mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-11-11 14:44:57 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 8

more unicode tweaks: make unichr(0xdddddddd) behave like u"\Udddddddd"

Browse source 
wrt surrogates.  (this extends the valid range from 65535 to 1114111)
This commit is contained in:
Fredrik Lundh 2001-06-26 20:01:56 +00:00
parent 5b97935604
commit 0dcf67e56d
1 changed files with 17 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

19
Python/bltinmodule.c
View file

@ -308,23 +308,34 @@ static PyObject *
builtin_unichr(PyObject *self, PyObject *args) builtin_unichr(PyObject *self, PyObject *args)
{ {
long x; long x;
Py_UNICODE s[1]; Py_UNICODE s[2];
if (!PyArg_ParseTuple(args, "l:unichr", &x)) if (!PyArg_ParseTuple(args, "l:unichr", &x))
return NULL; return NULL;
if (x < 0 || x >= 65536) {
if (x < 0 || x > 0x10ffff) {
PyErr_SetString(PyExc_ValueError, PyErr_SetString(PyExc_ValueError,
"unichr() arg not in range(65536)"); "unichr() arg not in range(0x10ffff)");
return NULL; return NULL;
} }
if (x <= 0xffff) {
/* UCS-2 character */
s[0] = (Py_UNICODE) x; s[0] = (Py_UNICODE) x;
return PyUnicode_FromUnicode(s, 1); return PyUnicode_FromUnicode(s, 1);
} else {
/* UCS-4 character. store as two surrogate characters */
x -= 0x10000L;
s[0] = 0xD800 + (Py_UNICODE) (x >> 10);
s[1] = 0xDC00 + (Py_UNICODE) (x & 0x03FF);
return PyUnicode_FromUnicode(s, 2);
}
} }
static char unichr_doc[] = static char unichr_doc[] =
"unichr(i) -> Unicode character\n\ "unichr(i) -> Unicode character\n\
\n\ \n\
Return a Unicode string of one character with ordinal i; 0 <= i < 65536."; Return a Unicode string of one character with ordinal i; 0 <= i <= 0x10ffff.";
static PyObject * static PyObject *