ICU 56 update step 1

source/data/brkitr/line_loose_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_loose_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=loose (BCP47 -u-lb-loose) as defined for languages other than 
+#         Chinese & Japanese.
+#         It sets characters of class CJ to behave like ID.
+#         In addition, it allows breaks before 3005, 303B, 309D, 309E, 30FD, 30FE (all NS).
 
 #
 #  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:] $CJ];
+$NSX = [\u3005 \u303B \u309D \u309E \u30FD \u30FE];
+$NS = [[:LineBreak =  Nonstarter:] - $NSX];
 $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 33 matching lines @@
 $HYcm = $HY $CM*;
 $H2cm = $H2 $CM*;
 $H3cm = $H3 $CM*;
 $IDcm = $ID $CM*;
 $INcm = $IN $CM*;
 $IScm = $IS $CM*;
 $JLcm = $JL $CM*;
 $JVcm = $JV $CM*;
 $JTcm = $JT $CM*;
 $NScm = $NS $CM*;
+$NSXcm = $NSX $CM*;
 $NUcm = $NU $CM*;
 $OPcm = $OP $CM*;
 $POcm = $PO $CM*;
 $PRcm = $PR $CM*;
 $QUcm = $QU $CM*;
 $RIcm = $RI $CM*;
 $SYcm = $SY $CM*;
 $WJcm = $WJ $CM*;
 
 ## -------------------------------------------------
@@ skipping 16 matching lines @@
 $HY $CM+;
 $H2 $CM+;
 $H3 $CM+;
 $ID $CM+;
 $IN $CM+;
 $IS $CM+;
 $JL $CM+;
 $JV $CM+;
 $JT $CM+;
 $NS $CM+;
+$NSX $CM+;
 $NU $CM+;
 $OP $CM+;
 $PO $CM+;
 $PR $CM+;
 $QU $CM+;
 $RI $CM+;
 $SY $CM+;
 $WJ $CM+;
 
 #
 # CAN_CM  is the set of characters that may combine with CM combining chars.
 #         Note that Linebreak UAX 14's concept of a combining char and the rules
 #         for what they can combine with are _very_ different from the rest of Unicode.
 #
 #         Note that $CM itself is left out of this set.  If CM is needed as a base
 #         it must be listed separately in the rule.
 #
 $CAN_CM  = [^$SP $BK $CR $LF $NL $ZW $CM];       # Bases that can   take CMs
 $CANT_CM = [ $SP $BK $CR $LF $NL $ZW $CM];       # Bases that can't take CMs
 
 #
 # AL_FOLLOW  set of chars that can unconditionally follow an AL
 #            Needed in rules where stand-alone $CM s are treated as AL.
 #            Chaining is disabled with CM because it causes other failures,
 #            so for this one case we need to manually list out longer sequences.
 #
 $AL_FOLLOW_NOCM = [$BK $CR $LF $NL $ZW $SP];
-$AL_FOLLOW_CM   = [$CL $CP $EX $HL $IS $SY $WJ $GL $OP $QU $BA $HH $HY $NS $IN $NU $ALPlus];
+$AL_FOLLOW_CM   = [$CL $CP $EX $HL $IS $SY $WJ $GL $OP $QU $BA $HH $HY $NS $NSX $IN $NU $ALPlus];
 $AL_FOLLOW      = [$AL_FOLLOW_NOCM $AL_FOLLOW_CM];
 
 
 #
 #  Rule LB 4, 5    Mandatory (Hard) breaks.
 #
 $LB4Breaks    = [$BK $CR $LF $NL];
 $LB4NonBreaks = [^$BK $CR $LF $NL];
 $CR $LF {100};
 
@@ skipping 82 matching lines @@
 #
 $OPcm $SP* $CAN_CM $CM*;
 $OPcm $SP* $CANT_CM;
 
 $OPcm $SP+ $CM+ $AL_FOLLOW?;    # by rule 10, stand-alone CM behaves as AL
 
 # LB 15
 $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
 $B2cm $SP* $B2cm;
 
 #
 # LB 18  Break after spaces.
 #
 $LB18NonBreaks = [$LB8NonBreaks - [$SP]];
 $LB18Breaks    = [$LB8Breaks $SP];
@@ skipping 13 matching lines @@
 # LB 20
 #        <break>  $CB
 #        $CB   <break>
 
 $LB20NonBreaks = [$LB18NonBreaks - $CB];
 
 # LB 20.09 added rule for Finnish tailoring
 # LB 21        x   (BA | HY | NS)
 #           BB x
 #
+# DO allow breaks here before NSXcm, so don't include it
 $LB20NonBreaks $CM* ($BAcm | $HHcm | $HYcm | $NScm) / $AL; 
 $LB20NonBreaks $CM* ($BAcm | $HHcm | $HYcm | $NScm); 
 ($HY | $HH) $AL;
 
 $BBcm [^$CB];                                  #  $BB  x
 $BBcm $LB20NonBreaks $CM*;
 
 # LB 21a Don't break after Hebrew + Hyphen
 #   HL (HY | BA) x
 #  
 $HLcm ($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 60 matching lines @@
 $CM+ $HY;
 $CM+ $H2;
 $CM+ $H3;
 $CM+ $ID;
 $CM+ $IN;
 $CM+ $IS;
 $CM+ $JL;
 $CM+ $JV;
 $CM+ $JT;
 $CM+ $NS;
+$CM+ $NSX;
 $CM+ $NU;
 $CM+ $OP;
 $CM+ $PO;
 $CM+ $PR;
 $CM+ $QU;
 $CM+ $RI;
 $CM+ $SY;
 $CM+ $WJ;
 $CM+;
 
@@ skipping 98 matching lines @@
      $AL_FOLLOW_NOCM $CM+ $SP+ $CM* $OP;
 $CM* $AL_FOLLOW_CM   $CM+ $SP+ $CM* $OP;
 $SY $CM $SP+ $OP;   # TODO:  Experiment.  Remove.
 
 
 
 # LB 15
 $CM* $OP $SP* $CM* $QU;
 
 # LB 16
+# Don't include $NSX here
 $CM* $NS $SP* $CM* ($CL | $CP);
 
 # LB 17
 $CM* $B2 $SP* $CM* $B2;
 
 # LB 18  break after spaces
 #        Nothing explicit needed here.
 
 
 #
 # LB 19
 #
 $CM* $QU $CM* $CAN_CM;                                #   . x QU
 $CM* $QU      $LB18NonBreaks;
 
 
 $CM* $CAN_CM  $CM* $QU;                               #   QU x .
      $CANT_CM $CM* $QU;
      
 #
 #  LB 20  Break before and after CB.
 #         nothing needed here.
 #
 
 # LB 20.09 added rule for Finnish tailoring
 $AL ($HY | $HH) / $SP;
 
 # LB 21
+# Don't include $NSX here
 $CM* ($BA | $HH | $HY | $NS) $CM* [$LB20NonBreaks-$CM];     #  . x (BA | HY | NS)
 
 $CM* [$LB20NonBreaks-$CM] $CM* $BB;                   #  BB x .
 [^$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;