[Dependencies|tokenizers] Make both SentencePiece and Tokenizers optional dependencies (#7659)

* splitting fast and slow tokenizers [WIP] * [WIP] splitting sentencepiece and tokenizers dependencies * update dummy objects * add name_or_path to models and tokenizers * prefix added to file names * prefix * styling + quality * spliting all the tokenizer files - sorting sentencepiece based ones * update tokenizer version up to 0.9.0 * remove hard dependency on sentencepiece 🎉 * and removed hard dependency on tokenizers 🎉 * update conversion script * update missing models * fixing tests * move test_tokenization_fast to main tokenization tests - fix bugs * bump up tokenizers * fix bert_generation * update ad fix several tokenizers * keep sentencepiece in deps for now * fix funnel and deberta tests * fix fsmt * fix marian tests * fix layoutlm * fix squeezebert and gpt2 * fix T5 tokenization * fix xlnet tests * style * fix mbart * bump up tokenizers to 0.9.2 * fix model tests * fix tf models * fix seq2seq examples * fix tests without sentencepiece * fix slow => fast conversion without sentencepiece * update auto and bert generation tests * fix mbart tests * fix auto and common test without tokenizers * fix tests without tokenizers * clean up tests lighten up when tokenizers + sentencepiece are both off * style quality and tests fixing * add sentencepiece to doc/examples reqs * leave sentencepiece on for now * style quality split hebert and fix pegasus * WIP Herbert fast * add sample_text_no_unicode and fix hebert tokenization * skip FSMT example test for now * fix style * fix fsmt in example tests * update following Lysandre and Sylvain's comments * Update src/transformers/testing_utils.py Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com> * Update src/transformers/testing_utils.py Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com> * Update src/transformers/tokenization_utils_base.py Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com> * Update src/transformers/tokenization_utils_base.py Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com> Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
2020-10-18 20:51:24 +02:00
parent c65863ce53
commit ba8c4d0ac0
140 changed files with 6551 additions and 3961 deletions
--- a/tests/test_tokenization_bert.py
+++ b/tests/test_tokenization_bert.py
@@ -17,27 +17,29 @@
 import os
 import unittest

-from transformers.testing_utils import slow
+from transformers import BertTokenizerFast
+from transformers.testing_utils import require_tokenizers, slow
 from transformers.tokenization_bert import (
    VOCAB_FILES_NAMES,
    BasicTokenizer,
    BertTokenizer,
-    BertTokenizerFast,
    WordpieceTokenizer,
    _is_control,
    _is_punctuation,
    _is_whitespace,
 )

-from .test_tokenization_common import TokenizerTesterMixin
+from .test_tokenization_common import TokenizerTesterMixin, filter_non_english


+@require_tokenizers
 class BertTokenizationTest(TokenizerTesterMixin, unittest.TestCase):

    tokenizer_class = BertTokenizer
    rust_tokenizer_class = BertTokenizerFast
    test_rust_tokenizer = True
    space_between_special_tokens = True
+    from_pretrained_filter = filter_non_english

    def setUp(self):
        super().setUp()
@@ -245,3 +247,55 @@ class BertTokenizationTest(TokenizerTesterMixin, unittest.TestCase):

        assert encoded_sentence == [101] + text + [102]
        assert encoded_pair == [101] + text + [102] + text_2 + [102]
+
+    def test_offsets_with_special_characters(self):
+        for tokenizer, pretrained_name, kwargs in self.tokenizers_list:
+            with self.subTest("{} ({})".format(tokenizer.__class__.__name__, pretrained_name)):
+                tokenizer_r = self.rust_tokenizer_class.from_pretrained(pretrained_name, **kwargs)
+
+                sentence = f"A, naïve {tokenizer_r.mask_token} AllenNLP sentence."
+                tokens = tokenizer_r.encode_plus(
+                    sentence,
+                    return_attention_mask=False,
+                    return_token_type_ids=False,
+                    return_offsets_mapping=True,
+                    add_special_tokens=True,
+                )
+
+                do_lower_case = tokenizer_r.do_lower_case if hasattr(tokenizer_r, "do_lower_case") else False
+                expected_results = (
+                    [
+                        ((0, 0), tokenizer_r.cls_token),
+                        ((0, 1), "A"),
+                        ((1, 2), ","),
+                        ((3, 5), "na"),
+                        ((5, 6), "##ï"),
+                        ((6, 8), "##ve"),
+                        ((9, 15), tokenizer_r.mask_token),
+                        ((16, 21), "Allen"),
+                        ((21, 23), "##NL"),
+                        ((23, 24), "##P"),
+                        ((25, 33), "sentence"),
+                        ((33, 34), "."),
+                        ((0, 0), tokenizer_r.sep_token),
+                    ]
+                    if not do_lower_case
+                    else [
+                        ((0, 0), tokenizer_r.cls_token),
+                        ((0, 1), "a"),
+                        ((1, 2), ","),
+                        ((3, 8), "naive"),
+                        ((9, 15), tokenizer_r.mask_token),
+                        ((16, 21), "allen"),
+                        ((21, 23), "##nl"),
+                        ((23, 24), "##p"),
+                        ((25, 33), "sentence"),
+                        ((33, 34), "."),
+                        ((0, 0), tokenizer_r.sep_token),
+                    ]
+                )
+
+                self.assertEqual(
+                    [e[1] for e in expected_results], tokenizer_r.convert_ids_to_tokens(tokens["input_ids"])
+                )
+                self.assertEqual([e[0] for e in expected_results], tokens["offset_mapping"])