You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by mg...@apache.org on 2020/05/18 11:13:49 UTC
[hive] branch master updated: HIVE-23470 Move TestCliDriver tests
to TestMiniLlapCliDriver if they are failing with
TestMiniLlapLocalCliDriver (Miklos Gergely,
reviewd by Jesus Camacho Rodriguez)
This is an automated email from the ASF dual-hosted git repository.
mgergely pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/hive.git
The following commit(s) were added to refs/heads/master by this push:
new c46bed6 HIVE-23470 Move TestCliDriver tests to TestMiniLlapCliDriver if they are failing with TestMiniLlapLocalCliDriver (Miklos Gergely, reviewd by Jesus Camacho Rodriguez)
c46bed6 is described below
commit c46bed637728f10482987f7a52a17f6399a9f6e6
Author: miklosgergely <mg...@cloudera.com>
AuthorDate: Mon May 18 12:59:56 2020 +0200
HIVE-23470 Move TestCliDriver tests to TestMiniLlapCliDriver if they are failing with TestMiniLlapLocalCliDriver (Miklos Gergely, reviewd by Jesus Camacho Rodriguez)
---
.../test/resources/testconfiguration.properties | 60 +-
ql/src/test/queries/clientpositive/input5.q | 2 +
.../test/queries/clientpositive/regexp_extract.q | 2 +
.../queries/clientpositive/select_transform_hint.q | 2 +
.../clientpositive/create_genericudaf.q.out | 107 -
ql/src/test/results/clientpositive/input14.q.out | 250 ---
.../results/clientpositive/input14_limit.q.out | 163 --
ql/src/test/results/clientpositive/input17.q.out | 174 --
ql/src/test/results/clientpositive/input18.q.out | 250 ---
ql/src/test/results/clientpositive/input5.q.out | 174 --
.../test/results/clientpositive/insert_into3.q.out | 568 ------
.../test/results/clientpositive/insert_into4.q.out | 460 -----
.../test/results/clientpositive/insert_into5.q.out | 637 ------
.../test/results/clientpositive/insert_into6.q.out | 383 ----
.../{ => llap}/autoColumnStats_6.q.out | 162 +-
.../{ => llap}/autogen_colalias.q.out | 0
.../{ => llap}/binary_output_format.q.out | 434 ++--
.../clientpositive/llap/create_genericudaf.q.out | 114 ++
.../clientpositive/{ => llap}/create_udaf.q.out | 24 +-
.../clientpositive/{ => llap}/create_view.q.out | 150 +-
.../{ => llap}/gen_udf_example_add10.q.out | 82 +-
.../{ => llap}/groupby_bigdata.q.out | 4 +-
.../test/results/clientpositive/llap/input14.q.out | 252 +++
.../clientpositive/llap/input14_limit.q.out | 177 ++
.../test/results/clientpositive/llap/input17.q.out | 176 ++
.../test/results/clientpositive/llap/input18.q.out | 252 +++
.../clientpositive/{ => llap}/input20.q.out | 181 +-
.../clientpositive/{ => llap}/input33.q.out | 181 +-
.../clientpositive/{ => llap}/input34.q.out | 174 +-
.../clientpositive/{ => llap}/input35.q.out | 174 +-
.../clientpositive/{ => llap}/input36.q.out | 174 +-
.../clientpositive/{ => llap}/input38.q.out | 160 +-
.../test/results/clientpositive/llap/input5.q.out | 176 ++
.../results/clientpositive/llap/insert_into3.q.out | 546 ++++++
.../results/clientpositive/llap/insert_into4.q.out | 436 +++++
.../results/clientpositive/llap/insert_into5.q.out | 550 ++++++
.../results/clientpositive/llap/insert_into6.q.out | 356 ++++
.../{ => llap}/load_binary_data.q.out | Bin 2392 -> 2405 bytes
.../clientpositive/{ => llap}/macro_1.q.out | 12 +-
.../{ => llap}/macro_duplicate.q.out | 4 +-
.../clientpositive/{ => llap}/mapreduce3.q.out | 164 +-
.../clientpositive/{ => llap}/mapreduce4.q.out | 166 +-
.../clientpositive/{ => llap}/mapreduce7.q.out | 164 +-
.../clientpositive/{ => llap}/mapreduce8.q.out | 166 +-
.../{ => llap}/merge_test_dummy_operator.q.out | 4 +-
.../clientpositive/{ => llap}/newline.q.out | 44 +-
.../llap/nonreserved_keywords_insert_into1.q.out | 449 +++++
.../clientpositive/{ => llap}/nullscript.q.out | 55 +-
.../clientpositive/{ => llap}/orc_createas1.q.out | 386 ++--
.../clientpositive/{ => llap}/partcols1.q.out | 4 +-
.../clientpositive/llap/ppd_transform.q.out | 459 +++++
.../{ => llap}/query_with_semi.q.out | 12 +-
.../clientpositive/{ => llap}/rcfile_bigdata.q.out | 4 +-
.../clientpositive/llap/regexp_extract.q.out | 512 +++++
.../{ => llap}/script_env_var1.q.out | 4 +-
.../{ => llap}/script_env_var2.q.out | 4 +-
.../results/clientpositive/llap/script_pipe.q.out | 134 ++
.../clientpositive/{ => llap}/scriptfile1.q.out | 4 +-
.../{ => llap}/select_transform_hint.q.out | 2062 ++++++++++----------
.../clientpositive/{ => llap}/str_to_map.q.out | 106 +-
.../{ => llap}/temp_table_partcols1.q.out | 4 +-
.../results/clientpositive/llap/transform1.q.out | 150 ++
.../clientpositive/{ => llap}/transform2.q.out | 4 +-
.../clientpositive/{ => llap}/transform3.q.out | 4 +-
.../clientpositive/llap/transform_ppr1.q.out | 487 +++++
.../clientpositive/llap/transform_ppr2.q.out | 402 ++++
.../clientpositive/{ => llap}/udaf_sum_list.q.out | 4 +-
.../clientpositive/{ => llap}/udf_printf.q.out | 26 +-
.../clientpositive/{ => llap}/union23.q.out | 114 +-
.../clientpositive/{ => llap}/union_script.q.out | 8 +-
.../{ => llap}/vector_custom_udf_configure.q.out | 45 +-
.../results/clientpositive/llap/vector_udf3.q.out | 106 +
.../nonreserved_keywords_insert_into1.q.out | 440 -----
.../results/clientpositive/ppd_transform.q.out | 436 -----
.../results/clientpositive/regexp_extract.q.out | 492 -----
.../test/results/clientpositive/script_pipe.q.out | 123 --
.../test/results/clientpositive/transform1.q.out | 144 --
.../results/clientpositive/transform_ppr1.q.out | 468 -----
.../results/clientpositive/transform_ppr2.q.out | 389 ----
.../test/results/clientpositive/vector_udf3.q.out | 103 -
80 files changed, 8411 insertions(+), 8624 deletions(-)
diff --git a/itests/src/test/resources/testconfiguration.properties b/itests/src/test/resources/testconfiguration.properties
index 2b98dc3..d6339f3 100644
--- a/itests/src/test/resources/testconfiguration.properties
+++ b/itests/src/test/resources/testconfiguration.properties
@@ -429,7 +429,65 @@ minillap.query.files=acid_bucket_pruning.q,\
cttl.q,\
vector_offset_limit.q,\
temp_table_add_part_with_loc.q,\
- temp_table_drop_partitions_filter4.q
+ temp_table_drop_partitions_filter4.q,\
+ autoColumnStats_6.q,\
+ autogen_colalias.q,\
+ binary_output_format.q,\
+ create_genericudaf.q,\
+ create_udaf.q,\
+ create_view.q,\
+ gen_udf_example_add10.q,\
+ groupby_bigdata.q,\
+ input14.q,\
+ input14_limit.q,\
+ input17.q,\
+ input18.q,\
+ input20.q,\
+ input33.q,\
+ input34.q,\
+ input35.q,\
+ input36.q,\
+ input38.q,\
+ input5.q,\
+ insert_into3.q,\
+ insert_into4.q,\
+ insert_into5.q,\
+ insert_into6.q,\
+ load_binary_data.q,\
+ macro_1.q,\
+ macro_duplicate.q,\
+ mapreduce3.q,\
+ mapreduce4.q,\
+ mapreduce7.q,\
+ mapreduce8.q,\
+ merge_test_dummy_operator.q,\
+ newline.q,\
+ nonreserved_keywords_insert_into1.q,\
+ nullscript.q,\
+ orc_createas1.q,\
+ partcols1.q,\
+ ppd_transform.q,\
+ query_with_semi.q,\
+ rcfile_bigdata.q,\
+ regexp_extract.q,\
+ script_env_var1.q,\
+ script_env_var2.q,\
+ script_pipe.q,\
+ scriptfile1.q,\
+ select_transform_hint.q,\
+ str_to_map.q,\
+ temp_table_partcols1.q,\
+ transform1.q,\
+ transform2.q,\
+ transform3.q,\
+ transform_ppr1.q,\
+ transform_ppr2.q,\
+ udaf_sum_list.q,\
+ udf_printf.q,\
+ union23.q,\
+ union_script.q,\
+ vector_custom_udf_configure.q,\
+ vector_udf3.q
minillaplocal.query.files=\
empty_files_external_table.q,\
diff --git a/ql/src/test/queries/clientpositive/input5.q b/ql/src/test/queries/clientpositive/input5.q
index bf598de..72a1e74 100644
--- a/ql/src/test/queries/clientpositive/input5.q
+++ b/ql/src/test/queries/clientpositive/input5.q
@@ -1,4 +1,6 @@
--! qt:dataset:src_thrift
+-- SORT_QUERY_RESULTS
+
CREATE TABLE dest1_n94(key STRING, value STRING) STORED AS TEXTFILE;
EXPLAIN
diff --git a/ql/src/test/queries/clientpositive/regexp_extract.q b/ql/src/test/queries/clientpositive/regexp_extract.q
index 678b8fa..e32094b 100644
--- a/ql/src/test/queries/clientpositive/regexp_extract.q
+++ b/ql/src/test/queries/clientpositive/regexp_extract.q
@@ -1,4 +1,6 @@
--! qt:dataset:src
+-- SORT_QUERY_RESULTS
+
EXPLAIN EXTENDED
FROM (
FROM src
diff --git a/ql/src/test/queries/clientpositive/select_transform_hint.q b/ql/src/test/queries/clientpositive/select_transform_hint.q
index 39577d1..9ad7a92 100644
--- a/ql/src/test/queries/clientpositive/select_transform_hint.q
+++ b/ql/src/test/queries/clientpositive/select_transform_hint.q
@@ -1,4 +1,6 @@
--! qt:dataset:src
+-- SORT_QUERY_RESULTS
+
set hive.entity.capture.transform=true;
EXPLAIN
diff --git a/ql/src/test/results/clientpositive/create_genericudaf.q.out b/ql/src/test/results/clientpositive/create_genericudaf.q.out
deleted file mode 100644
index 85d7850..0000000
--- a/ql/src/test/results/clientpositive/create_genericudaf.q.out
+++ /dev/null
@@ -1,107 +0,0 @@
-PREHOOK: query: EXPLAIN
-CREATE TEMPORARY FUNCTION test_avg AS 'org.apache.hadoop.hive.ql.udf.generic.GenericUDAFAverage'
-PREHOOK: type: CREATEFUNCTION
-PREHOOK: Output: test_avg
-POSTHOOK: query: EXPLAIN
-CREATE TEMPORARY FUNCTION test_avg AS 'org.apache.hadoop.hive.ql.udf.generic.GenericUDAFAverage'
-POSTHOOK: type: CREATEFUNCTION
-POSTHOOK: Output: test_avg
-STAGE DEPENDENCIES:
- Stage-0 is a root stage
-
-STAGE PLANS:
- Stage: Stage-0
- Create Function
- class: org.apache.hadoop.hive.ql.udf.generic.GenericUDAFAverage
- name: test_avg
- temporary: true
-
-PREHOOK: query: CREATE TEMPORARY FUNCTION test_avg AS 'org.apache.hadoop.hive.ql.udf.generic.GenericUDAFAverage'
-PREHOOK: type: CREATEFUNCTION
-PREHOOK: Output: test_avg
-POSTHOOK: query: CREATE TEMPORARY FUNCTION test_avg AS 'org.apache.hadoop.hive.ql.udf.generic.GenericUDAFAverage'
-POSTHOOK: type: CREATEFUNCTION
-POSTHOOK: Output: test_avg
-PREHOOK: query: EXPLAIN
-SELECT
- test_avg(1),
- test_avg(substr(value,5))
-FROM src
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-#### A masked pattern was here ####
-POSTHOOK: query: EXPLAIN
-SELECT
- test_avg(1),
- test_avg(substr(value,5))
-FROM src
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-#### A masked pattern was here ####
-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: src
- Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: substr(value, 5) (type: string)
- outputColumnNames: _col1
- Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: test_avg(1), test_avg(_col1)
- minReductionHashAggr: 0.99
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 332 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- null sort order:
- sort order:
- Statistics: Num rows: 1 Data size: 332 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: struct<count:bigint,sum:double,input:int>), _col1 (type: struct<count:bigint,sum:double,input:string>)
- Reduce Operator Tree:
- Group By Operator
- aggregations: test_avg(VALUE._col0), test_avg(VALUE._col1)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
-
-PREHOOK: query: SELECT
- test_avg(1),
- test_avg(substr(value,5))
-FROM src
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT
- test_avg(1),
- test_avg(substr(value,5))
-FROM src
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-#### A masked pattern was here ####
-1.0 260.182
-PREHOOK: query: DROP TEMPORARY FUNCTIOn test_avg
-PREHOOK: type: DROPFUNCTION
-PREHOOK: Output: test_avg
-POSTHOOK: query: DROP TEMPORARY FUNCTIOn test_avg
-POSTHOOK: type: DROPFUNCTION
-POSTHOOK: Output: test_avg
diff --git a/ql/src/test/results/clientpositive/input14.q.out b/ql/src/test/results/clientpositive/input14.q.out
deleted file mode 100644
index 0e61434..0000000
--- a/ql/src/test/results/clientpositive/input14.q.out
+++ /dev/null
@@ -1,250 +0,0 @@
-PREHOOK: query: CREATE TABLE dest1_n42(key INT, value STRING) STORED AS TEXTFILE
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@dest1_n42
-POSTHOOK: query: CREATE TABLE dest1_n42(key INT, value STRING) STORED AS TEXTFILE
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@dest1_n42
-PREHOOK: query: EXPLAIN
-FROM (
- FROM src
- SELECT TRANSFORM(src.key, src.value)
- USING 'cat' AS (tkey, tvalue)
- CLUSTER BY tkey
-) tmap
-INSERT OVERWRITE TABLE dest1_n42 SELECT tmap.tkey, tmap.tvalue WHERE tmap.tkey < 100
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@dest1_n42
-POSTHOOK: query: EXPLAIN
-FROM (
- FROM src
- SELECT TRANSFORM(src.key, src.value)
- USING 'cat' AS (tkey, tvalue)
- CLUSTER BY tkey
-) tmap
-INSERT OVERWRITE TABLE dest1_n42 SELECT tmap.tkey, tmap.tvalue WHERE tmap.tkey < 100
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@dest1_n42
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
- Stage-2 depends on stages: Stage-0, Stage-3
- Stage-3 depends on stages: Stage-1
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- Transform Operator
- command: cat
- output info:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator
- predicate: (_col0 < 100) (type: boolean)
- Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- null sort order: a
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: string), _col1 (type: string)
- Reduce Operator Tree:
- Select Operator
- expressions: UDFToInteger(VALUE._col0) (type: int), VALUE._col1 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.dest1_n42
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string)
- outputColumnNames: key, value
- Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
- minReductionHashAggr: 0.99
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-0
- Move Operator
- tables:
- replace: true
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.dest1_n42
-
- Stage: Stage-2
- Stats Work
- Basic Stats Work:
- Column Stats Desc:
- Columns: key, value
- Column Types: int, string
- Table: default.dest1_n42
-
- Stage: Stage-3
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- null sort order:
- sort order:
- Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
- Execution mode: vectorized
- Reduce Operator Tree:
- Group By Operator
- aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
-PREHOOK: query: FROM (
- FROM src
- SELECT TRANSFORM(src.key, src.value)
- USING 'cat' AS (tkey, tvalue)
- CLUSTER BY tkey
-) tmap
-INSERT OVERWRITE TABLE dest1_n42 SELECT tmap.tkey, tmap.tvalue WHERE tmap.tkey < 100
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@dest1_n42
-POSTHOOK: query: FROM (
- FROM src
- SELECT TRANSFORM(src.key, src.value)
- USING 'cat' AS (tkey, tvalue)
- CLUSTER BY tkey
-) tmap
-INSERT OVERWRITE TABLE dest1_n42 SELECT tmap.tkey, tmap.tvalue WHERE tmap.tkey < 100
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@dest1_n42
-POSTHOOK: Lineage: dest1_n42.key SCRIPT [(src)src.FieldSchema(name:key, type:string, comment:default), (src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: dest1_n42.value SCRIPT [(src)src.FieldSchema(name:key, type:string, comment:default), (src)src.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: SELECT dest1_n42.* FROM dest1_n42
-PREHOOK: type: QUERY
-PREHOOK: Input: default@dest1_n42
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT dest1_n42.* FROM dest1_n42
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@dest1_n42
-#### A masked pattern was here ####
-0 val_0
-0 val_0
-0 val_0
-10 val_10
-11 val_11
-12 val_12
-12 val_12
-15 val_15
-15 val_15
-17 val_17
-18 val_18
-18 val_18
-19 val_19
-2 val_2
-20 val_20
-24 val_24
-24 val_24
-26 val_26
-26 val_26
-27 val_27
-28 val_28
-30 val_30
-33 val_33
-34 val_34
-35 val_35
-35 val_35
-35 val_35
-37 val_37
-37 val_37
-4 val_4
-41 val_41
-42 val_42
-42 val_42
-43 val_43
-44 val_44
-47 val_47
-5 val_5
-5 val_5
-5 val_5
-51 val_51
-51 val_51
-53 val_53
-54 val_54
-57 val_57
-58 val_58
-58 val_58
-64 val_64
-65 val_65
-66 val_66
-67 val_67
-67 val_67
-69 val_69
-70 val_70
-70 val_70
-70 val_70
-72 val_72
-72 val_72
-74 val_74
-76 val_76
-76 val_76
-77 val_77
-78 val_78
-8 val_8
-80 val_80
-82 val_82
-83 val_83
-83 val_83
-84 val_84
-84 val_84
-85 val_85
-86 val_86
-87 val_87
-9 val_9
-90 val_90
-90 val_90
-90 val_90
-92 val_92
-95 val_95
-95 val_95
-96 val_96
-97 val_97
-97 val_97
-98 val_98
-98 val_98
diff --git a/ql/src/test/results/clientpositive/input14_limit.q.out b/ql/src/test/results/clientpositive/input14_limit.q.out
deleted file mode 100644
index fe9d907..0000000
--- a/ql/src/test/results/clientpositive/input14_limit.q.out
+++ /dev/null
@@ -1,163 +0,0 @@
-PREHOOK: query: CREATE TABLE dest1_n13(key INT, value STRING) STORED AS TEXTFILE
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@dest1_n13
-POSTHOOK: query: CREATE TABLE dest1_n13(key INT, value STRING) STORED AS TEXTFILE
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@dest1_n13
-PREHOOK: query: EXPLAIN
-FROM (
- FROM src
- SELECT TRANSFORM(src.key, src.value)
- USING 'cat' AS (tkey, tvalue)
- CLUSTER BY tkey LIMIT 20
-) tmap
-INSERT OVERWRITE TABLE dest1_n13 SELECT tmap.tkey, tmap.tvalue WHERE tmap.tkey < 100
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@dest1_n13
-POSTHOOK: query: EXPLAIN
-FROM (
- FROM src
- SELECT TRANSFORM(src.key, src.value)
- USING 'cat' AS (tkey, tvalue)
- CLUSTER BY tkey LIMIT 20
-) tmap
-INSERT OVERWRITE TABLE dest1_n13 SELECT tmap.tkey, tmap.tvalue WHERE tmap.tkey < 100
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@dest1_n13
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-2 depends on stages: Stage-1
- Stage-0 depends on stages: Stage-2
- Stage-3 depends on stages: Stage-0
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- Transform Operator
- command: cat
- output info:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- null sort order: a
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- TopN Hash Memory Usage: 0.1
- value expressions: _col0 (type: string), _col1 (type: string)
- Reduce Operator Tree:
- Select Operator
- expressions: VALUE._col0 (type: string), VALUE._col1 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- Limit
- Number of rows: 20
- Statistics: Num rows: 20 Data size: 3560 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: string)
- null sort order: a
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 20 Data size: 3560 Basic stats: COMPLETE Column stats: COMPLETE
- TopN Hash Memory Usage: 0.1
- value expressions: _col1 (type: string)
- Execution mode: vectorized
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 20 Data size: 3560 Basic stats: COMPLETE Column stats: COMPLETE
- Limit
- Number of rows: 20
- Statistics: Num rows: 20 Data size: 3560 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator
- predicate: (_col0 < 100) (type: boolean)
- Statistics: Num rows: 6 Data size: 1068 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: UDFToInteger(_col0) (type: int), _col1 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.dest1_n13
-
- Stage: Stage-0
- Move Operator
- tables:
- replace: true
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.dest1_n13
-
- Stage: Stage-3
- Stats Work
- Basic Stats Work:
-
-PREHOOK: query: FROM (
- FROM src
- SELECT TRANSFORM(src.key, src.value)
- USING 'cat' AS (tkey, tvalue)
- CLUSTER BY tkey LIMIT 20
-) tmap
-INSERT OVERWRITE TABLE dest1_n13 SELECT tmap.tkey, tmap.tvalue WHERE tmap.tkey < 100
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@dest1_n13
-POSTHOOK: query: FROM (
- FROM src
- SELECT TRANSFORM(src.key, src.value)
- USING 'cat' AS (tkey, tvalue)
- CLUSTER BY tkey LIMIT 20
-) tmap
-INSERT OVERWRITE TABLE dest1_n13 SELECT tmap.tkey, tmap.tvalue WHERE tmap.tkey < 100
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@dest1_n13
-POSTHOOK: Lineage: dest1_n13.key SCRIPT [(src)src.FieldSchema(name:key, type:string, comment:default), (src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: dest1_n13.value SCRIPT [(src)src.FieldSchema(name:key, type:string, comment:default), (src)src.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: SELECT dest1_n13.* FROM dest1_n13
-PREHOOK: type: QUERY
-PREHOOK: Input: default@dest1_n13
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT dest1_n13.* FROM dest1_n13
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@dest1_n13
-#### A masked pattern was here ####
-0 val_0
-0 val_0
-0 val_0
-10 val_10
-11 val_11
diff --git a/ql/src/test/results/clientpositive/input17.q.out b/ql/src/test/results/clientpositive/input17.q.out
deleted file mode 100644
index 9c03f5b..0000000
--- a/ql/src/test/results/clientpositive/input17.q.out
+++ /dev/null
@@ -1,174 +0,0 @@
-PREHOOK: query: CREATE TABLE dest1_n81(key INT, value STRING) STORED AS TEXTFILE
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@dest1_n81
-POSTHOOK: query: CREATE TABLE dest1_n81(key INT, value STRING) STORED AS TEXTFILE
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@dest1_n81
-PREHOOK: query: EXPLAIN
-FROM (
- FROM src_thrift
- SELECT TRANSFORM(src_thrift.aint + src_thrift.lint[0], src_thrift.lintstring[0])
- USING 'cat' AS (tkey, tvalue)
- CLUSTER BY tkey
-) tmap
-INSERT OVERWRITE TABLE dest1_n81 SELECT tmap.tkey, tmap.tvalue
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src_thrift
-PREHOOK: Output: default@dest1_n81
-POSTHOOK: query: EXPLAIN
-FROM (
- FROM src_thrift
- SELECT TRANSFORM(src_thrift.aint + src_thrift.lint[0], src_thrift.lintstring[0])
- USING 'cat' AS (tkey, tvalue)
- CLUSTER BY tkey
-) tmap
-INSERT OVERWRITE TABLE dest1_n81 SELECT tmap.tkey, tmap.tvalue
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src_thrift
-POSTHOOK: Output: default@dest1_n81
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
- Stage-2 depends on stages: Stage-0, Stage-3
- Stage-3 depends on stages: Stage-1
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: src_thrift
- Statistics: Num rows: 11 Data size: 29524 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: (aint + lint[0]) (type: int), lintstring[0] (type: struct<myint:int,mystring:string,underscore_int:int>)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 11 Data size: 29524 Basic stats: COMPLETE Column stats: NONE
- Transform Operator
- command: cat
- output info:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Statistics: Num rows: 11 Data size: 29524 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- null sort order: a
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 11 Data size: 29524 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: string), _col1 (type: string)
- Reduce Operator Tree:
- Select Operator
- expressions: UDFToInteger(VALUE._col0) (type: int), VALUE._col1 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 11 Data size: 29524 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 11 Data size: 29524 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.dest1_n81
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string)
- outputColumnNames: key, value
- Statistics: Num rows: 11 Data size: 29524 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
- minReductionHashAggr: 0.99
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 3548 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-0
- Move Operator
- tables:
- replace: true
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.dest1_n81
-
- Stage: Stage-2
- Stats Work
- Basic Stats Work:
- Column Stats Desc:
- Columns: key, value
- Column Types: int, string
- Table: default.dest1_n81
-
- Stage: Stage-3
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- null sort order:
- sort order:
- Statistics: Num rows: 1 Data size: 3548 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
- Execution mode: vectorized
- Reduce Operator Tree:
- Group By Operator
- aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 3564 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 3564 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
-PREHOOK: query: FROM (
- FROM src_thrift
- SELECT TRANSFORM(src_thrift.aint + src_thrift.lint[0], src_thrift.lintstring[0])
- USING 'cat' AS (tkey, tvalue)
- CLUSTER BY tkey
-) tmap
-INSERT OVERWRITE TABLE dest1_n81 SELECT tmap.tkey, tmap.tvalue
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src_thrift
-PREHOOK: Output: default@dest1_n81
-POSTHOOK: query: FROM (
- FROM src_thrift
- SELECT TRANSFORM(src_thrift.aint + src_thrift.lint[0], src_thrift.lintstring[0])
- USING 'cat' AS (tkey, tvalue)
- CLUSTER BY tkey
-) tmap
-INSERT OVERWRITE TABLE dest1_n81 SELECT tmap.tkey, tmap.tvalue
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src_thrift
-POSTHOOK: Output: default@dest1_n81
-POSTHOOK: Lineage: dest1_n81.key SCRIPT [(src_thrift)src_thrift.FieldSchema(name:aint, type:int, comment:from deserializer), (src_thrift)src_thrift.FieldSchema(name:lint, type:array<int>, comment:from deserializer), (src_thrift)src_thrift.FieldSchema(name:lintstring, type:array<struct<myint:int,mystring:string,underscore_int:int>>, comment:from deserializer), ]
-POSTHOOK: Lineage: dest1_n81.value SCRIPT [(src_thrift)src_thrift.FieldSchema(name:aint, type:int, comment:from deserializer), (src_thrift)src_thrift.FieldSchema(name:lint, type:array<int>, comment:from deserializer), (src_thrift)src_thrift.FieldSchema(name:lintstring, type:array<struct<myint:int,mystring:string,underscore_int:int>>, comment:from deserializer), ]
-PREHOOK: query: SELECT dest1_n81.* FROM dest1_n81
-PREHOOK: type: QUERY
-PREHOOK: Input: default@dest1_n81
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT dest1_n81.* FROM dest1_n81
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@dest1_n81
-#### A masked pattern was here ####
--1461153966 {"myint":49,"mystring":"343","underscore_int":7}
--1952710705 {"myint":25,"mystring":"125","underscore_int":5}
--734328905 {"myint":16,"mystring":"64","underscore_int":4}
--751827636 {"myint":4,"mystring":"8","underscore_int":2}
-1244525196 {"myint":36,"mystring":"216","underscore_int":6}
-1638581586 {"myint":64,"mystring":"512","underscore_int":8}
-1712634731 {"myint":0,"mystring":"0","underscore_int":0}
-336964422 {"myint":81,"mystring":"729","underscore_int":9}
-465985201 {"myint":1,"mystring":"1","underscore_int":1}
-477111225 {"myint":9,"mystring":"27","underscore_int":3}
-NULL NULL
diff --git a/ql/src/test/results/clientpositive/input18.q.out b/ql/src/test/results/clientpositive/input18.q.out
deleted file mode 100644
index ce731e6..0000000
--- a/ql/src/test/results/clientpositive/input18.q.out
+++ /dev/null
@@ -1,250 +0,0 @@
-PREHOOK: query: CREATE TABLE dest1_n124(key INT, value STRING) STORED AS TEXTFILE
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@dest1_n124
-POSTHOOK: query: CREATE TABLE dest1_n124(key INT, value STRING) STORED AS TEXTFILE
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@dest1_n124
-PREHOOK: query: EXPLAIN
-FROM (
- FROM src
- SELECT TRANSFORM(src.key, src.value, 1+2, 3+4)
- USING 'cat'
- CLUSTER BY key
-) tmap
-INSERT OVERWRITE TABLE dest1_n124 SELECT tmap.key, regexp_replace(tmap.value,'\t','+') WHERE tmap.key < 100
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@dest1_n124
-POSTHOOK: query: EXPLAIN
-FROM (
- FROM src
- SELECT TRANSFORM(src.key, src.value, 1+2, 3+4)
- USING 'cat'
- CLUSTER BY key
-) tmap
-INSERT OVERWRITE TABLE dest1_n124 SELECT tmap.key, regexp_replace(tmap.value,'\t','+') WHERE tmap.key < 100
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@dest1_n124
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
- Stage-2 depends on stages: Stage-0, Stage-3
- Stage-3 depends on stages: Stage-1
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: key (type: string), value (type: string), 3 (type: int), 7 (type: int)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE
- Transform Operator
- command: cat
- output info:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator
- predicate: (_col0 < 100) (type: boolean)
- Statistics: Num rows: 166 Data size: 30876 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- null sort order: a
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 166 Data size: 30876 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: string), _col1 (type: string)
- Reduce Operator Tree:
- Select Operator
- expressions: UDFToInteger(VALUE._col0) (type: int), regexp_replace(VALUE._col1, ' ', '+') (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 166 Data size: 31208 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 166 Data size: 31208 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.dest1_n124
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string)
- outputColumnNames: key, value
- Statistics: Num rows: 166 Data size: 31208 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
- minReductionHashAggr: 0.99
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-0
- Move Operator
- tables:
- replace: true
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.dest1_n124
-
- Stage: Stage-2
- Stats Work
- Basic Stats Work:
- Column Stats Desc:
- Columns: key, value
- Column Types: int, string
- Table: default.dest1_n124
-
- Stage: Stage-3
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- null sort order:
- sort order:
- Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
- Execution mode: vectorized
- Reduce Operator Tree:
- Group By Operator
- aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
-PREHOOK: query: FROM (
- FROM src
- SELECT TRANSFORM(src.key, src.value, 1+2, 3+4)
- USING 'cat'
- CLUSTER BY key
-) tmap
-INSERT OVERWRITE TABLE dest1_n124 SELECT tmap.key, regexp_replace(tmap.value,'\t','+') WHERE tmap.key < 100
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@dest1_n124
-POSTHOOK: query: FROM (
- FROM src
- SELECT TRANSFORM(src.key, src.value, 1+2, 3+4)
- USING 'cat'
- CLUSTER BY key
-) tmap
-INSERT OVERWRITE TABLE dest1_n124 SELECT tmap.key, regexp_replace(tmap.value,'\t','+') WHERE tmap.key < 100
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@dest1_n124
-POSTHOOK: Lineage: dest1_n124.key SCRIPT [(src)src.FieldSchema(name:key, type:string, comment:default), (src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: dest1_n124.value SCRIPT [(src)src.FieldSchema(name:key, type:string, comment:default), (src)src.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: SELECT dest1_n124.* FROM dest1_n124
-PREHOOK: type: QUERY
-PREHOOK: Input: default@dest1_n124
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT dest1_n124.* FROM dest1_n124
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@dest1_n124
-#### A masked pattern was here ####
-0 val_0+3+7
-0 val_0+3+7
-0 val_0+3+7
-10 val_10+3+7
-11 val_11+3+7
-12 val_12+3+7
-12 val_12+3+7
-15 val_15+3+7
-15 val_15+3+7
-17 val_17+3+7
-18 val_18+3+7
-18 val_18+3+7
-19 val_19+3+7
-2 val_2+3+7
-20 val_20+3+7
-24 val_24+3+7
-24 val_24+3+7
-26 val_26+3+7
-26 val_26+3+7
-27 val_27+3+7
-28 val_28+3+7
-30 val_30+3+7
-33 val_33+3+7
-34 val_34+3+7
-35 val_35+3+7
-35 val_35+3+7
-35 val_35+3+7
-37 val_37+3+7
-37 val_37+3+7
-4 val_4+3+7
-41 val_41+3+7
-42 val_42+3+7
-42 val_42+3+7
-43 val_43+3+7
-44 val_44+3+7
-47 val_47+3+7
-5 val_5+3+7
-5 val_5+3+7
-5 val_5+3+7
-51 val_51+3+7
-51 val_51+3+7
-53 val_53+3+7
-54 val_54+3+7
-57 val_57+3+7
-58 val_58+3+7
-58 val_58+3+7
-64 val_64+3+7
-65 val_65+3+7
-66 val_66+3+7
-67 val_67+3+7
-67 val_67+3+7
-69 val_69+3+7
-70 val_70+3+7
-70 val_70+3+7
-70 val_70+3+7
-72 val_72+3+7
-72 val_72+3+7
-74 val_74+3+7
-76 val_76+3+7
-76 val_76+3+7
-77 val_77+3+7
-78 val_78+3+7
-8 val_8+3+7
-80 val_80+3+7
-82 val_82+3+7
-83 val_83+3+7
-83 val_83+3+7
-84 val_84+3+7
-84 val_84+3+7
-85 val_85+3+7
-86 val_86+3+7
-87 val_87+3+7
-9 val_9+3+7
-90 val_90+3+7
-90 val_90+3+7
-90 val_90+3+7
-92 val_92+3+7
-95 val_95+3+7
-95 val_95+3+7
-96 val_96+3+7
-97 val_97+3+7
-97 val_97+3+7
-98 val_98+3+7
-98 val_98+3+7
diff --git a/ql/src/test/results/clientpositive/input5.q.out b/ql/src/test/results/clientpositive/input5.q.out
deleted file mode 100644
index becfc18..0000000
--- a/ql/src/test/results/clientpositive/input5.q.out
+++ /dev/null
@@ -1,174 +0,0 @@
-PREHOOK: query: CREATE TABLE dest1_n94(key STRING, value STRING) STORED AS TEXTFILE
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@dest1_n94
-POSTHOOK: query: CREATE TABLE dest1_n94(key STRING, value STRING) STORED AS TEXTFILE
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@dest1_n94
-PREHOOK: query: EXPLAIN
-FROM (
- FROM src_thrift
- SELECT TRANSFORM(src_thrift.lint, src_thrift.lintstring)
- USING 'cat' AS (tkey, tvalue)
- CLUSTER BY tkey
-) tmap
-INSERT OVERWRITE TABLE dest1_n94 SELECT tmap.tkey, tmap.tvalue
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src_thrift
-PREHOOK: Output: default@dest1_n94
-POSTHOOK: query: EXPLAIN
-FROM (
- FROM src_thrift
- SELECT TRANSFORM(src_thrift.lint, src_thrift.lintstring)
- USING 'cat' AS (tkey, tvalue)
- CLUSTER BY tkey
-) tmap
-INSERT OVERWRITE TABLE dest1_n94 SELECT tmap.tkey, tmap.tvalue
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src_thrift
-POSTHOOK: Output: default@dest1_n94
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
- Stage-2 depends on stages: Stage-0, Stage-3
- Stage-3 depends on stages: Stage-1
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: src_thrift
- Statistics: Num rows: 11 Data size: 29480 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: lint (type: array<int>), lintstring (type: array<struct<myint:int,mystring:string,underscore_int:int>>)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 11 Data size: 29480 Basic stats: COMPLETE Column stats: NONE
- Transform Operator
- command: cat
- output info:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Statistics: Num rows: 11 Data size: 29480 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- null sort order: a
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 11 Data size: 29480 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: string), _col1 (type: string)
- Reduce Operator Tree:
- Select Operator
- expressions: VALUE._col0 (type: string), VALUE._col1 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 11 Data size: 29480 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 11 Data size: 29480 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.dest1_n94
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string)
- outputColumnNames: key, value
- Statistics: Num rows: 11 Data size: 29480 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
- minReductionHashAggr: 0.99
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 3560 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-0
- Move Operator
- tables:
- replace: true
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.dest1_n94
-
- Stage: Stage-2
- Stats Work
- Basic Stats Work:
- Column Stats Desc:
- Columns: key, value
- Column Types: string, string
- Table: default.dest1_n94
-
- Stage: Stage-3
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- null sort order:
- sort order:
- Statistics: Num rows: 1 Data size: 3560 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
- Execution mode: vectorized
- Reduce Operator Tree:
- Group By Operator
- aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 3560 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 3560 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
-PREHOOK: query: FROM (
- FROM src_thrift
- SELECT TRANSFORM(src_thrift.lint, src_thrift.lintstring)
- USING 'cat' AS (tkey, tvalue)
- CLUSTER BY tkey
-) tmap
-INSERT OVERWRITE TABLE dest1_n94 SELECT tmap.tkey, tmap.tvalue
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src_thrift
-PREHOOK: Output: default@dest1_n94
-POSTHOOK: query: FROM (
- FROM src_thrift
- SELECT TRANSFORM(src_thrift.lint, src_thrift.lintstring)
- USING 'cat' AS (tkey, tvalue)
- CLUSTER BY tkey
-) tmap
-INSERT OVERWRITE TABLE dest1_n94 SELECT tmap.tkey, tmap.tvalue
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src_thrift
-POSTHOOK: Output: default@dest1_n94
-POSTHOOK: Lineage: dest1_n94.key SCRIPT [(src_thrift)src_thrift.FieldSchema(name:lint, type:array<int>, comment:from deserializer), (src_thrift)src_thrift.FieldSchema(name:lintstring, type:array<struct<myint:int,mystring:string,underscore_int:int>>, comment:from deserializer), ]
-POSTHOOK: Lineage: dest1_n94.value SCRIPT [(src_thrift)src_thrift.FieldSchema(name:lint, type:array<int>, comment:from deserializer), (src_thrift)src_thrift.FieldSchema(name:lintstring, type:array<struct<myint:int,mystring:string,underscore_int:int>>, comment:from deserializer), ]
-PREHOOK: query: SELECT dest1_n94.* FROM dest1_n94
-PREHOOK: type: QUERY
-PREHOOK: Input: default@dest1_n94
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT dest1_n94.* FROM dest1_n94
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@dest1_n94
-#### A masked pattern was here ####
-NULL NULL
-[0,0,0] [{"myint":0,"mystring":"0","underscore_int":0}]
-[1,2,3] [{"myint":1,"mystring":"1","underscore_int":1}]
-[2,4,6] [{"myint":4,"mystring":"8","underscore_int":2}]
-[3,6,9] [{"myint":9,"mystring":"27","underscore_int":3}]
-[4,8,12] [{"myint":16,"mystring":"64","underscore_int":4}]
-[5,10,15] [{"myint":25,"mystring":"125","underscore_int":5}]
-[6,12,18] [{"myint":36,"mystring":"216","underscore_int":6}]
-[7,14,21] [{"myint":49,"mystring":"343","underscore_int":7}]
-[8,16,24] [{"myint":64,"mystring":"512","underscore_int":8}]
-[9,18,27] [{"myint":81,"mystring":"729","underscore_int":9}]
diff --git a/ql/src/test/results/clientpositive/insert_into3.q.out b/ql/src/test/results/clientpositive/insert_into3.q.out
deleted file mode 100644
index 60fd42d..0000000
--- a/ql/src/test/results/clientpositive/insert_into3.q.out
+++ /dev/null
@@ -1,568 +0,0 @@
-PREHOOK: query: DROP TABLE insert_into3a
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: DROP TABLE insert_into3a
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: DROP TABLE insert_into3b
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: DROP TABLE insert_into3b
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: CREATE TABLE insert_into3a (key int, value string)
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@insert_into3a
-POSTHOOK: query: CREATE TABLE insert_into3a (key int, value string)
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@insert_into3a
-PREHOOK: query: CREATE TABLE insert_into3b (key int, value string)
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@insert_into3b
-POSTHOOK: query: CREATE TABLE insert_into3b (key int, value string)
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@insert_into3b
-PREHOOK: query: EXPLAIN FROM src INSERT INTO TABLE insert_into3a SELECT * ORDER BY key, value LIMIT 50
- INSERT INTO TABLE insert_into3b SELECT * ORDER BY key, value LIMIT 100
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@insert_into3a
-PREHOOK: Output: default@insert_into3b
-POSTHOOK: query: EXPLAIN FROM src INSERT INTO TABLE insert_into3a SELECT * ORDER BY key, value LIMIT 50
- INSERT INTO TABLE insert_into3b SELECT * ORDER BY key, value LIMIT 100
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@insert_into3a
-POSTHOOK: Output: default@insert_into3b
-STAGE DEPENDENCIES:
- Stage-2 is a root stage
- Stage-0 depends on stages: Stage-2
- Stage-3 depends on stages: Stage-0, Stage-4, Stage-7
- Stage-4 depends on stages: Stage-2
- Stage-6 depends on stages: Stage-1, Stage-4, Stage-7
- Stage-5 depends on stages: Stage-2
- Stage-1 depends on stages: Stage-5
- Stage-7 depends on stages: Stage-5
-
-STAGE PLANS:
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string)
- null sort order: zz
- sort order: ++
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- TopN Hash Memory Usage: 0.1
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
- Execution mode: vectorized
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- Limit
- Number of rows: 50
- Statistics: Num rows: 50 Data size: 8900 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: UDFToInteger(_col0) (type: int), _col1 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 50 Data size: 4750 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 50 Data size: 4750 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.insert_into3a
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string)
- outputColumnNames: key, value
- Statistics: Num rows: 50 Data size: 4750 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
- minReductionHashAggr: 0.99
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-0
- Move Operator
- tables:
- replace: false
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.insert_into3a
-
- Stage: Stage-3
- Stats Work
- Basic Stats Work:
- Column Stats Desc:
- Columns: key, value
- Column Types: int, string
- Table: default.insert_into3a
-
- Stage: Stage-4
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- null sort order:
- sort order:
- Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
- Execution mode: vectorized
- Reduce Operator Tree:
- Group By Operator
- aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-6
- Stats Work
- Basic Stats Work:
- Column Stats Desc:
- Columns: key, value
- Column Types: int, string
- Table: default.insert_into3b
-
- Stage: Stage-5
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string)
- null sort order: zz
- sort order: ++
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- TopN Hash Memory Usage: 0.1
- Execution mode: vectorized
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- Limit
- Number of rows: 100
- Statistics: Num rows: 100 Data size: 17800 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: UDFToInteger(_col0) (type: int), _col1 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 100 Data size: 9500 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 100 Data size: 9500 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.insert_into3b
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string)
- outputColumnNames: key, value
- Statistics: Num rows: 100 Data size: 9500 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
- minReductionHashAggr: 0.99
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-1
- Move Operator
- tables:
- replace: false
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.insert_into3b
-
- Stage: Stage-7
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- null sort order:
- sort order:
- Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
- Execution mode: vectorized
- Reduce Operator Tree:
- Group By Operator
- aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
-PREHOOK: query: FROM src INSERT INTO TABLE insert_into3a SELECT * ORDER BY key, value LIMIT 50
- INSERT INTO TABLE insert_into3b SELECT * ORDER BY key, value LIMIT 100
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@insert_into3a
-PREHOOK: Output: default@insert_into3b
-POSTHOOK: query: FROM src INSERT INTO TABLE insert_into3a SELECT * ORDER BY key, value LIMIT 50
- INSERT INTO TABLE insert_into3b SELECT * ORDER BY key, value LIMIT 100
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@insert_into3a
-POSTHOOK: Output: default@insert_into3b
-POSTHOOK: Lineage: insert_into3a.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: insert_into3a.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: insert_into3b.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: insert_into3b.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: SELECT SUM(HASH(c)) FROM (
- SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into3a
-) t
-PREHOOK: type: QUERY
-PREHOOK: Input: default@insert_into3a
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT SUM(HASH(c)) FROM (
- SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into3a
-) t
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@insert_into3a
-#### A masked pattern was here ####
--1254133670
-PREHOOK: query: SELECT SUM(HASH(c)) FROM (
- SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into3b
-) t
-PREHOOK: type: QUERY
-PREHOOK: Input: default@insert_into3b
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT SUM(HASH(c)) FROM (
- SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into3b
-) t
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@insert_into3b
-#### A masked pattern was here ####
--1142373758
-PREHOOK: query: EXPLAIN FROM src INSERT OVERWRITE TABLE insert_into3a SELECT * LIMIT 10
- INSERT INTO TABLE insert_into3b SELECT * LIMIT 10
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@insert_into3a
-PREHOOK: Output: default@insert_into3b
-POSTHOOK: query: EXPLAIN FROM src INSERT OVERWRITE TABLE insert_into3a SELECT * LIMIT 10
- INSERT INTO TABLE insert_into3b SELECT * LIMIT 10
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@insert_into3a
-POSTHOOK: Output: default@insert_into3b
-STAGE DEPENDENCIES:
- Stage-2 is a root stage
- Stage-0 depends on stages: Stage-2
- Stage-3 depends on stages: Stage-0, Stage-4, Stage-7
- Stage-4 depends on stages: Stage-2
- Stage-6 depends on stages: Stage-1, Stage-4, Stage-7
- Stage-5 depends on stages: Stage-2
- Stage-1 depends on stages: Stage-5
- Stage-7 depends on stages: Stage-5
-
-STAGE PLANS:
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- Limit
- Number of rows: 10
- Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- null sort order:
- sort order:
- Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
- TopN Hash Memory Usage: 0.1
- value expressions: _col0 (type: string), _col1 (type: string)
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- Limit
- Number of rows: 10
- Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
- Execution mode: vectorized
- Reduce Operator Tree:
- Select Operator
- expressions: VALUE._col0 (type: string), VALUE._col1 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
- Limit
- Number of rows: 10
- Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: UDFToInteger(_col0) (type: int), _col1 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.insert_into3a
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string)
- outputColumnNames: key, value
- Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
- minReductionHashAggr: 0.99
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-0
- Move Operator
- tables:
- replace: true
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.insert_into3a
-
- Stage: Stage-3
- Stats Work
- Basic Stats Work:
- Column Stats Desc:
- Columns: key, value
- Column Types: int, string
- Table: default.insert_into3a
-
- Stage: Stage-4
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- null sort order:
- sort order:
- Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
- Execution mode: vectorized
- Reduce Operator Tree:
- Group By Operator
- aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-6
- Stats Work
- Basic Stats Work:
- Column Stats Desc:
- Columns: key, value
- Column Types: int, string
- Table: default.insert_into3b
-
- Stage: Stage-5
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- null sort order:
- sort order:
- Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
- TopN Hash Memory Usage: 0.1
- value expressions: _col0 (type: string), _col1 (type: string)
- Execution mode: vectorized
- Reduce Operator Tree:
- Select Operator
- expressions: VALUE._col0 (type: string), VALUE._col1 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
- Limit
- Number of rows: 10
- Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: UDFToInteger(_col0) (type: int), _col1 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.insert_into3b
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string)
- outputColumnNames: key, value
- Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
- minReductionHashAggr: 0.99
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-1
- Move Operator
- tables:
- replace: false
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.insert_into3b
-
- Stage: Stage-7
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- null sort order:
- sort order:
- Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
- Execution mode: vectorized
- Reduce Operator Tree:
- Group By Operator
- aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
-PREHOOK: query: FROM src INSERT OVERWRITE TABLE insert_into3a SELECT * LIMIT 10
- INSERT INTO TABLE insert_into3b SELECT * LIMIT 10
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@insert_into3a
-PREHOOK: Output: default@insert_into3b
-POSTHOOK: query: FROM src INSERT OVERWRITE TABLE insert_into3a SELECT * LIMIT 10
- INSERT INTO TABLE insert_into3b SELECT * LIMIT 10
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@insert_into3a
-POSTHOOK: Output: default@insert_into3b
-POSTHOOK: Lineage: insert_into3a.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: insert_into3a.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: insert_into3b.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: insert_into3b.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: SELECT SUM(HASH(c)) FROM (
- SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into3a
-) t
-PREHOOK: type: QUERY
-PREHOOK: Input: default@insert_into3a
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT SUM(HASH(c)) FROM (
- SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into3a
-) t
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@insert_into3a
-#### A masked pattern was here ####
--826625916
-PREHOOK: query: SELECT SUM(HASH(c)) FROM (
- SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into3b
-) t
-PREHOOK: type: QUERY
-PREHOOK: Input: default@insert_into3b
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT SUM(HASH(c)) FROM (
- SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into3b
-) t
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@insert_into3b
-#### A masked pattern was here ####
--1968999674
-PREHOOK: query: DROP TABLE insert_into3a
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@insert_into3a
-PREHOOK: Output: default@insert_into3a
-POSTHOOK: query: DROP TABLE insert_into3a
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@insert_into3a
-POSTHOOK: Output: default@insert_into3a
-PREHOOK: query: DROP TABLE insert_into3b
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@insert_into3b
-PREHOOK: Output: default@insert_into3b
-POSTHOOK: query: DROP TABLE insert_into3b
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@insert_into3b
-POSTHOOK: Output: default@insert_into3b
diff --git a/ql/src/test/results/clientpositive/insert_into4.q.out b/ql/src/test/results/clientpositive/insert_into4.q.out
deleted file mode 100644
index 031d562..0000000
--- a/ql/src/test/results/clientpositive/insert_into4.q.out
+++ /dev/null
@@ -1,460 +0,0 @@
-PREHOOK: query: DROP TABLE insert_into4a
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: DROP TABLE insert_into4a
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: DROP TABLE insert_into4b
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: DROP TABLE insert_into4b
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: CREATE TABLE insert_into4a (key int, value string)
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@insert_into4a
-POSTHOOK: query: CREATE TABLE insert_into4a (key int, value string)
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@insert_into4a
-PREHOOK: query: CREATE TABLE insert_into4b (key int, value string)
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@insert_into4b
-POSTHOOK: query: CREATE TABLE insert_into4b (key int, value string)
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@insert_into4b
-PREHOOK: query: EXPLAIN INSERT INTO TABLE insert_into4a SELECT * FROM src LIMIT 10
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@insert_into4a
-POSTHOOK: query: EXPLAIN INSERT INTO TABLE insert_into4a SELECT * FROM src LIMIT 10
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@insert_into4a
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
- Stage-2 depends on stages: Stage-0, Stage-3
- Stage-3 depends on stages: Stage-1
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- Limit
- Number of rows: 10
- Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- null sort order:
- sort order:
- Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
- TopN Hash Memory Usage: 0.1
- value expressions: _col0 (type: string), _col1 (type: string)
- Execution mode: vectorized
- Reduce Operator Tree:
- Select Operator
- expressions: VALUE._col0 (type: string), VALUE._col1 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
- Limit
- Number of rows: 10
- Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: UDFToInteger(_col0) (type: int), _col1 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.insert_into4a
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string)
- outputColumnNames: key, value
- Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
- minReductionHashAggr: 0.99
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-0
- Move Operator
- tables:
- replace: false
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.insert_into4a
-
- Stage: Stage-2
- Stats Work
- Basic Stats Work:
- Column Stats Desc:
- Columns: key, value
- Column Types: int, string
- Table: default.insert_into4a
-
- Stage: Stage-3
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- null sort order:
- sort order:
- Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
- Execution mode: vectorized
- Reduce Operator Tree:
- Group By Operator
- aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
-PREHOOK: query: INSERT INTO TABLE insert_into4a SELECT * FROM src LIMIT 10
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@insert_into4a
-POSTHOOK: query: INSERT INTO TABLE insert_into4a SELECT * FROM src LIMIT 10
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@insert_into4a
-POSTHOOK: Lineage: insert_into4a.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: insert_into4a.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: SELECT SUM(HASH(c)) FROM (
- SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into4a
-) t
-PREHOOK: type: QUERY
-PREHOOK: Input: default@insert_into4a
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT SUM(HASH(c)) FROM (
- SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into4a
-) t
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@insert_into4a
-#### A masked pattern was here ####
--826625916
-PREHOOK: query: EXPLAIN INSERT INTO TABLE insert_into4a SELECT * FROM src LIMIT 10
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@insert_into4a
-POSTHOOK: query: EXPLAIN INSERT INTO TABLE insert_into4a SELECT * FROM src LIMIT 10
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@insert_into4a
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
- Stage-2 depends on stages: Stage-0, Stage-3
- Stage-3 depends on stages: Stage-1
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- Limit
- Number of rows: 10
- Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- null sort order:
- sort order:
- Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
- TopN Hash Memory Usage: 0.1
- value expressions: _col0 (type: string), _col1 (type: string)
- Execution mode: vectorized
- Reduce Operator Tree:
- Select Operator
- expressions: VALUE._col0 (type: string), VALUE._col1 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
- Limit
- Number of rows: 10
- Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: UDFToInteger(_col0) (type: int), _col1 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.insert_into4a
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string)
- outputColumnNames: key, value
- Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
- minReductionHashAggr: 0.99
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-0
- Move Operator
- tables:
- replace: false
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.insert_into4a
-
- Stage: Stage-2
- Stats Work
- Basic Stats Work:
- Column Stats Desc:
- Columns: key, value
- Column Types: int, string
- Table: default.insert_into4a
-
- Stage: Stage-3
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- null sort order:
- sort order:
- Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
- Execution mode: vectorized
- Reduce Operator Tree:
- Group By Operator
- aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
-PREHOOK: query: INSERT INTO TABLE insert_into4a SELECT * FROM src LIMIT 10
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@insert_into4a
-POSTHOOK: query: INSERT INTO TABLE insert_into4a SELECT * FROM src LIMIT 10
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@insert_into4a
-POSTHOOK: Lineage: insert_into4a.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: insert_into4a.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: SELECT SUM(HASH(c)) FROM (
- SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into4a
-) t
-PREHOOK: type: QUERY
-PREHOOK: Input: default@insert_into4a
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT SUM(HASH(c)) FROM (
- SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into4a
-) t
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@insert_into4a
-#### A masked pattern was here ####
--1653251832
-PREHOOK: query: EXPLAIN INSERT INTO TABLE insert_into4b SELECT * FROM insert_into4a
-PREHOOK: type: QUERY
-PREHOOK: Input: default@insert_into4a
-PREHOOK: Output: default@insert_into4b
-POSTHOOK: query: EXPLAIN INSERT INTO TABLE insert_into4b SELECT * FROM insert_into4a
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@insert_into4a
-POSTHOOK: Output: default@insert_into4b
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5
- Stage-4
- Stage-0 depends on stages: Stage-4, Stage-3, Stage-6
- Stage-2 depends on stages: Stage-0
- Stage-3
- Stage-5
- Stage-6 depends on stages: Stage-5
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: insert_into4a
- Statistics: Num rows: 20 Data size: 1900 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: key (type: int), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 20 Data size: 1900 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 20 Data size: 1900 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.insert_into4b
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string)
- outputColumnNames: key, value
- Statistics: Num rows: 20 Data size: 1900 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
- minReductionHashAggr: 0.99
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- null sort order:
- sort order:
- Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
- Reduce Operator Tree:
- Group By Operator
- aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-7
- Conditional Operator
-
- Stage: Stage-4
- Move Operator
- files:
- hdfs directory: true
-#### A masked pattern was here ####
-
- Stage: Stage-0
- Move Operator
- tables:
- replace: false
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.insert_into4b
-
- Stage: Stage-2
- Stats Work
- Basic Stats Work:
- Column Stats Desc:
- Columns: key, value
- Column Types: int, string
- Table: default.insert_into4b
-
- Stage: Stage-3
- Map Reduce
- Map Operator Tree:
- TableScan
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.insert_into4b
-
- Stage: Stage-5
- Map Reduce
- Map Operator Tree:
- TableScan
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.insert_into4b
-
- Stage: Stage-6
- Move Operator
- files:
- hdfs directory: true
-#### A masked pattern was here ####
-
-PREHOOK: query: INSERT INTO TABLE insert_into4b SELECT * FROM insert_into4a
-PREHOOK: type: QUERY
-PREHOOK: Input: default@insert_into4a
-PREHOOK: Output: default@insert_into4b
-POSTHOOK: query: INSERT INTO TABLE insert_into4b SELECT * FROM insert_into4a
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@insert_into4a
-POSTHOOK: Output: default@insert_into4b
-POSTHOOK: Lineage: insert_into4b.key SIMPLE [(insert_into4a)insert_into4a.FieldSchema(name:key, type:int, comment:null), ]
-POSTHOOK: Lineage: insert_into4b.value SIMPLE [(insert_into4a)insert_into4a.FieldSchema(name:value, type:string, comment:null), ]
-PREHOOK: query: SELECT SUM(HASH(c)) FROM (
- SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into4b
-) t
-PREHOOK: type: QUERY
-PREHOOK: Input: default@insert_into4b
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT SUM(HASH(c)) FROM (
- SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into4b
-) t
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@insert_into4b
-#### A masked pattern was here ####
--1653251832
-PREHOOK: query: DROP TABLE insert_into4a
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@insert_into4a
-PREHOOK: Output: default@insert_into4a
-POSTHOOK: query: DROP TABLE insert_into4a
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@insert_into4a
-POSTHOOK: Output: default@insert_into4a
-PREHOOK: query: DROP TABLE insert_into4b
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@insert_into4b
-PREHOOK: Output: default@insert_into4b
-POSTHOOK: query: DROP TABLE insert_into4b
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@insert_into4b
-POSTHOOK: Output: default@insert_into4b
diff --git a/ql/src/test/results/clientpositive/insert_into5.q.out b/ql/src/test/results/clientpositive/insert_into5.q.out
deleted file mode 100644
index 8ca94ee..0000000
--- a/ql/src/test/results/clientpositive/insert_into5.q.out
+++ /dev/null
@@ -1,637 +0,0 @@
-PREHOOK: query: DROP TABLE insert_into5a
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: DROP TABLE insert_into5a
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: DROP TABLE insert_into5b
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: DROP TABLE insert_into5b
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: CREATE TABLE insert_into5a (key int, value string)
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@insert_into5a
-POSTHOOK: query: CREATE TABLE insert_into5a (key int, value string)
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@insert_into5a
-PREHOOK: query: CREATE TABLE insert_into5b (key int, value string) PARTITIONED BY (ds string)
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@insert_into5b
-POSTHOOK: query: CREATE TABLE insert_into5b (key int, value string) PARTITIONED BY (ds string)
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@insert_into5b
-PREHOOK: query: EXPLAIN INSERT INTO TABLE insert_into5a SELECT 1, 'one' FROM src LIMIT 10
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@insert_into5a
-POSTHOOK: query: EXPLAIN INSERT INTO TABLE insert_into5a SELECT 1, 'one' FROM src LIMIT 10
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@insert_into5a
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
- Stage-2 depends on stages: Stage-0, Stage-3
- Stage-3 depends on stages: Stage-1
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: 1 (type: int), 'one' (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
- Limit
- Number of rows: 10
- Statistics: Num rows: 10 Data size: 910 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- null sort order:
- sort order:
- Statistics: Num rows: 10 Data size: 910 Basic stats: COMPLETE Column stats: COMPLETE
- TopN Hash Memory Usage: 0.1
- value expressions: _col0 (type: int), _col1 (type: string)
- Execution mode: vectorized
- Reduce Operator Tree:
- Select Operator
- expressions: VALUE._col0 (type: int), VALUE._col1 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 910 Basic stats: COMPLETE Column stats: COMPLETE
- Limit
- Number of rows: 10
- Statistics: Num rows: 10 Data size: 910 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 10 Data size: 910 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.insert_into5a
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string)
- outputColumnNames: key, value
- Statistics: Num rows: 10 Data size: 910 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
- minReductionHashAggr: 0.99
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-0
- Move Operator
- tables:
- replace: false
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.insert_into5a
-
- Stage: Stage-2
- Stats Work
- Basic Stats Work:
- Column Stats Desc:
- Columns: key, value
- Column Types: int, string
- Table: default.insert_into5a
-
- Stage: Stage-3
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- null sort order:
- sort order:
- Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
- Execution mode: vectorized
- Reduce Operator Tree:
- Group By Operator
- aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
-PREHOOK: query: INSERT INTO TABLE insert_into5a SELECT 1, 'one' FROM src LIMIT 10
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@insert_into5a
-POSTHOOK: query: INSERT INTO TABLE insert_into5a SELECT 1, 'one' FROM src LIMIT 10
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@insert_into5a
-POSTHOOK: Lineage: insert_into5a.key SIMPLE []
-POSTHOOK: Lineage: insert_into5a.value SIMPLE []
-PREHOOK: query: SELECT SUM(HASH(c)) FROM (
- SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into5a
-) t
-PREHOOK: type: QUERY
-PREHOOK: Input: default@insert_into5a
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT SUM(HASH(c)) FROM (
- SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into5a
-) t
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@insert_into5a
-#### A masked pattern was here ####
-481928560
-PREHOOK: query: EXPLAIN INSERT INTO TABLE insert_into5a SELECT * FROM insert_into5a
-PREHOOK: type: QUERY
-PREHOOK: Input: default@insert_into5a
-PREHOOK: Output: default@insert_into5a
-POSTHOOK: query: EXPLAIN INSERT INTO TABLE insert_into5a SELECT * FROM insert_into5a
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@insert_into5a
-POSTHOOK: Output: default@insert_into5a
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5
- Stage-4
- Stage-0 depends on stages: Stage-4, Stage-3, Stage-6
- Stage-2 depends on stages: Stage-0
- Stage-3
- Stage-5
- Stage-6 depends on stages: Stage-5
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: insert_into5a
- Statistics: Num rows: 10 Data size: 910 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: key (type: int), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 910 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 10 Data size: 910 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.insert_into5a
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string)
- outputColumnNames: key, value
- Statistics: Num rows: 10 Data size: 910 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
- minReductionHashAggr: 0.99
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- null sort order:
- sort order:
- Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
- Reduce Operator Tree:
- Group By Operator
- aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-7
- Conditional Operator
-
- Stage: Stage-4
- Move Operator
- files:
- hdfs directory: true
-#### A masked pattern was here ####
-
- Stage: Stage-0
- Move Operator
- tables:
- replace: false
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.insert_into5a
-
- Stage: Stage-2
- Stats Work
- Basic Stats Work:
- Column Stats Desc:
- Columns: key, value
- Column Types: int, string
- Table: default.insert_into5a
-
- Stage: Stage-3
- Map Reduce
- Map Operator Tree:
- TableScan
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.insert_into5a
-
- Stage: Stage-5
- Map Reduce
- Map Operator Tree:
- TableScan
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.insert_into5a
-
- Stage: Stage-6
- Move Operator
- files:
- hdfs directory: true
-#### A masked pattern was here ####
-
-PREHOOK: query: INSERT INTO TABLE insert_into5a SELECT * FROM insert_into5a
-PREHOOK: type: QUERY
-PREHOOK: Input: default@insert_into5a
-PREHOOK: Output: default@insert_into5a
-POSTHOOK: query: INSERT INTO TABLE insert_into5a SELECT * FROM insert_into5a
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@insert_into5a
-POSTHOOK: Output: default@insert_into5a
-POSTHOOK: Lineage: insert_into5a.key SIMPLE [(insert_into5a)insert_into5a.FieldSchema(name:key, type:int, comment:null), ]
-POSTHOOK: Lineage: insert_into5a.value SIMPLE [(insert_into5a)insert_into5a.FieldSchema(name:value, type:string, comment:null), ]
-PREHOOK: query: SELECT SUM(HASH(c)) FROM (
- SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into5a
-) t
-PREHOOK: type: QUERY
-PREHOOK: Input: default@insert_into5a
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT SUM(HASH(c)) FROM (
- SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into5a
-) t
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@insert_into5a
-#### A masked pattern was here ####
-963857120
-PREHOOK: query: EXPLAIN INSERT INTO TABLE insert_into5b PARTITION (ds='1')
- SELECT * FROM insert_into5a
-PREHOOK: type: QUERY
-PREHOOK: Input: default@insert_into5a
-PREHOOK: Output: default@insert_into5b@ds=1
-POSTHOOK: query: EXPLAIN INSERT INTO TABLE insert_into5b PARTITION (ds='1')
- SELECT * FROM insert_into5a
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@insert_into5a
-POSTHOOK: Output: default@insert_into5b@ds=1
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5
- Stage-4
- Stage-0 depends on stages: Stage-4, Stage-3, Stage-6
- Stage-2 depends on stages: Stage-0
- Stage-3
- Stage-5
- Stage-6 depends on stages: Stage-5
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: insert_into5a
- Statistics: Num rows: 20 Data size: 1820 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: key (type: int), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 20 Data size: 1820 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 20 Data size: 1820 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.insert_into5b
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string), '1' (type: string)
- outputColumnNames: key, value, ds
- Statistics: Num rows: 20 Data size: 3520 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
- keys: ds (type: string)
- minReductionHashAggr: 0.99
- mode: hash
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- null sort order: z
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
- Reduce Operator Tree:
- Group By Operator
- aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
- keys: KEY._col0 (type: string)
- mode: mergepartial
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-7
- Conditional Operator
-
- Stage: Stage-4
- Move Operator
- files:
- hdfs directory: true
-#### A masked pattern was here ####
-
- Stage: Stage-0
- Move Operator
- tables:
- partition:
- ds 1
- replace: false
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.insert_into5b
-
- Stage: Stage-2
- Stats Work
- Basic Stats Work:
- Column Stats Desc:
- Columns: key, value
- Column Types: int, string
- Table: default.insert_into5b
-
- Stage: Stage-3
- Map Reduce
- Map Operator Tree:
- TableScan
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.insert_into5b
-
- Stage: Stage-5
- Map Reduce
- Map Operator Tree:
- TableScan
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.insert_into5b
-
- Stage: Stage-6
- Move Operator
- files:
- hdfs directory: true
-#### A masked pattern was here ####
-
-PREHOOK: query: INSERT INTO TABLE insert_into5b PARTITION (ds='1') SELECT * FROM insert_into5a
-PREHOOK: type: QUERY
-PREHOOK: Input: default@insert_into5a
-PREHOOK: Output: default@insert_into5b@ds=1
-POSTHOOK: query: INSERT INTO TABLE insert_into5b PARTITION (ds='1') SELECT * FROM insert_into5a
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@insert_into5a
-POSTHOOK: Output: default@insert_into5b@ds=1
-POSTHOOK: Lineage: insert_into5b PARTITION(ds=1).key SIMPLE [(insert_into5a)insert_into5a.FieldSchema(name:key, type:int, comment:null), ]
-POSTHOOK: Lineage: insert_into5b PARTITION(ds=1).value SIMPLE [(insert_into5a)insert_into5a.FieldSchema(name:value, type:string, comment:null), ]
-PREHOOK: query: SELECT SUM(HASH(c)) FROM (
- SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into5b
-) t
-PREHOOK: type: QUERY
-PREHOOK: Input: default@insert_into5b
-PREHOOK: Input: default@insert_into5b@ds=1
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT SUM(HASH(c)) FROM (
- SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into5b
-) t
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@insert_into5b
-POSTHOOK: Input: default@insert_into5b@ds=1
-#### A masked pattern was here ####
--18626052920
-PREHOOK: query: EXPLAIN INSERT INTO TABLE insert_into5b PARTITION (ds='1')
- SELECT key, value FROM insert_into5b
-PREHOOK: type: QUERY
-PREHOOK: Input: default@insert_into5b
-PREHOOK: Input: default@insert_into5b@ds=1
-PREHOOK: Output: default@insert_into5b@ds=1
-POSTHOOK: query: EXPLAIN INSERT INTO TABLE insert_into5b PARTITION (ds='1')
- SELECT key, value FROM insert_into5b
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@insert_into5b
-POSTHOOK: Input: default@insert_into5b@ds=1
-POSTHOOK: Output: default@insert_into5b@ds=1
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5
- Stage-4
- Stage-0 depends on stages: Stage-4, Stage-3, Stage-6
- Stage-2 depends on stages: Stage-0
- Stage-3
- Stage-5
- Stage-6 depends on stages: Stage-5
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: insert_into5b
- Statistics: Num rows: 20 Data size: 1820 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: key (type: int), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 20 Data size: 1820 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 20 Data size: 1820 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.insert_into5b
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string), '1' (type: string)
- outputColumnNames: key, value, ds
- Statistics: Num rows: 20 Data size: 3520 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
- keys: ds (type: string)
- minReductionHashAggr: 0.99
- mode: hash
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- null sort order: z
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
- Reduce Operator Tree:
- Group By Operator
- aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
- keys: KEY._col0 (type: string)
- mode: mergepartial
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-7
- Conditional Operator
-
- Stage: Stage-4
- Move Operator
- files:
- hdfs directory: true
-#### A masked pattern was here ####
-
- Stage: Stage-0
- Move Operator
- tables:
- partition:
- ds 1
- replace: false
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.insert_into5b
-
- Stage: Stage-2
- Stats Work
- Basic Stats Work:
- Column Stats Desc:
- Columns: key, value
- Column Types: int, string
- Table: default.insert_into5b
-
- Stage: Stage-3
- Map Reduce
- Map Operator Tree:
- TableScan
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.insert_into5b
-
- Stage: Stage-5
- Map Reduce
- Map Operator Tree:
- TableScan
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.insert_into5b
-
- Stage: Stage-6
- Move Operator
- files:
- hdfs directory: true
-#### A masked pattern was here ####
-
-PREHOOK: query: INSERT INTO TABLE insert_into5b PARTITION (ds='1')
- SELECT key, value FROM insert_into5b
-PREHOOK: type: QUERY
-PREHOOK: Input: default@insert_into5b
-PREHOOK: Input: default@insert_into5b@ds=1
-PREHOOK: Output: default@insert_into5b@ds=1
-POSTHOOK: query: INSERT INTO TABLE insert_into5b PARTITION (ds='1')
- SELECT key, value FROM insert_into5b
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@insert_into5b
-POSTHOOK: Input: default@insert_into5b@ds=1
-POSTHOOK: Output: default@insert_into5b@ds=1
-POSTHOOK: Lineage: insert_into5b PARTITION(ds=1).key SIMPLE [(insert_into5b)insert_into5b.FieldSchema(name:key, type:int, comment:null), ]
-POSTHOOK: Lineage: insert_into5b PARTITION(ds=1).value SIMPLE [(insert_into5b)insert_into5b.FieldSchema(name:value, type:string, comment:null), ]
-PREHOOK: query: SELECT SUM(HASH(c)) FROM (
- SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into5b
-) t
-PREHOOK: type: QUERY
-PREHOOK: Input: default@insert_into5b
-PREHOOK: Input: default@insert_into5b@ds=1
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT SUM(HASH(c)) FROM (
- SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into5b
-) t
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@insert_into5b
-POSTHOOK: Input: default@insert_into5b@ds=1
-#### A masked pattern was here ####
--37252105840
-PREHOOK: query: DROP TABLE insert_into5a
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@insert_into5a
-PREHOOK: Output: default@insert_into5a
-POSTHOOK: query: DROP TABLE insert_into5a
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@insert_into5a
-POSTHOOK: Output: default@insert_into5a
diff --git a/ql/src/test/results/clientpositive/insert_into6.q.out b/ql/src/test/results/clientpositive/insert_into6.q.out
deleted file mode 100644
index 2c6cab5..0000000
--- a/ql/src/test/results/clientpositive/insert_into6.q.out
+++ /dev/null
@@ -1,383 +0,0 @@
-PREHOOK: query: DROP TABLE insert_into6a
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: DROP TABLE insert_into6a
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: DROP TABLE insert_into6b
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: DROP TABLE insert_into6b
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: CREATE TABLE insert_into6a (key int, value string) PARTITIONED BY (ds string)
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@insert_into6a
-POSTHOOK: query: CREATE TABLE insert_into6a (key int, value string) PARTITIONED BY (ds string)
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@insert_into6a
-PREHOOK: query: CREATE TABLE insert_into6b (key int, value string) PARTITIONED BY (ds string)
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@insert_into6b
-POSTHOOK: query: CREATE TABLE insert_into6b (key int, value string) PARTITIONED BY (ds string)
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@insert_into6b
-PREHOOK: query: EXPLAIN INSERT INTO TABLE insert_into6a PARTITION (ds='1')
- SELECT * FROM src LIMIT 150
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@insert_into6a@ds=1
-POSTHOOK: query: EXPLAIN INSERT INTO TABLE insert_into6a PARTITION (ds='1')
- SELECT * FROM src LIMIT 150
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@insert_into6a@ds=1
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
- Stage-2 depends on stages: Stage-0, Stage-3
- Stage-3 depends on stages: Stage-1
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- Limit
- Number of rows: 150
- Statistics: Num rows: 150 Data size: 26700 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- null sort order:
- sort order:
- Statistics: Num rows: 150 Data size: 26700 Basic stats: COMPLETE Column stats: COMPLETE
- TopN Hash Memory Usage: 0.1
- value expressions: _col0 (type: string), _col1 (type: string)
- Execution mode: vectorized
- Reduce Operator Tree:
- Select Operator
- expressions: VALUE._col0 (type: string), VALUE._col1 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 150 Data size: 26700 Basic stats: COMPLETE Column stats: COMPLETE
- Limit
- Number of rows: 150
- Statistics: Num rows: 150 Data size: 26700 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: UDFToInteger(_col0) (type: int), _col1 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 150 Data size: 14250 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 150 Data size: 14250 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.insert_into6a
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string), '1' (type: string)
- outputColumnNames: key, value, ds
- Statistics: Num rows: 150 Data size: 27000 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
- keys: ds (type: string)
- minReductionHashAggr: 0.99
- mode: hash
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-0
- Move Operator
- tables:
- partition:
- ds 1
- replace: false
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.insert_into6a
-
- Stage: Stage-2
- Stats Work
- Basic Stats Work:
- Column Stats Desc:
- Columns: key, value
- Column Types: int, string
- Table: default.insert_into6a
-
- Stage: Stage-3
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: string)
- null sort order: z
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
- Execution mode: vectorized
- Reduce Operator Tree:
- Group By Operator
- aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
- keys: KEY._col0 (type: string)
- mode: mergepartial
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
-PREHOOK: query: INSERT INTO TABLE insert_into6a PARTITION (ds='1') SELECT * FROM src LIMIT 150
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@insert_into6a@ds=1
-POSTHOOK: query: INSERT INTO TABLE insert_into6a PARTITION (ds='1') SELECT * FROM src LIMIT 150
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@insert_into6a@ds=1
-POSTHOOK: Lineage: insert_into6a PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: insert_into6a PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: INSERT INTO TABLE insert_into6a PARTITION (ds='2') SELECT * FROM src LIMIT 100
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@insert_into6a@ds=2
-POSTHOOK: query: INSERT INTO TABLE insert_into6a PARTITION (ds='2') SELECT * FROM src LIMIT 100
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@insert_into6a@ds=2
-POSTHOOK: Lineage: insert_into6a PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: insert_into6a PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: SELECT SUM(HASH(c)) FROM (
- SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into6a
-) t
-PREHOOK: type: QUERY
-PREHOOK: Input: default@insert_into6a
-PREHOOK: Input: default@insert_into6a@ds=1
-PREHOOK: Input: default@insert_into6a@ds=2
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT SUM(HASH(c)) FROM (
- SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into6a
-) t
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@insert_into6a
-POSTHOOK: Input: default@insert_into6a@ds=1
-POSTHOOK: Input: default@insert_into6a@ds=2
-#### A masked pattern was here ####
--35226404960
-PREHOOK: query: EXPLAIN INSERT INTO TABLE insert_into6b PARTITION (ds)
- SELECT * FROM insert_into6a
-PREHOOK: type: QUERY
-PREHOOK: Input: default@insert_into6a
-PREHOOK: Input: default@insert_into6a@ds=1
-PREHOOK: Input: default@insert_into6a@ds=2
-PREHOOK: Output: default@insert_into6b
-POSTHOOK: query: EXPLAIN INSERT INTO TABLE insert_into6b PARTITION (ds)
- SELECT * FROM insert_into6a
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@insert_into6a
-POSTHOOK: Input: default@insert_into6a@ds=1
-POSTHOOK: Input: default@insert_into6a@ds=2
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5
- Stage-4
- Stage-0 depends on stages: Stage-4, Stage-3, Stage-6
- Stage-2 depends on stages: Stage-0
- Stage-3
- Stage-5
- Stage-6 depends on stages: Stage-5
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: insert_into6a
- Statistics: Num rows: 250 Data size: 69750 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: key (type: int), value (type: string), ds (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 250 Data size: 69750 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 250 Data size: 69750 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.insert_into6b
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string)
- outputColumnNames: key, value, ds
- Statistics: Num rows: 250 Data size: 69750 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
- keys: ds (type: string)
- minReductionHashAggr: 0.99
- mode: hash
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 2 Data size: 2096 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- null sort order: z
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 2 Data size: 2096 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
- Reduce Operator Tree:
- Group By Operator
- aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
- keys: KEY._col0 (type: string)
- mode: mergepartial
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 2 Data size: 2128 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 2 Data size: 2128 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 2 Data size: 2128 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-7
- Conditional Operator
-
- Stage: Stage-4
- Move Operator
- files:
- hdfs directory: true
-#### A masked pattern was here ####
-
- Stage: Stage-0
- Move Operator
- tables:
- partition:
- ds
- replace: false
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.insert_into6b
-
- Stage: Stage-2
- Stats Work
- Basic Stats Work:
- Column Stats Desc:
- Columns: key, value
- Column Types: int, string
- Table: default.insert_into6b
-
- Stage: Stage-3
- Map Reduce
- Map Operator Tree:
- TableScan
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.insert_into6b
-
- Stage: Stage-5
- Map Reduce
- Map Operator Tree:
- TableScan
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.insert_into6b
-
- Stage: Stage-6
- Move Operator
- files:
- hdfs directory: true
-#### A masked pattern was here ####
-
-PREHOOK: query: INSERT INTO TABLE insert_into6b PARTITION (ds) SELECT * FROM insert_into6a
-PREHOOK: type: QUERY
-PREHOOK: Input: default@insert_into6a
-PREHOOK: Input: default@insert_into6a@ds=1
-PREHOOK: Input: default@insert_into6a@ds=2
-PREHOOK: Output: default@insert_into6b
-POSTHOOK: query: INSERT INTO TABLE insert_into6b PARTITION (ds) SELECT * FROM insert_into6a
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@insert_into6a
-POSTHOOK: Input: default@insert_into6a@ds=1
-POSTHOOK: Input: default@insert_into6a@ds=2
-POSTHOOK: Output: default@insert_into6b@ds=1
-POSTHOOK: Output: default@insert_into6b@ds=2
-POSTHOOK: Lineage: insert_into6b PARTITION(ds=1).key SIMPLE [(insert_into6a)insert_into6a.FieldSchema(name:key, type:int, comment:null), ]
-POSTHOOK: Lineage: insert_into6b PARTITION(ds=1).value SIMPLE [(insert_into6a)insert_into6a.FieldSchema(name:value, type:string, comment:null), ]
-POSTHOOK: Lineage: insert_into6b PARTITION(ds=2).key SIMPLE [(insert_into6a)insert_into6a.FieldSchema(name:key, type:int, comment:null), ]
-POSTHOOK: Lineage: insert_into6b PARTITION(ds=2).value SIMPLE [(insert_into6a)insert_into6a.FieldSchema(name:value, type:string, comment:null), ]
-PREHOOK: query: SELECT SUM(HASH(c)) FROM (
- SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into6b
-) t
-PREHOOK: type: QUERY
-PREHOOK: Input: default@insert_into6b
-PREHOOK: Input: default@insert_into6b@ds=1
-PREHOOK: Input: default@insert_into6b@ds=2
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT SUM(HASH(c)) FROM (
- SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into6b
-) t
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@insert_into6b
-POSTHOOK: Input: default@insert_into6b@ds=1
-POSTHOOK: Input: default@insert_into6b@ds=2
-#### A masked pattern was here ####
--35226404960
-PREHOOK: query: SHOW PARTITIONS insert_into6b
-PREHOOK: type: SHOWPARTITIONS
-PREHOOK: Input: default@insert_into6b
-POSTHOOK: query: SHOW PARTITIONS insert_into6b
-POSTHOOK: type: SHOWPARTITIONS
-POSTHOOK: Input: default@insert_into6b
-ds=1
-ds=2
-PREHOOK: query: DROP TABLE insert_into6a
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@insert_into6a
-PREHOOK: Output: default@insert_into6a
-POSTHOOK: query: DROP TABLE insert_into6a
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@insert_into6a
-POSTHOOK: Output: default@insert_into6a
-PREHOOK: query: DROP TABLE insert_into6b
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@insert_into6b
-PREHOOK: Output: default@insert_into6b
-POSTHOOK: query: DROP TABLE insert_into6b
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@insert_into6b
-POSTHOOK: Output: default@insert_into6b
diff --git a/ql/src/test/results/clientpositive/autoColumnStats_6.q.out b/ql/src/test/results/clientpositive/llap/autoColumnStats_6.q.out
similarity index 71%
rename from ql/src/test/results/clientpositive/autoColumnStats_6.q.out
rename to ql/src/test/results/clientpositive/llap/autoColumnStats_6.q.out
index ff708cb..b674164 100644
--- a/ql/src/test/results/clientpositive/autoColumnStats_6.q.out
+++ b/ql/src/test/results/clientpositive/llap/autoColumnStats_6.q.out
@@ -35,83 +35,87 @@ STAGE DEPENDENCIES:
STAGE PLANS:
Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: UDFToInteger(key) (type: int), value (type: string), CAST( (hash(key) pmod 10) AS STRING) (type: string), CAST( (hash(value) pmod 10) AS STRING) (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 500 Data size: 231500 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string), '1' (type: string), _col2 (type: string), _col3 (type: string)
- outputColumnNames: key, value, one, two, three
- Statistics: Num rows: 500 Data size: 274000 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
- keys: one (type: string), two (type: string), three (type: string)
- minReductionHashAggr: 0.99
- mode: hash
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+ Reducer 3 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: UDFToInteger(key) (type: int), value (type: string), CAST( (hash(key) pmod 10) AS STRING) (type: string), CAST( (hash(value) pmod 10) AS STRING) (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 500 Data size: 231500 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), '1' (type: string), _col2 (type: string), _col3 (type: string)
+ outputColumnNames: key, value, one, two, three
+ Statistics: Num rows: 500 Data size: 274000 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ keys: one (type: string), two (type: string), three (type: string)
+ minReductionHashAggr: 0.0
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 500 Data size: 658500 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
+ null sort order: zzz
+ sort order: +++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string)
+ Statistics: Num rows: 500 Data size: 658500 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col3 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col4 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reduce Output Operator
+ key expressions: _col2 (type: string), _col3 (type: string)
+ null sort order: aa
+ sort order: ++
+ Map-reduce partition columns: _col2 (type: string), _col3 (type: string)
+ Statistics: Num rows: 500 Data size: 231500 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: int), _col1 (type: string)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 500 Data size: 666500 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col3 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col4 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string), _col1 (type: string), _col2 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 250 Data size: 329250 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
- null sort order: zzz
- sort order: +++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string)
- Statistics: Num rows: 250 Data size: 329250 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col3 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col4 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
- Reduce Operator Tree:
- Group By Operator
- aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
- keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string)
- mode: mergepartial
- outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 250 Data size: 333250 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col3 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col4 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string), _col1 (type: string), _col2 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 250 Data size: 333250 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 250 Data size: 333250 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Statistics: Num rows: 500 Data size: 666500 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 500 Data size: 666500 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Reducer 3
+ Execution mode: vectorized, llap
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ File Output Operator
+ compressed: false
+ Dp Sort State: PARTITION_SORTED
+ Statistics: Num rows: 500 Data size: 231500 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
+ serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
+ name: default.orcfile_merge2a
Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col2 (type: string), _col3 (type: string)
- null sort order: aa
- sort order: ++
- Map-reduce partition columns: _col2 (type: string), _col3 (type: string)
- Statistics: Num rows: 500 Data size: 231500 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: int), _col1 (type: string)
- Execution mode: vectorized
- Reduce Operator Tree:
- Select Operator
- expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- File Output Operator
- compressed: false
- Dp Sort State: PARTITION_SORTED
- Statistics: Num rows: 500 Data size: 231500 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
- output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
- serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
- name: default.orcfile_merge2a
+ Dependency Collection
Stage: Stage-0
Move Operator
@@ -209,7 +213,7 @@ POSTHOOK: Lineage: orcfile_merge2a PARTITION(one=1,two=9,three=1).value SIMPLE [
POSTHOOK: Lineage: orcfile_merge2a PARTITION(one=1,two=9,three=7).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: orcfile_merge2a PARTITION(one=1,two=9,three=7).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
Found 1 items
-#### A masked pattern was here ####
+-rw-rw-rw- 3 ### USER ### ### GROUP ### 351 ### HDFS DATE ### hdfs://### HDFS PATH ###
PREHOOK: query: SELECT SUM(HASH(c)) FROM (
SELECT TRANSFORM(*) USING 'tr \t _' AS (c)
FROM orcfile_merge2a
@@ -236,7 +240,7 @@ PREHOOK: Input: default@orcfile_merge2a@one=1/two=8/three=0
PREHOOK: Input: default@orcfile_merge2a@one=1/two=8/three=6
PREHOOK: Input: default@orcfile_merge2a@one=1/two=9/three=1
PREHOOK: Input: default@orcfile_merge2a@one=1/two=9/three=7
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: SELECT SUM(HASH(c)) FROM (
SELECT TRANSFORM(*) USING 'tr \t _' AS (c)
FROM orcfile_merge2a
@@ -263,7 +267,7 @@ POSTHOOK: Input: default@orcfile_merge2a@one=1/two=8/three=0
POSTHOOK: Input: default@orcfile_merge2a@one=1/two=8/three=6
POSTHOOK: Input: default@orcfile_merge2a@one=1/two=9/three=1
POSTHOOK: Input: default@orcfile_merge2a@one=1/two=9/three=7
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
-4209012844
PREHOOK: query: SELECT SUM(HASH(c)) FROM (
SELECT TRANSFORM(key, value, '1', PMOD(HASH(key), 10),
@@ -272,7 +276,7 @@ PREHOOK: query: SELECT SUM(HASH(c)) FROM (
) t
PREHOOK: type: QUERY
PREHOOK: Input: default@src
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: SELECT SUM(HASH(c)) FROM (
SELECT TRANSFORM(key, value, '1', PMOD(HASH(key), 10),
PMOD(HASH(value), 10)) USING 'tr \t _' AS (c)
@@ -280,7 +284,7 @@ POSTHOOK: query: SELECT SUM(HASH(c)) FROM (
) t
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
-4209012844
PREHOOK: query: DROP TABLE orcfile_merge2a
PREHOOK: type: DROPTABLE
diff --git a/ql/src/test/results/clientpositive/autogen_colalias.q.out b/ql/src/test/results/clientpositive/llap/autogen_colalias.q.out
similarity index 100%
rename from ql/src/test/results/clientpositive/autogen_colalias.q.out
rename to ql/src/test/results/clientpositive/llap/autogen_colalias.q.out
diff --git a/ql/src/test/results/clientpositive/binary_output_format.q.out b/ql/src/test/results/clientpositive/llap/binary_output_format.q.out
similarity index 50%
rename from ql/src/test/results/clientpositive/binary_output_format.q.out
rename to ql/src/test/results/clientpositive/llap/binary_output_format.q.out
index 760d863..0b7a75e 100644
--- a/ql/src/test/results/clientpositive/binary_output_format.q.out
+++ b/ql/src/test/results/clientpositive/llap/binary_output_format.q.out
@@ -54,170 +54,171 @@ POSTHOOK: Input: default@src
POSTHOOK: Output: default@dest1_n109
STAGE DEPENDENCIES:
Stage-1 is a root stage
- Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5
- Stage-4
- Stage-0 depends on stages: Stage-4, Stage-3, Stage-6
- Stage-2 depends on stages: Stage-0
- Stage-3
- Stage-5
- Stage-6 depends on stages: Stage-5
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
STAGE PLANS:
Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- GatherStats: false
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- Transform Operator
- command: cat
- output info:
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ GatherStats: false
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Transform Operator
+ command: cat
+ output info:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucketing_version -1
+ columns _col0
+ columns.types string
+ field.delim 9
+ serialization.format 9
+ serialization.last.column.takes.rest true
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ bucketingVersion: 2
+ compressed: false
+ GlobalTableId: 1
+ directory: hdfs://### HDFS PATH ###
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Stats Publishing Key Prefix: hdfs://### HDFS PATH ###
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveBinaryOutputFormat
+ properties:
+ bucketing_version 2
+ column.name.delimiter ,
+ columns mydata
+ columns.comments
+ columns.types string
+#### A masked pattern was here ####
+ location hdfs://### HDFS PATH ###
+ name default.dest1_n109
+ serialization.format 1
+ serialization.last.column.takes.rest true
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest1_n109
+ TotalFiles: 1
+ GatherStats: true
+ MultiFileSpray: false
+ Select Operator
+ expressions: _col0 (type: string)
+ outputColumnNames: mydata
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(mydata, 'hll')
+ minReductionHashAggr: 0.99
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ bucketingVersion: 2
+ null sort order:
+ numBuckets: -1
+ sort order:
+ Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE
+ tag: -1
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ auto parallelism: false
+ Path -> Alias:
+ hdfs://### HDFS PATH ### [src]
+ Path -> Partition:
+ hdfs://### HDFS PATH ###
+ Partition
+ base file name: src
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ bucketing_version 2
+ column.name.delimiter ,
+ columns key,value
+ columns.types string:string
+#### A masked pattern was here ####
+ location hdfs://### HDFS PATH ###
+ name default.src
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- bucketing_version -1
- columns _col0
- columns.types string
- field.delim 9
- serialization.format 9
- serialization.last.column.takes.rest true
+ bucketing_version 2
+ column.name.delimiter ,
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ location hdfs://### HDFS PATH ###
+ name default.src
+ serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ name: default.src
+ name: default.src
+ Truncated Path -> Alias:
+ /src [src]
+ Reducer 2
+ Execution mode: llap
+ Needs Tagging: false
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
bucketingVersion: 2
compressed: false
- GlobalTableId: 1
-#### A masked pattern was here ####
+ GlobalTableId: 0
+ directory: hdfs://### HDFS PATH ###
NumFilesPerFileSink: 1
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
-#### A masked pattern was here ####
+ Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE
+ Stats Publishing Key Prefix: hdfs://### HDFS PATH ###
table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveBinaryOutputFormat
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
properties:
- bucketing_version 2
- column.name.delimiter ,
- columns mydata
- columns.comments
- columns.types string
-#### A masked pattern was here ####
- name default.dest1_n109
+ bucketing_version -1
+ columns _col0
+ columns.types struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>
+ escape.delim \
+ hive.serialization.extend.additional.nesting.levels true
+ serialization.escape.crlf true
serialization.format 1
- serialization.last.column.takes.rest true
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.dest1_n109
TotalFiles: 1
- GatherStats: true
+ GatherStats: false
MultiFileSpray: false
- Select Operator
- expressions: _col0 (type: string)
- outputColumnNames: mydata
- Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: compute_stats(mydata, 'hll')
- minReductionHashAggr: 0.99
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- bucketingVersion: 2
- null sort order:
- numBuckets: -1
- sort order:
- Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE
- tag: -1
- value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
- auto parallelism: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: src
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- bucketing_version 2
- column.name.delimiter ,
- columns key,value
- columns.types string:string
-#### A masked pattern was here ####
- name default.src
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucketing_version 2
- column.name.delimiter ,
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.src
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src
- name: default.src
- Truncated Path -> Alias:
- /src [src]
- Needs Tagging: false
- Reduce Operator Tree:
- Group By Operator
- aggregations: compute_stats(VALUE._col0)
- mode: mergepartial
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- bucketingVersion: 2
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- bucketing_version -1
- columns _col0
- columns.types struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>
- escape.delim \
- hive.serialization.extend.additional.nesting.levels true
- serialization.escape.crlf 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
- Stage: Stage-7
- Conditional Operator
-
- Stage: Stage-4
- Move Operator
- files:
- hdfs directory: true
-#### A masked pattern was here ####
+ Stage: Stage-2
+ Dependency Collection
Stage: Stage-0
Move Operator
tables:
replace: true
-#### A masked pattern was here ####
+ source: hdfs://### HDFS PATH ###
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveBinaryOutputFormat
@@ -228,6 +229,7 @@ STAGE PLANS:
columns.comments
columns.types string
#### A masked pattern was here ####
+ location hdfs://### HDFS PATH ###
name default.dest1_n109
serialization.format 1
serialization.last.column.takes.rest true
@@ -235,162 +237,16 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest1_n109
- Stage: Stage-2
+ Stage: Stage-3
Stats Work
Basic Stats Work:
-#### A masked pattern was here ####
+ Stats Aggregation Key Prefix: hdfs://### HDFS PATH ###
Column Stats Desc:
Columns: mydata
Column Types: string
Table: default.dest1_n109
Is Table Level Stats: true
- Stage: Stage-3
- Map Reduce
- Map Operator Tree:
- TableScan
- GatherStats: false
- File Output Operator
- bucketingVersion: 2
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveBinaryOutputFormat
- properties:
- bucketing_version 2
- column.name.delimiter ,
- columns mydata
- columns.comments
- columns.types string
-#### A masked pattern was here ####
- name default.dest1_n109
- serialization.format 1
- serialization.last.column.takes.rest true
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.dest1_n109
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: -ext-10002
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveBinaryOutputFormat
- properties:
- bucketing_version 2
- column.name.delimiter ,
- columns mydata
- columns.comments
- columns.types string
-#### A masked pattern was here ####
- name default.dest1_n109
- serialization.format 1
- serialization.last.column.takes.rest true
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveBinaryOutputFormat
- properties:
- bucketing_version 2
- column.name.delimiter ,
- columns mydata
- columns.comments
- columns.types string
-#### A masked pattern was here ####
- name default.dest1_n109
- serialization.format 1
- serialization.last.column.takes.rest true
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.dest1_n109
- name: default.dest1_n109
- Truncated Path -> Alias:
-#### A masked pattern was here ####
-
- Stage: Stage-5
- Map Reduce
- Map Operator Tree:
- TableScan
- GatherStats: false
- File Output Operator
- bucketingVersion: 2
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveBinaryOutputFormat
- properties:
- bucketing_version 2
- column.name.delimiter ,
- columns mydata
- columns.comments
- columns.types string
-#### A masked pattern was here ####
- name default.dest1_n109
- serialization.format 1
- serialization.last.column.takes.rest true
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.dest1_n109
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: -ext-10002
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveBinaryOutputFormat
- properties:
- bucketing_version 2
- column.name.delimiter ,
- columns mydata
- columns.comments
- columns.types string
-#### A masked pattern was here ####
- name default.dest1_n109
- serialization.format 1
- serialization.last.column.takes.rest true
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveBinaryOutputFormat
- properties:
- bucketing_version 2
- column.name.delimiter ,
- columns mydata
- columns.comments
- columns.types string
-#### A masked pattern was here ####
- name default.dest1_n109
- serialization.format 1
- serialization.last.column.takes.rest true
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.dest1_n109
- name: default.dest1_n109
- Truncated Path -> Alias:
-#### A masked pattern was here ####
-
- Stage: Stage-6
- Move Operator
- files:
- hdfs directory: true
-#### A masked pattern was here ####
-
PREHOOK: query: INSERT OVERWRITE TABLE dest1_n109
SELECT TRANSFORM(*)
USING 'cat'
@@ -423,11 +279,11 @@ POSTHOOK: Lineage: dest1_n109.mydata SCRIPT [(src)src.FieldSchema(name:key, type
PREHOOK: query: SELECT * FROM dest1_n109
PREHOOK: type: QUERY
PREHOOK: Input: default@dest1_n109
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: SELECT * FROM dest1_n109
POSTHOOK: type: QUERY
POSTHOOK: Input: default@dest1_n109
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
238 val_238
86 val_86
311 val_311
diff --git a/ql/src/test/results/clientpositive/llap/create_genericudaf.q.out b/ql/src/test/results/clientpositive/llap/create_genericudaf.q.out
new file mode 100644
index 0000000..a87f04a
--- /dev/null
+++ b/ql/src/test/results/clientpositive/llap/create_genericudaf.q.out
@@ -0,0 +1,114 @@
+PREHOOK: query: EXPLAIN
+CREATE TEMPORARY FUNCTION test_avg AS 'org.apache.hadoop.hive.ql.udf.generic.GenericUDAFAverage'
+PREHOOK: type: CREATEFUNCTION
+PREHOOK: Output: test_avg
+POSTHOOK: query: EXPLAIN
+CREATE TEMPORARY FUNCTION test_avg AS 'org.apache.hadoop.hive.ql.udf.generic.GenericUDAFAverage'
+POSTHOOK: type: CREATEFUNCTION
+POSTHOOK: Output: test_avg
+STAGE DEPENDENCIES:
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-0
+ Create Function
+ class: org.apache.hadoop.hive.ql.udf.generic.GenericUDAFAverage
+ name: test_avg
+ temporary: true
+
+PREHOOK: query: CREATE TEMPORARY FUNCTION test_avg AS 'org.apache.hadoop.hive.ql.udf.generic.GenericUDAFAverage'
+PREHOOK: type: CREATEFUNCTION
+PREHOOK: Output: test_avg
+POSTHOOK: query: CREATE TEMPORARY FUNCTION test_avg AS 'org.apache.hadoop.hive.ql.udf.generic.GenericUDAFAverage'
+POSTHOOK: type: CREATEFUNCTION
+POSTHOOK: Output: test_avg
+PREHOOK: query: EXPLAIN
+SELECT
+ test_avg(1),
+ test_avg(substr(value,5))
+FROM src
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: hdfs://### HDFS PATH ###
+POSTHOOK: query: EXPLAIN
+SELECT
+ test_avg(1),
+ test_avg(substr(value,5))
+FROM src
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: hdfs://### HDFS PATH ###
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: substr(value, 5) (type: string)
+ outputColumnNames: _col1
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: test_avg(1), test_avg(_col1)
+ minReductionHashAggr: 0.99
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 332 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ null sort order:
+ sort order:
+ Statistics: Num rows: 1 Data size: 332 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: struct<count:bigint,sum:double,input:int>), _col1 (type: struct<count:bigint,sum:double,input:string>)
+ Reducer 2
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: test_avg(VALUE._col0), test_avg(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: SELECT
+ test_avg(1),
+ test_avg(substr(value,5))
+FROM src
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: hdfs://### HDFS PATH ###
+POSTHOOK: query: SELECT
+ test_avg(1),
+ test_avg(substr(value,5))
+FROM src
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: hdfs://### HDFS PATH ###
+1.0 260.182
+PREHOOK: query: DROP TEMPORARY FUNCTIOn test_avg
+PREHOOK: type: DROPFUNCTION
+PREHOOK: Output: test_avg
+POSTHOOK: query: DROP TEMPORARY FUNCTIOn test_avg
+POSTHOOK: type: DROPFUNCTION
+POSTHOOK: Output: test_avg
diff --git a/ql/src/test/results/clientpositive/create_udaf.q.out b/ql/src/test/results/clientpositive/llap/create_udaf.q.out
similarity index 86%
rename from ql/src/test/results/clientpositive/create_udaf.q.out
rename to ql/src/test/results/clientpositive/llap/create_udaf.q.out
index 7bfce12..52e5fa6 100644
--- a/ql/src/test/results/clientpositive/create_udaf.q.out
+++ b/ql/src/test/results/clientpositive/llap/create_udaf.q.out
@@ -42,56 +42,56 @@ POSTHOOK: Lineage: dest1_n34.col EXPRESSION [(src)src.FieldSchema(name:value, ty
PREHOOK: query: SELECT dest1_n34.* FROM dest1_n34
PREHOOK: type: QUERY
PREHOOK: Input: default@dest1_n34
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: SELECT dest1_n34.* FROM dest1_n34
POSTHOOK: type: QUERY
POSTHOOK: Input: default@dest1_n34
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
7
PREHOOK: query: SELECT test_max(CAST(length(src.value) AS SMALLINT)) FROM src
PREHOOK: type: QUERY
PREHOOK: Input: default@src
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: SELECT test_max(CAST(length(src.value) AS SMALLINT)) FROM src
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
7
PREHOOK: query: SELECT test_max(CAST(length(src.value) AS BIGINT)) FROM src
PREHOOK: type: QUERY
PREHOOK: Input: default@src
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: SELECT test_max(CAST(length(src.value) AS BIGINT)) FROM src
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
7
PREHOOK: query: SELECT test_max(CAST(length(src.value) AS DOUBLE)) FROM src
PREHOOK: type: QUERY
PREHOOK: Input: default@src
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: SELECT test_max(CAST(length(src.value) AS DOUBLE)) FROM src
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
7.0
PREHOOK: query: SELECT test_max(CAST(length(src.value) AS FLOAT)) FROM src
PREHOOK: type: QUERY
PREHOOK: Input: default@src
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: SELECT test_max(CAST(length(src.value) AS FLOAT)) FROM src
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
7.0
PREHOOK: query: SELECT test_max(substr(src.value,5)) FROM src
PREHOOK: type: QUERY
PREHOOK: Input: default@src
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: SELECT test_max(substr(src.value,5)) FROM src
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
98
PREHOOK: query: DROP TEMPORARY FUNCTION test_max
PREHOOK: type: DROPFUNCTION
diff --git a/ql/src/test/results/clientpositive/create_view.q.out b/ql/src/test/results/clientpositive/llap/create_view.q.out
similarity index 94%
rename from ql/src/test/results/clientpositive/create_view.q.out
rename to ql/src/test/results/clientpositive/llap/create_view.q.out
index 9a251fc..52b77c7 100644
--- a/ql/src/test/results/clientpositive/create_view.q.out
+++ b/ql/src/test/results/clientpositive/llap/create_view.q.out
@@ -77,11 +77,11 @@ POSTHOOK: type: DROPFUNCTION
PREHOOK: query: SELECT * FROM src WHERE key=86
PREHOOK: type: QUERY
PREHOOK: Input: default@src
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: SELECT * FROM src WHERE key=86
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
86 val_86
PREHOOK: query: CREATE VIEW view1 AS SELECT value FROM src WHERE key=86
PREHOOK: type: CREATEVIEW
@@ -125,35 +125,35 @@ PREHOOK: query: SELECT * from view1
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Input: default@view1
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: SELECT * from view1
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Input: default@view1
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
val_86
PREHOOK: query: SELECT * from view2 where key=18
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Input: default@view2
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: SELECT * from view2 where key=18
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Input: default@view2
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
18 val_18
18 val_18
PREHOOK: query: SELECT * from view3
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Input: default@view3
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: SELECT * from view3
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Input: default@view3
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
VAL_86
PREHOOK: query: EXPLAIN
CREATE VIEW view0(valoo) AS SELECT upper(value) FROM src WHERE key=86
@@ -183,48 +183,32 @@ SELECT * from view2 where key=18
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Input: default@view2
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: EXPLAIN
SELECT * from view2 where key=18
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Input: default@view2
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
+ Stage-0 is a root stage
STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: src
- filterExpr: (UDFToDouble(key) = 18.0D) (type: boolean)
- properties:
- insideView TRUE
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator
- predicate: (UDFToDouble(key) = 18.0D) (type: boolean)
- Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Execution mode: vectorized
-
Stage: Stage-0
Fetch Operator
limit: -1
Processor Tree:
- ListSink
+ TableScan
+ alias: src
+ filterExpr: (UDFToDouble(key) = 18.0D) (type: boolean)
+ properties:
+ insideView TRUE
+ Filter Operator
+ predicate: (UDFToDouble(key) = 18.0D) (type: boolean)
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ ListSink
PREHOOK: query: SHOW TABLES 'view%'
PREHOOK: type: SHOWTABLES
@@ -481,11 +465,11 @@ POSTHOOK: Lineage: table1_n4.key EXPRESSION [(src)src.FieldSchema(name:key, type
PREHOOK: query: SELECT * FROM table1_n4
PREHOOK: type: QUERY
PREHOOK: Input: default@table1_n4
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: SELECT * FROM table1_n4
POSTHOOK: type: QUERY
POSTHOOK: Input: default@table1_n4
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
86
PREHOOK: query: CREATE VIEW view4 AS SELECT * FROM table1_n4
PREHOOK: type: CREATEVIEW
@@ -502,12 +486,12 @@ PREHOOK: query: SELECT * FROM view4
PREHOOK: type: QUERY
PREHOOK: Input: default@table1_n4
PREHOOK: Input: default@view4
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: SELECT * FROM view4
POSTHOOK: type: QUERY
POSTHOOK: Input: default@table1_n4
POSTHOOK: Input: default@view4
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
86
PREHOOK: query: DESCRIBE view4
PREHOOK: type: DESCTABLE
@@ -527,22 +511,22 @@ POSTHOOK: Output: default@table1_n4
PREHOOK: query: SELECT * FROM table1_n4
PREHOOK: type: QUERY
PREHOOK: Input: default@table1_n4
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: SELECT * FROM table1_n4
POSTHOOK: type: QUERY
POSTHOOK: Input: default@table1_n4
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
86 NULL
PREHOOK: query: SELECT * FROM view4
PREHOOK: type: QUERY
PREHOOK: Input: default@table1_n4
PREHOOK: Input: default@view4
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: SELECT * FROM view4
POSTHOOK: type: QUERY
POSTHOOK: Input: default@table1_n4
POSTHOOK: Input: default@view4
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
86
PREHOOK: query: DESCRIBE table1_n4
PREHOOK: type: DESCTABLE
@@ -575,19 +559,19 @@ POSTHOOK: Output: database:default
POSTHOOK: Output: default@view5
POSTHOOK: Lineage: view5.key1 SIMPLE [(table1_n4)table1_n4.FieldSchema(name:key, type:int, comment:null), ]
POSTHOOK: Lineage: view5.key2 SIMPLE [(table1_n4)table1_n4.FieldSchema(name:key, type:int, comment:null), ]
-Warning: Shuffle Join JOIN[6][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
+Warning: Shuffle Join MERGEJOIN[9][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: SELECT * FROM view5
PREHOOK: type: QUERY
PREHOOK: Input: default@table1_n4
PREHOOK: Input: default@view4
PREHOOK: Input: default@view5
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: SELECT * FROM view5
POSTHOOK: type: QUERY
POSTHOOK: Input: default@table1_n4
POSTHOOK: Input: default@view4
POSTHOOK: Input: default@view5
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
86 86
PREHOOK: query: DESCRIBE view5
PREHOOK: type: DESCTABLE
@@ -641,12 +625,12 @@ PREHOOK: query: SELECT * FROM view7
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Input: default@view7
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: SELECT * FROM view7
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Input: default@view7
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
82 val_82
83 val_83
83 val_83
@@ -661,12 +645,12 @@ PREHOOK: query: SELECT * FROM view7 ORDER BY key DESC, value
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Input: default@view7
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: SELECT * FROM view7 ORDER BY key DESC, value
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Input: default@view7
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
90 val_90
90 val_90
87 val_87
@@ -681,12 +665,12 @@ PREHOOK: query: SELECT * FROM view7 LIMIT 5
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Input: default@view7
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: SELECT * FROM view7 LIMIT 5
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Input: default@view7
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
82 val_82
83 val_83
83 val_83
@@ -696,12 +680,12 @@ PREHOOK: query: SELECT * FROM view7 LIMIT 20
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Input: default@view7
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: SELECT * FROM view7 LIMIT 20
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Input: default@view7
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
82 val_82
83 val_83
83 val_83
@@ -780,12 +764,12 @@ PREHOOK: query: SELECT * FROM view8
PREHOOK: type: QUERY
PREHOOK: Input: default@table1_n4
PREHOOK: Input: default@view8
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: SELECT * FROM view8
POSTHOOK: type: QUERY
POSTHOOK: Input: default@table1_n4
POSTHOOK: Input: default@view8
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
bbc
PREHOOK: query: CREATE TEMPORARY FUNCTION test_max AS
'org.apache.hadoop.hive.ql.udf.UDAFTestMax'
@@ -855,12 +839,12 @@ PREHOOK: query: SELECT * FROM view9
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Input: default@view9
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: SELECT * FROM view9
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Input: default@view9
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
7
PREHOOK: query: DROP VIEW view9
PREHOOK: type: DROPVIEW
@@ -930,12 +914,12 @@ PREHOOK: query: SELECT * FROM view9
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Input: default@view9
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: SELECT * FROM view9
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Input: default@view9
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
7
PREHOOK: query: CREATE VIEW view10 AS
SELECT slurp.* FROM (SELECT * FROM src WHERE key=86) slurp
@@ -996,12 +980,12 @@ PREHOOK: query: SELECT * FROM view10
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Input: default@view10
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: SELECT * FROM view10
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Input: default@view10
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
86 val_86
PREHOOK: query: CREATE TEMPORARY FUNCTION test_explode AS
'org.apache.hadoop.hive.ql.udf.generic.GenericUDTFExplode'
@@ -1071,12 +1055,12 @@ PREHOOK: query: SELECT * FROM view11
PREHOOK: type: QUERY
PREHOOK: Input: default@table1_n4
PREHOOK: Input: default@view11
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: SELECT * FROM view11
POSTHOOK: type: QUERY
POSTHOOK: Input: default@table1_n4
POSTHOOK: Input: default@view11
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
1
2
3
@@ -1143,26 +1127,26 @@ ORDER BY key ASC, myCol ASC LIMIT 1
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Input: default@view12
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: SELECT * FROM view12
ORDER BY key ASC, myCol ASC LIMIT 1
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Input: default@view12
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
0 val_0 1
PREHOOK: query: SELECT * FROM view2 LATERAL VIEW explode(array(1,2,3)) myTable AS myCol
ORDER BY key ASC, myCol ASC LIMIT 1
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Input: default@view2
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: SELECT * FROM view2 LATERAL VIEW explode(array(1,2,3)) myTable AS myCol
ORDER BY key ASC, myCol ASC LIMIT 1
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Input: default@view2
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
0 val_0 1
PREHOOK: query: CREATE VIEW view13 AS
SELECT s.key
@@ -1225,13 +1209,13 @@ ORDER BY key LIMIT 12
PREHOOK: type: QUERY
PREHOOK: Input: default@srcbucket
PREHOOK: Input: default@view13
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: SELECT * FROM view13
ORDER BY key LIMIT 12
POSTHOOK: type: QUERY
POSTHOOK: Input: default@srcbucket
POSTHOOK: Input: default@view13
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
1
8
8
@@ -1346,13 +1330,13 @@ ORDER BY k1
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Input: default@view14
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: SELECT * FROM view14
ORDER BY k1
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Input: default@view14
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
0 val_0 0 val_0
0 val_0 0 val_0
0 val_0 0 val_0
@@ -1445,14 +1429,14 @@ LIMIT 10
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Input: default@view15
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: SELECT * FROM view15
ORDER BY value_count DESC, key
LIMIT 10
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Input: default@view15
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
230 5
348 5
401 5
@@ -1525,14 +1509,14 @@ LIMIT 10
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Input: default@view16
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: SELECT * FROM view16
ORDER BY value
LIMIT 10
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Input: default@view16
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
val_0
val_10
val_100
@@ -1589,12 +1573,12 @@ PREHOOK: query: select * from view17
PREHOOK: type: QUERY
PREHOOK: Input: _dummy_database@_dummy_table
PREHOOK: Input: default@view17
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: select * from view17
POSTHOOK: type: QUERY
POSTHOOK: Input: _dummy_database@_dummy_table
POSTHOOK: Input: default@view17
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
1
PREHOOK: query: create view view18 as select v+1 from (select 1 as v) t
PREHOOK: type: CREATEVIEW
@@ -1611,12 +1595,12 @@ PREHOOK: query: select * from view18
PREHOOK: type: QUERY
PREHOOK: Input: _dummy_database@_dummy_table
PREHOOK: Input: default@view18
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: select * from view18
POSTHOOK: type: QUERY
POSTHOOK: Input: _dummy_database@_dummy_table
POSTHOOK: Input: default@view18
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
2
PREHOOK: query: create view if not exists view18 as select "should be ignored"
PREHOOK: type: CREATEVIEW
diff --git a/ql/src/test/results/clientpositive/gen_udf_example_add10.q.out b/ql/src/test/results/clientpositive/llap/gen_udf_example_add10.q.out
similarity index 52%
rename from ql/src/test/results/clientpositive/gen_udf_example_add10.q.out
rename to ql/src/test/results/clientpositive/llap/gen_udf_example_add10.q.out
index bfe3139..cb7ea6d 100644
--- a/ql/src/test/results/clientpositive/gen_udf_example_add10.q.out
+++ b/ql/src/test/results/clientpositive/llap/gen_udf_example_add10.q.out
@@ -23,48 +23,62 @@ POSTHOOK: Output: default@t1_n102
PREHOOK: query: explain select example_add10(x) as a,example_add10(y) as b from t1_n102 order by a desc,b limit 10
PREHOOK: type: QUERY
PREHOOK: Input: default@t1_n102
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: explain select example_add10(x) as a,example_add10(y) as b from t1_n102 order by a desc,b limit 10
POSTHOOK: type: QUERY
POSTHOOK: Input: default@t1_n102
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
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: t1_n102
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: add10(x) (type: int), add10(y) (type: double)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int), _col1 (type: double)
- null sort order: zz
- sort order: -+
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: t1_n102
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Top N Key Operator
+ sort order: -+
+ keys: add10(x) (type: int), add10(y) (type: double)
+ null sort order: zz
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ top n: 10
+ Select Operator
+ expressions: add10(x) (type: int), add10(y) (type: double)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int), _col1 (type: double)
+ null sort order: zz
+ sort order: -+
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
+ Execution mode: vectorized
+ Reducer 2
+ Execution mode: vectorized, llap
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: double)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
- TopN Hash Memory Usage: 0.1
- Execution mode: vectorized
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: double)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
- Limit
- Number of rows: 10
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Limit
+ Number of rows: 10
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
Fetch Operator
@@ -75,11 +89,11 @@ STAGE PLANS:
PREHOOK: query: select example_add10(x) as a,example_add10(y) as b from t1_n102 order by a desc,b limit 10
PREHOOK: type: QUERY
PREHOOK: Input: default@t1_n102
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: select example_add10(x) as a,example_add10(y) as b from t1_n102 order by a desc,b limit 10
POSTHOOK: type: QUERY
POSTHOOK: Input: default@t1_n102
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
18 28.0
18 38.0
17 27.0
diff --git a/ql/src/test/results/clientpositive/groupby_bigdata.q.out b/ql/src/test/results/clientpositive/llap/groupby_bigdata.q.out
similarity index 82%
rename from ql/src/test/results/clientpositive/groupby_bigdata.q.out
rename to ql/src/test/results/clientpositive/llap/groupby_bigdata.q.out
index 90ccc8c..9a7ca2f 100644
--- a/ql/src/test/results/clientpositive/groupby_bigdata.q.out
+++ b/ql/src/test/results/clientpositive/llap/groupby_bigdata.q.out
@@ -2,10 +2,10 @@ PREHOOK: query: select count(distinct subq.key) from
(FROM src MAP src.key USING 'python dumpdata_script.py' AS key WHERE src.key = 10) subq
PREHOOK: type: QUERY
PREHOOK: Input: default@src
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: select count(distinct subq.key) from
(FROM src MAP src.key USING 'python dumpdata_script.py' AS key WHERE src.key = 10) subq
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
1000022
diff --git a/ql/src/test/results/clientpositive/llap/input14.q.out b/ql/src/test/results/clientpositive/llap/input14.q.out
new file mode 100644
index 0000000..f3e5526
--- /dev/null
+++ b/ql/src/test/results/clientpositive/llap/input14.q.out
@@ -0,0 +1,252 @@
+PREHOOK: query: CREATE TABLE dest1_n42(key INT, value STRING) STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@dest1_n42
+POSTHOOK: query: CREATE TABLE dest1_n42(key INT, value STRING) STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@dest1_n42
+PREHOOK: query: EXPLAIN
+FROM (
+ FROM src
+ SELECT TRANSFORM(src.key, src.value)
+ USING 'cat' AS (tkey, tvalue)
+ CLUSTER BY tkey
+) tmap
+INSERT OVERWRITE TABLE dest1_n42 SELECT tmap.tkey, tmap.tvalue WHERE tmap.tkey < 100
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@dest1_n42
+POSTHOOK: query: EXPLAIN
+FROM (
+ FROM src
+ SELECT TRANSFORM(src.key, src.value)
+ USING 'cat' AS (tkey, tvalue)
+ CLUSTER BY tkey
+) tmap
+INSERT OVERWRITE TABLE dest1_n42 SELECT tmap.tkey, tmap.tvalue WHERE tmap.tkey < 100
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@dest1_n42
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Transform Operator
+ command: cat
+ output info:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: (_col0 < 100) (type: boolean)
+ Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ null sort order: a
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: string), _col1 (type: string)
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Select Operator
+ expressions: UDFToInteger(VALUE._col0) (type: int), VALUE._col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest1_n42
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ minReductionHashAggr: 0.99
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ null sort order:
+ sort order:
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reducer 3
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-2
+ Dependency Collection
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: true
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest1_n42
+
+ Stage: Stage-3
+ Stats Work
+ Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.dest1_n42
+
+PREHOOK: query: FROM (
+ FROM src
+ SELECT TRANSFORM(src.key, src.value)
+ USING 'cat' AS (tkey, tvalue)
+ CLUSTER BY tkey
+) tmap
+INSERT OVERWRITE TABLE dest1_n42 SELECT tmap.tkey, tmap.tvalue WHERE tmap.tkey < 100
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@dest1_n42
+POSTHOOK: query: FROM (
+ FROM src
+ SELECT TRANSFORM(src.key, src.value)
+ USING 'cat' AS (tkey, tvalue)
+ CLUSTER BY tkey
+) tmap
+INSERT OVERWRITE TABLE dest1_n42 SELECT tmap.tkey, tmap.tvalue WHERE tmap.tkey < 100
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@dest1_n42
+POSTHOOK: Lineage: dest1_n42.key SCRIPT [(src)src.FieldSchema(name:key, type:string, comment:default), (src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1_n42.value SCRIPT [(src)src.FieldSchema(name:key, type:string, comment:default), (src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: SELECT dest1_n42.* FROM dest1_n42
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest1_n42
+PREHOOK: Output: hdfs://### HDFS PATH ###
+POSTHOOK: query: SELECT dest1_n42.* FROM dest1_n42
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest1_n42
+POSTHOOK: Output: hdfs://### HDFS PATH ###
+0 val_0
+0 val_0
+0 val_0
+10 val_10
+11 val_11
+12 val_12
+12 val_12
+15 val_15
+15 val_15
+17 val_17
+18 val_18
+18 val_18
+19 val_19
+2 val_2
+20 val_20
+24 val_24
+24 val_24
+26 val_26
+26 val_26
+27 val_27
+28 val_28
+30 val_30
+33 val_33
+34 val_34
+35 val_35
+35 val_35
+35 val_35
+37 val_37
+37 val_37
+4 val_4
+41 val_41
+42 val_42
+42 val_42
+43 val_43
+44 val_44
+47 val_47
+5 val_5
+5 val_5
+5 val_5
+51 val_51
+51 val_51
+53 val_53
+54 val_54
+57 val_57
+58 val_58
+58 val_58
+64 val_64
+65 val_65
+66 val_66
+67 val_67
+67 val_67
+69 val_69
+70 val_70
+70 val_70
+70 val_70
+72 val_72
+72 val_72
+74 val_74
+76 val_76
+76 val_76
+77 val_77
+78 val_78
+8 val_8
+80 val_80
+82 val_82
+83 val_83
+83 val_83
+84 val_84
+84 val_84
+85 val_85
+86 val_86
+87 val_87
+9 val_9
+90 val_90
+90 val_90
+90 val_90
+92 val_92
+95 val_95
+95 val_95
+96 val_96
+97 val_97
+97 val_97
+98 val_98
+98 val_98
diff --git a/ql/src/test/results/clientpositive/llap/input14_limit.q.out b/ql/src/test/results/clientpositive/llap/input14_limit.q.out
new file mode 100644
index 0000000..25cfd31
--- /dev/null
+++ b/ql/src/test/results/clientpositive/llap/input14_limit.q.out
@@ -0,0 +1,177 @@
+PREHOOK: query: CREATE TABLE dest1_n13(key INT, value STRING) STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@dest1_n13
+POSTHOOK: query: CREATE TABLE dest1_n13(key INT, value STRING) STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@dest1_n13
+PREHOOK: query: EXPLAIN
+FROM (
+ FROM src
+ SELECT TRANSFORM(src.key, src.value)
+ USING 'cat' AS (tkey, tvalue)
+ CLUSTER BY tkey LIMIT 20
+) tmap
+INSERT OVERWRITE TABLE dest1_n13 SELECT tmap.tkey, tmap.tvalue WHERE tmap.tkey < 100
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@dest1_n13
+POSTHOOK: query: EXPLAIN
+FROM (
+ FROM src
+ SELECT TRANSFORM(src.key, src.value)
+ USING 'cat' AS (tkey, tvalue)
+ CLUSTER BY tkey LIMIT 20
+) tmap
+INSERT OVERWRITE TABLE dest1_n13 SELECT tmap.tkey, tmap.tvalue WHERE tmap.tkey < 100
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@dest1_n13
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Transform Operator
+ command: cat
+ output info:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Top N Key Operator
+ sort order: +
+ keys: _col0 (type: string)
+ null sort order: a
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ top n: 20
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ null sort order: a
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
+ value expressions: _col0 (type: string), _col1 (type: string)
+ Reducer 2
+ Execution mode: vectorized, llap
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col0 (type: string), VALUE._col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Limit
+ Number of rows: 20
+ Statistics: Num rows: 20 Data size: 3560 Basic stats: COMPLETE Column stats: COMPLETE
+ Top N Key Operator
+ sort order: +
+ keys: _col0 (type: string)
+ null sort order: a
+ Statistics: Num rows: 20 Data size: 3560 Basic stats: COMPLETE Column stats: COMPLETE
+ top n: 20
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ null sort order: a
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 20 Data size: 3560 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
+ value expressions: _col1 (type: string)
+ Reducer 3
+ Execution mode: vectorized, llap
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 20 Data size: 3560 Basic stats: COMPLETE Column stats: COMPLETE
+ Limit
+ Number of rows: 20
+ Statistics: Num rows: 20 Data size: 3560 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: (_col0 < 100) (type: boolean)
+ Statistics: Num rows: 6 Data size: 1068 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: UDFToInteger(_col0) (type: int), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest1_n13
+
+ Stage: Stage-2
+ Dependency Collection
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: true
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest1_n13
+
+ Stage: Stage-3
+ Stats Work
+ Basic Stats Work:
+
+PREHOOK: query: FROM (
+ FROM src
+ SELECT TRANSFORM(src.key, src.value)
+ USING 'cat' AS (tkey, tvalue)
+ CLUSTER BY tkey LIMIT 20
+) tmap
+INSERT OVERWRITE TABLE dest1_n13 SELECT tmap.tkey, tmap.tvalue WHERE tmap.tkey < 100
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@dest1_n13
+POSTHOOK: query: FROM (
+ FROM src
+ SELECT TRANSFORM(src.key, src.value)
+ USING 'cat' AS (tkey, tvalue)
+ CLUSTER BY tkey LIMIT 20
+) tmap
+INSERT OVERWRITE TABLE dest1_n13 SELECT tmap.tkey, tmap.tvalue WHERE tmap.tkey < 100
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@dest1_n13
+POSTHOOK: Lineage: dest1_n13.key SCRIPT [(src)src.FieldSchema(name:key, type:string, comment:default), (src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1_n13.value SCRIPT [(src)src.FieldSchema(name:key, type:string, comment:default), (src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: SELECT dest1_n13.* FROM dest1_n13
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest1_n13
+PREHOOK: Output: hdfs://### HDFS PATH ###
+POSTHOOK: query: SELECT dest1_n13.* FROM dest1_n13
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest1_n13
+POSTHOOK: Output: hdfs://### HDFS PATH ###
+0 val_0
+0 val_0
+0 val_0
+10 val_10
+11 val_11
diff --git a/ql/src/test/results/clientpositive/llap/input17.q.out b/ql/src/test/results/clientpositive/llap/input17.q.out
new file mode 100644
index 0000000..3074039
--- /dev/null
+++ b/ql/src/test/results/clientpositive/llap/input17.q.out
@@ -0,0 +1,176 @@
+PREHOOK: query: CREATE TABLE dest1_n81(key INT, value STRING) STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@dest1_n81
+POSTHOOK: query: CREATE TABLE dest1_n81(key INT, value STRING) STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@dest1_n81
+PREHOOK: query: EXPLAIN
+FROM (
+ FROM src_thrift
+ SELECT TRANSFORM(src_thrift.aint + src_thrift.lint[0], src_thrift.lintstring[0])
+ USING 'cat' AS (tkey, tvalue)
+ CLUSTER BY tkey
+) tmap
+INSERT OVERWRITE TABLE dest1_n81 SELECT tmap.tkey, tmap.tvalue
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src_thrift
+PREHOOK: Output: default@dest1_n81
+POSTHOOK: query: EXPLAIN
+FROM (
+ FROM src_thrift
+ SELECT TRANSFORM(src_thrift.aint + src_thrift.lint[0], src_thrift.lintstring[0])
+ USING 'cat' AS (tkey, tvalue)
+ CLUSTER BY tkey
+) tmap
+INSERT OVERWRITE TABLE dest1_n81 SELECT tmap.tkey, tmap.tvalue
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src_thrift
+POSTHOOK: Output: default@dest1_n81
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src_thrift
+ Statistics: Num rows: 11 Data size: 29524 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: (aint + lint[0]) (type: int), lintstring[0] (type: struct<myint:int,mystring:string,underscore_int:int>)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 11 Data size: 29524 Basic stats: COMPLETE Column stats: NONE
+ Transform Operator
+ command: cat
+ output info:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Statistics: Num rows: 11 Data size: 29524 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ null sort order: a
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 11 Data size: 29524 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string), _col1 (type: string)
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Select Operator
+ expressions: UDFToInteger(VALUE._col0) (type: int), VALUE._col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 11 Data size: 29524 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 11 Data size: 29524 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest1_n81
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 11 Data size: 29524 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ minReductionHashAggr: 0.99
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 3548 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ null sort order:
+ sort order:
+ Statistics: Num rows: 1 Data size: 3548 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reducer 3
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 3564 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 3564 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-2
+ Dependency Collection
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: true
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest1_n81
+
+ Stage: Stage-3
+ Stats Work
+ Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.dest1_n81
+
+PREHOOK: query: FROM (
+ FROM src_thrift
+ SELECT TRANSFORM(src_thrift.aint + src_thrift.lint[0], src_thrift.lintstring[0])
+ USING 'cat' AS (tkey, tvalue)
+ CLUSTER BY tkey
+) tmap
+INSERT OVERWRITE TABLE dest1_n81 SELECT tmap.tkey, tmap.tvalue
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src_thrift
+PREHOOK: Output: default@dest1_n81
+POSTHOOK: query: FROM (
+ FROM src_thrift
+ SELECT TRANSFORM(src_thrift.aint + src_thrift.lint[0], src_thrift.lintstring[0])
+ USING 'cat' AS (tkey, tvalue)
+ CLUSTER BY tkey
+) tmap
+INSERT OVERWRITE TABLE dest1_n81 SELECT tmap.tkey, tmap.tvalue
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src_thrift
+POSTHOOK: Output: default@dest1_n81
+POSTHOOK: Lineage: dest1_n81.key SCRIPT [(src_thrift)src_thrift.FieldSchema(name:aint, type:int, comment:from deserializer), (src_thrift)src_thrift.FieldSchema(name:lint, type:array<int>, comment:from deserializer), (src_thrift)src_thrift.FieldSchema(name:lintstring, type:array<struct<myint:int,mystring:string,underscore_int:int>>, comment:from deserializer), ]
+POSTHOOK: Lineage: dest1_n81.value SCRIPT [(src_thrift)src_thrift.FieldSchema(name:aint, type:int, comment:from deserializer), (src_thrift)src_thrift.FieldSchema(name:lint, type:array<int>, comment:from deserializer), (src_thrift)src_thrift.FieldSchema(name:lintstring, type:array<struct<myint:int,mystring:string,underscore_int:int>>, comment:from deserializer), ]
+PREHOOK: query: SELECT dest1_n81.* FROM dest1_n81
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest1_n81
+PREHOOK: Output: hdfs://### HDFS PATH ###
+POSTHOOK: query: SELECT dest1_n81.* FROM dest1_n81
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest1_n81
+POSTHOOK: Output: hdfs://### HDFS PATH ###
+-1461153966 {"myint":49,"mystring":"343","underscore_int":7}
+-1952710705 {"myint":25,"mystring":"125","underscore_int":5}
+-734328905 {"myint":16,"mystring":"64","underscore_int":4}
+-751827636 {"myint":4,"mystring":"8","underscore_int":2}
+1244525196 {"myint":36,"mystring":"216","underscore_int":6}
+1638581586 {"myint":64,"mystring":"512","underscore_int":8}
+1712634731 {"myint":0,"mystring":"0","underscore_int":0}
+336964422 {"myint":81,"mystring":"729","underscore_int":9}
+465985201 {"myint":1,"mystring":"1","underscore_int":1}
+477111225 {"myint":9,"mystring":"27","underscore_int":3}
+NULL NULL
diff --git a/ql/src/test/results/clientpositive/llap/input18.q.out b/ql/src/test/results/clientpositive/llap/input18.q.out
new file mode 100644
index 0000000..4623d8b
--- /dev/null
+++ b/ql/src/test/results/clientpositive/llap/input18.q.out
@@ -0,0 +1,252 @@
+PREHOOK: query: CREATE TABLE dest1_n124(key INT, value STRING) STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@dest1_n124
+POSTHOOK: query: CREATE TABLE dest1_n124(key INT, value STRING) STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@dest1_n124
+PREHOOK: query: EXPLAIN
+FROM (
+ FROM src
+ SELECT TRANSFORM(src.key, src.value, 1+2, 3+4)
+ USING 'cat'
+ CLUSTER BY key
+) tmap
+INSERT OVERWRITE TABLE dest1_n124 SELECT tmap.key, regexp_replace(tmap.value,'\t','+') WHERE tmap.key < 100
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@dest1_n124
+POSTHOOK: query: EXPLAIN
+FROM (
+ FROM src
+ SELECT TRANSFORM(src.key, src.value, 1+2, 3+4)
+ USING 'cat'
+ CLUSTER BY key
+) tmap
+INSERT OVERWRITE TABLE dest1_n124 SELECT tmap.key, regexp_replace(tmap.value,'\t','+') WHERE tmap.key < 100
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@dest1_n124
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string), value (type: string), 3 (type: int), 7 (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE
+ Transform Operator
+ command: cat
+ output info:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: (_col0 < 100) (type: boolean)
+ Statistics: Num rows: 166 Data size: 30876 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ null sort order: a
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 166 Data size: 30876 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: string), _col1 (type: string)
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Select Operator
+ expressions: UDFToInteger(VALUE._col0) (type: int), regexp_replace(VALUE._col1, ' ', '+') (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 166 Data size: 31208 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 166 Data size: 31208 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest1_n124
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 166 Data size: 31208 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ minReductionHashAggr: 0.99
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ null sort order:
+ sort order:
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reducer 3
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-2
+ Dependency Collection
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: true
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest1_n124
+
+ Stage: Stage-3
+ Stats Work
+ Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.dest1_n124
+
+PREHOOK: query: FROM (
+ FROM src
+ SELECT TRANSFORM(src.key, src.value, 1+2, 3+4)
+ USING 'cat'
+ CLUSTER BY key
+) tmap
+INSERT OVERWRITE TABLE dest1_n124 SELECT tmap.key, regexp_replace(tmap.value,'\t','+') WHERE tmap.key < 100
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@dest1_n124
+POSTHOOK: query: FROM (
+ FROM src
+ SELECT TRANSFORM(src.key, src.value, 1+2, 3+4)
+ USING 'cat'
+ CLUSTER BY key
+) tmap
+INSERT OVERWRITE TABLE dest1_n124 SELECT tmap.key, regexp_replace(tmap.value,'\t','+') WHERE tmap.key < 100
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@dest1_n124
+POSTHOOK: Lineage: dest1_n124.key SCRIPT [(src)src.FieldSchema(name:key, type:string, comment:default), (src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1_n124.value SCRIPT [(src)src.FieldSchema(name:key, type:string, comment:default), (src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: SELECT dest1_n124.* FROM dest1_n124
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest1_n124
+PREHOOK: Output: hdfs://### HDFS PATH ###
+POSTHOOK: query: SELECT dest1_n124.* FROM dest1_n124
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest1_n124
+POSTHOOK: Output: hdfs://### HDFS PATH ###
+0 val_0+3+7
+0 val_0+3+7
+0 val_0+3+7
+10 val_10+3+7
+11 val_11+3+7
+12 val_12+3+7
+12 val_12+3+7
+15 val_15+3+7
+15 val_15+3+7
+17 val_17+3+7
+18 val_18+3+7
+18 val_18+3+7
+19 val_19+3+7
+2 val_2+3+7
+20 val_20+3+7
+24 val_24+3+7
+24 val_24+3+7
+26 val_26+3+7
+26 val_26+3+7
+27 val_27+3+7
+28 val_28+3+7
+30 val_30+3+7
+33 val_33+3+7
+34 val_34+3+7
+35 val_35+3+7
+35 val_35+3+7
+35 val_35+3+7
+37 val_37+3+7
+37 val_37+3+7
+4 val_4+3+7
+41 val_41+3+7
+42 val_42+3+7
+42 val_42+3+7
+43 val_43+3+7
+44 val_44+3+7
+47 val_47+3+7
+5 val_5+3+7
+5 val_5+3+7
+5 val_5+3+7
+51 val_51+3+7
+51 val_51+3+7
+53 val_53+3+7
+54 val_54+3+7
+57 val_57+3+7
+58 val_58+3+7
+58 val_58+3+7
+64 val_64+3+7
+65 val_65+3+7
+66 val_66+3+7
+67 val_67+3+7
+67 val_67+3+7
+69 val_69+3+7
+70 val_70+3+7
+70 val_70+3+7
+70 val_70+3+7
+72 val_72+3+7
+72 val_72+3+7
+74 val_74+3+7
+76 val_76+3+7
+76 val_76+3+7
+77 val_77+3+7
+78 val_78+3+7
+8 val_8+3+7
+80 val_80+3+7
+82 val_82+3+7
+83 val_83+3+7
+83 val_83+3+7
+84 val_84+3+7
+84 val_84+3+7
+85 val_85+3+7
+86 val_86+3+7
+87 val_87+3+7
+9 val_9+3+7
+90 val_90+3+7
+90 val_90+3+7
+90 val_90+3+7
+92 val_92+3+7
+95 val_95+3+7
+95 val_95+3+7
+96 val_96+3+7
+97 val_97+3+7
+97 val_97+3+7
+98 val_98+3+7
+98 val_98+3+7
diff --git a/ql/src/test/results/clientpositive/input20.q.out b/ql/src/test/results/clientpositive/llap/input20.q.out
similarity index 54%
rename from ql/src/test/results/clientpositive/input20.q.out
rename to ql/src/test/results/clientpositive/llap/input20.q.out
index d90b908..819d888 100644
--- a/ql/src/test/results/clientpositive/input20.q.out
+++ b/ql/src/test/results/clientpositive/llap/input20.q.out
@@ -36,74 +36,99 @@ POSTHOOK: Input: default@src
POSTHOOK: Output: default@dest1_n138
STAGE DEPENDENCIES:
Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
- Stage-2 depends on stages: Stage-0, Stage-3
- Stage-3 depends on stages: Stage-1
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
STAGE PLANS:
Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: key (type: string), key (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE
- Transform Operator
- command: cat
- output info:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string), key (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE
+ Transform Operator
+ command: cat
+ output info:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Statistics: Num rows: 500 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ null sort order:
+ sort order:
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
+ Statistics: Num rows: 500 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: string), _col1 (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col0 (type: string), VALUE._col1 (type: string)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 500 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- null sort order:
- sort order:
- Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
+ Transform Operator
+ command: python input20_script.py
+ output info:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Statistics: Num rows: 500 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: string), _col1 (type: string)
- Reduce Operator Tree:
- Select Operator
- expressions: VALUE._col0 (type: string), VALUE._col1 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE
- Transform Operator
- command: python input20_script.py
- output info:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Statistics: Num rows: 500 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: UDFToInteger(_col0) (type: int), _col1 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.dest1_n138
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string)
- outputColumnNames: key, value
- Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
- minReductionHashAggr: 0.99
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ Select Operator
+ expressions: UDFToInteger(_col0) (type: int), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest1_n138
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ minReductionHashAggr: 0.99
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ null sort order:
+ sort order:
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reducer 3
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-2
+ Dependency Collection
Stage: Stage-0
Move Operator
@@ -115,7 +140,7 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest1_n138
- Stage: Stage-2
+ Stage: Stage-3
Stats Work
Basic Stats Work:
Column Stats Desc:
@@ -123,30 +148,6 @@ STAGE PLANS:
Column Types: int, string
Table: default.dest1_n138
- Stage: Stage-3
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- null sort order:
- sort order:
- Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
- Execution mode: vectorized
- Reduce Operator Tree:
- Group By Operator
- aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
PREHOOK: query: FROM (
FROM src
MAP src.key, src.key
@@ -178,11 +179,11 @@ POSTHOOK: Lineage: dest1_n138.value SCRIPT [(src)src.FieldSchema(name:key, type:
PREHOOK: query: SELECT * FROM dest1_n138 ORDER BY key, value
PREHOOK: type: QUERY
PREHOOK: Input: default@dest1_n138
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: SELECT * FROM dest1_n138 ORDER BY key, value
POSTHOOK: type: QUERY
POSTHOOK: Input: default@dest1_n138
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
1 105_105
1 10_10
1 111_111
diff --git a/ql/src/test/results/clientpositive/input33.q.out b/ql/src/test/results/clientpositive/llap/input33.q.out
similarity index 54%
rename from ql/src/test/results/clientpositive/input33.q.out
rename to ql/src/test/results/clientpositive/llap/input33.q.out
index c8df2ef..daf57de 100644
--- a/ql/src/test/results/clientpositive/input33.q.out
+++ b/ql/src/test/results/clientpositive/llap/input33.q.out
@@ -36,74 +36,99 @@ POSTHOOK: Input: default@src
POSTHOOK: Output: default@dest1_n135
STAGE DEPENDENCIES:
Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
- Stage-2 depends on stages: Stage-0, Stage-3
- Stage-3 depends on stages: Stage-1
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
STAGE PLANS:
Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: key (type: string), key (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE
- Transform Operator
- command: cat
- output info:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string), key (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE
+ Transform Operator
+ command: cat
+ output info:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Statistics: Num rows: 500 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ null sort order:
+ sort order:
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
+ Statistics: Num rows: 500 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: string), _col1 (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col0 (type: string), VALUE._col1 (type: string)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 500 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- null sort order:
- sort order:
- Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
+ Transform Operator
+ command: python input20_script.py
+ output info:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Statistics: Num rows: 500 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: string), _col1 (type: string)
- Reduce Operator Tree:
- Select Operator
- expressions: VALUE._col0 (type: string), VALUE._col1 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE
- Transform Operator
- command: python input20_script.py
- output info:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Statistics: Num rows: 500 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: UDFToInteger(_col0) (type: int), _col1 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.dest1_n135
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string)
- outputColumnNames: key, value
- Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
- minReductionHashAggr: 0.99
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ Select Operator
+ expressions: UDFToInteger(_col0) (type: int), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest1_n135
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ minReductionHashAggr: 0.99
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ null sort order:
+ sort order:
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reducer 3
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-2
+ Dependency Collection
Stage: Stage-0
Move Operator
@@ -115,7 +140,7 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest1_n135
- Stage: Stage-2
+ Stage: Stage-3
Stats Work
Basic Stats Work:
Column Stats Desc:
@@ -123,30 +148,6 @@ STAGE PLANS:
Column Types: int, string
Table: default.dest1_n135
- Stage: Stage-3
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- null sort order:
- sort order:
- Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
- Execution mode: vectorized
- Reduce Operator Tree:
- Group By Operator
- aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
PREHOOK: query: FROM (
FROM src
MAP src.key, src.key
@@ -178,11 +179,11 @@ POSTHOOK: Lineage: dest1_n135.value SCRIPT [(src)src.FieldSchema(name:key, type:
PREHOOK: query: SELECT * FROM dest1_n135 ORDER BY key, value
PREHOOK: type: QUERY
PREHOOK: Input: default@dest1_n135
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: SELECT * FROM dest1_n135 ORDER BY key, value
POSTHOOK: type: QUERY
POSTHOOK: Input: default@dest1_n135
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
1 105_105
1 10_10
1 111_111
diff --git a/ql/src/test/results/clientpositive/input34.q.out b/ql/src/test/results/clientpositive/llap/input34.q.out
similarity index 66%
rename from ql/src/test/results/clientpositive/input34.q.out
rename to ql/src/test/results/clientpositive/llap/input34.q.out
index 00dd35d..3f702cd 100644
--- a/ql/src/test/results/clientpositive/input34.q.out
+++ b/ql/src/test/results/clientpositive/llap/input34.q.out
@@ -30,81 +30,79 @@ POSTHOOK: Input: default@src
POSTHOOK: Output: default@dest1_n161
STAGE DEPENDENCIES:
Stage-1 is a root stage
- Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5
- Stage-4
- Stage-0 depends on stages: Stage-4, Stage-3, Stage-6
- Stage-2 depends on stages: Stage-0
- Stage-3
- Stage-5
- Stage-6 depends on stages: Stage-5
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
STAGE PLANS:
Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- Transform Operator
- command: cat
- output info:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: UDFToInteger(_col0) (type: int), _col1 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.dest1_n161
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
- expressions: _col0 (type: int), _col1 (type: string)
- outputColumnNames: key, value
- Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
- minReductionHashAggr: 0.99
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- null sort order:
- sort order:
- Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
- Reduce Operator Tree:
- Group By Operator
- aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Transform Operator
+ command: cat
+ output info:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: UDFToInteger(_col0) (type: int), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest1_n161
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ minReductionHashAggr: 0.99
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ null sort order:
+ sort order:
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Stage: Stage-7
- Conditional Operator
-
- Stage: Stage-4
- Move Operator
- files:
- hdfs directory: true
-#### A masked pattern was here ####
+ Stage: Stage-2
+ Dependency Collection
Stage: Stage-0
Move Operator
@@ -116,7 +114,7 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest1_n161
- Stage: Stage-2
+ Stage: Stage-3
Stats Work
Basic Stats Work:
Column Stats Desc:
@@ -124,36 +122,6 @@ STAGE PLANS:
Column Types: int, string
Table: default.dest1_n161
- Stage: Stage-3
- Map Reduce
- Map Operator Tree:
- TableScan
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.dest1_n161
-
- Stage: Stage-5
- Map Reduce
- Map Operator Tree:
- TableScan
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.dest1_n161
-
- Stage: Stage-6
- Move Operator
- files:
- hdfs directory: true
-#### A masked pattern was here ####
-
PREHOOK: query: FROM (
FROM src
SELECT TRANSFORM(src.key, src.value) ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe'
@@ -179,11 +147,11 @@ POSTHOOK: Lineage: dest1_n161.value SCRIPT [(src)src.FieldSchema(name:key, type:
PREHOOK: query: SELECT dest1_n161.* FROM dest1_n161
PREHOOK: type: QUERY
PREHOOK: Input: default@dest1_n161
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: SELECT dest1_n161.* FROM dest1_n161
POSTHOOK: type: QUERY
POSTHOOK: Input: default@dest1_n161
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
238 val_238
86 val_86
311 val_311
diff --git a/ql/src/test/results/clientpositive/input35.q.out b/ql/src/test/results/clientpositive/llap/input35.q.out
similarity index 65%
rename from ql/src/test/results/clientpositive/input35.q.out
rename to ql/src/test/results/clientpositive/llap/input35.q.out
index cee491f..85e5412 100644
--- a/ql/src/test/results/clientpositive/input35.q.out
+++ b/ql/src/test/results/clientpositive/llap/input35.q.out
@@ -30,81 +30,79 @@ POSTHOOK: Input: default@src
POSTHOOK: Output: default@dest1_n25
STAGE DEPENDENCIES:
Stage-1 is a root stage
- Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5
- Stage-4
- Stage-0 depends on stages: Stage-4, Stage-3, Stage-6
- Stage-2 depends on stages: Stage-0
- Stage-3
- Stage-5
- Stage-6 depends on stages: Stage-5
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
STAGE PLANS:
Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- Transform Operator
- command: cat
- output info:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: UDFToInteger(_col0) (type: int), _col1 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.dest1_n25
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
- expressions: _col0 (type: int), _col1 (type: string)
- outputColumnNames: key, value
- Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
- minReductionHashAggr: 0.99
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- null sort order:
- sort order:
- Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
- Reduce Operator Tree:
- Group By Operator
- aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Transform Operator
+ command: cat
+ output info:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: UDFToInteger(_col0) (type: int), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest1_n25
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ minReductionHashAggr: 0.99
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ null sort order:
+ sort order:
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Stage: Stage-7
- Conditional Operator
-
- Stage: Stage-4
- Move Operator
- files:
- hdfs directory: true
-#### A masked pattern was here ####
+ Stage: Stage-2
+ Dependency Collection
Stage: Stage-0
Move Operator
@@ -116,7 +114,7 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest1_n25
- Stage: Stage-2
+ Stage: Stage-3
Stats Work
Basic Stats Work:
Column Stats Desc:
@@ -124,36 +122,6 @@ STAGE PLANS:
Column Types: int, string
Table: default.dest1_n25
- Stage: Stage-3
- Map Reduce
- Map Operator Tree:
- TableScan
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.dest1_n25
-
- Stage: Stage-5
- Map Reduce
- Map Operator Tree:
- TableScan
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.dest1_n25
-
- Stage: Stage-6
- Move Operator
- files:
- hdfs directory: true
-#### A masked pattern was here ####
-
PREHOOK: query: FROM (
FROM src
SELECT TRANSFORM(src.key, src.value) ROW FORMAT DELIMITED FIELDS TERMINATED BY '\002'
@@ -179,11 +147,11 @@ POSTHOOK: Lineage: dest1_n25.value SCRIPT [(src)src.FieldSchema(name:key, type:s
PREHOOK: query: SELECT dest1_n25.* FROM dest1_n25
PREHOOK: type: QUERY
PREHOOK: Input: default@dest1_n25
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: SELECT dest1_n25.* FROM dest1_n25
POSTHOOK: type: QUERY
POSTHOOK: Input: default@dest1_n25
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
238 val_238
86 val_86
311 val_311
diff --git a/ql/src/test/results/clientpositive/input36.q.out b/ql/src/test/results/clientpositive/llap/input36.q.out
similarity index 63%
rename from ql/src/test/results/clientpositive/input36.q.out
rename to ql/src/test/results/clientpositive/llap/input36.q.out
index 45289b2..8a8e30c 100644
--- a/ql/src/test/results/clientpositive/input36.q.out
+++ b/ql/src/test/results/clientpositive/llap/input36.q.out
@@ -30,81 +30,79 @@ POSTHOOK: Input: default@src
POSTHOOK: Output: default@dest1_n70
STAGE DEPENDENCIES:
Stage-1 is a root stage
- Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5
- Stage-4
- Stage-0 depends on stages: Stage-4, Stage-3, Stage-6
- Stage-2 depends on stages: Stage-0
- Stage-3
- Stage-5
- Stage-6 depends on stages: Stage-5
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
STAGE PLANS:
Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- Transform Operator
- command: cat
- output info:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: UDFToInteger(_col0) (type: int), _col1 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.dest1_n70
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
- expressions: _col0 (type: int), _col1 (type: string)
- outputColumnNames: key, value
- Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
- minReductionHashAggr: 0.99
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- null sort order:
- sort order:
- Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
- Reduce Operator Tree:
- Group By Operator
- aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Transform Operator
+ command: cat
+ output info:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: UDFToInteger(_col0) (type: int), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest1_n70
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ minReductionHashAggr: 0.99
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ null sort order:
+ sort order:
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Stage: Stage-7
- Conditional Operator
-
- Stage: Stage-4
- Move Operator
- files:
- hdfs directory: true
-#### A masked pattern was here ####
+ Stage: Stage-2
+ Dependency Collection
Stage: Stage-0
Move Operator
@@ -116,7 +114,7 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest1_n70
- Stage: Stage-2
+ Stage: Stage-3
Stats Work
Basic Stats Work:
Column Stats Desc:
@@ -124,36 +122,6 @@ STAGE PLANS:
Column Types: int, string
Table: default.dest1_n70
- Stage: Stage-3
- Map Reduce
- Map Operator Tree:
- TableScan
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.dest1_n70
-
- Stage: Stage-5
- Map Reduce
- Map Operator Tree:
- TableScan
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.dest1_n70
-
- Stage: Stage-6
- Move Operator
- files:
- hdfs directory: true
-#### A masked pattern was here ####
-
PREHOOK: query: FROM (
FROM src
SELECT TRANSFORM(src.key, src.value) ROW FORMAT DELIMITED FIELDS TERMINATED BY '\002'
@@ -179,11 +147,11 @@ POSTHOOK: Lineage: dest1_n70.value SCRIPT [(src)src.FieldSchema(name:key, type:s
PREHOOK: query: SELECT dest1_n70.* FROM dest1_n70
PREHOOK: type: QUERY
PREHOOK: Input: default@dest1_n70
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: SELECT dest1_n70.* FROM dest1_n70
POSTHOOK: type: QUERY
POSTHOOK: Input: default@dest1_n70
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
NULL NULL
NULL NULL
NULL NULL
diff --git a/ql/src/test/results/clientpositive/input38.q.out b/ql/src/test/results/clientpositive/llap/input38.q.out
similarity index 72%
rename from ql/src/test/results/clientpositive/input38.q.out
rename to ql/src/test/results/clientpositive/llap/input38.q.out
index d46ddf0..161cda2 100644
--- a/ql/src/test/results/clientpositive/input38.q.out
+++ b/ql/src/test/results/clientpositive/llap/input38.q.out
@@ -28,77 +28,75 @@ POSTHOOK: Input: default@src
POSTHOOK: Output: default@dest1_n91
STAGE DEPENDENCIES:
Stage-1 is a root stage
- Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5
- Stage-4
- Stage-0 depends on stages: Stage-4, Stage-3, Stage-6
- Stage-2 depends on stages: Stage-0
- Stage-3
- Stage-5
- Stage-6 depends on stages: Stage-5
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
STAGE PLANS:
Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: key (type: string), value (type: string), 3 (type: int), 7 (type: int)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE
- Transform Operator
- command: cat
- output info:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string), value (type: string), 3 (type: int), 7 (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE
+ Transform Operator
+ command: cat
+ output info:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest1_n91
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ minReductionHashAggr: 0.99
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ null sort order:
+ sort order:
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.dest1_n91
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string)
- outputColumnNames: key, value
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
- minReductionHashAggr: 0.99
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- null sort order:
- sort order:
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
- Reduce Operator Tree:
- Group By Operator
- aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-7
- Conditional Operator
- Stage: Stage-4
- Move Operator
- files:
- hdfs directory: true
-#### A masked pattern was here ####
+ Stage: Stage-2
+ Dependency Collection
Stage: Stage-0
Move Operator
@@ -110,7 +108,7 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest1_n91
- Stage: Stage-2
+ Stage: Stage-3
Stats Work
Basic Stats Work:
Column Stats Desc:
@@ -118,36 +116,6 @@ STAGE PLANS:
Column Types: string, string
Table: default.dest1_n91
- Stage: Stage-3
- Map Reduce
- Map Operator Tree:
- TableScan
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.dest1_n91
-
- Stage: Stage-5
- Map Reduce
- Map Operator Tree:
- TableScan
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.dest1_n91
-
- Stage: Stage-6
- Move Operator
- files:
- hdfs directory: true
-#### A masked pattern was here ####
-
PREHOOK: query: FROM (
FROM src
SELECT TRANSFORM(src.key, src.value, 1+2, 3+4)
@@ -171,11 +139,11 @@ POSTHOOK: Lineage: dest1_n91.value SCRIPT [(src)src.FieldSchema(name:key, type:s
PREHOOK: query: SELECT dest1_n91.* FROM dest1_n91
PREHOOK: type: QUERY
PREHOOK: Input: default@dest1_n91
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: SELECT dest1_n91.* FROM dest1_n91
POSTHOOK: type: QUERY
POSTHOOK: Input: default@dest1_n91
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
238 val_238 3 7
86 val_86 3 7
311 val_311 3 7
diff --git a/ql/src/test/results/clientpositive/llap/input5.q.out b/ql/src/test/results/clientpositive/llap/input5.q.out
new file mode 100644
index 0000000..ab091fe
--- /dev/null
+++ b/ql/src/test/results/clientpositive/llap/input5.q.out
@@ -0,0 +1,176 @@
+PREHOOK: query: CREATE TABLE dest1_n94(key STRING, value STRING) STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@dest1_n94
+POSTHOOK: query: CREATE TABLE dest1_n94(key STRING, value STRING) STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@dest1_n94
+PREHOOK: query: EXPLAIN
+FROM (
+ FROM src_thrift
+ SELECT TRANSFORM(src_thrift.lint, src_thrift.lintstring)
+ USING 'cat' AS (tkey, tvalue)
+ CLUSTER BY tkey
+) tmap
+INSERT OVERWRITE TABLE dest1_n94 SELECT tmap.tkey, tmap.tvalue
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src_thrift
+PREHOOK: Output: default@dest1_n94
+POSTHOOK: query: EXPLAIN
+FROM (
+ FROM src_thrift
+ SELECT TRANSFORM(src_thrift.lint, src_thrift.lintstring)
+ USING 'cat' AS (tkey, tvalue)
+ CLUSTER BY tkey
+) tmap
+INSERT OVERWRITE TABLE dest1_n94 SELECT tmap.tkey, tmap.tvalue
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src_thrift
+POSTHOOK: Output: default@dest1_n94
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src_thrift
+ Statistics: Num rows: 11 Data size: 29480 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: lint (type: array<int>), lintstring (type: array<struct<myint:int,mystring:string,underscore_int:int>>)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 11 Data size: 29480 Basic stats: COMPLETE Column stats: NONE
+ Transform Operator
+ command: cat
+ output info:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Statistics: Num rows: 11 Data size: 29480 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ null sort order: a
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 11 Data size: 29480 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string), _col1 (type: string)
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col0 (type: string), VALUE._col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 11 Data size: 29480 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 11 Data size: 29480 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest1_n94
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 11 Data size: 29480 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ minReductionHashAggr: 0.99
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 3560 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ null sort order:
+ sort order:
+ Statistics: Num rows: 1 Data size: 3560 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reducer 3
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 3560 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 3560 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-2
+ Dependency Collection
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: true
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest1_n94
+
+ Stage: Stage-3
+ Stats Work
+ Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: string, string
+ Table: default.dest1_n94
+
+PREHOOK: query: FROM (
+ FROM src_thrift
+ SELECT TRANSFORM(src_thrift.lint, src_thrift.lintstring)
+ USING 'cat' AS (tkey, tvalue)
+ CLUSTER BY tkey
+) tmap
+INSERT OVERWRITE TABLE dest1_n94 SELECT tmap.tkey, tmap.tvalue
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src_thrift
+PREHOOK: Output: default@dest1_n94
+POSTHOOK: query: FROM (
+ FROM src_thrift
+ SELECT TRANSFORM(src_thrift.lint, src_thrift.lintstring)
+ USING 'cat' AS (tkey, tvalue)
+ CLUSTER BY tkey
+) tmap
+INSERT OVERWRITE TABLE dest1_n94 SELECT tmap.tkey, tmap.tvalue
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src_thrift
+POSTHOOK: Output: default@dest1_n94
+POSTHOOK: Lineage: dest1_n94.key SCRIPT [(src_thrift)src_thrift.FieldSchema(name:lint, type:array<int>, comment:from deserializer), (src_thrift)src_thrift.FieldSchema(name:lintstring, type:array<struct<myint:int,mystring:string,underscore_int:int>>, comment:from deserializer), ]
+POSTHOOK: Lineage: dest1_n94.value SCRIPT [(src_thrift)src_thrift.FieldSchema(name:lint, type:array<int>, comment:from deserializer), (src_thrift)src_thrift.FieldSchema(name:lintstring, type:array<struct<myint:int,mystring:string,underscore_int:int>>, comment:from deserializer), ]
+PREHOOK: query: SELECT dest1_n94.* FROM dest1_n94
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest1_n94
+PREHOOK: Output: hdfs://### HDFS PATH ###
+POSTHOOK: query: SELECT dest1_n94.* FROM dest1_n94
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest1_n94
+POSTHOOK: Output: hdfs://### HDFS PATH ###
+NULL NULL
+[0,0,0] [{"myint":0,"mystring":"0","underscore_int":0}]
+[1,2,3] [{"myint":1,"mystring":"1","underscore_int":1}]
+[2,4,6] [{"myint":4,"mystring":"8","underscore_int":2}]
+[3,6,9] [{"myint":9,"mystring":"27","underscore_int":3}]
+[4,8,12] [{"myint":16,"mystring":"64","underscore_int":4}]
+[5,10,15] [{"myint":25,"mystring":"125","underscore_int":5}]
+[6,12,18] [{"myint":36,"mystring":"216","underscore_int":6}]
+[7,14,21] [{"myint":49,"mystring":"343","underscore_int":7}]
+[8,16,24] [{"myint":64,"mystring":"512","underscore_int":8}]
+[9,18,27] [{"myint":81,"mystring":"729","underscore_int":9}]
diff --git a/ql/src/test/results/clientpositive/llap/insert_into3.q.out b/ql/src/test/results/clientpositive/llap/insert_into3.q.out
new file mode 100644
index 0000000..9c9820e
--- /dev/null
+++ b/ql/src/test/results/clientpositive/llap/insert_into3.q.out
@@ -0,0 +1,546 @@
+PREHOOK: query: DROP TABLE insert_into3a
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: DROP TABLE insert_into3a
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: DROP TABLE insert_into3b
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: DROP TABLE insert_into3b
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: CREATE TABLE insert_into3a (key int, value string)
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@insert_into3a
+POSTHOOK: query: CREATE TABLE insert_into3a (key int, value string)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@insert_into3a
+PREHOOK: query: CREATE TABLE insert_into3b (key int, value string)
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@insert_into3b
+POSTHOOK: query: CREATE TABLE insert_into3b (key int, value string)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@insert_into3b
+PREHOOK: query: EXPLAIN FROM src INSERT INTO TABLE insert_into3a SELECT * ORDER BY key, value LIMIT 50
+ INSERT INTO TABLE insert_into3b SELECT * ORDER BY key, value LIMIT 100
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@insert_into3a
+PREHOOK: Output: default@insert_into3b
+POSTHOOK: query: EXPLAIN FROM src INSERT INTO TABLE insert_into3a SELECT * ORDER BY key, value LIMIT 50
+ INSERT INTO TABLE insert_into3b SELECT * ORDER BY key, value LIMIT 100
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@insert_into3a
+POSTHOOK: Output: default@insert_into3b
+STAGE DEPENDENCIES:
+ Stage-2 is a root stage
+ Stage-3 depends on stages: Stage-2
+ Stage-0 depends on stages: Stage-3
+ Stage-4 depends on stages: Stage-0
+ Stage-1 depends on stages: Stage-3
+ Stage-5 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-2
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE)
+ Reducer 4 <- Map 1 (SIMPLE_EDGE)
+ Reducer 5 <- Reducer 4 (CUSTOM_SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Top N Key Operator
+ sort order: ++
+ keys: key (type: string), value (type: string)
+ null sort order: zz
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ top n: 50
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string)
+ null sort order: zz
+ sort order: ++
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
+ Top N Key Operator
+ sort order: ++
+ keys: key (type: string), value (type: string)
+ null sort order: zz
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ top n: 100
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string)
+ null sort order: zz
+ sort order: ++
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
+ Execution mode: vectorized, llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Limit
+ Number of rows: 50
+ Statistics: Num rows: 50 Data size: 8900 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: UDFToInteger(_col0) (type: int), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 50 Data size: 4750 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 50 Data size: 4750 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.insert_into3a
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 50 Data size: 4750 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ minReductionHashAggr: 0.98
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ null sort order:
+ sort order:
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reducer 3
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Reducer 4
+ Execution mode: llap
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Limit
+ Number of rows: 100
+ Statistics: Num rows: 100 Data size: 17800 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: UDFToInteger(_col0) (type: int), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 100 Data size: 9500 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 100 Data size: 9500 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.insert_into3b
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 100 Data size: 9500 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ minReductionHashAggr: 0.99
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ null sort order:
+ sort order:
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reducer 5
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-3
+ Dependency Collection
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: false
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.insert_into3a
+
+ Stage: Stage-4
+ Stats Work
+ Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.insert_into3a
+
+ Stage: Stage-1
+ Move Operator
+ tables:
+ replace: false
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.insert_into3b
+
+ Stage: Stage-5
+ Stats Work
+ Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.insert_into3b
+
+PREHOOK: query: FROM src INSERT INTO TABLE insert_into3a SELECT * ORDER BY key, value LIMIT 50
+ INSERT INTO TABLE insert_into3b SELECT * ORDER BY key, value LIMIT 100
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@insert_into3a
+PREHOOK: Output: default@insert_into3b
+POSTHOOK: query: FROM src INSERT INTO TABLE insert_into3a SELECT * ORDER BY key, value LIMIT 50
+ INSERT INTO TABLE insert_into3b SELECT * ORDER BY key, value LIMIT 100
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@insert_into3a
+POSTHOOK: Output: default@insert_into3b
+POSTHOOK: Lineage: insert_into3a.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: insert_into3a.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: insert_into3b.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: insert_into3b.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: SELECT SUM(HASH(c)) FROM (
+ SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into3a
+) t
+PREHOOK: type: QUERY
+PREHOOK: Input: default@insert_into3a
+PREHOOK: Output: hdfs://### HDFS PATH ###
+POSTHOOK: query: SELECT SUM(HASH(c)) FROM (
+ SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into3a
+) t
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@insert_into3a
+POSTHOOK: Output: hdfs://### HDFS PATH ###
+-1254133670
+PREHOOK: query: SELECT SUM(HASH(c)) FROM (
+ SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into3b
+) t
+PREHOOK: type: QUERY
+PREHOOK: Input: default@insert_into3b
+PREHOOK: Output: hdfs://### HDFS PATH ###
+POSTHOOK: query: SELECT SUM(HASH(c)) FROM (
+ SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into3b
+) t
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@insert_into3b
+POSTHOOK: Output: hdfs://### HDFS PATH ###
+-1142373758
+PREHOOK: query: EXPLAIN FROM src INSERT OVERWRITE TABLE insert_into3a SELECT * LIMIT 10
+ INSERT INTO TABLE insert_into3b SELECT * LIMIT 10
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@insert_into3a
+PREHOOK: Output: default@insert_into3b
+POSTHOOK: query: EXPLAIN FROM src INSERT OVERWRITE TABLE insert_into3a SELECT * LIMIT 10
+ INSERT INTO TABLE insert_into3b SELECT * LIMIT 10
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@insert_into3a
+POSTHOOK: Output: default@insert_into3b
+STAGE DEPENDENCIES:
+ Stage-2 is a root stage
+ Stage-3 depends on stages: Stage-2
+ Stage-0 depends on stages: Stage-3
+ Stage-4 depends on stages: Stage-0
+ Stage-1 depends on stages: Stage-3
+ Stage-5 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-2
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE)
+ Reducer 4 <- Map 1 (CUSTOM_SIMPLE_EDGE)
+ Reducer 5 <- Reducer 4 (CUSTOM_SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Limit
+ Number of rows: 10
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ null sort order:
+ sort order:
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
+ value expressions: _col0 (type: string), _col1 (type: string)
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Limit
+ Number of rows: 10
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ null sort order:
+ sort order:
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
+ value expressions: _col0 (type: string), _col1 (type: string)
+ Execution mode: vectorized, llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col0 (type: string), VALUE._col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
+ Limit
+ Number of rows: 10
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: UDFToInteger(_col0) (type: int), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.insert_into3a
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ minReductionHashAggr: 0.9
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ null sort order:
+ sort order:
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reducer 3
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Reducer 4
+ Execution mode: llap
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col0 (type: string), VALUE._col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
+ Limit
+ Number of rows: 10
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: UDFToInteger(_col0) (type: int), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.insert_into3b
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ minReductionHashAggr: 0.9
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ null sort order:
+ sort order:
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reducer 5
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-3
+ Dependency Collection
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: true
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.insert_into3a
+
+ Stage: Stage-4
+ Stats Work
+ Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.insert_into3a
+
+ Stage: Stage-1
+ Move Operator
+ tables:
+ replace: false
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.insert_into3b
+
+ Stage: Stage-5
+ Stats Work
+ Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.insert_into3b
+
+PREHOOK: query: FROM src INSERT OVERWRITE TABLE insert_into3a SELECT * LIMIT 10
+ INSERT INTO TABLE insert_into3b SELECT * LIMIT 10
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@insert_into3a
+PREHOOK: Output: default@insert_into3b
+POSTHOOK: query: FROM src INSERT OVERWRITE TABLE insert_into3a SELECT * LIMIT 10
+ INSERT INTO TABLE insert_into3b SELECT * LIMIT 10
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@insert_into3a
+POSTHOOK: Output: default@insert_into3b
+POSTHOOK: Lineage: insert_into3a.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: insert_into3a.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: insert_into3b.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: insert_into3b.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: SELECT SUM(HASH(c)) FROM (
+ SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into3a
+) t
+PREHOOK: type: QUERY
+PREHOOK: Input: default@insert_into3a
+PREHOOK: Output: hdfs://### HDFS PATH ###
+POSTHOOK: query: SELECT SUM(HASH(c)) FROM (
+ SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into3a
+) t
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@insert_into3a
+POSTHOOK: Output: hdfs://### HDFS PATH ###
+-826625916
+PREHOOK: query: SELECT SUM(HASH(c)) FROM (
+ SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into3b
+) t
+PREHOOK: type: QUERY
+PREHOOK: Input: default@insert_into3b
+PREHOOK: Output: hdfs://### HDFS PATH ###
+POSTHOOK: query: SELECT SUM(HASH(c)) FROM (
+ SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into3b
+) t
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@insert_into3b
+POSTHOOK: Output: hdfs://### HDFS PATH ###
+-1968999674
+PREHOOK: query: DROP TABLE insert_into3a
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@insert_into3a
+PREHOOK: Output: default@insert_into3a
+POSTHOOK: query: DROP TABLE insert_into3a
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@insert_into3a
+POSTHOOK: Output: default@insert_into3a
+PREHOOK: query: DROP TABLE insert_into3b
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@insert_into3b
+PREHOOK: Output: default@insert_into3b
+POSTHOOK: query: DROP TABLE insert_into3b
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@insert_into3b
+POSTHOOK: Output: default@insert_into3b
diff --git a/ql/src/test/results/clientpositive/llap/insert_into4.q.out b/ql/src/test/results/clientpositive/llap/insert_into4.q.out
new file mode 100644
index 0000000..f2e4bab
--- /dev/null
+++ b/ql/src/test/results/clientpositive/llap/insert_into4.q.out
@@ -0,0 +1,436 @@
+PREHOOK: query: DROP TABLE insert_into4a
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: DROP TABLE insert_into4a
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: DROP TABLE insert_into4b
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: DROP TABLE insert_into4b
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: CREATE TABLE insert_into4a (key int, value string)
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@insert_into4a
+POSTHOOK: query: CREATE TABLE insert_into4a (key int, value string)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@insert_into4a
+PREHOOK: query: CREATE TABLE insert_into4b (key int, value string)
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@insert_into4b
+POSTHOOK: query: CREATE TABLE insert_into4b (key int, value string)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@insert_into4b
+PREHOOK: query: EXPLAIN INSERT INTO TABLE insert_into4a SELECT * FROM src LIMIT 10
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@insert_into4a
+POSTHOOK: query: EXPLAIN INSERT INTO TABLE insert_into4a SELECT * FROM src LIMIT 10
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@insert_into4a
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Limit
+ Number of rows: 10
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ null sort order:
+ sort order:
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
+ value expressions: _col0 (type: string), _col1 (type: string)
+ Execution mode: vectorized, llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col0 (type: string), VALUE._col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
+ Limit
+ Number of rows: 10
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: UDFToInteger(_col0) (type: int), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.insert_into4a
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ minReductionHashAggr: 0.9
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ null sort order:
+ sort order:
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reducer 3
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-2
+ Dependency Collection
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: false
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.insert_into4a
+
+ Stage: Stage-3
+ Stats Work
+ Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.insert_into4a
+
+PREHOOK: query: INSERT INTO TABLE insert_into4a SELECT * FROM src LIMIT 10
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@insert_into4a
+POSTHOOK: query: INSERT INTO TABLE insert_into4a SELECT * FROM src LIMIT 10
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@insert_into4a
+POSTHOOK: Lineage: insert_into4a.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: insert_into4a.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: SELECT SUM(HASH(c)) FROM (
+ SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into4a
+) t
+PREHOOK: type: QUERY
+PREHOOK: Input: default@insert_into4a
+PREHOOK: Output: hdfs://### HDFS PATH ###
+POSTHOOK: query: SELECT SUM(HASH(c)) FROM (
+ SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into4a
+) t
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@insert_into4a
+POSTHOOK: Output: hdfs://### HDFS PATH ###
+-826625916
+PREHOOK: query: EXPLAIN INSERT INTO TABLE insert_into4a SELECT * FROM src LIMIT 10
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@insert_into4a
+POSTHOOK: query: EXPLAIN INSERT INTO TABLE insert_into4a SELECT * FROM src LIMIT 10
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@insert_into4a
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Limit
+ Number of rows: 10
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ null sort order:
+ sort order:
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
+ value expressions: _col0 (type: string), _col1 (type: string)
+ Execution mode: vectorized, llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col0 (type: string), VALUE._col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
+ Limit
+ Number of rows: 10
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: UDFToInteger(_col0) (type: int), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.insert_into4a
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ minReductionHashAggr: 0.9
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ null sort order:
+ sort order:
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reducer 3
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-2
+ Dependency Collection
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: false
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.insert_into4a
+
+ Stage: Stage-3
+ Stats Work
+ Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.insert_into4a
+
+PREHOOK: query: INSERT INTO TABLE insert_into4a SELECT * FROM src LIMIT 10
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@insert_into4a
+POSTHOOK: query: INSERT INTO TABLE insert_into4a SELECT * FROM src LIMIT 10
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@insert_into4a
+POSTHOOK: Lineage: insert_into4a.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: insert_into4a.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: SELECT SUM(HASH(c)) FROM (
+ SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into4a
+) t
+PREHOOK: type: QUERY
+PREHOOK: Input: default@insert_into4a
+PREHOOK: Output: hdfs://### HDFS PATH ###
+POSTHOOK: query: SELECT SUM(HASH(c)) FROM (
+ SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into4a
+) t
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@insert_into4a
+POSTHOOK: Output: hdfs://### HDFS PATH ###
+-1653251832
+PREHOOK: query: EXPLAIN INSERT INTO TABLE insert_into4b SELECT * FROM insert_into4a
+PREHOOK: type: QUERY
+PREHOOK: Input: default@insert_into4a
+PREHOOK: Output: default@insert_into4b
+POSTHOOK: query: EXPLAIN INSERT INTO TABLE insert_into4b SELECT * FROM insert_into4a
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@insert_into4a
+POSTHOOK: Output: default@insert_into4b
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: insert_into4a
+ Statistics: Num rows: 20 Data size: 1900 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: int), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 20 Data size: 1900 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 20 Data size: 1900 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.insert_into4b
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 20 Data size: 1900 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ minReductionHashAggr: 0.95
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ null sort order:
+ sort order:
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-2
+ Dependency Collection
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: false
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.insert_into4b
+
+ Stage: Stage-3
+ Stats Work
+ Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.insert_into4b
+
+PREHOOK: query: INSERT INTO TABLE insert_into4b SELECT * FROM insert_into4a
+PREHOOK: type: QUERY
+PREHOOK: Input: default@insert_into4a
+PREHOOK: Output: default@insert_into4b
+POSTHOOK: query: INSERT INTO TABLE insert_into4b SELECT * FROM insert_into4a
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@insert_into4a
+POSTHOOK: Output: default@insert_into4b
+POSTHOOK: Lineage: insert_into4b.key SIMPLE [(insert_into4a)insert_into4a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: insert_into4b.value SIMPLE [(insert_into4a)insert_into4a.FieldSchema(name:value, type:string, comment:null), ]
+PREHOOK: query: SELECT SUM(HASH(c)) FROM (
+ SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into4b
+) t
+PREHOOK: type: QUERY
+PREHOOK: Input: default@insert_into4b
+PREHOOK: Output: hdfs://### HDFS PATH ###
+POSTHOOK: query: SELECT SUM(HASH(c)) FROM (
+ SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into4b
+) t
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@insert_into4b
+POSTHOOK: Output: hdfs://### HDFS PATH ###
+-1653251832
+PREHOOK: query: DROP TABLE insert_into4a
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@insert_into4a
+PREHOOK: Output: default@insert_into4a
+POSTHOOK: query: DROP TABLE insert_into4a
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@insert_into4a
+POSTHOOK: Output: default@insert_into4a
+PREHOOK: query: DROP TABLE insert_into4b
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@insert_into4b
+PREHOOK: Output: default@insert_into4b
+POSTHOOK: query: DROP TABLE insert_into4b
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@insert_into4b
+POSTHOOK: Output: default@insert_into4b
diff --git a/ql/src/test/results/clientpositive/llap/insert_into5.q.out b/ql/src/test/results/clientpositive/llap/insert_into5.q.out
new file mode 100644
index 0000000..2573fd2
--- /dev/null
+++ b/ql/src/test/results/clientpositive/llap/insert_into5.q.out
@@ -0,0 +1,550 @@
+PREHOOK: query: DROP TABLE insert_into5a
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: DROP TABLE insert_into5a
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: DROP TABLE insert_into5b
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: DROP TABLE insert_into5b
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: CREATE TABLE insert_into5a (key int, value string)
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@insert_into5a
+POSTHOOK: query: CREATE TABLE insert_into5a (key int, value string)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@insert_into5a
+PREHOOK: query: CREATE TABLE insert_into5b (key int, value string) PARTITIONED BY (ds string)
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@insert_into5b
+POSTHOOK: query: CREATE TABLE insert_into5b (key int, value string) PARTITIONED BY (ds string)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@insert_into5b
+PREHOOK: query: EXPLAIN INSERT INTO TABLE insert_into5a SELECT 1, 'one' FROM src LIMIT 10
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@insert_into5a
+POSTHOOK: query: EXPLAIN INSERT INTO TABLE insert_into5a SELECT 1, 'one' FROM src LIMIT 10
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@insert_into5a
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: 1 (type: int), 'one' (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
+ Limit
+ Number of rows: 10
+ Statistics: Num rows: 10 Data size: 910 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ null sort order:
+ sort order:
+ Statistics: Num rows: 10 Data size: 910 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
+ value expressions: _col0 (type: int), _col1 (type: string)
+ Execution mode: vectorized, llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col0 (type: int), VALUE._col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 10 Data size: 910 Basic stats: COMPLETE Column stats: COMPLETE
+ Limit
+ Number of rows: 10
+ Statistics: Num rows: 10 Data size: 910 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 10 Data size: 910 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.insert_into5a
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 10 Data size: 910 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ minReductionHashAggr: 0.9
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ null sort order:
+ sort order:
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reducer 3
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-2
+ Dependency Collection
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: false
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.insert_into5a
+
+ Stage: Stage-3
+ Stats Work
+ Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.insert_into5a
+
+PREHOOK: query: INSERT INTO TABLE insert_into5a SELECT 1, 'one' FROM src LIMIT 10
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@insert_into5a
+POSTHOOK: query: INSERT INTO TABLE insert_into5a SELECT 1, 'one' FROM src LIMIT 10
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@insert_into5a
+POSTHOOK: Lineage: insert_into5a.key SIMPLE []
+POSTHOOK: Lineage: insert_into5a.value SIMPLE []
+PREHOOK: query: SELECT SUM(HASH(c)) FROM (
+ SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into5a
+) t
+PREHOOK: type: QUERY
+PREHOOK: Input: default@insert_into5a
+PREHOOK: Output: hdfs://### HDFS PATH ###
+POSTHOOK: query: SELECT SUM(HASH(c)) FROM (
+ SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into5a
+) t
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@insert_into5a
+POSTHOOK: Output: hdfs://### HDFS PATH ###
+481928560
+PREHOOK: query: EXPLAIN INSERT INTO TABLE insert_into5a SELECT * FROM insert_into5a
+PREHOOK: type: QUERY
+PREHOOK: Input: default@insert_into5a
+PREHOOK: Output: default@insert_into5a
+POSTHOOK: query: EXPLAIN INSERT INTO TABLE insert_into5a SELECT * FROM insert_into5a
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@insert_into5a
+POSTHOOK: Output: default@insert_into5a
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: insert_into5a
+ Statistics: Num rows: 10 Data size: 910 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: int), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 10 Data size: 910 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 10 Data size: 910 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.insert_into5a
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 10 Data size: 910 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ minReductionHashAggr: 0.9
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ null sort order:
+ sort order:
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-2
+ Dependency Collection
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: false
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.insert_into5a
+
+ Stage: Stage-3
+ Stats Work
+ Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.insert_into5a
+
+PREHOOK: query: INSERT INTO TABLE insert_into5a SELECT * FROM insert_into5a
+PREHOOK: type: QUERY
+PREHOOK: Input: default@insert_into5a
+PREHOOK: Output: default@insert_into5a
+POSTHOOK: query: INSERT INTO TABLE insert_into5a SELECT * FROM insert_into5a
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@insert_into5a
+POSTHOOK: Output: default@insert_into5a
+POSTHOOK: Lineage: insert_into5a.key SIMPLE [(insert_into5a)insert_into5a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: insert_into5a.value SIMPLE [(insert_into5a)insert_into5a.FieldSchema(name:value, type:string, comment:null), ]
+PREHOOK: query: SELECT SUM(HASH(c)) FROM (
+ SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into5a
+) t
+PREHOOK: type: QUERY
+PREHOOK: Input: default@insert_into5a
+PREHOOK: Output: hdfs://### HDFS PATH ###
+POSTHOOK: query: SELECT SUM(HASH(c)) FROM (
+ SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into5a
+) t
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@insert_into5a
+POSTHOOK: Output: hdfs://### HDFS PATH ###
+963857120
+PREHOOK: query: EXPLAIN INSERT INTO TABLE insert_into5b PARTITION (ds='1')
+ SELECT * FROM insert_into5a
+PREHOOK: type: QUERY
+PREHOOK: Input: default@insert_into5a
+PREHOOK: Output: default@insert_into5b@ds=1
+POSTHOOK: query: EXPLAIN INSERT INTO TABLE insert_into5b PARTITION (ds='1')
+ SELECT * FROM insert_into5a
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@insert_into5a
+POSTHOOK: Output: default@insert_into5b@ds=1
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: insert_into5a
+ Statistics: Num rows: 20 Data size: 1820 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: int), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 20 Data size: 1820 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 20 Data size: 1820 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.insert_into5b
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), '1' (type: string)
+ outputColumnNames: key, value, ds
+ Statistics: Num rows: 20 Data size: 3520 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ keys: ds (type: string)
+ minReductionHashAggr: 0.95
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ null sort order: z
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-2
+ Dependency Collection
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ partition:
+ ds 1
+ replace: false
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.insert_into5b
+
+ Stage: Stage-3
+ Stats Work
+ Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.insert_into5b
+
+PREHOOK: query: INSERT INTO TABLE insert_into5b PARTITION (ds='1') SELECT * FROM insert_into5a
+PREHOOK: type: QUERY
+PREHOOK: Input: default@insert_into5a
+PREHOOK: Output: default@insert_into5b@ds=1
+POSTHOOK: query: INSERT INTO TABLE insert_into5b PARTITION (ds='1') SELECT * FROM insert_into5a
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@insert_into5a
+POSTHOOK: Output: default@insert_into5b@ds=1
+POSTHOOK: Lineage: insert_into5b PARTITION(ds=1).key SIMPLE [(insert_into5a)insert_into5a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: insert_into5b PARTITION(ds=1).value SIMPLE [(insert_into5a)insert_into5a.FieldSchema(name:value, type:string, comment:null), ]
+PREHOOK: query: SELECT SUM(HASH(c)) FROM (
+ SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into5b
+) t
+PREHOOK: type: QUERY
+PREHOOK: Input: default@insert_into5b
+PREHOOK: Input: default@insert_into5b@ds=1
+PREHOOK: Output: hdfs://### HDFS PATH ###
+POSTHOOK: query: SELECT SUM(HASH(c)) FROM (
+ SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into5b
+) t
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@insert_into5b
+POSTHOOK: Input: default@insert_into5b@ds=1
+POSTHOOK: Output: hdfs://### HDFS PATH ###
+-18626052920
+PREHOOK: query: EXPLAIN INSERT INTO TABLE insert_into5b PARTITION (ds='1')
+ SELECT key, value FROM insert_into5b
+PREHOOK: type: QUERY
+PREHOOK: Input: default@insert_into5b
+PREHOOK: Input: default@insert_into5b@ds=1
+PREHOOK: Output: default@insert_into5b@ds=1
+POSTHOOK: query: EXPLAIN INSERT INTO TABLE insert_into5b PARTITION (ds='1')
+ SELECT key, value FROM insert_into5b
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@insert_into5b
+POSTHOOK: Input: default@insert_into5b@ds=1
+POSTHOOK: Output: default@insert_into5b@ds=1
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: insert_into5b
+ Statistics: Num rows: 20 Data size: 1820 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: int), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 20 Data size: 1820 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 20 Data size: 1820 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.insert_into5b
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), '1' (type: string)
+ outputColumnNames: key, value, ds
+ Statistics: Num rows: 20 Data size: 3520 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ keys: ds (type: string)
+ minReductionHashAggr: 0.95
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ null sort order: z
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-2
+ Dependency Collection
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ partition:
+ ds 1
+ replace: false
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.insert_into5b
+
+ Stage: Stage-3
+ Stats Work
+ Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.insert_into5b
+
+PREHOOK: query: INSERT INTO TABLE insert_into5b PARTITION (ds='1')
+ SELECT key, value FROM insert_into5b
+PREHOOK: type: QUERY
+PREHOOK: Input: default@insert_into5b
+PREHOOK: Input: default@insert_into5b@ds=1
+PREHOOK: Output: default@insert_into5b@ds=1
+POSTHOOK: query: INSERT INTO TABLE insert_into5b PARTITION (ds='1')
+ SELECT key, value FROM insert_into5b
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@insert_into5b
+POSTHOOK: Input: default@insert_into5b@ds=1
+POSTHOOK: Output: default@insert_into5b@ds=1
+POSTHOOK: Lineage: insert_into5b PARTITION(ds=1).key SIMPLE [(insert_into5b)insert_into5b.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: insert_into5b PARTITION(ds=1).value SIMPLE [(insert_into5b)insert_into5b.FieldSchema(name:value, type:string, comment:null), ]
+PREHOOK: query: SELECT SUM(HASH(c)) FROM (
+ SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into5b
+) t
+PREHOOK: type: QUERY
+PREHOOK: Input: default@insert_into5b
+PREHOOK: Input: default@insert_into5b@ds=1
+PREHOOK: Output: hdfs://### HDFS PATH ###
+POSTHOOK: query: SELECT SUM(HASH(c)) FROM (
+ SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into5b
+) t
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@insert_into5b
+POSTHOOK: Input: default@insert_into5b@ds=1
+POSTHOOK: Output: hdfs://### HDFS PATH ###
+-37252105840
+PREHOOK: query: DROP TABLE insert_into5a
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@insert_into5a
+PREHOOK: Output: default@insert_into5a
+POSTHOOK: query: DROP TABLE insert_into5a
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@insert_into5a
+POSTHOOK: Output: default@insert_into5a
diff --git a/ql/src/test/results/clientpositive/llap/insert_into6.q.out b/ql/src/test/results/clientpositive/llap/insert_into6.q.out
new file mode 100644
index 0000000..fabcf41
--- /dev/null
+++ b/ql/src/test/results/clientpositive/llap/insert_into6.q.out
@@ -0,0 +1,356 @@
+PREHOOK: query: DROP TABLE insert_into6a
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: DROP TABLE insert_into6a
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: DROP TABLE insert_into6b
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: DROP TABLE insert_into6b
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: CREATE TABLE insert_into6a (key int, value string) PARTITIONED BY (ds string)
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@insert_into6a
+POSTHOOK: query: CREATE TABLE insert_into6a (key int, value string) PARTITIONED BY (ds string)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@insert_into6a
+PREHOOK: query: CREATE TABLE insert_into6b (key int, value string) PARTITIONED BY (ds string)
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@insert_into6b
+POSTHOOK: query: CREATE TABLE insert_into6b (key int, value string) PARTITIONED BY (ds string)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@insert_into6b
+PREHOOK: query: EXPLAIN INSERT INTO TABLE insert_into6a PARTITION (ds='1')
+ SELECT * FROM src LIMIT 150
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@insert_into6a@ds=1
+POSTHOOK: query: EXPLAIN INSERT INTO TABLE insert_into6a PARTITION (ds='1')
+ SELECT * FROM src LIMIT 150
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@insert_into6a@ds=1
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Limit
+ Number of rows: 150
+ Statistics: Num rows: 150 Data size: 26700 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ null sort order:
+ sort order:
+ Statistics: Num rows: 150 Data size: 26700 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
+ value expressions: _col0 (type: string), _col1 (type: string)
+ Execution mode: vectorized, llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col0 (type: string), VALUE._col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 150 Data size: 26700 Basic stats: COMPLETE Column stats: COMPLETE
+ Limit
+ Number of rows: 150
+ Statistics: Num rows: 150 Data size: 26700 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: UDFToInteger(_col0) (type: int), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 150 Data size: 14250 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 150 Data size: 14250 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.insert_into6a
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), '1' (type: string)
+ outputColumnNames: key, value, ds
+ Statistics: Num rows: 150 Data size: 27000 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ keys: ds (type: string)
+ minReductionHashAggr: 0.99
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ null sort order: z
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reducer 3
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-2
+ Dependency Collection
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ partition:
+ ds 1
+ replace: false
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.insert_into6a
+
+ Stage: Stage-3
+ Stats Work
+ Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.insert_into6a
+
+PREHOOK: query: INSERT INTO TABLE insert_into6a PARTITION (ds='1') SELECT * FROM src LIMIT 150
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@insert_into6a@ds=1
+POSTHOOK: query: INSERT INTO TABLE insert_into6a PARTITION (ds='1') SELECT * FROM src LIMIT 150
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@insert_into6a@ds=1
+POSTHOOK: Lineage: insert_into6a PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: insert_into6a PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: INSERT INTO TABLE insert_into6a PARTITION (ds='2') SELECT * FROM src LIMIT 100
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@insert_into6a@ds=2
+POSTHOOK: query: INSERT INTO TABLE insert_into6a PARTITION (ds='2') SELECT * FROM src LIMIT 100
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@insert_into6a@ds=2
+POSTHOOK: Lineage: insert_into6a PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: insert_into6a PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: SELECT SUM(HASH(c)) FROM (
+ SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into6a
+) t
+PREHOOK: type: QUERY
+PREHOOK: Input: default@insert_into6a
+PREHOOK: Input: default@insert_into6a@ds=1
+PREHOOK: Input: default@insert_into6a@ds=2
+PREHOOK: Output: hdfs://### HDFS PATH ###
+POSTHOOK: query: SELECT SUM(HASH(c)) FROM (
+ SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into6a
+) t
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@insert_into6a
+POSTHOOK: Input: default@insert_into6a@ds=1
+POSTHOOK: Input: default@insert_into6a@ds=2
+POSTHOOK: Output: hdfs://### HDFS PATH ###
+-35226404960
+PREHOOK: query: EXPLAIN INSERT INTO TABLE insert_into6b PARTITION (ds)
+ SELECT * FROM insert_into6a
+PREHOOK: type: QUERY
+PREHOOK: Input: default@insert_into6a
+PREHOOK: Input: default@insert_into6a@ds=1
+PREHOOK: Input: default@insert_into6a@ds=2
+PREHOOK: Output: default@insert_into6b
+POSTHOOK: query: EXPLAIN INSERT INTO TABLE insert_into6b PARTITION (ds)
+ SELECT * FROM insert_into6a
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@insert_into6a
+POSTHOOK: Input: default@insert_into6a@ds=1
+POSTHOOK: Input: default@insert_into6a@ds=2
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: insert_into6a
+ Statistics: Num rows: 250 Data size: 69750 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: int), value (type: string), ds (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 250 Data size: 69750 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 250 Data size: 69750 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.insert_into6b
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string)
+ outputColumnNames: key, value, ds
+ Statistics: Num rows: 250 Data size: 69750 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ keys: ds (type: string)
+ minReductionHashAggr: 0.99
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 2 Data size: 2096 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ null sort order: z
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 2 Data size: 2096 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 2 Data size: 2128 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 2 Data size: 2128 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 2 Data size: 2128 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-2
+ Dependency Collection
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ partition:
+ ds
+ replace: false
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.insert_into6b
+
+ Stage: Stage-3
+ Stats Work
+ Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.insert_into6b
+
+PREHOOK: query: INSERT INTO TABLE insert_into6b PARTITION (ds) SELECT * FROM insert_into6a
+PREHOOK: type: QUERY
+PREHOOK: Input: default@insert_into6a
+PREHOOK: Input: default@insert_into6a@ds=1
+PREHOOK: Input: default@insert_into6a@ds=2
+PREHOOK: Output: default@insert_into6b
+POSTHOOK: query: INSERT INTO TABLE insert_into6b PARTITION (ds) SELECT * FROM insert_into6a
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@insert_into6a
+POSTHOOK: Input: default@insert_into6a@ds=1
+POSTHOOK: Input: default@insert_into6a@ds=2
+POSTHOOK: Output: default@insert_into6b@ds=1
+POSTHOOK: Output: default@insert_into6b@ds=2
+POSTHOOK: Lineage: insert_into6b PARTITION(ds=1).key SIMPLE [(insert_into6a)insert_into6a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: insert_into6b PARTITION(ds=1).value SIMPLE [(insert_into6a)insert_into6a.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: insert_into6b PARTITION(ds=2).key SIMPLE [(insert_into6a)insert_into6a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: insert_into6b PARTITION(ds=2).value SIMPLE [(insert_into6a)insert_into6a.FieldSchema(name:value, type:string, comment:null), ]
+PREHOOK: query: SELECT SUM(HASH(c)) FROM (
+ SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into6b
+) t
+PREHOOK: type: QUERY
+PREHOOK: Input: default@insert_into6b
+PREHOOK: Input: default@insert_into6b@ds=1
+PREHOOK: Input: default@insert_into6b@ds=2
+PREHOOK: Output: hdfs://### HDFS PATH ###
+POSTHOOK: query: SELECT SUM(HASH(c)) FROM (
+ SELECT TRANSFORM(*) USING 'tr \t _' AS (c) FROM insert_into6b
+) t
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@insert_into6b
+POSTHOOK: Input: default@insert_into6b@ds=1
+POSTHOOK: Input: default@insert_into6b@ds=2
+POSTHOOK: Output: hdfs://### HDFS PATH ###
+-35226404960
+PREHOOK: query: SHOW PARTITIONS insert_into6b
+PREHOOK: type: SHOWPARTITIONS
+PREHOOK: Input: default@insert_into6b
+POSTHOOK: query: SHOW PARTITIONS insert_into6b
+POSTHOOK: type: SHOWPARTITIONS
+POSTHOOK: Input: default@insert_into6b
+ds=1
+ds=2
+PREHOOK: query: DROP TABLE insert_into6a
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@insert_into6a
+PREHOOK: Output: default@insert_into6a
+POSTHOOK: query: DROP TABLE insert_into6a
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@insert_into6a
+POSTHOOK: Output: default@insert_into6a
+PREHOOK: query: DROP TABLE insert_into6b
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@insert_into6b
+PREHOOK: Output: default@insert_into6b
+POSTHOOK: query: DROP TABLE insert_into6b
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@insert_into6b
+POSTHOOK: Output: default@insert_into6b
diff --git a/ql/src/test/results/clientpositive/load_binary_data.q.out b/ql/src/test/results/clientpositive/llap/load_binary_data.q.out
similarity index 96%
rename from ql/src/test/results/clientpositive/load_binary_data.q.out
rename to ql/src/test/results/clientpositive/llap/load_binary_data.q.out
index b0d5c63..d3c0d29 100644
Binary files a/ql/src/test/results/clientpositive/load_binary_data.q.out and b/ql/src/test/results/clientpositive/llap/load_binary_data.q.out differ
diff --git a/ql/src/test/results/clientpositive/macro_1.q.out b/ql/src/test/results/clientpositive/llap/macro_1.q.out
similarity index 91%
rename from ql/src/test/results/clientpositive/macro_1.q.out
rename to ql/src/test/results/clientpositive/llap/macro_1.q.out
index 28230f9..44d6cca 100644
--- a/ql/src/test/results/clientpositive/macro_1.q.out
+++ b/ql/src/test/results/clientpositive/llap/macro_1.q.out
@@ -38,13 +38,13 @@ PREHOOK: query: SELECT
FROM macro_test
PREHOOK: type: QUERY
PREHOOK: Input: default@macro_test
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: SELECT
CONCAT(STRING_LEN(x), ":", STRING_LEN_PLUS_ONE(x), ":", STRING_LEN_PLUS_TWO(x)) a
FROM macro_test
POSTHOOK: type: QUERY
POSTHOOK: Input: default@macro_test
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
2:3:4
1:2:3
3:4:5
@@ -54,14 +54,14 @@ FROM macro_test
sort by a
PREHOOK: type: QUERY
PREHOOK: Input: default@macro_test
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: SELECT
CONCAT(STRING_LEN(x), ":", STRING_LEN_PLUS_ONE(x), ":", STRING_LEN_PLUS_TWO(x)) a
FROM macro_test
sort by a
POSTHOOK: type: QUERY
POSTHOOK: Input: default@macro_test
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
1:2:3
2:3:4
3:4:5
@@ -71,14 +71,14 @@ FROM macro_test
sort by a desc
PREHOOK: type: QUERY
PREHOOK: Input: default@macro_test
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: SELECT
CONCAT(STRING_LEN(x), ":", STRING_LEN_PLUS_ONE(x), ":", STRING_LEN_PLUS_TWO(x)) a
FROM macro_test
sort by a desc
POSTHOOK: type: QUERY
POSTHOOK: Input: default@macro_test
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
3:4:5
2:3:4
1:2:3
diff --git a/ql/src/test/results/clientpositive/macro_duplicate.q.out b/ql/src/test/results/clientpositive/llap/macro_duplicate.q.out
similarity index 96%
rename from ql/src/test/results/clientpositive/macro_duplicate.q.out
rename to ql/src/test/results/clientpositive/llap/macro_duplicate.q.out
index 9598126..ccdf735 100644
--- a/ql/src/test/results/clientpositive/macro_duplicate.q.out
+++ b/ql/src/test/results/clientpositive/llap/macro_duplicate.q.out
@@ -47,10 +47,10 @@ POSTHOOK: Output: database:default
PREHOOK: query: select math_square(a), math_square(b),factorial(a), factorial(b), math_add(a), math_add(b),int(c) from macro_testing order by int(c)
PREHOOK: type: QUERY
PREHOOK: Input: default@macro_testing
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: select math_square(a), math_square(b),factorial(a), factorial(b), math_add(a), math_add(b),int(c) from macro_testing order by int(c)
POSTHOOK: type: QUERY
POSTHOOK: Input: default@macro_testing
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
1 4 1 2 2 4 3
16 25 24 120 8 10 6
diff --git a/ql/src/test/results/clientpositive/mapreduce3.q.out b/ql/src/test/results/clientpositive/llap/mapreduce3.q.out
similarity index 69%
rename from ql/src/test/results/clientpositive/mapreduce3.q.out
rename to ql/src/test/results/clientpositive/llap/mapreduce3.q.out
index 9c0157c..f691d40 100644
--- a/ql/src/test/results/clientpositive/mapreduce3.q.out
+++ b/ql/src/test/results/clientpositive/llap/mapreduce3.q.out
@@ -26,63 +26,89 @@ POSTHOOK: Input: default@src
POSTHOOK: Output: default@dest1_n23
STAGE DEPENDENCIES:
Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
- Stage-2 depends on stages: Stage-0, Stage-3
- Stage-3 depends on stages: Stage-1
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
STAGE PLANS:
Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: key (type: string), UDFToInteger((key / 10)) (type: int), UDFToInteger((key % 10)) (type: int), value (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE
- Transform Operator
- command: cat
- output info:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col3 (type: string), _col0 (type: string)
- null sort order: zz
- sort order: ++
- Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)
- Reduce Operator Tree:
- Select Operator
- expressions: UDFToInteger(VALUE._col0) (type: int), UDFToInteger(VALUE._col1) (type: int), UDFToInteger(VALUE._col2) (type: int), VALUE._col3 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 500 Data size: 51500 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 500 Data size: 51500 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.dest1_n23
- Select Operator
- expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: string)
- outputColumnNames: key, ten, one, value
- Statistics: Num rows: 500 Data size: 51500 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: compute_stats(key, 'hll'), compute_stats(ten, 'hll'), compute_stats(one, 'hll'), compute_stats(value, 'hll')
- minReductionHashAggr: 0.99
- mode: hash
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string), UDFToInteger((key / 10)) (type: int), UDFToInteger((key % 10)) (type: int), value (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE
+ Transform Operator
+ command: cat
+ output info:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col3 (type: string), _col0 (type: string)
+ null sort order: zz
+ sort order: ++
+ Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Select Operator
+ expressions: UDFToInteger(VALUE._col0) (type: int), UDFToInteger(VALUE._col1) (type: int), UDFToInteger(VALUE._col2) (type: int), VALUE._col3 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 500 Data size: 51500 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 500 Data size: 51500 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest1_n23
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: string)
+ outputColumnNames: key, ten, one, value
+ Statistics: Num rows: 500 Data size: 51500 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(ten, 'hll'), compute_stats(one, 'hll'), compute_stats(value, 'hll')
+ minReductionHashAggr: 0.99
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ null sort order:
+ sort order:
+ Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reducer 3
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-2
+ Dependency Collection
Stage: Stage-0
Move Operator
@@ -94,7 +120,7 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest1_n23
- Stage: Stage-2
+ Stage: Stage-3
Stats Work
Basic Stats Work:
Column Stats Desc:
@@ -102,30 +128,6 @@ STAGE PLANS:
Column Types: int, int, int, string
Table: default.dest1_n23
- Stage: Stage-3
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- null sort order:
- sort order:
- Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
- Execution mode: vectorized
- Reduce Operator Tree:
- Group By Operator
- aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3)
- mode: mergepartial
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
PREHOOK: query: FROM src
INSERT OVERWRITE TABLE dest1_n23
MAP src.key, CAST(src.key / 10 AS INT), CAST(src.key % 10 AS INT), src.value
@@ -149,11 +151,11 @@ POSTHOOK: Lineage: dest1_n23.value SCRIPT [(src)src.FieldSchema(name:key, type:s
PREHOOK: query: SELECT dest1_n23.* FROM dest1_n23
PREHOOK: type: QUERY
PREHOOK: Input: default@dest1_n23
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: SELECT dest1_n23.* FROM dest1_n23
POSTHOOK: type: QUERY
POSTHOOK: Input: default@dest1_n23
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
0 0 0 val_0
0 0 0 val_0
0 0 0 val_0
diff --git a/ql/src/test/results/clientpositive/mapreduce4.q.out b/ql/src/test/results/clientpositive/llap/mapreduce4.q.out
similarity index 69%
rename from ql/src/test/results/clientpositive/mapreduce4.q.out
rename to ql/src/test/results/clientpositive/llap/mapreduce4.q.out
index a606df0..12882a8 100644
--- a/ql/src/test/results/clientpositive/mapreduce4.q.out
+++ b/ql/src/test/results/clientpositive/llap/mapreduce4.q.out
@@ -28,64 +28,90 @@ POSTHOOK: Input: default@src
POSTHOOK: Output: default@dest1_n93
STAGE DEPENDENCIES:
Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
- Stage-2 depends on stages: Stage-0, Stage-3
- Stage-3 depends on stages: Stage-1
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
STAGE PLANS:
Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: key (type: string), UDFToInteger((key / 10)) (type: int), UDFToInteger((key % 10)) (type: int), value (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE
- Transform Operator
- command: cat
- output info:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col1 (type: string), _col2 (type: string)
- null sort order: zz
- sort order: -+
- Map-reduce partition columns: _col3 (type: string), _col0 (type: string)
- Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)
- Reduce Operator Tree:
- Select Operator
- expressions: UDFToInteger(VALUE._col0) (type: int), UDFToInteger(VALUE._col1) (type: int), UDFToInteger(VALUE._col2) (type: int), VALUE._col3 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 500 Data size: 51500 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 500 Data size: 51500 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.dest1_n93
- Select Operator
- expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: string)
- outputColumnNames: key, ten, one, value
- Statistics: Num rows: 500 Data size: 51500 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: compute_stats(key, 'hll'), compute_stats(ten, 'hll'), compute_stats(one, 'hll'), compute_stats(value, 'hll')
- minReductionHashAggr: 0.99
- mode: hash
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string), UDFToInteger((key / 10)) (type: int), UDFToInteger((key % 10)) (type: int), value (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE
+ Transform Operator
+ command: cat
+ output info:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col1 (type: string), _col2 (type: string)
+ null sort order: zz
+ sort order: -+
+ Map-reduce partition columns: _col3 (type: string), _col0 (type: string)
+ Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Select Operator
+ expressions: UDFToInteger(VALUE._col0) (type: int), UDFToInteger(VALUE._col1) (type: int), UDFToInteger(VALUE._col2) (type: int), VALUE._col3 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 500 Data size: 51500 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 500 Data size: 51500 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest1_n93
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: string)
+ outputColumnNames: key, ten, one, value
+ Statistics: Num rows: 500 Data size: 51500 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(ten, 'hll'), compute_stats(one, 'hll'), compute_stats(value, 'hll')
+ minReductionHashAggr: 0.99
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ null sort order:
+ sort order:
+ Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reducer 3
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-2
+ Dependency Collection
Stage: Stage-0
Move Operator
@@ -97,7 +123,7 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest1_n93
- Stage: Stage-2
+ Stage: Stage-3
Stats Work
Basic Stats Work:
Column Stats Desc:
@@ -105,30 +131,6 @@ STAGE PLANS:
Column Types: int, int, int, string
Table: default.dest1_n93
- Stage: Stage-3
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- null sort order:
- sort order:
- Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
- Execution mode: vectorized
- Reduce Operator Tree:
- Group By Operator
- aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3)
- mode: mergepartial
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
PREHOOK: query: FROM src
INSERT OVERWRITE TABLE dest1_n93
MAP src.key, CAST(src.key / 10 AS INT), CAST(src.key % 10 AS INT), src.value
@@ -154,11 +156,11 @@ POSTHOOK: Lineage: dest1_n93.value SCRIPT [(src)src.FieldSchema(name:key, type:s
PREHOOK: query: SELECT dest1_n93.* FROM dest1_n93
PREHOOK: type: QUERY
PREHOOK: Input: default@dest1_n93
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: SELECT dest1_n93.* FROM dest1_n93
POSTHOOK: type: QUERY
POSTHOOK: Input: default@dest1_n93
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
90 9 0 val_90
90 9 0 val_90
90 9 0 val_90
diff --git a/ql/src/test/results/clientpositive/mapreduce7.q.out b/ql/src/test/results/clientpositive/llap/mapreduce7.q.out
similarity index 76%
rename from ql/src/test/results/clientpositive/mapreduce7.q.out
rename to ql/src/test/results/clientpositive/llap/mapreduce7.q.out
index ab369e6..10d42ce 100644
--- a/ql/src/test/results/clientpositive/mapreduce7.q.out
+++ b/ql/src/test/results/clientpositive/llap/mapreduce7.q.out
@@ -26,63 +26,89 @@ POSTHOOK: Input: default@src
POSTHOOK: Output: default@dest1_n37
STAGE DEPENDENCIES:
Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
- Stage-2 depends on stages: Stage-0, Stage-3
- Stage-3 depends on stages: Stage-1
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
STAGE PLANS:
Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: key (type: string), value (type: string), key (type: string), UDFToInteger((key / 10)) (type: int), UDFToInteger((key % 10)) (type: int), value (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 500 Data size: 182000 Basic stats: COMPLETE Column stats: COMPLETE
- Transform Operator
- command: cat
- output info:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Statistics: Num rows: 500 Data size: 182000 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col5 (type: string), _col2 (type: string)
- null sort order: zz
- sort order: ++
- Statistics: Num rows: 500 Data size: 182000 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string)
- Reduce Operator Tree:
- Select Operator
- expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), UDFToInteger(VALUE._col2) (type: int), UDFToInteger(VALUE._col3) (type: int), UDFToInteger(VALUE._col4) (type: int), VALUE._col5 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 500 Data size: 140500 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 500 Data size: 140500 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.dest1_n37
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: string)
- outputColumnNames: k, v, key, ten, one, value
- Statistics: Num rows: 500 Data size: 140500 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: compute_stats(k, 'hll'), compute_stats(v, 'hll'), compute_stats(key, 'hll'), compute_stats(ten, 'hll'), compute_stats(one, 'hll'), compute_stats(value, 'hll')
- minReductionHashAggr: 0.99
- mode: hash
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 1 Data size: 2592 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string), value (type: string), key (type: string), UDFToInteger((key / 10)) (type: int), UDFToInteger((key % 10)) (type: int), value (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 500 Data size: 182000 Basic stats: COMPLETE Column stats: COMPLETE
+ Transform Operator
+ command: cat
+ output info:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Statistics: Num rows: 500 Data size: 182000 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col5 (type: string), _col2 (type: string)
+ null sort order: zz
+ sort order: ++
+ Statistics: Num rows: 500 Data size: 182000 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string)
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), UDFToInteger(VALUE._col2) (type: int), UDFToInteger(VALUE._col3) (type: int), UDFToInteger(VALUE._col4) (type: int), VALUE._col5 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 500 Data size: 140500 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 500 Data size: 140500 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest1_n37
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: string)
+ outputColumnNames: k, v, key, ten, one, value
+ Statistics: Num rows: 500 Data size: 140500 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(k, 'hll'), compute_stats(v, 'hll'), compute_stats(key, 'hll'), compute_stats(ten, 'hll'), compute_stats(one, 'hll'), compute_stats(value, 'hll')
+ minReductionHashAggr: 0.99
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 1 Data size: 2592 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ null sort order:
+ sort order:
+ Statistics: Num rows: 1 Data size: 2592 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col4 (ty [...]
+ Reducer 3
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4), compute_stats(VALUE._col5)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 1 Data size: 2640 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 2640 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-2
+ Dependency Collection
Stage: Stage-0
Move Operator
@@ -94,7 +120,7 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest1_n37
- Stage: Stage-2
+ Stage: Stage-3
Stats Work
Basic Stats Work:
Column Stats Desc:
@@ -102,30 +128,6 @@ STAGE PLANS:
Column Types: string, string, int, int, int, string
Table: default.dest1_n37
- Stage: Stage-3
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- null sort order:
- sort order:
- Statistics: Num rows: 1 Data size: 2592 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col4 (type: stru [...]
- Execution mode: vectorized
- Reduce Operator Tree:
- Group By Operator
- aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4), compute_stats(VALUE._col5)
- mode: mergepartial
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 1 Data size: 2640 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 2640 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
PREHOOK: query: FROM src
INSERT OVERWRITE TABLE dest1_n37
MAP src.*, src.key, CAST(src.key / 10 AS INT), CAST(src.key % 10 AS INT), src.value
@@ -151,11 +153,11 @@ POSTHOOK: Lineage: dest1_n37.value SCRIPT [(src)src.FieldSchema(name:key, type:s
PREHOOK: query: SELECT dest1_n37.* FROM dest1_n37
PREHOOK: type: QUERY
PREHOOK: Input: default@dest1_n37
-#### A masked pattern was here ####
+PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: SELECT dest1_n37.* FROM dest1_n37
POSTHOOK: type: QUERY
POSTHOOK: Input: default@dest1_n37
-#### A masked pattern was here ####
+POSTHOOK: Output: hdfs://### HDFS PATH ###
0 val_0 0 0 0 val_0
0 val_0 0 0 0 val_0
0 val_0 0 0 0 val_0
diff --git a/ql/src/test/results/clientpositive/mapreduce8.q.out b/ql/src/test/results/clientpositive/llap/mapreduce8.q.out
similarity index 75%
rename from ql/src/test/results/clientpositive/mapreduce8.q.out
rename to ql/src/test/results/clientpositive/llap/mapreduce8.q.out
index d00ede8..1a38974 100644
--- a/ql/src/test/results/clientpositive/mapreduce8.q.out
+++ b/ql/src/test/results/clientpositive/llap/mapreduce8.q.out
@@ -28,64 +28,90 @@ POSTHOOK: Input: default@src
POSTHOOK: Output: default@dest1_n158
STAGE DEPENDENCIES:
Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
- Stage-2 depends on stages: Stage-0, Stage-3
- Stage-3 depends on stages: Stage-1
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
STAGE PLANS:
Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: key (type: string), value (type: string), key (type: string), UDFToInteger((key / 10)) (type: int), UDFToInteger((key % 10)) (type: int), value (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 500 Data size: 182000 Basic stats: COMPLETE Column stats: COMPLETE
- Transform Operator
- command: cat
- output info:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Statistics: Num rows: 500 Data size: 182000 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col5 (type: string), _col2 (type: string)
- null sort order: zz
- sort order: ++
- Map-reduce partition columns: rand(3) (type: double)
- Statistics: Num rows: 500 Data size: 182000 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string)
- Reduce Operator Tree:
- Select Operator
- expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), UDFToInteger(VALUE._col2) (type: int), UDFToInteger(VALUE._col3) (type: int), UDFToInteger(VALUE._col4) (type: int), VALUE._col5 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 500 Data size: 140500 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 500 Data size: 140500 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.dest1_n158
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: string)
- outputColumnNames: k, v, key, ten, one, value
- Statistics: Num rows: 500 Data size: 140500 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: compute_stats(k, 'hll'), compute_stats(v, 'hll'), compute_stats(key, 'hll'), compute_stats(ten, 'hll'), compute_stats(one, 'hll'), compute_stats(value, 'hll')
- minReductionHashAggr: 0.99
- mode: hash
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 1 Data size: 2592 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
... 9415 lines suppressed ...