feat: Support Unicode 17.0.0 (#157)

* feat: Support Unicode 17.0.0

* feat: Store right_significant_is_emoji state instead

* fix: Move check for right_significant_is_emoji above state machine

* doc: Add comments explaining connection to word boundary rules

Author: Martin005

scripts/unicode.py

@@ -54,7 +54,7 @@
 # these are the surrogate codepoints, which are not valid rust characters
 surrogate_codepoints = (0xd800, 0xdfff)
 
-UNICODE_VERSION = (16, 0, 0)
+UNICODE_VERSION = (17, 0, 0)
 
 UNICODE_VERSION_NUMBER = "%s.%s.%s" %UNICODE_VERSION
 

src/grapheme.rs

@@ -800,13 +800,14 @@ impl GraphemeCursor {
                 self.cat_after = self.cat_before.take();
                 self.state = GraphemeState::Unknown;
                 if let Some(incb_linker_count) = self.incb_linker_count {
-                    self.ris_count = if incb_linker_count > 0 && crate::tables::is_incb_linker(ch) {
-                        Some(incb_linker_count - 1)
-                    } else if crate::tables::derived_property::InCB_Extend(ch) {
-                        Some(incb_linker_count)
-                    } else {
-                        None
-                    };
+                    self.incb_linker_count =
+                        if incb_linker_count > 0 && crate::tables::is_incb_linker(ch) {
+                            Some(incb_linker_count - 1)
+                        } else if crate::tables::derived_property::InCB_Extend(ch) {
+                            Some(incb_linker_count)
+                        } else {
+                            None
+                        };
                 }
                 if let Some(ris_count) = self.ris_count {
                     self.ris_count = if ris_count > 0 {