ICU-551.30.tar.gz

[apple/icu.git] / icuSources / data / brkitr / line_fi.txt

diff --git a/icuSources/data/brkitr/line_fi.txt b/icuSources/data/brkitr/line_fi.txt
index 40e82369810b27d8ed9668c391525d68152fc56c..fd699c835b8b96f1095399c7804f67f8a28329ec 100644 (file)
--- a/icuSources/data/brkitr/line_fi.txt
+++ b/icuSources/data/brkitr/line_fi.txt
@@ -1,16 +1,21 @@
-# Copyright (c) 2002-2011  International Business Machines Corporation and
+# Copyright (c) 2002-2015  International Business Machines Corporation and
 # others. All Rights Reserved.
 #
 #  file:  line_fi.txt
 #
 #         Line Breaking Rules
 #         Implement default line breaking as defined by 
-#         Unicode Standard Annex #14 Revision 28 for Unicode 6.1
+#         Unicode Standard Annex #14 Revision 29 for Unicode 6.2
 #         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 for Finnish, while otherwise behaving
+#         per UAX 14 which corresponds to CSS line-break=strict (BCP47 -u-lb-strict).
+#         It sets characters of class CJ to behave like NS.
 
 #
 #  Character Classes defined by TR 14.
@@ -89,6 +94,7 @@ $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:];
@@ -97,6 +103,15 @@ $WJ = [:LineBreak =  Word_Joiner:];
 $XX = [:LineBreak =  Unknown:];
 $ZW = [:LineBreak =  ZWSpace:];
 
+# Special character classes for people & body part emoji:
+# Subsets of $CM:
+$ZWJ = \u200D;
+$EmojiVar = \uFE0F;
+# The following are subsets of $ID
+$EmojiForSeqs = [\u2764 \U0001F441 \U0001F466-\U0001F469 \U0001F48B \U0001F5E8];
+$EmojiForMods = [\u261D \u26F9 \u270A-\u270D \U0001F385 \U0001F3C3-\U0001F3C4 \U0001F3C7 \U0001F3CA-\U0001F3CB \U0001F442-\U0001F443 \U0001F446-\U0001F450 \U0001F466-\U0001F469 \U0001F46E-\U0001F478 \U0001F47C \U0001F481-\U0001F483 \U0001F485-\U0001F487 \U0001F4AA \U0001F590 \U0001F595 \U0001F596 \U0001F645-\U0001F647 \U0001F64B-\U0001F64F \U0001F6A3 \U0001F6B4-\U0001F6B6 \U0001F6C0 \U0001F918];
+$EmojiMods = [\U0001F3FB-\U0001F3FF];
+
 #   Dictionary character set, for triggering language-based break engines. Currently
 #   limited to LineBreak=Complex_Context. Note that this set only works in Unicode
 #   5.0 or later as the definition of Complex_Context was corrected to include all
@@ -141,6 +156,7 @@ $OPcm = $OP $CM*;
 $POcm = $PO $CM*;
 $PRcm = $PR $CM*;
 $QUcm = $QU $CM*;
+$RIcm = $RI $CM*;
 $SYcm = $SY $CM*;
 $WJcm = $WJ $CM*;
 
@@ -176,6 +192,7 @@ $OP $CM+;
 $PO $CM+;
 $PR $CM+;
 $QU $CM+;
+$RI $CM+;
 $SY $CM+;
 $WJ $CM+;
 
@@ -231,6 +248,10 @@ $LB8Breaks    = [$LB4Breaks $ZW];
 $LB8NonBreaks = [[$LB4NonBreaks] - [$ZW]];
 
 
+# Special forward rule for people & body part emoji:
+# don't break $ZWJ from subsequent $EmojiForSeqs
+$EmojiForSeqs $EmojiVar? $EmojiMods? $ZWJ $EmojiForSeqs;
+
 # LB 9     Combining marks.      X   $CM needs to behave like X, where X is not $SP, $BK $CR $LF $NL 
 #                                $CM not covered by the above needs to behave like $AL   
 #                                See definition of $CAN_CM.
@@ -345,6 +366,10 @@ $BBcm $LB20NonBreaks $CM*;
 #  
 $HLcm ($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
@@ -398,6 +423,12 @@ $IScm ($ALcm | $HLcm);
 $CM+ $OPcm;         # The $CM+ is from rule 10, an unattached CM is treated as AL.          
 $CPcm ($ALcm | $HLcm | $NUcm);
 
+# LB 30a  Do not break between regional indicators.
+$RIcm $RIcm;
+
+# Special forward rule for people & body part emoji:
+# don't break between relevant emoji and $EmojiMods
+$EmojiForMods $EmojiVar? $EmojiMods;
 
 #
 #  Reverse Rules.
@@ -431,6 +462,7 @@ $CM+ $OP;
 $CM+ $PO;
 $CM+ $PR;
 $CM+ $QU;
+$CM+ $RI;
 $CM+ $SY;
 $CM+ $WJ;
 $CM+;
@@ -481,6 +513,10 @@ $LF $CR;
 #           Requires an engine enhancement.
 #   / $SP* $ZW
 
+# Special reverse rule for people & body part emoji:
+# don't break $ZWJ from subsequent $EmojiForSeqs
+$EmojiForSeqs $ZWJ $EmojiMods? $EmojiVar? $EmojiForSeqs;
+
 # LB 9,10  Combining marks.
 #    X   $CM needs to behave like X, where X is not $SP or controls.
 #    $CM not covered by the above needs to behave like $AL
@@ -579,6 +615,8 @@ $CM* [$LB20NonBreaks-$CM] $CM* $BB;                   #  BB x .
 # LB21a
 [^$CB] $CM* ($HY | $BA | $HH) $CM* $HL;
 
+# LB21b (reverse)
+$CM* $HL $CM* $SY;
 
 # LB 22
 $CM* $IN $CM* ($ALPlus | $HL);
@@ -621,6 +659,12 @@ $CM* ($ALPlus | $HL) $CM* $IS;
 $CM* $OP $CM* ($ALPlus | $HL | $NU);
 $CM* ($ALPlus | $HL | $NU) $CM* $CP;
 
+# LB 30a
+$CM* $RI $CM* $RI;
+
+# Special reverse rule for people & body part emoji:
+# don't break between relevant emoji and $EmojiMods
+$EmojiMods $EmojiVar? $EmojiForMods;
 
 ## -------------------------------------------------