Add more to confusables list

U+04FB (ӻ) to f
U+050F (ԏ) to t
U+050B (ԋ) and U+0527 (ԧ) to h
U+0437(з) and U+04E1(ӡ) to 3

Add tests for the above entries and tests for ASCII-digit spoofing.

Bug: 816769,820068
Test: components_unittests --gtest_filter=*IDN*
Change-Id: I6cd0a7e97cd0ec2df522ce30f632acfd7b78eee2
Reviewed-on: https://chromium-review.googlesource.com/962875Reviewed-by: Peter Kasting <pkasting@chromium.org>
Commit-Queue: Peter Kasting <pkasting@chromium.org>
Cr-Commit-Position: refs/heads/master@{#543600}

components/url_formatter/idn_spoof_checker.cc

@@ -155,17 +155,17 @@ IDNSpoofChecker::IDNSpoofChecker() {
   // Supplement the Unicode confusable list by the following mapping.
   //   - {U+00FE (þ), U+03FC (ϼ), U+048F (ҏ)} => p
   //   - {U+0127 (ħ), U+043D (н), U+045B (ћ), U+04A3 (ң), U+04A5 (ҥ),
-  //      U+04C8 (ӈ), U+04CA (ӊ), U+0527 (ԧ), U+0529 (ԩ)} => h
+  //      U+04C8 (ӈ), U+04CA (ӊ), U+050B (ԋ), U+0527 (ԧ), U+0529 (ԩ)} => h
   //   - {U+0138 (ĸ), U+03BA (κ), U+043A (к), U+049B (қ), U+049D (ҝ),
   //      U+049F (ҟ), U+04A1(ҡ), U+04C4 (ӄ), U+051F (ԟ)} => k
   //   - {U+014B (ŋ), U+043F (п)} => n
-  //   - {U+0167 (ŧ), U+0442 (т), U+04AD (ҭ)} => t
+  //   - {U+0167 (ŧ), U+0442 (т), U+04AD (ҭ), U+050F (ԏ)} => t
   //   - {U+0185 (ƅ), U+044C (ь), U+048D (ҍ), U+0432 (в)} => b
   //   - {U+03C9 (ω), U+0448 (ш), U+0449 (щ), U+0E1F (ฟ)} => w
   //   - {U+043C (м), U+04CE (ӎ)} => m
   //   - {U+0454 (є), U+04BD (ҽ), U+04BF (ҿ), U+1054 (ၔ)} => e
   //   - U+0491 (ґ) => r
-  //   - U+0493 (ғ) => f
+  //   - {U+0493 (ғ), U+04FB (ӻ)} => f
   //   - {U+04AB (ҫ), U+1004 (င)} => c
   //   - U+04B1 (ұ) => y
   //   - U+03C7 (χ), U+04B3 (ҳ), U+04FD (ӽ), U+04FF (ӿ) => x
@@ -174,19 +174,21 @@ IDNSpoofChecker::IDNSpoofChecker() {
   //   - {U+050D (ԍ), U+100c (ဌ)} => g
   //   - {U+0D1F (ട), U+0E23 (ร)} => s
   //   - U+1042 (၂) => j
+  //   - {U+0437 (з), U+04E1 (ӡ)} => 3
   extra_confusable_mapper_.reset(icu::Transliterator::createFromRules(
       UNICODE_STRING_SIMPLE("ExtraConf"),
-      icu::UnicodeString::fromUTF8("[þϼҏ] > p; [ħнћңҥӈӊԧԩ] > h;"
-                                   "[ĸκкқҝҟҡӄԟ] > k; [ŋп] > n; [ŧтҭ] > t;"
+      icu::UnicodeString::fromUTF8("[þϼҏ] > p; [ħнћңҥӈӊԋԧԩ] > h;"
+                                   "[ĸκкқҝҟҡӄԟ] > k; [ŋп] > n; [ŧтҭԏ] > t;"
                                    "[ƅьҍв] > b;  [ωшщฟ] > w; [мӎ] > m;"
-                                   "[єҽҿၔ] > e; ґ > r; ғ > f; [ҫင] > c;"
+                                   "[єҽҿၔ] > e; ґ > r; [ғӻ] > f; [ҫင] > c;"
                                    "ұ > y; [χҳӽӿ] > x;"
 #if defined(OS_WIN)
                                    "ӏ > i;"
 #else
                                    "ӏ > l;"
 #endif
-                                   "ԃ  > d; [ԍဌ] > g; [ടร] > s; ၂ > j"),
+                                   "ԃ  > d; [ԍဌ] > g; [ടร] > s; ၂ > j;"
+                                   "[зӡ] > 3"),
       UTRANS_FORWARD, parse_error, status));
   DCHECK(U_SUCCESS(status))
       << "Spoofchecker initalization failed due to an error: "

components/url_formatter/top_domains/test_domains.list

@@ -14,3 +14,4 @@ ldg.com
 idg.com
 cegjo.com
 wsws.com
+1234567890.com

components/url_formatter/top_domains/test_skeletons.gperf

@@ -24,4 +24,5 @@ ldg.corn, 1
 idg.corn, 1
 cegjo.corn, 1
 wsws.corn, 1
+l23456789O.corn, 1
 %%

components/url_formatter/url_formatter_unittest.cc

@@ -423,6 +423,12 @@ const IDNTestCase idn_cases[] = {
     {"xn--l1acpzs.com", L"\x0449\x043c\x043d\x0442\x044c.com", false},
     // шмнтв.com
     {"xn--b1atdu1a.com", L"\x0448\x043c\x043d\x0442\x0432.com", false},
+    // шмԋтв.com
+    {"xn--b1atsw09g.com", L"\x0448\x043c\x050b\x0442\x0432.com", false},
+    // шмԧтв.com
+    {"xn--b1atsw03i.com", L"\x0448\x043c\x0527\x0442\x0432.com", false},
+    // шмԋԏв.com
+    {"xn--b1at9a12dua.com", L"\x0448\x043c\x050b\x050f\x0432.com", false},
     // ഠട345.com
     {"xn--345-jtke.com",
      L"\x0d20\x0d1f"
@@ -490,6 +496,8 @@ const IDNTestCase idn_cases[] = {
     {"xn--o1at1tsi.com", L"\x0449\x04ce\x043f\x0491.com", false},
     // ґғ.com
     {"xn--03ae.com", L"\x0491\x0493.com", false},
+    // ґӻ.com
+    {"xn--03a6s.com", L"\x0491\x04fb.com", false},
     // ҫұҳҽ.com
     {"xn--r4amg4b.com", L"\x04ab\x04b1\x04b3\x04bd.com", false},
     // ҫұӽҽ.com
@@ -503,6 +511,25 @@ const IDNTestCase idn_cases[] = {
     // ӏԃԍ.com
     {"xn--s5a8h4a.com", L"\x04cf\x0503\x050d.com", false},
 
+    // ꓲ2345б7890.com
+    {"xn--23457890-e7g93622b.com", L"\xa4f2" L"2345\x0431" L"7890.com", false},
+    // 1ᒿ345б7890.com
+    {"xn--13457890-e7g0943b.com", L"1\x14bf" L"345\x0431" L"7890.com", false},
+    // 12з4567890.com
+    {"xn--124567890-10h.com", L"12\x0437" L"4567890.com", false},
+    // 12ӡ4567890.com
+    {"xn--124567890-mfj.com", L"12\x04e1" L"4567890.com", false},
+    // 123Ꮞ567890.com
+    {"xn--123567890-dm4b.com", L"123\x13ce" L"567890.com", false},
+    // 12345б7890.com
+    {"xn--123457890-fzh.com", L"12345\x0431" L"7890.com", false},
+    // 1234567ȣ90.com
+    {"xn--123456790-6od.com", L"1234567\x0223" L"90.com", false},
+    // 12345678୨0.com
+    {"xn--123456780-71w.com", L"12345678\x0b68" L"0.com", false},
+    // 123456789ꓳ.com
+    {"xn--123456789-tx75a.com", L"123456789\xa4f3.com", false},
+
     // ငၔဌ၂ဝ.com (entirely made of Myanmar characters)
     {"xn--ridq5c9hnd.com", L"\x1004\x1054\x100c" L"\x1042\x101d.com", false},