diff options
Diffstat (limited to 'Build/source/libs/icu/icu-src/source/test/testdata/break_rules/line_normal_cj.txt')
-rw-r--r-- | Build/source/libs/icu/icu-src/source/test/testdata/break_rules/line_normal_cj.txt | 14 |
1 files changed, 5 insertions, 9 deletions
diff --git a/Build/source/libs/icu/icu-src/source/test/testdata/break_rules/line_normal_cj.txt b/Build/source/libs/icu/icu-src/source/test/testdata/break_rules/line_normal_cj.txt index a2704821441..a4e1428c2b2 100644 --- a/Build/source/libs/icu/icu-src/source/test/testdata/break_rules/line_normal_cj.txt +++ b/Build/source/libs/icu/icu-src/source/test/testdata/break_rules/line_normal_cj.txt @@ -20,7 +20,7 @@ # line-break=normal (BCP47 -u-lb-normal) as defined for Chinese & Japanese. # It sets characters of class CJ to behave like ID. # In addition, it allows breaks: -# * before hyphens 2010 & 2013 (both BA) and 301C, 30A0 (both NS) +# * before 301C, 30A0 (both NS) # It allows breaking before 201C and after 201D, for zh_Hans, zh_Hant, and ja. type = line; @@ -28,8 +28,7 @@ locale = ja@lb=normal; AI = [:LineBreak = Ambiguous:]; AL = [:LineBreak = Alphabetic:]; -BAX = [\u2010 \u2013]; -BA = [[:LineBreak = Break_After:] - BAX]; +BA = [:LineBreak = Break_After:]; HH = [\u2010]; # \u2010 is HYPHEN, default line break is BA. BB = [:LineBreak = Break_Before:]; BK = [:LineBreak = Mandatory_Break:]; @@ -154,7 +153,7 @@ LB11.3: WJ CM* [^CM]; LB12: GL CM* [^CM]; -LB12a: [^SP BA BAX HY] CM* GL; +LB12a: [^SP BA HY] CM* GL; # LB 13 Do not break before ‘]’ or ‘!’ or ‘/’, even after spaces. LB13.1: [^SP] CM* [CL CP EX SY]; @@ -182,12 +181,9 @@ LB20.09: ^(HY | HH) CM* AL; # Note: Rule 21a must come before 21 to prevent 21.1 from matching HL BA, then # not picking up the continuing match after the BA from 21a. -# TODO: For CJ tailorings (with BAX) does this rule want to include BAX? If so, -# should "HL BAX" not break when followed by a CB? Thats what the current -# rules do, which is why "[^CM CB]?" includes the ?. -LB21a: HL CM* (HY | BA | BAX) CM* [^CM CB]?; +LB21a: HL CM* (HY | BA) CM* [^CM CB]?; -# DO allow breaks here before $BAXcm and $NSXcm, so don't include them +# DO allow breaks here before $NSXcm, so don't include it LB21.1: . CM* [BA HY NS]; LB21.2: BB CM* [^CM CB]; |