Update aspirational_scripts per Unicode 9

components/url_formatter/url_formatter.cc

 // Copyright 2015 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/url_formatter.h"
 
 #include <algorithm>
 #include <utility>
 
 #include "base/lazy_instance.h"
@@ skipping 410 matching lines @@
   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
-  // version of Unicode is released. The current version is 8.0.0 and ICU 58
-  // will have Unicode 9.0 data.
-#if U_ICU_VERSION_MAJOR_NUM < 58
+  // version of Unicode is released. The current version is 9.0.0 and ICU 60
+  // will have Unicode 10.0 data.
+#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-\\U00016F7F"
+          "\\U00016F00-\\U00016F44\\U00016F50-\\U00016F7E"
           "\\U00016F8F-\\U00016F9F]",
           -1, US_INV),
       *status);
   allowed_set.addAll(aspirational_scripts);
 #else
-#error "Update aspirational_scripts per Unicode 9.0"
+#error "Update aspirational_scripts per Unicode 10.0"
 #endif
 
   // U+0338 is included in the recommended set, while U+05F4 and U+2027 are in
   // the inclusion set. However, they are blacklisted as a part of Mozilla's
   // IDN blacklist (http://kb.mozillazine.org/Network.IDN.blacklist_chars).
   // U+0338 and U+2027 are dropped; the former can look like a slash when
   // rendered with a broken font, and the latter can be confused with U+30FB
   // (Katakana Middle Dot). U+05F4 (Hebrew Punctuation Gershayim) is kept,
   // even though it can look like a double quotation mark. Using it in Hebrew
   // should be safe. When used with a non-Hebrew script, it'd be filtered by
@@ skipping 326 matching lines @@
   return base::StartsWith(text, www, base::CompareCase::SENSITIVE)
       ? text.substr(www.length()) : text;
 }
 
 base::string16 StripWWWFromHost(const GURL& url) {
   DCHECK(url.is_valid());
   return StripWWW(base::ASCIIToUTF16(url.host_piece()));
 }
 
 }  // namespace url_formatter