This is an automated email from the ASF dual-hosted git repository.
liurenjie1024 pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/iceberg-rust.git
The following commit(s) were added to refs/heads/main by this push:
new 94bed608 feat(catalog): Implement register_table for glue catalog
(#1568)
94bed608 is described below
commit 94bed6088a72cd3c3702b84fe4daa62bc53319f2
Author: Yiyang Chen <[email protected]>
AuthorDate: Wed Aug 27 03:00:00 2025 -0700
feat(catalog): Implement register_table for glue catalog (#1568)
## Which issue does this PR close?
- Closes #1515.
## What changes are included in this PR?
* implemented the register_table method in the Glue catalog.
* added an integration test to cover table registration via metadata
location.
## Are these changes tested?
Yes
* cargo build
* cargo test (including new test case for register_table)
I'm new to Rust and to Iceberg, any feedback or suggestions for
improvement are very welcome! 😊
---
crates/catalog/glue/src/catalog.rs | 65 +++++++++++++++++++++++---
crates/catalog/glue/tests/glue_catalog_test.rs | 32 +++++++++++++
2 files changed, 91 insertions(+), 6 deletions(-)
diff --git a/crates/catalog/glue/src/catalog.rs
b/crates/catalog/glue/src/catalog.rs
index c589cc79..9b383df2 100644
--- a/crates/catalog/glue/src/catalog.rs
+++ b/crates/catalog/glue/src/catalog.rs
@@ -20,6 +20,7 @@ use std::fmt::Debug;
use anyhow::anyhow;
use async_trait::async_trait;
+use aws_sdk_glue::operation::create_table::CreateTableError;
use aws_sdk_glue::operation::update_table::UpdateTableError;
use aws_sdk_glue::types::TableInput;
use iceberg::io::{
@@ -700,15 +701,67 @@ impl Catalog for GlueCatalog {
}
}
+ /// registers an existing table into the Glue Catalog.
+ ///
+ /// Converts the provided table identifier and metadata location into a
+ /// Glue-compatible table representation, and attempts to create the
+ /// corresponding table in the Glue Catalog.
+ ///
+ /// # Returns
+ /// Returns `Ok(Table)` if the table is successfully registered and loaded.
+ /// If the registration fails due to validation issues, existing table
conflicts,
+ /// metadata problems, or errors during the registration or loading
process,
+ /// an `Err(...)` is returned.
async fn register_table(
&self,
- _table_ident: &TableIdent,
- _metadata_location: String,
+ table_ident: &TableIdent,
+ metadata_location: String,
) -> Result<Table> {
- Err(Error::new(
- ErrorKind::FeatureUnsupported,
- "Registering a table is not supported yet",
- ))
+ let db_name = validate_namespace(table_ident.namespace())?;
+ let table_name = table_ident.name();
+ let metadata = TableMetadata::read_from(&self.file_io,
&metadata_location).await?;
+
+ let table_input = convert_to_glue_table(
+ table_name,
+ metadata_location.clone(),
+ &metadata,
+ metadata.properties(),
+ None,
+ )?;
+
+ let builder = self
+ .client
+ .0
+ .create_table()
+ .database_name(&db_name)
+ .table_input(table_input);
+ let builder = with_catalog_id!(builder, self.config);
+
+ builder.send().await.map_err(|e| {
+ let error = e.into_service_error();
+ match error {
+ CreateTableError::EntityNotFoundException(_) => Error::new(
+ ErrorKind::NamespaceNotFound,
+ format!("Database {db_name} does not exist"),
+ ),
+ CreateTableError::AlreadyExistsException(_) => Error::new(
+ ErrorKind::TableAlreadyExists,
+ format!("Table {table_ident} already exists"),
+ ),
+ _ => Error::new(
+ ErrorKind::Unexpected,
+ format!("Failed to register table {table_ident} due to AWS
SDK error"),
+ ),
+ }
+ .with_source(anyhow!("aws sdk error: {:?}", error))
+ })?;
+
+ Ok(Table::builder()
+ .identifier(table_ident.clone())
+ .metadata_location(metadata_location)
+ .metadata(metadata)
+ .file_io(self.file_io())
+ .build()?)
}
async fn update_table(&self, commit: TableCommit) -> Result<Table> {
diff --git a/crates/catalog/glue/tests/glue_catalog_test.rs
b/crates/catalog/glue/tests/glue_catalog_test.rs
index 3141a271..548fc4f0 100644
--- a/crates/catalog/glue/tests/glue_catalog_test.rs
+++ b/crates/catalog/glue/tests/glue_catalog_test.rs
@@ -469,3 +469,35 @@ async fn test_update_table() -> Result<()> {
Ok(())
}
+
+#[tokio::test]
+async fn test_register_table() -> Result<()> {
+ let catalog = get_catalog().await;
+ let namespace = NamespaceIdent::new("test_register_table".into());
+ set_test_namespace(&catalog, &namespace).await?;
+
+ let creation = set_table_creation(
+ Some("s3a://warehouse/hive/test_register_table".into()),
+ "my_table",
+ )?;
+ let table = catalog.create_table(&namespace, creation).await?;
+ let metadata_location = table
+ .metadata_location()
+ .expect("Expected metadata location to be set")
+ .to_string();
+
+ catalog.drop_table(table.identifier()).await?;
+ let ident = TableIdent::new(namespace.clone(), "my_table".to_string());
+
+ let registered = catalog
+ .register_table(&ident, metadata_location.clone())
+ .await?;
+
+ assert_eq!(registered.identifier(), &ident);
+ assert_eq!(
+ registered.metadata_location(),
+ Some(metadata_location.as_str())
+ );
+
+ Ok(())
+}
