/Users/andrewlamb/Software/arrow-rs/arrow-data/src/equal/fixed_binary.rs
Line | Count | Source |
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 | | |
18 | | use crate::bit_iterator::BitSliceIterator; |
19 | | use crate::contains_nulls; |
20 | | use crate::data::ArrayData; |
21 | | use crate::equal::primitive::NULL_SLICES_SELECTIVITY_THRESHOLD; |
22 | | use arrow_schema::DataType; |
23 | | |
24 | | use super::utils::equal_len; |
25 | | |
26 | 7 | pub(super) fn fixed_binary_equal( |
27 | 7 | lhs: &ArrayData, |
28 | 7 | rhs: &ArrayData, |
29 | 7 | lhs_start: usize, |
30 | 7 | rhs_start: usize, |
31 | 7 | len: usize, |
32 | 7 | ) -> bool { |
33 | 7 | let size = match lhs.data_type() { |
34 | 7 | DataType::FixedSizeBinary(i) => *i as usize, |
35 | 0 | _ => unreachable!(), |
36 | | }; |
37 | | |
38 | 7 | let lhs_values = &lhs.buffers()[0].as_slice()[lhs.offset() * size..]; |
39 | 7 | let rhs_values = &rhs.buffers()[0].as_slice()[rhs.offset() * size..]; |
40 | | |
41 | | // Only checking one null mask here because by the time the control flow reaches |
42 | | // this point, the equality of the two masks would have already been verified. |
43 | 7 | if !contains_nulls(lhs.nulls(), lhs_start, len) { |
44 | 5 | equal_len( |
45 | 5 | lhs_values, |
46 | 5 | rhs_values, |
47 | 5 | size * lhs_start, |
48 | 5 | size * rhs_start, |
49 | 5 | size * len, |
50 | | ) |
51 | | } else { |
52 | 2 | let selectivity_frac = lhs.null_count() as f64 / lhs.len() as f64; |
53 | | |
54 | 2 | if selectivity_frac >= NULL_SLICES_SELECTIVITY_THRESHOLD { |
55 | | // get a ref of the null buffer bytes, to use in testing for nullness |
56 | 2 | let lhs_nulls = lhs.nulls().unwrap(); |
57 | 2 | let rhs_nulls = rhs.nulls().unwrap(); |
58 | | // with nulls, we need to compare item by item whenever it is not null |
59 | 4 | (0..len)2 .all2 (|i| { |
60 | 4 | let lhs_pos = lhs_start + i; |
61 | 4 | let rhs_pos = rhs_start + i; |
62 | | |
63 | 4 | let lhs_is_null = lhs_nulls.is_null(lhs_pos); |
64 | 4 | let rhs_is_null = rhs_nulls.is_null(rhs_pos); |
65 | | |
66 | 4 | lhs_is_null |
67 | 2 | || (lhs_is_null == rhs_is_null) |
68 | 2 | && equal_len( |
69 | 2 | lhs_values, |
70 | 2 | rhs_values, |
71 | 2 | lhs_pos * size, |
72 | 2 | rhs_pos * size, |
73 | 2 | size, // 1 * size since we are comparing a single entry |
74 | | ) |
75 | 4 | }) |
76 | | } else { |
77 | 0 | let lhs_nulls = lhs.nulls().unwrap(); |
78 | 0 | let lhs_slices_iter = |
79 | 0 | BitSliceIterator::new(lhs_nulls.validity(), lhs_start + lhs_nulls.offset(), len); |
80 | 0 | let rhs_nulls = rhs.nulls().unwrap(); |
81 | 0 | let rhs_slices_iter = |
82 | 0 | BitSliceIterator::new(rhs_nulls.validity(), rhs_start + rhs_nulls.offset(), len); |
83 | | |
84 | 0 | lhs_slices_iter |
85 | 0 | .zip(rhs_slices_iter) |
86 | 0 | .all(|((l_start, l_end), (r_start, r_end))| { |
87 | 0 | l_start == r_start |
88 | 0 | && l_end == r_end |
89 | 0 | && equal_len( |
90 | 0 | lhs_values, |
91 | 0 | rhs_values, |
92 | 0 | (lhs_start + l_start) * size, |
93 | 0 | (rhs_start + r_start) * size, |
94 | 0 | (l_end - l_start) * size, |
95 | | ) |
96 | 0 | }) |
97 | | } |
98 | | } |
99 | 7 | } |