text.java

jsr170接口的java实现。是个apache的开源项目。

/*
 * 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.
 */
package org.apache.jackrabbit.util;

import java.io.UnsupportedEncodingException;
import java.io.ByteArrayOutputStream;
import java.security.MessageDigest;
import java.security.NoSuchAlgorithmException;
import java.util.ArrayList;
import java.util.BitSet;
import java.util.Properties;

/**
 * This Class provides some text related utilities
 */
public class Text {

    /**
     * Hidden constructor.
     */
    private Text() {
    }

    /**
     * used for the md5
     */
    public static final char[] hexTable = "0123456789abcdef".toCharArray();

    /**
     * Calculate an MD5 hash of the string given.
     *
     * @param data the data to encode
     * @param enc  the character encoding to use
     * @return a hex encoded string of the md5 digested input
     */
    public static String md5(String data, String enc)
            throws UnsupportedEncodingException {
        try {
            return digest("MD5", data.getBytes(enc));
        } catch (NoSuchAlgorithmException e) {
            throw new InternalError("MD5 digest not available???");
        }
    }

    /**
     * Calculate an MD5 hash of the string given using 'utf-8' encoding.
     *
     * @param data the data to encode
     * @return a hex encoded string of the md5 digested input
     */
    public static String md5(String data) {
        try {
            return md5(data, "utf-8");
        } catch (UnsupportedEncodingException e) {
            throw new InternalError("UTF8 digest not available???");
        }
    }

    /**
     * Digest the plain string using the given algorithm.
     *
     * @param algorithm The alogrithm for the digest. This algorithm must be
     *                  supported by the MessageDigest class.
     * @param data      The plain text String to be digested.
     * @param enc       The character encoding to use
     * @return The digested plain text String represented as Hex digits.
     * @throws java.security.NoSuchAlgorithmException     if the desired algorithm is not supported by
     *                                      the MessageDigest class.
     * @throws java.io.UnsupportedEncodingException if the encoding is not supported
     */
    public static String digest(String algorithm, String data, String enc)
            throws NoSuchAlgorithmException, UnsupportedEncodingException {

        return digest(algorithm, data.getBytes(enc));
    }

    /**
     * Digest the plain string using the given algorithm.
     *
     * @param algorithm The alogrithm for the digest. This algorithm must be
     *                  supported by the MessageDigest class.
     * @param data      the data to digest with the given algorithm
     * @return The digested plain text String represented as Hex digits.
     * @throws java.security.NoSuchAlgorithmException if the desired algorithm is not supported by
     *                                  the MessageDigest class.
     */
    public static String digest(String algorithm, byte[] data)
            throws NoSuchAlgorithmException {

        MessageDigest md = MessageDigest.getInstance(algorithm);
        byte[] digest = md.digest(data);
        StringBuffer res = new StringBuffer(digest.length * 2);
        for (int i = 0; i < digest.length; i++) {
            byte b = digest[i];
            res.append(hexTable[(b >> 4) & 15]);
            res.append(hexTable[b & 15]);
        }
        return res.toString();
    }

    /**
     * returns an array of strings decomposed of the original string, split at
     * every occurance of 'ch'. if 2 'ch' follow each other with no intermediate
     * characters, empty "" entries are avoided.
     *
     * @param str the string to decompose
     * @param ch  the character to use a split pattern
     * @return an array of strings
     */
    public static String[] explode(String str, int ch) {
        return explode(str, ch, false);
    }

    /**
     * returns an array of strings decomposed of the original string, split at
     * every occurance of 'ch'.
     *
     * @param str          the string to decompose
     * @param ch           the character to use a split pattern
     * @param respectEmpty if <code>true</code>, empty elements are generated
     * @return an array of strings
     */
    public static String[] explode(String str, int ch, boolean respectEmpty) {
        if (str == null || str.length() == 0) {
            return new String[0];
        }

        ArrayList strings = new ArrayList();
        int pos;
        int lastpos = 0;

        // add snipples
        while ((pos = str.indexOf(ch, lastpos)) >= 0) {
            if (pos - lastpos > 0 || respectEmpty) {
                strings.add(str.substring(lastpos, pos));
            }
            lastpos = pos + 1;
        }
        // add rest
        if (lastpos < str.length()) {
            strings.add(str.substring(lastpos));
        } else if (respectEmpty && lastpos == str.length()) {
            strings.add("");
        }

        // return stringarray
        return (String[]) strings.toArray(new String[strings.size()]);
    }

    /**
     * Concatenates all strings in the string array using the specified delimiter.
     * @param arr
     * @param delim
     * @return the concatenated string
     */
    public static String implode(String[] arr, String delim) {
        StringBuffer buf = new StringBuffer();
        for (int i = 0; i < arr.length; i++) {
            if (i > 0) {
                buf.append(delim);
            }
            buf.append(arr[i]);
        }
        return buf.toString();
    }

    /**
     * Replaces all occurences of <code>oldString</code> in <code>text</code>
     * with <code>newString</code>.
     *
     * @param text
     * @param oldString old substring to be replaced with <code>newString</code>
     * @param newString new substring to replace occurences of <code>oldString</code>
     * @return a string
     */
    public static String replace(String text, String oldString, String newString) {
        if (text == null || oldString == null || newString == null) {
            throw new IllegalArgumentException("null argument");
        }
        int pos = text.indexOf(oldString);
        if (pos == -1) {
            return text;
        }
        int lastPos = 0;
        StringBuffer sb = new StringBuffer(text.length());
        while (pos != -1) {
            sb.append(text.substring(lastPos, pos));
            sb.append(newString);
            lastPos = pos + oldString.length();
            pos = text.indexOf(oldString, lastPos);
        }
        if (lastPos < text.length()) {
            sb.append(text.substring(lastPos));
        }
        return sb.toString();
    }

    /**
     * Replaces illegal XML characters in the given string by their corresponding
     * predefined entity references.
     *
     * @param text text to be escaped
     * @return a string
     */
    public static String encodeIllegalXMLCharacters(String text) {
        if (text == null) {
            throw new IllegalArgumentException("null argument");
        }
        StringBuffer buf = null;
        int length = text.length();
        int pos = 0;
        for (int i = 0; i < length; i++) {
            int ch = text.charAt(i);
            switch (ch) {
                case '<':
                case '>':
                case '&':
                case '"':
                case '\'':
                    if (buf == null) {
                        buf = new StringBuffer();
                    }
                    if (i > 0) {
                        buf.append(text.substring(pos, i));
                    }
                    pos = i + 1;
                    break;
                default:
                    continue;
            }
            if (ch == '<') {
                buf.append("&lt;");
            } else if (ch == '>') {
                buf.append("&gt;");
            } else if (ch == '&') {
                buf.append("&amp;");
            } else if (ch == '"') {
                buf.append("&quot;");
            } else if (ch == '\'') {
                buf.append("&apos;");
            }
        }
        if (buf == null) {
            return text;
        } else {
            if (pos < length) {
                buf.append(text.substring(pos));
            }
            return buf.toString();
        }
    }

    /**
     * The list of characters that are not encoded by the <code>escape()</code>
     * and <code>unescape()</code> METHODS. They contains the characters as
     * defined 'unreserved' in section 2.3 of the RFC 2396 'URI generic syntax':
     * <p/>
     * <pre>
     * unreserved  = alphanum | mark
     * mark        = "-" | "_" | "." | "!" | "~" | "*" | "'" | "(" | ")"
     * </pre>
     */
    public static BitSet URISave;

    /**
     * Same as {@link #URISave} but also contains the '/'
     */
    public static BitSet URISaveEx;

    static {
        URISave = new BitSet(256);
        int i;
        for (i = 'a'; i <= 'z'; i++) {
            URISave.set(i);
        }
        for (i = 'A'; i <= 'Z'; i++) {
            URISave.set(i);
        }
        for (i = '0'; i <= '9'; i++) {
            URISave.set(i);
        }
        URISave.set('-');
        URISave.set('_');
        URISave.set('.');
        URISave.set('!');
        URISave.set('~');
        URISave.set('*');
        URISave.set('\'');
        URISave.set('(');
        URISave.set(')');

        URISaveEx = (BitSet) URISave.clone();
        URISaveEx.set('/');
    }

    /**
     * Does an URL encoding of the <code>string</code> using the
     * <code>escape</code> character. The characters that don't need encoding
     * are those defined 'unreserved' in section 2.3 of the 'URI generic syntax'
     * RFC 2396, but without the escape character.
     *
     * @param string the string to encode.
     * @param escape the escape character.
     * @return the escaped string
     * @throws NullPointerException if <code>string</code> is <code>null</code>.
     */
    public static String escape(String string, char escape) {
        return escape(string, escape, false);
    }

    /**
     * Does an URL encoding of the <code>string</code> using the
     * <code>escape</code> character. The characters that don't need encoding
     * are those defined 'unreserved' in section 2.3 of the 'URI generic syntax'
     * RFC 2396, but without the escape character. If <code>isPath</code> is
     * <code>true</code>, additionally the slash '/' is ignored, too.
     *
     * @param string the string to encode.
     * @param escape the escape character.
     * @param isPath if <code>true</code>, the string is treated as path
     * @return the escaped string
     * @throws NullPointerException if <code>string</code> is <code>null</code>.
     */
    public static String escape(String string, char escape, boolean isPath) {
        try {
            BitSet validChars = isPath ? URISaveEx : URISave;
            byte[] bytes = string.getBytes("utf-8");
            StringBuffer out = new StringBuffer(bytes.length);
            for (int i = 0; i < bytes.length; i++) {
                int c = bytes[i] & 0xff;
                if (validChars.get(c) && c != escape) {
                    out.append((char) c);
                } else {
                    out.append(escape);
                    out.append(hexTable[(c >> 4) & 0x0f]);
                    out.append(hexTable[(c) & 0x0f]);
                }
            }
            return out.toString();
        } catch (UnsupportedEncodingException e) {
            throw new InternalError(e.toString());
        }
    }

    /**
     * Does a URL encoding of the <code>string</code>. The characters that
     * don't need encoding are those defined 'unreserved' in section 2.3 of
     * the 'URI generic syntax' RFC 2396.
     *
     * @param string the string to encode
     * @return the escaped string
     * @throws NullPointerException if <code>string</code> is <code>null</code>.
     */
    public static String escape(String string) {
        return escape(string, '%');
    }