[PyOV] Allow replacing of invalid bytes in string-based data (openvin…

…otoolkit#21761) * [PyOV] Allow replacing of invalid bytes in string-based data * Fix linter
vishniakov-nikolai · Dec 19, 2023 · 712e374 · 712e374
1 parent 27c9ca7
commit 712e374
Show file tree

Hide file tree

Showing 2 changed files with 11 additions and 1 deletion.
diff --git a/src/bindings/python/src/pyopenvino/core/common.cpp b/src/bindings/python/src/pyopenvino/core/common.cpp
@@ -153,7 +153,7 @@ py::array string_array_from_tensor(ov::Tensor&& t) {
     auto data = t.data<std::string>();
     py::list _list;
     for (size_t i = 0; i < t.get_size(); ++i) {
-        PyObject* _unicode_obj = PyUnicode_DecodeUTF8(&data[i][0], data[i].length(), "strict");
+        PyObject* _unicode_obj = PyUnicode_DecodeUTF8(&data[i][0], data[i].length(), "replace");
         _list.append(_unicode_obj);
         Py_XDECREF(_unicode_obj);
     }

diff --git a/src/bindings/python/tests/test_runtime/test_tensor_string.py b/src/bindings/python/tests/test_runtime/test_tensor_string.py
@@ -254,3 +254,13 @@ def test_empty_tensor_populate(init_type, init_shape, string_data, data_getter):
     check_bytes_based(tensor, _string_data, to_flat=True)
     # Decoded:
     check_string_based(tensor, _string_data, to_flat=True)
+
+
+def test_invalid_bytes_replaced():
+    string_data = np.array(b"\xe2\x80")
+    tensor = ov.Tensor(string_data)
+
+    # Encoded:
+    check_bytes_based(tensor, string_data, to_flat=True)
+    # Decoded:
+    check_string_based(tensor, np.char.decode(string_data, encoding="utf=8", errors="replace"), to_flat=True)