IDN Display: Add whole-script-confusable characters for Myanmar

This CL adds a list of Myanmar characters that look like Latin
characters. A domain consisting only of these characters and not
having a .mm ccTLD or other Burmese TLDs will be
converted to punycode, as is done for other whole-script-confusables
such as Cyrillic and Hebrew.

No popular domain is affected by this change.

Bug: 722167
Change-Id: I8d099e716f79ef42ab3205fe590e5e9b9a1db7a4
Reviewed-on: https://chromium-review.googlesource.com/c/chromium/src/+/2005869Reviewed-by: Joe DeBlasio <jdeblasio@chromium.org>
Reviewed-by: Mustafa Emre Acer <meacer@chromium.org>
Commit-Queue: Joe DeBlasio <jdeblasio@chromium.org>
Cr-Commit-Position: refs/heads/master@{#733059}

components/url_formatter/spoof_checks/idn_spoof_checker.cc

@@ -243,6 +243,15 @@ IDNSpoofChecker::IDNSpoofChecker() {
        "[[:Taml:]]", "[டப௦]"},
       {// Telugu
        "[[:Telu:]]", "[౦౧]"},
+      {// Myanmar. Shan digits (႐႑႕႖႗) are already blocked from mixing with
+       // other Myanmar characters. However, they can still be used to form
+       // WSC spoofs, so they are included here (they are encoded because macOS
+       // doesn't display them properly).
+       // U+104A (၊) and U+U+104A(။) are excluded as they are signs and are
+       // blocked.
+       "[[:Mymr:]]",
+       "[ခဂငထပဝ၀၂ၔၜ\u1090\u1091\u1095\u1096\u1097]",
+       {"mm"}},
   };
   for (const WholeScriptConfusableData& data : kWholeScriptConfusables) {
     auto all_letters = std::make_unique<icu::UnicodeSet>(

components/url_formatter/spoof_checks/idn_spoof_checker_unittest.cc

@@ -1219,10 +1219,19 @@ const IDNTestCase kIdnCases[] = {
     {"xn--gpd3ag.com", L"ჽჿხ.com", kUnsafe},
     {"xn--gpd3ag.ge", L"ჽჿხ.ge", kSafe},
     {"xn--gpd3ag.xn--node", L"ჽჿხ.გე", kSafe},
-    // Hebrew.
+    // Hebrew:
     {"xn--7dbh4a.com", L"חסד.com", kUnsafe},
     {"xn--7dbh4a.il", L"חסד.il", kSafe},
     {"xn--9dbq2a.xn--7dbh4a", L"קום.חסד", kSafe},
+    // Myanmar:
+    {"xn--oidbbf41a.com", L"င၀ဂခဂ.com", kUnsafe},
+    {"xn--oidbbf41a.mm", L"င၀ဂခဂ.mm", kSafe},
+    {"xn--oidbbf41a.xn--7idjb0f4ck", L"င၀ဂခဂ.မြန်မာ", kSafe},
+    // Myanmar Shan digits:
+    {"xn--rmdcmef.com", L"႐႑႕႖႗.com", kUnsafe},
+    {"xn--rmdcmef.mm", L"႐႑႕႖႗.mm", kSafe},
+    {"xn--rmdcmef.xn--7idjb0f4ck", L"႐႑႕႖႗.မြန်မာ", kSafe},
+
     // Indic scripts:
     // Bengali:
     {"xn--07baub.com", L"০৭০৭.com", kUnsafe},