ICU-64232.0.1.tar.gz

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

diff --git a/icuSources/data/brkitr/rules/word_POSIX.txt b/icuSources/data/brkitr/rules/word_POSIX.txt
index 79126931ead2fbc5ef31d60376c67ed13514fa44..bf6013951d45b26e4e1ccf6f541fa3edfdb8bc7b 100644 (file)
--- a/icuSources/data/brkitr/rules/word_POSIX.txt
+++ b/icuSources/data/brkitr/rules/word_POSIX.txt
@@ -8,9 +8,7 @@
 #
 # ICU Word Break Rules, POSIX locale.
 #      See Unicode Standard Annex #29.
-#      These rules are based on UAX #29 Revision 29 for Unicode Version 9.0
-#      with additions for Emoji Sequences from https://goo.gl/cluFCn
-#      Plus additional characters introduces with Emoji 5, http://www.unicode.org/reports/tr51/proposed.html
+#      These rules are based on UAX #29 Revision 34 for Unicode Version 12.0
 #
 # Note:  Updates to word.txt will usually need to be merged into
 #        word_POSIX.txt also.
@@ -44,7 +42,7 @@ $Double_Quote       = [\p{Word_Break = Double_Quote}];
 $MidNumLet          = [\p{Word_Break = MidNumLet} - [.]];
 $MidLetter          = [\p{Word_Break = MidLetter} - [\:]];
 $MidNum             = [\p{Word_Break = MidNum} [.]];
-$Numeric            = [\p{Word_Break = Numeric}];
+$Numeric            = [[\p{Word_Break = Numeric}] [\uFF10-\uff19]];  # Patch for ICU-12079
 $ExtendNumLet       = [\p{Word_Break = ExtendNumLet}];
 $WSegSpace          = [\p{Word_Break = WSegSpace}];
 $Extended_Pict      = [:ExtPict:];