Skip to content

[rust] Decode only selected columns in remote Arrow logs #4922

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

Open
spoon-lz wants to merge 1 commit into
base: main
Choose a base branch
from
+327 −45
Open

[rust] Decode only selected columns in remote Arrow logs #4922

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
9 changes: 8 additions & 1 deletion fluss-rust/crates/fluss/src/client/table/log_fetch_buffer.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1551,7 +1551,14 @@ mod tests {
tables.push(table);
}
let target = &tables[2];
for fields in [vec![0], vec![2], vec![2, 0], vec![1, 0], vec![2, 1, 0]] {
for fields in [
vec![0],
vec![2],
vec![2, 0],
vec![1, 0],
vec![2, 1, 0],
vec![2, 0, 2],
] {
let full_schema = to_arrow_schema(target.get_row_type())?;
let output_schema = ReadContext::project_schema(full_schema.clone(), &fields)?;
let row_type = Arc::new(target.get_row_type().project(&fields)?);
Expand Down
90 changes: 66 additions & 24 deletions fluss-rust/crates/fluss/src/client/table/scanner.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2745,6 +2745,26 @@ mod tests {
}

async fn check_poll_remote_projection(batch_mode: bool) -> Result<()> {
for compression in ["NONE", "LZ4_FRAME", "ZSTD"] {
for fields in [
vec![2, 1, 0],
vec![0],
vec![1],
vec![2],
vec![2, 0, 2],
vec![0, 1, 2],
] {
check_poll_remote_projection_case(batch_mode, &fields, compression).await?;
}
}
Ok(())
}

async fn check_poll_remote_projection_case(
batch_mode: bool,
fields: &[usize],
compression: &str,
) -> Result<()> {
use crate::metadata::DataField;
use crate::row::DataGetters;
use crate::test_utils::build_table_info_with_columns;
Expand All @@ -2771,10 +2791,14 @@ mod tests {
],
);
target.schema_id = 2;
let mut builder = MemoryLogRecordsArrowBuilder::new(
uncompressed_arrow_batch_config(1, source.get_row_type(), usize::MAX),
false,
let mut config = uncompressed_arrow_batch_config(1, source.get_row_type(), usize::MAX);
config.compression = crate::compression::ArrowCompressionInfo::from_conf(
&std::collections::HashMap::from([(
"table.log.arrow.compression.type".to_string(),
compression.to_string(),
)]),
)?;
let mut builder = MemoryLogRecordsArrowBuilder::new(config, false)?;
for name in [Some("alice"), None] {
let mut row = GenericRow::new(2);
row.set_field(0, 7_i32);
Expand All @@ -2796,7 +2820,7 @@ mod tests {
Arc::clone(&metadata),
Arc::new(RpcClient::new()),
&Config::default(),
Some(vec![2, 1, 0]),
Some(fields.to_vec()),
fixed_schema,
None,
test_admin(&metadata),
Expand All @@ -2809,7 +2833,7 @@ mod tests {
Arc::clone(&metadata),
Arc::clone(&inner.log_scanner_status),
&Config::default(),
Some(vec![2, 1, 0]),
Some(fields.to_vec()),
fixed_schema,
None,
test_scanner_metrics(&table_path),
Expand Down Expand Up @@ -2846,23 +2870,32 @@ mod tests {
let batch = batches[0].batch();
assert_eq!(
batch.schema(),
to_arrow_schema(&target.get_row_type().project(&[2, 1, 0])?)?
to_arrow_schema(&target.get_row_type().project(fields)?)?
);
assert_eq!(batch.num_rows(), 2);
assert_eq!(batch.column(0).null_count(), 2);
let names = batch
.column(1)
.as_any()
.downcast_ref::<StringArray>()
.unwrap();
assert_eq!(names.value(0), "alice");
assert!(names.is_null(1));
let ids = batch
.column(2)
.as_any()
.downcast_ref::<Int32Array>()
.unwrap();
assert_eq!(ids.values().as_ref(), &[7, 7]);
for (column, field) in fields.iter().enumerate() {
match field {
0 => {
let ids = batch
.column(column)
.as_any()
.downcast_ref::<Int32Array>()
.unwrap();
assert_eq!(ids.values().as_ref(), &[7, 7]);
}
1 => {
let names = batch
.column(column)
.as_any()
.downcast_ref::<StringArray>()
.unwrap();
assert_eq!(names.value(0), "alice");
assert!(names.is_null(1));
}
2 => assert_eq!(batch.column(column).null_count(), 2),
_ => unreachable!(),
}
}
assert!(scanner.poll(Duration::ZERO).await?.is_empty());
} else {
let scanner = LogScanner {
Expand All @@ -2873,11 +2906,20 @@ mod tests {
assert_eq!(records.len(), 2);
for (index, record) in records.iter().enumerate() {
assert_eq!(record.offset(), index as i64);
assert!(record.row.is_null_at(0)?);
assert_eq!(record.row.is_null_at(1)?, index == 1);
assert_eq!(record.row.get_int(2)?, 7);
for (column, field) in fields.iter().enumerate() {
match field {
0 => assert_eq!(record.row.get_int(column)?, 7),
1 => {
assert_eq!(record.row.is_null_at(column)?, index == 1);
if index == 0 {
assert_eq!(record.row.get_string(column)?, "alice");
}
}
2 => assert!(record.row.is_null_at(column)?),
_ => unreachable!(),
}
}
}
assert_eq!(records[0].row.get_string(1)?, "alice");
assert!(scanner.poll(Duration::ZERO).await?.is_empty());
}
assert!(fetcher.resolver.resolve(1, true).is_some());
Expand Down
Loading
Loading