Mega Code Archive
General filename and filepath manipulation utilities
<![CDATA[
/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
import java.io.File;
import java.io.Serializable;
import java.util.ArrayList;
import java.util.Collection;
import java.util.Iterator;
import java.util.Stack;
/**
* General filename and filepath manipulation utilities.
* <p>
* When dealing with filenames you can hit problems when moving from a Windows
* based development machine to a Unix based production machine.
* This class aims to help avoid those problems.
* <p>
* <b>NOTE</b>: You may be able to avoid using this class entirely simply by
* using JDK {@link java.io.File File} objects and the two argument constructor
* {@link java.io.File#File(java.io.File, java.lang.String) File(File,String)}.
* <p>
* Most methods on this class are designed to work the same on both Unix and Windows.
* Those that don't include 'System', 'Unix' or 'Windows' in their name.
* <p>
* Most methods recognise both separators (forward and back), and both
* sets of prefixes. See the javadoc of each method for details.
* <p>
* This class defines six components within a filename
* (example C:\dev\project\file.txt):
* <ul>
* <li>the prefix - C:\</li>
* <li>the path - dev\project\</li>
* <li>the full path - C:\dev\project\</li>
* <li>the name - file.txt</li>
* <li>the base name - file</li>
* <li>the extension - txt</li>
* </ul>
* Note that this class works best if directory filenames end with a separator.
* If you omit the last separator, it is impossible to determine if the filename
* corresponds to a file or a directory. As a result, we have chosen to say
* it corresponds to a file.
* <p>
* This class only supports Unix and Windows style names.
* Prefixes are matched as follows:
* <pre>
* Windows:
* a\b\c.txt --> "" --> relative
* \a\b\c.txt --> "\" --> current drive absolute
* C:a\b\c.txt --> "C:" --> drive relative
* C:\a\b\c.txt --> "C:\" --> absolute
* \\server\a\b\c.txt --> "\\server\" --> UNC
*
* Unix:
* a/b/c.txt --> "" --> relative
* /a/b/c.txt --> "/" --> absolute
* ~/a/b/c.txt --> "~/" --> current user
* ~ --> "~/" --> current user (slash added)
* ~user/a/b/c.txt --> "~user/" --> named user
* ~user --> "~user/" --> named user (slash added)
* </pre>
* Both prefix styles are matched always, irrespective of the machine that you are
* currently running on.
* <p>
* Origin of code: Excalibur, Alexandria, Tomcat, Commons-Utils.
*
* @author <a href="mailto:burton@relativity.yi.org">Kevin A. Burton</A>
* @author <a href="mailto:sanders@apache.org">Scott Sanders</a>
* @author <a href="mailto:dlr@finemaltcoding.com">Daniel Rall</a>
* @author <a href="mailto:Christoph.Reck@dlr.de">Christoph.Reck</a>
* @author <a href="mailto:peter@apache.org">Peter Donald</a>
* @author <a href="mailto:jefft@apache.org">Jeff Turner</a>
* @author Matthew Hawthorne
* @author Martin Cooper
* @author <a href="mailto:jeremias@apache.org">Jeremias Maerki</a>
* @author Stephen Colebourne
* @version $Id: FilenameUtils.java 609870 2008-01-08 04:46:26Z niallp $
* @since Commons IO 1.1
*/
public class FilenameUtils {
/**
* The extension separator character.
* @since Commons IO 1.4
*/
public static final char EXTENSION_SEPARATOR = '.';
/**
* The extension separator String.
* @since Commons IO 1.4
*/
public static final String EXTENSION_SEPARATOR_STR = (new Character(EXTENSION_SEPARATOR)).toString();
/**
* The Unix separator character.
*/
private static final char UNIX_SEPARATOR = '/';
/**
* The Windows separator character.
*/
private static final char WINDOWS_SEPARATOR = '\\';
/**
* The system separator character.
*/
private static final char SYSTEM_SEPARATOR = File.separatorChar;
/**
* The separator character that is the opposite of the system separator.
*/
private static final char OTHER_SEPARATOR;
static {
if (isSystemWindows()) {
OTHER_SEPARATOR = UNIX_SEPARATOR;
} else {
OTHER_SEPARATOR = WINDOWS_SEPARATOR;
}
}
/**
* Instances should NOT be constructed in standard programming.
*/
public FilenameUtils() {
super();
}
//-----------------------------------------------------------------------
/**
* Determines if Windows file system is in use.
*
* @return true if the system is Windows
*/
static boolean isSystemWindows() {
return SYSTEM_SEPARATOR == WINDOWS_SEPARATOR;
}
//-----------------------------------------------------------------------
/**
* Checks if the character is a separator.
*
* @param ch the character to check
* @return true if it is a separator character
*/
private static boolean isSeparator(char ch) {
return (ch == UNIX_SEPARATOR) || (ch == WINDOWS_SEPARATOR);
}
//-----------------------------------------------------------------------
/**
* Normalizes a path, removing double and single dot path steps.
* <p>
* This method normalizes a path to a standard format.
* The input may contain separators in either Unix or Windows format.
* The output will contain separators in the format of the system.
* <p>
* A trailing slash will be retained.
* A double slash will be merged to a single slash (but UNC names are handled).
* A single dot path segment will be removed.
* A double dot will cause that path segment and the one before to be removed.
* If the double dot has no parent path segment to work with, <code>null</code>
* is returned.
* <p>
* The output will be the same on both Unix and Windows except
* for the separator character.
* <pre>
* /foo// --> /foo/
* /foo/./ --> /foo/
* /foo/../bar --> /bar
* /foo/../bar/ --> /bar/
* /foo/../bar/../baz --> /baz
* //foo//./bar --> /foo/bar
* /../ --> null
* ../foo --> null
* foo/bar/.. --> foo/
* foo/../../bar --> null
* foo/../bar --> bar
* //server/foo/../bar --> //server/bar
* //server/../bar --> null
* C:\foo\..\bar --> C:\bar
* C:\..\bar --> null
* ~/foo/../bar/ --> ~/bar/
* ~/../bar --> null
* </pre>
* (Note the file separator returned will be correct for Windows/Unix)
*
* @param filename the filename to normalize, null returns null
* @return the normalized filename, or null if invalid
*/
public static String normalize(String filename) {
return doNormalize(filename, true);
}
//-----------------------------------------------------------------------
/**
* Normalizes a path, removing double and single dot path steps,
* and removing any final directory separator.
* <p>
* This method normalizes a path to a standard format.
* The input may contain separators in either Unix or Windows format.
* The output will contain separators in the format of the system.
* <p>
* A trailing slash will be removed.
* A double slash will be merged to a single slash (but UNC names are handled).
* A single dot path segment will be removed.
* A double dot will cause that path segment and the one before to be removed.
* If the double dot has no parent path segment to work with, <code>null</code>
* is returned.
* <p>
* The output will be the same on both Unix and Windows except
* for the separator character.
* <pre>
* /foo// --> /foo
* /foo/./ --> /foo
* /foo/../bar --> /bar
* /foo/../bar/ --> /bar
* /foo/../bar/../baz --> /baz
* //foo//./bar --> /foo/bar
* /../ --> null
* ../foo --> null
* foo/bar/.. --> foo
* foo/../../bar --> null
* foo/../bar --> bar
* //server/foo/../bar --> //server/bar
* //server/../bar --> null
* C:\foo\..\bar --> C:\bar
* C:\..\bar --> null
* ~/foo/../bar/ --> ~/bar
* ~/../bar --> null
* </pre>
* (Note the file separator returned will be correct for Windows/Unix)
*
* @param filename the filename to normalize, null returns null
* @return the normalized filename, or null if invalid
*/
public static String normalizeNoEndSeparator(String filename) {
return doNormalize(filename, false);
}
/**
* Internal method to perform the normalization.
*
* @param filename the filename
* @param keepSeparator true to keep the final separator
* @return the normalized filename
*/
private static String doNormalize(String filename, boolean keepSeparator) {
if (filename == null) {
return null;
}
int size = filename.length();
if (size == 0) {
return filename;
}
int prefix = getPrefixLength(filename);
if (prefix < 0) {
return null;
}
char[] array = new char[size + 2]; // +1 for possible extra slash, +2 for arraycopy
filename.getChars(0, filename.length(), array, 0);
// fix separators throughout
for (int i = 0; i < array.length; i++) {
if (array[i] == OTHER_SEPARATOR) {
array[i] = SYSTEM_SEPARATOR;
}
}
// add extra separator on the end to simplify code below
boolean lastIsDirectory = true;
if (array[size - 1] != SYSTEM_SEPARATOR) {
array[size++] = SYSTEM_SEPARATOR;
lastIsDirectory = false;
}
// adjoining slashes
for (int i = prefix + 1; i < size; i++) {
if (array[i] == SYSTEM_SEPARATOR && array[i - 1] == SYSTEM_SEPARATOR) {
System.arraycopy(array, i, array, i - 1, size - i);
size--;
i--;
}
}
// dot slash
for (int i = prefix + 1; i < size; i++) {
if (array[i] == SYSTEM_SEPARATOR && array[i - 1] == '.' &&
(i == prefix + 1 || array[i - 2] == SYSTEM_SEPARATOR)) {
if (i == size - 1) {
lastIsDirectory = true;
}
System.arraycopy(array, i + 1, array, i - 1, size - i);
size -=2;
i--;
}
}
// double dot slash
outer:
for (int i = prefix + 2; i < size; i++) {
if (array[i] == SYSTEM_SEPARATOR && array[i - 1] == '.' && array[i - 2] == '.' &&
(i == prefix + 2 || array[i - 3] == SYSTEM_SEPARATOR)) {
if (i == prefix + 2) {
return null;
}
if (i == size - 1) {
lastIsDirectory = true;
}
int j;
for (j = i - 4 ; j >= prefix; j--) {
if (array[j] == SYSTEM_SEPARATOR) {
// remove b/../ from a/b/../c
System.arraycopy(array, i + 1, array, j + 1, size - i);
size -= (i - j);
i = j + 1;
continue outer;
}
}
// remove a/../ from a/../c
System.arraycopy(array, i + 1, array, prefix, size - i);
size -= (i + 1 - prefix);
i = prefix + 1;
}
}
if (size <= 0) { // should never be less than 0
return "";
}
if (size <= prefix) { // should never be less than prefix
return new String(array, 0, size);
}
if (lastIsDirectory && keepSeparator) {
return new String(array, 0, size); // keep trailing separator
}
return new String(array, 0, size - 1); // lose trailing separator
}
//-----------------------------------------------------------------------
/**
* Concatenates a filename to a base path using normal command line style rules.
* <p>
* The effect is equivalent to resultant directory after changing
* directory to the first argument, followed by changing directory to
* the second argument.
* <p>
* The first argument is the base path, the second is the path to concatenate.
* The returned path is always normalized via {@link #normalize(String)},
* thus <code>..</code> is handled.
* <p>
* If <code>pathToAdd</code> is absolute (has an absolute prefix), then
* it will be normalized and returned.
* Otherwise, the paths will be joined, normalized and returned.
* <p>
* The output will be the same on both Unix and Windows except
* for the separator character.
* <pre>
* /foo/ + bar --> /foo/bar
* /foo + bar --> /foo/bar
* /foo + /bar --> /bar
* /foo + C:/bar --> C:/bar
* /foo + C:bar --> C:bar (*)
* /foo/a/ + ../bar --> foo/bar
* /foo/ + ../../bar --> null
* /foo/ + /bar --> /bar
* /foo/.. + /bar --> /bar
* /foo + bar/c.txt --> /foo/bar/c.txt
* /foo/c.txt + bar --> /foo/c.txt/bar (!)
* </pre>
* (*) Note that the Windows relative drive prefix is unreliable when
* used with this method.
* (!) Note that the first parameter must be a path. If it ends with a name, then
* the name will be built into the concatenated path. If this might be a problem,
* use {@link #getFullPath(String)} on the base path argument.
*
* @param basePath the base path to attach to, always treated as a path
* @param fullFilenameToAdd the filename (or path) to attach to the base
* @return the concatenated path, or null if invalid
*/
public static String concat(String basePath, String fullFilenameToAdd) {
int prefix = getPrefixLength(fullFilenameToAdd);
if (prefix < 0) {
return null;
}
if (prefix > 0) {
return normalize(fullFilenameToAdd);
}
if (basePath == null) {
return null;
}
int len = basePath.length();
if (len == 0) {
return normalize(fullFilenameToAdd);
}
char ch = basePath.charAt(len - 1);
if (isSeparator(ch)) {
return normalize(basePath + fullFilenameToAdd);
} else {
return normalize(basePath + '/' + fullFilenameToAdd);
}
}
//-----------------------------------------------------------------------
/**
* Converts all separators to the Unix separator of forward slash.
*
* @param path the path to be changed, null ignored
* @return the updated path
*/
public static String separatorsToUnix(String path) {
if (path == null || path.indexOf(WINDOWS_SEPARATOR) == -1) {
return path;
}
return path.replace(WINDOWS_SEPARATOR, UNIX_SEPARATOR);
}
/**
* Converts all separators to the Windows separator of backslash.
*
* @param path the path to be changed, null ignored
* @return the updated path
*/
public static String separatorsToWindows(String path) {
if (path == null || path.indexOf(UNIX_SEPARATOR) == -1) {
return path;
}
return path.replace(UNIX_SEPARATOR, WINDOWS_SEPARATOR);
}
/**
* Converts all separators to the system separator.
*
* @param path the path to be changed, null ignored
* @return the updated path
*/
public static String separatorsToSystem(String path) {
if (path == null) {
return null;
}
if (isSystemWindows()) {
return separatorsToWindows(path);
} else {
return separatorsToUnix(path);
}
}
//-----------------------------------------------------------------------
/**
* Returns the length of the filename prefix, such as <code>C:/</code> or <code>~/</code>.
* <p>
* This method will handle a file in either Unix or Windows format.
* <p>
* The prefix length includes the first slash in the full filename
* if applicable. Thus, it is possible that the length returned is greater
* than the length of the input string.
* <pre>
* Windows:
* a\b\c.txt --> "" --> relative
* \a\b\c.txt --> "\" --> current drive absolute
* C:a\b\c.txt --> "C:" --> drive relative
* C:\a\b\c.txt --> "C:\" --> absolute
* \\server\a\b\c.txt --> "\\server\" --> UNC
*
* Unix:
* a/b/c.txt --> "" --> relative
* /a/b/c.txt --> "/" --> absolute
* ~/a/b/c.txt --> "~/" --> current user
* ~ --> "~/" --> current user (slash added)
* ~user/a/b/c.txt --> "~user/" --> named user
* ~user --> "~user/" --> named user (slash added)
* </pre>
* <p>
* The output will be the same irrespective of the machine that the code is running on.
* ie. both Unix and Windows prefixes are matched regardless.
*
* @param filename the filename to find the prefix in, null returns -1
* @return the length of the prefix, -1 if invalid or null
*/
public static int getPrefixLength(String filename) {
if (filename == null) {
return -1;
}
int len = filename.length();
if (len == 0) {
return 0;
}
char ch0 = filename.charAt(0);
if (ch0 == ':') {
return -1;
}
if (len == 1) {
if (ch0 == '~') {
return 2; // return a length greater than the input
}
return (isSeparator(ch0) ? 1 : 0);
} else {
if (ch0 == '~') {
int posUnix = filename.indexOf(UNIX_SEPARATOR, 1);
int posWin = filename.indexOf(WINDOWS_SEPARATOR, 1);
if (posUnix == -1 && posWin == -1) {
return len + 1; // return a length greater than the input
}
posUnix = (posUnix == -1 ? posWin : posUnix);
posWin = (posWin == -1 ? posUnix : posWin);
return Math.min(posUnix, posWin) + 1;
}
char ch1 = filename.charAt(1);
if (ch1 == ':') {
ch0 = Character.toUpperCase(ch0);
if (ch0 >= 'A' && ch0 <= 'Z') {
if (len == 2 || isSeparator(filename.charAt(2)) == false) {
return 2;
}
return 3;
}
return -1;
} else if (isSeparator(ch0) && isSeparator(ch1)) {
int posUnix = filename.indexOf(UNIX_SEPARATOR, 2);
int posWin = filename.indexOf(WINDOWS_SEPARATOR, 2);
if ((posUnix == -1 && posWin == -1) || posUnix == 2 || posWin == 2) {
return -1;
}
posUnix = (posUnix == -1 ? posWin : posUnix);
posWin = (posWin == -1 ? posUnix : posWin);
return Math.min(posUnix, posWin) + 1;
} else {
return (isSeparator(ch0) ? 1 : 0);
}
}
}
/**
* Returns the index of the last directory separator character.
* <p>
* This method will handle a file in either Unix or Windows format.
* The position of the last forward or backslash is returned.
* <p>
* The output will be the same irrespective of the machine that the code is running on.
*
* @param filename the filename to find the last path separator in, null returns -1
* @return the index of the last separator character, or -1 if there
* is no such character
*/
public static int indexOfLastSeparator(String filename) {
if (filename == null) {
return -1;
}
int lastUnixPos = filename.lastIndexOf(UNIX_SEPARATOR);
int lastWindowsPos = filename.lastIndexOf(WINDOWS_SEPARATOR);
return Math.max(lastUnixPos, lastWindowsPos);
}
/**
* Returns the index of the last extension separator character, which is a dot.
* <p>
* This method also checks that there is no directory separator after the last dot.
* To do this it uses {@link #indexOfLastSeparator(String)} which will
* handle a file in either Unix or Windows format.
* <p>
* The output will be the same irrespective of the machine that the code is running on.
*
* @param filename the filename to find the last path separator in, null returns -1
* @return the index of the last separator character, or -1 if there
* is no such character
*/
public static int indexOfExtension(String filename) {
if (filename == null) {
return -1;
}
int extensionPos = filename.lastIndexOf(EXTENSION_SEPARATOR);
int lastSeparator = indexOfLastSeparator(filename);
return (lastSeparator > extensionPos ? -1 : extensionPos);
}
//-----------------------------------------------------------------------
/**
* Gets the prefix from a full filename, such as <code>C:/</code>
* or <code>~/</code>.
* <p>
* This method will handle a file in either Unix or Windows format.
* The prefix includes the first slash in the full filename where applicable.
* <pre>
* Windows:
* a\b\c.txt --> "" --> relative
* \a\b\c.txt --> "\" --> current drive absolute
* C:a\b\c.txt --> "C:" --> drive relative
* C:\a\b\c.txt --> "C:\" --> absolute
* \\server\a\b\c.txt --> "\\server\" --> UNC
*
* Unix:
* a/b/c.txt --> "" --> relative
* /a/b/c.txt --> "/" --> absolute
* ~/a/b/c.txt --> "~/" --> current user
* ~ --> "~/" --> current user (slash added)
* ~user/a/b/c.txt --> "~user/" --> named user
* ~user --> "~user/" --> named user (slash added)
* </pre>
* <p>
* The output will be the same irrespective of the machine that the code is running on.
* ie. both Unix and Windows prefixes are matched regardless.
*
* @param filename the filename to query, null returns null
* @return the prefix of the file, null if invalid
*/
public static String getPrefix(String filename) {
if (filename == null) {
return null;
}
int len = getPrefixLength(filename);
if (len < 0) {
return null;
}
if (len > filename.length()) {
return filename + UNIX_SEPARATOR; // we know this only happens for unix
}
return filename.substring(0, len);
}
/**
* Gets the path from a full filename, which excludes the prefix.
* <p>
* This method will handle a file in either Unix or Windows format.
* The method is entirely text based, and returns the text before and
* including the last forward or backslash.
* <pre>
* C:\a\b\c.txt --> a\b\
* ~/a/b/c.txt --> a/b/
* a.txt --> ""
* a/b/c --> a/b/
* a/b/c/ --> a/b/c/
* </pre>
* <p>
* The output will be the same irrespective of the machine that the code is running on.
* <p>
* This method drops the prefix from the result.
* See {@link #getFullPath(String)} for the method that retains the prefix.
*
* @param filename the filename to query, null returns null
* @return the path of the file, an empty string if none exists, null if invalid
*/
public static String getPath(String filename) {
return doGetPath(filename, 1);
}
/**
* Gets the path from a full filename, which excludes the prefix, and
* also excluding the final directory separator.
* <p>
* This method will handle a file in either Unix or Windows format.
* The method is entirely text based, and returns the text before the
* last forward or backslash.
* <pre>
* C:\a\b\c.txt --> a\b
* ~/a/b/c.txt --> a/b
* a.txt --> ""
* a/b/c --> a/b
* a/b/c/ --> a/b/c
* </pre>
* <p>
* The output will be the same irrespective of the machine that the code is running on.
* <p>
* This method drops the prefix from the result.
* See {@link #getFullPathNoEndSeparator(String)} for the method that retains the prefix.
*
* @param filename the filename to query, null returns null
* @return the path of the file, an empty string if none exists, null if invalid
*/
public static String getPathNoEndSeparator(String filename) {
return doGetPath(filename, 0);
}
/**
* Does the work of getting the path.
*
* @param filename the filename
* @param separatorAdd 0 to omit the end separator, 1 to return it
* @return the path
*/
private static String doGetPath(String filename, int separatorAdd) {
if (filename == null) {
return null;
}
int prefix = getPrefixLength(filename);
if (prefix < 0) {
return null;
}
int index = indexOfLastSeparator(filename);
if (prefix >= filename.length() || index < 0) {
return "";
}
return filename.substring(prefix, index + separatorAdd);
}
/**
* Gets the full path from a full filename, which is the prefix + path.
* <p>
* This method will handle a file in either Unix or Windows format.
* The method is entirely text based, and returns the text before and
* including the last forward or backslash.
* <pre>
* C:\a\b\c.txt --> C:\a\b\
* ~/a/b/c.txt --> ~/a/b/
* a.txt --> ""
* a/b/c --> a/b/
* a/b/c/ --> a/b/c/
* C: --> C:
* C:\ --> C:\
* ~ --> ~/
* ~/ --> ~/
* ~user --> ~user/
* ~user/ --> ~user/
* </pre>
* <p>
* The output will be the same irrespective of the machine that the code is running on.
*
* @param filename the filename to query, null returns null
* @return the path of the file, an empty string if none exists, null if invalid
*/
public static String getFullPath(String filename) {
return doGetFullPath(filename, true);
}
/**
* Gets the full path from a full filename, which is the prefix + path,
* and also excluding the final directory separator.
* <p>
* This method will handle a file in either Unix or Windows format.
* The method is entirely text based, and returns the text before the
* last forward or backslash.
* <pre>
* C:\a\b\c.txt --> C:\a\b
* ~/a/b/c.txt --> ~/a/b
* a.txt --> ""
* a/b/c --> a/b
* a/b/c/ --> a/b/c
* C: --> C:
* C:\ --> C:\
* ~ --> ~
* ~/ --> ~
* ~user --> ~user
* ~user/ --> ~user
* </pre>
* <p>
* The output will be the same irrespective of the machine that the code is running on.
*
* @param filename the filename to query, null returns null
* @return the path of the file, an empty string if none exists, null if invalid
*/
public static String getFullPathNoEndSeparator(String filename) {
return doGetFullPath(filename, false);
}
/**
* Does the work of getting the path.
*
* @param filename the filename
* @param includeSeparator true to include the end separator
* @return the path
*/
private static String doGetFullPath(String filename, boolean includeSeparator) {
if (filename == null) {
return null;
}
int prefix = getPrefixLength(filename);
if (prefix < 0) {
return null;
}
if (prefix >= filename.length()) {
if (includeSeparator) {
return getPrefix(filename); // add end slash if necessary
} else {
return filename;
}
}
int index = indexOfLastSeparator(filename);
if (index < 0) {
return filename.substring(0, prefix);
}
int end = index + (includeSeparator ? 1 : 0);
return filename.substring(0, end);
}
/**
* Gets the name minus the path from a full filename.
* <p>
* This method will handle a file in either Unix or Windows format.
* The text after the last forward or backslash is returned.
* <pre>
* a/b/c.txt --> c.txt
* a.txt --> a.txt
* a/b/c --> c
* a/b/c/ --> ""
* </pre>
* <p>
* The output will be the same irrespective of the machine that the code is running on.
*
* @param filename the filename to query, null returns null
* @return the name of the file without the path, or an empty string if none exists
*/
public static String getName(String filename) {
if (filename == null) {
return null;
}
int index = indexOfLastSeparator(filename);
return filename.substring(index + 1);
}
/**
* Gets the base name, minus the full path and extension, from a full filename.
* <p>
* This method will handle a file in either Unix or Windows format.
* The text after the last forward or backslash and before the last dot is returned.
* <pre>
* a/b/c.txt --> c
* a.txt --> a
* a/b/c --> c
* a/b/c/ --> ""
* </pre>
* <p>
* The output will be the same irrespective of the machine that the code is running on.
*
* @param filename the filename to query, null returns null
* @return the name of the file without the path, or an empty string if none exists
*/
public static String getBaseName(String filename) {
return removeExtension(getName(filename));
}
/**
* Gets the extension of a filename.
* <p>
* This method returns the textual part of the filename after the last dot.
* There must be no directory separator after the dot.
* <pre>
* foo.txt --> "txt"
* a/b/c.jpg --> "jpg"
* a/b.txt/c --> ""
* a/b/c --> ""
* </pre>
* <p>
* The output will be the same irrespective of the machine that the code is running on.
*
* @param filename the filename to retrieve the extension of.
* @return the extension of the file or an empty string if none exists.
*/
public static String getExtension(String filename) {
if (filename == null) {
return null;
}
int index = indexOfExtension(filename);
if (index == -1) {
return "";
} else {
return filename.substring(index + 1);
}
}
//-----------------------------------------------------------------------
/**
* Removes the extension from a filename.
* <p>
* This method returns the textual part of the filename before the last dot.
* There must be no directory separator after the dot.
* <pre>
* foo.txt --> foo
* a\b\c.jpg --> a\b\c
* a\b\c --> a\b\c
* a.b\c --> a.b\c
* </pre>
* <p>
* The output will be the same irrespective of the machine that the code is running on.
*
* @param filename the filename to query, null returns null
* @return the filename minus the extension
*/
public static String removeExtension(String filename) {
if (filename == null) {
return null;
}
int index = indexOfExtension(filename);
if (index == -1) {
return filename;
} else {
return filename.substring(0, index);
}
}
//-----------------------------------------------------------------------
/**
* Checks whether two filenames are equal exactly.
* <p>
* No processing is performed on the filenames other than comparison,
* thus this is merely a null-safe case-sensitive equals.
*
* @param filename1 the first filename to query, may be null
* @param filename2 the second filename to query, may be null
* @return true if the filenames are equal, null equals null
* @see IOCase#SENSITIVE
*/
public static boolean equals(String filename1, String filename2) {
return equals(filename1, filename2, false, IOCase.SENSITIVE);
}
/**
* Checks whether two filenames are equal using the case rules of the system.
* <p>
* No processing is performed on the filenames other than comparison.
* The check is case-sensitive on Unix and case-insensitive on Windows.
*
* @param filename1 the first filename to query, may be null
* @param filename2 the second filename to query, may be null
* @return true if the filenames are equal, null equals null
* @see IOCase#SYSTEM
*/
public static boolean equalsOnSystem(String filename1, String filename2) {
return equals(filename1, filename2, false, IOCase.SYSTEM);
}
//-----------------------------------------------------------------------
/**
* Checks whether two filenames are equal after both have been normalized.
* <p>
* Both filenames are first passed to {@link #normalize(String)}.
* The check is then performed in a case-sensitive manner.
*
* @param filename1 the first filename to query, may be null
* @param filename2 the second filename to query, may be null
* @return true if the filenames are equal, null equals null
* @see IOCase#SENSITIVE
*/
public static boolean equalsNormalized(String filename1, String filename2) {
return equals(filename1, filename2, true, IOCase.SENSITIVE);
}
/**
* Checks whether two filenames are equal after both have been normalized
* and using the case rules of the system.
* <p>
* Both filenames are first passed to {@link #normalize(String)}.
* The check is then performed case-sensitive on Unix and
* case-insensitive on Windows.
*
* @param filename1 the first filename to query, may be null
* @param filename2 the second filename to query, may be null
* @return true if the filenames are equal, null equals null
* @see IOCase#SYSTEM
*/
public static boolean equalsNormalizedOnSystem(String filename1, String filename2) {
return equals(filename1, filename2, true, IOCase.SYSTEM);
}
/**
* Checks whether two filenames are equal, optionally normalizing and providing
* control over the case-sensitivity.
*
* @param filename1 the first filename to query, may be null
* @param filename2 the second filename to query, may be null
* @param normalized whether to normalize the filenames
* @param caseSensitivity what case sensitivity rule to use, null means case-sensitive
* @return true if the filenames are equal, null equals null
* @since Commons IO 1.3
*/
public static boolean equals(
String filename1, String filename2,
boolean normalized, IOCase caseSensitivity) {
if (filename1 == null || filename2 == null) {
return filename1 == filename2;
}
if (normalized) {
filename1 = normalize(filename1);
filename2 = normalize(filename2);
if (filename1 == null || filename2 == null) {
throw new NullPointerException(
"Error normalizing one or both of the file names");
}
}
if (caseSensitivity == null) {
caseSensitivity = IOCase.SENSITIVE;
}
return caseSensitivity.checkEquals(filename1, filename2);
}
//-----------------------------------------------------------------------
/**
* Checks whether the extension of the filename is that specified.
* <p>
* This method obtains the extension as the textual part of the filename
* after the last dot. There must be no directory separator after the dot.
* The extension check is case-sensitive on all platforms.
*
* @param filename the filename to query, null returns false
* @param extension the extension to check for, null or empty checks for no extension
* @return true if the filename has the specified extension
*/
public static boolean isExtension(String filename, String extension) {
if (filename == null) {
return false;
}
if (extension == null || extension.length() == 0) {
return (indexOfExtension(filename) == -1);
}
String fileExt = getExtension(filename);
return fileExt.equals(extension);
}
/**
* Checks whether the extension of the filename is one of those specified.
* <p>
* This method obtains the extension as the textual part of the filename
* after the last dot. There must be no directory separator after the dot.
* The extension check is case-sensitive on all platforms.
*
* @param filename the filename to query, null returns false
* @param extensions the extensions to check for, null checks for no extension
* @return true if the filename is one of the extensions
*/
public static boolean isExtension(String filename, String[] extensions) {
if (filename == null) {
return false;
}
if (extensions == null || extensions.length == 0) {
return (indexOfExtension(filename) == -1);
}
String fileExt = getExtension(filename);
for (int i = 0; i < extensions.length; i++) {
if (fileExt.equals(extensions[i])) {
return true;
}
}
return false;
}
/**
* Checks whether the extension of the filename is one of those specified.
* <p>
* This method obtains the extension as the textual part of the filename
* after the last dot. There must be no directory separator after the dot.
* The extension check is case-sensitive on all platforms.
*
* @param filename the filename to query, null returns false
* @param extensions the extensions to check for, null checks for no extension
* @return true if the filename is one of the extensions
*/
public static boolean isExtension(String filename, Collection extensions) {
if (filename == null) {
return false;
}
if (extensions == null || extensions.isEmpty()) {
return (indexOfExtension(filename) == -1);
}
String fileExt = getExtension(filename);
for (Iterator it = extensions.iterator(); it.hasNext();) {
if (fileExt.equals(it.next())) {
return true;
}
}
return false;
}
//-----------------------------------------------------------------------
/**
* Checks a filename to see if it matches the specified wildcard matcher,
* always testing case-sensitive.
* <p>
* The wildcard matcher uses the characters '?' and '*' to represent a
* single or multiple wildcard characters.
* This is the same as often found on Dos/Unix command lines.
* The check is case-sensitive always.
* <pre>
* wildcardMatch("c.txt", "*.txt") --> true
* wildcardMatch("c.txt", "*.jpg") --> false
* wildcardMatch("a/b/c.txt", "a/b/*") --> true
* wildcardMatch("c.txt", "*.???") --> true
* wildcardMatch("c.txt", "*.????") --> false
* </pre>
*
* @param filename the filename to match on
* @param wildcardMatcher the wildcard string to match against
* @return true if the filename matches the wilcard string
* @see IOCase#SENSITIVE
*/
public static boolean wildcardMatch(String filename, String wildcardMatcher) {
return wildcardMatch(filename, wildcardMatcher, IOCase.SENSITIVE);
}
/**
* Checks a filename to see if it matches the specified wildcard matcher
* using the case rules of the system.
* <p>
* The wildcard matcher uses the characters '?' and '*' to represent a
* single or multiple wildcard characters.
* This is the same as often found on Dos/Unix command lines.
* The check is case-sensitive on Unix and case-insensitive on Windows.
* <pre>
* wildcardMatch("c.txt", "*.txt") --> true
* wildcardMatch("c.txt", "*.jpg") --> false
* wildcardMatch("a/b/c.txt", "a/b/*") --> true
* wildcardMatch("c.txt", "*.???") --> true
* wildcardMatch("c.txt", "*.????") --> false
* </pre>
*
* @param filename the filename to match on
* @param wildcardMatcher the wildcard string to match against
* @return true if the filename matches the wilcard string
* @see IOCase#SYSTEM
*/
public static boolean wildcardMatchOnSystem(String filename, String wildcardMatcher) {
return wildcardMatch(filename, wildcardMatcher, IOCase.SYSTEM);
}
/**
* Checks a filename to see if it matches the specified wildcard matcher
* allowing control over case-sensitivity.
* <p>
* The wildcard matcher uses the characters '?' and '*' to represent a
* single or multiple wildcard characters.
*
* @param filename the filename to match on
* @param wildcardMatcher the wildcard string to match against
* @param caseSensitivity what case sensitivity rule to use, null means case-sensitive
* @return true if the filename matches the wilcard string
* @since Commons IO 1.3
*/
public static boolean wildcardMatch(String filename, String wildcardMatcher, IOCase caseSensitivity) {
if (filename == null && wildcardMatcher == null) {
return true;
}
if (filename == null || wildcardMatcher == null) {
return false;
}
if (caseSensitivity == null) {
caseSensitivity = IOCase.SENSITIVE;
}
filename = caseSensitivity.convertCase(filename);
wildcardMatcher = caseSensitivity.convertCase(wildcardMatcher);
String[] wcs = splitOnTokens(wildcardMatcher);
boolean anyChars = false;
int textIdx = 0;
int wcsIdx = 0;
Stack backtrack = new Stack();
// loop around a backtrack stack, to handle complex * matching
do {
if (backtrack.size() > 0) {
int[] array = (int[]) backtrack.pop();
wcsIdx = array[0];
textIdx = array[1];
anyChars = true;
}
// loop whilst tokens and text left to process
while (wcsIdx < wcs.length) {
if (wcs[wcsIdx].equals("?")) {
// ? so move to next text char
textIdx++;
anyChars = false;
} else if (wcs[wcsIdx].equals("*")) {
// set any chars status
anyChars = true;
if (wcsIdx == wcs.length - 1) {
textIdx = filename.length();
}
} else {
// matching text token
if (anyChars) {
// any chars then try to locate text token
textIdx = filename.indexOf(wcs[wcsIdx], textIdx);
if (textIdx == -1) {
// token not found
break;
}
int repeat = filename.indexOf(wcs[wcsIdx], textIdx + 1);
if (repeat >= 0) {
backtrack.push(new int[] {wcsIdx, repeat});
}
} else {
// matching from current position
if (!filename.startsWith(wcs[wcsIdx], textIdx)) {
// couldnt match token
break;
}
}
// matched text token, move text index to end of matched token
textIdx += wcs[wcsIdx].length();
anyChars = false;
}
wcsIdx++;
}
// full match
if (wcsIdx == wcs.length && textIdx == filename.length()) {
return true;
}
} while (backtrack.size() > 0);
return false;
}
/**
* Splits a string into a number of tokens.
*
* @param text the text to split
* @return the tokens, never null
*/
static String[] splitOnTokens(String text) {
// used by wildcardMatch
// package level so a unit test may run on this
if (text.indexOf("?") == -1 && text.indexOf("*") == -1) {
return new String[] { text };
}
char[] array = text.toCharArray();
ArrayList list = new ArrayList();
StringBuffer buffer = new StringBuffer();
for (int i = 0; i < array.length; i++) {
if (array[i] == '?' || array[i] == '*') {
if (buffer.length() != 0) {
list.add(buffer.toString());
buffer.setLength(0);
}
if (array[i] == '?') {
list.add("?");
} else if (list.size() == 0 ||
(i > 0 && list.get(list.size() - 1).equals("*") == false)) {
list.add("*");
}
} else {
buffer.append(array[i]);
}
}
if (buffer.length() != 0) {
list.add(buffer.toString());
}
return (String[]) list.toArray( new String[ list.size() ] );
}
}
/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
/**
* Enumeration of IO case sensitivity.
* <p>
* Different filing systems have different rules for case-sensitivity.
* Windows is case-insensitive, Unix is case-sensitive.
* <p>
* This class captures that difference, providing an enumeration to
* control how filename comparisons should be performed. It also provides
* methods that use the enumeration to perform comparisons.
* <p>
* Wherever possible, you should use the <code>check</code> methods in this
* class to compare filenames.
*
* @author Stephen Colebourne
* @version $Id: IOCase.java 606345 2007-12-21 23:43:01Z ggregory $
* @since Commons IO 1.3
*/
final class IOCase implements Serializable {
/**
* The constant for case sensitive regardless of operating system.
*/
public static final IOCase SENSITIVE = new IOCase("Sensitive", true);
/**
* The constant for case insensitive regardless of operating system.
*/
public static final IOCase INSENSITIVE = new IOCase("Insensitive", false);
/**
* The constant for case sensitivity determined by the current operating system.
* Windows is case-insensitive when comparing filenames, Unix is case-sensitive.
* <p>
* If you derialize this constant of Windows, and deserialize on Unix, or vice
* versa, then the value of the case-sensitivity flag will change.
*/
public static final IOCase SYSTEM = new IOCase("System", !FilenameUtils.isSystemWindows());
/** Serialization version. */
private static final long serialVersionUID = -6343169151696340687L;
/** The enumeration name. */
private final String name;
/** The sensitivity flag. */
private final transient boolean sensitive;
//-----------------------------------------------------------------------
/**
* Factory method to create an IOCase from a name.
*
* @param name the name to find
* @return the IOCase object
* @throws IllegalArgumentException if the name is invalid
*/
public static IOCase forName(String name) {
if (IOCase.SENSITIVE.name.equals(name)){
return IOCase.SENSITIVE;
}
if (IOCase.INSENSITIVE.name.equals(name)){
return IOCase.INSENSITIVE;
}
if (IOCase.SYSTEM.name.equals(name)){
return IOCase.SYSTEM;
}
throw new IllegalArgumentException("Invalid IOCase name: " + name);
}
//-----------------------------------------------------------------------
/**
* Private constructor.
*
* @param name the name
* @param sensitive the sensitivity
*/
private IOCase(String name, boolean sensitive) {
this.name = name;
this.sensitive = sensitive;
}
/**
* Replaces the enumeration from the stream with a real one.
* This ensures that the correct flag is set for SYSTEM.
*
* @return the resolved object
*/
private Object readResolve() {
return forName(name);
}
//-----------------------------------------------------------------------
/**
* Gets the name of the constant.
*
* @return the name of the constant
*/
public String getName() {
return name;
}
/**
* Does the object represent case sensitive comparison.
*
* @return true if case sensitive
*/
public boolean isCaseSensitive() {
return sensitive;
}
//-----------------------------------------------------------------------
/**
* Compares two strings using the case-sensitivity rule.
* <p>
* This method mimics {@link String#compareTo} but takes case-sensitivity
* into account.
*
* @param str1 the first string to compare, not null
* @param str2 the second string to compare, not null
* @return true if equal using the case rules
* @throws NullPointerException if either string is null
*/
public int checkCompareTo(String str1, String str2) {
if (str1 == null || str2 == null) {
throw new NullPointerException("The strings must not be null");
}
return sensitive ? str1.compareTo(str2) : str1.compareToIgnoreCase(str2);
}
/**
* Compares two strings using the case-sensitivity rule.
* <p>
* This method mimics {@link String#equals} but takes case-sensitivity
* into account.
*
* @param str1 the first string to compare, not null
* @param str2 the second string to compare, not null
* @return true if equal using the case rules
* @throws NullPointerException if either string is null
*/
public boolean checkEquals(String str1, String str2) {
if (str1 == null || str2 == null) {
throw new NullPointerException("The strings must not be null");
}
return sensitive ? str1.equals(str2) : str1.equalsIgnoreCase(str2);
}
/**
* Checks if one string starts with another using the case-sensitivity rule.
* <p>
* This method mimics {@link String#startsWith(String)} but takes case-sensitivity
* into account.
*
* @param str the string to check, not null
* @param start the start to compare against, not null
* @return true if equal using the case rules
* @throws NullPointerException if either string is null
*/
public boolean checkStartsWith(String str, String start) {
return str.regionMatches(!sensitive, 0, start, 0, start.length());
}
/**
* Checks if one string ends with another using the case-sensitivity rule.
* <p>
* This method mimics {@link String#endsWith} but takes case-sensitivity
* into account.
*
* @param str the string to check, not null
* @param end the end to compare against, not null
* @return true if equal using the case rules
* @throws NullPointerException if either string is null
*/
public boolean checkEndsWith(String str, String end) {
int endLen = end.length();
return str.regionMatches(!sensitive, str.length() - endLen, end, 0, endLen);
}
/**
* Checks if one string contains another at a specific index using the case-sensitivity rule.
* <p>
* This method mimics parts of {@link String#regionMatches(boolean, int, String, int, int)}
* but takes case-sensitivity into account.
*
* @param str the string to check, not null
* @param strStartIndex the index to start at in str
* @param search the start to search for, not null
* @return true if equal using the case rules
* @throws NullPointerException if either string is null
*/
public boolean checkRegionMatches(String str, int strStartIndex, String search) {
return str.regionMatches(!sensitive, strStartIndex, search, 0, search.length());
}
/**
* Converts the case of the input String to a standard format.
* Subsequent operations can then use standard String methods.
*
* @param str the string to convert, null returns null
* @return the lower-case version if case-insensitive
*/
String convertCase(String str) {
if (str == null) {
return null;
}
return sensitive ? str : str.toLowerCase();
}
//-----------------------------------------------------------------------
/**
* Gets a string describing the sensitivity.
*
* @return a string describing the sensitivity
*/
public String toString() {
return name;
}
}
]]>