diff options
Diffstat (limited to 'Build/source/libs/icu/icu-src/source/test/testdata/regextst.txt')
-rw-r--r-- | Build/source/libs/icu/icu-src/source/test/testdata/regextst.txt | 58 |
1 files changed, 57 insertions, 1 deletions
diff --git a/Build/source/libs/icu/icu-src/source/test/testdata/regextst.txt b/Build/source/libs/icu/icu-src/source/test/testdata/regextst.txt index a3f8dc78f5b..ee7bdf2227e 100644 --- a/Build/source/libs/icu/icu-src/source/test/testdata/regextst.txt +++ b/Build/source/libs/icu/icu-src/source/test/testdata/regextst.txt @@ -252,7 +252,7 @@ # Unicode word boundary mode # "(?w).*?\b" v "<0></0>hello, world" -"(?w).*?(\b.+?\b).*" v "<0><1> </1> 123.45 </0>" +"(?w).*?(\b.+?\b).*" v "<0><1> </1>123.45 </0>" "(?w).*?(\b\d.*?\b).*" v "<0> <1>123.45</1> </0>" ".*?(\b.+?\b).*" "<0> <1>123</1>.45 </0>" "(?w:.*?(\b\d.*?\b).*)" v "<0> <1>123.45</1> </0>" @@ -1363,6 +1363,62 @@ "abc" Z3 "abc abc <0>abc</0> xyz" "abc" z4 "abc abc abc xyz" +# Bug #13844 Verify that non-standard Java property names are recognized. +"[\p{IsAlphabetic}]" " <0>A</0>" +"[\P{IsAlphabetic}]" "A<0> </0>" +"[\p{IsIdeographic}]" "A<0>〆</0>" +"[\P{IsIdeographic}]" "〆<0>A</0>" +"[\p{IsLetter}]" " <0>A</0>" +"[\P{IsLetter}]" "A<0> </0>" +"[\p{Letter}]" " <0>A</0>" +"[\p{IsLowercase}]" "A<0>a</0>" +"[\P{IsLowercase}]" "a<0>A</0>" +"[\p{IsUppercase}]" "a<0>A</0>" +"[\P{IsUppercase}]" "A<0>a</0>" +"[\p{IsTitlecase}]" "D<0>Dz</0>" +"[\P{IsTitlecase}]" "Dz<0>D</0>" +"[\p{IsPunctuation}]" " <0>&</0>" +"[\P{IsPunctuation}]" "&<0> </0>" +"[\p{IsControl}]" " <0>\x{82}</0>" +"[\P{IsControl}]" "\x{82}<0> </0>" +"[\p{IsWhite_Space}]" "x<0> </0>" +"[\P{IsWhite_Space}]" " <0>x</0>" +"[\p{IsDigit}]" " <0>4</0>" +"[\P{IsDigit}]" "4<0> </0>" +"[\p{IsHex_Digit}]" " <0>F</0>" +"[\P{IsHex_Digit}]" "F<0> </0>" +"[\p{IsJoin_Control}]" " <0>\x{200d}</0>" +"[\P{IsJoin_Control}]" "\x{200d}<0> </0>" +"[\p{IsNoncharacter_Code_Point}]" "A<0>\x{5fffe}</0>" +"[\p{IsAssigned}]" "\x{10ffff}<0>a</0>" +"[\P{IsAssigned}]" "a<0>\x{10ffff}</0>" + +"[\p{InBasic Latin}]" "〆<0>A</0>" +"[\p{InBasicLatin}]" "〆<0>A</0>" +"[\p{InBasic-Latin}]" "〆<0>A</0>" # ICU accepts '-'; Java does not. +"[\p{InBasic_Latin}]" "〆<0>A</0>" +"[\p{Inbasiclatin}]" "〆<0>A</0>" +"[\p{inbasiclatin}]" E "〆<0>A</0>" # "In" must be cased as shown. Property name part is case insensitive. +"[\p{InCombining_Marks_for_Symbols}]" "a<0>\x{20DD}</0>" # COMBINING ENCLOSING CIRCLE + +"[\p{all}]*" "<0>\x{00}abc\x{10ffff}</0>" +"[\p{javaBadProperty}]" E "whatever" +"[\p{IsBadProperty}]" E "whatever" +"[\p{InBadBlock}]" E "whatever" +"[\p{In}]" E "whatever" +"[\p{Is}]" E "whatever" +"[\p{java}]" "x<0>ꦉ</0>" # Note: "java" is a valid script code. + +"[\p{javaLowerCase}]+" "A<0>a</0>" +"[\p{javaLowerCase}]+" i "<0>Aa</0>" +"[\P{javaLowerCase}]+" "<0>A</0>a" +"[\P{javaLowerCase}]+" i "Aa" # No Match because case fold of the set happens first, then negation. + # JDK is not case insensitive w named properties, even though + # the insensitive match flag is set. A JDK bug? + +"[a-z]+" i "<0>Aa</0>" # Matches JDK behavior. +"[^a-z]+" i "Aa" # (no match) which is JDK behavior. Case fold first, then negation. + # Random debugging, Temporary # |