char.txt   [plain text]

#
#   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
#      These rules are based on the Extended Grapheme Cluster rules from
#      Unicode UAX #29 Revision 34 for Unicode Version 12.0

!!quoted_literals_only;

#
#  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}];

#
#  From cldr/common/properties/segments/
#       and issue CLDR-10994
#
$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}];

# 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

$Extended_Pict = [:ExtPict:];

# The following classes are no longer needed for ICU rules but may
# still be needed for WebKit rules in charClasses.txt
# The first  is still valid using the Unicode 11 properties:
#  $EmojiNRK    = [[\p{Emoji}] - [\p{Grapheme_Cluster_Break = Regional_Indicator}*\u00230-9©®™〰〽]];
# The other two are no longer valid because no characters have GCB=EB or GCB=EBG anymore:
#  $E_Base      = [[\p{Grapheme_Cluster_Break = EB}];
#  $E_Base_GAZ  = [\p{Grapheme_Cluster_Break = EBG}];
# They must be replaced with updated versions as follows
#  $E_Base      = [:EBase:];
#  $E_Base_GAZ  = [\U0001F466-\U0001F469\U0001F91D\U0001F9D1]; # EBase that also occur after ZWJ in emoji-zwj-sequences

## -------------------------------------------------
!!chain;
!!lookAheadHardBreak;

$CR $LF;

$L ($L | $V | $LV | $LVT);
($LV | $V) ($V | $T);
($LVT | $T) $T;

# GB 9
[^$Control $CR $LF] ($Extend | $ZWJ);

# GB 9a
[^$Control $CR $LF] $SpacingMark;

# GB 9b
$Prepend [^$Control $CR $LF];

# GB 9.3, from CLDR-10994
$LinkingConsonant $ExtCccZwj* $Virama $ExtCccZwj* $LinkingConsonant;

# GB 11 Do not break within emoji modifier sequences or emoji zwj sequences.
$Extended_Pict $Extend* $ZWJ $Extended_Pict;

# 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;

# GB 999 Match a single code point if no other rule applies.
.;