kmx git

/* Word breaks in UTF-8 strings.
   Copyright (C) 2009-2025 Free Software Foundation, Inc.
   Written by Bruno Haible <bruno@clisp.org>, 2009.

   This file is free software.
   It is dual-licensed under "the GNU LGPLv3+ or the GNU GPLv2+".
   You can redistribute it and/or modify it under either
     - the terms of the GNU Lesser General Public License as published
       by the Free Software Foundation, either version 3, or (at your
       option) any later version, or
     - the terms of the GNU General Public License as published by the
       Free Software Foundation; either version 2, or (at your option)
       any later version, or
     - the same dual license "the GNU LGPLv3+ or the GNU GPLv2+".

   This file is distributed in the hope that it will be useful,
   but WITHOUT ANY WARRANTY; without even the implied warranty of
   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
   Lesser General Public License and the GNU General Public License
   for more details.

   You should have received a copy of the GNU Lesser General Public
   License and of the GNU General Public License along with this
   program.  If not, see <https://www.gnu.org/licenses/>.  */

#include <config.h>

/* Specification.  */
#include "uniwbrk.h"

#include <string.h>

#include "unictype.h"
#include "unistr.h"
#include "uniwbrk/wbrktable.h"

#define FUNC u8_wordbreaks
#define UNIT uint8_t
#define U_MBTOUC_UNSAFE u8_mbtouc_unsafe
#include "u-wordbreaks.h"


#ifdef TEST

#include <stdio.h>
#include <stdlib.h>

/* Read the contents of an input stream, and return it, terminated with a NUL
   byte. */
char *
read_file (FILE *stream)
{
#define BUFSIZE 4096
  char *buf = NULL;
  int alloc = 0;
  int size = 0;
  int count;

  while (! feof (stream))
    {
      if (size + BUFSIZE > alloc)
        {
          alloc = alloc + alloc / 2;
          if (alloc < size + BUFSIZE)
            alloc = size + BUFSIZE;
          buf = realloc (buf, alloc);
          if (buf == NULL)
            {
              fprintf (stderr, "out of memory\n");
              exit (1);
            }
        }
      count = fread (buf + size, 1, BUFSIZE, stream);
      if (count == 0)
        {
          if (ferror (stream))
            {
              perror ("fread");
              exit (1);
            }
        }
      else
        size += count;
    }
  buf = realloc (buf, size + 1);
  if (buf == NULL)
    {
      fprintf (stderr, "out of memory\n");
      exit (1);
    }
  buf[size] = '\0';
  return buf;
#undef BUFSIZE
}

int
main (int argc, char * argv[])
{
  if (argc == 1)
    {
      /* Display all the word breaks in the input string.  */
      char *input = read_file (stdin);
      int length = strlen (input);
      char *breaks = malloc (length);
      int i;

      u8_wordbreaks ((uint8_t *) input, length, breaks);

      for (i = 0; i < length; i++)
        {
          switch (breaks[i])
            {
            case 1:
              /* U+2027 in UTF-8 encoding */
              putc (0xe2, stdout); putc (0x80, stdout); putc (0xa7, stdout);
              break;
            case 0:
              break;
            default:
              abort ();
            }
          putc (input[i], stdout);
        }

      free (breaks);

      return 0;
    }
  else
    return 1;
}

#endif /* TEST */
kc3-lang/gnulib/lib/uniwbrk/u8-wordbreaks.c

Commit

lib/uniwbrk/u8-wordbreaks.c
