Skip to content

Add Utf8View support #296

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

Merged
returnString merged 2 commits into from
Apr 28, 2025
Merged

Add Utf8View support #296

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
2caa023
Add Utf8 support
mshauneu Apr 25, 2025
dcd7c87
Unpin chrono
mshauneu Apr 26, 2025
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
2 changes: 2 additions & 0 deletions .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,2 +1,4 @@
/target
Cargo.lock
.idea/

5 changes: 3 additions & 2 deletions convergence-arrow/src/table.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@ use convergence::protocol::{DataTypeOid, ErrorResponse, FieldDescription, SqlSta
use convergence::protocol_ext::DataRowBatch;
use datafusion::arrow::array::{
BooleanArray, Date32Array, Date64Array, Float16Array, Float32Array, Float64Array, Int16Array, Int32Array,
Int64Array, Int8Array, StringArray, TimestampMicrosecondArray, TimestampMillisecondArray, TimestampNanosecondArray,
Int64Array, Int8Array, StringArray, StringViewArray, TimestampMicrosecondArray, TimestampMillisecondArray, TimestampNanosecondArray,
TimestampSecondArray, UInt16Array, UInt32Array, UInt64Array, UInt8Array,
};
use datafusion::arrow::datatypes::{DataType, Schema, TimeUnit};
Expand Down Expand Up @@ -48,6 +48,7 @@ pub fn record_batch_to_rows(arrow_batch: &RecordBatch, pg_batch: &mut DataRowBat
DataType::Float32 => row.write_float4(array_val!(Float32Array, col, row_idx)),
DataType::Float64 => row.write_float8(array_val!(Float64Array, col, row_idx)),
DataType::Utf8 => row.write_string(array_val!(StringArray, col, row_idx)),
DataType::Utf8View => row.write_string(array_val!(StringViewArray, col, row_idx)),
DataType::Date32 => {
row.write_date(array_val!(Date32Array, col, row_idx, value_as_date).ok_or_else(|| {
ErrorResponse::error(SqlState::InvalidDatetimeFormat, "unsupported date type")
Expand Down Expand Up @@ -102,7 +103,7 @@ pub fn data_type_to_oid(ty: &DataType) -> Result<DataTypeOid, ErrorResponse> {
DataType::UInt64 => DataTypeOid::Int8,
DataType::Float16 | DataType::Float32 => DataTypeOid::Float4,
DataType::Float64 => DataTypeOid::Float8,
DataType::Utf8 => DataTypeOid::Text,
DataType::Utf8 | DataType::Utf8View => DataTypeOid::Text,
DataType::Date32 | DataType::Date64 => DataTypeOid::Date,
DataType::Timestamp(_, None) => DataTypeOid::Timestamp,
other => {
Expand Down
13 changes: 9 additions & 4 deletions convergence-arrow/tests/test_arrow.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,7 @@ use convergence::protocol_ext::DataRowBatch;
use convergence::server::{self, BindOptions};
use convergence::sqlparser::ast::Statement;
use convergence_arrow::table::{record_batch_to_rows, schema_to_field_desc};
use datafusion::arrow::array::{ArrayRef, Date32Array, Float32Array, Int32Array, StringArray, TimestampSecondArray};
use datafusion::arrow::array::{ArrayRef, Date32Array, Float32Array, Int32Array, StringArray, StringViewArray, TimestampSecondArray};
use datafusion::arrow::datatypes::{DataType, Field, Schema, TimeUnit};
use datafusion::arrow::record_batch::RecordBatch;
use std::sync::Arc;
Expand All @@ -32,19 +32,21 @@ impl ArrowEngine {
let int_col = Arc::new(Int32Array::from(vec![1, 2, 3])) as ArrayRef;
let float_col = Arc::new(Float32Array::from(vec![1.5, 2.5, 3.5])) as ArrayRef;
let string_col = Arc::new(StringArray::from(vec!["a", "b", "c"])) as ArrayRef;
let string_view_col = Arc::new(StringViewArray::from(vec!["aa", "bb", "cc"])) as ArrayRef;
let ts_col = Arc::new(TimestampSecondArray::from(vec![1577836800, 1580515200, 1583020800])) as ArrayRef;
let date_col = Arc::new(Date32Array::from(vec![0, 1, 2])) as ArrayRef;

let schema = Schema::new(vec![
Field::new("int_col", DataType::Int32, true),
Field::new("float_col", DataType::Float32, true),
Field::new("string_col", DataType::Utf8, true),
Field::new("string_view_col", DataType::Utf8View, true),
Field::new("ts_col", DataType::Timestamp(TimeUnit::Second, None), true),
Field::new("date_col", DataType::Date32, true),
]);

Self {
batch: RecordBatch::try_new(Arc::new(schema), vec![int_col, float_col, string_col, ts_col, date_col])
batch: RecordBatch::try_new(Arc::new(schema), vec![int_col, float_col, string_col, string_view_col, ts_col, date_col])
.expect("failed to create batch"),
}
}
Expand Down Expand Up @@ -89,8 +91,8 @@ async fn basic_data_types() {
let rows = client.query("select 1", &[]).await.unwrap();
let get_row = |idx: usize| {
let row = &rows[idx];
let cols: (i32, f32, &str, NaiveDateTime, NaiveDate) =
(row.get(0), row.get(1), row.get(2), row.get(3), row.get(4));
let cols: (i32, f32, &str, &str, NaiveDateTime, NaiveDate) =
(row.get(0), row.get(1), row.get(2), row.get(3), row.get(4), row.get(5));
cols
};

Expand All @@ -100,6 +102,7 @@ async fn basic_data_types() {
1,
1.5,
"a",
"aa",
NaiveDate::from_ymd_opt(2020, 1, 1)
.unwrap()
.and_hms_opt(0, 0, 0)
Expand All @@ -113,6 +116,7 @@ async fn basic_data_types() {
2,
2.5,
"b",
"bb",
NaiveDate::from_ymd_opt(2020, 2, 1)
.unwrap()
.and_hms_opt(0, 0, 0)
Expand All @@ -126,6 +130,7 @@ async fn basic_data_types() {
3,
3.5,
"c",
"cc",
NaiveDate::from_ymd_opt(2020, 3, 1)
.unwrap()
.and_hms_opt(0, 0, 0)
Expand Down
Loading