我已经阅读了所有关于堆栈溢出和谷歌关于 python 的段错误的内容，我的情况还没有落入我迄今为止所读过的任何内容中。
基本上我已经编写了一个从外部客户端接受 HTTP 的 API。客户端将二进制文件发布到 API，我将在该 API 上运行一些进程并在之后存储。
我正在导入一个用 Python 编码的模块来进行实际的数据处理。
我通过 API 连接到机器，并且能够通过命令行解释器很好地执行这些进程。但是，当我尝试在我的 API 中执行该过程时，我得到一个分段错误。对我来说奇怪的部分是在命令行解释器中复制和粘贴的代码部分完全相同。Seg 错误发生在调用导入模块中的函数的地方。
---------------------这是终端解释器------------ ------------
Python 2.7.3 (default, Apr 20 2012, 22:39:59)
[GCC 4.6.3] on linux2
Type "help", "copyright", "credits" or "license" for more information.
>>> postdata = open('binfile').read()
>>> postdata[0:10]
'MZ\x90\x00\x03\x00\x00\x00\x04\x00'
>>> import atklite
>>> metadata = atklite.FileAnalysis(data=postdata).return_analysis()
>>> metadata
{'sha1': '1f0c33a18a417bb09f85add08b2a675c1deda5ca', 'analyzetime': 'Thu Jun 21 12:03:23 2012', 'ftype': 'PE32 executable (GUI) Intel 80386, for MS Windows', 'ttime': 1340294603.405788, 'sha256': '287744fc9d7b4f509fc271cce0af873c2d53fd1aa678d96dfc9afa8d6d1ad7a0', 'ssdeep': '768:HA/gyc4PWUSrxWoG+RUlyesIkJAkV+xQHz3ClxEEAdK88uDC4wOVdfxCO/ysRXA9:g/gyc4PWUSrxWoG+RUlyesIkJAkV+xQc', 'md5': '000038fe4b46c210c37bdde767835007', 'size': 28672}
--------------这是API崩溃的部分------------
def POST(self):
a = web.ctx.env.get("HTTP_X_AUTH_TOKEN", None)
creds = authenticator(a)
x = web.input()
b = x.values()
written = open('binfile', 'wb')
for char in b[0]:
written.write(char)
written.close()
postdata = open('binfile').read()
print postdata[0:10]
analysis = atklite.FileAnalysis(data=postdata) #SEG FAULTS HERE!!!!
metadata = analysis.return_analysis()
---------------------------------------导入的模块功能-------------------- --------------
class FileAnalysis:
results = {'analyzetime': time.ctime(),'ttime': time.time()}
hash_libs = ('md5','sha1','sha256')
if ERROR:
sys.exit('This function requires dependencies that aren\'t satisfied')
__ssd = ssdeep()
__ms = magic.open(magic.MAGIC_NONE)
__ms.load()
def __init__(self, data=None, filename=None):
if filename:
return(self.analyze_file(filename))
if data:
return(self.analyze_data(data))
def hash_data(self, data):
for lib in self.hash_libs:
hl = getattr(hashlib, lib)
self.results[lib] = hl(data).hexdigest()
def hash_file(self, filename):
hlibs = {}
size = 0
for lib in self.hash_libs:
hlibs[lib] = getattr(hashlib, lib)()
for chunk in read_chunks(open(filename, 'rb')):
# We do this here so we don't have to read twice
size += len(chunk)
for hl in hlibs:
hlibs[hl].update(chunk)
self.results['size'] = size
for hl in hlibs:
self.results[hl] = hlibs[hl].hexdigest()
def analyze_data(self, data):
if not data:
return False
self.hash_data(data)
self.results['size'] = len(data)
self.results['ftype'] = self.__ms.buffer(data)
self.results['ssdeep'] = self.__ssd.hash_bytes(data)
def analyze_file(self, filename):
if not os.path.isfile(filename):
raise IOError("File: %s doesn't exist" % filename)
# Size is done inside the hash bytes function so we don't have to read multiple times
self.hash_file(filename)
self.results['ftype'] = self.__ms.file(filename)
self.results['ssdeep'] = self.__ssd.hash_file(filename)
def return_analysis(self):
return (self.results)
def dump(self):
res = []
for result in self.results:
res.append("%s: %s" % (result, self.results[result]))
return("\n".join(res))
使用邓肯的建议可以追溯到这个
> /home/spezzino/ProcessingCode/atklite.py(93)analyze_data()
-> self.results['ftype'] = self.__ms.buffer(data)
(Pdb) s
--Call--
> /usr/lib/python2.7/dist-packages/magic.py(126)buffer()
-> def buffer(self, buf):
(Pdb) s
> /usr/lib/python2.7/dist-packages/magic.py(132)buffer()
-> return _buffer(self._magic_t, buf, len(buf))
(Pdb) s
--Return--
> /usr/lib/python2.7/dist-packages/magic.py(132)buffer()->'PE32 executa...or MS Windows'
-> return _buffer(self._magic_t, buf, len(buf))
(Pdb) s
> /home/spezzino/ProcessingCode/atklite.py(94)analyze_data()
-> self.results['ssdeep'] = self.__ssd.hash_bytes(data)
(Pdb) s
Segmentation fault