Skip to content

Commit

Permalink
syntax: update to Unicode 13
Browse files Browse the repository at this point in the history
  • Loading branch information
BurntSushi committed Mar 13, 2020
1 parent 934e6e7 commit cd177d9
Show file tree
Hide file tree
Showing 15 changed files with 1,577 additions and 961 deletions.
1 change: 1 addition & 0 deletions regex-syntax/src/unicode.rs
Original file line number Diff line number Diff line change
Expand Up @@ -595,6 +595,7 @@ fn ages(canonical_age: &str) -> Result<impl Iterator<Item = Range>> {
("V11_0", age::V11_0),
("V12_0", age::V12_0),
("V12_1", age::V12_1),
("V13_0", age::V13_0),
];
assert_eq!(AGES.len(), age::BY_NAME.len(), "ages are out of sync");

Expand Down
183 changes: 123 additions & 60 deletions regex-syntax/src/unicode_tables/age.rs
Original file line number Diff line number Diff line change
@@ -1,14 +1,15 @@
// DO NOT EDIT THIS FILE. IT WAS AUTOMATICALLY GENERATED BY:
//
// ucd-generate age /tmp/ucd/12.1.0/ --chars
// ucd-generate age ucd-13.0.0 --chars
//
// ucd-generate is available on crates.io.
// ucd-generate 0.2.7 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),
("V1_1", V1_1),
("V2_0", V2_0),
("V2_1", V2_1),
Expand Down Expand Up @@ -135,69 +136,131 @@ pub const V11_0: &'static [(char, char)] = &[
];

pub const V12_0: &'static [(char, char)] = &[
('\u{c77}', '\u{c77}'),
('\u{e86}', '\u{e86}'),
('\u{e89}', '\u{e89}'),
('\u{e8c}', '\u{e8c}'),
('\u{e8e}', '\u{e93}'),
('\u{e98}', '\u{e98}'),
('\u{ea0}', '\u{ea0}'),
('\u{ea8}', '\u{ea9}'),
('\u{eac}', '\u{eac}'),
('', ''),
('', ''),
('', ''),
('', ''),
('', ''),
('', ''),
('', ''),
('', ''),
('', ''),
('\u{eba}', '\u{eba}'),
('\u{1cfa}', '\u{1cfa}'),
('\u{2bc9}', '\u{2bc9}'),
('\u{2bff}', '\u{2bff}'),
('\u{2e4f}', '\u{2e4f}'),
('\u{a7ba}', '\u{a7bf}'),
('\u{a7c2}', '\u{a7c6}'),
('\u{ab66}', '\u{ab67}'),
('\u{10fe0}', '\u{10ff6}'),
('\u{1145f}', '\u{1145f}'),
('\u{116b8}', '\u{116b8}'),
('\u{119a0}', '\u{119a7}'),
('\u{119aa}', '\u{119d7}'),
('\u{119da}', '\u{119e4}'),
('\u{11a84}', '\u{11a85}'),
('\u{11fc0}', '\u{11ff1}'),
('\u{11fff}', '\u{11fff}'),
('', ''),
('', ''),
('⯿', '⯿'),
('', ''),
('', ''),
('', ''),
('', ''),
('𐿠', '𐿶'),
('𑑟', '𑑟'),
('𑚸', '𑚸'),
('𑦠', '𑦧'),
('𑦪', '\u{119d7}'),
('\u{119da}', '𑧤'),
('𑪄', '𑪅'),
('𑿀', '𑿱'),
('𑿿', '𑿿'),
('\u{13430}', '\u{13438}'),
('\u{16f45}', '\u{16f4a}'),
('𖽅', '𖽊'),
('\u{16f4f}', '\u{16f4f}'),
('\u{16f7f}', '\u{16f87}'),
('\u{16fe2}', '\u{16fe3}'),
('\u{187f2}', '\u{187f7}'),
('\u{1b150}', '\u{1b152}'),
('\u{1b164}', '\u{1b167}'),
('\u{1e100}', '\u{1e12c}'),
('\u{1e130}', '\u{1e13d}'),
('\u{1e140}', '\u{1e149}'),
('\u{1e14e}', '\u{1e14f}'),
('\u{1e2c0}', '\u{1e2f9}'),
('\u{1e2ff}', '\u{1e2ff}'),
('\u{1e94b}', '\u{1e94b}'),
('\u{1ed01}', '\u{1ed3d}'),
('\u{1f16c}', '\u{1f16c}'),
('\u{1f6d5}', '\u{1f6d5}'),
('\u{1f6fa}', '\u{1f6fa}'),
('\u{1f7e0}', '\u{1f7eb}'),
('\u{1f90d}', '\u{1f90f}'),
('\u{1f93f}', '\u{1f93f}'),
('\u{1f971}', '\u{1f971}'),
('\u{1f97b}', '\u{1f97b}'),
('\u{1f9a5}', '\u{1f9aa}'),
('\u{1f9ae}', '\u{1f9af}'),
('\u{1f9ba}', '\u{1f9bf}'),
('\u{1f9c3}', '\u{1f9ca}'),
('\u{1f9cd}', '\u{1f9cf}'),
('\u{1fa00}', '\u{1fa53}'),
('\u{1fa70}', '\u{1fa73}'),
('\u{1fa78}', '\u{1fa7a}'),
('\u{1fa80}', '\u{1fa82}'),
('\u{1fa90}', '\u{1fa95}'),
('𖽿', '𖾇'),
('𖿢', '𖿣'),
('𘟲', '𘟷'),
('𛅐', '𛅒'),
('𛅤', '𛅧'),
('𞄀', '𞄬'),
('\u{1e130}', '𞄽'),
('𞅀', '𞅉'),
('𞅎', '𞅏'),
('𞋀', '𞋹'),
('𞋿', '𞋿'),
('𞥋', '𞥋'),
('𞴁', '𞴽'),
('🅬', '🅬'),
('🛕', '🛕'),
('🛺', '🛺'),
('🟠', '🟫'),
('🤍', '🤏'),
('🤿', '🤿'),
('🥱', '🥱'),
('🥻', '🥻'),
('🦥', '🦪'),
('🦮', '🦯'),
('🦺', '🦿'),
('🧃', '🧊'),
('🧍', '🧏'),
('🨀', '🩓'),
('🩰', '🩳'),
('🩸', '🩺'),
('🪀', '🪂'),
('🪐', '🪕'),
];

pub const V12_1: &'static [(char, char)] = &[('\u{32ff}', '\u{32ff}')];
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}'),
('\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}'),
('\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}'),
];

pub const V1_1: &'static [(char, char)] = &[
('\u{0}', 'ǵ'),
Expand Down
38 changes: 22 additions & 16 deletions regex-syntax/src/unicode_tables/case_folding_simple.rs
Original file line number Diff line number Diff line change
@@ -1,8 +1,8 @@
// DO NOT EDIT THIS FILE. IT WAS AUTOMATICALLY GENERATED BY:
//
// ucd-generate case-folding-simple /tmp/ucd/12.1.0/ --chars --all-pairs
// ucd-generate case-folding-simple ucd-13.0.0 --chars --all-pairs
//
// ucd-generate is available on crates.io.
// ucd-generate 0.2.7 is available on crates.io.

pub const CASE_FOLDING_SIMPLE: &'static [(char, &'static [char])] = &[
('A', &['a']),
Expand Down Expand Up @@ -459,7 +459,7 @@ pub const CASE_FOLDING_SIMPLE: &'static [(char, &'static [char])] = &[
('ɵ', &['Ɵ']),
('ɽ', &['Ɽ']),
('ʀ', &['Ʀ']),
('ʂ', &['\u{a7c5}']),
('ʂ', &['']),
('ʃ', &['Ʃ']),
('ʇ', &['Ʇ']),
('ʈ', &['Ʈ']),
Expand Down Expand Up @@ -1199,7 +1199,7 @@ pub const CASE_FOLDING_SIMPLE: &'static [(char, &'static [char])] = &[
('Ჿ', &['ჿ']),
('ᵹ', &['Ᵹ']),
('ᵽ', &['Ᵽ']),
('ᶎ', &['\u{a7c6}']),
('ᶎ', &['']),
('Ḁ', &['ḁ']),
('ḁ', &['Ḁ']),
('Ḃ', &['ḃ']),
Expand Down Expand Up @@ -2167,7 +2167,7 @@ pub const CASE_FOLDING_SIMPLE: &'static [(char, &'static [char])] = &[
('ꞑ', &['Ꞑ']),
('Ꞓ', &['ꞓ']),
('ꞓ', &['Ꞓ']),
('ꞔ', &['\u{a7c4}']),
('ꞔ', &['']),
('Ꞗ', &['ꞗ']),
('ꞗ', &['Ꞗ']),
('Ꞙ', &['ꞙ']),
Expand Down Expand Up @@ -2203,17 +2203,23 @@ pub const CASE_FOLDING_SIMPLE: &'static [(char, &'static [char])] = &[
('ꞷ', &['Ꞷ']),
('Ꞹ', &['ꞹ']),
('ꞹ', &['Ꞹ']),
('\u{a7ba}', &['\u{a7bb}']),
('\u{a7bb}', &['\u{a7ba}']),
('\u{a7bc}', &['\u{a7bd}']),
('\u{a7bd}', &['\u{a7bc}']),
('\u{a7be}', &['\u{a7bf}']),
('\u{a7bf}', &['\u{a7be}']),
('\u{a7c2}', &['\u{a7c3}']),
('\u{a7c3}', &['\u{a7c2}']),
('\u{a7c4}', &['ꞔ']),
('\u{a7c5}', &['ʂ']),
('\u{a7c6}', &['ᶎ']),
('Ꞻ', &['ꞻ']),
('ꞻ', &['Ꞻ']),
('Ꞽ', &['ꞽ']),
('ꞽ', &['Ꞽ']),
('Ꞿ', &['ꞿ']),
('ꞿ', &['Ꞿ']),
('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}']),
('ꭓ', &['Ꭓ']),
('ꭰ', &['Ꭰ']),
('ꭱ', &['Ꭱ']),
Expand Down
Loading

0 comments on commit cd177d9

Please sign in to comment.