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

Jump to bottom

feat: upgrade to Arrow 37 and Datafusion 23 #1314

Merged
merged 10 commits into from
Apr 29, 2023
Merged

feat: upgrade to Arrow 37 and Datafusion 23 #1314

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
c873c0a
Bump the release version to 0.10.0 to reflect major dependency changes
rtyler Apr 27, 2023
6f9a418
Upgrade the arrow and parquet crates to arrow 37
rtyler Apr 14, 2023
15cffa2
Enable the json feature for the parquet crate
rtyler Apr 19, 2023
c3b3358
Add the `json` feature to compile json support for parquet
rtyler Apr 23, 2023
513b439
Upgrade delta_arrow to the arrow 37 API changes
rtyler Apr 17, 2023
61d49b6
Upgrade datafusion to 23
rtyler Apr 27, 2023
28f3ab8
Minor API changes to support Datafusion upgrade
rtyler Apr 28, 2023
a3e1bd4
First pass of python bindings fixes
rtyler Apr 28, 2023
0dc134a
Switch internal APIs to use ArrowFieldRef instead of ArrowField
rtyler Apr 28, 2023
dbcffbc
remove old json function
wjones127 Apr 29, 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
12 changes: 0 additions & 12 deletions python/src/lib.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -321,18 +321,6 @@ impl RawDeltaTable {
.collect())
}

pub fn arrow_schema_json(&self) -> PyResult<String> {
let schema = self
._table
.get_schema()
.map_err(PyDeltaTableError::from_raw)?;
serde_json::to_string(
&<ArrowSchema as TryFrom<&deltalake::Schema>>::try_from(schema)
.map_err(PyDeltaTableError::from_arrow)?,
)
.map_err(|_| PyDeltaTableError::new_err("Got invalid table schema"))
}
Comment on lines -324 to -334
Copy link
Collaborator

Choose a reason for hiding this comment

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

I don't think this was used in our public API, and I know the arrow-rs folks wanted to remove the unofficial JSON schema serialization from their public API as well. I think it should be fine to drop this.


pub fn update_incremental(&mut self) -> PyResult<()> {
rt()?
.block_on(self._table.update_incremental(None))
Expand Down
44 changes: 25 additions & 19 deletions python/src/schema.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,8 @@
extern crate pyo3;

use deltalake::arrow::datatypes::{
DataType as ArrowDataType, Field as ArrowField, Schema as ArrowSchema,
DataType as ArrowDataType, Field as ArrowField, FieldRef as ArrowFieldRef,
Schema as ArrowSchema,
};
use deltalake::arrow::error::ArrowError;
use deltalake::arrow::pyarrow::PyArrowType;
Expand Down Expand Up @@ -1023,42 +1024,49 @@ impl PySchema {
.try_into()
.map_err(|err: ArrowError| PyException::new_err(err.to_string()))?;

fn convert_to_large_type(field: ArrowField, dt: ArrowDataType) -> ArrowField {
fn convert_to_large_type(field: ArrowFieldRef, dt: ArrowDataType) -> ArrowFieldRef {
let field = field.as_ref().clone();
match dt {
ArrowDataType::Utf8 => field.with_data_type(ArrowDataType::LargeUtf8),
ArrowDataType::Utf8 => field.with_data_type(ArrowDataType::LargeUtf8).into(),

ArrowDataType::Binary => field.with_data_type(ArrowDataType::LargeBinary),
ArrowDataType::Binary => field.with_data_type(ArrowDataType::LargeBinary).into(),

ArrowDataType::List(f) => {
let sub_field = convert_to_large_type(*f.clone(), f.data_type().clone());
field.with_data_type(ArrowDataType::LargeList(Box::from(sub_field)))
let sub_field = convert_to_large_type(f.clone(), f.data_type().clone());
field
.with_data_type(ArrowDataType::LargeList(sub_field))
.into()
}

ArrowDataType::FixedSizeList(f, size) => {
let sub_field = convert_to_large_type(*f.clone(), f.data_type().clone());
field.with_data_type(ArrowDataType::FixedSizeList(Box::from(sub_field), size))
let sub_field = convert_to_large_type(f.clone(), f.data_type().clone());
field
.with_data_type(ArrowDataType::FixedSizeList(sub_field, size))
.into()
}

ArrowDataType::Map(f, sorted) => {
let sub_field = convert_to_large_type(*f.clone(), f.data_type().clone());
field.with_data_type(ArrowDataType::Map(Box::from(sub_field), sorted))
let sub_field = convert_to_large_type(f.clone(), f.data_type().clone());
field
.with_data_type(ArrowDataType::Map(sub_field, sorted))
.into()
}

ArrowDataType::Struct(fields) => {
let sub_fields = fields
.iter()
.map(|f| {
let dt: ArrowDataType = f.data_type().clone();
let f: ArrowField = f.clone();

convert_to_large_type(f, dt)
convert_to_large_type(f.clone(), dt)
})
.collect();

field.with_data_type(ArrowDataType::Struct(sub_fields))
field
.with_data_type(ArrowDataType::Struct(sub_fields))
.into()
}

_ => field,
_ => field.into(),
}
}

Expand All @@ -1068,11 +1076,9 @@ impl PySchema {
.iter()
.map(|f| {
let dt: ArrowDataType = f.data_type().clone();
let f: ArrowField = f.clone();

convert_to_large_type(f, dt)
convert_to_large_type(f.clone(), dt)
})
.collect(),
.collect::<Vec<ArrowFieldRef>>(),
);

Ok(PyArrowType(schema))
Expand Down
20 changes: 10 additions & 10 deletions rust/Cargo.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
[package]
name = "deltalake"
version = "0.9.1"
version = "0.10.0"
rust-version = "1.64"
authors = ["Qingping Hou <dave2008713@gmail.com>"]
homepage = "https://github.com/delta-io/delta.rs"
Expand All @@ -13,7 +13,7 @@ readme = "README.md"
edition = "2021"

[dependencies]
arrow = { version = "36.0.0", optional = true }
arrow = { version = "37.0.0", optional = true }
async-trait = "0.1"
bytes = "1"
chrono = { version = "0.4.22", default-features = false, features = ["clock"] }
Expand All @@ -30,7 +30,7 @@ num-traits = "0.2.15"
object_store = "0.5.6"
once_cell = "1.16.0"
parking_lot = "0.12"
parquet = { version = "36", features = [
parquet = { version = "37", features = [
"async",
"object_store",
], optional = true }
Expand All @@ -54,14 +54,14 @@ rusoto_dynamodb = { version = "0.47", default-features = false, optional = true
rusoto_glue = { version = "0.47", default-features = false, optional = true }

# Datafusion
datafusion = { version = "22", optional = true }
datafusion-expr = { version = "22", optional = true }
datafusion-common = { version = "22", optional = true }
datafusion-proto = { version = "22", optional = true }
datafusion-sql = { version = "22", optional = true }
datafusion-physical-expr = { version = "22", optional = true }
datafusion = { version = "23", optional = true }
datafusion-expr = { version = "23", optional = true }
datafusion-common = { version = "23", optional = true }
datafusion-proto = { version = "23", optional = true }
datafusion-sql = { version = "23", optional = true }
datafusion-physical-expr = { version = "23", optional = true }

sqlparser = { version = "0.32", optional = true }
sqlparser = { version = "0.33", optional = true }

# NOTE dependencies only for integration tests
fs_extra = { version = "1.2.0", optional = true }
Expand Down
Loading