FIX: Fixes the PyUnicodeObject problem in py-3.3

Previously NumPy did not compile in Python 3.3 due to the changes in PEP 393.
This patch simply calls PyUnicode_FromKindAndData() from the new Python 3.3 API
and possibly swaps the data before calling it if needed. The data in NumPy is always UCS4 and the PyUnicode_FromKindAndData() internally converts it to UCS1, UCS2 or UCS4 depending on the maximum code point.

The following tests now fail, because they produce invalid unicode in the
process (will be fixed in the next patch):

======================================================================
ERROR: Check byteorder of 0-dimensional objects
----------------------------------------------------------------------
Traceback (most recent call last):
  File "/home/ondrej/py33/lib/python3.3/site-packages/numpy/core/tests/test_unicode.py", line 277, in test_values0D
    self.assertTrue(ua[()] != ua2[()])
SystemError: invalid maximum character passed to PyUnicode_New

======================================================================
ERROR: Check byteorder of multi-dimensional objects
----------------------------------------------------------------------
Traceback (most recent call last):
  File "/home/ondrej/py33/lib/python3.3/site-packages/numpy/core/tests/test_unicode.py", line 297, in test_valuesMD
    self.assertTrue(ua[0,0,0] != ua2[0,0,0])
SystemError: invalid maximum character passed to PyUnicode_New

======================================================================
ERROR: Check byteorder of single-dimensional objects
----------------------------------------------------------------------
Traceback (most recent call last):
  File "/home/ondrej/py33/lib/python3.3/site-packages/numpy/core/tests/test_unicode.py", line 286, in test_valuesSD
    self.assertTrue(ua[0] != ua2[0])
SystemError: invalid maximum character passed to PyUnicode_New

======================================================================
ERROR: Check byteorder of 0-dimensional objects
----------------------------------------------------------------------
Traceback (most recent call last):
  File "/home/ondrej/py33/lib/python3.3/site-packages/numpy/core/tests/test_unicode.py", line 277, in test_values0D
    self.assertTrue(ua[()] != ua2[()])
SystemError: invalid maximum character passed to PyUnicode_New

======================================================================
ERROR: Check byteorder of multi-dimensional objects
----------------------------------------------------------------------
Traceback (most recent call last):
  File "/home/ondrej/py33/lib/python3.3/site-packages/numpy/core/tests/test_unicode.py", line 297, in test_valuesMD
    self.assertTrue(ua[0,0,0] != ua2[0,0,0])
SystemError: invalid maximum character passed to PyUnicode_New

======================================================================
ERROR: Check byteorder of single-dimensional objects
----------------------------------------------------------------------
Traceback (most recent call last):
  File "/home/ondrej/py33/lib/python3.3/site-packages/numpy/core/tests/test_unicode.py", line 286, in test_valuesSD
    self.assertTrue(ua[0] != ua2[0])
SystemError: invalid maximum character passed to PyUnicode_New

2 files changed, 40 insertions, 0 deletions

diff --git a/numpy/core/src/multiarray/scalarapi.c b/numpy/core/src/multiarray/scalarapi.c
index 00c71f913..0afdc1700 100644
--- a/numpy/core/src/multiarray/scalarapi.c
+++ b/numpy/core/src/multiarray/scalarapi.c
@@ -641,6 +641,40 @@ PyArray_Scalar(void *data, PyArray_Descr *descr, PyObject *base)
             itemsize = (((itemsize - 1) >> 2) + 1) << 2;
         }
     }
+#if PY_VERSION_HEX >= 0x03030000
+    if (type_num == NPY_UNICODE) {
+        PyObject *u, *args;
+        char *buffer;
+        if (swap) {
+            buffer = malloc(itemsize);
+            if (buffer == NULL) {
+                PyErr_NoMemory();
+                return NULL;
+            }
+            memcpy(buffer, data, itemsize);
+            byte_swap_vector(buffer, itemsize >> 2, 4);
+        } else {
+            buffer = data;
+        }
+        u = PyUnicode_FromKindAndData(PyUnicode_4BYTE_KIND, buffer,
+                itemsize >> 2);
+        if (swap) {
+            free(buffer);
+        }
+        if (u == NULL) {
+            return NULL;
+        }
+        args = Py_BuildValue("(O)", u);
+        if (args == NULL) {
+            Py_DECREF(u);
+            return NULL;
+        }
+        obj = type->tp_new(type, args, NULL);
+        Py_DECREF(u);
+        Py_DECREF(args);
+        return obj;
+    }
+#endif
     if (type->tp_itemsize != 0) {
         /* String type */
         obj = type->tp_alloc(type, itemsize);
@@ -672,6 +706,7 @@ PyArray_Scalar(void *data, PyArray_Descr *descr, PyObject *base)
             memcpy(destptr, data, itemsize);
             return obj;
         }
+#if PY_VERSION_HEX < 0x03030000
         else if (type_num == NPY_UNICODE) {
             /* tp_alloc inherited from Python PyBaseObject_Type */
             PyUnicodeObject *uni = (PyUnicodeObject*)obj;
@@ -743,6 +778,7 @@ PyArray_Scalar(void *data, PyArray_Descr *descr, PyObject *base)
 #endif
             return obj;
         }
+#endif // PY_VERSION_HEX < 0x03030000
         else {
             PyVoidScalarObject *vobj = (PyVoidScalarObject *)obj;
             vobj->base = NULL;
diff --git a/numpy/core/src/multiarray/scalartypes.c.src b/numpy/core/src/multiarray/scalartypes.c.src
index e547071cc..12745d720 100644
--- a/numpy/core/src/multiarray/scalartypes.c.src
+++ b/numpy/core/src/multiarray/scalartypes.c.src
@@ -2592,7 +2592,11 @@ finish:
     *((npy_@name@ *)dest) = *((npy_@name@ *)src);
 #elif @default@ == 1 /* unicode and strings */
     if (itemsize == 0) { /* unicode */
+#if PY_VERSION_HEX >= 0x03030000
+        itemsize = PyUnicode_GetLength(robj) * PyUnicode_KIND(robj);
+#else
         itemsize = ((PyUnicodeObject *)robj)->length * sizeof(Py_UNICODE);
+#endif
     }
     memcpy(dest, src, itemsize);
     /* @default@ == 2 won't get here */