Implement a new IDN display policy

components/url_formatter/url_formatter_unittest.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 <stddef.h>
 #include <string.h>
 
 #include <vector>
 
 #include "base/macros.h"
 #include "base/strings/string_number_conversions.h"
 #include "base/strings/stringprintf.h"
 #include "base/strings/utf_string_conversions.h"
 #include "testing/gtest/include/gtest/gtest.h"
 #include "url/gurl.h"
 
 
 namespace url_formatter {
 
 namespace {
 
 using base::WideToUTF16;
 using base::ASCIIToUTF16;
 
 const size_t kNpos = base::string16::npos;
 
-const char* const kLanguages[] = {
-  "",      "en",    "zh-CN",    "ja",    "ko",
-  "he",    "ar",    "ru",       "el",    "fr",
-  "de",    "pt",    "sv",       "th",    "hi",
-  "de,en", "el,en", "zh-TW,en", "ko,ja", "he,ru,en",
-  "zh,ru,en"
-};
-
 struct IDNTestCase {
   const char* const input;
   const wchar_t* unicode_output;
-  const bool unicode_allowed[arraysize(kLanguages)];
+  const bool unicode_allowed;
 };
 
-// TODO(jungshik) This is just a random sample of languages and is far
-// from exhaustive.  We may have to generate all the combinations
-// of languages (powerset of a set of all the languages).
 const IDNTestCase idn_cases[] = {
   // No IDN
-  {"www.google.com", L"www.google.com",
-   {true,  true,  true,  true,  true,
-    true,  true,  true,  true,  true,
-    true,  true,  true,  true,  true,
-    true,  true,  true,  true,  true,
-    true}},
-  {"www.google.com.", L"www.google.com.",
-   {true,  true,  true,  true,  true,
-    true,  true,  true,  true,  true,
-    true,  true,  true,  true,  true,
-    true,  true,  true,  true,  true,
-    true}},
-  {".", L".",
-   {true,  true,  true,  true,  true,
-    true,  true,  true,  true,  true,
-    true,  true,  true,  true,  true,
-    true,  true,  true,  true,  true,
-    true}},
-  {"", L"",
-   {true,  true,  true,  true,  true,
-    true,  true,  true,  true,  true,
-    true,  true,  true,  true,  true,
-    true,  true,  true,  true,  true,
-    true}},
+  {"www.google.com", L"www.google.com", true},
+  {"www.google.com.", L"www.google.com.", true},
+  {".", L".", true},
+  {"", L"", true},
   // IDN
   // Hanzi (Traditional Chinese)
-  {"xn--1lq90ic7f1rc.cn", L"\x5317\x4eac\x5927\x5b78.cn",
-   {true,  false, true,  true,  false,
-    false, false, false, false, false,
-    false, false, false, false, false,
-    false, false, true,  true,  false,
-    true}},
-  // Hanzi ('video' in Simplified Chinese : will pass only in zh-CN,zh)
-  {"xn--cy2a840a.com", L"\x89c6\x9891.com",
-   {true,  false, true,  false,  false,
-    false, false, false, false, false,
-    false, false, false, false, false,
-    false, false, false, false,  false,
-    true}},
+  {"xn--1lq90ic7f1rc.cn", L"\x5317\x4eac\x5927\x5b78.cn", true},
+  // Hanzi ('video' in Simplified Chinese
+  {"xn--cy2a840a.com", L"\x89c6\x9891.com", true},
   // Hanzi + '123'
-  {"www.xn--123-p18d.com", L"www.\x4e00" L"123.com",
-   {true,  false, true,  true,  false,
-    false, false, false, false, false,
-    false, false, false, false, false,
-    false, false, true,  true,  false,
-    true}},
-  // Hanzi + Latin : U+56FD is simplified and is regarded
-  // as not supported in zh-TW.
-  {"www.xn--hello-9n1hm04c.com", L"www.hello\x4e2d\x56fd.com",
-   {false, false, true,  true,  false,
-    false, false, false, false, false,
-    false, false, false, false, false,
-    false, false, false, true,  false,
-    true}},
+  {"www.xn--123-p18d.com", L"www.\x4e00" L"123.com", true},
+  // Hanzi + Latin : U+56FD is simplified
+  {"www.xn--hello-9n1hm04c.com", L"www.hello\x4e2d\x56fd.com", true},
   // Kanji + Kana (Japanese)
-  {"xn--l8jvb1ey91xtjb.jp", L"\x671d\x65e5\x3042\x3055\x3072.jp",
-   {true,  false, false, true,  false,
-    false, false, false, false, false,
-    false, false, false, false, false,
-    false, false, false, true,  false,
-    false}},
+  {"xn--l8jvb1ey91xtjb.jp", L"\x671d\x65e5\x3042\x3055\x3072.jp", true},
   // Katakana including U+30FC
-  {"xn--tckm4i2e.jp", L"\x30b3\x30de\x30fc\x30b9.jp",
-   {true, false, false, true,  false,
-    false, false, false, false, false,
-    false, false, false, false, false,
-    false, false, false, true, false,
-    }},
-  {"xn--3ck7a7g.jp", L"\u30ce\u30f3\u30bd.jp",
-   {true, false, false, true,  false,
-    false, false, false, false, false,
-    false, false, false, false, false,
-    false, false, false, true, false,
-    }},
+  {"xn--tckm4i2e.jp", L"\x30b3\x30de\x30fc\x30b9.jp", true},
+  {"xn--3ck7a7g.jp", L"\u30ce\u30f3\u30bd.jp", true},
   // Katakana + Latin (Japanese)
-  // TODO(jungshik): Change 'false' in the first element to 'true'
-  // after upgrading to ICU 4.2.1 to use new uspoof_* APIs instead
-  // of our IsIDNComponentInSingleScript().
-  {"xn--e-efusa1mzf.jp", L"e\x30b3\x30de\x30fc\x30b9.jp",
-   {false, false, false, true,  false,
-    false, false, false, false, false,
-    false, false, false, false, false,
-    false, false, false, true, false,
-    }},
-  {"xn--3bkxe.jp", L"\x30c8\x309a.jp",
-   {false, false, false, true,  false,
-    false, false, false, false, false,
-    false, false, false, false, false,
-    false, false, false, true, false,
-    }},
+  {"xn--e-efusa1mzf.jp", L"e\x30b3\x30de\x30fc\x30b9.jp", true},
+  {"xn--3bkxe.jp", L"\x30c8\x309a.jp", true},
   // Hangul (Korean)
-  {"www.xn--or3b17p6jjc.kr", L"www.\xc804\xc790\xc815\xbd80.kr",
-   {true,  false, false, false, true,
-    false, false, false, false, false,
-    false, false, false, false, false,
-    false, false, false, true,  false,
-    false}},
+  {"www.xn--or3b17p6jjc.kr", L"www.\xc804\xc790\xc815\xbd80.kr", true},
   // b<u-umlaut>cher (German)
-  {"xn--bcher-kva.de", L"b\x00fc" L"cher.de",
-   {true,  false, false, false, false,
-    false, false, false, false, true,
-    true,  false,  false, false, false,
-    true,  false, false, false, false,
-    false}},
+  {"xn--bcher-kva.de", L"b\x00fc" L"cher.de", true},
   // a with diaeresis
-  {"www.xn--frgbolaget-q5a.se", L"www.f\x00e4rgbolaget.se",
-   {true,  false, false, false, false,
-    false, false, false, false, false,
-    true,  false, true, false, false,
-    true,  false, false, false, false,
-    false}},
+  {"www.xn--frgbolaget-q5a.se", L"www.f\x00e4rgbolaget.se", true},
   // c-cedilla (French)
-  {"www.xn--alliancefranaise-npb.fr", L"www.alliancefran\x00e7" L"aise.fr",
-   {true,  false, false, false, false,
-    false, false, false, false, true,
-    false, true,  false, false, false,
-    false, false, false, false, false,
-    false}},
+  {"www.xn--alliancefranaise-npb.fr",
+   L"www.alliancefran\x00e7" L"aise.fr", true},
   // caf'e with acute accent' (French)
-  {"xn--caf-dma.fr", L"caf\x00e9.fr",
-   {true,  false, false, false, false,
-    false, false, false, false, true,
-    false, true,  true,  false, false,
-    false, false, false, false, false,
-    false}},
+  {"xn--caf-dma.fr", L"caf\x00e9.fr", true},
   // c-cedillla and a with tilde (Portuguese)
-  {"xn--poema-9qae5a.com.br", L"p\x00e3oema\x00e7\x00e3.com.br",
-   {true,  false, false, false, false,
-    false, false, false, false, false,
-    false, true,  false, false, false,
-    false, false, false, false, false,
-    false}},
+  {"xn--poema-9qae5a.com.br", L"p\x00e3oema\x00e7\x00e3.com.br", true},
   // s with caron
-  {"xn--achy-f6a.com", L"\x0161" L"achy.com",
-   {true,  false, false, false, false,
-    false, false, false, false, false,
-    false, false, false, false, false,
-    false, false, false, false, false,
-    false}},
-  // TODO(jungshik) : Add examples with Cyrillic letters
-  // only used in some languages written in Cyrillic.
-  // Eutopia (Greek)
+  {"xn--achy-f6a.com", L"\x0161" L"achy.com", true},
   {"xn--kxae4bafwg.gr", L"\x03bf\x03c5\x03c4\x03bf\x03c0\x03af\x03b1.gr",
-   {true,  false, false, false, false,
-    false, false, false, true,  false,
-    false, false, false, false, false,
-    false, true,  false, false, false,
-    false}},
+   true},
   // Eutopia + 123 (Greek)
   {"xn---123-pldm0haj2bk.gr",
-   L"\x03bf\x03c5\x03c4\x03bf\x03c0\x03af\x03b1-123.gr",
-   {true,  false, false, false, false,
-    false, false, false, true,  false,
-    false, false, false, false, false,
-    false, true,  false, false, false,
-    false}},
+   L"\x03bf\x03c5\x03c4\x03bf\x03c0\x03af\x03b1-123.gr", true},
   // Cyrillic (Russian)
-  {"xn--n1aeec9b.ru", L"\x0442\x043e\x0440\x0442\x044b.ru",
-   {true,  false, false, false, false,
-    false, false, true,  false, false,
-    false, false, false, false, false,
-    false, false, false, false, true,
-    true}},
+  {"xn--n1aeec9b.ru", L"\x0442\x043e\x0440\x0442\x044b.ru", true},
   // Cyrillic + 123 (Russian)
-  {"xn---123-45dmmc5f.ru", L"\x0442\x043e\x0440\x0442\x044b-123.ru",
-   {true,  false, false, false, false,
-    false, false, true,  false, false,
-    false, false, false, false, false,
-    false, false, false, false, true,
-    true}},
+  {"xn---123-45dmmc5f.ru", L"\x0442\x043e\x0440\x0442\x044b-123.ru", true},
+  // 'president' in Russian. Is a wholescript confusable, but allowed.
+  {"xn--d1abbgf6aiiy.xn--p1ai",
+    L"\x043f\x0440\x0435\x0437\x0438\x0434\x0435\x043d\x0442.\x0440\x0444",
+    true},
   // Arabic
-  {"xn--mgba1fmg.ar", L"\x0627\x0641\x0644\x0627\x0645.ar",
-   {true,  false, false, false, false,
-    false, true,  false, false, false,
-    false, false, false, false, false,
-    false, false, false, false, false,
-    false}},
+  {"xn--mgba1fmg.eg", L"\x0627\x0641\x0644\x0627\x0645.eg", true},
   // Hebrew
-  {"xn--4dbib.he", L"\x05d5\x05d0\x05d4.he",
-   {true,  false, false, false, false,
-    true,  false, false, false, false,
-    false, false, false, false, false,
-    false, false, false, false, true,
-    false}},
+  {"xn--4dbib.he", L"\x05d5\x05d0\x05d4.he", true},
+  // Hebrew + Common
+  {"xn---123-ptf2c5c6bt.il", L"\x05e2\x05d1\x05e8\x05d9\x05ea-123.il", true},
   // Thai
   {"xn--12c2cc4ag3b4ccu.th",
-   L"\x0e2a\x0e32\x0e22\x0e01\x0e32\x0e23\x0e1a\x0e34\x0e19.th",
-   {true,  false, false, false, false,
-    false, false, false, false, false,
-    false, false, false, true,  false,
-    false, false, false, false, false,
-    false}},
+   L"\x0e2a\x0e32\x0e22\x0e01\x0e32\x0e23\x0e1a\x0e34\x0e19.th", true},
+  // Thai + Common
+  {"xn---123-9goxcp8c9db2r.th",
+    L"\x0e20\x0e32\x0e29\x0e32\x0e44\x0e17\x0e22-123.th", true},
   // Devangari (Hindi)
-  {"www.xn--l1b6a9e1b7c.in", L"www.\x0905\x0915\x094b\x0932\x093e.in",
-   {true,  false, false, false, false,
-    false, false, false, false, false,
-    false, false, false, false, true,
-    false, false, false, false, false,
-    false}},
-  // Invalid IDN
-  {"xn--hello?world.com", NULL,
-   {false, false, false, false, false,
-    false, false, false, false, false,
-    false, false, false, false, false,
-    false, false, false, false, false,
-    false}},
-  // Unsafe IDNs
+  {"www.xn--l1b6a9e1b7c.in", L"www.\x0905\x0915\x094b\x0932\x093e.in", true},
+  // Devanagari + Common
+  {"xn---123-kbjl2j0bl2k.in",
+    L"\x0939\x093f\x0928\x094d\x0926\x0940-123.in", true},
+
+  // 5 Aspirational scripts
+  // Unifieid Canadian Syllabary
+  {"xn--dfe0tte.ca", L"\x1456\x14c2\x14ef.ca", true},
+  // Tifinagh
+  {"xn--4ljxa2bb4a6bxb.ma",
+    L"\x2d5c\x2d49\x2d3c\x2d49\x2d4f\x2d30\x2d56.ma", true},
+  // Tifinagh with a disallowed character(U+2D6F)
+  {"xn--hmjzaby5d5f.ma", L"\x2d5c\x2d49\x2d3c\x2d6f\x2d49\x2d4f.ma", false},
+  // Yi
+  {"xn--4o7a6e1x64c.cn", L"\xa188\xa320\xa071\xa0b7.cn", true},
+  // Mongolian - 'ordu' (place, camp)
+  {"xn--56ec8bp.cn", L"\x1823\x1837\x1833\x1824.cn", true},
+  // Mongolian with a disallowed character
+  {"xn--95e5de3ds.cn", L"\x1823\x1837\x1804\x1833\x1824.cn", false},
+  // Miao/Pollad
+  {"xn--2u0fpf0a.cn", L"\U00016f04\U00016f62\U00016f59.cn", true},
+
+  // Script mixing tests
+  // The following script combinations are allowed.
+  // MODERATELY_RESTRICTIVE with Latin limited to ASCII-Latin.
+  // ASCII-Latin + Japn (Kana + Han)
+  // ASCII-Latin + Kore (Hangul + Han)
+  // ASCII-Latin + Han + Bopomofo
+  // ASCII-Latin + any allowed script other than Cyrillic, Greek and Cherokee
   // "payp<alpha>l.com"
-  {"www.xn--paypl-g9d.com", L"payp\x03b1l.com",
-   {false, false, false, false, false,
-    false, false, false, false, false,
-    false, false, false, false, false,
-    false, false, false, false, false,
-    false}},
+  {"www.xn--paypl-g9d.com", L"payp\x03b1l.com", false},
   // google.gr with Greek omicron and epsilon
-  {"xn--ggl-6xc1ca.gr", L"g\x03bf\x03bfgl\x03b5.gr",
-   {false, false, false, false, false,
-    false, false, false, false, false,
-    false, false, false, false, false,
-    false, false, false, false, false,
-    false}},
+  {"xn--ggl-6xc1ca.gr", L"g\x03bf\x03bfgl\x03b5.gr", false},
   // google.ru with Cyrillic o
-  {"xn--ggl-tdd6ba.ru", L"g\x043e\x043egl\x0435.ru",
-   {false, false, false, false, false,
-    false, false, false, false, false,
-    false, false, false, false, false,
-    false, false, false, false, false,
-    false}},
+  {"xn--ggl-tdd6ba.ru", L"g\x043e\x043egl\x0435.ru", false},
   // h<e with acute>llo<China in Han>.cn
-  {"xn--hllo-bpa7979ih5m.cn", L"h\x00e9llo\x4e2d\x56fd.cn",
-   {false, false, false, false, false,
-    false, false, false, false, false,
-    false, false, false, false, false,
-    false, false, false, false, false,
-    false}},
+  {"xn--hllo-bpa7979ih5m.cn", L"h\x00e9llo\x4e2d\x56fd.cn", false},
   // <Greek rho><Cyrillic a><Cyrillic u>.ru
-  {"xn--2xa6t2b.ru", L"\x03c1\x0430\x0443.ru",
-   {false, false, false, false, false,
-    false, false, false, false, false,
-    false, false, false, false, false,
-    false, false, false, false, false,
-    false}},
+  {"xn--2xa6t2b.ru", L"\x03c1\x0430\x0443.ru", false},
+  // Hangul + Latin
+  {"xn--han-eb9ll88m.kr", L"\xd55c\xae00han.kr", true},
+  // Hangul + Latin + Han with IDN ccTLD
+  {"xn--han-or0kq92gkm3c.xn--3e0b707e",
+    L"\xd55c\xae00han\x97d3.\xd55c\xad6d", true},
+  // non-ASCII Latin + Hangul
+  {"xn--caf-dma9024xvpg.kr", L"caf\x00e9\xce74\xd398.kr", false},
+  // Hangul + Hiragana
+  {"xn--y9j3b9855e.kr", L"\xd55c\x3072\x3089.kr", false},
+  // <Hiragana>.<Hangul> is allowed because script mixing check is per label.
+  {"xn--y9j3b.xn--3e0b707e", L"\x3072\x3089.\xd55c\xad6d", true},
+  //  Traditional Han + Latin
+  {"xn--hanzi-u57ii69i.tw", L"\x6f22\x5b57hanzi.tw", true},
+  //  Simplified Han + Latin
+  {"xn--hanzi-u57i952h.cn", L"\x6c49\x5b57hanzi.cn", true},
+  // Simplified Han + Traditonal Han
+  {"xn--hanzi-if9kt8n.cn", L"\x6c49\x6f22hanzi.cn", true},
+  //  Han + Hiragana + Katakana + Latin
+  {"xn--kanji-ii4dpizfq59yuykqr4b.jp",
+    L"\x632f\x308a\x4eee\x540d\x30ab\x30bfkanji.jp", true},
+  // Han + Bopomofo
+  {"xn--5ekcde0577e87tc.tw", L"\x6ce8\x97f3\x3105\x3106\x3107\x3108.tw", true},
+  // Han + Latin + Bopomofo
+  {"xn--bopo-ty4cghi8509kk7xd.tw",
+    L"\x6ce8\x97f3" L"bopo\x3105\x3106\x3107\x3108.tw", true},
+  // Latin + Bopomofo
+  {"xn--bopomofo-hj5gkalm.tw", L"bopomofo\x3105\x3106\x3107\x3108.tw", true},
+  // Bopomofo + Katakana
+  {"xn--lcka3d1bztghi.tw",
+    L"\x3105\x3106\x3107\x3108\x30ab\x30bf\x30ab\x30ca.tw", false},
+  //  Bopomofo + Hangul
+  {"xn--5ekcde4543qbec.tw", L"\x3105\x3106\x3107\x3108\xc8fc\xc74c.tw", false},
+  // Devanagari + Latin
+  {"xn--ab-3ofh8fqbj6h.in", L"ab\x0939\x093f\x0928\x094d\x0926\x0940.in", true},
+  // Thai + Latin
+  {"xn--ab-jsi9al4bxdb6n.th",
+    L"ab\x0e20\x0e32\x0e29\x0e32\x0e44\x0e17\x0e22.th", true},
+  // <vitamin in Katakana>b1.com
+  {"xn--b1-xi4a7cvc9f.com", L"\x30d3\x30bf\x30df\x30f3" L"b1.com", true},
+  // Devanagari + Han
+  {"xn--t2bes3ds6749n.com", L"\x0930\x094b\x0932\x0947\x76e7\x0938.com", false},
+  // Devanagari + Bengali
+  {"xn--11b0x.in", L"\x0915\x0995.in", false},
+
+  // Invisibility check
+  // Thai tone mark malek(U+0E48) repeated
+  {"xn--03c0b3ca.th", L"\x0e23\x0e35\x0e48\x0e48.th", false},
+  // Accute accent repeated
+  {"xn--a-xbba.com", L"a\x0301\x0301.com", false},
+  // 'a' with acuted accent + another acute accent
+  {"xn--1ca20i.com", L"\x00e1\x0301.com", false},
+
+  // Mixed script confusable
+  // google with Armenian Small Letter Oh(U+0585)
+  {"xn--gogle-lkg.com", L"g\x0585ogle.com", false},
+  // Hiragana HE(U+3078) mixed with Katakana
+  {"xn--49jxi3as0d0fpc.com",
+    L"\x30e2\x30d2\x30fc\x30c8\x3078\x30d6\x30f3.com", false},
+  // U+30FC + Han
+  {"xn--weka801xo02a.com", L"\x30fc\x52d5\x753b\x30fc.com", false},
+  // Han + U+30FC + Han
+  {"xn--wekz60nb2ay85atj0b.jp", L"\x65e5\x672c\x30fc\x91ce\x7403.jp", false},
+  // Latin + U+30FC + Latin
+  {"xn--abcdef-r64e.jp", L"abc\x30fc" L"def.jp", false},
+  // Latin + U+30FB + Latin
+  {"xn--abcdef-k64e.jp", L"abc\x30fb" L"def.jp", false},
+  // U+30FB + Latin
+  {"xn--abc-os4b.jp", L"\x30fb" L"abc.jp", 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},
+  // Latin + Deva digit + Beng digit
+  {"xn--devabeng-f0qu3f.co.in", L"deva\x0967" L"beng\x09e7.co.in", false},
+  // ASCII digit + Deva digit
+  {"xn--79-v5f.co.in", L"7\x09ea" L"9.co.in", false},
+  //  Deva digit + Beng digit
+  {"xn--e4b0x.co.in", L"\x0967\x09e7.co.in", false},
+  // U+4E00 (CJK Ideograph One) is not a digit
+  {"xn--d12-s18d.cn", L"d12\x4e00.cn", true},
   // One that's really long that will force a buffer realloc
   {"aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa"
-       "aaaaaaa",
+   "aaaaaaa",
    L"aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa"
-       L"aaaaaaaa",
-   {true,  true,  true,  true,  true,
-    true,  true,  true,  true,  true,
-    true,  true,  true,  true,  true,
-    true,  true,  true,  true,  true,
-    true}},
-  // Test cases for characters we blacklisted although allowed in IDN.
-  // Embedded spaces will be turned to %20 in the display.
-  // TODO(jungshik): We need to have more cases. This is a typical
-  // data-driven trap. The following test cases need to be separated
-  // and tested only for a couple of languages.
-  {"xn--osd3820f24c.kr", L"\xac00\xb098\x115f.kr",
-    {false, false, false, false, false,
-     false, false, false, false, false,
-     false, false, false, false, false,
-     false, false, false, false, false,
-     false}},
-  {"www.xn--google-ho0coa.com", L"www.\x2039google\x203a.com",
-    {false, false, false, false, false,
-     false, false, false, false, false,
-     false, false, false, false, false,
-     false, false, false, false, false,
-  }},
-  {"google.xn--comabc-k8d", L"google.com\x0338" L"abc",
-    {false, false, false, false, false,
-     false, false, false, false, false,
-     false, false, false, false, false,
-     false, false, false, false, false,
-  }},
-  {"google.xn--com-oh4ba.evil.jp", L"google.com\x309a\x309a.evil.jp",
-    {false, false, false, false, false,
-     false, false, false, false, false,
-     false, false, false, false, false,
-     false, false, false, false, false,
-  }},
-  {"google.xn--comevil-v04f.jp", L"google.com\x30ce" L"evil.jp",
-    {false, false, false, false, false,
-     false, false, false, false, false,
-     false, false, false, false, false,
-     false, false, false, false, false,
-  }},
+   L"aaaaaaaa",
+   true},
+
+  // Not allowed; characters outside [:Identifier_Status=Allowed:]
+  // Limited Use Scripts: UTS 31 Table 7.
+  // Vai
+  {"xn--sn8a.com", L"\xa50b.com", false},
+  // 'CARD' look-alike in Cherokee
+  {"xn--58db0a9q.com", L"\x13df\x13aa\x13a1\x13a0.com", false},
+  // Scripts excluded from Identifiers: UTS 31 Table 4
+  // Coptic
+  {"xn--5ya.com", L"\x03e7.com", false},
+  // Old Italic
+  {"xn--097cc.com", L"\U00010300\U00010301.com", false},
+
+  // 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
+  {"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
+  {"xn--0naa.com", L"\x0261\x0261.com", false},
+  // Hangul Jamo(U+11xx)
+  {"xn--0pdc3b.com", L"\x1102\x1103\x1110.com", false},
+  // degree sign
+  {"xn--36c-tfa.com", L"36\x00b0" L"c.com", false},
+  // Pound sign
+  {"xn--5free-9ga.com", L"5free\x00a8.com", false},
+  // Hebrew points (U+05B0, U+05B6)
+  {"xn--7cbl2kc2a.com", L"\x05e1\x05b6\x05e7\x05b0\x05e1.com", false},
+  // Danda(U+0964)
+  {"xn--81bp1b6ch8s.com", L"\x0924\x093f\x091c\x0964\x0930\x0940.com", false},
+  // Small letter script G(U+0261)
+  {"xn--oogle-qmc.com", L"\x0261oogle.com", false},
+  // Small Katakana Extension(U+31F1)
+  {"xn--wlk.com", L"\x31f1.com", false},
+  // Heart symbol
+  {"xn--ab-u0x.com", L"ab\x2665.com", false},
+  // Emoji
+  {"xn--vi8hiv.xyz", L"\U0001f355\U0001f4a9.xyz", false},
+  // Registered trade mark
+  {"xn--egistered-fna.com", L"\x00ae" L"egistered.com", false},
+  // Latin Letter Retroflex Click
+  {"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
+  {"xn--1naa7pn51hcbaa.com",
+    L"\x0262\x1d0f\x1d0f\x0262\x029f\x1d07.com", false},
   // Padlock icon spoof.
-  {"xn--google-hj64e", L"\U0001f512google.com",
-    {false, false, false, false, false,
-     false, false, false, false, false,
-     false, false, false, false, false,
-     false, false, false, false, false,
-  }},
-  // Ensure that blacklisting "\xd83d\xdd12" did not inadvertently blacklist
-  // all strings with the surrogate '\xdd12'.
-  {"xn--fk9c.com", L"\U00010912.com",
-    {true,  false, false, false, false,
-     false, false, false, false, false,
-     false, false, false, false, false,
-     false, false, false, false, false,
-  }},
-#if 0
-  // These two cases are special. We need a separate test.
-  // U+3000 and U+3002 are normalized to ASCII space and dot.
-  {"xn-- -kq6ay5z.cn", L"\x4e2d\x56fd\x3000.cn",
-    {false, false, true,  false, false,
-     false, false, false, false, false,
-     false, false, false, false, false,
-     false, false, true,  false, false,
-     true}},
-  {"xn--fiqs8s.cn", L"\x4e2d\x56fd\x3002" L"cn",
-    {false, false, true,  false, false,
-     false, false, false, false, false,
-     false, false, false, false, false,
-     false, false, true,  false, false,
-     true}},
-#endif
+  {"xn--google-hj64e", L"\U0001f512google.com", false},
+
+  // Custom black list
+  // Combining Long Solidus Overlay
+  {"google.xn--comabc-k8d", L"google.com\x0338" L"abc", false},
+  // Hyphenation Point instead of Katakana Middle dot
+  {"xn--svgy16dha.jp", L"\x30a1\x2027\x30a3.jp", false},
+  // Gershayim with other Hebrew characters is allowed.
+  {"xn--5db6bh9b.il", L"\x05e9\x05d1\x05f4\x05e6.il", true},
+  // Hebrew Gershayim with Latin is disallowed.
+  {"xn--ab-yod.com", L"a\x05f4" L"b.com", false},
+  // Hebrew Gershayim with Arabic is disallowed.
+  {"xn--5eb7h.eg", L"\x0628\x05f4.eg", false},
+
+  // Custom dangerous patterns
+  // Two Katakana-Hiragana combining mark in a row
+  {"google.xn--com-oh4ba.evil.jp", L"google.com\x309a\x309a.evil.jp", false},
+  // Katakana Letter No not enclosed by {Han,Hiragana,Katakana}.
+  {"google.xn--comevil-v04f.jp", L"google.com\x30ce" L"evil.jp", false},
+  // TODO(jshin): Review the danger of allowing the following two.
+  // Hiragana 'No' by itself is allowed.
+  {"xn--ldk.jp", L"\x30ce.jp", true},
+  // Hebrew Gershayim used by itself is allowed.
+  {"xn--5eb.il", L"\x05f4.il", true},
+
+  // 4 Deviation characters between IDNA 2003 and IDNA 2008
+  // When entered in Unicode, the first two are mapped to 'ss' and Greek sigma
+  // and the latter two are mapped away. However, the punycode form should
+  // remain in punycode.
+  // U+00DF(sharp-s)
+  {"xn--fu-hia.de", L"fu\x00df.de", false},
+  // U+03C2(final-sigma)
+  {"xn--mxac2c.gr", L"\x03b1\x03b2\x03c2.gr", false},
+  // U+200C(ZWNJ)
+  {"xn--h2by8byc123p.in", L"\x0924\x094d\x200c\x0930\x093f.in", false},
+  // U+200C(ZWJ)
+  {"xn--11b6iy14e.in", L"\x0915\x094d\x200d.in", false},
+
+  // Math Monospace Small A. When entered in Unicode, it's canonicalized to
+  // 'a'. The punycode form should remain in punycode.
+  {"xn--bc-9x80a.xyz", L"\U0001d68a" L"bc.xyz", false},
+  // Math Sans Bold Capital Alpha
+  {"xn--bc-rg90a.xyz", L"\U0001d756" L"bc.xyz", false},
+  // U+3000 is canonicalized to a space(U+0020), but the punycode form
+  // should remain in punycode.
+  {"xn--p6j412gn7f.cn", L"\x4e2d\x56fd\x3000", false},
+  // U+3002 is canonicalized to ASCII fullstop(U+002E), but the punycode form
+  // should remain in punycode.
+  {"xn--r6j012gn7f.cn", L"\x4e2d\x56fd\x3002", false},
+  // Invalid punycode
+  // Has a codepoint beyond U+10FFFF.
+  {"xn--krank-kg706554a", nullptr, false},
+  // '?' in punycode.
+  {"xn--hello?world.com", nullptr, false},
+
+  // Not allowed in UTS46/IDNA 2008
+  // Georgian Capital Letter(U+10BD)
+  {"xn--1nd.com", L"\x10bd.com", false},
+  // 3rd and 4th characters are '-'.
+  {"xn-----8kci4dhsd", L"\x0440\x0443--\x0430\x0432\x0442\x043e", false},
+  // Leading combining mark
+  {"xn--72b.com", L"\x093e.com", false},
+  // BiDi check per IDNA 2008/UTS 46
+  // Cannot starts with AN(Arabic-Indic Number)
+  {"xn--8hbae.eg", L"\x0662\x0660\x0660.eg", false},
+  // Cannot start with a RTL character and ends with a LTR
+  {"xn--x-ymcov.eg", L"\x062c\x0627\x0631x.eg", false},
+  // Can start with a RTL character and ends with EN(European Number)
+  {"xn--2-ymcov.eg", L"\x062c\x0627\x0631" L"2.eg", true},
+  // Can start with a RTL and end with AN
+  {"xn--mgbjq0r.eg", L"\x062c\x0627\x0631\x0662.eg", true},
 };
 
 struct AdjustOffsetCase {
   size_t input_offset;
   size_t output_offset;
 };
 
 struct UrlTestData {
   const char* const description;
   const char* const input;
-  const char* const languages;
   FormatUrlTypes format_types;
   net::UnescapeRule::Type escape_rules;
   const wchar_t* output;  // Use |wchar_t| to handle Unicode constants easily.
   size_t prefix_len;
 };
 
-// A helper for IDN*{Fast,Slow}.
-// Append "::<language list>" to |expected| and |actual| to make it
-// easy to tell which sub-case fails without debugging.
-void AppendLanguagesToOutputs(const char* languages,
-                              base::string16* expected,
-                              base::string16* actual) {
-  base::string16 to_append = ASCIIToUTF16("::") + ASCIIToUTF16(languages);
-  expected->append(to_append);
-  actual->append(to_append);
-}
-
 // A pair of helpers for the FormatUrlWithOffsets() test.
 void VerboseExpect(size_t expected,
                    size_t actual,
                    const std::string& original_url,
                    size_t position,
                    const base::string16& formatted_url) {
   EXPECT_EQ(expected, actual) << "Original URL: " << original_url
       << " (at char " << position << ")\nFormatted URL: " << formatted_url;
 }
 
 void CheckAdjustedOffsets(const std::string& url_string,
-                          const std::string& languages,
                           FormatUrlTypes format_types,
                           net::UnescapeRule::Type unescape_rules,
                           const size_t* output_offsets) {
   GURL url(url_string);
   size_t url_length = url_string.length();
   std::vector<size_t> offsets;
   for (size_t i = 0; i <= url_length + 1; ++i)
     offsets.push_back(i);
   offsets.push_back(500000);  // Something larger than any input length.
   offsets.push_back(std::string::npos);
-  base::string16 formatted_url = FormatUrlWithOffsets(url, languages,
+  base::string16 formatted_url = FormatUrlWithOffsets(url, std::string(),
       format_types, unescape_rules, NULL, NULL, &offsets);
   for (size_t i = 0; i < url_length; ++i)
     VerboseExpect(output_offsets[i], offsets[i], url_string, i, formatted_url);
   VerboseExpect(formatted_url.length(), offsets[url_length], url_string,
                 url_length, formatted_url);
   VerboseExpect(base::string16::npos, offsets[url_length + 1], url_string,
                 500000, formatted_url);
   VerboseExpect(base::string16::npos, offsets[url_length + 2], url_string,
                 std::string::npos, formatted_url);
 }
 
-TEST(UrlFormatterTest, IDNToUnicodeFast) {
+TEST(UrlFormatterTest, IDNToUnicode) {
   for (size_t i = 0; i < arraysize(idn_cases); i++) {
-    for (size_t j = 0; j < arraysize(kLanguages); j++) {
-      // ja || zh-TW,en || ko,ja -> IDNToUnicodeSlow
-      if (j == 3 || j == 17 || j == 18)
-        continue;
-      base::string16 output(IDNToUnicode(idn_cases[i].input, kLanguages[j]));
-      base::string16 expected(idn_cases[i].unicode_allowed[j] ?
-          WideToUTF16(idn_cases[i].unicode_output) :
-          ASCIIToUTF16(idn_cases[i].input));
-      AppendLanguagesToOutputs(kLanguages[j], &expected, &output);
-      EXPECT_EQ(expected, output) << "input: \"" << idn_cases[i].input
-                                  << "\", languages: \"" << kLanguages[j]
-                                  << "\"";
-    }
-  }
-}
-
-TEST(UrlFormatterTest, IDNToUnicodeSlow) {
-  for (size_t i = 0; i < arraysize(idn_cases); i++) {
-    for (size_t j = 0; j < arraysize(kLanguages); j++) {
-      // !(ja || zh-TW,en || ko,ja) -> IDNToUnicodeFast
-      if (!(j == 3 || j == 17 || j == 18))
-        continue;
-      base::string16 output(IDNToUnicode(idn_cases[i].input, kLanguages[j]));
-      base::string16 expected(idn_cases[i].unicode_allowed[j] ?
-          WideToUTF16(idn_cases[i].unicode_output) :
-          ASCIIToUTF16(idn_cases[i].input));
-      AppendLanguagesToOutputs(kLanguages[j], &expected, &output);
-      EXPECT_EQ(expected, output) << "input: \"" << idn_cases[i].input
-                                  << "\", languages: \"" << kLanguages[j]
-                                  << "\"";
-    }
-  }
-}
-
-// ulocdata_getExemplarSet may fail with some locales (currently bn, gu, and
-// te), which was causing a crash (See http://crbug.com/510551).  This may be an
-// icu bug, but regardless, that should not cause a crash.
-TEST(UrlFormatterTest, IDNToUnicodeNeverCrashes) {
-  for (char c1 = 'a'; c1 <= 'z'; c1++) {
-    for (char c2 = 'a'; c2 <= 'z'; c2++) {
-      std::string lang = base::StringPrintf("%c%c", c1, c2);
-      base::string16 output(IDNToUnicode("xn--74h", lang));
-    }
+    base::string16 output(IDNToUnicode(idn_cases[i].input, std::string()));
+    base::string16 expected(idn_cases[i].unicode_allowed
+                                ? WideToUTF16(idn_cases[i].unicode_output)
+                                : ASCIIToUTF16(idn_cases[i].input));
+    EXPECT_EQ(expected, output) << "input # " << i << ": \""
+                                << idn_cases[i].input << "\"";
   }
 }
 
 TEST(UrlFormatterTest, FormatUrl) {
   FormatUrlTypes default_format_type = kFormatUrlOmitUsernamePassword;
   const UrlTestData tests[] = {
-      {"Empty URL", "", "", default_format_type, net::UnescapeRule::NORMAL, L"",
+      {"Empty URL", "", default_format_type, net::UnescapeRule::NORMAL, L"",
        0},
 
-      {"Simple URL", "http://www.google.com/", "", default_format_type,
+      {"Simple URL", "http://www.google.com/",  default_format_type,
        net::UnescapeRule::NORMAL, L"http://www.google.com/", 7},
 
       {"With a port number and a reference",
-       "http://www.google.com:8080/#\xE3\x82\xB0", "", default_format_type,
+       "http://www.google.com:8080/#\xE3\x82\xB0", default_format_type,
        net::UnescapeRule::NORMAL, L"http://www.google.com:8080/#\x30B0", 7},
 
       // -------- IDN tests --------
-      {"Japanese IDN with ja", "http://xn--l8jvb1ey91xtjb.jp", "ja",
+      {"Japanese IDN with ja", "http://xn--l8jvb1ey91xtjb.jp",
        default_format_type, net::UnescapeRule::NORMAL,
        L"http://\x671d\x65e5\x3042\x3055\x3072.jp/", 7},
 
-      {"Japanese IDN with en", "http://xn--l8jvb1ey91xtjb.jp", "en",
-       default_format_type, net::UnescapeRule::NORMAL,
-       L"http://xn--l8jvb1ey91xtjb.jp/", 7},
-
-      {"Japanese IDN without any languages", "http://xn--l8jvb1ey91xtjb.jp", "",
-       default_format_type, net::UnescapeRule::NORMAL,
-       // Single script is safe for empty languages.
-       L"http://\x671d\x65e5\x3042\x3055\x3072.jp/", 7},
-
-      {"mailto: with Japanese IDN", "mailto:foo@xn--l8jvb1ey91xtjb.jp", "ja",
+      {"mailto: with Japanese IDN", "mailto:foo@xn--l8jvb1ey91xtjb.jp",
        default_format_type, net::UnescapeRule::NORMAL,
        // GURL doesn't assume an email address's domain part as a host name.
        L"mailto:foo@xn--l8jvb1ey91xtjb.jp", 7},
 
       {"file: with Japanese IDN", "file://xn--l8jvb1ey91xtjb.jp/config.sys",
-       "ja", default_format_type, net::UnescapeRule::NORMAL,
+       default_format_type, net::UnescapeRule::NORMAL,
        L"file://\x671d\x65e5\x3042\x3055\x3072.jp/config.sys", 7},
 
-      {"ftp: with Japanese IDN", "ftp://xn--l8jvb1ey91xtjb.jp/config.sys", "ja",
+      {"ftp: with Japanese IDN", "ftp://xn--l8jvb1ey91xtjb.jp/config.sys",
        default_format_type, net::UnescapeRule::NORMAL,
        L"ftp://\x671d\x65e5\x3042\x3055\x3072.jp/config.sys", 6},
 
       // -------- omit_username_password flag tests --------
       {"With username and password, omit_username_password=false",
-       "http://user:passwd@example.com/foo", "", kFormatUrlOmitNothing,
+       "http://user:passwd@example.com/foo", kFormatUrlOmitNothing,
        net::UnescapeRule::NORMAL, L"http://user:passwd@example.com/foo", 19},
 
       {"With username and password, omit_username_password=true",
-       "http://user:passwd@example.com/foo", "", default_format_type,
+       "http://user:passwd@example.com/foo", default_format_type,
        net::UnescapeRule::NORMAL, L"http://example.com/foo", 7},
 
-      {"With username and no password", "http://user@example.com/foo", "",
+      {"With username and no password", "http://user@example.com/foo",
        default_format_type, net::UnescapeRule::NORMAL,
        L"http://example.com/foo", 7},
 
-      {"Just '@' without username and password", "http://@example.com/foo", "",
+      {"Just '@' without username and password", "http://@example.com/foo",
        default_format_type, net::UnescapeRule::NORMAL,
        L"http://example.com/foo", 7},
 
       // GURL doesn't think local-part of an email address is username for URL.
-      {"mailto:, omit_username_password=true", "mailto:foo@example.com", "",
+      {"mailto:, omit_username_password=true", "mailto:foo@example.com",
        default_format_type, net::UnescapeRule::NORMAL,
        L"mailto:foo@example.com", 7},
 
       // -------- unescape flag tests --------
       {"Do not unescape",
        "http://%E3%82%B0%E3%83%BC%E3%82%B0%E3%83%AB.jp/"
        "%E3%82%B0%E3%83%BC%E3%82%B0%E3%83%AB"
        "?q=%E3%82%B0%E3%83%BC%E3%82%B0%E3%83%AB",
-       "en", default_format_type, net::UnescapeRule::NONE,
+       default_format_type, net::UnescapeRule::NONE,
        // GURL parses %-encoded hostnames into Punycode.
-       L"http://xn--qcka1pmc.jp/%E3%82%B0%E3%83%BC%E3%82%B0%E3%83%AB"
+       L"http://\x30B0\x30FC\x30B0\x30EB.jp/%E3%82%B0%E3%83%BC%E3%82%B0%E3%83%AB"
        L"?q=%E3%82%B0%E3%83%BC%E3%82%B0%E3%83%AB",
        7},
 
       {"Unescape normally",
        "http://%E3%82%B0%E3%83%BC%E3%82%B0%E3%83%AB.jp/"
        "%E3%82%B0%E3%83%BC%E3%82%B0%E3%83%AB"
        "?q=%E3%82%B0%E3%83%BC%E3%82%B0%E3%83%AB",
-       "en", default_format_type, net::UnescapeRule::NORMAL,
-       L"http://xn--qcka1pmc.jp/\x30B0\x30FC\x30B0\x30EB"
+       default_format_type, net::UnescapeRule::NORMAL,
+       L"http://\x30B0\x30FC\x30B0\x30EB.jp/\x30B0\x30FC\x30B0\x30EB"
        L"?q=\x30B0\x30FC\x30B0\x30EB",
        7},
 
       {"Unescape normally with BiDi control character",
-       "http://example.com/%E2%80%AEabc?q=%E2%80%8Fxy", "en",
+       "http://example.com/%E2%80%AEabc?q=%E2%80%8Fxy",
        default_format_type, net::UnescapeRule::NORMAL,
        L"http://example.com/%E2%80%AEabc?q=%E2%80%8Fxy", 7},
 
       {"Unescape normally including unescape spaces",
-       "http://www.google.com/search?q=Hello%20World", "en",
+       "http://www.google.com/search?q=Hello%20World",
        default_format_type, net::UnescapeRule::SPACES,
        L"http://www.google.com/search?q=Hello World", 7},
 
       /*
       {"unescape=true with some special characters",
-      "http://user%3A:%40passwd@example.com/foo%3Fbar?q=b%26z", "",
+      "http://user%3A:%40passwd@example.com/foo%3Fbar?q=b%26z",
       kFormatUrlOmitNothing, net::UnescapeRule::NORMAL,
       L"http://user%3A:%40passwd@example.com/foo%3Fbar?q=b%26z", 25},
       */
       // Disabled: the resultant URL becomes "...user%253A:%2540passwd...".
 
       // -------- omit http: --------
-      {"omit http with user name", "http://user@example.com/foo", "",
+      {"omit http with user name", "http://user@example.com/foo",
        kFormatUrlOmitAll, net::UnescapeRule::NORMAL, L"example.com/foo", 0},
 
-      {"omit http", "http://www.google.com/", "en", kFormatUrlOmitHTTP,
+      {"omit http", "http://www.google.com/", kFormatUrlOmitHTTP,
        net::UnescapeRule::NORMAL, L"www.google.com/", 0},
 
-      {"omit http with https", "https://www.google.com/", "en",
+      {"omit http with https", "https://www.google.com/",
        kFormatUrlOmitHTTP, net::UnescapeRule::NORMAL,
        L"https://www.google.com/", 8},
 
-      {"omit http starts with ftp.", "http://ftp.google.com/", "en",
+      {"omit http starts with ftp.", "http://ftp.google.com/",
        kFormatUrlOmitHTTP, net::UnescapeRule::NORMAL, L"http://ftp.google.com/",
        7},
 
       // -------- omit trailing slash on bare hostname --------
-      {"omit slash when it's the entire path", "http://www.google.com/", "en",
+      {"omit slash when it's the entire path", "http://www.google.com/",
        kFormatUrlOmitTrailingSlashOnBareHostname, net::UnescapeRule::NORMAL,
        L"http://www.google.com", 7},
-      {"omit slash when there's a ref", "http://www.google.com/#ref", "en",
+      {"omit slash when there's a ref", "http://www.google.com/#ref",
        kFormatUrlOmitTrailingSlashOnBareHostname, net::UnescapeRule::NORMAL,
        L"http://www.google.com/#ref", 7},
-      {"omit slash when there's a query", "http://www.google.com/?", "en",
+      {"omit slash when there's a query", "http://www.google.com/?",
        kFormatUrlOmitTrailingSlashOnBareHostname, net::UnescapeRule::NORMAL,
        L"http://www.google.com/?", 7},
       {"omit slash when it's not the entire path", "http://www.google.com/foo",
-       "en", kFormatUrlOmitTrailingSlashOnBareHostname,
+       kFormatUrlOmitTrailingSlashOnBareHostname,
        net::UnescapeRule::NORMAL, L"http://www.google.com/foo", 7},
-      {"omit slash for nonstandard URLs", "data:/", "en",
+      {"omit slash for nonstandard URLs", "data:/",
        kFormatUrlOmitTrailingSlashOnBareHostname, net::UnescapeRule::NORMAL,
        L"data:/", 5},
-      {"omit slash for file URLs", "file:///", "en",
+      {"omit slash for file URLs", "file:///",
        kFormatUrlOmitTrailingSlashOnBareHostname, net::UnescapeRule::NORMAL,
        L"file:///", 7},
 
       // -------- view-source: --------
-      {"view-source", "view-source:http://xn--qcka1pmc.jp/", "ja",
+      {"view-source", "view-source:http://xn--qcka1pmc.jp/",
        default_format_type, net::UnescapeRule::NORMAL,
        L"view-source:http://\x30B0\x30FC\x30B0\x30EB.jp/", 19},
 
       {"view-source of view-source",
-       "view-source:view-source:http://xn--qcka1pmc.jp/", "ja",
+       "view-source:view-source:http://xn--qcka1pmc.jp/",
        default_format_type, net::UnescapeRule::NORMAL,
        L"view-source:view-source:http://xn--qcka1pmc.jp/", 12},
 
       // view-source should omit http and trailing slash where non-view-source
       // would.
-      {"view-source omit http", "view-source:http://a.b/c", "en",
+      {"view-source omit http", "view-source:http://a.b/c",
        kFormatUrlOmitAll, net::UnescapeRule::NORMAL, L"view-source:a.b/c", 12},
       {"view-source omit http starts with ftp.", "view-source:http://ftp.b/c",
-       "en", kFormatUrlOmitAll, net::UnescapeRule::NORMAL,
+       kFormatUrlOmitAll, net::UnescapeRule::NORMAL,
        L"view-source:http://ftp.b/c", 19},
       {"view-source omit slash when it's the entire path",
-       "view-source:http://a.b/", "en", kFormatUrlOmitAll,
+       "view-source:http://a.b/", kFormatUrlOmitAll,
        net::UnescapeRule::NORMAL, L"view-source:a.b", 12},
   };
 
   for (size_t i = 0; i < arraysize(tests); ++i) {
     size_t prefix_len;
     base::string16 formatted = FormatUrl(
-        GURL(tests[i].input), tests[i].languages, tests[i].format_types,
-        tests[i].escape_rules, NULL, &prefix_len, NULL);
+        GURL(tests[i].input), std::string(), tests[i].format_types,
+        tests[i].escape_rules, NULL,  &prefix_len, NULL);
     EXPECT_EQ(WideToUTF16(tests[i].output), formatted) << tests[i].description;
     EXPECT_EQ(tests[i].prefix_len, prefix_len) << tests[i].description;
   }
 }
 
 TEST(UrlFormatterTest, FormatUrlParsed) {
   // No unescape case.
   url::Parsed parsed;
   base::string16 formatted =
       FormatUrl(GURL("http://\xE3\x82\xB0:\xE3\x83\xBC@xn--qcka1pmc.jp:8080/"
                      "%E3%82%B0/?q=%E3%82%B0#\xE3\x82\xB0"),
-                "ja", kFormatUrlOmitNothing, net::UnescapeRule::NONE, &parsed,
-                NULL, NULL);
+                std::string(), kFormatUrlOmitNothing, net::UnescapeRule::NONE,
+                &parsed, NULL, NULL);
   EXPECT_EQ(WideToUTF16(
       L"http://%E3%82%B0:%E3%83%BC@\x30B0\x30FC\x30B0\x30EB.jp:8080"
       L"/%E3%82%B0/?q=%E3%82%B0#\x30B0"), formatted);
   EXPECT_EQ(WideToUTF16(L"%E3%82%B0"),
       formatted.substr(parsed.username.begin, parsed.username.len));
   EXPECT_EQ(WideToUTF16(L"%E3%83%BC"),
       formatted.substr(parsed.password.begin, parsed.password.len));
   EXPECT_EQ(WideToUTF16(L"\x30B0\x30FC\x30B0\x30EB.jp"),
       formatted.substr(parsed.host.begin, parsed.host.len));
   EXPECT_EQ(WideToUTF16(L"8080"),
@@ skipping 194 matching lines @@
     if (test_char &&
         strchr(kUnescapedCharacters, static_cast<char>(test_char))) {
       EXPECT_NE(url.spec(), GURL(formatted).spec());
     } else {
       EXPECT_EQ(url.spec(), GURL(formatted).spec());
     }
   }
 }
 
 TEST(UrlFormatterTest, FormatUrlWithOffsets) {
-  CheckAdjustedOffsets(std::string(), "en", kFormatUrlOmitNothing,
+  CheckAdjustedOffsets(std::string(),  kFormatUrlOmitNothing,
                        net::UnescapeRule::NORMAL, NULL);
 
   const size_t basic_offsets[] = {
     0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20,
     21, 22, 23, 24, 25
   };
-  CheckAdjustedOffsets("http://www.google.com/foo/", "en",
+  CheckAdjustedOffsets("http://www.google.com/foo/",
                        kFormatUrlOmitNothing, net::UnescapeRule::NORMAL,
                        basic_offsets);
 
   const size_t omit_auth_offsets_1[] = {
     0, 1, 2, 3, 4, 5, 6, 7, kNpos, kNpos, kNpos, kNpos, kNpos, kNpos, kNpos, 7,
     8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21
   };
-  CheckAdjustedOffsets("http://foo:bar@www.google.com/", "en",
+  CheckAdjustedOffsets("http://foo:bar@www.google.com/",
                        kFormatUrlOmitUsernamePassword,
                        net::UnescapeRule::NORMAL, omit_auth_offsets_1);
 
   const size_t omit_auth_offsets_2[] = {
     0, 1, 2, 3, 4, 5, 6, 7, kNpos, kNpos, kNpos, 7, 8, 9, 10, 11, 12, 13, 14,
     15, 16, 17, 18, 19, 20, 21
   };
-  CheckAdjustedOffsets("http://foo@www.google.com/", "en",
+  CheckAdjustedOffsets("http://foo@www.google.com/",
                        kFormatUrlOmitUsernamePassword,
                        net::UnescapeRule::NORMAL, omit_auth_offsets_2);
 
   const size_t dont_omit_auth_offsets[] = {
     0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, kNpos, kNpos, kNpos, kNpos, kNpos, kNpos,
     kNpos, kNpos, 11, 12, kNpos, kNpos, kNpos, kNpos, kNpos, kNpos, kNpos,
     kNpos, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29,
     30, 31
   };
   // Unescape to "http://foo\x30B0:\x30B0bar@www.google.com".
-  CheckAdjustedOffsets("http://foo%E3%82%B0:%E3%82%B0bar@www.google.com/", "en",
+  CheckAdjustedOffsets("http://foo%E3%82%B0:%E3%82%B0bar@www.google.com/",
                        kFormatUrlOmitNothing, net::UnescapeRule::NORMAL,
                        dont_omit_auth_offsets);
 
   const size_t view_source_offsets[] = {
     0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, kNpos,
     kNpos, kNpos, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33
   };
-  CheckAdjustedOffsets("view-source:http://foo@www.google.com/", "en",
+  CheckAdjustedOffsets("view-source:http://foo@www.google.com/",
                        kFormatUrlOmitUsernamePassword,
                        net::UnescapeRule::NORMAL, view_source_offsets);
 
   const size_t idn_hostname_offsets_1[] = {
     0, 1, 2, 3, 4, 5, 6, 7, kNpos, kNpos, kNpos, kNpos, kNpos, kNpos, kNpos,
     kNpos, kNpos, kNpos, kNpos, kNpos, kNpos, kNpos, kNpos, kNpos, kNpos, 12,
     13, 14, 15, 16, 17, 18, 19
   };
   // Convert punycode to "http://\x671d\x65e5\x3042\x3055\x3072.jp/foo/".
-  CheckAdjustedOffsets("http://xn--l8jvb1ey91xtjb.jp/foo/", "ja",
+  CheckAdjustedOffsets("http://xn--l8jvb1ey91xtjb.jp/foo/",
                        kFormatUrlOmitNothing, net::UnescapeRule::NORMAL,
                        idn_hostname_offsets_1);
 
   const size_t idn_hostname_offsets_2[] = {
     0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, kNpos, kNpos, kNpos, kNpos, kNpos,
     kNpos, kNpos, kNpos, kNpos, kNpos, kNpos, 14, 15, kNpos, kNpos, kNpos,
     kNpos, kNpos, kNpos, kNpos, kNpos, kNpos, kNpos, kNpos, kNpos, kNpos, kNpos,
     kNpos, 19, 20, 21, 22, 23, 24
   };
   // Convert punycode to
   // "http://test.\x89c6\x9891.\x5317\x4eac\x5927\x5b78.test/".
   CheckAdjustedOffsets("http://test.xn--cy2a840a.xn--1lq90ic7f1rc.test/",
-                       "zh-CN", kFormatUrlOmitNothing,
+                       kFormatUrlOmitNothing,
                        net::UnescapeRule::NORMAL, idn_hostname_offsets_2);
 
   const size_t unescape_offsets[] = {
     0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20,
     21, 22, 23, 24, 25, kNpos, kNpos, 26, 27, 28, 29, 30, kNpos, kNpos, kNpos,
     kNpos, kNpos, kNpos, kNpos, kNpos, 31, kNpos, kNpos, kNpos, kNpos, kNpos,
     kNpos, kNpos, kNpos, 32, kNpos, kNpos, kNpos, kNpos, kNpos, kNpos, kNpos,
     kNpos, 33, kNpos, kNpos, kNpos, kNpos, kNpos, kNpos, kNpos, kNpos
   };
   // Unescape to "http://www.google.com/foo bar/\x30B0\x30FC\x30B0\x30EB".
   CheckAdjustedOffsets(
       "http://www.google.com/foo%20bar/%E3%82%B0%E3%83%BC%E3%82%B0%E3%83%AB",
-      "en", kFormatUrlOmitNothing, net::UnescapeRule::SPACES, unescape_offsets);
+      kFormatUrlOmitNothing, net::UnescapeRule::SPACES, unescape_offsets);
 
   const size_t ref_offsets[] = {
     0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20,
     21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, kNpos, kNpos, 32, kNpos, kNpos,
     33
   };
   // Unescape to "http://www.google.com/foo.html#\x30B0\x30B0z".
   CheckAdjustedOffsets(
-      "http://www.google.com/foo.html#\xE3\x82\xB0\xE3\x82\xB0z", "en",
+      "http://www.google.com/foo.html#\xE3\x82\xB0\xE3\x82\xB0z",
       kFormatUrlOmitNothing, net::UnescapeRule::NORMAL, ref_offsets);
 
   const size_t omit_http_offsets[] = {
     0, kNpos, kNpos, kNpos, kNpos, kNpos, kNpos, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9,
     10, 11, 12, 13, 14
   };
-  CheckAdjustedOffsets("http://www.google.com/", "en", kFormatUrlOmitHTTP,
+  CheckAdjustedOffsets("http://www.google.com/", kFormatUrlOmitHTTP,
                        net::UnescapeRule::NORMAL, omit_http_offsets);
 
   const size_t omit_http_start_with_ftp_offsets[] = {
     0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21
   };
-  CheckAdjustedOffsets("http://ftp.google.com/", "en", kFormatUrlOmitHTTP,
+  CheckAdjustedOffsets("http://ftp.google.com/", kFormatUrlOmitHTTP,
                        net::UnescapeRule::NORMAL,
                        omit_http_start_with_ftp_offsets);
 
   const size_t omit_all_offsets[] = {
     0, kNpos, kNpos, kNpos, kNpos, kNpos, kNpos, 0, kNpos, kNpos, kNpos, kNpos,
     0, 1, 2, 3, 4, 5, 6, 7
   };
-  CheckAdjustedOffsets("http://user@foo.com/", "en", kFormatUrlOmitAll,
+  CheckAdjustedOffsets("http://user@foo.com/", kFormatUrlOmitAll,
                        net::UnescapeRule::NORMAL, omit_all_offsets);
 }
 
 }  // namespace
 
 }  // namespace url_formatter