import base64

import ffmpeg
import pandas as pd
import whisper
import yt_dlp
from langchain.tools import tool
from langchain.tools.tavily_search import TavilySearchResults
from langchain_community.document_loaders import ArxivLoader, WikipediaLoader
from langchain_core.messages import HumanMessage
from typing import List
from functools import reduce
import operator
import contextlib
import os


@tool
def read_excel(file_path: str) -> str:
    """Extract readable text from an Excel file (.xlsx or .xls).

    Args:
        file_path: Path to the Excel file.

    Returns:
        A string representation of all sheets and their content.
    """
    try:
        df_dict = pd.read_excel(file_path, sheet_name=None)  # Read all sheets
        result = []
        for sheet_name, sheet_df in df_dict.items():
            sheet_text = sheet_df.to_json(orient="records", lines=False)
            result.append({f"Sheet: {sheet_name}": sheet_text})

        full_text = ""
        for sheet in result:
            for sheet_name, sheet_data in sheet.items():
                full_text += f"{sheet_name}\n{sheet_data}\n\n"

        return full_text

    except Exception as e:
        return f"Error reading Excel file: {str(e)}"


@tool
def read_python(file_path: str) -> str:
    """Extract source code from a Python (.py) file.

    Args:
        file_path: Path to the Python file.

    Returns:
        A string containing the full source code of the file.
    """
    try:
        with open(file_path, "r", encoding="utf-8") as f:
            return f.read()
    except Exception as e:
        return f"Error reading Python file: {str(e)}"


class ExtractTextFromImage:
    """Class to initialize the extract_text_from_image tool."""

    def __init__(self, multimodal_model):
        """Initialize multimodal model."""
        self.multimodal_model = multimodal_model

    def __call_extract_text_from_image__(self, img_path: str) -> str:
        """Extract text from an image file.

        Args:
            img_path: A string representing the path to an image (e.g., PNG, JPEG).

        Returns:
            A single string containing the concatenated text extracted from the image.
        """
        all_text = ""
        try:
            # Read image and encode as base64
            with open(img_path, "rb") as image_file:
                image_bytes = image_file.read()

            image_base64 = base64.b64encode(image_bytes).decode("utf-8")

            # Prepare the prompt including the base64 image data
            message = [
                HumanMessage(
                    content=[
                        {
                            "type": "text",
                            "text": (
                                "Extract all the text from this image. "
                                "Return only the extracted text, no explanations."
                            ),
                        },
                        {
                            "type": "image_url",
                            "image_url": {
                                "url": f"data:image/png;base64,{image_base64}"
                            },
                        },
                    ]
                )
            ]

            # Call the vision-capable model
            response = self.multimodal_model.invoke(message)

            # Append extracted text
            all_text += response.content + "\n\n"

            return all_text.strip()
        except Exception as e:
            error_msg = f"Error extracting text: {str(e)}"
            print(error_msg)
            return ""


class DescribeImage:
    """Class to initialize the describe_image tool."""

    def __init__(self, multimodal_model):
        """Initialize multimodal model."""
        self.multimodal_model = multimodal_model

    def __call_describe_image__(self, img_path: str, query: str) -> str:
        """Generate a detailed description of an image.

        This function reads a image from an url, encodes it, and sends it to a
        vision-capable language model to obtain a comprehensive, natural language
        description of the image's content, including its objects, actions, and context,
        following a specific query.

        Args:
            img_path: A string representing the path to an image (e.g., PNG, JPEG).
            query: Information to extract from the image.

        Returns:
            A single string containing a detailed description of the image.
        """
        try:
            # Read image and encode as base64
            with open(img_path, "rb") as image_file:
                image_bytes = image_file.read()

            image_base64 = base64.b64encode(image_bytes).decode("utf-8")

            # Prepare message payload
            message = [
                HumanMessage(
                    content=[
                        {
                            "type": "text",
                            "text": (
                                f"Describe this image in rich detail. Include objects, people, setting, background elements, and any inferred actions or context. Avoid technical jargon. In particular, extract the following information: {query}"
                            ),
                        },
                        {
                            "type": "image_url",
                            "image_url": {
                                "url": f"data:image/png;base64,{image_base64}"
                            },
                        },
                    ]
                )
            ]
            response = self.multimodal_model.invoke(message)
            return response.content.strip()

        except Exception as e:
            error_msg = f"Error describing image: {str(e)}"
            print(error_msg)
            return ""


@tool
def transcribe_audio(audio_path: str) -> str:
    """Transcribe an MP3 file.

    Args:
        audio_path: Path to the MP3 audio file.

    Returns:
        Transcribed text as a string.
    """
    try:

        model = whisper.load_model("small")  # or "tiny", "small", "medium", "large"
        result = model.transcribe(audio_path)
        return result

    except Exception as e:
        error_msg = f"Error transcribing audio: {str(e)}"
        print(error_msg)
        return ""


@tool
def download_youtube_video(youtube_url: str, output_path: str) -> str:
    """Download a YouTube video as an MP4 file.

    Args:
        youtube_url: The YouTube video URL.
        output_path: Desired output path for the downloaded MP4 file.

    Returns:
        Path to the saved video file.
    """
    ydl_opts = {
        "format": "bestvideo+bestaudio/best",
        "outtmpl": output_path,
        "merge_output_format": "mp4",
        "quiet": True,
    }
    with contextlib.redirect_stderr(open(os.devnull, "w")):
        with yt_dlp.YoutubeDL(ydl_opts) as ydl:
            ydl.download([youtube_url])
    return output_path


@tool
def extract_audio_from_video(video_path: str, audio_output: str) -> str:
    """Extracts audio from an MP4 video file and saves it as MP3.

    Args:
        video_path: Path to the input MP4 video file.
        audio_output: Path for the output MP3 file.

    Returns:
        Path to the audio file.
    """
    try:
        (
            ffmpeg.input(video_path)
            .output(
                audio_output, format="mp3", acodec="libmp3lame", t=60
            )  # limit to 60 sec
            .overwrite_output()
            .run(quiet=True)
        )
        return audio_output
    except Exception as e:
        error_msg = f"Error transcribing audio: {str(e)}"
        print(error_msg)
        return ""


@tool
def wiki_search(query: str) -> str:
    """Search Wikipedia for a query and return maximum 2 results.

    Args:
        query: The search query.
    """
    search_docs = WikipediaLoader(query=query, load_max_docs=2).load()
    formatted_search_docs = "\n\n---\n\n".join(
        [
            f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content}\n</Document>'
            for doc in search_docs
        ]
    )
    return {"wiki_results": formatted_search_docs}


@tool
def web_search(query: str) -> str:
    """Search Tavily for a query and return maximum 3 results.

    Args:
        query: The search query.
    """
    search_docs = TavilySearchResults(max_results=3).invoke(query)
    formatted_search_docs = "\n\n---\n\n".join(
        [
            f'<Document source="{doc["url"]}" title="{doc["title"]}" score="{doc.get("score", "")}">\n{doc["content"]}\n</Document>'
            for doc in search_docs
        ]
    )
    return {"web_results": formatted_search_docs}


@tool
def arxiv_search(query: str) -> str:
    """Search Arxiv for a paper.

    Args:
        query: The search query to retrieve a specific paper, consisting
        of title and/or authors name and/or year of publication.
    """
    search_docs = ArxivLoader(query=query, load_max_docs=2).load()
    formatted_search_docs = "\n\n---\n\n".join(
        [
            (
                f'<Document title="{doc.metadata.get("Title", "")}" '
                f'published="{doc.metadata.get("Published", "")}" '
                f'authors="{doc.metadata.get("Authors", "")}">\n'
                f'Summary: {doc.metadata.get("Summary", "")}\n\n'
                f"{doc.page_content}\n"
                f"</Document>"
            )
            for doc in search_docs
        ]
    )
    return {"arvix_results": formatted_search_docs}


@tool
def add(numbers: List[float]) -> float:
    """Calculates the sum of a list of numbers.

    Args:
        numbers: A list of numeric values to be summed.

    Returns:
        The sum of all numbers in the list.
    """
    return sum(numbers)


@tool
def multiply(numbers: List[float]) -> float:
    """Calculates the product of a list of numbers.

    Args:
        numbers: A list of numeric values to be multiplied.

    Returns:
        The product of all numbers in the list.
    """
    return reduce(operator.mul, numbers, 1.0)


@tool
def divide(a: int, b: int) -> float:
    """Divide a and b.

    Args:
        a: first number
        b: second number
    """
    return a / b