Chromium Code Reviews
chromiumcodereview-hr@appspot.gserviceaccount.com (chromiumcodereview-hr) | Please choose your nickname with Settings | Help | Chromium Project | Gerrit Changes | Sign out
(2)

Unified Diff: icu46/source/data/brkitr/line.txt

Issue 6349014: ... (Closed) Base URL: svn://chrome-svn/chrome/trunk/deps/third_party/
Patch Set: Created 9 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 | « icu46/source/data/brkitr/brklocal.mk ('k') | icu46/source/data/brkitr/word.txt » ('j') | no next file with comments »
Expand Comments ('e') | Collapse Comments ('c') | Show Comments Hide Comments ('s')
Index: icu46/source/data/brkitr/line.txt
===================================================================
--- icu46/source/data/brkitr/line.txt (revision 68397)
+++ icu46/source/data/brkitr/line.txt (working copy)
@@ -11,6 +11,9 @@
# 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.
+#
+# CHROME: Hebrew tailoring was incorporatd as well as some
+# other minor changes (CL, OP, ID).
#
# Character Classes defined by TR 14.
@@ -57,13 +60,15 @@
#
$AI = [:LineBreak = Ambiguous:];
-$AL = [:LineBreak = Alphabetic:];
-$BA = [:LineBreak = Break_After:];
+$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:];
+$CL = [[:LineBreak = Close_Punctuation:] [\uFE51\uFE10\u23B5]];
$CM = [:LineBreak = Combining_Mark:];
$CP = [:LineBreak = Close_Parenthesis:];
$CR = [:LineBreak = Carriage_Return:];
@@ -72,9 +77,9 @@
$HY = [:LineBreak = Hyphen:];
$H2 = [:LineBreak = H2:];
$H3 = [:LineBreak = H3:];
-$ID = [:LineBreak = Ideographic:];
+$ID = [[:LineBreak = Ideographic:] - [\uFE51]];
$IN = [:LineBreak = Inseperable:];
-$IS = [:LineBreak = Infix_Numeric:];
+$IS = [[:LineBreak = Infix_Numeric:] - [\uFE10]];
$JL = [:LineBreak = JL:];
$JV = [:LineBreak = JV:];
$JT = [:LineBreak = JT:];
@@ -82,7 +87,7 @@
$NL = [:LineBreak = Next_Line:];
$NS = [:LineBreak = Nonstarter:];
$NU = [:LineBreak = Numeric:];
-$OP = [:LineBreak = Open_Punctuation:];
+$OP = [[:LineBreak = Open_Punctuation:] \u23B4];
$PO = [:LineBreak = Postfix_Numeric:];
$PR = [:LineBreak = Prefix_Numeric:];
$QU = [:LineBreak = Quotation:];
@@ -108,13 +113,15 @@
# XX (Unknown, unassigned)
# as $AL (Alphabetic)
#
-$ALPlus = [$AL $AI $SA $SG $XX];
+$ALPlus = [$AL $HL $AI $SA $SG $XX];
#
# Combining Marks. X $CM* behaves as if it were X. Rule LB6.
#
$ALcm = $ALPlus $CM*;
+$HLcm = $HL $CM*;
$BAcm = $BA $CM*;
+$HHcm = $HH $CM*;
$BBcm = $BB $CM*;
$B2cm = $B2 $CM*;
$CLcm = $CL $CM*;
@@ -148,6 +155,7 @@
#
$ALPlus $CM+;
$BA $CM+;
+$HH $CM+;
$BB $CM+;
$B2 $CM+;
$CL $CM+;
@@ -190,7 +198,7 @@
# 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 $IS $SY $WJ $GL $OP $QU $BA $HY $NS $IN $NU $ALPlus];
+$AL_FOLLOW_CM = [$CL $CP $EX $IS $SY $WJ $GL $OP $QU $BA $HH $HY $NS $IN $NU $ALPlus];
$AL_FOLLOW = [$AL_FOLLOW_NOCM $AL_FOLLOW_CM];
@@ -252,7 +260,7 @@
# LB 12a Do not break before NBSP and related characters ...
# [^SP BA HY] x GL
#
-[[$LB8NonBreaks] - [$SP $BA $HY]] $CM* $GLcm;
+[[$LB8NonBreaks] - [$SP $BA $HH $HY]] $CM* $GLcm;
$CM+ GLcm;
@@ -325,7 +333,7 @@
# LB 21 x (BA | HY | NS)
# BB x
#
-$LB20NonBreaks $CM* ($BAcm | $HYcm | $NScm);
+$LB20NonBreaks $CM* ($BAcm | $HHcm | $HYcm | $NScm);
$BBcm [^$CB]; # $BB x
$BBcm $LB20NonBreaks $CM*;
@@ -381,6 +389,8 @@
$CM+ $OPcm; # The $CM+ is from rule 10, an unattached CM is treated as AL.
$CPcm ($ALcm | $NUcm);
+# (LB 31) Add new rule to prevent the break we do not want, this is the behavior change
+$HLcm ($HY | $HH) $ALcm;
#
# Reverse Rules.
@@ -391,6 +401,7 @@
$CM+ $ALPlus;
$CM+ $BA;
+$CM+ $HH;
$CM+ $BB;
$CM+ $B2;
$CM+ $CL;
@@ -479,7 +490,7 @@
# LB 12a
# [^SP BA HY] x GL
#
-$CM* $GL $CM* [$LB8NonBreaks-[$CM $SP $BA $HY]];
+$CM* $GL $CM* [$LB8NonBreaks-[$CM $SP $BA $HH $HY]];
# LB 12
# GL x
@@ -549,7 +560,7 @@
#
# LB 21
-$CM* ($BA | $HY | $NS) $CM* [$LB20NonBreaks-$CM]; # . x (BA | HY | NS)
+$CM* ($BA | $HH | $HY | $NS) $CM* [$LB20NonBreaks-$CM]; # . x (BA | HY | NS)
$CM* [$LB20NonBreaks-$CM] $CM* $BB; # BB x .
[^$CB] $CM* $BB; #
@@ -597,6 +608,8 @@
$CM* $OP $CM* ($ALPlus | $NU);
$CM* ($ALPlus | $NU) $CM* $CP;
+# (LB 31) Add new rule to prevent the break we do not want, this is the behavior change
+$CM* $ALPlus ($HY | $HH) $CM* $HL;
## -------------------------------------------------
« no previous file with comments | « icu46/source/data/brkitr/brklocal.mk ('k') | icu46/source/data/brkitr/word.txt » ('j') | no next file with comments »

Powered by Google App Engine
This is Rietveld 408576698