![[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 |
1.1.1.7 ! 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 1990-1996 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 <ctype.h> ! 25: #include "usuals.h" ! 26: #include "language.h" ! 27: #include "charset.h" ! 28: #include "system.h" ! 29: ! 30: #ifndef NULL ! 31: #define NULL 0 ! 32: #endif ! 33: ! 34: #define UNK '?' ! 35: ! 36: static unsigned char ! 37: intern2ascii[] = { /* ISO 8859-1 Latin Alphabet 1 to US ASCII */ ! 38: UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, ! 39: UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, ! 40: 32, 33, 99, 35, 36, 89, 124, 80, 34, 67, 97, 34, 126, 45, 82, 95, ! 41: 111, UNK, 50, 51, 39, 117, 45, 45, 44, 49, 111, 34, UNK, UNK, UNK, 63, ! 42: 65, 65, 65, 65, 65, 65, 65, 67, 69, 69, 69, 69, 73, 73, 73, 73, ! 43: 68, 78, 79, 79, 79, 79, 79, 120, 79, 85, 85, 85, 85, 89, 84, 115, ! 44: 97, 97, 97, 97, 97, 97, 97, 99, 101, 101, 101, 101, 105, 105, 105, 105, ! 45: 100, 110, 111, 111, 111, 111, 111, 47, 111, 117, 117, 117, 117, 121, 116, 121 ! 46: }; ! 47: ! 48: static unsigned char ! 49: intern2cp850[] = { /* ISO 8859-1 Latin Alphabet 1 (Latin-1) ! 50: to IBM Code Page 850 (International) */ ! 51: 186, 205, 201, 187, 200, 188, 204, 185, 203, 202, 206, 223, 220, 219, 254, 242, ! 52: 179, 196, 218, 191, 192, 217, 195, 180, 194, 193, 197, 176, 177, 178, 213, 159, ! 53: 255, 173, 189, 156, 207, 190, 221, 245, 249, 184, 166, 174, 170, 240, 169, 238, ! 54: 248, 241, 253, 252, 239, 230, 244, 250, 247, 251, 167, 175, 172, 171, 243, 168, ! 55: 183, 181, 182, 199, 142, 143, 146, 128, 212, 144, 210, 211, 222, 214, 215, 216, ! 56: 209, 165, 227, 224, 226, 229, 153, 158, 157, 235, 233, 234, 154, 237, 232, 225, ! 57: 133, 160, 131, 198, 132, 134, 145, 135, 138, 130, 136, 137, 141, 161, 140, 139, ! 58: 208, 164, 149, 162, 147, 228, 148, 246, 155, 151, 163, 150, 129, 236, 231, 152 ! 59: }; ! 60: ! 61: static unsigned char ! 62: cp8502intern[] = { /* IBM Code Page 850 to Latin-1 */ ! 63: 199, 252, 233, 226, 228, 224, 229, 231, 234, 235, 232, 239, 238, 236, 196, 197, ! 64: 201, 230, 198, 244, 246, 242, 251, 249, 255, 214, 220, 248, 163, 216, 215, 159, ! 65: 225, 237, 243, 250, 241, 209, 170, 186, 191, 174, 172, 189, 188, 161, 171, 187, ! 66: 155, 156, 157, 144, 151, 193, 194, 192, 169, 135, 128, 131, 133, 162, 165, 147, ! 67: 148, 153, 152, 150, 145, 154, 227, 195, 132, 130, 137, 136, 134, 129, 138, 164, ! 68: 240, 208, 202, 203, 200, 158, 205, 206, 207, 149, 146, 141, 140, 166, 204, 139, ! 69: 211, 223, 212, 210, 245, 213, 181, 254, 222, 218, 219, 217, 253, 221, 175, 180, ! 70: 173, 177, 143, 190, 182, 167, 247, 184, 176, 168, 183, 185, 179, 178, 142, 160 ! 71: }; ! 72: ! 73: static unsigned char ! 74: intern2cp852[] = { /* ISO 8859-2 Latin Alphabet 2 (Latin-2) ! 75: to IBM Code Page 852 (Eastern Europe) */ ! 76: 186, 205, 201, 187, 200, 188, 204, 185, 203, 202, 206, 223, 220, 219, 254, UNK, ! 77: 179, 196, 218, 191, 192, 217, 195, 180, 194, 193, 197, 176, 177, 178, UNK, UNK, ! 78: 255, 164, 244, 157, 207, 149, 151, 245, 249, 230, 184, 155, 141, 240, 166, 189, ! 79: 248, 165, 247, 136, 239, 150, 151, 243, 242, 231, 173, 156, 171, 241, 167, 190, ! 80: 232, 181, 182, 198, 142, 145, 143, 128, 172, 144, 168, 211, 183, 214, 73, 210, ! 81: 209, 227, 213, 224, 226, 138, 153, 158, 252, 222, 233, 235, 154, 237, 221, 225, ! 82: 234, 160, 131, 199, 132, 146, 134, 135, 159, 130, 169, 137, 216, 161, 140, 212, ! 83: 208, 228, 229, 162, 147, 139, 148, 246, 253, 133, 163, 251, 129, 236, 238, 250 ! 84: }; ! 85: ! 86: static unsigned char ! 87: cp8522intern[] = { /* IBM Code Page 852 to Latin-2 */ ! 88: 199, 252, 233, 226, 228, 249, 230, 231, 179, 235, 213, 245, 238, 172, 196, 198, ! 89: 201, 197, 229, 244, 246, 165, 181, 166, 182, 214, 220, 171, 187, 163, 215, 232, ! 90: 225, 237, 243, 250, 161, 177, 174, 190, 202, 234, UNK, 188, 200, 186, 60, 62, ! 91: 155, 156, 157, 144, 151, 193, 194, 204, 170, 135, 128, 131, 133, 175, 191, 147, ! 92: 148, 153, 152, 150, 145, 154, 195, 227, 132, 130, 137, 136, 134, 129, 138, 164, ! 93: 240, 208, 207, 203, 239, 210, 205, 85, 236, 149, 146, 141, 140, 222, 217, 139, ! 94: 211, 223, 212, 209, 241, 242, 169, 185, 192, 218, 224, 219, 253, 221, 254, 180, ! 95: 173, 189, 184, 183, 162, 167, 247, 178, 176, 168, 255, 251, 216, 248, 142, 160 ! 96: }; ! 97: ! 98: static unsigned char ! 99: intern2cp860[] = { /* ISO 8859-1 Latin Alphabet 1 (Latin-1) ! 100: to IBM Code Page 860 (Portuguese) */ ! 101: 186, 205, 201, 187, 200, 188, 204, 185, 203, 202, 206, 223, 220, 219, 254, 95, ! 102: 179, 196, 218, 191, 192, 217, 195, 180, 194, 193, 197, 176, 177, 178, UNK, UNK, ! 103: 255, 173, 155, 156, 36, 89, 124, 80, 34, 67, 166, 174, 170, 45, 82, 95, ! 104: 248, 241, 253, 51, 39, 230, 45, 250, 44, 49, 167, 175, 172, 171, UNK, 168, ! 105: 145, 134, 143, 142, 65, 65, 65, 128, 146, 144, 137, 69, 152, 139, 73, 73, ! 106: 68, 165, 169, 159, 140, 153, 79, 120, 79, 157, 150, 85, 154, 89, 84, 225, ! 107: 133, 160, 131, 132, 97, 97, 97, 135, 138, 130, 136, 101, 141, 161, 105, 105, ! 108: 100, 164, 149, 162, 147, 148, 111, 246, 111, 151, 163, 117, 129, 121, 116, 121 ! 109: }; ! 110: ! 111: static unsigned char ! 112: cp8602intern[] = { /* IBM Code Page 860 to Latin-1 */ ! 113: 199, 252, 233, 226, 227, 224, 193, 231, 234, 202, 232, 205, 212, 236, 195, 194, ! 114: 201, 192, 200, 244, 245, 242, 218, 249, 204, 213, 220, 162, 163, 217, 164, 211, ! 115: 225, 237, 243, 250, 241, 209, 170, 186, 191, 210, 172, 189, 188, 161, 171, 187, ! 116: 155, 156, 157, 144, 151, 151, 135, 147, 131, 135, 128, 131, 133, 149, 133, 147, ! 117: 148, 153, 152, 150, 145, 154, 150, 134, 132, 130, 137, 136, 134, 129, 138, 137, ! 118: 153, 136, 152, 148, 132, 130, 146, 154, 138, 149, 146, 141, 140, 141, 141, 139, ! 119: UNK, 223, UNK, UNK, UNK, UNK, 181, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, ! 120: 61, UNK, UNK, UNK, UNK, UNK, 247, 126, 176, 183, 183, UNK, 110, 178, 142, 160 ! 121: }; ! 122: ! 123: static unsigned char ! 124: intern2keybcs[] = { /* ISO 8859-2 Latin Alphabet 2 (Latin-2) ! 125: to KEYBCS2 (Eastern Europe) */ ! 126: UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, ! 127: UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, ! 128: UNK, 65, UNK, 76, UNK, 156, 83, 173, UNK, 155, 83, 134, 90, UNK, 146, 90, ! 129: 248, UNK, UNK, 108, UNK, 140, 115, UNK, UNK, 168, 115, 159, 122, UNK, 145, 122, ! 130: 171, 143, 65, 65, 142, 138, 67, 67, 128, 144, 69, 69, 137, 139, 73, 133, ! 131: 68, 78, 165, 149, 167, 79, 153, UNK, 158, 166, 151, 85, 154, 157, 84, 225, ! 132: 170, 160, 97, 97, 132, 141, 99, 99, 135, 130, 101, UNK, 136, 161, 105, 131, ! 133: 100, 110, 164, 162, 147, 111, 148, UNK, 169, 150, 163, 117, 129, 152, 116, UNK ! 134: }; ! 135: ! 136: static unsigned char ! 137: keybcs2intern[] = { /* KEYBCS2 to Latin-2 */ ! 138: 200, 252, 233, 239, 228, 207, 171, 232, 236, 204, 197, 205, 181, 229, 196, 193, ! 139: 201, 190, 174, 244, 246, 211, 249, 218, 253, 214, 220, 169, 165, 221, 216, 187, ! 140: 225, 237, 243, 250, 242, 210, 217, 212, 185, 248, 224, 192, UNK, 167, UNK, UNK, ! 141: UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, ! 142: UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, ! 143: UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, ! 144: UNK, 223, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, ! 145: UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, 176, UNK, UNK, UNK, UNK, UNK, UNK, UNK ! 146: }; ! 147: ! 148: static unsigned char ! 149: intern2next[] = { /* ISO 8859-1 Latin Alphabet 1 (Latin-1) ! 150: to NeXTSTEP char set */ ! 151: UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, ! 152: 0300, 0301, 0302, 0303, 0304, 0305, 0306, 0307, 0310, UNK, 0312, 0313, UNK, 0272, 0316, 0247, ! 153: UNK, 0241, 0242, 0243, 0250, 0245, 0265, UNK, 0310, 0240, 0343, 0253, 0276, 0261, 0260, 0320, ! 154: 0312, 0321, 0311, 0314, 0270, 0235, 0266, 0267, 0313, 0300, UNK, 0273, 0322, 0323, 0324, 0277, ! 155: 0201, 0202, 0203, 0204, 0205, 0206, 0341, 0207, 0210, 0211, 0212, 0213, 0214, 0215, 0216, 0217, ! 156: 0220, 0221, 0222, 0223, 0224, 0225, 0226, 0236, 0351, 0227, 0230, 0231, 0232, 0233, 0234, 0373, ! 157: 0325, 0326, 0327, 0330, 0331, 0332, 0361, 0333, 0334, 0335, 0336, 0337, 0340, 0342, 0344, 0345, ! 158: 0346, 0347, 0354, 0355, 0356, 0357, 0360, 0237, 0371, 0362, 0363, 0364, 0366, 0367, 0374, 0375 ! 159: }; ! 160: ! 161: static unsigned char ! 162: next2intern[] = { /* NeXTSTEP char set to Latin-1 */ ! 163: UNK, 0300, 0301, 0302, 0303, 0304, 0305, 0307, 0310, 0311, 0312, 0313, 0314, 0315, 0316, 0317, ! 164: 0320, 0321, 0322, 0323, 0324, 0325, 0326, 0331, 0332, 0333, 0334, 0335, 0336, 0265, 0337, 0267, ! 165: 0251, 0241, 0242, 0243, 0057, 0245, 0146, 0247, 0244, 0140, 0042, 0253, 0074, 0076, UNK, UNK, ! 166: 0256, 0255, UNK, UNK, 0056, 0246, 0266, 0267, 0054, 0042, 0235, 0273, UNK, UNK, 0254, 0277, ! 167: 0220, 0221, 0222, 0223, 0224, 0225, 0226, 0232, 0230, 0262, 0227, 0270, 0263, 0042, 0236, 0226, ! 168: 0257, 0261, 0274, 0275, 0276, 0340, 0341, 0342, 0343, 0344, 0345, 0347, 0350, 0351, 0352, 0353, ! 169: 0354, 0306, 0355, 0252, 0356, 0357, 0365, 0361, 0243, 0330, UNK, 0272, 0362, 0363, 0364, 0365, ! 170: 0366, 0346, 0371, 0372, 0373, 0151, 0374, 0375, 0154, 0370, UNK, 0337, 0376, 0377, UNK, UNK ! 171: }; ! 172: ! 173: #ifdef MACTC5 ! 174: Boolean iso_latin1 = false; ! 175: #endif ! 176: ! 177: static unsigned char ! 178: intern2mac[] = { /* ISO 8859-1 Latin Alphabet 1 (Latin1) ! 179: to Macintosh Geneva/Monaco */ ! 180: UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, ! 181: UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, ! 182: 202, 193, 162, 163, 217, 180, 124, 164, 172, 169, 187, 199, 194, 209, 168, 95, ! 183: 188, 177, 50, 51, 171, 181, 166, 165, 44, 49, 161, 200, UNK, UNK, UNK, 192, ! 184: 203, 135, 129, 204, 128, 129, 174, 130, 143, 131, 144, 145, 147, 146, 148, 149, ! 185: 68, 132, 152, 151, 153, 205, 133, 120, 175, 157, 156, 158, 134, 89, 84, 167, ! 186: 136, 135, 137, 139, 138, 140, 97, 141, 143, 142, 144, 145, 147, 146, 148, 149, ! 187: 100, 150, 152, 151, 153, 155, 154, 214, 191, 157, 156, 158, 159, 121, 116, 216 ! 188: }; ! 189: ! 190: static unsigned char ! 191: mac2intern[] = { /* Macintosh Geneva/Monaco to Latin-1 */ ! 192: 196, 197, 199, 201, 209, 214, 220, 225, 224, 226, 228, 227, 229, 231, 233, 232, ! 193: 234, 235, 237, 236, 238, 239, 241, 243, 242, 244, 246, 245, 250, 249, 251, 252, ! 194: UNK, 186, 162, 163, 167, 183, 182, 223, 174, 169, UNK, 180, 168, UNK, 198, 216, ! 195: UNK, 177, UNK, UNK, 165, 181, 100, 83, 80, 112, 83, 170, 176, 79, 230, 248, ! 196: 191, 161, 172, UNK, 102, 126, 68, 171, 187, UNK, 160, 192, 195, 213, 79, 111, ! 197: 45, 173, 34, 34, 96, 39, 247, UNK, 255, UNK, UNK, UNK, UNK, UNK, UNK, UNK, ! 198: UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, ! 199: UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK, UNK ! 200: }; ! 201: ! 202: /* Russian language specific conversation section */ ! 203: /* Two point-to-point charset decode tables */ ! 204: /* produced by Andrew A. Chernov */ ! 205: /* Decode single char from KOI8-R to ALT-CODES, if present */ ! 206: static unsigned char intern2alt[] = { ! 207: 0xc4, 0xb3, 0xda, 0xbf, 0xc0, 0xd9, 0xc3, 0xb4, ! 208: 0xc2, 0xc1, 0xc5, 0xdf, 0xdc, 0xdb, 0xdd, 0xde, ! 209: 0xb0, 0xb1, 0xb2, 0xf4, 0xfe, 0xf9, 0xfb, 0xf7, ! 210: 0xf3, 0xf2, 0xff, 0xf5, 0xf8, 0xfd, 0xfa, 0xf6, ! 211: 0xcd, 0xba, 0xd5, 0xf1, 0xd6, 0xc9, 0xb8, 0xb7, ! 212: 0xbb, 0xd4, 0xd3, 0xc8, 0xbe, 0xbd, 0xbc, 0xc6, ! 213: 0xc7, 0xcc, 0xb5, 0xf0, 0xb6, 0xb9, 0xd1, 0xd2, ! 214: 0xcb, 0xcf, 0xd0, 0xca, 0xd8, 0xd7, 0xce, 0xfc, ! 215: 0xee, 0xa0, 0xa1, 0xe6, 0xa4, 0xa5, 0xe4, 0xa3, ! 216: 0xe5, 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, ! 217: 0xaf, 0xef, 0xe0, 0xe1, 0xe2, 0xe3, 0xa6, 0xa2, ! 218: 0xec, 0xeb, 0xa7, 0xe8, 0xed, 0xe9, 0xe7, 0xea, ! 219: 0x9e, 0x80, 0x81, 0x96, 0x84, 0x85, 0x94, 0x83, ! 220: 0x95, 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, ! 221: 0x8f, 0x9f, 0x90, 0x91, 0x92, 0x93, 0x86, 0x82, ! 222: 0x9c, 0x9b, 0x87, 0x98, 0x9d, 0x99, 0x97, 0x9a ! 223: }; ! 224: ! 225: /* Decode single char from ALT-CODES, if present, to KOI8-R */ ! 226: static unsigned char alt2intern[] = { ! 227: 0xe1, 0xe2, 0xf7, 0xe7, 0xe4, 0xe5, 0xf6, 0xfa, ! 228: 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, 0xf0, ! 229: 0xf2, 0xf3, 0xf4, 0xf5, 0xe6, 0xe8, 0xe3, 0xfe, ! 230: 0xfb, 0xfd, 0xff, 0xf9, 0xf8, 0xfc, 0xe0, 0xf1, ! 231: 0xc1, 0xc2, 0xd7, 0xc7, 0xc4, 0xc5, 0xd6, 0xda, ! 232: 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, 0xd0, ! 233: 0x90, 0x91, 0x92, 0x81, 0x87, 0xb2, 0xb4, 0xa7, ! 234: 0xa6, 0xb5, 0xa1, 0xa8, 0xae, 0xad, 0xac, 0x83, ! 235: 0x84, 0x89, 0x88, 0x86, 0x80, 0x8a, 0xaf, 0xb0, ! 236: 0xab, 0xa5, 0xbb, 0xb8, 0xb1, 0xa0, 0xbe, 0xb9, ! 237: 0xba, 0xb6, 0xb7, 0xaa, 0xa9, 0xa2, 0xa4, 0xbd, ! 238: 0xbc, 0x85, 0x82, 0x8d, 0x8c, 0x8e, 0x8f, 0x8b, ! 239: 0xd2, 0xd3, 0xd4, 0xd5, 0xc6, 0xc8, 0xc3, 0xde, ! 240: 0xdb, 0xdd, 0xdf, 0xd9, 0xd8, 0xdc, 0xc0, 0xd1, ! 241: 0xb3, 0xa3, 0x99, 0x98, 0x93, 0x9b, 0x9f, 0x97, ! 242: 0x9c, 0x95, 0x9e, 0x96, 0xbf, 0x9d, 0x94, 0x9a ! 243: }; ! 244: ! 245: /* ! 246: * Most Unixes has KOI8, and DOS has ALT_CODES ! 247: * If your Unix is non-standard, set CHARSET to "alt_codes" ! 248: * in config.txt ! 249: */ ! 250: ! 251: #ifndef DEFAULT_RU_CSET ! 252: #ifdef MSDOS ! 253: #define DEFAULT_RU_CSET "alt_codes" ! 254: #else ! 255: #define DEFAULT_RU_CSET "koi8" ! 256: #endif ! 257: #endif ! 258: ! 259: /* End of Russian section */ ! 260: ! 261: #ifndef DEFAULT_CSET ! 262: #if defined(MSDOS) ! 263: #define DEFAULT_CSET "cp850" ! 264: #elif defined(NEXT) ! 265: #define DEFAULT_CSET "next" ! 266: #elif defined(MACTC5) ! 267: #define DEFAULT_CSET "mac" ! 268: #else ! 269: #define DEFAULT_CSET "noconv" ! 270: #endif ! 271: #endif ! 272: ! 273: #ifdef EBCDIC ! 274: /* ebcdic-ascii converting, accustom to your local MVS-settings */ ! 275: /* in this case it's taken from c370.c */ ! 276: #define ebcdic__ascii ebcdic_ascii ! 277: #define ascii__ebcdic ascii_ebcdic ! 278: #endif /* EBCDIC */ ! 279: ! 280: int CONVERSION = NO_CONV; /* None text file conversion at start time */ ! 281: ! 282: unsigned char *ext_c_ptr; ! 283: static unsigned char *int_c_ptr; ! 284: ! 285: char charset[16] = ""; ! 286: ! 287: void ! 288: init_charset(void) ! 289: { ! 290: ext_c_ptr = NULL; /* NULL means latin1 or KOI8 ! 291: (internal format) */ ! 292: int_c_ptr = NULL; ! 293: ! 294: if (charset[0] == '\0') { ! 295: /* use default character set for this system */ ! 296: #ifdef MACTC5 ! 297: if (iso_latin1) ! 298: strcpy(charset, DEFAULT_CSET); ! 299: else ! 300: strcpy(charset, "noconv"); ! 301: #else ! 302: if (strcmp(language, "ru") == 0) ! 303: strcpy(charset, DEFAULT_RU_CSET); ! 304: else ! 305: strcpy(charset, DEFAULT_CSET); ! 306: #endif ! 307: } else { ! 308: strlwr(charset); ! 309: } ! 310: ! 311: /* latin-1 and KOI8 are in internal format: no conversion needed */ ! 312: if (!strcmp(charset, "latin1") || !strcmp(charset, "koi8") || ! 313: !strcmp(charset, "noconv")) ! 314: return; ! 315: ! 316: if (!strcmp(charset, "cp850")) { ! 317: ext_c_ptr = intern2cp850; ! 318: int_c_ptr = cp8502intern; ! 319: } else if (!strcmp(charset, "cp852")) { ! 320: ext_c_ptr = intern2cp852; ! 321: int_c_ptr = cp8522intern; ! 322: } else if (!strcmp(charset, "cp860")) { ! 323: ext_c_ptr = intern2cp860; ! 324: int_c_ptr = cp8602intern; ! 325: } else if (!strcmp(charset, "cp866")) { ! 326: ext_c_ptr = intern2alt; ! 327: int_c_ptr = alt2intern; ! 328: } else if (!strcmp(charset, "alt_codes")) { ! 329: ext_c_ptr = intern2alt; ! 330: int_c_ptr = alt2intern; ! 331: } else if (!strcmp(charset, "keybcs2")) { ! 332: ext_c_ptr = intern2keybcs; ! 333: int_c_ptr = keybcs2intern; ! 334: } else if (!strcmp(charset, "next")) { ! 335: ext_c_ptr = intern2next; ! 336: int_c_ptr = next2intern; ! 337: } else if (!strcmp(charset, "mac")) { ! 338: ext_c_ptr = intern2mac; ! 339: int_c_ptr = mac2intern; ! 340: } else if (!strcmp(charset, "ascii")) { ! 341: ext_c_ptr = intern2ascii; ! 342: } else { ! 343: fprintf(stderr, LANG("Unsupported character set: '%s'\n"), ! 344: charset); ! 345: strcpy(charset, "noconv"); ! 346: } ! 347: } ! 348: ! 349: #ifdef EBCDIC ! 350: char EXT_C(char c) { return ascii__ebcdic[c]; } ! 351: char INT_C(char c) { return ebcdic__ascii[c]; } ! 352: #else /* !EBCDIC */ ! 353: char ! 354: EXT_C(char c) ! 355: { ! 356: if (!(c & 0x80) || !ext_c_ptr) ! 357: return c; ! 358: return ext_c_ptr[c & 0x7f]; ! 359: } ! 360: ! 361: char ! 362: INT_C(char c) ! 363: { ! 364: if (!(c & 0x80) || !int_c_ptr) ! 365: return c; ! 366: return int_c_ptr[c & 0x7f]; ! 367: } ! 368: #endif /* !EBCDIC */ ! 369: ! 370: /* ! 371: * to_upper() and to_lower(), replacement for toupper() and tolower(), ! 372: * calling to_upper() on uppercase or to_lower on lowercase characters ! 373: * is handled correctly. ! 374: * ! 375: * XXX: should handle local characterset when 8-bit userID's are allowed ! 376: */ ! 377: #ifdef EBCDIC ! 378: /* With EBCDIC-charset things like (c >= 'a' && c <= 'z') do not work!!! ! 379: * Therefor use the appropriate ctype-functions ! 380: */ ! 381: #include <ctype.h> ! 382: int to_upper(int c) { return toupper(c); } ! 383: int to_lower(int c) { return tolower(c); } ! 384: #else /* !EBCDIC */ ! 385: int ! 386: to_upper(int c) ! 387: { ! 388: c &= 0xFF; ! 389: if (islower(c)) ! 390: return (toupper(c)); ! 391: return c; ! 392: } ! 393: ! 394: int ! 395: to_lower(int c) ! 396: { ! 397: c &= 0xFF; ! 398: if (isupper(c)) ! 399: return (tolower(c)); ! 400: return c; ! 401: } ! 402: #endif /* !EBCDIC */ ! 403: ! 404: #ifdef EBCDIC ! 405: void CONVERT_TO_CANONICAL_CHARSET(char *s) /* String to internal string (at same place) */ ! 406: { ! 407: for (; *s; s++) *s = INT_C(*s); ! 408: } ! 409: ! 410: static char buf[128]; ! 411: char * LOCAL_CHARSET( char *s) /* String to external string (at extra place) */ ! 412: { ! 413: strcpy( buf, s ); ! 414: for (s=buf; *s; s++) *s = EXT_C(*s); ! 415: return buf; ! 416: } ! 417: #endif /* EBCDIC */
This archive runs on limited infrastructure. Preserving old code on modern bandwidth. Automated agents are requested to crawl responsibly.