anoopj commented on code in PR #2922:
URL: https://github.com/apache/iceberg-rust/pull/2922#discussion_r3687406901
##########
crates/iceberg/src/spec/manifest_list/manifest_file.rs:
##########
@@ -389,4 +436,157 @@ mod test {
.expect_err("load_manifest must fail when decrypting with the
wrong AAD prefix");
assert_eq!(err.kind(), ErrorKind::Unexpected);
}
+
+ /// Builds a data-file manifest entry with the given status, record count,
+ /// and pre-existing `first_row_id`.
+ fn data_entry(
+ status: ManifestStatus,
+ record_count: u64,
+ first_row_id: Option<i64>,
+ ) -> ManifestEntry {
+ let mut builder = DataFileBuilder::default();
+ builder
+ .content(DataContentType::Data)
+ .file_path("s3://bucket/table/data/00000.parquet".to_string())
+ .file_format(DataFileFormat::Parquet)
+ .file_size_in_bytes(4096)
+ .record_count(record_count);
+ if let Some(id) = first_row_id {
+ builder.first_row_id(Some(id));
+ }
+
+ ManifestEntry::builder()
+ .status(status)
+ .data_file(builder.build().unwrap())
+ .build()
+ }
+
+ /// Builds a manifest file with the given content type and manifest-level
+ /// `first_row_id`. Other fields are irrelevant to row-id assignment.
+ fn manifest_file(content: ManifestContentType, first_row_id: Option<u64>)
-> ManifestFile {
+ ManifestFile {
+ manifest_path: "memory:///m.avro".to_string(),
+ manifest_length: 0,
+ partition_spec_id: 0,
+ content,
+ sequence_number: 0,
+ min_sequence_number: 0,
+ added_snapshot_id: 0,
+ added_files_count: None,
+ existing_files_count: None,
+ deleted_files_count: None,
+ added_rows_count: None,
+ existing_rows_count: None,
+ deleted_rows_count: None,
+ partitions: None,
+ key_metadata: None,
+ first_row_id,
+ }
+ }
+
+ #[test]
+ fn test_assign_first_row_ids_interleaved() {
+ let manifest = manifest_file(ManifestContentType::Data, Some(10));
+ let mut entries = vec![
+ data_entry(ManifestStatus::Added, 3, None),
+ // A pre-assigned entry between two assigned ones: it keeps its id
and
+ // must not advance the running counter.
+ data_entry(ManifestStatus::Added, 5, Some(100)),
+ // A deleted entry likewise neither receives nor consumes a row id.
+ data_entry(ManifestStatus::Deleted, 7, None),
Review Comment:
Added. The interleaved test's deleted entry now carries Some(999) and
asserts it survives untouched
--
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]
