def _write_pyc(state, co, source_stat, pyc):
# Technically, we don't have to have the same pyc format as
# (C)Python, since these "pycs" should never be seen by builtin
# import. However, there's little reason deviate, and I hope
# sometime to be able to use imp.load_compiled to load them. (See
# the comment in load_module above.)
try:
fp = open(pyc, "wb")
except IOError:
err = sys.exc_info()[1].errno
state.trace("error writing pyc file at %s: errno=%s" %(pyc, err))
# we ignore any failure to write the cache file
# there are many reasons, permission-denied, __pycache__ being a
# file etc.
return False
try:
fp.write(imp.get_magic())
mtime = int(source_stat.mtime)
size = source_stat.size & 0xFFFFFFFF
fp.write(struct.pack("<ll", mtime, size))
marshal.dump(co, fp)
finally:
fp.close()
return True
python类dump()的实例源码
def process(ifile, ofile):
logger.info('Opening file ' + ifile)
ifPtr = open(ifile, 'rb')
header = ifPtr.read(8)
if not header.startswith('\x03\xF3\x0D\x0A'):
raise SystemExit('[!] Header mismatch. The input file is not a valid pyc file.')
logger.info('Input pyc file header matched')
logger.debug('Unmarshalling file')
rootCodeObject = marshal.load(ifPtr)
ifPtr.close()
deob = parse_code_object(rootCodeObject)
logger.info('Writing deobfuscated code object to disk')
ofPtr = open(ofile, 'wb')
ofPtr.write(header)
marshal.dump(deob, ofPtr)
ofPtr.close()
logger.info('Success')
def test_foreign_code(self):
py_compile.compile(self.file_name)
with open(self.compiled_name, "rb") as f:
header = f.read(8)
code = marshal.load(f)
constants = list(code.co_consts)
foreign_code = test_main.__code__
pos = constants.index(1)
constants[pos] = foreign_code
code = type(code)(code.co_argcount, code.co_kwonlyargcount,
code.co_nlocals, code.co_stacksize,
code.co_flags, code.co_code, tuple(constants),
code.co_names, code.co_varnames, code.co_filename,
code.co_name, code.co_firstlineno, code.co_lnotab,
code.co_freevars, code.co_cellvars)
with open(self.compiled_name, "wb") as f:
f.write(header)
marshal.dump(code, f)
mod = self.import_module()
self.assertEqual(mod.constant.co_filename, foreign_code.co_filename)
def test_multiple_dumps_and_loads(self):
# Issue 12291: marshal.load() should be callable multiple times
# with interleaved data written by non-marshal code
# Adapted from a patch by Engelbert Gruber.
data = (1, 'abc', b'def', 1.0, (2, 'a', ['b', b'c']))
for interleaved in (b'', b'0123'):
ilen = len(interleaved)
positions = []
try:
with open(support.TESTFN, 'wb') as f:
for d in data:
marshal.dump(d, f)
if ilen:
f.write(interleaved)
positions.append(f.tell())
with open(support.TESTFN, 'rb') as f:
for i, d in enumerate(data):
self.assertEqual(d, marshal.load(f))
if ilen:
f.read(ilen)
self.assertEqual(positions[i], f.tell())
finally:
support.unlink(support.TESTFN)
def test_foreign_code(self):
py_compile.compile(self.file_name)
with open(self.compiled_name, "rb") as f:
header = f.read(8)
code = marshal.load(f)
constants = list(code.co_consts)
foreign_code = test_main.func_code
pos = constants.index(1)
constants[pos] = foreign_code
code = type(code)(code.co_argcount, code.co_nlocals, code.co_stacksize,
code.co_flags, code.co_code, tuple(constants),
code.co_names, code.co_varnames, code.co_filename,
code.co_name, code.co_firstlineno, code.co_lnotab,
code.co_freevars, code.co_cellvars)
with open(self.compiled_name, "wb") as f:
f.write(header)
marshal.dump(code, f)
mod = self.import_module()
self.assertEqual(mod.constant.co_filename, foreign_code.co_filename)
def save_views(self):
# save the current color
self.__optiondb['RED'] = self.__red
self.__optiondb['GREEN'] = self.__green
self.__optiondb['BLUE'] = self.__blue
for v in self.__views:
if hasattr(v, 'save_options'):
v.save_options(self.__optiondb)
# save the name of the file used for the color database. we'll try to
# load this first.
self.__optiondb['DBFILE'] = self.__colordb.filename()
fp = None
try:
try:
fp = open(self.__initfile, 'w')
except IOError:
print >> sys.stderr, 'Cannot write options to file:', \
self.__initfile
else:
marshal.dump(self.__optiondb, fp)
finally:
if fp:
fp.close()
def save_views(self):
# save the current color
self.__optiondb['RED'] = self.__red
self.__optiondb['GREEN'] = self.__green
self.__optiondb['BLUE'] = self.__blue
for v in self.__views:
if hasattr(v, 'save_options'):
v.save_options(self.__optiondb)
# save the name of the file used for the color database. we'll try to
# load this first.
self.__optiondb['DBFILE'] = self.__colordb.filename()
fp = None
try:
try:
fp = open(self.__initfile, 'w')
except IOError:
print >> sys.stderr, 'Cannot write options to file:', \
self.__initfile
else:
marshal.dump(self.__optiondb, fp)
finally:
if fp:
fp.close()
def _write_pyc(state, co, source_stat, pyc):
# Technically, we don't have to have the same pyc format as
# (C)Python, since these "pycs" should never be seen by builtin
# import. However, there's little reason deviate, and I hope
# sometime to be able to use imp.load_compiled to load them. (See
# the comment in load_module above.)
try:
fp = open(pyc, "wb")
except IOError:
err = sys.exc_info()[1].errno
state.trace("error writing pyc file at %s: errno=%s" %(pyc, err))
# we ignore any failure to write the cache file
# there are many reasons, permission-denied, __pycache__ being a
# file etc.
return False
try:
fp.write(imp.get_magic())
mtime = int(source_stat.mtime)
size = source_stat.size & 0xFFFFFFFF
fp.write(struct.pack("<ll", mtime, size))
marshal.dump(co, fp)
finally:
fp.close()
return True
def test_foreign_code(self):
py_compile.compile(self.file_name)
with open(self.compiled_name, "rb") as f:
header = f.read(12)
code = marshal.load(f)
constants = list(code.co_consts)
foreign_code = test_main.__code__
pos = constants.index(1)
constants[pos] = foreign_code
code = type(code)(code.co_argcount, code.co_kwonlyargcount,
code.co_nlocals, code.co_stacksize,
code.co_flags, code.co_code, tuple(constants),
code.co_names, code.co_varnames, code.co_filename,
code.co_name, code.co_firstlineno, code.co_lnotab,
code.co_freevars, code.co_cellvars)
with open(self.compiled_name, "wb") as f:
f.write(header)
marshal.dump(code, f)
mod = self.import_module()
self.assertEqual(mod.constant.co_filename, foreign_code.co_filename)
def test_multiple_dumps_and_loads(self):
# Issue 12291: marshal.load() should be callable multiple times
# with interleaved data written by non-marshal code
# Adapted from a patch by Engelbert Gruber.
data = (1, 'abc', b'def', 1.0, (2, 'a', ['b', b'c']))
for interleaved in (b'', b'0123'):
ilen = len(interleaved)
positions = []
try:
with open(support.TESTFN, 'wb') as f:
for d in data:
marshal.dump(d, f)
if ilen:
f.write(interleaved)
positions.append(f.tell())
with open(support.TESTFN, 'rb') as f:
for i, d in enumerate(data):
self.assertEqual(d, marshal.load(f))
if ilen:
f.read(ilen)
self.assertEqual(positions[i], f.tell())
finally:
support.unlink(support.TESTFN)
def _write_pyc(state, co, source_stat, pyc):
# Technically, we don't have to have the same pyc format as
# (C)Python, since these "pycs" should never be seen by builtin
# import. However, there's little reason deviate, and I hope
# sometime to be able to use imp.load_compiled to load them. (See
# the comment in load_module above.)
try:
fp = open(pyc, "wb")
except IOError:
err = sys.exc_info()[1].errno
state.trace("error writing pyc file at %s: errno=%s" %(pyc, err))
# we ignore any failure to write the cache file
# there are many reasons, permission-denied, __pycache__ being a
# file etc.
return False
try:
fp.write(imp.get_magic())
mtime = int(source_stat.mtime)
size = source_stat.size & 0xFFFFFFFF
fp.write(struct.pack("<ll", mtime, size))
marshal.dump(co, fp)
finally:
fp.close()
return True
def _write_pyc(state, co, source_stat, pyc):
# Technically, we don't have to have the same pyc format as
# (C)Python, since these "pycs" should never be seen by builtin
# import. However, there's little reason deviate, and I hope
# sometime to be able to use imp.load_compiled to load them. (See
# the comment in load_module above.)
try:
fp = open(pyc, "wb")
except IOError:
err = sys.exc_info()[1].errno
state.trace("error writing pyc file at %s: errno=%s" %(pyc, err))
# we ignore any failure to write the cache file
# there are many reasons, permission-denied, __pycache__ being a
# file etc.
return False
try:
fp.write(imp.get_magic())
mtime = int(source_stat.mtime)
size = source_stat.size & 0xFFFFFFFF
fp.write(struct.pack("<ll", mtime, size))
marshal.dump(co, fp)
finally:
fp.close()
return True
def set_new_path(self, new_idf_path):
if self.path != new_idf_path:
self.path = new_idf_path
cache_file = "idf.cache"
cache_file = os.path.join(tempfile.gettempdir(), cache_file)
try:
with open(cache_file, 'rb') as cf:
self.idf_freq, self.median_idf = marshal.load(cf)
# print("Loading model from cache %s" % cache_file)
except Exception:
content = open(new_idf_path, 'rb').read().decode('utf-8')
self.idf_freq = {}
for line in content.splitlines():
word, freq = line.strip().split(' ')
self.idf_freq[word] = float(freq)
self.median_idf = sorted(
self.idf_freq.values())[len(self.idf_freq) // 2]
with open(cache_file, 'wb') as cf:
marshal.dump((self.idf_freq, self.median_idf), cf)
def dump_stats(self, file):
f = open(file, 'wb')
self.create_stats()
marshal.dump(self.stats, f)
f.close()
def _compile(pathname, timestamp):
"""Compile (and cache) a Python source file.
The file specified by <pathname> is compiled to a code object and
returned.
Presuming the appropriate privileges exist, the bytecodes will be
saved back to the filesystem for future imports. The source file's
modification timestamp must be provided as a Long value.
"""
codestring = open(pathname, 'rU').read()
if codestring and codestring[-1] != '\n':
codestring = codestring + '\n'
code = __builtin__.compile(codestring, pathname, 'exec')
# try to cache the compiled code
try:
f = open(pathname + _suffix_char, 'wb')
except IOError:
pass
else:
f.write('\0\0\0\0')
f.write(struct.pack('<I', timestamp))
marshal.dump(code, f)
f.flush()
f.seek(0, 0)
f.write(imp.get_magic())
f.close()
return code
def dump_stats(self, filename):
"""Write the profile data to a file we know how to load back."""
f = file(filename, 'wb')
try:
marshal.dump(self.stats, f)
finally:
f.close()
# list the tuple indices and directions for sorting,
# along with some printable description
def marshal_dump(code, f):
if isinstance(f, file):
marshal.dump(code, f)
else:
f.write(marshal.dumps(code))
def write_bytecode(self, f):
"""Dump the bytecode into the file or file like object passed."""
if self.code is None:
raise TypeError('can\'t write empty bucket')
f.write(bc_magic)
pickle.dump(self.checksum, f, 2)
marshal_dump(self.code, f)
def marshal_dump(code, f):
if isinstance(f, file):
marshal.dump(code, f)
else:
f.write(marshal.dumps(code))
def write_bytecode(self, f):
"""Dump the bytecode into the file or file like object passed."""
if self.code is None:
raise TypeError('can\'t write empty bucket')
f.write(bc_magic)
pickle.dump(self.checksum, f, 2)
marshal_dump(self.code, f)
def dump_marshal(data, path_to_file):
try:
with open(path_to_file, 'w') as f:
m.dump(data, f)
except Exception as e:
raise e
def dump_pickle(data, path_to_file):
try:
with open(path_to_file, 'w') as f:
pickle.dump(data, f)
except Exception as e:
raise e
def dump_json(data, file):
try:
with open(file, 'w') as datafile:
json.dump(data, datafile)
except Exception as e:
raise e
def marshal_dump(code, f):
if isinstance(f, file):
marshal.dump(code, f)
else:
f.write(marshal.dumps(code))
def write_bytecode(self, f):
"""Dump the bytecode into the file or file like object passed."""
if self.code is None:
raise TypeError('can\'t write empty bucket')
f.write(bc_magic)
pickle.dump(self.checksum, f, 2)
marshal_dump(self.code, f)
def marshal_dump(code, f):
if isinstance(f, file):
marshal.dump(code, f)
else:
f.write(marshal.dumps(code))
def write_bytecode(self, f):
"""Dump the bytecode into the file or file like object passed."""
if self.code is None:
raise TypeError('can\'t write empty bucket')
f.write(bc_magic)
pickle.dump(self.checksum, f, 2)
marshal_dump(self.code, f)
def _make_rewritten_pyc(state, source_stat, pyc, co):
"""Try to dump rewritten code to *pyc*."""
if sys.platform.startswith("win"):
# Windows grants exclusive access to open files and doesn't have atomic
# rename, so just write into the final file.
_write_pyc(state, co, source_stat, pyc)
else:
# When not on windows, assume rename is atomic. Dump the code object
# into a file specific to this process and atomically replace it.
proc_pyc = pyc + "." + str(os.getpid())
if _write_pyc(state, co, source_stat, proc_pyc):
os.rename(proc_pyc, pyc)
def dump_stats(self, file):
f = open(file, 'wb')
self.create_stats()
marshal.dump(self.stats, f)
f.close()
def _compile(pathname, timestamp):
"""Compile (and cache) a Python source file.
The file specified by <pathname> is compiled to a code object and
returned.
Presuming the appropriate privileges exist, the bytecodes will be
saved back to the filesystem for future imports. The source file's
modification timestamp must be provided as a Long value.
"""
codestring = open(pathname, 'rU').read()
if codestring and codestring[-1] != '\n':
codestring = codestring + '\n'
code = __builtin__.compile(codestring, pathname, 'exec')
# try to cache the compiled code
try:
f = open(pathname + _suffix_char, 'wb')
except IOError:
pass
else:
f.write('\0\0\0\0')
f.write(struct.pack('<I', timestamp))
marshal.dump(code, f)
f.flush()
f.seek(0, 0)
f.write(imp.get_magic())
f.close()
return code
