Make the Unicode database version used available

gen-wcwidth.py

@@ -45,6 +45,14 @@ def get_data(fname: str, folder: str = 'UCD') -> Iterable[str]:
             yield line
 
 
+def unicode_version():
+    for line in get_data("ReadMe.txt"):
+        m = re.search(r'Version\s+(\d+)\.(\d+)\.(\d+)', line)
+        if m is not None:
+            return int(m.group(1)), int(m.group(2)), int(m.group(3))
+    raise ValueError('Could not find Unicode Version')
+
+
 # Map of class names to set of codepoints in class
 class_maps: Dict[str, Set[int]] = {}
 all_symbols: Set[int] = set()
@@ -586,6 +594,11 @@ def gen_wcwidth() -> None:
         gop('\t}')
         p('\treturn true;\n}')
         gop('\n}')
+        uv = unicode_version()
+        p(f'#define UNICODE_MAJOR_VERSION {uv[0]}')
+        p(f'#define UNICODE_MINOR_VERSION {uv[1]}')
+        p(f'#define UNICODE_PATCH_VERSION {uv[2]}')
+        gop('var UnicodeDatabaseVersion [3]int = [3]int{' f'{uv[0]}, {uv[1]}, {uv[2]}' + '}')
     subprocess.check_call(['gofmt', '-w', '-s', gof.name])
 
 

kittens/unicode_input/names.h

@@ -1,4 +1,4 @@
-// unicode data, built from the unicode standard on: 2022-09-30
+// unicode data, built from the unicode standard on: 2022-11-17
 // see gen-wcwidth.py
 #pragma once
 #include "data-types.h"

kitty/data-types.c

@@ -221,6 +221,7 @@ static PyMethodDef module_methods[] = {
     {"get_docs_ref_map", (PyCFunction)get_docs_ref_map, METH_NOARGS, ""},
     {"getpeereid", (PyCFunction)py_getpeereid, METH_VARARGS, ""},
     {"wcswidth", (PyCFunction)wcswidth_std, METH_O, ""},
+    {"unicode_database_version", (PyCFunction)unicode_database_version, METH_NOARGS, ""},
     {"open_tty", open_tty, METH_VARARGS, ""},
     {"normal_tty", normal_tty, METH_VARARGS, ""},
     {"raw_tty", raw_tty, METH_VARARGS, ""},

kitty/emoji.h

@@ -1,4 +1,4 @@
-// unicode data, built from the unicode standard on: 2022-09-30
+// unicode data, built from the unicode standard on: 2022-11-17
 // see gen-wcwidth.py
 #pragma once
 #include "data-types.h"

kitty/fast_data_types.pyi

@@ -1492,3 +1492,4 @@ def set_clipboard_data_types(ct: int, mime_types: Tuple[str, ...]) -> None: ...
 def get_clipboard_mime(ct: int, mime: Optional[str], callback: Callable[[bytes], None]) -> None: ...
 def run_with_activation_token(func: Callable[[str], None]) -> None: ...
 def make_x11_window_a_dock_window(x11_window_id: int, strut: Tuple[int, int, int, int, int, int, int, int, int, int, int, int]) -> None: ...
+def unicode_database_version() -> Tuple[int, int, int]: ...

kitty/unicode-data.c

@@ -1,4 +1,4 @@
-// unicode data, built from the unicode standard on: 2022-09-30
+// unicode data, built from the unicode standard on: 2022-11-17
 // see gen-wcwidth.py
 #include "data-types.h"
 

kitty/wcswidth.c

@@ -142,3 +142,8 @@ wcswidth_std(PyObject UNUSED *self, PyObject *str) {
     }
     return PyLong_FromSize_t(ans);
 }
+
+PyObject*
+unicode_database_version(PyObject *self UNUSED, PyObject *args UNUSED) {
+    return Py_BuildValue("iii", UNICODE_MAJOR_VERSION, UNICODE_MINOR_VERSION, UNICODE_PATCH_VERSION);
+}

kitty/wcswidth.h

@@ -20,4 +20,5 @@ typedef struct {
 void initialize_wcs_state(WCSState *state);
 int wcswidth_step(WCSState *state, const char_type ch);
 PyObject * wcswidth_std(PyObject UNUSED *self, PyObject *str);
+PyObject * unicode_database_version(PyObject UNUSED *self, PyObject *str);
 size_t wcswidth_string(const char_type *s);

kitty/wcwidth-std.h

@@ -1,4 +1,4 @@
-// unicode data, built from the unicode standard on: 2022-09-30
+// unicode data, built from the unicode standard on: 2022-11-17
 // see gen-wcwidth.py
 #pragma once
 #include "data-types.h"
@@ -3250,5 +3250,8 @@ is_emoji_presentation_base(uint32_t code) {
 	}
 	return true;
 }
+#define UNICODE_MAJOR_VERSION 15
+#define UNICODE_MINOR_VERSION 0
+#define UNICODE_PATCH_VERSION 0
 
 END_ALLOW_CASE_RANGE

tools/wcswidth/std.go

@@ -3242,3 +3242,5 @@ func IsEmojiPresentationBase(code rune) bool {
 	}
 
 }
+
+var UnicodeDatabaseVersion [3]int = [3]int{15, 0, 0}