如何将python / cython unicode字符串转换为长整数数组，做levenshtein编辑距离[复制]

#---------------------------------------------------------------------------
cdef extern from "stdlib.h":
  ctypedef unsigned int size_t
  size_t strlen(char *s)
  void *malloc(size_t size)
  void *calloc(size_t n, size_t size)
  void free(void *ptr)
  int strcmp(char *a, char *b)
  char * strcpy(char *a, char *b)

#---------------------------------------------------------------------------
cdef extern from "Python.h":
  object PyTuple_GET_ITEM(object, int)
  void Py_INCREF(object)

#---------------------------------------------------------------------------
cdef inline size_t imin(int a, int b, int c):
  if a < b:
    if c < a:
      return c
    return a
  if c < b:
    return c
  return b

#---------------------------------------------------------------------------
cpdef int editdistance( char *a, char *b ):
  """Given two byte strings ``a`` and ``b``, return their absolute Damerau-
  Levenshtein distance. Each deletion, insertion, substitution, and
  transposition is counted as one difference, so the edit distance between
  ``abc`` and ``ab``, ``abcx``, ``abx``, ``acb``, respectively, is ``1``."""

  #.........................................................................
  if strcmp( a, b ) == 0: return 0
  #.........................................................................
  cdef int    alen    = strlen( a )
  cdef int    blen    = strlen( b )
  cdef int    R
  cdef char   *ctmp
  cdef size_t i
  cdef size_t j
  cdef size_t achr
  cdef size_t bchr
  #.........................................................................
  if alen > blen:
    ctmp = a;
    a = b;
    b = ctmp;
    alen, blen = blen, alen
  #.........................................................................
  cdef char   *m1     = <char *>calloc(   blen + 2,    sizeof( char ) )
  cdef char   *m2     = <char *>calloc(   blen + 2,    sizeof( char ) )
  cdef char   *m3     = <char *>malloc( ( blen + 2 ) * sizeof( char ) )
  #.........................................................................
  for i from 0 <= i <= blen:
    m2[ i ] = i
  #.........................................................................
  for i from 1 <= i <= alen:
    m1[ 0 ] =    i + 1
    achr    = a[ i - 1 ]
    for j from 1 <= j <= blen:
      bchr = b[ j- 1 ]
      if achr == bchr:
        m1[ j ] = m2[ j - 1 ]
      else:
        m1[ j ] = 1 + imin( m1[ j - 1 ], m2[ j - 1 ], m2[ j ] )
      if i != 1 and j != 1 and achr == b[ j - 2 ] and bchr == a[ i - 2 ]:
        m1[ j ] = m3[ j - 1 ]
    #.......................................................................
    m1, m2 = m2, m1
    strcpy( m3, m2 )
  #.........................................................................
  R = <int>m2[ blen ]
  #.........................................................................
  # cleanup:
  free( m3 )
  free( m1 )
  free( m2 )
  #.........................................................................
  return R

bytes

unsigned int

char *m1

char *m1