1 /*
   2  * Copyright (c) 2005, 2006, 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 /*
  25  * @test
  26  * @summary Unit test for sun.net.idn.Punycode
  27  * @bug 4737170
  28  * @modules java.base/sun.net.idn
  29  * @compile -XDignore.symbol.file PunycodeTest.java
  30  * @run main/othervm -ea PunycodeTest
  31  * @author Edward Wang
  32  */
  33 
  34 import java.util.Scanner;
  35 import java.text.ParseException;
  36 import sun.net.idn.Punycode;
  37 
  38 /**
  39  * unit test for Punycode that is also originated from the sample code
  40  * provided in rfc3492.txt
  41  */
  42 public class PunycodeTest {
  43 
  44     /* For testing, we'll just set some compile-time limits rather than */
  45     /* use malloc(), and set a compile-time option rather than using a  */
  46     /* command-line option.                                             */
  47 
  48     static final int  unicode_max_length = 256;
  49     static final int  ace_max_length = 256;
  50 
  51     static final String too_big =
  52             "input or output is too large, recompile with larger limits\n";
  53     static final String invalid_input = "invalid input\n";
  54     static final String overflow = "arithmetic overflow\n";
  55     static final String io_error = "I/O error\n";
  56 
  57     /* The following string is used to convert printable */
  58     /* characters between ASCII and the native charset:  */
  59 
  60     static void fail(String msg, String input) {
  61         System.out.println(msg+" input: "+input);
  62         throw new RuntimeException(msg+" input: "+input);
  63     }
  64 
  65 
  66     public int testCount = 0;
  67 
  68     private int input_length, j;
  69     private int output_length[] = new int[1];
  70     private boolean case_flags[] = new boolean[unicode_max_length];
  71 
  72     public String testEncoding(String inputS) {
  73         char input[] = new char[unicode_max_length];
  74         int codept = 0;
  75         char uplus[] = new char[2];
  76         StringBuffer output;
  77         int c;
  78 
  79         /* Read the input code points: */
  80 
  81         input_length = 0;
  82 
  83         Scanner sc = new Scanner(inputS);
  84 
  85         while (sc.hasNext()) {  // need to stop at end of line
  86             try {
  87                 String next = sc.next();
  88                 uplus[0] = next.charAt(0);
  89                 uplus[1] = next.charAt(1);
  90                 codept = Integer.parseInt(next.substring(2), 16);
  91             } catch (Exception ex) {
  92                 fail(invalid_input, inputS);
  93             }
  94 
  95             if (uplus[1] != '+' || codept > Integer.MAX_VALUE) {
  96                 fail(invalid_input, inputS);
  97             }
  98 
  99             if (input_length == unicode_max_length) fail(too_big, inputS);
 100 
 101             if (uplus[0] == 'u') case_flags[input_length] = false;
 102             else if (uplus[0] == 'U') case_flags[input_length] = true;
 103             else fail(invalid_input, inputS);
 104 
 105             input[input_length++] = (char)codept;
 106         }
 107 
 108         /* Encode: */
 109 
 110         output_length[0] = ace_max_length;
 111         try {
 112             output = Punycode.encode((new StringBuffer()).append(input, 0, input_length), case_flags);
 113         } catch (Exception e) {
 114             fail(invalid_input, inputS);
 115             // never reach here, just to make compiler happy
 116             return null;
 117         }
 118 
 119         testCount++;
 120         return output.toString();
 121     }
 122 
 123     public String testDecoding(String inputS) {
 124         char input[] = new char[0];
 125         int pp;
 126         StringBuffer output;
 127 
 128         /* Read the Punycode input string and convert to ASCII: */
 129 
 130         if (inputS.length() <= ace_max_length+2) {
 131             input = inputS.toCharArray();
 132         } else {
 133             fail(invalid_input, inputS);
 134         }
 135         input_length = input.length;
 136 
 137         /* Decode: */
 138 
 139         output_length[0] = unicode_max_length;
 140         try {
 141             output = Punycode.decode((new StringBuffer()).append(input, 0, input_length), case_flags);
 142         } catch (Exception e) {
 143             fail(invalid_input, inputS);
 144             // never reach here, just to make compiler happy
 145             return null;
 146         }
 147 
 148         /* Output the result: */
 149         StringBuffer result = new StringBuffer();
 150         for (j = 0;  j < output.length();  ++j) {
 151             result.append(String.format("%s+%04X ",
 152                     case_flags[j] ? "U" : "u",
 153                     (int)output.charAt(j) ));
 154         }
 155 
 156         testCount++;
 157         return result.substring(0, result.length() - 1);
 158     }
 159 
 160   // test data from rfc3492
 161   static String[][] testdata = {
 162     {"(A) Arabic (Egyptian):",
 163      "u+0644 u+064A u+0647 u+0645 u+0627 u+0628 u+062A u+0643 u+0644 "+
 164      "u+0645 u+0648 u+0634 u+0639 u+0631 u+0628 u+064A u+061F",
 165      "egbpdaj6bu4bxfgehfvwxn"},
 166     {"(B) Chinese (simplified):",
 167      "u+4ED6 u+4EEC u+4E3A u+4EC0 u+4E48 u+4E0D u+8BF4 u+4E2D u+6587",
 168      "ihqwcrb4cv8a8dqg056pqjye"},
 169     {"(C) Chinese (traditional):",
 170     "u+4ED6 u+5011 u+7232 u+4EC0 u+9EBD u+4E0D u+8AAA u+4E2D u+6587",
 171     "ihqwctvzc91f659drss3x8bo0yb"},
 172     {"(D) Czech: Pro<ccaron>prost<ecaron>nemluv<iacute><ccaron>esky",
 173     "U+0050 u+0072 u+006F u+010D u+0070 u+0072 u+006F u+0073 u+0074 "+
 174      "u+011B u+006E u+0065 u+006D u+006C u+0075 u+0076 u+00ED u+010D "+
 175      "u+0065 u+0073 u+006B u+0079",
 176     "Proprostnemluvesky-uyb24dma41a"},
 177     {"(E) Hebrew:",
 178     "u+05DC u+05DE u+05D4 u+05D4 u+05DD u+05E4 u+05E9 u+05D5 u+05D8 "+
 179      "u+05DC u+05D0 u+05DE u+05D3 u+05D1 u+05E8 u+05D9 u+05DD u+05E2 "+
 180      "u+05D1 u+05E8 u+05D9 u+05EA",
 181     "4dbcagdahymbxekheh6e0a7fei0b"},
 182     {"(F) Hindi (Devanagari):",
 183     "u+092F u+0939 u+0932 u+094B u+0917 u+0939 u+093F u+0928 u+094D "+
 184      "u+0926 u+0940 u+0915 u+094D u+092F u+094B u+0902 u+0928 u+0939 "+
 185      "u+0940 u+0902 u+092C u+094B u+0932 u+0938 u+0915 u+0924 u+0947 "+
 186      "u+0939 u+0948 u+0902",
 187     "i1baa7eci9glrd9b2ae1bj0hfcgg6iyaf8o0a1dig0cd"},
 188     {"(G) Japanese (kanji and hiragana):",
 189     "u+306A u+305C u+307F u+3093 u+306A u+65E5 u+672C u+8A9E u+3092 "+
 190      "u+8A71 u+3057 u+3066 u+304F u+308C u+306A u+3044 u+306E u+304B",
 191     "n8jok5ay5dzabd5bym9f0cm5685rrjetr6pdxa"},
 192     {"(H) Korean (Hangul syllables):",
 193     "u+C138 u+ACC4 u+C758 u+BAA8 u+B4E0 u+C0AC u+B78C u+B4E4 u+C774 "+
 194      "u+D55C u+AD6D u+C5B4 u+B97C u+C774 u+D574 u+D55C u+B2E4 u+BA74 "+
 195      "u+C5BC u+B9C8 u+B098 u+C88B u+C744 u+AE4C",
 196     "989aomsvi5e83db1d2a355cv1e0vak1dwrv93d5xbh15a0dt30a5j"+
 197     "psd879ccm6fea98c"},
 198     {"(I) Russian (Cyrillic):",
 199     "U+043F u+043E u+0447 u+0435 u+043C u+0443 u+0436 u+0435 u+043E "+
 200      "u+043D u+0438 u+043D u+0435 u+0433 u+043E u+0432 u+043E u+0440 "+
 201      "u+044F u+0442 u+043F u+043E u+0440 u+0443 u+0441 u+0441 u+043A "+
 202      "u+0438",
 203     "b1abfaaepdrnnbgefbaDotcwatmq2g4l"},
 204     {"(J) Spanish: Porqu<eacute>nopuedensimplementehablarenEspa<ntilde>ol",
 205     "U+0050 u+006F u+0072 u+0071 u+0075 u+00E9 u+006E u+006F u+0070 "+
 206      "u+0075 u+0065 u+0064 u+0065 u+006E u+0073 u+0069 u+006D u+0070 "+
 207      "u+006C u+0065 u+006D u+0065 u+006E u+0074 u+0065 u+0068 u+0061 "+
 208      "u+0062 u+006C u+0061 u+0072 u+0065 u+006E U+0045 u+0073 u+0070 "+
 209      "u+0061 u+00F1 u+006F u+006C",
 210     "PorqunopuedensimplementehablarenEspaol-fmd56a"},
 211     {"(K) Vietnamese:"+
 212      "T<adotbelow>isaoh<odotbelow>kh<ocirc>ngth<ecirchookabove>ch"+
 213      "<ihookabove>n<oacute>iti<ecircacute>ngVi<ecircdotbelow>t",
 214     "U+0054 u+1EA1 u+0069 u+0073 u+0061 u+006F u+0068 u+1ECD u+006B "+
 215      "u+0068 u+00F4 u+006E u+0067 u+0074 u+0068 u+1EC3 u+0063 u+0068 "+
 216      "u+1EC9 u+006E u+00F3 u+0069 u+0074 u+0069 u+1EBF u+006E u+0067 "+
 217      "U+0056 u+0069 u+1EC7 u+0074",
 218     "TisaohkhngthchnitingVit-kjcr8268qyxafd2f1b9g"},
 219     {"(L) 3<nen>B<gumi><kinpachi><sensei>",
 220      "u+0033 u+5E74 U+0042 u+7D44 u+91D1 u+516B u+5148 u+751F",
 221     "3B-ww4c5e180e575a65lsy2b"},
 222     {"(M) <amuro><namie>-with-SUPER-MONKEYS",
 223      "u+5B89 u+5BA4 u+5948 u+7F8E u+6075 u+002D u+0077 u+0069 u+0074 "+
 224      "u+0068 u+002D U+0053 U+0055 U+0050 U+0045 U+0052 u+002D U+004D "+
 225      "U+004F U+004E U+004B U+0045 U+0059 U+0053",
 226     "-with-SUPER-MONKEYS-pc58ag80a8qai00g7n9n"},
 227     {"(N) Hello-Another-Way-<sorezore><no><basho>",
 228     "U+0048 u+0065 u+006C u+006C u+006F u+002D U+0041 u+006E u+006F "+
 229      "u+0074 u+0068 u+0065 u+0072 u+002D U+0057 u+0061 u+0079 u+002D "+
 230      "u+305D u+308C u+305E u+308C u+306E u+5834 u+6240",
 231     "Hello-Another-Way--fc4qua05auwb3674vfr0b"},
 232     {"(O) <hitotsu><yane><no><shita>2",
 233      "u+3072 u+3068 u+3064 u+5C4B u+6839 u+306E u+4E0B u+0032",
 234     "2-u9tlzr9756bt3uc0v"},
 235     {"(P) Maji<de>Koi<suru>5<byou><mae>",
 236      "U+004D u+0061 u+006A u+0069 u+3067 U+004B u+006F u+0069 u+3059 "+
 237      "u+308B u+0035 u+79D2 u+524D",
 238     "MajiKoi5-783gue6qz075azm5e"},
 239     {"(Q) <pafii>de<runba>",
 240      "u+30D1 u+30D5 u+30A3 u+30FC u+0064 u+0065 u+30EB u+30F3 u+30D0",
 241     "de-jg4avhby1noc0d"},
 242     {"(R) <sono><supiido><de>",
 243      "u+305D u+306E u+30B9 u+30D4 u+30FC u+30C9 u+3067",
 244     "d9juau41awczczp"},
 245     {"(S) -> $1.00 <-",
 246      "u+002D u+003E u+0020 u+0024 u+0031 u+002E u+0030 u+0030 u+0020 "+
 247      "u+003C u+002D",
 248     "-> $1.00 <--"},
 249   };
 250 
 251   public static void main(String[] argv) throws Exception {
 252       PunycodeTest mytest = new PunycodeTest();
 253       for (int i = 0; i < testdata.length; i++) {
 254           String encodeResult = mytest.testEncoding(testdata[i][1]);
 255           String decodeResult = mytest.testDecoding(testdata[i][2]);
 256 
 257           checkResult(encodeResult, testdata[i][2]);
 258           checkResult(decodeResult, testdata[i][1]);
 259       }
 260 
 261       System.out.println("Test cases: " + mytest.testCount);
 262   }
 263 
 264   public static void checkResult(String actual, String expected) {
 265       if (!actual.equals(expected)) {
 266           System.out.printf("\n%15s: %s\n", "FAILED", actual);
 267           System.out.printf("%15s: %s\n\n", "should be", expected);
 268           throw new RuntimeException("Punycode test failed.");
 269       } else {
 270           System.out.printf("%15s: %s\n", "SUCCEEDED", actual);
 271       }
 272   }
 273 
 274 }