blob: 265c706d5096be5e585f3bfacaf68606ecea3794 [file] [log] [blame]
#
# Copyright (C) 2016 and later: Unicode, Inc. and others.
# License & terms of use: http://www.unicode.org/copyright.html
# Copyright (C) 2002-2016, International Business Machines Corporation and others.
# All Rights Reserved.
#
# file: char.txt
#
# ICU Character Break Rules, also known as Grapheme Cluster Boundaries
# See Unicode Standard Annex #29.
# These rules are based on UAX #29 Revision 29 for Unicode Version 9.0
# plus proposed updates for Emoji 4.0 from https://goo.gl/cluFCn
#
# Character Class Definitions.
#
$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}];
#
# Korean Syllable Definitions
#
$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}];
# Emoji defintions
$E_Base = [[\p{Grapheme_Cluster_Break = EB}] \U0001F3C2\U0001F3C7\U0001F3CC\U0001F46A-\U0001F46D\U0001F46F\U0001F574\U0001F6CC];
$E_Modifier = [\p{Grapheme_Cluster_Break = EM}];
# Data for Extended Pictographic scraped from CLDR common/properties/ExtendedPictographic.txt, r12773
$Extended_Pict = [\U0001F774-\U0001F77F\u2700-\u2701\u2703-\u2704\u270E\u2710-\u2711\u2765-\u2767\U0001F030-\U0001F093\U0001F094-\U0001F09F\U0001F10D-\U0001F10F\U0001F12F\U0001F16C-\U0001F16F\U0001F1AD-\U0001F1E5\U0001F203-\U0001F20F\U0001F23C-\U0001F23F\U0001F249-\U0001F24F\U0001F252-\U0001F2FF\U0001F7D5-\U0001F7FF\U0001F000-\U0001F003\U0001F005-\U0001F02B\U0001F02C-\U0001F02F\U0001F322-\U0001F323\U0001F394-\U0001F395\U0001F398\U0001F39C-\U0001F39D\U0001F3F1-\U0001F3F2\U0001F3F6\U0001F4FE\U0001F53E-\U0001F548\U0001F54F\U0001F568-\U0001F56E\U0001F571-\U0001F572\U0001F57B-\U0001F586\U0001F588-\U0001F589\U0001F58E-\U0001F58F\U0001F591-\U0001F594\U0001F597-\U0001F5A3\U0001F5A6-\U0001F5A7\U0001F5A9-\U0001F5B0\U0001F5B3-\U0001F5BB\U0001F5BD-\U0001F5C1\U0001F5C5-\U0001F5D0\U0001F5D4-\U0001F5DB\U0001F5DF-\U0001F5E0\U0001F5E2\U0001F5E4-\U0001F5E7\U0001F5E9-\U0001F5EE\U0001F5F0-\U0001F5F2\U0001F5F4-\U0001F5F9\u2605\u2607-\u260D\u260F-\u2610\u2612\u2616-\u2617\u2619-\u261C\u261E-\u261F\u2621\u2624-\u2625\u2627-\u2629\u262B-\u262D\u2630-\u2637\u263B-\u2647\u2654-\u265F\u2661-\u2662\u2664\u2667\u2669-\u267A\u267C-\u267E\u2680-\u2691\u2695\u2698\u269A\u269D-\u269F\u26A2-\u26A9\u26AC-\u26AF\u26B2-\u26BC\u26BF-\u26C3\u26C6-\u26C7\u26C9-\u26CD\u26D0\u26D2\u26D5-\u26E8\u26EB-\u26EF\u26F6\u26FB-\u26FC\u26FE-\u26FF\u2388\U0001FA00-\U0001FFFD\U0001F0A0-\U0001F0AE\U0001F0B1-\U0001F0BF\U0001F0C1-\U0001F0CF\U0001F0D1-\U0001F0F5\U0001F0AF-\U0001F0B0\U0001F0C0\U0001F0D0\U0001F0F6-\U0001F0FF\U0001F80C-\U0001F80F\U0001F848-\U0001F84F\U0001F85A-\U0001F85F\U0001F888-\U0001F88F\U0001F8AE-\U0001F8FF\U0001F900-\U0001F90F\U0001F91F\U0001F928-\U0001F92F\U0001F931-\U0001F932\U0001F93F\U0001F94C-\U0001F94F\U0001F95F-\U0001F97F\U0001F992-\U0001F9BF\U0001F9C1-\U0001F9FF\U0001F6C6-\U0001F6CA\U0001F6E6-\U0001F6E8\U0001F6EA\U0001F6F1-\U0001F6F2\U0001F6D3-\U0001F6DF\U0001F6ED-\U0001F6EF\U0001F6F7-\U0001F6FF];
$E_Base_GAZ = [\p{Grapheme_Cluster_Break = EBG}];
$EmojiNRK = [[\p{Emoji}] - [\p{Grapheme_Cluster_Break = Regional_Indicator}*\u00230-9©®™〰〽]];
## -------------------------------------------------
!!chain;
!!lookAheadHardBreak;
!!forward;
$CR $LF;
$L ($L | $V | $LV | $LVT);
($LV | $V) ($V | $T);
($LVT | $T) $T;
# GB 9
[^$Control $CR $LF] ($Extend | $ZWJ);
# GB 9a (only for extended grapheme clusters)
[^$Control $CR $LF] $SpacingMark;
# GB 9b
$Prepend [^$Control $CR $LF];
# GB 10 Do not break within emoji modifier sequences or emoji zwj sequences.
($E_Base | $E_Base_GAZ) $Extend* $E_Modifier;
# GB 11
($Extended_Pict | $EmojiNRK) $ZWJ ($Extended_Pict | $EmojiNRK);
# GB 12-13. Keep pairs of regional indicators together
# Note that hard break '/' rule triggers only if there are three or more initial RIs,
^$Prepend* $Regional_Indicator $Regional_Indicator / $Regional_Indicator;
^$Prepend* $Regional_Indicator $Regional_Indicator;
## -------------------------------------------------
!!reverse;
$LF $CR;
($L | $V | $LV | $LVT) $L;
($V | $T) ($LV | $V);
$T ($LVT | $T);
# GB 9
($Extend | $ZWJ) [^$Control $CR $LF]; #note that this will chain into Regional_Indicator when needed.
# GB 9a
$SpacingMark [^$Control $CR $LF];
# GB 9b
[^$Control $CR $LF] $Prepend;
# GB 10
$E_Modifier $Extend* ($E_Base | $E_Base_GAZ);
# GB 11 Don't break between ZWJ and Glue_After_ZWJ
($Extended_Pict | $EmojiNRK) $ZWJ ($Extended_Pict | $EmojiNRK);
# GB 12-13. Going backwards, we must scan through any number of regional indicators as pairs.
#
[{bof} $Extend $ZWJ $SpacingMark] $Regional_Indicator $Regional_Indicator / ($Regional_Indicator $Regional_Indicator)+ [{eof}[^$Regional_Indicator]];
[{bof} $Extend $ZWJ $SpacingMark] $Regional_Indicator / ($Regional_Indicator $Regional_Indicator)+ [{eof}[^$Regional_Indicator]];
$Regional_Indicator $Regional_Indicator;
$Regional_Indicator $Prepend;
## -------------------------------------------------
!!safe_reverse;
$Regional_Indicator $Regional_Indicator;
($Extend | $ZWJ | $EmojiNRK | $Extended_Pict)+ .;
## -------------------------------------------------
!!safe_forward;
$Regional_Indicator $Regional_Indicator;
($Extend | $ZWJ | $EmojiNRK | $Extended_Pict)+ .;