aboutsummaryrefslogtreecommitdiff
blob: 993df4c3cb6d4895a76c23cbdf9df501fec1b6a4 (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
/* Internal header for proving correct grouping in strings of numbers.
   Copyright (C) 1995-2020 Free Software Foundation, Inc.
   This file is part of the GNU C Library.
   Contributed by Ulrich Drepper <drepper@gnu.ai.mit.edu>, 1995.

   The GNU C Library 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 2.1 of the License, or (at your option) any later version.

   The GNU C Library 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 the GNU C Library; if not, see
   <https://www.gnu.org/licenses/>.  */

#include <limits.h>
#include <stddef.h>
#include <string.h>

#ifndef MAX
#define MAX(a,b)	({ typeof(a) _a = (a); typeof(b) _b = (b); \
			   _a > _b ? _a : _b; })
#endif

#ifdef USE_WIDE_CHAR
# include <wctype.h>
# define L_(Ch) L##Ch
# define UCHAR_TYPE wint_t
# define STRING_TYPE wchar_t
#else
# define L_(Ch) Ch
# define UCHAR_TYPE unsigned char
# define STRING_TYPE char
#endif

#include "grouping.h"

/* Find the maximum prefix of the string between BEGIN and END which
   satisfies the grouping rules.  It is assumed that at least one digit
   follows BEGIN directly.  */

const STRING_TYPE *
#ifdef USE_WIDE_CHAR
__correctly_grouped_prefixwc (const STRING_TYPE *begin, const STRING_TYPE *end,
			      wchar_t thousands,
#else
__correctly_grouped_prefixmb (const STRING_TYPE *begin, const STRING_TYPE *end,
			      const char *thousands,
#endif
			      const char *grouping)
{
#ifndef USE_WIDE_CHAR
  size_t thousands_len;
  int cnt;
#endif

  if (grouping == NULL)
    return end;

#ifndef USE_WIDE_CHAR
  thousands_len = strlen (thousands);
#endif

  while (end > begin)
    {
      const STRING_TYPE *cp = end - 1;
      const char *gp = grouping;

      /* Check first group.  */
      while (cp >= begin)
	{
#ifdef USE_WIDE_CHAR
	  if (*cp == thousands)
	    break;
#else
	  if (cp[thousands_len - 1] == *thousands)
	    {
	      for (cnt = 1; thousands[cnt] != '\0'; ++cnt)
		if (thousands[cnt] != cp[thousands_len - 1 - cnt])
		  break;
	      if (thousands[cnt] == '\0')
		break;
	    }
#endif
	  --cp;
	}

      /* We allow the representation to contain no grouping at all even if
	 the locale specifies we can have grouping.  */
      if (cp < begin)
	return end;

      if (end - cp == (int) *gp + 1)
	{
	  /* This group matches the specification.  */

	  const STRING_TYPE *new_end;

	  if (cp < begin)
	    /* There is just one complete group.  We are done.  */
	    return end;

	  /* CP points to a thousands separator character.  The preceding
	     remainder of the string from BEGIN to NEW_END is the part we
	     will consider if there is a grouping error in this trailing
	     portion from CP to END.  */
	  new_end = cp - 1;

	  /* Loop while the grouping is correct.  */
	  while (1)
	    {
	      /* Get the next grouping rule.  */
	      ++gp;
	      if (*gp == 0)
		/* If end is reached use last rule.  */
	        --gp;

	      /* Skip the thousands separator.  */
	      --cp;

	      if (*gp == CHAR_MAX
#if CHAR_MIN < 0
		  || *gp < 0
#endif
		  )
	        {
	          /* No more thousands separators are allowed to follow.  */
	          while (cp >= begin)
		    {
#ifdef USE_WIDE_CHAR
		      if (*cp == thousands)
			break;
#else
		      for (cnt = 0; thousands[cnt] != '\0'; ++cnt)
			if (thousands[cnt] != cp[thousands_len - cnt - 1])
			  break;
		      if (thousands[cnt] == '\0')
			break;
#endif
		      --cp;
		    }

	          if (cp < begin)
		    /* OK, only digits followed.  */
		    return end;
	        }
	      else
	        {
		  /* Check the next group.  */
	          const STRING_TYPE *group_end = cp;

		  while (cp >= begin)
		    {
#ifdef USE_WIDE_CHAR
		      if (*cp == thousands)
			break;
#else
		      for (cnt = 0; thousands[cnt] != '\0'; ++cnt)
			if (thousands[cnt] != cp[thousands_len - cnt - 1])
			  break;
		      if (thousands[cnt] == '\0')
			break;
#endif
		      --cp;
		    }

		  if (cp < begin && group_end - cp <= (int) *gp)
		    /* Final group is correct.  */
		    return end;

		  if (cp < begin || group_end - cp != (int) *gp)
		    /* Incorrect group.  Punt.  */
		    break;
		}
	    }

	  /* The trailing portion of the string starting at NEW_END
	     contains a grouping error.  So we will look for a correctly
	     grouped number in the preceding portion instead.  */
	  end = new_end;
	}
      else
	{
	  /* Even the first group was wrong; determine maximum shift.  */
	  if (end - cp > (int) *gp + 1)
	    end = cp + (int) *gp + 1;
	  else if (cp < begin)
	    /* This number does not fill the first group, but is correct.  */
	    return end;
	  else
	    /* CP points to a thousands separator character.  */
	    end = cp;
	}
    }

  return MAX (begin, end);
}