| 1 |
/* A program for converting characters to UTF-8 and vice versa */
|
| 2 |
|
| 3 |
#include <stdio.h>
|
| 4 |
#include <stdlib.h>
|
| 5 |
#include <ctype.h>
|
| 6 |
|
| 7 |
/* The valid ranges for UTF-8 characters are:
|
| 8 |
|
| 9 |
0000 0000 to 0000 007f 1 byte (ascii)
|
| 10 |
0000 0080 to 0000 07ff 2 bytes
|
| 11 |
0000 0800 to 0000 ffff 3 bytes
|
| 12 |
0001 0000 to 001f ffff 4 bytes
|
| 13 |
0020 0000 to 03ff ffff 5 bytes
|
| 14 |
0400 0000 to 7fff ffff 6 bytes
|
| 15 |
*/
|
| 16 |
|
| 17 |
|
| 18 |
static const int utf8_table1[] = {
|
| 19 |
0x0000007f, 0x000007ff, 0x0000ffff, 0x001fffff, 0x03ffffff, 0x7fffffff};
|
| 20 |
|
| 21 |
static const int utf8_table2[] = {
|
| 22 |
0, 0xc0, 0xe0, 0xf0, 0xf8, 0xfc};
|
| 23 |
|
| 24 |
static const int utf8_table3[] = {
|
| 25 |
0xff, 0x1f, 0x0f, 0x07, 0x03, 0x01};
|
| 26 |
|
| 27 |
static const unsigned char utf8_table4[] = {
|
| 28 |
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
|
| 29 |
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
|
| 30 |
2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,
|
| 31 |
3,3,3,3,3,3,3,3,4,4,4,4,5,5,6,6 };
|
| 32 |
|
| 33 |
|
| 34 |
/*************************************************
|
| 35 |
* Convert character value to UTF-8 *
|
| 36 |
*************************************************/
|
| 37 |
|
| 38 |
/* This function takes an integer value in the range 0 - 0x7fffffff
|
| 39 |
and encodes it as a UTF-8 character in 1 to 6 bytes.
|
| 40 |
|
| 41 |
Arguments:
|
| 42 |
cvalue the character value
|
| 43 |
buffer pointer to buffer for result - at least 6 bytes long
|
| 44 |
|
| 45 |
Returns: number of characters placed in the buffer
|
| 46 |
-1 if input character is negative
|
| 47 |
0 if input character is positive but too big (only when
|
| 48 |
int is longer than 32 bits)
|
| 49 |
*/
|
| 50 |
|
| 51 |
int
|
| 52 |
ord2utf8(int cvalue, unsigned char *buffer)
|
| 53 |
{
|
| 54 |
register int i, j;
|
| 55 |
for (i = 0; i < sizeof(utf8_table1)/sizeof(int); i++)
|
| 56 |
if (cvalue <= utf8_table1[i]) break;
|
| 57 |
if (i >= sizeof(utf8_table1)/sizeof(int)) return 0;
|
| 58 |
if (cvalue < 0) return -1;
|
| 59 |
buffer += i;
|
| 60 |
for (j = i; j > 0; j--)
|
| 61 |
{
|
| 62 |
*buffer-- = 0x80 | (cvalue & 0x3f);
|
| 63 |
cvalue >>= 6;
|
| 64 |
}
|
| 65 |
*buffer = utf8_table2[i] | cvalue;
|
| 66 |
return i + 1;
|
| 67 |
}
|
| 68 |
|
| 69 |
|
| 70 |
|
| 71 |
/*************************************************
|
| 72 |
* Convert UTF-8 string to value *
|
| 73 |
*************************************************/
|
| 74 |
|
| 75 |
/* This function takes one or more bytes that represents a UTF-8 character,
|
| 76 |
and returns the value of the character.
|
| 77 |
|
| 78 |
Argument:
|
| 79 |
buffer a pointer to the byte vector
|
| 80 |
vptr a pointer to an int to receive the value
|
| 81 |
|
| 82 |
Returns: > 0 => the number of bytes consumed
|
| 83 |
-6 to 0 => malformed UTF-8 character at offset = (-return)
|
| 84 |
*/
|
| 85 |
|
| 86 |
int
|
| 87 |
utf82ord(unsigned char *buffer, int *vptr)
|
| 88 |
{
|
| 89 |
int c = *buffer++;
|
| 90 |
int d = c;
|
| 91 |
int i, j, s;
|
| 92 |
|
| 93 |
for (i = -1; i < 6; i++) /* i is number of additional bytes */
|
| 94 |
{
|
| 95 |
if ((d & 0x80) == 0) break;
|
| 96 |
d <<= 1;
|
| 97 |
}
|
| 98 |
|
| 99 |
if (i == -1) { *vptr = c; return 1; } /* ascii character */
|
| 100 |
if (i == 0 || i == 6) return 0; /* invalid UTF-8 */
|
| 101 |
|
| 102 |
/* i now has a value in the range 1-5 */
|
| 103 |
|
| 104 |
s = 6*i;
|
| 105 |
d = (c & utf8_table3[i]) << s;
|
| 106 |
|
| 107 |
for (j = 0; j < i; j++)
|
| 108 |
{
|
| 109 |
c = *buffer++;
|
| 110 |
if ((c & 0xc0) != 0x80) return -(j+1);
|
| 111 |
s -= 6;
|
| 112 |
d |= (c & 0x3f) << s;
|
| 113 |
}
|
| 114 |
|
| 115 |
/* Check that encoding was the correct unique one */
|
| 116 |
|
| 117 |
for (j = 0; j < sizeof(utf8_table1)/sizeof(int); j++)
|
| 118 |
if (d <= utf8_table1[j]) break;
|
| 119 |
if (j != i) return -(i+1);
|
| 120 |
|
| 121 |
/* Valid value */
|
| 122 |
|
| 123 |
*vptr = d;
|
| 124 |
return i+1;
|
| 125 |
}
|
| 126 |
|
| 127 |
|
| 128 |
|
| 129 |
|
| 130 |
/*************************************************
|
| 131 |
* Main Program *
|
| 132 |
*************************************************/
|
| 133 |
|
| 134 |
|
| 135 |
int
|
| 136 |
main(int argc, char **argv)
|
| 137 |
{
|
| 138 |
int i;
|
| 139 |
unsigned char buffer[8];
|
| 140 |
for (i = 1; i < argc; i++)
|
| 141 |
{
|
| 142 |
unsigned char *x = argv[i];
|
| 143 |
if (strncmp(x, "0x", 2) == 0)
|
| 144 |
{
|
| 145 |
int j;
|
| 146 |
int d = strtol(x+2, NULL, 16);
|
| 147 |
int rc = ord2utf8(d, buffer);
|
| 148 |
printf("0x%08x => ", d);
|
| 149 |
if (rc <= 0) printf("*** Error %d ***", rc);
|
| 150 |
else for (j = 0; j < rc; j++) printf("%02x ", buffer[j]);
|
| 151 |
printf("\n");
|
| 152 |
}
|
| 153 |
else
|
| 154 |
{
|
| 155 |
int d, rc;
|
| 156 |
int j = 0;
|
| 157 |
int y = 0;
|
| 158 |
int z = 0;
|
| 159 |
for (;;)
|
| 160 |
{
|
| 161 |
while (*x == ' ') x++;
|
| 162 |
if (*x == 0 && !z) break;
|
| 163 |
if (!isxdigit(*x))
|
| 164 |
{
|
| 165 |
printf("Malformed hex string: %s\n", argv[i]);
|
| 166 |
j = -1;
|
| 167 |
break;
|
| 168 |
}
|
| 169 |
y = y * 16 + tolower(*x) - ((isdigit(*x))? '0' : 'W');
|
| 170 |
x++;
|
| 171 |
if (z)
|
| 172 |
{
|
| 173 |
buffer[j++] = y;
|
| 174 |
y = 0;
|
| 175 |
}
|
| 176 |
z ^= 1;
|
| 177 |
}
|
| 178 |
if (j < 0) continue;
|
| 179 |
buffer[j] = 0;
|
| 180 |
rc = utf82ord(buffer, &d);
|
| 181 |
if (rc > 0) printf("0x%08x <= %s\n", d, argv[i]);
|
| 182 |
else printf("Error %d <= %s\n", rc, argv[i]);
|
| 183 |
}
|
| 184 |
}
|
| 185 |
return 0;
|
| 186 |
}
|
| 187 |
|
| 188 |
/* End */
|
Parent Directory
| 
Revision Log