2013/2/28 Stefan Behnel <[email protected]>:
>> This allows to write unicode text parsing code almost at C speed
>> mostly in python (+ .pxd defintions).
>
> I suggest simply adding a constant flag argument to the existing function
> that states if checking should be done or not. Inlining will let the C
> compiler drop the corresponding code, which may or may nor make it a little
> faster.
It would be great.
To be sure I change the tests:
unicode_index.h
-----------------------
#include "unicodeobject.h"
static inline Py_UCS4 unicode_char(PyObject* ustring, Py_ssize_t i);
static inline Py_UCS4 unicode_char(PyObject* ustring, Py_ssize_t i) {
#if CYTHON_PEP393_ENABLED
if (PyUnicode_READY(ustring) < 0) return (Py_UCS4)-1;
#endif
return __Pyx_PyUnicode_READ_CHAR(ustring, i);
}
static inline Py_UCS4 unicode_char2(PyObject* ustring, Py_ssize_t i, int flag);
static inline Py_UCS4 unicode_char2(PyObject* ustring, Py_ssize_t i, int flag) {
Py_ssize_t length;
#if CYTHON_PEP393_ENABLED
if (PyUnicode_READY(ustring) < 0) return (Py_UCS4)-1;
#endif
if (flag) {
length = __Pyx_PyUnicode_GET_LENGTH(ustring);
if ((0 <= i) & (i < length)) {
return __Pyx_PyUnicode_READ_CHAR(ustring, i);
} else if ((-length <= i) & (i < 0)) {
return __Pyx_PyUnicode_READ_CHAR(ustring, i + length);
} else {
PyErr_SetString(PyExc_IndexError, "string index out of range");
return (Py_UCS4)-1;
}
} else {
return __Pyx_PyUnicode_READ_CHAR(ustring, i);
}
}
unicode_index.pyx
--------------------------
cdef extern from 'unicode_index.h':
inline Py_UCS4 unicode_char(unicode ustring, int i)
inline Py_UCS4 unicode_char2(unicode ustring, int i, int flag)
cdef unicode text = u"abcdefghigklmnopqrstuvwxyzabcdefghigklmnopqrstuvwxyz"
cdef long f_1(unicode text):
cdef int i, j
cdef int n = len(text)
cdef Py_UCS4 ch
cdef long S = 0
for j in range(1000000):
for i in range(n):
ch = text[i]
S += <int>ch * j
return S
cdef long f_2(unicode text):
cdef int i, j
cdef int n = len(text)
cdef Py_UCS4 ch
cdef long S = 0
for j in range(1000000):
for i in range(n):
ch = unicode_char(text, i)
S += <int>ch * j
return S
cdef long f_3(unicode text):
cdef int i, j
cdef int n = len(text)
cdef Py_UCS4 ch
cdef long S = 0
for j in range(1000000):
for i in range(n):
ch = unicode_char2(text, i, 0)
S += <int>ch * j
return S
def test_1():
f_1(text)
def test_2():
f_2(text)
def test_3():
f_3(text)
Here are timings:
(py33) zbook:mytests $ python3.3 -m timeit -n 50 -r 5 -s "from
mytests.unicode_index import test_1" "test_1()"
50 loops, best of 5: 152 msec per loop
(py33) zbook:mytests $ python3.3 -m timeit -n 50 -r 5 -s "from
mytests.unicode_index import test_2" "test_2()"
50 loops, best of 5: 86.5 msec per loop
(py33) zbook:mytests $ python3.3 -m timeit -n 50 -r 5 -s "from
mytests.unicode_index import test_3" "test_3()"
50 loops, best of 5: 86.5 msec per loop
So your suggestion would be preferable.
_______________________________________________
cython-devel mailing list
[email protected]
http://mail.python.org/mailman/listinfo/cython-devel
