1# 2# Copyright (C) 2016 and later: Unicode, Inc. and others. 3# License & terms of use: http://www.unicode.org/copyright.html 4# Copyright (C) 2002-2016, International Business Machines Corporation and others. 5# All Rights Reserved. 6# 7# file: char.txt 8# 9# ICU Character Break Rules 10# These rules are based on the Extended Grapheme Cluster rules from 11# Unicode UAX #29 Revision 34 for Unicode Version 12.0 12 13!!quoted_literals_only; 14 15# 16# Character Class Definitions. 17# 18$CR = [\p{Grapheme_Cluster_Break = CR}]; 19$LF = [\p{Grapheme_Cluster_Break = LF}]; 20$Control = [[\p{Grapheme_Cluster_Break = Control}]]; 21$Extend = [[\p{Grapheme_Cluster_Break = Extend}]]; 22$ZWJ = [\p{Grapheme_Cluster_Break = ZWJ}]; 23$Regional_Indicator = [\p{Grapheme_Cluster_Break = Regional_Indicator}]; 24$Prepend = [\p{Grapheme_Cluster_Break = Prepend}]; 25$SpacingMark = [\p{Grapheme_Cluster_Break = SpacingMark}]; 26 27# 28# From cldr/common/properties/segments/ 29# and issue CLDR-10994 30# 31$Virama = [\p{Gujr}\p{sc=Telu}\p{sc=Mlym}\p{sc=Orya}\p{sc=Beng}\p{sc=Deva}&\p{Indic_Syllabic_Category=Virama}]; 32$LinkingConsonant = [\p{Gujr}\p{sc=Telu}\p{sc=Mlym}\p{sc=Orya}\p{sc=Beng}\p{sc=Deva}&\p{Indic_Syllabic_Category=Consonant}]; 33$ExtCccZwj = [[\p{gcb=Extend}-\p{ccc=0}] \p{gcb=ZWJ}]; 34 35# Korean Syllable Definitions 36# 37$L = [\p{Grapheme_Cluster_Break = L}]; 38$V = [\p{Grapheme_Cluster_Break = V}]; 39$T = [\p{Grapheme_Cluster_Break = T}]; 40 41$LV = [\p{Grapheme_Cluster_Break = LV}]; 42$LVT = [\p{Grapheme_Cluster_Break = LVT}]; 43 44# Emoji defintions 45 46$Extended_Pict = [:ExtPict:]; 47 48## ------------------------------------------------- 49!!chain; 50!!lookAheadHardBreak; 51 52$CR $LF; 53 54$L ($L | $V | $LV | $LVT); 55($LV | $V) ($V | $T); 56($LVT | $T) $T; 57 58# GB 9 59[^$Control $CR $LF] ($Extend | $ZWJ); 60 61# GB 9a 62[^$Control $CR $LF] $SpacingMark; 63 64# GB 9b 65$Prepend [^$Control $CR $LF]; 66 67# GB 9.3, from CLDR-10994 68$LinkingConsonant $ExtCccZwj* $Virama $ExtCccZwj* $LinkingConsonant; 69 70# GB 11 Do not break within emoji modifier sequences or emoji zwj sequences. 71$Extended_Pict $Extend* $ZWJ $Extended_Pict; 72 73# GB 12-13. Keep pairs of regional indicators together 74# Note that hard break '/' rule triggers only if there are three or more initial RIs, 75 76^$Prepend* $Regional_Indicator $Regional_Indicator / $Regional_Indicator; 77^$Prepend* $Regional_Indicator $Regional_Indicator; 78 79# GB 999 Match a single code point if no other rule applies. 80.; 81 82