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

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

This CL also reorders and regroups some of the recent test cases.

No popular domain is affected by this change.

Bug: 722167
Change-Id: Ib68b3ef68ac55576141b9cb2cd6096d149456227
Reviewed-on: https://chromium-review.googlesource.com/c/chromium/src/+/1990326
Commit-Queue: Mustafa Emre Acer <meacer@chromium.org>
Commit-Queue: Joe DeBlasio <jdeblasio@chromium.org>
Reviewed-by: Joe DeBlasio <jdeblasio@chromium.org>
Reviewed-by: Mustafa Emre Acer <meacer@chromium.org>
Cr-Commit-Position: refs/heads/master@{#732564}

components/url_formatter/spoof_checks/idn_spoof_checker.cc

@@ -193,33 +193,37 @@ IDNSpoofChecker::IDNSpoofChecker() {
   combining_diacritics_exceptions_.freeze();
 
   const WholeScriptConfusableData kWholeScriptConfusables[] = {
+      {// Armenian
+       "[[:Armn:]]",
+       "[ագզէլհյոսւօՙ]",
+       {"am"}},
       {// Cyrillic
        "[[:Cyrl:]]",
        "[аысԁеԍһіюјӏорԗԛѕԝхуъЬҽпгѵѡ]",
        // TLDs containing most of the Cyrillic domains.
        {"bg", "by", "kz", "pyc", "ru", "su", "ua", "uz"}},
-      {// Hebrew
-       "[[:Hebr:]]",
-       "[דוחיןסװײ׳ﬦ]",
-       // TLDs containing most of the Hebrew domains.
-       {"il"}},
       {// Ethiopic (Ge'ez). Variants of these characters such as ሁ and ሡ could
        // arguably be added to this list. However, we are only restricting
        // the more obvious characters to keep the list short and to reduce the
        // probability of false positives.
-       // (Potential set: [ሀሁሃሠሡሰሱሲስበቡቢተቱቲታነከኩኪካኬክዐዑዕዖዘዙዚዛዝዞጠጡጢጣጦፐፒꬁꬂꬅ])
+       // Potential set: [ሀሁሃሠሡሰሱሲስበቡቢተቱቲታነከኩኪካኬክዐዑዕዖዘዙዚዛዝዞጠጡጢጣጦፐፒꬁꬂꬅ]
        "[[:Ethi:]]",
        "[ሀሠሰስበነተከዐዕዘጠፐꬅ]",
        {"er", "et"}},
+      {// Georgian
+       "[[:Geor:]]",
+       "[იოყძხჽჿ]",
+       {"ge"}},
       {// Greek
        "[[:Grek:]]",
        // This ignores variants such as ά, έ, ή, ί.
        "[αικνρυωηοτ]",
        {"gr"}},
-      {// Armenian
-       "[[:Armn:]]",
-       "[ագզէլհյոսւօՙ]",
-       {"am"}},
+      {// Hebrew
+       "[[:Hebr:]]",
+       "[דוחיןסװײ׳ﬦ]",
+       // TLDs containing most of the Hebrew domains.
+       {"il"}},
       // Indic scripts in the recommended set. No ccTLDs are allowlisted.
       {// Bengali
        "[[:Beng:]]", "[০৭]"},

components/url_formatter/spoof_checks/idn_spoof_checker_unittest.cc

@@ -1201,40 +1201,46 @@ const IDNTestCase kIdnCases[] = {
     {"xn--googlecom-g040a.com", L"google讠com.com", kUnsafe},  // (U+8BA0)
     {"xn--googlecom-b85n.com", L"google丁com.com", kUnsafe},   // (U+4E01)
 
-    {"xn--7dbh4a.com", L"חסד.com", kUnsafe},
-    {"xn--7dbh4a.il", L"חסד.il", kSafe},
-
-    // Whole-script-confusable in Ethiopic.
+    // Whole-script-confusables. Cyrillic is sufficiently handled in cases above
+    // so it's not included here.
+    // Armenian:
+    {"xn--mbbkpm.com", L"ոսւօ.com", kUnsafe},
+    {"xn--mbbkpm.am", L"ոսւօ.am", kSafe},
+    {"xn--mbbkpm.xn--y9a3aq", L"ոսւօ.հայ", kSafe},
+    // Ethiopic:
     {"xn--6xd66aa62c.com", L"ሠዐዐፐ.com", kUnsafe},
     {"xn--6xd66aa62c.et", L"ሠዐዐፐ.et", kSafe},
-
-    // Whole-script-confusable in Greek.
+    {"xn--6xd66aa62c.xn--m0d3gwjla96a", L"ሠዐዐፐ.ኢትዮጵያ", kSafe},
+    // Greek:
     {"xn--mxapd.com", L"ικα.com", kUnsafe},
     {"xn--mxapd.gr", L"ικα.gr", kSafe},
     {"xn--mxapd.xn--qxam", L"ικα.ελ", kSafe},
-
-    // Whole-script-confusable in Armenian.
-    {"xn--mbbkpm.com", L"ոսւօ.com", kUnsafe},
-    {"xn--mbbkpm.am", L"ոսւօ.am", kSafe},
-    {"xn--mbbkpm.xn--y9a3aq", L"ոսւօ.հայ", kSafe},
-
-    // Whole-script-confusable in Bengali:
+    // Georgian:
+    {"xn--gpd3ag.com", L"ჽჿხ.com", kUnsafe},
+    {"xn--gpd3ag.ge", L"ჽჿხ.ge", kSafe},
+    {"xn--gpd3ag.xn--node", L"ჽჿხ.გე", kSafe},
+    // Hebrew.
+    {"xn--7dbh4a.com", L"חסד.com", kUnsafe},
+    {"xn--7dbh4a.il", L"חסד.il", kSafe},
+    {"xn--9dbq2a.xn--7dbh4a", L"קום.חסד", kSafe},
+    // Indic scripts:
+    // Bengali:
     {"xn--07baub.com", L"০৭০৭.com", kUnsafe},
-    // Whole-script-confusable in Devanagari:
+    // Devanagari:
     {"xn--62ba6j.com", L"ऽ०ऽ.com", kUnsafe},
-    // Whole-script-confusable in Gujarati:
+    // Gujarati:
     {"xn--becd.com", L"ડટ.com", kUnsafe},
-    // Whole-script-confusable in Gurmukhi:
+    // Gurmukhi:
     {"xn--occacb.com", L"੦੧੦੧.com", kUnsafe},
-    // Whole-script-confusable in Kannada:
+    // Kannada:
     {"xn--stca6jf.com", L"ಽ೦ಽ೧.com", kUnsafe},
-    // Whole-script-confusable in Malayalam:
+    // Malayalam:
     {"xn--lwccv.com", L"ടഠധ.com", kUnsafe},
-    // Whole-script-confusable in Oriya:
+    // Oriya:
     {"xn--zhca6ub.com", L"୮ଠ୮ଠ.com", kUnsafe},
-    // Whole-script-confusable in Tamil:
+    // Tamil:
     {"xn--mlca6ab.com", L"டபடப.com", kUnsafe},
-    // Whole-script-confusable in Telugu:
+    // Telugu:
     {"xn--brcaabbb.com", L"౧౦౧౦౧౦.com", kUnsafe},
 
     // IDN domain matching an IDN top-domain (fóó.com)