Fokko commented on code in PR #349:
URL: https://github.com/apache/iceberg-rust/pull/349#discussion_r1611273092
##########
crates/iceberg/src/transaction.rs:
##########
@@ -121,6 +190,313 @@ impl<'a> Transaction<'a> {
}
}
+/// FastAppendAction is a transaction action for fast append data files to the
table.
+pub struct FastAppendAction<'a> {
+ tx: Transaction<'a>,
+
+ parent_snapshot_id: Option<i64>,
+ snapshot_id: i64,
+ schema: Schema,
+ schema_id: i32,
+ format_version: FormatVersion,
+ partition_spec: PartitionSpec,
+ key_metadata: Vec<u8>,
+
+ commit_uuid: String,
+ manifest_id: i64,
+
+ appended_data_files: Vec<DataFile>,
+}
+
+impl<'a> FastAppendAction<'a> {
+ #[allow(clippy::too_many_arguments)]
+ pub(crate) fn new(
+ tx: Transaction<'a>,
+ parent_snapshot_id: Option<i64>,
+ snapshot_id: i64,
+ schema: Schema,
+ schema_id: i32,
+ format_version: FormatVersion,
+ partition_spec: PartitionSpec,
+ key_metadata: Vec<u8>,
+ commit_uuid: String,
+ ) -> Result<Self> {
+ Ok(Self {
+ tx,
+ parent_snapshot_id,
+ snapshot_id,
+ schema,
+ schema_id,
+ format_version,
+ partition_spec,
+ key_metadata,
+ commit_uuid,
+ manifest_id: 0,
+ appended_data_files: vec![],
+ })
+ }
+
+ // Check if the partition value is compatible with the partition type.
+ fn validate_partition_value(
+ partition_value: &Struct,
+ partition_type: &StructType,
+ ) -> Result<()> {
+ if partition_value.fields().len() != partition_type.fields().len() {
+ return Err(Error::new(
+ ErrorKind::DataInvalid,
+ "Partition value is not compatitable with partition type",
+ ));
+ }
+ if partition_value
+ .fields()
+ .iter()
+ .zip(partition_type.fields())
+ .any(|(field, field_type)|
!field_type.field_type.compatible(field))
+ {
+ return Err(Error::new(
+ ErrorKind::DataInvalid,
+ "Partition value is not compatitable partition type",
+ ));
+ }
+ Ok(())
+ }
+
+ /// Add data files to the snapshot.
+ pub fn add_data_files(
+ &mut self,
+ data_files: impl IntoIterator<Item = DataFile>,
+ ) -> Result<&mut Self> {
+ let data_files: Vec<DataFile> = data_files.into_iter().collect();
+ for data_file in &data_files {
+ if data_file.content_type() != crate::spec::DataContentType::Data {
+ return Err(Error::new(
+ ErrorKind::DataInvalid,
+ "Only data content type is allowed for fast append",
+ ));
+ }
+ Self::validate_partition_value(
+ data_file.partition(),
+ &self.partition_spec.partition_type(&self.schema)?,
+ )?;
+ }
+ self.appended_data_files.extend(data_files);
+ Ok(self)
+ }
+
+ fn generate_manifest_file_path(&mut self) -> String {
+ let manifest_id = self.manifest_id;
+ self.manifest_id += 1;
+ format!(
+ "{}/{}/{}-m{}.{}",
+ self.tx.table.metadata().location(),
+ META_ROOT_PATH,
+ &self.commit_uuid,
+ manifest_id,
+ DataFileFormat::Avro
+ )
+ }
+
+ async fn manifest_from_parent_snapshot(&self) -> Result<Vec<ManifestFile>>
{
Review Comment:
```suggestion
async fn manifests_from_parent_snapshot(&self) ->
Result<Vec<ManifestFile>> {
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org
For additional commands, e-mail: issues-h...@iceberg.apache.org
