Looking into IndexNode class in ExprNode.py I have seen a possibility
for addition of more fast code path for unicode[index] as it done in
method `generate_setitem_code` in case of lists.
This is files for evaluation of performance difference:
#### unicode_index.h
/* This is striped version of __Pyx_GetItemInt_Unicode_Fast */
#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);
}
##### unicode_index.pyx
# coding: utf-8
cdef extern from 'unicode_index.h':
inline Py_UCS4 unicode_char(unicode ustring, int i)
cdef unicode text = u"abcdefghigklmnopqrstuvwxyzabcdefghigklmnopqrstuvwxyz"
def f_1(unicode text):
cdef int i, j
cdef int n = len(text)
cdef Py_UCS4 ch
for j from 0<=j<=1000000:
for i from 0<=i<=n-1:
ch = text[i]
def f_2(unicode text):
cdef int i, j
cdef int n = len(text)
cdef Py_UCS4 ch
for j from 0<=j<=1000000:
for i from 0<=i<=n-1:
ch = unicode_char(text, i)
def test_1():
f_1(text)
def test_2():
f_2(text)
Timing results:
(py33) zbook:mytests $ python3.3 -m timeit -n 100 -r 10 -s "from
mytests.unicode_index import test_1" "test_1()"
100 loops, best of 10: 89 msec per loop
(py33) zbook:mytests $ python3.3 -m timeit -n 100 -r 10 -s "from
mytests.unicode_index import test_2" "test_2()"
100 loops, best of 10: 46.1 msec per loop
in setup.py globally:
"boundscheck": False
"wraparound": False
"nonecheck": False
Zaur Shibzukhov
_______________________________________________
cython-devel mailing list
cython-devel@python.org
http://mail.python.org/mailman/listinfo/cython-devel
