ARROW-12431: [Python] Mask is inverted when creating FixedSizeBinaryA…

…rray Closes apache#10199 from amol-/ARROW-12431 Authored-by: Alessandro Molina <[email protected]> Signed-off-by: Antoine Pitrou <[email protected]>
michalursa · Jun 15, 2021 · 4b3f6c3 · 4b3f6c3
1 parent 655b281
commit 4b3f6c3
Show file tree

Hide file tree

Showing 3 changed files with 59 additions and 3 deletions.
diff --git a/cpp/src/arrow/python/numpy_to_arrow.cc b/cpp/src/arrow/python/numpy_to_arrow.cc
@@ -594,9 +594,20 @@ Status NumPyConverter::Visit(const FixedSizeBinaryType& type) {
 
   if (mask_ != nullptr) {
     Ndarray1DIndexer<uint8_t> mask_values(mask_);
-    RETURN_NOT_OK(builder.AppendValues(data, length_, mask_values.data()));
+    RETURN_NOT_OK(builder.Reserve(length_));
+    for (int64_t i = 0; i < length_; ++i) {
+      if (mask_values[i]) {
+        RETURN_NOT_OK(builder.AppendNull());
+      } else {
+        RETURN_NOT_OK(builder.Append(data));
+      }
+      data += stride_;
+    }
   } else {
-    RETURN_NOT_OK(builder.AppendValues(data, length_));
+    for (int64_t i = 0; i < length_; ++i) {
+      RETURN_NOT_OK(builder.Append(data));
+      data += stride_;
+    }
   }
 
   std::shared_ptr<Array> result;

diff --git a/python/pyarrow/tests/test_array.py b/python/pyarrow/tests/test_array.py
@@ -2714,6 +2714,51 @@ def test_array_masked():
     assert arr.type == pa.int64()
 
 
+def test_binary_array_masked():
+    # ARROW-12431
+    masked_basic = pa.array([b'\x05'], type=pa.binary(1),
+                            mask=np.array([False]))
+    assert [b'\x05'] == masked_basic.to_pylist()
+
+    # Fixed Length Binary
+    masked = pa.array(np.array([b'\x05']), type=pa.binary(1),
+                      mask=np.array([False]))
+    assert [b'\x05'] == masked.to_pylist()
+
+    masked_nulls = pa.array(np.array([b'\x05']), type=pa.binary(1),
+                            mask=np.array([True]))
+    assert [None] == masked_nulls.to_pylist()
+
+    # Variable Length Binary
+    masked = pa.array(np.array([b'\x05']), type=pa.binary(),
+                      mask=np.array([False]))
+    assert [b'\x05'] == masked.to_pylist()
+
+    masked_nulls = pa.array(np.array([b'\x05']), type=pa.binary(),
+                            mask=np.array([True]))
+    assert [None] == masked_nulls.to_pylist()
+
+    # Fixed Length Binary, copy
+    npa = np.array([b'aaa', b'bbb', b'ccc']*10)
+    arrow_array = pa.array(npa, type=pa.binary(3),
+                           mask=np.array([False, False, False]*10))
+    npa[npa == b"bbb"] = b"XXX"
+    assert ([b'aaa', b'bbb', b'ccc']*10) == arrow_array.to_pylist()
+
+
+def test_binary_array_strided():
+    # Masked
+    nparray = np.array([b"ab", b"cd", b"ef"])
+    arrow_array = pa.array(nparray[::2], pa.binary(2),
+                           mask=np.array([False, False]))
+    assert [b"ab", b"ef"] == arrow_array.to_pylist()
+
+    # Unmasked
+    nparray = np.array([b"ab", b"cd", b"ef"])
+    arrow_array = pa.array(nparray[::2], pa.binary(2))
+    assert [b"ab", b"ef"] == arrow_array.to_pylist()
+
+
 def test_array_invalid_mask_raises():
     # ARROW-10742
     cases = [

diff --git a/python/pyarrow/tests/test_pandas.py b/python/pyarrow/tests/test_pandas.py
@@ -1705,7 +1705,7 @@ def test_numpy_string_array_to_fixed_size_binary(self):
         expected = pa.array(list(arr), type=pa.binary(3))
         assert converted.equals(expected)
 
-        mask = np.array([True, False, True])
+        mask = np.array([False, True, False])
         converted = pa.array(arr, type=pa.binary(3), mask=mask)
         expected = pa.array([b'foo', None, b'baz'], type=pa.binary(3))
         assert converted.equals(expected)