001/* 002 * Licensed to the Apache Software Foundation (ASF) under one or more 003 * contributor license agreements. See the NOTICE file distributed with 004 * this work for additional information regarding copyright ownership. 005 * The ASF licenses this file to You under the Apache License, Version 2.0 006 * (the "License"); you may not use this file except in compliance with 007 * the License. You may obtain a copy of the License at 008 * 009 * http://www.apache.org/licenses/LICENSE-2.0 010 * 011 * Unless required by applicable law or agreed to in writing, software 012 * distributed under the License is distributed on an "AS IS" BASIS, 013 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 014 * See the License for the specific language governing permissions and 015 * limitations under the License. 016 */ 017package org.apache.commons.io.input; 018 019import java.io.Reader; 020import java.util.Arrays; 021import java.util.Collections; 022import java.util.HashSet; 023import java.util.Set; 024import java.util.function.IntPredicate; 025 026/** 027 * A filter reader that removes a given set of characters represented as {@code int} code points, handy to remove known 028 * junk characters from CSV files for example. 029 * <p> 030 * This class must convert each {@code int} read to an {@link Integer}. You can increase the Integer cache with a system 031 * property, see {@link Integer}. 032 * </p> 033 */ 034public class CharacterSetFilterReader extends AbstractCharacterFilterReader { 035 036 private static IntPredicate toIntPredicate(final Set<Integer> skip) { 037 if (skip == null) { 038 return SKIP_NONE; 039 } 040 final Set<Integer> unmodifiableSet = Collections.unmodifiableSet(skip); 041 return c -> unmodifiableSet.contains(Integer.valueOf(c)); 042 } 043 044 /** 045 * Constructs a new reader. 046 * 047 * @param reader the reader to filter. 048 * @param skip the set of characters to filter out. 049 * @since 2.9.0 050 */ 051 public CharacterSetFilterReader(final Reader reader, final Integer... skip) { 052 this(reader, new HashSet<>(Arrays.asList(skip))); 053 } 054 055 /** 056 * Constructs a new reader. 057 * 058 * @param reader the reader to filter. 059 * @param skip the set of characters to filter out. 060 */ 061 public CharacterSetFilterReader(final Reader reader, final Set<Integer> skip) { 062 super(reader, toIntPredicate(skip)); 063 } 064 065}