commons-xml/java/external/src/javax/xml/parsers/FilePathToURI.java

/*
 * The Apache Software License, Version 1.1
 *
 *
 * Copyright (c) 2002 The Apache Software Foundation.
 * All rights reserved.
 *
 * 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 the
 *        Apache Software Foundation (http://www.apache.org/)."
 *    Alternately, this acknowledgment may appear in the software itself,
 *    if and wherever such third-party acknowledgments normally appear.
 *
 * 4. The names "Xerces" and "Apache Software Foundation" must
 *    not be used to endorse or promote products derived from this
 *    software without prior written permission. For written
 *    permission, please contact apache@apache.org.
 *
 * 5. Products derived from this software may not be called "Apache",
 *    nor may "Apache" appear in their name, without prior written
 *    permission of the Apache Software Foundation.
 *
 * 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 THE APACHE SOFTWARE FOUNDATION 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 the Apache Software Foundation and was
 * originally based on software copyright (c) 1999, International
 * Business Machines, Inc., http://www.apache.org.  For more
 * information on the Apache Software Foundation, please see
 * <http://www.apache.org/>.
 */

package javax.xml.parsers;

class FilePathToURI {

    // which ASCII characters need to be escaped
    private static boolean gNeedEscaping[] = new boolean[128];
    // the first hex character if a character needs to be escaped
    private static char gAfterEscaping1[] = new char[128];
    // the second hex character if a character needs to be escaped
    private static char gAfterEscaping2[] = new char[128];
    private static char[] gHexChs = {'0', '1', '2', '3', '4', '5', '6', '7',
                                     '8', '9', 'A', 'B', 'C', 'D', 'E', 'F'};
    // initialize the above 3 arrays
    static {
        for (int i = 0; i <= 0x1f; i++) {
            gNeedEscaping[i] = true;
            gAfterEscaping1[i] = gHexChs[i >> 4];
            gAfterEscaping2[i] = gHexChs[i & 0xf];
        }
        gNeedEscaping[0x7f] = true;
        gAfterEscaping1[0x7f] = '7';
        gAfterEscaping2[0x7f] = 'F';
        char[] escChs = {' ', '<', '>', '#', '%', '"', '{', '}',
                         '|', '\\', '^', '~', '[', ']', '`'};
        int len = escChs.length;
        char ch;
        for (int i = 0; i < len; i++) {
            ch = escChs[i];
            gNeedEscaping[ch] = true;
            gAfterEscaping1[ch] = gHexChs[ch >> 4];
            gAfterEscaping2[ch] = gHexChs[ch & 0xf];
        }
    }

    // To escape a file path to a URI, by using %HH to represent
    // special ASCII characters: 0x00~0x1F, 0x7F, ' ', '<', '>', '#', '%'
    // and '"' and non-ASCII characters (whose value >= 128).
    public static String filepath2URI(String path){
        // return null if path is null.
        if (path == null)
            return null;

        char separator = java.io.File.separatorChar;
        path = path.replace(separator, '/');

        int len = path.length(), ch;
        StringBuffer buffer = new StringBuffer(len*3);
        buffer.append("file://");
        // change C:/blah to /C:/blah
        if (len >= 2 && path.charAt(1) == ':') {
            ch = Character.toUpperCase(path.charAt(0));
            if (ch >= 'A' && ch <= 'Z') {
                buffer.append('/');
            }
        }

        // for each character in the path
        int i = 0;
        for (; i < len; i++) {
            ch = path.charAt(i);
            // if it's not an ASCII character, break here, and use UTF-8 encoding
            if (ch >= 128)
                break;
            if (gNeedEscaping[ch]) {
                buffer.append('%');
                buffer.append(gAfterEscaping1[ch]);
                buffer.append(gAfterEscaping2[ch]);
                // record the fact that it's escaped
            }
            else {
                buffer.append((char)ch);
            }
        }
        
        // we saw some non-ascii character
        if (i < len) {
            // get UTF-8 bytes for the remaining sub-string
            byte[] bytes = null;
            byte b;
            try {
                bytes = path.substring(i).getBytes("UTF-8");
            } catch (java.io.UnsupportedEncodingException e) {
                // should never happen
                return path;
            }
            len = bytes.length;

            // for each byte
            for (i = 0; i < len; i++) {
                b = bytes[i];
                // for non-ascii character: make it positive, then escape
                if (b < 0) {
                    ch = b + 256;
                    buffer.append('%');
                    buffer.append(gHexChs[ch >> 4]);
                    buffer.append(gHexChs[ch & 0xf]);
                }
                else if (gNeedEscaping[b]) {
                    buffer.append('%');
                    buffer.append(gAfterEscaping1[b]);
                    buffer.append(gAfterEscaping2[b]);
                }
                else {
                    buffer.append((char)b);
                }
            }
        }

        return buffer.toString();
    }

}//FilePathToURI