vvysotskyi commented on a change in pull request #2026: DRILL-7330: Implement
metadata usage for all format plugins
URL: https://github.com/apache/drill/pull/2026#discussion_r392708620
##########
File path:
exec/java-exec/src/main/java/org/apache/drill/exec/store/parquet/BaseParquetMetadataProvider.java
##########
@@ -103,34 +110,39 @@
// whether metadata for row groups should be collected to create files,
partitions and table metadata
private final boolean collectMetadata = false;
- public BaseParquetMetadataProvider(List<ReadEntryWithPath> entries,
- ParquetReaderConfig readerConfig,
- String tableName,
- Path tableLocation,
- TupleMetadata schema,
- DrillStatsTable statsTable) {
- this(readerConfig, entries, tableName, tableLocation, schema, statsTable);
- }
+ protected BaseParquetMetadataProvider(Builder<?> builder) {
+ if (builder.entries != null) {
+ // reuse previously stored metadata
+ this.entries = builder.entries;
+ this.tableName = builder.selectionRoot != null ?
builder.selectionRoot.toUri().getPath() : "";
+ this.tableLocation = builder.selectionRoot;
+ } else if (builder.selection != null) {
+ this.entries = new ArrayList<>();
+ this.tableName = builder.selection.getSelectionRoot() != null ?
builder.selection.getSelectionRoot().toUri().getPath() : "";
+ this.tableLocation = builder.selection.getSelectionRoot();
+ } else {
+ // case of hive parquet table
+ this.entries = new ArrayList<>();
+ this.tableName = null;
+ this.tableLocation = null;
+ }
- public BaseParquetMetadataProvider(ParquetReaderConfig readerConfig,
- List<ReadEntryWithPath> entries,
- String tableName,
- Path tableLocation,
- TupleMetadata schema,
- DrillStatsTable statsTable) {
- this.entries = entries == null ? new ArrayList<>() : entries;
- this.readerConfig = readerConfig == null ?
ParquetReaderConfig.getDefaultInstance() : readerConfig;
- this.tableName = tableName;
- this.tableLocation = tableLocation;
- this.schema = schema;
- this.statsTable = statsTable;
- }
+ SchemaProvider schemaProvider =
builder.metadataProviderManager.getSchemaProvider();
+ TupleMetadata schema = builder.schema;
+ // schema passed into the builder has greater priority
+ if (schema == null && schemaProvider != null) {
+ try {
+ schema = schemaProvider.read().getSchema();
Review comment:
This code is connected with schema provisioning. The schema will be used
further in the scan using existing schema provisioning rules for formats that
support it.
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
With regards,
Apache Git Services
