# coding=utf-8
# Copyright 2026 The Qwen team, Alibaba Group 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 transformers.feature_extraction_utils import BatchFeature
from transformers.processing_utils import ProcessingKwargs, ProcessorMixin


class Qwen3TTSProcessorKwargs(ProcessingKwargs, total=False):
    _defaults = {
        "text_kwargs": {
            "padding": False,
            "padding_side": "left",
        }
    }

class Qwen3TTSProcessor(ProcessorMixin):
    r"""
    Constructs a Qwen3TTS processor.

    Args:
        tokenizer ([`Qwen2TokenizerFast`], *optional*):
            The text tokenizer.
        chat_template (`Optional[str]`, *optional*):
            The Jinja template to use for formatting the conversation. If not provided, the default chat template is used.
    """

    attributes = ["tokenizer"]
    tokenizer_class = ("Qwen2Tokenizer", "Qwen2TokenizerFast")

    def __init__(
        self, tokenizer=None, chat_template=None
    ):
        super().__init__(tokenizer, chat_template=chat_template)

    def __call__(self, text=None, **kwargs) -> BatchFeature:
        """
        Main method to prepare for the model one or several sequences(s) and audio(s). This method forwards the `text`
        and `kwargs` arguments to Qwen2TokenizerFast's [`~Qwen2TokenizerFast.__call__`] if `text` is not `None` to encode
        the text. 

        Args:
            text (`str`, `List[str]`, `List[List[str]]`):
                The sequence or batch of sequences to be encoded. Each sequence can be a string or a list of strings
                (pretokenized string). If the sequences are provided as list of strings (pretokenized), you must set
                `is_split_into_words=True` (to lift the ambiguity with a batch of sequences).
        """

        if text is None:
            raise ValueError("You need to specify either a `text` input to process.")

        output_kwargs = self._merge_kwargs(
            Qwen3TTSProcessorKwargs,
            tokenizer_init_kwargs=self.tokenizer.init_kwargs,
            **kwargs,
        )
        if not isinstance(text, list):
            text = [text]

        texts_inputs = self.tokenizer(text, **output_kwargs["text_kwargs"])

        return BatchFeature(
            data={**texts_inputs},
            tensor_type=kwargs.get("return_tensors"),
        )

    def batch_decode(self, *args, **kwargs):
        """
        This method forwards all its arguments to Qwen2TokenizerFast's [`~PreTrainedTokenizer.batch_decode`]. Please
        refer to the docstring of this method for more information.
        """
        return self.tokenizer.batch_decode(*args, **kwargs)

    def decode(self, *args, **kwargs):
        """
        This method forwards all its arguments to Qwen2TokenizerFast's [`~PreTrainedTokenizer.decode`]. Please refer to
        the docstring of this method for more information.
        """
        return self.tokenizer.decode(*args, **kwargs)

    def apply_chat_template(self, conversations, chat_template=None, **kwargs):
        if isinstance(conversations[0], dict):
            conversations = [conversations]
        return super().apply_chat_template(conversations, chat_template, **kwargs)

    @property
    def model_input_names(self):
        tokenizer_input_names = self.tokenizer.model_input_names
        return list(
            dict.fromkeys(
                tokenizer_input_names
            )
        )


__all__ = ["Qwen3TTSProcessor"]