kasakrisz commented on code in PR #3745:
URL: https://github.com/apache/hive/pull/3745#discussion_r1020142810
##########
iceberg/iceberg-handler/src/main/java/org/apache/iceberg/mr/hive/HiveIcebergStorageHandler.java:
##########
@@ -804,31 +806,59 @@ public static Schema schema(Configuration config) {
@VisibleForTesting
static void overlayTableProperties(Configuration configuration, TableDesc
tableDesc, Map<String, String> map) {
Properties props = tableDesc.getProperties();
- Table table = IcebergTableUtil.getTable(configuration, props);
- String schemaJson = SchemaParser.toJson(table.schema());
Maps.fromProperties(props).entrySet().stream()
.filter(entry -> !map.containsKey(entry.getKey())) // map overrides
tableDesc properties
.forEach(entry -> map.put(entry.getKey(), entry.getValue()));
- map.put(InputFormatConfig.TABLE_IDENTIFIER,
props.getProperty(Catalogs.NAME));
- map.put(InputFormatConfig.TABLE_LOCATION, table.location());
- map.put(InputFormatConfig.TABLE_SCHEMA, schemaJson);
- props.put(InputFormatConfig.PARTITION_SPEC,
PartitionSpecParser.toJson(table.spec()));
-
- // serialize table object into config
- Table serializableTable = SerializableTable.copyOf(table);
- checkAndSkipIoConfigSerialization(configuration, serializableTable);
- map.put(InputFormatConfig.SERIALIZED_TABLE_PREFIX +
tableDesc.getTableName(),
- SerializationUtil.serializeToBase64(serializableTable));
+ try {
+ Table table = IcebergTableUtil.getTable(configuration, props);
+ String schemaJson = SchemaParser.toJson(table.schema());
+
+ map.put(InputFormatConfig.TABLE_IDENTIFIER,
props.getProperty(Catalogs.NAME));
+ map.put(InputFormatConfig.TABLE_LOCATION, table.location());
+ map.put(InputFormatConfig.TABLE_SCHEMA, schemaJson);
+ props.put(InputFormatConfig.PARTITION_SPEC,
PartitionSpecParser.toJson(table.spec()));
+
+ // serialize table object into config
+ Table serializableTable = SerializableTable.copyOf(table);
+ checkAndSkipIoConfigSerialization(configuration, serializableTable);
+ map.put(InputFormatConfig.SERIALIZED_TABLE_PREFIX +
tableDesc.getTableName(),
+ SerializationUtil.serializeToBase64(serializableTable));
+
+ // We need to remove this otherwise the job.xml will be invalid as
column comments are separated with '\0' and
+ // the serialization utils fail to serialize this character
+ map.remove("columns.comments");
+
+ // save schema into table props as well to avoid repeatedly hitting the
HMS during serde initializations
+ // this is an exception to the interface documentation, but it's a safe
operation to add this property
+ props.put(InputFormatConfig.TABLE_SCHEMA, schemaJson);
+ } catch (NoSuchTableException ex) {
+ if
(!(StringUtils.isNotBlank(props.getProperty(hive_metastoreConstants.TABLE_IS_CTAS))
&&
+
Boolean.parseBoolean(props.getProperty(org.apache.hadoop.hive.conf.Constants.IS_EXPLAIN))))
{
+ throw ex;
+ }
- // We need to remove this otherwise the job.xml will be invalid as column
comments are separated with '\0' and
- // the serialization utils fail to serialize this character
- map.remove("columns.comments");
+ try {
+ map.put(InputFormatConfig.TABLE_IDENTIFIER,
props.getProperty(Catalogs.NAME));
Review Comment:
The only common part seems to be
```
map.put(InputFormatConfig.TABLE_IDENTIFIER,
props.getProperty(Catalogs.NAME));
```
However this cannot be extracted because `props` are modified by `getTable`
--
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]
