Apache
/
druid
mirror of https://github.com/apache/druid.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

log invalid rows in mapper of Hadoop indexer

This commit is contained in:
Dia Kharrat 2015-03-19 17:34:37 -07:00
parent 58d5f5e7f0
commit 3a6dc99384
1 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
indexing-hadoop/src/main/java/io/druid/indexer/HadoopDruidIndexerMapper.java
View File

@ -17,6 +17,7 @@
package io.druid.indexer;
import com.metamx.common.logger.Logger;
import io.druid.data.input.InputRow;
import io.druid.data.input.impl.InputRowParser;
import io.druid.data.input.impl.MapInputRowParser;
@ -42,6 +43,8 @@ import com.metamx.common.RE;
public abstract class HadoopDruidIndexerMapper<KEYOUT, VALUEOUT> extends Mapper<Writable, Writable, KEYOUT, VALUEOUT>
{
private static final Logger log = new Logger(HadoopDruidIndexerMapper.class);
private HadoopDruidIndexerConfig config;
private InputRowParser parser;
protected GranularitySpec granularitySpec;
@ -77,6 +80,7 @@ public abstract class HadoopDruidIndexerMapper<KEYOUT, VALUEOUT> extends Mapper<
}
catch (Exception e) {
if (config.isIgnoreInvalidRows()) {
log.debug(e, "Ignoring invalid row [%s] due to parsing error", value.toString());
context.getCounter(HadoopDruidIndexerConfig.IndexJobCounters.INVALID_ROW_COUNTER).increment(1);
return; // we're ignoring this invalid row
} else {