PREHOOK: query: -- Tests truncating a column from a list bucketing table -- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23) CREATE TABLE test_tab (key STRING, value STRING) PARTITIONED BY (part STRING) STORED AS RCFILE PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@test_tab POSTHOOK: query: -- Tests truncating a column from a list bucketing table -- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23) CREATE TABLE test_tab (key STRING, value STRING) PARTITIONED BY (part STRING) STORED AS RCFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@test_tab PREHOOK: query: ALTER TABLE test_tab SKEWED BY (key) ON ("484") STORED AS DIRECTORIES PREHOOK: type: ALTERTABLE_SKEWED PREHOOK: Input: default@test_tab PREHOOK: Output: default@test_tab POSTHOOK: query: ALTER TABLE test_tab SKEWED BY (key) ON ("484") STORED AS DIRECTORIES POSTHOOK: type: ALTERTABLE_SKEWED POSTHOOK: Input: default@test_tab POSTHOOK: Output: default@test_tab PREHOOK: query: INSERT OVERWRITE TABLE test_tab PARTITION (part = '1') SELECT * FROM src PREHOOK: type: QUERY PREHOOK: Input: default@src PREHOOK: Output: default@test_tab@part=1 POSTHOOK: query: INSERT OVERWRITE TABLE test_tab PARTITION (part = '1') SELECT * FROM src POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@test_tab@part=1 POSTHOOK: Lineage: test_tab PARTITION(part=1).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: test_tab PARTITION(part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: SELECT * FROM test_tab WHERE part = '1' AND key = '0' PREHOOK: type: QUERY PREHOOK: Input: default@test_tab PREHOOK: Input: default@test_tab@part=1 #### A masked pattern was here #### POSTHOOK: query: SELECT * FROM test_tab WHERE part = '1' AND key = '0' POSTHOOK: type: QUERY POSTHOOK: Input: default@test_tab POSTHOOK: Input: default@test_tab@part=1 #### A masked pattern was here #### 0 val_0 1 0 val_0 1 0 val_0 1 PREHOOK: query: TRUNCATE TABLE test_tab PARTITION (part ='1') COLUMNS (value) PREHOOK: type: TRUNCATETABLE PREHOOK: Input: default@test_tab PREHOOK: Output: default@test_tab@part=1 POSTHOOK: query: TRUNCATE TABLE test_tab PARTITION (part ='1') COLUMNS (value) POSTHOOK: type: TRUNCATETABLE POSTHOOK: Input: default@test_tab POSTHOOK: Output: default@test_tab@part=1 PREHOOK: query: -- In the following select statements the list bucketing optimization should still be used -- In both cases value should be null EXPLAIN EXTENDED SELECT * FROM test_tab WHERE part = '1' AND key = '484' PREHOOK: type: QUERY POSTHOOK: query: -- In the following select statements the list bucketing optimization should still be used -- In both cases value should be null EXPLAIN EXTENDED SELECT * FROM test_tab WHERE part = '1' AND key = '484' POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: TOK_QUERY TOK_FROM TOK_TABREF TOK_TABNAME test_tab TOK_INSERT TOK_DESTINATION TOK_DIR TOK_TMP_FILE TOK_SELECT TOK_SELEXPR TOK_ALLCOLREF TOK_WHERE AND = TOK_TABLE_OR_COL part '1' = TOK_TABLE_OR_COL key '484' STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan alias: test_tab Statistics: Num rows: 17 Data size: 1761 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (key = '484') (type: boolean) Statistics: Num rows: 8 Data size: 828 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '484' (type: string), value (type: string), '1' (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 8 Data size: 828 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 Statistics: Num rows: 8 Data size: 828 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: columns _col0,_col1,_col2 columns.types string:string:string escape.delim \ hive.serialization.extend.nesting.levels true serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TotalFiles: 1 GatherStats: false MultiFileSpray: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: key=484 input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat partition values: part 1 properties: COLUMN_STATS_ACCURATE true bucket_count -1 columns key,value columns.comments columns.types string:string #### A masked pattern was here #### name default.test_tab numFiles 2 numRows 0 partition_columns part partition_columns.types string rawDataSize 0 serialization.ddl struct test_tab { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe totalSize 1761 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat properties: bucket_count -1 columns key,value columns.comments columns.types string:string #### A masked pattern was here #### name default.test_tab partition_columns part partition_columns.types string serialization.ddl struct test_tab { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe name: default.test_tab name: default.test_tab Truncated Path -> Alias: /test_tab/part=1/key=484 [test_tab] Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: ListSink PREHOOK: query: SELECT * FROM test_tab WHERE part = '1' AND key = '484' PREHOOK: type: QUERY PREHOOK: Input: default@test_tab PREHOOK: Input: default@test_tab@part=1 #### A masked pattern was here #### POSTHOOK: query: SELECT * FROM test_tab WHERE part = '1' AND key = '484' POSTHOOK: type: QUERY POSTHOOK: Input: default@test_tab POSTHOOK: Input: default@test_tab@part=1 #### A masked pattern was here #### 484 NULL 1 PREHOOK: query: EXPLAIN EXTENDED SELECT * FROM test_tab WHERE part = '1' AND key = '0' PREHOOK: type: QUERY POSTHOOK: query: EXPLAIN EXTENDED SELECT * FROM test_tab WHERE part = '1' AND key = '0' POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: TOK_QUERY TOK_FROM TOK_TABREF TOK_TABNAME test_tab TOK_INSERT TOK_DESTINATION TOK_DIR TOK_TMP_FILE TOK_SELECT TOK_SELEXPR TOK_ALLCOLREF TOK_WHERE AND = TOK_TABLE_OR_COL part '1' = TOK_TABLE_OR_COL key '0' STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan alias: test_tab Statistics: Num rows: 17 Data size: 1761 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (key = '0') (type: boolean) Statistics: Num rows: 8 Data size: 828 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '0' (type: string), value (type: string), '1' (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 8 Data size: 828 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 Statistics: Num rows: 8 Data size: 828 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: columns _col0,_col1,_col2 columns.types string:string:string escape.delim \ hive.serialization.extend.nesting.levels true serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TotalFiles: 1 GatherStats: false MultiFileSpray: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat partition values: part 1 properties: COLUMN_STATS_ACCURATE true bucket_count -1 columns key,value columns.comments columns.types string:string #### A masked pattern was here #### name default.test_tab numFiles 2 numRows 0 partition_columns part partition_columns.types string rawDataSize 0 serialization.ddl struct test_tab { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe totalSize 1761 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat properties: bucket_count -1 columns key,value columns.comments columns.types string:string #### A masked pattern was here #### name default.test_tab partition_columns part partition_columns.types string serialization.ddl struct test_tab { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe name: default.test_tab name: default.test_tab Truncated Path -> Alias: /test_tab/part=1/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME [test_tab] Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: ListSink PREHOOK: query: SELECT * FROM test_tab WHERE part = '1' AND key = '0' PREHOOK: type: QUERY PREHOOK: Input: default@test_tab PREHOOK: Input: default@test_tab@part=1 #### A masked pattern was here #### POSTHOOK: query: SELECT * FROM test_tab WHERE part = '1' AND key = '0' POSTHOOK: type: QUERY POSTHOOK: Input: default@test_tab POSTHOOK: Input: default@test_tab@part=1 #### A masked pattern was here #### 0 NULL 1 0 NULL 1 0 NULL 1