def query_index(query, hit_logs_for_each, score_logs_for_each):
### 1_Query Alternation
user_code_query = Generator(query)
directory = SimpleFSDirectory(File(INDICES_PATH + 'bigclonebench_3'))
searchermgr = SearcherManager(directory, SearcherFactory())
searchermgr.maybeRefresh()
searcher = searchermgr.acquire()
bench_results = []
benchsearcher = BenchSearcher(searcher) # BigCloneBench
### 8_Querying for the Final Results
# Log : Bench_result for each query
bench_result, score_logs_for_each = benchsearcher.more_like_this3(5000, score_logs_for_each, user_code_query)
searchermgr.release(searcher)
searchermgr.close()
searcher = None
directory.close()
directory = None
if bench_result:
hit_logs_for_each += str(len(bench_result)) + '\t'
else:
hit_logs_for_each += ('0' + '\t')
sorted_bench_results = sorted(bench_result, key=attrgetter('score'), reverse=True)
print 'Search Count : ', len(sorted_bench_results)
recommended = recommend(sorted_bench_results)
print 'Final Count : ', len(recommended)
if bench_result:
hit_logs_for_each += str(len(recommended)) + '\t'
else:
hit_logs_for_each += ('0' + '\t')
return recommended, hit_logs_for_each, score_logs_for_each
def query_index(query, hit_logs_for_each, score_logs_for_each):
### 1_Query Alternation
user_code_query = Generator(query)
directory = SimpleFSDirectory(File(INDICES_PATH + 'stackoverflow'))
searchermgr = SearcherManager(directory, SearcherFactory())
searchermgr.maybeRefresh()
searcher = searchermgr.acquire()
### 2_Finding 3 Answer Snippets using the User Query (refined)
answers = SnippetSearcher(searcher, user_code_query)
answer_ids = answers.more_like_this(20, query=user_code_query)
searchermgr.release(searcher)
searchermgr.close()
searcher = None
directory.close()
directory = None
# Log : Answer count
if answer_ids:
hit_logs_for_each += str(len(answer_ids)) + '\t'
else:
hit_logs_for_each += ('0' + '\t')
### 3_Finding the Associated Questions
question_ids = answers.find_question_ids(answer_ids)
# Log : Answer - Question count
if question_ids:
hit_logs_for_each += str(len(question_ids)) + '\t'
else:
hit_logs_for_each += ('0' + '\t')
directory = SimpleFSDirectory(File(INDICES_PATH + 'questionIndex'))
searchermgr = SearcherManager(directory, SearcherFactory())
searchermgr.maybeRefresh()
searcher = searchermgr.acquire()
getDoc = GettingQuestionDocs(searcher)
item_docs = getDoc.search(
question_ids, 20)[0:7] # 순위대로 최소 7개의 question을 얻기 위해서 여기서 7개를 자름.
searchermgr.release(searcher)
searchermgr.close()
searcher = None
directory.close()
directory = None
# Log : Question ItemDoc count
if item_docs:
hit_logs_for_each += str(len(item_docs)) + '\t'
else:
hit_logs_for_each += ('0' + '\t')
directory = SimpleFSDirectory(File(INDICES_PATH + 'questionIndex'))
searchermgr = SearcherManager(directory, SearcherFactory())
searchermgr.maybeRefresh()
searcher = searchermgr.acquire()
### 4_Finding 3 Similar Questions per a Question (3 X 3)
similar_questions = []
question = SimilarQsSearcher(searcher)
# Log : Similar Question count for each of Question ItemDoc
i = 1
if item_docs:
for item_doc in item_docs:
similar_question = question.more_like_this2(
item_doc, 7) # 각 question 들에 대해 7개씩 비슷한 것들 찾음.
if similar_question:
hit_logs_for_each += str(len(similar_question)) + '\t'
else:
hit_logs_for_each += ('0' + '\t')
similar_questions += similar_question
i += 1
else:
hit_logs_for_each += ('0' + '\t' + '0' + '\t' + '0' + '\t' + '0' +
'\t' + '0' + '\t' + '0' + '\t' + '0' + '\t'
) # 7개
searchermgr.release(searcher)
searchermgr.close()
searcher = None
directory.close()
directory = None
# Log : Similar Question result count
if similar_questions:
hit_logs_for_each += str(len(similar_questions)) + '\t'
else:
hit_logs_for_each += ('0' + '\t')
### 5_Finding Associated Answers for each Question (9 - 9)
answer_ids = find_answer_ids(similar_questions)
# Log : Question - Answer count
if answer_ids:
hit_logs_for_each += str(len(answer_ids)) + '\t'
else:
hit_logs_for_each += ('0' + '\t')
directory = SimpleFSDirectory(File(INDICES_PATH + 'stackoverflow'))
searchermgr = SearcherManager(directory, SearcherFactory())
searchermgr.maybeRefresh()
searcher = searchermgr.acquire()
### 6_Getting Answer Docs for the Final Query
getDoc = GettingAnswerDocs(searcher)
answer_docs = getDoc.search(answer_ids)
searchermgr.release(searcher)
searchermgr.close()
searcher = None
directory.close()
directory = None
# Log : Answer Docs count
if answer_docs:
hit_logs_for_each += str(len(answer_docs)) + '\t'
else:
hit_logs_for_each += ('0' + '\t')
directory = SimpleFSDirectory(File(INDICES_PATH + 'bigclonebench_2'))
searchermgr = SearcherManager(directory, SearcherFactory())
searchermgr.maybeRefresh()
searcher = searchermgr.acquire()
bench_results = []
benchsearcher = BenchSearcher(searcher) # BigCloneBench
# Exceptional
### 7_Appending for the user query results
### 8_Querying for the Final Results
# Log : Bench_result for each query
for answer_doc in answer_docs:
bench_result, score_logs_for_each = benchsearcher.more_like_this2(
100, answer_doc, score_logs_for_each, user_code_query,
0) # , user_query=user_code_query)
if bench_result:
hit_logs_for_each += str(len(bench_result)) + '\t'
else:
hit_logs_for_each += ('0' + '\t')
bench_results += bench_result
searchermgr.release(searcher)
searchermgr.close()
searcher = None
directory.close()
directory = None
if answer_docs < 49:
for a in range(49 - len(answer_docs)):
hit_logs_for_each += ('0' + '\t')
if bench_results:
hit_logs_for_each += str(len(bench_results)) + '\t'
else:
hit_logs_for_each += ('0' + '\t')
sorted_bench_results = sorted(bench_results,
key=attrgetter('score'),
reverse=True)
print 'Search Count : ', len(sorted_bench_results)
recommended = recommend(sorted_bench_results)
print 'Final Count : ', len(recommended)
if bench_results:
hit_logs_for_each += str(len(recommended)) + '\t'
else:
hit_logs_for_each += ('0' + '\t')
return recommended, hit_logs_for_each, score_logs_for_each
def query_index(query):
### 1_Query Alternation
user_code_query = Generator(query)
print 'query: ', query
print 'user_code_query: ', user_code_query
#open
directory = SimpleFSDirectory(File(INDICES_PATH + 'stackoverflow'))
searchermgr = SearcherManager(directory, SearcherFactory())
searchermgr.maybeRefresh()
searcher = searchermgr.acquire()
### 2_Finding 3 Answer Snippets using the User Query (refined)
answers = SnippetSearcher(searcher, user_code_query)
answer_ids = answers.more_like_this(10, query=user_code_query)
print 'answer_ids: ', answer_ids
#close
searchermgr.release(searcher)
searchermgr.close()
searcher = None
directory.close()
directory = None
### 3_Finding the Associated Questions
question_ids = answers.find_question_ids(answer_ids)
print 'question ids: ', question_ids
#open
directory = SimpleFSDirectory(File(INDICES_PATH + 'questionIndex'))
searchermgr = SearcherManager(directory, SearcherFactory())
searchermgr.maybeRefresh()
searcher = searchermgr.acquire()
### 4_Cutting items
getDoc = GettingQuestionDocs(searcher)
item_docs = getDoc.search(
question_ids, 10)[0:3] # 순위대로 최소 7개의 question을 얻기 위해서 여기서 7개를 자름.
# print 'item docs: ', item_docs
### 5_Finding 3 Similar Questions per a Question (3 X 3)
similar_questions = []
question = SimilarQsSearcher(searcher)
if item_docs:
for item_doc in item_docs:
similar_question = question.more_like_this2(
item_doc, 3) # 각 question 들에 대해 7개씩 비슷한 것들 찾음.
similar_questions += similar_question
print 'similar_questions: ', similar_questions
searchermgr.release(searcher)
searchermgr.close()
searcher = None
directory.close()
directory = None
### 6_Finding Associated Answers for each Question (9 - 9)
answer_ids = find_answer_ids(similar_questions)
print 'answer ids: ', answer_ids
if not answer_ids:
recommended = ''
return recommended
# dest_path = u'/Users/Falcon/Desktop/***Ongoing***/***[4]_FaCoY_Defect4J_Data_Share_Kui/Defect4J_Results/'
# project_name = u'Chart/'###################################################
# write_file()
directory = SimpleFSDirectory(File(INDICES_PATH + 'stackoverflow'))
searchermgr = SearcherManager(directory, SearcherFactory())
searchermgr.maybeRefresh()
searcher = searchermgr.acquire()
### 7_Getting Answer Docs for the Final Query
getDoc = GettingAnswerDocs(searcher)
answer_docs = getDoc.search(answer_ids)
# print 'answer docs: ', answer_docs
searchermgr.release(searcher)
searchermgr.close()
searcher = None
directory.close()
directory = None
directory = SimpleFSDirectory(File(INDICES_PATH + 'github'))
searchermgr = SearcherManager(directory, SearcherFactory())
searchermgr.maybeRefresh()
searcher = searchermgr.acquire()
git_results = []
gitsearcher = GitSearcher(searcher)
### 7_Appending for the user query results
git_result = gitsearcher.more_like_this2(10, answer_docs[0],
user_code_query, 1)
git_results += git_result
# print 'answer docs: ', answer_docs
### 8_Querying for the Final Results
for answer_doc in answer_docs:
git_result = gitsearcher.more_like_this2(10, answer_doc,
user_code_query, 0)
git_results += git_result
searchermgr.release(searcher)
searchermgr.close()
searcher = None
directory.close()
directory = None
git_results = sorted(git_results,
key=attrgetter('so_item.answer_id'),
reverse=True)
id = 0
i = 0
temp_result = []
for item in git_results:
if id != item.so_item.answer_id:
id = item.so_item.answer_id
i = 1
temp_result.append(item)
elif id == item.so_item.answer_id and i < 3:
i += 1
temp_result.append(item)
elif id == item.so_item.answer_id and i > 3:
continue
sorted_git_results = sorted(temp_result,
key=attrgetter('score'),
reverse=True)
print 'Search Count : ', len(sorted_git_results)
recommended = recommend(sorted_git_results)
print 'Final Count : ', len(recommended)
# Defect4J 쿼리 결과저장
# cot = 0
# for c, item in enumerate(recommended):
# cot += 1
# if cot > 10:
# break
# result_file = "/Users/Falcon/Desktop/Pycharm_Project/FaCoY_Project/GitSearch/Defect4J_FaCoY/" + str(c+1) + "_" + str('_'.join(str(item[0]).split("/")[6:]))
# write_file_over(result_file, str(item.file_content))
# result_file = '/Users/Falcon/Desktop/test.txt'
# if os.path.exists(result_file):
# os.remove(result_file)
#
# write_file(result_file, 'User Code Query \n' + str(query) + '\n' + '---------------------------' + '\n')
# for c, i in enumerate(recommended):
# contents = ''
# contents = 'Rank: %d' % (int(c)+int(1))
# contents += '\nFile path: %s' % str(i.file[6:]) + '\n' + '---------------------------' + '\n'
# contents += str(i.file_content) +'\n' + '=================================================================' + '\n\n\n'
# write_file(result_file, contents)
return recommended
def query_index(query, hit_logs_for_each, score_logs_for_each):
print "*************** Searching Starts ***************"
### 1_Query Alternation
user_code_query = Generator(query)
### 2_Finding 3 Answer Snippets using the User Query (refined)
answers = SnippetSearcher("%sstackoverflow" % (INDICES_PATH),
user_code_query)
answer_ids = answers.more_like_this(
20, query=user_code_query
) #여기서 3개를 자르면, 3개의 answer 중 question 아이디가 존재하지 않을 경우, 그 수가 현저히 적어짐..
#Log : Answer count
if answer_ids: hit_logs_for_each += str(len(answer_ids)) + '\t'
else: hit_logs_for_each += ('0' + '\t')
answers.reader.close()
answers.directory.close()
### 3_Finding the Associated Questions
question_ids = answers.find_question_ids(answer_ids)
# Log : Answer - Question count
if question_ids: hit_logs_for_each += str(len(question_ids)) + '\t'
else: hit_logs_for_each += ('0' + '\t')
getDoc = GettingQuestionDocs("%squestionIndex" % (INDICES_PATH))
item_docs = getDoc.search(
question_ids, 20)[0:7] #순위대로 최소 7개의 question을 얻기 위해서 여기서 7개를 자름.
# Log : Question ItemDoc count
if item_docs: hit_logs_for_each += str(len(item_docs)) + '\t'
else: hit_logs_for_each += ('0' + '\t')
getDoc.reader.close()
getDoc.directory.close()
### 4_Finding 3 Similar Questions per a Question (3 X 3)
similar_questions = []
question = SimilarQsSearcher("%squestionIndex" % (INDICES_PATH))
# Log : Similar Question count for each of Question ItemDoc
i = 1
if item_docs:
for item_doc in item_docs:
similar_question = question.more_like_this2(
item_doc, 7) #각 question 들에 대해 7개씩 비슷한 것들 찾음.
if similar_question:
hit_logs_for_each += str(len(similar_question)) + '\t'
else:
hit_logs_for_each += ('0' + '\t')
similar_questions += similar_question
i += 1
else:
hit_logs_for_each += ('0' + '\t' + '0' + '\t' + '0' + '\t' + '0' +
'\t' + '0' + '\t' + '0' + '\t' + '0' + '\t') #7개
# Log : Similar Question result count
if similar_questions:
hit_logs_for_each += str(len(similar_questions)) + '\t'
else:
hit_logs_for_each += ('0' + '\t')
question.reader.close()
question.directory.close()
### 5_Finding Associated Answers for each Question (9 - 9)
answer_ids = find_answer_ids(similar_questions)
# Log : Question - Answer count
if answer_ids: hit_logs_for_each += str(len(answer_ids)) + '\t'
else: hit_logs_for_each += ('0' + '\t')
### 6_Getting Answer Docs for the Final Query
getDoc = GettingAnswerDocs("%sstackoverflow" % (INDICES_PATH))
answer_docs = getDoc.search(answer_ids)
# Log : Answer Docs count
if answer_docs: hit_logs_for_each += str(len(answer_docs)) + '\t'
else: hit_logs_for_each += ('0' + '\t')
# temp_doc = getDoc.search(['0',])
getDoc.reader.close()
getDoc.directory.close()
bench_results = []
benchsearcher = BenchSearcher("%sbigclonebench" %
(INDICES_PATH)) # BigCloneBench
# Exceptional
### 7_Appending for the user query results
# Log : Bench_result for UQ
# temp_doc = ResultItem(None, 0, 'No Title', 'No Question id', 'No Answer id', 'No Description')
bench_result, score_logs_for_each = benchsearcher.more_like_this2(
1, answer_docs[0], score_logs_for_each, user_code_query, 1)
if bench_result: hit_logs_for_each += str(len(bench_results)) + '\t'
else: hit_logs_for_each += ('0' + '\t')
bench_results += bench_result
### 8_Querying for the Final Results
# Log : Bench_result for each query
for answer_doc in answer_docs:
bench_result, score_logs_for_each = benchsearcher.more_like_this2(
1, answer_doc, score_logs_for_each, user_code_query,
0) #, user_query=user_code_query)
if bench_result: hit_logs_for_each += str(len(bench_result)) + '\t'
else: hit_logs_for_each += ('0' + '\t')
bench_results += bench_result
if answer_docs < 49:
for a in range(49 - len(answer_docs)):
hit_logs_for_each += ('0' + '\t')
# print 'Count(Sum of the bench results) : ', len(bench_results)
# Log : Results count
if bench_results: hit_logs_for_each += str(len(bench_results)) + '\t'
else: hit_logs_for_each += ('0' + '\t')
benchsearcher.reader.close()
benchsearcher.directory.close()
# print '%%%final_results : ', final_result
sorted_bench_results = sorted(bench_results,
key=attrgetter('score'),
reverse=True)
# results = sorted(final_result, key=attrgetter('so_item.answer_id'), reverse=True)
# print '%%%final_results_____ : ', results
print "***********************************************************************************"
# print sorted_bench_results
# Answer set에서 나오는 숫자 제한하기.. 즉, 이걸 제한하면 같은 종류의 answer에 대한 snippet들이 반복되어 출력되는걸 막는다.
# id = 0; i = 0; final_temp_result = []
# for item in sorted_bench_results:
# if id != item.so_item.answer_id:
# id = item.so_item.answer_id
# i = 1
# final_temp_result.append(item)
# elif id == item.so_item.answer_id and i < 500:
# i += 1
# final_temp_result.append(item)
# elif id == item.so_item.answer_id and i > 500:
# continue
# final_results = sorted(final_temp_result, key=attrgetter('score'), reverse=True)
# print 'Count(Final results) : ', len(final_results)
# recommended = recommend(final_results)
print 'Count(Final results) : ', len(sorted_bench_results)
recommended = recommend(sorted_bench_results)
return recommended, hit_logs_for_each, score_logs_for_each