def test_run():
global grade, test_number, num_test_failed
num_test_failed = 0
orig_stdout = sys.stdout
run_file = open('run.txt', 'w')
sys.stdout = run_file
try:
test_number += 1
search_engine.main(corpus_path, output_path, stemming, queries,
num_doc_to_retrieve)
student_answers_all = [
line.rstrip('\n') for line in open('run.txt')
]
student_answers = [
len(student_answers_all[i:i + num_doc_to_retrieve]) for i
in range(0, len(student_answers_all), num_doc_to_retrieve)
]
correct_answers = [
num_doc_to_retrieve for _ in range(len(queries))
]
test_part(correct_answers, student_answers, error_str="run")
if num_test_failed == 0:
results_summary.append('Running Passed')
else:
results_summary.append('You are printing in your project')
except Exception as e:
results_summary.append(
f'Test Number: {test_number} Running Main Program Failed with the following error: {e}'
)
run_file.close()
sys.stdout = orig_stdout
def test_input_one(self, stdout):
main()
self.assertEqual(stdout.getvalue(), "\n".join([
'1 2',
'3',
'2 1',
]) + '\n')
def main(stemmer_obj):
LOGGER.info("Starting run script")
generate_configs.main(stemmer_obj)
queries_parser.main(stemmer_obj)
make_inverse_index.main(stemmer_obj)
create_model.main()
search_engine.main()
evaluate_results.main(stemmer_obj)
LOGGER.info("Finishing run script")
def result():
if request.method == 'POST':
result = request.form
query_list = create_tokens.tokenizer(result.values())
main_urls = search_engine.main(query_list)
if len(main_urls) > 0:
return render_template("result.html", result = main_urls)
else:
return render_template("no_result.html")
def search(event):
output = se.main(self.entry.get())
self.button['state'] = DISABLED
self.button.unbind("<Button-1>")
if len(output) != 0:
text = ""
for i in range(0, len(output[:20])):
text += "Document #" + str(
output[i][0]) + " with score " + str(
round((output[i][1]), 5)) + "\n"
self.message_output['text'] = text
self.message_output.bind(
"<Button-1>",
functools.partial(callback, index=output[0][0]))
self.nothing['text'] = "Results: " + str(len(output))
elif len(output) == 0:
self.nothing['text'] = "No coincidence"
self.message_output['text'] = ""
self.message_output.unbind("<Button-1>")
else:
self.nothing['text'] = output
self.message_output['text'] = ""
self.message_output.unbind("<Button-1>")
import search_engine
if __name__ == '__main__':
search_engine.main('Data', 'posting', False, 'C:/Users/maorb/OneDrive/Desktop/arnona/queries.txt', 2000)
import search_engine
# import search_engine_best
if __name__ == '__main__':
corpus_path = 'C:\\Users\\amitv\\University\\Information retrieval\\corpus'
output_path = 'C:\\Users\\amitv\\University\\Information retrieval\\output'
stemming = False
queries = 'C:\\Users\\amitv\\University\\Information retrieval\\Search_Engine\\data\\queries_train.tsv'
num_docs_to_retrieve = 100
search_engine.main(corpus_path, output_path, stemming, queries,
num_docs_to_retrieve)
# srarch_engine_best.main()
import search_engine
if __name__ == '__main__':
search_engine.main(
'C:\\Users\elitm\PycharmProjects\Search_Engine-maste\Data',
'C:\\Users\elitm\PycharmProjects\Search_Engine-maste\output_path',
False, 'C:\\Users\elitm\PycharmProjects\queries.txt', 2000)
import search_engine
if __name__ == '__main__':
search_engine.main('corpus', 'posting', True, 'queries.txt', 100)
import search_engine
if __name__ == '__main__':
search_engine.main(stemming=True, index_corpus=True, query_engine=True)
import search_engine
if __name__ == '__main__':
search_engine.main('C:\\Users\\guykl\\PycharmProjects\\Data', 'posting',
False, "queries.txt", 250)
def setUp(self):
from search_engine import main
app = main({})
from webtest import TestApp
self.testapp = TestApp(app)
import search_engine
import parser_module
import os
if __name__ == '__main__':
search_engine.main(f"{os.getcwd()}\\Data", f"{os.getcwd()}\\Postings",
False, "queries.txt", 2000)
#parser = parser_module.Parse()
#parser.parse_sentence('https://www.instagram.com/p/CD7fAPWs3WM/?igshid=o9kf0ugp1l8x https://twitter.com/i/web/status/1290533420381085697')
import nltk
import search_engine
nltk.download('stopwords')
nltk.download('punkt')
search_engine.main()
import search_engine
import utils
from MapReduce import MapReduce
if __name__ == '__main__':
# lstQuery=['Dr. Anthony Fauci wrote in a 2005 paper published in Virology Journal that hydroxychloroquine was effective in treating SARS.',
# 'The seasonal flu kills more people every year in the U.S. than COVID-19 has to date.',
# 'Coronavirus is less dangerous than the flu']
# x = list()
# x.append()
lstQuery = ['schools we need', 'Donald Trump']
search_engine.main("C:\\Code\\Python\\Data", "C:\\Code\\Answers", False,
lstQuery, 20)
# inv = search_engine.load_index()
# search_engine.search_and_rank_query('schools we need', inv, 20)
# term_lst =['Abx','Trg','TRG','Bcd','bcc','erg','png']
# term_lst.sort(key=lambda x: x.lower())
# x.clear()
# print(x[0])
# map_reduce = MapRe duce.import_map_reduce('MapReduceData/')
# x = map_reduce.read_from_func('@brettboyter24')
# print(len(x))
# inverted_index = utils.load_obj("inverted_idx")
# print(inverted_index)
"""
path= 'MapReduceData/'
map_reduce = MapReduce(path=path)
doc_0 ='doc0fgfgfgfgfgfgfgfgfgfgfgfgfgfgfgfgfgfgfgfgfgfgfgfgfghjjjjjjjjjjjj'
doc_1 ='doc1'
doc_2 ='doc2'
import search_engine
if __name__ == '__main__':
search_engine.main('C:\\Users\\Ben Rozilio\\Desktop\\SemA\\engine\\Data\\Data2','output_path',True,'C:\\Users\\Ben Rozilio\\Desktop\\SemA\\engine\\queries.txt',5)
import search_engine
if __name__ == '__main__':
### guy's main ###
q = "queries.txt"
c_path = r'C:\Users\Guyza\OneDrive\Desktop\Information_Systems\University\Third_year\Semester_E' \
r'\Information_Retrieval\Search_Engine_Project\Data\Data'
search_engine.main(stemming=False,
num_docs_to_retrieve=20,
queries=q,
corpus_path=c_path,
output_path='')
### yoni's main ###
q = r"C:\Users\yonym\Desktop\ThirdYear\IR\engineV1\full_run_data\queries.txt"
search_engine.main(
stemming=False,
num_docs_to_retrieve=20,
queries=q,
corpus_path=
'C:\\Users\\yonym\\Desktop\\ThirdYear\\IR\\engineV1\\Data\\',
output_path='')
import search_engine
if __name__ == '__main__':
corpus_path = "C:/Users/gal/Desktop/Data"
output_path = "C:/Users/gal/Desktop"
queries = []
numOfDocs = 20
stemming = False
search_engine.main(corpus_path, output_path, stemming, queries, numOfDocs)
import search_engine
import configuration
if __name__ == '__main__':
search_engine.main(**configuration.config)
def test_input_two(self, stdout):
main()
self.assertEqual(stdout.getvalue(), "\n".join([
'4 5 1 2 3',
]) + '\n')
"The COVID-19 pandemic was planned by the Rockefeller Foundation in Operation Lockstep.",
"COVID-19 could lose its epidemic status in the United States because of declining coronavirus death rates according to CDC data.",
"healthy people should NOT wear masks",
"coronavirus is a bioweapon created in a lab in Wuhan",
"The outbreak began because people ate bat soup",
"Outbreak people ate bat", "Coronavirus eat bat soup",
"Wearing a mask to prevent the spread of COVID-19 is unnecessary because the disease can also be spread via farts.",
"For younger people, seasonal flu is “in many cases” a deadlier virus than COVID-19.",
"The coronavirus disease (COVID-19) is caused by a virus",
"Covid-19 is not caused by bacteria",
"The prolonged use of medical masks when properly worn, DOES NOT cause CO2 intoxication nor oxygen deficiency",
"Masks don't cause CO2 intoxication.",
"The COVID-19 coronavirus pandemic caused a nationwide shortage of U.S. coins in circulation during the summer of 2020."
"Coins shortage due to coronavirus"
]
search_engine.main("C:\\Users\\ayman\\Downloads\\Data", "", False,
lstQuery, 20)
print('Finish all Time ' + str(time.time() - start_time))
# inv = search_engine.load_index()
# search_engine.search_and_rank_query('schools we need', inv, 20)
# term_lst =['Abx','Trg','TRG','Bcd','bcc','erg','png']
# term_lst.sort(key=lambda x: x.lower())
# x.clear()
# print(x[0])
# map_reduce = MapRe duce.import_map_reduce('MapReduceData/')
# x = map_reduce.read_from_func('@brettboyter24')
# print(len(x))
# inverted_index = utils.load_obj("inverted_idx")
# print(inverted_index)
"""
