Annotation of pgp/src/charset.c, revision 1.1.1.6

1.1.1.5   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:  * (c) Copyright 1990-1994 by Philip Zimmermann.  All rights reserved.
                      8:  * The author assumes no liability for damages resulting from the use
                      9:  * of this software, even if the damage results from defects in this
                     10:  * software.  No warranty is expressed or implied.
                     11:  *
                     12:  * Code that has been incorporated into PGP from other sources was
                     13:  * either originally published in the public domain or is used with
                     14:  * permission from the various authors.
                     15:  *
                     16:  * PGP is available for free to the public under certain restrictions.
                     17:  * See the PGP User's Guide (included in the release package) for
                     18:  * important information about licensing, patent restrictions on
                     19:  * certain algorithms, trademarks, copyrights, and export controls.
                     20:  */
                     21: 
                     22: #include <stdio.h>
                     23: #include <string.h>
                     24: #include "usuals.h"
                     25: #include "language.h"
                     26: #include "charset.h"
                     27: #include "system.h"
                     28: 
                     29: #ifndef NULL
                     30: #define        NULL    0
                     31: #endif
                     32: 
                     33: #define UNK    '?'
                     34: 
                     35: static unsigned char
                     36: intern2ascii[] = {  /* ISO 8859-1 Latin Alphabet 1 to US ASCII */
                     37: UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK,
                     38: UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK,
                     39:  32,  33,  99,  35,  36,  89, 124,  80,  34,  67,  97,  34, 126,  45,  82,  95,
                     40: 111, UNK,  50,  51,  39, 117,  45,  45,  44,  49, 111,  34, UNK, UNK, UNK,  63,
                     41:  65,  65,  65,  65,  65,  65,  65,  67,  69,  69,  69,  69,  73,  73,  73,  73,
                     42:  68,  78,  79,  79,  79,  79,  79, 120,  79,  85,  85,  85,  85,  89,  84, 115,
                     43:  97,  97,  97,  97,  97,  97,  97,  99, 101, 101, 101, 101, 105, 105, 105, 105,
                     44: 100, 110, 111, 111, 111, 111, 111,  47, 111, 117, 117, 117, 117, 121, 116, 121
                     45: };
                     46: 
                     47: static unsigned char
1.1.1.6 ! root       48: intern2cp850[] = { /* ISO 8859-1 Latin Alphabet 1
        !            49:                      (Latin-1) to IBM Code Page 850 */
1.1.1.5   root       50: 186, 205, 201, 187, 200, 188, 204, 185, 203, 202, 206, 223, 220, 219, 254, 242,
                     51: 179, 196, 218, 191, 192, 217, 195, 180, 194, 193, 197, 176, 177, 178, 213, 159,
                     52: 255, 173, 189, 156, 207, 190, 221, 245, 249, 184, 166, 174, 170, 240, 169, 238,
                     53: 248, 241, 253, 252, 239, 230, 244, 250, 247, 251, 167, 175, 172, 171, 243, 168,
                     54: 183, 181, 182, 199, 142, 143, 146, 128, 212, 144, 210, 211, 222, 214, 215, 216,
                     55: 209, 165, 227, 224, 226, 229, 153, 158, 157, 235, 233, 234, 154, 237, 232, 225,
                     56: 133, 160, 131, 198, 132, 134, 145, 135, 138, 130, 136, 137, 141, 161, 140, 139,
                     57: 208, 164, 149, 162, 147, 228, 148, 246, 155, 151, 163, 150, 129, 236, 231, 152
                     58: };
                     59: 
                     60: static unsigned char
                     61: cp8502intern[] = {  /* IBM Code Page 850 to Latin-1 */
                     62: 199, 252, 233, 226, 228, 224, 229, 231, 234, 235, 232, 239, 238, 236, 196, 197,
                     63: 201, 230, 198, 244, 246, 242, 251, 249, 255, 214, 220, 248, 163, 216, 215, 159,
                     64: 225, 237, 243, 250, 241, 209, 170, 186, 191, 174, 172, 189, 188, 161, 171, 187,
                     65: 155, 156, 157, 144, 151, 193, 194, 192, 169, 135, 128, 131, 133, 162, 165, 147,
                     66: 148, 153, 152, 150, 145, 154, 227, 195, 132, 130, 137, 136, 134, 129, 138, 164,
                     67: 240, 208, 202, 203, 200, 158, 205, 206, 207, 149, 146, 141, 140, 166, 204, 139,
                     68: 211, 223, 212, 210, 245, 213, 181, 254, 222, 218, 219, 217, 253, 221, 175, 180,
                     69: 173, 177, 143, 190, 182, 167, 247, 184, 176, 168, 183, 185, 179, 178, 142, 160
                     70: };
                     71: 
                     72: /* Russian language specific conversation section */
                     73: /* Two point-to-point charset decode tables       */
                     74: /* produced by Andrew A. Chernov                  */
                     75: /* Decode single char from KOI8-R to ALT-CODES, if present */
                     76: static unsigned char intern2alt[] = {
                     77:        0xc4, 0xb3, 0xda, 0xbf, 0xc0, 0xd9, 0xc3, 0xb4,
                     78:        0xc2, 0xc1, 0xc5, 0xdf, 0xdc, 0xdb, 0xdd, 0xde,
                     79:        0xb0, 0xb1, 0xb2, 0xf4, 0xfe, 0xf9, 0xfb, 0xf7,
                     80:        0xf3, 0xf2, 0xff, 0xf5, 0xf8, 0xfd, 0xfa, 0xf6,
                     81:        0xcd, 0xba, 0xd5, 0xf1, 0xd6, 0xc9, 0xb8, 0xb7,
                     82:        0xbb, 0xd4, 0xd3, 0xc8, 0xbe, 0xbd, 0xbc, 0xc6,
                     83:        0xc7, 0xcc, 0xb5, 0xf0, 0xb6, 0xb9, 0xd1, 0xd2,
                     84:        0xcb, 0xcf, 0xd0, 0xca, 0xd8, 0xd7, 0xce, 0xfc,
                     85:        0xee, 0xa0, 0xa1, 0xe6, 0xa4, 0xa5, 0xe4, 0xa3,
                     86:        0xe5, 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae,
                     87:        0xaf, 0xef, 0xe0, 0xe1, 0xe2, 0xe3, 0xa6, 0xa2,
                     88:        0xec, 0xeb, 0xa7, 0xe8, 0xed, 0xe9, 0xe7, 0xea,
                     89:        0x9e, 0x80, 0x81, 0x96, 0x84, 0x85, 0x94, 0x83,
                     90:        0x95, 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e,
                     91:        0x8f, 0x9f, 0x90, 0x91, 0x92, 0x93, 0x86, 0x82,
                     92:        0x9c, 0x9b, 0x87, 0x98, 0x9d, 0x99, 0x97, 0x9a
                     93: };
                     94: 
                     95: /* Decode single char from ALT-CODES, if present, to KOI8-R */
                     96: static unsigned char alt2intern[] = {
                     97:        0xe1, 0xe2, 0xf7, 0xe7, 0xe4, 0xe5, 0xf6, 0xfa,
                     98:        0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, 0xf0,
                     99:        0xf2, 0xf3, 0xf4, 0xf5, 0xe6, 0xe8, 0xe3, 0xfe,
                    100:        0xfb, 0xfd, 0xff, 0xf9, 0xf8, 0xfc, 0xe0, 0xf1,
                    101:        0xc1, 0xc2, 0xd7, 0xc7, 0xc4, 0xc5, 0xd6, 0xda,
                    102:        0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, 0xd0,
                    103:        0x90, 0x91, 0x92, 0x81, 0x87, 0xb2, 0xb4, 0xa7,
                    104:        0xa6, 0xb5, 0xa1, 0xa8, 0xae, 0xad, 0xac, 0x83,
                    105:        0x84, 0x89, 0x88, 0x86, 0x80, 0x8a, 0xaf, 0xb0,
                    106:        0xab, 0xa5, 0xbb, 0xb8, 0xb1, 0xa0, 0xbe, 0xb9,
                    107:        0xba, 0xb6, 0xb7, 0xaa, 0xa9, 0xa2, 0xa4, 0xbd,
                    108:        0xbc, 0x85, 0x82, 0x8d, 0x8c, 0x8e, 0x8f, 0x8b,
                    109:        0xd2, 0xd3, 0xd4, 0xd5, 0xc6, 0xc8, 0xc3, 0xde,
                    110:        0xdb, 0xdd, 0xdf, 0xd9, 0xd8, 0xdc, 0xc0, 0xd1,
                    111:        0xb3, 0xa3, 0x99, 0x98, 0x93, 0x9b, 0x9f, 0x97,
                    112:        0x9c, 0x95, 0x9e, 0x96, 0xbf, 0x9d, 0x94, 0x9a
                    113: };
                    114: 
                    115: /*
                    116:  * Most Unixes has KOI8, and DOS has ALT_CODE
                    117:  * If your Unix is non-standard, set CHARSET to "alt_codes"
                    118:  * in config.txt
                    119:  */
                    120: 
                    121: #ifndef        DEFAULT_CSET
                    122: #define        DEFAULT_CSET    "noconv"
                    123: #endif
                    124: #ifndef        DEFAULT_RU_CSET
                    125: #define        DEFAULT_RU_CSET "noconv"
                    126: #endif
                    127: 
                    128: /* End of Russian section */
                    129: 
                    130: int CONVERSION = NO_CONV;      /* None text file conversion at start time */
                    131: 
                    132: unsigned char *ext_c_ptr;
                    133: static unsigned char *int_c_ptr;
                    134: 
                    135: #ifdef MSDOS
                    136: char charset[64] = "cp850";
                    137: #else
                    138: char charset[64] = "";
                    139: #endif
                    140: 
                    141: void
                    142: init_charset(void)
                    143: {
1.1.1.6 ! root      144:        ext_c_ptr = NULL;       /* NULL means latin1 or KOI8
        !           145:                                   (internal format) */
1.1.1.5   root      146:        int_c_ptr = NULL;
                    147: 
                    148:        if (charset[0] == '\0') {
                    149:                /* use default character set for this system */
                    150:                if (strcmp(language, "ru") == 0)
                    151:                        strcpy(charset, DEFAULT_RU_CSET);
                    152:                else
                    153:                        strcpy(charset, DEFAULT_CSET);
                    154:        } else {
                    155:                strlwr(charset);
                    156:        }
                    157: 
                    158:        /* latin-1 and KOI8 are in internal format: no conversion needed */
                    159:        if (!strcmp(charset, "latin1") || !strcmp(charset, "koi8") ||
                    160:                !strcmp(charset, "noconv"))
                    161:                return;
                    162: 
                    163:        if (!strcmp(charset, "alt_codes")) {
                    164:                ext_c_ptr = intern2alt;
                    165:                int_c_ptr = alt2intern;
                    166:        } else if (!strcmp(charset, "cp850")) {
                    167:                ext_c_ptr = intern2cp850;
                    168:                int_c_ptr = cp8502intern;
                    169:        } else if (!strcmp(charset, "ascii")) {
                    170:                ext_c_ptr = intern2ascii;
                    171:        } else {
1.1.1.6 ! root      172:                fprintf(stderr, LANG("Unsupported character set: '%s'\n"),
        !           173:                        charset);
1.1.1.5   root      174:        }
                    175: }
                    176: 
                    177: char
                    178: EXT_C(char c)
                    179: {
                    180:        if (c > '\0' || !ext_c_ptr)
                    181:                return c;
                    182:        return ext_c_ptr[c & 0x7f];
                    183: }
                    184: 
                    185: char
                    186: INT_C(char c)
                    187: {
                    188:        if (c > '\0' || !int_c_ptr)
                    189:                return c;
                    190:        return int_c_ptr[c & 0x7f];
                    191: }
                    192: 
                    193: /*
                    194:  * to_upper() and to_lower(), replacement for toupper() and tolower(),
                    195:  * calling to_upper() on uppercase or to_lower on lowercase characters
                    196:  * is handled correctly.
                    197:  * 
                    198:  * XXX: should handle local characterset when 8-bit userID's are allowed
                    199:  */
                    200: int
                    201: to_upper(int c)
                    202: {
                    203:        return (c >= 'a' && c <= 'z' ? c - ('a' - 'A') : c);
                    204: }
                    205: 
                    206: int
                    207: to_lower(int c)
                    208: {
                    209:        return (c >= 'A' && c <= 'Z' ? c + ('a' - 'A') : c);
                    210: }

unix.superglobalmegacorp.com

This archive runs on limited infrastructure. Preserving old code on modern bandwidth. Automated agents are requested to crawl responsibly.