punycode_test.go 5.8 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198
  1. // Copyright 2012 The Go Authors. All rights reserved.
  2. // Use of this source code is governed by a BSD-style
  3. // license that can be found in the LICENSE file.
  4. package idna
  5. import (
  6. "strings"
  7. "testing"
  8. )
  9. var punycodeTestCases = [...]struct {
  10. s, encoded string
  11. }{
  12. {"", ""},
  13. {"-", "--"},
  14. {"-a", "-a-"},
  15. {"-a-", "-a--"},
  16. {"a", "a-"},
  17. {"a-", "a--"},
  18. {"a-b", "a-b-"},
  19. {"books", "books-"},
  20. {"bücher", "bcher-kva"},
  21. {"Hello世界", "Hello-ck1hg65u"},
  22. {"ü", "tda"},
  23. {"üý", "tdac"},
  24. // The test cases below come from RFC 3492 section 7.1 with Errata 3026.
  25. {
  26. // (A) Arabic (Egyptian).
  27. "\u0644\u064A\u0647\u0645\u0627\u0628\u062A\u0643\u0644" +
  28. "\u0645\u0648\u0634\u0639\u0631\u0628\u064A\u061F",
  29. "egbpdaj6bu4bxfgehfvwxn",
  30. },
  31. {
  32. // (B) Chinese (simplified).
  33. "\u4ED6\u4EEC\u4E3A\u4EC0\u4E48\u4E0D\u8BF4\u4E2D\u6587",
  34. "ihqwcrb4cv8a8dqg056pqjye",
  35. },
  36. {
  37. // (C) Chinese (traditional).
  38. "\u4ED6\u5011\u7232\u4EC0\u9EBD\u4E0D\u8AAA\u4E2D\u6587",
  39. "ihqwctvzc91f659drss3x8bo0yb",
  40. },
  41. {
  42. // (D) Czech.
  43. "\u0050\u0072\u006F\u010D\u0070\u0072\u006F\u0073\u0074" +
  44. "\u011B\u006E\u0065\u006D\u006C\u0075\u0076\u00ED\u010D" +
  45. "\u0065\u0073\u006B\u0079",
  46. "Proprostnemluvesky-uyb24dma41a",
  47. },
  48. {
  49. // (E) Hebrew.
  50. "\u05DC\u05DE\u05D4\u05D4\u05DD\u05E4\u05E9\u05D5\u05D8" +
  51. "\u05DC\u05D0\u05DE\u05D3\u05D1\u05E8\u05D9\u05DD\u05E2" +
  52. "\u05D1\u05E8\u05D9\u05EA",
  53. "4dbcagdahymbxekheh6e0a7fei0b",
  54. },
  55. {
  56. // (F) Hindi (Devanagari).
  57. "\u092F\u0939\u0932\u094B\u0917\u0939\u093F\u0928\u094D" +
  58. "\u0926\u0940\u0915\u094D\u092F\u094B\u0902\u0928\u0939" +
  59. "\u0940\u0902\u092C\u094B\u0932\u0938\u0915\u0924\u0947" +
  60. "\u0939\u0948\u0902",
  61. "i1baa7eci9glrd9b2ae1bj0hfcgg6iyaf8o0a1dig0cd",
  62. },
  63. {
  64. // (G) Japanese (kanji and hiragana).
  65. "\u306A\u305C\u307F\u3093\u306A\u65E5\u672C\u8A9E\u3092" +
  66. "\u8A71\u3057\u3066\u304F\u308C\u306A\u3044\u306E\u304B",
  67. "n8jok5ay5dzabd5bym9f0cm5685rrjetr6pdxa",
  68. },
  69. {
  70. // (H) Korean (Hangul syllables).
  71. "\uC138\uACC4\uC758\uBAA8\uB4E0\uC0AC\uB78C\uB4E4\uC774" +
  72. "\uD55C\uAD6D\uC5B4\uB97C\uC774\uD574\uD55C\uB2E4\uBA74" +
  73. "\uC5BC\uB9C8\uB098\uC88B\uC744\uAE4C",
  74. "989aomsvi5e83db1d2a355cv1e0vak1dwrv93d5xbh15a0dt30a5j" +
  75. "psd879ccm6fea98c",
  76. },
  77. {
  78. // (I) Russian (Cyrillic).
  79. "\u043F\u043E\u0447\u0435\u043C\u0443\u0436\u0435\u043E" +
  80. "\u043D\u0438\u043D\u0435\u0433\u043E\u0432\u043E\u0440" +
  81. "\u044F\u0442\u043F\u043E\u0440\u0443\u0441\u0441\u043A" +
  82. "\u0438",
  83. "b1abfaaepdrnnbgefbadotcwatmq2g4l",
  84. },
  85. {
  86. // (J) Spanish.
  87. "\u0050\u006F\u0072\u0071\u0075\u00E9\u006E\u006F\u0070" +
  88. "\u0075\u0065\u0064\u0065\u006E\u0073\u0069\u006D\u0070" +
  89. "\u006C\u0065\u006D\u0065\u006E\u0074\u0065\u0068\u0061" +
  90. "\u0062\u006C\u0061\u0072\u0065\u006E\u0045\u0073\u0070" +
  91. "\u0061\u00F1\u006F\u006C",
  92. "PorqunopuedensimplementehablarenEspaol-fmd56a",
  93. },
  94. {
  95. // (K) Vietnamese.
  96. "\u0054\u1EA1\u0069\u0073\u0061\u006F\u0068\u1ECD\u006B" +
  97. "\u0068\u00F4\u006E\u0067\u0074\u0068\u1EC3\u0063\u0068" +
  98. "\u1EC9\u006E\u00F3\u0069\u0074\u0069\u1EBF\u006E\u0067" +
  99. "\u0056\u0069\u1EC7\u0074",
  100. "TisaohkhngthchnitingVit-kjcr8268qyxafd2f1b9g",
  101. },
  102. {
  103. // (L) 3<nen>B<gumi><kinpachi><sensei>.
  104. "\u0033\u5E74\u0042\u7D44\u91D1\u516B\u5148\u751F",
  105. "3B-ww4c5e180e575a65lsy2b",
  106. },
  107. {
  108. // (M) <amuro><namie>-with-SUPER-MONKEYS.
  109. "\u5B89\u5BA4\u5948\u7F8E\u6075\u002D\u0077\u0069\u0074" +
  110. "\u0068\u002D\u0053\u0055\u0050\u0045\u0052\u002D\u004D" +
  111. "\u004F\u004E\u004B\u0045\u0059\u0053",
  112. "-with-SUPER-MONKEYS-pc58ag80a8qai00g7n9n",
  113. },
  114. {
  115. // (N) Hello-Another-Way-<sorezore><no><basho>.
  116. "\u0048\u0065\u006C\u006C\u006F\u002D\u0041\u006E\u006F" +
  117. "\u0074\u0068\u0065\u0072\u002D\u0057\u0061\u0079\u002D" +
  118. "\u305D\u308C\u305E\u308C\u306E\u5834\u6240",
  119. "Hello-Another-Way--fc4qua05auwb3674vfr0b",
  120. },
  121. {
  122. // (O) <hitotsu><yane><no><shita>2.
  123. "\u3072\u3068\u3064\u5C4B\u6839\u306E\u4E0B\u0032",
  124. "2-u9tlzr9756bt3uc0v",
  125. },
  126. {
  127. // (P) Maji<de>Koi<suru>5<byou><mae>
  128. "\u004D\u0061\u006A\u0069\u3067\u004B\u006F\u0069\u3059" +
  129. "\u308B\u0035\u79D2\u524D",
  130. "MajiKoi5-783gue6qz075azm5e",
  131. },
  132. {
  133. // (Q) <pafii>de<runba>
  134. "\u30D1\u30D5\u30A3\u30FC\u0064\u0065\u30EB\u30F3\u30D0",
  135. "de-jg4avhby1noc0d",
  136. },
  137. {
  138. // (R) <sono><supiido><de>
  139. "\u305D\u306E\u30B9\u30D4\u30FC\u30C9\u3067",
  140. "d9juau41awczczp",
  141. },
  142. {
  143. // (S) -> $1.00 <-
  144. "\u002D\u003E\u0020\u0024\u0031\u002E\u0030\u0030\u0020" +
  145. "\u003C\u002D",
  146. "-> $1.00 <--",
  147. },
  148. }
  149. func TestPunycode(t *testing.T) {
  150. for _, tc := range punycodeTestCases {
  151. if got, err := decode(tc.encoded); err != nil {
  152. t.Errorf("decode(%q): %v", tc.encoded, err)
  153. } else if got != tc.s {
  154. t.Errorf("decode(%q): got %q, want %q", tc.encoded, got, tc.s)
  155. }
  156. if got, err := encode("", tc.s); err != nil {
  157. t.Errorf(`encode("", %q): %v`, tc.s, err)
  158. } else if got != tc.encoded {
  159. t.Errorf(`encode("", %q): got %q, want %q`, tc.s, got, tc.encoded)
  160. }
  161. }
  162. }
  163. var punycodeErrorTestCases = [...]string{
  164. "decode -", // A sole '-' is invalid.
  165. "decode foo\x00bar", // '\x00' is not in [0-9A-Za-z].
  166. "decode foo#bar", // '#' is not in [0-9A-Za-z].
  167. "decode foo\u00A3bar", // '\u00A3' is not in [0-9A-Za-z].
  168. "decode 9", // "9a" decodes to codepoint \u00A3; "9" is truncated.
  169. "decode 99999a", // "99999a" decodes to codepoint \U0048A3C1, which is > \U0010FFFF.
  170. "decode 9999999999a", // "9999999999a" overflows the int32 calculation.
  171. "encode " + strings.Repeat("x", 65536) + "\uff00", // int32 overflow.
  172. }
  173. func TestPunycodeErrors(t *testing.T) {
  174. for _, tc := range punycodeErrorTestCases {
  175. var err error
  176. switch {
  177. case strings.HasPrefix(tc, "decode "):
  178. _, err = decode(tc[7:])
  179. case strings.HasPrefix(tc, "encode "):
  180. _, err = encode("", tc[7:])
  181. }
  182. if err == nil {
  183. if len(tc) > 256 {
  184. tc = tc[:100] + "..." + tc[len(tc)-100:]
  185. }
  186. t.Errorf("no error for %s", tc)
  187. }
  188. }
  189. }