pvary commented on code in PR #8803:
URL: https://github.com/apache/iceberg/pull/8803#discussion_r1365196098
##########
api/src/main/java/org/apache/iceberg/ContentFile.java:
##########
@@ -165,6 +166,19 @@ default Long fileSequenceNumber() {
*/
F copyWithoutStats();
+ /**
+ * Copies this file with only specific column stats. Manifest readers can
reuse file instances;
+ * use this method to copy data and only copy specific stats when collecting
files.
+ *
+ * @param statsToKeep the collection of the column ids for the columns which
stats are kept
+ * @return a copy of this data file, with stats lower bounds, upper bounds,
value counts, null
+ * value counts, and nan value counts for only specific columns.
+ */
+ default F copyWithSpecificStats(Collection<Integer> statsToKeep) {
Review Comment:
Done
##########
api/src/main/java/org/apache/iceberg/Scan.java:
##########
@@ -77,6 +77,20 @@ public interface Scan<ThisT, T extends ScanTask, G extends
ScanTaskGroup<T>> {
*/
ThisT includeColumnStats();
+ /**
+ * Create a new scan from this that loads the column stats for the specific
columns with each data
+ * file.
+ *
+ * <p>Column stats include: value count, null value count, lower bounds, and
upper bounds.
+ *
+ * @param columns column ids from the table's schema
+ * @return a new scan based on this that loads column stats for specific
columns.
+ */
+ default ThisT includeColumnStats(Collection<Integer> columns) {
Review Comment:
Done
--
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
