FazBrowse GitHub Viewer | Trending |
URL:
| Home
Tools: [Download Repo ZIP]   [Original HTTPS Page]

gh-94808: Cover `PyUnicode_Count` in CAPI by sobolevn · Pull Request #96929 · python/cpython · GitHub

/ cpython Public

gh-94808: Cover PyUnicode_Count in CAPI #96929

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
encukou merged 1 commit into from
Oct 6, 2022
+59 −0
Conversation 3 Commits 1 Checks 0 Files changed 2
Merged

gh-94808: Cover PyUnicode_Count in CAPI #96929

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension .c  (1) .py  (1) All 2 file types selected
Viewed files
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Unified
Split
Hide whitespace
Diff view
Unified
Split
Hide whitespace
38 changes: 38 additions & 0 deletions Lib/test/test_unicode.py
Show comments
View file
Open in desktop
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
Show hidden characters
Original file line number Diff line number Diff line change
Expand Up @@ -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')
Expand Down
21 changes: 21 additions & 0 deletions Modules/_testcapi/unicode.c
Show comments
View file
Open in desktop
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
Show hidden characters
Original file line number Diff line number Diff line change
Expand Up @@ -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)
{
Expand Down Expand Up @@ -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},
Expand Down
Back | FazBrowse Home | New Git URL