Update comments and documentation dealing with utf
[p5sagit/p5-mst-13.2.git] / utfebcdic.h
CommitLineData
1d72bdf6 1/* utfebcdic.h
2 *
663f364b 3 * Copyright (C) 2001, 2002, 2003, 2005, 2006, 2007, by Larry Wall, Nick
699a97de 4 * Ing-Simmons, and others
1d72bdf6 5 *
6 * You may distribute under the terms of either the GNU General Public
7 * License or the Artistic License, as specified in the README file.
8 *
9 * Macros to implement UTF-EBCDIC as perl's internal encoding
10 * Taken from version 7.1 of Unicode Techical Report #16:
11 * http://www.unicode.org/unicode/reports/tr16
fe749c9a 12 *
13 * To summarize, the way it works is:
14 * To convert an EBCDIC character to UTF-EBCDIC:
15 * 1) convert to Unicode. The table in this file that does this is for
16 * EBCDIC bytes is PL_e2a (with inverse PLa2e). The 'a' stands for
17 * ASCIIish, meaning latin1.
18 * 2) convert that to a utf8-like string called I8 with variant characters
19 * occupying multiple bytes. This step is similar to the utf8-creating
20 * step from Unicode, but the details are different. There is a chart
21 * about the bit patterns in a comment later in this file. But
22 * essentially here are the differences:
23 * UTF8 I8
24 * invariant byte starts with 0 starts with 0 or 100
25 * continuation byte starts with 10 starts with 101
26 * start byte same in both: if the code point requires N bytes,
27 * then the leading N bits are 1, followed by a 0. (No
28 * trailing 0 for the very largest possible allocation
29 * in I8, far beyond the current Unicode standard's
30 * max, as shown in the comment later in this file.)
31 * 3) Use the table published in tr16 to convert each byte from step 2 into
32 * final UTF-EBCDIC. The table in this file is PL_utf2e, and its invverse
33 * is PL_e2utf. They are constructed so that all EBCDIC invariants remain
34 * invariant, but no others do. For example, the ordinal value of 'A' is
35 * 193 in EBCDIC, and also is 193 in UTF-EBCDIC. Step 1) converts it to
36 * 65, Step 2 leaves it at 65, and Step 3 converts it back to 193. As an
37 * example of how a variant character works, take LATIN SMALL LETTER Y
38 * WITH DIAERESIS, which is typicially 0xDF in EBCDIC. Step 1 converts it
39 * to the Unicode value, 0xFF. Step 2 converts that to two bytes =
40 * 11000111 10111111 = C7 BF, and Step 3 converts those to 0x47 0xE7
41 *
42 * If you're starting from Unicode, skip step 1. For UTF-EBCDIC to straight
43 * EBCDIC, reverse the steps.
44 *
45 * The EBCDIC invariants have been chosen to be those characters whose Unicode
46 * equivalents have ordinal numbers less than 160, that is the same characters
47 * that are expressible in ASCII, plus the C1 controls. So there are 160
48 * invariants instead of the 128 in UTF-8. (My guess is that this is because
49 * the C1 control NEL (and maybe others) is important in IBM.)
50 *
51 * The purpose of Step 3 is to make the encoding be invariant for the chosen
52 * characters. This messes up the convenient patterns found in step 2, so
53 * generally, one has to undo step 3 into a temporary to use them. However,
54 * a "shadow", or parallel table, PL_utf8skip, has been constructed so that for
55 * each byte, it says how long the sequence is if that byte were to begin it
56 *
57 * There are actually 3 slightly different UTF-EBCDIC encodings in this file,
58 * one for each of the code pages recognized by Perl. That means that there
59 * are actually three different sets of tables, one for each code page. (If
60 * Perl is compiled on platforms using other EBCDIC code pages, it may not
61 * compile, or silently mistake it for one of the three.)
62 *
63 * EBCDIC characters above 0xFF are the same as Unicode in Perl's
64 * implementation of all 3 encodings, so for those Step 1 is trivial.
65 *
66 * (Note that the entries for invariant characters are necessarily the same in
67 * PL_e2a and PLe2f, and the same for their inverses.)
68 *
69 * UTF-EBCDIC strings are the same length or longer than UTF-8 representations
70 * of the same string. The maximum code point representable as 2 bytes in
71 * UTF-EBCDIC is 0x3FFF, instead of 0x7FFF in UTF-8.
1d72bdf6 72 */
73
74START_EXTERN_C
75
76#ifdef DOINIT
77/* Indexed by encoded byte this table gives the length of the sequence.
78 Adapted from the shadow flags table in tr16.
c4d5f83a 79 The entries marked 9 in tr6 are continuation bytes and are marked
80 as length 1 here so that we can recover.
1d72bdf6 81*/
f5e1abaf 82#if '^' == 95 /* if defined(__MVS__) || defined(??) (VM/ESA?) 1047 */
1d72bdf6 83EXTCONST unsigned char PL_utf8skip[] = {
841,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
851,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
861,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
871,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
c4d5f83a 881,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
891,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
901,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
911,1,1,1,2,2,2,2,2,1,1,1,1,1,1,1,
1d72bdf6 922,1,1,1,1,1,1,1,1,1,2,2,2,2,2,2,
932,1,1,1,1,1,1,1,1,1,2,2,2,2,2,2,
942,1,1,1,1,1,1,1,1,1,2,2,2,1,2,2,
952,2,2,2,2,2,2,3,3,3,3,3,3,1,3,3,
961,1,1,1,1,1,1,1,1,1,3,3,3,3,3,3,
971,1,1,1,1,1,1,1,1,1,3,3,4,4,4,4,
981,4,1,1,1,1,1,1,1,1,4,4,4,5,5,5,
991,1,1,1,1,1,1,1,1,1,5,6,6,7,7,1
100};
f5e1abaf 101#endif
102
103#if '^' == 106 /* if defined(_OSD_POSIX) POSIX-BC */
104unsigned char PL_utf8skip[] = {
1051,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
1061,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
1071,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
1081,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
1091,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
1101,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
1111,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
1121,1,1,1,2,2,2,2,2,3,1,1,1,1,1,1,
1132,1,1,1,1,1,1,1,1,1,2,2,2,2,2,2,
1142,1,1,1,1,1,1,1,1,1,2,2,2,2,2,2,
1152,3,1,1,1,1,1,1,1,1,2,2,2,3,2,2,
1161,2,2,2,2,2,2,3,3,3,2,1,1,1,3,3,
1174,1,1,1,1,1,1,1,1,1,3,3,3,3,3,3,
1181,1,1,1,1,1,1,1,1,1,3,3,4,6,4,4,
1197,4,1,1,1,1,1,1,1,1,4,4,4,5,5,5,
1201,1,1,1,1,1,1,1,1,1,5,1,6,1,7,1
121};
122#endif
123
124#if '^' == 176 /* if defined(??) (OS/400?) 037 */
125unsigned char PL_utf8skip[] = {
1261,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
1271,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
1281,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
1291,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
1301,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
1311,1,1,1,1,1,1,1,1,1,1,1,1,1,1,2,
1321,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
1331,1,1,1,2,2,2,2,2,1,1,1,1,1,1,1,
1342,1,1,1,1,1,1,1,1,1,2,2,2,2,2,2,
1352,1,1,1,1,1,1,1,1,1,2,2,2,2,2,2,
1362,1,1,1,1,1,1,1,1,1,2,2,2,3,2,2,
1371,2,2,2,2,2,2,3,3,3,1,1,3,3,3,3,
1381,1,1,1,1,1,1,1,1,1,3,3,3,3,3,3,
1391,1,1,1,1,1,1,1,1,1,3,3,4,4,4,4,
1401,4,1,1,1,1,1,1,1,1,4,4,4,5,5,5,
1411,1,1,1,1,1,1,1,1,1,5,6,6,7,7,1
142};
143#endif
1d72bdf6 144
fe749c9a 145/* Transform tables from tr16 applied after encoding to render encoding EBCDIC
146 * like, meaning that all the invariants are actually invariant, eg, that 'A'
147 * remains 'A' */
1d72bdf6 148
f5e1abaf 149#if '^' == 95 /* if defined(__MVS__) || defined(??) (VM/ESA?) 1047 */
1d72bdf6 150EXTCONST unsigned char PL_utf2e[] = { /* UTF-8-mod to EBCDIC (IBM-1047) */
151 0x00, 0x01, 0x02, 0x03, 0x37, 0x2D, 0x2E, 0x2F, 0x16, 0x05, 0x15, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
152 0x10, 0x11, 0x12, 0x13, 0x3C, 0x3D, 0x32, 0x26, 0x18, 0x19, 0x3F, 0x27, 0x1C, 0x1D, 0x1E, 0x1F,
153 0x40, 0x5A, 0x7F, 0x7B, 0x5B, 0x6C, 0x50, 0x7D, 0x4D, 0x5D, 0x5C, 0x4E, 0x6B, 0x60, 0x4B, 0x61,
154 0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0xF7, 0xF8, 0xF9, 0x7A, 0x5E, 0x4C, 0x7E, 0x6E, 0x6F,
155 0x7C, 0xC1, 0xC2, 0xC3, 0xC4, 0xC5, 0xC6, 0xC7, 0xC8, 0xC9, 0xD1, 0xD2, 0xD3, 0xD4, 0xD5, 0xD6,
156 0xD7, 0xD8, 0xD9, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7, 0xE8, 0xE9, 0xAD, 0xE0, 0xBD, 0x5F, 0x6D,
157 0x79, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88, 0x89, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96,
158 0x97, 0x98, 0x99, 0xA2, 0xA3, 0xA4, 0xA5, 0xA6, 0xA7, 0xA8, 0xA9, 0xC0, 0x4F, 0xD0, 0xA1, 0x07,
159 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x06, 0x17, 0x28, 0x29, 0x2A, 0x2B, 0x2C, 0x09, 0x0A, 0x1B,
160 0x30, 0x31, 0x1A, 0x33, 0x34, 0x35, 0x36, 0x08, 0x38, 0x39, 0x3A, 0x3B, 0x04, 0x14, 0x3E, 0xFF,
161 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48, 0x49, 0x4A, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56,
162 0x57, 0x58, 0x59, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0x6A, 0x70, 0x71, 0x72, 0x73,
163 0x74, 0x75, 0x76, 0x77, 0x78, 0x80, 0x8A, 0x8B, 0x8C, 0x8D, 0x8E, 0x8F, 0x90, 0x9A, 0x9B, 0x9C,
164 0x9D, 0x9E, 0x9F, 0xA0, 0xAA, 0xAB, 0xAC, 0xAE, 0xAF, 0xB0, 0xB1, 0xB2, 0xB3, 0xB4, 0xB5, 0xB6,
165 0xB7, 0xB8, 0xB9, 0xBA, 0xBB, 0xBC, 0xBE, 0xBF, 0xCA, 0xCB, 0xCC, 0xCD, 0xCE, 0xCF, 0xDA, 0xDB,
166 0xDC, 0xDD, 0xDE, 0xDF, 0xE1, 0xEA, 0xEB, 0xEC, 0xED, 0xEE, 0xEF, 0xFA, 0xFB, 0xFC, 0xFD, 0xFE,
167};
168
f5e1abaf 169EXTCONST unsigned char PL_e2utf[] = { /* EBCDIC (IBM-1047) to UTF-8-mod */
1d72bdf6 170 0x00, 0x01, 0x02, 0x03, 0x9C, 0x09, 0x86, 0x7F, 0x97, 0x8D, 0x8E, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
171 0x10, 0x11, 0x12, 0x13, 0x9D, 0x0A, 0x08, 0x87, 0x18, 0x19, 0x92, 0x8F, 0x1C, 0x1D, 0x1E, 0x1F,
172 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x17, 0x1B, 0x88, 0x89, 0x8A, 0x8B, 0x8C, 0x05, 0x06, 0x07,
173 0x90, 0x91, 0x16, 0x93, 0x94, 0x95, 0x96, 0x04, 0x98, 0x99, 0x9A, 0x9B, 0x14, 0x15, 0x9E, 0x1A,
174 0x20, 0xA0, 0xA1, 0xA2, 0xA3, 0xA4, 0xA5, 0xA6, 0xA7, 0xA8, 0xA9, 0x2E, 0x3C, 0x28, 0x2B, 0x7C,
175 0x26, 0xAA, 0xAB, 0xAC, 0xAD, 0xAE, 0xAF, 0xB0, 0xB1, 0xB2, 0x21, 0x24, 0x2A, 0x29, 0x3B, 0x5E,
176 0x2D, 0x2F, 0xB3, 0xB4, 0xB5, 0xB6, 0xB7, 0xB8, 0xB9, 0xBA, 0xBB, 0x2C, 0x25, 0x5F, 0x3E, 0x3F,
177 0xBC, 0xBD, 0xBE, 0xBF, 0xC0, 0xC1, 0xC2, 0xC3, 0xC4, 0x60, 0x3A, 0x23, 0x40, 0x27, 0x3D, 0x22,
178 0xC5, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0xC6, 0xC7, 0xC8, 0xC9, 0xCA, 0xCB,
179 0xCC, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F, 0x70, 0x71, 0x72, 0xCD, 0xCE, 0xCF, 0xD0, 0xD1, 0xD2,
180 0xD3, 0x7E, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, 0x79, 0x7A, 0xD4, 0xD5, 0xD6, 0x5B, 0xD7, 0xD8,
181 0xD9, 0xDA, 0xDB, 0xDC, 0xDD, 0xDE, 0xDF, 0xE0, 0xE1, 0xE2, 0xE3, 0xE4, 0xE5, 0x5D, 0xE6, 0xE7,
182 0x7B, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48, 0x49, 0xE8, 0xE9, 0xEA, 0xEB, 0xEC, 0xED,
183 0x7D, 0x4A, 0x4B, 0x4C, 0x4D, 0x4E, 0x4F, 0x50, 0x51, 0x52, 0xEE, 0xEF, 0xF0, 0xF1, 0xF2, 0xF3,
184 0x5C, 0xF4, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58, 0x59, 0x5A, 0xF5, 0xF6, 0xF7, 0xF8, 0xF9, 0xFA,
185 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38, 0x39, 0xFB, 0xFC, 0xFD, 0xFE, 0xFF, 0x9F,
186};
f5e1abaf 187#endif /* 1047 */
188
189#if '^' == 106 /* if defined(_OSD_POSIX) POSIX-BC */
190unsigned char PL_utf2e[] = { /* UTF-8-mod to EBCDIC (POSIX-BC) */
191 0x00, 0x01, 0x02, 0x03, 0x37, 0x2D, 0x2E, 0x2F, 0x16, 0x05, 0x15, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
192 0x10, 0x11, 0x12, 0x13, 0x3C, 0x3D, 0x32, 0x26, 0x18, 0x19, 0x3F, 0x27, 0x1C, 0x1D, 0x1E, 0x1F,
193 0x40, 0x5A, 0x7F, 0x7B, 0x5B, 0x6C, 0x50, 0x7D, 0x4D, 0x5D, 0x5C, 0x4E, 0x6B, 0x60, 0x4B, 0x61,
194 0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0xF7, 0xF8, 0xF9, 0x7A, 0x5E, 0x4C, 0x7E, 0x6E, 0x6F,
195 0x7C, 0xC1, 0xC2, 0xC3, 0xC4, 0xC5, 0xC6, 0xC7, 0xC8, 0xC9, 0xD1, 0xD2, 0xD3, 0xD4, 0xD5, 0xD6,
196 0xD7, 0xD8, 0xD9, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7, 0xE8, 0xE9, 0xBB, 0xBC, 0xBD, 0x6A, 0x6D,
197 0x4A, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88, 0x89, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96,
198 0x97, 0x98, 0x99, 0xA2, 0xA3, 0xA4, 0xA5, 0xA6, 0xA7, 0xA8, 0xA9, 0xFB, 0x4F, 0xFD, 0xFF, 0x07,
199 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x06, 0x17, 0x28, 0x29, 0x2A, 0x2B, 0x2C, 0x09, 0x0A, 0x1B,
200 0x30, 0x31, 0x1A, 0x33, 0x34, 0x35, 0x36, 0x08, 0x38, 0x39, 0x3A, 0x3B, 0x04, 0x14, 0x3E, 0x5F,
201 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48, 0x49, 0xB0, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56,
202 0x57, 0x58, 0x59, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0xD0, 0x70, 0x71, 0x72, 0x73,
203 0x74, 0x75, 0x76, 0x77, 0x78, 0x80, 0x8A, 0x8B, 0x8C, 0x8D, 0x8E, 0x8F, 0x90, 0x9A, 0x9B, 0x9C,
204 0x9D, 0x9E, 0x9F, 0xA0, 0xAA, 0xAB, 0xAC, 0xAE, 0xAF, 0xBA, 0xB1, 0xB2, 0xB3, 0xB4, 0xB5, 0xB6,
205 0xB7, 0xB8, 0xB9, 0xAD, 0x79, 0xA1, 0xBE, 0xBF, 0xCA, 0xCB, 0xCC, 0xCD, 0xCE, 0xCF, 0xDA, 0xDB,
206 0xDC, 0xC0, 0xDE, 0xDF, 0xE1, 0xEA, 0xEB, 0xEC, 0xED, 0xEE, 0xEF, 0xFA, 0xDD, 0xFC, 0xE0, 0xFE,
207};
208
209unsigned char PL_e2utf[] = { /* EBCDIC (POSIX-BC) to UTF-8-mod */
210 0x00, 0x01, 0x02, 0x03, 0x9C, 0x09, 0x86, 0x7F, 0x97, 0x8D, 0x8E, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
211 0x10, 0x11, 0x12, 0x13, 0x9D, 0x0A, 0x08, 0x87, 0x18, 0x19, 0x92, 0x8F, 0x1C, 0x1D, 0x1E, 0x1F,
212 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x17, 0x1B, 0x88, 0x89, 0x8A, 0x8B, 0x8C, 0x05, 0x06, 0x07,
213 0x90, 0x91, 0x16, 0x93, 0x94, 0x95, 0x96, 0x04, 0x98, 0x99, 0x9A, 0x9B, 0x14, 0x15, 0x9E, 0x1A,
214 0x20, 0xA0, 0xA1, 0xA2, 0xA3, 0xA4, 0xA5, 0xA6, 0xA7, 0xA8, 0x60, 0x2E, 0x3C, 0x28, 0x2B, 0x7C,
215 0x26, 0xAA, 0xAB, 0xAC, 0xAD, 0xAE, 0xAF, 0xB0, 0xB1, 0xB2, 0x21, 0x24, 0x2A, 0x29, 0x3B, 0x9F,
216 0x2D, 0x2F, 0xB3, 0xB4, 0xB5, 0xB6, 0xB7, 0xB8, 0xB9, 0xBA, 0x5E, 0x2C, 0x25, 0x5F, 0x3E, 0x3F,
217 0xBC, 0xBD, 0xBE, 0xBF, 0xC0, 0xC1, 0xC2, 0xC3, 0xC4, 0xE4, 0x3A, 0x23, 0x40, 0x27, 0x3D, 0x22,
218 0xC5, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0xC6, 0xC7, 0xC8, 0xC9, 0xCA, 0xCB,
219 0xCC, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F, 0x70, 0x71, 0x72, 0xCD, 0xCE, 0xCF, 0xD0, 0xD1, 0xD2,
220 0xD3, 0xE5, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, 0x79, 0x7A, 0xD4, 0xD5, 0xD6, 0xE3, 0xD7, 0xD8,
221 0xA9, 0xDA, 0xDB, 0xDC, 0xDD, 0xDE, 0xDF, 0xE0, 0xE1, 0xE2, 0xD9, 0x5B, 0x5C, 0x5D, 0xE6, 0xE7,
222 0xF1, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48, 0x49, 0xE8, 0xE9, 0xEA, 0xEB, 0xEC, 0xED,
223 0xBB, 0x4A, 0x4B, 0x4C, 0x4D, 0x4E, 0x4F, 0x50, 0x51, 0x52, 0xEE, 0xEF, 0xF0, 0xFC, 0xF2, 0xF3,
224 0xFE, 0xF4, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58, 0x59, 0x5A, 0xF5, 0xF6, 0xF7, 0xF8, 0xF9, 0xFA,
225 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38, 0x39, 0xFB, 0x7B, 0xFD, 0x7D, 0xFF, 0x7E,
226};
227#endif /* POSIX-BC */
228
229#if '^' == 176 /* if defined(??) (OS/400?) 037 */
230unsigned char PL_utf2e[] = { /* UTF-8-mod to EBCDIC (IBM-037) */
231 0x00, 0x01, 0x02, 0x03, 0x37, 0x2D, 0x2E, 0x2F, 0x16, 0x05, 0x25, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
232 0x10, 0x11, 0x12, 0x13, 0x3C, 0x3D, 0x32, 0x26, 0x18, 0x19, 0x3F, 0x27, 0x1C, 0x1D, 0x1E, 0x1F,
233 0x40, 0x5A, 0x7F, 0x7B, 0x5B, 0x6C, 0x50, 0x7D, 0x4D, 0x5D, 0x5C, 0x4E, 0x6B, 0x60, 0x4B, 0x61,
234 0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0xF7, 0xF8, 0xF9, 0x7A, 0x5E, 0x4C, 0x7E, 0x6E, 0x6F,
235 0x7C, 0xC1, 0xC2, 0xC3, 0xC4, 0xC5, 0xC6, 0xC7, 0xC8, 0xC9, 0xD1, 0xD2, 0xD3, 0xD4, 0xD5, 0xD6,
236 0xD7, 0xD8, 0xD9, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7, 0xE8, 0xE9, 0xBA, 0xE0, 0xBB, 0xB0, 0x6D,
237 0x79, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88, 0x89, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96,
238 0x97, 0x98, 0x99, 0xA2, 0xA3, 0xA4, 0xA5, 0xA6, 0xA7, 0xA8, 0xA9, 0xC0, 0x4F, 0xD0, 0xA1, 0x07,
239 0x20, 0x21, 0x22, 0x23, 0x24, 0x15, 0x06, 0x17, 0x28, 0x29, 0x2A, 0x2B, 0x2C, 0x09, 0x0A, 0x1B,
240 0x30, 0x31, 0x1A, 0x33, 0x34, 0x35, 0x36, 0x08, 0x38, 0x39, 0x3A, 0x3B, 0x04, 0x14, 0x3E, 0xFF,
241 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48, 0x49, 0x4A, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56,
242 0x57, 0x58, 0x59, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0x6A, 0x70, 0x71, 0x72, 0x73,
243 0x74, 0x75, 0x76, 0x77, 0x78, 0x80, 0x8A, 0x8B, 0x8C, 0x8D, 0x8E, 0x8F, 0x90, 0x9A, 0x9B, 0x9C,
244 0x9D, 0x9E, 0x9F, 0xA0, 0xAA, 0xAB, 0xAC, 0xAE, 0xAF, 0x5F, 0xB1, 0xB2, 0xB3, 0xB4, 0xB5, 0xB6,
245 0xB7, 0xB8, 0xB9, 0xAD, 0xBD, 0xBC, 0xBE, 0xBF, 0xCA, 0xCB, 0xCC, 0xCD, 0xCE, 0xCF, 0xDA, 0xDB,
246 0xDC, 0xDD, 0xDE, 0xDF, 0xE1, 0xEA, 0xEB, 0xEC, 0xED, 0xEE, 0xEF, 0xFA, 0xFB, 0xFC, 0xFD, 0xFE,
247};
248
249unsigned char PL_e2utf[] = { /* EBCDIC (IBM-037) to UTF-8-mod */
250 0x00, 0x01, 0x02, 0x03, 0x9C, 0x09, 0x86, 0x7F, 0x97, 0x8D, 0x8E, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
251 0x10, 0x11, 0x12, 0x13, 0x9D, 0x85, 0x08, 0x87, 0x18, 0x19, 0x92, 0x8F, 0x1C, 0x1D, 0x1E, 0x1F,
252 0x80, 0x81, 0x82, 0x83, 0x84, 0x0A, 0x17, 0x1B, 0x88, 0x89, 0x8A, 0x8B, 0x8C, 0x05, 0x06, 0x07,
253 0x90, 0x91, 0x16, 0x93, 0x94, 0x95, 0x96, 0x04, 0x98, 0x99, 0x9A, 0x9B, 0x14, 0x15, 0x9E, 0x1A,
254 0x20, 0xA0, 0xA1, 0xA2, 0xA3, 0xA4, 0xA5, 0xA6, 0xA7, 0xA8, 0xA9, 0x2E, 0x3C, 0x28, 0x2B, 0x7C,
255 0x26, 0xAA, 0xAB, 0xAC, 0xAD, 0xAE, 0xAF, 0xB0, 0xB1, 0xB2, 0x21, 0x24, 0x2A, 0x29, 0x3B, 0xD9,
256 0x2D, 0x2F, 0xB3, 0xB4, 0xB5, 0xB6, 0xB7, 0xB8, 0xB9, 0xBA, 0xBB, 0x2C, 0x25, 0x5F, 0x3E, 0x3F,
257 0xBC, 0xBD, 0xBE, 0xBF, 0xC0, 0xC1, 0xC2, 0xC3, 0xC4, 0x60, 0x3A, 0x23, 0x40, 0x27, 0x3D, 0x22,
258 0xC5, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0xC6, 0xC7, 0xC8, 0xC9, 0xCA, 0xCB,
259 0xCC, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F, 0x70, 0x71, 0x72, 0xCD, 0xCE, 0xCF, 0xD0, 0xD1, 0xD2,
260 0xD3, 0x7E, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, 0x79, 0x7A, 0xD4, 0xD5, 0xD6, 0xE3, 0xD7, 0xD8,
261 0x5E, 0xDA, 0xDB, 0xDC, 0xDD, 0xDE, 0xDF, 0xE0, 0xE1, 0xE2, 0x5B, 0x5D, 0xE5, 0xE4, 0xE6, 0xE7,
262 0x7B, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48, 0x49, 0xE8, 0xE9, 0xEA, 0xEB, 0xEC, 0xED,
263 0x7D, 0x4A, 0x4B, 0x4C, 0x4D, 0x4E, 0x4F, 0x50, 0x51, 0x52, 0xEE, 0xEF, 0xF0, 0xF1, 0xF2, 0xF3,
264 0x5C, 0xF4, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58, 0x59, 0x5A, 0xF5, 0xF6, 0xF7, 0xF8, 0xF9, 0xFA,
265 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38, 0x39, 0xFB, 0xFC, 0xFD, 0xFE, 0xFF, 0x9F,
266};
267#endif /* 037 */
1d72bdf6 268
269/* These tables moved from perl.h and converted to hex.
270 They map platfrom code page from/to bottom 256 codes of Unicode (i.e. iso-8859-1).
271*/
272
273#if '^' == 95 /* if defined(__MVS__) || defined(??) (VM/ESA?) 1047 */
274EXTCONST unsigned char PL_a2e[] = { /* ASCII (iso-8859-1) to EBCDIC (IBM-1047) */
275 0x00, 0x01, 0x02, 0x03, 0x37, 0x2D, 0x2E, 0x2F, 0x16, 0x05, 0x15, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
276 0x10, 0x11, 0x12, 0x13, 0x3C, 0x3D, 0x32, 0x26, 0x18, 0x19, 0x3F, 0x27, 0x1C, 0x1D, 0x1E, 0x1F,
277 0x40, 0x5A, 0x7F, 0x7B, 0x5B, 0x6C, 0x50, 0x7D, 0x4D, 0x5D, 0x5C, 0x4E, 0x6B, 0x60, 0x4B, 0x61,
278 0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0xF7, 0xF8, 0xF9, 0x7A, 0x5E, 0x4C, 0x7E, 0x6E, 0x6F,
279 0x7C, 0xC1, 0xC2, 0xC3, 0xC4, 0xC5, 0xC6, 0xC7, 0xC8, 0xC9, 0xD1, 0xD2, 0xD3, 0xD4, 0xD5, 0xD6,
280 0xD7, 0xD8, 0xD9, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7, 0xE8, 0xE9, 0xAD, 0xE0, 0xBD, 0x5F, 0x6D,
281 0x79, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88, 0x89, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96,
282 0x97, 0x98, 0x99, 0xA2, 0xA3, 0xA4, 0xA5, 0xA6, 0xA7, 0xA8, 0xA9, 0xC0, 0x4F, 0xD0, 0xA1, 0x07,
283 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x06, 0x17, 0x28, 0x29, 0x2A, 0x2B, 0x2C, 0x09, 0x0A, 0x1B,
284 0x30, 0x31, 0x1A, 0x33, 0x34, 0x35, 0x36, 0x08, 0x38, 0x39, 0x3A, 0x3B, 0x04, 0x14, 0x3E, 0xFF,
285 0x41, 0xAA, 0x4A, 0xB1, 0x9F, 0xB2, 0x6A, 0xB5, 0xBB, 0xB4, 0x9A, 0x8A, 0xB0, 0xCA, 0xAF, 0xBC,
286 0x90, 0x8F, 0xEA, 0xFA, 0xBE, 0xA0, 0xB6, 0xB3, 0x9D, 0xDA, 0x9B, 0x8B, 0xB7, 0xB8, 0xB9, 0xAB,
287 0x64, 0x65, 0x62, 0x66, 0x63, 0x67, 0x9E, 0x68, 0x74, 0x71, 0x72, 0x73, 0x78, 0x75, 0x76, 0x77,
288 0xAC, 0x69, 0xED, 0xEE, 0xEB, 0xEF, 0xEC, 0xBF, 0x80, 0xFD, 0xFE, 0xFB, 0xFC, 0xBA, 0xAE, 0x59,
289 0x44, 0x45, 0x42, 0x46, 0x43, 0x47, 0x9C, 0x48, 0x54, 0x51, 0x52, 0x53, 0x58, 0x55, 0x56, 0x57,
290 0x8C, 0x49, 0xCD, 0xCE, 0xCB, 0xCF, 0xCC, 0xE1, 0x70, 0xDD, 0xDE, 0xDB, 0xDC, 0x8D, 0x8E, 0xDF
291};
292
431fc773 293EXTCONST unsigned char PL_e2a[] = { /* EBCDIC (IBM-1047) to ASCII (iso-8859-1) */
1d72bdf6 294 0x00, 0x01, 0x02, 0x03, 0x9C, 0x09, 0x86, 0x7F, 0x97, 0x8D, 0x8E, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
295 0x10, 0x11, 0x12, 0x13, 0x9D, 0x0A, 0x08, 0x87, 0x18, 0x19, 0x92, 0x8F, 0x1C, 0x1D, 0x1E, 0x1F,
296 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x17, 0x1B, 0x88, 0x89, 0x8A, 0x8B, 0x8C, 0x05, 0x06, 0x07,
297 0x90, 0x91, 0x16, 0x93, 0x94, 0x95, 0x96, 0x04, 0x98, 0x99, 0x9A, 0x9B, 0x14, 0x15, 0x9E, 0x1A,
298 0x20, 0xA0, 0xE2, 0xE4, 0xE0, 0xE1, 0xE3, 0xE5, 0xE7, 0xF1, 0xA2, 0x2E, 0x3C, 0x28, 0x2B, 0x7C,
299 0x26, 0xE9, 0xEA, 0xEB, 0xE8, 0xED, 0xEE, 0xEF, 0xEC, 0xDF, 0x21, 0x24, 0x2A, 0x29, 0x3B, 0x5E,
300 0x2D, 0x2F, 0xC2, 0xC4, 0xC0, 0xC1, 0xC3, 0xC5, 0xC7, 0xD1, 0xA6, 0x2C, 0x25, 0x5F, 0x3E, 0x3F,
301 0xF8, 0xC9, 0xCA, 0xCB, 0xC8, 0xCD, 0xCE, 0xCF, 0xCC, 0x60, 0x3A, 0x23, 0x40, 0x27, 0x3D, 0x22,
302 0xD8, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0xAB, 0xBB, 0xF0, 0xFD, 0xFE, 0xB1,
303 0xB0, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F, 0x70, 0x71, 0x72, 0xAA, 0xBA, 0xE6, 0xB8, 0xC6, 0xA4,
304 0xB5, 0x7E, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, 0x79, 0x7A, 0xA1, 0xBF, 0xD0, 0x5B, 0xDE, 0xAE,
305 0xAC, 0xA3, 0xA5, 0xB7, 0xA9, 0xA7, 0xB6, 0xBC, 0xBD, 0xBE, 0xDD, 0xA8, 0xAF, 0x5D, 0xB4, 0xD7,
306 0x7B, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48, 0x49, 0xAD, 0xF4, 0xF6, 0xF2, 0xF3, 0xF5,
307 0x7D, 0x4A, 0x4B, 0x4C, 0x4D, 0x4E, 0x4F, 0x50, 0x51, 0x52, 0xB9, 0xFB, 0xFC, 0xF9, 0xFA, 0xFF,
308 0x5C, 0xF7, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58, 0x59, 0x5A, 0xB2, 0xD4, 0xD6, 0xD2, 0xD3, 0xD5,
309 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38, 0x39, 0xB3, 0xDB, 0xDC, 0xD9, 0xDA, 0x9F
310};
311#endif /* 1047 */
312
313#if '^' == 106 /* if defined(_OSD_POSIX) POSIX-BC */
314EXTCONST unsigned char PL_a2e[] = { /* ASCII (ISO8859-1) to EBCDIC (POSIX-BC) */
315 0x00, 0x01, 0x02, 0x03, 0x37, 0x2D, 0x2E, 0x2F, 0x16, 0x05, 0x15, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
316 0x10, 0x11, 0x12, 0x13, 0x3C, 0x3D, 0x32, 0x26, 0x18, 0x19, 0x3F, 0x27, 0x1C, 0x1D, 0x1E, 0x1F,
317 0x40, 0x5A, 0x7F, 0x7B, 0x5B, 0x6C, 0x50, 0x7D, 0x4D, 0x5D, 0x5C, 0x4E, 0x6B, 0x60, 0x4B, 0x61,
318 0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0xF7, 0xF8, 0xF9, 0x7A, 0x5E, 0x4C, 0x7E, 0x6E, 0x6F,
319 0x7C, 0xC1, 0xC2, 0xC3, 0xC4, 0xC5, 0xC6, 0xC7, 0xC8, 0xC9, 0xD1, 0xD2, 0xD3, 0xD4, 0xD5, 0xD6,
320 0xD7, 0xD8, 0xD9, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7, 0xE8, 0xE9, 0xBB, 0xBC, 0xBD, 0x6A, 0x6D,
321 0x4A, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88, 0x89, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96,
322 0x97, 0x98, 0x99, 0xA2, 0xA3, 0xA4, 0xA5, 0xA6, 0xA7, 0xA8, 0xA9, 0xFB, 0x4F, 0xFD, 0xFF, 0x07,
323 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x06, 0x17, 0x28, 0x29, 0x2A, 0x2B, 0x2C, 0x09, 0x0A, 0x1B,
324 0x30, 0x31, 0x1A, 0x33, 0x34, 0x35, 0x36, 0x08, 0x38, 0x39, 0x3A, 0x3B, 0x04, 0x14, 0x3E, 0x5F,
325 0x41, 0xAA, 0xB0, 0xB1, 0x9F, 0xB2, 0xD0, 0xB5, 0x79, 0xB4, 0x9A, 0x8A, 0xBA, 0xCA, 0xAF, 0xA1,
326 0x90, 0x8F, 0xEA, 0xFA, 0xBE, 0xA0, 0xB6, 0xB3, 0x9D, 0xDA, 0x9B, 0x8B, 0xB7, 0xB8, 0xB9, 0xAB,
327 0x64, 0x65, 0x62, 0x66, 0x63, 0x67, 0x9E, 0x68, 0x74, 0x71, 0x72, 0x73, 0x78, 0x75, 0x76, 0x77,
328 0xAC, 0x69, 0xED, 0xEE, 0xEB, 0xEF, 0xEC, 0xBF, 0x80, 0xE0, 0xFE, 0xDD, 0xFC, 0xAD, 0xAE, 0x59,
329 0x44, 0x45, 0x42, 0x46, 0x43, 0x47, 0x9C, 0x48, 0x54, 0x51, 0x52, 0x53, 0x58, 0x55, 0x56, 0x57,
330 0x8C, 0x49, 0xCD, 0xCE, 0xCB, 0xCF, 0xCC, 0xE1, 0x70, 0xC0, 0xDE, 0xDB, 0xDC, 0x8D, 0x8E, 0xDF
331};
332
333EXTCONST unsigned char PL_e2a[] = { /* EBCDIC (POSIX-BC) to ASCII (ISO8859-1) */
334 0x00, 0x01, 0x02, 0x03, 0x9C, 0x09, 0x86, 0x7F, 0x97, 0x8D, 0x8E, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
335 0x10, 0x11, 0x12, 0x13, 0x9D, 0x0A, 0x08, 0x87, 0x18, 0x19, 0x92, 0x8F, 0x1C, 0x1D, 0x1E, 0x1F,
336 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x17, 0x1B, 0x88, 0x89, 0x8A, 0x8B, 0x8C, 0x05, 0x06, 0x07,
337 0x90, 0x91, 0x16, 0x93, 0x94, 0x95, 0x96, 0x04, 0x98, 0x99, 0x9A, 0x9B, 0x14, 0x15, 0x9E, 0x1A,
338 0x20, 0xA0, 0xE2, 0xE4, 0xE0, 0xE1, 0xE3, 0xE5, 0xE7, 0xF1, 0x60, 0x2E, 0x3C, 0x28, 0x2B, 0x7C,
339 0x26, 0xE9, 0xEA, 0xEB, 0xE8, 0xED, 0xEE, 0xEF, 0xEC, 0xDF, 0x21, 0x24, 0x2A, 0x29, 0x3B, 0x9F,
340 0x2D, 0x2F, 0xC2, 0xC4, 0xC0, 0xC1, 0xC3, 0xC5, 0xC7, 0xD1, 0x5E, 0x2C, 0x25, 0x5F, 0x3E, 0x3F,
341 0xF8, 0xC9, 0xCA, 0xCB, 0xC8, 0xCD, 0xCE, 0xCF, 0xCC, 0xA8, 0x3A, 0x23, 0x40, 0x27, 0x3D, 0x22,
342 0xD8, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0xAB, 0xBB, 0xF0, 0xFD, 0xFE, 0xB1,
343 0xB0, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F, 0x70, 0x71, 0x72, 0xAA, 0xBA, 0xE6, 0xB8, 0xC6, 0xA4,
344 0xB5, 0xAF, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, 0x79, 0x7A, 0xA1, 0xBF, 0xD0, 0xDD, 0xDE, 0xAE,
345 0xA2, 0xA3, 0xA5, 0xB7, 0xA9, 0xA7, 0xB6, 0xBC, 0xBD, 0xBE, 0xAC, 0x5B, 0x5C, 0x5D, 0xB4, 0xD7,
346 0xF9, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48, 0x49, 0xAD, 0xF4, 0xF6, 0xF2, 0xF3, 0xF5,
347 0xA6, 0x4A, 0x4B, 0x4C, 0x4D, 0x4E, 0x4F, 0x50, 0x51, 0x52, 0xB9, 0xFB, 0xFC, 0xDB, 0xFA, 0xFF,
348 0xD9, 0xF7, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58, 0x59, 0x5A, 0xB2, 0xD4, 0xD6, 0xD2, 0xD3, 0xD5,
349 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38, 0x39, 0xB3, 0x7B, 0xDC, 0x7D, 0xDA, 0x7E
350};
351#endif /* POSIX-BC */
f5e1abaf 352
1d72bdf6 353#if '^' == 176 /* if defined(??) (OS/400?) 037 */
354EXTCONST unsigned char PL_a2e[] = { /* ASCII (ISO8859-1) to EBCDIC (IBM-037) */
355 0x00, 0x01, 0x02, 0x03, 0x37, 0x2D, 0x2E, 0x2F, 0x16, 0x05, 0x25, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
356 0x10, 0x11, 0x12, 0x13, 0x3C, 0x3D, 0x32, 0x26, 0x18, 0x19, 0x3F, 0x27, 0x1C, 0x1D, 0x1E, 0x1F,
357 0x40, 0x5A, 0x7F, 0x7B, 0x5B, 0x6C, 0x50, 0x7D, 0x4D, 0x5D, 0x5C, 0x4E, 0x6B, 0x60, 0x4B, 0x61,
358 0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0xF7, 0xF8, 0xF9, 0x7A, 0x5E, 0x4C, 0x7E, 0x6E, 0x6F,
359 0x7C, 0xC1, 0xC2, 0xC3, 0xC4, 0xC5, 0xC6, 0xC7, 0xC8, 0xC9, 0xD1, 0xD2, 0xD3, 0xD4, 0xD5, 0xD6,
360 0xD7, 0xD8, 0xD9, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7, 0xE8, 0xE9, 0xBA, 0xE0, 0xBB, 0xB0, 0x6D,
361 0x79, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88, 0x89, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96,
362 0x97, 0x98, 0x99, 0xA2, 0xA3, 0xA4, 0xA5, 0xA6, 0xA7, 0xA8, 0xA9, 0xC0, 0x4F, 0xD0, 0xA1, 0x07,
363 0x20, 0x21, 0x22, 0x23, 0x24, 0x15, 0x06, 0x17, 0x28, 0x29, 0x2A, 0x2B, 0x2C, 0x09, 0x0A, 0x1B,
364 0x30, 0x31, 0x1A, 0x33, 0x34, 0x35, 0x36, 0x08, 0x38, 0x39, 0x3A, 0x3B, 0x04, 0x14, 0x3E, 0xFF,
365 0x41, 0xAA, 0x4A, 0xB1, 0x9F, 0xB2, 0x6A, 0xB5, 0xBD, 0xB4, 0x9A, 0x8A, 0x5F, 0xCA, 0xAF, 0xBC,
366 0x90, 0x8F, 0xEA, 0xFA, 0xBE, 0xA0, 0xB6, 0xB3, 0x9D, 0xDA, 0x9B, 0x8B, 0xB7, 0xB8, 0xB9, 0xAB,
367 0x64, 0x65, 0x62, 0x66, 0x63, 0x67, 0x9E, 0x68, 0x74, 0x71, 0x72, 0x73, 0x78, 0x75, 0x76, 0x77,
368 0xAC, 0x69, 0xED, 0xEE, 0xEB, 0xEF, 0xEC, 0xBF, 0x80, 0xFD, 0xFE, 0xFB, 0xFC, 0xAD, 0xAE, 0x59,
369 0x44, 0x45, 0x42, 0x46, 0x43, 0x47, 0x9C, 0x48, 0x54, 0x51, 0x52, 0x53, 0x58, 0x55, 0x56, 0x57,
370 0x8C, 0x49, 0xCD, 0xCE, 0xCB, 0xCF, 0xCC, 0xE1, 0x70, 0xDD, 0xDE, 0xDB, 0xDC, 0x8D, 0x8E, 0xDF
371};
372
373EXTCONST unsigned char PL_e2a[] = { /* EBCDIC (IBM-037) to ASCII (ISO8859-1) */
374 0x00, 0x01, 0x02, 0x03, 0x9C, 0x09, 0x86, 0x7F, 0x97, 0x8D, 0x8E, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
375 0x10, 0x11, 0x12, 0x13, 0x9D, 0x85, 0x08, 0x87, 0x18, 0x19, 0x92, 0x8F, 0x1C, 0x1D, 0x1E, 0x1F,
376 0x80, 0x81, 0x82, 0x83, 0x84, 0x0A, 0x17, 0x1B, 0x88, 0x89, 0x8A, 0x8B, 0x8C, 0x05, 0x06, 0x07,
377 0x90, 0x91, 0x16, 0x93, 0x94, 0x95, 0x96, 0x04, 0x98, 0x99, 0x9A, 0x9B, 0x14, 0x15, 0x9E, 0x1A,
378 0x20, 0xA0, 0xE2, 0xE4, 0xE0, 0xE1, 0xE3, 0xE5, 0xE7, 0xF1, 0xA2, 0x2E, 0x3C, 0x28, 0x2B, 0x7C,
379 0x26, 0xE9, 0xEA, 0xEB, 0xE8, 0xED, 0xEE, 0xEF, 0xEC, 0xDF, 0x21, 0x24, 0x2A, 0x29, 0x3B, 0xAC,
380 0x2D, 0x2F, 0xC2, 0xC4, 0xC0, 0xC1, 0xC3, 0xC5, 0xC7, 0xD1, 0xA6, 0x2C, 0x25, 0x5F, 0x3E, 0x3F,
381 0xF8, 0xC9, 0xCA, 0xCB, 0xC8, 0xCD, 0xCE, 0xCF, 0xCC, 0x60, 0x3A, 0x23, 0x40, 0x27, 0x3D, 0x22,
382 0xD8, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0xAB, 0xBB, 0xF0, 0xFD, 0xFE, 0xB1,
383 0xB0, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F, 0x70, 0x71, 0x72, 0xAA, 0xBA, 0xE6, 0xB8, 0xC6, 0xA4,
384 0xB5, 0x7E, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, 0x79, 0x7A, 0xA1, 0xBF, 0xD0, 0xDD, 0xDE, 0xAE,
385 0x5E, 0xA3, 0xA5, 0xB7, 0xA9, 0xA7, 0xB6, 0xBC, 0xBD, 0xBE, 0x5B, 0x5D, 0xAF, 0xA8, 0xB4, 0xD7,
386 0x7B, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48, 0x49, 0xAD, 0xF4, 0xF6, 0xF2, 0xF3, 0xF5,
387 0x7D, 0x4A, 0x4B, 0x4C, 0x4D, 0x4E, 0x4F, 0x50, 0x51, 0x52, 0xB9, 0xFB, 0xFC, 0xF9, 0xFA, 0xFF,
388 0x5C, 0xF7, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58, 0x59, 0x5A, 0xB2, 0xD4, 0xD6, 0xD2, 0xD3, 0xD5,
389 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38, 0x39, 0xB3, 0xDB, 0xDC, 0xD9, 0xDA, 0x9F
390};
391#endif /* 037 */
392
393#else
394EXTCONST unsigned char PL_utf8skip[];
395EXTCONST unsigned char PL_e2utf[];
396EXTCONST unsigned char PL_utf2e[];
397EXTCONST unsigned char PL_e2a[];
398EXTCONST unsigned char PL_a2e[];
399#endif
400
401END_EXTERN_C
402
66af24e1 403#define UTF8SKIP(s) PL_utf8skip[*(const U8*)(s)]
1d72bdf6 404
1e54db1a 405/* EBCDIC-happy ways of converting native code to UTF-8 */
1d72bdf6 406
407/* Native to iso-8859-1 */
408#define NATIVE_TO_ASCII(ch) PL_e2a[(U8)(ch)]
409#define ASCII_TO_NATIVE(ch) PL_a2e[(U8)(ch)]
410/* Transform after encoding */
411#define NATIVE_TO_UTF(ch) PL_e2utf[(U8)(ch)]
412#define UTF_TO_NATIVE(ch) PL_utf2e[(U8)(ch)]
413/* Transform in wide UV char space */
414#define NATIVE_TO_UNI(ch) (((ch) > 255) ? (ch) : NATIVE_TO_ASCII(ch))
c4d5f83a 415#define UNI_TO_NATIVE(ch) (((ch) > 255) ? (ch) : ASCII_TO_NATIVE(ch))
1d72bdf6 416/* Transform in invariant..byte space */
417#define NATIVE_TO_NEED(enc,ch) ((enc) ? UTF_TO_NATIVE(NATIVE_TO_ASCII(ch)) : (ch))
418#define ASCII_TO_NEED(enc,ch) ((enc) ? UTF_TO_NATIVE(ch) : ASCII_TO_NATIVE(ch))
419
420/*
421 * Note: we should try and be careful never to call the isXXX_utf8() functions
422 * unless we're pretty sure we've seen the beginning of a UTF-EBCDIC character
979f2922 423 * Otherwise we risk loading in the heavy-duty swash_init and swash_fetch
424 * routines unnecessarily.
1d72bdf6 425 */
426
0064a8a9 427#define isIDFIRST_lazy_if(p,c) ((IN_BYTES || (!c || UTF8_IS_INVARIANT(*p))) \
1d72bdf6 428 ? isIDFIRST(*(p)) \
e1ec3a88 429 : isIDFIRST_utf8((const U8*)p))
0064a8a9 430#define isALNUM_lazy_if(p,c) ((IN_BYTES || (!c || UTF8_IS_INVARIANT(*p))) \
1d72bdf6 431 ? isALNUM(*(p)) \
e1ec3a88 432 : isALNUM_utf8((const U8*)p))
1d72bdf6 433
434/*
435 The following table is adapted from tr16, it shows UTF-8-mod encoding of Unicode code points.
436
437 Unicode Bit pattern 1st Byte 2nd Byte 3rd Byte 4th Byte 5th Byte 6th Byte 7th byte
438 U+0000..U+007F 000000000xxxxxxx 0xxxxxxx
439 U+0080..U+009F 00000000100xxxxx 100xxxxx
440 U+00A0..U+00FF 00000000yyyxxxxx 11000yyy 101xxxxx
441
442 U+00A0..U+03FF 000000yyyyyxxxxx 110yyyyy 101xxxxx
443 U+0400..U+3FFF 00zzzzyyyyyxxxxx 1110zzzz 101yyyyy 101xxxxx
444 U+4000..U+3FFFF 0wwwzzzzzyyyyyxxxxx 11110www 101zzzzz 101yyyyy 101xxxxx
445 U+40000..U+3FFFFF 0vvwwwwwzzzzzyyyyyxxxxx 111110vv 101wwwww 101zzzzz 101yyyyy 101xxxxx
446 U+400000..U+3FFFFFF 0uvvvvvwwwwwzzzzzyyyyyxxxxx 1111110u 101vvvvv 101wwwww 101zzzzz 101yyyyy 101xxxxx
447 U+4000000..U+7FFFFFFF 0tuuuuuvvvvvwwwwwzzzzzyyyyyxxxxx 1111111t 101uuuuu 101vvvvv 101wwwww 101zzzzz 101yyyyy 101xxxxx
448
449 Note: The UTF-8-Mod transformation is valid for UCS-4 values X'0' to
450 X'7FFFFFFF' (the full extent of ISO/IEC 10646 coding space).
451
452 */
453
454#define UNISKIP(uv) ( (uv) < 0xA0 ? 1 : \
455 (uv) < 0x400 ? 2 : \
456 (uv) < 0x4000 ? 3 : \
457 (uv) < 0x40000 ? 4 : \
458 (uv) < 0x400000 ? 5 : \
459 (uv) < 0x4000000 ? 6 : 7 )
460
c4d5f83a 461
462#define UNI_IS_INVARIANT(c) ((c) < 0xA0)
1d72bdf6 463/* UTF-EBCDIC sematic macros - transform back into UTF-8-Mod and then compare */
c4d5f83a 464#define NATIVE_IS_INVARIANT(c) UNI_IS_INVARIANT(NATIVE_TO_ASCII(c))
465#define UTF8_IS_INVARIANT(c) UNI_IS_INVARIANT(NATIVE_TO_UTF(c))
1d72bdf6 466#define UTF8_IS_START(c) (NATIVE_TO_UTF(c) >= 0xA0 && (NATIVE_TO_UTF(c) & 0xE0) != 0xA0)
2b9d42f0 467#define UTF8_IS_CONTINUATION(c) ((NATIVE_TO_UTF(c) & 0xE0) == 0xA0)
1d72bdf6 468#define UTF8_IS_CONTINUED(c) (NATIVE_TO_UTF(c) >= 0xA0)
469#define UTF8_IS_DOWNGRADEABLE_START(c) (NATIVE_TO_UTF(c) >= 0xA0 && (NATIVE_TO_UTF(c) & 0xF8) == 0xC0)
470
471#define UTF_START_MARK(len) ((len > 7) ? 0xFF : (0xFE << (7-len)))
472#define UTF_START_MASK(len) ((len >= 6) ? 0x01 : (0x1F >> (len-2)))
473#define UTF_CONTINUATION_MARK 0xA0
474#define UTF_CONTINUATION_MASK ((U8)0x1f)
475#define UTF_ACCUMULATION_SHIFT 5
476
75383841 477#define UTF8_ACCUMULATE(old, new) (((old) << UTF_ACCUMULATION_SHIFT)|(NATIVE_TO_UTF(new) & UTF_CONTINUATION_MASK))
1d72bdf6 478
479/* UTF-EBCDIC encode a downgradeable value */
480#define UTF8_EIGHT_BIT_HI(c) UTF_TO_NATIVE((((U8)(c))>>UTF_ACCUMULATION_SHIFT)|UTF_START_MARK(2))
481#define UTF8_EIGHT_BIT_LO(c) UTF_TO_NATIVE(((((U8)(c)))&UTF_CONTINUATION_MASK)|UTF_CONTINUATION_MARK)
482
e9a8c099 483/*
484 * Local variables:
485 * c-indentation-style: bsd
486 * c-basic-offset: 4
487 * indent-tabs-mode: t
488 * End:
489 *
490 * ex: set ts=8 sts=4 sw=4 noet:
491 */