Spaces:
Running
Running
File size: 11,037 Bytes
029c7a1 45d10c4 c78ec74 029c7a1 350b1a0 029c7a1 350b1a0 8e79582 350b1a0 8e79582 350b1a0 029c7a1 350b1a0 029c7a1 9c75413 2b72059 029c7a1 350b1a0 029c7a1 350b1a0 029c7a1 c78ec74 d03ef17 029c7a1 8e79582 029c7a1 d03ef17 8e79582 d03ef17 8e79582 d03ef17 c0a6bc9 c78ec74 74f95a7 c78ec74 c0a6bc9 7ec48d6 350b1a0 c0a6bc9 350b1a0 c0a6bc9 350b1a0 c0a6bc9 350b1a0 8e79582 350b1a0 8e79582 350b1a0 9c75413 350b1a0 c0a6bc9 350b1a0 c0a6bc9 029c7a1 9c75413 029c7a1 8e79582 af21e05 350b1a0 af21e05 d03ef17 413cf6e 029c7a1 c0a6bc9 9c75413 62f91f8 c0a6bc9 029c7a1 c0a6bc9 029c7a1 c0a6bc9 029c7a1 c0a6bc9 c78ec74 d03ef17 c78ec74 c0a6bc9 c78ec74 c0a6bc9 7ec48d6 029c7a1 c0a6bc9 029c7a1 c0a6bc9 029c7a1 c0a6bc9 029c7a1 c0a6bc9 7ec48d6 029c7a1 c0a6bc9 029c7a1 c0a6bc9 7ec48d6 c0a6bc9 7ec48d6 029c7a1 c0a6bc9 350b1a0 9c75413 350b1a0 d03ef17 350b1a0 9c75413 350b1a0 164a7aa 350b1a0 9c75413 d03ef17 9c75413 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 |
import time
from nltk.tokenize import sent_tokenize
from googleapiclient.discovery import build
from collections import Counter
import re, math
from sentence_transformers import SentenceTransformer, util
import asyncio
import httpx
from bs4 import BeautifulSoup
import numpy as np
import concurrent
from multiprocessing import Pool
WORD = re.compile(r"\w+")
model = SentenceTransformer("sentence-transformers/all-MiniLM-L6-v2")
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",
}
color_map = [
"#cf2323",
"#d65129",
"#d66329",
"#d67129",
"#eb9d59",
"#c2ad36",
"#d6ae29",
"#d6b929",
"#e1ed72",
"#c2db76",
"#a2db76",
]
def text_to_vector(text):
words = WORD.findall(text)
return Counter(words)
def cosineSim(text1, text2):
vector1 = text_to_vector(text1)
vector2 = text_to_vector(text2)
# print vector1,vector2
cosine = get_cosine(vector1, vector2)
return cosine
def get_cosine(vec1, vec2):
intersection = set(vec1.keys()) & set(vec2.keys())
numerator = sum([vec1[x] * vec2[x] for x in intersection])
sum1 = sum([vec1[x] ** 2 for x in vec1.keys()])
sum2 = sum([vec2[x] ** 2 for x in vec2.keys()])
denominator = math.sqrt(sum1) * math.sqrt(sum2)
if denominator == 0:
return 0.0
else:
return float(numerator) / denominator
def split_sentence_blocks(text, size):
if size == "Paragraph":
blocks = text.split("\n")
return blocks
else:
sents = sent_tokenize(text)
return sents
def build_date(year=2024, month="March", day=1):
return f"{year}{months[month]}{day}"
def split_ngrams(text, n):
words = text.split()
return [words[i : i + n] for i in range(len(words) - n + 1)]
def sentence_similarity(text1, text2):
embedding_1 = model.encode(text1, convert_to_tensor=True)
embedding_2 = model.encode(text2, convert_to_tensor=True)
o = util.pytorch_cos_sim(embedding_1, embedding_2)
return o.item()
async def get_url_data(url, client):
try:
r = await client.get(url)
if r.status_code == 200:
soup = BeautifulSoup(r.content, "html.parser")
return soup
except Exception:
return None
async def parallel_scrap(urls):
async with httpx.AsyncClient(timeout=30) as client:
tasks = []
for url in urls:
tasks.append(get_url_data(url=url, client=client))
results = await asyncio.gather(*tasks, return_exceptions=True)
return results
def matching_score(sentence_content_tuple):
sentence, content, score = sentence_content_tuple
if sentence in content:
return 1
if score > 0.9:
return score
else:
n = 5
# ngrams = split_ngrams(sentence, n)
# if len(ngrams) == 0:
# return 0
# matched = [x for x in ngrams if " ".join(x) in content]
# return len(matched) / len(ngrams)
ngrams_sentence = split_ngrams(sentence, n)
if len(ngrams_sentence) == 0:
return 0
ngrams_content = set(tuple(ngram) for ngram in split_ngrams(content, n))
matched_count = sum(
1 for ngram in ngrams_sentence if tuple(ngram) in ngrams_content
)
return matched_count / len(ngrams_sentence)
def process_with_multiprocessing(input_data):
with Pool(processes=8) as pool:
scores = pool.map(matching_score, input_data)
return scores
def map_sentence_url(sentences, score_array):
sentenceToMaxURL = [-1] * len(sentences)
for j in range(len(sentences)):
if j > 0:
maxScore = score_array[sentenceToMaxURL[j - 1]][j]
sentenceToMaxURL[j] = sentenceToMaxURL[j - 1]
else:
maxScore = -1
for i in range(len(score_array)):
margin = (
0.05
if (j > 0 and sentenceToMaxURL[j] == sentenceToMaxURL[j - 1])
else 0
)
if score_array[i][j] - maxScore > margin:
maxScore = score_array[i][j]
sentenceToMaxURL[j] = i
return sentenceToMaxURL
def google_search(
plag_option,
sentences,
url_count,
score_array,
url_list,
sorted_date,
domains_to_skip,
api_key,
cse_id,
**kwargs,
):
service = build("customsearch", "v1", developerKey=api_key)
num_pages = 3
for i, sentence in enumerate(sentences):
results = (
service.cse()
.list(q=sentence, cx=cse_id, sort=sorted_date, **kwargs)
.execute()
)
if "items" in results and len(results["items"]) > 0:
for count, link in enumerate(results["items"]):
if count >= num_pages:
break
# skip user selected domains
if (domains_to_skip is not None) and any(
("." + domain) in link["link"] for domain in domains_to_skip
):
continue
# clean up snippet of '...'
snippet = link["snippet"]
ind = snippet.find("...")
if ind < 20 and ind > 9:
snippet = snippet[ind + len("... ") :]
ind = snippet.find("...")
if ind > len(snippet) - 5:
snippet = snippet[:ind]
# update cosine similarity between snippet and given text
url = link["link"]
if url not in url_list:
url_list.append(url)
score_array.append([0] * len(sentences))
url_count[url] = url_count[url] + 1 if url in url_count else 1
if plag_option == "Standard":
score_array[url_list.index(url)][i] = cosineSim(
sentence, snippet
)
else:
score_array[url_list.index(url)][i] = sentence_similarity(
sentence, snippet
)
return url_count, score_array
def plagiarism_check(
plag_option,
input,
year_from,
month_from,
day_from,
year_to,
month_to,
day_to,
domains_to_skip,
source_block_size,
):
# api_key = "AIzaSyCLyCCpOPLZWuptuPAPSg8cUIZhdEMVf6g"
api_key = "AIzaSyA5VVwY1eEoIoflejObrxFDI0DJvtbmgW8"
# api_key = "AIzaSyCLyCCpOPLZWuptuPAPSg8cUIZhdEMVf6g"
# api_key = "AIzaSyCS1WQDMl1IMjaXtwSd_2rA195-Yc4psQE"
# api_key = "AIzaSyCB61O70B8AC3l5Kk3KMoLb6DN37B7nqIk"
# api_key = "AIzaSyCg1IbevcTAXAPYeYreps6wYWDbU0Kz8tg"
# api_key = "AIzaSyA5VVwY1eEoIoflejObrxFDI0DJvtbmgW8"
cse_id = "851813e81162b4ed4"
url_scores = []
sentence_scores = []
sentences = split_sentence_blocks(input, source_block_size)
print(sentences)
url_count = {}
score_array = []
url_list = []
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
url_count, score_array = google_search(
plag_option,
sentences,
url_count,
score_array,
url_list,
sort_date,
domains_to_skip,
api_key,
cse_id,
)
# Scrape URLs in list
soups = asyncio.run(parallel_scrap(url_list))
input_data = []
for i, soup in enumerate(soups):
if soup:
page_content = soup.text
for j, sent in enumerate(sentences):
input_data.append((sent, page_content, score_array[i][j]))
scores = process_with_multiprocessing(input_data)
k = 0
# Update score array for each (soup, sentence)
for i, soup in enumerate(soups):
if soup:
for j, _ in enumerate(sentences):
score_array[i][j] = scores[k]
k += 1
sentenceToMaxURL = map_sentence_url(sentences, score_array)
index = np.unique(sentenceToMaxURL)
url_source = {}
for url in index:
s = [
score_array[url][sen]
for sen in range(len(sentences))
if sentenceToMaxURL[sen] == url
]
url_source[url] = sum(s) / len(s)
index_descending = sorted(url_source, key=url_source.get, reverse=True)
urlMap = {}
for count, i in enumerate(index_descending):
urlMap[i] = count + 1
# build results
for i, sent in enumerate(sentences):
ind = sentenceToMaxURL[i]
if url_source[ind] > 0.1:
sentence_scores.append(
[sent, url_source[ind], url_list[ind], urlMap[ind]]
)
else:
sentence_scores.append([sent, None, url_list[ind], -1])
for ind in index_descending:
if url_source[ind] > 0.1:
url_scores.append(
[url_list[ind], round(url_source[ind] * 100, 2), urlMap[ind]]
)
return sentence_scores, url_scores
def html_highlight(
plag_option,
input,
year_from,
month_from,
day_from,
year_to,
month_to,
day_to,
domains_to_skip,
source_block_size,
):
start_time = time.perf_counter()
sentence_scores, url_scores = plagiarism_check(
plag_option,
input,
year_from,
month_from,
day_from,
year_to,
month_to,
day_to,
domains_to_skip,
source_block_size,
)
html_content = "<link href='https://fonts.googleapis.com/css?family=Roboto' rel='stylesheet'>\n<div style='font-family: {font}; border: 2px solid black; padding: 10px; color: #FFFFFF;'>"
prev_idx = None
combined_sentence = ""
for sentence, _, _, idx in sentence_scores:
if idx != prev_idx and prev_idx is not None:
color = color_map[prev_idx - 1]
index_part = f'<span style="background-color: {color}; padding: 2px;">[{prev_idx}]</span>'
formatted_sentence = f"<p>{combined_sentence} {index_part}</p>"
html_content += formatted_sentence
combined_sentence = ""
combined_sentence += " " + sentence
prev_idx = idx
if combined_sentence:
color = color_map[prev_idx - 1]
index_part = f'<span style="background-color: {color}; padding: 2px;">[{prev_idx}]</span>'
formatted_sentence = f"<p>{combined_sentence} {index_part}</p>"
html_content += formatted_sentence
html_content += "<hr>"
for url, score, idx in url_scores:
color = color_map[idx - 1]
formatted_url = f'<p style="background-color: {color}; padding: 5px;">({idx}) <b>{url}</b></p><p> --- Matching Score: {score}%</p>'
html_content += formatted_url
html_content += "</div>"
print("PLAGIARISM PROCESSING TIME: ", time.perf_counter() - start_time)
return html_content
|