#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
#           This file was automatically generated from src/transformers/models/paddleocr_vl/modular_paddleocr_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_paddleocr_vl.py file directly. One of our CI enforces this.
#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
# Copyright 2025 The PaddlePaddle Team and The HuggingFace Inc. team. All rights reserved.
#
# This code is based on EleutherAI's GPT-NeoX library and the GPT-NeoX
# and OPT implementations in this library. It has been modified from its
# original forms to accommodate minor architectural differences compared
# to GPT-NeoX and OPT used by the Meta AI team that trained the model.
#
# 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


class PaddleOCRVLProcessorKwargs(ProcessingKwargs, total=False):
    _defaults = {
        "text_kwargs": {
            "padding": False,
            "return_mm_token_type_ids": True,
        },
    }


class PaddleOCRVLProcessor(ProcessorMixin):
    r"""
    [`PaddleOCRVLProcessor`] offers all the functionalities of [`PaddleOCRVLImageProcessor`] and [`LLamaTokenizerFast`]. See the
    [`~PaddleOCRVLProcessor.__call__`] and [`~PaddleOCRVLProcessor.decode`] for more information.
    Args:
        image_processor ([`PaddleOCRVLImageProcessor`], *optional*):
            The image processor is a required input.
        tokenizer ([`LLamaTokenizerFast`], *optional*):
            The tokenizer is a required input.
        chat_template (`str`, *optional*): A Jinja template which will be used to convert lists of messages
            in a chat into a tokenizable string.
    """

    image_processor_class = "AutoImageProcessor"
    tokenizer_class = "AutoTokenizer"
    valid_processor_kwargs = PaddleOCRVLProcessorKwargs

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

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


__all__ = ["PaddleOCRVLProcessor"]