# Copyright 2024 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 shutil
import tempfile
import unittest

from transformers import GemmaTokenizer
from transformers.testing_utils import get_tests_dir, require_torch, require_vision
from transformers.utils import is_vision_available

from ...test_processing_common import ProcessorTesterMixin


if is_vision_available():
    from transformers import (
        PaliGemmaProcessor,
        SiglipImageProcessor,
        is_vision_available,
    )

SAMPLE_VOCAB = get_tests_dir("fixtures/test_sentencepiece.model")


@require_vision
class PaliGemmaProcessorTest(ProcessorTesterMixin, unittest.TestCase):
    processor_class = PaliGemmaProcessor

    def setUp(self):
        self.tmpdirname = tempfile.mkdtemp()
        image_processor = SiglipImageProcessor.from_pretrained("google/siglip-so400m-patch14-384")
        image_processor.image_seq_length = 0
        tokenizer = GemmaTokenizer(SAMPLE_VOCAB, keep_accents=True)
        processor = PaliGemmaProcessor(image_processor=image_processor, tokenizer=tokenizer)
        processor.save_pretrained(self.tmpdirname)

    def tearDown(self):
        shutil.rmtree(self.tmpdirname)

    @require_torch
    @require_vision
    def test_image_seq_length(self):
        input_str = "lower newer"
        image_input = self.prepare_image_inputs()
        image_processor = self.get_component("image_processor")
        tokenizer = self.get_component("tokenizer", max_length=112, padding="max_length")
        image_processor.image_seq_length = 14
        processor = self.processor_class(tokenizer=tokenizer, image_processor=image_processor)
        inputs = processor(
            text=input_str, images=image_input, return_tensors="pt", max_length=112, padding="max_length"
        )
        self.assertEqual(len(inputs["input_ids"][0]), 112 + 14)

    @require_torch
    @require_vision
    def test_unstructured_kwargs_batched(self):
        if "image_processor" not in self.processor_class.attributes:
            self.skipTest(f"image_processor attribute not present in {self.processor_class}")
        image_processor = self.get_component("image_processor")
        tokenizer = self.get_component("tokenizer")

        processor = self.processor_class(tokenizer=tokenizer, image_processor=image_processor)
        self.skip_processor_without_typed_kwargs(processor)

        input_str = ["lower newer", "upper older longer string"]
        image_input = self.prepare_image_inputs() * 2
        inputs = processor(
            text=input_str,
            images=image_input,
            return_tensors="pt",
            size={"height": 214, "width": 214},
            padding="longest",
            max_length=76,
        )

        self.assertEqual(inputs["pixel_values"].shape[2], 214)

        self.assertEqual(len(inputs["input_ids"][0]), 10)