jeesou commented on code in PR #11035:
URL: https://github.com/apache/iceberg/pull/11035#discussion_r1770621280
##########
spark/v3.5/spark/src/main/java/org/apache/iceberg/spark/source/SparkScan.java:
##########
@@ -198,27 +198,31 @@ protected Statistics estimateStatistics(Snapshot
snapshot) {
if (!files.isEmpty()) {
List<BlobMetadata> metadataList = (files.get(0)).blobMetadata();
- for (BlobMetadata blobMetadata : metadataList) {
- int id = blobMetadata.fields().get(0);
- String colName = table.schema().findColumnName(id);
+ Map<Integer, List<BlobMetadata>> groupedByField =
+ metadataList.stream()
+ .collect(
+ Collectors.groupingBy(
+ metadata -> metadata.fields().get(0),
Collectors.toList()));
+
+ for (Map.Entry<Integer, List<BlobMetadata>> entry :
groupedByField.entrySet()) {
+ String colName = table.schema().findColumnName(entry.getKey());
NamedReference ref = FieldReference.column(colName);
-
Long ndv = null;
- if (blobMetadata
- .type()
-
.equals(org.apache.iceberg.puffin.StandardBlobTypes.APACHE_DATASKETCHES_THETA_V1))
{
- 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);
+
+ for (BlobMetadata blobMetadata : entry.getValue()) {
+ if (blobMetadata
+ .type()
+
.equals(org.apache.iceberg.puffin.StandardBlobTypes.APACHE_DATASKETCHES_THETA_V1))
{
+ 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 =
- new SparkColumnStatistics(ndv, null, null, null, null, null,
null);
+ new SparkColumnStatistics(ndv, null, null, null, null, null,
null);
Review Comment:
Corrected.
--
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
