快速字符串数组 - Cython

Question

Having following hypothetical code:

cdef extern from "string.h":
    int strcmp(char* str1, char* str2)

def foo(list_str1, list_str2):
    cdef unsigned int i, j
    c_arr1 = ??
    c_arr2 = ??
    for i in xrange(len(list_str1)):
        for j in xrange(len(list_str2)):
            if not strcmp(c_arr1[i], c_arr2[j]):
                do some funny stuff

is there some way how to convert the lists to c arrays?

I have read and tried Cython - converting list of strings to char ** but that only throws errors.

Answer 1

Try following code. to_cstring_array function in the following code is what you want.

from libc.stdlib cimport malloc, free
from libc.string cimport strcmp
from cpython.string cimport PyString_AsString

cdef char ** to_cstring_array(list_str):
    cdef char **ret = <char **>malloc(len(list_str) * sizeof(char *))
    for i in xrange(len(list_str)):
        ret[i] = PyString_AsString(list_str[i])
    return ret

def foo(list_str1, list_str2):
    cdef unsigned int i, j
    cdef char **c_arr1 = to_cstring_array(list_str1)
    cdef char **c_arr2 = to_cstring_array(list_str2)

    for i in xrange(len(list_str1)):
        for j in xrange(len(list_str2)):
            if i != j and strcmp(c_arr1[i], c_arr2[j]) == 0:
                print i, j, list_str1[i]
    free(c_arr1)
    free(c_arr2)

foo(['hello', 'python', 'world'], ['python', 'rules'])

Answer 2

If you're on Python 3, here's an update to @falsetru's answer (untested on Python 2).

cdef extern from "Python.h":
    char* PyUnicode_AsUTF8(object unicode)

from libc.stdlib cimport malloc, free
from libc.string cimport strcmp

cdef char ** to_cstring_array(list_str):
    cdef char **ret = <char **>malloc(len(list_str) * sizeof(char *))
    for i in xrange(len(list_str)):
        ret[i] = PyUnicode_AsUTF8(list_str[i])
    return ret

def foo(list_str1, list_str2):
    cdef unsigned int i, j
    cdef char **c_arr1 = to_cstring_array(list_str1)
    cdef char **c_arr2 = to_cstring_array(list_str2)

    for i in range(len(list_str1)):
        for j in range(len(list_str2)):
            if i != j and strcmp(c_arr1[i], c_arr2[j]) == 0:
                print(i, j, list_str1[i])
    free(c_arr1)
    free(c_arr2)

foo(['hello', 'python', 'world'], ['python', 'rules'])

---

Warning: The pointer returned by PyUnicode_AsUTF8 is cached in the parent unicode-object. Which has two consequences:

1. this pointer is only valid as long as the parent unicode-object is alive. Accessing it afterwards leads to undefined behavior (eg possible segmentation fault).
2. The caller of the PyUnicode_AsUTF8 isn't responsible for the freeing the memory.