viirya commented on code in PR #179: URL: https://github.com/apache/arrow-datafusion-comet/pull/179#discussion_r1522709466
########## core/src/execution/datafusion/util/spark_bit_array.rs: ########## @@ -0,0 +1,133 @@ +// Licensed to the Apache Software Foundation (ASF) under one +// or more contributor license agreements. See the NOTICE file +// distributed with this work for additional information +// regarding copyright ownership. The ASF licenses this file +// to you under the Apache License, Version 2.0 (the +// "License"); you may not use this file except in compliance +// with the License. You may obtain a copy of the License at +// +// http://www.apache.org/licenses/LICENSE-2.0 +// +// Unless required by applicable law or agreed to in writing, +// software distributed under the License is distributed on an +// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY +// KIND, either express or implied. See the License for the +// specific language governing permissions and limitations +// under the License. + +/// A simple bit array implementation that simulates the behavior of Spark's BitArray which is +/// used in the BloomFilter implementation. Some methods are not implemented as they are not +/// required for the current use case. +#[derive(Debug, Hash)] +pub struct SparkBitArray { + data: Vec<u64>, + bit_count: usize, +} + +impl SparkBitArray { + pub fn new(buf: Vec<u64>) -> Self { + let num_bits = buf.iter().map(|x| x.count_ones() as usize).sum(); + Self { + data: buf, + bit_count: num_bits, + } + } + + pub fn new_from_bit_count(num_bits: usize) -> Self { + let num_words = (num_bits + 63) / 64; + debug_assert!(num_words < u32::MAX as usize, "num_words is too large"); + Self { + data: vec![0u64; num_words], + bit_count: num_bits, + } + } + + pub fn set(&mut self, index: usize) -> bool { + if !self.get(index) { + self.data[index >> 6] |= 1u64 << (index & 0x3f); Review Comment: Why `(index & 0x3f)`? I don't see Spark does this. -- 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]
