Commit

Author: StanFromIreland

Doc/library/unicodedata.rst

@@ -144,6 +144,32 @@ following functions:
       1
 
 
+.. function:: isidstart(chr, /)
+
+   Return ``True`` if the character has the ``XID_Start`` property, ``False``
+   otherwise. For example::
+
+      >>> unicodedata.isidstart('S')
+      True
+      >>> unicodedata.isidstart('0')
+      False
+
+   .. versionadded:: next
+
+
+.. function:: isidcontinue(chr, /)
+
+   Return ``True`` if the character has the ``XID_Continue`` property, ``False``
+   otherwise. For example::
+
+      >>> unicodedata.isidcontinue('S')
+      True
+      >>> unicodedata.isidcontinue(' ')
+      False
+
+   .. versionadded:: next
+
+
 .. function:: decomposition(chr)
 
    Returns the character decomposition mapping assigned to the character

Doc/whatsnew/3.15.rst

@@ -768,6 +768,10 @@ unicodedata
 
 * The Unicode database has been updated to Unicode 17.0.0.
 
+* Add :func:`unicodedata.isidstart` and :func:`unicodedata.isidcontinue`
+  functions.
+  (Contributed by Stan Ulbrych in :gh:`129117`.)
+
 
 wave
 ----

Include/cpython/unicodeobject.h

@@ -733,6 +733,14 @@ PyAPI_FUNC(int) _PyUnicode_IsAlpha(
     Py_UCS4 ch       /* Unicode character */
     );
 
+PyAPI_FUNC(int) _PyUnicode_IsXidStart(
+    Py_UCS4 ch       /* Unicode character */
+    );
+
+PyAPI_FUNC(int) _PyUnicode_IsXidContinue(
+    Py_UCS4 ch       /* Unicode character */
+    );
+
 // Helper array used by Py_UNICODE_ISSPACE().
 PyAPI_DATA(const unsigned char) _Py_ascii_whitespace[];
 

Lib/test/test_unicodedata.py

@@ -276,6 +276,33 @@ def test_east_asian_width_9_0_changes(self):
         self.assertEqual(self.db.ucd_3_2_0.east_asian_width('\u231a'), 'N')
         self.assertEqual(self.db.east_asian_width('\u231a'), 'W')
 
+    def test_isidstart(self):
+        self.assertTrue(self.db.isidstart('S'))
+        self.assertTrue(self.db.isidstart('\u0AD0'))  # GUJARATI OM
+        self.assertTrue(self.db.isidstart('\u0EC6'))  # LAO KO LA
+        self.assertTrue(self.db.isidstart('\u17DC'))  # KHMER SIGN AVAKRAHASANYA
+        self.assertTrue(self.db.isidstart('\uA015'))  # YI SYLLABLE WU
+        self.assertTrue(self.db.isidstart('\uFE7B'))  # ARABIC KASRA MEDIAL FORM
+
+        self.assertFalse(self.db.isidstart(' '))
+        self.assertRaises(TypeError, self.db.isidstart)
+        self.assertRaises(TypeError, self.db.isidstart, 'xx')
+
+    def test_isidcontinue(self):
+        self.assertTrue(self.db.isidcontinue('S'))
+        self.assertTrue(self.db.isidcontinue('_'))
+        self.assertTrue(self.db.isidcontinue('0'))
+        self.assertTrue(self.db.isidcontinue('\u00BA'))  # MASCULINE ORDINAL INDICATOR
+        self.assertTrue(self.db.isidcontinue('\u0640'))  # ARABIC TATWEEL
+        self.assertTrue(self.db.isidcontinue('\u0710'))  # SYRIAC LETTER ALAPH
+        self.assertTrue(self.db.isidcontinue('\u0B3E'))  # ORIYA VOWEL SIGN AA
+        self.assertTrue(self.db.isidcontinue('\u17D7'))  # KHMER SIGN LEK TOO
+
+        self.assertFalse(self.db.isidcontinue(' '))
+        self.assertFalse(self.db.isidstart('0'))
+        self.assertRaises(TypeError, self.db.isidcontinue)
+        self.assertRaises(TypeError, self.db.isidcontinue, 'xx')
+
 class UnicodeMiscTest(UnicodeDatabaseTest):
 
     @cpython_only

Misc/NEWS.d/next/Library/2025-10-17-20-42-38.gh-issue-129117.X9jr4p.rst

@@ -0,0 +1,2 @@
+:mod:`unicodedata`: Add :func:`~unicodedata.isidstart` and
+:func:`~unicodedata.isidcontinue` functions.

Modules/clinic/unicodedata.c.h

@@ -1525,6 +1525,62 @@ unicodedata_UCD_name_impl(PyObject *self, int chr, PyObject *default_value)
     return PyUnicode_FromString(name);
 }
 
+/*[clinic input]
+unicodedata.UCD.isidstart
+
+    self: self
+    chr: int(accept={str})
+    /
+
+Return True if the character has the XID_Start property, else False.
+
+[clinic start generated code]*/
+
+static PyObject *
+unicodedata_UCD_isidstart_impl(PyObject *self, int chr)
+/*[clinic end generated code: output=29fbeaf6491d9f85 input=b71b6b1b2db3c16d]*/
+{
+    Py_UCS4 c = (Py_UCS4)chr;
+
+    if (UCD_Check(self)) {
+        const change_record *old = get_old_record(self, c);
+        if (old->category_changed == 0) {
+            /* unassigned */
+            Py_RETURN_FALSE;
+        }
+    }
+
+    return PyBool_FromLong(_PyUnicode_IsXidStart(c));
+}
+
+/*[clinic input]
+unicodedata.UCD.isidcontinue
+
+    self: self
+    chr: int(accept={str})
+    /
+
+Return True if the character has the XID_Continue property, else False.
+
+[clinic start generated code]*/
+
+static PyObject *
+unicodedata_UCD_isidcontinue_impl(PyObject *self, int chr)
+/*[clinic end generated code: output=5ae694da0ee16534 input=01b4ccd399484e6b]*/
+{
+    Py_UCS4 c = (Py_UCS4)chr;
+
+    if (UCD_Check(self)) {
+        const change_record *old = get_old_record(self, c);
+        if (old->category_changed == 0) {
+            /* unassigned */
+            Py_RETURN_FALSE;
+        }
+    }
+
+    return PyBool_FromLong(_PyUnicode_IsXidContinue(c));
+}
+
 /*[clinic input]
 unicodedata.UCD.lookup
 
@@ -1590,6 +1646,8 @@ static PyMethodDef unicodedata_functions[] = {
     UNICODEDATA_UCD_EAST_ASIAN_WIDTH_METHODDEF
     UNICODEDATA_UCD_DECOMPOSITION_METHODDEF
     UNICODEDATA_UCD_NAME_METHODDEF
+    UNICODEDATA_UCD_ISIDSTART_METHODDEF
+    UNICODEDATA_UCD_ISIDCONTINUE_METHODDEF
     UNICODEDATA_UCD_LOOKUP_METHODDEF
     UNICODEDATA_UCD_IS_NORMALIZED_METHODDEF
     UNICODEDATA_UCD_NORMALIZE_METHODDEF