import gradio as gr
import requests
from PIL import Image

from src.application.content_detection import NewsVerification
from src.application.content_generation import (
    generate_fake_image,
    generate_fake_text,
    replace_text,
)
from src.application.url_reader import URLReader

AZURE_TEXT_MODEL = ["gpt-4o-mini", "gpt-4o"]
AZURE_IMAGE_MODEL = ["dall-e-3", "Stable Diffusion (not supported)"]


def load_url(url):
    """
    Load content from the given URL.
    """
    content = URLReader(url)
    image = None
    header = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/100.0.4896.127 Safari/537.36",  # noqa: E501
    }
    try:
        response = requests.get(
            url,
            headers=header,
            stream=True,
        )
        response.raise_for_status()  # Raise an exception for bad status codes

        image_response = requests.get(content.top_image, stream=True)
        try:
            image = Image.open(image_response.raw)
        except OSError as e:
            print(f"Error loading image from {content.top_image}: {e}")

    except (requests.exceptions.RequestException, FileNotFoundError) as e:
        print(f"Error fetching image: {e}")

    return content.title, content.text, image


def generate_analysis_report(
    news_title: str,
    news_content: str,
    news_image: Image,
):
    news_analysis = NewsVerification()
    news_analysis.load_news(news_title, news_content, news_image)
    news_analysis.generate_analysis_report()
    return news_analysis.analyze_details()


# Define the GUI
with gr.Blocks() as demo:
    gr.Markdown("# NEWS VERIFICATION")

    with gr.Row():
        # SETTINGS
        with gr.Column(scale=1):
            with gr.Accordion("1. Enter a URL"):
                url_input = gr.Textbox(
                    label="",
                    show_label=False,
                    value="",
                )
                load_button = gr.Button("Load URL")

            with gr.Accordion(
                "2. Select content-generation models",
                open=True,
                visible=False,
            ):
                with gr.Row():
                    text_generation_model = gr.Dropdown(
                        choices=AZURE_TEXT_MODEL,
                        label="Text-generation model",
                    )
                    image_generation_model = gr.Dropdown(
                        choices=AZURE_IMAGE_MODEL,
                        label="Image-generation model",
                    )
                    generate_text_button = gr.Button("Generate text")
                    generate_image_button = gr.Button("Generate image")

            with gr.Accordion(
                "3. Replace any terms",
                open=True,
                visible=False,
            ):
                replace_df = gr.Dataframe(
                    headers=["Find what:", "Replace with:"],
                    datatype=["str", "str"],
                    row_count=(1, "dynamic"),
                    col_count=(2, "fixed"),
                    interactive=True,
                )
                replace_button = gr.Button("Replace all")

            # GENERATED CONTENT
            with gr.Accordion("Input News"):
                news_title = gr.Textbox(label="Title", value="")
                news_image = gr.Image(label="Image", type="filepath")
                news_content = gr.Textbox(label="Content", value="", lines=13)

        # NEWS ANALYSIS REPORT
        ordinary_user_explanation = """
FOR ORDINARY USER<br>
- Green texts are the matched words in the input and source news.<br>
- Each highlighted pair (marked with a number) shows the key differences
between the input text and the source.
        """
        fact_checker_explanation = """
FOR FACT CHECKER<br>
- Green texts are the matched words in the input and source news.<br>
- Each highlighted pair (marked with a number) shows the key differences
between the input text and the source.
        """
        governor_explanation = """
FOR GOVERNOR<br>
- Green texts are the matched words in the input and source news.<br>
- Each highlighted pair (marked with a number) shows the key differences
between the input text and the source.
        """
        table = """
<h5>Comparison between input news and source news:</h5>
    <table border="1" style="width:100%; text-align:left;">
    <col style="width: 170px;">
    <col style="width: 170px;">
    <col style="width: 30px;">
    <col style="width: 75px;">
        <thead>
            <tr>
                <th>Input news</th>
                <th>Source (corresponding URL provided in Originality)</th>
                <th>Forensic</th>
                <th>Originality</th>
            </tr>
        </thead>
        <tbody>
            <tr>
                <th>TBD</th>
                <th>TBD</th>
                <th>TBD</th>
                <th>TBD</th>
            </tr>
        </tbody>
    </table>

    <style>"""
        with gr.Column(scale=2):
            with gr.Accordion("NEWS ANALYSIS"):
                verification_button = gr.Button("Verify news")
                with gr.Tab("Orinary User"):
                    gr.HTML(ordinary_user_explanation)
                    ordinary_user_result = gr.HTML(table)
                with gr.Tab("Fact Checker"):
                    gr.HTML(fact_checker_explanation)
                    fact_checker_result = gr.HTML(table)
                with gr.Tab("Governor"):
                    gr.HTML(governor_explanation)
                    governor_result = gr.HTML(table)

    # Connect events
    load_button.click(
        load_url,
        inputs=url_input,
        outputs=[news_title, news_content, news_image],
    )
    replace_button.click(
        replace_text,
        inputs=[news_title, news_content, replace_df],
        outputs=[news_title, news_content],
    )
    generate_text_button.click(
        generate_fake_text,
        inputs=[text_generation_model, news_title, news_content],
        outputs=[news_title, news_content],
    )
    generate_image_button.click(
        generate_fake_image,
        inputs=[image_generation_model, news_title],
        outputs=[news_image],
    )
    verification_button.click(
        generate_analysis_report,
        inputs=[news_title, news_content, news_image],
        outputs=[ordinary_user_result, fact_checker_result, governor_result],
    )

    # change Image
    # url_input.change(load_image, inputs=url_input, outputs=image_view)

    try:
        with open(
            "examples/example_text_real.txt",
            encoding="utf-8",
        ) as file:
            text_real_1 = file.read()
        with open(
            "examples/example_text_real_2.txt",
            encoding="utf-8",
        ) as file:
            text_real_2 = file.read()
        with open(
            "examples/example_text_LLM_topic.txt",
            encoding="utf-8",
        ) as file:
            text_llm_topic = file.read()
        with open(
            "examples/example_text_LLM_modification.txt",
            encoding="utf-8",
        ) as file:
            text_llm_modification = file.read()
        with open(
            "examples/example_text_LLM_entities.txt",
            encoding="utf-8",
        ) as file:
            text_llm_entities = file.read()
    except FileNotFoundError:
        print("File not found.")
    except Exception as e:
        print(f"An error occurred: {e}")

    title_1 = "Southampton news: Leeds target striker Cameron Archer."
    title_2 = "Southampton news: Leeds target striker Cameron Archer."
    title_4 = "Japan pledges support for Ukraine with 100-year pact."

    image_1 = "examples/example_image_real_1.jpg.webp"
    image_2 = "examples/example_image_real_2.jpg.webp"
    image_3 = "examples/example_image_real_3.jpg"
    image_4 = "examples/example_image_real_4.jpg.webp"

    gr.Examples(
        examples=[
            [title_1, image_1, text_real_1 + "\n\n" + text_real_2],
            [title_1, image_2, text_real_1 + "\n\n" + text_llm_modification],
            [title_1, image_3, text_real_1 + "\n\n" + text_llm_topic],
            [title_4, image_4, text_llm_entities],
        ],
        inputs=[news_title, news_image, news_content],
        label="Examples",
        example_labels=[
            "2 real news",
            "1 real news + 1 LLM modification-based news",
            "1 real news + 1 LLM topic-based news",
            "1 LLM changed-entities news",
        ],
    )

demo.launch(share=True)