app.py

import gradio as gr
import numpy as np
from datetime import date
from predictors import predict_bc_scores, predict_mc_scores, predict_1on1_scores
from analysis import depth_analysis
from predictors import predict_quillbot
from plagiarism import plagiarism_check, build_date, html_highlight
from highlighter import analyze_and_highlight
from utils import extract_text_from_pdf, len_validator
import yaml
from functools import partial


np.set_printoptions(suppress=True)

with open("config.yaml", "r") as file:
    params = yaml.safe_load(file)

model_list = params["MC_OUTPUT_LABELS"]


analyze_and_highlight_bc = partial(analyze_and_highlight, model_type="bc")
analyze_and_highlight_quillbot = partial(
    analyze_and_highlight, model_type="quillbot"
)


def ai_generated_test(option, input, models):
    if option == "Human vs AI":
        return predict_bc_scores(input), None
    elif option == "Human vs AI Source Models":
        return predict_bc_scores(input), predict_1on1_scores(input, models)
    return None, None


# COMBINED
def main(
    ai_option,
    plag_option,
    input,
    models,
    year_from,
    month_from,
    day_from,
    year_to,
    month_to,
    day_to,
    domains_to_skip,
    source_block_size,
):

    # formatted_tokens = plagiarism_check(
    #     plag_option,
    #     input,
    #     year_from,
    #     month_from,
    #     day_from,
    #     year_to,
    #     month_to,
    #     day_to,
    #     domains_to_skip,
    # )
    formatted_tokens = html_highlight(
        plag_option,
        input,
        year_from,
        month_from,
        day_from,
        year_to,
        month_to,
        day_to,
        domains_to_skip,
        source_block_size,
    )
    depth_analysis_plot = depth_analysis(input)
    bc_score = predict_bc_scores(input)
    mc_score = predict_1on1_scores(input, models)
    quilscore = predict_quillbot(input)

    return (
        bc_score,
        mc_score,
        formatted_tokens,
        depth_analysis_plot,
        quilscore,
    )


# START OF GRADIO

title = "Copyright Checker"
months = {
    "January": "01",
    "February": "02",
    "March": "03",
    "April": "04",
    "May": "05",
    "June": "06",
    "July": "07",
    "August": "08",
    "September": "09",
    "October": "10",
    "November": "11",
    "December": "12",
}


with gr.Blocks() as demo:
    today = date.today()
    # dd/mm/YY
    d1 = today.strftime("%d/%B/%Y")
    d1 = d1.split("/")

    domain_list = ["com", "org", "net", "int", "edu", "gov", "mil"]
    gr.Markdown(
        """
    # Copyright Checker 
    """
    )
    with gr.Row():
        input_text = gr.Textbox(label="Input text", lines=6, placeholder="")
        file_input = gr.File(label="Upload PDF")
        file_input.change(
            fn=extract_text_from_pdf, inputs=file_input, outputs=input_text
        )

    char_count = gr.Textbox(label="Minumum Character Limit Check")
    input_text.change(fn=len_validator, inputs=input_text, outputs=char_count)

    with gr.Row():
        models = gr.Dropdown(
            model_list,
            value=model_list,
            multiselect=True,
            label="Models to test against",
        )
    with gr.Row():
        with gr.Column():
            ai_option = gr.Radio(
                [
                    "Human vs AI",
                    "Human vs AI Source Models",
                    # "Human vs AI Source Models (1 on 1)",
                ],
                label="Choose an option please.",
            )
        with gr.Column():
            plag_option = gr.Radio(
                ["Standard", "Advanced"], label="Choose an option please."
            )
    with gr.Row():
        source_block_size = gr.Dropdown(
            choices=["1", "2", "3", "Paragraph"],
            label="Source Check Granularity",
            value="2",
            interactive=True,
        )

    with gr.Row():
        with gr.Column():
            only_ai_btn = gr.Button("AI Check")
        with gr.Column():
            only_plagiarism_btn = gr.Button("Source Check")

        with gr.Column():
            quillbot_check = gr.Button("Humanized Text Check")

    with gr.Row():
        with gr.Column():
            bc_highlighter_button = gr.Button("Human vs. AI Highlighter")
        with gr.Column():
            quillbot_highlighter_button = gr.Button("Humanized Highlighter")

    with gr.Row():
        depth_analysis_btn = gr.Button("Detailed Writing Analysis")

    with gr.Row():
        full_check_btn = gr.Button("Full Check")

    gr.Markdown(
        """
        ## Output
        """
    )

    with gr.Row():
        with gr.Column():
            bcLabel = gr.Label(label="Source")
        with gr.Column():
            mcLabel = gr.Label(label="Creator")
    with gr.Row():
        with gr.Column():
            bc_highlighter_output = gr.HTML(label="Human vs. AI Highlighter")

        # with gr.Column():
        #     mc1on1Label = gr.Label(label="Creator(1 on 1 Approach)")

    with gr.Row():
        with gr.Column():
            QLabel = gr.Label(label="Humanized")

    with gr.Row():
        quillbot_highlighter_output = gr.HTML(label="Humanized Highlighter")

    with gr.Group():
        with gr.Row():
            month_from = gr.Dropdown(
                choices=months,
                label="From Month",
                value="January",
                interactive=True,
            )
            day_from = gr.Textbox(label="From Day", value="01")
            year_from = gr.Textbox(label="From Year", value="2000")
            # from_date_button = gr.Button("Submit")

        with gr.Row():
            month_to = gr.Dropdown(
                choices=months,
                label="To Month",
                value=d1[1],
                interactive=True,
            )
            day_to = gr.Textbox(label="To Day", value=d1[0])
            year_to = gr.Textbox(label="To Year", value=d1[2])
            # to_date_button = gr.Button("Submit")
        with gr.Row():
            domains_to_skip = gr.Dropdown(
                domain_list,
                multiselect=True,
                label="Domain To Skip",
            )

    with gr.Row():
        with gr.Column():
            sentenceBreakdown = gr.HTML(
                label="Source Detection Sentence Breakdown",
                value="Source Detection Sentence Breakdown",
            )

    with gr.Row():
        with gr.Column():
            writing_analysis_plot = gr.Plot(label="Writing Analysis Plot")
        with gr.Column():
            interpretation = """
<h2>Writing Analysis Interpretation</h2>
<ul>
    <li><b>Lexical Diversity</b>: This feature measures the range of unique words used in a text.
        <ul>
            <li>🤖 Higher tends to be AI.</li>
        </ul>
    </li>
    <li><b>Vocabulary Level</b>: This feature assesses the complexity of the words used in a text.
        <ul>
            <li>🤖 Higher tends to be AI.</li>
        </ul>
    </li>
    <li><b>Unique Words</b>: This feature counts the number of words that appear only once within the text.
        <ul>
            <li>🤖 Higher tends to be AI.</li>
        </ul>
    </li>
    <li><b>Determiner Use</b>: This feature tracks the frequency of articles and quantifiers in the text.
        <ul>
            <li>🤖 Higher tends to be AI.</li>
        </ul>
    </li>
    <li><b>Punctuation Variety</b>: This feature indicates the diversity of punctuation marks used in the text.
        <ul>
            <li>👤 Higher tends to be Human.</li>
        </ul>
    </li>
    <li><b>Sentence Depth</b>: This feature evaluates the complexity of the sentence structures used in the text.
        <ul>
            <li>🤖 Higher tends to be AI.</li>
        </ul>
    </li>
    <li><b>Vocabulary Stability</b>: This feature measures the consistency of vocabulary use throughout the text.
        <ul>
            <li>🤖 Higher tends to be AI.</li>
        </ul>
    </li>
    <li><b>Entity Ratio</b>: This feature calculates the proportion of named entities, such as names and places, within the text.
        <ul>
            <li>👤 Higher tends to be Human.</li>
        </ul>
    </li>
    <li><b>Perplexity</b>: This feature assesses the predictability of the text based on the sequence of words.
        <ul>
            <li>👤 Higher tends to be Human.</li>
        </ul>
    </li>
</ul>

"""
            gr.HTML(interpretation, label="Interpretation of Writing Analysis")

    full_check_btn.click(
        fn=main,
        inputs=[
            ai_option,
            plag_option,
            input_text,
            models,
            year_from,
            month_from,
            day_from,
            year_to,
            month_to,
            day_to,
            domains_to_skip,
            source_block_size,
        ],
        outputs=[
            bcLabel,
            mcLabel,
            # mc1on1Label,
            sentenceBreakdown,
            writing_analysis_plot,
            QLabel,
        ],
        api_name="main",
    )

    only_ai_btn.click(
        fn=ai_generated_test,
        inputs=[ai_option, input_text, models],
        # outputs=[bcLabel, mcLabel, mc1on1Label],
        outputs=[bcLabel, mcLabel],
        api_name="ai_check",
    )

    quillbot_check.click(
        fn=predict_quillbot,
        inputs=[input_text],
        outputs=[QLabel],
        api_name="quillbot_check",
    )

    only_plagiarism_btn.click(
        # fn=plagiarism_check,
        fn=html_highlight,
        inputs=[
            plag_option,
            input_text,
            year_from,
            month_from,
            day_from,
            year_to,
            month_to,
            day_to,
            domains_to_skip,
            source_block_size,
        ],
        outputs=[
            sentenceBreakdown,
        ],
        api_name="plagiarism_check",
    )

    depth_analysis_btn.click(
        fn=depth_analysis,
        inputs=[input_text],
        outputs=[writing_analysis_plot],
        api_name="depth_analysis",
    )

    quillbot_highlighter_button.click(
        fn=analyze_and_highlight_quillbot,
        inputs=[input_text],
        outputs=[quillbot_highlighter_output],
        api_name="humanized_highlighter",
    )

    bc_highlighter_button.click(
        fn=analyze_and_highlight_bc,
        inputs=[input_text],
        outputs=[bc_highlighter_output],
        api_name="bc_highlighter",
    )

    date_from = ""
    date_to = ""


if __name__ == "__main__":
    demo.launch(
        share=True, server_name="0.0.0.0", auth=("polygraf-admin", "test@aisd")
    )