Skip to content

bpo-7940: add support for negative end positions to re.finditer and re.findall #14744

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

Open
anilbey wants to merge 5 commits into
base: main
Choose a base branch
from
+74 −0
Open

bpo-7940: add support for negative end positions to re.finditer and re.findall #14744

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
f47dad7
bpo7940: add support for negative end positions to re.finditer and re…
anilbey Jul 13, 2019
75e7c5f
bpo7940: added test cases adressing the review
anilbey Jul 13, 2019
530afdf
emit FutureWarning for negative start/end indices
anilbey Mar 14, 2023
8bc3fb8
test_bug_7940: assure warnings are effective via assertWarns
anilbey Mar 14, 2023
46349e5
Merge branch 'main' into bpo7940
anilbey Oct 15, 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
59 changes: 59 additions & 0 deletions Lib/test/test_re.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -502,6 +502,65 @@ def test_bug_117612(self):
self.assertEqual(re.findall(r"(a|(b))", "aba"),
[("a", ""),("b", "b"),("a", "")])

def test_bug_7940(self):
# Issue 7940: re.finditer and re.findall should support negative end positions
pat = re.compile(".")

with self.assertWarns(FutureWarning) as cm:
self.assertEqual(pat.findall("abcd", -1, 1), [])
self.assertEqual(str(cm.warning), "Negative start index will not "
"be truncated to zero in the future")

with self.assertWarns(FutureWarning) as cm:
self.assertEqual(pat.findall("abcd", 1, -1), ['b', 'c'])
self.assertEqual(str(cm.warning), "Negative end index will not "
"be truncated to zero in the future")

with self.assertWarns(FutureWarning) as cm:
self.assertEqual(pat.findall("abcd", 1, 3), ['b', 'c'])
self.assertEqual(pat.findall("abcd", 1, -1), ['b', 'c'])
self.assertEqual(pat.findall("abcd", -3, -1), ['b', 'c'])
self.assertEqual(pat.findall("abcd", -3, 3), ['b', 'c'])
self.assertEqual(pat.findall("abcd", -1, 1), [])
self.assertEqual(pat.findall("abcd", -1, -3), [])
self.assertEqual(pat.findall("abcd", -200, -1), ['a', 'b', 'c'])
self.assertEqual(pat.findall("abcd", -200, -100), [])
self.assertEqual(pat.findall("abcd", pos=1, endpos=-1), ['b', 'c'])
self.assertEqual(len(cm.warnings), 12)

with self.assertWarns(FutureWarning) as cm:
self.assertEqual([m[0] for m in pat.finditer("abcd", -1, 1)],
[])
self.assertEqual(str(cm.warning), "Negative start index will not "
"be truncated to zero in the future")

with self.assertWarns(FutureWarning) as cm:
self.assertEqual([m[0] for m in pat.finditer("abcd", 1, -1)],
['b', 'c'])
self.assertEqual(str(cm.warning), "Negative end index will not "
"be truncated to zero in the future")

with self.assertWarns(FutureWarning) as cm:
self.assertEqual([m[0] for m in pat.finditer("abcd", 1, 3)],
['b', 'c'])
self.assertEqual([m[0] for m in pat.finditer("abcd", 1, -1)],
['b', 'c'])
self.assertEqual([m[0] for m in pat.finditer("abcd", -3, -1)],
['b', 'c'])
self.assertEqual([m[0] for m in pat.finditer("abcd", -3, 3)],
['b', 'c'])
self.assertEqual([m[0] for m in pat.finditer("abcd", -1, 1)],
[])
self.assertEqual([m[0] for m in pat.finditer("abcd", -1, -3)],
[])
self.assertEqual([m[0] for m in pat.finditer("abcd", -200, -1)],
['a', 'b', 'c'])
self.assertEqual([m[0] for m in pat.finditer("abcd", -200, -100)],
[])
self.assertEqual([m[0] for m in pat.finditer("abcd", pos=1,
endpos=-1)], ['b', 'c'])
self.assertEqual(len(cm.warnings), 12)

def test_re_match(self):
for string in 'a', S('a'):
self.assertEqual(re.match('a', string).groups(), ())
Expand Down
1 change: 1 addition & 0 deletions Misc/ACKS
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1873,6 +1873,7 @@ Steven Troxler
Brent Tubbs
Anthony Tuininga
Erno Tukia
Anıl Tuncel
Adam Turner
David Turner
Stephen Turner
Expand Down
2 changes: 2 additions & 0 deletions Misc/NEWS.d/next/Library/2019-07-13-15-23-34.bpo-7940.NDghRj.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
Add support for negative end positions to re.finditer and re.findall
(original patch by Matthew Barnett, tests and PR by Mustafa Anıl Tuncel).
12 changes: 12 additions & 0 deletions Modules/_sre/sre.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -482,11 +482,23 @@ state_init(SRE_STATE* state, PatternObject* pattern, PyObject* string,
}

/* adjust boundaries */
if (start < 0) {
PyErr_WarnEx(PyExc_FutureWarning,
"Negative start index will not be truncated to zero in the future",
1);
start += length;
}
if (start < 0)
start = 0;
else if (start > length)
start = length;

if (end < 0) {
PyErr_WarnEx(PyExc_FutureWarning,
"Negative end index will not be truncated to zero in the future",
1);
end += length;
}
if (end < 0)
end = 0;
else if (end > length)
Expand Down