Add support for Unicode 15 (#128)

Cargo.toml

@@ -38,7 +38,7 @@ itertools = "0.11.0"
 lazy_static = "1.4.0"
 ndarray = "0.15.6"
 petgraph = {version = "0.6.3", default-features = false, features = ["stable_graph"]}
-regex = "1.7.0"
+regex = "1.9.1"
 unic-char-range = "0.9.0"
 unic-ucd-category = "0.9.0"
 unicode-segmentation = "1.10.1"
@@ -48,13 +48,13 @@ wasm-bindgen = "0.2.87"
 
 [dev-dependencies]
 indoc = "2.0.3"
-rstest = "0.16.0"
+rstest = "0.18.1"
 
 [target.'cfg(not(target_family = "wasm"))'.dev-dependencies]
 assert_cmd = "2.0.12"
 criterion = "0.5.1"
 predicates = "3.0.3"
-proptest = "1.0.0"
+proptest = "1.2.0"
 tempfile = "3.7.0"
 
 [target.'cfg(target_family = "wasm")'.dev-dependencies]

src/unicode_tables/decimal.rs

@@ -16,11 +16,11 @@
 
 // DO NOT EDIT THIS FILE. IT WAS AUTOMATICALLY GENERATED BY:
 //
-//   ucd-generate general-category ucd-14.0.0 --chars --include decimalnumber
+//   ucd-generate general-category ucd-15.0.0 --chars --include decimalnumber
 //
-// Unicode version: 14.0.0.
+// Unicode version: 15.0.0.
 //
-// ucd-generate 0.2.10 is available on crates.io.
+// ucd-generate 0.3.0 is available on crates.io.
 
 pub const DECIMAL_NUMBER: &[(char, char)] = &[
     ('0', '9'),
@@ -77,12 +77,14 @@ pub const DECIMAL_NUMBER: &[(char, char)] = &[
     ('𑱐', '𑱙'),
     ('𑵐', '𑵙'),
     ('𑶠', '𑶩'),
+    ('𑽐', '𑽙'),
     ('𖩠', '𖩩'),
     ('𖫀', '𖫉'),
     ('𖭐', '𖭙'),
     ('𝟎', '𝟿'),
     ('𞅀', '𞅉'),
     ('𞋰', '𞋹'),
+    ('𞓰', '𞓹'),
     ('𞥐', '𞥙'),
     ('🯰', '🯹'),
 ];

src/unicode_tables/space.rs

@@ -16,11 +16,11 @@
 
 // DO NOT EDIT THIS FILE. IT WAS AUTOMATICALLY GENERATED BY:
 //
-//   ucd-generate property-bool ucd-14.0.0 --chars --include whitespace
+//   ucd-generate property-bool ucd-15.0.0 --chars --include whitespace
 //
-// Unicode version: 14.0.0.
+// Unicode version: 15.0.0.
 //
-// ucd-generate 0.2.10 is available on crates.io.
+// ucd-generate 0.3.0 is available on crates.io.
 
 pub const WHITE_SPACE: &[(char, char)] = &[
     ('\t', '\r'),

src/unicode_tables/word.rs

@@ -16,11 +16,11 @@
 
 // DO NOT EDIT THIS FILE. IT WAS AUTOMATICALLY GENERATED BY:
 //
-//   ucd-generate perl-word ucd-14.0.0 --chars
+//   ucd-generate perl-word ucd-15.0.0 --chars
 //
-// Unicode version: 14.0.0.
+// Unicode version: 15.0.0.
 //
-// ucd-generate 0.2.10 is available on crates.io.
+// ucd-generate 0.3.0 is available on crates.io.
 
 pub const WORD: &[(char, char)] = &[
     ('0', '9'),
@@ -180,7 +180,7 @@ pub const WORD: &[(char, char)] = &[
     ('ೝ', 'ೞ'),
     ('ೠ', '\u{ce3}'),
     ('೦', '೯'),
-    ('ೱ', 'ೲ'),
+    ('ೱ', 'ೳ'),
     ('\u{d00}', 'ഌ'),
     ('എ', 'ഐ'),
     ('ഒ', '\u{d44}'),
@@ -213,7 +213,7 @@ pub const WORD: &[(char, char)] = &[
     ('ວ', 'ຽ'),
     ('ເ', 'ໄ'),
     ('ໆ', 'ໆ'),
-    ('\u{ec8}', '\u{ecd}'),
+    ('\u{ec8}', '\u{ece}'),
     ('໐', '໙'),
     ('ໜ', 'ໟ'),
     ('ༀ', 'ༀ'),
@@ -527,7 +527,7 @@ pub const WORD: &[(char, char)] = &[
     ('𐺀', '𐺩'),
     ('\u{10eab}', '\u{10eac}'),
     ('𐺰', '𐺱'),
-    ('𐼀', '𐼜'),
+    ('\u{10efd}', '𐼜'),
     ('𐼧', '𐼧'),
     ('𐼰', '\u{10f50}'),
     ('𐽰', '\u{10f85}'),
@@ -550,7 +550,7 @@ pub const WORD: &[(char, char)] = &[
     ('𑇜', '𑇜'),
     ('𑈀', '𑈑'),
     ('𑈓', '\u{11237}'),
-    ('\u{1123e}', '\u{1123e}'),
+    ('\u{1123e}', '\u{11241}'),
     ('𑊀', '𑊆'),
     ('𑊈', '𑊈'),
     ('𑊊', '𑊍'),
@@ -631,12 +631,17 @@ pub const WORD: &[(char, char)] = &[
     ('𑶓', '𑶘'),
     ('𑶠', '𑶩'),
     ('𑻠', '𑻶'),
+    ('\u{11f00}', '𑼐'),
+    ('𑼒', '\u{11f3a}'),
+    ('𑼾', '\u{11f42}'),
+    ('𑽐', '𑽙'),
     ('𑾰', '𑾰'),
     ('𒀀', '𒎙'),
     ('𒐀', '𒑮'),
     ('𒒀', '𒕃'),
     ('𒾐', '𒿰'),
-    ('𓀀', '𓐮'),
+    ('𓀀', '𓐯'),
+    ('\u{13440}', '\u{13455}'),
     ('𔐀', '𔙆'),
     ('𖠀', '𖨸'),
     ('𖩀', '𖩞'),
@@ -664,7 +669,9 @@ pub const WORD: &[(char, char)] = &[
     ('𚿵', '𚿻'),
     ('𚿽', '𚿾'),
     ('𛀀', '𛄢'),
+    ('𛄲', '𛄲'),
     ('𛅐', '𛅒'),
+    ('𛅕', '𛅕'),
     ('𛅤', '𛅧'),
     ('𛅰', '𛋻'),
     ('𛰀', '𛱪'),
@@ -718,17 +725,21 @@ pub const WORD: &[(char, char)] = &[
     ('\u{1da9b}', '\u{1da9f}'),
     ('\u{1daa1}', '\u{1daaf}'),
     ('𝼀', '𝼞'),
+    ('𝼥', '𝼪'),
     ('\u{1e000}', '\u{1e006}'),
     ('\u{1e008}', '\u{1e018}'),
     ('\u{1e01b}', '\u{1e021}'),
     ('\u{1e023}', '\u{1e024}'),
     ('\u{1e026}', '\u{1e02a}'),
+    ('𞀰', '𞁭'),
+    ('\u{1e08f}', '\u{1e08f}'),
     ('𞄀', '𞄬'),
     ('\u{1e130}', '𞄽'),
     ('𞅀', '𞅉'),
     ('𞅎', '𞅎'),
     ('𞊐', '\u{1e2ae}'),
     ('𞋀', '𞋹'),
+    ('𞓐', '𞓹'),
     ('𞟠', '𞟦'),
     ('𞟨', '𞟫'),
     ('𞟭', '𞟮'),
@@ -775,11 +786,12 @@ pub const WORD: &[(char, char)] = &[
     ('🅰', '🆉'),
     ('🯰', '🯹'),
     ('𠀀', '𪛟'),
-    ('𪜀', '𫜸'),
+    ('𪜀', '𫜹'),
     ('𫝀', '𫠝'),
     ('𫠠', '𬺡'),
     ('𬺰', '𮯠'),
     ('丽', '𪘀'),
     ('𰀀', '𱍊'),
+    ('𱍐', '𲎯'),
     ('\u{e0100}', '\u{e01ef}'),
 ];