Skip to content

Commit

Permalink
update arrow
Browse files Browse the repository at this point in the history
  • Loading branch information
ritchie46 committed Feb 4, 2022
1 parent df74850 commit 7ea47cb
Show file tree
Hide file tree
Showing 5 changed files with 22 additions and 24 deletions.
4 changes: 2 additions & 2 deletions polars/polars-arrow/Cargo.toml
Original file line number Diff line number Diff line change
Expand Up @@ -9,8 +9,8 @@ description = "Arrow interfaces for Polars DataFrame library"
# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html

[dependencies]
# arrow = { package = "arrow2", git = "https://github.com/jorgecarleitao/arrow2", rev = "086c54d00aee7b26ba3c8d0c5c683c531e2c75c1", default-features = false }
arrow = { package = "arrow2", git = "https://github.com/ritchie46/arrow2", branch = "from_iter_variants2", default-features = false }
arrow = { package = "arrow2", git = "https://github.com/jorgecarleitao/arrow2", rev = "b46a636f31d70a20bd54df9c7f9e9363053ade08", default-features = false }
# arrow = { package = "arrow2", git = "https://github.com/ritchie46/arrow2", branch = "from_iter_variants", default-features = false }
# arrow = { package = "arrow2", version = "0.9", default-features = false, features = ["compute_concatenate"] }
hashbrown = "0.12"
num = "^0.4"
Expand Down
8 changes: 4 additions & 4 deletions polars/polars-core/Cargo.toml
Original file line number Diff line number Diff line change
Expand Up @@ -160,10 +160,10 @@ unsafe_unwrap = "^0.1.0"

[dependencies.arrow]
package = "arrow2"
# git = "https://github.com/jorgecarleitao/arrow2"
git = "https://github.com/ritchie46/arrow2"
# rev = "54797de5e4860cebc4eb73ad1890457cd1a658eb"
branch = "from_iter_variants2"
git = "https://github.com/jorgecarleitao/arrow2"
# git = "https://github.com/ritchie46/arrow2"
rev = "b46a636f31d70a20bd54df9c7f9e9363053ade08"
# branch = "from_iter_variants"
# version = "0.9"
default-features = false
features = [
Expand Down
4 changes: 2 additions & 2 deletions polars/polars-io/Cargo.toml
Original file line number Diff line number Diff line change
Expand Up @@ -31,8 +31,8 @@ private = []
[dependencies]
ahash = "0.7"
anyhow = "1.0"
# arrow = { package = "arrow2", git = "https://github.com/jorgecarleitao/arrow2", rev = "086c54d00aee7b26ba3c8d0c5c683c531e2c75c1", default-features = false }
arrow = { package = "arrow2", git = "https://github.com/ritchie46/arrow2", branch = "from_iter_variants2", default-features = false }
arrow = { package = "arrow2", git = "https://github.com/jorgecarleitao/arrow2", rev = "b46a636f31d70a20bd54df9c7f9e9363053ade08", default-features = false }
# arrow = { package = "arrow2", git = "https://github.com/ritchie46/arrow2", branch = "from_iter_variants", default-features = false }
# arrow = { package = "arrow2", version = "0.9", default-features = false }
csv-core = { version = "0.1.10", optional = true }
dirs = "4.0"
Expand Down
24 changes: 11 additions & 13 deletions polars/polars-io/src/parquet/write.rs
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
use super::ArrowResult;
use arrow::datatypes::PhysicalType;
use arrow::error::ArrowError;
use arrow::io::parquet::write::{self, *};
use arrow::io::parquet::write::{self, FileWriter, *};
use arrow::io::parquet::write::{array_to_pages, DynIter, DynStreamingIterator, Encoding};
use polars_core::prelude::*;
use rayon::prelude::*;
Expand Down Expand Up @@ -103,13 +103,11 @@ where
})
.collect::<Vec<_>>();

// clone is needed because parquet schema is moved into `write_file`
let parquet_schema_iter = parquet_schema.clone();
let row_group_iter = rb_iter.map(|batch| {
let columns = batch
.columns()
.par_iter()
.zip(parquet_schema_iter.columns().par_iter())
.zip(parquet_schema.columns().par_iter())
.zip(encodings.par_iter())
.map(|((array, descriptor), encoding)| {
let encoded_pages =
Expand All @@ -127,17 +125,17 @@ where
.into_iter()
.map(|column| Ok(DynStreamingIterator::new(Bla::new(column)))),
);
ArrowResult::Ok(row_group)
ArrowResult::Ok((row_group, batch.columns()[0].len()))
});

write::write_file(
&mut self.writer,
row_group_iter,
&schema,
parquet_schema,
options,
None,
)?;
let mut writer = FileWriter::try_new(&mut self.writer, schema, options)?;
// write the headers
writer.start()?;
for group in row_group_iter {
let (group, len) = group?;
writer.write(group, len)?;
}
let _ = writer.end(None)?;

Ok(())
}
Expand Down
6 changes: 3 additions & 3 deletions py-polars/Cargo.lock

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

0 comments on commit 7ea47cb

Please sign in to comment.