simhadri-g commented on code in PR #4131:
URL: https://github.com/apache/hive/pull/4131#discussion_r1161857242
##########
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());
+ String snapshotId = tbl.name() + tbl.currentSnapshot().snapshotId();
+ byte[] serializeColStats = SerializationUtils.serialize((Serializable)
colStats);
+
+ try (PuffinWriter writer =
Puffin.write(tbl.io().newOutputFile(getStatsPath(tbl).toString()))
+ .createdBy("Hive").build()) {
Review Comment:
Done
##########
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());
+ String snapshotId = tbl.name() + tbl.currentSnapshot().snapshotId();
+ byte[] serializeColStats = SerializationUtils.serialize((Serializable)
colStats);
+
+ try (PuffinWriter writer =
Puffin.write(tbl.io().newOutputFile(getStatsPath(tbl).toString()))
+ .createdBy("Hive").build()) {
+ writer.add(
+ new Blob(
+ tbl.name() + "-" + snapshotId,
+ ImmutableList.of(1),
+ tbl.currentSnapshot().snapshotId(),
+ tbl.currentSnapshot().sequenceNumber(),
+ ByteBuffer.wrap(serializeColStats),
+ PuffinCompressionCodec.NONE,
+ ImmutableMap.of()));
+ writer.finish();
+ } catch (IOException e) {
+ LOG.error(String.valueOf(e));
+ }
+ return false;
+ }
+
+ private String getStatsSource() {
+ return HiveConf.getVar(conf, HiveConf.ConfVars.HIVE_ICEBERG_STATS_SOURCE,
"metastore").toLowerCase();
+ }
Review Comment:
Fixed
--
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]
