我想向C函数发送一个字符串列表:
from ctypes import c_double, c_void_p, Structure, cast, c_char_p, c_size_t, POINTER
import numpy as np
class FFIArray(Structure):
"""
Convert sequence of structs or types to C-compatible void array
"""
_fields_ = [("data", c_void_p), ("len", c_size_t)]
@classmethod
def from_param(cls, seq):
""" Allow implicit conversions """
return seq if isinstance(seq, cls) else cls(seq)
def __init__(self, seq, data_type):
array = np.ctypeslib.as_array((data_type * len(seq))(*seq))
self._buffer = array.data
self.data = cast(array.ctypes.data_as(POINTER(data_type)), c_void_p)
self.len = len(array)
class Coordinates(Structure):
_fields_ = [("lat", c_double), ("lon", c_double)]
def __str__(self):
return "Latitude: {}, Longitude: {}".format(self.lat, self.lon)
if __name__ == "__main__":
tup = Coordinates(0.0, 1.0)
coords = [tup, tup]
a = b"foo"
b = b"bar"
words = [a, b]
coord_array = FFIArray(coords, data_type=Coordinates)
print(coord_array)
word_array = FFIArray(words, c_char_p)
print(word_array)
这适用于例如c_double
,但当我尝试使用c_char_p
时失败,出现以下错误(在Python2.7.16和3.7.4以及NumPy 1.16.5、1.17.2上测试):
Traceback (most recent call last):
File "/Users/sth/dev/test/venv3/lib/python3.7/site-packages/numpy/core/_internal.py", line 600, in _dtype_from_pep3118
dtype, align = __dtype_from_pep3118(stream, is_subdtype=False)
File "/Users/sth/dev/test/venv3/lib/python3.7/site-packages/numpy/core/_internal.py", line 677, in __dtype_from_pep3118
raise ValueError("Unknown PEP 3118 data type specifier %r" % stream.s)
ValueError: Unknown PEP 3118 data type specifier 'z'
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "so_example.py", line 42, in <module>
word_array = FFIArray(words, c_char_p)
File "so_example.py", line 19, in __init__
array = np.ctypeslib.as_array((data_type * len(seq))(*seq))
File "/Users/sth/dev/test/venv3/lib/python3.7/site-packages/numpy/ctypeslib.py", line 523, in as_array
return array(obj, copy=False)
ValueError: '<z' is not a valid PEP 3118 buffer format string
有更好的方法吗?我也不习惯使用numpy
,尽管它对于将数字类型的迭代和numpy
数组转换为其他地方的_FFIArray
很有用。
清单[Python.Docs]: ctype-用于Python的外部函数库。
我还没有弄清NumPy的错误(到目前为止,我找到了_multiarray_umath(C)源,但我不知道如何调用_internal.py中的函数)。
同时,这里有一个不使用NumPy的变体(在这种情况下不需要它,但是你提到你在其他部分使用它,所以这可能只解决了你的问题的一部分)。
code03.py:
#!/usr/bin/env python3
import sys
import ctypes
import numpy as np
class FFIArray(ctypes.Structure):
"""
Convert sequence of structs or types to C-compatible void array
"""
_fields_ = [
("data", ctypes.c_void_p),
("len", ctypes.c_size_t)
]
@classmethod
def from_param(cls, seq, data_type):
""" Allow implicit conversions """
return seq if isinstance(seq, cls) else cls(seq, data_type)
def __init__(self, seq, data_type):
self.len = len(seq)
self._data_type = data_type
self._DataTypeArr = self._data_type * self.len
self.data = ctypes.cast(self._DataTypeArr(*seq), ctypes.c_void_p)
def __str__(self):
ret = super().__str__() # Python 3
#ret = super(FFIArray, self).__str__() # !!! Python 2 !!!
ret += "\nType: {0:s}\nLength: {1:d}\nElement Type: {2:}\nElements:\n".format(
self.__class__.__name__, self.len, self._data_type)
arr_data = self._DataTypeArr.from_address(self.data)
for idx, item in enumerate(arr_data):
ret += " {0:d}: {1:}\n".format(idx, item)
return ret
class Coordinates(ctypes.Structure):
_fields_ = [
("lat", ctypes.c_double),
("lon", ctypes.c_double)
]
def __str__(self):
return "Latitude: {0:.3f}, Longitude: {1:.3f}".format(self.lat, self.lon)
def main():
coord_list = [Coordinates(i+ 1, i * 2) for i in range(4)]
s0 = b"foo"
s1 = b"bar"
word_list = [s0, s1]
coord_array = FFIArray(coord_list, data_type=Coordinates)
print(coord_array)
word_array = FFIArray(word_list, ctypes.c_char_p)
print(word_array)
if __name__ == "__main__":
print("Python {0:s} {1:d}bit on {2:s}\n".format(" ".join(item.strip() for item in sys.version.split("\n")), 64 if sys.maxsize > 0x100000000 else 32, sys.platform))
print("NumPy: {0:s}\n".format(np.version.version))
main()
print("\nDone.")
注意事项:
输出:
[cfati@CFATI-5510-0:e:\Work\Dev\StackOverflow\q058049957]> "e:\Work\Dev\VEnvs\py_064_03.07.03_test0\Scripts\python.exe" code03.py
Python 3.7.3 (v3.7.3:ef4ec6ed12, Mar 25 2019, 22:22:05) [MSC v.1916 64 bit (AMD64)] 64bit on win32
NumPy: 1.16.2
<__main__.FFIArray object at 0x0000019CFEB63648>
Type: FFIArray
Length: 4
Element Type: <class '__main__.Coordinates'>
Elements:
0: Latitude: 1.000, Longitude: 0.000
1: Latitude: 2.000, Longitude: 2.000
2: Latitude: 3.000, Longitude: 4.000
3: Latitude: 4.000, Longitude: 6.000
<__main__.FFIArray object at 0x0000019CFEB637C8>
Type: FFIArray
Length: 2
Element Type: <class 'ctypes.c_char_p'>
Elements:
0: b'foo'
1: b'bar'
Done.
PEP3118定义了访问(共享)内存的标准。其中一部分是用于在缓冲区内容和相关数据之间进行转换的格式字符串说明符。这些在[Python.Docs]中列出:PEP3118-struct string-语法的添加和从[Python3.Docs]扩展的那些:struct-Format Characters。
ctype类型有一个(!!!未记录!!!)_type_属性,(我认为)在执行从/到np的转换时使用该属性:
>>> import ctypes
>>>
>>> data_types = list()
>>>
>>> for attr_name in dir(ctypes):
... attr = getattr(ctypes, attr_name, None)
... if isinstance(attr, (type,)) and issubclass(attr, (ctypes._SimpleCData,)):
... data_types.append((attr, attr_name))
...
>>> for data_type, data_type_name in data_types:
... print("{0:} ({1:}) - {2:}".format(data_type, data_type_name, getattr(data_type, "_type_", None)))
...
<class 'ctypes.HRESULT'> (HRESULT) - l
<class '_ctypes._SimpleCData'> (_SimpleCData) - None
<class 'ctypes.c_bool'> (c_bool) - ?
<class 'ctypes.c_byte'> (c_byte) - b
<class 'ctypes.c_char'> (c_char) - c
<class 'ctypes.c_char_p'> (c_char_p) - z
<class 'ctypes.c_double'> (c_double) - d
<class 'ctypes.c_float'> (c_float) - f
<class 'ctypes.c_long'> (c_int) - l
<class 'ctypes.c_short'> (c_int16) - h
<class 'ctypes.c_long'> (c_int32) - l
<class 'ctypes.c_longlong'> (c_int64) - q
<class 'ctypes.c_byte'> (c_int8) - b
<class 'ctypes.c_long'> (c_long) - l
<class 'ctypes.c_double'> (c_longdouble) - d
<class 'ctypes.c_longlong'> (c_longlong) - q
<class 'ctypes.c_short'> (c_short) - h
<class 'ctypes.c_ulonglong'> (c_size_t) - Q
<class 'ctypes.c_longlong'> (c_ssize_t) - q
<class 'ctypes.c_ubyte'> (c_ubyte) - B
<class 'ctypes.c_ulong'> (c_uint) - L
<class 'ctypes.c_ushort'> (c_uint16) - H
<class 'ctypes.c_ulong'> (c_uint32) - L
<class 'ctypes.c_ulonglong'> (c_uint64) - Q
<class 'ctypes.c_ubyte'> (c_uint8) - B
<class 'ctypes.c_ulong'> (c_ulong) - L
<class 'ctypes.c_ulonglong'> (c_ulonglong) - Q
<class 'ctypes.c_ushort'> (c_ushort) - H
<class 'ctypes.c_void_p'> (c_void_p) - P
<class 'ctypes.c_void_p'> (c_voidp) - P
<class 'ctypes.c_wchar'> (c_wchar) - u
<class 'ctypes.c_wchar_p'> (c_wchar_p) - Z
<class 'ctypes.py_object'> (py_object) - O
如上所述,c_char_p和c_whar_p没有找到或与标准不匹配。乍一看,这似乎是一个ctypebug因为它不尊重标准,但在进一步调查之前,我不会急于声称这一事实(也许提交bug)(特别是因为这个领域已经报告了错误:[Python. Bugs]:ctype数组的缓冲区信息不正确(PEP-3118))。
下面是一个也处理np数组的变体。
code04.py:
#!/usr/bin/env python3
import sys
import ctypes
import numpy as np
class FFIArray(ctypes.Structure):
"""
Convert sequence of structs or types to C-compatible void array
"""
_fields_ = [
("data", ctypes.c_void_p),
("len", ctypes.c_size_t)
]
_special_np_types_mapping = {
ctypes.c_char_p: "S",
ctypes.c_wchar_p: "U",
}
@classmethod
def from_param(cls, seq, data_type=ctypes.c_void_p):
""" Allow implicit conversions """
return seq if isinstance(seq, cls) else cls(seq, data_type=data_type)
def __init__(self, seq, data_type=ctypes.c_void_p):
self.len = len(seq)
self.__data_type = data_type # Used just to hold the value passed to the initializer
if isinstance(seq, np.ndarray):
arr = np.ctypeslib.as_ctypes(seq)
self._data_type = arr._type_ # !!! data_type is ignored in this case !!!
self._DataTypeArr = arr.__class__
self.data = ctypes.cast(arr, ctypes.c_void_p)
else:
self._data_type = data_type
self._DataTypeArr = self._data_type * self.len
self.data = ctypes.cast(self._DataTypeArr(*seq), ctypes.c_void_p)
def __str__(self):
strings = [super().__str__()] # Python 3
#strings = [super(FFIArray, self).__str__()] # !!! Python 2 (ugly) !!!
strings.append("Type: {0:s}\nElement Type: {1:}{2:}\nElements ({3:d}):".format(
self.__class__.__name__, self._data_type,
"" if self._data_type == self.__data_type else " ({0:})".format(self.__data_type),
self.len))
arr_data = self._DataTypeArr.from_address(self.data)
for idx, item in enumerate(arr_data):
strings.append(" {0:d}: {1:}".format(idx, item))
return "\n".join(strings) + "\n"
def to_np(self):
arr_data = self._DataTypeArr.from_address(self.data)
if self._data_type in self._special_np_types_mapping:
dtype = np.dtype(self._special_np_types_mapping[self._data_type] + str(max(len(item) for item in arr_data)))
np_arr = np.empty(self.len, dtype=dtype)
for idx, item in enumerate(arr_data):
np_arr[idx] = item
return np_arr
else:
return np.ctypeslib.as_array(arr_data)
class Coordinates(ctypes.Structure):
_fields_ = [
("lat", ctypes.c_double),
("lon", ctypes.c_double)
]
def __str__(self):
return "Latitude: {0:.3f}, Longitude: {1:.3f}".format(self.lat, self.lon)
def main():
coord_list = [Coordinates(i + 1, i * 2) for i in range(4)]
s0 = b"foo"
s1 = b"bar (beyond all recognition)" # To avoid having 2 equal strings
word_list = [s0, s1]
coord_array0 = FFIArray(coord_list, data_type=Coordinates)
print(coord_array0)
word_array0 = FFIArray(word_list, data_type=ctypes.c_char_p)
print(word_array0)
print("to_np: {0:}\n".format(word_array0.to_np()))
np_array_src = np.array([0, -3.141593, 2.718282, -0.577, 0.618])
float_array0 = FFIArray.from_param(np_array_src, data_type=None)
print(float_array0)
np_array_dst = float_array0.to_np()
print("to_np: {0:}".format(np_array_dst))
print("Equal np arrays: {0:}\n".format(all(np_array_src == np_array_dst)))
empty_array0 = FFIArray.from_param([])
print(empty_array0)
if __name__ == "__main__":
print("Python {0:s} {1:d}bit on {2:s}\n".format(" ".join(item.strip() for item in sys.version.split("\n")), 64 if sys.maxsize > 0x100000000 else 32, sys.platform))
print("NumPy: {0:s}\n".format(np.version.version))
main()
print("\nDone.")
输出:
[cfati@CFATI-5510-0:e:\Work\Dev\StackOverflow\q058049957]> "e:\Work\Dev\VEnvs\py_064_03.07.03_test0\Scripts\python.exe" code04.py
Python 3.7.3 (v3.7.3:ef4ec6ed12, Mar 25 2019, 22:22:05) [MSC v.1916 64 bit (AMD64)] 64bit on win32
NumPy: 1.16.2
<__main__.FFIArray object at 0x000002484A2265C8>
Type: FFIArray
Element Type: <class '__main__.Coordinates'>
Elements (4):
0: Latitude: 1.000, Longitude: 0.000
1: Latitude: 2.000, Longitude: 2.000
2: Latitude: 3.000, Longitude: 4.000
3: Latitude: 4.000, Longitude: 6.000
<__main__.FFIArray object at 0x000002484A2267C8>
Type: FFIArray
Element Type: <class 'ctypes.c_char_p'>
Elements (2):
0: b'foo'
1: b'bar (beyond all recognition)'
to_np: [b'foo' b'bar (beyond all recognition)']
<__main__.FFIArray object at 0x000002484A2264C8>
Type: FFIArray
Element Type: <class 'ctypes.c_double'> (None)
Elements (5):
0: 0.0
1: -3.141593
2: 2.718282
3: -0.577
4: 0.618
to_np: [ 0. -3.141593 2.718282 -0.577 0.618 ]
Equal np arrays: True
<__main__.FFIArray object at 0x000002484A226848>
Type: FFIArray
Element Type: <class 'ctypes.c_void_p'>
Elements (0):
Done.
当然,这是可能性之一。另一个可能涉及(弃用)[SciPy.Docs]: numpy.char.ray用法,但我不想让事情过于复杂(没有明确的场景)。
添加了FFIArray到np数组转换(我不是np专家,所以对于一个np专家来说可能看起来很麻烦)。字符串需要特殊处理。
没有发布新的代码版本(因为更改不是很重要),而是在以前的版本上工作。