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_4_text'))
searchermgr = SearcherManager(directory, SearcherFactory())
searchermgr.maybeRefresh()
searcher = searchermgr.acquire()
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