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

refine: refine interface of ManifestWriter #738

Merged
merged 4 commits into from
Jan 18, 2025
Merged

refine: refine interface of ManifestWriter #738

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
1a4adfc
refine interface of manifest writer:
Dec 19, 2024
19ac4dc
1. add method for data file
Jan 16, 2025
97c0369
make snapshot id optional
Jan 17, 2025
bd71120
refine interface
Jan 17, 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
57 changes: 26 additions & 31 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 @@ -192,9 +192,8 @@ mod tests {
use super::*;
use crate::io::{FileIO, OutputFile};
use crate::spec::{
DataContentType, DataFileBuilder, DataFileFormat, FormatVersion, Literal, Manifest,
ManifestContentType, ManifestEntry, ManifestListWriter, ManifestMetadata, ManifestStatus,
ManifestWriter, Struct, TableMetadata,
DataContentType, DataFileBuilder, DataFileFormat, Literal, ManifestEntry,
ManifestListWriter, ManifestStatus, ManifestWriterBuilder, Struct, TableMetadata,
};
use crate::table::Table;
use crate::TableIdent;
Expand Down Expand Up @@ -264,37 +263,33 @@ mod tests {
let current_partition_spec = self.table.metadata().default_partition_spec();

// Write data files
let data_file_manifest = ManifestWriter::new(
let mut writer = ManifestWriterBuilder::new(
self.next_manifest_file(),
current_snapshot.snapshot_id(),
Some(current_snapshot.snapshot_id()),
vec![],
current_schema.clone(),
current_partition_spec.as_ref().clone(),
)
.write(Manifest::new(
ManifestMetadata::builder()
.schema(current_schema.clone())
.content(ManifestContentType::Data)
.format_version(FormatVersion::V2)
.partition_spec((**current_partition_spec).clone())
.schema_id(current_schema.schema_id())
.build(),
vec![ManifestEntry::builder()
.status(ManifestStatus::Added)
.data_file(
DataFileBuilder::default()
.content(DataContentType::Data)
.file_path(format!("{}/1.parquet", &self.table_location))
.file_format(DataFileFormat::Parquet)
.file_size_in_bytes(100)
.record_count(1)
.partition(Struct::from_iter([Some(Literal::long(100))]))
.key_metadata(None)
.build()
.unwrap(),
)
.build()],
))
.await
.unwrap();
.build_v2_data();
writer
.add_entry(
ManifestEntry::builder()
.status(ManifestStatus::Added)
.data_file(
DataFileBuilder::default()
.content(DataContentType::Data)
.file_path(format!("{}/1.parquet", &self.table_location))
.file_format(DataFileFormat::Parquet)
.file_size_in_bytes(100)
.record_count(1)
.partition(Struct::from_iter([Some(Literal::long(100))]))
.build()
.unwrap(),
)
.build(),
)
.unwrap();
let data_file_manifest = writer.write_manifest_file().await.unwrap();

// Write to manifest list
let mut manifest_list_write = ManifestListWriter::v2(
Expand Down
39 changes: 21 additions & 18 deletions crates/iceberg/src/scan.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -983,9 +983,9 @@ pub mod tests {
use crate::io::{FileIO, OutputFile};
use crate::scan::FileScanTask;
use crate::spec::{
DataContentType, DataFileBuilder, DataFileFormat, Datum, FormatVersion, Literal, Manifest,
ManifestContentType, ManifestEntry, ManifestListWriter, ManifestMetadata, ManifestStatus,
ManifestWriter, NestedField, PrimitiveType, Schema, Struct, TableMetadata, Type,
DataContentType, DataFileBuilder, DataFileFormat, Datum, Literal, ManifestEntry,
ManifestListWriter, ManifestStatus, ManifestWriterBuilder, NestedField, PrimitiveType,
Schema, Struct, TableMetadata, Type,
};
use crate::table::Table;
use crate::TableIdent;
Expand Down Expand Up @@ -1059,20 +1059,16 @@ pub mod tests {
let current_partition_spec = self.table.metadata().default_partition_spec();

// Write data files
let data_file_manifest = ManifestWriter::new(
let mut writer = ManifestWriterBuilder::new(
self.next_manifest_file(),
current_snapshot.snapshot_id(),
Some(current_snapshot.snapshot_id()),
vec![],
current_schema.clone(),
current_partition_spec.as_ref().clone(),
)
.write(Manifest::new(
ManifestMetadata::builder()
.schema(current_schema.clone())
.content(ManifestContentType::Data)
.format_version(FormatVersion::V2)
.partition_spec((**current_partition_spec).clone())
.schema_id(current_schema.schema_id())
.build(),
vec![
.build_v2_data();
writer
.add_entry(
ManifestEntry::builder()
.status(ManifestStatus::Added)
.data_file(
Expand All @@ -1088,6 +1084,10 @@ pub mod tests {
.unwrap(),
)
.build(),
)
.unwrap();
writer
.add_delete_entry(
ManifestEntry::builder()
.status(ManifestStatus::Deleted)
.snapshot_id(parent_snapshot.snapshot_id())
Expand All @@ -1105,6 +1105,10 @@ pub mod tests {
.unwrap(),
)
.build(),
)
.unwrap();
writer
.add_existing_entry(
ManifestEntry::builder()
.status(ManifestStatus::Existing)
.snapshot_id(parent_snapshot.snapshot_id())
Expand All @@ -1122,10 +1126,9 @@ pub mod tests {
.unwrap(),
)
.build(),
],
))
.await
.unwrap();
)
.unwrap();
let data_file_manifest = writer.write_manifest_file().await.unwrap();

// Write to manifest list
let mut manifest_list_write = ManifestListWriter::v2(
Expand Down
Loading
Loading