FAQ
Repository: hive
Updated Branches:
   refs/heads/master 6dc362f0f -> d8705a12f


HIVE-13261: Can not compute column stats for partition when schema evolves (Pengcheng Xiong, reviewed by Ashutosh Chauhan)


Project: http://git-wip-us.apache.org/repos/asf/hive/repo
Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/d8705a12
Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/d8705a12
Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/d8705a12

Branch: refs/heads/master
Commit: d8705a12f617722837b56602a4da4d76be3f1675
Parents: 6dc362f
Author: Pengcheng Xiong <pxiong@apache.org>
Authored: Wed Mar 23 17:35:59 2016 -0700
Committer: Pengcheng Xiong <pxiong@apache.org>
Committed: Wed Mar 23 17:35:59 2016 -0700

----------------------------------------------------------------------
  .../test/resources/testconfiguration.properties | 1 +
  .../hadoop/hive/metastore/ObjectStore.java | 6 +-
  .../queries/clientpositive/schema_evol_stats.q | 50 +++
  .../clientpositive/schema_evol_stats.q.out | 392 +++++++++++++++++++
  .../clientpositive/tez/schema_evol_stats.q.out | 384 ++++++++++++++++++
  5 files changed, 829 insertions(+), 4 deletions(-)
----------------------------------------------------------------------


http://git-wip-us.apache.org/repos/asf/hive/blob/d8705a12/itests/src/test/resources/testconfiguration.properties
----------------------------------------------------------------------
diff --git a/itests/src/test/resources/testconfiguration.properties b/itests/src/test/resources/testconfiguration.properties
index 8d145c1..232e262 100644
--- a/itests/src/test/resources/testconfiguration.properties
+++ b/itests/src/test/resources/testconfiguration.properties
@@ -184,6 +184,7 @@ minitez.query.files.shared=acid_globallimit.q,\
    ptf_matchpath.q,\
    ptf_streaming.q,\
    sample1.q,\
+ schema_evol_stats.q,\
    schema_evol_text_nonvec_mapwork_table.q,\
    schema_evol_text_nonvec_fetchwork_table.q,\
    schema_evol_orc_nonvec_fetchwork_part.q,\

http://git-wip-us.apache.org/repos/asf/hive/blob/d8705a12/metastore/src/java/org/apache/hadoop/hive/metastore/ObjectStore.java
----------------------------------------------------------------------
diff --git a/metastore/src/java/org/apache/hadoop/hive/metastore/ObjectStore.java b/metastore/src/java/org/apache/hadoop/hive/metastore/ObjectStore.java
index ec24fe9..35adb39 100644
--- a/metastore/src/java/org/apache/hadoop/hive/metastore/ObjectStore.java
+++ b/metastore/src/java/org/apache/hadoop/hive/metastore/ObjectStore.java
@@ -6482,16 +6482,14 @@ public class ObjectStore implements RawStore, Configurable {
      boolean foundCol = false;
      List<FieldSchema> colList = partition.getSd().getCols();
      for (FieldSchema col : colList) {
- if (col.getName().equals(mStatsObj.getColName().trim())) {
+ if (col.getName().equals(mStatsObj.getColName())) {
          foundCol = true;
          break;
        }
      }

      if (!foundCol) {
- throw new
- NoSuchObjectException("Column " + colName +
- " for which stats gathering is requested doesn't exist.");
+ LOG.warn("Column " + colName + " for which stats gathering is requested doesn't exist.");
      }

      QueryWrapper queryWrapper = new QueryWrapper();

http://git-wip-us.apache.org/repos/asf/hive/blob/d8705a12/ql/src/test/queries/clientpositive/schema_evol_stats.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/schema_evol_stats.q b/ql/src/test/queries/clientpositive/schema_evol_stats.q
new file mode 100644
index 0000000..322379d
--- /dev/null
+++ b/ql/src/test/queries/clientpositive/schema_evol_stats.q
@@ -0,0 +1,50 @@
+set hive.mapred.mode=nonstrict;
+SET hive.exec.schema.evolution=true;
+
+CREATE TABLE partitioned1(a INT, b STRING) PARTITIONED BY(part INT) STORED AS TEXTFILE;
+
+insert into table partitioned1 partition(part=1) values(1, 'original'),(2, 'original'), (3, 'original'),(4, 'original');
+
+-- Table-Non-Cascade ADD COLUMNS ...
+alter table partitioned1 add columns(c int, d string);
+
+insert into table partitioned1 partition(part=2) values(1, 'new', 10, 'ten'),(2, 'new', NULL, 'twenty'), (3, 'new', 30, 'thirty'),(4, 'new', 40, 'forty');
+
+analyze table partitioned1 compute statistics for columns;
+
+desc formatted partitioned1;
+
+desc formatted partitioned1 PARTITION(part=1);
+
+desc formatted partitioned1 PARTITION(part=2);
+
+set hive.compute.query.using.stats=true;
+
+explain select count(c) from partitioned1;
+
+select count(c) from partitioned1;
+
+drop table partitioned1;
+
+CREATE TABLE partitioned1(a INT, b STRING) PARTITIONED BY(part INT) STORED AS ORC;
+
+insert into table partitioned1 partition(part=1) values(1, 'original'),(2, 'original'), (3, 'original'),(4, 'original');
+
+-- Table-Non-Cascade ADD COLUMNS ...
+alter table partitioned1 add columns(c int, d string);
+
+insert into table partitioned1 partition(part=2) values(1, 'new', 10, 'ten'),(2, 'new', NULL, 'twenty'), (3, 'new', 30, 'thirty'),(4, 'new', 40, 'forty');
+
+analyze table partitioned1 compute statistics for columns;
+
+desc formatted partitioned1;
+
+desc formatted partitioned1 PARTITION(part=1);
+
+desc formatted partitioned1 PARTITION(part=2);
+
+set hive.compute.query.using.stats=true;
+
+explain select count(c) from partitioned1;
+
+select count(c) from partitioned1;

http://git-wip-us.apache.org/repos/asf/hive/blob/d8705a12/ql/src/test/results/clientpositive/schema_evol_stats.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/schema_evol_stats.q.out b/ql/src/test/results/clientpositive/schema_evol_stats.q.out
new file mode 100644
index 0000000..63dab2e
--- /dev/null
+++ b/ql/src/test/results/clientpositive/schema_evol_stats.q.out
@@ -0,0 +1,392 @@
+PREHOOK: query: CREATE TABLE partitioned1(a INT, b STRING) PARTITIONED BY(part INT) STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@partitioned1
+POSTHOOK: query: CREATE TABLE partitioned1(a INT, b STRING) PARTITIONED BY(part INT) STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@partitioned1
+PREHOOK: query: insert into table partitioned1 partition(part=1) values(1, 'original'),(2, 'original'), (3, 'original'),(4, 'original')
+PREHOOK: type: QUERY
+PREHOOK: Input: default@values__tmp__table__1
+PREHOOK: Output: default@partitioned1@part=1
+POSTHOOK: query: insert into table partitioned1 partition(part=1) values(1, 'original'),(2, 'original'), (3, 'original'),(4, 'original')
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@values__tmp__table__1
+POSTHOOK: Output: default@partitioned1@part=1
+POSTHOOK: Lineage: partitioned1 PARTITION(part=1).a EXPRESSION [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col1, type:string, comment:), ]
+POSTHOOK: Lineage: partitioned1 PARTITION(part=1).b SIMPLE [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col2, type:string, comment:), ]
+PREHOOK: query: -- Table-Non-Cascade ADD COLUMNS ...
+alter table partitioned1 add columns(c int, d string)
+PREHOOK: type: ALTERTABLE_ADDCOLS
+PREHOOK: Input: default@partitioned1
+PREHOOK: Output: default@partitioned1
+POSTHOOK: query: -- Table-Non-Cascade ADD COLUMNS ...
+alter table partitioned1 add columns(c int, d string)
+POSTHOOK: type: ALTERTABLE_ADDCOLS
+POSTHOOK: Input: default@partitioned1
+POSTHOOK: Output: default@partitioned1
+PREHOOK: query: insert into table partitioned1 partition(part=2) values(1, 'new', 10, 'ten'),(2, 'new', NULL, 'twenty'), (3, 'new', 30, 'thirty'),(4, 'new', 40, 'forty')
+PREHOOK: type: QUERY
+PREHOOK: Input: default@values__tmp__table__2
+PREHOOK: Output: default@partitioned1@part=2
+POSTHOOK: query: insert into table partitioned1 partition(part=2) values(1, 'new', 10, 'ten'),(2, 'new', NULL, 'twenty'), (3, 'new', 30, 'thirty'),(4, 'new', 40, 'forty')
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@values__tmp__table__2
+POSTHOOK: Output: default@partitioned1@part=2
+POSTHOOK: Lineage: partitioned1 PARTITION(part=2).a EXPRESSION [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col1, type:string, comment:), ]
+POSTHOOK: Lineage: partitioned1 PARTITION(part=2).b SIMPLE [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col2, type:string, comment:), ]
+POSTHOOK: Lineage: partitioned1 PARTITION(part=2).c EXPRESSION [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col3, type:string, comment:), ]
+POSTHOOK: Lineage: partitioned1 PARTITION(part=2).d SIMPLE [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col4, type:string, comment:), ]
+PREHOOK: query: analyze table partitioned1 compute statistics for columns
+PREHOOK: type: QUERY
+PREHOOK: Input: default@partitioned1
+PREHOOK: Input: default@partitioned1@part=1
+PREHOOK: Input: default@partitioned1@part=2
+#### A masked pattern was here ####
+POSTHOOK: query: analyze table partitioned1 compute statistics for columns
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@partitioned1
+POSTHOOK: Input: default@partitioned1@part=1
+POSTHOOK: Input: default@partitioned1@part=2
+#### A masked pattern was here ####
+PREHOOK: query: desc formatted partitioned1
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@partitioned1
+POSTHOOK: query: desc formatted partitioned1
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@partitioned1
+# col_name data_type comment
+
+a int
+b string
+c int
+d string
+
+# Partition Information
+# col_name data_type comment
+
+part int
+
+# Detailed Table Information
+Database: default
+#### A masked pattern was here ####
+Retention: 0
+#### A masked pattern was here ####
+Table Type: MANAGED_TABLE
+Table Parameters:
+#### A masked pattern was here ####
+
+# Storage Information
+SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+InputFormat: org.apache.hadoop.mapred.TextInputFormat
+OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+Compressed: No
+Num Buckets: -1
+Bucket Columns: []
+Sort Columns: []
+Storage Desc Params:
+ serialization.format 1
+PREHOOK: query: desc formatted partitioned1 PARTITION(part=1)
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@partitioned1
+POSTHOOK: query: desc formatted partitioned1 PARTITION(part=1)
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@partitioned1
+# col_name data_type comment
+
+a int
+b string
+
+# Partition Information
+# col_name data_type comment
+
+part int
+
+# Detailed Partition Information
+Partition Value: [1]
+Database: default
+Table: partitioned1
+#### A masked pattern was here ####
+Partition Parameters:
+ COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\",\"c\":\"true\",\"d\":\"true\"},\"BASIC_STATS\":\"true\"}
+ numFiles 1
+ numRows 4
+ rawDataSize 40
+ totalSize 44
+#### A masked pattern was here ####
+
+# Storage Information
+SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+InputFormat: org.apache.hadoop.mapred.TextInputFormat
+OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+Compressed: No
+Num Buckets: -1
+Bucket Columns: []
+Sort Columns: []
+Storage Desc Params:
+ serialization.format 1
+PREHOOK: query: desc formatted partitioned1 PARTITION(part=2)
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@partitioned1
+POSTHOOK: query: desc formatted partitioned1 PARTITION(part=2)
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@partitioned1
+# col_name data_type comment
+
+a int
+b string
+c int
+d string
+
+# Partition Information
+# col_name data_type comment
+
+part int
+
+# Detailed Partition Information
+Partition Value: [2]
+Database: default
+Table: partitioned1
+#### A masked pattern was here ####
+Partition Parameters:
+ COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\",\"c\":\"true\",\"d\":\"true\"},\"BASIC_STATS\":\"true\"}
+ numFiles 1
+ numRows 4
+ rawDataSize 56
+ totalSize 60
+#### A masked pattern was here ####
+
+# Storage Information
+SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+InputFormat: org.apache.hadoop.mapred.TextInputFormat
+OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+Compressed: No
+Num Buckets: -1
+Bucket Columns: []
+Sort Columns: []
+Storage Desc Params:
+ serialization.format 1
+PREHOOK: query: explain select count(c) from partitioned1
+PREHOOK: type: QUERY
+POSTHOOK: query: explain select count(c) from partitioned1
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-0
+ Fetch Operator
+ limit: 1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select count(c) from partitioned1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@partitioned1
+#### A masked pattern was here ####
+POSTHOOK: query: select count(c) from partitioned1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@partitioned1
+#### A masked pattern was here ####
+3
+PREHOOK: query: drop table partitioned1
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@partitioned1
+PREHOOK: Output: default@partitioned1
+POSTHOOK: query: drop table partitioned1
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@partitioned1
+POSTHOOK: Output: default@partitioned1
+PREHOOK: query: CREATE TABLE partitioned1(a INT, b STRING) PARTITIONED BY(part INT) STORED AS ORC
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@partitioned1
+POSTHOOK: query: CREATE TABLE partitioned1(a INT, b STRING) PARTITIONED BY(part INT) STORED AS ORC
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@partitioned1
+PREHOOK: query: insert into table partitioned1 partition(part=1) values(1, 'original'),(2, 'original'), (3, 'original'),(4, 'original')
+PREHOOK: type: QUERY
+PREHOOK: Input: default@values__tmp__table__3
+PREHOOK: Output: default@partitioned1@part=1
+POSTHOOK: query: insert into table partitioned1 partition(part=1) values(1, 'original'),(2, 'original'), (3, 'original'),(4, 'original')
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@values__tmp__table__3
+POSTHOOK: Output: default@partitioned1@part=1
+POSTHOOK: Lineage: partitioned1 PARTITION(part=1).a EXPRESSION [(values__tmp__table__3)values__tmp__table__3.FieldSchema(name:tmp_values_col1, type:string, comment:), ]
+POSTHOOK: Lineage: partitioned1 PARTITION(part=1).b SIMPLE [(values__tmp__table__3)values__tmp__table__3.FieldSchema(name:tmp_values_col2, type:string, comment:), ]
+PREHOOK: query: -- Table-Non-Cascade ADD COLUMNS ...
+alter table partitioned1 add columns(c int, d string)
+PREHOOK: type: ALTERTABLE_ADDCOLS
+PREHOOK: Input: default@partitioned1
+PREHOOK: Output: default@partitioned1
+POSTHOOK: query: -- Table-Non-Cascade ADD COLUMNS ...
+alter table partitioned1 add columns(c int, d string)
+POSTHOOK: type: ALTERTABLE_ADDCOLS
+POSTHOOK: Input: default@partitioned1
+POSTHOOK: Output: default@partitioned1
+PREHOOK: query: insert into table partitioned1 partition(part=2) values(1, 'new', 10, 'ten'),(2, 'new', NULL, 'twenty'), (3, 'new', 30, 'thirty'),(4, 'new', 40, 'forty')
+PREHOOK: type: QUERY
+PREHOOK: Input: default@values__tmp__table__4
+PREHOOK: Output: default@partitioned1@part=2
+POSTHOOK: query: insert into table partitioned1 partition(part=2) values(1, 'new', 10, 'ten'),(2, 'new', NULL, 'twenty'), (3, 'new', 30, 'thirty'),(4, 'new', 40, 'forty')
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@values__tmp__table__4
+POSTHOOK: Output: default@partitioned1@part=2
+POSTHOOK: Lineage: partitioned1 PARTITION(part=2).a EXPRESSION [(values__tmp__table__4)values__tmp__table__4.FieldSchema(name:tmp_values_col1, type:string, comment:), ]
+POSTHOOK: Lineage: partitioned1 PARTITION(part=2).b SIMPLE [(values__tmp__table__4)values__tmp__table__4.FieldSchema(name:tmp_values_col2, type:string, comment:), ]
+POSTHOOK: Lineage: partitioned1 PARTITION(part=2).c EXPRESSION [(values__tmp__table__4)values__tmp__table__4.FieldSchema(name:tmp_values_col3, type:string, comment:), ]
+POSTHOOK: Lineage: partitioned1 PARTITION(part=2).d SIMPLE [(values__tmp__table__4)values__tmp__table__4.FieldSchema(name:tmp_values_col4, type:string, comment:), ]
+PREHOOK: query: analyze table partitioned1 compute statistics for columns
+PREHOOK: type: QUERY
+PREHOOK: Input: default@partitioned1
+PREHOOK: Input: default@partitioned1@part=1
+PREHOOK: Input: default@partitioned1@part=2
+#### A masked pattern was here ####
+POSTHOOK: query: analyze table partitioned1 compute statistics for columns
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@partitioned1
+POSTHOOK: Input: default@partitioned1@part=1
+POSTHOOK: Input: default@partitioned1@part=2
+#### A masked pattern was here ####
+PREHOOK: query: desc formatted partitioned1
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@partitioned1
+POSTHOOK: query: desc formatted partitioned1
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@partitioned1
+# col_name data_type comment
+
+a int
+b string
+c int
+d string
+
+# Partition Information
+# col_name data_type comment
+
+part int
+
+# Detailed Table Information
+Database: default
+#### A masked pattern was here ####
+Retention: 0
+#### A masked pattern was here ####
+Table Type: MANAGED_TABLE
+Table Parameters:
+#### A masked pattern was here ####
+
+# Storage Information
+SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde
+InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
+Compressed: No
+Num Buckets: -1
+Bucket Columns: []
+Sort Columns: []
+Storage Desc Params:
+ serialization.format 1
+PREHOOK: query: desc formatted partitioned1 PARTITION(part=1)
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@partitioned1
+POSTHOOK: query: desc formatted partitioned1 PARTITION(part=1)
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@partitioned1
+# col_name data_type comment
+
+a int
+b string
+
+# Partition Information
+# col_name data_type comment
+
+part int
+
+# Detailed Partition Information
+Partition Value: [1]
+Database: default
+Table: partitioned1
+#### A masked pattern was here ####
+Partition Parameters:
+ COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\",\"c\":\"true\",\"d\":\"true\"},\"BASIC_STATS\":\"true\"}
+ numFiles 1
+ numRows 4
+ rawDataSize 384
+ totalSize 313
+#### A masked pattern was here ####
+
+# Storage Information
+SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde
+InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
+Compressed: No
+Num Buckets: -1
+Bucket Columns: []
+Sort Columns: []
+Storage Desc Params:
+ serialization.format 1
+PREHOOK: query: desc formatted partitioned1 PARTITION(part=2)
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@partitioned1
+POSTHOOK: query: desc formatted partitioned1 PARTITION(part=2)
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@partitioned1
+# col_name data_type comment
+
+a int
+b string
+c int
+d string
+
+# Partition Information
+# col_name data_type comment
+
+part int
+
+# Detailed Partition Information
+Partition Value: [2]
+Database: default
+Table: partitioned1
+#### A masked pattern was here ####
+Partition Parameters:
+ COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\",\"c\":\"true\",\"d\":\"true\"},\"BASIC_STATS\":\"true\"}
+ numFiles 1
+ numRows 4
+ rawDataSize 732
+ totalSize 506
+#### A masked pattern was here ####
+
+# Storage Information
+SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde
+InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
+Compressed: No
+Num Buckets: -1
+Bucket Columns: []
+Sort Columns: []
+Storage Desc Params:
+ serialization.format 1
+PREHOOK: query: explain select count(c) from partitioned1
+PREHOOK: type: QUERY
+POSTHOOK: query: explain select count(c) from partitioned1
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-0
+ Fetch Operator
+ limit: 1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select count(c) from partitioned1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@partitioned1
+#### A masked pattern was here ####
+POSTHOOK: query: select count(c) from partitioned1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@partitioned1
+#### A masked pattern was here ####
+3

http://git-wip-us.apache.org/repos/asf/hive/blob/d8705a12/ql/src/test/results/clientpositive/tez/schema_evol_stats.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/schema_evol_stats.q.out b/ql/src/test/results/clientpositive/tez/schema_evol_stats.q.out
new file mode 100644
index 0000000..d396a61
--- /dev/null
+++ b/ql/src/test/results/clientpositive/tez/schema_evol_stats.q.out
@@ -0,0 +1,384 @@
+PREHOOK: query: CREATE TABLE partitioned1(a INT, b STRING) PARTITIONED BY(part INT) STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@partitioned1
+POSTHOOK: query: CREATE TABLE partitioned1(a INT, b STRING) PARTITIONED BY(part INT) STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@partitioned1
+PREHOOK: query: insert into table partitioned1 partition(part=1) values(1, 'original'),(2, 'original'), (3, 'original'),(4, 'original')
+PREHOOK: type: QUERY
+PREHOOK: Input: default@values__tmp__table__1
+PREHOOK: Output: default@partitioned1@part=1
+POSTHOOK: query: insert into table partitioned1 partition(part=1) values(1, 'original'),(2, 'original'), (3, 'original'),(4, 'original')
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@values__tmp__table__1
+POSTHOOK: Output: default@partitioned1@part=1
+POSTHOOK: Lineage: partitioned1 PARTITION(part=1).a EXPRESSION [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col1, type:string, comment:), ]
+POSTHOOK: Lineage: partitioned1 PARTITION(part=1).b SIMPLE [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col2, type:string, comment:), ]
+PREHOOK: query: -- Table-Non-Cascade ADD COLUMNS ...
+alter table partitioned1 add columns(c int, d string)
+PREHOOK: type: ALTERTABLE_ADDCOLS
+PREHOOK: Input: default@partitioned1
+PREHOOK: Output: default@partitioned1
+POSTHOOK: query: -- Table-Non-Cascade ADD COLUMNS ...
+alter table partitioned1 add columns(c int, d string)
+POSTHOOK: type: ALTERTABLE_ADDCOLS
+POSTHOOK: Input: default@partitioned1
+POSTHOOK: Output: default@partitioned1
+PREHOOK: query: insert into table partitioned1 partition(part=2) values(1, 'new', 10, 'ten'),(2, 'new', NULL, 'twenty'), (3, 'new', 30, 'thirty'),(4, 'new', 40, 'forty')
+PREHOOK: type: QUERY
+PREHOOK: Input: default@values__tmp__table__2
+PREHOOK: Output: default@partitioned1@part=2
+POSTHOOK: query: insert into table partitioned1 partition(part=2) values(1, 'new', 10, 'ten'),(2, 'new', NULL, 'twenty'), (3, 'new', 30, 'thirty'),(4, 'new', 40, 'forty')
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@values__tmp__table__2
+POSTHOOK: Output: default@partitioned1@part=2
+POSTHOOK: Lineage: partitioned1 PARTITION(part=2).a EXPRESSION [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col1, type:string, comment:), ]
+POSTHOOK: Lineage: partitioned1 PARTITION(part=2).b SIMPLE [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col2, type:string, comment:), ]
+POSTHOOK: Lineage: partitioned1 PARTITION(part=2).c EXPRESSION [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col3, type:string, comment:), ]
+POSTHOOK: Lineage: partitioned1 PARTITION(part=2).d SIMPLE [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col4, type:string, comment:), ]
+PREHOOK: query: analyze table partitioned1 compute statistics for columns
+PREHOOK: type: QUERY
+PREHOOK: Input: default@partitioned1
+PREHOOK: Input: default@partitioned1@part=1
+PREHOOK: Input: default@partitioned1@part=2
+#### A masked pattern was here ####
+POSTHOOK: query: analyze table partitioned1 compute statistics for columns
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@partitioned1
+POSTHOOK: Input: default@partitioned1@part=1
+POSTHOOK: Input: default@partitioned1@part=2
+#### A masked pattern was here ####
+PREHOOK: query: desc formatted partitioned1
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@partitioned1
+POSTHOOK: query: desc formatted partitioned1
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@partitioned1
+# col_name data_type comment
+
+a int
+b string
+c int
+d string
+
+# Partition Information
+# col_name data_type comment
+
+part int
+
+# Detailed Table Information
+Database: default
+#### A masked pattern was here ####
+Retention: 0
+#### A masked pattern was here ####
+Table Type: MANAGED_TABLE
+Table Parameters:
+#### A masked pattern was here ####
+
+# Storage Information
+SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+InputFormat: org.apache.hadoop.mapred.TextInputFormat
+OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+Compressed: No
+Num Buckets: -1
+Bucket Columns: []
+Sort Columns: []
+Storage Desc Params:
+ serialization.format 1
+PREHOOK: query: desc formatted partitioned1 PARTITION(part=1)
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@partitioned1
+POSTHOOK: query: desc formatted partitioned1 PARTITION(part=1)
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@partitioned1
+# col_name data_type comment
+
+a int
+b string
+
+# Partition Information
+# col_name data_type comment
+
+part int
+
+# Detailed Partition Information
+Partition Value: [1]
+Database: default
+Table: partitioned1
+#### A masked pattern was here ####
+Partition Parameters:
+ COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\",\"c\":\"true\",\"d\":\"true\"},\"BASIC_STATS\":\"true\"}
+ numFiles 1
+ numRows 4
+ rawDataSize 40
+ totalSize 44
+#### A masked pattern was here ####
+
+# Storage Information
+SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+InputFormat: org.apache.hadoop.mapred.TextInputFormat
+OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+Compressed: No
+Num Buckets: -1
+Bucket Columns: []
+Sort Columns: []
+Storage Desc Params:
+ serialization.format 1
+PREHOOK: query: desc formatted partitioned1 PARTITION(part=2)
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@partitioned1
+POSTHOOK: query: desc formatted partitioned1 PARTITION(part=2)
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@partitioned1
+# col_name data_type comment
+
+a int
+b string
+c int
+d string
+
+# Partition Information
+# col_name data_type comment
+
+part int
+
+# Detailed Partition Information
+Partition Value: [2]
+Database: default
+Table: partitioned1
+#### A masked pattern was here ####
+Partition Parameters:
+ COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\",\"c\":\"true\",\"d\":\"true\"},\"BASIC_STATS\":\"true\"}
+ numFiles 1
+ numRows 4
+ rawDataSize 56
+ totalSize 60
+#### A masked pattern was here ####
+
+# Storage Information
+SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+InputFormat: org.apache.hadoop.mapred.TextInputFormat
+OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+Compressed: No
+Num Buckets: -1
+Bucket Columns: []
+Sort Columns: []
+Storage Desc Params:
+ serialization.format 1
+PREHOOK: query: explain select count(c) from partitioned1
+PREHOOK: type: QUERY
+POSTHOOK: query: explain select count(c) from partitioned1
+POSTHOOK: type: QUERY
+Plan optimized by CBO.
+
+Stage-0
+ Fetch Operator
+ limit:1
+
+PREHOOK: query: select count(c) from partitioned1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@partitioned1
+#### A masked pattern was here ####
+POSTHOOK: query: select count(c) from partitioned1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@partitioned1
+#### A masked pattern was here ####
+3
+PREHOOK: query: drop table partitioned1
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@partitioned1
+PREHOOK: Output: default@partitioned1
+POSTHOOK: query: drop table partitioned1
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@partitioned1
+POSTHOOK: Output: default@partitioned1
+PREHOOK: query: CREATE TABLE partitioned1(a INT, b STRING) PARTITIONED BY(part INT) STORED AS ORC
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@partitioned1
+POSTHOOK: query: CREATE TABLE partitioned1(a INT, b STRING) PARTITIONED BY(part INT) STORED AS ORC
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@partitioned1
+PREHOOK: query: insert into table partitioned1 partition(part=1) values(1, 'original'),(2, 'original'), (3, 'original'),(4, 'original')
+PREHOOK: type: QUERY
+PREHOOK: Input: default@values__tmp__table__3
+PREHOOK: Output: default@partitioned1@part=1
+POSTHOOK: query: insert into table partitioned1 partition(part=1) values(1, 'original'),(2, 'original'), (3, 'original'),(4, 'original')
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@values__tmp__table__3
+POSTHOOK: Output: default@partitioned1@part=1
+POSTHOOK: Lineage: partitioned1 PARTITION(part=1).a EXPRESSION [(values__tmp__table__3)values__tmp__table__3.FieldSchema(name:tmp_values_col1, type:string, comment:), ]
+POSTHOOK: Lineage: partitioned1 PARTITION(part=1).b SIMPLE [(values__tmp__table__3)values__tmp__table__3.FieldSchema(name:tmp_values_col2, type:string, comment:), ]
+PREHOOK: query: -- Table-Non-Cascade ADD COLUMNS ...
+alter table partitioned1 add columns(c int, d string)
+PREHOOK: type: ALTERTABLE_ADDCOLS
+PREHOOK: Input: default@partitioned1
+PREHOOK: Output: default@partitioned1
+POSTHOOK: query: -- Table-Non-Cascade ADD COLUMNS ...
+alter table partitioned1 add columns(c int, d string)
+POSTHOOK: type: ALTERTABLE_ADDCOLS
+POSTHOOK: Input: default@partitioned1
+POSTHOOK: Output: default@partitioned1
+PREHOOK: query: insert into table partitioned1 partition(part=2) values(1, 'new', 10, 'ten'),(2, 'new', NULL, 'twenty'), (3, 'new', 30, 'thirty'),(4, 'new', 40, 'forty')
+PREHOOK: type: QUERY
+PREHOOK: Input: default@values__tmp__table__4
+PREHOOK: Output: default@partitioned1@part=2
+POSTHOOK: query: insert into table partitioned1 partition(part=2) values(1, 'new', 10, 'ten'),(2, 'new', NULL, 'twenty'), (3, 'new', 30, 'thirty'),(4, 'new', 40, 'forty')
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@values__tmp__table__4
+POSTHOOK: Output: default@partitioned1@part=2
+POSTHOOK: Lineage: partitioned1 PARTITION(part=2).a EXPRESSION [(values__tmp__table__4)values__tmp__table__4.FieldSchema(name:tmp_values_col1, type:string, comment:), ]
+POSTHOOK: Lineage: partitioned1 PARTITION(part=2).b SIMPLE [(values__tmp__table__4)values__tmp__table__4.FieldSchema(name:tmp_values_col2, type:string, comment:), ]
+POSTHOOK: Lineage: partitioned1 PARTITION(part=2).c EXPRESSION [(values__tmp__table__4)values__tmp__table__4.FieldSchema(name:tmp_values_col3, type:string, comment:), ]
+POSTHOOK: Lineage: partitioned1 PARTITION(part=2).d SIMPLE [(values__tmp__table__4)values__tmp__table__4.FieldSchema(name:tmp_values_col4, type:string, comment:), ]
+PREHOOK: query: analyze table partitioned1 compute statistics for columns
+PREHOOK: type: QUERY
+PREHOOK: Input: default@partitioned1
+PREHOOK: Input: default@partitioned1@part=1
+PREHOOK: Input: default@partitioned1@part=2
+#### A masked pattern was here ####
+POSTHOOK: query: analyze table partitioned1 compute statistics for columns
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@partitioned1
+POSTHOOK: Input: default@partitioned1@part=1
+POSTHOOK: Input: default@partitioned1@part=2
+#### A masked pattern was here ####
+PREHOOK: query: desc formatted partitioned1
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@partitioned1
+POSTHOOK: query: desc formatted partitioned1
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@partitioned1
+# col_name data_type comment
+
+a int
+b string
+c int
+d string
+
+# Partition Information
+# col_name data_type comment
+
+part int
+
+# Detailed Table Information
+Database: default
+#### A masked pattern was here ####
+Retention: 0
+#### A masked pattern was here ####
+Table Type: MANAGED_TABLE
+Table Parameters:
+#### A masked pattern was here ####
+
+# Storage Information
+SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde
+InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
+Compressed: No
+Num Buckets: -1
+Bucket Columns: []
+Sort Columns: []
+Storage Desc Params:
+ serialization.format 1
+PREHOOK: query: desc formatted partitioned1 PARTITION(part=1)
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@partitioned1
+POSTHOOK: query: desc formatted partitioned1 PARTITION(part=1)
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@partitioned1
+# col_name data_type comment
+
+a int
+b string
+
+# Partition Information
+# col_name data_type comment
+
+part int
+
+# Detailed Partition Information
+Partition Value: [1]
+Database: default
+Table: partitioned1
+#### A masked pattern was here ####
+Partition Parameters:
+ COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\",\"c\":\"true\",\"d\":\"true\"},\"BASIC_STATS\":\"true\"}
+ numFiles 1
+ numRows 4
+ rawDataSize 384
+ totalSize 313
+#### A masked pattern was here ####
+
+# Storage Information
+SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde
+InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
+Compressed: No
+Num Buckets: -1
+Bucket Columns: []
+Sort Columns: []
+Storage Desc Params:
+ serialization.format 1
+PREHOOK: query: desc formatted partitioned1 PARTITION(part=2)
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@partitioned1
+POSTHOOK: query: desc formatted partitioned1 PARTITION(part=2)
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@partitioned1
+# col_name data_type comment
+
+a int
+b string
+c int
+d string
+
+# Partition Information
+# col_name data_type comment
+
+part int
+
+# Detailed Partition Information
+Partition Value: [2]
+Database: default
+Table: partitioned1
+#### A masked pattern was here ####
+Partition Parameters:
+ COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\",\"c\":\"true\",\"d\":\"true\"},\"BASIC_STATS\":\"true\"}
+ numFiles 1
+ numRows 4
+ rawDataSize 732
+ totalSize 506
+#### A masked pattern was here ####
+
+# Storage Information
+SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde
+InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
+Compressed: No
+Num Buckets: -1
+Bucket Columns: []
+Sort Columns: []
+Storage Desc Params:
+ serialization.format 1
+PREHOOK: query: explain select count(c) from partitioned1
+PREHOOK: type: QUERY
+POSTHOOK: query: explain select count(c) from partitioned1
+POSTHOOK: type: QUERY
+Plan optimized by CBO.
+
+Stage-0
+ Fetch Operator
+ limit:1
+
+PREHOOK: query: select count(c) from partitioned1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@partitioned1
+#### A masked pattern was here ####
+POSTHOOK: query: select count(c) from partitioned1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@partitioned1
+#### A masked pattern was here ####
+3

Search Discussions

Related Discussions

Discussion Navigation
viewthread | post
posts ‹ prev | 1 of 1 | next ›
Discussion Overview
groupcommits @
categorieshive, hadoop
postedMar 24, '16 at 12:36a
activeMar 24, '16 at 12:36a
posts1
users1
websitehive.apache.org

1 user in discussion

Pxiong: 1 post

People

Translate

site design / logo © 2021 Grokbase