std/src/unicode/word_data.nv - main - nv-lang/nova

// AUTO-GENERATED by `nova-codegen unicode`. DO NOT EDIT BY HAND.
// Source: UCD WordBreakProperty.txt (UAX #29 word boundaries).
// Regenerate: nova-codegen unicode --ucd-dir <UCD-dir> --root <repo>
//
// WB_DATA : "lo,hi,cat;.."  Word_Break category ranges
//   cat: 1=CR 2=LF 3=Newline 4=Extend 5=ZWJ 6=Regional_Indicator 7=Format
//        8=Katakana 9=Hebrew_Letter 10=ALetter 11=Single_Quote 12=Double_Quote
//        13=MidNumLet 14=MidLetter 15=MidNum 16=Numeric 17=ExtendNumLet
//        18=WSegSpace (Other=absent). Ranges sorted by lo (binary search).

module std.unicode

export const WORD_UNICODE_VERSION = "16.0"

const WB_DATA = "a,a,2;b,c,3;d,d,1;20,20,12;22,22,c;27,27,b;2c,2c,f;2e,2e,d;30,39,10;3a,3a,e;3b,3b,f;41,5a,a;5f,5f,11;61,7a,a;85,85,3;aa,aa,a;ad,ad,7;b5,b5,a;b7,b7,e;ba,ba,a;c0,d6,a;d8,f6,a;f8,1ba,a;1 … [Строка слишком длинная. Вы можете скачать файл]