ICU-66108.tar.gz

[apple/icu.git] / icuSources / data / brkitr / rules / char.txt

diff --git a/icuSources/data/brkitr/rules/char.txt b/icuSources/data/brkitr/rules/char.txt
index 808f36d9e91256607f287ff51d6e82eb13c610e2..ffa3faf451cd8a6f979dce5c27f5cd29c606746f 100644 (file)
--- a/icuSources/data/brkitr/rules/char.txt
+++ b/icuSources/data/brkitr/rules/char.txt
@@ -1,4 +1,4 @@
-#
+#

 #   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.
 #   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.


@@ -6,11 +6,11 @@
 #
 #   file:  char.txt
 #
 #
 #   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 revisions to rule GB 11 from http://unicode.org/cldr/trac/ticket/10088
-#      Plus additional characters introduces with Emoji 5, http://www.unicode.org/reports/tr51/proposed.html
+#   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.
 
 #
 #  Character Class Definitions.


@@ -25,6 +25,13 @@ $Prepend     = [\p{Grapheme_Cluster_Break = Prepend}];
 $SpacingMark = [\p{Grapheme_Cluster_Break = SpacingMark}];
 
 #
 $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}];
 # Korean Syllable Definitions
 #
 $L           = [\p{Grapheme_Cluster_Break = L}];


@@ -36,18 +43,22 @@ $LVT         = [\p{Grapheme_Cluster_Break = LVT}];
 
 # Emoji defintions
 
 
 # Emoji defintions
 

-$E_Base      = [[\p{Grapheme_Cluster_Break = EB}] \U0001F46A-\U0001F46D\U0001F46F\U0001F91D\U0001F93C];
-$E_Modifier  = [\p{Grapheme_Cluster_Break = EM}];
+$Extended_Pict = [:ExtPict:];

 
 

-# Data for Extended Pictographic scraped from CLDR common/properties/ExtendedPictographic.txt, r13267
-$Extended_Pict = [\U0001F774-\U0001F77F\U00002700-\U00002701\U00002703-\U00002704\U0000270E\U00002710-\U00002711\U00002765-\U00002767\U0001F030-\U0001F093\U0001F094-\U0001F09F\U0001F10D-\U0001F10F\U0001F12F\U0001F16C-\U0001F16F\U0001F1AD-\U0001F1E5\U0001F260-\U0001F265\U0001F203-\U0001F20F\U0001F23C-\U0001F23F\U0001F249-\U0001F24F\U0001F252-\U0001F25F\U0001F266-\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\U00002605\U00002607-\U0000260D\U0000260F-\U00002610\U00002612\U00002616-\U00002617\U00002619-\U0000261C\U0000261E-\U0000261F\U00002621\U00002624-\U00002625\U00002627-\U00002629\U0000262B-\U0000262D\U00002630-\U00002637\U0000263B-\U00002647\U00002654-\U0000265F\U00002661-\U00002662\U00002664\U00002667\U00002669-\U0000267A\U0000267C-\U0000267E\U00002680-\U00002691\U00002695\U00002698\U0000269A\U0000269D-\U0000269F\U000026A2-\U000026A9\U000026AC-\U000026AF\U000026B2-\U000026BC\U000026BF-\U000026C3\U000026C6-\U000026C7\U000026C9-\U000026CD\U000026D0\U000026D2\U000026D5-\U000026E8\U000026EB-\U000026EF\U000026F6\U000026FB-\U000026FC\U000026FE-\U000026FF\U00002388\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-\U0001F90B\U0001F91F\U0001F928-\U0001F92F\U0001F931-\U0001F932\U0001F94C\U0001F95F-\U0001F96B\U0001F992-\U0001F997\U0001F9D0-\U0001F9E6\U0001F90C-\U0001F90F\U0001F93F\U0001F94D-\U0001F94F\U0001F96C-\U0001F97F\U0001F998-\U0001F9BF\U0001F9C1-\U0001F9CF\U0001F9E7-\U0001F9FF\U0001F6C6-\U0001F6CA\U0001F6D3-\U0001F6D4\U0001F6E6-\U0001F6E8\U0001F6EA\U0001F6F1-\U0001F6F2\U0001F6F7-\U0001F6F8\U0001F6D5-\U0001F6DF\U0001F6ED-\U0001F6EF\U0001F6F9-\U0001F6FF];
-$E_Base_GAZ  = [\p{Grapheme_Cluster_Break = EBG}];
-$EmojiNRK    = [[\p{Emoji}] - [\p{Grapheme_Cluster_Break = Regional_Indicator}*\u00230-9©®™〰〽]];
+# 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;
 
 ## -------------------------------------------------
 !!chain;
 !!lookAheadHardBreak;

-!!forward;

 
 $CR $LF;
 
 
 $CR $LF;
 


@@ -58,17 +69,17 @@ $L ($L | $V | $LV | $LVT);
 # GB 9
 [^$Control $CR $LF] ($Extend | $ZWJ);
 
 # GB 9
 [^$Control $CR $LF] ($Extend | $ZWJ);
 

-# GB 9a (only for extended grapheme clusters)
+# GB 9a

 [^$Control $CR $LF] $SpacingMark;
 
 # GB 9b
 $Prepend [^$Control $CR $LF];
 
 [^$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* $E_Modifier;
+# GB 9.3, from CLDR-10994
+$LinkingConsonant $ExtCccZwj* $Virama $ExtCccZwj* $LinkingConsonant;

 
 

-# GB 11
-($Extended_Pict | $EmojiNRK) $Extend* $ZWJ ($Extended_Pict | $EmojiNRK);
+# GB 11 Do not break within emoji modifier sequences or emoji zwj sequences.
+$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,
 
 # GB 12-13. Keep pairs of regional indicators together
 #           Note that hard break '/' rule triggers only if there are three or more initial RIs,


@@ -76,44 +87,6 @@ $Prepend [^$Control $CR $LF];
 ^$Prepend* $Regional_Indicator $Regional_Indicator / $Regional_Indicator;
 ^$Prepend* $Regional_Indicator $Regional_Indicator;
 
 ^$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 $Extend* ($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)+ .;
-
-## -------------------------------------------------
+# GB 999 Match a single code point if no other rule applies.
+.;

 
 

-!!safe_forward;
-$Regional_Indicator $Regional_Indicator;
-($Extend | $ZWJ | $EmojiNRK | $Extended_Pict)+ .;