Merge pull request #98 from artichoke/unicode-14.0

Update case folding rules to Unicode 14.0.0

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "focaccia"
-version = "1.0.2" # remember to set `html_root_url` in `src/lib.rs`.
+version = "1.1.0" # remember to set `html_root_url` in `src/lib.rs`.
 authors = ["Ryan Lopopolo <rjl@hyperbo.la>"]
 license = "MIT"
 edition = "2018"

CaseFolding.txt

@@ -1,6 +1,6 @@
-# CaseFolding-13.0.0.txt
-# Date: 2019-09-08, 23:30:59 GMT
-# © 2019 Unicode®, Inc.
+# CaseFolding-14.0.0.txt
+# Date: 2021-03-08, 19:35:41 GMT
+# © 2021 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 http://www.unicode.org/terms_of_use.html
 #
@@ -1050,6 +1050,7 @@
 2C2C; C; 2C5C; # GLAGOLITIC CAPITAL LETTER SHTAPIC
 2C2D; C; 2C5D; # GLAGOLITIC CAPITAL LETTER TROKUTASTI A
 2C2E; C; 2C5E; # GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE
+2C2F; C; 2C5F; # GLAGOLITIC CAPITAL LETTER CAUDATE CHRIVI
 2C60; C; 2C61; # LATIN CAPITAL LETTER L WITH DOUBLE BAR
 2C62; C; 026B; # LATIN CAPITAL LETTER L WITH MIDDLE TILDE
 2C63; C; 1D7D; # LATIN CAPITAL LETTER P WITH STROKE
@@ -1230,12 +1231,16 @@ A7B8; C; A7B9; # LATIN CAPITAL LETTER U WITH STROKE
 A7BA; C; A7BB; # LATIN CAPITAL LETTER GLOTTAL A
 A7BC; C; A7BD; # LATIN CAPITAL LETTER GLOTTAL I
 A7BE; C; A7BF; # LATIN CAPITAL LETTER GLOTTAL U
+A7C0; C; A7C1; # LATIN CAPITAL LETTER OLD POLISH O
 A7C2; C; A7C3; # LATIN CAPITAL LETTER ANGLICANA W
 A7C4; C; A794; # LATIN CAPITAL LETTER C WITH PALATAL HOOK
 A7C5; C; 0282; # LATIN CAPITAL LETTER S WITH HOOK
 A7C6; C; 1D8E; # LATIN CAPITAL LETTER Z WITH PALATAL HOOK
 A7C7; C; A7C8; # LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY
 A7C9; C; A7CA; # LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY
+A7D0; C; A7D1; # LATIN CAPITAL LETTER CLOSED INSULAR G
+A7D6; C; A7D7; # LATIN CAPITAL LETTER MIDDLE SCOTS S
+A7D8; C; A7D9; # LATIN CAPITAL LETTER SIGMOID S
 A7F5; C; A7F6; # LATIN CAPITAL LETTER REVERSED HALF H
 AB70; C; 13A0; # CHEROKEE SMALL LETTER A
 AB71; C; 13A1; # CHEROKEE SMALL LETTER E
@@ -1431,6 +1436,41 @@ FF3A; C; FF5A; # FULLWIDTH LATIN CAPITAL LETTER Z
 104D1; C; 104F9; # OSAGE CAPITAL LETTER GHA
 104D2; C; 104FA; # OSAGE CAPITAL LETTER ZA
 104D3; C; 104FB; # OSAGE CAPITAL LETTER ZHA
+10570; C; 10597; # VITHKUQI CAPITAL LETTER A
+10571; C; 10598; # VITHKUQI CAPITAL LETTER BBE
+10572; C; 10599; # VITHKUQI CAPITAL LETTER BE
+10573; C; 1059A; # VITHKUQI CAPITAL LETTER CE
+10574; C; 1059B; # VITHKUQI CAPITAL LETTER CHE
+10575; C; 1059C; # VITHKUQI CAPITAL LETTER DE
+10576; C; 1059D; # VITHKUQI CAPITAL LETTER DHE
+10577; C; 1059E; # VITHKUQI CAPITAL LETTER EI
+10578; C; 1059F; # VITHKUQI CAPITAL LETTER E
+10579; C; 105A0; # VITHKUQI CAPITAL LETTER FE
+1057A; C; 105A1; # VITHKUQI CAPITAL LETTER GA
+1057C; C; 105A3; # VITHKUQI CAPITAL LETTER HA
+1057D; C; 105A4; # VITHKUQI CAPITAL LETTER HHA
+1057E; C; 105A5; # VITHKUQI CAPITAL LETTER I
+1057F; C; 105A6; # VITHKUQI CAPITAL LETTER IJE
+10580; C; 105A7; # VITHKUQI CAPITAL LETTER JE
+10581; C; 105A8; # VITHKUQI CAPITAL LETTER KA
+10582; C; 105A9; # VITHKUQI CAPITAL LETTER LA
+10583; C; 105AA; # VITHKUQI CAPITAL LETTER LLA
+10584; C; 105AB; # VITHKUQI CAPITAL LETTER ME
+10585; C; 105AC; # VITHKUQI CAPITAL LETTER NE
+10586; C; 105AD; # VITHKUQI CAPITAL LETTER NJE
+10587; C; 105AE; # VITHKUQI CAPITAL LETTER O
+10588; C; 105AF; # VITHKUQI CAPITAL LETTER PE
+10589; C; 105B0; # VITHKUQI CAPITAL LETTER QA
+1058A; C; 105B1; # VITHKUQI CAPITAL LETTER RE
+1058C; C; 105B3; # VITHKUQI CAPITAL LETTER SE
+1058D; C; 105B4; # VITHKUQI CAPITAL LETTER SHE
+1058E; C; 105B5; # VITHKUQI CAPITAL LETTER TE
+1058F; C; 105B6; # VITHKUQI CAPITAL LETTER THE
+10590; C; 105B7; # VITHKUQI CAPITAL LETTER U
+10591; C; 105B8; # VITHKUQI CAPITAL LETTER VE
+10592; C; 105B9; # VITHKUQI CAPITAL LETTER XE
+10594; C; 105BB; # VITHKUQI CAPITAL LETTER Y
+10595; C; 105BC; # VITHKUQI CAPITAL LETTER ZE
 10C80; C; 10CC0; # OLD HUNGARIAN CAPITAL LETTER A
 10C81; C; 10CC1; # OLD HUNGARIAN CAPITAL LETTER AA
 10C82; C; 10CC2; # OLD HUNGARIAN CAPITAL LETTER EB

README.md

@@ -8,9 +8,9 @@
 [![API](https://docs.rs/focaccia/badge.svg)](https://docs.rs/focaccia)
 [![API trunk](https://img.shields.io/badge/docs-trunk-blue.svg)](https://artichoke.github.io/focaccia/focaccia/)
 
-Unicode case folding methods for case-insensitive string comparisons. Used to
-implement case folding operations on the [`Symbol`] and [`String`] classes in
-the Ruby Core implementation in [Artichoke Ruby][artichoke].
+Unicode 14.0.0 case folding methods for case-insensitive string comparisons.
+Used to implement case folding operations on the [`Symbol`] and [`String`]
+classes in the Ruby Core implementation in [Artichoke Ruby][artichoke].
 
 Focaccia supports full, ASCII, and Turkic [Unicode case folding] equality
 comparisons. ASCII folding supports determining case-insensitive ordering.
@@ -32,7 +32,7 @@ Add this to your `Cargo.toml`:
 
 ```toml
 [dependencies]
-focaccia = "1.0"
+focaccia = "1.1"
 ```
 
 Then make case insensitive string comparisons like:
@@ -113,6 +113,15 @@ All features are enabled by default.
 This crate requires at least Rust 1.52.0. This version can be bumped in minor
 releases.
 
+## Unicode Version
+
+Focaccia implements Unicode case folding with the Unicode 14.0.0 case folding
+ruleset.
+
+Each new release of Unicode may bring updates to the `CaseFolding.txt` which is
+the source for the folding mappings in this crate. Updates to the case folding
+rules will be accompanied with a minor version bump.
+
 ## License
 
 `focaccia` is licensed under the [MIT License](LICENSE) (c) Ryan Lopopolo.

Rakefile

@@ -97,7 +97,7 @@ namespace :unicode do
 
   desc 'Update Unicode data'
   task :update do
-    open('https://www.unicode.org/Public/UCD/latest/ucd/CaseFolding.txt') do |data|
+    URI.parse('https://www.unicode.org/Public/UCD/latest/ucd/CaseFolding.txt').open do |data|
       File.open('CaseFolding.txt', 'w') do |file|
         data.each_line do |line|
           file.write(line)

src/folding/mapping/lookup.rs

@@ -3,12 +3,12 @@
 // This source is autogenerated. Do not modify it directly.
 // To make modfications to this code, see `scripts/gen_case_lookups.rb`.
 //
-// Last generated on 2021-05-17 14:24:38 UTC.
+// Last generated on 2021-11-15 18:32:20 UTC.
 //
 // Unicode version:
-// CaseFolding-13.0.0.txt
-// Date: 2019-09-08, 23:30:59 GMT
-// © 2019 Unicode®, Inc.
+// CaseFolding-14.0.0.txt
+// Date: 2021-03-08, 19:35:41 GMT
+// © 2021 Unicode®, Inc.
 
 use super::{Mapping, Mode};
 
@@ -593,7 +593,7 @@ pub const fn lookup(c: char, mode: Mode) -> Mapping {
             _ => Mapping::Single(codepoint),
         },
         (0x0000, 0x2C) => match c {
-            '\u{2C00}'..='\u{2C2E}' => Mapping::Single(codepoint.wrapping_add(0x0030)),
+            '\u{2C00}'..='\u{2C2F}' => Mapping::Single(codepoint.wrapping_add(0x0030)),
             '\u{2C60}' => Mapping::Single(0x2C61),
             '\u{2C62}' => Mapping::Single(0x026B),
             '\u{2C63}' => Mapping::Single(0x1D7D),
@@ -779,12 +779,16 @@ pub const fn lookup(c: char, mode: Mode) -> Mapping {
             '\u{A7BA}' => Mapping::Single(0xA7BB),
             '\u{A7BC}' => Mapping::Single(0xA7BD),
             '\u{A7BE}' => Mapping::Single(0xA7BF),
+            '\u{A7C0}' => Mapping::Single(0xA7C1),
             '\u{A7C2}' => Mapping::Single(0xA7C3),
             '\u{A7C4}' => Mapping::Single(0xA794),
             '\u{A7C5}' => Mapping::Single(0x0282),
             '\u{A7C6}' => Mapping::Single(0x1D8E),
             '\u{A7C7}' => Mapping::Single(0xA7C8),
             '\u{A7C9}' => Mapping::Single(0xA7CA),
+            '\u{A7D0}' => Mapping::Single(0xA7D1),
+            '\u{A7D6}' => Mapping::Single(0xA7D7),
+            '\u{A7D8}' => Mapping::Single(0xA7D9),
             '\u{A7F5}' => Mapping::Single(0xA7F6),
             _ => Mapping::Single(codepoint),
         },
@@ -816,6 +820,13 @@ pub const fn lookup(c: char, mode: Mode) -> Mapping {
             '\u{104B0}'..='\u{104D3}' => Mapping::Single(codepoint.wrapping_add(0x0028)),
             _ => Mapping::Single(codepoint),
         },
+        (0x0001, 0x05) => match c {
+            '\u{10570}'..='\u{1057A}' => Mapping::Single(codepoint.wrapping_add(0x0027)),
+            '\u{1057C}'..='\u{1058A}' => Mapping::Single(codepoint.wrapping_add(0x0027)),
+            '\u{1058C}'..='\u{10592}' => Mapping::Single(codepoint.wrapping_add(0x0027)),
+            '\u{10594}'..='\u{10595}' => Mapping::Single(codepoint.wrapping_add(0x0027)),
+            _ => Mapping::Single(codepoint),
+        },
         (0x0001, 0x0C) => match c {
             '\u{10C80}'..='\u{10CB2}' => Mapping::Single(codepoint.wrapping_add(0x0040)),
             _ => Mapping::Single(codepoint),

src/lib.rs

@@ -88,14 +88,23 @@
 //! - **std** - Enable linking to the [Rust Standard Library]. Enabling this
 //!   feature adds [`Error`] implementations to error types in this crate.
 //!
+//! # Unicode Version
+//!
+//! Focaccia implements Unicode case folding with the Unicode 14.0.0 case folding
+//! ruleset.
+//!
+//! Each new release of Unicode may bring updates to the `CaseFolding.txt` which is
+//! the source for the folding mappings in this crate. Updates to the case folding
+//! rules will be accompanied with a minor version bump.
+//!
 //! [Unicode case folding]: https://www.w3.org/International/wiki/Case_folding
 //! [`Ordering`]: core::cmp::Ordering
 //! [dotted and dotless I]: https://en.wikipedia.org/wiki/Dotted_and_dotless_I
 //! [Rust Standard Library]: https://doc.rust-lang.org/stable/std/index.html
 //! [`Error`]: https://doc.rust-lang.org/stable/std/error/trait.Error.html
 
 #![no_std]
-#![doc(html_root_url = "https://docs.rs/focaccia/1.0.2")]
+#![doc(html_root_url = "https://docs.rs/focaccia/1.1.0")]
 
 // Ensure code blocks in README.md compile
 #[cfg(doctest)]

tests/integration/full_fold_exhaustive.rs

@@ -3,12 +3,12 @@
 // This source is autogenerated. Do not modify it directly.
 // To make modfications to this code, see `scripts/gen_case_lookups.rb`.
 //
-// Last generated on 2021-05-17 14:24:38 UTC.
+// Last generated on 2021-11-15 18:32:20 UTC.
 //
 // Unicode version:
-// CaseFolding-13.0.0.txt
-// Date: 2019-09-08, 23:30:59 GMT
-// © 2019 Unicode®, Inc.
+// CaseFolding-14.0.0.txt
+// Date: 2021-03-08, 19:35:41 GMT
+// © 2021 Unicode®, Inc.
 
 use core::cmp::Ordering;
 use focaccia::{unicode_full_case_eq, unicode_full_casecmp};
@@ -977,6 +977,7 @@ fn lookup_naive(c: char, buf: &mut [u8; 4]) -> &str {
         '\u{2C2C}' => "\u{2C5C}",
         '\u{2C2D}' => "\u{2C5D}",
         '\u{2C2E}' => "\u{2C5E}",
+        '\u{2C2F}' => "\u{2C5F}",
         '\u{2C60}' => "\u{2C61}",
         '\u{2C62}' => "\u{026B}",
         '\u{2C63}' => "\u{1D7D}",
@@ -1157,12 +1158,16 @@ fn lookup_naive(c: char, buf: &mut [u8; 4]) -> &str {
         '\u{A7BA}' => "\u{A7BB}",
         '\u{A7BC}' => "\u{A7BD}",
         '\u{A7BE}' => "\u{A7BF}",
+        '\u{A7C0}' => "\u{A7C1}",
         '\u{A7C2}' => "\u{A7C3}",
         '\u{A7C4}' => "\u{A794}",
         '\u{A7C5}' => "\u{0282}",
         '\u{A7C6}' => "\u{1D8E}",
         '\u{A7C7}' => "\u{A7C8}",
         '\u{A7C9}' => "\u{A7CA}",
+        '\u{A7D0}' => "\u{A7D1}",
+        '\u{A7D6}' => "\u{A7D7}",
+        '\u{A7D8}' => "\u{A7D9}",
         '\u{A7F5}' => "\u{A7F6}",
         '\u{AB70}' => "\u{13A0}",
         '\u{AB71}' => "\u{13A1}",
@@ -1358,6 +1363,41 @@ fn lookup_naive(c: char, buf: &mut [u8; 4]) -> &str {
         '\u{104D1}' => "\u{104F9}",
         '\u{104D2}' => "\u{104FA}",
         '\u{104D3}' => "\u{104FB}",
+        '\u{10570}' => "\u{10597}",
+        '\u{10571}' => "\u{10598}",
+        '\u{10572}' => "\u{10599}",
+        '\u{10573}' => "\u{1059A}",
+        '\u{10574}' => "\u{1059B}",
+        '\u{10575}' => "\u{1059C}",
+        '\u{10576}' => "\u{1059D}",
+        '\u{10577}' => "\u{1059E}",
+        '\u{10578}' => "\u{1059F}",
+        '\u{10579}' => "\u{105A0}",
+        '\u{1057A}' => "\u{105A1}",
+        '\u{1057C}' => "\u{105A3}",
+        '\u{1057D}' => "\u{105A4}",
+        '\u{1057E}' => "\u{105A5}",
+        '\u{1057F}' => "\u{105A6}",
+        '\u{10580}' => "\u{105A7}",
+        '\u{10581}' => "\u{105A8}",
+        '\u{10582}' => "\u{105A9}",
+        '\u{10583}' => "\u{105AA}",
+        '\u{10584}' => "\u{105AB}",
+        '\u{10585}' => "\u{105AC}",
+        '\u{10586}' => "\u{105AD}",
+        '\u{10587}' => "\u{105AE}",
+        '\u{10588}' => "\u{105AF}",
+        '\u{10589}' => "\u{105B0}",
+        '\u{1058A}' => "\u{105B1}",
+        '\u{1058C}' => "\u{105B3}",
+        '\u{1058D}' => "\u{105B4}",
+        '\u{1058E}' => "\u{105B5}",
+        '\u{1058F}' => "\u{105B6}",
+        '\u{10590}' => "\u{105B7}",
+        '\u{10591}' => "\u{105B8}",
+        '\u{10592}' => "\u{105B9}",
+        '\u{10594}' => "\u{105BB}",
+        '\u{10595}' => "\u{105BC}",
         '\u{10C80}' => "\u{10CC0}",
         '\u{10C81}' => "\u{10CC1}",
         '\u{10C82}' => "\u{10CC2}",

tests/integration/full_turkic_fold_exhaustive.rs

@@ -3,12 +3,12 @@
 // This source is autogenerated. Do not modify it directly.
 // To make modfications to this code, see `scripts/gen_case_lookups.rb`.
 //
-// Last generated on 2021-05-17 14:24:38 UTC.
+// Last generated on 2021-11-15 18:32:20 UTC.
 //
 // Unicode version:
-// CaseFolding-13.0.0.txt
-// Date: 2019-09-08, 23:30:59 GMT
-// © 2019 Unicode®, Inc.
+// CaseFolding-14.0.0.txt
+// Date: 2021-03-08, 19:35:41 GMT
+// © 2021 Unicode®, Inc.
 
 use core::cmp::Ordering;
 use focaccia::{unicode_full_turkic_case_eq, unicode_full_turkic_casecmp};
@@ -977,6 +977,7 @@ fn lookup_naive(c: char, buf: &mut [u8; 4]) -> &str {
         '\u{2C2C}' => "\u{2C5C}",
         '\u{2C2D}' => "\u{2C5D}",
         '\u{2C2E}' => "\u{2C5E}",
+        '\u{2C2F}' => "\u{2C5F}",
         '\u{2C60}' => "\u{2C61}",
         '\u{2C62}' => "\u{026B}",
         '\u{2C63}' => "\u{1D7D}",
@@ -1157,12 +1158,16 @@ fn lookup_naive(c: char, buf: &mut [u8; 4]) -> &str {
         '\u{A7BA}' => "\u{A7BB}",
         '\u{A7BC}' => "\u{A7BD}",
         '\u{A7BE}' => "\u{A7BF}",
+        '\u{A7C0}' => "\u{A7C1}",
         '\u{A7C2}' => "\u{A7C3}",
         '\u{A7C4}' => "\u{A794}",
         '\u{A7C5}' => "\u{0282}",
         '\u{A7C6}' => "\u{1D8E}",
         '\u{A7C7}' => "\u{A7C8}",
         '\u{A7C9}' => "\u{A7CA}",
+        '\u{A7D0}' => "\u{A7D1}",
+        '\u{A7D6}' => "\u{A7D7}",
+        '\u{A7D8}' => "\u{A7D9}",
         '\u{A7F5}' => "\u{A7F6}",
         '\u{AB70}' => "\u{13A0}",
         '\u{AB71}' => "\u{13A1}",
@@ -1358,6 +1363,41 @@ fn lookup_naive(c: char, buf: &mut [u8; 4]) -> &str {
         '\u{104D1}' => "\u{104F9}",
         '\u{104D2}' => "\u{104FA}",
         '\u{104D3}' => "\u{104FB}",
+        '\u{10570}' => "\u{10597}",
+        '\u{10571}' => "\u{10598}",
+        '\u{10572}' => "\u{10599}",
+        '\u{10573}' => "\u{1059A}",
+        '\u{10574}' => "\u{1059B}",
+        '\u{10575}' => "\u{1059C}",
+        '\u{10576}' => "\u{1059D}",
+        '\u{10577}' => "\u{1059E}",
+        '\u{10578}' => "\u{1059F}",
+        '\u{10579}' => "\u{105A0}",
+        '\u{1057A}' => "\u{105A1}",
+        '\u{1057C}' => "\u{105A3}",
+        '\u{1057D}' => "\u{105A4}",
+        '\u{1057E}' => "\u{105A5}",
+        '\u{1057F}' => "\u{105A6}",
+        '\u{10580}' => "\u{105A7}",
+        '\u{10581}' => "\u{105A8}",
+        '\u{10582}' => "\u{105A9}",
+        '\u{10583}' => "\u{105AA}",
+        '\u{10584}' => "\u{105AB}",
+        '\u{10585}' => "\u{105AC}",
+        '\u{10586}' => "\u{105AD}",
+        '\u{10587}' => "\u{105AE}",
+        '\u{10588}' => "\u{105AF}",
+        '\u{10589}' => "\u{105B0}",
+        '\u{1058A}' => "\u{105B1}",
+        '\u{1058C}' => "\u{105B3}",
+        '\u{1058D}' => "\u{105B4}",
+        '\u{1058E}' => "\u{105B5}",
+        '\u{1058F}' => "\u{105B6}",
+        '\u{10590}' => "\u{105B7}",
+        '\u{10591}' => "\u{105B8}",
+        '\u{10592}' => "\u{105B9}",
+        '\u{10594}' => "\u{105BB}",
+        '\u{10595}' => "\u{105BC}",
         '\u{10C80}' => "\u{10CC0}",
         '\u{10C81}' => "\u{10CC1}",
         '\u{10C82}' => "\u{10CC2}",