homepage

# Bug
# ---
# 
# Py_UNICODE *
# PyUnicode_AsUnicodeAndSize(PyObject *unicode, Py_ssize_t *size)
# {
# ...
# #endif
# wchar_t *w;
# wchar_t *wchar_end;
# 
# ...
# 1 _PyUnicode_WSTR(unicode) = (wchar_t *) PyObject_MALLOC(sizeof(wchar_t) *
# (_PyUnicode_LENGTH(unicode) + 1));
# ...
# w = _PyUnicode_WSTR(unicode);
# 2 wchar_end = w + _PyUnicode_LENGTH(unicode);
# 
# if (PyUnicode_KIND(unicode) == PyUnicode_1BYTE_KIND) {
# one_byte = PyUnicode_1BYTE_DATA(unicode);
# 3 for (; w < wchar_end; ++one_byte, ++w)
# *w = *one_byte;
# /* null-terminate the wstr */
# 4 *w = 0;
# }
# 
# 1. if length(unicode)==2**30-1, then malloced buffer has size equal to 
# 4*(2^30-1+1)=2^32 == 0 (modulo 2^32)
# 2. wchar_end is equal to w-4 because of pointer arithmetic (nonexplicit 
# multiplication by 4)
# 3. w > wchar_end, so we don't enter the loop
# 4. 4 byte write to a 0 size buffer
# 
# GDB output
# ----------
# 
# 3860 _PyUnicode_WSTR(unicode) = (wchar_t *) PyObject_MALLOC(sizeof(wchar_t) *
# ...
# (gdb) print sizeof(wchar_t)*(((PyASCIIObject*)(unicode))->length+1)
# 21ドル = 0
# ...
# (gdb) n
# 3868 w = _PyUnicode_WSTR(unicode);
# (gdb) n
# 3869 wchar_end = w + _PyUnicode_LENGTH(unicode);
# (gdb) n
# 3871 if (PyUnicode_KIND(unicode) == PyUnicode_1BYTE_KIND) {
# (gdb) print w
# 22ドル = 0x805fc028 L"\xfbfbfbfb\xced00000"
# (gdb) print wchar_end
# 23ドル = 0x805fc024 L"\xfbfbfb6f\xfbfbfbfb\xced00000"
# ...
# 3876 *w = 0;
# 
# )
# OS info
# -------
# 
# % ./python -V
# Python 3.4.1
# 
# % uname -a
# Linux ubuntu 3.8.0-29-generic #42~precise1-Ubuntu SMP Wed Aug 14 15:31:16 UTC 2013 i686 i686 i386 GNU/Linux
 
import locale
s='a'*(2**30-1)
locale.strxfrm(s)