# unicode_repr(PyObject *unicode)
# {
#     ...
# 1   isize = PyUnicode_GET_LENGTH(unicode);
#     idata = PyUnicode_DATA(unicode);
# 
#     /* Compute length of output, quote characters, and
#        maximum character */
#     osize = 0;
#     ...
#     for (i = 0; i < isize; i++) {
#         Py_UCS4 ch = PyUnicode_READ(ikind, idata, i);
#         switch (ch) {
#         ...
#         default:
#             /* Fast-path ASCII */
#             if (ch < ' ' || ch == 0x7f)
# 2               osize += 4; /* \xHH */ 
#             ...
#         }
#     }
# 
#     ...
# 3   repr = PyUnicode_New(osize, max);
#     ...
#         for (i = 0, o = 1; i < isize; i++) {
#             Py_UCS4 ch = PyUnicode_READ(ikind, idata, i);
#             ...
#                 else {
# 4                   PyUnicode_WRITE(okind, odata, o++, ch);
#                 }
#             }
#         }
#     }
#     /* Closing quote already added at the beginning */
# 5   assert(_PyUnicode_CheckConsistency(repr, 1));
#     return repr;
# }
# 
# 1. isize=2^30+1
# 2. osize=isize*4=4
# 3. allocated buffer is too small
# 4. heap overflow
# 5. this assert will likely fail, since there is a good chance the allocated
#    buffer is just before the huge one, so the huge one will overwrite itself.

New changeset 8ba7e5f43952 by Benjamin Peterson in branch '3.3':
prevent overflow in unicode_repr (closes #22520)
https://hg.python.org/cpython/rev/8ba7e5f43952

New changeset 6f54dfa675eb by Benjamin Peterson in branch '3.4':
merge 3.3 (#22520)
https://hg.python.org/cpython/rev/6f54dfa675eb

New changeset 245d9679cd5b by Benjamin Peterson in branch 'default':
merge 3.4 (#22520)
https://hg.python.org/cpython/rev/245d9679cd5b

It would be nice to add a bigmem test to check that repr('\x00'*(2**30+1)) doesn't crash anymore.

As Serhiy has noted on other bugs, the fact that the tests must be restricted to 32-bits limits their usefulness unfortunately.