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,
013 * software distributed under the License is distributed on an
014 * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
015 * KIND, either express or implied.  See the License for the
016 * specific language governing permissions and limitations
017 * under the License.
018 */
019package org.apache.commons.compress.archivers.tar;
020
021import java.io.IOException;
022import java.util.ArrayList;
023import java.util.List;
024
025/**
026 * A sparse entry in a <a href="https://www.gnu.org/software/tar/manual/html_node/Standard.html">Tar archive</a>.
027 *
028 * <p>
029 * The C structure for a sparse entry is:
030 *
031 * <pre>
032 * struct posix_header {
033 * struct sparse sp[21]; // TarConstants.SPARSELEN_GNU_SPARSE     - offset 0
034 * char isextended;      // TarConstants.ISEXTENDEDLEN_GNU_SPARSE - offset 504
035 * };
036 * </pre>
037 *
038 * Whereas, "struct sparse" is:
039 *
040 * <pre>
041 * struct sparse {
042 * char offset[12];   // offset 0
043 * char numbytes[12]; // offset 12
044 * };
045 * </pre>
046 *
047 * <p>
048 * Each such struct describes a block of data that has actually been written to the archive. The offset describes where in the extracted file the data is
049 * supposed to start and the numbytes provides the length of the block. When extracting the entry the gaps between the sparse structs are equivalent to areas
050 * filled with zero bytes.
051 * </p>
052 */
053
054public class TarArchiveSparseEntry implements TarConstants {
055    /** If an extension sparse header follows. */
056    private final boolean isExtended;
057
058    private final List<TarArchiveStructSparse> sparseHeaders;
059
060    /**
061     * Constructs an entry from an archive's header bytes. File is set to null.
062     *
063     * @param headerBuf The header bytes from a tar archive entry.
064     * @throws IOException on unknown format
065     */
066    public TarArchiveSparseEntry(final byte[] headerBuf) throws IOException {
067        int offset = 0;
068        sparseHeaders = new ArrayList<>(TarUtils.readSparseStructs(headerBuf, 0, SPARSE_HEADERS_IN_EXTENSION_HEADER));
069        offset += SPARSELEN_GNU_SPARSE;
070        isExtended = TarUtils.parseBoolean(headerBuf, offset);
071    }
072
073    /**
074     * Gets information about the configuration for the sparse entry.
075     *
076     * @since 1.20
077     * @return information about the configuration for the sparse entry.
078     */
079    public List<TarArchiveStructSparse> getSparseHeaders() {
080        return sparseHeaders;
081    }
082
083    public boolean isExtended() {
084        return isExtended;
085    }
086}