You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by px...@apache.org on 2017/07/15 08:06:58 UTC
[19/24] hive git commit: HIVE-16996: Add HLL as an alternative to FM
sketch to compute stats (Pengcheng Xiong, reviewed by Ashutosh Chauhan,
Prasanth Jayachandran)
http://git-wip-us.apache.org/repos/asf/hive/blob/b883d313/ql/src/test/results/clientpositive/alter_table_column_stats.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/alter_table_column_stats.q.out b/ql/src/test/results/clientpositive/alter_table_column_stats.q.out
index 2cc7cbc..96dce1e 100644
--- a/ql/src/test/results/clientpositive/alter_table_column_stats.q.out
+++ b/ql/src/test/results/clientpositive/alter_table_column_stats.q.out
@@ -125,7 +125,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testtable0
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col1 int 27 484 0 8 from deserializer
+col1 int 27 484 0 10 from deserializer
COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"col1\":\"true\",\"col2\":\"true\",\"col3\":\"true\"}}
PREHOOK: query: describe formatted statsdb1.testtable0 col2
PREHOOK: type: DESCTABLE
@@ -135,7 +135,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testtable0
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col2 string 0 12 6.7 7 from deserializer
+col2 string 0 10 6.7 7 from deserializer
COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"col1\":\"true\",\"col2\":\"true\",\"col3\":\"true\"}}
PREHOOK: query: describe formatted statsdb1.testtable0 col3
PREHOOK: type: DESCTABLE
@@ -201,7 +201,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testtable1
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col1 int 27 484 0 8 from deserializer
+col1 int 27 484 0 10 from deserializer
COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"col1\":\"true\",\"col2\":\"true\",\"col3\":\"true\"}}
PREHOOK: query: describe formatted statsdb1.testtable1 col2
PREHOOK: type: DESCTABLE
@@ -211,7 +211,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testtable1
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col2 string 0 12 6.7 7 from deserializer
+col2 string 0 10 6.7 7 from deserializer
COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"col1\":\"true\",\"col2\":\"true\",\"col3\":\"true\"}}
PREHOOK: query: describe formatted statsdb1.testtable1 col3
PREHOOK: type: DESCTABLE
@@ -276,7 +276,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testtable1
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col1 int 27 484 0 8 from deserializer
+col1 int 27 484 0 10 from deserializer
COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"col1\":\"true\",\"col2\":\"true\"}}
PREHOOK: query: describe formatted statsdb1.testtable1 col2
PREHOOK: type: DESCTABLE
@@ -286,7 +286,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testtable1
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col2 string 0 12 6.7 7 from deserializer
+col2 string 0 10 6.7 7 from deserializer
COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"col1\":\"true\",\"col2\":\"true\"}}
PREHOOK: query: describe formatted statsdb1.testtable1 col4
PREHOOK: type: DESCTABLE
@@ -361,7 +361,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testtable1
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col2 string 0 12 6.7 7 from deserializer
+col2 string 0 10 6.7 7 from deserializer
COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"col2\":\"true\"}}
PREHOOK: query: describe formatted statsdb1.testtable1 col4
PREHOOK: type: DESCTABLE
@@ -437,7 +437,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb2@testtable2
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col2 string 0 12 6.7 7 from deserializer
+col2 string 0 10 6.7 7 from deserializer
COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"col2\":\"true\"}}
PREHOOK: query: describe formatted statsdb2.testtable2 col4
PREHOOK: type: DESCTABLE
@@ -551,7 +551,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testpart0
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col1 int 27 484 0 8 from deserializer
+col1 int 27 484 0 10 from deserializer
PREHOOK: query: describe formatted statsdb1.testpart0 partition (part = 'part1') col2
PREHOOK: type: DESCTABLE
PREHOOK: Input: statsdb1@testpart0
@@ -560,7 +560,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testpart0
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col2 string 0 12 6.7 7 from deserializer
+col2 string 0 10 6.7 7 from deserializer
PREHOOK: query: describe formatted statsdb1.testpart0 partition (part = 'part1') col3
PREHOOK: type: DESCTABLE
PREHOOK: Input: statsdb1@testpart0
@@ -618,7 +618,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testpart0
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col1 int 27 484 0 18 from deserializer
+col1 int 27 484 0 20 from deserializer
PREHOOK: query: describe formatted statsdb1.testpart0 partition (part = 'part2') col2
PREHOOK: type: DESCTABLE
PREHOOK: Input: statsdb1@testpart0
@@ -627,7 +627,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testpart0
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col2 string 0 18 6.8 7 from deserializer
+col2 string 0 20 6.8 7 from deserializer
PREHOOK: query: describe formatted statsdb1.testpart0 partition (part = 'part2') col3
PREHOOK: type: DESCTABLE
PREHOOK: Input: statsdb1@testpart0
@@ -737,7 +737,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testpart1
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col1 int 27 484 0 8 from deserializer
+col1 int 27 484 0 10 from deserializer
PREHOOK: query: describe formatted statsdb1.testpart1 partition (part = 'part1') col2
PREHOOK: type: DESCTABLE
PREHOOK: Input: statsdb1@testpart1
@@ -746,7 +746,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testpart1
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col2 string 0 12 6.7 7 from deserializer
+col2 string 0 10 6.7 7 from deserializer
PREHOOK: query: describe formatted statsdb1.testpart1 partition (part = 'part1') col3
PREHOOK: type: DESCTABLE
PREHOOK: Input: statsdb1@testpart1
@@ -804,7 +804,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testpart1
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col1 int 27 484 0 18 from deserializer
+col1 int 27 484 0 20 from deserializer
PREHOOK: query: describe formatted statsdb1.testpart1 partition (part = 'part2') col2
PREHOOK: type: DESCTABLE
PREHOOK: Input: statsdb1@testpart1
@@ -813,7 +813,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testpart1
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col2 string 0 18 6.8 7 from deserializer
+col2 string 0 20 6.8 7 from deserializer
PREHOOK: query: describe formatted statsdb1.testpart1 partition (part = 'part2') col3
PREHOOK: type: DESCTABLE
PREHOOK: Input: statsdb1@testpart1
@@ -924,7 +924,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testpart1
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col1 int 27 484 0 8 from deserializer
+col1 int 27 484 0 10 from deserializer
PREHOOK: query: describe formatted statsdb1.testpart1 partition (part = 'part11') col2
PREHOOK: type: DESCTABLE
PREHOOK: Input: statsdb1@testpart1
@@ -933,7 +933,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testpart1
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col2 string 0 12 6.7 7 from deserializer
+col2 string 0 10 6.7 7 from deserializer
PREHOOK: query: describe formatted statsdb1.testpart1 partition (part = 'part11') col3
PREHOOK: type: DESCTABLE
PREHOOK: Input: statsdb1@testpart1
@@ -991,7 +991,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testpart1
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col1 int 27 484 0 18 from deserializer
+col1 int 27 484 0 20 from deserializer
PREHOOK: query: describe formatted statsdb1.testpart1 partition (part = 'part2') col2
PREHOOK: type: DESCTABLE
PREHOOK: Input: statsdb1@testpart1
@@ -1000,7 +1000,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testpart1
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col2 string 0 18 6.8 7 from deserializer
+col2 string 0 20 6.8 7 from deserializer
PREHOOK: query: describe formatted statsdb1.testpart1 partition (part = 'part2') col3
PREHOOK: type: DESCTABLE
PREHOOK: Input: statsdb1@testpart1
@@ -1113,7 +1113,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testpart1
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col1 int 27 484 0 8 from deserializer
+col1 int 27 484 0 10 from deserializer
PREHOOK: query: describe formatted statsdb1.testpart1 partition (part = 'part11') col2
PREHOOK: type: DESCTABLE
PREHOOK: Input: statsdb1@testpart1
@@ -1122,7 +1122,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testpart1
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col2 string 0 12 6.7 7 from deserializer
+col2 string 0 10 6.7 7 from deserializer
PREHOOK: query: describe formatted statsdb1.testpart1 partition (part = 'part11') col4
PREHOOK: type: DESCTABLE
PREHOOK: Input: statsdb1@testpart1
@@ -1180,7 +1180,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testpart1
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col1 int 27 484 0 18 from deserializer
+col1 int 27 484 0 20 from deserializer
PREHOOK: query: describe formatted statsdb1.testpart1 partition (part = 'part2') col2
PREHOOK: type: DESCTABLE
PREHOOK: Input: statsdb1@testpart1
@@ -1189,7 +1189,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testpart1
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col2 string 0 18 6.8 7 from deserializer
+col2 string 0 20 6.8 7 from deserializer
PREHOOK: query: describe formatted statsdb1.testpart1 partition (part = 'part2') col4
PREHOOK: type: DESCTABLE
PREHOOK: Input: statsdb1@testpart1
@@ -1311,7 +1311,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testpart1
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col2 string 0 12 6.7 7 from deserializer
+col2 string 0 10 6.7 7 from deserializer
PREHOOK: query: describe formatted statsdb1.testpart1 partition (part = 'part11') col4
PREHOOK: type: DESCTABLE
PREHOOK: Input: statsdb1@testpart1
@@ -1378,7 +1378,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testpart1
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col2 string 0 18 6.8 7 from deserializer
+col2 string 0 20 6.8 7 from deserializer
PREHOOK: query: describe formatted statsdb1.testpart1 partition (part = 'part2') col4
PREHOOK: type: DESCTABLE
PREHOOK: Input: statsdb1@testpart1
@@ -1457,7 +1457,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb2@testpart2
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col2 string 0 12 6.7 7 from deserializer
+col2 string 0 10 6.7 7 from deserializer
PREHOOK: query: describe formatted statsdb2.testpart2 partition (part = 'part11') col4
PREHOOK: type: DESCTABLE
PREHOOK: Input: statsdb2@testpart2
@@ -1484,7 +1484,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb2@testpart2
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col2 string 0 18 6.8 7 from deserializer
+col2 string 0 20 6.8 7 from deserializer
PREHOOK: query: describe formatted statsdb2.testpart2 partition (part = 'part2') col4
PREHOOK: type: DESCTABLE
PREHOOK: Input: statsdb2@testpart2
@@ -1665,7 +1665,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testtable0
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col1 int 27 484 0 8 from deserializer
+col1 int 27 484 0 10 from deserializer
COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"col1\":\"true\",\"col2\":\"true\",\"col3\":\"true\"}}
PREHOOK: query: describe formatted statsdb1.testtable0 col2
PREHOOK: type: DESCTABLE
@@ -1675,7 +1675,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testtable0
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col2 string 0 12 6.7 7 from deserializer
+col2 string 0 10 6.7 7 from deserializer
COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"col1\":\"true\",\"col2\":\"true\",\"col3\":\"true\"}}
PREHOOK: query: describe formatted statsdb1.testtable0 col3
PREHOOK: type: DESCTABLE
@@ -1741,7 +1741,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testtable1
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col1 int 27 484 0 8 from deserializer
+col1 int 27 484 0 10 from deserializer
COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"col1\":\"true\",\"col2\":\"true\",\"col3\":\"true\"}}
PREHOOK: query: describe formatted statsdb1.testtable1 col2
PREHOOK: type: DESCTABLE
@@ -1751,7 +1751,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testtable1
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col2 string 0 12 6.7 7 from deserializer
+col2 string 0 10 6.7 7 from deserializer
COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"col1\":\"true\",\"col2\":\"true\",\"col3\":\"true\"}}
PREHOOK: query: describe formatted statsdb1.testtable1 col3
PREHOOK: type: DESCTABLE
@@ -1816,7 +1816,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testtable1
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col1 int 27 484 0 8 from deserializer
+col1 int 27 484 0 10 from deserializer
COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"col1\":\"true\",\"col2\":\"true\"}}
PREHOOK: query: describe formatted statsdb1.testtable1 col2
PREHOOK: type: DESCTABLE
@@ -1826,7 +1826,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testtable1
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col2 string 0 12 6.7 7 from deserializer
+col2 string 0 10 6.7 7 from deserializer
COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"col1\":\"true\",\"col2\":\"true\"}}
PREHOOK: query: describe formatted statsdb1.testtable1 col4
PREHOOK: type: DESCTABLE
@@ -1901,7 +1901,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testtable1
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col2 string 0 12 6.7 7 from deserializer
+col2 string 0 10 6.7 7 from deserializer
COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"col2\":\"true\"}}
PREHOOK: query: describe formatted statsdb1.testtable1 col4
PREHOOK: type: DESCTABLE
@@ -1977,7 +1977,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb2@testtable2
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col2 string 0 12 6.7 7 from deserializer
+col2 string 0 10 6.7 7 from deserializer
COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"col2\":\"true\"}}
PREHOOK: query: describe formatted statsdb2.testtable2 col4
PREHOOK: type: DESCTABLE
@@ -2091,7 +2091,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testpart0
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col1 int 27 484 0 8 from deserializer
+col1 int 27 484 0 10 from deserializer
PREHOOK: query: describe formatted statsdb1.testpart0 partition (part = 'part1') col2
PREHOOK: type: DESCTABLE
PREHOOK: Input: statsdb1@testpart0
@@ -2100,7 +2100,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testpart0
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col2 string 0 12 6.7 7 from deserializer
+col2 string 0 10 6.7 7 from deserializer
PREHOOK: query: describe formatted statsdb1.testpart0 partition (part = 'part1') col3
PREHOOK: type: DESCTABLE
PREHOOK: Input: statsdb1@testpart0
@@ -2158,7 +2158,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testpart0
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col1 int 27 484 0 18 from deserializer
+col1 int 27 484 0 20 from deserializer
PREHOOK: query: describe formatted statsdb1.testpart0 partition (part = 'part2') col2
PREHOOK: type: DESCTABLE
PREHOOK: Input: statsdb1@testpart0
@@ -2167,7 +2167,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testpart0
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col2 string 0 18 6.8 7 from deserializer
+col2 string 0 20 6.8 7 from deserializer
PREHOOK: query: describe formatted statsdb1.testpart0 partition (part = 'part2') col3
PREHOOK: type: DESCTABLE
PREHOOK: Input: statsdb1@testpart0
@@ -2277,7 +2277,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testpart1
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col1 int 27 484 0 8 from deserializer
+col1 int 27 484 0 10 from deserializer
PREHOOK: query: describe formatted statsdb1.testpart1 partition (part = 'part1') col2
PREHOOK: type: DESCTABLE
PREHOOK: Input: statsdb1@testpart1
@@ -2286,7 +2286,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testpart1
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col2 string 0 12 6.7 7 from deserializer
+col2 string 0 10 6.7 7 from deserializer
PREHOOK: query: describe formatted statsdb1.testpart1 partition (part = 'part1') col3
PREHOOK: type: DESCTABLE
PREHOOK: Input: statsdb1@testpart1
@@ -2344,7 +2344,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testpart1
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col1 int 27 484 0 18 from deserializer
+col1 int 27 484 0 20 from deserializer
PREHOOK: query: describe formatted statsdb1.testpart1 partition (part = 'part2') col2
PREHOOK: type: DESCTABLE
PREHOOK: Input: statsdb1@testpart1
@@ -2353,7 +2353,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testpart1
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col2 string 0 18 6.8 7 from deserializer
+col2 string 0 20 6.8 7 from deserializer
PREHOOK: query: describe formatted statsdb1.testpart1 partition (part = 'part2') col3
PREHOOK: type: DESCTABLE
PREHOOK: Input: statsdb1@testpart1
@@ -2464,7 +2464,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testpart1
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col1 int 27 484 0 8 from deserializer
+col1 int 27 484 0 10 from deserializer
PREHOOK: query: describe formatted statsdb1.testpart1 partition (part = 'part11') col2
PREHOOK: type: DESCTABLE
PREHOOK: Input: statsdb1@testpart1
@@ -2473,7 +2473,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testpart1
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col2 string 0 12 6.7 7 from deserializer
+col2 string 0 10 6.7 7 from deserializer
PREHOOK: query: describe formatted statsdb1.testpart1 partition (part = 'part11') col3
PREHOOK: type: DESCTABLE
PREHOOK: Input: statsdb1@testpart1
@@ -2531,7 +2531,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testpart1
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col1 int 27 484 0 18 from deserializer
+col1 int 27 484 0 20 from deserializer
PREHOOK: query: describe formatted statsdb1.testpart1 partition (part = 'part2') col2
PREHOOK: type: DESCTABLE
PREHOOK: Input: statsdb1@testpart1
@@ -2540,7 +2540,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testpart1
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col2 string 0 18 6.8 7 from deserializer
+col2 string 0 20 6.8 7 from deserializer
PREHOOK: query: describe formatted statsdb1.testpart1 partition (part = 'part2') col3
PREHOOK: type: DESCTABLE
PREHOOK: Input: statsdb1@testpart1
@@ -2653,7 +2653,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testpart1
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col1 int 27 484 0 8 from deserializer
+col1 int 27 484 0 10 from deserializer
PREHOOK: query: describe formatted statsdb1.testpart1 partition (part = 'part11') col2
PREHOOK: type: DESCTABLE
PREHOOK: Input: statsdb1@testpart1
@@ -2662,7 +2662,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testpart1
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col2 string 0 12 6.7 7 from deserializer
+col2 string 0 10 6.7 7 from deserializer
PREHOOK: query: describe formatted statsdb1.testpart1 partition (part = 'part11') col4
PREHOOK: type: DESCTABLE
PREHOOK: Input: statsdb1@testpart1
@@ -2720,7 +2720,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testpart1
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col1 int 27 484 0 18 from deserializer
+col1 int 27 484 0 20 from deserializer
PREHOOK: query: describe formatted statsdb1.testpart1 partition (part = 'part2') col2
PREHOOK: type: DESCTABLE
PREHOOK: Input: statsdb1@testpart1
@@ -2729,7 +2729,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testpart1
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col2 string 0 18 6.8 7 from deserializer
+col2 string 0 20 6.8 7 from deserializer
PREHOOK: query: describe formatted statsdb1.testpart1 partition (part = 'part2') col4
PREHOOK: type: DESCTABLE
PREHOOK: Input: statsdb1@testpart1
@@ -2851,7 +2851,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testpart1
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col2 string 0 12 6.7 7 from deserializer
+col2 string 0 10 6.7 7 from deserializer
PREHOOK: query: describe formatted statsdb1.testpart1 partition (part = 'part11') col4
PREHOOK: type: DESCTABLE
PREHOOK: Input: statsdb1@testpart1
@@ -2918,7 +2918,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb1@testpart1
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col2 string 0 18 6.8 7 from deserializer
+col2 string 0 20 6.8 7 from deserializer
PREHOOK: query: describe formatted statsdb1.testpart1 partition (part = 'part2') col4
PREHOOK: type: DESCTABLE
PREHOOK: Input: statsdb1@testpart1
@@ -2997,7 +2997,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb2@testpart2
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col2 string 0 12 6.7 7 from deserializer
+col2 string 0 10 6.7 7 from deserializer
PREHOOK: query: describe formatted statsdb2.testpart2 partition (part = 'part11') col4
PREHOOK: type: DESCTABLE
PREHOOK: Input: statsdb2@testpart2
@@ -3024,7 +3024,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: statsdb2@testpart2
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-col2 string 0 18 6.8 7 from deserializer
+col2 string 0 20 6.8 7 from deserializer
PREHOOK: query: describe formatted statsdb2.testpart2 partition (part = 'part2') col4
PREHOOK: type: DESCTABLE
PREHOOK: Input: statsdb2@testpart2
http://git-wip-us.apache.org/repos/asf/hive/blob/b883d313/ql/src/test/results/clientpositive/alter_table_update_status.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/alter_table_update_status.q.out b/ql/src/test/results/clientpositive/alter_table_update_status.q.out
index e26e8cb..9cd9a8d 100644
--- a/ql/src/test/results/clientpositive/alter_table_update_status.q.out
+++ b/ql/src/test/results/clientpositive/alter_table_update_status.q.out
@@ -48,7 +48,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@src_stat
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-key string 0 14 1.72 3 from deserializer
+key string 0 16 1.72 3 from deserializer
COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\"}}
PREHOOK: query: ALTER TABLE src_stat UPDATE STATISTICS for column key SET ('numDVs'='1111','avgColLen'='1.111')
PREHOOK: type: ALTERTABLE_UPDATETABLESTATS
@@ -94,7 +94,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@src_stat_int
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-key double 66.0 406.0 10 14 from deserializer
+key double 66.0 406.0 10 15 from deserializer
COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"key\":\"true\"}}
PREHOOK: query: ALTER TABLE src_stat_int UPDATE STATISTICS for column key SET ('numDVs'='2222','lowValue'='333.22','highValue'='22.22')
PREHOOK: type: ALTERTABLE_UPDATETABLESTATS
http://git-wip-us.apache.org/repos/asf/hive/blob/b883d313/ql/src/test/results/clientpositive/analyze_tbl_part.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/analyze_tbl_part.q.out b/ql/src/test/results/clientpositive/analyze_tbl_part.q.out
index ed90b6f..6a3fbc0 100644
--- a/ql/src/test/results/clientpositive/analyze_tbl_part.q.out
+++ b/ql/src/test/results/clientpositive/analyze_tbl_part.q.out
@@ -50,7 +50,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@src_stat_part
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-key string 0 14 1.72 3 from deserializer
+key string 0 16 1.72 3 from deserializer
PREHOOK: query: ANALYZE TABLE src_stat_part partition (partitionId) COMPUTE STATISTICS for columns key, value
PREHOOK: type: QUERY
PREHOOK: Input: default@src_stat_part
@@ -71,7 +71,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@src_stat_part
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-key string 0 14 1.72 3 from deserializer
+key string 0 16 1.72 3 from deserializer
PREHOOK: query: describe formatted src_stat_part PARTITION(partitionId=2) value
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@src_stat_part
@@ -80,7 +80,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@src_stat_part
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-value string 0 14 4.92 7 from deserializer
+value string 0 19 4.92 7 from deserializer
PREHOOK: query: create table src_stat_string_part(key string, value string) partitioned by (partitionName string)
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
http://git-wip-us.apache.org/repos/asf/hive/blob/b883d313/ql/src/test/results/clientpositive/annotate_stats_deep_filters.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/annotate_stats_deep_filters.q.out b/ql/src/test/results/clientpositive/annotate_stats_deep_filters.q.out
index 95dd6ab..6e2975e 100644
--- a/ql/src/test/results/clientpositive/annotate_stats_deep_filters.q.out
+++ b/ql/src/test/results/clientpositive/annotate_stats_deep_filters.q.out
@@ -121,9 +121,9 @@ STAGE PLANS:
Statistics: Num rows: 2098 Data size: 16744 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (((t = 1) and (si = 2)) or ((t = 2) and (si = 3)) or ((t = 3) and (si = 4)) or ((t = 4) and (si = 5)) or ((t = 5) and (si = 6)) or ((t = 6) and (si = 7)) or ((t = 7) and (si = 8)) or ((t = 9) and (si = 10)) or ((t = 10) and (si = 11)) or ((t = 11) and (si = 12)) or ((t = 12) and (si = 13)) or ((t = 13) and (si = 14)) or ((t = 14) and (si = 15)) or ((t = 15) and (si = 16)) or ((t = 16) and (si = 17)) or ((t = 17) and (si = 18)) or ((t = 27) and (si = 28)) or ((t = 37) and (si = 38)) or ((t = 47) and (si = 48)) or ((t = 52) and (si = 53))) (type: boolean)
- Statistics: Num rows: 300 Data size: 2400 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 160 Data size: 1280 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
- Statistics: Num rows: 300 Data size: 2400 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 160 Data size: 1280 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
http://git-wip-us.apache.org/repos/asf/hive/blob/b883d313/ql/src/test/results/clientpositive/annotate_stats_groupby.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/annotate_stats_groupby.q.out b/ql/src/test/results/clientpositive/annotate_stats_groupby.q.out
index a8e4854..fccfabd 100644
--- a/ql/src/test/results/clientpositive/annotate_stats_groupby.q.out
+++ b/ql/src/test/results/clientpositive/annotate_stats_groupby.q.out
@@ -129,13 +129,13 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 7 Data size: 658 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 564 Basic stats: COMPLETE Column stats: PARTIAL
Group By Operator
aggregations: min(_col1)
keys: _col0 (type: string), _col2 (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 7 Data size: 686 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: PARTIAL
File Output Operator
compressed: false
table:
@@ -151,7 +151,7 @@ STAGE PLANS:
key expressions: _col0 (type: string), _col1 (type: bigint)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint)
- Statistics: Num rows: 7 Data size: 686 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: PARTIAL
value expressions: _col2 (type: int)
Reduce Operator Tree:
Group By Operator
@@ -159,10 +159,10 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 7 Data size: 686 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: PARTIAL
File Output Operator
compressed: false
- Statistics: Num rows: 7 Data size: 686 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: PARTIAL
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/b883d313/ql/src/test/results/clientpositive/annotate_stats_join.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/annotate_stats_join.q.out b/ql/src/test/results/clientpositive/annotate_stats_join.q.out
index c1a140b..736016f 100644
--- a/ql/src/test/results/clientpositive/annotate_stats_join.q.out
+++ b/ql/src/test/results/clientpositive/annotate_stats_join.q.out
@@ -236,10 +236,10 @@ STAGE PLANS:
0 _col0 (type: string), _col1 (type: int)
1 _col1 (type: string), _col0 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 6 Data size: 1164 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 8 Data size: 1552 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 6 Data size: 1164 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 8 Data size: 1552 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -302,10 +302,10 @@ STAGE PLANS:
0 _col0 (type: string), _col1 (type: int)
1 _col1 (type: string), _col0 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 6 Data size: 1164 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 8 Data size: 1552 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 6 Data size: 1164 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 8 Data size: 1552 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -368,10 +368,10 @@ STAGE PLANS:
0 _col0 (type: string), _col1 (type: int)
1 _col1 (type: string), _col0 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 6 Data size: 1164 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 8 Data size: 1552 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 6 Data size: 1164 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 8 Data size: 1552 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -538,10 +538,10 @@ STAGE PLANS:
1 _col0 (type: int)
2 _col1 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 47 Data size: 13912 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 64 Data size: 18944 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 47 Data size: 13912 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 64 Data size: 18944 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -682,10 +682,10 @@ STAGE PLANS:
0 _col0 (type: string), _col1 (type: int)
1 _col1 (type: string), _col0 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 48 Data size: 5417 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 48 Data size: 5607 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 48 Data size: 5417 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 48 Data size: 5607 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -753,10 +753,10 @@ STAGE PLANS:
0 _col0 (type: string), _col1 (type: int)
1 _col0 (type: string), _col1 (type: int)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 3 Data size: 297 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 3 Data size: 297 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -813,10 +813,10 @@ STAGE PLANS:
0 _col0 (type: string), _col1 (type: int)
1 _col1 (type: string), _col0 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 6 Data size: 1164 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 8 Data size: 1552 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 6 Data size: 1164 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 8 Data size: 1552 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -873,10 +873,10 @@ STAGE PLANS:
0 _col0 (type: string), _col1 (type: int)
1 _col1 (type: string), _col0 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 54 Data size: 1358 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 54 Data size: 1746 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 54 Data size: 1358 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 54 Data size: 1746 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/b883d313/ql/src/test/results/clientpositive/annotate_stats_join_pkfk.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/annotate_stats_join_pkfk.q.out b/ql/src/test/results/clientpositive/annotate_stats_join_pkfk.q.out
index f7d73c9..e04c1c6 100644
--- a/ql/src/test/results/clientpositive/annotate_stats_join_pkfk.q.out
+++ b/ql/src/test/results/clientpositive/annotate_stats_join_pkfk.q.out
@@ -807,14 +807,14 @@ STAGE PLANS:
1 _col0 (type: int)
2 _col0 (type: int)
outputColumnNames: _col1
- Statistics: Num rows: 821 Data size: 3284 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 964 Data size: 3856 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 821 Data size: 3284 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 964 Data size: 3856 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 821 Data size: 3284 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 964 Data size: 3856 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -979,14 +979,14 @@ STAGE PLANS:
1 _col0 (type: int)
2 _col0 (type: int)
outputColumnNames: _col1
- Statistics: Num rows: 821 Data size: 3284 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 964 Data size: 3856 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 821 Data size: 3284 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 964 Data size: 3856 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 821 Data size: 3284 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 964 Data size: 3856 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1065,14 +1065,14 @@ STAGE PLANS:
1 _col0 (type: int)
2 _col0 (type: int)
outputColumnNames: _col2
- Statistics: Num rows: 273 Data size: 1092 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 321 Data size: 1284 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col2 (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 273 Data size: 1092 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 321 Data size: 1284 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 273 Data size: 1092 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 321 Data size: 1284 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1177,14 +1177,14 @@ STAGE PLANS:
0 _col0 (type: int)
1 _col0 (type: int)
outputColumnNames: _col2
- Statistics: Num rows: 210 Data size: 840 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 241 Data size: 964 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col2 (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 210 Data size: 840 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 241 Data size: 964 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 210 Data size: 840 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 241 Data size: 964 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/b883d313/ql/src/test/results/clientpositive/autoColumnStats_4.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/autoColumnStats_4.q.out b/ql/src/test/results/clientpositive/autoColumnStats_4.q.out
index fe3b9e5..e844999 100644
--- a/ql/src/test/results/clientpositive/autoColumnStats_4.q.out
+++ b/ql/src/test/results/clientpositive/autoColumnStats_4.q.out
@@ -116,10 +116,10 @@ STAGE PLANS:
outputColumnNames: a, b
Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE
Group By Operator
- aggregations: compute_stats(a, 16), compute_stats(b, 16)
+ aggregations: compute_stats(a, 'hll'), compute_stats(b, 'hll')
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 968 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 944 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
@@ -153,17 +153,17 @@ STAGE PLANS:
TableScan
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 968 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>)
+ Statistics: Num rows: 1 Data size: 944 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:string>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string>)
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: 972 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 960 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 972 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 960 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/b883d313/ql/src/test/results/clientpositive/autoColumnStats_5.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/autoColumnStats_5.q.out b/ql/src/test/results/clientpositive/autoColumnStats_5.q.out
index e19fb5f..e3abba5 100644
--- a/ql/src/test/results/clientpositive/autoColumnStats_5.q.out
+++ b/ql/src/test/results/clientpositive/autoColumnStats_5.q.out
@@ -46,7 +46,7 @@ STAGE PLANS:
outputColumnNames: a, b, part
Statistics: Num rows: 1 Data size: 44 Basic stats: COMPLETE Column stats: NONE
Group By Operator
- aggregations: compute_stats(a, 16), compute_stats(b, 16)
+ aggregations: compute_stats(a, 'hll'), compute_stats(b, 'hll')
keys: part (type: int)
mode: hash
outputColumnNames: _col0, _col1, _col2
@@ -56,7 +56,7 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 1 Data size: 44 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>)
+ value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:string>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string>)
Reduce Operator Tree:
Group By Operator
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
@@ -195,7 +195,7 @@ POSTHOOK: Input: default@partitioned1
col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-a int 1 4 0 5 from deserializer
+a int 1 4 0 4 from deserializer
PREHOOK: query: alter table partitioned1 add columns(c int, d string)
PREHOOK: type: ALTERTABLE_ADDCOLS
PREHOOK: Input: default@partitioned1
@@ -284,7 +284,7 @@ STAGE PLANS:
outputColumnNames: a, b, c, d, part
Statistics: Num rows: 1 Data size: 60 Basic stats: COMPLETE Column stats: NONE
Group By Operator
- aggregations: compute_stats(a, 16), compute_stats(b, 16), compute_stats(c, 16), compute_stats(d, 16)
+ aggregations: compute_stats(a, 'hll'), compute_stats(b, 'hll'), compute_stats(c, 'hll'), compute_stats(d, 'hll')
keys: part (type: int)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4
@@ -294,7 +294,7 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 1 Data size: 60 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col3 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col4 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>)
+ value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:string>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string>), _col3 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:string>), _col4 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string>)
Reduce Operator Tree:
Group By Operator
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3)
@@ -478,7 +478,7 @@ STAGE PLANS:
outputColumnNames: a, b, c, d, part
Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE
Group By Operator
- aggregations: compute_stats(a, 16), compute_stats(b, 16), compute_stats(c, 16), compute_stats(d, 16)
+ aggregations: compute_stats(a, 'hll'), compute_stats(b, 'hll'), compute_stats(c, 'hll'), compute_stats(d, 'hll')
keys: part (type: int)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4
@@ -488,7 +488,7 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col3 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col4 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>)
+ value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:string>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string>), _col3 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:string>), _col4 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string>)
Reduce Operator Tree:
Group By Operator
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3)
@@ -629,7 +629,7 @@ POSTHOOK: Input: default@partitioned1
col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-a int 1 6 0 5 from deserializer
+a int 1 6 0 4 from deserializer
PREHOOK: query: desc formatted partitioned1 partition(part=1) c
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@partitioned1
@@ -639,4 +639,4 @@ POSTHOOK: Input: default@partitioned1
col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-c int 100 200 0 3 from deserializer
+c int 100 200 0 2 from deserializer