Index: source/data/brkitr/line_normal.txt |
diff --git a/source/data/brkitr/line_ja.txt b/source/data/brkitr/line_normal.txt |
similarity index 97% |
copy from source/data/brkitr/line_ja.txt |
copy to source/data/brkitr/line_normal.txt |
index 70b203d1b0d26afae1aa80d16797c0c40be68a8b..b03d01fc1518545393a571cc2a54454321f06142 100644 |
--- a/source/data/brkitr/line_ja.txt |
+++ b/source/data/brkitr/line_normal.txt |
@@ -1,16 +1,22 @@ |
-# Copyright (c) 2002-2013 International Business Machines Corporation and |
+# Copyright (c) 2002-2015 International Business Machines Corporation and |
# others. All Rights Reserved. |
# |
-# file: line_ja.txt |
+# file: line_normal.txt |
# |
# Line Breaking Rules |
# Implement default line breaking as defined by |
-# Unicode Standard Annex #14 Revision 29 for Unicode 6.2 |
+# Unicode Standard Annex #14 Revision 34 for Unicode 8.0 |
# http://www.unicode.org/reports/tr14/ |
+# tailored as noted in 2nd paragraph below.. |
# |
# TODO: Rule LB 8 remains as it was in Unicode 5.2 |
# This is only because of a limitation of ICU break engine implementation, |
# not because the older behavior is desirable. |
+# |
+# This tailors the line break behavior to correspond to CSS |
+# line-break=normal (BCP47 -u-lb-normal) as defined for languages other than |
+# Chinese & Japanese. |
+# It sets characters of class CJ to behave like ID. |
# |
# Character Classes defined by TR 14. |
@@ -349,6 +355,7 @@ $SYcm $HLcm; |
# LB 22 |
($ALcm | $HLcm) $INcm; |
$CM+ $INcm; # by rule 10, any otherwise unattached CM behaves as AL |
+$EXcm $INcm; |
$IDcm $INcm; |
$INcm $INcm; |
$NUcm $INcm; |
@@ -584,6 +591,7 @@ $CM* $HL $CM* $SY; |
# LB 22 |
$CM* $IN $CM* ($ALPlus | $HL); |
+$CM* $IN $CM* $EX; |
$CM* $IN $CM* $ID; |
$CM* $IN $CM* $IN; |
$CM* $IN $CM* $NU; |