为doc2vec生成训练向量的数据集
代码?:
'''
此处的函数名-函数体已经是经过处理的啦。因此,就不需要再对于函数名进行筛选啦。
'''
import json
import re
l_name = []
func_cfg = []
global count
count = 0
def main():
# json_path = r'F:\test\my_test\五种架构的CFG文件\364759_arm64_funcname_and_cfg.json'
json_path = r'F:\test\my_test\五种架构的CFG文件\236296_x8664_funcname_and_cfg.json'
with open(json_path, 'r') as f_json:
data = json.load(f_json)
print(len(data))
for i in range(len(data)):
# for i in range(60):
print(str(i) + ' ' + str(len(data)))
for k in range(len(data[i].get("func_cfg"))):
new_temp = str(data[i].get("func_cfg")[k]).split('**')
for q in range(len(new_temp)):
if (q+1) % 2 == 0:
with open('236296_x8664_funcname_and_cfg.txt','a+') as f_txt:
f_txt.write(str(new_temp[q-1])+' '+str(new_temp[q])+'\n')
if __name__ == '__main__':
main()
ok
文章出处登录后可见!
已经登录?立即刷新