Index: components/url_formatter/idn_spoof_checker.h |
diff --git a/components/url_formatter/idn_spoof_checker.h b/components/url_formatter/idn_spoof_checker.h |
index 41eafc637b1ce2847df644f26768fbbfa687b20a..41b46fcd09bcaadc5d64dd31d126d2d56e2c058f 100644 |
--- a/components/url_formatter/idn_spoof_checker.h |
+++ b/components/url_formatter/idn_spoof_checker.h |
@@ -17,6 +17,7 @@ |
// 'icu' does not work. Use U_ICU_NAMESPACE. |
namespace U_ICU_NAMESPACE { |
+class Transliterator; |
class UnicodeString; |
} // namespace U_ICU_NAMESPACE |
@@ -40,19 +41,35 @@ class IDNSpoofChecker { |
// See the function body for details on the specific safety checks performed. |
bool SafeToDisplayAsUnicode(base::StringPiece16 label, bool is_tld_ascii); |
+ // Returns true if |hostname| or the last few components of |hostname| looks |
+ // similar to one of top domains listed in top_domains/alexa_domains.list. Two |
+ // checks are done: |
+ // 1. Calculate the skeleton of |hostname| based on the Unicode confusable |
+ // character list and look it up in the pre-calculated skeleton list of |
+ // top domains. |
+ // 2. Look up the diacritic-free version of |hostname| in the list of |
+ // top domains. Note that non-IDN hostnames will not get here. |
+ bool SimilarToTopDomains(base::StringPiece16 hostname); |
+ |
private: |
// Sets allowed characters in IDN labels and turns on USPOOF_CHAR_LIMIT. |
void SetAllowedUnicodeSet(UErrorCode* status); |
// Returns true if all the Cyrillic letters in |label| belong to a set of |
Peter Kasting
2017/05/15 18:55:31
Nit: I would put a blank line above this comment a
jungshik at Google
2017/05/17 23:11:04
Done.
|
// Cyrillic letters that look like ASCII Latin letters. |
bool IsMadeOfLatinAlikeCyrillic(const icu::UnicodeString& label); |
+ // Returns true if the confusability skeleton for |hostname| is calculated |
+ // successfully and stored in |skeleton|. |
Peter Kasting
2017/05/15 18:55:31
Nit: This comment sounds like the function just ch
jungshik at Google
2017/05/17 23:11:04
ooops. Yeah, it's gone a few PS's ago. Thank you f
|
+ bool GetSkeleton(base::StringPiece16 hostname, std::string* skeleton); |
USpoofChecker* checker_; |
icu::UnicodeSet deviation_characters_; |
icu::UnicodeSet non_ascii_latin_letters_; |
icu::UnicodeSet kana_letters_exceptions_; |
+ icu::UnicodeSet combining_diacritics_exceptions_; |
icu::UnicodeSet cyrillic_letters_; |
icu::UnicodeSet cyrillic_letters_latin_alike_; |
+ icu::UnicodeSet lgc_letters_n_ascii_; |
+ std::unique_ptr<icu::Transliterator> transliterator_; |
IDNSpoofChecker(const IDNSpoofChecker&) = delete; |
void operator=(const IDNSpoofChecker&) = delete; |