from ...processing_utils import ProcessorMixin, ProcessingKwargs, Unpack

class MyModelProcessorKwargs(ProcessingKwargs, total=False):
    images_kwargs: MyModelImageProcessorKwargs
    _defaults = {
        "text_kwargs": {"padding": True},
        "images_kwargs": {"do_convert_rgb": True},
    }

class MyModelProcessor(ProcessorMixin):
    valid_processor_kwargs = MyModelProcessorKwargs

    def __init__(self, image_processor, tokenizer, chat_template=None, **kwargs):
        self.image_token = tokenizer.image_token
        self.image_token_id = tokenizer.image_token_id
        super().__init__(
            image_processor=image_processor,
            tokenizer=tokenizer,
            chat_template=chat_template,
            **kwargs,
        )

def replace_image_token(self, image_inputs: dict, image_idx: int) -> str:
    num_crops = image_inputs["num_crops"][image_idx]
    return f"{self.boi_token}{self.image_token * self.num_image_tokens * num_crops}{self.eoi_token}"

def prepare_inputs_layout(self, images=None, text=None, videos=None, audio=None, **kwargs):
    # Call `super()` to apply common preparation steps first 
    images, text, videos, audio = super().prepare_inputs_layout(images, text, videos, audio)
    if images is not None:
        images = make_nested_list_of_images(images)
    return images, text, videos, audio

def validate_inputs(self, images=None, text=None, videos=None, audio=None, **kwargs):
    super().validate_inputs(images=images, text=text, **kwargs)
    if text is not None and images is not None:
        n_tokens = [s.count(self.image_token) for s in text]
        n_images = [len(img_list) for img_list in images]
        if n_tokens != n_images:
            raise ValueError(
                f"Number of {self.image_token} tokens in text {n_tokens} does not match "
                f"number of images {n_images}."
            )

# tests/models/my_model_name/test_processor_<my_model_name>.py

from transformers.testing_utils import require_vision
from transformers.utils import is_vision_available
from ...test_processing_common import ProcessorTesterMixin

if is_vision_available():
    from transformers import MyModelProcessor

@require_vision
class MyModelProcessorTest(ProcessorTesterMixin, unittest.TestCase):
    processor_class = MyModelProcessor

    def get_processor(self):
        return MyModelProcessor.from_pretrained("hf-internal-testing/my-model-test")