[Python-checkins] gh-94808: Cover `PyUnicode_Count` in CAPI (#96929)

[encukou]

https://github.com/python/cpython/commit/e63d7dae90d15957303688285daeebc2e931e04b
commit: e63d7dae90d15957303688285daeebc2e931e04b
branch: main
author: Nikita Sobolev <mail at sobolevn.me>
committer: encukou <encukou at gmail.com>
date: 2022-10-06T17:20:22+02:00
summary:

gh-94808: Cover `PyUnicode_Count` in CAPI (#96929)

files:
M Lib/test/test_unicode.py
M Modules/_testcapi/unicode.c

diff --git a/Lib/test/test_unicode.py b/Lib/test/test_unicode.py
index 63bccb72e046..30faaaf83bec 100644
--- a/Lib/test/test_unicode.py
+++ b/Lib/test/test_unicode.py
@@ -2945,6 +2945,44 @@ def test_asutf8andsize(self):
         self.assertEqual(unicode_asutf8andsize(nonbmp), (b'\xf4\x8f\xbf\xbf', 4))
         self.assertRaises(UnicodeEncodeError, unicode_asutf8andsize, 'a\ud800b\udfffc')
 
+    # Test PyUnicode_Count()
+    @support.cpython_only
+    @unittest.skipIf(_testcapi is None, 'need _testcapi module')
+    def test_count(self):
+        from _testcapi import unicode_count
+
+        st = 'abcabd'
+        self.assertEqual(unicode_count(st, 'a', 0, len(st)), 2)
+        self.assertEqual(unicode_count(st, 'ab', 0, len(st)), 2)
+        self.assertEqual(unicode_count(st, 'abc', 0, len(st)), 1)
+        self.assertEqual(unicode_count(st, 'а', 0, len(st)), 0)  # cyrillic "a"
+        # start < end
+        self.assertEqual(unicode_count(st, 'a', 3, len(st)), 1)
+        self.assertEqual(unicode_count(st, 'a', 4, len(st)), 0)
+        self.assertEqual(unicode_count(st, 'a', 0, sys.maxsize), 2)
+        # start >= end
+        self.assertEqual(unicode_count(st, 'abc', 0, 0), 0)
+        self.assertEqual(unicode_count(st, 'a', 3, 2), 0)
+        self.assertEqual(unicode_count(st, 'a', sys.maxsize, 5), 0)
+        # negative
+        self.assertEqual(unicode_count(st, 'ab', -len(st), -1), 2)
+        self.assertEqual(unicode_count(st, 'a', -len(st), -3), 1)
+        # wrong args
+        self.assertRaises(TypeError, unicode_count, 'a', 'a')
+        self.assertRaises(TypeError, unicode_count, 'a', 'a', 1)
+        self.assertRaises(TypeError, unicode_count, 1, 'a', 0, 1)
+        self.assertRaises(TypeError, unicode_count, 'a', 1, 0, 1)
+        # empty string
+        self.assertEqual(unicode_count('abc', '', 0, 3), 4)
+        self.assertEqual(unicode_count('abc', '', 1, 3), 3)
+        self.assertEqual(unicode_count('', '', 0, 1), 1)
+        self.assertEqual(unicode_count('', 'a', 0, 1), 0)
+        # different unicode kinds
+        for uni in "\xa1", "\u8000\u8080", "\ud800\udc02", "\U0001f100\U0001f1f1":
+            for ch in uni:
+                self.assertEqual(unicode_count(uni, ch, 0, len(uni)), 1)
+                self.assertEqual(unicode_count(st, ch, 0, len(st)), 0)
+
     # Test PyUnicode_FindChar()
     @support.cpython_only
     @unittest.skipIf(_testcapi is None, 'need _testcapi module')
diff --git a/Modules/_testcapi/unicode.c b/Modules/_testcapi/unicode.c
index d0f1e2abdc82..d5c4a9e5b95e 100644
--- a/Modules/_testcapi/unicode.c
+++ b/Modules/_testcapi/unicode.c
@@ -223,6 +223,26 @@ unicode_asutf8andsize(PyObject *self, PyObject *args)
     return Py_BuildValue("(Nn)", result, utf8_len);
 }
 
+static PyObject *
+unicode_count(PyObject *self, PyObject *args)
+{
+    PyObject *str;
+    PyObject *substr;
+    Py_ssize_t result;
+    Py_ssize_t start, end;
+
+    if (!PyArg_ParseTuple(args, "UUnn:unicode_count", &str, &substr,
+                          &start, &end)) {
+        return NULL;
+    }
+
+    result = PyUnicode_Count(str, substr, start, end);
+    if (result == -1)
+        return NULL;
+    else
+        return PyLong_FromSsize_t(result);
+}
+
 static PyObject *
 unicode_findchar(PyObject *self, PyObject *args)
 {
@@ -696,6 +716,7 @@ static PyMethodDef TestMethods[] = {
     {"unicode_asucs4",           unicode_asucs4,                 METH_VARARGS},
     {"unicode_asutf8",           unicode_asutf8,                 METH_VARARGS},
     {"unicode_asutf8andsize",    unicode_asutf8andsize,          METH_VARARGS},
+    {"unicode_count",            unicode_count,                  METH_VARARGS},
     {"unicode_findchar",         unicode_findchar,               METH_VARARGS},
     {"unicode_copycharacters",   unicode_copycharacters,         METH_VARARGS},
     {NULL},