Index: icu52/source/data/brkitr/line.txt |
=================================================================== |
--- icu52/source/data/brkitr/line.txt (revision 259715) |
+++ icu52/source/data/brkitr/line.txt (working copy) |
@@ -12,9 +12,10 @@ |
# This is only because of a limitation of ICU break engine implementation, |
# not because the older behavior is desirable. |
-# |
-# Character Classes defined by TR 14. |
-# |
+# CHROME: 1. Use line_ja.txt to apply small kana rules in all locales. |
+# 2. Adjust CL, OP, and IS to handle 'comma-variants' consistently. |
+# 3. Adjust CL, QU, and OP to handle quotation marks around Chinese |
+# characters. |
!!chain; |
!!LBCMNoChain; |
@@ -57,14 +58,15 @@ |
# |
$AI = [:LineBreak = Ambiguous:]; |
-$AL = [:LineBreak = Alphabetic:]; |
+$AL = [[:LineBreak = Alphabetic:] - [\u23B4\u23B5]]; |
$BA = [:LineBreak = Break_After:]; |
$BB = [:LineBreak = Break_Before:]; |
$BK = [:LineBreak = Mandatory_Break:]; |
$B2 = [:LineBreak = Break_Both:]; |
$CB = [:LineBreak = Contingent_Break:]; |
$CJ = [:LineBreak = Conditional_Japanese_Starter:]; |
-$CL = [:LineBreak = Close_Punctuation:]; |
+$QU2CL = [\u2019\u201D\u275C\u275E]; |
+$CL = [[:LineBreak = Close_Punctuation:] [\uFE51\uFE10\u23B5] $QU2CL]; |
$CM = [:LineBreak = Combining_Mark:]; |
$CP = [:LineBreak = Close_Parenthesis:]; |
$CR = [:LineBreak = Carriage_Return:]; |
@@ -74,20 +76,21 @@ |
$HY = [:LineBreak = Hyphen:]; |
$H2 = [:LineBreak = H2:]; |
$H3 = [:LineBreak = H3:]; |
-$ID = [:LineBreak = Ideographic:]; |
+$ID = [[[:LineBreak = Ideographic:] $CJ] - [\uFE51]]; |
$IN = [:LineBreak = Inseperable:]; |
-$IS = [:LineBreak = Infix_Numeric:]; |
+$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:] $CJ]; |
+$NS = [:LineBreak = Nonstarter:]; |
$NU = [:LineBreak = Numeric:]; |
-$OP = [:LineBreak = Open_Punctuation:]; |
+$QU2OP = [\u2018\u201B\u201C\u201F\u275B\u275D]; |
+$OP = [[:LineBreak = Open_Punctuation:] \u23B4 $QU2OP]; |
$PO = [:LineBreak = Postfix_Numeric:]; |
$PR = [:LineBreak = Prefix_Numeric:]; |
-$QU = [:LineBreak = Quotation:]; |
+$QU = [[:LineBreak = Quotation:] - $QU2CL - $QU2OP]; |
$RI = [:LineBreak = Regional_Indicator:]; |
$SA = [:LineBreak = Complex_Context:]; |
$SG = [:LineBreak = Surrogate:]; |