Fix some ICU locale data

source/data/brkitr/line.txt

 # Copyright (c) 2002-2010  International Business Machines Corporation and
 # others. All Rights Reserved.
 #
 #  file:  line.txt
 #
 #         Line Breaking Rules
 #         Implement default line breaking as defined by 
 #         Unicode Standard Annex #14 Revision 24 for Unicode 6.0
 #         http://www.unicode.org/reports/tr14/
 #
@@ skipping 40 matching lines @@
 #
 #           If the CM is unattached, we need to force a break.
 #
 #           !!lookAheadHardBreak forces the run time state machine to
 #           stop immediately when a look ahead rule ( '/' operator) matches,
 #           and set the match position to that of the look-ahead operator,
 #           no matter what other rules may be in play at the time.
 #
 #           See rule LB 19 for an example.
 #
+$SmallHira = [\u3041 \u3043 \u3045 \u3047 \u3049 \u3063 \u3083 \u3085 \u3087 \u308E \u3095 \u3096];
+$SmallKata = [\u30A1 \u30A3 \u30A5 \u30A7 \u30A9 \u30C3 \u30E3 \u30E5 \u30E7 \u30EE \u30F5 \u30F6];
+$SmallKataExt = [\u31F0 \u31F1 \u31F2 \u31F3 \u31F4 \u31F5 \u31F6 \u31F7 \u31F8 \u31F9 \u31FA \u31FB \u31FC \u31FD \u31FE \u31FF];
+$SmallKanaAndProlongedMark = [[$SmallHira] [$SmallKata] [$SmallKataExt] [\u30FC]];
+
 
 $AI = [:LineBreak =  Ambiguous:];
 $AL = [[:LineBreak =  Alphabetic:] - [[:Hebrew:] & [:Letter:]] - [\u23B4\u23B5]];
 $HL = [[:Hebrew:] & [:Letter:]];
 $BA = [[:LineBreak =  Break_After:] - [\u2010]];
 $HH = [\u2010];
 $BB = [:LineBreak =  Break_Before:];
 $BK = [:LineBreak =  Mandatory_Break:];
 $B2 = [:LineBreak =  Break_Both:];
 $CB = [:LineBreak =  Contingent_Break:];
 $CL = [[:LineBreak =  Close_Punctuation:] [\uFE51\uFE10\u23B5]];
 $CM = [:LineBreak =  Combining_Mark:];
 $CP = [:LineBreak =  Close_Parenthesis:];
 $CR = [:LineBreak =  Carriage_Return:];
 $EX = [:LineBreak =  Exclamation:];
 $GL = [:LineBreak =  Glue:];
 $HY = [:LineBreak =  Hyphen:];
 $H2 = [:LineBreak =  H2:];
 $H3 = [:LineBreak =  H3:];
-$ID = [[:LineBreak =  Ideographic:] - [\uFE51]];
+$ID = [[[:LineBreak =  Ideographic:] - [\uFE51]] [$SmallKanaAndProlongedMark]];
 $IN = [:LineBreak =  Inseperable:];
 $IS = [[:LineBreak =  Infix_Numeric:] - [\uFE10]];
 $JL = [:LineBreak =  JL:];
 $JV = [:LineBreak =  JV:];
 $JT = [:LineBreak =  JT:];
 $LF = [:LineBreak =  Line_Feed:];
 $NL = [:LineBreak =  Next_Line:];
-$NS = [:LineBreak =  Nonstarter:];
+$NS = [[:LineBreak =  Nonstarter:] - [$SmallKanaAndProlongedMark]];
 $NU = [:LineBreak =  Numeric:];
 $OP = [[:LineBreak =  Open_Punctuation:] \u23B4];
 $PO = [:LineBreak =  Postfix_Numeric:];
 $PR = [:LineBreak =  Prefix_Numeric:];
 $QU = [:LineBreak =  Quotation:];
 $SA = [:LineBreak =  Complex_Context:];
 $SG = [:LineBreak =  Surrogate:];
 $SP = [:LineBreak =  Space:];
 $SY = [:LineBreak =  Break_Symbols:];
 $WJ = [:LineBreak =  Word_Joiner:];
@@ skipping 548 matching lines @@
 #   of context.
 #
 #  It might be slightly more efficient to have specific rules
 #  instead of one generic one, but only if we could
 #  turn off rule chaining.  We don't want to move more
 #  than necessary.
 #
 [$CM $OP $QU $CL $CP $B2 $PR $HY $SP $dictionary]+ [^$CM $OP $QU $CL $CP $B2 $PR $HY $dictionary];
 $dictionary $dictionary;