| 1 |
/* |
| 2 |
* Copyright (c) 2022 joshua stein <jcs@jcs.org> |
| 3 |
* |
| 4 |
* Permission to use, copy, modify, and distribute this software for any |
| 5 |
* purpose with or without fee is hereby granted, provided that the above |
| 6 |
* copyright notice and this permission notice appear in all copies. |
| 7 |
* |
| 8 |
* THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES |
| 9 |
* WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF |
| 10 |
* MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR |
| 11 |
* ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES |
| 12 |
* WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN |
| 13 |
* ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF |
| 14 |
* OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. |
| 15 |
*/ |
| 16 |
|
| 17 |
#include "utf8.h" |
| 18 |
|
| 19 |
const struct utf8_macroman_pair { |
| 20 |
unsigned char macroman; |
| 21 |
utf8_char utf8; |
| 22 |
} utf8_macroman_pairs[] = { |
| 23 |
{ 'x', { 0xc3, 0x97 } }, |
| 24 |
{ 'è', { 0xc3, 0xa8 } }, |
| 25 |
{ 'é', { 0xc3, 0xa9 } }, |
| 26 |
{ 'ö', { 0xc3, 0xb6 } }, |
| 27 |
{ 'ü', { 0xc3, 0xbc } }, |
| 28 |
{ '"', { 0xe2, 0x80, 0x9c } }, |
| 29 |
{ '–', { 0xe2, 0x80, 0x93 } }, |
| 30 |
{ '—', { 0xe2, 0x80, 0x94 } }, |
| 31 |
{ '\'', { 0xe2, 0x80, 0x98 } }, |
| 32 |
{ '\'', { 0xe2, 0x80, 0x99 } }, |
| 33 |
{ 0, 0 } |
| 34 |
}; |
| 35 |
|
| 36 |
unsigned char |
| 37 |
utf8_to_macroman(utf8_char *utf8) |
| 38 |
{ |
| 39 |
short n; |
| 40 |
short bytes = 0; |
| 41 |
struct utf8_macroman_pair *p = NULL; |
| 42 |
|
| 43 |
if ((*utf8)[0] >= 0xc2 && (*utf8)[0] <= 0xdf && (*utf8)[1] != 0) |
| 44 |
bytes = 2; |
| 45 |
else if ((*utf8)[0] >= 0xe0 && (*utf8)[0] <= 0xef && (*utf8)[2] != 0) |
| 46 |
bytes = 3; |
| 47 |
else if ((*utf8)[0] >= 0xf0 && (*utf8)[0] <= 0xf4 && (*utf8)[3] != 0) |
| 48 |
bytes = 4; |
| 49 |
else if ((*utf8)[0] != 0 && (*utf8)[1] != 0 && (*utf8)[2] != 0 && |
| 50 |
(*utf8)[3] != 0) |
| 51 |
return '?'; |
| 52 |
|
| 53 |
if (bytes == 0) |
| 54 |
return 0; |
| 55 |
|
| 56 |
for (n = 0; ; n++) { |
| 57 |
p = (struct utf8_macroman_pair *)&utf8_macroman_pairs[n]; |
| 58 |
|
| 59 |
if (p->macroman == 0) |
| 60 |
break; |
| 61 |
|
| 62 |
if (p->utf8[0] != (*utf8)[0]) |
| 63 |
continue; |
| 64 |
|
| 65 |
if (p->utf8[1] != (*utf8)[1]) |
| 66 |
continue; |
| 67 |
|
| 68 |
if (p->utf8[2] == 0 && (*utf8)[2] == 0) |
| 69 |
return p->macroman; |
| 70 |
|
| 71 |
if (p->utf8[2] != (*utf8)[2]) |
| 72 |
continue; |
| 73 |
|
| 74 |
if (p->utf8[3] == 0 && (*utf8)[3] == 0) |
| 75 |
return p->macroman; |
| 76 |
|
| 77 |
if (p->utf8[3] != (*utf8)[3]) |
| 78 |
continue; |
| 79 |
|
| 80 |
if (p->utf8[4] == (*utf8)[4]) |
| 81 |
return p->macroman; |
| 82 |
} |
| 83 |
|
| 84 |
return '?'; |
| 85 |
} |
| 86 |
|
| 87 |
const utf8_char * |
| 88 |
macroman_to_utf8(unsigned char c) |
| 89 |
{ |
| 90 |
short n; |
| 91 |
struct utf8_macroman_pair *p = NULL; |
| 92 |
|
| 93 |
for (n = 0; ; n++) { |
| 94 |
p = (struct utf8_macroman_pair *)&utf8_macroman_pairs[n]; |
| 95 |
|
| 96 |
if (p->macroman == 0) |
| 97 |
break; |
| 98 |
|
| 99 |
if (p->macroman == c) |
| 100 |
return (const utf8_char *)&p->utf8; |
| 101 |
} |
| 102 |
|
| 103 |
return NULL; |
| 104 |
} |
| 105 |
|
| 106 |
unsigned char * |
| 107 |
macroman_to_utf8_string(unsigned char *str, size_t len) |
| 108 |
{ |
| 109 |
const utf8_char *utf8; |
| 110 |
unsigned char *tmp, *ret, c; |
| 111 |
size_t ulen, n; |
| 112 |
const utf8_char *u; |
| 113 |
|
| 114 |
tmp = xmalloc((len * 4) + 1); |
| 115 |
if (tmp == NULL) { |
| 116 |
warn("utf8: Failed allocating (%ld * 4) + 1", len); |
| 117 |
return NULL; |
| 118 |
} |
| 119 |
|
| 120 |
ulen = 0; |
| 121 |
for (n = 0; n < len; n++) { |
| 122 |
c = str[n]; |
| 123 |
u = macroman_to_utf8(c); |
| 124 |
|
| 125 |
if (u == NULL) { |
| 126 |
tmp[ulen++] = c; |
| 127 |
continue; |
| 128 |
} |
| 129 |
|
| 130 |
tmp[ulen++] = (*u)[0]; |
| 131 |
|
| 132 |
if ((*u)[1] == 0) |
| 133 |
continue; |
| 134 |
tmp[ulen++] = (*u)[1]; |
| 135 |
|
| 136 |
if ((*u)[2] == 0) |
| 137 |
continue; |
| 138 |
tmp[ulen++] = (*u)[2]; |
| 139 |
|
| 140 |
if ((*u)[3] == 0) |
| 141 |
continue; |
| 142 |
tmp[ulen++] = (*u)[3]; |
| 143 |
|
| 144 |
if ((*u)[4] == 0) |
| 145 |
continue; |
| 146 |
tmp[ulen++] = (*u)[4]; |
| 147 |
} |
| 148 |
tmp[ulen] = '\0'; |
| 149 |
|
| 150 |
ret = (unsigned char *)xstrdup((char *)tmp); |
| 151 |
xfree(&tmp); |
| 152 |
|
| 153 |
if (ret == NULL) |
| 154 |
warn("utf8: Out of memory!"); |
| 155 |
|
| 156 |
return ret; |
| 157 |
} |