X-Git-Url: https://perl5.git.perl.org/perl5.git/blobdiff_plain/b35552de5cea8eb47ccb046284ecb9a099430255..8d72e74e3dc5017c5a3fade48e0c74109c297ebc:/unicode_constants.h diff --git a/unicode_constants.h b/unicode_constants.h index a7ddfeb..a3d50ad 100644 --- a/unicode_constants.h +++ b/unicode_constants.h @@ -5,13 +5,14 @@ */ -#ifndef H_UNICODE_CONSTANTS /* Guard against nested #includes */ -#define H_UNICODE_CONSTANTS 1 - -/* This file contains #defines for various Unicode code points. The values - * the macros expand to are the native Unicode code point, or all or portions - * of the UTF-8 encoding for the code point. In the former case, the macro - * name has the suffix "_NATIVE"; otherwise, the suffix "_UTF8". +#ifndef PERL_UNICODE_CONSTANTS_H_ /* Guard against nested #includes */ +#define PERL_UNICODE_CONSTANTS_H_ 1 + +/* This file contains #defines for the version of Unicode being used and + * various Unicode code points. The values the code point macros expand to + * are the native Unicode code point, or all or portions of the UTF-8 encoding + * for the code point. In the former case, the macro name has the suffix + * "_NATIVE"; otherwise, the suffix "_UTF8". * * The macros that have the suffix "_UTF8" may have further suffixes, as * follows: @@ -20,6 +21,34 @@ * "_TAIL" if instead it represents all but the first byte. This, and * with no additional suffix are both string constants */ +/* +=head1 Unicode Support + +=for apidoc AmU|placeholder|BOM_UTF8 + +This is a macro that evaluates to a string constant of the UTF-8 bytes that +define the Unicode BYTE ORDER MARK (U+FEFF) for the platform that perl +is compiled on. This allows code to use a mnemonic for this character that +works on both ASCII and EBCDIC platforms. +S> can be used to get its length in +bytes. + +=for apidoc AmU|placeholder|REPLACEMENT_CHARACTER_UTF8 + +This is a macro that evaluates to a string constant of the UTF-8 bytes that +define the Unicode REPLACEMENT CHARACTER (U+FFFD) for the platform that perl +is compiled on. This allows code to use a mnemonic for this character that +works on both ASCII and EBCDIC platforms. +S> can be used to get its length in +bytes. + +=cut +*/ + +#define UNICODE_MAJOR_VERSION 10 +#define UNICODE_DOT_VERSION 0 +#define UNICODE_DOT_DOT_VERSION 0 + #if 'A' == 65 /* ASCII/Latin1 */ # define LATIN_SMALL_LETTER_LONG_S_UTF8 "\xC5\xBF" /* U+017F */ @@ -33,12 +62,19 @@ # define LATIN_SMALL_LIGATURE_LONG_S_T_UTF8 "\xEF\xAC\x85" /* U+FB05 */ # define LATIN_SMALL_LIGATURE_ST_UTF8 "\xEF\xAC\x86" /* U+FB06 */ +# define LATIN_CAPITAL_LETTER_I_WITH_DOT_ABOVE_UTF8 "\xC4\xB0" /* U+0130 */ +# define LATIN_SMALL_LETTER_DOTLESS_I_UTF8 "\xC4\xB1" /* U+0131 */ # define HYPHEN_UTF8 "\xE2\x80\x90" /* U+2010 */ -# define FIRST_SURROGATE_UTF8_FIRST_BYTE 0xED /* U+D800 */ # define BOM_UTF8_FIRST_BYTE 0xEF /* U+FEFF */ # define BOM_UTF8_TAIL "\xBB\xBF" /* U+FEFF */ +# define BOM_UTF8 "\xEF\xBB\xBF" /* U+FEFF */ + +# define REPLACEMENT_CHARACTER_UTF8 "\xEF\xBF\xBD" /* U+FFFD */ + +# define MAX_UNICODE_UTF8 "\xF4\x8F\xBF\xBF" /* U+10FFFF */ + # define NBSP_NATIVE 0xA0 /* U+00A0 */ # define NBSP_UTF8 "\xC2\xA0" /* U+00A0 */ @@ -71,12 +107,19 @@ # define LATIN_SMALL_LIGATURE_LONG_S_T_UTF8 "\xDD\x72\x67\x46" /* U+FB05 */ # define LATIN_SMALL_LIGATURE_ST_UTF8 "\xDD\x72\x67\x47" /* U+FB06 */ +# define LATIN_CAPITAL_LETTER_I_WITH_DOT_ABOVE_UTF8 "\x8D\x57" /* U+0130 */ +# define LATIN_SMALL_LETTER_DOTLESS_I_UTF8 "\x8D\x58" /* U+0131 */ # define HYPHEN_UTF8 "\xCA\x41\x57" /* U+2010 */ -# define FIRST_SURROGATE_UTF8_FIRST_BYTE 0xDD /* U+D800 */ # define BOM_UTF8_FIRST_BYTE 0xDD /* U+FEFF */ # define BOM_UTF8_TAIL "\x73\x66\x73" /* U+FEFF */ +# define BOM_UTF8 "\xDD\x73\x66\x73" /* U+FEFF */ + +# define REPLACEMENT_CHARACTER_UTF8 "\xDD\x73\x73\x71" /* U+FFFD */ + +# define MAX_UNICODE_UTF8 "\xEE\x42\x73\x73\x73" /* U+10FFFF */ + # define NBSP_NATIVE 0x41 /* U+00A0 */ # define NBSP_UTF8 "\x80\x41" /* U+00A0 */ @@ -109,12 +152,19 @@ # define LATIN_SMALL_LIGATURE_LONG_S_T_UTF8 "\xDD\x71\x66\x46" /* U+FB05 */ # define LATIN_SMALL_LIGATURE_ST_UTF8 "\xDD\x71\x66\x47" /* U+FB06 */ +# define LATIN_CAPITAL_LETTER_I_WITH_DOT_ABOVE_UTF8 "\x8C\x57" /* U+0130 */ +# define LATIN_SMALL_LETTER_DOTLESS_I_UTF8 "\x8C\x58" /* U+0131 */ # define HYPHEN_UTF8 "\xCA\x41\x57" /* U+2010 */ -# define FIRST_SURROGATE_UTF8_FIRST_BYTE 0xDD /* U+D800 */ # define BOM_UTF8_FIRST_BYTE 0xDD /* U+FEFF */ # define BOM_UTF8_TAIL "\x72\x65\x72" /* U+FEFF */ +# define BOM_UTF8 "\xDD\x72\x65\x72" /* U+FEFF */ + +# define REPLACEMENT_CHARACTER_UTF8 "\xDD\x72\x72\x70" /* U+FFFD */ + +# define MAX_UNICODE_UTF8 "\xEE\x42\x72\x72\x72" /* U+10FFFF */ + # define NBSP_NATIVE 0x41 /* U+00A0 */ # define NBSP_UTF8 "\x78\x41" /* U+00A0 */ @@ -132,47 +182,12 @@ #endif /* EBCDIC 037 */ -#if 'A' == 193 /* EBCDIC POSIX-BC */ \ - && '\\' == 188 && '[' == 187 && ']' == 189 && '{' == 251 && '}' == 253 \ - && '^' == 106 && '~' == 255 && '!' == 90 && '#' == 123 && '|' == 79 \ - && '$' == 91 && '@' == 124 && '`' == 74 -# define LATIN_SMALL_LETTER_LONG_S_UTF8 "\x90\x75" /* U+017F */ - -# define COMBINING_GRAVE_ACCENT_UTF8 "\xAE\x41" /* U+0300 */ - -# define GREEK_CAPITAL_LETTER_IOTA_UTF8 "\xB2\x69" /* U+0399 */ -# define GREEK_SMALL_LETTER_MU_UTF8 "\xB3\x72" /* U+03BC */ - -# define LATIN_CAPITAL_LETTER_SHARP_S_UTF8 "\xC0\x64\x74" /* U+1E9E */ - -# define LATIN_SMALL_LIGATURE_LONG_S_T_UTF8 "\xDC\x74\x68\x46" /* U+FB05 */ -# define LATIN_SMALL_LIGATURE_ST_UTF8 "\xDC\x74\x68\x47" /* U+FB06 */ - -# define HYPHEN_UTF8 "\xCA\x41\x58" /* U+2010 */ -# define FIRST_SURROGATE_UTF8_FIRST_BYTE 0xDC /* U+D800 */ -# define BOM_UTF8_FIRST_BYTE 0xDC /* U+FEFF */ -# define BOM_UTF8_TAIL "\x75\x67\x75" /* U+FEFF */ - -# define NBSP_NATIVE 0x41 /* U+00A0 */ -# define NBSP_UTF8 "\x8A\x41" /* U+00A0 */ - -# define DEL_NATIVE 0x07 /* U+007F */ -# define CR_NATIVE 0x0D /* U+000D */ -# define LF_NATIVE 0x15 /* U+000A */ -# define VT_NATIVE 0x0B /* U+000B */ -# define ESC_NATIVE 0x27 /* U+001B */ -# define LATIN_SMALL_LETTER_SHARP_S_NATIVE 0x59 /* U+00DF */ -# define LATIN_SMALL_LETTER_A_WITH_RING_ABOVE_NATIVE 0x47 /* U+00E5 */ -# define LATIN_CAPITAL_LETTER_A_WITH_RING_ABOVE_NATIVE 0x67 /* U+00C5 */ -# define LATIN_SMALL_LETTER_Y_WITH_DIAERESIS_NATIVE 0xDF /* U+00FF */ -# define MICRO_SIGN_NATIVE 0xA0 /* U+00B5 */ -# define MAX_PRINT_A_FOR_USE_ONLY_BY_REGCOMP_DOT_C 0xFF /* The max code point that isPRINT_A */ - -#endif /* EBCDIC POSIX-BC */ - /* The number of code points not matching \pC */ -#define NON_OTHER_COUNT_FOR_USE_ONLY_BY_REGCOMP_DOT_C 112806 +#define NON_OTHER_COUNT_FOR_USE_ONLY_BY_REGCOMP_DOT_C 136539 + +/* The highest code point that has any type of case change */ +#define HIGHEST_CASE_CHANGING_CP_FOR_USE_ONLY_BY_UTF8_DOT_C 0x1E943 -#endif /* H_UNICODE_CONSTANTS */ +#endif /* PERL_UNICODE_CONSTANTS_H_ */ /* ex: set ro: */