You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by pr...@apache.org on 2016/08/29 21:16:23 UTC
hive git commit: HIVE-14627: Improvements to MiniMr tests (Prasanth
Jayachandran reviewed by Siddharth Seth)
Repository: hive
Updated Branches:
refs/heads/master 673f3263a -> b80bcd058
HIVE-14627: Improvements to MiniMr tests (Prasanth Jayachandran reviewed by Siddharth Seth)
Project: http://git-wip-us.apache.org/repos/asf/hive/repo
Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/b80bcd05
Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/b80bcd05
Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/b80bcd05
Branch: refs/heads/master
Commit: b80bcd0583cfd069e2ca77a393c191bef8eb5eb3
Parents: 673f326
Author: Prasanth Jayachandran <pr...@apache.org>
Authored: Mon Aug 29 14:16:09 2016 -0700
Committer: Prasanth Jayachandran <pr...@apache.org>
Committed: Mon Aug 29 14:16:09 2016 -0700
----------------------------------------------------------------------
data/scripts/q_test_init_for_minimr.sql | 48 ++++++++++++++++++++
.../test/resources/testconfiguration.properties | 9 +---
.../hadoop/hive/cli/control/CliConfigs.java | 2 +-
.../test/results/clientpositive/bucket4.q.out | 20 ++++----
.../test/results/clientpositive/bucket5.q.out | 28 ++++++------
.../test/results/clientpositive/bucket6.q.out | 10 ++--
.../results/clientpositive/bucket_many.q.out | 20 ++++----
.../disable_merge_for_bucketing.q.out | 20 ++++----
.../test/results/clientpositive/groupby2.q.out | 16 +++----
.../clientpositive/index_bitmap_auto.q.out | 4 --
.../infer_bucket_sort_dyn_part.q.out | 14 +++---
.../infer_bucket_sort_map_operators.q.out | 12 ++---
.../infer_bucket_sort_num_buckets.q.out | 10 ++--
.../infer_bucket_sort_reducers_power_two.q.out | 4 +-
ql/src/test/results/clientpositive/join1.q.out | 22 ++++-----
.../clientpositive/list_bucket_dml_10.q.out | 16 +++----
.../clientpositive/orc_merge_diff_fs.q.out | 18 ++++----
.../clientpositive/reduce_deduplicate.q.out | 20 ++++----
18 files changed, 159 insertions(+), 134 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/hive/blob/b80bcd05/data/scripts/q_test_init_for_minimr.sql
----------------------------------------------------------------------
diff --git a/data/scripts/q_test_init_for_minimr.sql b/data/scripts/q_test_init_for_minimr.sql
new file mode 100644
index 0000000..ab2e1d7
--- /dev/null
+++ b/data/scripts/q_test_init_for_minimr.sql
@@ -0,0 +1,48 @@
+--
+-- Table src
+--
+DROP TABLE IF EXISTS src;
+
+CREATE TABLE src (key STRING COMMENT 'default', value STRING COMMENT 'default') STORED AS TEXTFILE;
+
+LOAD DATA LOCAL INPATH "${hiveconf:test.data.dir}/kv1.txt" INTO TABLE src;
+
+--
+-- Table srcpart
+--
+DROP TABLE IF EXISTS srcpart;
+
+CREATE TABLE srcpart (key STRING COMMENT 'default', value STRING COMMENT 'default')
+PARTITIONED BY (ds STRING, hr STRING)
+STORED AS TEXTFILE;
+
+LOAD DATA LOCAL INPATH "${hiveconf:test.data.dir}/kv1.txt"
+OVERWRITE INTO TABLE srcpart PARTITION (ds="2008-04-08", hr="11");
+
+LOAD DATA LOCAL INPATH "${hiveconf:test.data.dir}/kv1.txt"
+OVERWRITE INTO TABLE srcpart PARTITION (ds="2008-04-08", hr="12");
+
+LOAD DATA LOCAL INPATH "${hiveconf:test.data.dir}/kv1.txt"
+OVERWRITE INTO TABLE srcpart PARTITION (ds="2008-04-09", hr="11");
+
+LOAD DATA LOCAL INPATH "${hiveconf:test.data.dir}/kv1.txt"
+OVERWRITE INTO TABLE srcpart PARTITION (ds="2008-04-09", hr="12");
+
+--
+-- Table part
+--
+drop table if exists part;
+
+CREATE TABLE part(
+ p_partkey INT,
+ p_name STRING,
+ p_mfgr STRING,
+ p_brand STRING,
+ p_type STRING,
+ p_size INT,
+ p_container STRING,
+ p_retailprice DOUBLE,
+ p_comment STRING
+);
+
+LOAD DATA LOCAL INPATH '../../data/files/part_tiny.txt' overwrite into table part;
http://git-wip-us.apache.org/repos/asf/hive/blob/b80bcd05/itests/src/test/resources/testconfiguration.properties
----------------------------------------------------------------------
diff --git a/itests/src/test/resources/testconfiguration.properties b/itests/src/test/resources/testconfiguration.properties
index 8f996d1..d5ee9ed 100644
--- a/itests/src/test/resources/testconfiguration.properties
+++ b/itests/src/test/resources/testconfiguration.properties
@@ -34,7 +34,6 @@ minimr.query.files=auto_sortmerge_join_16.q,\
load_hdfs_file_with_space_in_the_name.q,\
non_native_window_udf.q, \
orc_merge_diff_fs.q,\
- optrstat_groupby.q,\
parallel_orderby.q,\
quotedid_smb.q,\
reduce_deduplicate.q,\
@@ -45,14 +44,11 @@ minimr.query.files=auto_sortmerge_join_16.q,\
scriptfile1.q,\
scriptfile1_win.q,\
skewjoin_onesideskew.q,\
- stats_counter.q,\
- stats_counter_partitioned.q,\
table_nonprintable.q,\
temp_table_external.q,\
truncate_column_buckets.q,\
uber_reduce.q,\
- udf_using.q,\
- orc_mr_pathalias.q
+ udf_using.q
# These tests are disabled for minimr
# ql_rewrite_gbtoidx.q,\
@@ -248,8 +244,6 @@ minillap.shared.query.files=acid_globallimit.q,\
selectDistinctStar.q,\
select_dummy_source.q,\
skewjoin.q,\
- stats_counter.q,\
- stats_counter_partitioned.q,\
stats_noscan_1.q,\
stats_only_null.q,\
subquery_exists.q,\
@@ -1334,7 +1328,6 @@ miniSparkOnYarn.query.files=auto_sortmerge_join_16.q,\
list_bucket_dml_10.q,\
load_fs2.q,\
load_hdfs_file_with_space_in_the_name.q,\
- optrstat_groupby.q,\
orc_merge1.q,\
orc_merge2.q,\
orc_merge3.q,\
http://git-wip-us.apache.org/repos/asf/hive/blob/b80bcd05/itests/util/src/main/java/org/apache/hadoop/hive/cli/control/CliConfigs.java
----------------------------------------------------------------------
diff --git a/itests/util/src/main/java/org/apache/hadoop/hive/cli/control/CliConfigs.java b/itests/util/src/main/java/org/apache/hadoop/hive/cli/control/CliConfigs.java
index 319a205..1a3583d 100644
--- a/itests/util/src/main/java/org/apache/hadoop/hive/cli/control/CliConfigs.java
+++ b/itests/util/src/main/java/org/apache/hadoop/hive/cli/control/CliConfigs.java
@@ -97,7 +97,7 @@ public class CliConfigs {
setResultsDir("ql/src/test/results/clientpositive");
setLogDir("itests/qtest/target/qfile-results/clientpositive");
- setInitScript("q_test_init.sql");
+ setInitScript("q_test_init_for_minimr.sql");
setCleanupScript("q_test_cleanup.sql");
setHiveConfDir("");
http://git-wip-us.apache.org/repos/asf/hive/blob/b80bcd05/ql/src/test/results/clientpositive/bucket4.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/bucket4.q.out b/ql/src/test/results/clientpositive/bucket4.q.out
index ec28d09..d06c7ed 100644
--- a/ql/src/test/results/clientpositive/bucket4.q.out
+++ b/ql/src/test/results/clientpositive/bucket4.q.out
@@ -25,18 +25,18 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: UDFToInteger(_col0) (type: int)
null sort order: a
sort order: +
Map-reduce partition columns: UDFToInteger(_col0) (type: int)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
tag: -1
value expressions: _col0 (type: string), _col1 (type: string)
auto parallelism: false
@@ -49,7 +49,6 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -57,8 +56,8 @@ STAGE PLANS:
#### A masked pattern was here ####
name default.src
numFiles 1
- numRows 500
- rawDataSize 5312
+ numRows 0
+ rawDataSize 0
serialization.ddl struct src { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -69,7 +68,6 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -77,8 +75,8 @@ STAGE PLANS:
#### A masked pattern was here ####
name default.src
numFiles 1
- numRows 500
- rawDataSize 5312
+ numRows 0
+ rawDataSize 0
serialization.ddl struct src { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -94,13 +92,13 @@ STAGE PLANS:
Select Operator
expressions: UDFToInteger(VALUE._col0) (type: int), VALUE._col1 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
GlobalTableId: 1
#### A masked pattern was here ####
NumFilesPerFileSink: 2
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
#### A masked pattern was here ####
table:
input format: org.apache.hadoop.mapred.TextInputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/b80bcd05/ql/src/test/results/clientpositive/bucket5.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/bucket5.q.out b/ql/src/test/results/clientpositive/bucket5.q.out
index bd1013a..30994a7 100644
--- a/ql/src/test/results/clientpositive/bucket5.q.out
+++ b/ql/src/test/results/clientpositive/bucket5.q.out
@@ -49,25 +49,25 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: UDFToInteger(_col0) (type: int)
null sort order: a
sort order: +
Map-reduce partition columns: UDFToInteger(_col0) (type: int)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
tag: -1
value expressions: _col0 (type: string), _col1 (type: string)
auto parallelism: false
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
GlobalTableId: 0
@@ -94,7 +94,6 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -102,8 +101,8 @@ STAGE PLANS:
#### A masked pattern was here ####
name default.src
numFiles 1
- numRows 500
- rawDataSize 5312
+ numRows 0
+ rawDataSize 0
serialization.ddl struct src { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -114,7 +113,6 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -122,8 +120,8 @@ STAGE PLANS:
#### A masked pattern was here ####
name default.src
numFiles 1
- numRows 500
- rawDataSize 5312
+ numRows 0
+ rawDataSize 0
serialization.ddl struct src { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -139,13 +137,13 @@ STAGE PLANS:
Select Operator
expressions: UDFToInteger(VALUE._col0) (type: int), VALUE._col1 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
GlobalTableId: 1
#### A masked pattern was here ####
NumFilesPerFileSink: 1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
#### A masked pattern was here ####
table:
input format: org.apache.hadoop.mapred.TextInputFormat
@@ -217,7 +215,7 @@ STAGE PLANS:
null sort order: a
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
tag: -1
value expressions: _col1 (type: string)
auto parallelism: false
@@ -251,13 +249,13 @@ STAGE PLANS:
Select Operator
expressions: UDFToInteger(KEY.reducesinkkey0) (type: int), VALUE._col0 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
GlobalTableId: 2
#### A masked pattern was here ####
NumFilesPerFileSink: 1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
#### A masked pattern was here ####
table:
input format: org.apache.hadoop.mapred.TextInputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/b80bcd05/ql/src/test/results/clientpositive/bucket6.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/bucket6.q.out b/ql/src/test/results/clientpositive/bucket6.q.out
index 72fec49..c7f696f 100644
--- a/ql/src/test/results/clientpositive/bucket6.q.out
+++ b/ql/src/test/results/clientpositive/bucket6.q.out
@@ -23,25 +23,25 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: srcpart
- Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 116 Data size: 23248 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 116 Data size: 23248 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 116 Data size: 23248 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string)
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 116 Data size: 23248 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 116 Data size: 23248 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/b80bcd05/ql/src/test/results/clientpositive/bucket_many.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/bucket_many.q.out b/ql/src/test/results/clientpositive/bucket_many.q.out
index 87954e0..d6dda03 100644
--- a/ql/src/test/results/clientpositive/bucket_many.q.out
+++ b/ql/src/test/results/clientpositive/bucket_many.q.out
@@ -25,17 +25,17 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
null sort order:
sort order:
Map-reduce partition columns: UDFToInteger(_col0) (type: int)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
tag: -1
value expressions: _col0 (type: string), _col1 (type: string)
auto parallelism: false
@@ -48,7 +48,6 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -56,8 +55,8 @@ STAGE PLANS:
#### A masked pattern was here ####
name default.src
numFiles 1
- numRows 500
- rawDataSize 5312
+ numRows 0
+ rawDataSize 0
serialization.ddl struct src { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -68,7 +67,6 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -76,8 +74,8 @@ STAGE PLANS:
#### A masked pattern was here ####
name default.src
numFiles 1
- numRows 500
- rawDataSize 5312
+ numRows 0
+ rawDataSize 0
serialization.ddl struct src { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -93,13 +91,13 @@ STAGE PLANS:
Select Operator
expressions: UDFToInteger(VALUE._col0) (type: int), VALUE._col1 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
GlobalTableId: 1
#### A masked pattern was here ####
NumFilesPerFileSink: 16
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
#### A masked pattern was here ####
table:
input format: org.apache.hadoop.mapred.TextInputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/b80bcd05/ql/src/test/results/clientpositive/disable_merge_for_bucketing.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/disable_merge_for_bucketing.q.out b/ql/src/test/results/clientpositive/disable_merge_for_bucketing.q.out
index ba7c640..34a261c 100644
--- a/ql/src/test/results/clientpositive/disable_merge_for_bucketing.q.out
+++ b/ql/src/test/results/clientpositive/disable_merge_for_bucketing.q.out
@@ -25,17 +25,17 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
null sort order:
sort order:
Map-reduce partition columns: UDFToInteger(_col0) (type: int)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
tag: -1
value expressions: _col0 (type: string), _col1 (type: string)
auto parallelism: false
@@ -48,7 +48,6 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -56,8 +55,8 @@ STAGE PLANS:
#### A masked pattern was here ####
name default.src
numFiles 1
- numRows 500
- rawDataSize 5312
+ numRows 0
+ rawDataSize 0
serialization.ddl struct src { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -68,7 +67,6 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -76,8 +74,8 @@ STAGE PLANS:
#### A masked pattern was here ####
name default.src
numFiles 1
- numRows 500
- rawDataSize 5312
+ numRows 0
+ rawDataSize 0
serialization.ddl struct src { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -93,13 +91,13 @@ STAGE PLANS:
Select Operator
expressions: UDFToInteger(VALUE._col0) (type: int), VALUE._col1 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
GlobalTableId: 1
#### A masked pattern was here ####
NumFilesPerFileSink: 2
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
#### A masked pattern was here ####
table:
input format: org.apache.hadoop.mapred.TextInputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/b80bcd05/ql/src/test/results/clientpositive/groupby2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/groupby2.q.out b/ql/src/test/results/clientpositive/groupby2.q.out
index 4ecb807..428ca67 100644
--- a/ql/src/test/results/clientpositive/groupby2.q.out
+++ b/ql/src/test/results/clientpositive/groupby2.q.out
@@ -26,23 +26,23 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: substr(key, 1, 1) (type: string), substr(value, 5) (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
Reduce Operator Tree:
Group By Operator
aggregations: count(DISTINCT KEY._col1:0._col0), sum(KEY._col1:0._col0)
keys: KEY._col0 (type: string)
mode: partial1
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
@@ -58,7 +58,7 @@ STAGE PLANS:
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint), _col2 (type: double)
Reduce Operator Tree:
Group By Operator
@@ -66,14 +66,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: final
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 14 Data size: 2805 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), concat(_col0, _col2) (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 14 Data size: 2805 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 14 Data size: 2805 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/b80bcd05/ql/src/test/results/clientpositive/index_bitmap_auto.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/index_bitmap_auto.q.out b/ql/src/test/results/clientpositive/index_bitmap_auto.q.out
index bfab87f..7546dd3 100644
--- a/ql/src/test/results/clientpositive/index_bitmap_auto.q.out
+++ b/ql/src/test/results/clientpositive/index_bitmap_auto.q.out
@@ -262,14 +262,10 @@ POSTHOOK: Input: default@src
0 val_0
PREHOOK: query: SELECT key, value FROM src WHERE key=0 AND value = "val_0"
PREHOOK: type: QUERY
-PREHOOK: Input: default@default__src_src1_index__
-PREHOOK: Input: default@default__src_src2_index__
PREHOOK: Input: default@src
#### A masked pattern was here ####
POSTHOOK: query: SELECT key, value FROM src WHERE key=0 AND value = "val_0"
POSTHOOK: type: QUERY
-POSTHOOK: Input: default@default__src_src1_index__
-POSTHOOK: Input: default@default__src_src2_index__
POSTHOOK: Input: default@src
#### A masked pattern was here ####
0 val_0
http://git-wip-us.apache.org/repos/asf/hive/blob/b80bcd05/ql/src/test/results/clientpositive/infer_bucket_sort_dyn_part.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/infer_bucket_sort_dyn_part.q.out b/ql/src/test/results/clientpositive/infer_bucket_sort_dyn_part.q.out
index 7e3b48f..6d2ca0c 100644
--- a/ql/src/test/results/clientpositive/infer_bucket_sort_dyn_part.q.out
+++ b/ql/src/test/results/clientpositive/infer_bucket_sort_dyn_part.q.out
@@ -470,22 +470,22 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: srcpart
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string)
outputColumnNames: key
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
keys: key (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint)
Reduce Operator Tree:
Group By Operator
@@ -493,14 +493,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: string), UDFToString(_col1) (type: string), if(((UDFToDouble(_col0) % 100.0) = 0.0), '11', '12') (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/b80bcd05/ql/src/test/results/clientpositive/infer_bucket_sort_map_operators.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/infer_bucket_sort_map_operators.q.out b/ql/src/test/results/clientpositive/infer_bucket_sort_map_operators.q.out
index 4ca6517..3f7ae91 100644
--- a/ql/src/test/results/clientpositive/infer_bucket_sort_map_operators.q.out
+++ b/ql/src/test/results/clientpositive/infer_bucket_sort_map_operators.q.out
@@ -255,19 +255,19 @@ STAGE PLANS:
value expressions: _col0 (type: string), _col1 (type: bigint)
TableScan
alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: value is not null (type: boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: value (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: UDFToDouble(_col0) (type: double)
sort order: +
Map-reduce partition columns: UDFToDouble(_col0) (type: double)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
Reduce Operator Tree:
Join Operator
condition map:
@@ -276,10 +276,10 @@ STAGE PLANS:
0 UDFToDouble(_col1) (type: double)
1 UDFToDouble(_col0) (type: double)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/b80bcd05/ql/src/test/results/clientpositive/infer_bucket_sort_num_buckets.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/infer_bucket_sort_num_buckets.q.out b/ql/src/test/results/clientpositive/infer_bucket_sort_num_buckets.q.out
index 54b4500..f467168 100644
--- a/ql/src/test/results/clientpositive/infer_bucket_sort_num_buckets.q.out
+++ b/ql/src/test/results/clientpositive/infer_bucket_sort_num_buckets.q.out
@@ -59,24 +59,24 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: srcpart
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 58 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: if(((key % 3) < 2), 0, 1) (type: int), value (type: string), UDFToInteger((key % 2)) (type: int)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 58 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
sort order:
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 58 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int)
Reduce Operator Tree:
Select Operator
expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), VALUE._col2 (type: int)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 58 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 58 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/b80bcd05/ql/src/test/results/clientpositive/infer_bucket_sort_reducers_power_two.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/infer_bucket_sort_reducers_power_two.q.out b/ql/src/test/results/clientpositive/infer_bucket_sort_reducers_power_two.q.out
index 05b91e5..5fc5e91 100644
--- a/ql/src/test/results/clientpositive/infer_bucket_sort_reducers_power_two.q.out
+++ b/ql/src/test/results/clientpositive/infer_bucket_sort_reducers_power_two.q.out
@@ -275,8 +275,8 @@ InputFormat: org.apache.hadoop.mapred.TextInputFormat
OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
Compressed: No
Num Buckets: 16
-Bucket Columns: [key]
-Sort Columns: [Order(col:key, order:1)]
+Bucket Columns: [value]
+Sort Columns: [Order(col:value, order:1)]
Storage Desc Params:
serialization.format 1
PREHOOK: query: -- Test group by in subquery with another group by outside, should be bucketed and sorted by the
http://git-wip-us.apache.org/repos/asf/hive/blob/b80bcd05/ql/src/test/results/clientpositive/join1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/join1.q.out b/ql/src/test/results/clientpositive/join1.q.out
index fbe5f91..5d54ee3 100644
--- a/ql/src/test/results/clientpositive/join1.q.out
+++ b/ql/src/test/results/clientpositive/join1.q.out
@@ -29,34 +29,34 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
TableScan
alias: src2
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string)
Reduce Operator Tree:
Join Operator
@@ -66,14 +66,14 @@ STAGE PLANS:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col2
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 63 Data size: 6393 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: UDFToInteger(_col0) (type: int), _col2 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 63 Data size: 6393 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 63 Data size: 6393 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/b80bcd05/ql/src/test/results/clientpositive/list_bucket_dml_10.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_10.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_10.q.out
index 02dd93f..97ab521 100644
--- a/ql/src/test/results/clientpositive/list_bucket_dml_10.q.out
+++ b/ql/src/test/results/clientpositive/list_bucket_dml_10.q.out
@@ -68,19 +68,19 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
GlobalTableId: 1
#### A masked pattern was here ####
NumFilesPerFileSink: 1
Static Partition Specification: ds=2008-04-08/hr=11/
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
#### A masked pattern was here ####
table:
input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
@@ -111,7 +111,6 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -119,8 +118,8 @@ STAGE PLANS:
#### A masked pattern was here ####
name default.src
numFiles 1
- numRows 500
- rawDataSize 5312
+ numRows 0
+ rawDataSize 0
serialization.ddl struct src { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -131,7 +130,6 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -139,8 +137,8 @@ STAGE PLANS:
#### A masked pattern was here ####
name default.src
numFiles 1
- numRows 500
- rawDataSize 5312
+ numRows 0
+ rawDataSize 0
serialization.ddl struct src { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
http://git-wip-us.apache.org/repos/asf/hive/blob/b80bcd05/ql/src/test/results/clientpositive/orc_merge_diff_fs.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/orc_merge_diff_fs.q.out b/ql/src/test/results/clientpositive/orc_merge_diff_fs.q.out
index 3f047da..6ac3d35 100644
--- a/ql/src/test/results/clientpositive/orc_merge_diff_fs.q.out
+++ b/ql/src/test/results/clientpositive/orc_merge_diff_fs.q.out
@@ -67,14 +67,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: UDFToInteger(key) (type: int), value (type: string), (hash(key) pmod 2) (type: int)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
@@ -144,14 +144,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: UDFToInteger(key) (type: int), value (type: string), (hash(key) pmod 2) (type: int)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
@@ -260,14 +260,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: UDFToInteger(key) (type: int), value (type: string), (hash(key) pmod 2) (type: int)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/b80bcd05/ql/src/test/results/clientpositive/reduce_deduplicate.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/reduce_deduplicate.q.out b/ql/src/test/results/clientpositive/reduce_deduplicate.q.out
index dfcbd7d..2bb08b1 100644
--- a/ql/src/test/results/clientpositive/reduce_deduplicate.q.out
+++ b/ql/src/test/results/clientpositive/reduce_deduplicate.q.out
@@ -25,18 +25,18 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
tag: -1
value expressions: _col1 (type: string)
auto parallelism: false
@@ -49,7 +49,6 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -57,8 +56,8 @@ STAGE PLANS:
#### A masked pattern was here ####
name default.src
numFiles 1
- numRows 500
- rawDataSize 5312
+ numRows 0
+ rawDataSize 0
serialization.ddl struct src { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -69,7 +68,6 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -77,8 +75,8 @@ STAGE PLANS:
#### A masked pattern was here ####
name default.src
numFiles 1
- numRows 500
- rawDataSize 5312
+ numRows 0
+ rawDataSize 0
serialization.ddl struct src { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -94,13 +92,13 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
GlobalTableId: 1
#### A masked pattern was here ####
NumFilesPerFileSink: 2
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
#### A masked pattern was here ####
table:
input format: org.apache.hadoop.mapred.TextInputFormat