arrow_data/equal/
primitive.rs

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 crate::bit_iterator::BitSliceIterator;
19use crate::contains_nulls;
20use std::mem::size_of;
21
22use crate::data::ArrayData;
23
24use super::utils::equal_len;
25
26pub(crate) const NULL_SLICES_SELECTIVITY_THRESHOLD: f64 = 0.4;
27
28pub(super) fn primitive_equal<T>(
29    lhs: &ArrayData,
30    rhs: &ArrayData,
31    lhs_start: usize,
32    rhs_start: usize,
33    len: usize,
34) -> bool {
35    let byte_width = size_of::<T>();
36    let lhs_values = &lhs.buffers()[0].as_slice()[lhs.offset() * byte_width..];
37    let rhs_values = &rhs.buffers()[0].as_slice()[rhs.offset() * byte_width..];
38
39    // Only checking one null mask here because by the time the control flow reaches
40    // this point, the equality of the two masks would have already been verified.
41    if !contains_nulls(lhs.nulls(), lhs_start, len) {
42        // without nulls, we just need to compare slices
43        equal_len(
44            lhs_values,
45            rhs_values,
46            lhs_start * byte_width,
47            rhs_start * byte_width,
48            len * byte_width,
49        )
50    } else {
51        let selectivity_frac = lhs.null_count() as f64 / lhs.len() as f64;
52
53        // get a ref of the null buffer bytes, to use in testing for nullness
54        let lhs_nulls = lhs.nulls().unwrap();
55        let rhs_nulls = rhs.nulls().unwrap();
56
57        if selectivity_frac >= NULL_SLICES_SELECTIVITY_THRESHOLD {
58            // with nulls, we need to compare item by item whenever it is not null
59            (0..len).all(|i| {
60                let lhs_pos = lhs_start + i;
61                let rhs_pos = rhs_start + i;
62                let lhs_is_null = lhs_nulls.is_null(lhs_pos);
63                let rhs_is_null = rhs_nulls.is_null(rhs_pos);
64
65                lhs_is_null
66                    || (lhs_is_null == rhs_is_null)
67                        && equal_len(
68                            lhs_values,
69                            rhs_values,
70                            lhs_pos * byte_width,
71                            rhs_pos * byte_width,
72                            byte_width, // 1 * byte_width since we are comparing a single entry
73                        )
74            })
75        } else {
76            let lhs_slices_iter =
77                BitSliceIterator::new(lhs_nulls.validity(), lhs_start + lhs_nulls.offset(), len);
78            let rhs_slices_iter =
79                BitSliceIterator::new(rhs_nulls.validity(), rhs_start + rhs_nulls.offset(), len);
80
81            lhs_slices_iter
82                .zip(rhs_slices_iter)
83                .all(|((l_start, l_end), (r_start, r_end))| {
84                    l_start == r_start
85                        && l_end == r_end
86                        && equal_len(
87                            lhs_values,
88                            rhs_values,
89                            (lhs_start + l_start) * byte_width,
90                            (rhs_start + r_start) * byte_width,
91                            (l_end - l_start) * byte_width,
92                        )
93                })
94        }
95    }
96}
arrow_data/equal/primitive.rs

arrow_data/equal/
primitive.rs
