Fix for astype('S') string truncate issue

Calling astype('S') for an array of string objects results in a string array where dtype='S64', even if the original string objects are longer than 64 characters. Add call to GetParamsFromObject() to determine maximum string object length, and use that as string dtype size.

2 files changed, 33 insertions, 0 deletions

diff --git a/numpy/core/src/multiarray/convert_datatype.c b/numpy/core/src/multiarray/convert_datatype.c
index e1483f4e1..457844618 100644
--- a/numpy/core/src/multiarray/convert_datatype.c
+++ b/numpy/core/src/multiarray/convert_datatype.c
@@ -141,6 +141,12 @@ PyArray_AdaptFlexibleDType(PyObject *data_obj, PyArray_Descr *data_dtype,
 {
     PyArray_DatetimeMetaData *meta;
     int flex_type_num;
+    PyArrayObject *arr = NULL, *ret;
+    PyArray_Descr *dtype = NULL;
+    int ndim = 0;
+    npy_intp dims[NPY_MAXDIMS];
+    PyObject *list = NULL;
+    int result;
 
     if (*flex_dtype == NULL) {
         if (!PyErr_Occurred()) {
@@ -220,6 +226,26 @@ 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. */
+                        list = PyArray_ToList(data_obj);
+                        if (list != NULL) {
+                            result = PyArray_GetArrayParamsFromObject(
+                                list,
+                                flex_dtype,
+                                0, &dtype,
+                                &ndim, dims, &arr, NULL);
+                            if (result == 0 && dtype != NULL) {
+                                size = dtype->elsize;
+                            }
+                            Py_DECREF(list);
+                        }
+                    }
                     break;
                 case NPY_STRING:
                 case NPY_VOID:
diff --git a/numpy/core/tests/test_api.py b/numpy/core/tests/test_api.py
index 1d4b93b0f..388c23d3a 100644
--- a/numpy/core/tests/test_api.py
+++ b/numpy/core/tests/test_api.py
@@ -89,6 +89,13 @@ def test_array_astype():
     assert_(not (a is b))
     assert_(type(b) != np.matrix)
 
+    # Make sure converting from string object to fixed length string
+    # does not truncate.
+    a = np.array(['a'*100], dtype='O')
+    b = a.astype('S')
+    assert_equal(a, b)
+    assert_equal(b.dtype, np.dtype('S100'))
+
 def test_copyto_fromscalar():
     a = np.arange(6, dtype='f4').reshape(2,3)