#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
#           This file was automatically generated from src/transformers/models/dots3_note/modular_dots3_note.py.
#               Do NOT edit this file manually as any edits will be overwritten by the generation of
#             the file from the modular. If any change should be done, please apply the change to the
#                          modular_dots3_note.py file directly. One of our CI enforces this.
#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
# Copyright 2026 The Dots Studio team and the HuggingFace Inc. 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.
from ...processing_utils import MultiModalData, ProcessingKwargs, ProcessorMixin
from ...utils import auto_docstring


@auto_docstring
class Dots3NoteProcessor(ProcessorMixin):
    valid_processor_kwargs = ProcessingKwargs

    def __init__(
        self,
        image_processor=None,
        tokenizer=None,
        video_processor=None,
        feature_extractor=None,
        chat_template=None,
    ):
        self.image_token = "<|imgpad|>"
        self.video_token = "<|video_pad|>"
        self.audio_token = "<|audio_comp_pad|>"
        self.image_token_id = tokenizer.convert_tokens_to_ids(self.image_token)
        self.video_token_id = tokenizer.convert_tokens_to_ids(self.video_token)
        self.audio_token_id = tokenizer.convert_tokens_to_ids(self.audio_token)
        super().__init__(
            image_processor=image_processor,
            tokenizer=tokenizer,
            video_processor=video_processor,
            feature_extractor=feature_extractor,
            chat_template=chat_template,
        )

    def replace_image_token(self, image_inputs: dict, image_idx: int, **kwargs) -> str:
        merge_length = self.image_processor.merge_size**2
        num_image_tokens = image_inputs["image_grid_thw"][image_idx].prod() // merge_length
        return self.image_token * num_image_tokens

    def replace_video_token(self, video_inputs: dict, video_idx: int, **kwargs) -> str:
        merge_length = self.video_processor.merge_size**2
        num_video_tokens = video_inputs["video_grid_thw"][video_idx].prod() // merge_length
        return self.video_token * num_video_tokens

    def _get_num_multimodal_tokens(self, image_sizes=None, video_sizes=None, **kwargs):
        """
        Computes the number of placeholder tokens needed for multimodal inputs with the given sizes.
        Args:
            image_sizes (`list[list[int]]`, *optional*):
                The input sizes formatted as (height, width) per each image.
            video_sizes (`list[list[int]]`, *optional*):
                The input sizes formatted as (num_frames, height, width) per each video.
        Returns:
            `MultiModalData`: A `MultiModalData` object holding number of tokens per each of the provided
            input modalities, along with other useful data.
        """

        merged_kwargs = self._merge_kwargs(**kwargs)
        vision_data = {}
        if image_sizes is not None:
            images_kwargs = merged_kwargs.get("images_kwargs", {})
            merge_size = images_kwargs.get("merge_size", None) or self.image_processor.merge_size

            num_image_patches = [
                self.image_processor.get_number_of_image_patches(*image_size, images_kwargs)
                for image_size in image_sizes
            ]
            num_image_tokens = [(num_patches // merge_size**2) for num_patches in num_image_patches]
            vision_data.update({"num_image_tokens": num_image_tokens, "num_image_patches": num_image_patches})

        if video_sizes is not None:
            videos_kwargs = merged_kwargs.get("videos_kwargs", {})
            merge_size = videos_kwargs.get("merge_size", None) or self.video_processor.merge_size
            num_video_patches = [
                self.video_processor.get_num_of_video_patches(*video_size, videos_kwargs) for video_size in video_sizes
            ]
            num_video_tokens = [(num_patches // merge_size**2) for num_patches in num_video_patches]
            vision_data["num_video_tokens"] = num_video_tokens

        return MultiModalData(**vision_data)

    def post_process_image_text_to_text(
        self, generated_outputs, skip_special_tokens=True, clean_up_tokenization_spaces=False, **kwargs
    ):
        """
        Post-process the output of the model to decode the text.

        Args:
            generated_outputs (`torch.Tensor` or `np.ndarray`):
                The output of the model `generate` function. The output is expected to be a tensor of shape `(batch_size, sequence_length)`
                or `(sequence_length,)`.
            skip_special_tokens (`bool`, *optional*, defaults to `True`):
                Whether or not to remove special tokens in the output. Argument passed to the tokenizer's `batch_decode` method.
            clean_up_tokenization_spaces (`bool`, *optional*, defaults to `False`):
                Whether or not to clean up the tokenization spaces. Argument passed to the tokenizer's `batch_decode` method.
            **kwargs:
                Additional arguments to be passed to the tokenizer's `batch_decode method`.

        Returns:
            `list[str]`: The decoded text.
        """
        return self.tokenizer.batch_decode(
            generated_outputs,
            skip_special_tokens=skip_special_tokens,
            clean_up_tokenization_spaces=clean_up_tokenization_spaces,
            **kwargs,
        )

    @property
    def unused_input_names(self):
        return ["num_audio_tokens"]

    def replace_audio_token(self, audio_inputs: dict, audio_idx: int, **kwargs) -> str:
        return self.audio_token * audio_inputs["num_audio_tokens"][audio_idx]


__all__ = ["Dots3NoteProcessor"]
