1 /*
   2  * Copyright (c) 2003, Oracle and/or its affiliates. All rights reserved.
   3  * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
   4  *
   5  * This code is free software; you can redistribute it and/or modify it
   6  * under the terms of the GNU General Public License version 2 only, as
   7  * published by the Free Software Foundation.
   8  *
   9  * This code is distributed in the hope that it will be useful, but WITHOUT
  10  * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
  11  * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
  12  * version 2 for more details (a copy is included in the LICENSE file that
  13  * accompanied this code).
  14  *
  15  * You should have received a copy of the GNU General Public License version
  16  * 2 along with this work; if not, write to the Free Software Foundation,
  17  * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
  18  *
  19  * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
  20  * or visit www.oracle.com if you need additional information or have any
  21  * questions.
  22  */
  23 
  24 /* @test
  25    @bug 4922813
  26    @summary Check the new impl of encodePath will not cause regression
  27  */
  28 
  29 import java.util.BitSet;
  30 import java.io.File;
  31 import java.util.Random;
  32 import sun.net.www.ParseUtil;
  33 
  34 public class ParseUtil_4922813 {
  35     public static void main(String[] argv) throws Exception {
  36 
  37         int num = 400;
  38         while (num-- >= 0) {
  39             String source = getTestSource();
  40             String ec = sun.net.www.ParseUtil.encodePath(source);
  41             String v117 = ParseUtil_V117.encodePath(source);
  42             if (!ec.equals(v117)) {
  43                 throw new RuntimeException("Test Failed for : \n"
  44                                            + "   source  =<"
  45                                            + getUnicodeString(source)
  46                                            + ">");
  47             }
  48 
  49         }
  50     }
  51 
  52     static int maxCharCount = 200;
  53     static int maxCodePoint = 0x10ffff;
  54     static Random random;
  55     static String getTestSource() {
  56         if (random == null) {
  57             long seed = System.currentTimeMillis();
  58             random = new Random(seed);
  59         }
  60         String source = "";
  61         int i = 0;
  62         int count = random.nextInt(maxCharCount) + 1;
  63         while (i < count) {
  64             int codepoint = random.nextInt(127);
  65             source = source + String.valueOf((char)codepoint);
  66 
  67             codepoint = random.nextInt(0x7ff);
  68             source = source + String.valueOf((char)codepoint);
  69 
  70             codepoint = random.nextInt(maxCodePoint);
  71             source = source + new String(Character.toChars(codepoint));
  72 
  73             i += 3;
  74         }
  75         return source;
  76     }
  77 
  78     static String getUnicodeString(String s){
  79         String unicodeString = "";
  80         for(int j=0; j< s.length(); j++){
  81              unicodeString += "0x"+ Integer.toString(s.charAt(j), 16);
  82         }
  83         return unicodeString;
  84     }
  85 }
  86 class ParseUtil_V117 {
  87     static BitSet encodedInPath;
  88     static {
  89         encodedInPath = new BitSet(256);
  90 
  91         // Set the bits corresponding to characters that are encoded in the
  92         // path component of a URI.
  93 
  94         // These characters are reserved in the path segment as described in
  95         // RFC2396 section 3.3.
  96         encodedInPath.set('=');
  97         encodedInPath.set(';');
  98         encodedInPath.set('?');
  99         encodedInPath.set('/');
 100 
 101         // These characters are defined as excluded in RFC2396 section 2.4.3
 102         // and must be escaped if they occur in the data part of a URI.
 103         encodedInPath.set('#');
 104         encodedInPath.set(' ');
 105         encodedInPath.set('<');
 106         encodedInPath.set('>');
 107         encodedInPath.set('%');
 108         encodedInPath.set('"');
 109         encodedInPath.set('{');
 110         encodedInPath.set('}');
 111         encodedInPath.set('|');
 112         encodedInPath.set('\\');
 113         encodedInPath.set('^');
 114         encodedInPath.set('[');
 115         encodedInPath.set(']');
 116         encodedInPath.set('`');
 117 
 118         // US ASCII control characters 00-1F and 7F.
 119         for (int i=0; i<32; i++)
 120             encodedInPath.set(i);
 121         encodedInPath.set(127);
 122     }
 123     /**
 124      * Constructs an encoded version of the specified path string suitable
 125      * for use in the construction of a URL.
 126      *
 127      * A path separator is replaced by a forward slash. The string is UTF8
 128      * encoded. The % escape sequence is used for characters that are above
 129      * 0x7F or those defined in RFC2396 as reserved or excluded in the path
 130      * component of a URL.
 131      */
 132     public static String encodePath(String path) {
 133         StringBuffer sb = new StringBuffer();
 134         int n = path.length();
 135         for (int i=0; i<n; i++) {
 136             char c = path.charAt(i);
 137             if (c == File.separatorChar)
 138                 sb.append('/');
 139             else {
 140                 if (c <= 0x007F) {
 141                     if (encodedInPath.get(c))
 142                         escape(sb, c);
 143                     else
 144                         sb.append(c);
 145                 } else if (c > 0x07FF) {
 146                     escape(sb, (char)(0xE0 | ((c >> 12) & 0x0F)));
 147                     escape(sb, (char)(0x80 | ((c >>  6) & 0x3F)));
 148                     escape(sb, (char)(0x80 | ((c >>  0) & 0x3F)));
 149                 } else {
 150                     escape(sb, (char)(0xC0 | ((c >>  6) & 0x1F)));
 151                     escape(sb, (char)(0x80 | ((c >>  0) & 0x3F)));
 152                 }
 153             }
 154         }
 155         return sb.toString();
 156     }
 157 
 158     /**
 159      * Appends the URL escape sequence for the specified char to the
 160      * specified StringBuffer.
 161      */
 162     private static void escape(StringBuffer s, char c) {
 163         s.append('%');
 164         s.append(Character.forDigit((c >> 4) & 0xF, 16));
 165         s.append(Character.forDigit(c & 0xF, 16));
 166     }
 167 }