Apache/druid
1
0
Fork 0
mirror of https://github.com/apache/druid.git synced 2025-02-17 07:25:02 +00:00
Code Issues Packages Projects Releases Wiki Activity

Honor ignoreInvalidRows in Hadoop indexer

Browse Source 
The reducer of the hadoop indexer now ignores lines with parsing
exceptions (if enabled by the indexer config).
This commit is contained in:
Dia Kharrat 2015-03-19 17:33:54 -07:00
parent 46eae49bf5
commit 58d5f5e7f0
1 changed files with 15 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
indexing-hadoop/src/main/java/io/druid/indexer/IndexGeneratorJob.java
View File

@ -17,6 +17,7 @@
package io.druid.indexer;
import com.metamx.common.parsers.ParseException;
import io.druid.collections.StupidPool;
import io.druid.data.input.InputRow;
import io.druid.data.input.Rows;
@ -378,10 +379,21 @@ public class IndexGeneratorJob implements Jobby
for (final Writable value : values) {
context.progress();
final InputRow inputRow = index.formatRow(HadoopDruidIndexerMapper.parseInputRow(value, parser));
allDimensionNames.addAll(inputRow.getDimensions());
int numRows;
try {
final InputRow inputRow = index.formatRow(HadoopDruidIndexerMapper.parseInputRow(value, parser));
allDimensionNames.addAll(inputRow.getDimensions());
int numRows = index.add(inputRow);
numRows = index.add(inputRow);
} catch (ParseException 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);
continue;
} else {
throw e;
}
}
++lineCount;
if (!index.canAppendRow()) {