def copyConfirm(listfile, dir):
content = read_file(listfile)
projects = content.split('\n')
error_count = 0
for i in os.listdir(dir):
if i in projects:
continue
else:
error_count += 1
print i
print "error count: ", error_count
def copy_projects_from_gitbase(listfile, gitbase, dst):
print 'Copying the target projects...'
count_copy = 0
target_list = read_file(listfile)
for i in target_list.split('\n'):
if i == '.DS_Store':
continue
count_copy += 1
print "Processing " + i + '...' + str(count_copy)
try:
copytree(gitbase + i, dst + i)
except:
print '!!!!!!!!!!!!!!!!!!!!!!!! Copy failed with ' + i
print 'Done..'
def buildLinePosDict(file):
contents = read_file(file)
char = len(contents)
line_endpos_dict = {}
pos = 0
maxline = len(contents.splitlines())
print maxline
for i, line in enumerate(contents.split('\n'), 1):
if maxline < i:
break
if line == '':
pos += 1
else:
pos += len(line) + 1
print i, pos
line_endpos_dict[i] = pos
print char
print pos
return line_endpos_dict
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..'
if __name__ == '__main__':
src = '/Users/Falcon/Desktop/GitArchive/Git_testcode_only/'
# refineDirectories(src)
# check_for_duplicates(src)
# rm_dup(src)
# javafiles = java_files_from_dir(src)
# count = 0
# for i in javafiles:
# count += 1
#
# print count
aset = set()
contents = read_file(
'/Users/Falcon/Desktop/projects_with_test_code_only.txt')
for i in contents.split('\n'):
aset.add(i)
for i in aset:
write_file('/Users/Falcon/Desktop/projects_test_code_only.txt', i)
pass
# {hunk: lines} dict 생성 (한 파일 당, 분산된 여러 hunk 가 있을 수 있음.)
hunk_num = 0
hunk_lines_dict = {}
# diff 정보 가져오기
# hunk_lines_dict
# h[1]:63..74 // 63, 64, 65, ... , 74
# h[2]:78..89 //
hunk_lines_dict = getDiffNew(user_repo_, commit_hash, prev_hash, file_name)
if hunk_lines_dict is None:
print("Failed to get the diff for ...Commit: %s /// File: %s" % (commit_hash, file_hash))
continue
# 2개의 파일을 받아서 [변경된 라인 번호] + [각 라인 별 Position range] 얻기
before = read_file(before_file_path)
after = read_file(after_file_path)
# {line: position} dict 생성 (한 라인 당, position)
f_pos_1 = 0
f_pos_2 = 0
f_init_line_num = 0
line_positions_dict = {}
for i in before.split('\n'):
f_init_line_num += 1
f_pos_2 = f_pos_1 + i.__len__()
# line_positions_dict
# l[0]:0..12
# l[1]:13..21
line_positions_dict[f_init_line_num] = str(f_pos_1) + ".." + str(f_pos_2)
def charCounter(st):
count = 0
for _ in read_file(st):
count += 1
return count
def stripFile(file):
return read_file(file).strip()