simhadri-g commented on code in PR #4131:
URL: https://github.com/apache/hive/pull/4131#discussion_r1161856412
##########
iceberg/iceberg-handler/src/main/java/org/apache/iceberg/mr/hive/HiveIcebergStorageHandler.java:
##########
@@ -361,6 +378,83 @@ private Table
getTable(org.apache.hadoop.hive.ql.metadata.Table hmsTable) {
return table;
}
+
+ @Override
+ public boolean canSetColStatistics() {
+ return getStatsSource().equals(ICEBERG);
+ }
+
+ @Override
+ public boolean
canProvideColStatistics(org.apache.hadoop.hive.ql.metadata.Table hmsTable) {
+ Table table = Catalogs.loadTable(conf,
Utilities.getTableDesc(hmsTable).getProperties());
+ if (table.currentSnapshot() != null) {
+ Path statsPath = getStatsPath(table);
+ if (getStatsSource().equals(ICEBERG)) {
+ try (FileSystem fs = statsPath.getFileSystem(conf)) {
+ if (fs.exists(statsPath)) {
+ return true;
+ }
+ } catch (IOException e) {
+ LOG.warn(e.getMessage());
+ }
+ }
+ }
+ return false;
+ }
+
+ @Override
+ public List<ColumnStatisticsObj>
getColStatistics(org.apache.hadoop.hive.ql.metadata.Table hmsTable) {
+ Table table = Catalogs.loadTable(conf,
Utilities.getTableDesc(hmsTable).getProperties());
+ String statsPath = getStatsPath(table).toString();
+ LOG.info("Using stats from puffin file at:" + statsPath);
+ try (PuffinReader reader =
Puffin.read(table.io().newInputFile(statsPath)).build()) {
+ List<BlobMetadata> blobMetadata = reader.fileMetadata().blobs();
+ Map<BlobMetadata, List<ColumnStatistics>> collect =
+
Streams.stream(reader.readAll(blobMetadata)).collect(Collectors.toMap(Pair::first,
+ blobMetadataByteBufferPair -> SerializationUtils.deserialize(
+
ByteBuffers.toByteArray(blobMetadataByteBufferPair.second()))));
+ return collect.get(blobMetadata.get(0)).get(0).getStatsObj();
+ } catch (IOException e) {
+ LOG.error(String.valueOf(e));
+ }
+ return null;
Review Comment:
Even in the absence of stats the query can run successfully.
I was thinking it would be better to throw an error message rather than
filing the entire query.
##########
iceberg/iceberg-handler/src/main/java/org/apache/iceberg/mr/hive/HiveIcebergStorageHandler.java:
##########
@@ -361,6 +378,83 @@ private Table
getTable(org.apache.hadoop.hive.ql.metadata.Table hmsTable) {
return table;
}
+
+ @Override
+ public boolean canSetColStatistics() {
+ return getStatsSource().equals(ICEBERG);
+ }
+
+ @Override
+ public boolean
canProvideColStatistics(org.apache.hadoop.hive.ql.metadata.Table hmsTable) {
+ Table table = Catalogs.loadTable(conf,
Utilities.getTableDesc(hmsTable).getProperties());
+ if (table.currentSnapshot() != null) {
+ Path statsPath = getStatsPath(table);
+ if (getStatsSource().equals(ICEBERG)) {
+ try (FileSystem fs = statsPath.getFileSystem(conf)) {
+ if (fs.exists(statsPath)) {
+ return true;
+ }
+ } catch (IOException e) {
+ LOG.warn(e.getMessage());
+ }
+ }
+ }
+ return false;
+ }
+
+ @Override
+ public List<ColumnStatisticsObj>
getColStatistics(org.apache.hadoop.hive.ql.metadata.Table hmsTable) {
+ Table table = Catalogs.loadTable(conf,
Utilities.getTableDesc(hmsTable).getProperties());
+ String statsPath = getStatsPath(table).toString();
+ LOG.info("Using stats from puffin file at:" + statsPath);
+ try (PuffinReader reader =
Puffin.read(table.io().newInputFile(statsPath)).build()) {
+ List<BlobMetadata> blobMetadata = reader.fileMetadata().blobs();
+ Map<BlobMetadata, List<ColumnStatistics>> collect =
+
Streams.stream(reader.readAll(blobMetadata)).collect(Collectors.toMap(Pair::first,
+ blobMetadataByteBufferPair -> SerializationUtils.deserialize(
+
ByteBuffers.toByteArray(blobMetadataByteBufferPair.second()))));
+ return collect.get(blobMetadata.get(0)).get(0).getStatsObj();
+ } catch (IOException e) {
+ LOG.error(String.valueOf(e));
+ }
+ return null;
+ }
+
+
+ @Override
+ public boolean setColStatistics(org.apache.hadoop.hive.ql.metadata.Table
table,
+ List<ColumnStatistics> colStats) {
+ TableDesc tableDesc = Utilities.getTableDesc(table);
+ Table tbl = Catalogs.loadTable(conf, tableDesc.getProperties());
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: gitbox-unsubscr...@hive.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: gitbox-unsubscr...@hive.apache.org
For additional commands, e-mail: gitbox-h...@hive.apache.org
