ICU 56 update step 1

source/data/brkitr/line_normal_cj.txt

Index: source/data/brkitr/line_normal_cj.txt
diff --git a/source/data/brkitr/line_ja.txt b/source/data/brkitr/line_normal_cj.txt
similarity index 91%
rename from source/data/brkitr/line_ja.txt
rename to source/data/brkitr/line_normal_cj.txt
index 70b203d1b0d26afae1aa80d16797c0c40be68a8b..908a41017fc5d2f4824139e9ea7917d5b81cd032 100644
--- a/source/data/brkitr/line_ja.txt
+++ b/source/data/brkitr/line_normal_cj.txt
@@ -1,16 +1,23 @@
-# 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_cj.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 Chinese & Japanese.
+#         It sets characters of class CJ to behave like ID.
+#         In addition, it allows breaks:
+#         * before hyphens 2010 & 2013 (both BA) and 301C, 30A0 (both NS)
 
 #
 #  Character Classes defined by TR 14.
@@ -58,7 +65,8 @@
 
 $AI = [:LineBreak =  Ambiguous:];
 $AL = [:LineBreak =  Alphabetic:];
-$BA = [:LineBreak =  Break_After:];
+$BAX = [\u2010 \u2013];
+$BA = [[:LineBreak =  Break_After:] - $BAX];
 $BB = [:LineBreak =  Break_Before:];
 $BK = [:LineBreak =  Mandatory_Break:];
 $B2 = [:LineBreak =  Break_Both:];
@@ -82,7 +90,8 @@ $JV = [:LineBreak =  JV:];
 $JT = [:LineBreak =  JT:];
 $LF = [:LineBreak =  Line_Feed:];
 $NL = [:LineBreak =  Next_Line:];
-$NS = [:LineBreak =  Nonstarter:];
+$NSX = [\u301C \u30A0];
+$NS = [[:LineBreak =  Nonstarter:] - $NSX];
 $NU = [:LineBreak =  Numeric:];
 $OP = [:LineBreak =  Open_Punctuation:];
 $PO = [:LineBreak =  Postfix_Numeric:];
@@ -118,6 +127,7 @@ $ALPlus = [$AL $AI $SA $SG $XX];
 #
 $ALcm = $ALPlus $CM*;
 $BAcm = $BA $CM*;
+$BAXcm = $BAX $CM*;
 $BBcm = $BB $CM*;
 $B2cm = $B2 $CM*;
 $CLcm = $CL $CM*;
@@ -135,6 +145,7 @@ $JLcm = $JL $CM*;
 $JVcm = $JV $CM*;
 $JTcm = $JT $CM*;
 $NScm = $NS $CM*;
+$NSXcm = $NSX $CM*;
 $NUcm = $NU $CM*;
 $OPcm = $OP $CM*;
 $POcm = $PO $CM*;
@@ -153,6 +164,7 @@ $WJcm = $WJ $CM*;
 #
 $ALPlus $CM+;
 $BA $CM+;
+$BAX $CM+;
 $BB $CM+;
 $B2 $CM+;
 $CL $CM+;
@@ -170,6 +182,7 @@ $JL $CM+;
 $JV $CM+;
 $JT $CM+;
 $NS $CM+;
+$NSX $CM+;
 $NU $CM+;
 $OP $CM+;
 $PO $CM+;
@@ -259,7 +272,7 @@ $GLcm $CANT_CM;
 # LB 12a  Do not break before NBSP and related characters ...
 #            [^SP BA HY] x GL
 #
-[[$LB8NonBreaks] - [$SP $BA $HY]] $CM* $GLcm;
+[[$LB8NonBreaks] - [$SP $BA $BAX $HY]] $CM* $GLcm;
 $CM+ GLcm;
 
 
@@ -300,6 +313,8 @@ $OPcm $SP+ $CM+ $AL_FOLLOW?;    # by rule 10, stand-alone CM behaves as AL
 $QUcm $SP* $OPcm;
 
 # LB 16
+# Do not break between closing punctuation and $NS, even with intervening spaces
+# But DO allow a break between closing punctuation and $NSX, don't include it here
 ($CLcm | $CPcm) $SP* $NScm;
 
 # LB 17
@@ -332,6 +347,7 @@ $LB20NonBreaks = [$LB18NonBreaks - $CB];
 # LB 21        x   (BA | HY | NS)
 #           BB x
 #
+# DO allow breaks here before $BAXcm and $NSXcm, so don't include them
 $LB20NonBreaks $CM* ($BAcm | $HYcm | $NScm); 
 
 $BBcm [^$CB];                                  #  $BB  x
@@ -340,7 +356,7 @@ $BBcm $LB20NonBreaks $CM*;
 # LB 21a Don't break after Hebrew + Hyphen
 #   HL (HY | BA) x
 #  
-$HLcm ($HYcm | $BAcm) [^$CB]?;
+$HLcm ($HYcm | $BAcm | $BAXcm) [^$CB]?;
 
 # LB 21b (forward) Don't break between SY and HL
 # (break between HL and SY already disallowed by LB 13 above)
@@ -349,6 +365,7 @@ $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;
@@ -411,6 +428,7 @@ $RIcm $RIcm;
 
 $CM+ $ALPlus;
 $CM+ $BA;
+$CM+ $BAX;
 $CM+ $BB;
 $CM+ $B2;
 $CM+ $CL;
@@ -428,6 +446,7 @@ $CM+ $JL;
 $CM+ $JV;
 $CM+ $JT;
 $CM+ $NS;
+$CM+ $NSX;
 $CM+ $NU;
 $CM+ $OP;
 $CM+ $PO;
@@ -501,7 +520,7 @@ $CM* $CAN_CM  $CM* $WJ;
 # LB 12a
 #      [^SP BA HY] x GL
 #
-$CM* $GL $CM* [$LB8NonBreaks-[$CM $SP $BA $HY]];
+$CM* $GL $CM* [$LB8NonBreaks-[$CM $SP $BA $BAX $HY]];
 
 # LB 12
 #     GL  x
@@ -546,6 +565,7 @@ $SY $CM $SP+ $OP;   # TODO:  Experiment.  Remove.
 $CM* $OP $SP* $CM* $QU;
 
 # LB 16
+# Don't include $NSX here
 $CM* $NS $SP* $CM* ($CL | $CP);
 
 # LB 17
@@ -571,19 +591,21 @@ $CM* $CAN_CM  $CM* $QU;                               #   QU x .
 #
 
 # LB 21
+# Don't include $BAX or $NSX here
 $CM* ($BA | $HY | $NS) $CM* [$LB20NonBreaks-$CM];     #  . x (BA | HY | NS)
 
 $CM* [$LB20NonBreaks-$CM] $CM* $BB;                   #  BB x .
 [^$CB] $CM* $BB;                                      # 
 
 # LB21a
-[^$CB] $CM* ($HY | $BA) $CM* $HL;
+[^$CB]? $CM* ($HY | $BA | $BAX) $CM* $HL;
 
 # LB21b (reverse)
 $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;
@@ -647,7 +669,7 @@ $SP+ $CM* ($CL | $CP);
 $SP+ $CM* $B2;
 
 # LB 21
-$CM* ($HY | $BA) $CM* $HL;
+$CM* ($HY | $BA | $BAX) $CM* $HL;
 
 # LB 25
 ($CM* ($IS | $SY))+ $CM* $NU;
@@ -669,6 +691,6 @@ $dictionary $dictionary;
 #  turn off rule chaining.  We don't want to move more
 #  than necessary.
 #
-[$CM $OP $QU $CL $CP $B2 $PR $HY $BA $SP $dictionary]+ [^$CM $OP $QU $CL $CP $B2 $PR $HY $BA $dictionary];
+[$CM $OP $QU $CL $CP $B2 $PR $HY $BA $BAX $SP $dictionary]+ [^$CM $OP $QU $CL $CP $B2 $PR $HY $BA $BAX $dictionary];
 $dictionary $dictionary;