stringutils.java

Jive Forums 1.0 src

/**
 * StringUtils.java
 * August 24, 2000
 *
 * Copyright (C) 2000 CoolServlets.com. All rights reserved.
 *
 * ===================================================================
 * The Apache Software License, Version 1.1
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 *
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 *
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in
 *    the documentation and/or other materials provided with the
 *    distribution.
 *
 * 3. The end-user documentation included with the redistribution,
 *    if any, must include the following acknowledgment:
 *       "This product includes software developed by
 *        CoolServlets.com (http://www.coolservlets.com)."
 *    Alternately, this acknowledgment may appear in the software itself,
 *    if and wherever such third-party acknowledgments normally appear.
 *
 * 4. The names "Jive" and "CoolServlets.com" must not be used to
 *    endorse or promote products derived from this software without
 *    prior written permission. For written permission, please
 *    contact [e-mail].
 *
 * 5. Products derived from this software may not be called "Jive",
 *    nor may "Jive" appear in their name, without prior written
 *    permission of CoolServlets.com.
 *
 * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED
 * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
 * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
 * DISCLAIMED.  IN NO EVENT SHALL COOLSERVLETS.COM OR
 * ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
 * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
 * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
 * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
 * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
 * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 * ====================================================================
 *
 * This software consists of voluntary contributions made by many
 * individuals on behalf of CoolServlets.com. For more information
 * on CoolServlets.com, please see <http://www.coolservlets.com>.
 */

package com.coolservlets.util;

import java.security.*;
import java.text.*;
import java.util.*;

/**
 * Utility class to peform common String manipulation algorithms.
 */
public class StringUtils {

    /**
     * Initialization lock for the whole class. Init's only happen once per
     * class load so this shouldn't be a bottleneck.
     */
    private static Object initLock = new Object();

    /**
     * Replaces all instances of oldString with newString in line.
     *
     * @param line the String to search to perform replacements on
     * @param oldString the String that should be replaced by newString
     * @param newString the String that will replace all instances of oldString
     *
     * @return a String will all instances of oldString replaced by newString
     */
    public static final String replace( String line, String oldString, String newString )
    {
        int i=0;
        if ( ( i=line.indexOf( oldString, i ) ) >= 0 ) {
            char [] line2 = line.toCharArray();
	        char [] newString2 = newString.toCharArray();
            int oLength = oldString.length();
            StringBuffer buf = new StringBuffer(line2.length);
            buf.append(line2, 0, i).append(newString2);
            i += oLength;
            int j = i;
            while( ( i=line.indexOf( oldString, i ) ) > 0 ) {
                buf.append(line2, j, i-j).append(newString2);
                i += oLength;
                j = i;
            }
            buf.append(line2, j, line2.length - j);
            return buf.toString();
        }
        return line;
    }

   /**
    * Replaces all instances of oldString with newString in line.
    * The count Integer is updated with number of replaces.
    *
    * @param line the String to search to perform replacements on
    * @param oldString the String that should be replaced by newString
    * @param newString the String that will replace all instances of oldString
    *
    * @return a String will all instances of oldString replaced by newString
    */
    public static final String replace( String line, String oldString,
            String newString, int[] count)
    {
        if (line == null) {
            return null;
        }
        int i=0;
        if ( ( i=line.indexOf( oldString, i ) ) >= 0 ) {
            int counter = 0;
            counter++;
            char [] line2 = line.toCharArray();
	        char [] newString2 = newString.toCharArray();
            int oLength = oldString.length();
            StringBuffer buf = new StringBuffer(line2.length);
            buf.append(line2, 0, i).append(newString2);
            i += oLength;
            int j = i;
            while( ( i=line.indexOf( oldString, i ) ) > 0 ) {
                counter++;
                buf.append(line2, j, i-j).append(newString2);
                i += oLength;
                j = i;
            }
            buf.append(line2, j, line2.length - j);
            count[0] = counter;
            return buf.toString();
        }
        return line;
    }

    private final static String LT = "&lt;";
    private final static String GT = "&gt;";

    /**
     * This method takes a string which may contain HTML tags (ie, &lt;b&gt;,
     * &lt;table&gt;, etc) and converts the '&lt'' and '&gt;' characters to
     * their HTML escape sequences.
     *
     * @param input the text to be converted.
     * @return the input string with the characters '&lt;' and '&gt;' replaced
     *  with their HTML escape sequences.
     */
    public static final String escapeHTMLTags( String input ) {
        //Check if the string is null or zero length -- if so, return
        //what was sent in.
        if( input == null || input.length() == 0 ) {
            return input;
        }
        //Use a StringBuffer in lieu of String concatenation -- it is
        //much more efficient this way.
        StringBuffer buf = new StringBuffer(input.length());
        char ch = ' ';
        for( int i=0; i<input.length(); i++ ) {
            ch = input.charAt(i);
            if( ch == '<' ) {
                buf.append( LT );
            }
            else if( ch == '>' ) {
                buf.append( GT );
            }
            else {
                buf.append( ch );
            }
        }
        return buf.toString();
    }

    /**
     * Used by the hash method.
     */
    private static MessageDigest digest = null;

    /**
     * Hashes a String using the Md5 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.
     * <p>
     * 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.
     * <p>
     * In Jive, every time a user logs in, we simply
     * take their plain text password, compute the hash, and compare the
     * generated hash to the stored hash. Since it is almost impossible that
     * two passwords will generate the same hash, we know if the user gave us
     * the correct password or not. The only negative to this system is that
     * password recovery is basically impossible. Therefore, a reset password
     * method is used instead.
     *
     * @param data the String to compute the hash of.
     * @return a hashed version of the passed-in String
     */
    public synchronized static final String hash(String data) {
        if (digest == null) {
            try {
                digest = MessageDigest.getInstance("MD5");
            }
            catch (NoSuchAlgorithmException nsae) {
                System.err.println("Failed to load the MD5 MessageDigest. " +
                "Jive will be unable to function normally.");
                nsae.printStackTrace();
            }
        }
        //Now, compute hash.
        digest.update(data.getBytes());
        return toHex(digest.digest());
    }

    /**
     * Turns an array of bytes into a String representing each byte as an
     * unsigned hex number.
     * <p>
     * Method by Santeri Paavolainen, Helsinki Finland 1996<br>
     * (c) Santeri Paavolainen, Helsinki Finland 1996<br>
     * Distributed under LGPL.
     *
     * @param hash an rray of bytes to convert to a hex-string
     * @return generated hex string
     */
    public static final String toHex (byte hash[]) {
        StringBuffer buf = new StringBuffer(hash.length * 2);
        int i;

        for (i = 0; i < hash.length; i++) {
            if (((int) hash[i] & 0xff) < 0x10) {
                buf.append("0");
            }
            buf.append(Long.toString((int) hash[i] & 0xff, 16));
        }
        return buf.toString();
    }

    /**
     * Converts a line of text into an array of lower case words. Words are
     * delimited by the following characters: , .\r\n:/\+
     * <p>
     * In the future, this method should be changed to use a
     * BreakIterator.wordInstance(). That class offers much more fexibility.
     *
     * @param text a String of text to convert into an array of words
     * @return text broken up into an array of words.
     */
    public static final String [] toLowerCaseWordArray(String text) {
        if (text == null || text.length() == 0) {
    		return new String[0];
        }
        StringTokenizer tokens = new StringTokenizer(text, " ,\r\n.:/\\+");
        String [] words = new String[tokens.countTokens()];
        for (int i=0; i<words.length; i++) {
            words[i] = tokens.nextToken().toLowerCase();
        }
        return words;
    }

    /**
     * A list of some of the most common words. For searching and indexing, we
     * often want to filter out these words since they just confuse searches.
     * The list was not created scientifically so may be incomplete :)
     */
    private static final String [] commonWords =  new String [] {
        "a", "and", "as", "at", "be", "do", "i", "if", "in", "is", "it", "so",
        "the", "to"
    };
    private static Map commonWordsMap = null;

    /**
     * Returns a new String array with some of the most common English words
     * removed. The specific words removed are: a, and, as, at, be, do, i, if,
     * in, is, it, so, the, to
     */
    public static final String [] removeCommonWords(String [] words) {
        //See if common words map has been initialized. We don't statically
        //initialize it to save some memory. Even though this a small savings,
        //it adds up with hundreds of classes being loaded.
        if (commonWordsMap == null) {
            synchronized(initLock) {
                if (commonWordsMap == null) {
                    commonWordsMap = new HashMap();
                    for (int i=0; i<commonWords.length; i++) {
                        commonWordsMap.put(commonWords[i], commonWords[i]);
                    }
                }
            }
        }
        //Now, add all words that aren't in the common map to results
        ArrayList results = new ArrayList(words.length);
        for (int i=0; i<words.length; i++) {
            if (!commonWordsMap.containsKey(words[i])) {
                results.add(words[i]);
            }
        }
        return (String[])results.toArray(new String[results.size()]);
    }
}