anoopj commented on code in PR #2922:
URL: https://github.com/apache/iceberg-rust/pull/2922#discussion_r3686841320
##########
crates/iceberg/src/spec/manifest_list/manifest_file.rs:
##########
@@ -195,8 +195,61 @@ impl ManifestFile {
entry.inherit_data(self);
}
+ self.assign_first_row_ids(&mut entries)?;
+
Ok(Manifest::new(metadata, entries))
}
+
+ /// Assigns `first_row_id` to data-file entries that do not already have
one,
+ /// starting from the manifest-level `first_row_id` and advancing by each
+ /// entry's record count. See the row-lineage inheritance rules in
+ ///
<https://github.com/apache/iceberg/blob/main/format/spec.md#first-row-id-inheritance>.
+ fn assign_first_row_ids(&self, entries: &mut [ManifestEntry]) ->
Result<()> {
+ let Some(manifest_first_row_id) = self.first_row_id else {
+ return Ok(());
+ };
+
+ // A `first_row_id` is only valid on data manifests; delete files
always
+ // have a null `first_row_id`.
+ if self.content != ManifestContentType::Data {
+ return Err(Error::new(
+ ErrorKind::DataInvalid,
+ format!(
+ "first_row_id is not valid for delete manifests (found
{manifest_first_row_id} on {})",
+ self.manifest_path
+ ),
+ ));
+ }
+
+ let mut next_row_id = i64::try_from(manifest_first_row_id).map_err(|_|
{
+ Error::new(
+ ErrorKind::DataInvalid,
+ format!("Invalid first_row_id: {manifest_first_row_id}
(exceeds i64::MAX)"),
+ )
+ })?;
+
+ for entry in entries {
+ if !entry.is_alive() {
+ continue;
+ }
+
+ if entry.data_file.first_row_id.is_none() {
+ entry.data_file.first_row_id = Some(next_row_id);
+ let record_count = entry.data_file.record_count;
+ next_row_id =
next_row_id.checked_add_unsigned(record_count).ok_or_else(|| {
+ Error::new(
+ ErrorKind::DataInvalid,
+ format!(
+ "Row ID overflow assigning first_row_id in {}.
Next Row ID: {next_row_id}, Record Count: {record_count}",
Review Comment:
Reworded, and introduced a `file_first_row_id` binding so the message names
the triggering file's own id rather than "next".
--
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]
