HIVE-11493: Predicate with integer column equals double evaluates to false (Pengcheng Xiong, reviewed by Hari Sankar Sivarama Subramaniyan)
Project: http://git-wip-us.apache.org/repos/asf/hive/repo Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/b8f1ae11 Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/b8f1ae11 Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/b8f1ae11 Branch: refs/heads/llap Commit: b8f1ae110616a8fe162f79140c785f76be76fc67 Parents: 6e76291 Author: Pengcheng Xiong <pxi...@apache.org> Authored: Thu Aug 13 21:01:54 2015 -0700 Committer: Pengcheng Xiong <pxi...@apache.org> Committed: Thu Aug 13 21:02:40 2015 -0700 ---------------------------------------------------------------------- .../hive/ql/parse/TypeCheckProcFactory.java | 2 +- .../clientpositive/cast_tinyint_to_double.q | 7 ++++ .../clientpositive/cast_tinyint_to_double.q.out | 38 ++++++++++++++++++++ .../clientpositive/infer_const_type.q.out | 7 ++-- .../clientpositive/spark/vectorization_0.q.out | 2 +- .../spark/vectorization_short_regress.q.out | 20 +++++------ .../clientpositive/tez/vectorization_0.q.out | 2 +- .../tez/vectorization_short_regress.q.out | 20 +++++------ .../clientpositive/vectorization_0.q.out | 2 +- .../vectorization_short_regress.q.out | 20 +++++------ 10 files changed, 84 insertions(+), 36 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/hive/blob/b8f1ae11/ql/src/java/org/apache/hadoop/hive/ql/parse/TypeCheckProcFactory.java ---------------------------------------------------------------------- diff --git a/ql/src/java/org/apache/hadoop/hive/ql/parse/TypeCheckProcFactory.java b/ql/src/java/org/apache/hadoop/hive/ql/parse/TypeCheckProcFactory.java index cd68f4e..ab5d006 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/parse/TypeCheckProcFactory.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/parse/TypeCheckProcFactory.java @@ -1034,7 +1034,7 @@ public class TypeCheckProcFactory { // we'll try again to convert it to double // however, if we already tried this, or the column is NUMBER type and // the operator is EQUAL, return false due to the type mismatch - if (triedDouble || + if (triedDouble && (genericUDF instanceof GenericUDFOPEqual && !columnType.equals(serdeConstants.STRING_TYPE_NAME))) { return new ExprNodeConstantDesc(false); http://git-wip-us.apache.org/repos/asf/hive/blob/b8f1ae11/ql/src/test/queries/clientpositive/cast_tinyint_to_double.q ---------------------------------------------------------------------- diff --git a/ql/src/test/queries/clientpositive/cast_tinyint_to_double.q b/ql/src/test/queries/clientpositive/cast_tinyint_to_double.q new file mode 100644 index 0000000..59c5e89 --- /dev/null +++ b/ql/src/test/queries/clientpositive/cast_tinyint_to_double.q @@ -0,0 +1,7 @@ +drop table t; +CREATE TABLE t(c tinyint); +insert overwrite table t select 10 from src limit 1; + +select * from t where c = 10.0; + +select * from t where c = -10.0; \ No newline at end of file http://git-wip-us.apache.org/repos/asf/hive/blob/b8f1ae11/ql/src/test/results/clientpositive/cast_tinyint_to_double.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/cast_tinyint_to_double.q.out b/ql/src/test/results/clientpositive/cast_tinyint_to_double.q.out new file mode 100644 index 0000000..c29df65 --- /dev/null +++ b/ql/src/test/results/clientpositive/cast_tinyint_to_double.q.out @@ -0,0 +1,38 @@ +PREHOOK: query: drop table t +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table t +POSTHOOK: type: DROPTABLE +PREHOOK: query: CREATE TABLE t(c tinyint) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@t +POSTHOOK: query: CREATE TABLE t(c tinyint) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@t +PREHOOK: query: insert overwrite table t select 10 from src limit 1 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@t +POSTHOOK: query: insert overwrite table t select 10 from src limit 1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@t +POSTHOOK: Lineage: t.c EXPRESSION [] +PREHOOK: query: select * from t where c = 10.0 +PREHOOK: type: QUERY +PREHOOK: Input: default@t +#### A masked pattern was here #### +POSTHOOK: query: select * from t where c = 10.0 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t +#### A masked pattern was here #### +10 +PREHOOK: query: select * from t where c = -10.0 +PREHOOK: type: QUERY +PREHOOK: Input: default@t +#### A masked pattern was here #### +POSTHOOK: query: select * from t where c = -10.0 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t +#### A masked pattern was here #### http://git-wip-us.apache.org/repos/asf/hive/blob/b8f1ae11/ql/src/test/results/clientpositive/infer_const_type.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/infer_const_type.q.out b/ql/src/test/results/clientpositive/infer_const_type.q.out index 6368e4a..05c6a45 100644 --- a/ql/src/test/results/clientpositive/infer_const_type.q.out +++ b/ql/src/test/results/clientpositive/infer_const_type.q.out @@ -102,6 +102,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@infertypes #### A masked pattern was here #### 127 32767 12345 -12345 906.0 -307.0 1234 +WARNING: Comparing a bigint and a double may result in a loss of precision. PREHOOK: query: -- all should return false as all numbers exceeed the largest number -- which could be represented by the corresponding type -- and string_col = long_const should return false @@ -136,7 +137,7 @@ STAGE PLANS: alias: infertypes Statistics: Num rows: 1 Data size: 117 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: false (type: boolean) + predicate: ((UDFToDouble(ti) = 128.0) or (UDFToDouble(si) = 32768.0) or (UDFToDouble(i) = 2.147483648E9) or (UDFToDouble(bi) = 9.223372036854776E18)) (type: boolean) Statistics: Num rows: 1 Data size: 117 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ti (type: tinyint), si (type: smallint), i (type: int), bi (type: bigint), fl (type: float), db (type: double), str (type: string) @@ -156,6 +157,7 @@ STAGE PLANS: Processor Tree: ListSink +WARNING: Comparing a bigint and a double may result in a loss of precision. PREHOOK: query: SELECT * FROM infertypes WHERE ti = '128' OR si = 32768 OR @@ -200,7 +202,7 @@ STAGE PLANS: alias: infertypes Statistics: Num rows: 1 Data size: 117 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: false (type: boolean) + predicate: ((UDFToDouble(ti) = 127.0) or (UDFToDouble(si) = 327.0) or (UDFToDouble(i) = -100.0)) (type: boolean) Statistics: Num rows: 1 Data size: 117 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ti (type: tinyint), si (type: smallint), i (type: int), bi (type: bigint), fl (type: float), db (type: double), str (type: string) @@ -234,6 +236,7 @@ POSTHOOK: query: SELECT * FROM infertypes WHERE POSTHOOK: type: QUERY POSTHOOK: Input: default@infertypes #### A masked pattern was here #### +127 32767 12345 -12345 906.0 -307.0 1234 PREHOOK: query: EXPLAIN SELECT * FROM infertypes WHERE ti < '127.0' AND i > '100.0' AND http://git-wip-us.apache.org/repos/asf/hive/blob/b8f1ae11/ql/src/test/results/clientpositive/spark/vectorization_0.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/vectorization_0.q.out b/ql/src/test/results/clientpositive/spark/vectorization_0.q.out index 90bcc1b..3ad059c 100644 --- a/ql/src/test/results/clientpositive/spark/vectorization_0.q.out +++ b/ql/src/test/results/clientpositive/spark/vectorization_0.q.out @@ -994,7 +994,7 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((cstring2 like '%b%') or (79.553 <> UDFToDouble(cint)) or (UDFToDouble(cbigint) < cdouble)) (type: boolean) + predicate: ((cstring2 like '%b%') or (79.553 <> UDFToDouble(cint)) or (UDFToDouble(cbigint) < cdouble) or ((UDFToShort(ctinyint) >= csmallint) and (cboolean2 = 1) and (3569.0 = UDFToDouble(ctinyint)))) (type: boolean) Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint), cfloat (type: float), ctinyint (type: tinyint) http://git-wip-us.apache.org/repos/asf/hive/blob/b8f1ae11/ql/src/test/results/clientpositive/spark/vectorization_short_regress.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/vectorization_short_regress.q.out b/ql/src/test/results/clientpositive/spark/vectorization_short_regress.q.out index 6bd1bb2..3d17aba 100644 --- a/ql/src/test/results/clientpositive/spark/vectorization_short_regress.q.out +++ b/ql/src/test/results/clientpositive/spark/vectorization_short_regress.q.out @@ -2085,23 +2085,23 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((cdouble > 2563.58) and (((cbigint >= UDFToLong(cint)) and (UDFToInteger(csmallint) < cint) and (UDFToDouble(cfloat) < -5638.15)) or ((cdouble <= UDFToDouble(cbigint)) and (-5638.15 > UDFToDouble(cbigint))))) (type: boolean) - Statistics: Num rows: 606 Data size: 18603 Basic stats: COMPLETE Column stats: NONE + predicate: ((cdouble > 2563.58) and (((cbigint >= UDFToLong(cint)) and (UDFToInteger(csmallint) < cint) and (UDFToDouble(cfloat) < -5638.15)) or (2563.58 = UDFToDouble(ctinyint)) or ((cdouble <= UDFToDouble(cbigint)) and (-5638.15 > UDFToDouble(cbigint))))) (type: boolean) + Statistics: Num rows: 2654 Data size: 81476 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdouble (type: double), cfloat (type: float) outputColumnNames: _col0, _col1 - Statistics: Num rows: 606 Data size: 18603 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2654 Data size: 81476 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: var_samp(_col0), count(_col1), sum(_col1), var_pop(_col0), stddev_pop(_col0), sum(_col0) keys: _col0 (type: double) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 606 Data size: 18603 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2654 Data size: 81476 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: double) sort order: + Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 606 Data size: 18603 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2654 Data size: 81476 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: struct<count:bigint,sum:double,variance:double>), _col2 (type: bigint), _col3 (type: double), _col4 (type: struct<count:bigint,sum:double,variance:double>), _col5 (type: struct<count:bigint,sum:double,variance:double>), _col6 (type: double) Execution mode: vectorized Reducer 2 @@ -2111,25 +2111,25 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 303 Data size: 9301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1327 Data size: 40738 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: double), _col1 (type: double), _col5 (type: double), (_col0 + _col1) (type: double), (_col0 * 762.0) (type: double), _col6 (type: double), (-863.257 % (_col0 * 762.0)) (type: double), (2563.58 * _col1) (type: double), (- _col1) (type: double), _col2 (type: bigint), ((2563.58 * _col1) + -5638.15) (type: double), ((- _col1) * ((2563.58 * _col1) + -5638.15)) (type: double), _col3 (type: double), _col4 (type: double), (_col0 - (- _col1)) (type: double) outputColumnNames: _col0, _col1, _col10, _col11, _col12, _col13, _col14, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 303 Data size: 9301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1327 Data size: 40738 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: double) sort order: + - Statistics: Num rows: 303 Data size: 9301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1327 Data size: 40738 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: double), _col4 (type: bigint), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: double), _col13 (type: double), _col14 (type: double) Reducer 3 Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: double), VALUE._col0 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: double), VALUE._col3 (type: bigint), VALUE._col4 (type: double), VALUE._col5 (type: double), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: double), VALUE._col9 (type: double), VALUE._col10 (type: double), VALUE._col11 (type: double), VALUE._col12 (type: double), VALUE._col13 (type: double), VALUE._col12 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15 - Statistics: Num rows: 303 Data size: 9301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1327 Data size: 40738 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 303 Data size: 9301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1327 Data size: 40738 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/b8f1ae11/ql/src/test/results/clientpositive/tez/vectorization_0.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/tez/vectorization_0.q.out b/ql/src/test/results/clientpositive/tez/vectorization_0.q.out index cfbe9ce..18e042d 100644 --- a/ql/src/test/results/clientpositive/tez/vectorization_0.q.out +++ b/ql/src/test/results/clientpositive/tez/vectorization_0.q.out @@ -994,7 +994,7 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((cstring2 like '%b%') or (79.553 <> UDFToDouble(cint)) or (UDFToDouble(cbigint) < cdouble)) (type: boolean) + predicate: ((cstring2 like '%b%') or (79.553 <> UDFToDouble(cint)) or (UDFToDouble(cbigint) < cdouble) or ((UDFToShort(ctinyint) >= csmallint) and (cboolean2 = 1) and (3569.0 = UDFToDouble(ctinyint)))) (type: boolean) Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint), cfloat (type: float), ctinyint (type: tinyint) http://git-wip-us.apache.org/repos/asf/hive/blob/b8f1ae11/ql/src/test/results/clientpositive/tez/vectorization_short_regress.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/tez/vectorization_short_regress.q.out b/ql/src/test/results/clientpositive/tez/vectorization_short_regress.q.out index 5e0d42c..59b457a 100644 --- a/ql/src/test/results/clientpositive/tez/vectorization_short_regress.q.out +++ b/ql/src/test/results/clientpositive/tez/vectorization_short_regress.q.out @@ -2085,23 +2085,23 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((cdouble > 2563.58) and (((cbigint >= UDFToLong(cint)) and (UDFToInteger(csmallint) < cint) and (UDFToDouble(cfloat) < -5638.15)) or ((cdouble <= UDFToDouble(cbigint)) and (-5638.15 > UDFToDouble(cbigint))))) (type: boolean) - Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE + predicate: ((cdouble > 2563.58) and (((cbigint >= UDFToLong(cint)) and (UDFToInteger(csmallint) < cint) and (UDFToDouble(cfloat) < -5638.15)) or (2563.58 = UDFToDouble(ctinyint)) or ((cdouble <= UDFToDouble(cbigint)) and (-5638.15 > UDFToDouble(cbigint))))) (type: boolean) + Statistics: Num rows: 2654 Data size: 570619 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdouble (type: double), cfloat (type: float) outputColumnNames: _col0, _col1 - Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2654 Data size: 570619 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: var_samp(_col0), count(_col1), sum(_col1), var_pop(_col0), stddev_pop(_col0), sum(_col0) keys: _col0 (type: double) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2654 Data size: 570619 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: double) sort order: + Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2654 Data size: 570619 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: struct<count:bigint,sum:double,variance:double>), _col2 (type: bigint), _col3 (type: double), _col4 (type: struct<count:bigint,sum:double,variance:double>), _col5 (type: struct<count:bigint,sum:double,variance:double>), _col6 (type: double) Execution mode: vectorized Reducer 2 @@ -2111,25 +2111,25 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1327 Data size: 285309 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: double), _col1 (type: double), _col5 (type: double), (_col0 + _col1) (type: double), (_col0 * 762.0) (type: double), _col6 (type: double), (-863.257 % (_col0 * 762.0)) (type: double), (2563.58 * _col1) (type: double), (- _col1) (type: double), _col2 (type: bigint), ((2563.58 * _col1) + -5638.15) (type: double), ((- _col1) * ((2563.58 * _col1) + -5638.15)) (type: double), _col3 (type: double), _col4 (type: double), (_col0 - (- _col1)) (type: double) outputColumnNames: _col0, _col1, _col10, _col11, _col12, _col13, _col14, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1327 Data size: 285309 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: double) sort order: + - Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1327 Data size: 285309 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: double), _col4 (type: bigint), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: double), _col13 (type: double), _col14 (type: double) Reducer 3 Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: double), VALUE._col0 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: double), VALUE._col3 (type: bigint), VALUE._col4 (type: double), VALUE._col5 (type: double), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: double), VALUE._col9 (type: double), VALUE._col10 (type: double), VALUE._col11 (type: double), VALUE._col12 (type: double), VALUE._col13 (type: double), VALUE._col12 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15 - Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1327 Data size: 285309 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1327 Data size: 285309 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/b8f1ae11/ql/src/test/results/clientpositive/vectorization_0.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/vectorization_0.q.out b/ql/src/test/results/clientpositive/vectorization_0.q.out index 3fab2ff..89163cd 100644 --- a/ql/src/test/results/clientpositive/vectorization_0.q.out +++ b/ql/src/test/results/clientpositive/vectorization_0.q.out @@ -1010,7 +1010,7 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((cstring2 like '%b%') or (79.553 <> UDFToDouble(cint)) or (UDFToDouble(cbigint) < cdouble)) (type: boolean) + predicate: ((cstring2 like '%b%') or (79.553 <> UDFToDouble(cint)) or (UDFToDouble(cbigint) < cdouble) or ((UDFToShort(ctinyint) >= csmallint) and (cboolean2 = 1) and (3569.0 = UDFToDouble(ctinyint)))) (type: boolean) Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint), cfloat (type: float), ctinyint (type: tinyint) http://git-wip-us.apache.org/repos/asf/hive/blob/b8f1ae11/ql/src/test/results/clientpositive/vectorization_short_regress.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/vectorization_short_regress.q.out b/ql/src/test/results/clientpositive/vectorization_short_regress.q.out index f2cb3ec..728f628 100644 --- a/ql/src/test/results/clientpositive/vectorization_short_regress.q.out +++ b/ql/src/test/results/clientpositive/vectorization_short_regress.q.out @@ -2031,23 +2031,23 @@ STAGE PLANS: alias: alltypesorc Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((cdouble > 2563.58) and (((cbigint >= UDFToLong(cint)) and (UDFToInteger(csmallint) < cint) and (UDFToDouble(cfloat) < -5638.15)) or ((cdouble <= UDFToDouble(cbigint)) and (-5638.15 > UDFToDouble(cbigint))))) (type: boolean) - Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE + predicate: ((cdouble > 2563.58) and (((cbigint >= UDFToLong(cint)) and (UDFToInteger(csmallint) < cint) and (UDFToDouble(cfloat) < -5638.15)) or (2563.58 = UDFToDouble(ctinyint)) or ((cdouble <= UDFToDouble(cbigint)) and (-5638.15 > UDFToDouble(cbigint))))) (type: boolean) + Statistics: Num rows: 2654 Data size: 570619 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdouble (type: double), cfloat (type: float) outputColumnNames: _col0, _col1 - Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2654 Data size: 570619 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: var_samp(_col0), count(_col1), sum(_col1), var_pop(_col0), stddev_pop(_col0), sum(_col0) keys: _col0 (type: double) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2654 Data size: 570619 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: double) sort order: + Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2654 Data size: 570619 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: struct<count:bigint,sum:double,variance:double>), _col2 (type: bigint), _col3 (type: double), _col4 (type: struct<count:bigint,sum:double,variance:double>), _col5 (type: struct<count:bigint,sum:double,variance:double>), _col6 (type: double) Execution mode: vectorized Reduce Operator Tree: @@ -2056,11 +2056,11 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1327 Data size: 285309 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: double), _col1 (type: double), _col5 (type: double), (_col0 + _col1) (type: double), (_col0 * 762.0) (type: double), _col6 (type: double), (-863.257 % (_col0 * 762.0)) (type: double), (2563.58 * _col1) (type: double), (- _col1) (type: double), _col2 (type: bigint), ((2563.58 * _col1) + -5638.15) (type: double), ((- _col1) * ((2563.58 * _col1) + -5638.15)) (type: double), _col3 (type: double), _col4 (type: double), (_col0 - (- _col1)) (type: double) outputColumnNames: _col0, _col1, _col10, _col11, _col12, _col13, _col14, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1327 Data size: 285309 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -2075,16 +2075,16 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: double) sort order: + - Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1327 Data size: 285309 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: double), _col4 (type: bigint), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: double), _col13 (type: double), _col14 (type: double) Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: double), VALUE._col0 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: double), VALUE._col3 (type: bigint), VALUE._col4 (type: double), VALUE._col5 (type: double), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: double), VALUE._col9 (type: double), VALUE._col10 (type: double), VALUE._col11 (type: double), VALUE._col12 (type: double), VALUE._col13 (type: double), VALUE._col12 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15 - Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1327 Data size: 285309 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1327 Data size: 285309 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
