Skip to content

feat: add process delete enrty in snapshot produce #33

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
merged 5 commits into from
Mar 18, 2025
Merged

feat: add process delete enrty in snapshot produce #33

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
9fb7626
support spec id in data file
ZENOTME Mar 14, 2025
d82c2f3
support proccess delete entry
ZENOTME Mar 14, 2025
59af94f
fullfill partition spec id
ZENOTME Mar 17, 2025
55d772b
fix
ZENOTME Mar 18, 2025
fc5e7d3
fix spelling mistake
ZENOTME Mar 18, 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
6 changes: 5 additions & 1 deletion crates/iceberg/src/arrow/record_batch_partition_spliter.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,7 @@ use parquet::arrow::PARQUET_FIELD_ID_META_KEY;

use super::record_batch_projector::RecordBatchProjector;
use crate::arrow::{arrow_struct_to_literal, type_to_arrow_type};
use crate::spec::{Literal, PartitionSpecRef, SchemaRef, Struct, StructType, Type};
use crate::spec::{Literal, PartitionSpec, PartitionSpecRef, SchemaRef, Struct, StructType, Type};
use crate::transform::{create_transform_function, BoxedTransformFunction};
use crate::{Error, ErrorKind, Result};

Expand Down Expand Up @@ -186,6 +186,10 @@ impl RecordBatchPartitionSpliter {
})
}

pub(crate) fn partition_spec(&self) -> &PartitionSpec {
self.partition_spec.as_ref()
}

/// Split the record batch into multiple record batches by the partition spec.
pub(crate) fn split(&self, batch: &RecordBatch) -> Result<Vec<(OwnedRow, RecordBatch)>> {
// get array using partition spec
Expand Down
2 changes: 2 additions & 0 deletions crates/iceberg/src/expr/visitors/expression_evaluator.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -346,6 +346,7 @@ mod tests {
split_offsets: vec![],
equality_ids: vec![],
sort_order_id: None,
partition_spec_id: 0,
}
}

Expand All @@ -369,6 +370,7 @@ mod tests {
split_offsets: vec![],
equality_ids: vec![],
sort_order_id: None,
partition_spec_id: 0,
}
}

Expand Down
6 changes: 6 additions & 0 deletions crates/iceberg/src/expr/visitors/inclusive_metrics_evaluator.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1996,6 +1996,7 @@ mod test {
split_offsets: vec![],
equality_ids: vec![],
sort_order_id: None,
partition_spec_id: 0,
}
}

Expand All @@ -2017,6 +2018,7 @@ mod test {
split_offsets: vec![],
equality_ids: vec![],
sort_order_id: None,
partition_spec_id: 0,
}
}

Expand Down Expand Up @@ -2074,6 +2076,7 @@ mod test {
split_offsets: vec![],
equality_ids: vec![],
sort_order_id: None,
partition_spec_id: 0,
}
}
fn get_test_file_2() -> DataFile {
Expand All @@ -2100,6 +2103,7 @@ mod test {
split_offsets: vec![],
equality_ids: vec![],
sort_order_id: None,
partition_spec_id: 0,
}
}

Expand Down Expand Up @@ -2127,6 +2131,7 @@ mod test {
split_offsets: vec![],
equality_ids: vec![],
sort_order_id: None,
partition_spec_id: 0,
}
}

Expand Down Expand Up @@ -2154,6 +2159,7 @@ mod test {
split_offsets: vec![],
equality_ids: vec![],
sort_order_id: None,
partition_spec_id: 0,
}
}
}
4 changes: 4 additions & 0 deletions crates/iceberg/src/expr/visitors/strict_metrics_evaluator.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -581,6 +581,7 @@ mod test {
split_offsets: vec![],
equality_ids: vec![],
sort_order_id: None,
partition_spec_id: 0,
}
}

Expand All @@ -602,6 +603,7 @@ mod test {
split_offsets: vec![],
equality_ids: vec![],
sort_order_id: None,
partition_spec_id: 0,
}
}

Expand All @@ -623,6 +625,7 @@ mod test {
split_offsets: vec![],
equality_ids: vec![],
sort_order_id: None,
partition_spec_id: 0,
}
}

Expand All @@ -645,6 +648,7 @@ mod test {
split_offsets: vec![],
equality_ids: vec![],
sort_order_id: None,
partition_spec_id: 0,
}
}

Expand Down
1 change: 1 addition & 0 deletions crates/iceberg/src/io/object_cache.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -277,6 +277,7 @@ mod tests {
.status(ManifestStatus::Added)
.data_file(
DataFileBuilder::default()
.partition_spec_id(0)
.content(DataContentType::Data)
.file_path(format!("{}/1.parquet", &self.table_location))
.file_format(DataFileFormat::Parquet)
Expand Down
6 changes: 6 additions & 0 deletions crates/iceberg/src/scan.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1308,6 +1308,7 @@ pub mod tests {
.status(ManifestStatus::Added)
.data_file(
DataFileBuilder::default()
.partition_spec_id(0)
.content(DataContentType::Data)
.file_path(format!("{}/1.parquet", &self.table_location))
.file_format(DataFileFormat::Parquet)
Expand All @@ -1330,6 +1331,7 @@ pub mod tests {
.file_sequence_number(parent_snapshot.sequence_number())
.data_file(
DataFileBuilder::default()
.partition_spec_id(0)
.content(DataContentType::Data)
.file_path(format!("{}/2.parquet", &self.table_location))
.file_format(DataFileFormat::Parquet)
Expand All @@ -1351,6 +1353,7 @@ pub mod tests {
.file_sequence_number(parent_snapshot.sequence_number())
.data_file(
DataFileBuilder::default()
.partition_spec_id(0)
.content(DataContentType::Data)
.file_path(format!("{}/3.parquet", &self.table_location))
.file_format(DataFileFormat::Parquet)
Expand Down Expand Up @@ -1521,6 +1524,7 @@ pub mod tests {
.status(ManifestStatus::Added)
.data_file(
DataFileBuilder::default()
.partition_spec_id(0)
.content(DataContentType::Data)
.file_path(format!("{}/1.parquet", &self.table_location))
.file_format(DataFileFormat::Parquet)
Expand All @@ -1544,6 +1548,7 @@ pub mod tests {
.file_sequence_number(parent_snapshot.sequence_number())
.data_file(
DataFileBuilder::default()
.partition_spec_id(0)
.content(DataContentType::Data)
.file_path(format!("{}/2.parquet", &self.table_location))
.file_format(DataFileFormat::Parquet)
Expand All @@ -1566,6 +1571,7 @@ pub mod tests {
.file_sequence_number(parent_snapshot.sequence_number())
.data_file(
DataFileBuilder::default()
.partition_spec_id(0)
.content(DataContentType::Data)
.file_path(format!("{}/3.parquet", &self.table_location))
.file_format(DataFileFormat::Parquet)
Expand Down
Loading
Loading