380b2a0317
* remove tf/flax * fix * style * Update add_new_model_like.py * work in progress * continue * more cleanup * simplify and first final version * fixes -> it works * add linter checks * Update add_new_model_like.py * fix * add modular conversion at the end * Update add_new_model_like.py * add video processor * Update add_new_model_like.py * Update add_new_model_like.py * Update add_new_model_like.py * fix * Update image_processing_auto.py * Update image_processing_auto.py * fix post rebase * start test filenames replacement * rename all test_processor -> test_processing * fix copied from * add docstrings * Update add_new_model_like.py * fix regex * improve wording * Update add_new_model_like.py * Update add_new_model_like.py * Update add_new_model_like.py * start adding test * fix * fix * proper first test * tests * fix * fix * fix * fix * modular can be used from anywhere * protect import * fix * Update add_new_model_like.py * fix
64 lines
2.2 KiB
Python
64 lines
2.2 KiB
Python
# Copyright 2022 HuggingFace Inc.
|
|
#
|
|
# 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 tempfile
|
|
import unittest
|
|
|
|
from transformers import DonutImageProcessor, DonutProcessor, XLMRobertaTokenizerFast
|
|
|
|
from ...test_processing_common import ProcessorTesterMixin
|
|
|
|
|
|
class DonutProcessorTest(ProcessorTesterMixin, unittest.TestCase):
|
|
from_pretrained_id = "naver-clova-ix/donut-base"
|
|
processor_class = DonutProcessor
|
|
|
|
@classmethod
|
|
def setUpClass(cls):
|
|
cls.processor = DonutProcessor.from_pretrained(cls.from_pretrained_id)
|
|
cls.tmpdirname = tempfile.mkdtemp()
|
|
|
|
image_processor = DonutImageProcessor()
|
|
tokenizer = XLMRobertaTokenizerFast.from_pretrained(cls.from_pretrained_id)
|
|
|
|
processor = DonutProcessor(image_processor, tokenizer)
|
|
|
|
processor.save_pretrained(cls.tmpdirname)
|
|
|
|
def test_token2json(self):
|
|
expected_json = {
|
|
"name": "John Doe",
|
|
"age": "99",
|
|
"city": "Atlanta",
|
|
"state": "GA",
|
|
"zip": "30301",
|
|
"phone": "123-4567",
|
|
"nicknames": [{"nickname": "Johnny"}, {"nickname": "JD"}],
|
|
"multiline": "text\nwith\nnewlines",
|
|
"empty": "",
|
|
}
|
|
|
|
sequence = (
|
|
"<s_name>John Doe</s_name><s_age>99</s_age><s_city>Atlanta</s_city>"
|
|
"<s_state>GA</s_state><s_zip>30301</s_zip><s_phone>123-4567</s_phone>"
|
|
"<s_nicknames><s_nickname>Johnny</s_nickname>"
|
|
"<sep/><s_nickname>JD</s_nickname></s_nicknames>"
|
|
"<s_multiline>text\nwith\nnewlines</s_multiline>"
|
|
"<s_empty></s_empty>"
|
|
)
|
|
actual_json = self.processor.token2json(sequence)
|
|
|
|
self.assertDictEqual(actual_json, expected_json)
|