stringutils.java

Jive是基于JSP/JAVA技术构架的一个大型BBS论坛系统,这是Jive论坛2.6版本的源程序

     *
     * @param data a base64 encode byte array to decode.
     * @return the decoded String.
     */
    public static String decodeBase64(byte[] data) {
        int c, c1;
        int len = data.length;
        StringBuffer ret = new StringBuffer((len * 3) / 4);
        for (int i = 0; i < len; ++i) {
            c = cvt.indexOf(data[i]);
            ++i;
            c1 = cvt.indexOf(data[i]);
            c = ((c << 2) | ((c1 >> 4) & 0x3));
            ret.append((char) c);
            if (++i < len) {
                c = data[i];
                if (fillchar == c)
                    break;

                c = cvt.indexOf((char) c);
                c1 = ((c1 << 4) & 0xf0) | ((c >> 2) & 0xf);
                ret.append((char) c1);
            }

            if (++i < len) {
                c1 = data[i];
                if (fillchar == c1)
                    break;

                c1 = cvt.indexOf((char) c1);
                c = ((c << 6) & 0xc0) | c1;
                ret.append((char) c);
            }
        }
        return ret.toString();
    }

    private static final int fillchar = '=';
    private static final String cvt = "ABCDEFGHIJKLMNOPQRSTUVWXYZ"
                                    + "abcdefghijklmnopqrstuvwxyz"
                                    + "0123456789+/";

    /**
     * Converts a line of text into an array of lower case words using a
     * BreakIterator.wordInstance(). <p>
     *
     * This method is under the Jive Open Source Software License and was
     * written by Mark Imbriaco.
     *
     * @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];
        }

        ArrayList wordList = new ArrayList();
        BreakIterator boundary = BreakIterator.getWordInstance();
        boundary.setText(text);
        int start = 0;

        for (int end = boundary.next(); end != BreakIterator.DONE;
                start = end, end = boundary.next())
        {
            String tmp = text.substring(start,end).trim();
            // Remove characters that are not needed.
            tmp = replace(tmp, "+", "");
            tmp = replace(tmp, "/", "");
            tmp = replace(tmp, "\\", "");
            tmp = replace(tmp, "#", "");
            tmp = replace(tmp, "*", "");
            tmp = replace(tmp, ")", "");
            tmp = replace(tmp, "(", "");
            tmp = replace(tmp, "&", "");
            if (tmp.length() > 0) {
                wordList.add(tmp);
            }
        }
        return (String[]) wordList.toArray(new String[wordList.size()]);
    }

    /**
     * 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.<p>
     *
     * 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 final 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<randBuffer.length; i++) {
            randBuffer[i] = numbersAndLetters[randGen.nextInt(71)];
        }
        return new String(randBuffer);
    }

   /**
    * Intelligently chops a String at a word boundary (whitespace) that occurs
    * at the specified index in the argument or before. However, if there is a
    * newline character before <code>length</code>, the String will be chopped
    * there. If no newline or whitespace is found in <code>string</code> up to
    * the index <code>length</code>, the String will chopped at <code>length</code>.
    * <p>
    * For example, chopAtWord("This is a nice String", 10) will return
    * "This is a" which is the first word boundary less than or equal to 10
    * characters into the original String.
    *
    * @param string the String to chop.
    * @param length the index in <code>string</code> to start looking for a
    *       whitespace boundary at.
    * @return a substring of <code>string</code> whose length is less than or
    *       equal to <code>length</code>, and that is chopped at whitespace.
    */
    public static final String chopAtWord(String string, int length) {
        if (string == null || string.length() == 0) {
            return string;
        }

        char [] charArray = string.toCharArray();
        int sLength = string.length();
        if (length < sLength) {
            sLength = length;
        }

        // First check if there is a newline character before length; if so,
        // chop word there.
        for (int i=0; i<sLength-1; i++) {
            // Windows
            if (charArray[i] == '\r' && charArray[i+1] == '\n') {
                return string.substring(0, i+1);
            }
            // Unix
            else if (charArray[i] == '\n') {
                return string.substring(0, i);
            }
        }
        // Also check boundary case of Unix newline
        if (charArray[sLength-1] == '\n') {
            return string.substring(0, sLength-1);
        }

        // Done checking for newline, now see if the total string is less than
        // the specified chop point.
        if (string.length() < length) {
            return string;
        }

        // No newline, so chop at the first whitespace.
        for (int i = length-1; i > 0; i--) {
            if (charArray[i] == ' ') {
                return string.substring(0, i).trim();
            }
        }

        // Did not find word boundary so return original String chopped at
        // specified length.
        return string.substring(0, length);
    }

    /**
     * Reformats a string where lines that are longer than <tt>width</tt>
     * are split apart at the earliest wordbreak or at maxLength, whichever is
     * sooner. If the width specified is less than 5 or greater than the input
     * Strings length the string will be returned as is.
     * <p>
     * Please note that this method can be lossy - trailing spaces on wrapped
     * lines may be trimmed.
     *
     * @param input the String to reformat.
     * @param width the maximum length of any one line.
     * @return a new String with reformatted as needed.
     */
    public static String wordWrap(String input, int width, Locale locale) {
        // protect ourselves
        if (input == null) {
            return "";
        }
        else if (width < 5) {
            return input;
        }
        else if (width >= input.length()) {
            return input;
        }

        // default locale
        if (locale == null) {
            locale = JiveGlobals.getLocale();
        }

        StringBuffer buf  = new StringBuffer(input);
        boolean endOfLine = false;
        int lineStart     = 0;

        for (int i = 0; i < buf.length(); i++) {
            if (buf.charAt(i) == '\n') {
                lineStart = i + 1;
                endOfLine = true;
            }

            // handle splitting at width character
            if (i > lineStart + width - 1) {
                if (!endOfLine) {
                    int limit = i - lineStart - 1;
                    BreakIterator breaks = BreakIterator.getLineInstance(locale);
                    breaks.setText(buf.substring(lineStart, i));
                    int end = breaks.last();

                    // if the last character in the search string isn't a space,
                    // we can't split on it (looks bad). Search for a previous
                    // break character
                   if (end == limit + 1) {
                        if (!Character.isWhitespace(buf.charAt(lineStart + end))) {
                            end = breaks.preceding(end - 1);
                        }
                    }

                    // if the last character is a space, replace it with a \n
                    if (end != BreakIterator.DONE && end == limit + 1) {
                        buf.replace(lineStart + end, lineStart + end + 1, "\n");
                        lineStart = lineStart + end;
                    }
                    // otherwise, just insert a \n
                    else if (end != BreakIterator.DONE && end != 0) {
                        buf.insert(lineStart + end, '\n');
                        lineStart = lineStart + end + 1;
                    }
                    else {
                        buf.insert(i, '\n');
                        lineStart = i + 1;
                    }
                }
                else {
                    buf.insert(i, '\n');
                    lineStart = i + 1;
                    endOfLine = false;
                }
            }
        }

        return buf.toString();
    }

    // Create a regular expression engine that is used by the highlightWords
    // method below.
    private static Perl5Util perl5Util = new Perl5Util();

    /**
     * Highlights words in a string. Words matching ignores case. The actual
     * higlighting method is specified with the start and end higlight tags.
     * Those might be beginning and ending HTML bold tags, or anything else.<p>
     *
     * This method is under the Jive Open Source Software License and was
     * written by Mark Imbriaco.
     *
     * @param string the String to highlight words in.
     * @param words an array of words that should be highlighted in the string.
     * @param startHighlight the tag that should be inserted to start highlighting.
     * @param endHighlight the tag that should be inserted to end highlighting.
     * @return a new String with the specified words highlighted.
     */
    public static final String highlightWords(String string, String[] words,
        String startHighlight, String endHighlight)
    {
        if (string == null || words == null ||
                startHighlight == null || endHighlight == null)
        {
            return null;
        }

        StringBuffer regexp = new StringBuffer();

        // Iterate through each word and generate a word list for the regexp.
        for (int x=0; x<words.length; x++)
        {
            // Excape "|" and "/"  to keep us out of trouble in our regexp.
            words[x] = perl5Util.substitute("s#([\\|\\/\\.])#\\\\$1#g", words[x]);
            if (regexp.length() > 0)
            {
                regexp.append("|");
            }
            regexp.append(words[x]);
        }

        // Escape the regular expression delimiter ("/").
        startHighlight = perl5Util.substitute("s#\\/#\\\\/#g", startHighlight);
        endHighlight = perl5Util.substitute("s#\\/#\\\\/#g", endHighlight);

        // Build the regular expression. insert() the first part.
        regexp.insert(0, "s/\\b(");
        // The word list is here already, so just append the rest.
        regexp.append(")\\b/");
        regexp.append(startHighlight);
        regexp.append("$1");
        regexp.append(endHighlight);
        regexp.append("/igm");

        // Do the actual substitution via a simple regular expression.
        return perl5Util.substitute(regexp.toString(), string);
    }

    /**
     * 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 final 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;
        StringBuffer out = new StringBuffer((int)(len*1.3));
        for (; i < len; i++) {
            ch = input[i];
            if (ch > '>') {
                continue;
            } 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(AMP_ENCODE);
            } else if (ch == '"') {
                if (i > last) {
                    out.append(input, last, i - last);
                }
                last = i + 1;
                out.append(QUOTE_ENCODE);
            }
        }
        if (last == 0) {
            return string;
        }
        if (i > last) {
            out.append(input, last, i - last);
        }
        return out.toString();
    }

    /**
     * Unescapes the String by converting XML escape sequences back into normal
     * characters.
     *
     * @param string the string to unescape.
     * @return the string with appropriate characters unescaped.
     */
    public static final String unescapeFromXML(String string) {
        string = replace(string, "&lt;", "<");
        string = replace(string, "&gt;", ">");
        string = replace(string, "&quot;", "\"");
        return replace(string, "&amp;", "&");
    }

    private static final char[] zeroArray = "0000000000000000".toCharArray();

    /**
     * Pads the supplied String with 0's to the specified length and returns
     * the result as a new String. For example, if the initial String is
     * "9999" and the desired length is 8, the result would be "00009999".
     * This type of padding is useful for creating numerical values that need
     * to be stored and sorted as character data. Note: the current
     * implementation of this method allows for a maximum <tt>length</tt> of
     * 16.
     *
     * @param string the original String to pad.
     * @param length the desired length of the new padded String.
     * @return a new String padded with the required number of 0's.
     */
     public static final String zeroPadString(String string, int length) {
        if (string == null || string.length() > length) {
            return string;
        }
        StringBuffer buf = new StringBuffer(length);
        buf.append(zeroArray, 0, length-string.length()).append(string);
        return buf.toString();
     }

     /**
      * Formats a Date as a fifteen character long String made up of the Date's
      * padded millisecond value.
      *
      * @return a Date encoded as a String.
      */
     public static final String dateToMillis(Date date) {
        return zeroPadString(Long.toString(date.getTime()), 15);
     }
}