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

components/url_formatter/idn_spoof_checker.cc

 // Copyright 2017 The Chromium Authors. All rights reserved.
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file.
 
 #include "components/url_formatter/idn_spoof_checker.h"
 
 #include "base/numerics/safe_conversions.h"
 #include "base/strings/string_split.h"
 #include "base/strings/string_util.h"
 #include "base/threading/thread_local_storage.h"
@@ skipping 214 matching lines @@
     // detection. ICU 58 does not detect MSC any more for a single input string.
     // See http://bugs.icu-project.org/trac/ticket/12823 .
     // TODO(jshin): adjust the pattern once the above ICU bug is fixed.
     // - Disallow U+30FB (Katakana Middle Dot) and U+30FC (Hiragana-Katakana
     //   Prolonged Sound) used out-of-context.
     // - Dislallow U+30FD/E (Katakana iteration mark/voiced iteration mark)
     //   unless they're preceded by a Katakana.
     // - 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.
     dangerous_pattern = new icu::RegexMatcher(
         icu::UnicodeString(
             R"([^\p{scx=kana}\p{scx=hira}\p{scx=hani}])"
             R"([\u30ce\u30f3\u30bd\u30be])"
             R"([^\p{scx=kana}\p{scx=hira}\p{scx=hani}]|)"
             R"([^\p{scx=kana}\p{scx=hira}]\u30fc|^\u30fc|)"
             R"([^\p{scx=kana}][\u30fd\u30fe]|^[\u30fd\u30fe]|)"
             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);
   }
   dangerous_pattern->reset(label_string);
   return !dangerous_pattern->find();
 }
 
 bool IDNSpoofChecker::SimilarToTopDomains(base::StringPiece16 hostname) {
   size_t hostname_length = hostname.length() - (hostname.back() == '.' ? 1 : 0);
   icu::UnicodeString ustr_host(FALSE, hostname.data(), hostname_length);
@@ skipping 52 matching lines @@
   allowed_set.addAll(*recommended_set);
   const icu::UnicodeSet* inclusion_set = uspoof_getInclusionUnicodeSet(status);
   allowed_set.addAll(*inclusion_set);
 
 // Five aspirational scripts are taken from UTR 31 Table 6 at
 // http://www.unicode.org/reports/tr31/#Aspirational_Use_Scripts .
 // Not all the characters of aspirational scripts are suitable for
 // 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
           "\\u2D30-\\u2D67\\u2D7F"
           // Yi
           "\\uA000-\\uA48C"
           // Miao
           "\\U00016F00-\\U00016F44\\U00016F50-\\U00016F7E"
           "\\U00016F8F-\\U00016F9F]",
           -1, US_INV),
@@ skipping 31 matching lines @@
   allowed_set.remove(0x0F8Cu);
   allowed_set.remove(0x0F8Du);
   allowed_set.remove(0x0F8Eu);
   allowed_set.remove(0x0F8Fu);
 #endif
 
   uspoof_setAllowedUnicodeSet(checker_, &allowed_set, status);
 }
 
 }  // namespace url_formatter