Stowage/cpython
2
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-10-31 05:31:20 +00:00
Code Issues Projects Releases Packages Wiki Activity

Optimize _PyUnicode_AsKind() for UCS1->UCS4 and UCS2->UCS4

Browse source 
* Ensure that the input string is ready
 * Raise a ValueError instead of of a fatal error
This commit is contained in:
Victor Stinner 2011-10-02 01:00:40 +02:00
parent 7a48ff7e06
commit bc603d12b7
1 changed files with 43 additions and 25 deletions
Download patch file Download diff file Expand all files Collapse all files

68
Objects/unicodeobject.c
View file

@ -1264,43 +1264,61 @@ PyUnicode_Copy(PyObject *unicode)
}
/* Widen Unicode objects to larger buffers.
Return NULL if the string is too wide already. */
/* Widen Unicode objects to larger buffers. Don't write terminating null
character. Return NULL on error. */
void*
_PyUnicode_AsKind(PyObject *s, unsigned int kind)
{
Py_ssize_t i;
Py_ssize_t len = PyUnicode_GET_LENGTH(s);
void *d = PyUnicode_DATA(s);
unsigned int skind = PyUnicode_KIND(s);
if (PyUnicode_KIND(s) >= kind) {
Py_ssize_t len;
void *result;
unsigned int skind;
if (PyUnicode_READY(s))
return NULL;
len = PyUnicode_GET_LENGTH(s);
skind = PyUnicode_KIND(s);
if (skind >= kind) {
PyErr_SetString(PyExc_RuntimeError, "invalid widening attempt");
return NULL;
}
switch(kind) {
case PyUnicode_2BYTE_KIND: {
Py_UCS2 *result = PyMem_Malloc(PyUnicode_GET_LENGTH(s) * sizeof(Py_UCS2));
if (!result) {
PyErr_NoMemory();
return 0;
}
for (i = 0; i < len; i++)
result[i] = ((Py_UCS1*)d)[i];
case PyUnicode_2BYTE_KIND:
result = PyMem_Malloc(len * sizeof(Py_UCS2));
if (!result)
return PyErr_NoMemory();
assert(skind == PyUnicode_1BYTE_KIND);
_PyUnicode_CONVERT_BYTES(
Py_UCS1, Py_UCS2,
PyUnicode_1BYTE_DATA(s),
PyUnicode_1BYTE_DATA(s) + len,
result);
return result;
}
case PyUnicode_4BYTE_KIND: {
Py_UCS4 *result = PyMem_Malloc(PyUnicode_GET_LENGTH(s) * sizeof(Py_UCS4));
if (!result) {
PyErr_NoMemory();
return 0;
case PyUnicode_4BYTE_KIND:
result = PyMem_Malloc(len * sizeof(Py_UCS4));
if (!result)
return PyErr_NoMemory();
if (skind == PyUnicode_2BYTE_KIND) {
_PyUnicode_CONVERT_BYTES(
Py_UCS2, Py_UCS4,
PyUnicode_2BYTE_DATA(s),
PyUnicode_2BYTE_DATA(s) + len,
result);
}
else {
assert(skind == PyUnicode_1BYTE_KIND);
_PyUnicode_CONVERT_BYTES(
Py_UCS1, Py_UCS4,
PyUnicode_1BYTE_DATA(s),
PyUnicode_1BYTE_DATA(s) + len,
result);
}
for (i = 0; i < len; i++)
result[i] = PyUnicode_READ(skind, d, i);
return result;
default:
break;
}
}
Py_FatalError("invalid kind");
PyErr_SetString(PyExc_ValueError, "invalid kind");
return NULL;
}