Last active
March 22, 2024 01:05
-
-
Save andjc/37c4b6564e01171bf1faaade23560137 to your computer and use it in GitHub Desktop.
Rules sets for custom break iterators
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"din": "!!quoted_literals_only; $CR = [\\p{Grapheme_Cluster_Break = CR}]; $LF = [\\p{Grapheme_Cluster_Break = LF}]; $Control = [[\\p{Grapheme_Cluster_Break = Control}]]; $Extend = [[\\p{Grapheme_Cluster_Break = Extend}]]; $ZWJ = [\\p{Grapheme_Cluster_Break = ZWJ}]; $Regional_Indicator = [\\p{Grapheme_Cluster_Break = Regional_Indicator}]; $Prepend = [\\p{Grapheme_Cluster_Break = Prepend}]; $SpacingMark = [\\p{Grapheme_Cluster_Break = SpacingMark}]; $Virama = [\\p{Gujr}\\p{sc=Telu}\\p{sc=Mlym}\\p{sc=Orya}\\p{sc=Beng}\\p{sc=Deva}&\\p{Indic_Syllabic_Category=Virama}]; $LinkingConsonant = [\\p{Gujr}\\p{sc=Telu}\\p{sc=Mlym}\\p{sc=Orya}\\p{sc=Beng}\\p{sc=Deva}&\\p{Indic_Syllabic_Category=Consonant}]; $ExtCccZwj = [[\\p{gcb=Extend}-\\p{ccc=0}] \\p{gcb=ZWJ}]; $L = [\\p{Grapheme_Cluster_Break = L}]; $V = [\\p{Grapheme_Cluster_Break = V}]; $T = [\\p{Grapheme_Cluster_Break = T}]; $LV = [\\p{Grapheme_Cluster_Break = LV}]; $LVT = [\\p{Grapheme_Cluster_Break = LVT}]; $Extended_Pict = [:ExtPict:]; !!chain; 'AA'|'Aa'|'aa'; '\u00c4\u00c4'|'\u00c4\u00e4'|'\u00e4\u00e4'; 'EE'|'Ee'|'ee'; '\u00cb\u00cb'|'\u00cb\u00eb'|'\u00eb\u00eb'; '\u0190\u0190'|'\u0190\u025b'|'\u025b\u025b'; '\u0190\u0308\u0190\u0308'|'\u0190\u0308\u025b\u0308'|'\u025b\u0308\u025b\u0308'; 'II'|'Ii'|'ii'; '\u00cf\u00cf'|'\u00cf\u00ef'|'\u00ef\u00ef'; 'OO'|'Oo'|'oo'; '\u00d6\u00d6'|'\u00d6\u00f6'|'\u00f6\u00f6'; '\u0186\u0186'|'\u0186\u0254'|'\u0254\u0254'; '\u0186\u0308\u0186\u0308'|'\u0186\u0308\u0254\u0308'|'\u0254\u0308\u0254\u0308'; 'UU'|'Uu'|'uu'; 'DH'|'Dh'|'dh'; 'NH'|'Nh'|'nh'; 'NY'|'Ny'|'ny'; 'TH'|'Th'|'th'; !!lookAheadHardBreak; $CR $LF; $L ($L | $V | $LV | $LVT); ($LV | $V) ($V | $T); ($LVT | $T) $T; [^$Control $CR $LF] ($Extend | $ZWJ); [^$Control $CR $LF] $SpacingMark; $Prepend [^$Control $CR $LF]; $LinkingConsonant $ExtCccZwj* $Virama $ExtCccZwj* $LinkingConsonant; $Extended_Pict $Extend* $ZWJ $Extended_Pict; ^$Prepend* $Regional_Indicator $Regional_Indicator / $Regional_Indicator; ^$Prepend* $Regional_Indicator $Regional_Indicator; .;" | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment