org.jivesoftware.smack.util.StringUtils Maven / Gradle / Ivy
/**
* $RCSfile$
* $Revision: 11823 $
* $Date: 2010-08-15 08:20:48 -0500 (Sun, 15 Aug 2010) $
*
* Copyright 2003-2007 Jive Software.
*
* All rights reserved. Licensed 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.
*/
package org.jivesoftware.smack.util;
import java.io.UnsupportedEncodingException;
import java.security.MessageDigest;
import java.security.NoSuchAlgorithmException;
import java.text.DateFormat;
import java.text.ParseException;
import java.text.SimpleDateFormat;
import java.util.Date;
import java.util.Random;
import java.util.TimeZone;
/**
* A collection of utility methods for String objects.
*/
public class StringUtils {
/**
* Date format as defined in XEP-0082 - XMPP Date and Time Profiles. The time zone is set to
* UTC.
*
* Date formats are not synchronized. Since multiple threads access the format concurrently, it
* must be synchronized externally or you can use the convenience methods
* {@link #parseXEP0082Date(String)} and {@link #formatXEP0082Date(Date)}.
*/
public static final DateFormat XEP_0082_UTC_FORMAT = new SimpleDateFormat(
"yyyy-MM-dd'T'HH:mm:ss.SSS'Z'");
static {
XEP_0082_UTC_FORMAT.setTimeZone(TimeZone.getTimeZone("UTC"));
}
private static final char[] QUOTE_ENCODE = """.toCharArray();
private static final char[] APOS_ENCODE = "'".toCharArray();
private static final char[] AMP_ENCODE = "&".toCharArray();
private static final char[] LT_ENCODE = "<".toCharArray();
private static final char[] GT_ENCODE = ">".toCharArray();
/**
* Parses the given date string in the XEP-0082 - XMPP Date and Time Profiles format.
*
* @param dateString the date string to parse
* @return the parsed Date
* @throws ParseException if the specified string cannot be parsed
*/
public static Date parseXEP0082Date(String dateString) throws ParseException {
synchronized (XEP_0082_UTC_FORMAT) {
return XEP_0082_UTC_FORMAT.parse(dateString);
}
}
/**
* Formats a Date into a XEP-0082 - XMPP Date and Time Profiles string.
*
* @param date the time value to be formatted into a time string
* @return the formatted time string in XEP-0082 format
*/
public static String formatXEP0082Date(Date date) {
synchronized (XEP_0082_UTC_FORMAT) {
return XEP_0082_UTC_FORMAT.format(date);
}
}
/**
* Returns the name portion of a XMPP address. For example, for the
* address "[email protected]/Smack", "matt" would be returned. If no
* username is present in the address, the empty string will be returned.
*
* @param XMPPAddress the XMPP address.
* @return the name portion of the XMPP address.
*/
public static String parseName(String XMPPAddress) {
if (XMPPAddress == null) {
return null;
}
int atIndex = XMPPAddress.lastIndexOf("@");
if (atIndex <= 0) {
return "";
}
else {
return XMPPAddress.substring(0, atIndex);
}
}
/**
* Returns the server portion of a XMPP address. For example, for the
* address "[email protected]/Smack", "jivesoftware.com" would be returned.
* If no server is present in the address, the empty string will be returned.
*
* @param XMPPAddress the XMPP address.
* @return the server portion of the XMPP address.
*/
public static String parseServer(String XMPPAddress) {
if (XMPPAddress == null) {
return null;
}
int atIndex = XMPPAddress.lastIndexOf("@");
// If the String ends with '@', return the empty string.
if (atIndex + 1 > XMPPAddress.length()) {
return "";
}
int slashIndex = XMPPAddress.indexOf("/");
if (slashIndex > 0 && slashIndex > atIndex) {
return XMPPAddress.substring(atIndex + 1, slashIndex);
}
else {
return XMPPAddress.substring(atIndex + 1);
}
}
/**
* Returns the resource portion of a XMPP address. For example, for the
* address "[email protected]/Smack", "Smack" would be returned. If no
* resource is present in the address, the empty string will be returned.
*
* @param XMPPAddress the XMPP address.
* @return the resource portion of the XMPP address.
*/
public static String parseResource(String XMPPAddress) {
if (XMPPAddress == null) {
return null;
}
int slashIndex = XMPPAddress.indexOf("/");
if (slashIndex + 1 > XMPPAddress.length() || slashIndex < 0) {
return "";
}
else {
return XMPPAddress.substring(slashIndex + 1);
}
}
/**
* Returns the XMPP address with any resource information removed. For example,
* for the address "[email protected]/Smack", "[email protected]" would
* be returned.
*
* @param XMPPAddress the XMPP address.
* @return the bare XMPP address without resource information.
*/
public static String parseBareAddress(String XMPPAddress) {
if (XMPPAddress == null) {
return null;
}
int slashIndex = XMPPAddress.indexOf("/");
if (slashIndex < 0) {
return XMPPAddress;
}
else if (slashIndex == 0) {
return "";
}
else {
return XMPPAddress.substring(0, slashIndex);
}
}
/**
* Escapes the node portion of a JID according to "JID Escaping" (JEP-0106).
* Escaping replaces characters prohibited by node-prep with escape sequences,
* as follows:
*
*
* Unescaped Character Encoded Sequence <space> \20 " \22 & \26 ' \27 / \2f : \3a < \3c > \3e @ \40 \ \5c
*
* This process is useful when the node comes from an external source that doesn't
* conform to nodeprep. For example, a username in LDAP may be "Joe Smith". Because
* the <space> character isn't a valid part of a node, the username should
* be escaped to "Joe\20Smith" before being made into a JID (e.g. "joe\[email protected]"
* after case-folding, etc. has been applied).
*
* All node escaping and un-escaping must be performed manually at the appropriate
* time; the JID class will not escape or un-escape automatically.
*
* @param node the node.
* @return the escaped version of the node.
*/
public static String escapeNode(String node) {
if (node == null) {
return null;
}
StringBuilder buf = new StringBuilder(node.length() + 8);
for (int i=0, n=node.length(); i': buf.append("\\3e"); break;
case '@': buf.append("\\40"); break;
case '\\': buf.append("\\5c"); break;
default: {
if (Character.isWhitespace(c)) {
buf.append("\\20");
}
else {
buf.append(c);
}
}
}
}
return buf.toString();
}
/**
* Un-escapes the node portion of a JID according to "JID Escaping" (JEP-0106).
* Escaping replaces characters prohibited by node-prep with escape sequences,
* as follows:
*
*
* Unescaped Character Encoded Sequence <space> \20 " \22 & \26 ' \27 / \2f : \3a < \3c > \3e @ \40 \ \5c
*
* This process is useful when the node comes from an external source that doesn't
* conform to nodeprep. For example, a username in LDAP may be "Joe Smith". Because
* the <space> character isn't a valid part of a node, the username should
* be escaped to "Joe\20Smith" before being made into a JID (e.g. "joe\[email protected]"
* after case-folding, etc. has been applied).
*
* All node escaping and un-escaping must be performed manually at the appropriate
* time; the JID class will not escape or un-escape automatically.
*
* @param node the escaped version of the node.
* @return the un-escaped version of the node.
*/
public static String unescapeNode(String node) {
if (node == null) {
return null;
}
char [] nodeChars = node.toCharArray();
StringBuilder buf = new StringBuilder(nodeChars.length);
for (int i=0, n=nodeChars.length; i'); i+=2; break compare;
}
}
else if (c2 == '4') {
if (c3 == '0') {
buf.append("@");
i+=2;
break compare;
}
}
else if (c2 == '5') {
if (c3 == 'c') {
buf.append("\\");
i+=2;
break compare;
}
}
}
buf.append(c);
}
}
return buf.toString();
}
/**
* Escapes all necessary characters in the String so that it can be used
* in an XML doc.
*
* @param string the string to escape.
* @return the string with appropriate characters escaped.
*/
public static String escapeForXML(String string) {
if (string == null) {
return null;
}
char ch;
int i=0;
int last=0;
char[] input = string.toCharArray();
int len = input.length;
StringBuilder out = new StringBuilder((int)(len*1.3));
for (; i < len; i++) {
ch = input[i];
if (ch > '>') {
}
else if (ch == '<') {
if (i > last) {
out.append(input, last, i - last);
}
last = i + 1;
out.append(LT_ENCODE);
}
else if (ch == '>') {
if (i > last) {
out.append(input, last, i - last);
}
last = i + 1;
out.append(GT_ENCODE);
}
else if (ch == '&') {
if (i > last) {
out.append(input, last, i - last);
}
// Do nothing if the string is of the form ë (unicode value)
if (!(len > i + 5
&& input[i + 1] == '#'
&& Character.isDigit(input[i + 2])
&& Character.isDigit(input[i + 3])
&& Character.isDigit(input[i + 4])
&& input[i + 5] == ';')) {
last = i + 1;
out.append(AMP_ENCODE);
}
}
else if (ch == '"') {
if (i > last) {
out.append(input, last, i - last);
}
last = i + 1;
out.append(QUOTE_ENCODE);
}
else if (ch == '\'') {
if (i > last) {
out.append(input, last, i - last);
}
last = i + 1;
out.append(APOS_ENCODE);
}
}
if (last == 0) {
return string;
}
if (i > last) {
out.append(input, last, i - last);
}
return out.toString();
}
/**
* Used by the hash method.
*/
private static MessageDigest digest = null;
/**
* Hashes a String using the SHA-1 algorithm and returns the result as a
* String of hexadecimal numbers. This method is synchronized to avoid
* excessive MessageDigest object creation. If calling this method becomes
* a bottleneck in your code, you may wish to maintain a pool of
* MessageDigest objects instead of using this method.
*
* A hash is a one-way function -- that is, given an
* input, an output is easily computed. However, given the output, the
* input is almost impossible to compute. This is useful for passwords
* since we can store the hash and a hacker will then have a very hard time
* determining the original password.
*
* @param data the String to compute the hash of.
* @return a hashed version of the passed-in String
*/
public synchronized static String hash(String data) {
if (digest == null) {
try {
digest = MessageDigest.getInstance("SHA-1");
}
catch (NoSuchAlgorithmException nsae) {
System.err.println("Failed to load the SHA-1 MessageDigest. " +
"Jive will be unable to function normally.");
}
}
// Now, compute hash.
try {
digest.update(data.getBytes("UTF-8"));
}
catch (UnsupportedEncodingException e) {
System.err.println(e);
}
return encodeHex(digest.digest());
}
/**
* Encodes an array of bytes as String representation of hexadecimal.
*
* @param bytes an array of bytes to convert to a hex string.
* @return generated hex string.
*/
public static String encodeHex(byte[] bytes) {
StringBuilder hex = new StringBuilder(bytes.length * 2);
for (byte aByte : bytes) {
if (((int) aByte & 0xff) < 0x10) {
hex.append("0");
}
hex.append(Integer.toString((int) aByte & 0xff, 16));
}
return hex.toString();
}
/**
* Encodes a String as a base64 String.
*
* @param data a String to encode.
* @return a base64 encoded String.
*/
public static String encodeBase64(String data) {
byte [] bytes = null;
try {
bytes = data.getBytes("ISO-8859-1");
}
catch (UnsupportedEncodingException uee) {
uee.printStackTrace();
}
return encodeBase64(bytes);
}
/**
* Encodes a byte array into a base64 String.
*
* @param data a byte array to encode.
* @return a base64 encode String.
*/
public static String encodeBase64(byte[] data) {
return encodeBase64(data, false);
}
/**
* Encodes a byte array into a bse64 String.
*
* @param data The byte arry to encode.
* @param lineBreaks True if the encoding should contain line breaks and false if it should not.
* @return A base64 encoded String.
*/
public static String encodeBase64(byte[] data, boolean lineBreaks) {
return encodeBase64(data, 0, data.length, lineBreaks);
}
/**
* Encodes a byte array into a bse64 String.
*
* @param data The byte arry to encode.
* @param offset the offset of the bytearray to begin encoding at.
* @param len the length of bytes to encode.
* @param lineBreaks True if the encoding should contain line breaks and false if it should not.
* @return A base64 encoded String.
*/
public static String encodeBase64(byte[] data, int offset, int len, boolean lineBreaks) {
return Base64.encodeBytes(data, offset, len, (lineBreaks ? Base64.NO_OPTIONS : Base64.DONT_BREAK_LINES));
}
/**
* Decodes a base64 String.
*
* @param data a base64 encoded String to decode.
* @return the decoded String.
*/
public static byte[] decodeBase64(String data) {
return Base64.decode(data);
}
/**
* Pseudo-random number generator object for use with randomString().
* The Random class is not considered to be cryptographically secure, so
* only use these random Strings for low to medium security applications.
*/
private static Random randGen = new Random();
/**
* Array of numbers and letters of mixed case. Numbers appear in the list
* twice so that there is a more equal chance that a number will be picked.
* We can use the array to get a random number or letter by picking a random
* array index.
*/
private static char[] numbersAndLetters = ("0123456789abcdefghijklmnopqrstuvwxyz" +
"0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ").toCharArray();
/**
* Returns a random String of numbers and letters (lower and upper case)
* of the specified length. The method uses the Random class that is
* built-in to Java which is suitable for low to medium grade security uses.
* This means that the output is only pseudo random, i.e., each number is
* mathematically generated so is not truly random.
*
* The specified length must be at least one. If not, the method will return
* null.
*
* @param length the desired length of the random String to return.
* @return a random String of numbers and letters of the specified length.
*/
public static String randomString(int length) {
if (length < 1) {
return null;
}
// Create a char buffer to put random letters and numbers in.
char [] randBuffer = new char[length];
for (int i=0; i