diff -r 18ed518d2eef Lib/test/test_unicode.py --- a/Lib/test/test_unicode.py Tue Nov 29 09:56:07 2016 +0200 +++ b/Lib/test/test_unicode.py Tue Nov 29 23:46:20 2016 +0800 @@ -2728,6 +2728,29 @@ self.assertEqual(unicode_asucs4(s, len(s), 1), s+'\0') self.assertEqual(unicode_asucs4(s, len(s), 0), s+'\uffff') + # Test PyUnicode_FindChar() + @support.cpython_only + def test_findchar(self): + from _testcapi import unicode_findchar + + for str in "\xa1", "\u8000\u8080", "\ud800\udc02", "\U0001f100\U0001f1f1": + for i, ch in enumerate(str): + self.assertEqual(unicode_findchar(str, ord(ch), 0, len(str), 1), i) + self.assertEqual(unicode_findchar(str, ord(ch), 0, len(str), -1), i) + + str = "!>_= end + self.assertEqual(unicode_findchar(str, ord('!'), 0, 0, 1), -1) + self.assertEqual(unicode_findchar(str, ord('!'), len(str), 0, 1), -1) + # negative + self.assertEqual(unicode_findchar(str, ord('!'), -len(str), -1, 1), 0) + self.assertEqual(unicode_findchar(str, ord('!'), -len(str), -1, -1), 0) + # Test PyUnicode_CopyCharacters() @support.cpython_only def test_copycharacters(self): diff -r 18ed518d2eef Modules/_testcapimodule.c --- a/Modules/_testcapimodule.c Tue Nov 29 09:56:07 2016 +0200 +++ b/Modules/_testcapimodule.c Tue Nov 29 23:46:20 2016 +0800 @@ -1875,6 +1875,27 @@ } static PyObject * +unicode_findchar(PyObject *self, PyObject *args) +{ + PyObject *str; + int direction; + unsigned int ch; + Py_ssize_t result; + Py_ssize_t start, end; + + if (!PyArg_ParseTuple(args, "UInni:unicode_findchar", &str, &ch, + &start, &end, &direction)) { + return NULL; + } + + result = PyUnicode_FindChar(str, (Py_UCS4)ch, start, end, direction); + if (result == -2) + return NULL; + else + return PyLong_FromSsize_t(result); +} + +static PyObject * unicode_copycharacters(PyObject *self, PyObject *args) { PyObject *from, *to, *to_copy; @@ -4107,6 +4128,7 @@ {"unicode_aswidechar", unicode_aswidechar, METH_VARARGS}, {"unicode_aswidecharstring",unicode_aswidecharstring, METH_VARARGS}, {"unicode_asucs4", unicode_asucs4, METH_VARARGS}, + {"unicode_findchar", unicode_findchar, METH_VARARGS}, {"unicode_copycharacters", unicode_copycharacters, METH_VARARGS}, {"unicode_encodedecimal", unicode_encodedecimal, METH_VARARGS}, {"unicode_transformdecimaltoascii", unicode_transformdecimaltoascii, METH_VARARGS}, diff -r 18ed518d2eef Objects/unicodeobject.c --- a/Objects/unicodeobject.c Tue Nov 29 09:56:07 2016 +0200 +++ b/Objects/unicodeobject.c Tue Nov 29 23:46:20 2016 +0800 @@ -9461,16 +9461,12 @@ int direction) { int kind; - Py_ssize_t result; + Py_ssize_t len, result; if (PyUnicode_READY(str) == -1) return -2; - if (start < 0 || end < 0) { - PyErr_SetString(PyExc_IndexError, "string index out of range"); - return -2; - } - if (end > PyUnicode_GET_LENGTH(str)) - end = PyUnicode_GET_LENGTH(str); - if (start >= end) + len = PyUnicode_GET_LENGTH(str); + ADJUST_INDICES(start, end, len); + if (end - start < 1) return -1; kind = PyUnicode_KIND(str); result = findchar(PyUnicode_1BYTE_DATA(str) + kind*start,