1 /*
   2  * Copyright (c) 2005, 2020, 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 jdk.internal.icu.impl.Punycode
  27  * @bug 4737170 8174270
  28  * @modules java.base/jdk.internal.icu.impl
  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 jdk.internal.icu.impl.Punycode;
  36 
  37 /**
  38  * unit test for Punycode that is also originated from the sample code
  39  * provided in rfc3492.txt
  40  */
  41 public class PunycodeTest {
  42 
  43     /* For testing, we'll just set some compile-time limits rather than */
  44     /* use malloc(), and set a compile-time option rather than using a  */
  45     /* command-line option.                                             */
  46 
  47     static final int  unicode_max_length = 256;
  48     static final int  ace_max_length = 256;
  49 
  50     static final String too_big =
  51             "input or output is too large, recompile with larger limits\n";
  52     static final String invalid_input = "invalid input\n";
  53     static final String overflow = "arithmetic overflow\n";
  54     static final String io_error = "I/O error\n";
  55 
  56     /* The following string is used to convert printable */
  57     /* characters between ASCII and the native charset:  */
  58 
  59     static void fail(String msg, String input) {
  60         System.out.println(msg+" input: "+input);
  61         throw new RuntimeException(msg+" input: "+input);
  62     }
  63 
  64 
  65     public int testCount = 0;
  66 
  67     private int input_length, j;
  68     private int output_length[] = new int[1];
  69     private boolean case_flags[] = new boolean[unicode_max_length];
  70 
  71     public String testEncoding(String inputS) {
  72         char input[] = new char[unicode_max_length];
  73         int codept = 0;
  74         char uplus[] = new char[2];
  75         StringBuffer output;
  76         int c;
  77 
  78         /* Read the input code points: */
  79 
  80         input_length = 0;
  81 
  82         Scanner sc = new Scanner(inputS);
  83 
  84         while (sc.hasNext()) {  // need to stop at end of line
  85             try {
  86                 String next = sc.next();
  87                 uplus[0] = next.charAt(0);
  88                 uplus[1] = next.charAt(1);
  89                 codept = Integer.parseInt(next.substring(2), 16);
  90             } catch (Exception ex) {
  91                 fail(invalid_input, inputS);
  92             }
  93 
  94             if (uplus[1] != '+' || codept > Integer.MAX_VALUE) {
  95                 fail(invalid_input, inputS);
  96             }
  97 
  98             if (input_length == unicode_max_length) fail(too_big, inputS);
  99 
 100             if (uplus[0] == 'u') case_flags[input_length] = false;
 101             else if (uplus[0] == 'U') case_flags[input_length] = true;
 102             else fail(invalid_input, inputS);
 103 
 104             input[input_length++] = (char)codept;
 105         }
 106 
 107         /* Encode: */
 108 
 109         output_length[0] = ace_max_length;
 110         try {
 111             output = Punycode.encode((new StringBuffer()).append(input, 0, input_length), case_flags);
 112         } catch (Exception e) {
 113             fail(invalid_input, inputS);
 114             // never reach here, just to make compiler happy
 115             return null;
 116         }
 117 
 118         testCount++;
 119         return output.toString();
 120     }
 121 
 122     public String testDecoding(String inputS) {
 123         char input[] = new char[0];
 124         int pp;
 125         StringBuffer output;
 126 
 127         /* Read the Punycode input string and convert to ASCII: */
 128 
 129         if (inputS.length() <= ace_max_length+2) {
 130             input = inputS.toCharArray();
 131         } else {
 132             fail(invalid_input, inputS);
 133         }
 134         input_length = input.length;
 135 
 136         /* Decode: */
 137 
 138         output_length[0] = unicode_max_length;
 139         try {
 140             output = Punycode.decode((new StringBuffer()).append(input, 0, input_length), case_flags);
 141         } catch (Exception e) {
 142             fail(invalid_input, inputS);
 143             // never reach here, just to make compiler happy
 144             return null;
 145         }
 146 
 147         /* Output the result: */
 148         StringBuffer result = new StringBuffer();
 149         for (j = 0;  j < output.length();  ++j) {
 150             result.append(String.format("%s+%04X ",
 151                     case_flags[j] ? "U" : "u",
 152                     (int)output.charAt(j) ));
 153         }
 154 
 155         testCount++;
 156         return result.substring(0, result.length() - 1);
 157     }
 158 
 159   // test data from rfc3492
 160   static String[][] testdata = {
 161     {"(A) Arabic (Egyptian):",
 162      "u+0644 u+064A u+0647 u+0645 u+0627 u+0628 u+062A u+0643 u+0644 "+
 163      "u+0645 u+0648 u+0634 u+0639 u+0631 u+0628 u+064A u+061F",
 164      "egbpdaj6bu4bxfgehfvwxn"},
 165     {"(B) Chinese (simplified):",
 166      "u+4ED6 u+4EEC u+4E3A u+4EC0 u+4E48 u+4E0D u+8BF4 u+4E2D u+6587",
 167      "ihqwcrb4cv8a8dqg056pqjye"},
 168     {"(C) Chinese (traditional):",
 169     "u+4ED6 u+5011 u+7232 u+4EC0 u+9EBD u+4E0D u+8AAA u+4E2D u+6587",
 170     "ihqwctvzc91f659drss3x8bo0yb"},
 171     {"(D) Czech: Pro<ccaron>prost<ecaron>nemluv<iacute><ccaron>esky",
 172     "U+0050 u+0072 u+006F u+010D u+0070 u+0072 u+006F u+0073 u+0074 "+
 173      "u+011B u+006E u+0065 u+006D u+006C u+0075 u+0076 u+00ED u+010D "+
 174      "u+0065 u+0073 u+006B u+0079",
 175     "Proprostnemluvesky-uyb24dma41a"},
 176     {"(E) Hebrew:",
 177     "u+05DC u+05DE u+05D4 u+05D4 u+05DD u+05E4 u+05E9 u+05D5 u+05D8 "+
 178      "u+05DC u+05D0 u+05DE u+05D3 u+05D1 u+05E8 u+05D9 u+05DD u+05E2 "+
 179      "u+05D1 u+05E8 u+05D9 u+05EA",
 180     "4dbcagdahymbxekheh6e0a7fei0b"},
 181     {"(F) Hindi (Devanagari):",
 182     "u+092F u+0939 u+0932 u+094B u+0917 u+0939 u+093F u+0928 u+094D "+
 183      "u+0926 u+0940 u+0915 u+094D u+092F u+094B u+0902 u+0928 u+0939 "+
 184      "u+0940 u+0902 u+092C u+094B u+0932 u+0938 u+0915 u+0924 u+0947 "+
 185      "u+0939 u+0948 u+0902",
 186     "i1baa7eci9glrd9b2ae1bj0hfcgg6iyaf8o0a1dig0cd"},
 187     {"(G) Japanese (kanji and hiragana):",
 188     "u+306A u+305C u+307F u+3093 u+306A u+65E5 u+672C u+8A9E u+3092 "+
 189      "u+8A71 u+3057 u+3066 u+304F u+308C u+306A u+3044 u+306E u+304B",
 190     "n8jok5ay5dzabd5bym9f0cm5685rrjetr6pdxa"},
 191     {"(H) Korean (Hangul syllables):",
 192     "u+C138 u+ACC4 u+C758 u+BAA8 u+B4E0 u+C0AC u+B78C u+B4E4 u+C774 "+
 193      "u+D55C u+AD6D u+C5B4 u+B97C u+C774 u+D574 u+D55C u+B2E4 u+BA74 "+
 194      "u+C5BC u+B9C8 u+B098 u+C88B u+C744 u+AE4C",
 195     "989aomsvi5e83db1d2a355cv1e0vak1dwrv93d5xbh15a0dt30a5j"+
 196     "psd879ccm6fea98c"},
 197     {"(I) Russian (Cyrillic):",
 198     "U+043F u+043E u+0447 u+0435 u+043C u+0443 u+0436 u+0435 u+043E "+
 199      "u+043D u+0438 u+043D u+0435 u+0433 u+043E u+0432 u+043E u+0440 "+
 200      "u+044F u+0442 u+043F u+043E u+0440 u+0443 u+0441 u+0441 u+043A "+
 201      "u+0438",
 202     "b1abfaaepdrnnbgefbaDotcwatmq2g4l"},
 203     {"(J) Spanish: Porqu<eacute>nopuedensimplementehablarenEspa<ntilde>ol",
 204     "U+0050 u+006F u+0072 u+0071 u+0075 u+00E9 u+006E u+006F u+0070 "+
 205      "u+0075 u+0065 u+0064 u+0065 u+006E u+0073 u+0069 u+006D u+0070 "+
 206      "u+006C u+0065 u+006D u+0065 u+006E u+0074 u+0065 u+0068 u+0061 "+
 207      "u+0062 u+006C u+0061 u+0072 u+0065 u+006E U+0045 u+0073 u+0070 "+
 208      "u+0061 u+00F1 u+006F u+006C",
 209     "PorqunopuedensimplementehablarenEspaol-fmd56a"},
 210     {"(K) Vietnamese:"+
 211      "T<adotbelow>isaoh<odotbelow>kh<ocirc>ngth<ecirchookabove>ch"+
 212      "<ihookabove>n<oacute>iti<ecircacute>ngVi<ecircdotbelow>t",
 213     "U+0054 u+1EA1 u+0069 u+0073 u+0061 u+006F u+0068 u+1ECD u+006B "+
 214      "u+0068 u+00F4 u+006E u+0067 u+0074 u+0068 u+1EC3 u+0063 u+0068 "+
 215      "u+1EC9 u+006E u+00F3 u+0069 u+0074 u+0069 u+1EBF u+006E u+0067 "+
 216      "U+0056 u+0069 u+1EC7 u+0074",
 217     "TisaohkhngthchnitingVit-kjcr8268qyxafd2f1b9g"},
 218     {"(L) 3<nen>B<gumi><kinpachi><sensei>",
 219      "u+0033 u+5E74 U+0042 u+7D44 u+91D1 u+516B u+5148 u+751F",
 220     "3B-ww4c5e180e575a65lsy2b"},
 221     {"(M) <amuro><namie>-with-SUPER-MONKEYS",
 222      "u+5B89 u+5BA4 u+5948 u+7F8E u+6075 u+002D u+0077 u+0069 u+0074 "+
 223      "u+0068 u+002D U+0053 U+0055 U+0050 U+0045 U+0052 u+002D U+004D "+
 224      "U+004F U+004E U+004B U+0045 U+0059 U+0053",
 225     "-with-SUPER-MONKEYS-pc58ag80a8qai00g7n9n"},
 226     {"(N) Hello-Another-Way-<sorezore><no><basho>",
 227     "U+0048 u+0065 u+006C u+006C u+006F u+002D U+0041 u+006E u+006F "+
 228      "u+0074 u+0068 u+0065 u+0072 u+002D U+0057 u+0061 u+0079 u+002D "+
 229      "u+305D u+308C u+305E u+308C u+306E u+5834 u+6240",
 230     "Hello-Another-Way--fc4qua05auwb3674vfr0b"},
 231     {"(O) <hitotsu><yane><no><shita>2",
 232      "u+3072 u+3068 u+3064 u+5C4B u+6839 u+306E u+4E0B u+0032",
 233     "2-u9tlzr9756bt3uc0v"},
 234     {"(P) Maji<de>Koi<suru>5<byou><mae>",
 235      "U+004D u+0061 u+006A u+0069 u+3067 U+004B u+006F u+0069 u+3059 "+
 236      "u+308B u+0035 u+79D2 u+524D",
 237     "MajiKoi5-783gue6qz075azm5e"},
 238     {"(Q) <pafii>de<runba>",
 239      "u+30D1 u+30D5 u+30A3 u+30FC u+0064 u+0065 u+30EB u+30F3 u+30D0",
 240     "de-jg4avhby1noc0d"},
 241     {"(R) <sono><supiido><de>",
 242      "u+305D u+306E u+30B9 u+30D4 u+30FC u+30C9 u+3067",
 243     "d9juau41awczczp"},
 244     {"(S) -> $1.00 <-",
 245      "u+002D u+003E u+0020 u+0024 u+0031 u+002E u+0030 u+0030 u+0020 "+
 246      "u+003C u+002D",
 247     "-> $1.00 <--"},
 248   };
 249 
 250   public static void main(String[] argv) throws Exception {
 251       PunycodeTest mytest = new PunycodeTest();
 252       for (int i = 0; i < testdata.length; i++) {
 253           String encodeResult = mytest.testEncoding(testdata[i][1]);
 254           String decodeResult = mytest.testDecoding(testdata[i][2]);
 255 
 256           checkResult(encodeResult, testdata[i][2]);
 257           checkResult(decodeResult, testdata[i][1]);
 258       }
 259 
 260       System.out.println("Test cases: " + mytest.testCount);
 261   }
 262 
 263   public static void checkResult(String actual, String expected) {
 264       if (!actual.equals(expected)) {
 265           System.out.printf("\n%15s: %s\n", "FAILED", actual);
 266           System.out.printf("%15s: %s\n\n", "should be", expected);
 267           throw new RuntimeException("Punycode test failed.");
 268       } else {
 269           System.out.printf("%15s: %s\n", "SUCCEEDED", actual);
 270       }
 271   }
 272 
 273 }