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.compressors;
020
021import java.util.Collections;
022import java.util.HashMap;
023import java.util.Locale;
024import java.util.Map;
025
026/**
027 * File name mapping code for the compression formats.
028 *
029 * @ThreadSafe
030 * @since 1.4
031 */
032public class FileNameUtil {
033
034    /**
035     * Map from common file name suffixes to the suffixes that identify compressed versions of those file types. For example: from ".tar" to ".tgz".
036     */
037    private final Map<String, String> compressSuffix = new HashMap<>();
038
039    /**
040     * Map from common file name suffixes of compressed files to the corresponding suffixes of uncompressed files. For example: from ".tgz" to ".tar".
041     * <p>
042     * This map also contains format-specific suffixes like ".gz" and "-z". These suffixes are mapped to the empty string, as they should simply be removed from
043     * the file name when the file is uncompressed.
044     */
045    private final Map<String, String> uncompressSuffix;
046
047    /**
048     * Length of the longest compressed suffix.
049     */
050    private final int longestCompressedSuffix;
051
052    /**
053     * Length of the shortest compressed suffix.
054     */
055    private final int shortestCompressedSuffix;
056
057    /**
058     * Length of the longest uncompressed suffix.
059     */
060    private final int longestUncompressedSuffix;
061
062    /**
063     * Length of the shortest uncompressed suffix longer than the empty string.
064     */
065    private final int shortestUncompressedSuffix;
066
067    /**
068     * The format's default extension.
069     */
070    private final String defaultExtension;
071
072    /**
073     * sets up the utility with a map of known compressed to uncompressed suffix mappings and the default extension of the format.
074     *
075     * @param uncompressSuffix Map from common file name suffixes of compressed files to the corresponding suffixes of uncompressed files. For example: from
076     *                         ".tgz" to ".tar". This map also contains format-specific suffixes like ".gz" and "-z". These suffixes are mapped to the empty
077     *                         string, as they should simply be removed from the file name when the file is uncompressed.
078     *
079     * @param defaultExtension the format's default extension like ".gz"
080     */
081    public FileNameUtil(final Map<String, String> uncompressSuffix, final String defaultExtension) {
082        this.uncompressSuffix = Collections.unmodifiableMap(uncompressSuffix);
083        int lc = Integer.MIN_VALUE, sc = Integer.MAX_VALUE;
084        int lu = Integer.MIN_VALUE, su = Integer.MAX_VALUE;
085        for (final Map.Entry<String, String> ent : uncompressSuffix.entrySet()) {
086            final int cl = ent.getKey().length();
087            if (cl > lc) {
088                lc = cl;
089            }
090            if (cl < sc) {
091                sc = cl;
092            }
093
094            final String u = ent.getValue();
095            final int ul = u.length();
096            if (ul > 0) {
097                compressSuffix.computeIfAbsent(u, k -> ent.getKey());
098                if (ul > lu) {
099                    lu = ul;
100                }
101                if (ul < su) {
102                    su = ul;
103                }
104            }
105        }
106        longestCompressedSuffix = lc;
107        longestUncompressedSuffix = lu;
108        shortestCompressedSuffix = sc;
109        shortestUncompressedSuffix = su;
110        this.defaultExtension = defaultExtension;
111    }
112
113    /**
114     * Maps the given file name to the name that the file should have after compression. Common file types with custom suffixes for compressed versions are
115     * automatically detected and correctly mapped. For example the name "package.tar" is mapped to "package.tgz". If no custom mapping is applicable, then the
116     * default ".gz" suffix is appended to the file name.
117     *
118     * @param fileName name of a file
119     * @return name of the corresponding compressed file
120     * @deprecated Use {@link #getCompressedFileName(String)}.
121     */
122    @Deprecated
123    public String getCompressedFilename(final String fileName) {
124        return getCompressedFileName(fileName);
125    }
126
127    /**
128     * Maps the given file name to the name that the file should have after compression. Common file types with custom suffixes for compressed versions are
129     * automatically detected and correctly mapped. For example the name "package.tar" is mapped to "package.tgz". If no custom mapping is applicable, then the
130     * default ".gz" suffix is appended to the file name.
131     *
132     * @param fileName name of a file
133     * @return name of the corresponding compressed file
134     * @since 1.25.0
135     */
136    public String getCompressedFileName(final String fileName) {
137        final String lower = fileName.toLowerCase(Locale.ENGLISH);
138        final int n = lower.length();
139        for (int i = shortestUncompressedSuffix; i <= longestUncompressedSuffix && i < n; i++) {
140            final String suffix = compressSuffix.get(lower.substring(n - i));
141            if (suffix != null) {
142                return fileName.substring(0, n - i) + suffix;
143            }
144        }
145        // No custom suffix found, just append the default
146        return fileName + defaultExtension;
147    }
148
149    /**
150     * Maps the given name of a compressed file to the name that the file should have after uncompression. Commonly used file type specific suffixes like ".tgz"
151     * or ".svgz" are automatically detected and correctly mapped. For example the name "package.tgz" is mapped to "package.tar". And any file names with the
152     * generic ".gz" suffix (or any other generic gzip suffix) is mapped to a name without that suffix. If no format suffix is detected, then the file name is
153     * returned unmapped.
154     *
155     * @param fileName name of a file
156     * @return name of the corresponding uncompressed file
157     * @deprecated Use {@link #getUncompressedFileName(String)}.
158     */
159    @Deprecated
160    public String getUncompressedFilename(final String fileName) {
161        return getUncompressedFileName(fileName);
162    }
163
164    /**
165     * Maps the given name of a compressed file to the name that the file should have after uncompression. Commonly used file type specific suffixes like ".tgz"
166     * or ".svgz" are automatically detected and correctly mapped. For example the name "package.tgz" is mapped to "package.tar". And any file names with the
167     * generic ".gz" suffix (or any other generic gzip suffix) is mapped to a name without that suffix. If no format suffix is detected, then the file name is
168     * returned unmapped.
169     *
170     * @param fileName name of a file
171     * @return name of the corresponding uncompressed file
172     * @since 1.25.0
173     */
174    public String getUncompressedFileName(final String fileName) {
175        final String lower = fileName.toLowerCase(Locale.ENGLISH);
176        final int n = lower.length();
177        for (int i = shortestCompressedSuffix; i <= longestCompressedSuffix && i < n; i++) {
178            final String suffix = uncompressSuffix.get(lower.substring(n - i));
179            if (suffix != null) {
180                return fileName.substring(0, n - i) + suffix;
181            }
182        }
183        return fileName;
184    }
185
186    /**
187     * Detects common format suffixes in the given file name.
188     *
189     * @param fileName name of a file
190     * @return {@code true} if the file name has a common format suffix, {@code false} otherwise
191     * @deprecated Use {@link #isCompressedFileName(String)}.
192     */
193    @Deprecated
194    public boolean isCompressedFilename(final String fileName) {
195        return isCompressedFileName(fileName);
196    }
197
198    /**
199     * Detects common format suffixes in the given file name.
200     *
201     * @param fileName name of a file
202     * @return {@code true} if the file name has a common format suffix, {@code false} otherwise
203     * @since 1.25.0
204     */
205    public boolean isCompressedFileName(final String fileName) {
206        final String lower = fileName.toLowerCase(Locale.ENGLISH);
207        final int n = lower.length();
208        for (int i = shortestCompressedSuffix; i <= longestCompressedSuffix && i < n; i++) {
209            if (uncompressSuffix.containsKey(lower.substring(n - i))) {
210                return true;
211            }
212        }
213        return false;
214    }
215}