Add support for unicode strings

2 files changed, 29 insertions, 13 deletions

diff --git a/numpy/core/src/multiarray/convert_datatype.c b/numpy/core/src/multiarray/convert_datatype.c
index 457844618..cb1caec08 100644
--- a/numpy/core/src/multiarray/convert_datatype.c
+++ b/numpy/core/src/multiarray/convert_datatype.c
@@ -226,22 +226,33 @@ PyArray_AdaptFlexibleDType(PyObject *data_obj, PyArray_Descr *data_dtype,
                     break;
                 case NPY_OBJECT:
                     size = 64;
-                    /* If we're adapting a string dtype for an array of string
-                       objects, call GetArrayParamsFromObject to figure out
-                       maximum string size, and use that as new dtype size. */
-                    if (flex_type_num == NPY_STRING && data_obj != NULL) {
-                        /* Convert data array to list of objects since
-                           GetArrayParamsFromObject won't iterator through
-                           items in an array. */
+                    /* 
+                     * If we're adapting a string dtype for an array of string
+                     * objects, call GetArrayParamsFromObject to figure out
+                     * maximum string size, and use that as new dtype size.
+                     */
+                    if ((flex_type_num == NPY_STRING ||
+                            flex_type_num == NPY_UNICODE) &&
+                            data_obj != NULL) {
+                        /*
+                         * Convert data array to list of objects since
+                         * GetArrayParamsFromObject won't iterator through
+                         * items in an array.
+                         */
                         list = PyArray_ToList(data_obj);
                         if (list != NULL) {
                             result = PyArray_GetArrayParamsFromObject(
-                                list,
-                                flex_dtype,
-                                0, &dtype,
-                                &ndim, dims, &arr, NULL);
+                                    list,
+                                    flex_dtype,
+                                    0, &dtype,
+                                    &ndim, dims, &arr, NULL);
                             if (result == 0 && dtype != NULL) {
-                                size = dtype->elsize;
+                                if (flex_type_num == NPY_UNICODE) {
+                                    size = dtype->elsize / 4;
+                                }
+                                else {
+                                    size = dtype->elsize;
+                                }
                             }
                             Py_DECREF(list);
                         }
diff --git a/numpy/core/tests/test_api.py b/numpy/core/tests/test_api.py
index 388c23d3a..ce4658fd4 100644
--- a/numpy/core/tests/test_api.py
+++ b/numpy/core/tests/test_api.py
@@ -6,6 +6,7 @@ import numpy as np
 from numpy.testing import *
 from numpy.testing.utils import WarningManager
 import warnings
+from numpy.compat import sixu
 
 # Switch between new behaviour when NPY_RELAXED_STRIDES_CHECKING is set.
 NPY_RELAXED_STRIDES_CHECKING = np.ones((10,1), order='C').flags.f_contiguous
@@ -91,10 +92,14 @@ def test_array_astype():
 
     # Make sure converting from string object to fixed length string
     # does not truncate.
-    a = np.array(['a'*100], dtype='O')
+    a = np.array([b'a'*100], dtype='O')
     b = a.astype('S')
     assert_equal(a, b)
     assert_equal(b.dtype, np.dtype('S100'))
+    a = np.array([sixu('a')*100], dtype='O')
+    b = a.astype('U')
+    assert_equal(a, b)
+    assert_equal(b.dtype, np.dtype('U100'))
 
 def test_copyto_fromscalar():
     a = np.arange(6, dtype='f4').reshape(2,3)