1 /* Convert UTF-8 string to UTF-32 string.
2 Copyright (C) 2002, 2006-2007, 2009-2020 Free Software Foundation, Inc.
3 Written by Bruno Haible <bruno@clisp.org>, 2002.
4
5 This program is free software: you can redistribute it and/or
6 modify it under the terms of either:
7
8 * the GNU Lesser General Public License as published by the Free
9 Software Foundation; either version 3 of the License, or (at your
10 option) any later version.
11
12 or
13
14 * the GNU General Public License as published by the Free
15 Software Foundation; either version 2 of the License, or (at your
16 option) any later version.
17
18 or both in parallel, as here.
19 This program is distributed in the hope that it will be useful,
20 but WITHOUT ANY WARRANTY; without even the implied warranty of
21 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
22 Lesser General Public License for more details.
23
24 You should have received a copy of the GNU Lesser General Public License
25 along with this program. If not, see <https://www.gnu.org/licenses/>. */
26
27 #include <config.h>
28
29 /* Specification. */
30 #include "unistr.h"
31
32 #define FUNC u8_to_u32
33 #define SRC_UNIT uint8_t
34 #define DST_UNIT uint32_t
35
36 #include <errno.h>
37 #include <stdlib.h>
38 #include <string.h>
39
40 DST_UNIT *
FUNC(const SRC_UNIT * s,size_t n,DST_UNIT * resultbuf,size_t * lengthp)41 FUNC (const SRC_UNIT *s, size_t n, DST_UNIT *resultbuf, size_t *lengthp)
42 {
43 const SRC_UNIT *s_end = s + n;
44 /* Output string accumulator. */
45 DST_UNIT *result;
46 size_t allocated;
47 size_t length;
48
49 if (resultbuf != NULL)
50 {
51 result = resultbuf;
52 allocated = *lengthp;
53 }
54 else
55 {
56 result = NULL;
57 allocated = 0;
58 }
59 length = 0;
60 /* Invariants:
61 result is either == resultbuf or == NULL or malloc-allocated.
62 If length > 0, then result != NULL. */
63
64 while (s < s_end)
65 {
66 ucs4_t uc;
67 int count;
68
69 /* Fetch a Unicode character from the input string. */
70 count = u8_mbtoucr (&uc, s, s_end - s);
71 if (count < 0)
72 {
73 if (!(result == resultbuf || result == NULL))
74 free (result);
75 errno = EILSEQ;
76 return NULL;
77 }
78 s += count;
79
80 /* Store it in the output string. */
81 if (length + 1 > allocated)
82 {
83 DST_UNIT *memory;
84
85 allocated = (allocated > 0 ? 2 * allocated : 12);
86 if (length + 1 > allocated)
87 allocated = length + 1;
88 if (result == resultbuf || result == NULL)
89 memory = (DST_UNIT *) malloc (allocated * sizeof (DST_UNIT));
90 else
91 memory =
92 (DST_UNIT *) realloc (result, allocated * sizeof (DST_UNIT));
93
94 if (memory == NULL)
95 {
96 if (!(result == resultbuf || result == NULL))
97 free (result);
98 errno = ENOMEM;
99 return NULL;
100 }
101 if (result == resultbuf && length > 0)
102 memcpy ((char *) memory, (char *) result,
103 length * sizeof (DST_UNIT));
104 result = memory;
105 }
106 result[length++] = uc;
107 }
108
109 if (length == 0)
110 {
111 if (result == NULL)
112 {
113 /* Return a non-NULL value. NULL means error. */
114 result = (DST_UNIT *) malloc (1);
115 if (result == NULL)
116 {
117 errno = ENOMEM;
118 return NULL;
119 }
120 }
121 }
122 else if (result != resultbuf && length < allocated)
123 {
124 /* Shrink the allocated memory if possible. */
125 DST_UNIT *memory;
126
127 memory = (DST_UNIT *) realloc (result, length * sizeof (DST_UNIT));
128 if (memory != NULL)
129 result = memory;
130 }
131
132 *lengthp = length;
133 return result;
134 }
135