def filtering_test_code_only(src, dst):
progress = 0
test_code_count = 0
if not os.path.isdir(dst):
os.mkdir(dst)
project_only_test = set()
for javafile in java_files_from_dir(src):
progress += 1
if progress % 1000 == 0: print 'Parsing: ', progress
if ('test' or 'tests'
) in javafile.split('/'): # and 'test' in javafile.split('/')[-1]:
test_code_count += 1
project_path = '/'.join(javafile.split('/')[:7])
project_only_test.add(project_path)
write_file('/Users/Falcon/Desktop/projects_with_test_code_only.txt',
project_path)
progress = 0
for i in project_only_test:
progress = progress + 1
if progress % 1000 == 0: print 'Copy: ', progress
target_destination_detail = dst + i.split('/')[6]
if not os.path.isdir(target_destination_detail):
os.mkdir(target_destination_detail)
copytree(i, target_destination_detail)
else:
print 'The directory is already existing..'
for javafile in java_files_from_dir(dst):
if not ('test' or 'Test') in javafile.split('/'):
os.remove(javafile)
def __init__(self, github_items, hit_logs_for_each, score_logs_for_each,
count):
self.hashes = set()
self.items = []
self.global_matched_terms = []
self.load_gitsearch_items(github_items)
print "Search Count : ", len(self.items)
hit_logs_for_each += str(len(self.items))
write_file(hitlog_path, hit_logs_for_each + '\t')
score_final_path = ''
score_final_path += scorelog_path + str(count) + '.txt'
if not os.path.exists(scorelog_path):
os.makedirs(scorelog_path)
write_file(score_final_path, score_logs_for_each + '\n')
self.rank_by_multiplication_score()
def run(name=None):
total_time = time.time()
if not os.path.exists(scorelog_path):
os.makedirs(scorelog_path)
targets = read_content_in_file(base_path +
"targets_for_recommendation_test.txt")
for query_number in targets.splitlines():
hit_logs_for_each = ''
score_logs_for_each = ''
run.counter += 1
print '[%s] : [%d] / [%d] : ' % (
str(query_number), run.counter, len(targets.split('\n'))), round(
(float(run.counter) / float(len(targets.split('\n'))) * 100),
2), '%', 'In progress..'
target_file = base_path + "targets/" + query_number + ".txt"
code_query = read_content_in_file(target_file)
code_query = cgi.escape(re.sub(r'[^\x00-\x80]+', '', code_query))
#!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!현재 이코드, 추천안하는 것들을 저장하지 않는다...
try:
if code_query:
search_time = time.time()
final_items, hit_logs_for_each, score_logs_for_each = query_index(
code_query, hit_logs_for_each, score_logs_for_each)
git_search_result = GitSearch_Result_speed_1.GitSearchResult(
final_items)
for i in git_search_result.items:
# print u'************************************************', i.file_name
save_experiment_result(query_number,
i.file_name.split('.')[0])
if not git_search_result.items:
save_experiment_result(query_number, '0')
write_file(hitlog_path, hit_logs_for_each)
score_final_path = scorelog_path + query_number + '.txt'
write_file(score_final_path, score_logs_for_each + '\n')
print("Item Searching Time : %s seconds" %
(time.time() - search_time))
print('Total Time Taken : %s seconds' % (time.time() - total_time))
print "***********************************************************************************"
except:
hit_logs_for_each += '0' # java lexer recursion limit exceeded
write_file(hitlog_path, hit_logs_for_each)
score_final_path = scorelog_path + query_number + '.txt'
write_file(score_final_path, score_logs_for_each + '\n')
save_experiment_result(query_number, '0')
print(traceback.format_exc())
print('Total Time Taken : %s seconds' % (time.time() - total_time))
print "***********************************************************************************"
def index(name=None):
index.counter += 1
print index.counter
query = request.args.get('q')
hit_logs_for_each = ''
score_logs_for_each = ''
try:
if query:
start_time = time.time()
query = cgi.escape(re.sub(r'[^\x00-\x80]+', '', query))
final_items, hit_logs_for_each, score_logs_for_each = query_index(
query, hit_logs_for_each, score_logs_for_each)
git_search_result = GitSearchResult(final_items, hit_logs_for_each,
score_logs_for_each,
index.counter)
for i in git_search_result.items:
print i.file_name
search_log = None
print("$$$%s\tseconds" % (time.time() - start_time))
return render_template("search.html",
query=query,
git_search_result=git_search_result,
search_log=search_log)
except:
hit_logs_for_each += '0' # java lexer recursion limit exceeded
write_file(hitlog_path, hit_logs_for_each)
score_final_path = ''
score_final_path = scorelog_path + str(index.counter) + '.txt'
if not os.path.exists(scorelog_path):
os.makedirs(scorelog_path)
write_file(score_final_path, score_logs_for_each + '\n')
print(traceback.format_exc())
return render_template("index.html", name=name)
def save_experiment_result(input, string):
write_file(
base_path + "New_Recommended_Set_2/" + str(input) + "_result.txt",
string)
def listing_projects_without_testcode(original, test):
for i in os.listdir(original):
if i in os.listdir(test):
continue
else:
write_file('/Users/Falcon/Desktop/list.txt', i)