Chromium Code Reviews| Index: components/url_formatter/url_formatter_unittest.cc |
| diff --git a/components/url_formatter/url_formatter_unittest.cc b/components/url_formatter/url_formatter_unittest.cc |
| index 4b114f0f87a50fc1aec091ebcb91b25eba8df4a5..53e9deb18329121d1c09ec4e2f34377dcabb146b 100644 |
| --- a/components/url_formatter/url_formatter_unittest.cc |
| +++ b/components/url_formatter/url_formatter_unittest.cc |
| @@ -275,6 +275,34 @@ const IDNTestCase idn_cases[] = { |
| // музей (museum in Russian) has characters without a Latin-look-alike. |
| {"xn--e1adhj9a.com", L"\x043c\x0443\x0437\x0435\x0439.com", true}, |
| + // Combining Diacritic marks after a script other than Latin-Greek-Cyrillic |
| + {"xn--rsa2568fvxya.com", L"\xd55c\x0301\xae00.com", false}, // 한́글.com |
| + {"xn--rsa0336bjom.com", L"\x6f22\x0307\x5b57.com", false}, // 漢̇字.com |
| + // नागरी́.com |
| + {"xn--lsa922apb7a6do.com", L"\x0928\x093e\x0917\x0930\x0940\x0301.com", |
| + false}, |
| + |
| + // Similarity checks against the list of top domains. "digklmo68.com" and |
| + // 'digklmo68.co.uk" are listed for unittest in the top domain list. |
|
Peter Kasting
2017/05/10 22:38:47
I still would like to see the test poke these into
jungshik at Google
2017/05/14 09:36:23
I don't disagree with you, but couldn't think of a
ncarter (slow)
2017/05/15 18:27:57
The way the other unittests work, we do a separate
Peter Kasting
2017/05/15 18:55:31
SGTM
|
| + {"xn--igklmo68-nea32c.com", L"\x0111igklmo68.com", false}, // đigklmo68.com |
| + {"www.xn--igklmo68-nea32c.com", L"www.\x0111igklmo68.com", false}, |
| + {"foo.bar.xn--igklmo68-nea32c.com", L"foo.bar.\x0111igklmo68.com", false}, |
| + {"xn--igklmo68-nea32c.co.uk", L"\x0111igklmo68.co.uk", false}, |
| + {"mail.xn--igklmo68-nea32c.co.uk", L"mail.\x0111igklmo68.co.uk", false}, |
| + {"xn--digklmo68-6jf.com", L"di\x0307gklmo68.com", false}, // di̇gklmo68.com |
| + {"xn--digklmo68-7vf.com", L"dig\x0331klmo68.com", false}, // dig̱klmo68.com |
| + {"xn--diglmo68-omb.com", L"dig\x0138lmo68.com", false}, // digĸlmo68.com |
| + {"xn--digkmo68-9ob.com", L"digk\x0142mo68.com", false}, // digkłmo68.com |
| + {"xn--digklo68-l89c.com", L"digkl\x1e43o68.com", false}, // digklṃo68.com |
| + {"xn--digklm68-b5a.com", L"digklm\x00f8" L"68.com", false}, // digklmø68.com |
| + {"xn--digklmo8-h7g.com", L"digklmo\x0431" L"8.com", false}, // digklmoб8.com |
| + {"xn--digklmo6-7yr.com", L"digklmo6\x09ea.com", false}, // digklmo6৪.com |
| + |
| + // 'islkpx123.com' is listed for unitest in the top domain list. |
| + // 'іѕӏкрх123' can look like 'islkpx123' in some fonts. |
| + {"xn--123-bed4a4a6hh40i.com", |
| + L"\x0456\x0455\x04cf\x043a\x0440\x0445" L"123.com", false}, |
| + |
| // Mixed digits: the first two will also fail mixed script test |
| // Latin + ASCII digit + Deva digit |
| {"xn--asc1deva-j0q.co.in", L"asc1deva\x0967.co.in", false}, |
| @@ -308,15 +336,15 @@ const IDNTestCase idn_cases[] = { |
| // U+115F (Hangul Filler) |
| {"xn--osd3820f24c.kr", L"\xac00\xb098\x115f.kr", false}, |
| {"www.xn--google-ho0coa.com", L"www.\x2039google\x203a.com", false}, |
| - // Latin small capital w |
| + // Latin small capital w: hardᴡare.com |
| {"xn--hardare-l41c.com", L"hard\x1d21" L"are.com", false}, |
| // Minus Sign(U+2212) |
| {"xn--t9g238xc2a.jp", L"\x65e5\x2212\x672c.jp", false}, |
| - // Latin Small Letter Script G |
| + // Latin Small Letter Script G: ɡɡ.com |
| {"xn--0naa.com", L"\x0261\x0261.com", false}, |
| // Hangul Jamo(U+11xx) |
| {"xn--0pdc3b.com", L"\x1102\x1103\x1110.com", false}, |
| - // degree sign |
| + // degree sign: 36°c.com |
| {"xn--36c-tfa.com", L"36\x00b0" L"c.com", false}, |
| // Pound sign |
| {"xn--5free-9ga.com", L"5free\x00a8.com", false}, |
| @@ -328,7 +356,7 @@ const IDNTestCase idn_cases[] = { |
| {"xn--oogle-qmc.com", L"\x0261oogle.com", false}, |
| // Small Katakana Extension(U+31F1) |
| {"xn--wlk.com", L"\x31f1.com", false}, |
| - // Heart symbol |
| + // Heart symbol: ♥ |
| {"xn--ab-u0x.com", L"ab\x2665.com", false}, |
| // Emoji |
| {"xn--vi8hiv.xyz", L"\U0001f355\U0001f4a9.xyz", false}, |
| @@ -338,7 +366,7 @@ const IDNTestCase idn_cases[] = { |
| {"xn--registered-25c.com", L"registered\x01c3.com", false}, |
| // ASCII '!' not allowed in IDN |
| {"xn--!-257eu42c.kr", L"\xc548\xb155!.kr", false}, |
| - // 'GOOGLE' in IPA extension |
| + // 'GOOGLE' in IPA extension: ɢᴏᴏɢʟᴇ |
| {"xn--1naa7pn51hcbaa.com", |
| L"\x0262\x1d0f\x1d0f\x0262\x029f\x1d07.com", false}, |
| // Padlock icon spoof. |