Fix so that string and unicode types don't print NULL bytes

3 files changed, 53 insertions, 9 deletions

diff --git a/numpy/core/src/arrayobject.c b/numpy/core/src/arrayobject.c
index f79e78aa4..0257fe476 100644
--- a/numpy/core/src/arrayobject.c
+++ b/numpy/core/src/arrayobject.c
@@ -4391,7 +4391,7 @@ array_descr_set(PyArrayObject *self, PyObject *arg)
 
         if (!(PyArray_DescrConverter(arg, &newtype)) ||
             newtype == NULL) {
-                PyErr_SetString(PyExc_TypeError, "invalid type for array");
+                PyErr_SetString(PyExc_TypeError, "invalid data-type for array");
 		return -1;
         }
 	if (newtype->type_num == PyArray_OBJECT || \
diff --git a/numpy/core/src/arraytypes.inc.src b/numpy/core/src/arraytypes.inc.src
index a973a9dac..4fdb2f99b 100644
--- a/numpy/core/src/arraytypes.inc.src
+++ b/numpy/core/src/arraytypes.inc.src
@@ -35,12 +35,12 @@ _getNAN(void) {
 #ifdef NAN
         return NAN;
 #else
-        double mul = 1e100;
-        double tmp = 0.0;
-        double pinf=0;
         static double nan=0;
         
         if (nan == 0) {
+		double mul = 1e100;
+		double tmp = 0.0;
+		double pinf=0;
                 pinf = mul;
                 for (;;) {
                         pinf *= mul;
@@ -225,13 +225,16 @@ UNICODE_getitem(char *ip, PyArrayObject *ap)
 {
 	PyObject *obj;
 	size_t size = sizeof(Py_UNICODE);
+	int mysize;
+	Py_UNICODE *dptr;
 
-	
-	obj = PyUnicode_FromUnicode((const Py_UNICODE *)ip, 
-				    ap->descr->elsize / size);
+	mysize = ap->descr->elsize / size;
+	dptr = (Py_UNICODE *)ip + mysize-1;
+	while(mysize > 0 && *dptr-- == 0) mysize--;
+	obj = PyUnicode_FromUnicode((const Py_UNICODE *)ip, mysize);
 	if (!PyArray_ISNOTSWAPPED(ap) && (obj != NULL)) {
 		byte_swap_vector(PyUnicode_AS_UNICODE(obj),
-				 ap->descr->elsize / size, size);
+				 mysize, size);
 	}
 	return obj;
 }
@@ -1861,7 +1864,7 @@ PyArray_DescrFromType(int type)
 	}
 	if (ret==NULL) {
 		PyErr_SetString(PyExc_ValueError, 
-				"Invalid type for array"); 
+				"Invalid data-type for array"); 
 	}
 	else Py_INCREF(ret);
 	return ret;
diff --git a/numpy/core/src/scalartypes.inc.src b/numpy/core/src/scalartypes.inc.src
index 2e1e7f1d1..7a39d0ad1 100644
--- a/numpy/core/src/scalartypes.inc.src
+++ b/numpy/core/src/scalartypes.inc.src
@@ -530,6 +530,41 @@ format_longdouble(char *buf, size_t buflen, longdouble val, int precision)
         }
 }
 
+/* over-ride repr and str of array-scalar strings and unicode to 
+   remove NULL bytes and then call the corresponding functions 
+   of string and unicode. 
+ */
+
+/**begin repeat
+#name=string*2,unicode*2#
+#form=(repr,str)*2#
+#Name=String*2,Unicode*2#
+#NAME=STRING*2,UNICODE*2#
+#extra=AndSize*2,,#
+#type=char*2, Py_UNICODE*2#
+*/
+static PyObject *
+@name@type_@form@(PyObject *self)
+{
+	const @type@ *dptr, *ip;
+	int len;
+	PyObject *new;
+	PyObject *ret;
+
+	ip = dptr = Py@Name@_AS_@NAME@(self);
+	len = Py@Name@_GET_SIZE(self);
+	dptr += len-1;
+	while(len > 0 && *dptr-- == 0) len--;
+	new = Py@Name@_From@Name@@extra@(ip, len);
+	if (new == NULL) return PyString_FromString("");
+	ret = Py@Name@_Type.tp_@form@(new);
+	Py_DECREF(new);
+	return ret;
+}
+/**end repeat**/
+
+
+
 #if SIZEOF_LONGDOUBLE == SIZEOF_DOUBLE
 #define PREC_REPR 15
 #define PREC_STR 15
@@ -2133,6 +2168,12 @@ initialize_numeric_types(void)
 
 	PyStringArrType_Type.tp_alloc = NULL;
 	PyStringArrType_Type.tp_free = NULL;
+	
+	PyStringArrType_Type.tp_repr = stringtype_repr;
+	PyStringArrType_Type.tp_str = stringtype_str;
+
+	PyUnicodeArrType_Type.tp_repr = unicodetype_repr;
+	PyUnicodeArrType_Type.tp_str = unicodetype_str;
 
 	PyVoidArrType_Type.tp_methods = voidtype_methods;
 	PyVoidArrType_Type.tp_getset = voidtype_getsets;