In Perl_pad_check_dup(), use sv rather than name for diagnostics.
[p5sagit/p5-mst-13.2.git] / utfebcdic.h
CommitLineData
1d72bdf6 1/* utfebcdic.h
2 *
83706693 3 * Copyright (C) 2001, 2002, 2003, 2005, 2006, 2007, 2009 by Larry Wall,
4 * Nick 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
b3ab6785 32 * final UTF-EBCDIC. The table in this file is PL_utf2e, and its inverse
fe749c9a 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 =
cbbb00c6 40 * 11000111 10111111 = C7 BF, and Step 3 converts those to 0x8B 0x73. The
41 * table is constructed so that the first bytes of a variant will always
42 * have its upper bit set (at least in the encodings that Perl recognizes,
43 * and probably all).
fe749c9a 44 *
45 * If you're starting from Unicode, skip step 1. For UTF-EBCDIC to straight
46 * EBCDIC, reverse the steps.
47 *
48 * The EBCDIC invariants have been chosen to be those characters whose Unicode
49 * equivalents have ordinal numbers less than 160, that is the same characters
50 * that are expressible in ASCII, plus the C1 controls. So there are 160
51 * invariants instead of the 128 in UTF-8. (My guess is that this is because
52 * the C1 control NEL (and maybe others) is important in IBM.)
53 *
54 * The purpose of Step 3 is to make the encoding be invariant for the chosen
55 * characters. This messes up the convenient patterns found in step 2, so
56 * generally, one has to undo step 3 into a temporary to use them. However,
57 * a "shadow", or parallel table, PL_utf8skip, has been constructed so that for
58 * each byte, it says how long the sequence is if that byte were to begin it
59 *
60 * There are actually 3 slightly different UTF-EBCDIC encodings in this file,
61 * one for each of the code pages recognized by Perl. That means that there
62 * are actually three different sets of tables, one for each code page. (If
63 * Perl is compiled on platforms using other EBCDIC code pages, it may not
64 * compile, or silently mistake it for one of the three.)
65 *
66 * EBCDIC characters above 0xFF are the same as Unicode in Perl's
67 * implementation of all 3 encodings, so for those Step 1 is trivial.
68 *
69 * (Note that the entries for invariant characters are necessarily the same in
70 * PL_e2a and PLe2f, and the same for their inverses.)
71 *
72 * UTF-EBCDIC strings are the same length or longer than UTF-8 representations
73 * of the same string. The maximum code point representable as 2 bytes in
74 * UTF-EBCDIC is 0x3FFF, instead of 0x7FFF in UTF-8.
1d72bdf6 75 */
76
77START_EXTERN_C
78
79#ifdef DOINIT
80/* Indexed by encoded byte this table gives the length of the sequence.
81 Adapted from the shadow flags table in tr16.
c4d5f83a 82 The entries marked 9 in tr6 are continuation bytes and are marked
83 as length 1 here so that we can recover.
1d72bdf6 84*/
f5e1abaf 85#if '^' == 95 /* if defined(__MVS__) || defined(??) (VM/ESA?) 1047 */
1d72bdf6 86EXTCONST unsigned char PL_utf8skip[] = {
871,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
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,
c4d5f83a 911,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
921,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
931,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
941,1,1,1,2,2,2,2,2,1,1,1,1,1,1,1,
1d72bdf6 952,1,1,1,1,1,1,1,1,1,2,2,2,2,2,2,
962,1,1,1,1,1,1,1,1,1,2,2,2,2,2,2,
972,1,1,1,1,1,1,1,1,1,2,2,2,1,2,2,
982,2,2,2,2,2,2,3,3,3,3,3,3,1,3,3,
991,1,1,1,1,1,1,1,1,1,3,3,3,3,3,3,
1001,1,1,1,1,1,1,1,1,1,3,3,4,4,4,4,
1011,4,1,1,1,1,1,1,1,1,4,4,4,5,5,5,
1021,1,1,1,1,1,1,1,1,1,5,6,6,7,7,1
103};
f5e1abaf 104#endif
105
106#if '^' == 106 /* if defined(_OSD_POSIX) POSIX-BC */
107unsigned char PL_utf8skip[] = {
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,
1121,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
1131,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
1141,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
1151,1,1,1,2,2,2,2,2,3,1,1,1,1,1,1,
1162,1,1,1,1,1,1,1,1,1,2,2,2,2,2,2,
1172,1,1,1,1,1,1,1,1,1,2,2,2,2,2,2,
1182,3,1,1,1,1,1,1,1,1,2,2,2,3,2,2,
1191,2,2,2,2,2,2,3,3,3,2,1,1,1,3,3,
1204,1,1,1,1,1,1,1,1,1,3,3,3,3,3,3,
1211,1,1,1,1,1,1,1,1,1,3,3,4,6,4,4,
1227,4,1,1,1,1,1,1,1,1,4,4,4,5,5,5,
1231,1,1,1,1,1,1,1,1,1,5,1,6,1,7,1
124};
125#endif
126
127#if '^' == 176 /* if defined(??) (OS/400?) 037 */
128unsigned char PL_utf8skip[] = {
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,
1311,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
1321,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
1331,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
1341,1,1,1,1,1,1,1,1,1,1,1,1,1,1,2,
1351,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
1361,1,1,1,2,2,2,2,2,1,1,1,1,1,1,1,
1372,1,1,1,1,1,1,1,1,1,2,2,2,2,2,2,
1382,1,1,1,1,1,1,1,1,1,2,2,2,2,2,2,
1392,1,1,1,1,1,1,1,1,1,2,2,2,3,2,2,
1401,2,2,2,2,2,2,3,3,3,1,1,3,3,3,3,
1411,1,1,1,1,1,1,1,1,1,3,3,3,3,3,3,
1421,1,1,1,1,1,1,1,1,1,3,3,4,4,4,4,
1431,4,1,1,1,1,1,1,1,1,4,4,4,5,5,5,
1441,1,1,1,1,1,1,1,1,1,5,6,6,7,7,1
145};
146#endif
1d72bdf6 147
fe749c9a 148/* Transform tables from tr16 applied after encoding to render encoding EBCDIC
149 * like, meaning that all the invariants are actually invariant, eg, that 'A'
150 * remains 'A' */
1d72bdf6 151
f5e1abaf 152#if '^' == 95 /* if defined(__MVS__) || defined(??) (VM/ESA?) 1047 */
1d72bdf6 153EXTCONST unsigned char PL_utf2e[] = { /* UTF-8-mod to EBCDIC (IBM-1047) */
154 0x00, 0x01, 0x02, 0x03, 0x37, 0x2D, 0x2E, 0x2F, 0x16, 0x05, 0x15, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
155 0x10, 0x11, 0x12, 0x13, 0x3C, 0x3D, 0x32, 0x26, 0x18, 0x19, 0x3F, 0x27, 0x1C, 0x1D, 0x1E, 0x1F,
156 0x40, 0x5A, 0x7F, 0x7B, 0x5B, 0x6C, 0x50, 0x7D, 0x4D, 0x5D, 0x5C, 0x4E, 0x6B, 0x60, 0x4B, 0x61,
157 0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0xF7, 0xF8, 0xF9, 0x7A, 0x5E, 0x4C, 0x7E, 0x6E, 0x6F,
158 0x7C, 0xC1, 0xC2, 0xC3, 0xC4, 0xC5, 0xC6, 0xC7, 0xC8, 0xC9, 0xD1, 0xD2, 0xD3, 0xD4, 0xD5, 0xD6,
159 0xD7, 0xD8, 0xD9, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7, 0xE8, 0xE9, 0xAD, 0xE0, 0xBD, 0x5F, 0x6D,
160 0x79, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88, 0x89, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96,
161 0x97, 0x98, 0x99, 0xA2, 0xA3, 0xA4, 0xA5, 0xA6, 0xA7, 0xA8, 0xA9, 0xC0, 0x4F, 0xD0, 0xA1, 0x07,
162 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x06, 0x17, 0x28, 0x29, 0x2A, 0x2B, 0x2C, 0x09, 0x0A, 0x1B,
163 0x30, 0x31, 0x1A, 0x33, 0x34, 0x35, 0x36, 0x08, 0x38, 0x39, 0x3A, 0x3B, 0x04, 0x14, 0x3E, 0xFF,
164 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48, 0x49, 0x4A, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56,
165 0x57, 0x58, 0x59, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0x6A, 0x70, 0x71, 0x72, 0x73,
166 0x74, 0x75, 0x76, 0x77, 0x78, 0x80, 0x8A, 0x8B, 0x8C, 0x8D, 0x8E, 0x8F, 0x90, 0x9A, 0x9B, 0x9C,
167 0x9D, 0x9E, 0x9F, 0xA0, 0xAA, 0xAB, 0xAC, 0xAE, 0xAF, 0xB0, 0xB1, 0xB2, 0xB3, 0xB4, 0xB5, 0xB6,
168 0xB7, 0xB8, 0xB9, 0xBA, 0xBB, 0xBC, 0xBE, 0xBF, 0xCA, 0xCB, 0xCC, 0xCD, 0xCE, 0xCF, 0xDA, 0xDB,
cbbb00c6 169 0xDC, 0xDD, 0xDE, 0xDF, 0xE1, 0xEA, 0xEB, 0xEC, 0xED, 0xEE, 0xEF, 0xFA, 0xFB, 0xFC, 0xFD, 0xFE
1d72bdf6 170};
171
f5e1abaf 172EXTCONST unsigned char PL_e2utf[] = { /* EBCDIC (IBM-1047) to UTF-8-mod */
1d72bdf6 173 0x00, 0x01, 0x02, 0x03, 0x9C, 0x09, 0x86, 0x7F, 0x97, 0x8D, 0x8E, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
174 0x10, 0x11, 0x12, 0x13, 0x9D, 0x0A, 0x08, 0x87, 0x18, 0x19, 0x92, 0x8F, 0x1C, 0x1D, 0x1E, 0x1F,
175 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x17, 0x1B, 0x88, 0x89, 0x8A, 0x8B, 0x8C, 0x05, 0x06, 0x07,
176 0x90, 0x91, 0x16, 0x93, 0x94, 0x95, 0x96, 0x04, 0x98, 0x99, 0x9A, 0x9B, 0x14, 0x15, 0x9E, 0x1A,
177 0x20, 0xA0, 0xA1, 0xA2, 0xA3, 0xA4, 0xA5, 0xA6, 0xA7, 0xA8, 0xA9, 0x2E, 0x3C, 0x28, 0x2B, 0x7C,
178 0x26, 0xAA, 0xAB, 0xAC, 0xAD, 0xAE, 0xAF, 0xB0, 0xB1, 0xB2, 0x21, 0x24, 0x2A, 0x29, 0x3B, 0x5E,
179 0x2D, 0x2F, 0xB3, 0xB4, 0xB5, 0xB6, 0xB7, 0xB8, 0xB9, 0xBA, 0xBB, 0x2C, 0x25, 0x5F, 0x3E, 0x3F,
180 0xBC, 0xBD, 0xBE, 0xBF, 0xC0, 0xC1, 0xC2, 0xC3, 0xC4, 0x60, 0x3A, 0x23, 0x40, 0x27, 0x3D, 0x22,
181 0xC5, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0xC6, 0xC7, 0xC8, 0xC9, 0xCA, 0xCB,
182 0xCC, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F, 0x70, 0x71, 0x72, 0xCD, 0xCE, 0xCF, 0xD0, 0xD1, 0xD2,
183 0xD3, 0x7E, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, 0x79, 0x7A, 0xD4, 0xD5, 0xD6, 0x5B, 0xD7, 0xD8,
184 0xD9, 0xDA, 0xDB, 0xDC, 0xDD, 0xDE, 0xDF, 0xE0, 0xE1, 0xE2, 0xE3, 0xE4, 0xE5, 0x5D, 0xE6, 0xE7,
185 0x7B, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48, 0x49, 0xE8, 0xE9, 0xEA, 0xEB, 0xEC, 0xED,
186 0x7D, 0x4A, 0x4B, 0x4C, 0x4D, 0x4E, 0x4F, 0x50, 0x51, 0x52, 0xEE, 0xEF, 0xF0, 0xF1, 0xF2, 0xF3,
187 0x5C, 0xF4, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58, 0x59, 0x5A, 0xF5, 0xF6, 0xF7, 0xF8, 0xF9, 0xFA,
cbbb00c6 188 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38, 0x39, 0xFB, 0xFC, 0xFD, 0xFE, 0xFF, 0x9F
1d72bdf6 189};
f5e1abaf 190#endif /* 1047 */
191
192#if '^' == 106 /* if defined(_OSD_POSIX) POSIX-BC */
193unsigned char PL_utf2e[] = { /* UTF-8-mod to EBCDIC (POSIX-BC) */
194 0x00, 0x01, 0x02, 0x03, 0x37, 0x2D, 0x2E, 0x2F, 0x16, 0x05, 0x15, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
195 0x10, 0x11, 0x12, 0x13, 0x3C, 0x3D, 0x32, 0x26, 0x18, 0x19, 0x3F, 0x27, 0x1C, 0x1D, 0x1E, 0x1F,
196 0x40, 0x5A, 0x7F, 0x7B, 0x5B, 0x6C, 0x50, 0x7D, 0x4D, 0x5D, 0x5C, 0x4E, 0x6B, 0x60, 0x4B, 0x61,
197 0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0xF7, 0xF8, 0xF9, 0x7A, 0x5E, 0x4C, 0x7E, 0x6E, 0x6F,
198 0x7C, 0xC1, 0xC2, 0xC3, 0xC4, 0xC5, 0xC6, 0xC7, 0xC8, 0xC9, 0xD1, 0xD2, 0xD3, 0xD4, 0xD5, 0xD6,
199 0xD7, 0xD8, 0xD9, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7, 0xE8, 0xE9, 0xBB, 0xBC, 0xBD, 0x6A, 0x6D,
200 0x4A, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88, 0x89, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96,
201 0x97, 0x98, 0x99, 0xA2, 0xA3, 0xA4, 0xA5, 0xA6, 0xA7, 0xA8, 0xA9, 0xFB, 0x4F, 0xFD, 0xFF, 0x07,
202 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x06, 0x17, 0x28, 0x29, 0x2A, 0x2B, 0x2C, 0x09, 0x0A, 0x1B,
203 0x30, 0x31, 0x1A, 0x33, 0x34, 0x35, 0x36, 0x08, 0x38, 0x39, 0x3A, 0x3B, 0x04, 0x14, 0x3E, 0x5F,
204 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48, 0x49, 0xB0, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56,
205 0x57, 0x58, 0x59, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0xD0, 0x70, 0x71, 0x72, 0x73,
206 0x74, 0x75, 0x76, 0x77, 0x78, 0x80, 0x8A, 0x8B, 0x8C, 0x8D, 0x8E, 0x8F, 0x90, 0x9A, 0x9B, 0x9C,
207 0x9D, 0x9E, 0x9F, 0xA0, 0xAA, 0xAB, 0xAC, 0xAE, 0xAF, 0xBA, 0xB1, 0xB2, 0xB3, 0xB4, 0xB5, 0xB6,
208 0xB7, 0xB8, 0xB9, 0xAD, 0x79, 0xA1, 0xBE, 0xBF, 0xCA, 0xCB, 0xCC, 0xCD, 0xCE, 0xCF, 0xDA, 0xDB,
cbbb00c6 209 0xDC, 0xC0, 0xDE, 0xDF, 0xE1, 0xEA, 0xEB, 0xEC, 0xED, 0xEE, 0xEF, 0xFA, 0xDD, 0xFC, 0xE0, 0xFE
f5e1abaf 210};
211
212unsigned char PL_e2utf[] = { /* EBCDIC (POSIX-BC) to UTF-8-mod */
213 0x00, 0x01, 0x02, 0x03, 0x9C, 0x09, 0x86, 0x7F, 0x97, 0x8D, 0x8E, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
214 0x10, 0x11, 0x12, 0x13, 0x9D, 0x0A, 0x08, 0x87, 0x18, 0x19, 0x92, 0x8F, 0x1C, 0x1D, 0x1E, 0x1F,
215 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x17, 0x1B, 0x88, 0x89, 0x8A, 0x8B, 0x8C, 0x05, 0x06, 0x07,
216 0x90, 0x91, 0x16, 0x93, 0x94, 0x95, 0x96, 0x04, 0x98, 0x99, 0x9A, 0x9B, 0x14, 0x15, 0x9E, 0x1A,
217 0x20, 0xA0, 0xA1, 0xA2, 0xA3, 0xA4, 0xA5, 0xA6, 0xA7, 0xA8, 0x60, 0x2E, 0x3C, 0x28, 0x2B, 0x7C,
218 0x26, 0xAA, 0xAB, 0xAC, 0xAD, 0xAE, 0xAF, 0xB0, 0xB1, 0xB2, 0x21, 0x24, 0x2A, 0x29, 0x3B, 0x9F,
219 0x2D, 0x2F, 0xB3, 0xB4, 0xB5, 0xB6, 0xB7, 0xB8, 0xB9, 0xBA, 0x5E, 0x2C, 0x25, 0x5F, 0x3E, 0x3F,
220 0xBC, 0xBD, 0xBE, 0xBF, 0xC0, 0xC1, 0xC2, 0xC3, 0xC4, 0xE4, 0x3A, 0x23, 0x40, 0x27, 0x3D, 0x22,
221 0xC5, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0xC6, 0xC7, 0xC8, 0xC9, 0xCA, 0xCB,
222 0xCC, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F, 0x70, 0x71, 0x72, 0xCD, 0xCE, 0xCF, 0xD0, 0xD1, 0xD2,
223 0xD3, 0xE5, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, 0x79, 0x7A, 0xD4, 0xD5, 0xD6, 0xE3, 0xD7, 0xD8,
224 0xA9, 0xDA, 0xDB, 0xDC, 0xDD, 0xDE, 0xDF, 0xE0, 0xE1, 0xE2, 0xD9, 0x5B, 0x5C, 0x5D, 0xE6, 0xE7,
225 0xF1, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48, 0x49, 0xE8, 0xE9, 0xEA, 0xEB, 0xEC, 0xED,
226 0xBB, 0x4A, 0x4B, 0x4C, 0x4D, 0x4E, 0x4F, 0x50, 0x51, 0x52, 0xEE, 0xEF, 0xF0, 0xFC, 0xF2, 0xF3,
227 0xFE, 0xF4, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58, 0x59, 0x5A, 0xF5, 0xF6, 0xF7, 0xF8, 0xF9, 0xFA,
cbbb00c6 228 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38, 0x39, 0xFB, 0x7B, 0xFD, 0x7D, 0xFF, 0x7E
f5e1abaf 229};
230#endif /* POSIX-BC */
231
232#if '^' == 176 /* if defined(??) (OS/400?) 037 */
233unsigned char PL_utf2e[] = { /* UTF-8-mod to EBCDIC (IBM-037) */
234 0x00, 0x01, 0x02, 0x03, 0x37, 0x2D, 0x2E, 0x2F, 0x16, 0x05, 0x25, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
235 0x10, 0x11, 0x12, 0x13, 0x3C, 0x3D, 0x32, 0x26, 0x18, 0x19, 0x3F, 0x27, 0x1C, 0x1D, 0x1E, 0x1F,
236 0x40, 0x5A, 0x7F, 0x7B, 0x5B, 0x6C, 0x50, 0x7D, 0x4D, 0x5D, 0x5C, 0x4E, 0x6B, 0x60, 0x4B, 0x61,
237 0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0xF7, 0xF8, 0xF9, 0x7A, 0x5E, 0x4C, 0x7E, 0x6E, 0x6F,
238 0x7C, 0xC1, 0xC2, 0xC3, 0xC4, 0xC5, 0xC6, 0xC7, 0xC8, 0xC9, 0xD1, 0xD2, 0xD3, 0xD4, 0xD5, 0xD6,
239 0xD7, 0xD8, 0xD9, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7, 0xE8, 0xE9, 0xBA, 0xE0, 0xBB, 0xB0, 0x6D,
240 0x79, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88, 0x89, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96,
241 0x97, 0x98, 0x99, 0xA2, 0xA3, 0xA4, 0xA5, 0xA6, 0xA7, 0xA8, 0xA9, 0xC0, 0x4F, 0xD0, 0xA1, 0x07,
242 0x20, 0x21, 0x22, 0x23, 0x24, 0x15, 0x06, 0x17, 0x28, 0x29, 0x2A, 0x2B, 0x2C, 0x09, 0x0A, 0x1B,
243 0x30, 0x31, 0x1A, 0x33, 0x34, 0x35, 0x36, 0x08, 0x38, 0x39, 0x3A, 0x3B, 0x04, 0x14, 0x3E, 0xFF,
244 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48, 0x49, 0x4A, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56,
245 0x57, 0x58, 0x59, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0x6A, 0x70, 0x71, 0x72, 0x73,
246 0x74, 0x75, 0x76, 0x77, 0x78, 0x80, 0x8A, 0x8B, 0x8C, 0x8D, 0x8E, 0x8F, 0x90, 0x9A, 0x9B, 0x9C,
247 0x9D, 0x9E, 0x9F, 0xA0, 0xAA, 0xAB, 0xAC, 0xAE, 0xAF, 0x5F, 0xB1, 0xB2, 0xB3, 0xB4, 0xB5, 0xB6,
248 0xB7, 0xB8, 0xB9, 0xAD, 0xBD, 0xBC, 0xBE, 0xBF, 0xCA, 0xCB, 0xCC, 0xCD, 0xCE, 0xCF, 0xDA, 0xDB,
cbbb00c6 249 0xDC, 0xDD, 0xDE, 0xDF, 0xE1, 0xEA, 0xEB, 0xEC, 0xED, 0xEE, 0xEF, 0xFA, 0xFB, 0xFC, 0xFD, 0xFE
f5e1abaf 250};
251
252unsigned char PL_e2utf[] = { /* EBCDIC (IBM-037) to UTF-8-mod */
253 0x00, 0x01, 0x02, 0x03, 0x9C, 0x09, 0x86, 0x7F, 0x97, 0x8D, 0x8E, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
254 0x10, 0x11, 0x12, 0x13, 0x9D, 0x85, 0x08, 0x87, 0x18, 0x19, 0x92, 0x8F, 0x1C, 0x1D, 0x1E, 0x1F,
255 0x80, 0x81, 0x82, 0x83, 0x84, 0x0A, 0x17, 0x1B, 0x88, 0x89, 0x8A, 0x8B, 0x8C, 0x05, 0x06, 0x07,
256 0x90, 0x91, 0x16, 0x93, 0x94, 0x95, 0x96, 0x04, 0x98, 0x99, 0x9A, 0x9B, 0x14, 0x15, 0x9E, 0x1A,
257 0x20, 0xA0, 0xA1, 0xA2, 0xA3, 0xA4, 0xA5, 0xA6, 0xA7, 0xA8, 0xA9, 0x2E, 0x3C, 0x28, 0x2B, 0x7C,
258 0x26, 0xAA, 0xAB, 0xAC, 0xAD, 0xAE, 0xAF, 0xB0, 0xB1, 0xB2, 0x21, 0x24, 0x2A, 0x29, 0x3B, 0xD9,
259 0x2D, 0x2F, 0xB3, 0xB4, 0xB5, 0xB6, 0xB7, 0xB8, 0xB9, 0xBA, 0xBB, 0x2C, 0x25, 0x5F, 0x3E, 0x3F,
260 0xBC, 0xBD, 0xBE, 0xBF, 0xC0, 0xC1, 0xC2, 0xC3, 0xC4, 0x60, 0x3A, 0x23, 0x40, 0x27, 0x3D, 0x22,
261 0xC5, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0xC6, 0xC7, 0xC8, 0xC9, 0xCA, 0xCB,
262 0xCC, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F, 0x70, 0x71, 0x72, 0xCD, 0xCE, 0xCF, 0xD0, 0xD1, 0xD2,
263 0xD3, 0x7E, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, 0x79, 0x7A, 0xD4, 0xD5, 0xD6, 0xE3, 0xD7, 0xD8,
264 0x5E, 0xDA, 0xDB, 0xDC, 0xDD, 0xDE, 0xDF, 0xE0, 0xE1, 0xE2, 0x5B, 0x5D, 0xE5, 0xE4, 0xE6, 0xE7,
265 0x7B, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48, 0x49, 0xE8, 0xE9, 0xEA, 0xEB, 0xEC, 0xED,
266 0x7D, 0x4A, 0x4B, 0x4C, 0x4D, 0x4E, 0x4F, 0x50, 0x51, 0x52, 0xEE, 0xEF, 0xF0, 0xF1, 0xF2, 0xF3,
267 0x5C, 0xF4, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58, 0x59, 0x5A, 0xF5, 0xF6, 0xF7, 0xF8, 0xF9, 0xFA,
cbbb00c6 268 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38, 0x39, 0xFB, 0xFC, 0xFD, 0xFE, 0xFF, 0x9F
f5e1abaf 269};
270#endif /* 037 */
1d72bdf6 271
272/* These tables moved from perl.h and converted to hex.
273 They map platfrom code page from/to bottom 256 codes of Unicode (i.e. iso-8859-1).
274*/
275
276#if '^' == 95 /* if defined(__MVS__) || defined(??) (VM/ESA?) 1047 */
277EXTCONST unsigned char PL_a2e[] = { /* ASCII (iso-8859-1) to EBCDIC (IBM-1047) */
278 0x00, 0x01, 0x02, 0x03, 0x37, 0x2D, 0x2E, 0x2F, 0x16, 0x05, 0x15, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
279 0x10, 0x11, 0x12, 0x13, 0x3C, 0x3D, 0x32, 0x26, 0x18, 0x19, 0x3F, 0x27, 0x1C, 0x1D, 0x1E, 0x1F,
280 0x40, 0x5A, 0x7F, 0x7B, 0x5B, 0x6C, 0x50, 0x7D, 0x4D, 0x5D, 0x5C, 0x4E, 0x6B, 0x60, 0x4B, 0x61,
281 0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0xF7, 0xF8, 0xF9, 0x7A, 0x5E, 0x4C, 0x7E, 0x6E, 0x6F,
282 0x7C, 0xC1, 0xC2, 0xC3, 0xC4, 0xC5, 0xC6, 0xC7, 0xC8, 0xC9, 0xD1, 0xD2, 0xD3, 0xD4, 0xD5, 0xD6,
283 0xD7, 0xD8, 0xD9, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7, 0xE8, 0xE9, 0xAD, 0xE0, 0xBD, 0x5F, 0x6D,
284 0x79, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88, 0x89, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96,
285 0x97, 0x98, 0x99, 0xA2, 0xA3, 0xA4, 0xA5, 0xA6, 0xA7, 0xA8, 0xA9, 0xC0, 0x4F, 0xD0, 0xA1, 0x07,
286 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x06, 0x17, 0x28, 0x29, 0x2A, 0x2B, 0x2C, 0x09, 0x0A, 0x1B,
287 0x30, 0x31, 0x1A, 0x33, 0x34, 0x35, 0x36, 0x08, 0x38, 0x39, 0x3A, 0x3B, 0x04, 0x14, 0x3E, 0xFF,
288 0x41, 0xAA, 0x4A, 0xB1, 0x9F, 0xB2, 0x6A, 0xB5, 0xBB, 0xB4, 0x9A, 0x8A, 0xB0, 0xCA, 0xAF, 0xBC,
289 0x90, 0x8F, 0xEA, 0xFA, 0xBE, 0xA0, 0xB6, 0xB3, 0x9D, 0xDA, 0x9B, 0x8B, 0xB7, 0xB8, 0xB9, 0xAB,
290 0x64, 0x65, 0x62, 0x66, 0x63, 0x67, 0x9E, 0x68, 0x74, 0x71, 0x72, 0x73, 0x78, 0x75, 0x76, 0x77,
291 0xAC, 0x69, 0xED, 0xEE, 0xEB, 0xEF, 0xEC, 0xBF, 0x80, 0xFD, 0xFE, 0xFB, 0xFC, 0xBA, 0xAE, 0x59,
292 0x44, 0x45, 0x42, 0x46, 0x43, 0x47, 0x9C, 0x48, 0x54, 0x51, 0x52, 0x53, 0x58, 0x55, 0x56, 0x57,
293 0x8C, 0x49, 0xCD, 0xCE, 0xCB, 0xCF, 0xCC, 0xE1, 0x70, 0xDD, 0xDE, 0xDB, 0xDC, 0x8D, 0x8E, 0xDF
294};
295
5cd46e1f 296#define LATIN_SMALL_LETTER_Y_WITH_DIAERESIS 0xDF
297#define LATIN_SMALL_LETTER_SHARP_S 0x59
298#define MICRO_SIGN 0xA0
299
431fc773 300EXTCONST unsigned char PL_e2a[] = { /* EBCDIC (IBM-1047) to ASCII (iso-8859-1) */
1d72bdf6 301 0x00, 0x01, 0x02, 0x03, 0x9C, 0x09, 0x86, 0x7F, 0x97, 0x8D, 0x8E, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
302 0x10, 0x11, 0x12, 0x13, 0x9D, 0x0A, 0x08, 0x87, 0x18, 0x19, 0x92, 0x8F, 0x1C, 0x1D, 0x1E, 0x1F,
303 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x17, 0x1B, 0x88, 0x89, 0x8A, 0x8B, 0x8C, 0x05, 0x06, 0x07,
304 0x90, 0x91, 0x16, 0x93, 0x94, 0x95, 0x96, 0x04, 0x98, 0x99, 0x9A, 0x9B, 0x14, 0x15, 0x9E, 0x1A,
305 0x20, 0xA0, 0xE2, 0xE4, 0xE0, 0xE1, 0xE3, 0xE5, 0xE7, 0xF1, 0xA2, 0x2E, 0x3C, 0x28, 0x2B, 0x7C,
306 0x26, 0xE9, 0xEA, 0xEB, 0xE8, 0xED, 0xEE, 0xEF, 0xEC, 0xDF, 0x21, 0x24, 0x2A, 0x29, 0x3B, 0x5E,
307 0x2D, 0x2F, 0xC2, 0xC4, 0xC0, 0xC1, 0xC3, 0xC5, 0xC7, 0xD1, 0xA6, 0x2C, 0x25, 0x5F, 0x3E, 0x3F,
308 0xF8, 0xC9, 0xCA, 0xCB, 0xC8, 0xCD, 0xCE, 0xCF, 0xCC, 0x60, 0x3A, 0x23, 0x40, 0x27, 0x3D, 0x22,
309 0xD8, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0xAB, 0xBB, 0xF0, 0xFD, 0xFE, 0xB1,
310 0xB0, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F, 0x70, 0x71, 0x72, 0xAA, 0xBA, 0xE6, 0xB8, 0xC6, 0xA4,
311 0xB5, 0x7E, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, 0x79, 0x7A, 0xA1, 0xBF, 0xD0, 0x5B, 0xDE, 0xAE,
312 0xAC, 0xA3, 0xA5, 0xB7, 0xA9, 0xA7, 0xB6, 0xBC, 0xBD, 0xBE, 0xDD, 0xA8, 0xAF, 0x5D, 0xB4, 0xD7,
313 0x7B, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48, 0x49, 0xAD, 0xF4, 0xF6, 0xF2, 0xF3, 0xF5,
314 0x7D, 0x4A, 0x4B, 0x4C, 0x4D, 0x4E, 0x4F, 0x50, 0x51, 0x52, 0xB9, 0xFB, 0xFC, 0xF9, 0xFA, 0xFF,
315 0x5C, 0xF7, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58, 0x59, 0x5A, 0xB2, 0xD4, 0xD6, 0xD2, 0xD3, 0xD5,
316 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38, 0x39, 0xB3, 0xDB, 0xDC, 0xD9, 0xDA, 0x9F
317};
318#endif /* 1047 */
319
320#if '^' == 106 /* if defined(_OSD_POSIX) POSIX-BC */
321EXTCONST unsigned char PL_a2e[] = { /* ASCII (ISO8859-1) to EBCDIC (POSIX-BC) */
322 0x00, 0x01, 0x02, 0x03, 0x37, 0x2D, 0x2E, 0x2F, 0x16, 0x05, 0x15, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
323 0x10, 0x11, 0x12, 0x13, 0x3C, 0x3D, 0x32, 0x26, 0x18, 0x19, 0x3F, 0x27, 0x1C, 0x1D, 0x1E, 0x1F,
324 0x40, 0x5A, 0x7F, 0x7B, 0x5B, 0x6C, 0x50, 0x7D, 0x4D, 0x5D, 0x5C, 0x4E, 0x6B, 0x60, 0x4B, 0x61,
325 0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0xF7, 0xF8, 0xF9, 0x7A, 0x5E, 0x4C, 0x7E, 0x6E, 0x6F,
326 0x7C, 0xC1, 0xC2, 0xC3, 0xC4, 0xC5, 0xC6, 0xC7, 0xC8, 0xC9, 0xD1, 0xD2, 0xD3, 0xD4, 0xD5, 0xD6,
327 0xD7, 0xD8, 0xD9, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7, 0xE8, 0xE9, 0xBB, 0xBC, 0xBD, 0x6A, 0x6D,
328 0x4A, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88, 0x89, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96,
329 0x97, 0x98, 0x99, 0xA2, 0xA3, 0xA4, 0xA5, 0xA6, 0xA7, 0xA8, 0xA9, 0xFB, 0x4F, 0xFD, 0xFF, 0x07,
330 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x06, 0x17, 0x28, 0x29, 0x2A, 0x2B, 0x2C, 0x09, 0x0A, 0x1B,
331 0x30, 0x31, 0x1A, 0x33, 0x34, 0x35, 0x36, 0x08, 0x38, 0x39, 0x3A, 0x3B, 0x04, 0x14, 0x3E, 0x5F,
332 0x41, 0xAA, 0xB0, 0xB1, 0x9F, 0xB2, 0xD0, 0xB5, 0x79, 0xB4, 0x9A, 0x8A, 0xBA, 0xCA, 0xAF, 0xA1,
333 0x90, 0x8F, 0xEA, 0xFA, 0xBE, 0xA0, 0xB6, 0xB3, 0x9D, 0xDA, 0x9B, 0x8B, 0xB7, 0xB8, 0xB9, 0xAB,
334 0x64, 0x65, 0x62, 0x66, 0x63, 0x67, 0x9E, 0x68, 0x74, 0x71, 0x72, 0x73, 0x78, 0x75, 0x76, 0x77,
335 0xAC, 0x69, 0xED, 0xEE, 0xEB, 0xEF, 0xEC, 0xBF, 0x80, 0xE0, 0xFE, 0xDD, 0xFC, 0xAD, 0xAE, 0x59,
336 0x44, 0x45, 0x42, 0x46, 0x43, 0x47, 0x9C, 0x48, 0x54, 0x51, 0x52, 0x53, 0x58, 0x55, 0x56, 0x57,
337 0x8C, 0x49, 0xCD, 0xCE, 0xCB, 0xCF, 0xCC, 0xE1, 0x70, 0xC0, 0xDE, 0xDB, 0xDC, 0x8D, 0x8E, 0xDF
338};
339
5cd46e1f 340#define LATIN_SMALL_LETTER_Y_WITH_DIAERESIS 0xDF
341#define LATIN_SMALL_LETTER_SHARP_S 0x59
342#define MICRO_SIGN 0xA0
343
1d72bdf6 344EXTCONST unsigned char PL_e2a[] = { /* EBCDIC (POSIX-BC) to ASCII (ISO8859-1) */
345 0x00, 0x01, 0x02, 0x03, 0x9C, 0x09, 0x86, 0x7F, 0x97, 0x8D, 0x8E, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
346 0x10, 0x11, 0x12, 0x13, 0x9D, 0x0A, 0x08, 0x87, 0x18, 0x19, 0x92, 0x8F, 0x1C, 0x1D, 0x1E, 0x1F,
347 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x17, 0x1B, 0x88, 0x89, 0x8A, 0x8B, 0x8C, 0x05, 0x06, 0x07,
348 0x90, 0x91, 0x16, 0x93, 0x94, 0x95, 0x96, 0x04, 0x98, 0x99, 0x9A, 0x9B, 0x14, 0x15, 0x9E, 0x1A,
349 0x20, 0xA0, 0xE2, 0xE4, 0xE0, 0xE1, 0xE3, 0xE5, 0xE7, 0xF1, 0x60, 0x2E, 0x3C, 0x28, 0x2B, 0x7C,
350 0x26, 0xE9, 0xEA, 0xEB, 0xE8, 0xED, 0xEE, 0xEF, 0xEC, 0xDF, 0x21, 0x24, 0x2A, 0x29, 0x3B, 0x9F,
351 0x2D, 0x2F, 0xC2, 0xC4, 0xC0, 0xC1, 0xC3, 0xC5, 0xC7, 0xD1, 0x5E, 0x2C, 0x25, 0x5F, 0x3E, 0x3F,
352 0xF8, 0xC9, 0xCA, 0xCB, 0xC8, 0xCD, 0xCE, 0xCF, 0xCC, 0xA8, 0x3A, 0x23, 0x40, 0x27, 0x3D, 0x22,
353 0xD8, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0xAB, 0xBB, 0xF0, 0xFD, 0xFE, 0xB1,
354 0xB0, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F, 0x70, 0x71, 0x72, 0xAA, 0xBA, 0xE6, 0xB8, 0xC6, 0xA4,
355 0xB5, 0xAF, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, 0x79, 0x7A, 0xA1, 0xBF, 0xD0, 0xDD, 0xDE, 0xAE,
356 0xA2, 0xA3, 0xA5, 0xB7, 0xA9, 0xA7, 0xB6, 0xBC, 0xBD, 0xBE, 0xAC, 0x5B, 0x5C, 0x5D, 0xB4, 0xD7,
357 0xF9, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48, 0x49, 0xAD, 0xF4, 0xF6, 0xF2, 0xF3, 0xF5,
358 0xA6, 0x4A, 0x4B, 0x4C, 0x4D, 0x4E, 0x4F, 0x50, 0x51, 0x52, 0xB9, 0xFB, 0xFC, 0xDB, 0xFA, 0xFF,
359 0xD9, 0xF7, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58, 0x59, 0x5A, 0xB2, 0xD4, 0xD6, 0xD2, 0xD3, 0xD5,
360 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38, 0x39, 0xB3, 0x7B, 0xDC, 0x7D, 0xDA, 0x7E
361};
362#endif /* POSIX-BC */
f5e1abaf 363
1d72bdf6 364#if '^' == 176 /* if defined(??) (OS/400?) 037 */
365EXTCONST unsigned char PL_a2e[] = { /* ASCII (ISO8859-1) to EBCDIC (IBM-037) */
366 0x00, 0x01, 0x02, 0x03, 0x37, 0x2D, 0x2E, 0x2F, 0x16, 0x05, 0x25, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
367 0x10, 0x11, 0x12, 0x13, 0x3C, 0x3D, 0x32, 0x26, 0x18, 0x19, 0x3F, 0x27, 0x1C, 0x1D, 0x1E, 0x1F,
368 0x40, 0x5A, 0x7F, 0x7B, 0x5B, 0x6C, 0x50, 0x7D, 0x4D, 0x5D, 0x5C, 0x4E, 0x6B, 0x60, 0x4B, 0x61,
369 0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0xF7, 0xF8, 0xF9, 0x7A, 0x5E, 0x4C, 0x7E, 0x6E, 0x6F,
370 0x7C, 0xC1, 0xC2, 0xC3, 0xC4, 0xC5, 0xC6, 0xC7, 0xC8, 0xC9, 0xD1, 0xD2, 0xD3, 0xD4, 0xD5, 0xD6,
371 0xD7, 0xD8, 0xD9, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7, 0xE8, 0xE9, 0xBA, 0xE0, 0xBB, 0xB0, 0x6D,
372 0x79, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88, 0x89, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96,
373 0x97, 0x98, 0x99, 0xA2, 0xA3, 0xA4, 0xA5, 0xA6, 0xA7, 0xA8, 0xA9, 0xC0, 0x4F, 0xD0, 0xA1, 0x07,
374 0x20, 0x21, 0x22, 0x23, 0x24, 0x15, 0x06, 0x17, 0x28, 0x29, 0x2A, 0x2B, 0x2C, 0x09, 0x0A, 0x1B,
375 0x30, 0x31, 0x1A, 0x33, 0x34, 0x35, 0x36, 0x08, 0x38, 0x39, 0x3A, 0x3B, 0x04, 0x14, 0x3E, 0xFF,
376 0x41, 0xAA, 0x4A, 0xB1, 0x9F, 0xB2, 0x6A, 0xB5, 0xBD, 0xB4, 0x9A, 0x8A, 0x5F, 0xCA, 0xAF, 0xBC,
377 0x90, 0x8F, 0xEA, 0xFA, 0xBE, 0xA0, 0xB6, 0xB3, 0x9D, 0xDA, 0x9B, 0x8B, 0xB7, 0xB8, 0xB9, 0xAB,
378 0x64, 0x65, 0x62, 0x66, 0x63, 0x67, 0x9E, 0x68, 0x74, 0x71, 0x72, 0x73, 0x78, 0x75, 0x76, 0x77,
379 0xAC, 0x69, 0xED, 0xEE, 0xEB, 0xEF, 0xEC, 0xBF, 0x80, 0xFD, 0xFE, 0xFB, 0xFC, 0xAD, 0xAE, 0x59,
380 0x44, 0x45, 0x42, 0x46, 0x43, 0x47, 0x9C, 0x48, 0x54, 0x51, 0x52, 0x53, 0x58, 0x55, 0x56, 0x57,
381 0x8C, 0x49, 0xCD, 0xCE, 0xCB, 0xCF, 0xCC, 0xE1, 0x70, 0xDD, 0xDE, 0xDB, 0xDC, 0x8D, 0x8E, 0xDF
382};
383
5cd46e1f 384
385#define LATIN_SMALL_LETTER_Y_WITH_DIAERESIS 0xDF
386#define LATIN_SMALL_LETTER_SHARP_S 0x59
387#define MICRO_SIGN 0xA0
388
1d72bdf6 389EXTCONST unsigned char PL_e2a[] = { /* EBCDIC (IBM-037) to ASCII (ISO8859-1) */
390 0x00, 0x01, 0x02, 0x03, 0x9C, 0x09, 0x86, 0x7F, 0x97, 0x8D, 0x8E, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
391 0x10, 0x11, 0x12, 0x13, 0x9D, 0x85, 0x08, 0x87, 0x18, 0x19, 0x92, 0x8F, 0x1C, 0x1D, 0x1E, 0x1F,
392 0x80, 0x81, 0x82, 0x83, 0x84, 0x0A, 0x17, 0x1B, 0x88, 0x89, 0x8A, 0x8B, 0x8C, 0x05, 0x06, 0x07,
393 0x90, 0x91, 0x16, 0x93, 0x94, 0x95, 0x96, 0x04, 0x98, 0x99, 0x9A, 0x9B, 0x14, 0x15, 0x9E, 0x1A,
394 0x20, 0xA0, 0xE2, 0xE4, 0xE0, 0xE1, 0xE3, 0xE5, 0xE7, 0xF1, 0xA2, 0x2E, 0x3C, 0x28, 0x2B, 0x7C,
395 0x26, 0xE9, 0xEA, 0xEB, 0xE8, 0xED, 0xEE, 0xEF, 0xEC, 0xDF, 0x21, 0x24, 0x2A, 0x29, 0x3B, 0xAC,
396 0x2D, 0x2F, 0xC2, 0xC4, 0xC0, 0xC1, 0xC3, 0xC5, 0xC7, 0xD1, 0xA6, 0x2C, 0x25, 0x5F, 0x3E, 0x3F,
397 0xF8, 0xC9, 0xCA, 0xCB, 0xC8, 0xCD, 0xCE, 0xCF, 0xCC, 0x60, 0x3A, 0x23, 0x40, 0x27, 0x3D, 0x22,
398 0xD8, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0xAB, 0xBB, 0xF0, 0xFD, 0xFE, 0xB1,
399 0xB0, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F, 0x70, 0x71, 0x72, 0xAA, 0xBA, 0xE6, 0xB8, 0xC6, 0xA4,
400 0xB5, 0x7E, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, 0x79, 0x7A, 0xA1, 0xBF, 0xD0, 0xDD, 0xDE, 0xAE,
401 0x5E, 0xA3, 0xA5, 0xB7, 0xA9, 0xA7, 0xB6, 0xBC, 0xBD, 0xBE, 0x5B, 0x5D, 0xAF, 0xA8, 0xB4, 0xD7,
402 0x7B, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48, 0x49, 0xAD, 0xF4, 0xF6, 0xF2, 0xF3, 0xF5,
403 0x7D, 0x4A, 0x4B, 0x4C, 0x4D, 0x4E, 0x4F, 0x50, 0x51, 0x52, 0xB9, 0xFB, 0xFC, 0xF9, 0xFA, 0xFF,
404 0x5C, 0xF7, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58, 0x59, 0x5A, 0xB2, 0xD4, 0xD6, 0xD2, 0xD3, 0xD5,
405 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38, 0x39, 0xB3, 0xDB, 0xDC, 0xD9, 0xDA, 0x9F
406};
407#endif /* 037 */
408
409#else
410EXTCONST unsigned char PL_utf8skip[];
411EXTCONST unsigned char PL_e2utf[];
412EXTCONST unsigned char PL_utf2e[];
413EXTCONST unsigned char PL_e2a[];
414EXTCONST unsigned char PL_a2e[];
415#endif
416
417END_EXTERN_C
418
66af24e1 419#define UTF8SKIP(s) PL_utf8skip[*(const U8*)(s)]
1d72bdf6 420
1e54db1a 421/* EBCDIC-happy ways of converting native code to UTF-8 */
1d72bdf6 422
423/* Native to iso-8859-1 */
424#define NATIVE_TO_ASCII(ch) PL_e2a[(U8)(ch)]
5cd46e1f 425#define NATIVE8_TO_UNI(ch) NATIVE_TO_ASCII(ch) /* a clearer synonym */
1d72bdf6 426#define ASCII_TO_NATIVE(ch) PL_a2e[(U8)(ch)]
427/* Transform after encoding */
428#define NATIVE_TO_UTF(ch) PL_e2utf[(U8)(ch)]
429#define UTF_TO_NATIVE(ch) PL_utf2e[(U8)(ch)]
430/* Transform in wide UV char space */
431#define NATIVE_TO_UNI(ch) (((ch) > 255) ? (ch) : NATIVE_TO_ASCII(ch))
c4d5f83a 432#define UNI_TO_NATIVE(ch) (((ch) > 255) ? (ch) : ASCII_TO_NATIVE(ch))
1d72bdf6 433/* Transform in invariant..byte space */
434#define NATIVE_TO_NEED(enc,ch) ((enc) ? UTF_TO_NATIVE(NATIVE_TO_ASCII(ch)) : (ch))
435#define ASCII_TO_NEED(enc,ch) ((enc) ? UTF_TO_NATIVE(ch) : ASCII_TO_NATIVE(ch))
436
437/*
438 * Note: we should try and be careful never to call the isXXX_utf8() functions
439 * unless we're pretty sure we've seen the beginning of a UTF-EBCDIC character
979f2922 440 * Otherwise we risk loading in the heavy-duty swash_init and swash_fetch
441 * routines unnecessarily.
1d72bdf6 442 */
443
0064a8a9 444#define isIDFIRST_lazy_if(p,c) ((IN_BYTES || (!c || UTF8_IS_INVARIANT(*p))) \
1d72bdf6 445 ? isIDFIRST(*(p)) \
e1ec3a88 446 : isIDFIRST_utf8((const U8*)p))
0064a8a9 447#define isALNUM_lazy_if(p,c) ((IN_BYTES || (!c || UTF8_IS_INVARIANT(*p))) \
1d72bdf6 448 ? isALNUM(*(p)) \
e1ec3a88 449 : isALNUM_utf8((const U8*)p))
1d72bdf6 450
451/*
452 The following table is adapted from tr16, it shows UTF-8-mod encoding of Unicode code points.
453
454 Unicode Bit pattern 1st Byte 2nd Byte 3rd Byte 4th Byte 5th Byte 6th Byte 7th byte
455 U+0000..U+007F 000000000xxxxxxx 0xxxxxxx
456 U+0080..U+009F 00000000100xxxxx 100xxxxx
457 U+00A0..U+00FF 00000000yyyxxxxx 11000yyy 101xxxxx
458
459 U+00A0..U+03FF 000000yyyyyxxxxx 110yyyyy 101xxxxx
460 U+0400..U+3FFF 00zzzzyyyyyxxxxx 1110zzzz 101yyyyy 101xxxxx
461 U+4000..U+3FFFF 0wwwzzzzzyyyyyxxxxx 11110www 101zzzzz 101yyyyy 101xxxxx
462 U+40000..U+3FFFFF 0vvwwwwwzzzzzyyyyyxxxxx 111110vv 101wwwww 101zzzzz 101yyyyy 101xxxxx
463 U+400000..U+3FFFFFF 0uvvvvvwwwwwzzzzzyyyyyxxxxx 1111110u 101vvvvv 101wwwww 101zzzzz 101yyyyy 101xxxxx
464 U+4000000..U+7FFFFFFF 0tuuuuuvvvvvwwwwwzzzzzyyyyyxxxxx 1111111t 101uuuuu 101vvvvv 101wwwww 101zzzzz 101yyyyy 101xxxxx
465
466 Note: The UTF-8-Mod transformation is valid for UCS-4 values X'0' to
467 X'7FFFFFFF' (the full extent of ISO/IEC 10646 coding space).
468
469 */
470
471#define UNISKIP(uv) ( (uv) < 0xA0 ? 1 : \
472 (uv) < 0x400 ? 2 : \
473 (uv) < 0x4000 ? 3 : \
474 (uv) < 0x40000 ? 4 : \
475 (uv) < 0x400000 ? 5 : \
476 (uv) < 0x4000000 ? 6 : 7 )
477
c4d5f83a 478
479#define UNI_IS_INVARIANT(c) ((c) < 0xA0)
1d72bdf6 480/* UTF-EBCDIC sematic macros - transform back into UTF-8-Mod and then compare */
b3ab6785 481#define NATIVE_IS_INVARIANT(c) UNI_IS_INVARIANT(NATIVE8_TO_UNI(c))
c4d5f83a 482#define UTF8_IS_INVARIANT(c) UNI_IS_INVARIANT(NATIVE_TO_UTF(c))
1d72bdf6 483#define UTF8_IS_START(c) (NATIVE_TO_UTF(c) >= 0xA0 && (NATIVE_TO_UTF(c) & 0xE0) != 0xA0)
2b9d42f0 484#define UTF8_IS_CONTINUATION(c) ((NATIVE_TO_UTF(c) & 0xE0) == 0xA0)
1d72bdf6 485#define UTF8_IS_CONTINUED(c) (NATIVE_TO_UTF(c) >= 0xA0)
486#define UTF8_IS_DOWNGRADEABLE_START(c) (NATIVE_TO_UTF(c) >= 0xA0 && (NATIVE_TO_UTF(c) & 0xF8) == 0xC0)
487
22901f30 488#define UTF_START_MARK(len) (((len) > 7) ? 0xFF : ((U8)(0xFE << (7-(len)))))
489#define UTF_START_MASK(len) (((len) >= 6) ? 0x01 : (0x1F >> ((len)-2)))
1d72bdf6 490#define UTF_CONTINUATION_MARK 0xA0
491#define UTF_CONTINUATION_MASK ((U8)0x1f)
492#define UTF_ACCUMULATION_SHIFT 5
493
75383841 494#define UTF8_ACCUMULATE(old, new) (((old) << UTF_ACCUMULATION_SHIFT)|(NATIVE_TO_UTF(new) & UTF_CONTINUATION_MASK))
1d72bdf6 495
496/* UTF-EBCDIC encode a downgradeable value */
497#define UTF8_EIGHT_BIT_HI(c) UTF_TO_NATIVE((((U8)(c))>>UTF_ACCUMULATION_SHIFT)|UTF_START_MARK(2))
498#define UTF8_EIGHT_BIT_LO(c) UTF_TO_NATIVE(((((U8)(c)))&UTF_CONTINUATION_MASK)|UTF_CONTINUATION_MARK)
499
e9a8c099 500/*
501 * Local variables:
502 * c-indentation-style: bsd
503 * c-basic-offset: 4
504 * indent-tabs-mode: t
505 * End:
506 *
507 * ex: set ts=8 sts=4 sw=4 noet:
508 */