blackmwk commented on code in PR #3145:
URL: https://github.com/apache/iceberg-rust/pull/3145#discussion_r3947405474
##########
crates/iceberg/src/scan/task.rs:
##########
@@ -400,7 +404,145 @@ pub struct FileScanTaskDeleteFile {
#[serde(default)]
#[serde(skip_serializing_if = "Option::is_none")]
#[builder(default)]
- pub key_metadata: Option<Box<[u8]>>,
+ key_metadata: Option<Box<[u8]>>,
+}
+
+impl FileScanTaskDeleteFile {
+ /// Returns the delete file path.
+ pub fn file_path(&self) -> &str {
+ &self.file_path
+ }
+
+ /// Returns the total size of the delete file in bytes.
+ pub fn file_size_in_bytes(&self) -> u64 {
+ self.file_size_in_bytes
+ }
+
+ /// Returns the delete file content type.
+ pub fn file_type(&self) -> DataContentType {
+ self.file_type
+ }
+
+ /// Returns the delete file format.
+ pub fn file_format(&self) -> DataFileFormat {
+ self.file_format
+ }
+
+ /// Returns the partition spec id.
+ pub fn partition_spec_id(&self) -> i32 {
+ self.partition_spec_id
+ }
+
+ /// Returns the equality field ids for an equality delete file.
+ pub fn equality_ids(&self) -> Option<&[i32]> {
+ self.equality_ids.as_deref()
+ }
+
+ /// Returns the referenced data file path.
+ pub fn referenced_data_file(&self) -> Option<&str> {
+ self.referenced_data_file.as_deref()
+ }
+
+ /// Returns the deletion vector blob offset.
+ pub fn content_offset(&self) -> Option<i64> {
+ self.content_offset
+ }
+
+ /// Returns the deletion vector blob size in bytes.
+ pub fn content_size_in_bytes(&self) -> Option<i64> {
+ self.content_size_in_bytes
+ }
+
+ /// Returns the number of records in the delete file.
+ pub fn record_count(&self) -> Option<u64> {
+ self.record_count
+ }
+
+ /// Returns the key metadata for the encrypted delete file.
+ pub fn key_metadata(&self) -> Option<&[u8]> {
+ self.key_metadata.as_deref()
+ }
+
+ fn is_deletion_vector(&self) -> bool {
+ self.file_type == DataContentType::PositionDeletes
+ && self.file_format == DataFileFormat::Puffin
+ }
+
+ fn validate(&self) -> Result<()> {
+ if !self.is_deletion_vector() {
+ return Ok(());
+ }
+
+ if self.referenced_data_file.is_none() {
+ return Err(Error::new(
+ ErrorKind::DataInvalid,
+ format!(
+ "deletion vector {} is missing referenced_data_file",
+ self.file_path
+ ),
+ ));
+ }
+
+ match self.content_offset {
+ None => {
+ return Err(Error::new(
+ ErrorKind::DataInvalid,
+ format!(
+ "deletion vector {} is missing content_offset",
+ self.file_path
+ ),
+ ));
+ }
+ Some(offset) if offset < 0 => {
+ return Err(Error::new(
+ ErrorKind::DataInvalid,
+ format!(
+ "deletion vector {} has negative content_offset {}",
+ self.file_path, offset
+ ),
+ ));
+ }
+ Some(_) => {}
+ }
+
+ match self.content_size_in_bytes {
+ None => {
+ return Err(Error::new(
+ ErrorKind::DataInvalid,
+ format!(
+ "deletion vector {} is missing content_size_in_bytes",
+ self.file_path
+ ),
+ ));
+ }
+ Some(size) if size < 0 => {
+ return Err(Error::new(
+ ErrorKind::DataInvalid,
+ format!(
+ "deletion vector {} has negative content_size_in_bytes
{}",
+ self.file_path, size
+ ),
+ ));
+ }
+ Some(_) => {}
+ }
+
+ if self.record_count.is_none() {
Review Comment:
I think this should also apply to non deletion vector? Also why not remove
the Option
##########
crates/iceberg/src/scan/task.rs:
##########
@@ -400,7 +404,145 @@ pub struct FileScanTaskDeleteFile {
#[serde(default)]
#[serde(skip_serializing_if = "Option::is_none")]
#[builder(default)]
- pub key_metadata: Option<Box<[u8]>>,
+ key_metadata: Option<Box<[u8]>>,
+}
+
+impl FileScanTaskDeleteFile {
+ /// Returns the delete file path.
+ pub fn file_path(&self) -> &str {
+ &self.file_path
+ }
+
+ /// Returns the total size of the delete file in bytes.
+ pub fn file_size_in_bytes(&self) -> u64 {
+ self.file_size_in_bytes
+ }
+
+ /// Returns the delete file content type.
+ pub fn file_type(&self) -> DataContentType {
+ self.file_type
+ }
+
+ /// Returns the delete file format.
+ pub fn file_format(&self) -> DataFileFormat {
+ self.file_format
+ }
+
+ /// Returns the partition spec id.
+ pub fn partition_spec_id(&self) -> i32 {
+ self.partition_spec_id
+ }
+
+ /// Returns the equality field ids for an equality delete file.
+ pub fn equality_ids(&self) -> Option<&[i32]> {
+ self.equality_ids.as_deref()
+ }
+
+ /// Returns the referenced data file path.
+ pub fn referenced_data_file(&self) -> Option<&str> {
+ self.referenced_data_file.as_deref()
+ }
+
+ /// Returns the deletion vector blob offset.
+ pub fn content_offset(&self) -> Option<i64> {
+ self.content_offset
+ }
+
+ /// Returns the deletion vector blob size in bytes.
+ pub fn content_size_in_bytes(&self) -> Option<i64> {
+ self.content_size_in_bytes
+ }
+
+ /// Returns the number of records in the delete file.
+ pub fn record_count(&self) -> Option<u64> {
+ self.record_count
+ }
+
+ /// Returns the key metadata for the encrypted delete file.
+ pub fn key_metadata(&self) -> Option<&[u8]> {
+ self.key_metadata.as_deref()
+ }
+
+ fn is_deletion_vector(&self) -> bool {
+ self.file_type == DataContentType::PositionDeletes
+ && self.file_format == DataFileFormat::Puffin
+ }
+
+ fn validate(&self) -> Result<()> {
+ if !self.is_deletion_vector() {
+ return Ok(());
+ }
+
+ if self.referenced_data_file.is_none() {
+ return Err(Error::new(
+ ErrorKind::DataInvalid,
+ format!(
+ "deletion vector {} is missing referenced_data_file",
+ self.file_path
+ ),
+ ));
+ }
+
+ match self.content_offset {
+ None => {
+ return Err(Error::new(
+ ErrorKind::DataInvalid,
+ format!(
+ "deletion vector {} is missing content_offset",
+ self.file_path
+ ),
+ ));
+ }
+ Some(offset) if offset < 0 => {
+ return Err(Error::new(
+ ErrorKind::DataInvalid,
+ format!(
+ "deletion vector {} has negative content_offset {}",
+ self.file_path, offset
+ ),
+ ));
+ }
+ Some(_) => {}
+ }
+
+ match self.content_size_in_bytes {
Review Comment:
See above
##########
crates/iceberg/src/scan/task.rs:
##########
@@ -400,7 +404,145 @@ pub struct FileScanTaskDeleteFile {
#[serde(default)]
#[serde(skip_serializing_if = "Option::is_none")]
#[builder(default)]
- pub key_metadata: Option<Box<[u8]>>,
+ key_metadata: Option<Box<[u8]>>,
+}
+
+impl FileScanTaskDeleteFile {
+ /// Returns the delete file path.
+ pub fn file_path(&self) -> &str {
+ &self.file_path
+ }
+
+ /// Returns the total size of the delete file in bytes.
+ pub fn file_size_in_bytes(&self) -> u64 {
+ self.file_size_in_bytes
+ }
+
+ /// Returns the delete file content type.
+ pub fn file_type(&self) -> DataContentType {
+ self.file_type
+ }
+
+ /// Returns the delete file format.
+ pub fn file_format(&self) -> DataFileFormat {
+ self.file_format
+ }
+
+ /// Returns the partition spec id.
+ pub fn partition_spec_id(&self) -> i32 {
+ self.partition_spec_id
+ }
+
+ /// Returns the equality field ids for an equality delete file.
+ pub fn equality_ids(&self) -> Option<&[i32]> {
+ self.equality_ids.as_deref()
+ }
+
+ /// Returns the referenced data file path.
+ pub fn referenced_data_file(&self) -> Option<&str> {
+ self.referenced_data_file.as_deref()
+ }
+
+ /// Returns the deletion vector blob offset.
+ pub fn content_offset(&self) -> Option<i64> {
+ self.content_offset
+ }
+
+ /// Returns the deletion vector blob size in bytes.
+ pub fn content_size_in_bytes(&self) -> Option<i64> {
+ self.content_size_in_bytes
+ }
+
+ /// Returns the number of records in the delete file.
+ pub fn record_count(&self) -> Option<u64> {
+ self.record_count
+ }
+
+ /// Returns the key metadata for the encrypted delete file.
+ pub fn key_metadata(&self) -> Option<&[u8]> {
+ self.key_metadata.as_deref()
+ }
+
+ fn is_deletion_vector(&self) -> bool {
+ self.file_type == DataContentType::PositionDeletes
+ && self.file_format == DataFileFormat::Puffin
+ }
+
+ fn validate(&self) -> Result<()> {
+ if !self.is_deletion_vector() {
+ return Ok(());
+ }
+
+ if self.referenced_data_file.is_none() {
+ return Err(Error::new(
+ ErrorKind::DataInvalid,
+ format!(
+ "deletion vector {} is missing referenced_data_file",
+ self.file_path
+ ),
+ ));
+ }
+
+ match self.content_offset {
Review Comment:
1. I think this check should also apply to non deletion vector?
2. Why not make offset usize?
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
