001/* 002 * Licensed to the Apache Software Foundation (ASF) under one 003 * or more contributor license agreements. See the NOTICE file 004 * distributed with this work for additional information 005 * regarding copyright ownership. The ASF licenses this file 006 * to you under the Apache License, Version 2.0 (the 007 * "License"); you may not use this file except in compliance 008 * with the License. You may obtain a copy of the License at 009 * 010 * http://www.apache.org/licenses/LICENSE-2.0 011 * 012 * Unless required by applicable law or agreed to in writing, software 013 * distributed under the License is distributed on an "AS IS" BASIS, 014 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 015 * See the License for the specific language governing permissions and 016 * limitations under the License. 017 */ 018package org.apache.hadoop.hbase.io.compress; 019 020import org.apache.yetus.audience.InterfaceAudience; 021 022@InterfaceAudience.Private 023public final class CompressionUtil { 024 025 private CompressionUtil() { 026 } 027 028 /** 029 * Round up to the next power of two, unless the value would become negative (ints are signed), in 030 * which case just return Integer.MAX_VALUE. 031 */ 032 public static int roundInt2(int v) { 033 v = Integer.highestOneBit(v) << 1; 034 if (v < 0) { 035 return Integer.MAX_VALUE; 036 } 037 return v; 038 } 039 040 /** 041 * Most compression algorithms can be presented with pathological input that causes an expansion 042 * rather than a compression. Hadoop's compression API requires that we calculate additional 043 * buffer space required for the worst case. There is a formula developed for gzip that applies as 044 * a ballpark to all LZ variants. It should be good enough for now and has been tested as such 045 * with a range of different inputs. 046 */ 047 public static int compressionOverhead(int bufferSize) { 048 // Given an input buffer of 'buffersize' bytes we presume a worst case expansion of 049 // 32 bytes (block header) and addition 1/6th of the input size. 050 return (bufferSize / 6) + 32; 051 } 052}