Skip to content

Commit

Permalink
syntax: update to Unicode 14
Browse files Browse the repository at this point in the history
Closes #878
  • Loading branch information
BurntSushi committed Jul 5, 2022
1 parent 99d90e5 commit fb2458c
Show file tree
Hide file tree
Showing 15 changed files with 2,012 additions and 1,153 deletions.
1 change: 1 addition & 0 deletions regex-syntax/src/unicode.rs
Expand Up @@ -604,6 +604,7 @@ fn ages(canonical_age: &str) -> Result<impl Iterator<Item = Range>> {
("V12_0", age::V12_0),
("V12_1", age::V12_1),
("V13_0", age::V13_0),
("V14_0", age::V14_0),
];
assert_eq!(AGES.len(), age::BY_NAME.len(), "ages are out of sync");

Expand Down
198 changes: 140 additions & 58 deletions regex-syntax/src/unicode_tables/age.rs
@@ -1,17 +1,18 @@
// DO NOT EDIT THIS FILE. IT WAS AUTOMATICALLY GENERATED BY:
//
// ucd-generate age ucd-13.0.0 --chars
// ucd-generate age /tmp/ucd --chars
//
// Unicode version: 13.0.0.
// Unicode version: 14.0.0.
//
// ucd-generate 0.2.8 is available on crates.io.
// ucd-generate 0.2.11 is available on crates.io.

pub const BY_NAME: &'static [(&'static str, &'static [(char, char)])] = &[
("V10_0", V10_0),
("V11_0", V11_0),
("V12_0", V12_0),
("V12_1", V12_1),
("V13_0", V13_0),
("V14_0", V14_0),
("V1_1", V1_1),
("V2_0", V2_0),
("V2_1", V2_1),
Expand Down Expand Up @@ -203,69 +204,150 @@ pub const V12_0: &'static [(char, char)] = &[
pub const V12_1: &'static [(char, char)] = &[('㋿', '㋿')];

pub const V13_0: &'static [(char, char)] = &[
('\u{8be}', '\u{8c7}'),
('', ''),
('\u{b55}', '\u{b55}'),
('\u{d04}', '\u{d04}'),
('', ''),
('\u{d81}', '\u{d81}'),
('\u{1abf}', '\u{1ac0}'),
('\u{2b97}', '\u{2b97}'),
('\u{2e50}', '\u{2e52}'),
('\u{31bb}', '\u{31bf}'),
('\u{4db6}', '\u{4dbf}'),
('\u{9ff0}', '\u{9ffc}'),
('\u{a7c7}', '\u{a7ca}'),
('\u{a7f5}', '\u{a7f6}'),
('', ''),
('', ''),
('', ''),
('', '䶿'),
('', ''),
('', ''),
('', ''),
('\u{a82c}', '\u{a82c}'),
('\u{ab68}', '\u{ab6b}'),
('\u{1019c}', '\u{1019c}'),
('\u{10e80}', '\u{10ea9}'),
('\u{10eab}', '\u{10ead}'),
('\u{10eb0}', '\u{10eb1}'),
('\u{10fb0}', '\u{10fcb}'),
('\u{11147}', '\u{11147}'),
('\u{111ce}', '\u{111cf}'),
('\u{1145a}', '\u{1145a}'),
('\u{11460}', '\u{11461}'),
('\u{11900}', '\u{11906}'),
('\u{11909}', '\u{11909}'),
('\u{1190c}', '\u{11913}'),
('\u{11915}', '\u{11916}'),
('\u{11918}', '\u{11935}'),
('\u{11937}', '\u{11938}'),
('\u{1193b}', '\u{11946}'),
('\u{11950}', '\u{11959}'),
('\u{11fb0}', '\u{11fb0}'),
('', ''),
('𐆜', '𐆜'),
('𐺀', '𐺩'),
('\u{10eab}', '𐺭'),
('𐺰', '𐺱'),
('𐾰', '𐿋'),
('𑅇', '𑅇'),
('𑇎', '\u{111cf}'),
('𑑚', '𑑚'),
('𑑠', '𑑡'),
('𑤀', '𑤆'),
('𑤉', '𑤉'),
('𑤌', '𑤓'),
('𑤕', '𑤖'),
('𑤘', '𑤵'),
('𑤷', '𑤸'),
('\u{1193b}', '𑥆'),
('𑥐', '𑥙'),
('𑾰', '𑾰'),
('\u{16fe4}', '\u{16fe4}'),
('\u{16ff0}', '\u{16ff1}'),
('\u{18af3}', '\u{18cd5}'),
('\u{18d00}', '\u{18d08}'),
('\u{1f10d}', '\u{1f10f}'),
('\u{1f16d}', '\u{1f16f}'),
('\u{1f1ad}', '\u{1f1ad}'),
('\u{1f6d6}', '\u{1f6d7}'),
('\u{1f6fb}', '\u{1f6fc}'),
('\u{1f8b0}', '\u{1f8b1}'),
('\u{1f90c}', '\u{1f90c}'),
('\u{1f972}', '\u{1f972}'),
('\u{1f977}', '\u{1f978}'),
('\u{1f9a3}', '\u{1f9a4}'),
('\u{1f9ab}', '\u{1f9ad}'),
('\u{1f9cb}', '\u{1f9cb}'),
('\u{1fa74}', '\u{1fa74}'),
('\u{1fa83}', '\u{1fa86}'),
('\u{1fa96}', '\u{1faa8}'),
('\u{1fab0}', '\u{1fab6}'),
('\u{1fac0}', '\u{1fac2}'),
('\u{1fad0}', '\u{1fad6}'),
('\u{1fb00}', '\u{1fb92}'),
('\u{1fb94}', '\u{1fbca}'),
('\u{1fbf0}', '\u{1fbf9}'),
('\u{2a6d7}', '\u{2a6dd}'),
('\u{30000}', '\u{3134a}'),
('𖿰', '𖿱'),
('𘫳', '𘳕'),
('𘴀', '𘴈'),
('🄍', '🄏'),
('🅭', '🅯'),
('🆭', '🆭'),
('🛖', '🛗'),
('🛻', '🛼'),
('🢰', '🢱'),
('🤌', '🤌'),
('🥲', '🥲'),
('🥷', '🥸'),
('🦣', '🦤'),
('🦫', '🦭'),
('🧋', '🧋'),
('🩴', '🩴'),
('🪃', '🪆'),
('🪖', '🪨'),
('🪰', '🪶'),
('🫀', '🫂'),
('🫐', '🫖'),
('🬀', '🮒'),
('🮔', '🯊'),
('🯰', '🯹'),
('𪛗', '𪛝'),
('𰀀', '𱍊'),
];

pub const V14_0: &'static [(char, char)] = &[
('؝', '؝'),
('ࡰ', 'ࢎ'),
('\u{890}', '\u{891}'),
('\u{898}', '\u{89f}'),
('ࢵ', 'ࢵ'),
('ࣈ', '\u{8d2}'),
('\u{c3c}', '\u{c3c}'),
('ౝ', 'ౝ'),
('ೝ', 'ೝ'),
('ᜍ', 'ᜍ'),
('᜕', '᜕'),
('ᜟ', 'ᜟ'),
('\u{180f}', '\u{180f}'),
('\u{1ac1}', '\u{1ace}'),
('ᭌ', 'ᭌ'),
('᭽', '᭾'),
('\u{1dfa}', '\u{1dfa}'),
('⃀', '⃀'),
('Ⱟ', 'Ⱟ'),
('ⱟ', 'ⱟ'),
('⹓', '⹝'),
('鿽', '鿿'),
('Ꟁ', 'ꟁ'),
('Ꟑ', 'ꟑ'),
('ꟓ', 'ꟓ'),
('ꟕ', 'ꟙ'),
('ꟲ', 'ꟴ'),
('﯂', '﯂'),
('﵀', '﵏'),
('﷏', '﷏'),
('﷾', '﷿'),
('𐕰', '𐕺'),
('𐕼', '𐖊'),
('𐖌', '𐖒'),
('𐖔', '𐖕'),
('𐖗', '𐖡'),
('𐖣', '𐖱'),
('𐖳', '𐖹'),
('𐖻', '𐖼'),
('𐞀', '𐞅'),
('𐞇', '𐞰'),
('𐞲', '𐞺'),
('𐽰', '𐾉'),
('\u{11070}', '𑁵'),
('\u{110c2}', '\u{110c2}'),
('𑚹', '𑚹'),
('𑝀', '𑝆'),
('𑪰', '𑪿'),
('𒾐', '𒿲'),
('𖩰', '𖪾'),
('𖫀', '𖫉'),
('𚿰', '𚿳'),
('𚿵', '𚿻'),
('𚿽', '𚿾'),
('𛄟', '𛄢'),
('\u{1cf00}', '\u{1cf2d}'),
('\u{1cf30}', '\u{1cf46}'),
('𜽐', '𜿃'),
('𝇩', '𝇪'),
('𝼀', '𝼞'),
('𞊐', '\u{1e2ae}'),
('𞟠', '𞟦'),
('𞟨', '𞟫'),
('𞟭', '𞟮'),
('𞟰', '𞟾'),
('🛝', '🛟'),
('🟰', '🟰'),
('🥹', '🥹'),
('🧌', '🧌'),
('🩻', '🩼'),
('🪩', '🪬'),
('🪷', '🪺'),
('🫃', '🫅'),
('🫗', '🫙'),
('🫠', '🫧'),
('🫰', '🫶'),
('𪛞', '𪛟'),
('𫜵', '𫜸'),
];

pub const V1_1: &'static [(char, char)] = &[
('\u{0}', 'ǵ'),
('\0', 'ǵ'),
('Ǻ', 'ȗ'),
('ɐ', 'ʨ'),
('ʰ', '˞'),
Expand Down
98 changes: 89 additions & 9 deletions regex-syntax/src/unicode_tables/case_folding_simple.rs
@@ -1,10 +1,10 @@
// DO NOT EDIT THIS FILE. IT WAS AUTOMATICALLY GENERATED BY:
//
// ucd-generate case-folding-simple ucd-13.0.0 --chars --all-pairs
// ucd-generate case-folding-simple /tmp/ucd --chars --all-pairs
//
// Unicode version: 13.0.0.
// Unicode version: 14.0.0.
//
// ucd-generate 0.2.8 is available on crates.io.
// ucd-generate 0.2.11 is available on crates.io.

pub const CASE_FOLDING_SIMPLE: &'static [(char, &'static [char])] = &[
('A', &['a']),
Expand Down Expand Up @@ -1781,6 +1781,7 @@ pub const CASE_FOLDING_SIMPLE: &'static [(char, &'static [char])] = &[
('Ⱜ', &['ⱜ']),
('Ⱝ', &['ⱝ']),
('Ⱞ', &['ⱞ']),
('Ⱟ', &['ⱟ']),
('ⰰ', &['Ⰰ']),
('ⰱ', &['Ⰱ']),
('ⰲ', &['Ⰲ']),
Expand Down Expand Up @@ -1828,6 +1829,7 @@ pub const CASE_FOLDING_SIMPLE: &'static [(char, &'static [char])] = &[
('ⱜ', &['Ⱜ']),
('ⱝ', &['Ⱝ']),
('ⱞ', &['Ⱞ']),
('ⱟ', &['Ⱟ']),
('Ⱡ', &['ⱡ']),
('ⱡ', &['Ⱡ']),
('Ɫ', &['ɫ']),
Expand Down Expand Up @@ -2211,17 +2213,25 @@ pub const CASE_FOLDING_SIMPLE: &'static [(char, &'static [char])] = &[
('ꞽ', &['Ꞽ']),
('Ꞿ', &['ꞿ']),
('ꞿ', &['Ꞿ']),
('Ꟁ', &['ꟁ']),
('ꟁ', &['Ꟁ']),
('Ꟃ', &['ꟃ']),
('ꟃ', &['Ꟃ']),
('Ꞔ', &['ꞔ']),
('Ʂ', &['ʂ']),
('Ᶎ', &['ᶎ']),
('\u{a7c7}', &['\u{a7c8}']),
('\u{a7c8}', &['\u{a7c7}']),
('\u{a7c9}', &['\u{a7ca}']),
('\u{a7ca}', &['\u{a7c9}']),
('\u{a7f5}', &['\u{a7f6}']),
('\u{a7f6}', &['\u{a7f5}']),
('Ꟈ', &['ꟈ']),
('ꟈ', &['Ꟈ']),
('Ꟊ', &['ꟊ']),
('ꟊ', &['Ꟊ']),
('Ꟑ', &['ꟑ']),
('ꟑ', &['Ꟑ']),
('Ꟗ', &['ꟗ']),
('ꟗ', &['Ꟗ']),
('Ꟙ', &['ꟙ']),
('ꟙ', &['Ꟙ']),
('Ꟶ', &['ꟶ']),
('ꟶ', &['Ꟶ']),
('ꭓ', &['Ꭓ']),
('ꭰ', &['Ꭰ']),
('ꭱ', &['Ꭱ']),
Expand Down Expand Up @@ -2507,6 +2517,76 @@ pub const CASE_FOLDING_SIMPLE: &'static [(char, &'static [char])] = &[
('𐓹', &['𐓑']),
('𐓺', &['𐓒']),
('𐓻', &['𐓓']),
('𐕰', &['𐖗']),
('𐕱', &['𐖘']),
('𐕲', &['𐖙']),
('𐕳', &['𐖚']),
('𐕴', &['𐖛']),
('𐕵', &['𐖜']),
('𐕶', &['𐖝']),
('𐕷', &['𐖞']),
('𐕸', &['𐖟']),
('𐕹', &['𐖠']),
('𐕺', &['𐖡']),
('𐕼', &['𐖣']),
('𐕽', &['𐖤']),
('𐕾', &['𐖥']),
('𐕿', &['𐖦']),
('𐖀', &['𐖧']),
('𐖁', &['𐖨']),
('𐖂', &['𐖩']),
('𐖃', &['𐖪']),
('𐖄', &['𐖫']),
('𐖅', &['𐖬']),
('𐖆', &['𐖭']),
('𐖇', &['𐖮']),
('𐖈', &['𐖯']),
('𐖉', &['𐖰']),
('𐖊', &['𐖱']),
('𐖌', &['𐖳']),
('𐖍', &['𐖴']),
('𐖎', &['𐖵']),
('𐖏', &['𐖶']),
('𐖐', &['𐖷']),
('𐖑', &['𐖸']),
('𐖒', &['𐖹']),
('𐖔', &['𐖻']),
('𐖕', &['𐖼']),
('𐖗', &['𐕰']),
('𐖘', &['𐕱']),
('𐖙', &['𐕲']),
('𐖚', &['𐕳']),
('𐖛', &['𐕴']),
('𐖜', &['𐕵']),
('𐖝', &['𐕶']),
('𐖞', &['𐕷']),
('𐖟', &['𐕸']),
('𐖠', &['𐕹']),
('𐖡', &['𐕺']),
('𐖣', &['𐕼']),
('𐖤', &['𐕽']),
('𐖥', &['𐕾']),
('𐖦', &['𐕿']),
('𐖧', &['𐖀']),
('𐖨', &['𐖁']),
('𐖩', &['𐖂']),
('𐖪', &['𐖃']),
('𐖫', &['𐖄']),
('𐖬', &['𐖅']),
('𐖭', &['𐖆']),
('𐖮', &['𐖇']),
('𐖯', &['𐖈']),
('𐖰', &['𐖉']),
('𐖱', &['𐖊']),
('𐖳', &['𐖌']),
('𐖴', &['𐖍']),
('𐖵', &['𐖎']),
('𐖶', &['𐖏']),
('𐖷', &['𐖐']),
('𐖸', &['𐖑']),
('𐖹', &['𐖒']),
('𐖻', &['𐖔']),
('𐖼', &['𐖕']),
('𐲀', &['𐳀']),
('𐲁', &['𐳁']),
('𐲂', &['𐳂']),
Expand Down

0 comments on commit fb2458c

Please sign in to comment.