catch segfault on read

Author: alimanfoo

zarr/core.py

@@ -1570,7 +1570,8 @@ def _chunk_getitem(self, chunk_coords, chunk_selection, out, out_selection,
                     not fields and
                     is_contiguous_selection(out_selection) and
                     is_total_slice(chunk_selection, self._chunks) and
-                    not self._filters):
+                    not self._filters and
+                    self._dtype != object):
 
                 dest = out[out_selection]
                 write_direct = (
@@ -1727,7 +1728,12 @@ def _decode_chunk(self, cdata):
                 chunk = f.decode(chunk)
 
         # view as correct dtype
-        if isinstance(chunk, np.ndarray):
+        if self._dtype == object:
+            if isinstance(chunk, np.ndarray):
+                chunk = chunk.astype(self._dtype)
+            else:
+                raise RuntimeError('cannot read object array without object codec')
+        elif isinstance(chunk, np.ndarray):
             chunk = chunk.view(self._dtype)
         else:
             chunk = np.frombuffer(chunk, self._dtype)
@@ -1746,8 +1752,7 @@ def _encode_chunk(self, chunk):
 
         # check object encoding
         if isinstance(chunk, np.ndarray) and chunk.dtype == object:
-            # TODO review error message
-            raise RuntimeError('object array detected without encoding')
+            raise RuntimeError('cannot write object array without object codec')
 
         # compress
         if self._compressor:

zarr/tests/test_core.py

@@ -21,7 +21,8 @@
 from zarr.errors import PermissionError
 from zarr.compat import PY2
 from zarr.util import buffer_size
-from numcodecs import Delta, FixedScaleOffset, Zlib, Blosc, BZ2, MsgPack, Pickle
+from numcodecs import (Delta, FixedScaleOffset, Zlib, Blosc, BZ2, MsgPack, Pickle,
+                       Categorize)
 
 
 # noinspection PyMethodMayBeStatic
@@ -911,6 +912,32 @@ def test_object_arrays_danger(self):
         with assert_raises(RuntimeError):
             z[:] = 42
 
+        # do something else dangerous
+        labels = [
+            '¡Hola mundo!',
+            'Hej Världen!',
+            'Servus Woid!',
+            'Hei maailma!',
+            'Xin chào thế giới',
+            'Njatjeta Botë!',
+            'Γεια σου κόσμε!',
+            'こんにちは世界',
+            '世界，你好！',
+            'Helló, világ!',
+            'Zdravo svete!',
+            'เฮลโลเวิลด์'
+        ]
+        data = labels * 10
+        for compressor in Zlib(1), Blosc():
+            z = self.create_array(shape=len(data), chunks=30, dtype=object,
+                                  object_codec=Categorize(labels, dtype=object),
+                                  compressor=compressor)
+            z[:] = data
+            v = z.view(filters=[])
+            with assert_raises(RuntimeError):
+                # noinspection PyStatementEffect
+                v[:]
+
 
 class TestArrayWithPath(TestArray):