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 */ 017 018package org.apache.commons.compress.archivers.zip; 019 020import static java.nio.charset.StandardCharsets.UTF_8; 021 022import java.nio.ByteBuffer; 023import java.nio.charset.Charset; 024import java.nio.charset.StandardCharsets; 025import java.nio.charset.UnsupportedCharsetException; 026 027import org.apache.commons.io.Charsets; 028 029/** 030 * Static helper functions for robustly encoding file names in ZIP files. 031 */ 032public abstract class ZipEncodingHelper { 033 034 /** 035 * UTF-8. 036 */ 037 static final ZipEncoding ZIP_ENCODING_UTF_8 = getZipEncoding(StandardCharsets.UTF_8); 038 039 /** 040 * Instantiates a ZIP encoding. An NIO based character set encoder/decoder will be returned. As a special case, if the character set is UTF-8, the NIO 041 * encoder will be configured replace malformed and unmappable characters with '?'. This matches existing behavior from the older fallback encoder. 042 * <p> 043 * If the requested character set cannot be found, the platform default will be used instead. 044 * </p> 045 * 046 * @param charset The charset of the ZIP encoding. Specify {@code null} for the platform's default encoding. 047 * @return A ZIP encoding for the given encoding name. 048 * @since 1.26.0 049 */ 050 public static ZipEncoding getZipEncoding(final Charset charset) { 051 return new NioZipEncoding(Charsets.toCharset(charset), isUTF8(Charsets.toCharset(charset))); 052 } 053 054 /** 055 * Instantiates a ZIP encoding. An NIO based character set encoder/decoder will be returned. As a special case, if the character set is UTF-8, the NIO 056 * encoder will be configured replace malformed and unmappable characters with '?'. This matches existing behavior from the older fallback encoder. 057 * <p> 058 * If the requested character set cannot be found, the platform default will be used instead. 059 * </p> 060 * 061 * @param name The name of the ZIP encoding. Specify {@code null} for the platform's default encoding. 062 * @return A ZIP encoding for the given encoding name. 063 */ 064 public static ZipEncoding getZipEncoding(final String name) { 065 return new NioZipEncoding(toSafeCharset(name), isUTF8(toSafeCharset(name).name())); 066 } 067 068 static ByteBuffer growBufferBy(final ByteBuffer buffer, final int increment) { 069 buffer.limit(buffer.position()); 070 buffer.rewind(); 071 final ByteBuffer on = ByteBuffer.allocate(buffer.capacity() + increment); 072 on.put(buffer); 073 return on; 074 } 075 076 /** 077 * Tests whether a given encoding is UTF-8. If the given name is null, then check the platform's default encoding. 078 * 079 * @param charset If the given charset is null, then check the platform's default encoding. 080 */ 081 static boolean isUTF8(final Charset charset) { 082 return isUTF8Alias(Charsets.toCharset(charset).name()); 083 } 084 085 /** 086 * Tests whether a given encoding is UTF-8. If the given name is null, then check the platform's default encoding. 087 * 088 * @param charsetName If the given name is null, then check the platform's default encoding. 089 */ 090 static boolean isUTF8(final String charsetName) { 091 return isUTF8Alias(charsetName != null ? charsetName : Charset.defaultCharset().name()); 092 } 093 094 private static boolean isUTF8Alias(final String actual) { 095 return UTF_8.name().equalsIgnoreCase(actual) || UTF_8.aliases().stream().anyMatch(alias -> alias.equalsIgnoreCase(actual)); 096 } 097 098 private static Charset toSafeCharset(final String name) { 099 Charset charset = Charset.defaultCharset(); 100 try { 101 charset = Charsets.toCharset(name); 102 } catch (final UnsupportedCharsetException ignore) { // NOSONAR we use the default encoding instead 103 } 104 return charset; 105 } 106}