Python中关于Sequence切片的下标问题详解

sequence = [1,2,3,4,5]
sequence [ilow:ihigh] # 从ilow开始到ihigh-1结束
sequence [ilow:]  # 从ilow开始直到末尾
sequence [:ihigh]  # 从头部开始直到ihigh结束
sequence [:]   # 复制整个列表

sequence = [1,2,3,4,5]
print sequence[1] # 输出2
print sequence[2] # 输出3

sequence = [1,2,3,4,5]
print sequence[15] 

### 输出 ###
Traceback (most recent call last):
 File "test.py", line 2, in <module>
 print a[20]
IndexError: list index out of range

# version: python2.7

a = [1, 2, 3, 5]
print a[10:20] # 结果会报异常吗?

>>> a = [1, 2, 3, 5]
>>> print a[10:20]
[]

>>> s = '23123123123'
>>> print s[400:2000]
''
>>> t = (1, 2, 3,4)
>>> print t[200: 1000]
()

############# 切片 ################
[root@iZ23pynfq19Z ~]# cat test.py
a = [11,2,3,4]
print a[20:30]

#结果:
[root@iZ23pynfq19Z ~]# python -m dis test.py 
 1   0 LOAD_CONST    0 (11)
    3 LOAD_CONST    1 (2)
    6 LOAD_CONST    2 (3)
    9 LOAD_CONST    3 (4)
    12 BUILD_LIST    4
    15 STORE_NAME    0 (a)

 2   18 LOAD_NAME    0 (a)
    21 LOAD_CONST    4 (20)
    24 LOAD_CONST    5 (30)
    27 SLICE+3    
    28 PRINT_ITEM   
    29 PRINT_NEWLINE  
    30 LOAD_CONST    6 (None)
    33 RETURN_VALUE 

############# 单下标取值 ################
[root@gitlab ~]# cat test2.py
a = [11,2,3,4]
print a[20]

#结果:
[root@gitlab ~]# python -m dis test2.py
 1   0 LOAD_CONST    0 (11)
    3 LOAD_CONST    1 (2)
    6 LOAD_CONST    2 (3)
    9 LOAD_CONST    3 (4)
    12 BUILD_LIST    4
    15 STORE_NAME    0 (a)

 2   18 LOAD_NAME    0 (a)
    21 LOAD_CONST    4 (20)
    24 BINARY_SUBSCR  
    25 PRINT_ITEM   
    26 PRINT_NEWLINE  
    27 LOAD_CONST    5 (None)
    30 RETURN_VALUE 

/*取自: python2.7 python/ceval.c */

// 第一步: 
PyEval_EvalFrameEx(PyFrameObject *f, int throwflag)
{
  .... // 省略n行代码
  TARGET_WITH_IMPL_NOARG(SLICE, _slice)
  TARGET_WITH_IMPL_NOARG(SLICE_1, _slice)
  TARGET_WITH_IMPL_NOARG(SLICE_2, _slice)
  TARGET_WITH_IMPL_NOARG(SLICE_3, _slice)
  _slice:
  {
   if ((opcode-SLICE) & 2)
    w = POP();
   else
    w = NULL;
   if ((opcode-SLICE) & 1)
    v = POP();
   else
    v = NULL;
   u = TOP();
   x = apply_slice(u, v, w); // 取出v: ilow, w: ihigh, 然后调用apply_slice
   Py_DECREF(u);
   Py_XDECREF(v);
   Py_XDECREF(w);
   SET_TOP(x);
   if (x != NULL) DISPATCH();
   break;
  }

 .... // 省略n行代码
}

// 第二步:
apply_slice(PyObject *u, PyObject *v, PyObject *w) /* return u[v:w] */
{
 PyTypeObject *tp = u->ob_type;  
 PySequenceMethods *sq = tp->tp_as_sequence;

 if (sq && sq->sq_slice && ISINDEX(v) && ISINDEX(w)) { // v,w的类型检查,要整型/长整型对象
  Py_ssize_t ilow = 0, ihigh = PY_SSIZE_T_MAX;
  if (!_PyEval_SliceIndex(v, &ilow))    // 将v对象再做检查, 并将其值转换出来,存给ilow
   return NULL;
  if (!_PyEval_SliceIndex(w, &ihigh))    // 同上
   return NULL;
  return PySequence_GetSlice(u, ilow, ihigh);  // 获取u对象对应的切片函数
 }
 else {
  PyObject *slice = PySlice_New(v, w, NULL);
  if (slice != NULL) {
   PyObject *res = PyObject_GetItem(u, slice);
   Py_DECREF(slice);
   return res;
  }
  else
   return NULL;
 }

// 第三步:
PySequence_GetSlice(PyObject *s, Py_ssize_t i1, Py_ssize_t i2)
{
 PySequenceMethods *m;
 PyMappingMethods *mp;

 if (!s) return null_error();

 m = s->ob_type->tp_as_sequence;
 if (m && m->sq_slice) {
  if (i1 < 0 || i2 < 0) {
   if (m->sq_length) {
    // 先做个简单的初始化, 如果左右下表小于, 将其加上sequence长度使其归为0
    Py_ssize_t l = (*m->sq_length)(s);
    if (l < 0)
     return NULL;
    if (i1 < 0)
     i1 += l;
    if (i2 < 0)
     i2 += l;
   }
  }
  // 真正调用对象的sq_slice函数, 来执行切片的操作
  return m->sq_slice(s, i1, i2);
 } else if ((mp = s->ob_type->tp_as_mapping) && mp->mp_subscript) {
  PyObject *res;
  PyObject *slice = _PySlice_FromIndices(i1, i2);
  if (!slice)
   return NULL;
  res = mp->mp_subscript(s, slice);
  Py_DECREF(slice);
  return res;
 }

 return type_error("'%.200s' object is unsliceable", s);

// 字符串对象
StringObject.c: (ssizessizeargfunc)string_slice, /*sq_slice*/

// 列表对象
ListObject.c: (ssizessizeargfunc)list_slice,  /* sq_slice */

// 元组
TupleObject.c: (ssizessizeargfunc)tupleslice,  /* sq_slice */

/* 取自ListObject.c */
static PyObject *
list_slice(PyListObject *a, Py_ssize_t ilow, Py_ssize_t ihigh)
{
 PyListObject *np;
 PyObject **src, **dest;
 Py_ssize_t i, len;
 if (ilow < 0)
  ilow = 0;
 else if (ilow > Py_SIZE(a))    // 如果ilow大于a长度, 那么重新赋值为a的长度
  ilow = Py_SIZE(a);
 if (ihigh < ilow)  
  ihigh = ilow;
 else if (ihigh > Py_SIZE(a))    // 如果ihigh大于a长度, 那么重新赋值为a的长度 
  ihigh = Py_SIZE(a);
 len = ihigh - ilow;
 np = (PyListObject *) PyList_New(len); // 创建一个ihigh - ilow的新列表对象
 if (np == NULL)
  return NULL;

 src = a->ob_item + ilow;
 dest = np->ob_item;
 for (i = 0; i < len; i++) {    // 将a处于该范围内的成员, 添加到新列表对象
  PyObject *v = src[i];
  Py_INCREF(v);
  dest[i] = v;
 }
 return (PyObject *)np;
}