Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

idnatest with NormalizationCorrections #829

Merged
merged 1 commit into from
May 23, 2024
Merged

idnatest with NormalizationCorrections #829

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 6 additions & 1 deletion unicodetools/data/idna/dev/IdnaTestV2.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
# IdnaTestV2.txt
# Date: 2024-05-22, 02:31:53 GMT
# Date: 2024-05-22, 22:45:49 GMT
# © 2024 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use and license, see https://www.unicode.org/terms_of_use.html
Expand Down Expand Up @@ -554,6 +554,11 @@ xn--ASCII-; ascii; [P4]; ; ; ; # ascii
ascii; ; ; ; ; ; # ascii
xn--unicode-.org; unicode.org; [P4]; ; ; ; # unicode.org
unicode.org; ; ; ; ; ; # unicode.org
陋㛼当𤎫竮䗗; 陋㛼当𤎫竮䗗; ; xn--snl253bgitxhzwu2arn60c; ; ; # 陋㛼当𤎫竮䗗
陋㛼当𤎫竮䗗; ; ; xn--snl253bgitxhzwu2arn60c; ; ; # 陋㛼当𤎫竮䗗
xn--snl253bgitxhzwu2arn60c; 陋㛼当𤎫竮䗗; ; xn--snl253bgitxhzwu2arn60c; ; ; # 陋㛼当𤎫竮䗗
電𡍪弳䎫窮䵗; ; ; xn--kbo60w31ob3z6t3av9z5b; ; ; # 電𡍪弳䎫窮䵗
xn--kbo60w31ob3z6t3av9z5b; 電𡍪弳䎫窮䵗; ; xn--kbo60w31ob3z6t3av9z5b; ; ; # 電𡍪弳䎫窮䵗

# RANDOMIZED TESTS

Expand Down
33 changes: 33 additions & 0 deletions unicodetools/src/main/java/org/unicode/idna/GenerateIdnaTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -935,5 +935,38 @@ public static UnicodeSet getIdna2008Valid() {
"xn---",
"xn--ASCII-",
"xn--unicode-.org",
// Characters in NormalizationCorrections.txt.
// Escpecially ones that changed in Unicode 4.0, after IDNA2003 was baked.
// F951;96FB;964B;3.2.0 # Corrigendum 3
// 2F868;2136A;36FC;4.0.0 # Corrigendum 4
// 2F874;5F33;5F53;4.0.0 # Corrigendum 4
// 2F91F;43AB;243AB;4.0.0 # Corrigendum 4
// 2F95F;7AAE;7AEE;4.0.0 # Corrigendum 4
// 2F9BF;4D57;45D7;4.0.0 # Corrigendum 4
//
// source characters
new StringBuilder("\uF951")
.appendCodePoint(0x2F868)
.appendCodePoint(0x2F874)
.appendCodePoint(0x2F91F)
.appendCodePoint(0x2F95F)
.appendCodePoint(0x2F9BF)
.toString(),
// old decompositions
new StringBuilder("\u96FB")
.appendCodePoint(0x2136A)
.appendCodePoint(0x5F33)
.appendCodePoint(0x43AB)
.appendCodePoint(0x7AAE)
.appendCodePoint(0x4D57)
.toString(),
// corrected decompositions
new StringBuilder("\u964B")
.appendCodePoint(0x36FC)
.appendCodePoint(0x5F53)
.appendCodePoint(0x243AB)
.appendCodePoint(0x7AEE)
.appendCodePoint(0x45D7)
.toString(),
};
}
Loading