Skip to content

Commit

Permalink
UTS #46 minimize base exclusion set (#724)
Browse files Browse the repository at this point in the history
  • Loading branch information
@markusicu
markusicu authored May 4, 2024
1 parent d95d537 commit dbc2ad7
Show file tree
Hide file tree
Showing 4 changed files with 1,000 additions and 970 deletions.
81 changes: 57 additions & 24 deletions unicodetools/data/idna/dev/IdnaMappingTable.txt
View file
Original file line number Diff line number Diff line change
@@ -1,8 +1,8 @@
# IdnaMappingTable.txt
# Date: 2024-04-25, 18:06:27 GMT
# Date: 2024-05-03, 23:53:50 GMT
# © 2024 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see https://www.unicode.org/terms_of_use.html
# For terms of use and license, see https://www.unicode.org/terms_of_use.html
#
# Unicode IDNA Compatible Preprocessing for UTS #46
# Version: 16.0.0
Expand Down Expand Up @@ -710,7 +710,7 @@
04BD ; valid # 1.1 CYRILLIC SMALL LETTER ABKHASIAN CHE
04BE ; mapped ; 04BF # 1.1 CYRILLIC CAPITAL LETTER ABKHASIAN CHE WITH DESCENDER
04BF ; valid # 1.1 CYRILLIC SMALL LETTER ABKHASIAN CHE WITH DESCENDER
04C0 ; disallowed # 1.1 CYRILLIC LETTER PALOCHKA
04C0 ; mapped ; 04CF # 1.1 CYRILLIC LETTER PALOCHKA
04C1 ; mapped ; 04C2 # 1.1 CYRILLIC CAPITAL LETTER ZHE WITH BREVE
04C2 ; valid # 1.1 CYRILLIC SMALL LETTER ZHE WITH BREVE
04C3 ; mapped ; 04C4 # 1.1 CYRILLIC CAPITAL LETTER KA WITH HOOK
Expand Down Expand Up @@ -1490,7 +1490,44 @@
105A..1099 ; valid # 5.1 MYANMAR LETTER MON NGA..MYANMAR SHAN DIGIT NINE
109A..109D ; valid # 5.2 MYANMAR SIGN KHAMTI TONE-1..MYANMAR VOWEL SIGN AITON AI
109E..109F ; valid ; ; NV8 # 5.1 MYANMAR SYMBOL SHAN ONE..MYANMAR SYMBOL SHAN EXCLAMATION
10A0..10C5 ; disallowed # 1.1 GEORGIAN CAPITAL LETTER AN..GEORGIAN CAPITAL LETTER HOE
10A0 ; mapped ; 2D00 # 1.1 GEORGIAN CAPITAL LETTER AN
10A1 ; mapped ; 2D01 # 1.1 GEORGIAN CAPITAL LETTER BAN
10A2 ; mapped ; 2D02 # 1.1 GEORGIAN CAPITAL LETTER GAN
10A3 ; mapped ; 2D03 # 1.1 GEORGIAN CAPITAL LETTER DON
10A4 ; mapped ; 2D04 # 1.1 GEORGIAN CAPITAL LETTER EN
10A5 ; mapped ; 2D05 # 1.1 GEORGIAN CAPITAL LETTER VIN
10A6 ; mapped ; 2D06 # 1.1 GEORGIAN CAPITAL LETTER ZEN
10A7 ; mapped ; 2D07 # 1.1 GEORGIAN CAPITAL LETTER TAN
10A8 ; mapped ; 2D08 # 1.1 GEORGIAN CAPITAL LETTER IN
10A9 ; mapped ; 2D09 # 1.1 GEORGIAN CAPITAL LETTER KAN
10AA ; mapped ; 2D0A # 1.1 GEORGIAN CAPITAL LETTER LAS
10AB ; mapped ; 2D0B # 1.1 GEORGIAN CAPITAL LETTER MAN
10AC ; mapped ; 2D0C # 1.1 GEORGIAN CAPITAL LETTER NAR
10AD ; mapped ; 2D0D # 1.1 GEORGIAN CAPITAL LETTER ON
10AE ; mapped ; 2D0E # 1.1 GEORGIAN CAPITAL LETTER PAR
10AF ; mapped ; 2D0F # 1.1 GEORGIAN CAPITAL LETTER ZHAR
10B0 ; mapped ; 2D10 # 1.1 GEORGIAN CAPITAL LETTER RAE
10B1 ; mapped ; 2D11 # 1.1 GEORGIAN CAPITAL LETTER SAN
10B2 ; mapped ; 2D12 # 1.1 GEORGIAN CAPITAL LETTER TAR
10B3 ; mapped ; 2D13 # 1.1 GEORGIAN CAPITAL LETTER UN
10B4 ; mapped ; 2D14 # 1.1 GEORGIAN CAPITAL LETTER PHAR
10B5 ; mapped ; 2D15 # 1.1 GEORGIAN CAPITAL LETTER KHAR
10B6 ; mapped ; 2D16 # 1.1 GEORGIAN CAPITAL LETTER GHAN
10B7 ; mapped ; 2D17 # 1.1 GEORGIAN CAPITAL LETTER QAR
10B8 ; mapped ; 2D18 # 1.1 GEORGIAN CAPITAL LETTER SHIN
10B9 ; mapped ; 2D19 # 1.1 GEORGIAN CAPITAL LETTER CHIN
10BA ; mapped ; 2D1A # 1.1 GEORGIAN CAPITAL LETTER CAN
10BB ; mapped ; 2D1B # 1.1 GEORGIAN CAPITAL LETTER JIL
10BC ; mapped ; 2D1C # 1.1 GEORGIAN CAPITAL LETTER CIL
10BD ; mapped ; 2D1D # 1.1 GEORGIAN CAPITAL LETTER CHAR
10BE ; mapped ; 2D1E # 1.1 GEORGIAN CAPITAL LETTER XAN
10BF ; mapped ; 2D1F # 1.1 GEORGIAN CAPITAL LETTER JHAN
10C0 ; mapped ; 2D20 # 1.1 GEORGIAN CAPITAL LETTER HAE
10C1 ; mapped ; 2D21 # 1.1 GEORGIAN CAPITAL LETTER HE
10C2 ; mapped ; 2D22 # 1.1 GEORGIAN CAPITAL LETTER HIE
10C3 ; mapped ; 2D23 # 1.1 GEORGIAN CAPITAL LETTER WE
10C4 ; mapped ; 2D24 # 1.1 GEORGIAN CAPITAL LETTER HAR
10C5 ; mapped ; 2D25 # 1.1 GEORGIAN CAPITAL LETTER HOE
10C6 ; disallowed # NA <reserved-10C6>
10C7 ; mapped ; 2D27 # 6.1 GEORGIAN CAPITAL LETTER YN
10C8..10CC ; disallowed # NA <reserved-10C8>..<reserved-10CC>
Expand All @@ -1504,7 +1541,7 @@
10FD..10FF ; valid # 6.1 GEORGIAN LETTER AEN..GEORGIAN LETTER LABIAL SIGN
1100..1159 ; valid ; ; NV8 # 1.1 HANGUL CHOSEONG KIYEOK..HANGUL CHOSEONG YEORINHIEUH
115A..115E ; valid ; ; NV8 # 5.2 HANGUL CHOSEONG KIYEOK-TIKEUT..HANGUL CHOSEONG TIKEUT-RIEUL
115F..1160 ; disallowed # 1.1 HANGUL CHOSEONG FILLER..HANGUL JUNGSEONG FILLER
115F..1160 ; ignored # 1.1 HANGUL CHOSEONG FILLER..HANGUL JUNGSEONG FILLER
1161..11A2 ; valid ; ; NV8 # 1.1 HANGUL JUNGSEONG A..HANGUL JUNGSEONG SSANGARAEA
11A3..11A7 ; valid ; ; NV8 # 5.2 HANGUL JUNGSEONG A-EU..HANGUL JUNGSEONG O-YAE
11A8..11F9 ; valid ; ; NV8 # 1.1 HANGUL JONGSEONG KIYEOK..HANGUL JONGSEONG YEORINHIEUH
Expand Down Expand Up @@ -1608,7 +1645,7 @@
1772..1773 ; valid # 3.2 TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U
1774..177F ; disallowed # NA <reserved-1774>..<reserved-177F>
1780..17B3 ; valid # 3.0 KHMER LETTER KA..KHMER INDEPENDENT VOWEL QAU
17B4..17B5 ; disallowed # 3.0 KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA
17B4..17B5 ; ignored # 3.0 KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA
17B6..17D3 ; valid # 3.0 KHMER VOWEL SIGN AA..KHMER SIGN BATHAMASAT
17D4..17D6 ; valid ; ; NV8 # 3.0 KHMER SIGN KHAN..KHMER SIGN CAMNUC PII KUUH
17D7 ; valid # 3.0 KHMER SIGN LEK TOO
Expand All @@ -1620,11 +1657,8 @@
17EA..17EF ; disallowed # NA <reserved-17EA>..<reserved-17EF>
17F0..17F9 ; valid ; ; NV8 # 4.0 KHMER SYMBOL LEK ATTAK SON..KHMER SYMBOL LEK ATTAK PRAM-BUON
17FA..17FF ; disallowed # NA <reserved-17FA>..<reserved-17FF>
1800..1805 ; valid ; ; NV8 # 3.0 MONGOLIAN BIRGA..MONGOLIAN FOUR DOTS
1806 ; disallowed # 3.0 MONGOLIAN TODO SOFT HYPHEN
1807..180A ; valid ; ; NV8 # 3.0 MONGOLIAN SIBE SYLLABLE BOUNDARY MARKER..MONGOLIAN NIRUGU
180B..180D ; ignored # 3.0 MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE
180E ; disallowed # 3.0 MONGOLIAN VOWEL SEPARATOR
1800..180A ; valid ; ; NV8 # 3.0 MONGOLIAN BIRGA..MONGOLIAN NIRUGU
180B..180E ; ignored # 3.0 MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN VOWEL SEPARATOR
180F ; ignored # 14.0 MONGOLIAN FREE VARIATION SELECTOR FOUR
1810..1819 ; valid # 3.0 MONGOLIAN DIGIT ZERO..MONGOLIAN DIGIT NINE
181A..181F ; disallowed # NA <reserved-181A>..<reserved-181F>
Expand Down Expand Up @@ -2367,12 +2401,11 @@
2057 ; mapped ; 2032 2032 2032 2032 #3.2 QUADRUPLE PRIME
2058..205E ; valid ; ; NV8 # 4.1 FOUR DOT PUNCTUATION..VERTICAL FOUR DOTS
205F ; disallowed_STD3_mapped ; 0020 # 3.2 MEDIUM MATHEMATICAL SPACE
2060 ; ignored # 3.2 WORD JOINER
2061..2063 ; disallowed # 3.2 FUNCTION APPLICATION..INVISIBLE SEPARATOR
2060..2063 ; ignored # 3.2 WORD JOINER..INVISIBLE SEPARATOR
2064 ; ignored # 5.1 INVISIBLE PLUS
2065 ; disallowed # NA <reserved-2065>
2066..2069 ; disallowed # 6.3 LEFT-TO-RIGHT ISOLATE..POP DIRECTIONAL ISOLATE
206A..206F ; disallowed # 1.1 INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES
206A..206F ; ignored # 1.1 INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES
2070 ; mapped ; 0030 # 1.1 SUPERSCRIPT ZERO
2071 ; mapped ; 0069 # 3.2 SUPERSCRIPT LATIN SMALL LETTER I
2072..2073 ; disallowed # NA <reserved-2072>..<reserved-2073>
Expand Down Expand Up @@ -2481,7 +2514,7 @@
212E ; valid ; ; NV8 # 1.1 ESTIMATED SYMBOL
212F..2130 ; mapped ; 0065 # 1.1 SCRIPT SMALL E..SCRIPT CAPITAL E
2131 ; mapped ; 0066 # 1.1 SCRIPT CAPITAL F
2132 ; disallowed # 1.1 TURNED CAPITAL F
2132 ; mapped ; 214E # 1.1 TURNED CAPITAL F
2133 ; mapped ; 006D # 1.1 SCRIPT CAPITAL M
2134 ; mapped ; 006F # 1.1 SCRIPT SMALL O
2135 ; mapped ; 05D0 # 1.1 ALEF SYMBOL
Expand Down Expand Up @@ -2554,7 +2587,7 @@
217E ; mapped ; 0064 # 1.1 SMALL ROMAN NUMERAL FIVE HUNDRED
217F ; mapped ; 006D # 1.1 SMALL ROMAN NUMERAL ONE THOUSAND
2180..2182 ; valid ; ; NV8 # 1.1 ROMAN NUMERAL ONE THOUSAND C D..ROMAN NUMERAL TEN THOUSAND
2183 ; disallowed # 3.0 ROMAN NUMERAL REVERSED ONE HUNDRED
2183 ; mapped ; 2184 # 3.0 ROMAN NUMERAL REVERSED ONE HUNDRED
2184 ; valid # 5.0 LATIN SMALL LETTER REVERSED C
2185..2188 ; valid ; ; NV8 # 5.1 ROMAN NUMERAL SIX LATE FORM..ROMAN NUMERAL ONE HUNDRED THOUSAND
2189 ; mapped ; 0030 2044 0033 #5.2 VULGAR FRACTION ZERO THIRDS
Expand Down Expand Up @@ -3362,7 +3395,7 @@
3161 ; mapped ; 1173 # 1.1 HANGUL LETTER EU
3162 ; mapped ; 1174 # 1.1 HANGUL LETTER YI
3163 ; mapped ; 1175 # 1.1 HANGUL LETTER I
3164 ; disallowed # 1.1 HANGUL FILLER
3164 ; ignored # 1.1 HANGUL FILLER
3165 ; mapped ; 1114 # 1.1 HANGUL LETTER SSANGNIEUN
3166 ; mapped ; 1115 # 1.1 HANGUL LETTER NIEUN-TIKEUT
3167 ; mapped ; 11C7 # 1.1 HANGUL LETTER NIEUN-SIOS
Expand Down Expand Up @@ -5725,7 +5758,7 @@ FF9C ; mapped ; 30EF # 1.1 HALFWIDTH KATAKANA
FF9D ; mapped ; 30F3 # 1.1 HALFWIDTH KATAKANA LETTER N
FF9E ; mapped ; 3099 # 1.1 HALFWIDTH KATAKANA VOICED SOUND MARK
FF9F ; mapped ; 309A # 1.1 HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK
FFA0 ; disallowed # 1.1 HALFWIDTH HANGUL FILLER
FFA0 ; ignored # 1.1 HALFWIDTH HANGUL FILLER
FFA1 ; mapped ; 1100 # 1.1 HALFWIDTH HANGUL LETTER KIYEOK
FFA2 ; mapped ; 1101 # 1.1 HALFWIDTH HANGUL LETTER SSANGKIYEOK
FFA3 ; mapped ; 11AA # 1.1 HALFWIDTH HANGUL LETTER KIYEOK-SIOS
Expand Down Expand Up @@ -6799,7 +6832,7 @@ FFFE..FFFF ; disallowed # 1.1 <noncharacter-FFFE
1D163 ; mapped ; 1D158 1D165 1D171 #3.1 MUSICAL SYMBOL SIXTY-FOURTH NOTE
1D164 ; mapped ; 1D158 1D165 1D172 #3.1 MUSICAL SYMBOL ONE HUNDRED TWENTY-EIGHTH NOTE
1D165..1D172 ; valid ; ; NV8 # 3.1 MUSICAL SYMBOL COMBINING STEM..MUSICAL SYMBOL COMBINING FLAG-5
1D173..1D17A ; disallowed # 3.1 MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE
1D173..1D17A ; ignored # 3.1 MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE
1D17B..1D1BA ; valid ; ; NV8 # 3.1 MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL SEMIBREVIS BLACK
1D1BB ; mapped ; 1D1B9 1D165 # 3.1 MUSICAL SYMBOL MINIMA
1D1BC ; mapped ; 1D1BA 1D165 # 3.1 MUSICAL SYMBOL MINIMA BLACK
Expand Down Expand Up @@ -8691,7 +8724,7 @@ FFFE..FFFF ; disallowed # 1.1 <noncharacter-FFFE
2F865 ; mapped ; 59D8 # 3.1 CJK COMPATIBILITY IDEOGRAPH-2F865
2F866 ; mapped ; 5A66 # 3.1 CJK COMPATIBILITY IDEOGRAPH-2F866
2F867 ; mapped ; 36EE # 3.1 CJK COMPATIBILITY IDEOGRAPH-2F867
2F868 ; disallowed # 3.1 CJK COMPATIBILITY IDEOGRAPH-2F868
2F868 ; mapped ; 36FC # 3.1 CJK COMPATIBILITY IDEOGRAPH-2F868
2F869 ; mapped ; 5B08 # 3.1 CJK COMPATIBILITY IDEOGRAPH-2F869
2F86A..2F86B ; mapped ; 5B3E # 3.1 CJK COMPATIBILITY IDEOGRAPH-2F86A..CJK COMPATIBILITY IDEOGRAPH-2F86B
2F86C ; mapped ; 219C8 # 3.1 CJK COMPATIBILITY IDEOGRAPH-2F86C
Expand All @@ -8702,7 +8735,7 @@ FFFE..FFFF ; disallowed # 1.1 <noncharacter-FFFE
2F871 ; mapped ; 21B18 # 3.1 CJK COMPATIBILITY IDEOGRAPH-2F871
2F872 ; mapped ; 5BFF # 3.1 CJK COMPATIBILITY IDEOGRAPH-2F872
2F873 ; mapped ; 5C06 # 3.1 CJK COMPATIBILITY IDEOGRAPH-2F873
2F874 ; disallowed # 3.1 CJK COMPATIBILITY IDEOGRAPH-2F874
2F874 ; mapped ; 5F53 # 3.1 CJK COMPATIBILITY IDEOGRAPH-2F874
2F875 ; mapped ; 5C22 # 3.1 CJK COMPATIBILITY IDEOGRAPH-2F875
2F876 ; mapped ; 3781 # 3.1 CJK COMPATIBILITY IDEOGRAPH-2F876
2F877 ; mapped ; 5C60 # 3.1 CJK COMPATIBILITY IDEOGRAPH-2F877
Expand Down Expand Up @@ -8871,7 +8904,7 @@ FFFE..FFFF ; disallowed # 1.1 <noncharacter-FFFE
2F91C ; mapped ; 7145 # 3.1 CJK COMPATIBILITY IDEOGRAPH-2F91C
2F91D ; mapped ; 24263 # 3.1 CJK COMPATIBILITY IDEOGRAPH-2F91D
2F91E ; mapped ; 719C # 3.1 CJK COMPATIBILITY IDEOGRAPH-2F91E
2F91F ; disallowed # 3.1 CJK COMPATIBILITY IDEOGRAPH-2F91F
2F91F ; mapped ; 243AB # 3.1 CJK COMPATIBILITY IDEOGRAPH-2F91F
2F920 ; mapped ; 7228 # 3.1 CJK COMPATIBILITY IDEOGRAPH-2F920
2F921 ; mapped ; 7235 # 3.1 CJK COMPATIBILITY IDEOGRAPH-2F921
2F922 ; mapped ; 7250 # 3.1 CJK COMPATIBILITY IDEOGRAPH-2F922
Expand Down Expand Up @@ -8932,7 +8965,7 @@ FFFE..FFFF ; disallowed # 1.1 <noncharacter-FFFE
2F95B ; mapped ; 7A4F # 3.1 CJK COMPATIBILITY IDEOGRAPH-2F95B
2F95C ; mapped ; 2597C # 3.1 CJK COMPATIBILITY IDEOGRAPH-2F95C
2F95D..2F95E ; mapped ; 25AA7 # 3.1 CJK COMPATIBILITY IDEOGRAPH-2F95D..CJK COMPATIBILITY IDEOGRAPH-2F95E
2F95F ; disallowed # 3.1 CJK COMPATIBILITY IDEOGRAPH-2F95F
2F95F ; mapped ; 7AEE # 3.1 CJK COMPATIBILITY IDEOGRAPH-2F95F
2F960 ; mapped ; 4202 # 3.1 CJK COMPATIBILITY IDEOGRAPH-2F960
2F961 ; mapped ; 25BAB # 3.1 CJK COMPATIBILITY IDEOGRAPH-2F961
2F962 ; mapped ; 7BC6 # 3.1 CJK COMPATIBILITY IDEOGRAPH-2F962
Expand Down Expand Up @@ -9028,7 +9061,7 @@ FFFE..FFFF ; disallowed # 1.1 <noncharacter-FFFE
2F9BC ; mapped ; 8728 # 3.1 CJK COMPATIBILITY IDEOGRAPH-2F9BC
2F9BD ; mapped ; 876B # 3.1 CJK COMPATIBILITY IDEOGRAPH-2F9BD
2F9BE ; mapped ; 8786 # 3.1 CJK COMPATIBILITY IDEOGRAPH-2F9BE
2F9BF ; disallowed # 3.1 CJK COMPATIBILITY IDEOGRAPH-2F9BF
2F9BF ; mapped ; 45D7 # 3.1 CJK COMPATIBILITY IDEOGRAPH-2F9BF
2F9C0 ; mapped ; 87E1 # 3.1 CJK COMPATIBILITY IDEOGRAPH-2F9C0
2F9C1 ; mapped ; 8801 # 3.1 CJK COMPATIBILITY IDEOGRAPH-2F9C1
2F9C2 ; mapped ; 45F9 # 3.1 CJK COMPATIBILITY IDEOGRAPH-2F9C2
Expand Down
Loading

0 comments on commit dbc2ad7

Please sign in to comment.