def test_run_a_query(engine, keywords, driver):
title = 'Need a bigger string to simulate a cenario that that exceeds the maximum size allowed by the search base science direct'
#generate string
source_string = util.create_search_string(keywords, engine, title=title)
print("String: ", source_string)
#create the bots
acm_bot = ACM(source_string, driver)
ieee_bot = IEEE(source_string, driver)
scidirect_bot = Scidirect(source_string, driver)
scopus_bot = Scopus(source_string, driver)
springer_bot = Springer(source_string, driver)
source_results = []
#get the source query results
if engine == "ACM":
source_results = acm_bot.test_ACM()
if engine == "IEEE":
source_results = ieee_bot.test_IEEE()
if engine == "Scidirect":
source_results = scidirect_bot.test_scidirect()
if engine == "Springer":
source_results = springer_bot.test_springer()
if engine == "Scopus":
source_results = scopus_bot.test_Scopus()
def Top1Absent(engine, keywords, driver):
#get the time using a specific format
starting_time = datetime.datetime.now().strftime('%H:%M:%S')
results = []
#source search
source_string = util.create_search_string(keywords, engine)
#create the bots
acm_bot = ACM(source_string, driver)
ieee_bot = IEEE(source_string, driver)
scidirect_bot = Scidirect(source_string, driver)
scopus_bot = Scopus(source_string, driver)
springer_bot = Springer(source_string, driver)
source_results = []
#get the source query results
if engine == "ACM":
source_results = acm_bot.test_ACM()
if engine == "IEEE":
source_results = ieee_bot.test_IEEE()
if engine == "Scidirect":
source_results = scidirect_bot.test_scidirect()
if engine == "Springer":
source_results = springer_bot.test_springer()
if engine == "Scopus":
source_results = scopus_bot.test_Scopus()
#get the list of papers and conferences from source query
source_papers = source_results[1]
conferences_list = source_results[2]
#surround by try to avoid exceptions
try:
#get the first paper name
first_paper = source_papers[0]
except:
first_paper = ''
try:
#conference of the first paper
first_conference = conferences_list[0]
except:
first_conference = ''
#generate the followup string
follow_string = util.create_search_string(keywords,
engine,
title=first_paper)
#create a new instance of the bots
acm_bot = ACM(follow_string, driver)
ieee_bot = IEEE(follow_string, driver)
scidirect_bot = Scidirect(follow_string, driver)
scopus_bot = Scopus(follow_string, driver)
springer_bot = Springer(follow_string, driver)
follow_up_results = []
#get the followup query results
if engine == "ACM":
follow_up_results = acm_bot.test_ACM()
if engine == "IEEE":
follow_up_results = ieee_bot.test_IEEE()
if engine == "Scidirect":
#Scidirect limitation.. Strings bigger than 255 chars are not suported. End the execution and sent a False value to not registre the entry
if (len(follow_string) > 255):
print(
"W: Follow-up string exceeds the allowed size limit for the base! This execution will be aborted and will not be logged."
)
return [], False
follow_up_results = scidirect_bot.test_scidirect()
if engine == "Springer":
follow_up_results = springer_bot.test_springer()
if engine == "Scopus":
follow_up_results = scopus_bot.test_Scopus()
#papers from follow up query
try:
followup_papers = follow_up_results[1]
except:
followup_papers = []
try:
first_followup_paper = follow_up_results[1]
except:
first_followup_paper = ''
#check if the first paper of both query is equal
if (first_paper == first_followup_paper) and (first_paper != ''):
#working good
fault = False
else:
#there is a bug
fault = True
results = [source_string] + source_results + [
follow_string
] + follow_up_results + [fault] + [starting_time]
#add an extra return value to ensure that the execution runned as expected
return results, True
def Top1Absent(engine, keywords, driver):
#get the time using a specific format
starting_time = datetime.datetime.now().strftime('%H:%M:%S')
results = []
#source search
source_string = util.create_search_string(keywords, engine)
#create the bots
acm_bot = ACM(source_string, driver)
ieee_bot = IEEE(source_string, driver)
scidirect_bot = Scidirect(source_string, driver)
scopus_bot = Scopus(source_string, driver)
springer_bot = Springer(source_string, driver)
#get the source query results
if engine == "ACM":
source_results = acm_bot.test_ACM()
if engine == "IEEE":
source_results = ieee_bot.test_IEEE()
if engine == "Scidirect":
source_results = scidirect_bot.test_scidirect()
if engine == "Springer":
source_results = springer_bot.test_springer()
if engine == "SCOPUS":
source_results = scopus_bot.test_Scopus()
#get the first paper from source query
source_papers = source_results[1]
first_paper = source_papers[0]
#get the conference of the first paper
conferences_list = source_results[2]
first_conference = conferences_list[0]
#generate the followup string
follow_string = util.create_search_string(keywords,
engine,
title=first_paper)
#create a new instance of the bots
acm_bot = ACM(follow_string, driver)
ieee_bot = IEEE(follow_string, driver)
scidirect_bot = Scidirect(follow_string, driver)
scopus_bot = Scopus(follow_string, driver)
springer_bot = Springer(follow_string, driver)
#get the followup query results
if engine == "ACM":
follow_up_results = acm_bot.test_ACM()
if engine == "IEEE":
follow_up_results = ieee_bot.test_IEEE()
if engine == "Scidirect":
follow_up_results = scidirect_bot.test_scidirect()
if engine == "Springer":
follow_up_results = springer_bot.test_springer()
if engine == "Scopus":
follow_up_results = scopus_bot.test_Scopus()
#papers from follow up query
followup_papers = follow_up_results[1]
#check if the first paper of both query is equal
if first_paper == followup_papers[0]:
#working good
fault = False
else:
#there is a bug
fault = True
results = [source_string] + source_results + [
follow_string
] + follow_up_results + [fault] + [starting_time]
return results
def MPShuffleJD(engine, keywords, driver):
#get the time using a specific format
starting_time = datetime.datetime.now().strftime('%H:%M:%S')
results = []
#source search
source_string = util.create_search_string(keywords, engine)
#create the bots
acm_bot = ACM(source_string, driver)
ieee_bot = IEEE(source_string, driver)
scidirect_bot = Scidirect(source_string, driver)
scopus_bot = Scopus(source_string, driver)
springer_bot = Springer(source_string, driver)
source_results = []
#get the source query results
if engine == "ACM":
source_results = acm_bot.test_ACM()
if engine == "IEEE":
source_results = ieee_bot.test_IEEE()
if engine == "Scidirect":
source_results = scidirect_bot.test_scidirect()
if engine == "Springer":
source_results = springer_bot.test_springer()
if engine == "Scopus":
source_results = scopus_bot.test_Scopus()
#shufle the keywords
from random import shuffle
shuffle(keywords)
#generate the followup string
follow_string = util.create_search_string(keywords, engine)
#create a new instance of the bots
acm_bot = ACM(follow_string, driver)
ieee_bot = IEEE(follow_string, driver)
scidirect_bot = Scidirect(follow_string, driver)
scopus_bot = Scopus(follow_string, driver)
springer_bot = Springer(follow_string, driver)
follow_up_results = []
#get the followup query results
if engine == "ACM":
follow_up_results = acm_bot.test_ACM()
if engine == "IEEE":
follow_up_results = ieee_bot.test_IEEE()
if engine == "Scidirect":
#Scidirect limitation.. Strings bigger than 255 chars are not suported. End the execution and sent a False value to not registre the entry
if (len(follow_string) > 255):
print(
"W: Follow-up string exceeds the allowed size limit for the base! This execution will be aborted and will not be logged."
)
return [], False
follow_up_results = scidirect_bot.test_scidirect()
if engine == "Springer":
follow_up_results = springer_bot.test_springer()
if engine == "Scopus":
follow_up_results = scopus_bot.test_Scopus()
#get the first paper from source query
try:
num_source = source_results[0]
except:
num_source = 0
try:
source_papers = source_results[1]
except:
source_papers = []
#get followup results
try:
num_followup = follow_up_results[0]
except:
num_followup = 0
try:
followup_papers = follow_up_results[1]
except:
followup_papers = []
#If the number of results is diferent then found a anomaly
if num_source == num_followup:
anon = False
else:
anon = True
#check similarity from both results
jaccard = metrics.check_similarity(source_papers, followup_papers)
results = [source_string] + source_results + [
follow_string
] + follow_up_results + [anon] + [jaccard] + [starting_time]
#add an extra return value to ensure that the execution runned as expected
return results, True
def MPReverseJD_SwapJD(engine, keywords, driver):
#get the time using a specific format
starting_time = datetime.datetime.now().strftime('%H:%M:%S')
results = []
#source search
source_string = util.create_search_string(keywords, engine)
#create the bots
acm_bot = ACM(source_string, driver)
ieee_bot = IEEE(source_string, driver)
scidirect_bot = Scidirect(source_string, driver)
scopus_bot = Scopus(source_string, driver)
springer_bot = Springer(source_string, driver)
#get the source query results
if engine == "ACM":
source_results = acm_bot.test_ACM()
if engine == "IEEE":
source_results = ieee_bot.test_IEEE()
if engine == "Scidirect":
source_results = scidirect_bot.test_scidirect()
if engine == "Springer":
source_results = springer_bot.test_springer()
if engine == "SCOPUS":
source_results = scopus_bot.test_Scopus()
#shufle the keywords
from random import shuffle
shuffle(keywords)
#generate the followup string
follow_string = util.create_search_string(keywords, engine)
#create a new instance of the bots
acm_bot = ACM(follow_string, driver)
ieee_bot = IEEE(follow_string, driver)
scidirect_bot = Scidirect(follow_string, driver)
scopus_bot = Scopus(follow_string, driver)
springer_bot = Springer(follow_string, driver)
#get the followup query results
if engine == "ACM":
follow_up_results = acm_bot.test_ACM()
if engine == "IEEE":
follow_up_results = ieee_bot.test_IEEE()
if engine == "Scidirect":
follow_up_results = scidirect_bot.test_scidirect()
if engine == "Springer":
follow_up_results = springer_bot.test_springer()
if engine == "SCOPUS":
follow_up_results = scopus_bot.test_Scopus()
#get the first paper from source query
num_source = source_results[0]
source_papers = source_results[1]
#get followup results
num_followup = follow_up_results[0]
followup_papers = follow_up_results[1]
#If the number of results is diferent then found a anomaly
if num_source == num_followup:
anon = False
else:
anon = True
#check similarity from both results
jaccard = statistics.check_similarity(source_papers, followup_papers)
results = [source_string] + source_results + [
follow_string
] + follow_up_results + [anon] + [jaccard] + [starting_time]
return results