Chromium Code Reviews
chromiumcodereview-hr@appspot.gserviceaccount.com (chromiumcodereview-hr) | Please choose your nickname with Settings | Help | Chromium Project | Gerrit Changes | Sign out
(207)

Unified Diff: source/data/brkitr/line_loose_fi.txt

Issue 1621843002: ICU 56 update step 1 (Closed) Base URL: https://chromium.googlesource.com/chromium/deps/icu.git@561
Patch Set: Created 4 years, 11 months ago
Use n/p to move between diff chunks; N/P to move between comments. Draft comments are only viewable by you.
Jump to:
View side-by-side diff with in-line comments
Download patch
« no previous file with comments | « source/data/brkitr/line_loose_cj.txt ('k') | source/data/brkitr/line_normal.txt » ('j') | no next file with comments »
Expand Comments ('e') | Collapse Comments ('c') | Show Comments Hide Comments ('s')
Index: source/data/brkitr/line_loose_fi.txt
diff --git a/source/data/brkitr/line_fi.txt b/source/data/brkitr/line_loose_fi.txt
similarity index 93%
copy from source/data/brkitr/line_fi.txt
copy to source/data/brkitr/line_loose_fi.txt
index adf78bd3887404c8c429c6f4fb16167f11501db9..c5dae9f85eea0fb59b5ceadc421cc621c77ecb67 100644
--- a/source/data/brkitr/line_fi.txt
+++ b/source/data/brkitr/line_loose_fi.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_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.
@@ -75,7 +82,7 @@ $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:];
@@ -83,7 +90,8 @@ $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:];
@@ -137,6 +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*;
@@ -173,6 +182,7 @@ $JL $CM+;
$JV $CM+;
$JT $CM+;
$NS $CM+;
+$NSX $CM+;
$NU $CM+;
$OP $CM+;
$PO $CM+;
@@ -200,7 +210,7 @@ $CANT_CM = [ $SP $BK $CR $LF $NL $ZW $CM]; # Bases that can't take CMs
# 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];
@@ -303,6 +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
@@ -336,6 +348,7 @@ $LB20NonBreaks = [$LB18NonBreaks - $CB];
# 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;
@@ -355,6 +368,7 @@ $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;
@@ -435,6 +449,7 @@ $CM+ $JL;
$CM+ $JV;
$CM+ $JT;
$CM+ $NS;
+$CM+ $NSX;
$CM+ $NU;
$CM+ $OP;
$CM+ $PO;
@@ -553,6 +568,7 @@ $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
@@ -581,6 +597,7 @@ $CM* $CAN_CM $CM* $QU; # QU x .
$AL ($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 .
@@ -594,6 +611,7 @@ $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;
« no previous file with comments | « source/data/brkitr/line_loose_cj.txt ('k') | source/data/brkitr/line_normal.txt » ('j') | no next file with comments »

Powered by Google App Engine
This is Rietveld 408576698