kojote/unicode/ucd.ha

95 lines
2.7 KiB
Hare
Raw Normal View History

2024-01-25 15:05:32 +00:00
type ucd_encodedrec = (u8, u8, u8, u8, u8);
type ucd_record = struct {
category: u8,
combining: u8,
bidirectional: u8,
mirrored: u8,
east_asian_width: u8,
};
fn get_ucdrecord(rn: rune) *ucd_record = {
const code = rn: u32;
let index = 0u8;
if (code < 0x110000) {
index = index1[(code>>UCD_RECORD_SHIFT)];
index = index2[(index<<UCD_RECORD_SHIFT)+(code&((1<<UCD_RECORD_SHIFT)-1))];
};
return &ucd_records[index]: *ucd_record;
};
// Unicode character General_Category attribute
export type gc = enum u8 {
CONTROL, // Cc
FORMAT, // Cf
UNASSIGNED, // Cn
PRIVATE_USE, // Co
SURROGATE, // Cs
LOWERCASE_LETTER, // Ll
MODIFIER_LETTER, // Lm
OTHER_LETTER, // Lo
TITLECASE_LETTER, // Lt
UPPERCASE_LETTER, // Lu
SPACING_MARK, // Mc
ENCLOSING_MARK, // Me
NON_SPACING_MARK, // Mn
DECIMAL_NUMBER, // Nd
LETTER_NUMBER, // Nl
OTHER_NUMBER, // No
CONNECT_PUNCTUATION, // Pc
DASH_PUNCTUATION, // Pd
CLOSE_PUNCTUATION, // Pe
FINAL_PUNCTUATION, // Pf
INITIAL_PUNCTUATION, // Pi
OTHER_PUNCTUATION, // Po
OPEN_PUNCTUATION, // Ps
CURRENCY_SYMBOL, // Sc
MODIFIER_SYMBOL, // Sk
MATH_SYMBOL, // Sm
OTHER_SYMBOL, // So
LINE_SEPARATOR, // Zl
PARAGRAPH_SEPARATOR, // Zp
SPACE_SEPARATOR, // Zs
};
// Returns the [[general_category]] corresponding to this rune.
export fn rune_gc(rn: rune) gc = {
return get_ucdrecord(rn).category: gc;
};
// Returns the two-character code associated with a [[gc]] value.
export fn gc_code(v: gc) const str = {
switch (v) {
case gc::CONTROL => return "Cc";
case gc::FORMAT => return "Cf";
case gc::UNASSIGNED => return "Cn";
case gc::PRIVATE_USE => return "Co";
case gc::SURROGATE => return "Cs";
case gc::LOWERCASE_LETTER => return "Ll";
case gc::MODIFIER_LETTER => return "Lm";
case gc::OTHER_LETTER => return "Lo";
case gc::TITLECASE_LETTER => return "Lt";
case gc::UPPERCASE_LETTER => return "Lu";
case gc::SPACING_MARK => return "Mc";
case gc::ENCLOSING_MARK => return "Me";
case gc::NON_SPACING_MARK => return "Mn";
case gc::DECIMAL_NUMBER => return "Nd";
case gc::LETTER_NUMBER => return "Nl";
case gc::OTHER_NUMBER => return "No";
case gc::CONNECT_PUNCTUATION => return "Pc";
case gc::DASH_PUNCTUATION => return "Pd";
case gc::CLOSE_PUNCTUATION => return "Pe";
case gc::FINAL_PUNCTUATION => return "Pf";
case gc::INITIAL_PUNCTUATION => return "Pi";
case gc::OTHER_PUNCTUATION => return "Po";
case gc::OPEN_PUNCTUATION => return "Ps";
case gc::CURRENCY_SYMBOL => return "Sc";
case gc::MODIFIER_SYMBOL => return "Sk";
case gc::MATH_SYMBOL => return "Sm";
case gc::OTHER_SYMBOL => return "So";
case gc::LINE_SEPARATOR => return "Zl";
case gc::PARAGRAPH_SEPARATOR => return "Zp";
case gc::SPACE_SEPARATOR => return "Zs";
};
};