faultnum = csv.reader(file(subject_dir+subject+'\\fault_log.csv','rb')) for line in faultnum: if faultnum.line_num == 1: continue currenttime = datetime.datetime.strptime(line[2], '%Y-%m-%d %H:%M:%S') if tagtime[tag] >= currenttime or nexttagtime < currenttime: continue elif currenttime > tagtime[tag] and currenttime<=nexttagtime and len(line)==6: if line[5] in fault_info.keys(): fault_info[line[5]] = fault_info[line[5]] + 1 else: fault_info[line[5]] = 1 for currentFileName in walkDirectory(sourcedir): try: astContent = customast.parse_file(currentFileName) except: print subject,tag,currentFileName continue lines = set() for n in ast.walk(astContent): if hasattr(n,'lineno'): lines.add(n.lineno) if currentFileName in change_info.keys(): change_count = change_info[currentFileName] else: change_count = 0 if currentFileName in fault_info.keys(): fault_count = fault_info[currentFileName]
def code_change_extraction(left_file, right_file):
# 对两个源程序进行处理，生成各自的中间抽象语法树，并获取节点列表等相应信息
left_AstContent = customast.parse_file(left_file)
left_tree = Tree('头指针', 'left_head')
left_root = Node('AstRoot', 'root')
left_tree.linktohead(left_root)
ast_process(left_AstContent, left_root)
id_set(left_tree.head)
left_child_to_parent = child_parent_information(left_tree.head)
left_node_list, left_inner_node_list, left_leaf_node_list = node_get(left_tree.head)
left_id_to_node = id_to_node_get(left_node_list)
# 设置每个节点的parent_id属性
for pair in left_child_to_parent:
for left_id in left_id_to_node:
if left_id == pair[0]:
left_node = left_id_to_node.get(left_id)
left_node.parent = pair[1]
right_AstContent = customast.parse_file(right_file)
right_tree = Tree('头指针', 'right_head')
right_root = Node('AstRoot', 'root')
right_tree.linktohead(right_root)
ast_process(right_AstContent, right_root)
id_set(right_tree.head)
right_child_to_parent = child_parent_information(right_tree.head)
right_node_list, right_inner_node_list, right_leaf_node_list = node_get(right_tree.head)
right_id_to_node = id_to_node_get(right_node_list)
for pair in right_child_to_parent:
for right_id in right_id_to_node:
if right_id == pair[0]:
right_node = right_id_to_node.get(right_id)
right_node.parent = pair[1]
# 匹配叶子节点
match_temp = leaf_match(left_leaf_node_list, right_leaf_node_list, 0.6)
match_final = best_match(match_temp)
leaf_matched_set(left_leaf_node_list, right_leaf_node_list, match_final)
# 匹配中间节点
# 对T1中所有标记为unmatched的中间节点，如果T2中存在一个节点y与之匹配，则将(x, y)加入match_final集合
# 在匹配中间节点时采用first match，对于中间节点而言，first is best的概率较大
for node1 in left_inner_node_list:
for node2 in right_inner_node_list:
if node1.matched == 0 and node2.matched == 0:
inner_node_match(node1, node2, match_final, 0.4, 0.6)
# 将头指针和根节点加入match_final集合，并将matched标志置为1，确保头指针和根节点一定匹配
match_final.append((0, 0, 1.0))
match_final.append(('head_parent', 'head_parent', 1.0))
match_final.append((1, 1, 1.0))
# 根据T1与T2的匹配节点集合match_final计算从T1转换为T2的编辑操作
edit_script, change_information, change_information2 = \
editscript_calculate(left_node_list, match_final, left_id_to_node, right_id_to_node, right_node_list)
# 根据编辑操作得到相应的ChangeType
change_type_list, scc_list, parent_entity_list, changed_entity_list = \
changetype_generation(change_information, change_information2)
'''
# 输出change信息
for i in range(len(change_type_list)):
if change_type_list[i] != '':
print('\nChangeType:', change_type_list[i])
print('scc:', scc_list[i])
print('ChangedEntity:', changed_entity_list[i])
print('ParentEntity:', parent_entity_list[i])
'''
# 根据变更抽取结果统计ChangeType的分布
change_type = change_type_enum()
change_type_percentage = [0] * len(change_type) # 用于保存每种change出现的百分比
# 若change_type_list长度为0，表示没有不同，change_type_percentage中的元素全为0，否则计算每种change出现的频率
change_type_dict = changetype_statistic(change_type_list)
if len(change_type_list) != 0:
for key, value in change_type_dict.items():
for i in range(len(change_type)):
if key == change_type[i]:
change_type_percentage[i] = value / len(change_type_list)
# change_type_percentage在对应位置保存了每种change_type的分布百分比
# 例如，change_type_percentage[i]保存的是change_type[i]出现的频率
return change_type_percentage
continue
if alias.asname is not None:
for (name,file,lineno) in self.imports:
if name==alias.asname and self.fileName==file:
break
else:
self.imports.add((alias.asname,self.fileName,node.lineno))
elif alias.name != '*':
for (name,file,lineno) in self.imports:
if name==alias.name and self.fileName==file:
break
else:
self.imports.add((alias.name,self.fileName,node.lineno))
self.generic_visit(node)
if __name__ == '__main__':
myast = MyAst()
astContent = customast.parse_file('C:\\Users\\JOJO\\Desktop\\pysmell\\detection\\test.py')
myast.fileName = "C:\\Users\\JOJO\\Desktop\\pysmell\\detection\\test.py"
myast.visit(astContent)
print myast.imports
# print myast.defmagic
# print myast.usedmagic
# for useitem in myast.usedmagic:
# for defitem in myast.defmagic:
# if useitem[0] == defitem[0]:
# break
# else:
# myast.result.append((12,useitem[1],useitem[2],useitem[0]))
# print myast.result
def count_lines(node):
childnodes = list(ast.walk(node))
lines = [0]
for n in childnodes:
if hasattr(n, 'lineno'):
lines.append(n.lineno)
return max(lines)
projects = os.listdir(subject_dir)
for projectName in projects:
total_projects += 1
project_dir = subject_dir + projectName
lines = 0
files = 0
for currentFileName in walkDirectory(project_dir):
try:
astContent = customast.parse_file(currentFileName)
except:
print(project_dir, currentFileName)
continue
lines = lines + count_lines(astContent)
files = files + 1
project_info_file.writerow([projectName, files, lines])
total_lines = total_lines + lines
total_files = total_files + files
project_info_file.writerow([total_projects, total_files, total_lines])
