PREHOOK: query: DROP TABLE rcfile_createas1a PREHOOK: type: DROPTABLE POSTHOOK: query: DROP TABLE rcfile_createas1a POSTHOOK: type: DROPTABLE PREHOOK: query: DROP TABLE rcfile_createas1b PREHOOK: type: DROPTABLE POSTHOOK: query: DROP TABLE rcfile_createas1b POSTHOOK: type: DROPTABLE PREHOOK: query: CREATE TABLE rcfile_createas1a (key INT, value STRING) PARTITIONED BY (ds string) PREHOOK: type: CREATETABLE POSTHOOK: query: CREATE TABLE rcfile_createas1a (key INT, value STRING) PARTITIONED BY (ds string) POSTHOOK: type: CREATETABLE POSTHOOK: Output: default@rcfile_createas1a PREHOOK: query: INSERT OVERWRITE TABLE rcfile_createas1a PARTITION (ds='1') SELECT * FROM src PREHOOK: type: QUERY PREHOOK: Input: default@src PREHOOK: Output: default@rcfile_createas1a@ds=1 POSTHOOK: query: INSERT OVERWRITE TABLE rcfile_createas1a PARTITION (ds='1') SELECT * FROM src POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@rcfile_createas1a@ds=1 POSTHOOK: Lineage: rcfile_createas1a PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: rcfile_createas1a PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: INSERT OVERWRITE TABLE rcfile_createas1a PARTITION (ds='2') SELECT * FROM src PREHOOK: type: QUERY PREHOOK: Input: default@src PREHOOK: Output: default@rcfile_createas1a@ds=2 POSTHOOK: query: INSERT OVERWRITE TABLE rcfile_createas1a PARTITION (ds='2') SELECT * FROM src POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@rcfile_createas1a@ds=2 POSTHOOK: Lineage: rcfile_createas1a PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: rcfile_createas1a PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: rcfile_createas1a PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: rcfile_createas1a PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: EXPLAIN CREATE TABLE rcfile_createas1b STORED AS RCFILE AS SELECT key, value, PMOD(HASH(key), 50) as part FROM rcfile_createas1a PREHOOK: type: CREATETABLE_AS_SELECT POSTHOOK: query: EXPLAIN CREATE TABLE rcfile_createas1b STORED AS RCFILE AS SELECT key, value, PMOD(HASH(key), 50) as part FROM rcfile_createas1a POSTHOOK: type: CREATETABLE_AS_SELECT POSTHOOK: Lineage: rcfile_createas1a PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: rcfile_createas1a PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: rcfile_createas1a PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: rcfile_createas1a PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] ABSTRACT SYNTAX TREE: (TOK_CREATETABLE (TOK_TABNAME rcfile_createas1b) TOK_LIKETABLE TOK_TBLRCFILE (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME rcfile_createas1a))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_TABLE_OR_COL value)) (TOK_SELEXPR (TOK_FUNCTION PMOD (TOK_FUNCTION HASH (TOK_TABLE_OR_COL key)) 50) part))))) STAGE DEPENDENCIES: Stage-1 is a root stage Stage-4 depends on stages: Stage-1 , consists of Stage-3, Stage-2 Stage-3 Stage-0 depends on stages: Stage-3, Stage-2 Stage-5 depends on stages: Stage-0 Stage-2 STAGE PLANS: Stage: Stage-1 Map Reduce Alias -> Map Operator Tree: rcfile_createas1a TableScan alias: rcfile_createas1a Select Operator expressions: expr: key type: int expr: value type: string expr: pmod(hash(key), 50) type: int outputColumnNames: _col0, _col1, _col2 File Output Operator compressed: false GlobalTableId: 1 table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat Stage: Stage-4 Conditional Operator Stage: Stage-3 Move Operator files: hdfs directory: true destination: pfile:/data/users/franklin/hive-block-merge/build/ql/scratchdir/hive_2011-06-09_16-06-50_525_4856448737963146161/-ext-10001 Stage: Stage-0 Move Operator files: hdfs directory: true destination: pfile:/data/users/franklin/hive-block-merge/build/ql/test/data/warehouse/rcfile_createas1b Stage: Stage-5 Create Table Operator: Create Table columns: key int, value string, part int if not exists: false input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat # buckets: -1 output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat serde name: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe name: rcfile_createas1b isExternal: false Stage: Stage-2 Block level merge PREHOOK: query: CREATE TABLE rcfile_createas1b STORED AS RCFILE AS SELECT key, value, PMOD(HASH(key), 50) as part FROM rcfile_createas1a PREHOOK: type: CREATETABLE_AS_SELECT PREHOOK: Input: default@rcfile_createas1a@ds=1 PREHOOK: Input: default@rcfile_createas1a@ds=2 POSTHOOK: query: CREATE TABLE rcfile_createas1b STORED AS RCFILE AS SELECT key, value, PMOD(HASH(key), 50) as part FROM rcfile_createas1a POSTHOOK: type: CREATETABLE_AS_SELECT POSTHOOK: Input: default@rcfile_createas1a@ds=1 POSTHOOK: Input: default@rcfile_createas1a@ds=2 POSTHOOK: Output: default@rcfile_createas1b POSTHOOK: Lineage: rcfile_createas1a PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: rcfile_createas1a PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: rcfile_createas1a PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: rcfile_createas1a PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: SELECT SUM(HASH(c)) FROM ( SELECT TRANSFORM(key, value) USING 'tr \t _' AS (c) FROM rcfile_createas1a ) t PREHOOK: type: QUERY PREHOOK: Input: default@rcfile_createas1a@ds=1 PREHOOK: Input: default@rcfile_createas1a@ds=2 PREHOOK: Output: file:/tmp/franklin/hive_2011-06-09_16-06-54_053_5965587433920310393/-mr-10000 POSTHOOK: query: SELECT SUM(HASH(c)) FROM ( SELECT TRANSFORM(key, value) USING 'tr \t _' AS (c) FROM rcfile_createas1a ) t POSTHOOK: type: QUERY POSTHOOK: Input: default@rcfile_createas1a@ds=1 POSTHOOK: Input: default@rcfile_createas1a@ds=2 POSTHOOK: Output: file:/tmp/franklin/hive_2011-06-09_16-06-54_053_5965587433920310393/-mr-10000 POSTHOOK: Lineage: rcfile_createas1a PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: rcfile_createas1a PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: rcfile_createas1a PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: rcfile_createas1a PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 14412220296 PREHOOK: query: SELECT SUM(HASH(c)) FROM ( SELECT TRANSFORM(key, value) USING 'tr \t _' AS (c) FROM rcfile_createas1b ) t PREHOOK: type: QUERY PREHOOK: Input: default@rcfile_createas1b PREHOOK: Output: file:/tmp/franklin/hive_2011-06-09_16-06-57_460_3734087433150140544/-mr-10000 POSTHOOK: query: SELECT SUM(HASH(c)) FROM ( SELECT TRANSFORM(key, value) USING 'tr \t _' AS (c) FROM rcfile_createas1b ) t POSTHOOK: type: QUERY POSTHOOK: Input: default@rcfile_createas1b POSTHOOK: Output: file:/tmp/franklin/hive_2011-06-09_16-06-57_460_3734087433150140544/-mr-10000 POSTHOOK: Lineage: rcfile_createas1a PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: rcfile_createas1a PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: rcfile_createas1a PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: rcfile_createas1a PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 14412220296 PREHOOK: query: DROP TABLE rcfile_createas1a PREHOOK: type: DROPTABLE PREHOOK: Input: default@rcfile_createas1a PREHOOK: Output: default@rcfile_createas1a POSTHOOK: query: DROP TABLE rcfile_createas1a POSTHOOK: type: DROPTABLE POSTHOOK: Input: default@rcfile_createas1a POSTHOOK: Output: default@rcfile_createas1a POSTHOOK: Lineage: rcfile_createas1a PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: rcfile_createas1a PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: rcfile_createas1a PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: rcfile_createas1a PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: DROP TABLE rcfile_createas1b PREHOOK: type: DROPTABLE PREHOOK: Input: default@rcfile_createas1b PREHOOK: Output: default@rcfile_createas1b POSTHOOK: query: DROP TABLE rcfile_createas1b POSTHOOK: type: DROPTABLE POSTHOOK: Input: default@rcfile_createas1b POSTHOOK: Output: default@rcfile_createas1b POSTHOOK: Lineage: rcfile_createas1a PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: rcfile_createas1a PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: rcfile_createas1a PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: rcfile_createas1a PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]