5
0
mirror of https://github.com/apache/sqoop.git synced 2025-05-03 20:40:58 +08:00

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

(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

View File

@ -103,7 +103,9 @@ protected void configureMapper(Job job, String tableName,
// Parquet data records. The import will fail, if schema is invalid. // Parquet data records. The import will fail, if schema is invalid.
Schema schema = generateAvroSchema(tableName); Schema schema = generateAvroSchema(tableName);
String uri = getKiteUri(conf, 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()); job.setMapperClass(getMapperClass());

View File

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