summaryrefslogtreecommitdiff
path: root/lib/unilbrk/ulc-possible-linebreaks.c
blob: cb952419bbd4e6d8877f6e479eb246e5bff44ca8 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
/* Line breaking of strings.
   Copyright (C) 2001-2003, 2006-2009 Free Software Foundation, Inc.
   Written by Bruno Haible <bruno@clisp.org>, 2001.

   This program is free software: you can redistribute it and/or modify it
   under the terms of the GNU Lesser General Public License as published
   by the Free Software Foundation; either version 3 of the License, or
   (at your option) any later version.

   This program 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 for more details.

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

#include <config.h>

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

#include <stdlib.h>
#include <string.h>

#include "c-ctype.h"
#include "uniconv.h"
#include "unilbrk/ulc-common.h"

/* Line breaking of a string in an arbitrary encoding.

   We convert the input string to Unicode.

   The standardized Unicode encodings are UTF-8, UCS-2, UCS-4, UTF-16,
   UTF-16BE, UTF-16LE, UTF-7.  UCS-2 supports only characters up to
   \U0000FFFF.  UTF-16 and variants support only characters up to
   \U0010FFFF.  UTF-7 is way too complex and not supported by glibc-2.1.
   UCS-4 specification leaves doubts about endianness and byte order mark.
   glibc currently interprets it as big endian without byte order mark,
   but this is not backed by an RFC.  So we use UTF-8. It supports
   characters up to \U7FFFFFFF and is unambiguously defined.  */

void
ulc_possible_linebreaks (const char *s, size_t n, const char *encoding,
			 char *p)
{
  if (n > 0)
    {
      if (is_utf8_encoding (encoding))
	u8_possible_linebreaks ((const uint8_t *) s, n, encoding, p);
      else
	{
	  /* Convert the string to UTF-8 and build a translation table
	     from offsets into s to offsets into the translated string.  */
	  size_t *offsets = (size_t *) malloc (n * sizeof (size_t));

	  if (offsets != NULL)
	    {
	      uint8_t *t;
	      size_t m;

	      t = u8_conv_from_encoding (encoding, iconveh_question_mark,
					 s, n, offsets, NULL, &m);
	      if (t != NULL)
		{
		  char *q = (char *) (m > 0 ? malloc (m) : NULL);

		  if (m == 0 || q != NULL)
		    {
		      size_t i;

		      /* Determine the possible line breaks of the UTF-8
			 string.  */
		      u8_possible_linebreaks (t, m, encoding, q);

		      /* Translate the result back to the original string.  */
		      memset (p, UC_BREAK_PROHIBITED, n);
		      for (i = 0; i < n; i++)
			if (offsets[i] != (size_t)(-1))
			  p[i] = q[offsets[i]];

		      free (q);
		      free (t);
		      free (offsets);
		      return;
		    }
		  free (t);
		}
	      free (offsets);
	    }

	  /* Impossible to convert.  */
#if C_CTYPE_ASCII
	  if (is_all_ascii (s, n))
	    {
	      /* ASCII is a subset of UTF-8.  */
	      u8_possible_linebreaks ((const uint8_t *) s, n, encoding, p);
	      return;
	    }
#endif
	  /* We have a non-ASCII string and cannot convert it.
	     Don't produce line breaks except those already present in the
	     input string.  All we assume here is that the encoding is
	     minimally ASCII compatible.  */
	  {
	    const char *s_end = s + n;
	    while (s < s_end)
	      {
		*p = (*s == '\n' ? UC_BREAK_MANDATORY : UC_BREAK_PROHIBITED);
		s++;
		p++;
	      }
	  }
	}
    }
}


#ifdef TEST

#include <stdio.h>
#include <locale.h>
#include <string.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[])
{
  setlocale (LC_CTYPE, "");
  if (argc == 1)
    {
      /* Display all the break opportunities in the input string.  */
      char *input = read_file (stdin);
      int length = strlen (input);
      char *breaks = malloc (length);
      int i;

      ulc_possible_linebreaks (input, length, locale_charset (), breaks);

      for (i = 0; i < length; i++)
	{
	  switch (breaks[i])
	    {
	    case UC_BREAK_POSSIBLE:
	      putc ('|', stdout);
	      break;
	    case UC_BREAK_MANDATORY:
	      break;
	    case UC_BREAK_PROHIBITED:
	      break;
	    default:
	      abort ();
	    }
	  putc (input[i], stdout);
	}

      free (breaks);

      return 0;
    }
  else
    return 1;
}

#endif /* TEST */