arrow_data/transform/
utils.rs

Help
1// Licensed to the Apache Software Foundation (ASF) under one
2// or more contributor license agreements.  See the NOTICE file
3// distributed with this work for additional information
4// regarding copyright ownership.  The ASF licenses this file
5// to you under the Apache License, Version 2.0 (the
6// "License"); you may not use this file except in compliance
7// with the License.  You may obtain a copy of the License at
8//
9//   http://www.apache.org/licenses/LICENSE-2.0
10//
11// Unless required by applicable law or agreed to in writing,
12// software distributed under the License is distributed on an
13// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
14// KIND, either express or implied.  See the License for the
15// specific language governing permissions and limitations
16// under the License.
17
18use arrow_buffer::{bit_util, ArrowNativeType, MutableBuffer};
19use num::{CheckedAdd, Integer};
20
21/// extends the `buffer` to be able to hold `len` bits, setting all bits of the new size to zero.
22#[inline]
23pub(super) fn resize_for_bits(buffer: &mut MutableBuffer, len: usize) {
24    let needed_bytes = bit_util::ceil(len, 8);
25    if buffer.len() < needed_bytes {
26        buffer.resize(needed_bytes, 0);
27    }
28}
29
30pub(super) fn extend_offsets<T: ArrowNativeType + Integer + CheckedAdd>(
31    buffer: &mut MutableBuffer,
32    mut last_offset: T,
33    offsets: &[T],
34) {
35    buffer.reserve(std::mem::size_of_val(offsets));
36    offsets.windows(2).for_each(|offsets| {
37        // compute the new offset
38        let length = offsets[1] - offsets[0];
39        // if you hit this appending to a StringArray / BinaryArray it is because you
40        // are trying to add more data than can fit into that type. Try breaking your data into
41        // smaller batches or using LargeStringArray / LargeBinaryArray
42        last_offset = last_offset.checked_add(&length).expect("offset overflow");
43        buffer.push(last_offset);
44    });
45}
46
47#[inline]
48pub(super) unsafe fn get_last_offset<T: ArrowNativeType>(offset_buffer: &MutableBuffer) -> T {
49    // JUSTIFICATION
50    //  Benefit
51    //      20% performance improvement extend of variable sized arrays (see bench `mutable_array`)
52    //  Soundness
53    //      * offset buffer is always extended in slices of T and aligned accordingly.
54    //      * Buffer[0] is initialized with one element, 0, and thus `mutable_offsets.len() - 1` is always valid.
55    let (prefix, offsets, suffix) = offset_buffer.as_slice().align_to::<T>();
56    debug_assert!(prefix.is_empty() && suffix.is_empty());
57    *offsets.get_unchecked(offsets.len() - 1)
58}
59
60#[cfg(test)]
61mod tests {
62    use crate::transform::utils::extend_offsets;
63    use arrow_buffer::MutableBuffer;
64
65    #[test]
66    #[should_panic(expected = "offset overflow")]
67    fn test_overflow() {
68        let mut buffer = MutableBuffer::new(10);
69        extend_offsets(&mut buffer, i32::MAX - 4, &[0, 5]);
70    }
71}
arrow_data/transform/utils.rs

arrow_data/transform/
utils.rs
