fx19880617 commented on a change in pull request #4888: Refactor file format
based RecordReader constructors
URL: https://github.com/apache/incubator-pinot/pull/4888#discussion_r354007185
##########
File path:
pinot-core/src/main/java/org/apache/pinot/core/data/readers/RecordReaderFactory.java
##########
@@ -20,26 +20,60 @@
import com.google.common.base.Preconditions;
import java.io.File;
-import org.apache.pinot.avro.data.readers.AvroRecordReader;
-import org.apache.pinot.csv.data.readers.CSVRecordReader;
-import org.apache.pinot.csv.data.readers.CSVRecordReaderConfig;
-import org.apache.pinot.json.data.readers.JSONRecordReader;
-import org.apache.pinot.spi.data.Schema;
+import java.util.HashMap;
+import java.util.Map;
import org.apache.pinot.core.indexsegment.generator.SegmentGeneratorConfig;
+import org.apache.pinot.spi.data.Schema;
import org.apache.pinot.spi.data.readers.RecordReader;
-import org.apache.pinot.thrift.data.readers.ThriftRecordReader;
-import org.apache.pinot.thrift.data.readers.ThriftRecordReaderConfig;
+import org.apache.pinot.spi.data.readers.RecordReaderConfig;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
public class RecordReaderFactory {
private static final Logger LOGGER =
LoggerFactory.getLogger(RecordReaderFactory.class);
+ private static final Map<FileFormat, String> DEFAULT_RECORD_READER_CLASS_MAP
= new HashMap<>();
+
+ private static final String DEFAULT_AVRO_RECORD_READER_CLASS =
"org.apache.pinot.avro.data.readers.AvroRecordReader";
+ private static final String DEFAULT_CSV_RECORD_READER_CLASS =
"org.apache.pinot.csv.data.readers.CSVRecordReader";
+ private static final String DEFAULT_JSON_RECORD_READER_CLASS =
"org.apache.pinot.json.data.readers.JSONRecordReader";
+ private static final String DEFAULT_THRIFT_RECORD_READER_CLASS =
+ "org.apache.pinot.thrift.data.readers.ThriftRecordReader";
+ private static final String DEFAULT_ORC_RECORD_READER_CLASS =
"org.apache.pinot.orc.data.readers.ORCRecordReader";
+ private static final String DEFAULT_PARQUET_RECORD_READER_CLASS =
+ "org.apache.pinot.parquet.data.readers.ParquetRecordReader";
+
+ static {
+ DEFAULT_RECORD_READER_CLASS_MAP.put(FileFormat.AVRO,
DEFAULT_AVRO_RECORD_READER_CLASS);
+ DEFAULT_RECORD_READER_CLASS_MAP.put(FileFormat.GZIPPED_AVRO,
DEFAULT_AVRO_RECORD_READER_CLASS);
+ DEFAULT_RECORD_READER_CLASS_MAP.put(FileFormat.CSV,
DEFAULT_CSV_RECORD_READER_CLASS);
+ DEFAULT_RECORD_READER_CLASS_MAP.put(FileFormat.JSON,
DEFAULT_JSON_RECORD_READER_CLASS);
+ DEFAULT_RECORD_READER_CLASS_MAP.put(FileFormat.THRIFT,
DEFAULT_THRIFT_RECORD_READER_CLASS);
+ DEFAULT_RECORD_READER_CLASS_MAP.put(FileFormat.ORC,
DEFAULT_ORC_RECORD_READER_CLASS);
+ DEFAULT_RECORD_READER_CLASS_MAP.put(FileFormat.PARQUET,
DEFAULT_PARQUET_RECORD_READER_CLASS);
+ }
private RecordReaderFactory() {
}
+ public static RecordReader getRecordReader(String recordReaderClassName,
File dataFile, Schema schema,
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.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
