app.py

from utils import cosineSim, googleSearch, getSentences, parallel_scrap, matchingScore
import gradio as gr
from urllib.request import urlopen, Request
from googleapiclient.discovery import build
import requests
import httpx
import re
from bs4 import BeautifulSoup
import numpy as np
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import asyncio
from scipy.special import softmax
from evaluate import load
from datetime import date
import nltk

from transformers import GPT2LMHeadModel, GPT2TokenizerFast
import nltk, spacy, subprocess, torch
import plotly.graph_objects as go
from writing_analysis import (
    normalize,
    preprocess_text1,
    preprocess_text2, 
    vocabulary_richness_ttr,
    calculate_gunning_fog,
    calculate_average_sentence_length,
    calculate_average_word_length,
    calculate_syntactic_tree_depth,
    calculate_perplexity,

    )

np.set_printoptions(suppress=True)


def plagiarism_check(
    input,
    year_from,
    month_from,
    day_from,
    year_to,
    month_to,
    day_to,
    domains_to_skip,
):
    api_key = "AIzaSyCLyCCpOPLZWuptuPAPSg8cUIZhdEMVf6g"
    api_key = "AIzaSyCS1WQDMl1IMjaXtwSd_2rA195-Yc4psQE"
    api_key = "AIzaSyCB61O70B8AC3l5Kk3KMoLb6DN37B7nqIk"
    api_key = "AIzaSyCg1IbevcTAXAPYeYreps6wYWDbU0Kz8tg"
    # api_key = "AIzaSyBrx_pgb6A64wPFQXSGQRgGtukoxVV_0Fk"
    cse_id = "851813e81162b4ed4"

    sentences = getSentences(input)
    urlCount = {}
    ScoreArray = []
    urlList = []

    date_from = build_date(year_from, month_from, day_from)
    date_to = build_date(year_to, month_to, day_to)
    sort_date = f"date:r:{date_from}:{date_to}"
    # get list of URLS to check
    urlCount, ScoreArray = googleSearch(
        sentences,
        urlCount,
        ScoreArray,
        urlList,
        sort_date,
        domains_to_skip,
        api_key,
        cse_id,
    )
    print("Number of URLs: ", len(urlCount))
    # print("Old Score Array:\n")
    # print2D(ScoreArray)

    # Scrape URLs in list
    formatted_tokens = []
    soups = asyncio.run(parallel_scrap(urlList))
    print(len(soups))
    print(
        "Successful scraping: "
        + str(len([x for x in soups if x is not None]))
        + "out of "
        + str(len(urlList))
    )

    # Populate matching scores for scrapped pages
    for i, soup in enumerate(soups):
        print(f"Analyzing {i+1} of {len(soups)} soups........................")
        if soup:
            page_content = soup.text
            for j, sent in enumerate(sentences):
                score = matchingScore(sent, page_content)
                ScoreArray[i][j] = score

    # ScoreArray = asyncio.run(parallel_analyze_2(soups, sentences, ScoreArray))
    # print("New Score Array:\n")
    # print2D(ScoreArray)


    # Gradio formatting section
    sentencePlag = [False] * len(sentences)
    sentenceToMaxURL = [-1] * len(sentences)
    for j in range(len(sentences)):
        if j > 0:
            maxScore = ScoreArray[sentenceToMaxURL[j - 1]][j]
            sentenceToMaxURL[j] = sentenceToMaxURL[j - 1]
        else:
            maxScore = -1
        for i in range(len(ScoreArray)):
            margin = (
                0.1
                if (j > 0 and sentenceToMaxURL[j] == sentenceToMaxURL[j - 1])
                else 0
            )
            if ScoreArray[i][j] - maxScore > margin:
                maxScore = ScoreArray[i][j]
                sentenceToMaxURL[j] = i
        if maxScore > 0.5:
            sentencePlag[j] = True
    
    if (
        (len(sentences) > 1)
        and (sentenceToMaxURL[1] != sentenceToMaxURL[0])
        and (
            ScoreArray[sentenceToMaxURL[0]][0]
            - ScoreArray[sentenceToMaxURL[1]][0]
            < 0.1
        )
    ):
        sentenceToMaxURL[0] = sentenceToMaxURL[1]

    index = np.unique(sentenceToMaxURL)

    urlMap = {}
    for count, i in enumerate(index):
        urlMap[i] = count + 1
    for i, sent in enumerate(sentences):
        formatted_tokens.append(
            (sent, "[" + str(urlMap[sentenceToMaxURL[i]]) + "]")
        )

    formatted_tokens.append(("\n", None))
    formatted_tokens.append(("\n", None))
    formatted_tokens.append(("\n", None))

    urlScore = {}
    for url in index:
        s = [
            ScoreArray[url][sen]
            for sen in range(len(sentences))
            if sentenceToMaxURL[sen] == url
        ]
        urlScore[url] = sum(s) / len(s)

    for ind in index:
        formatted_tokens.append(
            (
                urlList[ind] + " --- Matching Score: " + str(urlScore[ind]),
                "[" + str(urlMap[ind]) + "]",
            )
        )
        formatted_tokens.append(("\n", None))

    print(f"Formatted Tokens: {formatted_tokens}")

    return formatted_tokens


"""
AI DETECTION SECTION
"""

text_bc_model_path = "polygraf-ai/ai-text-bc-bert-1-4m"
text_bc_tokenizer = AutoTokenizer.from_pretrained(text_bc_model_path)
text_bc_model = AutoModelForSequenceClassification.from_pretrained(text_bc_model_path)

text_mc_model_path = "polygraf-ai/ai-text-mc-v5-lighter-spec"
text_mc_tokenizer = AutoTokenizer.from_pretrained(text_mc_model_path)
text_mc_model = AutoModelForSequenceClassification.from_pretrained(text_mc_model_path)

def remove_special_characters(text):
    cleaned_text = re.sub(r'[^a-zA-Z0-9\s]', '', text)
    return cleaned_text

def predict_bc(model, tokenizer, text):
    tokens = tokenizer(
        text, padding=True, truncation=True, return_tensors="pt"
    )["input_ids"]
    output = model(tokens)
    output_norm = softmax(output.logits.detach().numpy(), 1)[0]
    print("BC Score: ", output_norm)
    bc_score = {"AI": output_norm[1].item(), "HUMAN": output_norm[0].item()}
    return bc_score


def predict_mc(model, tokenizer, text):
    tokens = tokenizer(
        text, padding=True, truncation=True, return_tensors="pt"
    )["input_ids"]
    output = model(tokens)
    output_norm = softmax(output.logits.detach().numpy(), 1)[0]
    print("MC Score: ", output_norm)
    mc_score = {}
    label_map = ["GPT 3.5", "GPT 4", "CLAUDE", "BARD", "LLAMA 2"]
    for score, label in zip(output_norm, label_map):
        mc_score[label.upper()] = score.item()
    return mc_score


def ai_generated_test(input):

    cleaned_text = remove_special_characters(input)
    bc_score = predict_bc(text_bc_model, text_bc_tokenizer, cleaned_text)
    mc_score = predict_mc(text_mc_model, text_mc_tokenizer, cleaned_text)
    
    sum_prob = 1 - bc_score["HUMAN"]
    for key, value in mc_score.items():
        mc_score[key] = value * sum_prob

    return bc_score, mc_score


# COMBINED
def main(
    input,
    # models,
    year_from,
    month_from,
    day_from,
    year_to,
    month_to,
    day_to,
    domains_to_skip,
):
    bc_score, mc_score = ai_generated_test(input)
    formatted_tokens = plagiarism_check(
        input,
        year_from,
        month_from,
        day_from,
        year_to,
        month_to,
        day_to,
        domains_to_skip,
    )
    return (
        bc_score,
        mc_score,
        formatted_tokens,
    )


def build_date(year, month, day):
    return f"{year}{months[month]}{day}"


# DEPTH ANALYSIS
print("loading depth analysis")
nltk.download('stopwords')
nltk.download('punkt')
command = ['python', '-m', 'spacy', 'download', 'en_core_web_sm']
nlp = spacy.load("en_core_web_sm")

# Execute the command
subprocess.run(command)

# for perplexity
device = "cuda" if torch.cuda.is_available() else "cpu"
model_id = "gpt2"
gpt2_model = GPT2LMHeadModel.from_pretrained(model_id).to(device)
gpt2_tokenizer = GPT2TokenizerFast.from_pretrained(model_id)

def depth_analysis(input_text):

    # vocanulary richness
    processed_words = preprocess_text1(input_text)
    ttr_value = vocabulary_richness_ttr(processed_words)

    # readability
    gunning_fog = calculate_gunning_fog(input_text)
    gunning_fog_norm = normalize(gunning_fog, min_value=0, max_value=20)
    
    # average sentence length and average word length
    words, sentences = preprocess_text2(input_text)
    average_sentence_length = calculate_average_sentence_length(sentences)
    average_word_length = calculate_average_word_length(words)
    average_sentence_length_norm = normalize(average_sentence_length, min_value=0, max_value=40)
    average_word_length_norm = normalize(average_word_length, min_value=0, max_value=8)

    # syntactic_tree_depth
    average_tree_depth = calculate_syntactic_tree_depth(nlp, input_text)
    average_tree_depth_norm = normalize(average_tree_depth, min_value=0, max_value=10)

    # perplexity
    perplexity = calculate_perplexity(input_text, gpt2_model, gpt2_tokenizer, device)
    perplexity_norm = normalize(perplexity, min_value=0, max_value=30)

    features = {
        "readability": gunning_fog_norm, 
        "syntactic tree depth": average_tree_depth_norm,
        "vocabulary richness": ttr_value,
        "perplexity": perplexity_norm,
        "average sentence length": average_sentence_length_norm,
        "average word length": average_word_length_norm, 
    }

    print(features)

    fig = go.Figure()

    fig.add_trace(go.Scatterpolar(
        r=list(features.values()),
        theta=list(features.keys()),
        fill='toself',
        name='Radar Plot'
    ))

    fig.update_layout(
        polar=dict(
            radialaxis=dict(
                visible=True,
                range=[0, 100],
            )),
        showlegend=False,
        # autosize=False,
        # width=600,
        # height=600,
        margin=dict(
            l=10,
            r=20,
            b=10,
            t=10,
            # pad=100
        ),
    )

    return fig



# 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("/")

    model_list = ["GPT 3.5", "GPT 4", "CLAUDE", "BARD", "LLAMA2"]
    domain_list = ["com", "org", "net", "int", "edu", "gov", "mil"]
    gr.Markdown(
        """
    # Copyright Checker 
    """
    )
    input_text = gr.Textbox(label="Input text", lines=5, placeholder="")
    
    with gr.Row():
        with gr.Column():
            only_ai_btn = gr.Button("AI Check")
        with gr.Column():
            only_plagiarism_btn = gr.Button("Plagiarism Check")
        with gr.Column():
            submit_btn = gr.Button("Full Check")
        with gr.Column():
            depth_analysis_btn = gr.Button("Depth Analysis")
    gr.Markdown(
        """
        ## Output
        """
    )
    
    # models = gr.Dropdown(
            # model_list,
            # value=model_list,
            # multiselect=True,
            # label="Models to test against",
        # )
    
    with gr.Row():
        with gr.Column():
            bcLabel = gr.Label(label="Source")
        with gr.Column():
            mcLabel = gr.Label(label="Creator")

    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.HighlightedText(
                label="Plagiarism Sentence Breakdown",
                combine_adjacent=True,
                color_map={
                    "[1]": "red",
                    "[2]": "orange",
                    "[3]": "yellow",
                    "[4]": "green",
                },
            )

    with gr.Row():
        with gr.Column():
            writing_analysis_plot = gr.Plot(
                label="Radar Plot"
            )

    submit_btn.click(
        fn=main,
        inputs=[
            input_text,
            # models,
            year_from,
            month_from,
            day_from,
            year_to,
            month_to,
            day_to,
            domains_to_skip,
        ],
        outputs=[
            bcLabel,
            mcLabel,
            sentenceBreakdown,
        ],
        api_name="main",
    )

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

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

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

    date_from = ""
    date_to = ""

demo.launch()