tests/uniwbrk/test-uc-wordbreaks.c

   1 /* Word break function test, using test data from UCD.
   2    Copyright (C) 2010-2025 Free Software Foundation, Inc.
   3
   4    This program is free software: you can redistribute it and/or modify it
   5    under the terms of the GNU Lesser General Public License as published
   6    by 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 GNU
  12    Lesser General Public License for more details.
  13
  14    You should have received a copy of the GNU Lesser General Public License
  15    along with this program.  If not, see <https://www.gnu.org/licenses/>.  */
  16
  17 /* Written by Daiki Ueno <ueno@gnu.org>, 2014.
  18
  19    Largely based on unigbrk/test-uc-is-grapheme-break.c,
  20    written by Ben Pfaff <blp@cs.stanford.edu>, 2010.  */
  21
  22 #include <config.h>
  23
  24 /* Specification. */
  25 #include <uniwbrk.h>
  26
  27 #include <stdio.h>
  28 #include <stdlib.h>
  29 #include <string.h>
  30
  31 const char *
  32 wordbreakproperty_to_string (int wbp)
  33 {
  34   switch (wbp)
  35     {
  36 #define CASE(VALUE) case WBP_##VALUE: return #VALUE;
  37       CASE(OTHER)
  38       CASE(CR)
  39       CASE(LF)
  40       CASE(NEWLINE)
  41       CASE(EXTEND)
  42       CASE(FORMAT)
  43       CASE(KATAKANA)
  44       CASE(ALETTER)
  45       CASE(MIDNUMLET)
  46       CASE(MIDLETTER)
  47       CASE(MIDNUM)
  48       CASE(NUMERIC)
  49       CASE(EXTENDNUMLET)
  50       CASE(RI)
  51       CASE(DQ)
  52       CASE(SQ)
  53       CASE(HL)
  54       CASE(ZWJ)
  55       CASE(EB)
  56       CASE(EM)
  57       CASE(GAZ)
  58       CASE(EBG)
  59       CASE(WSS)
  60     }
  61   abort ();
  62 }
  63
  64 int
  65 main (int argc, char *argv[])
  66 {
  67   const char *filename;
  68   FILE *stream;
  69   int exit_code;
  70   int lineno;
  71   char line[4096];
  72
  73   if (argc != 2)
  74     {
  75       fprintf (stderr, "usage: %s FILENAME\n"
  76                "where FILENAME is the location of the WordBreakTest.txt\n"
  77                "test file.\n", argv[0]);
  78       exit (1);
  79     }
  80
  81   filename = argv[1];
  82   stream = fopen (filename, "r");
  83   if (stream == NULL)
  84     {
  85       fprintf (stderr, "error during fopen of '%s'\n", filename);
  86       exit (1);
  87     }
  88
  89   exit_code = 0;
  90   lineno = 0;
  91   while (fgets (line, sizeof (line), stream))
  92     {
  93       lineno++;
  94
  95       /* Cut off the trailing comment, if any.  */
  96       char *comment = strchr (line, '#');
  97       if (comment != NULL)
  98         *comment = '\0';
  99       /* Is the remaining line blank?  */
 100       if (line[strspn (line, " \t\r\n")] == '\0')
 101         continue;
 102
 103       const char *p;
 104       uint32_t input[100];
 105       char breaks[100];
 106       char breaks_expected[101];
 107       int i;
 108
 109       i = 0;
 110       p = line;
 111       do
 112         {
 113           p += strspn (p, " \t\r\n");
 114           if (!strncmp (p, "\303\267" /* ÷ */, 2))
 115             {
 116               breaks_expected[i] = 1;
 117               p += 2;
 118             }
 119           else if (!strncmp (p, "\303\227" /* × */, 2))
 120             {
 121               breaks_expected[i] = 0;
 122               p += 2;
 123             }
 124           else
 125             {
 126               fprintf (stderr, "%s:%d.%d: syntax error expecting '÷' or '×'\n",
 127                        filename, lineno, (int) (p - line + 1));
 128               exit (1);
 129             }
 130
 131           p += strspn (p, " \t\r\n");
 132           if (*p != '\0')
 133             {
 134               unsigned int next_int;
 135               int n;
 136
 137               if (sscanf (p, "%x%n", &next_int, &n) != 1)
 138                 {
 139                   fprintf (stderr, "%s:%d.%d: syntax error at '%s' "
 140                            "expecting hexadecimal Unicode code point number\n",
 141                            filename, lineno, (int) (p - line + 1), p);
 142                   exit (1);
 143                 }
 144               p += n;
 145
 146               input[i] = next_int;
 147             }
 148
 149           p += strspn (p, " \t\r\n");
 150           i++;
 151         }
 152       while (*p != '\0');
 153
 154       u32_wordbreaks (input, i - 1, breaks);
 155
 156       /* u32_wordbreaks always set BREAKS[0] to 0.  */
 157       breaks[0] = breaks_expected[0] = 1;
 158       if (memcmp (breaks, breaks_expected, i - 1) != 0)
 159         {
 160           int j;
 161
 162           fprintf (stderr, "%s:%d: expected: ", filename, lineno);
 163           for (j = 0; j < i - 1; j++)
 164             {
 165               int input_wbp = uc_wordbreak_property (input[j]);
 166               fprintf (stderr, "%s U+%04X (%s) ",
 167                        breaks_expected[j] == 1 ? "\303\267" : "\303\227",
 168                        input[j], wordbreakproperty_to_string (input_wbp));
 169             }
 170           fprintf (stderr, "\n");
 171           fprintf (stderr, "%s:%d: actual:   ", filename, lineno);
 172           for (j = 0; j < i - 1; j++)
 173             {
 174               int input_wbp = uc_wordbreak_property (input[j]);
 175               fprintf (stderr, "%s U+%04X (%s) ",
 176                        breaks[j] == 1 ? "\303\267" : "\303\227",
 177                        input[j], wordbreakproperty_to_string (input_wbp));
 178             }
 179           fprintf (stderr, "\n");
 180           exit_code = 1;
 181         }
 182     }
 183
 184   return exit_code;
 185 }