root/maint/gnulib/tests/unilbrk/test-u16-possible-linebreaks.c

/* */

DEFINITIONS

1. main

   1 /* Test of line breaking of UTF-16 strings.
   2    Copyright (C) 2008-2021 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 <https://www.gnu.org/licenses/>.  */
  16 
  17 /* Written by Bruno Haible <bruno@clisp.org>, 2008.  */
  18 
  19 #include <config.h>
  20 
  21 #include "unilbrk.h"
  22 
  23 #include <stdlib.h>
  24 
  25 #include "macros.h"
  26 
  27 int
  28 main ()
     /*  */
  29 {
  30   /* Test case n = 0.  */
  31   u16_possible_linebreaks (NULL, 0, "GB18030", NULL);
  32 
  33   {
  34     static const uint16_t input[61] =
  35       /* "Grüß Gott. Здравствуйте! x=(-b±sqrt(b²-4ac))/(2a)  日本語,中文,한글" */
  36       { 'G', 'r', 0x00FC, 0x00DF, ' ', 'G', 'o', 't', 't', '.', ' ',
  37         0x0417, 0x0434, 0x0440, 0x0430, 0x0432, 0x0441, 0x0442, 0x0432, 0x0443,
  38         0x0439, 0x0442, 0x0435, '!', ' ',
  39         'x', '=', '(', '-', 'b', 0x00B1, 's', 'q', 'r', 't', '(', 'b', 0x00B2,
  40         '-', '4', 'a', 'c', ')', ')', '/', '(', '2', 'a', ')', ' ', ' ',
  41         0x65E5, 0x672C, 0x8A9E, ',', 0x4E2D, 0x6587, ',', 0xD55C, 0xAE00, '\n'
  42       };
  43 
  44     {
  45       char *p = (char *) malloc (SIZEOF (input));
  46       size_t i;
  47 
  48       u16_possible_linebreaks (input, SIZEOF (input), "GB18030", p);
  49       for (i = 0; i < 61; i++)
  50         {
  51           ASSERT (p[i] == (i == 60 ? UC_BREAK_MANDATORY :
  52                            i == 5
  53                            || i == 11 || i == 25
  54                            || i == 29 || i == 30
  55                            || i == 45 || i == 51
  56                            || i == 52 || i == 53 || i == 55 || i == 56
  57                            || i == 58 || i == 59 ? UC_BREAK_POSSIBLE :
  58                            UC_BREAK_PROHIBITED));
  59         }
  60       free (p);
  61     }
  62 
  63     {
  64       char *p = (char *) malloc (SIZEOF (input));
  65       size_t i;
  66 
  67       u16_possible_linebreaks (input, SIZEOF (input), "GB2312", p);
  68       for (i = 0; i < 61; i++)
  69         {
  70           ASSERT (p[i] == (i == 60 ? UC_BREAK_MANDATORY :
  71                            i == 5
  72                            || i == 11 || i == 25
  73                            || i == 29 || i == 30
  74                            || i == 37 || i == 45 || i == 51
  75                            || i == 52 || i == 53 || i == 55 || i == 56
  76                            || i == 58 || i == 59 ? UC_BREAK_POSSIBLE :
  77                            UC_BREAK_PROHIBITED));
  78         }
  79       free (p);
  80     }
  81   }
  82 
  83   /* Test that a break is possible after a zero-width space followed by some
  84      regular spaces (rule LB8 in Unicode TR#14 revision 26).  */
  85   {
  86     static const uint16_t input[4] = { 'x', 0x200B, ' ', 'y' };
  87     char *p = (char *) malloc (SIZEOF (input));
  88     size_t i;
  89 
  90     u16_possible_linebreaks (input, SIZEOF (input), "UTF-8", p);
  91     for (i = 0; i < 4; i++)
  92       {
  93         ASSERT (p[i] == (i == 3 ? UC_BREAK_POSSIBLE : UC_BREAK_PROHIBITED));
  94       }
  95     free (p);
  96   }
  97 
  98   return 0;
  99 }

/* */