Skip to content
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

fix: Csv stop simd cache if eol char is hit #20199

Merged
merged 1 commit into from
Dec 6, 2024
Merged

fix: Csv stop simd cache if eol char is hit #20199

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
4 changes: 2 additions & 2 deletions crates/polars-io/src/csv/read/read_impl.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -404,6 +404,8 @@ impl<'a> CoreReader<'a> {

let counter = CountLines::new(self.quote_char, self.eol_char);
let mut total_offset = 0;
let check_utf8 = matches!(self.encoding, CsvEncoding::Utf8)
Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

take this out of the loop

&& self.schema.iter_fields().any(|f| f.dtype().is_string());

pool.scope(|s| {
loop {
Expand Down Expand Up @@ -432,8 +434,6 @@ impl<'a> CoreReader<'a> {
total_offset = end;
(b, count)
};
let check_utf8 = matches!(self.encoding, CsvEncoding::Utf8)
&& self.schema.iter_fields().any(|f| f.dtype().is_string());

if !b.is_empty() {
let results = results.clone();
Expand Down
34 changes: 20 additions & 14 deletions crates/polars-io/src/csv/read/splitfields.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -188,11 +188,11 @@ mod inner {
unsafe fn finish_eol(
&mut self,
need_escaping: bool,
idx: usize,
pos: usize,
) -> Option<(&'a [u8], bool)> {
self.finished = true;
debug_assert!(idx <= self.v.len());
Some((self.v.get_unchecked(..idx), need_escaping))
debug_assert!(pos <= self.v.len());
Some((self.v.get_unchecked(..pos), need_escaping))
}

#[inline]
Expand All @@ -212,7 +212,11 @@ mod inner {

#[inline]
fn next(&mut self) -> Option<(&'a [u8], bool)> {
// First check cached value as this is hot.
// This must be before we check the cached value
if self.finished {
return None;
}
// Then check cached value as this is hot.
if self.previous_valid_ends != 0 {
let pos = self.previous_valid_ends.trailing_zeros() as usize;
self.previous_valid_ends >>= (pos + 1) as u64;
Expand All @@ -221,22 +225,24 @@ mod inner {
debug_assert!(pos < self.v.len());
// SAFETY:
// we are in bounds
let needs_escaping = self
.v
.first()
.map(|c| *c == self.quote_char && self.quoting)
.unwrap_or(false);

if *self.v.get_unchecked(pos) == self.eol_char {
return self.finish_eol(needs_escaping, pos);
}

let bytes = self.v.get_unchecked(..pos);

self.v = self.v.get_unchecked(pos + 1..);
let ret = Some((
bytes,
bytes
.first()
.map(|c| *c == self.quote_char && self.quoting)
.unwrap_or(false),
));
let ret = Some((bytes, needs_escaping));

return ret;
}
}
if self.finished {
return None;
}
if self.v.is_empty() {
return self.finish(false);
}
Expand Down
Loading