----------------------------------------------------------- This is an automatically generated e-mail. To reply, visit: https://reviews.apache.org/r/23438/ -----------------------------------------------------------
Review request for hive. Bugs: HIVE-4765 https://issues.apache.org/jira/browse/HIVE-4765 Repository: hive-git Description ------- With some patches, bulk loading process for HBase could be simplified a lot. {noformat} CREATE EXTERNAL TABLE hbase_export(rowkey STRING, col1 STRING, col2 STRING) ROW FORMAT SERDE 'org.apache.hadoop.hive.hbase.HBaseExportSerDe' WITH SERDEPROPERTIES ("hbase.columns.mapping" = ":key,cf1:key,cf2:value") STORED AS INPUTFORMAT 'org.apache.hadoop.mapred.TextInputFormat' OUTPUTFORMAT 'org.apache.hadoop.hive.hbase.HiveHFileExporter' LOCATION '/tmp/export'; SET mapred.reduce.tasks=4; set hive.optimize.sampling.orderby=true; INSERT OVERWRITE TABLE hbase_export SELECT * from (SELECT union_kv(key,key,value,":key,cf1:key,cf2:value") as (rowkey,union) FROM src) A ORDER BY rowkey,union; hive> !hadoop fs -lsr /tmp/export; drwxr-xr-x - navis supergroup 0 2013-06-20 11:05 /tmp/export/cf1 -rw-r--r-- 1 navis supergroup 4317 2013-06-20 11:05 /tmp/export/cf1/384abe795e1a471cac6d3770ee38e835 -rw-r--r-- 1 navis supergroup 5868 2013-06-20 11:05 /tmp/export/cf1/b8b6d746c48f4d12a4cf1a2077a28a2d -rw-r--r-- 1 navis supergroup 5214 2013-06-20 11:05 /tmp/export/cf1/c8be8117a1734bd68a74338dfc4180f8 -rw-r--r-- 1 navis supergroup 4290 2013-06-20 11:05 /tmp/export/cf1/ce41f5b1cfdc4722be25207fc59a9f10 drwxr-xr-x - navis supergroup 0 2013-06-20 11:05 /tmp/export/cf2 -rw-r--r-- 1 navis supergroup 6744 2013-06-20 11:05 /tmp/export/cf2/409673b517d94e16920e445d07710f52 -rw-r--r-- 1 navis supergroup 4975 2013-06-20 11:05 /tmp/export/cf2/96af002a6b9f4ebd976ecd83c99c8d7e -rw-r--r-- 1 navis supergroup 6096 2013-06-20 11:05 /tmp/export/cf2/c4f696587c5e42ee9341d476876a3db4 -rw-r--r-- 1 navis supergroup 4890 2013-06-20 11:05 /tmp/export/cf2/fd9adc9e982f4fe38c8d62f9a44854ba hbase org.apache.hadoop.hbase.mapreduce.LoadIncrementalHFiles /tmp/export test {noformat} Diffs ----- hbase-handler/build.xml PRE-CREATION hbase-handler/src/java/org/apache/hadoop/hive/hbase/ColumnMappings.java 9cae5d3 hbase-handler/src/java/org/apache/hadoop/hive/hbase/DefaultHBaseKeyFactory.java 5731e45 hbase-handler/src/java/org/apache/hadoop/hive/hbase/HBaseExportSerDe.java PRE-CREATION hbase-handler/src/java/org/apache/hadoop/hive/hbase/HBaseRowSerializer.java fe6081e hbase-handler/src/java/org/apache/hadoop/hive/hbase/HBaseSerDe.java 6c1ce5c hbase-handler/src/java/org/apache/hadoop/hive/hbase/HiveHFileExporter.java PRE-CREATION hbase-handler/src/test/queries/positive/hbase_bulk2.m PRE-CREATION hbase-handler/src/test/results/positive/hbase_bulk2.m.out PRE-CREATION itests/qtest/pom.xml 249956f ql/src/java/org/apache/hadoop/hive/ql/exec/FunctionRegistry.java a80feb9 ql/src/java/org/apache/hadoop/hive/ql/io/HiveOutputCommitter.java PRE-CREATION ql/src/java/org/apache/hadoop/hive/ql/metadata/Hive.java fea1e47 ql/src/java/org/apache/hadoop/hive/ql/udf/generic/HFileKeyValue.java PRE-CREATION serde/src/java/org/apache/hadoop/hive/serde2/lazybinary/LazyBinaryFactory.java cae4faa serde/src/java/org/apache/hadoop/hive/serde2/lazybinary/LazyBinarySerDe.java 1c8f795 serde/src/java/org/apache/hadoop/hive/serde2/lazybinary/LazyBinaryUnion.java PRE-CREATION serde/src/java/org/apache/hadoop/hive/serde2/lazybinary/LazyBinaryUnionObjectInspector.java PRE-CREATION serde/src/java/org/apache/hadoop/hive/serde2/lazybinary/LazyBinaryUtils.java f7cfb36 serde/src/java/org/apache/hadoop/hive/serde2/lazybinary/objectinspector/LazyBinaryObjectInspectorFactory.java b3ec24d Diff: https://reviews.apache.org/r/23438/diff/ Testing ------- Thanks, Navis Ryu