arrow_data/equal/
fixed_binary.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 crate::data::{ArrayData, get_fixed_size_binary_width};
21use crate::equal::primitive::NULL_SLICES_SELECTIVITY_THRESHOLD;
22
23use super::utils::equal_len;
24
25pub(super) fn fixed_binary_equal(
26    lhs: &ArrayData,
27    rhs: &ArrayData,
28    lhs_start: usize,
29    rhs_start: usize,
30    len: usize,
31) -> bool {
32    let size = get_fixed_size_binary_width(lhs.data_type());
33
34    let lhs_values = &lhs.buffers()[0].as_slice()[lhs.offset() * size..];
35    let rhs_values = &rhs.buffers()[0].as_slice()[rhs.offset() * size..];
36
37    // Only checking one null mask here because by the time the control flow reaches
38    // this point, the equality of the two masks would have already been verified.
39    if !contains_nulls(lhs.nulls(), lhs_start, len) {
40        equal_len(
41            lhs_values,
42            rhs_values,
43            size * lhs_start,
44            size * rhs_start,
45            size * len,
46        )
47    } else {
48        let selectivity_frac = lhs.null_count() as f64 / lhs.len() as f64;
49
50        if selectivity_frac >= NULL_SLICES_SELECTIVITY_THRESHOLD {
51            // get a ref of the null buffer bytes, to use in testing for nullness
52            let lhs_nulls = lhs.nulls().unwrap();
53            let rhs_nulls = rhs.nulls().unwrap();
54            // with nulls, we need to compare item by item whenever it is not null
55            (0..len).all(|i| {
56                let lhs_pos = lhs_start + i;
57                let rhs_pos = rhs_start + i;
58
59                let lhs_is_null = lhs_nulls.is_null(lhs_pos);
60                let rhs_is_null = rhs_nulls.is_null(rhs_pos);
61
62                lhs_is_null
63                    || (lhs_is_null == rhs_is_null)
64                        && equal_len(
65                            lhs_values,
66                            rhs_values,
67                            lhs_pos * size,
68                            rhs_pos * size,
69                            size, // 1 * size since we are comparing a single entry
70                        )
71            })
72        } else {
73            let lhs_nulls = lhs.nulls().unwrap();
74            let lhs_slices_iter =
75                BitSliceIterator::new(lhs_nulls.validity(), lhs_start + lhs_nulls.offset(), len);
76            let rhs_nulls = rhs.nulls().unwrap();
77            let rhs_slices_iter =
78                BitSliceIterator::new(rhs_nulls.validity(), rhs_start + rhs_nulls.offset(), len);
79
80            lhs_slices_iter
81                .zip(rhs_slices_iter)
82                .all(|((l_start, l_end), (r_start, r_end))| {
83                    l_start == r_start
84                        && l_end == r_end
85                        && equal_len(
86                            lhs_values,
87                            rhs_values,
88                            (lhs_start + l_start) * size,
89                            (rhs_start + r_start) * size,
90                            (l_end - l_start) * size,
91                        )
92                })
93        }
94    }
95}
arrow_data/equal/fixed_binary.rs

arrow_data/equal/
fixed_binary.rs
