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

Support LargeUtf8 #1

Merged
merged 5 commits into from
Jun 21, 2024
Merged
Changes from 3 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
26 changes: 21 additions & 5 deletions crates/duckdb/src/vtab/arrow.rs
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@ use crate::vtab::vector::Inserter;
use arrow::array::{
as_boolean_array, as_generic_binary_array, as_large_list_array, as_list_array, as_primitive_array, as_string_array,
as_struct_array, Array, ArrayData, AsArray, BinaryArray, BooleanArray, Decimal128Array, FixedSizeListArray,
GenericListArray, OffsetSizeTrait, PrimitiveArray, StringArray, StructArray,
GenericListArray, GenericStringArray, LargeStringArray, OffsetSizeTrait, PrimitiveArray, StructArray,
};

use arrow::{
Expand Down Expand Up @@ -229,6 +229,15 @@ pub fn record_batch_to_duckdb_data_chunk(
DataType::Utf8 => {
string_array_to_vector(as_string_array(col.as_ref()), &mut chunk.flat_vector(i));
}
DataType::LargeUtf8 => {
string_array_to_vector(
col.as_ref()
.as_any()
.downcast_ref::<LargeStringArray>()
.ok_or_else(|| Box::<dyn std::error::Error>::from("Unable to downcast to LargeStringArray"))?,
&mut chunk.flat_vector(i),
);
}
DataType::Binary => {
binary_array_to_vector(as_generic_binary_array(col.as_ref()), &mut chunk.flat_vector(i));
}
Expand Down Expand Up @@ -453,7 +462,7 @@ fn boolean_array_to_vector(array: &BooleanArray, out: &mut FlatVector) {
}
}

fn string_array_to_vector(array: &StringArray, out: &mut FlatVector) {
fn string_array_to_vector<O: OffsetSizeTrait>(array: &GenericStringArray<O>, out: &mut FlatVector) {
assert!(array.len() <= out.capacity());

// TODO: zero copy assignment
Expand Down Expand Up @@ -612,9 +621,9 @@ mod test {
use arrow::{
array::{
Array, ArrayRef, AsArray, BinaryArray, Date32Array, Date64Array, Decimal128Array, Decimal256Array,
FixedSizeListArray, GenericListArray, Int32Array, ListArray, OffsetSizeTrait, PrimitiveArray, StringArray,
StructArray, Time32SecondArray, Time64MicrosecondArray, TimestampMicrosecondArray,
TimestampMillisecondArray, TimestampNanosecondArray, TimestampSecondArray,
FixedSizeListArray, GenericListArray, Int32Array, LargeStringArray, ListArray, OffsetSizeTrait,
PrimitiveArray, StringArray, StructArray, Time32SecondArray, Time64MicrosecondArray,
TimestampMicrosecondArray, TimestampMillisecondArray, TimestampNanosecondArray, TimestampSecondArray,
},
buffer::{OffsetBuffer, ScalarBuffer},
datatypes::{i256, ArrowPrimitiveType, DataType, Field, Fields, Schema},
Expand Down Expand Up @@ -862,6 +871,13 @@ mod test {
Ok(())
}

#[test]
fn test_utf8_roundtrip() -> Result<(), Box<dyn Error>> {
check_generic_array_roundtrip(StringArray::from(vec![Some("foo"), None, Some("bar")]))?;
check_generic_array_roundtrip(LargeStringArray::from(vec![Some("foo"), None, Some("bar")]))?;
Ok(())
}

#[test]
fn test_timestamp_roundtrip() -> Result<(), Box<dyn Error>> {
check_rust_primitive_array_roundtrip(Int32Array::from(vec![1, 2, 3]), Int32Array::from(vec![1, 2, 3]))?;
Expand Down