tustvold commented on a change in pull request #1248:
URL: https://github.com/apache/arrow-rs/pull/1248#discussion_r795106504



##########
File path: arrow/src/compute/kernels/filter.rs
##########
@@ -244,6 +419,110 @@ pub fn filter_record_batch(
     RecordBatch::try_new(record_batch.schema(), filtered_arrays)
 }
 
+fn filter_null_mask(
+    data: &ArrayData,
+    filter: &BooleanArray,
+    filter_count: usize,
+) -> Option<(usize, Buffer)> {
+    if data.null_count() == 0 {
+        return None;
+    }
+
+    let nulls = filter_bits(data.null_buffer()?, data.offset(), filter, 
filter_count);
+    let null_count = filter_count - nulls.count_set_bits();
+
+    if null_count == 0 {
+        return None;
+    }
+
+    Some((null_count, nulls))
+}
+
+fn filter_bits(
+    buffer: &Buffer,
+    offset: usize,
+    filter: &BooleanArray,
+    filter_count: usize,
+) -> Buffer {
+    let src = buffer.as_slice();
+
+    // TODO: Optimise this
+    let mut buf = MutableBuffer::from_len_zeroed(bit_util::ceil(filter_count, 
8));
+    let dst = buf.as_slice_mut();
+
+    for (dst_idx, src_idx) in IndexIterator::new(filter).enumerate() {
+        if bit_util::get_bit(src, src_idx + offset) {
+            bit_util::set_bit(dst, dst_idx);
+        }
+    }
+
+    buf.into()
+}
+
+/// `filter` implementation for boolean buffers
+fn filter_boolean(
+    values: &BooleanArray,
+    filter: &BooleanArray,
+    filter_count: usize,
+) -> BooleanArray {
+    let data = values.data();
+    assert_eq!(data.buffers().len(), 1);
+    assert_eq!(data.child_data().len(), 0);
+
+    let values = filter_bits(&data.buffers()[0], data.offset(), filter, 
filter_count);
+
+    let mut builder = ArrayDataBuilder::new(DataType::Boolean)
+        .len(filter_count)
+        .add_buffer(values);
+
+    if let Some((null_count, nulls)) = filter_null_mask(data, filter, 
filter_count) {
+        builder = builder.null_count(null_count).null_bit_buffer(nulls);
+    }
+
+    let data = builder.build().unwrap(); // TODO: unsafe { 
builder.build_unchecked() };
+    BooleanArray::from(data)
+}
+
+/// `filter` implementation for primitive arrays
+fn filter_primitive<T>(
+    values: &PrimitiveArray<T>,
+    filter: &BooleanArray,
+    filter_count: usize,
+) -> PrimitiveArray<T>
+where
+    T: ArrowPrimitiveType,
+{
+    let data = values.data();
+    assert_eq!(data.buffers().len(), 1);
+    assert_eq!(data.child_data().len(), 0);
+
+    let values = data.buffer::<T::Native>(0);
+
+    let mut buffer = MutableBuffer::with_capacity(filter_count * 
T::get_byte_width());
+
+    let selectivity_frac = filter_count as f64 / filter.len() as f64;

Review comment:
       Credit to @sunchao for the inspiration behind this hybrid approach - 
https://github.com/apache/arrow-rs/issues/1191#issuecomment-1023658537




-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]


Reply via email to