ICU 56 update step 1

source/data/brkitr/line_normal_fi.txt

-# 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.
 #
 
 !!chain;
 !!LBCMNoChain;
 
 
 !!lookAheadHardBreak;
@@ skipping 44 matching lines @@
 $CL = [:LineBreak =  Close_Punctuation:];
 $CM = [:LineBreak =  Combining_Mark:];
 $CP = [:LineBreak =  Close_Parenthesis:];
 $CR = [:LineBreak =  Carriage_Return:];
 $EX = [:LineBreak =  Exclamation:];
 $GL = [:LineBreak =  Glue:];
 $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:];
 $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:];
 $PR = [:LineBreak =  Prefix_Numeric:];
 $QU = [:LineBreak =  Quotation:];
 $RI = [:LineBreak =  Regional_Indicator:];
 $SA = [:LineBreak =  Complex_Context:];
 $SG = [:LineBreak =  Surrogate:];
 $SP = [:LineBreak =  Space:];
 $SY = [:LineBreak =  Break_Symbols:];
@@ skipping 251 matching lines @@
 #  
 $HLcm ($HYcm | $BAcm | $HHcm) [^$CB]?;
 
 # LB 21b (forward) Don't break between SY and HL
 # (break between HL and SY already disallowed by LB 13 above)
 $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;
 
 
 # $LB 23
 $IDcm  $POcm;
 $ALcm  $NUcm;       # includes $LB19
 $HLcm  $NUcm;
 $CM+   $NUcm;       # Rule 10, any otherwise unattached CM behaves as AL
@@ skipping 219 matching lines @@
 [^$CB] $CM* $BB;                                      # 
 
 # LB21a
 [^$CB] $CM* ($HY | $BA | $HH) $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;
 
 # LB 23
 $CM* $PO $CM* $ID;
 $CM* $NU $CM* ($ALPlus | $HL);
 $CM* ($ALPlus | $HL) $CM* $NU;
 
 # LB 24
@@ skipping 68 matching lines @@
 #   of context.
 #
 #  It might be slightly more efficient to have specific rules
 #  instead of one generic one, but only if we could
 #  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];
 $dictionary $dictionary;