1 /* -*- buffer-read-only: t -*-
2 * !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
3 * This file is built by regen/unicode_constants.pl from Unicode data.
4 * Any changes made here will be lost!
8 #ifndef PERL_UNICODE_CONSTANTS_H_ /* Guard against nested #includes */
9 #define PERL_UNICODE_CONSTANTS_H_ 1
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".
17 * The macros that have the suffix "_UTF8" may have further suffixes, as
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 */
25 =head1 Unicode Support
27 =for apidoc AmU|placeholder|BOM_UTF8
29 This is a macro that evaluates to a string constant of the UTF-8 bytes that
30 define the Unicode BYTE ORDER MARK (U+FEFF) for the platform that perl
31 is compiled on. This allows code to use a mnemonic for this character that
32 works on both ASCII and EBCDIC platforms.
33 S<C<sizeof(BOM_UTF8) - 1>> can be used to get its length in
36 =for apidoc AmU|placeholder|REPLACEMENT_CHARACTER_UTF8
38 This is a macro that evaluates to a string constant of the UTF-8 bytes that
39 define the Unicode REPLACEMENT CHARACTER (U+FFFD) for the platform that perl
40 is compiled on. This allows code to use a mnemonic for this character that
41 works on both ASCII and EBCDIC platforms.
42 S<C<sizeof(REPLACEMENT_CHARACTER_UTF8) - 1>> can be used to get its length in
48 #define UNICODE_MAJOR_VERSION 11
49 #define UNICODE_DOT_VERSION 0
50 #define UNICODE_DOT_DOT_VERSION 0
53 #if 'A' == 65 /* ASCII/Latin1 */
54 # define LATIN_SMALL_LETTER_LONG_S_UTF8 "\xC5\xBF" /* U+017F */
56 # define COMBINING_GRAVE_ACCENT_UTF8 "\xCC\x80" /* U+0300 */
58 # define GREEK_CAPITAL_LETTER_IOTA_UTF8 "\xCE\x99" /* U+0399 */
59 # define GREEK_SMALL_LETTER_MU_UTF8 "\xCE\xBC" /* U+03BC */
61 # define LATIN_CAPITAL_LETTER_SHARP_S_UTF8 "\xE1\xBA\x9E" /* U+1E9E */
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 */
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 */
68 # define HYPHEN_UTF8 "\xE2\x80\x90" /* U+2010 */
69 # define BOM_UTF8_FIRST_BYTE 0xEF /* U+FEFF */
70 # define BOM_UTF8_TAIL "\xBB\xBF" /* U+FEFF */
72 # define BOM_UTF8 "\xEF\xBB\xBF" /* U+FEFF */
74 # define REPLACEMENT_CHARACTER_UTF8 "\xEF\xBF\xBD" /* U+FFFD */
76 # define MAX_UNICODE_UTF8 "\xF4\x8F\xBF\xBF" /* U+10FFFF */
78 # define NBSP_NATIVE 0xA0 /* U+00A0 */
79 # define NBSP_UTF8 "\xC2\xA0" /* U+00A0 */
81 # define DEL_NATIVE 0x7F /* U+007F */
82 # define CR_NATIVE 0x0D /* U+000D */
83 # define LF_NATIVE 0x0A /* U+000A */
84 # define VT_NATIVE 0x0B /* U+000B */
85 # define ESC_NATIVE 0x1B /* U+001B */
86 # define LATIN_SMALL_LETTER_SHARP_S_NATIVE 0xDF /* U+00DF */
87 # define LATIN_SMALL_LETTER_A_WITH_RING_ABOVE_NATIVE 0xE5 /* U+00E5 */
88 # define LATIN_CAPITAL_LETTER_A_WITH_RING_ABOVE_NATIVE 0xC5 /* U+00C5 */
89 # define LATIN_SMALL_LETTER_Y_WITH_DIAERESIS_NATIVE 0xFF /* U+00FF */
90 # define MICRO_SIGN_NATIVE 0xB5 /* U+00B5 */
91 # define MAX_PRINT_A_FOR_USE_ONLY_BY_REGCOMP_DOT_C 0x7E /* The max code point that isPRINT_A */
93 #endif /* ASCII/Latin1 */
95 #if 'A' == 193 /* EBCDIC 1047 */ \
96 && '\\' == 224 && '[' == 173 && ']' == 189 && '{' == 192 && '}' == 208 \
97 && '^' == 95 && '~' == 161 && '!' == 90 && '#' == 123 && '|' == 79 \
98 && '$' == 91 && '@' == 124 && '`' == 121
99 # define LATIN_SMALL_LETTER_LONG_S_UTF8 "\x8F\x73" /* U+017F */
101 # define COMBINING_GRAVE_ACCENT_UTF8 "\xAF\x41" /* U+0300 */
103 # define GREEK_CAPITAL_LETTER_IOTA_UTF8 "\xB3\x68" /* U+0399 */
104 # define GREEK_SMALL_LETTER_MU_UTF8 "\xB4\x70" /* U+03BC */
106 # define LATIN_CAPITAL_LETTER_SHARP_S_UTF8 "\xBF\x63\x72" /* U+1E9E */
108 # define LATIN_SMALL_LIGATURE_LONG_S_T_UTF8 "\xDD\x72\x67\x46" /* U+FB05 */
109 # define LATIN_SMALL_LIGATURE_ST_UTF8 "\xDD\x72\x67\x47" /* U+FB06 */
110 # define LATIN_CAPITAL_LETTER_I_WITH_DOT_ABOVE_UTF8 "\x8D\x57" /* U+0130 */
111 # define LATIN_SMALL_LETTER_DOTLESS_I_UTF8 "\x8D\x58" /* U+0131 */
113 # define HYPHEN_UTF8 "\xCA\x41\x57" /* U+2010 */
114 # define BOM_UTF8_FIRST_BYTE 0xDD /* U+FEFF */
115 # define BOM_UTF8_TAIL "\x73\x66\x73" /* U+FEFF */
117 # define BOM_UTF8 "\xDD\x73\x66\x73" /* U+FEFF */
119 # define REPLACEMENT_CHARACTER_UTF8 "\xDD\x73\x73\x71" /* U+FFFD */
121 # define MAX_UNICODE_UTF8 "\xEE\x42\x73\x73\x73" /* U+10FFFF */
123 # define NBSP_NATIVE 0x41 /* U+00A0 */
124 # define NBSP_UTF8 "\x80\x41" /* U+00A0 */
126 # define DEL_NATIVE 0x07 /* U+007F */
127 # define CR_NATIVE 0x0D /* U+000D */
128 # define LF_NATIVE 0x15 /* U+000A */
129 # define VT_NATIVE 0x0B /* U+000B */
130 # define ESC_NATIVE 0x27 /* U+001B */
131 # define LATIN_SMALL_LETTER_SHARP_S_NATIVE 0x59 /* U+00DF */
132 # define LATIN_SMALL_LETTER_A_WITH_RING_ABOVE_NATIVE 0x47 /* U+00E5 */
133 # define LATIN_CAPITAL_LETTER_A_WITH_RING_ABOVE_NATIVE 0x67 /* U+00C5 */
134 # define LATIN_SMALL_LETTER_Y_WITH_DIAERESIS_NATIVE 0xDF /* U+00FF */
135 # define MICRO_SIGN_NATIVE 0xA0 /* U+00B5 */
136 # define MAX_PRINT_A_FOR_USE_ONLY_BY_REGCOMP_DOT_C 0xF9 /* The max code point that isPRINT_A */
138 #endif /* EBCDIC 1047 */
140 #if 'A' == 193 /* EBCDIC 037 */ \
141 && '\\' == 224 && '[' == 186 && ']' == 187 && '{' == 192 && '}' == 208 \
142 && '^' == 176 && '~' == 161 && '!' == 90 && '#' == 123 && '|' == 79 \
143 && '$' == 91 && '@' == 124 && '`' == 121
144 # define LATIN_SMALL_LETTER_LONG_S_UTF8 "\x8E\x72" /* U+017F */
146 # define COMBINING_GRAVE_ACCENT_UTF8 "\xAD\x41" /* U+0300 */
148 # define GREEK_CAPITAL_LETTER_IOTA_UTF8 "\xB2\x67" /* U+0399 */
149 # define GREEK_SMALL_LETTER_MU_UTF8 "\xB3\x6A" /* U+03BC */
151 # define LATIN_CAPITAL_LETTER_SHARP_S_UTF8 "\xBF\x62\x71" /* U+1E9E */
153 # define LATIN_SMALL_LIGATURE_LONG_S_T_UTF8 "\xDD\x71\x66\x46" /* U+FB05 */
154 # define LATIN_SMALL_LIGATURE_ST_UTF8 "\xDD\x71\x66\x47" /* U+FB06 */
155 # define LATIN_CAPITAL_LETTER_I_WITH_DOT_ABOVE_UTF8 "\x8C\x57" /* U+0130 */
156 # define LATIN_SMALL_LETTER_DOTLESS_I_UTF8 "\x8C\x58" /* U+0131 */
158 # define HYPHEN_UTF8 "\xCA\x41\x57" /* U+2010 */
159 # define BOM_UTF8_FIRST_BYTE 0xDD /* U+FEFF */
160 # define BOM_UTF8_TAIL "\x72\x65\x72" /* U+FEFF */
162 # define BOM_UTF8 "\xDD\x72\x65\x72" /* U+FEFF */
164 # define REPLACEMENT_CHARACTER_UTF8 "\xDD\x72\x72\x70" /* U+FFFD */
166 # define MAX_UNICODE_UTF8 "\xEE\x42\x72\x72\x72" /* U+10FFFF */
168 # define NBSP_NATIVE 0x41 /* U+00A0 */
169 # define NBSP_UTF8 "\x78\x41" /* U+00A0 */
171 # define DEL_NATIVE 0x07 /* U+007F */
172 # define CR_NATIVE 0x0D /* U+000D */
173 # define LF_NATIVE 0x25 /* U+000A */
174 # define VT_NATIVE 0x0B /* U+000B */
175 # define ESC_NATIVE 0x27 /* U+001B */
176 # define LATIN_SMALL_LETTER_SHARP_S_NATIVE 0x59 /* U+00DF */
177 # define LATIN_SMALL_LETTER_A_WITH_RING_ABOVE_NATIVE 0x47 /* U+00E5 */
178 # define LATIN_CAPITAL_LETTER_A_WITH_RING_ABOVE_NATIVE 0x67 /* U+00C5 */
179 # define LATIN_SMALL_LETTER_Y_WITH_DIAERESIS_NATIVE 0xDF /* U+00FF */
180 # define MICRO_SIGN_NATIVE 0xA0 /* U+00B5 */
181 # define MAX_PRINT_A_FOR_USE_ONLY_BY_REGCOMP_DOT_C 0xF9 /* The max code point that isPRINT_A */
183 #endif /* EBCDIC 037 */
185 /* The number of code points not matching \pC */
186 #define NON_OTHER_COUNT_FOR_USE_ONLY_BY_REGCOMP_DOT_C 137222
188 /* The highest code point that has any type of case change */
189 #define HIGHEST_CASE_CHANGING_CP_FOR_USE_ONLY_BY_UTF8_DOT_C 0x1E943
191 #endif /* PERL_UNICODE_CONSTANTS_H_ */