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.

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

refactor(rust): Rename ChunkedArray.chunk_id to chunk_lengths #16273

Merged
merged 6 commits into from
May 17, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
6 changes: 3 additions & 3 deletions crates/polars-core/src/chunked_array/mod.rs
Original file line number Diff line number Diff line change
Expand Up @@ -59,7 +59,7 @@ use crate::utils::{first_non_null, last_non_null};
#[cfg(not(feature = "dtype-categorical"))]
pub struct RevMapping {}

pub type ChunkIdIter<'a> = std::iter::Map<std::slice::Iter<'a, ArrayRef>, fn(&ArrayRef) -> usize>;
pub type ChunkLenIter<'a> = std::iter::Map<std::slice::Iter<'a, ArrayRef>, fn(&ArrayRef) -> usize>;

/// # ChunkedArray
///
Expand Down Expand Up @@ -359,8 +359,8 @@ impl<T: PolarsDataType> ChunkedArray<T> {
Ok(unsafe { self.unpack_series_matching_physical_type(series) })
}

/// Unique id representing the number of chunks
pub fn chunk_id(&self) -> ChunkIdIter {
/// Returns an iterator over the lengths of the chunks of the array.
pub fn chunk_lengths(&self) -> ChunkLenIter {
self.chunks.iter().map(|chunk| chunk.len())
}

Expand Down
2 changes: 1 addition & 1 deletion crates/polars-core/src/chunked_array/ops/downcast.rs
Original file line number Diff line number Diff line change
Expand Up @@ -129,7 +129,7 @@ impl<T: PolarsDataType> ChunkedArray<T> {
(1, index - len)
};
}
let chunk_lens = self.downcast_iter().map(|arr| arr.len());
let chunk_lens = self.chunk_lengths();
let len = self.len();
if index <= len / 2 {
// Access from lhs.
Expand Down
2 changes: 1 addition & 1 deletion crates/polars-core/src/prelude.rs
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,7 @@ pub use crate::chunked_array::ops::rolling_window::RollingOptionsFixedWindow;
pub use crate::chunked_array::ops::*;
#[cfg(feature = "temporal")]
pub use crate::chunked_array::temporal::conversion::*;
pub(crate) use crate::chunked_array::ChunkIdIter;
pub(crate) use crate::chunked_array::ChunkLenIter;
pub use crate::chunked_array::ChunkedArray;
#[cfg(feature = "dtype-categorical")]
pub use crate::datatypes::string_cache::StringCacheHolder;
Expand Down
4 changes: 2 additions & 2 deletions crates/polars-core/src/series/implementations/array.rs
Original file line number Diff line number Diff line change
Expand Up @@ -58,8 +58,8 @@ impl SeriesTrait for SeriesWrap<ArrayChunked> {
self.0.rename(name);
}

fn chunk_lengths(&self) -> ChunkIdIter {
self.0.chunk_id()
fn chunk_lengths(&self) -> ChunkLenIter {
self.0.chunk_lengths()
}
fn name(&self) -> &str {
self.0.name()
Expand Down
4 changes: 2 additions & 2 deletions crates/polars-core/src/series/implementations/binary.rs
Original file line number Diff line number Diff line change
Expand Up @@ -98,8 +98,8 @@ impl SeriesTrait for SeriesWrap<BinaryChunked> {
self.0.rename(name);
}

fn chunk_lengths(&self) -> ChunkIdIter {
self.0.chunk_id()
fn chunk_lengths(&self) -> ChunkLenIter {
self.0.chunk_lengths()
}
fn name(&self) -> &str {
self.0.name()
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -62,8 +62,8 @@ impl SeriesTrait for SeriesWrap<BinaryOffsetChunked> {
self.0.rename(name);
}

fn chunk_lengths(&self) -> ChunkIdIter {
self.0.chunk_id()
fn chunk_lengths(&self) -> ChunkLenIter {
self.0.chunk_lengths()
}
fn name(&self) -> &str {
self.0.name()
Expand Down
4 changes: 2 additions & 2 deletions crates/polars-core/src/series/implementations/boolean.rs
Original file line number Diff line number Diff line change
Expand Up @@ -120,8 +120,8 @@ impl SeriesTrait for SeriesWrap<BooleanChunked> {
self.0.rename(name);
}

fn chunk_lengths(&self) -> ChunkIdIter {
self.0.chunk_id()
fn chunk_lengths(&self) -> ChunkLenIter {
self.0.chunk_lengths()
}
fn name(&self) -> &str {
self.0.name()
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -133,8 +133,8 @@ impl SeriesTrait for SeriesWrap<CategoricalChunked> {
self.0.physical_mut().rename(name);
}

fn chunk_lengths(&self) -> ChunkIdIter {
self.0.physical().chunk_id()
fn chunk_lengths(&self) -> ChunkLenIter {
self.0.physical().chunk_lengths()
}
fn name(&self) -> &str {
self.0.physical().name()
Expand Down
4 changes: 2 additions & 2 deletions crates/polars-core/src/series/implementations/dates_time.rs
Original file line number Diff line number Diff line change
Expand Up @@ -143,8 +143,8 @@ macro_rules! impl_dyn_series {
self.0.rename(name);
}

fn chunk_lengths(&self) -> ChunkIdIter {
self.0.chunk_id()
fn chunk_lengths(&self) -> ChunkLenIter {
self.0.chunk_lengths()
}
fn name(&self) -> &str {
self.0.name()
Expand Down
4 changes: 2 additions & 2 deletions crates/polars-core/src/series/implementations/datetime.rs
Original file line number Diff line number Diff line change
Expand Up @@ -148,8 +148,8 @@ impl SeriesTrait for SeriesWrap<DatetimeChunked> {
self.0.rename(name);
}

fn chunk_lengths(&self) -> ChunkIdIter {
self.0.chunk_id()
fn chunk_lengths(&self) -> ChunkLenIter {
self.0.chunk_lengths()
}
fn name(&self) -> &str {
self.0.name()
Expand Down
4 changes: 2 additions & 2 deletions crates/polars-core/src/series/implementations/decimal.rs
Original file line number Diff line number Diff line change
Expand Up @@ -175,8 +175,8 @@ impl SeriesTrait for SeriesWrap<DecimalChunked> {
self.0.rename(name)
}

fn chunk_lengths(&self) -> ChunkIdIter {
self.0.chunk_id()
fn chunk_lengths(&self) -> ChunkLenIter {
self.0.chunk_lengths()
}

fn name(&self) -> &str {
Expand Down
4 changes: 2 additions & 2 deletions crates/polars-core/src/series/implementations/duration.rs
Original file line number Diff line number Diff line change
Expand Up @@ -208,8 +208,8 @@ impl SeriesTrait for SeriesWrap<DurationChunked> {
self.0.rename(name);
}

fn chunk_lengths(&self) -> ChunkIdIter {
self.0.chunk_id()
fn chunk_lengths(&self) -> ChunkLenIter {
self.0.chunk_lengths()
}
fn name(&self) -> &str {
self.0.name()
Expand Down
4 changes: 2 additions & 2 deletions crates/polars-core/src/series/implementations/floats.rs
Original file line number Diff line number Diff line change
Expand Up @@ -139,8 +139,8 @@ macro_rules! impl_dyn_series {
self.0.rename(name);
}

fn chunk_lengths(&self) -> ChunkIdIter {
self.0.chunk_id()
fn chunk_lengths(&self) -> ChunkLenIter {
self.0.chunk_lengths()
}
fn name(&self) -> &str {
self.0.name()
Expand Down
4 changes: 2 additions & 2 deletions crates/polars-core/src/series/implementations/list.rs
Original file line number Diff line number Diff line change
Expand Up @@ -54,8 +54,8 @@ impl SeriesTrait for SeriesWrap<ListChunked> {
self.0.rename(name);
}

fn chunk_lengths(&self) -> ChunkIdIter {
self.0.chunk_id()
fn chunk_lengths(&self) -> ChunkLenIter {
self.0.chunk_lengths()
}
fn name(&self) -> &str {
self.0.name()
Expand Down
4 changes: 2 additions & 2 deletions crates/polars-core/src/series/implementations/mod.rs
Original file line number Diff line number Diff line change
Expand Up @@ -242,8 +242,8 @@ macro_rules! impl_dyn_series {
self.0.rename(name);
}

fn chunk_lengths(&self) -> ChunkIdIter {
self.0.chunk_id()
fn chunk_lengths(&self) -> ChunkLenIter {
self.0.chunk_lengths()
}
fn name(&self) -> &str {
self.0.name()
Expand Down
2 changes: 1 addition & 1 deletion crates/polars-core/src/series/implementations/null.rs
Original file line number Diff line number Diff line change
Expand Up @@ -160,7 +160,7 @@ impl SeriesTrait for NullChunked {
&mut self.chunks
}

fn chunk_lengths(&self) -> ChunkIdIter {
fn chunk_lengths(&self) -> ChunkLenIter {
self.chunks.iter().map(|chunk| chunk.len())
}

Expand Down
4 changes: 2 additions & 2 deletions crates/polars-core/src/series/implementations/object.rs
Original file line number Diff line number Diff line change
Expand Up @@ -80,8 +80,8 @@ where
ObjectChunked::rename(&mut self.0, name)
}

fn chunk_lengths(&self) -> ChunkIdIter {
ObjectChunked::chunk_id(&self.0)
fn chunk_lengths(&self) -> ChunkLenIter {
ObjectChunked::chunk_lengths(&self.0)
}

fn name(&self) -> &str {
Expand Down
4 changes: 2 additions & 2 deletions crates/polars-core/src/series/implementations/string.rs
Original file line number Diff line number Diff line change
Expand Up @@ -99,8 +99,8 @@ impl SeriesTrait for SeriesWrap<StringChunked> {
self.0.rename(name);
}

fn chunk_lengths(&self) -> ChunkIdIter {
self.0.chunk_id()
fn chunk_lengths(&self) -> ChunkLenIter {
self.0.chunk_lengths()
}
fn name(&self) -> &str {
self.0.name()
Expand Down
2 changes: 1 addition & 1 deletion crates/polars-core/src/series/implementations/struct_.rs
Original file line number Diff line number Diff line change
Expand Up @@ -97,7 +97,7 @@ impl SeriesTrait for SeriesWrap<StructChunked> {
self.0.name()
}

fn chunk_lengths(&self) -> ChunkIdIter {
fn chunk_lengths(&self) -> ChunkLenIter {
let s = self.0.fields().first().unwrap();
s.chunk_lengths()
}
Expand Down
2 changes: 1 addition & 1 deletion crates/polars-core/src/series/series_trait.rs
Original file line number Diff line number Diff line change
Expand Up @@ -193,7 +193,7 @@ pub trait SeriesTrait:
}

/// Get the lengths of the underlying chunks
fn chunk_lengths(&self) -> ChunkIdIter;
fn chunk_lengths(&self) -> ChunkLenIter;

/// Name of series.
fn name(&self) -> &str;
Expand Down
42 changes: 21 additions & 21 deletions crates/polars-core/src/utils/mod.rs
Original file line number Diff line number Diff line change
Expand Up @@ -709,13 +709,13 @@ where
assert();
(
Cow::Borrowed(left),
Cow::Owned(right.match_chunks(left.chunk_id())),
Cow::Owned(right.match_chunks(left.chunk_lengths())),
)
},
(1, _) => {
assert();
(
Cow::Owned(left.match_chunks(right.chunk_id())),
Cow::Owned(left.match_chunks(right.chunk_lengths())),
Cow::Borrowed(right),
)
},
Expand All @@ -724,7 +724,7 @@ where
// could optimize to choose to rechunk a primitive and not a string or list type
let left = left.rechunk();
(
Cow::Owned(left.match_chunks(right.chunk_id())),
Cow::Owned(left.match_chunks(right.chunk_lengths())),
Cow::Borrowed(right),
)
},
Expand Down Expand Up @@ -786,50 +786,50 @@ where
match (a.chunks.len(), b.chunks.len(), c.chunks.len()) {
(_, 1, 1) => (
Cow::Borrowed(a),
Cow::Owned(b.match_chunks(a.chunk_id())),
Cow::Owned(c.match_chunks(a.chunk_id())),
Cow::Owned(b.match_chunks(a.chunk_lengths())),
Cow::Owned(c.match_chunks(a.chunk_lengths())),
),
(1, 1, _) => (
Cow::Owned(a.match_chunks(c.chunk_id())),
Cow::Owned(b.match_chunks(c.chunk_id())),
Cow::Owned(a.match_chunks(c.chunk_lengths())),
Cow::Owned(b.match_chunks(c.chunk_lengths())),
Cow::Borrowed(c),
),
(1, _, 1) => (
Cow::Owned(a.match_chunks(b.chunk_id())),
Cow::Owned(a.match_chunks(b.chunk_lengths())),
Cow::Borrowed(b),
Cow::Owned(c.match_chunks(b.chunk_id())),
Cow::Owned(c.match_chunks(b.chunk_lengths())),
),
(1, _, _) => {
let b = b.rechunk();
(
Cow::Owned(a.match_chunks(c.chunk_id())),
Cow::Owned(b.match_chunks(c.chunk_id())),
Cow::Owned(a.match_chunks(c.chunk_lengths())),
Cow::Owned(b.match_chunks(c.chunk_lengths())),
Cow::Borrowed(c),
)
},
(_, 1, _) => {
let a = a.rechunk();
(
Cow::Owned(a.match_chunks(c.chunk_id())),
Cow::Owned(b.match_chunks(c.chunk_id())),
Cow::Owned(a.match_chunks(c.chunk_lengths())),
Cow::Owned(b.match_chunks(c.chunk_lengths())),
Cow::Borrowed(c),
)
},
(_, _, 1) => {
let b = b.rechunk();
(
Cow::Borrowed(a),
Cow::Owned(b.match_chunks(a.chunk_id())),
Cow::Owned(c.match_chunks(a.chunk_id())),
Cow::Owned(b.match_chunks(a.chunk_lengths())),
Cow::Owned(c.match_chunks(a.chunk_lengths())),
)
},
_ => {
// could optimize to choose to rechunk a primitive and not a string or list type
let a = a.rechunk();
let b = b.rechunk();
(
Cow::Owned(a.match_chunks(c.chunk_id())),
Cow::Owned(b.match_chunks(c.chunk_id())),
Cow::Owned(a.match_chunks(c.chunk_lengths())),
Cow::Owned(b.match_chunks(c.chunk_lengths())),
Cow::Borrowed(c),
)
},
Expand Down Expand Up @@ -1051,8 +1051,8 @@ mod test {
b.append(&b2);
let (a, b) = align_chunks_binary(&a, &b);
assert_eq!(
a.chunk_id().collect::<Vec<_>>(),
b.chunk_id().collect::<Vec<_>>()
a.chunk_lengths().collect::<Vec<_>>(),
b.chunk_lengths().collect::<Vec<_>>()
);

let a = Int32Chunked::new("", &[1, 2, 3, 4]);
Expand All @@ -1063,8 +1063,8 @@ mod test {
b.append(&b1);
let (a, b) = align_chunks_binary(&a, &b);
assert_eq!(
a.chunk_id().collect::<Vec<_>>(),
b.chunk_id().collect::<Vec<_>>()
a.chunk_lengths().collect::<Vec<_>>(),
b.chunk_lengths().collect::<Vec<_>>()
);
}
}