Skip to content

Fix swapcase() #7788

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

Draft
joshuamegnauth54 wants to merge 1 commit into
base: main
Choose a base branch
from
+36 −21
Draft

Fix swapcase() #7788

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
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 0 additions & 1 deletion Lib/test/test_str.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -974,7 +974,6 @@ def test_title(self):
self.assertEqual('A\u03a3 \u1fa1xy'.title(), 'A\u03c2 \u1fa9xy')
self.assertEqual('A\u03a3A'.title(), 'A\u03c3a')

@unittest.expectedFailure # TODO: RUSTPYTHON; + 𐐧
def test_swapcase(self):
string_tests.StringLikeTest.test_swapcase(self)
self.assertEqual('\U0001044F'.swapcase(), '\U00010427')
Expand Down
39 changes: 28 additions & 11 deletions crates/vm/src/builtins/str.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1089,19 +1089,22 @@ impl PyStr {

#[pymethod]
fn swapcase(&self) -> Wtf8Buf {
let mut swapped_str = Wtf8Buf::with_capacity(self.data.len());
for c_orig in self.as_wtf8().code_points() {
let c = c_orig.to_char_lossy();
// to_uppercase returns an iterator because case changes may be multiple bytes
if c.is_lowercase() {
swapped_str.extend(c.to_uppercase());
} else if c.is_uppercase() {
swapped_str.extend(c.to_lowercase());
} else {
swapped_str.push(c_orig);
match self.as_str_kind() {
PyKindStr::Ascii(s) => swapcase_ascii(s.as_bytes()).into(),
PyKindStr::Utf8(s) => {
let mut out = VecFmtWriter(Vec::with_capacity(s.len()));
swapcase_utf8(s, &mut out);
out.0.into()
}
PyKindStr::Wtf8(s) => {
let mut out = VecFmtWriter(Vec::with_capacity(s.len()));
for chunk in s.as_bytes().utf8_chunks() {
swapcase_utf8(chunk.valid(), &mut out);
out.0.extend(chunk.invalid());
}
out.0.into()
}
}
swapped_str
}

#[pymethod]
Expand Down Expand Up @@ -1555,6 +1558,20 @@ impl PyStr {
}
}

fn swapcase_utf8(s: &str, out: &mut VecFmtWriter) {
for (i, ch) in s.char_indices() {
if ch.is_uppercase() {
lowercase_or_sigma(ch, s, i, out);
} else {
for ch in ch.to_lowercase() {
let mut buf = [0u8; 4];
let s = ch.encode_utf8(&mut buf);
out.0.extend(s.as_bytes());
}
}
}
}

impl PyRef<PyStr> {
#[must_use]
pub fn is_empty(&self) -> bool {
Expand Down
17 changes: 8 additions & 9 deletions crates/vm/src/bytes_inner.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -413,15 +413,7 @@ impl PyBytesInner {
}

pub fn swapcase(&self) -> Vec<u8> {
let mut new: Vec<u8> = Vec::with_capacity(self.elements.len());
for w in &self.elements {
match w {
b'A'..=b'Z' => new.push(w.to_ascii_lowercase()),
b'a'..=b'z' => new.push(w.to_ascii_uppercase()),
x => new.push(*x),
}
}
new
swapcase_ascii(self.as_bytes())
}

pub fn hex(
Expand Down Expand Up @@ -1236,3 +1228,10 @@ pub(crate) fn bytes_to_hex(
pub(crate) const fn is_py_ascii_whitespace(b: u8) -> bool {
matches!(b, b'\t' | b'\n' | b'\x0C' | b'\r' | b' ' | b'\x0B')
}

pub(crate) fn swapcase_ascii(bytes: &[u8]) -> Vec<u8> {
bytes
.iter()
.map(|&b| if b.is_ascii_alphabetic() { b ^ 0x20 } else { b })
.collect()
}
Loading