tests/unistr/test-u8-mbsnlen.c

   1 /* Test of u8_mbsnlen() function.
   2    Copyright (C) 2010-2017 Free Software Foundation, Inc.
   3
   4    This program is free software: you can redistribute it and/or modify
   5    it under the terms of the GNU General Public License as published by
   6    the Free Software Foundation; either version 3 of the License, or
   7    (at your option) any later version.
   8
   9    This program is distributed in the hope that it will be useful,
  10    but WITHOUT ANY WARRANTY; without even the implied warranty of
  11    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  12    GNU General Public License for more details.
  13
  14    You should have received a copy of the GNU General Public License
  15    along with this program.  If not, see <http://www.gnu.org/licenses/>.  */
  16
  17 /* Written by Bruno Haible <bruno@clisp.org>, 2010.  */
  18
  19 #include <config.h>
  20
  21 #include "unistr.h"
  22
  23 #include "macros.h"
  24
  25 int
  26 main ()
  27 {
  28   /* Simple string.  */
  29   { /* "Grüß Gott. Здравствуйте! x=(-b±sqrt(b²-4ac))/(2a)  日本語,中文,한글" */
  30     static const uint8_t input[] =
  31       { 'G', 'r', 0xC3, 0xBC, 0xC3, 0x9F, ' ', 'G', 'o', 't', 't', '.', ' ',
  32         0xD0, 0x97, 0xD0, 0xB4, 0xD1, 0x80, 0xD0, 0xB0, 0xD0, 0xB2, 0xD1, 0x81,
  33         0xD1, 0x82, 0xD0, 0xB2, 0xD1, 0x83, 0xD0, 0xB9, 0xD1, 0x82, 0xD0, 0xB5,
  34         '!', ' ', 'x', '=', '(', '-', 'b', 0xC2, 0xB1, 's', 'q', 'r', 't', '(',
  35         'b', 0xC2, 0xB2, '-', '4', 'a', 'c', ')', ')', '/', '(', '2', 'a', ')',
  36         ' ', ' ', 0xE6, 0x97, 0xA5, 0xE6, 0x9C, 0xAC, 0xE8, 0xAA, 0x9E, ',',
  37         0xE4, 0xB8, 0xAD, 0xE6, 0x96, 0x87, ',',
  38         0xED, 0x95, 0x9C, 0xEA, 0xB8, 0x80, '\n'
  39       };
  40     static const size_t expected[SIZEOF (input) + 1] =
  41       { 0,
  42         1, 2, 3, 3, 4, 4, 5, 6, 7, 8, 9, 10, 11,
  43         12, 12, 13, 13, 14, 14, 15, 15, 16, 16, 17, 17,
  44         18, 18, 19, 19, 20, 20, 21, 21, 22, 22, 23, 23,
  45         24, 25, 26, 27, 28, 29, 30, 31, 31, 32, 33, 34, 35, 36,
  46         37, 38, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49,
  47         50, 51, 52, 52, 52, 53, 53, 53, 54, 54, 54, 55,
  48         56, 56, 56, 57, 57, 57, 58,
  49         59, 59, 59, 60, 60, 60, 61
  50       };
  51     size_t n;
  52
  53     for (n = 0; n <= SIZEOF (input); n++)
  54       {
  55         size_t len = u8_mbsnlen (input, n);
  56         ASSERT (len == expected[n]);
  57       }
  58   }
  59
  60   /* Test behaviour required by ISO 10646-1, sections R.7 and 2.3c, namely,
  61      that a "malformed sequence" is interpreted in the same way as
  62      "a character that is outside the adopted subset".
  63      Reference:
  64        Markus Kuhn: UTF-8 decoder capability and stress test
  65        <http://www.cl.cam.ac.uk/~mgk25/ucs/examples/UTF-8-test.txt>
  66        <http://www.w3.org/2001/06/utf-8-wrong/UTF-8-test.html>
  67    */
  68   /* 3.1. Test that each unexpected continuation byte is signalled as a
  69      malformed sequence of its own.  */
  70   {
  71     static const uint8_t input[] = { '"', 0x80, 0xBF, 0x80, 0xBF, '"' };
  72     ASSERT (u8_mbsnlen (input, 6) == 6);
  73   }
  74   /* 3.2. Lonely start characters.  */
  75   {
  76     ucs4_t c;
  77     uint8_t input[2];
  78
  79     for (c = 0xC0; c <= 0xFF; c++)
  80       {
  81         input[0] = c;
  82         input[1] = ' ';
  83
  84         ASSERT (u8_mbsnlen (input, 2) == 2);
  85       }
  86   }
  87   /* 3.3. Sequences with last continuation byte missing.  */
  88   /* 3.3.1. 2-byte sequence with last byte missing.  */
  89   {
  90     static const uint8_t input[] = { '"', 0xC0, '"' };
  91     ASSERT (u8_mbsnlen (input, 3) == 3);
  92   }
  93   /* 3.3.6. 2-byte sequence with last byte missing.  */
  94   {
  95     static const uint8_t input[] = { '"', 0xDF, '"' };
  96     ASSERT (u8_mbsnlen (input, 3) == 3);
  97   }
  98   /* 3.3.2. 3-byte sequence with last byte missing.  */
  99   {
 100     static const uint8_t input[] = { '"', 0xE0, 0x80, '"' };
 101     ASSERT (u8_mbsnlen (input, 4) == 3);
 102   }
 103   /* 3.3.7. 3-byte sequence with last byte missing.  */
 104   {
 105     static const uint8_t input[] = { '"', 0xEF, 0xBF, '"' };
 106     ASSERT (u8_mbsnlen (input, 4) == 3);
 107   }
 108   /* 3.3.3. 4-byte sequence with last byte missing.  */
 109   {
 110     static const uint8_t input[] = { '"', 0xF0, 0x80, 0x80, '"' };
 111     ASSERT (u8_mbsnlen (input, 5) == 3);
 112   }
 113   /* 3.3.8. 4-byte sequence with last byte missing.  */
 114   {
 115     static const uint8_t input[] = { '"', 0xF7, 0xBF, 0xBF, '"' };
 116     ASSERT (u8_mbsnlen (input, 5) == 3);
 117   }
 118
 119   return 0;
 120 }