Drop Mongolian from the IDN script list and tighten up the policy on Armenian-Latin mixing

components/url_formatter/idn_spoof_checker.cc

Index: components/url_formatter/idn_spoof_checker.cc
diff --git a/components/url_formatter/idn_spoof_checker.cc b/components/url_formatter/idn_spoof_checker.cc
index c3209cc6d4a699c012225de86f165a7fd3203613..f6a1a51b3d43ef2c8b394e15d7d5da984fb48cfa 100644
--- a/components/url_formatter/idn_spoof_checker.cc
+++ b/components/url_formatter/idn_spoof_checker.cc
@@ -232,11 +232,10 @@ bool IDNSpoofChecker::SafeToDisplayAsUnicode(base::StringPiece16 label,
     // - Disallow three Hiragana letters (U+307[8-A]) or Katakana letters
     //   (U+30D[8-A]) that look exactly like each other when they're used in a
     //   label otherwise entirely in Katakna or Hiragana.
-    // - Disallow U+0585 (Armenian Small Letter Oh) and U+0581 (Armenian Small
-    //   Letter Co) to be next to Latin.
-    // - Disallow Latin 'o' and 'g' next to Armenian.
+    // - Disalow mixing of Latin and Armenian

[Peter Kasting, 2017/08/29 04:08:30]

Nit: Period at end (2 places)

     // - Disalow mixing of Latin and Canadian Syllabary.
     // - Disalow mixing of Latin and Tifinagh.
+    // - Disalow mixing of Latin and Miao
     // - Disallow combining diacritical mark (U+0300-U+0339) after a non-LGC
     //   character. Other combining diacritical marks are not in the allowed
     //   character set.
@@ -250,14 +249,11 @@ bool IDNSpoofChecker::SafeToDisplayAsUnicode(base::StringPiece16 label,
             R"(^[\p{scx=kana}]+[\u3078-\u307a][\p{scx=kana}]+$|)"
             R"(^[\p{scx=hira}]+[\u30d8-\u30da][\p{scx=hira}]+$|)"
             R"([a-z]\u30fb|\u30fb[a-z]|)"
-            R"(^[\u0585\u0581]+[a-z]|[a-z][\u0585\u0581]+$|)"
-            R"([a-z][\u0585\u0581]+[a-z]|)"
-            R"(^[og]+[\p{scx=armn}]|[\p{scx=armn}][og]+$|)"
-            R"([\p{scx=armn}][og]+[\p{scx=armn}]|)"
+            R"([\p{sc=armn}].*[a-z]|[a-z].*[\p{sc=armn}]|)"
             R"([\p{sc=cans}].*[a-z]|[a-z].*[\p{sc=cans}]|)"
             R"([\p{sc=tfng}].*[a-z]|[a-z].*[\p{sc=tfng}]|)"
-            R"([^\p{scx=latn}\p{scx=grek}\p{scx=cyrl}][\u0300-\u0339])",
-            -1, US_INV),

[Peter Kasting, 2017/08/29 04:08:29]

Were these just default values?

+            R"([\p{sc=miao}].*[a-z]|[a-z].*[\p{sc=miao}]|)"
+            R"([^\p{scx=latn}\p{scx=grek}\p{scx=cyrl}][\u0300-\u0339])"),
         0, status);
     tls_index.Set(dangerous_pattern);
   }
@@ -330,17 +326,16 @@ void IDNSpoofChecker::SetAllowedUnicodeSet(UErrorCode* status) {
 // identifiers. Therefore, only characters belonging to
 // [:Identifier_Type=Aspirational:] (listed in 'Status/Type=Aspirational'
 // section at
-// http://www.unicode.org/Public/security/latest/xidmodifications.txt) are
-// are added to the allowed set. The list has to be updated when a new
+// http://www.unicode.org/Public/security/9.0.0/IdentifierType.txt) are
+// added to the allowed set. The list has to be updated when a new
 // version of Unicode is released. The current version is 9.0.0 and ICU 60
 // will have Unicode 10.0 data.
+// Note that Mongolian is dropped because it's written vertically.
 #if U_ICU_VERSION_MAJOR_NUM < 60
   const icu::UnicodeSet aspirational_scripts(
       icu::UnicodeString(
           // Unified Canadian Syllabics
           "[\\u1401-\\u166C\\u166F-\\u167F"
-          // Mongolian
-          "\\u1810-\\u1819\\u1820-\\u1877\\u1880-\\u18AA"
           // Unified Canadian Syllabics
           "\\u18B0-\\u18F5"
           // Tifinagh