modules/tomcat-lite/java/org/apache/tomcat/lite/util/URLEncoder.java

/*
 * 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.tomcat.lite.util;

import java.io.ByteArrayOutputStream;
import java.io.IOException;
import java.io.OutputStreamWriter;
import java.io.UnsupportedEncodingException;
import java.util.BitSet;

/**
 *
 * This class is very similar to the java.net.URLEncoder class.
 *
 * Unfortunately, with java.net.URLEncoder there is no way to specify to the
 * java.net.URLEncoder which characters should NOT be encoded.
 *
 * This code was moved from DefaultServlet.java
 *
 * @author Craig R. McClanahan
 * @author Remy Maucherat
 */
public class URLEncoder {
    protected static final char[] hexadecimal =
    {'0', '1', '2', '3', '4', '5', '6', '7', '8', '9',
     'A', 'B', 'C', 'D', 'E', 'F'};

    //Array containing the safe characters set.
    protected BitSet safeChars = new BitSet(128);

    public URLEncoder() {
        for (char i = 'a'; i <= 'z'; i++) {
            addSafeCharacter(i);
        }
        for (char i = 'A'; i <= 'Z'; i++) {
            addSafeCharacter(i);
        }
        for (char i = '0'; i <= '9'; i++) {
            addSafeCharacter(i);
        }
        //safe
        safeChars.set('$');
        safeChars.set('-');
        safeChars.set('_');
        safeChars.set('.');

        // Dangerous: someone may treat this as " "
        // RFC1738 does allow it, it's not reserved
        //    safeChars.set('+');
        //extra
        safeChars.set('!');
        safeChars.set('*');
        safeChars.set('\'');
        safeChars.set('(');
        safeChars.set(')');
        safeChars.set(',');
    }

    public void addSafeCharacter( char c ) {
        safeChars.set( c );
    }

    public String encodeURL(String path) {
        return encodeURL(path, "UTF-8", true);
    }

    public String encodeURL(String path, String enc, boolean allowSlash) {
        int maxBytesPerChar = 10;

        StringBuffer rewrittenPath = new StringBuffer(path.length());
        ByteArrayOutputStream buf = new ByteArrayOutputStream(maxBytesPerChar);
        OutputStreamWriter writer = null;
        try {
            writer = new OutputStreamWriter(buf, enc);
        } catch (UnsupportedEncodingException e1) {
            // shouldn't happen.
        }

        for (int i = 0; i < path.length(); i++) {
            int c = (int) path.charAt(i);
            if (c < 128 && safeChars.get(c) || allowSlash && c == '/') {
                rewrittenPath.append((char)c);
            } else {
                // convert to external encoding before hex conversion
                try {
                    writer.write((char)c);
                    if (c >= 0xD800 && c <= 0xDBFF) {
                        if ( (i+1) < path.length()) {
                            int d = path.charAt(i+1);
                            if (d >= 0xDC00 && d <= 0xDFFF) {
                                writer.write((char) d);
                                i++;
                            }
                        }
                    }
                    writer.flush();
                } catch(IOException e) {
                    buf.reset();
                    continue;
                }
                byte[] ba = buf.toByteArray();
                for (int j = 0; j < ba.length; j++) {
                    // Converting each byte in the buffer
                    byte toEncode = ba[j];
                    rewrittenPath.append('%');
                    int low = (int) (toEncode & 0x0f);
                    int high = (int) ((toEncode & 0xf0) >> 4);
                    rewrittenPath.append(hexadecimal[high]);
                    rewrittenPath.append(hexadecimal[low]);
                }
                buf.reset();
            }
        }
        return rewrittenPath.toString();
    }

    /**
     * Decode and return the specified URL-encoded String.
     *
     * @param str The url-encoded string
     * @param enc The encoding to use; if null, the default encoding is used
     * @exception IllegalArgumentException if a '%' character is not followed
     * by a valid 2-digit hexadecimal number
     */
    public static String URLDecode(String str, String enc) {

        if (str == null)
            return (null);

        // use the specified encoding to extract bytes out of the
        // given string so that the encoding is not lost. If an
        // encoding is not specified, let it use platform default
        byte[] bytes = null;
        try {
            if (enc == null) {
                bytes = str.getBytes();
            } else {
                bytes = str.getBytes(enc);
            }
        } catch (UnsupportedEncodingException uee) {}

        return URLDecode(bytes, enc);

    }


    /**
     * Decode and return the specified URL-encoded String.
     * When the byte array is converted to a string, the system default
     * character encoding is used...  This may be different than some other
     * servers.
     *
     * @param str The url-encoded string
     *
     * @exception IllegalArgumentException if a '%' character is not followed
     * by a valid 2-digit hexadecimal number
     */
    public static String URLDecode(String str) {

        return URLDecode(str, null);

    }

    /**
     * Decode and return the specified URL-encoded byte array.
     *
     * @param bytes The url-encoded byte array
     * @param enc The encoding to use; if null, the default encoding is used
     * @exception IllegalArgumentException if a '%' character is not followed
     * by a valid 2-digit hexadecimal number
     */
    private static String URLDecode(byte[] bytes, String enc) {

        if (bytes == null)
            return (null);

        int len = bytes.length;
        int ix = 0;
        int ox = 0;
        while (ix < len) {
            byte b = bytes[ix++];     // Get byte to test
            if (b == '+') {
                b = (byte)' ';
            } else if (b == '%') {
                b = (byte) ((convertHexDigit(bytes[ix++]) << 4)
                            + convertHexDigit(bytes[ix++]));
            }
            bytes[ox++] = b;
        }
        if (enc != null) {
            try {
                return new String(bytes, 0, ox, enc);
            } catch (Exception e) {
                e.printStackTrace();
            }
        }
        return new String(bytes, 0, ox);

    }

    /**
     * Convert a byte character value to hexidecimal digit value.
     *
     * @param b the character value byte
     */
    private static byte convertHexDigit( byte b ) {
        if ((b >= '0') && (b <= '9')) return (byte)(b - '0');
        if ((b >= 'a') && (b <= 'f')) return (byte)(b - 'a' + 10);
        if ((b >= 'A') && (b <= 'F')) return (byte)(b - 'A' + 10);
        return 0;
    }

}