(self.tmpdirname)
|
|
|
|
def test_full_tokenizer(self):
|
|
tokenizer = XLNetTokenizer(SAMPLE_VOCAB, keep_accents=True)
|
|
|
|
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_tokenizer_lower(self):
|
|
tokenizer = XLNetTokenizer(SAMPLE_VOCAB, do_lower_case=True)
|
|
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",
|
|
"se",
|
|
".",
|
|
],
|
|
)
|
|
self.assertListEqual(tokenizer.tokenize("H\u00E9llo"), ["▁he", "ll", "o"])
|
|
|
|
def test_tokenizer_no_lower(self):
|
|
tokenizer = XLNetTokenizer(SAMPLE_VOCAB, do_lower_case=False)
|
|
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",
|
|
"se",
|
|
".",
|
|
],
|
|
)
|
|
|
|
@slow
|
|
def test_sequence_builders(self):
|
|
tokenizer = XLNetTokenizer.from_pretrained("xlnet-base-cased")
|
|
|
|
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)
|
|
|
|
assert encoded_sentence == text + [4, 3]
|
|
assert encoded_pair == text + [4] + text_2 + [4, 3]
|