Add tests

Author: lysnikolaou

Lib/test/test_capi/test_unicode.py

@@ -1753,6 +1753,55 @@ def test_GET_CACHED_HASH(self):
         # impl detail: ASCII string hashes are equal to bytes ones
         self.assertEqual(unicode_GET_CACHED_HASH(obj), hash(content_bytes))
 
+    @support.cpython_only
+    @unittest.skipIf(_testcapi is None, 'need _testcapi module')
+    def test_tolower(self):
+        import string
+        from _testcapi import unicode_tolower
+
+        for i, c in enumerate(string.ascii_uppercase):
+            with self.subTest(c):
+                self.assertEqual(unicode_tolower(c), string.ascii_lowercase[i])
+
+        # Test unicode character
+        self.assertEqual(unicode_tolower("Č"), "č")
+
+    @support.cpython_only
+    @unittest.skipIf(_testcapi is None, 'need _testcapi module')
+    def test_toupper(self):
+        import string
+        from _testcapi import unicode_toupper
+
+        for i, c in enumerate(string.ascii_lowercase):
+            with self.subTest(c):
+                self.assertEqual(unicode_toupper(c), string.ascii_uppercase[i])
+
+        # Test unicode character
+        self.assertEqual(unicode_toupper("č"), "Č")
+
+    @support.cpython_only
+    @unittest.skipIf(_testcapi is None, 'need _testcapi module')
+    def test_totitle(self):
+        from _testcapi import unicode_totitle
+
+        self.assertEqual(unicode_totitle("t"), "T")
+
+        # Test unicode character
+        self.assertEqual(unicode_totitle("ł"), "Ł")
+
+    @support.cpython_only
+    @unittest.skipIf(_testcapi is None, 'need _testcapi module')
+    def test_tofolded(self):
+        from _testcapi import unicode_tofolded
+
+        self.assertEqual(unicode_tofolded("T"), "t")
+
+        # Test unicode character
+        self.assertEqual(unicode_tofolded("Ł"), "ł")
+
+        # Test case-ignorable character
+        self.assertEqual(unicode_tofolded("👍"), "👍")
+
 
 class PyUnicodeWriterTest(unittest.TestCase):
     def create_writer(self, size):

Modules/_testcapi/unicode.c

@@ -220,6 +220,112 @@ unicode_copycharacters(PyObject *self, PyObject *args)
     return Py_BuildValue("(Nn)", to_copy, copied);
 }
 
+/* Test PyUnicode_ToLower() */
+static PyObject *
+unicode_tolower(PyObject *self, PyObject *arg)
+{
+    if (PyUnicode_GET_LENGTH(arg) != 1) {
+        PyErr_SetString(PyExc_ValueError, "unicode_tolower only accepts 1-character strings");
+        return NULL;
+    }
+
+    Py_UCS4 c = PyUnicode_READ_CHAR(arg, 0);
+
+    Py_UCS4 lower[3];
+    int chars = PyUnicode_ToLower(c, lower, Py_ARRAY_LENGTH(lower));
+    assert(chars >= 1);
+
+    PyUnicodeWriter *writer = PyUnicodeWriter_Create(1);
+    if (writer == NULL) {
+        return NULL;
+    }
+    if (PyUnicodeWriter_WriteUCS4(writer, lower, chars) < 0) {
+        PyUnicodeWriter_Discard(writer);
+        return NULL;
+    }
+    return PyUnicodeWriter_Finish(writer);
+}
+
+/* Test PyUnicode_ToUpper() */
+static PyObject *
+unicode_toupper(PyObject *self, PyObject *arg)
+{
+    if (PyUnicode_GET_LENGTH(arg) != 1) {
+        PyErr_SetString(PyExc_ValueError, "unicode_toupper only accepts 1-character strings");
+        return NULL;
+    }
+
+    Py_UCS4 c = PyUnicode_READ_CHAR(arg, 0);
+
+    Py_UCS4 upper[3];
+    int chars = PyUnicode_ToUpper(c, upper, Py_ARRAY_LENGTH(upper));
+    assert(chars >= 1);
+
+    PyUnicodeWriter *writer = PyUnicodeWriter_Create(1);
+    if (writer == NULL) {
+        return NULL;
+    }
+    if (PyUnicodeWriter_WriteUCS4(writer, upper, chars) < 0) {
+        PyUnicodeWriter_Discard(writer);
+        return NULL;
+    }
+    return PyUnicodeWriter_Finish(writer);
+}
+
+
+/* Test PyUnicode_ToLower() */
+static PyObject *
+unicode_totitle(PyObject *self, PyObject *arg)
+{
+    if (PyUnicode_GET_LENGTH(arg) != 1) {
+        PyErr_SetString(PyExc_ValueError, "unicode_totitle only accepts 1-character strings");
+        return NULL;
+    }
+
+    Py_UCS4 c = PyUnicode_READ_CHAR(arg, 0);
+
+    Py_UCS4 title[3];
+    int chars = PyUnicode_ToTitle(c, title, Py_ARRAY_LENGTH(title));
+    assert(chars >= 1);
+
+    PyUnicodeWriter *writer = PyUnicodeWriter_Create(1);
+    if (writer == NULL) {
+        return NULL;
+    }
+    if (PyUnicodeWriter_WriteUCS4(writer, title, chars) < 0) {
+        PyUnicodeWriter_Discard(writer);
+        return NULL;
+    }
+    return PyUnicodeWriter_Finish(writer);
+}
+
+/* Test PyUnicode_ToLower() */
+static PyObject *
+unicode_tofolded(PyObject *self, PyObject *arg)
+{
+    if (PyUnicode_GET_LENGTH(arg) != 1) {
+        PyErr_SetString(PyExc_ValueError, "unicode_tofolded only accepts 1-character strings");
+        return NULL;
+    }
+
+    Py_UCS4 c = PyUnicode_READ_CHAR(arg, 0);
+
+    Py_UCS4 folded[3];
+    int chars = PyUnicode_ToFolded(c, folded, Py_ARRAY_LENGTH(folded));
+    assert(chars >= 1);
+
+    PyUnicodeWriter *writer = PyUnicodeWriter_Create(1);
+    if (writer == NULL) {
+        return NULL;
+    }
+    if (PyUnicodeWriter_WriteUCS4(writer, folded, chars) < 0) {
+        PyUnicodeWriter_Discard(writer);
+        return NULL;
+    }
+    return PyUnicodeWriter_Finish(writer);
+}
+
+
 static PyObject*
 unicode_GET_CACHED_HASH(PyObject *self, PyObject *arg)
 {
@@ -577,6 +683,10 @@ static PyMethodDef TestMethods[] = {
     {"unicode_asutf8",           unicode_asutf8,                 METH_VARARGS},
     {"unicode_copycharacters",   unicode_copycharacters,         METH_VARARGS},
     {"unicode_GET_CACHED_HASH",  unicode_GET_CACHED_HASH,        METH_O},
+    {"unicode_tolower",          unicode_tolower,                METH_O},
+    {"unicode_toupper",          unicode_toupper,                METH_O},
+    {"unicode_totitle",          unicode_totitle,                METH_O},
+    {"unicode_tofolded",         unicode_tofolded,               METH_O},
     {NULL},
 };