#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
#           This file was automatically generated from src/transformers/models/deepseek_vl/modular_deepseek_vl.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_deepseek_vl.py file directly. One of our CI enforces this.
#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
# Copyright 2025 Deepseek AI and 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.


from ...processing_utils import ProcessingKwargs, ProcessorMixin
from ...utils import auto_docstring


class DeepseekVLProcessorKwargs(ProcessingKwargs, total=False):
    _defaults = {
        "text_kwargs": {
            "padding": False,
            "return_mm_token_type_ids": False,
            "return_text_replacement_offsets": False,
        },
        "common_kwargs": {"return_tensors": "pt"},
    }


@auto_docstring
class DeepseekVLProcessor(ProcessorMixin):
    valid_processor_kwargs = DeepseekVLProcessorKwargs

    def __init__(
        self,
        image_processor,
        tokenizer,
        chat_template=None,
        num_image_tokens=576,
    ):
        r"""
        num_image_tokens (`int`, *optional*, defaults to 576):
            The number of special image tokens used as placeholders for visual content in text sequences.
        """
        self.image_token = tokenizer.image_token
        self.image_token_id = tokenizer.convert_tokens_to_ids(self.image_token)
        self.num_image_tokens = num_image_tokens

        super().__init__(image_processor, tokenizer, chat_template=chat_template)

    def replace_image_token(self, image_inputs: dict, image_idx: int, **kwargs) -> str:
        return self.image_token * self.num_image_tokens


__all__ = ["DeepseekVLProcessor"]