This is a live mirror of the Perl 5 development currently hosted at https://github.com/perl/perl5
Add C macros for UTF-8 for BOM and REPLACEMENT CHARACTER
[perl5.git] / unicode_constants.h
CommitLineData
61dad979
KW
1/* -*- buffer-read-only: t -*-
2 * !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
1b0f46bf 3 * This file is built by regen/unicode_constants.pl from Unicode data.
61dad979
KW
4 * Any changes made here will be lost!
5 */
6
d10c72f2 7
1b0f46bf
KW
8#ifndef H_UNICODE_CONSTANTS /* Guard against nested #includes */
9#define H_UNICODE_CONSTANTS 1
d10c72f2 10
4b4853d1
KW
11/* This file contains #defines for the version of Unicode being used and
12 * various Unicode code points. The values the code point macros expand to
13 * are the native Unicode code point, or all or portions of the UTF-8 encoding
14 * for the code point. In the former case, the macro name has the suffix
15 * "_NATIVE"; otherwise, the suffix "_UTF8".
61dad979 16 *
525b6419
KW
17 * The macros that have the suffix "_UTF8" may have further suffixes, as
18 * follows:
19 * "_FIRST_BYTE" if the value is just the first byte of the UTF-8
20 * representation; the value will be a numeric constant.
21 * "_TAIL" if instead it represents all but the first byte. This, and
22 * with no additional suffix are both string constants */
61dad979 23
69bc4c1f
KW
24/*
25=head1 Unicode Support
26
27=for apidoc AmU|placeholder|BOM_UTF8
28
29This is a macro that evaluates to a string constant of the UTF-8 bytes that
30define the Unicode BYTE ORDER MARK (U+FEFF) for the platform that perl
31is compiled on. This allows code to use a mnemonic for this character that
32works on both ASCII and EBCDIC platforms.
33S<C<sizeof(BOM_UTF8) - 1>> can be used to get its length in
34bytes.
35
36=for apidoc AmU|placeholder|REPLACEMENT_CHARACTER_UTF8
37
38This is a macro that evaluates to a string constant of the UTF-8 bytes that
39define the Unicode REPLACEMENT CHARACTER (U+FFFD) for the platform that perl
40is compiled on. This allows code to use a mnemonic for this character that
41works on both ASCII and EBCDIC platforms.
42S<C<sizeof(REPLACEMENT_CHARACTER_UTF8) - 1>> can be used to get its length in
43bytes.
44
45=cut
46*/
47
f2bfbac0 48#define UNICODE_MAJOR_VERSION 9
4b4853d1
KW
49#define UNICODE_DOT_VERSION 0
50#define UNICODE_DOT_DOT_VERSION 0
51
76837d21 52
ad88cddb
KW
53#if 'A' == 65 /* ASCII/Latin1 */
54# define LATIN_SMALL_LETTER_LONG_S_UTF8 "\xC5\xBF" /* U+017F */
76837d21 55
ad88cddb 56# define COMBINING_GRAVE_ACCENT_UTF8 "\xCC\x80" /* U+0300 */
a78bc3c6 57
ad88cddb
KW
58# define GREEK_CAPITAL_LETTER_IOTA_UTF8 "\xCE\x99" /* U+0399 */
59# define GREEK_SMALL_LETTER_MU_UTF8 "\xCE\xBC" /* U+03BC */
f2e06375 60
ad88cddb 61# define LATIN_CAPITAL_LETTER_SHARP_S_UTF8 "\xE1\xBA\x9E" /* U+1E9E */
a9f50d33 62
ad88cddb
KW
63# define LATIN_SMALL_LIGATURE_LONG_S_T_UTF8 "\xEF\xAC\x85" /* U+FB05 */
64# define LATIN_SMALL_LIGATURE_ST_UTF8 "\xEF\xAC\x86" /* U+FB06 */
a0ffb25e
KW
65# define LATIN_CAPITAL_LETTER_I_WITH_DOT_ABOVE_UTF8 "\xC4\xB0" /* U+0130 */
66# define LATIN_SMALL_LETTER_DOTLESS_I_UTF8 "\xC4\xB1" /* U+0131 */
1dfa4f52 67
ad88cddb 68# define HYPHEN_UTF8 "\xE2\x80\x90" /* U+2010 */
ad88cddb
KW
69# define BOM_UTF8_FIRST_BYTE 0xEF /* U+FEFF */
70# define BOM_UTF8_TAIL "\xBB\xBF" /* U+FEFF */
df758df2 71
69bc4c1f
KW
72# define BOM_UTF8 "\xEF\xBB\xBF" /* U+FEFF */
73
74# define REPLACEMENT_CHARACTER_UTF8 "\xEF\xBF\xBD" /* U+FFFD */
75
ad88cddb
KW
76# define NBSP_NATIVE 0xA0 /* U+00A0 */
77# define NBSP_UTF8 "\xC2\xA0" /* U+00A0 */
78
79# define DEL_NATIVE 0x7F /* U+007F */
80# define CR_NATIVE 0x0D /* U+000D */
81# define LF_NATIVE 0x0A /* U+000A */
d804860b
KW
82# define VT_NATIVE 0x0B /* U+000B */
83# define ESC_NATIVE 0x1B /* U+001B */
ad88cddb
KW
84# define LATIN_SMALL_LETTER_SHARP_S_NATIVE 0xDF /* U+00DF */
85# define LATIN_SMALL_LETTER_A_WITH_RING_ABOVE_NATIVE 0xE5 /* U+00E5 */
86# define LATIN_CAPITAL_LETTER_A_WITH_RING_ABOVE_NATIVE 0xC5 /* U+00C5 */
87# define LATIN_SMALL_LETTER_Y_WITH_DIAERESIS_NATIVE 0xFF /* U+00FF */
88# define MICRO_SIGN_NATIVE 0xB5 /* U+00B5 */
09cc440d 89# define MAX_PRINT_A_FOR_USE_ONLY_BY_REGCOMP_DOT_C 0x7E /* The max code point that isPRINT_A */
ad88cddb
KW
90
91#endif /* ASCII/Latin1 */
92
93#if 'A' == 193 /* EBCDIC 1047 */ \
94 && '\\' == 224 && '[' == 173 && ']' == 189 && '{' == 192 && '}' == 208 \
95 && '^' == 95 && '~' == 161 && '!' == 90 && '#' == 123 && '|' == 79 \
96 && '$' == 91 && '@' == 124 && '`' == 121
97# define LATIN_SMALL_LETTER_LONG_S_UTF8 "\x8F\x73" /* U+017F */
98
99# define COMBINING_GRAVE_ACCENT_UTF8 "\xAF\x41" /* U+0300 */
100
101# define GREEK_CAPITAL_LETTER_IOTA_UTF8 "\xB3\x68" /* U+0399 */
102# define GREEK_SMALL_LETTER_MU_UTF8 "\xB4\x70" /* U+03BC */
103
104# define LATIN_CAPITAL_LETTER_SHARP_S_UTF8 "\xBF\x63\x72" /* U+1E9E */
105
106# define LATIN_SMALL_LIGATURE_LONG_S_T_UTF8 "\xDD\x72\x67\x46" /* U+FB05 */
107# define LATIN_SMALL_LIGATURE_ST_UTF8 "\xDD\x72\x67\x47" /* U+FB06 */
a0ffb25e
KW
108# define LATIN_CAPITAL_LETTER_I_WITH_DOT_ABOVE_UTF8 "\x8D\x57" /* U+0130 */
109# define LATIN_SMALL_LETTER_DOTLESS_I_UTF8 "\x8D\x58" /* U+0131 */
ad88cddb
KW
110
111# define HYPHEN_UTF8 "\xCA\x41\x57" /* U+2010 */
ad88cddb
KW
112# define BOM_UTF8_FIRST_BYTE 0xDD /* U+FEFF */
113# define BOM_UTF8_TAIL "\x73\x66\x73" /* U+FEFF */
114
69bc4c1f
KW
115# define BOM_UTF8 "\xDD\x73\x66\x73" /* U+FEFF */
116
117# define REPLACEMENT_CHARACTER_UTF8 "\xDD\x73\x73\x71" /* U+FFFD */
118
ad88cddb
KW
119# define NBSP_NATIVE 0x41 /* U+00A0 */
120# define NBSP_UTF8 "\x80\x41" /* U+00A0 */
121
122# define DEL_NATIVE 0x07 /* U+007F */
123# define CR_NATIVE 0x0D /* U+000D */
124# define LF_NATIVE 0x15 /* U+000A */
d804860b
KW
125# define VT_NATIVE 0x0B /* U+000B */
126# define ESC_NATIVE 0x27 /* U+001B */
ad88cddb
KW
127# define LATIN_SMALL_LETTER_SHARP_S_NATIVE 0x59 /* U+00DF */
128# define LATIN_SMALL_LETTER_A_WITH_RING_ABOVE_NATIVE 0x47 /* U+00E5 */
129# define LATIN_CAPITAL_LETTER_A_WITH_RING_ABOVE_NATIVE 0x67 /* U+00C5 */
130# define LATIN_SMALL_LETTER_Y_WITH_DIAERESIS_NATIVE 0xDF /* U+00FF */
131# define MICRO_SIGN_NATIVE 0xA0 /* U+00B5 */
09cc440d 132# define MAX_PRINT_A_FOR_USE_ONLY_BY_REGCOMP_DOT_C 0xF9 /* The max code point that isPRINT_A */
ad88cddb
KW
133
134#endif /* EBCDIC 1047 */
135
136#if 'A' == 193 /* EBCDIC 037 */ \
137 && '\\' == 224 && '[' == 186 && ']' == 187 && '{' == 192 && '}' == 208 \
138 && '^' == 176 && '~' == 161 && '!' == 90 && '#' == 123 && '|' == 79 \
139 && '$' == 91 && '@' == 124 && '`' == 121
140# define LATIN_SMALL_LETTER_LONG_S_UTF8 "\x8E\x72" /* U+017F */
141
142# define COMBINING_GRAVE_ACCENT_UTF8 "\xAD\x41" /* U+0300 */
143
144# define GREEK_CAPITAL_LETTER_IOTA_UTF8 "\xB2\x67" /* U+0399 */
145# define GREEK_SMALL_LETTER_MU_UTF8 "\xB3\x6A" /* U+03BC */
146
147# define LATIN_CAPITAL_LETTER_SHARP_S_UTF8 "\xBF\x62\x71" /* U+1E9E */
148
149# define LATIN_SMALL_LIGATURE_LONG_S_T_UTF8 "\xDD\x71\x66\x46" /* U+FB05 */
150# define LATIN_SMALL_LIGATURE_ST_UTF8 "\xDD\x71\x66\x47" /* U+FB06 */
a0ffb25e
KW
151# define LATIN_CAPITAL_LETTER_I_WITH_DOT_ABOVE_UTF8 "\x8C\x57" /* U+0130 */
152# define LATIN_SMALL_LETTER_DOTLESS_I_UTF8 "\x8C\x58" /* U+0131 */
ad88cddb
KW
153
154# define HYPHEN_UTF8 "\xCA\x41\x57" /* U+2010 */
ad88cddb
KW
155# define BOM_UTF8_FIRST_BYTE 0xDD /* U+FEFF */
156# define BOM_UTF8_TAIL "\x72\x65\x72" /* U+FEFF */
157
69bc4c1f
KW
158# define BOM_UTF8 "\xDD\x72\x65\x72" /* U+FEFF */
159
160# define REPLACEMENT_CHARACTER_UTF8 "\xDD\x72\x72\x70" /* U+FFFD */
161
ad88cddb
KW
162# define NBSP_NATIVE 0x41 /* U+00A0 */
163# define NBSP_UTF8 "\x78\x41" /* U+00A0 */
164
165# define DEL_NATIVE 0x07 /* U+007F */
166# define CR_NATIVE 0x0D /* U+000D */
167# define LF_NATIVE 0x25 /* U+000A */
d804860b
KW
168# define VT_NATIVE 0x0B /* U+000B */
169# define ESC_NATIVE 0x27 /* U+001B */
ad88cddb
KW
170# define LATIN_SMALL_LETTER_SHARP_S_NATIVE 0x59 /* U+00DF */
171# define LATIN_SMALL_LETTER_A_WITH_RING_ABOVE_NATIVE 0x47 /* U+00E5 */
172# define LATIN_CAPITAL_LETTER_A_WITH_RING_ABOVE_NATIVE 0x67 /* U+00C5 */
173# define LATIN_SMALL_LETTER_Y_WITH_DIAERESIS_NATIVE 0xDF /* U+00FF */
174# define MICRO_SIGN_NATIVE 0xA0 /* U+00B5 */
09cc440d 175# define MAX_PRINT_A_FOR_USE_ONLY_BY_REGCOMP_DOT_C 0xF9 /* The max code point that isPRINT_A */
ad88cddb
KW
176
177#endif /* EBCDIC 037 */
178
b35552de 179/* The number of code points not matching \pC */
f2bfbac0 180#define NON_OTHER_COUNT_FOR_USE_ONLY_BY_REGCOMP_DOT_C 128021
b35552de 181
3bfc1e70 182/* The highest code point that has any type of case change */
f2bfbac0 183#define HIGHEST_CASE_CHANGING_CP_FOR_USE_ONLY_BY_UTF8_DOT_C 0x1E943
3bfc1e70 184
1b0f46bf 185#endif /* H_UNICODE_CONSTANTS */
d10c72f2 186
61dad979 187/* ex: set ro: */