From 76d4dfbb04ceca3d37dc983771f1236e48de3d7d Mon Sep 17 00:00:00 2001 From: Ben McIlwain Date: Mon, 24 Nov 2025 16:26:05 -0500 Subject: [PATCH] Add "augmented_latin.txt" IDN table in existing txt table format (#2884) This contains the same codepoints from the core/src/main/java/google/registry/idn/Latin-IDN.xml file, just in the old .txt IDN format that Nomulus actually ingests. --- .../tldconfig/idn/augmented_latin.txt | 177 ++++++++++++++++++ 1 file changed, 177 insertions(+) create mode 100644 core/src/main/java/google/registry/tldconfig/idn/augmented_latin.txt diff --git a/core/src/main/java/google/registry/tldconfig/idn/augmented_latin.txt b/core/src/main/java/google/registry/tldconfig/idn/augmented_latin.txt new file mode 100644 index 000000000..187f2a914 --- /dev/null +++ b/core/src/main/java/google/registry/tldconfig/idn/augmented_latin.txt @@ -0,0 +1,177 @@ +# URL: https://www.iana.org/domains/idn-tables/tables/google_latn_1.0.txt +# Policy: https://www.registry.google/about/policies/domainabuse/ +U+002D # HYPHEN-MINUS +U+0030 # DIGIT ZERO +U+0031 # DIGIT ONE +U+0032 # DIGIT TWO +U+0033 # DIGIT THREE +U+0034 # DIGIT FOUR +U+0035 # DIGIT FIVE +U+0036 # DIGIT SIX +U+0037 # DIGIT SEVEN +U+0038 # DIGIT EIGHT +U+0039 # DIGIT NINE +U+0061 # LATIN SMALL LETTER A +U+0062 # LATIN SMALL LETTER B +U+0063 # LATIN SMALL LETTER C +U+0064 # LATIN SMALL LETTER D +U+0065 # LATIN SMALL LETTER E +U+0066 # LATIN SMALL LETTER F +U+0067 # LATIN SMALL LETTER G +U+0068 # LATIN SMALL LETTER H +U+0069 # LATIN SMALL LETTER I +U+006A # LATIN SMALL LETTER J +U+006B # LATIN SMALL LETTER K +U+006C # LATIN SMALL LETTER L +U+006D # LATIN SMALL LETTER M +U+006E # LATIN SMALL LETTER N +U+006F # LATIN SMALL LETTER O +U+0070 # LATIN SMALL LETTER P +U+0071 # LATIN SMALL LETTER Q +U+0072 # LATIN SMALL LETTER R +U+0073 # LATIN SMALL LETTER S +U+0074 # LATIN SMALL LETTER T +U+0075 # LATIN SMALL LETTER U +U+0076 # LATIN SMALL LETTER V +U+0077 # LATIN SMALL LETTER W +U+0078 # LATIN SMALL LETTER X +U+0079 # LATIN SMALL LETTER Y +U+007A # LATIN SMALL LETTER Z +U+00E0 # LATIN SMALL LETTER A WITH GRAVE +U+00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX +U+00E3 # LATIN SMALL LETTER A WITH TILDE +U+00E4 # LATIN SMALL LETTER A WITH DIAERESIS +U+00E5 # LATIN SMALL LETTER A WITH RING ABOVE +U+00E6 # LATIN SMALL LETTER AE +U+00E7 # LATIN SMALL LETTER C WITH CEDILLA +U+00E8 # LATIN SMALL LETTER E WITH GRAVE +U+00E9 # LATIN SMALL LETTER E WITH ACUTE +U+00EA # LATIN SMALL LETTER E WITH CIRCUMFLEX +U+00EB # LATIN SMALL LETTER E WITH DIAERESIS +U+00EC # LATIN SMALL LETTER I WITH GRAVE +U+00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX +U+00F0 # LATIN SMALL LETTER ETH +U+00F2 # LATIN SMALL LETTER O WITH GRAVE +U+00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX +U+00F5 # LATIN SMALL LETTER O WITH TILDE +U+00F6 # LATIN SMALL LETTER O WITH DIAERESIS +U+00F8 # LATIN SMALL LETTER O WITH STROKE +U+00F9 # LATIN SMALL LETTER U WITH GRAVE +U+00FB # LATIN SMALL LETTER U WITH CIRCUMFLEX +U+00FD # LATIN SMALL LETTER Y WITH ACUTE +U+00FE # LATIN SMALL LETTER THORN +U+00FF # LATIN SMALL LETTER Y WITH DIAERESIS +U+0103 # LATIN SMALL LETTER A WITH BREVE +U+0105 # LATIN SMALL LETTER A WITH OGONEK +U+0107 # LATIN SMALL LETTER C WITH ACUTE +U+0109 # LATIN SMALL LETTER C WITH CIRCUMFLEX +U+010D # LATIN SMALL LETTER C WITH CARON +U+010F # LATIN SMALL LETTER D WITH CARON +U+0111 # LATIN SMALL LETTER D WITH STROKE +U+0113 # LATIN SMALL LETTER E WITH MACRON +U+0117 # LATIN SMALL LETTER E WITH DOT ABOVE +U+0119 # LATIN SMALL LETTER E WITH OGONEK +U+011B # LATIN SMALL LETTER E WITH CARON +U+011D # LATIN SMALL LETTER G WITH CIRCUMFLEX +U+011F # LATIN SMALL LETTER G WITH BREVE +U+0123 # LATIN SMALL LETTER G WITH CEDILLA +U+0125 # LATIN SMALL LETTER H WITH CIRCUMFLEX +U+0127 # LATIN SMALL LETTER H WITH STROKE +U+012B # LATIN SMALL LETTER I WITH MACRON +U+012F # LATIN SMALL LETTER I WITH OGONEK +U+0135 # LATIN SMALL LETTER J WITH CIRCUMFLEX +U+0137 # LATIN SMALL LETTER K WITH CEDILLA +U+013A # LATIN SMALL LETTER L WITH ACUTE +U+013C # LATIN SMALL LETTER L WITH CEDILLA +U+013E # LATIN SMALL LETTER L WITH CARON +U+0142 # LATIN SMALL LETTER L WITH STROKE +U+0146 # LATIN SMALL LETTER N WITH CEDILLA +U+0148 # LATIN SMALL LETTER N WITH CARON +U+0151 # LATIN SMALL LETTER O WITH DOUBLE ACUTE +U+0153 # LATIN SMALL LIGATURE OE +U+0155 # LATIN SMALL LETTER R WITH ACUTE +U+0159 # LATIN SMALL LETTER R WITH CARON +U+015B # LATIN SMALL LETTER S WITH ACUTE +U+015D # LATIN SMALL LETTER S WITH CIRCUMFLEX +U+015F # LATIN SMALL LETTER S WITH CEDILLA +U+0161 # LATIN SMALL LETTER S WITH CARON +U+0165 # LATIN SMALL LETTER T WITH CARON +U+0167 # LATIN SMALL LETTER T WITH STROKE +U+016B # LATIN SMALL LETTER U WITH MACRON +U+016D # LATIN SMALL LETTER U WITH BREVE +U+016F # LATIN SMALL LETTER U WITH RING ABOVE +U+0171 # LATIN SMALL LETTER U WITH DOUBLE ACUTE +U+0173 # LATIN SMALL LETTER U WITH OGONEK +U+0175 # LATIN SMALL LETTER W WITH CIRCUMFLEX +U+0177 # LATIN SMALL LETTER Y WITH CIRCUMFLEX +U+017A # LATIN SMALL LETTER Z WITH ACUTE +U+017E # LATIN SMALL LETTER Z WITH CARON +U+0188 # LATIN SMALL LETTER C WITH HOOK +U+0199 # LATIN SMALL LETTER K WITH HOOK +U+01A1 # LATIN SMALL LETTER O WITH HORN +U+01A5 # LATIN SMALL LETTER P WITH HOOK +U+01AD # LATIN SMALL LETTER T WITH HOOK +U+01B0 # LATIN SMALL LETTER U WITH HORN +U+01B4 # LATIN SMALL LETTER Y WITH HOOK +U+01E9 # LATIN SMALL LETTER K WITH CARON +U+01EF # LATIN SMALL LETTER EZH WITH CARON +U+0219 # LATIN SMALL LETTER S WITH COMMA BELOW +U+021B # LATIN SMALL LETTER T WITH COMMA BELOW +U+024D # LATIN SMALL LETTER R WITH STROKE +U+0253 # LATIN SMALL LETTER B WITH HOOK +U+0254 # LATIN SMALL LETTER OPEN O +U+0256 # LATIN SMALL LETTER D WITH TAIL +U+0257 # LATIN SMALL LETTER D WITH HOOK +U+0259 # LATIN SMALL LETTER SCHWA +U+025B # LATIN SMALL LETTER OPEN E +U+0260 # LATIN SMALL LETTER G WITH HOOK +U+0268 # LATIN SMALL LETTER I WITH STROKE +U+0272 # LATIN SMALL LETTER N WITH LEFT HOOK +U+0289 # LATIN SMALL LETTER U BAR +U+0292 # LATIN SMALL LETTER EZH +U+1E13 # LATIN SMALL LETTER D WITH CIRCUMFLEX BELOW +U+1E3D # LATIN SMALL LETTER L WITH CIRCUMFLEX BELOW +U+1E49 # LATIN SMALL LETTER N WITH LINE BELOW +U+1E4B # LATIN SMALL LETTER N WITH CIRCUMFLEX BELOW +U+1E63 # LATIN SMALL LETTER S WITH DOT BELOW +U+1E6D # LATIN SMALL LETTER T WITH DOT BELOW +U+1E71 # LATIN SMALL LETTER T WITH CIRCUMFLEX BELOW +U+1E8D # LATIN SMALL LETTER X WITH DIAERESIS +U+1EA1 # LATIN SMALL LETTER A WITH DOT BELOW +U+1EA5 # LATIN SMALL LETTER A WITH CIRCUMFLEX AND ACUTE +U+1EA7 # LATIN SMALL LETTER A WITH CIRCUMFLEX AND GRAVE +U+1EA9 # LATIN SMALL LETTER A WITH CIRCUMFLEX AND HOOK ABOVE +U+1EAB # LATIN SMALL LETTER A WITH CIRCUMFLEX AND TILDE +U+1EAD # LATIN SMALL LETTER A WITH CIRCUMFLEX AND DOT BELOW +U+1EAF # LATIN SMALL LETTER A WITH BREVE AND ACUTE +U+1EB1 # LATIN SMALL LETTER A WITH BREVE AND GRAVE +U+1EB3 # LATIN SMALL LETTER A WITH BREVE AND HOOK ABOVE +U+1EB5 # LATIN SMALL LETTER A WITH BREVE AND TILDE +U+1EB7 # LATIN SMALL LETTER A WITH BREVE AND DOT BELOW +U+1EB9 # LATIN SMALL LETTER E WITH DOT BELOW +U+1EBB # LATIN SMALL LETTER E WITH HOOK ABOVE +U+1EBF # LATIN SMALL LETTER E WITH CIRCUMFLEX AND ACUTE +U+1EC1 # LATIN SMALL LETTER E WITH CIRCUMFLEX AND GRAVE +U+1EC3 # LATIN SMALL LETTER E WITH CIRCUMFLEX AND HOOK ABOVE +U+1EC5 # LATIN SMALL LETTER E WITH CIRCUMFLEX AND TILDE +U+1EC7 # LATIN SMALL LETTER E WITH CIRCUMFLEX AND DOT BELOW +U+1ECB # LATIN SMALL LETTER I WITH DOT BELOW +U+1ECD # LATIN SMALL LETTER O WITH DOT BELOW +U+1ED1 # LATIN SMALL LETTER O WITH CIRCUMFLEX AND ACUTE +U+1ED3 # LATIN SMALL LETTER O WITH CIRCUMFLEX AND GRAVE +U+1ED5 # LATIN SMALL LETTER O WITH CIRCUMFLEX AND HOOK ABOVE +U+1ED7 # LATIN SMALL LETTER O WITH CIRCUMFLEX AND TILDE +U+1ED9 # LATIN SMALL LETTER O WITH CIRCUMFLEX AND DOT BELOW +U+1EDB # LATIN SMALL LETTER O WITH HORN AND ACUTE +U+1EDD # LATIN SMALL LETTER O WITH HORN AND GRAVE +U+1EDF # LATIN SMALL LETTER O WITH HORN AND HOOK ABOVE +U+1EE1 # LATIN SMALL LETTER O WITH HORN AND TILDE +U+1EE3 # LATIN SMALL LETTER O WITH HORN AND DOT BELOW +U+1EE5 # LATIN SMALL LETTER U WITH DOT BELOW +U+1EE9 # LATIN SMALL LETTER U WITH HORN AND ACUTE +U+1EEB # LATIN SMALL LETTER U WITH HORN AND GRAVE +U+1EED # LATIN SMALL LETTER U WITH HORN AND HOOK ABOVE +U+1EEF # LATIN SMALL LETTER U WITH HORN AND TILDE +U+1EF1 # LATIN SMALL LETTER U WITH HORN AND DOT BELOW +U+1EF5 # LATIN SMALL LETTER Y WITH DOT BELOW +U+1EF9 # LATIN SMALL LETTER Y WITH TILDE