add unicodedata.grapheme_cluster_break()

Author: Vermeille

Modules/clinic/unicodedata.c.h

@@ -255,6 +255,34 @@ unicodedata_UCD_east_asian_width(PyObject *self, PyObject *arg)
     return return_value;
 }
 
+PyDoc_STRVAR(unicodedata_UCD_grapheme_cluster_break__doc__,
+"grapheme_cluster_break($self, chr, /)\n"
+"--\n"
+"\n"
+"Returns the east asian width assigned to the character chr as string.");
+
+#define UNICODEDATA_UCD_GRAPHEME_CLUSTER_BREAK_METHODDEF    \
+    {"grapheme_cluster_break", (PyCFunction)unicodedata_UCD_grapheme_cluster_break, \
+        METH_O, unicodedata_UCD_grapheme_cluster_break__doc__},
+
+static PyObject *
+unicodedata_UCD_grapheme_cluster_break_impl(PyObject *self, int chr);
+
+static PyObject *
+unicodedata_UCD_grapheme_cluster_break(PyObject *self, PyObject *arg)
+{
+    PyObject *return_value = NULL;
+    int chr;
+
+    if (!PyArg_Parse(arg, "C:grapheme_cluster_break", &chr)) {
+        goto exit;
+    }
+    return_value = unicodedata_UCD_grapheme_cluster_break_impl(self, chr);
+
+exit:
+    return return_value;
+}
+
 PyDoc_STRVAR(unicodedata_UCD_decomposition__doc__,
 "decomposition($self, chr, /)\n"
 "--\n"

Modules/unicodedata.c

@@ -37,6 +37,7 @@ typedef struct {
     const unsigned char east_asian_width;       /* index into
                                                    _PyUnicode_EastAsianWidth */
     const unsigned char normalization_quick_check; /* see is_normalized() */
+    const unsigned char grapheme_cluster_break;
 } _PyUnicode_DatabaseRecord;
 
 typedef struct change_record {
@@ -382,6 +383,26 @@ unicodedata_UCD_east_asian_width_impl(PyObject *self, int chr)
     return PyUnicode_FromString(_PyUnicode_EastAsianWidthNames[index]);
 }
 
+/*[clinic input]
+unicodedata.UCD.grapheme_cluster_break
+
+    self: self
+    chr: int(accept={str})
+    /
+
+Returns the east asian width assigned to the character chr as string.
+[clinic start generated code]*/
+
+static PyObject *
+unicodedata_UCD_grapheme_cluster_break_impl(PyObject *self, int chr)
+/*[clinic end generated code: output=484e8537d9ee8197 input=c4854798aab026e0]*/
+{
+    int index;
+    Py_UCS4 c = (Py_UCS4)chr;
+    index = (int) _getrecord_ex(c)->grapheme_cluster_break;
+    return PyUnicode_FromString(_PyUnicode_GraphemeBreakProperty[index]);
+}
+
 /*[clinic input]
 unicodedata.UCD.decomposition
 
@@ -1264,6 +1285,7 @@ static PyMethodDef unicodedata_functions[] = {
     UNICODEDATA_UCD_COMBINING_METHODDEF
     UNICODEDATA_UCD_MIRRORED_METHODDEF
     UNICODEDATA_UCD_EAST_ASIAN_WIDTH_METHODDEF
+    UNICODEDATA_UCD_GRAPHEME_CLUSTER_BREAK_METHODDEF
     UNICODEDATA_UCD_DECOMPOSITION_METHODDEF
     UNICODEDATA_UCD_NAME_METHODDEF
     UNICODEDATA_UCD_LOOKUP_METHODDEF