root/maint/gnulib/tests/unilbrk/test-u8-possible-linebreaks.c

/* */

DEFINITIONS

1. main

   1 /* Test of line breaking of UTF-8 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   u8_possible_linebreaks (NULL, 0, "GB18030", NULL);
  32 
  33   {
  34     static const uint8_t input[91] =
  35       /* "Grüß Gott. Здравствуйте! x=(-b±sqrt(b²-4ac))/(2a)  日本語,中文,한글" */
  36       "Gr\303\274\303\237 Gott. \320\227\320\264\321\200\320\260\320\262\321\201\321\202\320\262\321\203\320\271\321\202\320\265! x=(-b\302\261sqrt(b\302\262-4ac))/(2a)  \346\227\245\346\234\254\350\252\236,\344\270\255\346\226\207,\355\225\234\352\270\200\n";
  37 
  38     {
  39       char *p = (char *) malloc (SIZEOF (input));
  40       size_t i;
  41 
  42       u8_possible_linebreaks (input, SIZEOF (input), "GB18030", p);
  43       for (i = 0; i < 91; i++)
  44         {
  45           ASSERT (p[i] == (i == 90 ? UC_BREAK_MANDATORY :
  46                            i == 7
  47                            || i == 13 || i == 39
  48                            || i == 43 || i == 44
  49                            || i == 61 || i == 67
  50                            || i == 70 || i == 73 || i == 77 || i == 80
  51                            || i == 84 || i == 87 ? UC_BREAK_POSSIBLE :
  52                            UC_BREAK_PROHIBITED));
  53         }
  54       free (p);
  55     }
  56 
  57     {
  58       char *p = (char *) malloc (SIZEOF (input));
  59       size_t i;
  60 
  61       u8_possible_linebreaks (input, SIZEOF (input), "GB2312", p);
  62       for (i = 0; i < 91; i++)
  63         {
  64           ASSERT (p[i] == (i == 90 ? UC_BREAK_MANDATORY :
  65                            i == 7
  66                            || i == 13 || i == 39
  67                            || i == 43 || i == 44
  68                            || i == 52 || i == 61 || i == 67
  69                            || i == 70 || i == 73 || i == 77 || i == 80
  70                            || i == 84 || i == 87 ? UC_BREAK_POSSIBLE :
  71                            UC_BREAK_PROHIBITED));
  72         }
  73       free (p);
  74     }
  75   }
  76 
  77   /* Test that a break is possible after a zero-width space followed by some
  78      regular spaces (rule LB8 in Unicode TR#14 revision 26).  */
  79   {
  80     static const uint8_t input[6] = "x\342\200\213 y";
  81     char *p = (char *) malloc (SIZEOF (input));
  82     size_t i;
  83 
  84     u8_possible_linebreaks (input, SIZEOF (input), "UTF-8", p);
  85     for (i = 0; i < 4; i++)
  86       {
  87         ASSERT (p[i] == (i == 5 ? UC_BREAK_POSSIBLE : UC_BREAK_PROHIBITED));
  88       }
  89     free (p);
  90   }
  91 
  92   return 0;
  93 }

/* */