8000 BUG: three string ufunc bugs, one leading to segfault by mhvk · Pull Request #25515 · numpy/numpy · GitHub
[go: up one dir, main page]
Skip to content

BUG: three string ufunc bugs, one leading to segfault #25515

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
merged 3 commits into from
Jan 2, 2024
Merged

BUG: three string ufunc bugs, one leading to segfault #25515

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
925471d
BUG: fix find of single-character with memchr
mhvk Dec 31, 2023
a9e50b5
BUG: solve core dump in chararray.replace
mhvk Jan 2, 2024
5b5b568
BUG: fix replacement with a string longer than input
mhvk Dec 31, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Next Next commit
BUG: fix find of single-character with memchr
  • Loading branch information
@mhvk
mhvk committed Jan 2, 2024
commit 925471d47f8f1ff7a972fd2335db8235c8e79334
14 changes: 8 additions & 6 deletions numpy/_core/src/umath/string_buffer.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -109,7 +109,7 @@ struct Buffer {
{
Buffer<enc> old = *this;
operator++();
return old;
return old;
}

inline Buffer<enc>&
Expand All @@ -124,7 +124,7 @@ struct Buffer {
{
Buffer<enc> old = *this;
operator--();
return old;
return old;
}

inline npy_ucs4
Expand All @@ -151,14 +151,16 @@ struct Buffer {
inline Buffer<enc>
buffer_memchr(npy_ucs4 ch, int len)
{
Buffer<enc> newbuf = *this;
switch (enc) {
case ENCODING::ASCII:
buf = (char *) memchr(buf, ch, len);
return *this;
newbuf.buf = (char *) memchr(buf, ch, len);
break;
case ENCODING::UTF32:
buf = (char *) wmemchr((wchar_t *) buf, ch, len);
return *this;
newbuf.buf = (char *) wmemchr((wchar_t *) buf, ch, len);
break;
}
return newbuf;
}

inline int
Expand Down
28 changes: 22 additions & 6 deletions numpy/_core/tests/test_defchararray.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -213,6 +213,10 @@ def setup_method(self):
['12345', 'MixedCase'],
['123 \t 345 \0 ', 'UPPER']]) \
.view(np.char.chararray)
# Array with longer strings, > MEMCHR_CUT_OFF in code.
self.C = (np.array(['ABCDEFGHIJKLMNOPQRSTUVWXYZ',
'01234567890123456789012345'])
.view(np.char.chararray))

def test_len(self):
assert_(issubclass(np.char.str_len(self.A).dtype.type, np.integer))
Expand Down Expand Up @@ -240,12 +244,24 @@ def fail():

assert_raises(TypeError, fail)

def test_find(self):
assert_(issubclass(self.A.find('a').dtype.type, np.integer))
assert_array_equal(self.A.find('a'), [[1, -1], [-1, 6], [-1, -1]])
assert_array_equal(self.A.find('3'), [[-1, -1], [2, -1], [2, -1]])
assert_array_equal(self.A.find('a', 0, 2), [[1, -1], [-1, -1], [-1, -1]])
assert_array_equal(self.A.find(['1', 'P']), [[-1, -1], [0, -1], [0, 1]])
@pytest.mark.parametrize(
"dtype, encode",
[("U", str),
("S", lambda x: x.encode('ascii')),
])
def test_find(self, dtype, encode):
A = self.A.astype(dtype)
assert_(issubclass(A.find(encode('a')).dtype.type, np.integer))
assert_array_equal(A.find(encode('a')),
[[1, -1], [-1, 6], [-1, -1]])
assert_array_equal(A.find(encode('3')),
[[-1, -1], [2, -1], [2, -1]])
assert_array_equal(A.find(encode('a'), 0, 2),
[[1, -1], [-1, -1], [-1, -1]])
assert_array_equal(A.find([encode('1'), encode('P')]),
[[-1, -1], [0, -1], [0, 1]])
C = self.C.astype(dtype)
assert_array_equal(C.find(encode('M')), [12, -1])

def test_index(self):

Expand Down
0