tests/models/donut/test_processing_donut.py - main - githubmirror/transformers

tests/models/donut/test_processing_donut.py

59 строк2 KB

Yih-Dar

tests: reduce processor test memory usage and use tiny test assets (#47168)

08 июл 2026, 14:50

08 июл 2026, 14:5041fc5b4

# 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 unittest

from transformers import DonutProcessor

from ...test_processing_common import ProcessorTesterMixin


class DonutProcessorTest(ProcessorTesterMixin, unittest.TestCase):
    # Tiny processor created with make_tiny_processor.py from "naver-clova-ix/donut-base"
    tiny_model_id = "hf-internal-testing/tiny-processor-donut"
    processor_class = DonutProcessor

    @classmethod
    def _setup_image_processor(cls):
        image_processor_class = cls._get_component_class_from_processor("image_processor")
        # Default size=2560×1920 is the document-scanning resolution (~59 MB per image as float32).
        # Use 64×64 for tests — no assertions check spatial dimensions.
        return image_processor_class.from_pretrained(cls.tiny_model_id, size={"height": 64, "width": 64})

    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>"
        )
        processor = self.get_processor()
        actual_json = processor.token2json(sequence)

        self.assertDictEqual(actual_json, expected_json)