Add a new Unconfusable Latin table (#1981)

This new table has just been approved by ICANN. It is the same as our existing
Extended Latin table, except with the removal of some lesser-used characters
with diacritic marks that are confusable variants.

The filenames for the IDN tables are made explicit to improve code readability.

And this reverses the removal of G with stroke from the existing Extended Latin
table (see PR #1938), so that that table continues to accurately reflect the
state of our previously launched TLDs.

This is the full list of removed characters:

U+00E1                         # LATIN SMALL LETTER A WITH ACUTE
U+0101                         # LATIN SMALL LETTER A WITH MACRON
U+01CE                         # LATIN SMALL LETTER A WITH CARON
U+010B                         # LATIN SMALL LETTER C WITH DOT ABOVE
U+01E7                         # LATIN SMALL LETTER G WITH CARON
U+0123                         # LATIN SMALL LETTER G WITH CEDILLA
U+01E5                         # LATIN SMALL LETTER G WITH STROKE
U+0131                         # LATIN SMALL LETTER DOTLESS I
U+00ED                         # LATIN SMALL LETTER I WITH ACUTE
U+00EF                         # LATIN SMALL LETTER I WITH DIAERESIS
U+01D0                         # LATIN SMALL LETTER I WITH CARON
U+0144                         # LATIN SMALL LETTER N WITH ACUTE
U+014B                         # LATIN SMALL LETTER ENG
U+00F3                         # LATIN SMALL LETTER O WITH ACUTE
U+014D                         # LATIN SMALL LETTER O WITH MACRON
U+01D2                         # LATIN SMALL LETTER O WITH CARON
U+0157                         # LATIN SMALL LETTER R WITH CEDILLA
U+0163                         # LATIN SMALL LETTER T WITH CEDILLA
U+00FA                         # LATIN SMALL LETTER U WITH ACUTE
U+00FC                         # LATIN SMALL LETTER U WITH DIAERESIS
U+01D4                         # LATIN SMALL LETTER U WITH CARON
U+1E83                         # LATIN SMALL LETTER W WITH ACUTE
U+1E81                         # LATIN SMALL LETTER W WITH GRAVE
U+1E85                         # LATIN SMALL LETTER W WITH DIAERESIS
U+1EF3                         # LATIN SMALL LETTER Y WITH GRAVE
U+017C                         # LATIN SMALL LETTER Z WITH DOT ABOVE
This commit is contained in:
Ben McIlwain
2023-04-06 15:49:36 -04:00
committed by GitHub
parent 11c60b8c8f
commit 20c673840e
10 changed files with 178 additions and 12 deletions
@@ -21,6 +21,11 @@
<rdeIDN:urlPolicy>https://www.registry.google/about/policies/domainabuse/</rdeIDN:urlPolicy>
</rdeIDN:idnTableRef>
<rdeIDN:idnTableRef id="unconfusable_latin">
<rdeIDN:url>https://www.iana.org/domains/idn-tables/tables/google_latn_2.0.txt</rdeIDN:url>
<rdeIDN:urlPolicy>https://www.registry.google/about/policies/domainabuse/</rdeIDN:urlPolicy>
</rdeIDN:idnTableRef>
<rdeIDN:idnTableRef id="ja">
<rdeIDN:url>https://www.iana.org/domains/idn-tables/tables/google_ja_1.0.txt</rdeIDN:url>
<rdeIDN:urlPolicy>https://www.registry.google/about/policies/domainabuse/</rdeIDN:urlPolicy>
@@ -32,7 +37,7 @@
<rdeHeader:count uri="urn:ietf:params:xml:ns:rdeDomain-1.0">1</rdeHeader:count>
<rdeHeader:count uri="urn:ietf:params:xml:ns:rdeHost-1.0">1</rdeHeader:count>
<rdeHeader:count uri="urn:ietf:params:xml:ns:rdeRegistrar-1.0">1</rdeHeader:count>
<rdeHeader:count uri="urn:ietf:params:xml:ns:rdeIDN-1.0">2</rdeHeader:count>
<rdeHeader:count uri="urn:ietf:params:xml:ns:rdeIDN-1.0">3</rdeHeader:count>
</rdeHeader:header>
</rde:contents>
@@ -14,6 +14,6 @@
<rdeHeader:count uri="urn:ietf:params:xml:ns:rdeDomain-1.0">1</rdeHeader:count>
<rdeHeader:count uri="urn:ietf:params:xml:ns:rdeHost-1.0">1</rdeHeader:count>
<rdeHeader:count uri="urn:ietf:params:xml:ns:rdeRegistrar-1.0">1</rdeHeader:count>
<rdeHeader:count uri="urn:ietf:params:xml:ns:rdeIDN-1.0">2</rdeHeader:count>
<rdeHeader:count uri="urn:ietf:params:xml:ns:rdeIDN-1.0">3</rdeHeader:count>
</rdeHeader:header>
</rdeReport:report>
@@ -245,6 +245,11 @@
<rdeIDN:urlPolicy>https://www.registry.google/about/policies/domainabuse/</rdeIDN:urlPolicy>
</rdeIDN:idnTableRef>
<rdeIDN:idnTableRef id="unconfusable_latin">
<rdeIDN:url>https://www.iana.org/domains/idn-tables/tables/google_latn_2.0.txt</rdeIDN:url>
<rdeIDN:urlPolicy>https://www.registry.google/about/policies/domainabuse/</rdeIDN:urlPolicy>
</rdeIDN:idnTableRef>
<rdeIDN:idnTableRef id="ja">
<rdeIDN:url>https://www.iana.org/domains/idn-tables/tables/google_ja_1.0.txt</rdeIDN:url>
<rdeIDN:urlPolicy>https://www.registry.google/about/policies/domainabuse/</rdeIDN:urlPolicy>
@@ -256,7 +261,7 @@
<rdeHeader:count uri="urn:ietf:params:xml:ns:rdeDomain-1.0">1</rdeHeader:count>
<rdeHeader:count uri="urn:ietf:params:xml:ns:rdeHost-1.0">2</rdeHeader:count>
<rdeHeader:count uri="urn:ietf:params:xml:ns:rdeRegistrar-1.0">2</rdeHeader:count>
<rdeHeader:count uri="urn:ietf:params:xml:ns:rdeIDN-1.0">2</rdeHeader:count>
<rdeHeader:count uri="urn:ietf:params:xml:ns:rdeIDN-1.0">3</rdeHeader:count>
</rdeHeader:header>
</rde:contents>
@@ -37,6 +37,6 @@
<rdeHeader:count uri="urn:ietf:params:xml:ns:rdeDomain-1.0">1</rdeHeader:count>
<rdeHeader:count uri="urn:ietf:params:xml:ns:rdeHost-1.0">2</rdeHeader:count>
<rdeHeader:count uri="urn:ietf:params:xml:ns:rdeRegistrar-1.0">2</rdeHeader:count>
<rdeHeader:count uri="urn:ietf:params:xml:ns:rdeIDN-1.0">2</rdeHeader:count>
<rdeHeader:count uri="urn:ietf:params:xml:ns:rdeIDN-1.0">3</rdeHeader:count>
</rdeHeader:header>
</rdeReport:report>
@@ -119,6 +119,11 @@
<rdeIDN:urlPolicy>https://www.registry.google/about/policies/domainabuse/</rdeIDN:urlPolicy>
</rdeIDN:idnTableRef>
<rdeIDN:idnTableRef id="unconfusable_latin">
<rdeIDN:url>https://www.iana.org/domains/idn-tables/tables/google_latn_2.0.txt</rdeIDN:url>
<rdeIDN:urlPolicy>https://www.registry.google/about/policies/domainabuse/</rdeIDN:urlPolicy>
</rdeIDN:idnTableRef>
<rdeIDN:idnTableRef id="ja">
<rdeIDN:url>https://www.iana.org/domains/idn-tables/tables/google_ja_1.0.txt</rdeIDN:url>
<rdeIDN:urlPolicy>https://www.registry.google/about/policies/domainabuse/</rdeIDN:urlPolicy>
@@ -130,7 +135,7 @@
<rdeHeader:count uri="urn:ietf:params:xml:ns:rdeContact-1.0">0</rdeHeader:count>
<rdeHeader:count uri="urn:ietf:params:xml:ns:rdeHost-1.0">1</rdeHeader:count>
<rdeHeader:count uri="urn:ietf:params:xml:ns:rdeRegistrar-1.0">2</rdeHeader:count>
<rdeHeader:count uri="urn:ietf:params:xml:ns:rdeIDN-1.0">2</rdeHeader:count>
<rdeHeader:count uri="urn:ietf:params:xml:ns:rdeIDN-1.0">3</rdeHeader:count>
</rdeHeader:header>
</rde:contents>