![[BACK]](/cvsweb/icons/back.gif){kind=icon}
Return to charset.c CVS log ![[TXT]](/cvsweb/icons/text.gif){kind=icon}
![[DIR]](/cvsweb/icons/dir.gif){kind=icon}
Up to [PGP] / pgp / src|
Return to charset.c CVS log | Up to [PGP] / pgp / src |
1.1.1.2 root 1: /*
2: * charset.c
3: *
4: * Conversion tables and routines to support different character sets.
5: * The PGP internal format is latin-1.
6: */
7:
8: #include <stdio.h>
1.1.1.3 ! root 9: #include <string.h>
1.1.1.2 root 10: #include "usuals.h"
11: #include "language.h"
1.1.1.3 ! root 12: #include "charset.h"
! 13: #include "system.h"
1.1.1.2 root 14:
15: #ifndef NULL
16: #define NULL 0
17: #endif
18:
19: #define UNK '?'
20:
21: static unsigned char
22: intern2ascii[] = { /* ISO 8859-1 Latin Alphabet 1 to US ASCII */
23: UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK,
24: UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK,
25: 32, 33, 99, 35, 36, 89, 124, 80, 34, 67, 97, 34, 126, 45, 82, 95,
26: 111, UNK, 50, 51, 39, 117, 45, 45, 44, 49, 111, 34, UNK, UNK, UNK, 63,
27: 65, 65, 65, 65, 65, 65, 65, 67, 69, 69, 69, 69, 73, 73, 73, 73,
28: 68, 78, 79, 79, 79, 79, 79, 120, 79, 85, 85, 85, 85, 89, 84, 115,
29: 97, 97, 97, 97, 97, 97, 97, 99, 101, 101, 101, 101, 105, 105, 105, 105,
30: 100, 110, 111, 111, 111, 111, 111, 47, 111, 117, 117, 117, 117, 121, 116, 121
31: };
32:
33: static unsigned char
34: intern2cp850[] = { /* ISO 8859-1 Latin Alphabet 1 (Latin-1) to IBM Code Page 850 */
35: 186, 205, 201, 187, 200, 188, 204, 185, 203, 202, 206, 223, 220, 219, 254, 242,
36: 179, 196, 218, 191, 192, 217, 195, 180, 194, 193, 197, 176, 177, 178, 213, 159,
37: 255, 173, 189, 156, 207, 190, 221, 245, 249, 184, 166, 174, 170, 240, 169, 238,
38: 248, 241, 253, 252, 239, 230, 244, 250, 247, 251, 167, 175, 172, 171, 243, 168,
39: 183, 181, 182, 199, 142, 143, 146, 128, 212, 144, 210, 211, 222, 214, 215, 216,
40: 209, 165, 227, 224, 226, 229, 153, 158, 157, 235, 233, 234, 154, 237, 232, 225,
41: 133, 160, 131, 198, 132, 134, 145, 135, 138, 130, 136, 137, 141, 161, 140, 139,
42: 208, 164, 149, 162, 147, 228, 148, 246, 155, 151, 163, 150, 129, 236, 231, 152
43: };
44:
45: static unsigned char
46: cp8502intern[] = { /* IBM Code Page 850 to Latin-1 */
47: 199, 252, 233, 226, 228, 224, 229, 231, 234, 235, 232, 239, 238, 236, 196, 197,
48: 201, 230, 198, 244, 246, 242, 251, 249, 255, 214, 220, 248, 163, 216, 215, 159,
49: 225, 237, 243, 250, 241, 209, 170, 186, 191, 174, 172, 189, 188, 161, 171, 187,
50: 155, 156, 157, 144, 151, 193, 194, 192, 169, 135, 128, 131, 133, 162, 165, 147,
51: 148, 153, 152, 150, 145, 154, 227, 195, 132, 130, 137, 136, 134, 129, 138, 164,
52: 240, 208, 202, 203, 200, 158, 205, 206, 207, 149, 146, 141, 140, 166, 204, 139,
53: 211, 223, 212, 210, 245, 213, 181, 254, 222, 218, 219, 217, 253, 221, 175, 180,
54: 173, 177, 143, 190, 182, 167, 247, 184, 176, 168, 183, 185, 179, 178, 142, 160
55: };
56:
57: /* Russian language specific conversation section */
58: /* Two point-to-point charset decode tables */
59:
60: /* Decode single char from KOI8 to ALT-CODES, if present */
61: static unsigned char intern2alt[] = {
62: 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7,
63: 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf,
64: 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7,
65: 0xc8, 0xc9, 0xca, 0xff, 0xcc, 0xcd, 0xce, 0xcf,
66: 0xd0, 0xd1, 0xd2, 0xf1, 0xd4, 0xd5, 0xd6, 0xd7,
67: 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf,
68: 0xd3, 0xf3, 0xf2, 0xf0, 0xf4, 0xf5, 0xf6, 0xf7,
69: 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xcb,
70: 0xee, 0xa0, 0xa1, 0xe6, 0xa4, 0xa5, 0xe4, 0xa3,
71: 0xe5, 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae,
72: 0xaf, 0xef, 0xe0, 0xe1, 0xe2, 0xe3, 0xa6, 0xa2,
73: 0xec, 0xeb, 0xa7, 0xe8, 0xed, 0xe9, 0xe7, 0xea,
74: 0x9e, 0x80, 0x81, 0x96, 0x84, 0x85, 0x94, 0x83,
75: 0x95, 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e,
76: 0x8f, 0x9f, 0x90, 0x91, 0x92, 0x93, 0x86, 0x82,
77: 0x9c, 0x9b, 0x87, 0x98, 0x9d, 0x99, 0x97, 0x9a
78: };
79:
80: /* Decode single char from ALT-CODES, if present, to KOI8 */
81: static unsigned char alt2intern[] = {
82: 0xe1, 0xe2, 0xf7, 0xe7, 0xe4, 0xe5, 0xf6, 0xfa,
83: 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, 0xf0,
84: 0xf2, 0xf3, 0xf4, 0xf5, 0xe6, 0xe8, 0xe3, 0xfe,
85: 0xfb, 0xfd, 0xff, 0xf9, 0xf8, 0xfc, 0xe0, 0xf1,
86: 0xc1, 0xc2, 0xd7, 0xc7, 0xc4, 0xc5, 0xd6, 0xda,
87: 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, 0xd0,
88: 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
89: 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
90: 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
91: 0x98, 0x99, 0x9a, 0xbf, 0x9c, 0x9d, 0x9e, 0x9f,
92: 0xa0, 0xa1, 0xa2, 0xb0, 0xa4, 0xa5, 0xa6, 0xa7,
93: 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf,
94: 0xd2, 0xd3, 0xd4, 0xd5, 0xc6, 0xc8, 0xc3, 0xde,
95: 0xdb, 0xdd, 0xdf, 0xd9, 0xd8, 0xdc, 0xc0, 0xd1,
96: 0xb3, 0xa3, 0xb2, 0xb1, 0xb4, 0xb5, 0xb6, 0xb7,
97: 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0x9b
98: };
99:
100: /* End of Russian section */
101:
102: /*
103: * Most Unixes has KOI8, and DOS has ALT_CODE
104: * If your Unix is non-standard, set CHARSET to "alt_codes"
105: * in config.txt
106: */
107:
108: #ifndef DEFAULT_CSET
109: #define DEFAULT_CSET "noconv"
110: #endif
111: #ifndef DEFAULT_RU_CSET
112: #define DEFAULT_RU_CSET "noconv"
113: #endif
114:
115:
116: int CONVERSION = NO_CONV; /* None text file conversion at start time */
117:
118: unsigned char *ext_c_ptr;
1.1.1.3 ! root 119: static unsigned char *int_c_ptr;
1.1.1.2 root 120:
121: #ifdef MSDOS
122: char charset[64] = "cp850";
123: #else
124: char charset[64] = "";
125: #endif
126:
127: void
1.1.1.3 ! root 128: init_charset(void)
1.1.1.2 root 129: {
130: ext_c_ptr = NULL; /* NULL means latin1 or KOI8 (internal format) */
131: int_c_ptr = NULL;
132:
133: if (charset[0] == '\0')
134: { /* use default character set for this system */
135: if (strcmp(language, "ru") == 0)
136: strcpy(charset, DEFAULT_RU_CSET);
137: else
138: strcpy(charset, DEFAULT_CSET);
139: }
140: else
141: strlwr(charset);
142:
143: /* latin-1 and KOI8 are in internal format: no conversion needed */
144: if (!strcmp(charset, "latin1") || !strcmp(charset, "koi8") ||
145: !strcmp(charset, "noconv"))
146: return;
147:
148: if (!strcmp(charset, "alt_codes"))
149: { ext_c_ptr = intern2alt;
150: int_c_ptr = alt2intern;
151: } else if (!strcmp(charset, "cp850"))
152: { ext_c_ptr = intern2cp850;
153: int_c_ptr = cp8502intern;
154: } else if (!strcmp(charset, "ascii"))
155: { ext_c_ptr = intern2ascii;
156: } else
157: {
158: fprintf(stderr, PSTR("Unsupported character set: '%s'\n"), charset);
159: }
160: }
161:
162: char
163: EXT_C(char c)
164: {
165: if (c > '\0' || !ext_c_ptr)
166: return c;
167: return ext_c_ptr[c & 0x7f];
168: }
169:
170: char
171: INT_C(char c)
172: {
173: if (c > '\0' || !int_c_ptr)
174: return c;
175: return int_c_ptr[c & 0x7f];
176: }
177:
178: /*
179: * to_upper() and to_lower(), replacement for toupper() and tolower(),
180: * calling to_upper() on uppercase or to_lower on lowercase characters
181: * is handled correctly.
182: *
183: * XXX: should handle local characterset when 8-bit userID's are allowed
184: */
185: int
186: to_upper(int c)
187: {
188: return (c >= 'a' && c <= 'z' ? c - ('a' - 'A') : c);
189: }
190:
191: int
192: to_lower(int c)
193: {
194: return (c >= 'A' && c <= 'Z' ? c + ('a' - 'A') : c);
195: }
This archive runs on limited infrastructure. Preserving old code on modern bandwidth. Automated agents are requested to crawl responsibly.