| 1 | /* utfebcdic.h
|
|---|
| 2 | *
|
|---|
| 3 | * Copyright (C) 2001, 2002, by Larry Wall, Nick Ing-Simmons, and others
|
|---|
| 4 | *
|
|---|
| 5 | * You may distribute under the terms of either the GNU General Public
|
|---|
| 6 | * License or the Artistic License, as specified in the README file.
|
|---|
| 7 | *
|
|---|
| 8 | * Macros to implement UTF-EBCDIC as perl's internal encoding
|
|---|
| 9 | * Taken from version 7.1 of Unicode Techical Report #16:
|
|---|
| 10 | * http://www.unicode.org/unicode/reports/tr16
|
|---|
| 11 | */
|
|---|
| 12 |
|
|---|
| 13 | START_EXTERN_C
|
|---|
| 14 |
|
|---|
| 15 | #ifdef DOINIT
|
|---|
| 16 | /* Indexed by encoded byte this table gives the length of the sequence.
|
|---|
| 17 | Adapted from the shadow flags table in tr16.
|
|---|
| 18 | The entries marked 9 in tr6 are continuation bytes and are marked
|
|---|
| 19 | as length 1 here so that we can recover.
|
|---|
| 20 | */
|
|---|
| 21 | #if '^' == 95 /* if defined(__MVS__) || defined(??) (VM/ESA?) 1047 */
|
|---|
| 22 | EXTCONST unsigned char PL_utf8skip[] = {
|
|---|
| 23 | 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
|
|---|
| 24 | 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
|
|---|
| 25 | 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
|
|---|
| 26 | 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
|
|---|
| 27 | 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
|
|---|
| 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 | 1,1,1,1,2,2,2,2,2,1,1,1,1,1,1,1,
|
|---|
| 31 | 2,1,1,1,1,1,1,1,1,1,2,2,2,2,2,2,
|
|---|
| 32 | 2,1,1,1,1,1,1,1,1,1,2,2,2,2,2,2,
|
|---|
| 33 | 2,1,1,1,1,1,1,1,1,1,2,2,2,1,2,2,
|
|---|
| 34 | 2,2,2,2,2,2,2,3,3,3,3,3,3,1,3,3,
|
|---|
| 35 | 1,1,1,1,1,1,1,1,1,1,3,3,3,3,3,3,
|
|---|
| 36 | 1,1,1,1,1,1,1,1,1,1,3,3,4,4,4,4,
|
|---|
| 37 | 1,4,1,1,1,1,1,1,1,1,4,4,4,5,5,5,
|
|---|
| 38 | 1,1,1,1,1,1,1,1,1,1,5,6,6,7,7,1
|
|---|
| 39 | };
|
|---|
| 40 | #endif
|
|---|
| 41 |
|
|---|
| 42 | #if '^' == 106 /* if defined(_OSD_POSIX) POSIX-BC */
|
|---|
| 43 | unsigned char PL_utf8skip[] = {
|
|---|
| 44 | 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
|
|---|
| 45 | 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
|
|---|
| 46 | 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
|
|---|
| 47 | 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
|
|---|
| 48 | 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
|
|---|
| 49 | 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
|
|---|
| 50 | 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
|
|---|
| 51 | 1,1,1,1,2,2,2,2,2,3,1,1,1,1,1,1,
|
|---|
| 52 | 2,1,1,1,1,1,1,1,1,1,2,2,2,2,2,2,
|
|---|
| 53 | 2,1,1,1,1,1,1,1,1,1,2,2,2,2,2,2,
|
|---|
| 54 | 2,3,1,1,1,1,1,1,1,1,2,2,2,3,2,2,
|
|---|
| 55 | 1,2,2,2,2,2,2,3,3,3,2,1,1,1,3,3,
|
|---|
| 56 | 4,1,1,1,1,1,1,1,1,1,3,3,3,3,3,3,
|
|---|
| 57 | 1,1,1,1,1,1,1,1,1,1,3,3,4,6,4,4,
|
|---|
| 58 | 7,4,1,1,1,1,1,1,1,1,4,4,4,5,5,5,
|
|---|
| 59 | 1,1,1,1,1,1,1,1,1,1,5,1,6,1,7,1
|
|---|
| 60 | };
|
|---|
| 61 | #endif
|
|---|
| 62 |
|
|---|
| 63 | #if '^' == 176 /* if defined(??) (OS/400?) 037 */
|
|---|
| 64 | unsigned char PL_utf8skip[] = {
|
|---|
| 65 | 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
|
|---|
| 66 | 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
|
|---|
| 67 | 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
|
|---|
| 68 | 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
|
|---|
| 69 | 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
|
|---|
| 70 | 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,2,
|
|---|
| 71 | 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
|
|---|
| 72 | 1,1,1,1,2,2,2,2,2,1,1,1,1,1,1,1,
|
|---|
| 73 | 2,1,1,1,1,1,1,1,1,1,2,2,2,2,2,2,
|
|---|
| 74 | 2,1,1,1,1,1,1,1,1,1,2,2,2,2,2,2,
|
|---|
| 75 | 2,1,1,1,1,1,1,1,1,1,2,2,2,3,2,2,
|
|---|
| 76 | 1,2,2,2,2,2,2,3,3,3,1,1,3,3,3,3,
|
|---|
| 77 | 1,1,1,1,1,1,1,1,1,1,3,3,3,3,3,3,
|
|---|
| 78 | 1,1,1,1,1,1,1,1,1,1,3,3,4,4,4,4,
|
|---|
| 79 | 1,4,1,1,1,1,1,1,1,1,4,4,4,5,5,5,
|
|---|
| 80 | 1,1,1,1,1,1,1,1,1,1,5,6,6,7,7,1
|
|---|
| 81 | };
|
|---|
| 82 | #endif
|
|---|
| 83 |
|
|---|
| 84 | /* Transform tables from tr16 applied after encoding to render encoding EBCDIC like */
|
|---|
| 85 |
|
|---|
| 86 | #if '^' == 95 /* if defined(__MVS__) || defined(??) (VM/ESA?) 1047 */
|
|---|
| 87 | EXTCONST unsigned char PL_utf2e[] = { /* UTF-8-mod to EBCDIC (IBM-1047) */
|
|---|
| 88 | 0x00, 0x01, 0x02, 0x03, 0x37, 0x2D, 0x2E, 0x2F, 0x16, 0x05, 0x15, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
|
|---|
| 89 | 0x10, 0x11, 0x12, 0x13, 0x3C, 0x3D, 0x32, 0x26, 0x18, 0x19, 0x3F, 0x27, 0x1C, 0x1D, 0x1E, 0x1F,
|
|---|
| 90 | 0x40, 0x5A, 0x7F, 0x7B, 0x5B, 0x6C, 0x50, 0x7D, 0x4D, 0x5D, 0x5C, 0x4E, 0x6B, 0x60, 0x4B, 0x61,
|
|---|
| 91 | 0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0xF7, 0xF8, 0xF9, 0x7A, 0x5E, 0x4C, 0x7E, 0x6E, 0x6F,
|
|---|
| 92 | 0x7C, 0xC1, 0xC2, 0xC3, 0xC4, 0xC5, 0xC6, 0xC7, 0xC8, 0xC9, 0xD1, 0xD2, 0xD3, 0xD4, 0xD5, 0xD6,
|
|---|
| 93 | 0xD7, 0xD8, 0xD9, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7, 0xE8, 0xE9, 0xAD, 0xE0, 0xBD, 0x5F, 0x6D,
|
|---|
| 94 | 0x79, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88, 0x89, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96,
|
|---|
| 95 | 0x97, 0x98, 0x99, 0xA2, 0xA3, 0xA4, 0xA5, 0xA6, 0xA7, 0xA8, 0xA9, 0xC0, 0x4F, 0xD0, 0xA1, 0x07,
|
|---|
| 96 | 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x06, 0x17, 0x28, 0x29, 0x2A, 0x2B, 0x2C, 0x09, 0x0A, 0x1B,
|
|---|
| 97 | 0x30, 0x31, 0x1A, 0x33, 0x34, 0x35, 0x36, 0x08, 0x38, 0x39, 0x3A, 0x3B, 0x04, 0x14, 0x3E, 0xFF,
|
|---|
| 98 | 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48, 0x49, 0x4A, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56,
|
|---|
| 99 | 0x57, 0x58, 0x59, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0x6A, 0x70, 0x71, 0x72, 0x73,
|
|---|
| 100 | 0x74, 0x75, 0x76, 0x77, 0x78, 0x80, 0x8A, 0x8B, 0x8C, 0x8D, 0x8E, 0x8F, 0x90, 0x9A, 0x9B, 0x9C,
|
|---|
| 101 | 0x9D, 0x9E, 0x9F, 0xA0, 0xAA, 0xAB, 0xAC, 0xAE, 0xAF, 0xB0, 0xB1, 0xB2, 0xB3, 0xB4, 0xB5, 0xB6,
|
|---|
| 102 | 0xB7, 0xB8, 0xB9, 0xBA, 0xBB, 0xBC, 0xBE, 0xBF, 0xCA, 0xCB, 0xCC, 0xCD, 0xCE, 0xCF, 0xDA, 0xDB,
|
|---|
| 103 | 0xDC, 0xDD, 0xDE, 0xDF, 0xE1, 0xEA, 0xEB, 0xEC, 0xED, 0xEE, 0xEF, 0xFA, 0xFB, 0xFC, 0xFD, 0xFE,
|
|---|
| 104 | };
|
|---|
| 105 |
|
|---|
| 106 | EXTCONST unsigned char PL_e2utf[] = { /* EBCDIC (IBM-1047) to UTF-8-mod */
|
|---|
| 107 | 0x00, 0x01, 0x02, 0x03, 0x9C, 0x09, 0x86, 0x7F, 0x97, 0x8D, 0x8E, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
|
|---|
| 108 | 0x10, 0x11, 0x12, 0x13, 0x9D, 0x0A, 0x08, 0x87, 0x18, 0x19, 0x92, 0x8F, 0x1C, 0x1D, 0x1E, 0x1F,
|
|---|
| 109 | 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x17, 0x1B, 0x88, 0x89, 0x8A, 0x8B, 0x8C, 0x05, 0x06, 0x07,
|
|---|
| 110 | 0x90, 0x91, 0x16, 0x93, 0x94, 0x95, 0x96, 0x04, 0x98, 0x99, 0x9A, 0x9B, 0x14, 0x15, 0x9E, 0x1A,
|
|---|
| 111 | 0x20, 0xA0, 0xA1, 0xA2, 0xA3, 0xA4, 0xA5, 0xA6, 0xA7, 0xA8, 0xA9, 0x2E, 0x3C, 0x28, 0x2B, 0x7C,
|
|---|
| 112 | 0x26, 0xAA, 0xAB, 0xAC, 0xAD, 0xAE, 0xAF, 0xB0, 0xB1, 0xB2, 0x21, 0x24, 0x2A, 0x29, 0x3B, 0x5E,
|
|---|
| 113 | 0x2D, 0x2F, 0xB3, 0xB4, 0xB5, 0xB6, 0xB7, 0xB8, 0xB9, 0xBA, 0xBB, 0x2C, 0x25, 0x5F, 0x3E, 0x3F,
|
|---|
| 114 | 0xBC, 0xBD, 0xBE, 0xBF, 0xC0, 0xC1, 0xC2, 0xC3, 0xC4, 0x60, 0x3A, 0x23, 0x40, 0x27, 0x3D, 0x22,
|
|---|
| 115 | 0xC5, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0xC6, 0xC7, 0xC8, 0xC9, 0xCA, 0xCB,
|
|---|
| 116 | 0xCC, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F, 0x70, 0x71, 0x72, 0xCD, 0xCE, 0xCF, 0xD0, 0xD1, 0xD2,
|
|---|
| 117 | 0xD3, 0x7E, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, 0x79, 0x7A, 0xD4, 0xD5, 0xD6, 0x5B, 0xD7, 0xD8,
|
|---|
| 118 | 0xD9, 0xDA, 0xDB, 0xDC, 0xDD, 0xDE, 0xDF, 0xE0, 0xE1, 0xE2, 0xE3, 0xE4, 0xE5, 0x5D, 0xE6, 0xE7,
|
|---|
| 119 | 0x7B, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48, 0x49, 0xE8, 0xE9, 0xEA, 0xEB, 0xEC, 0xED,
|
|---|
| 120 | 0x7D, 0x4A, 0x4B, 0x4C, 0x4D, 0x4E, 0x4F, 0x50, 0x51, 0x52, 0xEE, 0xEF, 0xF0, 0xF1, 0xF2, 0xF3,
|
|---|
| 121 | 0x5C, 0xF4, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58, 0x59, 0x5A, 0xF5, 0xF6, 0xF7, 0xF8, 0xF9, 0xFA,
|
|---|
| 122 | 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38, 0x39, 0xFB, 0xFC, 0xFD, 0xFE, 0xFF, 0x9F,
|
|---|
| 123 | };
|
|---|
| 124 | #endif /* 1047 */
|
|---|
| 125 |
|
|---|
| 126 | #if '^' == 106 /* if defined(_OSD_POSIX) POSIX-BC */
|
|---|
| 127 | unsigned char PL_utf2e[] = { /* UTF-8-mod to EBCDIC (POSIX-BC) */
|
|---|
| 128 | 0x00, 0x01, 0x02, 0x03, 0x37, 0x2D, 0x2E, 0x2F, 0x16, 0x05, 0x15, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
|
|---|
| 129 | 0x10, 0x11, 0x12, 0x13, 0x3C, 0x3D, 0x32, 0x26, 0x18, 0x19, 0x3F, 0x27, 0x1C, 0x1D, 0x1E, 0x1F,
|
|---|
| 130 | 0x40, 0x5A, 0x7F, 0x7B, 0x5B, 0x6C, 0x50, 0x7D, 0x4D, 0x5D, 0x5C, 0x4E, 0x6B, 0x60, 0x4B, 0x61,
|
|---|
| 131 | 0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0xF7, 0xF8, 0xF9, 0x7A, 0x5E, 0x4C, 0x7E, 0x6E, 0x6F,
|
|---|
| 132 | 0x7C, 0xC1, 0xC2, 0xC3, 0xC4, 0xC5, 0xC6, 0xC7, 0xC8, 0xC9, 0xD1, 0xD2, 0xD3, 0xD4, 0xD5, 0xD6,
|
|---|
| 133 | 0xD7, 0xD8, 0xD9, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7, 0xE8, 0xE9, 0xBB, 0xBC, 0xBD, 0x6A, 0x6D,
|
|---|
| 134 | 0x4A, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88, 0x89, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96,
|
|---|
| 135 | 0x97, 0x98, 0x99, 0xA2, 0xA3, 0xA4, 0xA5, 0xA6, 0xA7, 0xA8, 0xA9, 0xFB, 0x4F, 0xFD, 0xFF, 0x07,
|
|---|
| 136 | 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x06, 0x17, 0x28, 0x29, 0x2A, 0x2B, 0x2C, 0x09, 0x0A, 0x1B,
|
|---|
| 137 | 0x30, 0x31, 0x1A, 0x33, 0x34, 0x35, 0x36, 0x08, 0x38, 0x39, 0x3A, 0x3B, 0x04, 0x14, 0x3E, 0x5F,
|
|---|
| 138 | 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48, 0x49, 0xB0, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56,
|
|---|
| 139 | 0x57, 0x58, 0x59, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0xD0, 0x70, 0x71, 0x72, 0x73,
|
|---|
| 140 | 0x74, 0x75, 0x76, 0x77, 0x78, 0x80, 0x8A, 0x8B, 0x8C, 0x8D, 0x8E, 0x8F, 0x90, 0x9A, 0x9B, 0x9C,
|
|---|
| 141 | 0x9D, 0x9E, 0x9F, 0xA0, 0xAA, 0xAB, 0xAC, 0xAE, 0xAF, 0xBA, 0xB1, 0xB2, 0xB3, 0xB4, 0xB5, 0xB6,
|
|---|
| 142 | 0xB7, 0xB8, 0xB9, 0xAD, 0x79, 0xA1, 0xBE, 0xBF, 0xCA, 0xCB, 0xCC, 0xCD, 0xCE, 0xCF, 0xDA, 0xDB,
|
|---|
| 143 | 0xDC, 0xC0, 0xDE, 0xDF, 0xE1, 0xEA, 0xEB, 0xEC, 0xED, 0xEE, 0xEF, 0xFA, 0xDD, 0xFC, 0xE0, 0xFE,
|
|---|
| 144 | };
|
|---|
| 145 |
|
|---|
| 146 | unsigned char PL_e2utf[] = { /* EBCDIC (POSIX-BC) to UTF-8-mod */
|
|---|
| 147 | 0x00, 0x01, 0x02, 0x03, 0x9C, 0x09, 0x86, 0x7F, 0x97, 0x8D, 0x8E, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
|
|---|
| 148 | 0x10, 0x11, 0x12, 0x13, 0x9D, 0x0A, 0x08, 0x87, 0x18, 0x19, 0x92, 0x8F, 0x1C, 0x1D, 0x1E, 0x1F,
|
|---|
| 149 | 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x17, 0x1B, 0x88, 0x89, 0x8A, 0x8B, 0x8C, 0x05, 0x06, 0x07,
|
|---|
| 150 | 0x90, 0x91, 0x16, 0x93, 0x94, 0x95, 0x96, 0x04, 0x98, 0x99, 0x9A, 0x9B, 0x14, 0x15, 0x9E, 0x1A,
|
|---|
| 151 | 0x20, 0xA0, 0xA1, 0xA2, 0xA3, 0xA4, 0xA5, 0xA6, 0xA7, 0xA8, 0x60, 0x2E, 0x3C, 0x28, 0x2B, 0x7C,
|
|---|
| 152 | 0x26, 0xAA, 0xAB, 0xAC, 0xAD, 0xAE, 0xAF, 0xB0, 0xB1, 0xB2, 0x21, 0x24, 0x2A, 0x29, 0x3B, 0x9F,
|
|---|
| 153 | 0x2D, 0x2F, 0xB3, 0xB4, 0xB5, 0xB6, 0xB7, 0xB8, 0xB9, 0xBA, 0x5E, 0x2C, 0x25, 0x5F, 0x3E, 0x3F,
|
|---|
| 154 | 0xBC, 0xBD, 0xBE, 0xBF, 0xC0, 0xC1, 0xC2, 0xC3, 0xC4, 0xE4, 0x3A, 0x23, 0x40, 0x27, 0x3D, 0x22,
|
|---|
| 155 | 0xC5, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0xC6, 0xC7, 0xC8, 0xC9, 0xCA, 0xCB,
|
|---|
| 156 | 0xCC, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F, 0x70, 0x71, 0x72, 0xCD, 0xCE, 0xCF, 0xD0, 0xD1, 0xD2,
|
|---|
| 157 | 0xD3, 0xE5, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, 0x79, 0x7A, 0xD4, 0xD5, 0xD6, 0xE3, 0xD7, 0xD8,
|
|---|
| 158 | 0xA9, 0xDA, 0xDB, 0xDC, 0xDD, 0xDE, 0xDF, 0xE0, 0xE1, 0xE2, 0xD9, 0x5B, 0x5C, 0x5D, 0xE6, 0xE7,
|
|---|
| 159 | 0xF1, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48, 0x49, 0xE8, 0xE9, 0xEA, 0xEB, 0xEC, 0xED,
|
|---|
| 160 | 0xBB, 0x4A, 0x4B, 0x4C, 0x4D, 0x4E, 0x4F, 0x50, 0x51, 0x52, 0xEE, 0xEF, 0xF0, 0xFC, 0xF2, 0xF3,
|
|---|
| 161 | 0xFE, 0xF4, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58, 0x59, 0x5A, 0xF5, 0xF6, 0xF7, 0xF8, 0xF9, 0xFA,
|
|---|
| 162 | 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38, 0x39, 0xFB, 0x7B, 0xFD, 0x7D, 0xFF, 0x7E,
|
|---|
| 163 | };
|
|---|
| 164 | #endif /* POSIX-BC */
|
|---|
| 165 |
|
|---|
| 166 | #if '^' == 176 /* if defined(??) (OS/400?) 037 */
|
|---|
| 167 | unsigned char PL_utf2e[] = { /* UTF-8-mod to EBCDIC (IBM-037) */
|
|---|
| 168 | 0x00, 0x01, 0x02, 0x03, 0x37, 0x2D, 0x2E, 0x2F, 0x16, 0x05, 0x25, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
|
|---|
| 169 | 0x10, 0x11, 0x12, 0x13, 0x3C, 0x3D, 0x32, 0x26, 0x18, 0x19, 0x3F, 0x27, 0x1C, 0x1D, 0x1E, 0x1F,
|
|---|
| 170 | 0x40, 0x5A, 0x7F, 0x7B, 0x5B, 0x6C, 0x50, 0x7D, 0x4D, 0x5D, 0x5C, 0x4E, 0x6B, 0x60, 0x4B, 0x61,
|
|---|
| 171 | 0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0xF7, 0xF8, 0xF9, 0x7A, 0x5E, 0x4C, 0x7E, 0x6E, 0x6F,
|
|---|
| 172 | 0x7C, 0xC1, 0xC2, 0xC3, 0xC4, 0xC5, 0xC6, 0xC7, 0xC8, 0xC9, 0xD1, 0xD2, 0xD3, 0xD4, 0xD5, 0xD6,
|
|---|
| 173 | 0xD7, 0xD8, 0xD9, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7, 0xE8, 0xE9, 0xBA, 0xE0, 0xBB, 0xB0, 0x6D,
|
|---|
| 174 | 0x79, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88, 0x89, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96,
|
|---|
| 175 | 0x97, 0x98, 0x99, 0xA2, 0xA3, 0xA4, 0xA5, 0xA6, 0xA7, 0xA8, 0xA9, 0xC0, 0x4F, 0xD0, 0xA1, 0x07,
|
|---|
| 176 | 0x20, 0x21, 0x22, 0x23, 0x24, 0x15, 0x06, 0x17, 0x28, 0x29, 0x2A, 0x2B, 0x2C, 0x09, 0x0A, 0x1B,
|
|---|
| 177 | 0x30, 0x31, 0x1A, 0x33, 0x34, 0x35, 0x36, 0x08, 0x38, 0x39, 0x3A, 0x3B, 0x04, 0x14, 0x3E, 0xFF,
|
|---|
| 178 | 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48, 0x49, 0x4A, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56,
|
|---|
| 179 | 0x57, 0x58, 0x59, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0x6A, 0x70, 0x71, 0x72, 0x73,
|
|---|
| 180 | 0x74, 0x75, 0x76, 0x77, 0x78, 0x80, 0x8A, 0x8B, 0x8C, 0x8D, 0x8E, 0x8F, 0x90, 0x9A, 0x9B, 0x9C,
|
|---|
| 181 | 0x9D, 0x9E, 0x9F, 0xA0, 0xAA, 0xAB, 0xAC, 0xAE, 0xAF, 0x5F, 0xB1, 0xB2, 0xB3, 0xB4, 0xB5, 0xB6,
|
|---|
| 182 | 0xB7, 0xB8, 0xB9, 0xAD, 0xBD, 0xBC, 0xBE, 0xBF, 0xCA, 0xCB, 0xCC, 0xCD, 0xCE, 0xCF, 0xDA, 0xDB,
|
|---|
| 183 | 0xDC, 0xDD, 0xDE, 0xDF, 0xE1, 0xEA, 0xEB, 0xEC, 0xED, 0xEE, 0xEF, 0xFA, 0xFB, 0xFC, 0xFD, 0xFE,
|
|---|
| 184 | };
|
|---|
| 185 |
|
|---|
| 186 | unsigned char PL_e2utf[] = { /* EBCDIC (IBM-037) to UTF-8-mod */
|
|---|
| 187 | 0x00, 0x01, 0x02, 0x03, 0x9C, 0x09, 0x86, 0x7F, 0x97, 0x8D, 0x8E, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
|
|---|
| 188 | 0x10, 0x11, 0x12, 0x13, 0x9D, 0x85, 0x08, 0x87, 0x18, 0x19, 0x92, 0x8F, 0x1C, 0x1D, 0x1E, 0x1F,
|
|---|
| 189 | 0x80, 0x81, 0x82, 0x83, 0x84, 0x0A, 0x17, 0x1B, 0x88, 0x89, 0x8A, 0x8B, 0x8C, 0x05, 0x06, 0x07,
|
|---|
| 190 | 0x90, 0x91, 0x16, 0x93, 0x94, 0x95, 0x96, 0x04, 0x98, 0x99, 0x9A, 0x9B, 0x14, 0x15, 0x9E, 0x1A,
|
|---|
| 191 | 0x20, 0xA0, 0xA1, 0xA2, 0xA3, 0xA4, 0xA5, 0xA6, 0xA7, 0xA8, 0xA9, 0x2E, 0x3C, 0x28, 0x2B, 0x7C,
|
|---|
| 192 | 0x26, 0xAA, 0xAB, 0xAC, 0xAD, 0xAE, 0xAF, 0xB0, 0xB1, 0xB2, 0x21, 0x24, 0x2A, 0x29, 0x3B, 0xD9,
|
|---|
| 193 | 0x2D, 0x2F, 0xB3, 0xB4, 0xB5, 0xB6, 0xB7, 0xB8, 0xB9, 0xBA, 0xBB, 0x2C, 0x25, 0x5F, 0x3E, 0x3F,
|
|---|
| 194 | 0xBC, 0xBD, 0xBE, 0xBF, 0xC0, 0xC1, 0xC2, 0xC3, 0xC4, 0x60, 0x3A, 0x23, 0x40, 0x27, 0x3D, 0x22,
|
|---|
| 195 | 0xC5, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0xC6, 0xC7, 0xC8, 0xC9, 0xCA, 0xCB,
|
|---|
| 196 | 0xCC, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F, 0x70, 0x71, 0x72, 0xCD, 0xCE, 0xCF, 0xD0, 0xD1, 0xD2,
|
|---|
| 197 | 0xD3, 0x7E, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, 0x79, 0x7A, 0xD4, 0xD5, 0xD6, 0xE3, 0xD7, 0xD8,
|
|---|
| 198 | 0x5E, 0xDA, 0xDB, 0xDC, 0xDD, 0xDE, 0xDF, 0xE0, 0xE1, 0xE2, 0x5B, 0x5D, 0xE5, 0xE4, 0xE6, 0xE7,
|
|---|
| 199 | 0x7B, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48, 0x49, 0xE8, 0xE9, 0xEA, 0xEB, 0xEC, 0xED,
|
|---|
| 200 | 0x7D, 0x4A, 0x4B, 0x4C, 0x4D, 0x4E, 0x4F, 0x50, 0x51, 0x52, 0xEE, 0xEF, 0xF0, 0xF1, 0xF2, 0xF3,
|
|---|
| 201 | 0x5C, 0xF4, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58, 0x59, 0x5A, 0xF5, 0xF6, 0xF7, 0xF8, 0xF9, 0xFA,
|
|---|
| 202 | 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38, 0x39, 0xFB, 0xFC, 0xFD, 0xFE, 0xFF, 0x9F,
|
|---|
| 203 | };
|
|---|
| 204 | #endif /* 037 */
|
|---|
| 205 |
|
|---|
| 206 | /* These tables moved from perl.h and converted to hex.
|
|---|
| 207 | They map platfrom code page from/to bottom 256 codes of Unicode (i.e. iso-8859-1).
|
|---|
| 208 | */
|
|---|
| 209 |
|
|---|
| 210 | #if '^' == 95 /* if defined(__MVS__) || defined(??) (VM/ESA?) 1047 */
|
|---|
| 211 | EXTCONST unsigned char PL_a2e[] = { /* ASCII (iso-8859-1) to EBCDIC (IBM-1047) */
|
|---|
| 212 | 0x00, 0x01, 0x02, 0x03, 0x37, 0x2D, 0x2E, 0x2F, 0x16, 0x05, 0x15, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
|
|---|
| 213 | 0x10, 0x11, 0x12, 0x13, 0x3C, 0x3D, 0x32, 0x26, 0x18, 0x19, 0x3F, 0x27, 0x1C, 0x1D, 0x1E, 0x1F,
|
|---|
| 214 | 0x40, 0x5A, 0x7F, 0x7B, 0x5B, 0x6C, 0x50, 0x7D, 0x4D, 0x5D, 0x5C, 0x4E, 0x6B, 0x60, 0x4B, 0x61,
|
|---|
| 215 | 0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0xF7, 0xF8, 0xF9, 0x7A, 0x5E, 0x4C, 0x7E, 0x6E, 0x6F,
|
|---|
| 216 | 0x7C, 0xC1, 0xC2, 0xC3, 0xC4, 0xC5, 0xC6, 0xC7, 0xC8, 0xC9, 0xD1, 0xD2, 0xD3, 0xD4, 0xD5, 0xD6,
|
|---|
| 217 | 0xD7, 0xD8, 0xD9, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7, 0xE8, 0xE9, 0xAD, 0xE0, 0xBD, 0x5F, 0x6D,
|
|---|
| 218 | 0x79, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88, 0x89, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96,
|
|---|
| 219 | 0x97, 0x98, 0x99, 0xA2, 0xA3, 0xA4, 0xA5, 0xA6, 0xA7, 0xA8, 0xA9, 0xC0, 0x4F, 0xD0, 0xA1, 0x07,
|
|---|
| 220 | 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x06, 0x17, 0x28, 0x29, 0x2A, 0x2B, 0x2C, 0x09, 0x0A, 0x1B,
|
|---|
| 221 | 0x30, 0x31, 0x1A, 0x33, 0x34, 0x35, 0x36, 0x08, 0x38, 0x39, 0x3A, 0x3B, 0x04, 0x14, 0x3E, 0xFF,
|
|---|
| 222 | 0x41, 0xAA, 0x4A, 0xB1, 0x9F, 0xB2, 0x6A, 0xB5, 0xBB, 0xB4, 0x9A, 0x8A, 0xB0, 0xCA, 0xAF, 0xBC,
|
|---|
| 223 | 0x90, 0x8F, 0xEA, 0xFA, 0xBE, 0xA0, 0xB6, 0xB3, 0x9D, 0xDA, 0x9B, 0x8B, 0xB7, 0xB8, 0xB9, 0xAB,
|
|---|
| 224 | 0x64, 0x65, 0x62, 0x66, 0x63, 0x67, 0x9E, 0x68, 0x74, 0x71, 0x72, 0x73, 0x78, 0x75, 0x76, 0x77,
|
|---|
| 225 | 0xAC, 0x69, 0xED, 0xEE, 0xEB, 0xEF, 0xEC, 0xBF, 0x80, 0xFD, 0xFE, 0xFB, 0xFC, 0xBA, 0xAE, 0x59,
|
|---|
| 226 | 0x44, 0x45, 0x42, 0x46, 0x43, 0x47, 0x9C, 0x48, 0x54, 0x51, 0x52, 0x53, 0x58, 0x55, 0x56, 0x57,
|
|---|
| 227 | 0x8C, 0x49, 0xCD, 0xCE, 0xCB, 0xCF, 0xCC, 0xE1, 0x70, 0xDD, 0xDE, 0xDB, 0xDC, 0x8D, 0x8E, 0xDF
|
|---|
| 228 | };
|
|---|
| 229 |
|
|---|
| 230 | EXTCONST unsigned char PL_e2a[] = { /* EBCDIC (IBM-1047) to ASCII (iso-8859-1) */
|
|---|
| 231 | 0x00, 0x01, 0x02, 0x03, 0x9C, 0x09, 0x86, 0x7F, 0x97, 0x8D, 0x8E, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
|
|---|
| 232 | 0x10, 0x11, 0x12, 0x13, 0x9D, 0x0A, 0x08, 0x87, 0x18, 0x19, 0x92, 0x8F, 0x1C, 0x1D, 0x1E, 0x1F,
|
|---|
| 233 | 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x17, 0x1B, 0x88, 0x89, 0x8A, 0x8B, 0x8C, 0x05, 0x06, 0x07,
|
|---|
| 234 | 0x90, 0x91, 0x16, 0x93, 0x94, 0x95, 0x96, 0x04, 0x98, 0x99, 0x9A, 0x9B, 0x14, 0x15, 0x9E, 0x1A,
|
|---|
| 235 | 0x20, 0xA0, 0xE2, 0xE4, 0xE0, 0xE1, 0xE3, 0xE5, 0xE7, 0xF1, 0xA2, 0x2E, 0x3C, 0x28, 0x2B, 0x7C,
|
|---|
| 236 | 0x26, 0xE9, 0xEA, 0xEB, 0xE8, 0xED, 0xEE, 0xEF, 0xEC, 0xDF, 0x21, 0x24, 0x2A, 0x29, 0x3B, 0x5E,
|
|---|
| 237 | 0x2D, 0x2F, 0xC2, 0xC4, 0xC0, 0xC1, 0xC3, 0xC5, 0xC7, 0xD1, 0xA6, 0x2C, 0x25, 0x5F, 0x3E, 0x3F,
|
|---|
| 238 | 0xF8, 0xC9, 0xCA, 0xCB, 0xC8, 0xCD, 0xCE, 0xCF, 0xCC, 0x60, 0x3A, 0x23, 0x40, 0x27, 0x3D, 0x22,
|
|---|
| 239 | 0xD8, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0xAB, 0xBB, 0xF0, 0xFD, 0xFE, 0xB1,
|
|---|
| 240 | 0xB0, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F, 0x70, 0x71, 0x72, 0xAA, 0xBA, 0xE6, 0xB8, 0xC6, 0xA4,
|
|---|
| 241 | 0xB5, 0x7E, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, 0x79, 0x7A, 0xA1, 0xBF, 0xD0, 0x5B, 0xDE, 0xAE,
|
|---|
| 242 | 0xAC, 0xA3, 0xA5, 0xB7, 0xA9, 0xA7, 0xB6, 0xBC, 0xBD, 0xBE, 0xDD, 0xA8, 0xAF, 0x5D, 0xB4, 0xD7,
|
|---|
| 243 | 0x7B, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48, 0x49, 0xAD, 0xF4, 0xF6, 0xF2, 0xF3, 0xF5,
|
|---|
| 244 | 0x7D, 0x4A, 0x4B, 0x4C, 0x4D, 0x4E, 0x4F, 0x50, 0x51, 0x52, 0xB9, 0xFB, 0xFC, 0xF9, 0xFA, 0xFF,
|
|---|
| 245 | 0x5C, 0xF7, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58, 0x59, 0x5A, 0xB2, 0xD4, 0xD6, 0xD2, 0xD3, 0xD5,
|
|---|
| 246 | 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38, 0x39, 0xB3, 0xDB, 0xDC, 0xD9, 0xDA, 0x9F
|
|---|
| 247 | };
|
|---|
| 248 | #endif /* 1047 */
|
|---|
| 249 |
|
|---|
| 250 | #if '^' == 106 /* if defined(_OSD_POSIX) POSIX-BC */
|
|---|
| 251 | EXTCONST unsigned char PL_a2e[] = { /* ASCII (ISO8859-1) to EBCDIC (POSIX-BC) */
|
|---|
| 252 | 0x00, 0x01, 0x02, 0x03, 0x37, 0x2D, 0x2E, 0x2F, 0x16, 0x05, 0x15, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
|
|---|
| 253 | 0x10, 0x11, 0x12, 0x13, 0x3C, 0x3D, 0x32, 0x26, 0x18, 0x19, 0x3F, 0x27, 0x1C, 0x1D, 0x1E, 0x1F,
|
|---|
| 254 | 0x40, 0x5A, 0x7F, 0x7B, 0x5B, 0x6C, 0x50, 0x7D, 0x4D, 0x5D, 0x5C, 0x4E, 0x6B, 0x60, 0x4B, 0x61,
|
|---|
| 255 | 0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0xF7, 0xF8, 0xF9, 0x7A, 0x5E, 0x4C, 0x7E, 0x6E, 0x6F,
|
|---|
| 256 | 0x7C, 0xC1, 0xC2, 0xC3, 0xC4, 0xC5, 0xC6, 0xC7, 0xC8, 0xC9, 0xD1, 0xD2, 0xD3, 0xD4, 0xD5, 0xD6,
|
|---|
| 257 | 0xD7, 0xD8, 0xD9, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7, 0xE8, 0xE9, 0xBB, 0xBC, 0xBD, 0x6A, 0x6D,
|
|---|
| 258 | 0x4A, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88, 0x89, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96,
|
|---|
| 259 | 0x97, 0x98, 0x99, 0xA2, 0xA3, 0xA4, 0xA5, 0xA6, 0xA7, 0xA8, 0xA9, 0xFB, 0x4F, 0xFD, 0xFF, 0x07,
|
|---|
| 260 | 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x06, 0x17, 0x28, 0x29, 0x2A, 0x2B, 0x2C, 0x09, 0x0A, 0x1B,
|
|---|
| 261 | 0x30, 0x31, 0x1A, 0x33, 0x34, 0x35, 0x36, 0x08, 0x38, 0x39, 0x3A, 0x3B, 0x04, 0x14, 0x3E, 0x5F,
|
|---|
| 262 | 0x41, 0xAA, 0xB0, 0xB1, 0x9F, 0xB2, 0xD0, 0xB5, 0x79, 0xB4, 0x9A, 0x8A, 0xBA, 0xCA, 0xAF, 0xA1,
|
|---|
| 263 | 0x90, 0x8F, 0xEA, 0xFA, 0xBE, 0xA0, 0xB6, 0xB3, 0x9D, 0xDA, 0x9B, 0x8B, 0xB7, 0xB8, 0xB9, 0xAB,
|
|---|
| 264 | 0x64, 0x65, 0x62, 0x66, 0x63, 0x67, 0x9E, 0x68, 0x74, 0x71, 0x72, 0x73, 0x78, 0x75, 0x76, 0x77,
|
|---|
| 265 | 0xAC, 0x69, 0xED, 0xEE, 0xEB, 0xEF, 0xEC, 0xBF, 0x80, 0xE0, 0xFE, 0xDD, 0xFC, 0xAD, 0xAE, 0x59,
|
|---|
| 266 | 0x44, 0x45, 0x42, 0x46, 0x43, 0x47, 0x9C, 0x48, 0x54, 0x51, 0x52, 0x53, 0x58, 0x55, 0x56, 0x57,
|
|---|
| 267 | 0x8C, 0x49, 0xCD, 0xCE, 0xCB, 0xCF, 0xCC, 0xE1, 0x70, 0xC0, 0xDE, 0xDB, 0xDC, 0x8D, 0x8E, 0xDF
|
|---|
| 268 | };
|
|---|
| 269 |
|
|---|
| 270 | EXTCONST unsigned char PL_e2a[] = { /* EBCDIC (POSIX-BC) to ASCII (ISO8859-1) */
|
|---|
| 271 | 0x00, 0x01, 0x02, 0x03, 0x9C, 0x09, 0x86, 0x7F, 0x97, 0x8D, 0x8E, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
|
|---|
| 272 | 0x10, 0x11, 0x12, 0x13, 0x9D, 0x0A, 0x08, 0x87, 0x18, 0x19, 0x92, 0x8F, 0x1C, 0x1D, 0x1E, 0x1F,
|
|---|
| 273 | 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x17, 0x1B, 0x88, 0x89, 0x8A, 0x8B, 0x8C, 0x05, 0x06, 0x07,
|
|---|
| 274 | 0x90, 0x91, 0x16, 0x93, 0x94, 0x95, 0x96, 0x04, 0x98, 0x99, 0x9A, 0x9B, 0x14, 0x15, 0x9E, 0x1A,
|
|---|
| 275 | 0x20, 0xA0, 0xE2, 0xE4, 0xE0, 0xE1, 0xE3, 0xE5, 0xE7, 0xF1, 0x60, 0x2E, 0x3C, 0x28, 0x2B, 0x7C,
|
|---|
| 276 | 0x26, 0xE9, 0xEA, 0xEB, 0xE8, 0xED, 0xEE, 0xEF, 0xEC, 0xDF, 0x21, 0x24, 0x2A, 0x29, 0x3B, 0x9F,
|
|---|
| 277 | 0x2D, 0x2F, 0xC2, 0xC4, 0xC0, 0xC1, 0xC3, 0xC5, 0xC7, 0xD1, 0x5E, 0x2C, 0x25, 0x5F, 0x3E, 0x3F,
|
|---|
| 278 | 0xF8, 0xC9, 0xCA, 0xCB, 0xC8, 0xCD, 0xCE, 0xCF, 0xCC, 0xA8, 0x3A, 0x23, 0x40, 0x27, 0x3D, 0x22,
|
|---|
| 279 | 0xD8, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0xAB, 0xBB, 0xF0, 0xFD, 0xFE, 0xB1,
|
|---|
| 280 | 0xB0, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F, 0x70, 0x71, 0x72, 0xAA, 0xBA, 0xE6, 0xB8, 0xC6, 0xA4,
|
|---|
| 281 | 0xB5, 0xAF, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, 0x79, 0x7A, 0xA1, 0xBF, 0xD0, 0xDD, 0xDE, 0xAE,
|
|---|
| 282 | 0xA2, 0xA3, 0xA5, 0xB7, 0xA9, 0xA7, 0xB6, 0xBC, 0xBD, 0xBE, 0xAC, 0x5B, 0x5C, 0x5D, 0xB4, 0xD7,
|
|---|
| 283 | 0xF9, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48, 0x49, 0xAD, 0xF4, 0xF6, 0xF2, 0xF3, 0xF5,
|
|---|
| 284 | 0xA6, 0x4A, 0x4B, 0x4C, 0x4D, 0x4E, 0x4F, 0x50, 0x51, 0x52, 0xB9, 0xFB, 0xFC, 0xDB, 0xFA, 0xFF,
|
|---|
| 285 | 0xD9, 0xF7, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58, 0x59, 0x5A, 0xB2, 0xD4, 0xD6, 0xD2, 0xD3, 0xD5,
|
|---|
| 286 | 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38, 0x39, 0xB3, 0x7B, 0xDC, 0x7D, 0xDA, 0x7E
|
|---|
| 287 | };
|
|---|
| 288 | #endif /* POSIX-BC */
|
|---|
| 289 |
|
|---|
| 290 | #if '^' == 176 /* if defined(??) (OS/400?) 037 */
|
|---|
| 291 | EXTCONST unsigned char PL_a2e[] = { /* ASCII (ISO8859-1) to EBCDIC (IBM-037) */
|
|---|
| 292 | 0x00, 0x01, 0x02, 0x03, 0x37, 0x2D, 0x2E, 0x2F, 0x16, 0x05, 0x25, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
|
|---|
| 293 | 0x10, 0x11, 0x12, 0x13, 0x3C, 0x3D, 0x32, 0x26, 0x18, 0x19, 0x3F, 0x27, 0x1C, 0x1D, 0x1E, 0x1F,
|
|---|
| 294 | 0x40, 0x5A, 0x7F, 0x7B, 0x5B, 0x6C, 0x50, 0x7D, 0x4D, 0x5D, 0x5C, 0x4E, 0x6B, 0x60, 0x4B, 0x61,
|
|---|
| 295 | 0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0xF7, 0xF8, 0xF9, 0x7A, 0x5E, 0x4C, 0x7E, 0x6E, 0x6F,
|
|---|
| 296 | 0x7C, 0xC1, 0xC2, 0xC3, 0xC4, 0xC5, 0xC6, 0xC7, 0xC8, 0xC9, 0xD1, 0xD2, 0xD3, 0xD4, 0xD5, 0xD6,
|
|---|
| 297 | 0xD7, 0xD8, 0xD9, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7, 0xE8, 0xE9, 0xBA, 0xE0, 0xBB, 0xB0, 0x6D,
|
|---|
| 298 | 0x79, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88, 0x89, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96,
|
|---|
| 299 | 0x97, 0x98, 0x99, 0xA2, 0xA3, 0xA4, 0xA5, 0xA6, 0xA7, 0xA8, 0xA9, 0xC0, 0x4F, 0xD0, 0xA1, 0x07,
|
|---|
| 300 | 0x20, 0x21, 0x22, 0x23, 0x24, 0x15, 0x06, 0x17, 0x28, 0x29, 0x2A, 0x2B, 0x2C, 0x09, 0x0A, 0x1B,
|
|---|
| 301 | 0x30, 0x31, 0x1A, 0x33, 0x34, 0x35, 0x36, 0x08, 0x38, 0x39, 0x3A, 0x3B, 0x04, 0x14, 0x3E, 0xFF,
|
|---|
| 302 | 0x41, 0xAA, 0x4A, 0xB1, 0x9F, 0xB2, 0x6A, 0xB5, 0xBD, 0xB4, 0x9A, 0x8A, 0x5F, 0xCA, 0xAF, 0xBC,
|
|---|
| 303 | 0x90, 0x8F, 0xEA, 0xFA, 0xBE, 0xA0, 0xB6, 0xB3, 0x9D, 0xDA, 0x9B, 0x8B, 0xB7, 0xB8, 0xB9, 0xAB,
|
|---|
| 304 | 0x64, 0x65, 0x62, 0x66, 0x63, 0x67, 0x9E, 0x68, 0x74, 0x71, 0x72, 0x73, 0x78, 0x75, 0x76, 0x77,
|
|---|
| 305 | 0xAC, 0x69, 0xED, 0xEE, 0xEB, 0xEF, 0xEC, 0xBF, 0x80, 0xFD, 0xFE, 0xFB, 0xFC, 0xAD, 0xAE, 0x59,
|
|---|
| 306 | 0x44, 0x45, 0x42, 0x46, 0x43, 0x47, 0x9C, 0x48, 0x54, 0x51, 0x52, 0x53, 0x58, 0x55, 0x56, 0x57,
|
|---|
| 307 | 0x8C, 0x49, 0xCD, 0xCE, 0xCB, 0xCF, 0xCC, 0xE1, 0x70, 0xDD, 0xDE, 0xDB, 0xDC, 0x8D, 0x8E, 0xDF
|
|---|
| 308 | };
|
|---|
| 309 |
|
|---|
| 310 | EXTCONST unsigned char PL_e2a[] = { /* EBCDIC (IBM-037) to ASCII (ISO8859-1) */
|
|---|
| 311 | 0x00, 0x01, 0x02, 0x03, 0x9C, 0x09, 0x86, 0x7F, 0x97, 0x8D, 0x8E, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
|
|---|
| 312 | 0x10, 0x11, 0x12, 0x13, 0x9D, 0x85, 0x08, 0x87, 0x18, 0x19, 0x92, 0x8F, 0x1C, 0x1D, 0x1E, 0x1F,
|
|---|
| 313 | 0x80, 0x81, 0x82, 0x83, 0x84, 0x0A, 0x17, 0x1B, 0x88, 0x89, 0x8A, 0x8B, 0x8C, 0x05, 0x06, 0x07,
|
|---|
| 314 | 0x90, 0x91, 0x16, 0x93, 0x94, 0x95, 0x96, 0x04, 0x98, 0x99, 0x9A, 0x9B, 0x14, 0x15, 0x9E, 0x1A,
|
|---|
| 315 | 0x20, 0xA0, 0xE2, 0xE4, 0xE0, 0xE1, 0xE3, 0xE5, 0xE7, 0xF1, 0xA2, 0x2E, 0x3C, 0x28, 0x2B, 0x7C,
|
|---|
| 316 | 0x26, 0xE9, 0xEA, 0xEB, 0xE8, 0xED, 0xEE, 0xEF, 0xEC, 0xDF, 0x21, 0x24, 0x2A, 0x29, 0x3B, 0xAC,
|
|---|
| 317 | 0x2D, 0x2F, 0xC2, 0xC4, 0xC0, 0xC1, 0xC3, 0xC5, 0xC7, 0xD1, 0xA6, 0x2C, 0x25, 0x5F, 0x3E, 0x3F,
|
|---|
| 318 | 0xF8, 0xC9, 0xCA, 0xCB, 0xC8, 0xCD, 0xCE, 0xCF, 0xCC, 0x60, 0x3A, 0x23, 0x40, 0x27, 0x3D, 0x22,
|
|---|
| 319 | 0xD8, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0xAB, 0xBB, 0xF0, 0xFD, 0xFE, 0xB1,
|
|---|
| 320 | 0xB0, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F, 0x70, 0x71, 0x72, 0xAA, 0xBA, 0xE6, 0xB8, 0xC6, 0xA4,
|
|---|
| 321 | 0xB5, 0x7E, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, 0x79, 0x7A, 0xA1, 0xBF, 0xD0, 0xDD, 0xDE, 0xAE,
|
|---|
| 322 | 0x5E, 0xA3, 0xA5, 0xB7, 0xA9, 0xA7, 0xB6, 0xBC, 0xBD, 0xBE, 0x5B, 0x5D, 0xAF, 0xA8, 0xB4, 0xD7,
|
|---|
| 323 | 0x7B, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48, 0x49, 0xAD, 0xF4, 0xF6, 0xF2, 0xF3, 0xF5,
|
|---|
| 324 | 0x7D, 0x4A, 0x4B, 0x4C, 0x4D, 0x4E, 0x4F, 0x50, 0x51, 0x52, 0xB9, 0xFB, 0xFC, 0xF9, 0xFA, 0xFF,
|
|---|
| 325 | 0x5C, 0xF7, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58, 0x59, 0x5A, 0xB2, 0xD4, 0xD6, 0xD2, 0xD3, 0xD5,
|
|---|
| 326 | 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38, 0x39, 0xB3, 0xDB, 0xDC, 0xD9, 0xDA, 0x9F
|
|---|
| 327 | };
|
|---|
| 328 | #endif /* 037 */
|
|---|
| 329 |
|
|---|
| 330 | #else
|
|---|
| 331 | EXTCONST unsigned char PL_utf8skip[];
|
|---|
| 332 | EXTCONST unsigned char PL_e2utf[];
|
|---|
| 333 | EXTCONST unsigned char PL_utf2e[];
|
|---|
| 334 | EXTCONST unsigned char PL_e2a[];
|
|---|
| 335 | EXTCONST unsigned char PL_a2e[];
|
|---|
| 336 | #endif
|
|---|
| 337 |
|
|---|
| 338 | END_EXTERN_C
|
|---|
| 339 |
|
|---|
| 340 | #define UTF8SKIP(s) PL_utf8skip[*(const U8*)s]
|
|---|
| 341 |
|
|---|
| 342 | /* EBCDIC-happy ways of converting native code to UTF-8 */
|
|---|
| 343 |
|
|---|
| 344 | /* Native to iso-8859-1 */
|
|---|
| 345 | #define NATIVE_TO_ASCII(ch) PL_e2a[(U8)(ch)]
|
|---|
| 346 | #define ASCII_TO_NATIVE(ch) PL_a2e[(U8)(ch)]
|
|---|
| 347 | /* Transform after encoding */
|
|---|
| 348 | #define NATIVE_TO_UTF(ch) PL_e2utf[(U8)(ch)]
|
|---|
| 349 | #define UTF_TO_NATIVE(ch) PL_utf2e[(U8)(ch)]
|
|---|
| 350 | /* Transform in wide UV char space */
|
|---|
| 351 | #define NATIVE_TO_UNI(ch) (((ch) > 255) ? (ch) : NATIVE_TO_ASCII(ch))
|
|---|
| 352 | #define UNI_TO_NATIVE(ch) (((ch) > 255) ? (ch) : ASCII_TO_NATIVE(ch))
|
|---|
| 353 | /* Transform in invariant..byte space */
|
|---|
| 354 | #define NATIVE_TO_NEED(enc,ch) ((enc) ? UTF_TO_NATIVE(NATIVE_TO_ASCII(ch)) : (ch))
|
|---|
| 355 | #define ASCII_TO_NEED(enc,ch) ((enc) ? UTF_TO_NATIVE(ch) : ASCII_TO_NATIVE(ch))
|
|---|
| 356 |
|
|---|
| 357 | /*
|
|---|
| 358 | * Note: we should try and be careful never to call the isXXX_utf8() functions
|
|---|
| 359 | * unless we're pretty sure we've seen the beginning of a UTF-EBCDIC character
|
|---|
| 360 | * Otherwise we risk loading in the heavy-duty SWASHINIT and SWASHGET routines
|
|---|
| 361 | * unnecessarily.
|
|---|
| 362 | */
|
|---|
| 363 |
|
|---|
| 364 | #define isIDFIRST_lazy_if(p,c) ((IN_BYTES || (!c || UTF8_IS_INVARIANT(*p))) \
|
|---|
| 365 | ? isIDFIRST(*(p)) \
|
|---|
| 366 | : isIDFIRST_utf8((const U8*)p))
|
|---|
| 367 | #define isALNUM_lazy_if(p,c) ((IN_BYTES || (!c || UTF8_IS_INVARIANT(*p))) \
|
|---|
| 368 | ? isALNUM(*(p)) \
|
|---|
| 369 | : isALNUM_utf8((const U8*)p))
|
|---|
| 370 |
|
|---|
| 371 | /*
|
|---|
| 372 | The following table is adapted from tr16, it shows UTF-8-mod encoding of Unicode code points.
|
|---|
| 373 |
|
|---|
| 374 | Unicode Bit pattern 1st Byte 2nd Byte 3rd Byte 4th Byte 5th Byte 6th Byte 7th byte
|
|---|
| 375 | U+0000..U+007F 000000000xxxxxxx 0xxxxxxx
|
|---|
| 376 | U+0080..U+009F 00000000100xxxxx 100xxxxx
|
|---|
| 377 | U+00A0..U+00FF 00000000yyyxxxxx 11000yyy 101xxxxx
|
|---|
| 378 |
|
|---|
| 379 | U+00A0..U+03FF 000000yyyyyxxxxx 110yyyyy 101xxxxx
|
|---|
| 380 | U+0400..U+3FFF 00zzzzyyyyyxxxxx 1110zzzz 101yyyyy 101xxxxx
|
|---|
| 381 | U+4000..U+3FFFF 0wwwzzzzzyyyyyxxxxx 11110www 101zzzzz 101yyyyy 101xxxxx
|
|---|
| 382 | U+40000..U+3FFFFF 0vvwwwwwzzzzzyyyyyxxxxx 111110vv 101wwwww 101zzzzz 101yyyyy 101xxxxx
|
|---|
| 383 | U+400000..U+3FFFFFF 0uvvvvvwwwwwzzzzzyyyyyxxxxx 1111110u 101vvvvv 101wwwww 101zzzzz 101yyyyy 101xxxxx
|
|---|
| 384 | U+4000000..U+7FFFFFFF 0tuuuuuvvvvvwwwwwzzzzzyyyyyxxxxx 1111111t 101uuuuu 101vvvvv 101wwwww 101zzzzz 101yyyyy 101xxxxx
|
|---|
| 385 |
|
|---|
| 386 | Note: The UTF-8-Mod transformation is valid for UCS-4 values X'0' to
|
|---|
| 387 | X'7FFFFFFF' (the full extent of ISO/IEC 10646 coding space).
|
|---|
| 388 |
|
|---|
| 389 | */
|
|---|
| 390 |
|
|---|
| 391 | #define UNISKIP(uv) ( (uv) < 0xA0 ? 1 : \
|
|---|
| 392 | (uv) < 0x400 ? 2 : \
|
|---|
| 393 | (uv) < 0x4000 ? 3 : \
|
|---|
| 394 | (uv) < 0x40000 ? 4 : \
|
|---|
| 395 | (uv) < 0x400000 ? 5 : \
|
|---|
| 396 | (uv) < 0x4000000 ? 6 : 7 )
|
|---|
| 397 |
|
|---|
| 398 |
|
|---|
| 399 | #define UNI_IS_INVARIANT(c) ((c) < 0xA0)
|
|---|
| 400 | /* UTF-EBCDIC sematic macros - transform back into UTF-8-Mod and then compare */
|
|---|
| 401 | #define NATIVE_IS_INVARIANT(c) UNI_IS_INVARIANT(NATIVE_TO_ASCII(c))
|
|---|
| 402 | #define UTF8_IS_INVARIANT(c) UNI_IS_INVARIANT(NATIVE_TO_UTF(c))
|
|---|
| 403 | #define UTF8_IS_START(c) (NATIVE_TO_UTF(c) >= 0xA0 && (NATIVE_TO_UTF(c) & 0xE0) != 0xA0)
|
|---|
| 404 | #define UTF8_IS_CONTINUATION(c) ((NATIVE_TO_UTF(c) & 0xE0) == 0xA0)
|
|---|
| 405 | #define UTF8_IS_CONTINUED(c) (NATIVE_TO_UTF(c) >= 0xA0)
|
|---|
| 406 | #define UTF8_IS_DOWNGRADEABLE_START(c) (NATIVE_TO_UTF(c) >= 0xA0 && (NATIVE_TO_UTF(c) & 0xF8) == 0xC0)
|
|---|
| 407 |
|
|---|
| 408 | #define UTF_START_MARK(len) ((len > 7) ? 0xFF : (0xFE << (7-len)))
|
|---|
| 409 | #define UTF_START_MASK(len) ((len >= 6) ? 0x01 : (0x1F >> (len-2)))
|
|---|
| 410 | #define UTF_CONTINUATION_MARK 0xA0
|
|---|
| 411 | #define UTF_CONTINUATION_MASK ((U8)0x1f)
|
|---|
| 412 | #define UTF_ACCUMULATION_SHIFT 5
|
|---|
| 413 |
|
|---|
| 414 | #define UTF8_ACCUMULATE(old, new) (((old) << UTF_ACCUMULATION_SHIFT)|(NATIVE_TO_UTF(new) & UTF_CONTINUATION_MASK))
|
|---|
| 415 |
|
|---|
| 416 | /* UTF-EBCDIC encode a downgradeable value */
|
|---|
| 417 | #define UTF8_EIGHT_BIT_HI(c) UTF_TO_NATIVE((((U8)(c))>>UTF_ACCUMULATION_SHIFT)|UTF_START_MARK(2))
|
|---|
| 418 | #define UTF8_EIGHT_BIT_LO(c) UTF_TO_NATIVE(((((U8)(c)))&UTF_CONTINUATION_MASK)|UTF_CONTINUATION_MARK)
|
|---|
| 419 |
|
|---|
| 420 |
|
|---|