github/sqoop
5
0
Fork 0
mirror of https://github.com/apache/sqoop.git synced 2025-05-03 07:42:00 +08:00
Code Issues Projects Releases Wiki Activity

SQOOP-2257: Parquet target for imports with Hive overwrite option does not work

Browse Source 
(Qian Xu via Jarek Jarcec Cecho)
This commit is contained in:
Jarek Jarcec Cecho 2015-03-24 06:43:30 -07:00
parent 38c054d8a2
commit fa8518998f
2 changed files with 5 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
src/java/org/apache/sqoop/mapreduce/DataDrivenImportJob.java
View File

@ -103,7 +103,9 @@ protected void configureMapper(Job job, String tableName,
// Parquet data records. The import will fail, if schema is invalid.
Schema schema = generateAvroSchema(tableName);
String uri = getKiteUri(conf, tableName);
ParquetJob.configureImportJob(conf, schema, uri, options.isAppendMode());
boolean reuseExistingDataset = options.isAppendMode() ||
(options.doHiveImport() && options.doOverwriteHiveTable());
ParquetJob.configureImportJob(conf, schema, uri, reuseExistingDataset);
}
job.setMapperClass(getMapperClass());

4
src/java/org/apache/sqoop/mapreduce/ParquetJob.java
View File

@ -71,9 +71,9 @@ public static CompressionType getCompressionType(Configuration conf) {
* {@link org.apache.avro.generic.GenericRecord}.
*/
public static void configureImportJob(Configuration conf, Schema schema,
String uri, boolean doAppend) throws IOException {
String uri, boolean reuseExistingDataset) throws IOException {
Dataset dataset;
if (doAppend) {
if (reuseExistingDataset) {
try {
dataset = Datasets.load(uri);
} catch (DatasetNotFoundException ex) {