class DataProc(object):
def __init__(self, data_path):
# 源代码生成的txt文件的临时存放区域
self._data_path = data_path
self._extractor = Extractor()
self._interpreter = Interpreter(self._data_path)
self._path_vec = []
# 生成txt文件
def get_feature_path(self, file_path, file_name):
out, _ = self._extractor.extract(os.path.join(file_path, file_name))
out_path = os.path.join(self._data_path,
file_name.replace('java', 'txt'))
f = open(out_path, 'w')
f.write(out.decode())
f.close()
# 从txt文件解析得到path
def get_interpr_path(self):
self._interpreter.file_iterator()
self._path_vec = self._interpreter.ret_vec
@property
def path_vec(self):
return self._path_vec
self._ret_vec = []
# 用于存储hash code
self._hash_code = []
# dict,用于存储树的索引
self._hash_tree = {}
def __call__(self, out, err):
if isinstance(out, bytes):
out = out.decode()
if isinstance(err, bytes):
err = err.decode()
assert isinstance(out, str)
assert isinstance(err, str)
self.__init__()
if len(out) == 0:
raise RuntimeError("Source file error:" + err)
else:
self.data_handler(out)
result_con = str()
result_con += self._method_name.replace("\n", " ")
for s in self._ret_vec:
result_con += s
result_con += ' '
return result_con
if __name__ == "__main__":
out, err = Extractor.extract("/Users/LeonWong/Desktop/Test.java")
interpreter = SingleInterpreter()
print(interpreter(out.decode(), err.decode()))
def extractFeatures(data):
extractor = Extractor(data)
data = extractor.extractFeatures()
def __init__(self, data_path):
# 源代码生成的txt文件的临时存放区域
self._data_path = data_path
self._extractor = Extractor()
self._interpreter = Interpreter(self._data_path)
self._path_vec = []
import cv2
import numpy as np
import Config
from tqdm import tqdm
from PIL import Image
from sklearn.svm import LinearSVC
from sklearn.neural_network import MLPClassifier
from skimage.transform import pyramid_gaussian
from sklearn.externals import joblib
from FeatureExtractor import Extractor
## Initialize the Extractor
conf = Config.Config()
extractor = Extractor(conf)
class Classifier(object):
def __init__(self, config):
self.config = config
def load_data(self):
'''
This function is used to load the training data, positive data
and negtive data.The features of images are stored in self.fds,
the labels are stored in self.labels.
:return: None
'''
self.fds = []
self.labels = []