karuppayya commented on code in PR #11035:
URL: https://github.com/apache/iceberg/pull/11035#discussion_r1734965325
##########
spark/v3.5/spark/src/main/java/org/apache/iceberg/spark/source/SparkScan.java:
##########
@@ -199,28 +199,24 @@ protected Statistics estimateStatistics(Snapshot
snapshot) {
List<BlobMetadata> metadataList = (files.get(0)).blobMetadata();
for (BlobMetadata blobMetadata : metadataList) {
- int id = blobMetadata.fields().get(0);
- String colName = table.schema().findColumnName(id);
- NamedReference ref = FieldReference.column(colName);
-
- Long ndv = null;
if (blobMetadata
.type()
.equals(org.apache.iceberg.puffin.StandardBlobTypes.APACHE_DATASKETCHES_THETA_V1))
{
+ int id = blobMetadata.fields().get(0);
+ String colName = table.schema().findColumnName(id);
+ NamedReference ref = FieldReference.column(colName);
+ Long ndv = null;
String ndvStr = blobMetadata.properties().get(NDV_KEY);
if (!Strings.isNullOrEmpty(ndvStr)) {
ndv = Long.parseLong(ndvStr);
} else {
LOG.debug("ndv is not set in BlobMetadata for column {}",
colName);
}
- } else {
- LOG.debug("DataSketch blob is not available for column {}",
colName);
- }
+ ColumnStatistics colStats =
Review Comment:
+1
##########
core/src/main/java/org/apache/iceberg/puffin/StandardBlobTypes.java:
##########
@@ -26,4 +26,6 @@ private StandardBlobTypes() {}
* href="https://datasketches.apache.org/";>Apache DataSketches</a> library
*/
public static final String APACHE_DATASKETCHES_THETA_V1 =
"apache-datasketches-theta-v1";
+
+ public static final String PRESTO_SUM_DATA_SIZE_BYTES_V1 =
"presto-sum-data-size-bytes-v1";
Review Comment:
I think we should remove this since Iceberg doesn't support this yet
--
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
