Index: source/data/brkitr/line_normal_fi.txt |
diff --git a/source/data/brkitr/line_fi.txt b/source/data/brkitr/line_normal_fi.txt |
similarity index 96% |
copy from source/data/brkitr/line_fi.txt |
copy to source/data/brkitr/line_normal_fi.txt |
index adf78bd3887404c8c429c6f4fb16167f11501db9..626fdbe9776dc226b880b1e8c71bc4de6a4b71fa 100644 |
--- a/source/data/brkitr/line_fi.txt |
+++ b/source/data/brkitr/line_normal_fi.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_fi.txt |
+# file: line_normal_fi.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 both for Finnish and to correpond 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. |
@@ -75,7 +81,7 @@ $HL = [:LineBreak = Hebrew_Letter:]; |
$HY = [:LineBreak = Hyphen:]; |
$H2 = [:LineBreak = H2:]; |
$H3 = [:LineBreak = H3:]; |
-$ID = [:LineBreak = Ideographic:]; |
+$ID = [[:LineBreak = Ideographic:] $CJ]; |
$IN = [:LineBreak = Inseperable:]; |
$IS = [:LineBreak = Infix_Numeric:]; |
$JL = [:LineBreak = JL:]; |
@@ -83,7 +89,7 @@ $JV = [:LineBreak = JV:]; |
$JT = [:LineBreak = JT:]; |
$LF = [:LineBreak = Line_Feed:]; |
$NL = [:LineBreak = Next_Line:]; |
-$NS = [[:LineBreak = Nonstarter:] $CJ]; |
+$NS = [:LineBreak = Nonstarter:]; |
$NU = [:LineBreak = Numeric:]; |
$OP = [:LineBreak = Open_Punctuation:]; |
$PO = [:LineBreak = Postfix_Numeric:]; |
@@ -355,6 +361,7 @@ $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; |
@@ -594,6 +601,7 @@ $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; |