X-Git-Url: https://perl5.git.perl.org/perl5.git/blobdiff_plain/78a0d3cc3d649167a7a58cbe7d5f494d42d154bd..5810a9df535b520e92fdee246a94d22d00cd0aad:/utf8.h diff --git a/utf8.h b/utf8.h index aa0f0c7..c40fb58 100644 --- a/utf8.h +++ b/utf8.h @@ -16,6 +16,9 @@ # define USE_UTF8_IN_NAMES (PL_hints & HINT_UTF8) #endif +#define to_uni_fold(c, p, lenp) _to_uni_fold_flags(c, p, lenp, 1) +#define to_utf8_fold(c, p, lenp) _to_utf8_fold_flags(c, p, lenp, 1) + /* Source backward compatibility. */ #define uvuni_to_utf8(d, uv) uvuni_to_utf8_flags(d, uv, 0) #define is_utf8_string_loc(s, len, ep) is_utf8_string_loclen(s, len, ep, 0) @@ -226,8 +229,9 @@ Perl's extended UTF-8 means we can have start bytes up to FF. * version. An example of maximal expansion is the U+03B0 which * uppercases to U+03C5 U+0308 U+0301. The Unicode databases that * tell these things are UnicodeData.txt, CaseFolding.txt, and - * SpecialCasing.txt. */ -#define UTF8_MAXBYTES_CASE 6 + * SpecialCasing.txt. The value is 6 for strict Unicode characters, but it has + * to be as big as Perl allows for a single character */ +#define UTF8_MAXBYTES_CASE UTF8_MAXBYTES /* A Unicode character can fold to up to 3 characters */ #define UTF8_MAX_FOLD_CHAR_EXPAND 3 @@ -426,6 +430,7 @@ Perl's extended UTF-8 means we can have start bytes up to FF. #define GREEK_SMALL_LETTER_MU 0x03BC #define GREEK_CAPITAL_LETTER_MU 0x039C /* Upper and title case of MICRON */ #define LATIN_CAPITAL_LETTER_Y_WITH_DIAERESIS 0x0178 /* Also is title case */ +#define LATIN_CAPITAL_LETTER_SHARP_S 0x1E9E #define UNI_DISPLAY_ISPRINT 0x0001 #define UNI_DISPLAY_BACKSLASH 0x0002 @@ -436,6 +441,8 @@ Perl's extended UTF-8 means we can have start bytes up to FF. # define LATIN_SMALL_LETTER_SHARP_S 0x00DF # define LATIN_SMALL_LETTER_Y_WITH_DIAERESIS 0x00FF # define MICRO_SIGN 0x00B5 +# define LATIN_CAPITAL_LETTER_A_WITH_RING_ABOVE 0x00C5 +# define LATIN_SMALL_LETTER_A_WITH_RING_ABOVE 0x00E5 #endif #define ANYOF_FOLD_SHARP_S(node, input, end) \