...

docs/changelog.rst

@@ -115,11 +115,11 @@ Detailed list of changes
   line (:iss:`8464`)
 
 - Fix a regression in 0.40.1 that caused copying to clipboard via OSC 52 from
-  applications that dont specify a destination in the escape code not working
+  applications that don't specify a destination in the escape code not working
   (:iss:`8459`)
 
 - Wayland: Fix a regression in the previous release that caused crashes on
-  compositors that dont support the xdg-toplevel-icon protocol and the user has
+  compositors that don't support the xdg-toplevel-icon protocol and the user has
   set a custom kitty icon (:iss:`8471`)
 
 0.40.1 [2025-03-18]

kitty/char-props.h

@@ -9,6 +9,30 @@
 
 #include "data-types.h"
 
+// CharPropsDeclaration
+// Uses 23 bits
+typedef union CharProps {
+    struct {
+        uint8_t shifted_width : 3;
+        uint8_t is_extended_pictographic : 1;
+        uint8_t grapheme_break : 4;
+        uint8_t indic_conjunct_break : 2;
+        uint8_t category : 5;
+        uint8_t is_emoji : 1;
+        uint8_t is_emoji_presentation_base : 1;
+        uint8_t is_invalid : 1;
+        uint8_t is_non_rendered : 1;
+        uint8_t is_symbol : 1;
+        uint8_t is_combining_char : 1;
+        uint8_t is_word_char : 1;
+        uint8_t is_punctuation : 1;
+    };
+    uint32_t val;
+} CharProps;
+static_assert(sizeof(CharProps) == sizeof(uint32_t), "Fix the ordering of CharProps");
+// EndCharPropsDeclaration
+
+
 // UCBDeclaration
 typedef enum UnicodeCategory {
 	UC_Cn,
@@ -46,29 +70,6 @@ typedef enum UnicodeCategory {
 // EndUCBDeclaration
 
 
-// CharPropsDeclaration
-// Uses 23 bits
-typedef union CharProps {
-    struct {
-        uint8_t shifted_width : 3;
-        uint8_t is_extended_pictographic : 1;
-        uint8_t grapheme_break : 4;
-        uint8_t indic_conjunct_break : 2;
-        uint8_t category : 5;
-        uint8_t is_emoji : 1;
-        uint8_t is_emoji_presentation_base : 1;
-        uint8_t is_invalid : 1;
-        uint8_t is_non_rendered : 1;
-        uint8_t is_symbol : 1;
-        uint8_t is_combining_char : 1;
-        uint8_t is_word_char : 1;
-        uint8_t is_punctuation : 1;
-    };
-    uint32_t val;
-} CharProps;
-static_assert(sizeof(CharProps) == sizeof(uint32_t), "Fix the ordering of CharProps");
-// EndCharPropsDeclaration
-
 typedef struct GraphemeSegmentationState {
     int last_char_prop;
 

kitty/data-types.c

@@ -638,9 +638,9 @@ py_char_props_for(PyObject *self UNUSED, PyObject *ch) {
     char_type c = PyUnicode_READ_CHAR(ch, 0);
     CharProps cp = char_props_for(c);
 #define B(x) #x, cp.x ? Py_True : Py_False
-    return Py_BuildValue("{ si sO sB sB ss }",
+    return Py_BuildValue("{si sO sB sB ss sO sO}",
         "width", wcwidth_std(cp), B(is_extended_pictographic), "grapheme_break", cp.grapheme_break,
-        "indic_conjunct_break", cp.indic_conjunct_break, "category", char_category(cp)
+        "indic_conjunct_break", cp.indic_conjunct_break, "category", char_category(cp), B(is_emoji), B(is_emoji_presentation_base)
     );
 #undef B
 }

kitty_tests/datatypes.py

@@ -637,8 +637,8 @@ def test_shlex_split(self):
             self.ae(expected, actual, f'Failed for text: {q!r}')
 
     def test_split_into_graphemes(self):
+        self.assertEqual(char_props_for('\ue000')['category'], 'Co')
         for i, test in enumerate(json.loads(read_kitty_resource('GraphemeBreakTest.json', __name__.rpartition('.')[0]))):
             expected = test['data']
             actual = split_into_graphemes(''.join(expected))
             self.ae(expected, actual, f'Test #{i} failed: {test["comment"]}')
-        self.assertEqual(char_props_for('\ue000')['category'], 'Co')