diff --git ql/src/gen/vectorization/ExpressionTemplates/FilterColumnCompareColumn.txt ql/src/gen/vectorization/ExpressionTemplates/FilterColumnCompareColumn.txt index ee80606..fb02c68 100644 --- ql/src/gen/vectorization/ExpressionTemplates/FilterColumnCompareColumn.txt +++ ql/src/gen/vectorization/ExpressionTemplates/FilterColumnCompareColumn.txt @@ -27,7 +27,7 @@ import org.apache.hadoop.hive.ql.exec.vector.VectorExpressionDescriptor; /** * Generated from template FilterColumnCompareColumn.txt, which covers binary comparison * expressions between two columns, however output is not produced in a separate column. - * The selected vector of the input {@link VectorizedRowBatch} is updated for in-place filtering. + * The selected vector of the input {@link org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch} is updated for in-place filtering. */ public class extends VectorExpression { diff --git ql/src/gen/vectorization/ExpressionTemplates/FilterColumnCompareScalar.txt ql/src/gen/vectorization/ExpressionTemplates/FilterColumnCompareScalar.txt index 248a66a..15b8e62 100644 --- ql/src/gen/vectorization/ExpressionTemplates/FilterColumnCompareScalar.txt +++ ql/src/gen/vectorization/ExpressionTemplates/FilterColumnCompareScalar.txt @@ -26,7 +26,7 @@ import org.apache.hadoop.hive.ql.exec.vector.VectorExpressionDescriptor; /** * Generated from template FilterColumnCompareScalar.txt, which covers binary comparison * expressions between a column and a scalar, however output is not produced in a separate column. - * The selected vector of the input {@link VectorizedRowBatch} is updated for in-place filtering. + * The selected vector of the input {@link org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch} is updated for in-place filtering. */ public class extends VectorExpression { diff --git ql/src/gen/vectorization/ExpressionTemplates/FilterDTIColumnCompareScalar.txt ql/src/gen/vectorization/ExpressionTemplates/FilterDTIColumnCompareScalar.txt index 2351230..0027033 100644 --- ql/src/gen/vectorization/ExpressionTemplates/FilterDTIColumnCompareScalar.txt +++ ql/src/gen/vectorization/ExpressionTemplates/FilterDTIColumnCompareScalar.txt @@ -24,7 +24,7 @@ import org.apache.hadoop.hive.ql.exec.vector.VectorExpressionDescriptor; * Generated from template FilterDTIColumnCompareScalar.txt, which covers comparison * expressions between a datetime/interval column and a scalar of the same type, however output is not * produced in a separate column. - * The selected vector of the input {@link VectorizedRowBatch} is updated for in-place filtering. + * The selected vector of the input {@link org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch} is updated for in-place filtering. */ public class extends { diff --git ql/src/gen/vectorization/ExpressionTemplates/FilterDTIScalarCompareColumn.txt ql/src/gen/vectorization/ExpressionTemplates/FilterDTIScalarCompareColumn.txt index f9fb12e..91cf4f7 100644 --- ql/src/gen/vectorization/ExpressionTemplates/FilterDTIScalarCompareColumn.txt +++ ql/src/gen/vectorization/ExpressionTemplates/FilterDTIScalarCompareColumn.txt @@ -24,7 +24,7 @@ import org.apache.hadoop.hive.ql.exec.vector.VectorExpressionDescriptor; * Generated from template FilterDTIScalarCompareColumn.txt, which covers comparison * expressions between a datetime/interval scalar and a column of the same type, * however output is not produced in a separate column. - * The selected vector of the input {@link VectorizedRowBatch} is updated for in-place filtering. + * The selected vector of the input {@link org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch} is updated for in-place filtering. */ public class extends { diff --git ql/src/gen/vectorization/ExpressionTemplates/FilterDecimalColumnCompareDecimalColumn.txt ql/src/gen/vectorization/ExpressionTemplates/FilterDecimalColumnCompareDecimalColumn.txt index ee450d3..4edb371 100644 --- ql/src/gen/vectorization/ExpressionTemplates/FilterDecimalColumnCompareDecimalColumn.txt +++ ql/src/gen/vectorization/ExpressionTemplates/FilterDecimalColumnCompareDecimalColumn.txt @@ -27,7 +27,7 @@ import org.apache.hadoop.hive.serde2.io.HiveDecimalWritable; /** * Generated from template FilterDecimalColumnCompareColumn.txt, which covers binary comparison * filter expressions between two columns. Output is not produced in a separate column. - * The selected vector of the input {@link VectorizedRowBatch} is updated for in-place filtering. + * The selected vector of the input {@link org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch} is updated for in-place filtering. */ public class extends VectorExpression { diff --git ql/src/gen/vectorization/ExpressionTemplates/FilterDecimalColumnCompareDecimalScalar.txt ql/src/gen/vectorization/ExpressionTemplates/FilterDecimalColumnCompareDecimalScalar.txt index 9943f45..4a116ec 100644 --- ql/src/gen/vectorization/ExpressionTemplates/FilterDecimalColumnCompareDecimalScalar.txt +++ ql/src/gen/vectorization/ExpressionTemplates/FilterDecimalColumnCompareDecimalScalar.txt @@ -27,7 +27,7 @@ import org.apache.hadoop.hive.serde2.io.HiveDecimalWritable; import org.apache.hadoop.hive.common.type.HiveDecimal; /** - * This is a generated class to evaluate a comparison on a vector of decimal + * This is a generated class to evaluate a comparison on a vector of decimal * values. */ public class extends VectorExpression { diff --git ql/src/gen/vectorization/ExpressionTemplates/FilterDecimalScalarCompareDecimalColumn.txt ql/src/gen/vectorization/ExpressionTemplates/FilterDecimalScalarCompareDecimalColumn.txt index 4477aff..58f9a2f 100644 --- ql/src/gen/vectorization/ExpressionTemplates/FilterDecimalScalarCompareDecimalColumn.txt +++ ql/src/gen/vectorization/ExpressionTemplates/FilterDecimalScalarCompareDecimalColumn.txt @@ -27,7 +27,7 @@ import org.apache.hadoop.hive.serde2.io.HiveDecimalWritable; import org.apache.hadoop.hive.common.type.HiveDecimal; /** - * This is a generated class to evaluate a comparison on a vector of decimal + * This is a generated class to evaluate a comparison on a vector of decimal * values. */ public class extends VectorExpression { diff --git ql/src/gen/vectorization/ExpressionTemplates/FilterLongDoubleColumnCompareTimestampColumn.txt ql/src/gen/vectorization/ExpressionTemplates/FilterLongDoubleColumnCompareTimestampColumn.txt index 610c062..5cda930 100644 --- ql/src/gen/vectorization/ExpressionTemplates/FilterLongDoubleColumnCompareTimestampColumn.txt +++ ql/src/gen/vectorization/ExpressionTemplates/FilterLongDoubleColumnCompareTimestampColumn.txt @@ -30,7 +30,7 @@ import org.apache.hadoop.hive.ql.exec.vector.VectorExpressionDescriptor; /** * Generated from template FilterColumnCompareColumn.txt, which covers binary comparison * expressions between two columns, however output is not produced in a separate column. - * The selected vector of the input {@link VectorizedRowBatch} is updated for in-place filtering. + * The selected vector of the input {@link org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch} is updated for in-place filtering. */ public class extends VectorExpression { diff --git ql/src/gen/vectorization/ExpressionTemplates/FilterLongDoubleColumnCompareTimestampScalar.txt ql/src/gen/vectorization/ExpressionTemplates/FilterLongDoubleColumnCompareTimestampScalar.txt index 1b86691..5af0adb 100644 --- ql/src/gen/vectorization/ExpressionTemplates/FilterLongDoubleColumnCompareTimestampScalar.txt +++ ql/src/gen/vectorization/ExpressionTemplates/FilterLongDoubleColumnCompareTimestampScalar.txt @@ -29,7 +29,7 @@ import org.apache.hadoop.hive.ql.exec.vector.VectorExpressionDescriptor; /** * Generated from template FilterColumnCompareScalar.txt, which covers binary comparison * expressions between a column and a scalar, however output is not produced in a separate column. - * The selected vector of the input {@link VectorizedRowBatch} is updated for in-place filtering. + * The selected vector of the input {@link org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch} is updated for in-place filtering. */ public class extends { diff --git ql/src/gen/vectorization/ExpressionTemplates/FilterLongDoubleScalarCompareTimestampColumn.txt ql/src/gen/vectorization/ExpressionTemplates/FilterLongDoubleScalarCompareTimestampColumn.txt index 73c46a1..1f07ed9 100644 --- ql/src/gen/vectorization/ExpressionTemplates/FilterLongDoubleScalarCompareTimestampColumn.txt +++ ql/src/gen/vectorization/ExpressionTemplates/FilterLongDoubleScalarCompareTimestampColumn.txt @@ -30,7 +30,7 @@ import org.apache.hadoop.hive.ql.exec.vector.VectorExpressionDescriptor; /** * Generated from template FilterScalarCompareTimestampColumn.txt, which covers comparison * expressions between a long/double scalar and a timestamp column, however output is not produced - * in a separate column. The selected vector of the input {@link VectorizedRowBatch} is updated + * in a separate column. The selected vector of the input {@link org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch} is updated * for in-place filtering. */ public class extends VectorExpression { diff --git ql/src/gen/vectorization/ExpressionTemplates/FilterScalarCompareColumn.txt ql/src/gen/vectorization/ExpressionTemplates/FilterScalarCompareColumn.txt index 037382c..549c923 100644 --- ql/src/gen/vectorization/ExpressionTemplates/FilterScalarCompareColumn.txt +++ ql/src/gen/vectorization/ExpressionTemplates/FilterScalarCompareColumn.txt @@ -26,7 +26,7 @@ import org.apache.hadoop.hive.ql.exec.vector.VectorExpressionDescriptor; /** * Generated from template FilterScalarCompareColumn.txt, which covers binary comparison * expressions between a scalar and a column, however output is not produced in a separate column. - * The selected vector of the input {@link VectorizedRowBatch} is updated for in-place filtering. + * The selected vector of the input {@link org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch} is updated for in-place filtering. */ public class extends VectorExpression { diff --git ql/src/gen/vectorization/ExpressionTemplates/FilterStringGroupColumnCompareStringGroupScalarBase.txt ql/src/gen/vectorization/ExpressionTemplates/FilterStringGroupColumnCompareStringGroupScalarBase.txt index 916bc12..70e601f 100644 --- ql/src/gen/vectorization/ExpressionTemplates/FilterStringGroupColumnCompareStringGroupScalarBase.txt +++ ql/src/gen/vectorization/ExpressionTemplates/FilterStringGroupColumnCompareStringGroupScalarBase.txt @@ -27,7 +27,7 @@ import org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch; import org.apache.hadoop.hive.ql.exec.vector.VectorExpressionDescriptor; /** - * This is a generated class to evaluate a comparison on a vector of strings. + * This is a generated class to evaluate a comparison on a vector of strings. */ public abstract class extends VectorExpression { diff --git ql/src/gen/vectorization/ExpressionTemplates/FilterStringGroupColumnCompareStringScalar.txt ql/src/gen/vectorization/ExpressionTemplates/FilterStringGroupColumnCompareStringScalar.txt index 7ab9f66..ca8b5d9 100644 --- ql/src/gen/vectorization/ExpressionTemplates/FilterStringGroupColumnCompareStringScalar.txt +++ ql/src/gen/vectorization/ExpressionTemplates/FilterStringGroupColumnCompareStringScalar.txt @@ -27,7 +27,7 @@ import org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch; import org.apache.hadoop.hive.ql.exec.vector.VectorExpressionDescriptor; /** - * This is a generated class to evaluate a comparison on a vector of strings. + * This is a generated class to evaluate a comparison on a vector of strings. */ public class extends { diff --git ql/src/gen/vectorization/ExpressionTemplates/FilterStringGroupColumnCompareTruncStringScalar.txt ql/src/gen/vectorization/ExpressionTemplates/FilterStringGroupColumnCompareTruncStringScalar.txt index aa229c8..f75c924 100644 --- ql/src/gen/vectorization/ExpressionTemplates/FilterStringGroupColumnCompareTruncStringScalar.txt +++ ql/src/gen/vectorization/ExpressionTemplates/FilterStringGroupColumnCompareTruncStringScalar.txt @@ -29,7 +29,7 @@ import org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch; import org.apache.hadoop.hive.ql.exec.vector.VectorExpressionDescriptor; /** - * This is a generated class to evaluate a comparison on a vector of strings. + * This is a generated class to evaluate a comparison on a vector of strings. */ public class extends { diff --git ql/src/gen/vectorization/ExpressionTemplates/FilterStringGroupScalarCompareStringGroupColumnBase.txt ql/src/gen/vectorization/ExpressionTemplates/FilterStringGroupScalarCompareStringGroupColumnBase.txt index bfc58a1..9c66f8e 100644 --- ql/src/gen/vectorization/ExpressionTemplates/FilterStringGroupScalarCompareStringGroupColumnBase.txt +++ ql/src/gen/vectorization/ExpressionTemplates/FilterStringGroupScalarCompareStringGroupColumnBase.txt @@ -27,7 +27,7 @@ import org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch; import org.apache.hadoop.hive.ql.exec.vector.VectorExpressionDescriptor; /** - * This is a generated class to evaluate a comparison on a vector of strings. + * This is a generated class to evaluate a comparison on a vector of strings. * Do not edit the generated code directly. */ public abstract class extends VectorExpression { diff --git ql/src/gen/vectorization/ExpressionTemplates/FilterStringScalarCompareStringGroupColumn.txt ql/src/gen/vectorization/ExpressionTemplates/FilterStringScalarCompareStringGroupColumn.txt index bb638a4..ae1a0e3 100644 --- ql/src/gen/vectorization/ExpressionTemplates/FilterStringScalarCompareStringGroupColumn.txt +++ ql/src/gen/vectorization/ExpressionTemplates/FilterStringScalarCompareStringGroupColumn.txt @@ -27,7 +27,7 @@ import org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch; import org.apache.hadoop.hive.ql.exec.vector.VectorExpressionDescriptor; /** - * This is a generated class to evaluate a comparison on a vector of strings. + * This is a generated class to evaluate a comparison on a vector of strings. * Do not edit the generated code directly. */ public class extends { diff --git ql/src/gen/vectorization/ExpressionTemplates/FilterTimestampColumnCompareLongDoubleColumn.txt ql/src/gen/vectorization/ExpressionTemplates/FilterTimestampColumnCompareLongDoubleColumn.txt index 8873826..35ca40f 100644 --- ql/src/gen/vectorization/ExpressionTemplates/FilterTimestampColumnCompareLongDoubleColumn.txt +++ ql/src/gen/vectorization/ExpressionTemplates/FilterTimestampColumnCompareLongDoubleColumn.txt @@ -27,7 +27,7 @@ import org.apache.hadoop.hive.ql.exec.vector.VectorExpressionDescriptor; /** * Generated from template FilterColumnCompareColumn.txt, which covers binary comparison * expressions between two columns, however output is not produced in a separate column. - * The selected vector of the input {@link VectorizedRowBatch} is updated for in-place filtering. + * The selected vector of the input {@link org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch} is updated for in-place filtering. */ public class extends VectorExpression { diff --git ql/src/gen/vectorization/ExpressionTemplates/FilterTimestampColumnCompareLongDoubleScalar.txt ql/src/gen/vectorization/ExpressionTemplates/FilterTimestampColumnCompareLongDoubleScalar.txt index 8583eee..0a5419b 100644 --- ql/src/gen/vectorization/ExpressionTemplates/FilterTimestampColumnCompareLongDoubleScalar.txt +++ ql/src/gen/vectorization/ExpressionTemplates/FilterTimestampColumnCompareLongDoubleScalar.txt @@ -26,7 +26,7 @@ import org.apache.hadoop.hive.ql.exec.vector.VectorExpressionDescriptor; /** * Generated from template FilterTimestampColumnCompareScalar.txt, which covers comparison * expressions between a timestamp column and a long/double scalar, however output is not produced - * in a separate column. The selected vector of the input {@link VectorizedRowBatch} is updated + * in a separate column. The selected vector of the input {@link org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch} is updated * for in-place filtering. */ public class extends VectorExpression { diff --git ql/src/gen/vectorization/ExpressionTemplates/FilterTimestampColumnCompareTimestampColumn.txt ql/src/gen/vectorization/ExpressionTemplates/FilterTimestampColumnCompareTimestampColumn.txt index eeb73c9..0e1c9fe 100644 --- ql/src/gen/vectorization/ExpressionTemplates/FilterTimestampColumnCompareTimestampColumn.txt +++ ql/src/gen/vectorization/ExpressionTemplates/FilterTimestampColumnCompareTimestampColumn.txt @@ -31,7 +31,7 @@ import org.apache.hadoop.hive.serde2.io.HiveDecimalWritable; /** * Generated from template FilterTimestampColumnCompareColumn.txt, which covers binary comparison * filter expressions between two columns. Output is not produced in a separate column. - * The selected vector of the input {@link VectorizedRowBatch} is updated for in-place filtering. + * The selected vector of the input {@link org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch} is updated for in-place filtering. */ public class extends VectorExpression { diff --git ql/src/gen/vectorization/ExpressionTemplates/FilterTimestampColumnCompareTimestampScalar.txt ql/src/gen/vectorization/ExpressionTemplates/FilterTimestampColumnCompareTimestampScalar.txt index 23790a5..034af81 100644 --- ql/src/gen/vectorization/ExpressionTemplates/FilterTimestampColumnCompareTimestampScalar.txt +++ ql/src/gen/vectorization/ExpressionTemplates/FilterTimestampColumnCompareTimestampScalar.txt @@ -30,7 +30,7 @@ import org.apache.hadoop.hive.ql.exec.vector.VectorExpressionDescriptor; /** * Generated from template FilterColumnCompareScalar.txt, which covers binary comparison * expressions between a column and a scalar, however output is not produced in a separate column. - * The selected vector of the input {@link VectorizedRowBatch} is updated for in-place filtering. + * The selected vector of the input {@link org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch} is updated for in-place filtering. */ public class extends VectorExpression { diff --git ql/src/gen/vectorization/ExpressionTemplates/FilterTimestampScalarCompareLongDoubleColumn.txt ql/src/gen/vectorization/ExpressionTemplates/FilterTimestampScalarCompareLongDoubleColumn.txt index 0e10779..1b4c4da 100644 --- ql/src/gen/vectorization/ExpressionTemplates/FilterTimestampScalarCompareLongDoubleColumn.txt +++ ql/src/gen/vectorization/ExpressionTemplates/FilterTimestampScalarCompareLongDoubleColumn.txt @@ -28,7 +28,7 @@ import org.apache.hadoop.hive.ql.exec.vector.VectorExpressionDescriptor; /** * Generated from template FilterScalarCompareColumn.txt, which covers binary comparison * expressions between a scalar and a column, however output is not produced in a separate column. - * The selected vector of the input {@link VectorizedRowBatch} is updated for in-place filtering. + * The selected vector of the input {@link org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch} is updated for in-place filtering. */ public class extends { diff --git ql/src/gen/vectorization/ExpressionTemplates/FilterTimestampScalarCompareTimestampColumn.txt ql/src/gen/vectorization/ExpressionTemplates/FilterTimestampScalarCompareTimestampColumn.txt index 5a6def3..0439b4e 100644 --- ql/src/gen/vectorization/ExpressionTemplates/FilterTimestampScalarCompareTimestampColumn.txt +++ ql/src/gen/vectorization/ExpressionTemplates/FilterTimestampScalarCompareTimestampColumn.txt @@ -30,7 +30,7 @@ import org.apache.hadoop.hive.serde2.io.HiveDecimalWritable; import org.apache.hadoop.hive.common.type.HiveDecimal; /** - * This is a generated class to evaluate a comparison on a vector of timestamp + * This is a generated class to evaluate a comparison on a vector of timestamp * values. */ public class extends VectorExpression { diff --git ql/src/gen/vectorization/ExpressionTemplates/FilterTruncStringScalarCompareStringGroupColumn.txt ql/src/gen/vectorization/ExpressionTemplates/FilterTruncStringScalarCompareStringGroupColumn.txt index c4745d3..53681ee 100644 --- ql/src/gen/vectorization/ExpressionTemplates/FilterTruncStringScalarCompareStringGroupColumn.txt +++ ql/src/gen/vectorization/ExpressionTemplates/FilterTruncStringScalarCompareStringGroupColumn.txt @@ -29,7 +29,7 @@ import org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch; import org.apache.hadoop.hive.ql.exec.vector.VectorExpressionDescriptor; /** - * This is a generated class to evaluate a comparison on a vector of strings. + * This is a generated class to evaluate a comparison on a vector of strings. * Do not edit the generated code directly. */ public class extends { diff --git ql/src/gen/vectorization/ExpressionTemplates/StringGroupColumnCompareStringGroupScalarBase.txt ql/src/gen/vectorization/ExpressionTemplates/StringGroupColumnCompareStringGroupScalarBase.txt index 08b3e75..7f34c05 100644 --- ql/src/gen/vectorization/ExpressionTemplates/StringGroupColumnCompareStringGroupScalarBase.txt +++ ql/src/gen/vectorization/ExpressionTemplates/StringGroupColumnCompareStringGroupScalarBase.txt @@ -28,7 +28,7 @@ import org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch; import org.apache.hadoop.hive.ql.exec.vector.VectorExpressionDescriptor; /** - * This is a generated class to evaluate a comparison on a vector of strings. + * This is a generated class to evaluate a comparison on a vector of strings. */ public abstract class extends VectorExpression { diff --git ql/src/gen/vectorization/ExpressionTemplates/StringGroupColumnCompareStringScalar.txt ql/src/gen/vectorization/ExpressionTemplates/StringGroupColumnCompareStringScalar.txt index 9b11c5e..f478f36 100644 --- ql/src/gen/vectorization/ExpressionTemplates/StringGroupColumnCompareStringScalar.txt +++ ql/src/gen/vectorization/ExpressionTemplates/StringGroupColumnCompareStringScalar.txt @@ -28,7 +28,7 @@ import org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch; import org.apache.hadoop.hive.ql.exec.vector.VectorExpressionDescriptor; /** - * This is a generated class to evaluate a comparison on a vector of strings. + * This is a generated class to evaluate a comparison on a vector of strings. */ public class extends { diff --git ql/src/gen/vectorization/ExpressionTemplates/StringGroupColumnCompareTruncStringScalar.txt ql/src/gen/vectorization/ExpressionTemplates/StringGroupColumnCompareTruncStringScalar.txt index 969fe1b..d894935 100644 --- ql/src/gen/vectorization/ExpressionTemplates/StringGroupColumnCompareTruncStringScalar.txt +++ ql/src/gen/vectorization/ExpressionTemplates/StringGroupColumnCompareTruncStringScalar.txt @@ -32,7 +32,7 @@ import org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch; import org.apache.hadoop.hive.ql.exec.vector.VectorExpressionDescriptor; /** - * This is a generated class to evaluate a comparison on a vector of strings. + * This is a generated class to evaluate a comparison on a vector of strings. */ public class extends { diff --git ql/src/gen/vectorization/ExpressionTemplates/StringGroupScalarCompareStringGroupColumnBase.txt ql/src/gen/vectorization/ExpressionTemplates/StringGroupScalarCompareStringGroupColumnBase.txt index dee2bfc..f34e534 100644 --- ql/src/gen/vectorization/ExpressionTemplates/StringGroupScalarCompareStringGroupColumnBase.txt +++ ql/src/gen/vectorization/ExpressionTemplates/StringGroupScalarCompareStringGroupColumnBase.txt @@ -28,7 +28,7 @@ import org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch; import org.apache.hadoop.hive.ql.exec.vector.VectorExpressionDescriptor; /** - * This is a generated class to evaluate a comparison on a vector of strings. + * This is a generated class to evaluate a comparison on a vector of strings. * Do not edit the generated code directly. */ public abstract class extends VectorExpression { diff --git ql/src/gen/vectorization/ExpressionTemplates/StringScalarCompareStringGroupColumn.txt ql/src/gen/vectorization/ExpressionTemplates/StringScalarCompareStringGroupColumn.txt index 5b5e02e..e656a43 100644 --- ql/src/gen/vectorization/ExpressionTemplates/StringScalarCompareStringGroupColumn.txt +++ ql/src/gen/vectorization/ExpressionTemplates/StringScalarCompareStringGroupColumn.txt @@ -28,7 +28,7 @@ import org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch; import org.apache.hadoop.hive.ql.exec.vector.VectorExpressionDescriptor; /** - * This is a generated class to evaluate a comparison on a vector of strings. + * This is a generated class to evaluate a comparison on a vector of strings. * Do not edit the generated code directly. */ public class extends { diff --git ql/src/gen/vectorization/ExpressionTemplates/TruncStringScalarCompareStringGroupColumn.txt ql/src/gen/vectorization/ExpressionTemplates/TruncStringScalarCompareStringGroupColumn.txt index 26da73a..5ad8da9 100644 --- ql/src/gen/vectorization/ExpressionTemplates/TruncStringScalarCompareStringGroupColumn.txt +++ ql/src/gen/vectorization/ExpressionTemplates/TruncStringScalarCompareStringGroupColumn.txt @@ -32,7 +32,7 @@ import org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch; import org.apache.hadoop.hive.ql.exec.vector.VectorExpressionDescriptor; /** - * This is a generated class to evaluate a comparison on a vector of strings. + * This is a generated class to evaluate a comparison on a vector of strings. * Do not edit the generated code directly. */ public class extends { diff --git ql/src/java/org/apache/hadoop/hive/ql/exec/AbstractFileMergeOperator.java ql/src/java/org/apache/hadoop/hive/ql/exec/AbstractFileMergeOperator.java index dfad6c1..ff71411 100644 --- ql/src/java/org/apache/hadoop/hive/ql/exec/AbstractFileMergeOperator.java +++ ql/src/java/org/apache/hadoop/hive/ql/exec/AbstractFileMergeOperator.java @@ -115,8 +115,8 @@ private void updatePaths(Path tp, Path ttp) { /** * Fixes tmpPath to point to the correct partition. Initialize operator will * set tmpPath and taskTmpPath based on root table directory. So initially, - * tmpPath will be /_tmp.-ext-10000 and taskTmpPath will be - * /_task_tmp.-ext-10000. The depth of these two paths will be 0. + * tmpPath will be <prefix>/_tmp.-ext-10000 and taskTmpPath will be + * <prefix>/_task_tmp.-ext-10000. The depth of these two paths will be 0. * Now, in case of dynamic partitioning or list bucketing the inputPath will * have additional sub-directories under root table directory. This function * updates the tmpPath and taskTmpPath to reflect these additional @@ -129,10 +129,10 @@ private void updatePaths(Path tp, Path ttp) { * Note: The path difference between inputPath and tmpDepth can be DP or DP+LB. * This method will automatically handle it. * - * Continuing the example above, if inputPath is /-ext-10000/hr=a1/, + * Continuing the example above, if inputPath is <prefix>/-ext-10000/hr=a1/, * newPath will be hr=a1/. Then, tmpPath and taskTmpPath will be updated to - * /-ext-10000/hr=a1/_tmp.ext-10000 and - * /-ext-10000/hr=a1/_task_tmp.ext-10000 respectively. + * <prefix>/-ext-10000/hr=a1/_tmp.ext-10000 and + * <prefix>/-ext-10000/hr=a1/_task_tmp.ext-10000 respectively. * We have list_bucket_dml_6.q cover this case: DP + LP + multiple skewed * values + merge. * diff --git ql/src/java/org/apache/hadoop/hive/ql/exec/CommonJoinOperator.java ql/src/java/org/apache/hadoop/hive/ql/exec/CommonJoinOperator.java index df1898e..79daeea 100644 --- ql/src/java/org/apache/hadoop/hive/ql/exec/CommonJoinOperator.java +++ ql/src/java/org/apache/hadoop/hive/ql/exec/CommonJoinOperator.java @@ -70,8 +70,8 @@ * evaluated before emitting rows. Currently, relevant only for outer joins. * * For instance, given the query: - * select * from t1 right outer join t2 on t1.c1 + t2.c2 > t1.c3; - * The expression evaluator for t1.c1 + t2.c2 > t1.c3 will be stored in this list. + * select * from t1 right outer join t2 on t1.c1 + t2.c2 > t1.c3; + * The expression evaluator for t1.c1 + t2.c2 > t1.c3 will be stored in this list. */ protected transient List residualJoinFilters; @@ -437,21 +437,21 @@ protected long getNextSize(long sz) { * a = 100, 10 | 100, 20 | 100, 30 * b = 100, 10 | 100, 20 | 100, 30 * - * the query "a FO b ON a.k=b.k AND a.v>10 AND b.v>30" makes filter map - * 0(a) = [1(b),1] : a.v>10 - * 1(b) = [0(a),1] : b.v>30 + * the query "a FO b ON a.k=b.k AND a.v>10 AND b.v>30" makes filter map + * 0(a) = [1(b),1] : a.v>10 + * 1(b) = [0(a),1] : b.v>0 * * for filtered rows in a (100,10) create a-NULL * for filtered rows in b (100,10) (100,20) (100,30) create NULL-b * - * with 0(a) = [1(b),1] : a.v>10 + * with 0(a) = [1(b),1] : a.v>10 * 100, 10 = 00000010 (filtered) * 100, 20 = 00000000 (valid) * 100, 30 = 00000000 (valid) * ------------------------- * sum = 00000000 : for valid rows in b, there is at least one pair in a * - * with 1(b) = [0(a),1] : b.v>30 + * with 1(b) = [0(a),1] : b.v>30 * 100, 10 = 00000001 (filtered) * 100, 20 = 00000001 (filtered) * 100, 30 = 00000001 (filtered) diff --git ql/src/java/org/apache/hadoop/hive/ql/exec/ComparisonOpMethodResolver.java ql/src/java/org/apache/hadoop/hive/ql/exec/ComparisonOpMethodResolver.java index 41a9cb3..794291a 100644 --- ql/src/java/org/apache/hadoop/hive/ql/exec/ComparisonOpMethodResolver.java +++ ql/src/java/org/apache/hadoop/hive/ql/exec/ComparisonOpMethodResolver.java @@ -28,8 +28,8 @@ import org.apache.hadoop.hive.serde2.typeinfo.TypeInfoUtils; /** - * The class implements the method resolution for operators like (> < <= >= = - * <>). The resolution logic is as follows: 1. If one of the parameters is null, + * The class implements the method resolution for operators like (> < <= >= = + * <>). The resolution logic is as follows: 1. If one of the parameters is null, * then it resolves to evaluate(Double, Double) 2. If both of the parameters are * of type T, then it resolves to evaluate(T, T) 3. If 1 and 2 fails then it * resolves to evaluate(Double, Double). diff --git ql/src/java/org/apache/hadoop/hive/ql/exec/DDLTask.java ql/src/java/org/apache/hadoop/hive/ql/exec/DDLTask.java index 757b7fc..a1e2f5d 100644 --- ql/src/java/org/apache/hadoop/hive/ql/exec/DDLTask.java +++ ql/src/java/org/apache/hadoop/hive/ql/exec/DDLTask.java @@ -4768,13 +4768,13 @@ private void makeLocationQualified(CreateIndexDesc crtIndex, String name) throws } } - /** + public static final String DATABASE_PATH_SUFFIX = ".db"; + /** * Make qualified location for a database . * * @param database * Database. */ - public static final String DATABASE_PATH_SUFFIX = ".db"; private void makeLocationQualified(Database database) throws HiveException { if (database.isSetLocationUri()) { database.setLocationUri(Utilities.getQualifiedPath(conf, new Path(database.getLocationUri()))); diff --git ql/src/java/org/apache/hadoop/hive/ql/exec/DummyStoreOperator.java ql/src/java/org/apache/hadoop/hive/ql/exec/DummyStoreOperator.java index 2a1be63..9d3507d 100644 --- ql/src/java/org/apache/hadoop/hive/ql/exec/DummyStoreOperator.java +++ ql/src/java/org/apache/hadoop/hive/ql/exec/DummyStoreOperator.java @@ -36,9 +36,9 @@ * Consider a query like: * * select * from - * (subq1 --> has a filter) + * (subq1 --> has a filter) * join - * (subq2 --> has a filter) + * (subq2 --> has a filter) * on some key * * Let us assume that subq1 is the small table (either specified by the user or inferred @@ -50,12 +50,12 @@ * * Therefore the following operator tree is created: * - * TableScan (subq1) --> Select --> Filter --> DummyStore + * TableScan (subq1) --> Select --> Filter --> DummyStore * \ * \ SMBJoin * / * / - * TableScan (subq2) --> Select --> Filter + * TableScan (subq2) --> Select --> Filter * * In order to fetch the row with the least join key from the small table, the row from subq1 * is partially processed, and stored in DummyStore. For the actual processing of the join, diff --git ql/src/java/org/apache/hadoop/hive/ql/exec/FunctionRegistry.java ql/src/java/org/apache/hadoop/hive/ql/exec/FunctionRegistry.java index bf18a8d..36a3350 100644 --- ql/src/java/org/apache/hadoop/hive/ql/exec/FunctionRegistry.java +++ ql/src/java/org/apache/hadoop/hive/ql/exec/FunctionRegistry.java @@ -696,8 +696,8 @@ static int getCommonLength(int aLen, int bLen) { * return a TypeInfo corresponding to the common PrimitiveCategory, and with type qualifiers * (if applicable) that match the 2 TypeInfo types. * Examples: - * varchar(10), varchar(20), primitive category varchar => varchar(20) - * date, string, primitive category string => string + * varchar(10), varchar(20), primitive category varchar => varchar(20) + * date, string, primitive category string => string * @param a TypeInfo of the first type * @param b TypeInfo of the second type * @param typeCategory PrimitiveCategory of the designated common type between a and b @@ -1309,7 +1309,6 @@ public static Method getMethodInternal(Class udfClass, List mlist, bo /** * A shortcut to get the "index" GenericUDF. This is used for getting elements * out of array and getting values out of map. - * @throws SemanticException */ public static GenericUDF getGenericUDFForIndex() { try { @@ -1321,7 +1320,6 @@ public static GenericUDF getGenericUDFForIndex() { /** * A shortcut to get the "and" GenericUDF. - * @throws SemanticException */ public static GenericUDF getGenericUDFForAnd() { try { diff --git ql/src/java/org/apache/hadoop/hive/ql/exec/LateralViewJoinOperator.java ql/src/java/org/apache/hadoop/hive/ql/exec/LateralViewJoinOperator.java index cf3c5f0..1698ea0 100644 --- ql/src/java/org/apache/hadoop/hive/ql/exec/LateralViewJoinOperator.java +++ ql/src/java/org/apache/hadoop/hive/ql/exec/LateralViewJoinOperator.java @@ -64,7 +64,7 @@ * * The output of select in the left branch and output of the UDTF in the right * branch are then sent to the lateral view join (LVJ). In most cases, the UDTF - * will generate > 1 row for every row received from the TS, while the left + * will generate > 1 row for every row received from the TS, while the left * select operator will generate only one. For each row output from the TS, the * LVJ outputs all possible rows that can be created by joining the row from the * left select and one of the rows output from the UDTF. diff --git ql/src/java/org/apache/hadoop/hive/ql/exec/TopNHash.java ql/src/java/org/apache/hadoop/hive/ql/exec/TopNHash.java index 48ae02f..9ee8a1a 100644 --- ql/src/java/org/apache/hadoop/hive/ql/exec/TopNHash.java +++ ql/src/java/org/apache/hadoop/hive/ql/exec/TopNHash.java @@ -264,7 +264,7 @@ public void tryStoreVectorizedKey(HiveKey key, boolean partColsIsNull, int batch /** * Get vectorized batch result for particular index. * @param batchIndex index of the key in the batch. - * @return the result, same as from {@link #tryStoreKey(HiveKey)} + * @return the result, same as from {@link TopNHash#tryStoreKey(HiveKey,boolean)} */ public int getVectorizedBatchResult(int batchIndex) { int result = batchIndexToResult[batchIndex]; @@ -309,9 +309,8 @@ public int getVectorizedKeyHashCode(int batchIndex) { /** * Stores the value for the key in the heap. * @param index The index, either from tryStoreKey or from tryStoreVectorizedKey result. - * @param hasCode hashCode of key, used by ptfTopNHash. + * @param hashCode hashCode of key, used by ptfTopNHash. * @param value The value to store. - * @param keyHash The key hash to store. * @param vectorized Whether the result is coming from a vectorized batch. */ public void storeValue(int index, int hashCode, BytesWritable value, boolean vectorized) { diff --git ql/src/java/org/apache/hadoop/hive/ql/exec/UDAF.java ql/src/java/org/apache/hadoop/hive/ql/exec/UDAF.java index 57a2d71..3e771e1 100755 --- ql/src/java/org/apache/hadoop/hive/ql/exec/UDAF.java +++ ql/src/java/org/apache/hadoop/hive/ql/exec/UDAF.java @@ -20,9 +20,9 @@ /** * Please see the deprecation notice - *

+ *
* Base class for all User-defined Aggregation Function (UDAF) classes. - *

+ *
* Requirements for a UDAF class: *

    *
  1. Implement the {@code init()} method, which resets the status of the aggregation function.
  2. @@ -57,7 +57,7 @@ * aggregation result and returns a boolean. The method should always return * {@code true} on valid inputs, or the framework will throw an Exception. *
- *

+ *
* Following are some examples: *

    *
  • public int evaluatePartial();
  • @@ -65,7 +65,6 @@ *
  • public String evaluatePartial();
  • *
  • public boolean aggregatePartial(String partial);
  • *
- *

* * @deprecated Either implement {@link org.apache.hadoop.hive.ql.udf.generic.GenericUDAFResolver2} or extend * {@link org.apache.hadoop.hive.ql.udf.generic.AbstractGenericUDAFResolver} instead. diff --git ql/src/java/org/apache/hadoop/hive/ql/exec/Utilities.java ql/src/java/org/apache/hadoop/hive/ql/exec/Utilities.java index 9036d9e..047394c 100644 --- ql/src/java/org/apache/hadoop/hive/ql/exec/Utilities.java +++ ql/src/java/org/apache/hadoop/hive/ql/exec/Utilities.java @@ -1926,7 +1926,7 @@ public static String formatBinaryString(byte[] array, int start, int length) { * If there is no db name part, set the current sessions default db * @param dbtable * @return String array with two elements, first is db name, second is table name - * @throws HiveException + * @throws SemanticException */ public static String[] getDbTableName(String dbtable) throws SemanticException { return getDbTableName(SessionState.get().getCurrentDatabase(), dbtable); @@ -3585,9 +3585,9 @@ public static boolean isDefaultNameNode(HiveConf conf) { } /** - * Checks if the current HiveServer2 logging operation level is >= PERFORMANCE. + * Checks if the current HiveServer2 logging operation level is >= PERFORMANCE. * @param conf Hive configuration. - * @return true if current HiveServer2 logging operation level is >= PERFORMANCE. + * @return true if current HiveServer2 logging operation level is >= PERFORMANCE. * Else, false. */ public static boolean isPerfOrAboveLogging(HiveConf conf) { diff --git ql/src/java/org/apache/hadoop/hive/ql/exec/errors/ScriptErrorHeuristic.java ql/src/java/org/apache/hadoop/hive/ql/exec/errors/ScriptErrorHeuristic.java index 2d6d1b5..3a66c23 100644 --- ql/src/java/org/apache/hadoop/hive/ql/exec/errors/ScriptErrorHeuristic.java +++ ql/src/java/org/apache/hadoop/hive/ql/exec/errors/ScriptErrorHeuristic.java @@ -28,7 +28,7 @@ * * Conditions to check: * - * 1. "Script failed with code " is in the log + * 1. "Script failed with code <some number>" is in the log * */ diff --git ql/src/java/org/apache/hadoop/hive/ql/exec/persistence/BytesBytesMultiHashMap.java ql/src/java/org/apache/hadoop/hive/ql/exec/persistence/BytesBytesMultiHashMap.java index 360b639..782ff06 100644 --- ql/src/java/org/apache/hadoop/hive/ql/exec/persistence/BytesBytesMultiHashMap.java +++ ql/src/java/org/apache/hadoop/hive/ql/exec/persistence/BytesBytesMultiHashMap.java @@ -491,7 +491,7 @@ public byte getValueResult(byte[] key, int offset, int length, Result hashMapRes } /** - * Take the segment reference from {@link #getValueRefs(byte[], int, List)} + * Take the segment reference from getValueRefs(byte[],int,List) * result and makes it self-contained - adds byte array where the value is stored, and * updates the offset from "global" write buffers offset to offset within that array. */ diff --git ql/src/java/org/apache/hadoop/hive/ql/exec/tez/DagUtils.java ql/src/java/org/apache/hadoop/hive/ql/exec/tez/DagUtils.java index 6497495..fe271a0 100644 --- ql/src/java/org/apache/hadoop/hive/ql/exec/tez/DagUtils.java +++ ql/src/java/org/apache/hadoop/hive/ql/exec/tez/DagUtils.java @@ -839,7 +839,7 @@ public Path getDefaultDestDir(Configuration conf) throws LoginException, IOExcep * to provide on the cluster as resources for execution. * * @param conf - * @return List local resources to add to execution + * @return List<LocalResource> local resources to add to execution * @throws IOException when hdfs operation fails * @throws LoginException when getDefaultDestDir fails with the same exception */ @@ -883,7 +883,7 @@ public Path getDefaultDestDir(Configuration conf) throws LoginException, IOExcep * @param hdfsDirPathStr Destination directory in HDFS. * @param conf Configuration. * @param inputOutputJars The file names to localize. - * @return List local resources to add to execution + * @return List<LocalResource> local resources to add to execution * @throws IOException when hdfs operation fails. * @throws LoginException when getDefaultDestDir fails with the same exception */ diff --git ql/src/java/org/apache/hadoop/hive/ql/exec/tez/HivePreWarmProcessor.java ql/src/java/org/apache/hadoop/hive/ql/exec/tez/HivePreWarmProcessor.java index c10e53d..453e293 100644 --- ql/src/java/org/apache/hadoop/hive/ql/exec/tez/HivePreWarmProcessor.java +++ ql/src/java/org/apache/hadoop/hive/ql/exec/tez/HivePreWarmProcessor.java @@ -47,7 +47,7 @@ * A simple sleep processor implementation that sleeps for the configured * time in milliseconds. * - * @see Config for configuring the HivePreWarmProcessor + * @see Configuration for configuring the HivePreWarmProcessor */ public class HivePreWarmProcessor extends AbstractLogicalIOProcessor { diff --git ql/src/java/org/apache/hadoop/hive/ql/exec/tez/TezSessionState.java ql/src/java/org/apache/hadoop/hive/ql/exec/tez/TezSessionState.java index 036e918..2d04feb 100644 --- ql/src/java/org/apache/hadoop/hive/ql/exec/tez/TezSessionState.java +++ ql/src/java/org/apache/hadoop/hive/ql/exec/tez/TezSessionState.java @@ -167,11 +167,6 @@ public boolean isOpen() { return true; } - - /** - * Get all open sessions. Only used to clean up at shutdown. - * @return List - */ public static String makeSessionId() { return UUID.randomUUID().toString(); } @@ -189,7 +184,7 @@ public void open(HiveConf conf) * @throws URISyntaxException * @throws LoginException * @throws TezException - * @throws InterruptedException + * @throws IllegalArgumentException */ public void open(HiveConf conf, String[] additionalFiles) throws IOException, LoginException, IllegalArgumentException, URISyntaxException, TezException { diff --git ql/src/java/org/apache/hadoop/hive/ql/exec/vector/VectorHashKeyWrapper.java ql/src/java/org/apache/hadoop/hive/ql/exec/vector/VectorHashKeyWrapper.java index 3e1fcdd..922945a 100644 --- ql/src/java/org/apache/hadoop/hive/ql/exec/vector/VectorHashKeyWrapper.java +++ ql/src/java/org/apache/hadoop/hive/ql/exec/vector/VectorHashKeyWrapper.java @@ -38,7 +38,7 @@ * A hash map key wrapper for vectorized processing. * It stores the key values as primitives in arrays for each supported primitive type. * This works in conjunction with - * {@link org.apache.hadoop.hive.ql.exec.VectorHashKeyWrapperBatch VectorHashKeyWrapperBatch} + * {@link org.apache.hadoop.hive.ql.exec.vector.VectorHashKeyWrapperBatch VectorHashKeyWrapperBatch} * to hash vectorized processing units (batches). */ public class VectorHashKeyWrapper extends KeyWrapper { diff --git ql/src/java/org/apache/hadoop/hive/ql/exec/vector/VectorizedRowBatchCtx.java ql/src/java/org/apache/hadoop/hive/ql/exec/vector/VectorizedRowBatchCtx.java index e546a65..abfcaee 100644 --- ql/src/java/org/apache/hadoop/hive/ql/exec/vector/VectorizedRowBatchCtx.java +++ ql/src/java/org/apache/hadoop/hive/ql/exec/vector/VectorizedRowBatchCtx.java @@ -194,7 +194,6 @@ public static void getPartitionValues(VectorizedRowBatchCtx vrbCtx, PartitionDes * Creates a Vectorized row batch and the column vectors. * * @return VectorizedRowBatch - * @throws HiveException */ public VectorizedRowBatch createVectorizedRowBatch() { @@ -241,7 +240,6 @@ public VectorizedRowBatch createVectorizedRowBatch() * * @param batch * @param partitionValues - * @throws HiveException */ public void addPartitionColsToBatch(VectorizedRowBatch batch, Object[] partitionValues) { diff --git ql/src/java/org/apache/hadoop/hive/ql/exec/vector/expressions/CuckooSetBytes.java ql/src/java/org/apache/hadoop/hive/ql/exec/vector/expressions/CuckooSetBytes.java index 266365e..2f2bdc5 100644 --- ql/src/java/org/apache/hadoop/hive/ql/exec/vector/expressions/CuckooSetBytes.java +++ ql/src/java/org/apache/hadoop/hive/ql/exec/vector/expressions/CuckooSetBytes.java @@ -24,7 +24,7 @@ * A high-performance set implementation used to support fast set membership testing, * using Cuckoo hashing. This is used to support fast tests of the form * - * column IN ( getRealClass() throws IOException { return (Class) conf.getClass(SerializationSubclassKey, null, @@ -145,8 +140,6 @@ public Configuration getConf() { * deserialized; in this context, that assumption isn't necessarily true. * * @return the serialization object for this context - * @exception does - * not currently throw any IOException */ @Override public Serialization getSerialization() throws IOException { diff --git ql/src/java/org/apache/hadoop/hive/ql/io/HiveContextAwareRecordReader.java ql/src/java/org/apache/hadoop/hive/ql/io/HiveContextAwareRecordReader.java index 46f9970..617a507 100644 --- ql/src/java/org/apache/hadoop/hive/ql/io/HiveContextAwareRecordReader.java +++ ql/src/java/org/apache/hadoop/hive/ql/io/HiveContextAwareRecordReader.java @@ -50,7 +50,7 @@ * data. The binary search can be used by setting the value of inputFormatSorted in the * MapreduceWork to true, but it should only be used if the data is going to a FilterOperator, * which filters by comparing a value in the data with a constant, using one of the comparisons - * =, <, >, <=, >=. If the RecordReader's underlying format is an RCFile, this object can perform + * =, <, >, <=, >=. If the RecordReader's underlying format is an RCFile, this object can perform * a binary search to find the block to begin reading from, and stop reading once it can be * determined no other entries will match the filter. */ diff --git ql/src/java/org/apache/hadoop/hive/ql/io/HiveIgnoreKeyTextOutputFormat.java ql/src/java/org/apache/hadoop/hive/ql/io/HiveIgnoreKeyTextOutputFormat.java index 9ad7f37..d4fc6ea 100644 --- ql/src/java/org/apache/hadoop/hive/ql/io/HiveIgnoreKeyTextOutputFormat.java +++ ql/src/java/org/apache/hadoop/hive/ql/io/HiveIgnoreKeyTextOutputFormat.java @@ -37,8 +37,8 @@ import org.apache.hadoop.util.Progressable; /** - * HiveIgnoreKeyTextOutputFormat replaces key with null before feeding the to TextOutputFormat.RecordWriter. + * HiveIgnoreKeyTextOutputFormat replaces key with null before feeding the <key, + * value> to TextOutputFormat.RecordWriter. * */ public class HiveIgnoreKeyTextOutputFormat diff --git ql/src/java/org/apache/hadoop/hive/ql/io/IgnoreKeyTextOutputFormat.java ql/src/java/org/apache/hadoop/hive/ql/io/IgnoreKeyTextOutputFormat.java index 7eeaa3b..044ee46 100755 --- ql/src/java/org/apache/hadoop/hive/ql/io/IgnoreKeyTextOutputFormat.java +++ ql/src/java/org/apache/hadoop/hive/ql/io/IgnoreKeyTextOutputFormat.java @@ -30,7 +30,7 @@ import org.apache.hadoop.util.Progressable; /** - * This class replaces key with null before feeding the to + * This class replaces key with null before feeding the <key, value> to * TextOutputFormat.RecordWriter. * * @deprecated use {@link HiveIgnoreKeyTextOutputFormat} instead} diff --git ql/src/java/org/apache/hadoop/hive/ql/io/RCFile.java ql/src/java/org/apache/hadoop/hive/ql/io/RCFile.java index f41edc4..d089320 100644 --- ql/src/java/org/apache/hadoop/hive/ql/io/RCFile.java +++ ql/src/java/org/apache/hadoop/hive/ql/io/RCFile.java @@ -99,10 +99,10 @@ * The {@link Reader} is used to read and explain the bytes of RCFile. *

* - *

RCFile Formats

+ *

RCFile Formats

* * - * + * *
    *
  • version - 3 bytes of magic header RCF, followed by 1 byte of * actual version number (e.g. RCF1)
  • @@ -114,10 +114,10 @@ *
  • sync - A sync marker to denote end of the header.
  • *
* - *
RCFile Format
+ *

RCFile Format

*
    *
  • Header
  • - *
  • Record + *
  • Record
  • *
  • Key part *
      *
    • Record length in bytes
    • @@ -133,7 +133,6 @@ *
    • ...
    • *
    *
  • - * *
  • Value part *
      *
    • Compressed or plain data of [column_1_row_1_value, @@ -143,7 +142,6 @@ *
    *
  • *
- *

*

  * {@code
  * The following is a pseudo-BNF grammar for RCFile. Comments are prefixed
@@ -336,7 +334,6 @@
  * Text ::= VInt, Chars (Length prefixed UTF-8 characters)
  * }
  * 
- *

*/ public class RCFile { @@ -1095,7 +1092,7 @@ private void checkAndWriteSync() throws IOException { private int columnBufferSize = 0; /** - * Append a row of values. Currently it only can accept < + * Append a row of values. Currently it only can accept < * {@link BytesRefArrayWritable}. If its size() is less than the * column number in the file, zero bytes are appended for the empty columns. * If its size() is greater then the column number in the file, the exceeded diff --git ql/src/java/org/apache/hadoop/hive/ql/io/merge/MergeFileWork.java ql/src/java/org/apache/hadoop/hive/ql/io/merge/MergeFileWork.java index 94b9431..4f20e61 100644 --- ql/src/java/org/apache/hadoop/hive/ql/io/merge/MergeFileWork.java +++ ql/src/java/org/apache/hadoop/hive/ql/io/merge/MergeFileWork.java @@ -143,7 +143,7 @@ public void resolveDynamicPartitionStoredAsSubDirsMerge(HiveConf conf, /** * alter table ... concatenate - *

+ *
* If it is skewed table, use subdirectories in inputpaths. */ public void resolveConcatenateMerge(HiveConf conf) { diff --git ql/src/java/org/apache/hadoop/hive/ql/io/orc/package-info.java ql/src/java/org/apache/hadoop/hive/ql/io/orc/package-info.java index a591ce8..7d9a927 100644 --- ql/src/java/org/apache/hadoop/hive/ql/io/orc/package-info.java +++ ql/src/java/org/apache/hadoop/hive/ql/io/orc/package-info.java @@ -43,7 +43,7 @@ *

  • Support for additional generic compression: LZO, SNAPPY, ZLIB.
  • * * - *

    + *
    * Format: *

      * {@code
    @@ -54,9 +54,8 @@
      * PS LENGTH (1 byte)
      * }
      * 
    - *

    * - *

    + *
    * Stripe: *

      * {@code
    @@ -65,6 +64,5 @@
      * STRIPE-FOOTER
      * }
      * 
    - *

    */ package org.apache.hadoop.hive.ql.io.orc; diff --git ql/src/java/org/apache/hadoop/hive/ql/io/parquet/serde/ArrayWritableObjectInspector.java ql/src/java/org/apache/hadoop/hive/ql/io/parquet/serde/ArrayWritableObjectInspector.java index f350035..31658ff 100644 --- ql/src/java/org/apache/hadoop/hive/ql/io/parquet/serde/ArrayWritableObjectInspector.java +++ ql/src/java/org/apache/hadoop/hive/ql/io/parquet/serde/ArrayWritableObjectInspector.java @@ -36,7 +36,7 @@ /** * - * The ArrayWritableObjectInspector will inspect an ArrayWritable, considering it as a Hive struct.
    + * The ArrayWritableObjectInspector will inspect an ArrayWritable, considering it as a Hive struct.
    * It can also inspect a List if Hive decides to inspect the result of an inspection. * */ diff --git ql/src/java/org/apache/hadoop/hive/ql/io/parquet/serde/DeepParquetHiveMapInspector.java ql/src/java/org/apache/hadoop/hive/ql/io/parquet/serde/DeepParquetHiveMapInspector.java index 143d72e..139ed82 100644 --- ql/src/java/org/apache/hadoop/hive/ql/io/parquet/serde/DeepParquetHiveMapInspector.java +++ ql/src/java/org/apache/hadoop/hive/ql/io/parquet/serde/DeepParquetHiveMapInspector.java @@ -21,8 +21,8 @@ import org.apache.hadoop.io.Writable; /** - * The DeepParquetHiveMapInspector will inspect an ArrayWritable, considering it as a Hive map.
    - * It can also inspect a Map if Hive decides to inspect the result of an inspection.
    + * The DeepParquetHiveMapInspector will inspect an ArrayWritable, considering it as a Hive map.
    + * It can also inspect a Map if Hive decides to inspect the result of an inspection.
    * When trying to access elements from the map it will iterate over all keys, inspecting them and comparing them to the * desired key. * diff --git ql/src/java/org/apache/hadoop/hive/ql/io/parquet/serde/ParquetHiveArrayInspector.java ql/src/java/org/apache/hadoop/hive/ql/io/parquet/serde/ParquetHiveArrayInspector.java index 55614a3..8e55766 100644 --- ql/src/java/org/apache/hadoop/hive/ql/io/parquet/serde/ParquetHiveArrayInspector.java +++ ql/src/java/org/apache/hadoop/hive/ql/io/parquet/serde/ParquetHiveArrayInspector.java @@ -22,7 +22,7 @@ import org.apache.hadoop.io.Writable; /** - * The ParquetHiveArrayInspector will inspect an ArrayWritable, considering it as an Hive array.
    + * The ParquetHiveArrayInspector will inspect an ArrayWritable, considering it as an Hive array.
    * It can also inspect a List if Hive decides to inspect the result of an inspection. * */ diff --git ql/src/java/org/apache/hadoop/hive/ql/io/parquet/serde/StandardParquetHiveMapInspector.java ql/src/java/org/apache/hadoop/hive/ql/io/parquet/serde/StandardParquetHiveMapInspector.java index 22250b3..bd66d9c 100644 --- ql/src/java/org/apache/hadoop/hive/ql/io/parquet/serde/StandardParquetHiveMapInspector.java +++ ql/src/java/org/apache/hadoop/hive/ql/io/parquet/serde/StandardParquetHiveMapInspector.java @@ -20,7 +20,7 @@ import org.apache.hadoop.io.Writable; /** - * The StandardParquetHiveMapInspector will inspect an ArrayWritable, considering it as a Hive map.
    + * The StandardParquetHiveMapInspector will inspect an ArrayWritable, considering it as a Hive map.
    * It can also inspect a Map if Hive decides to inspect the result of an inspection. * */ diff --git ql/src/java/org/apache/hadoop/hive/ql/io/parquet/timestamp/NanoTimeUtils.java ql/src/java/org/apache/hadoop/hive/ql/io/parquet/timestamp/NanoTimeUtils.java index dbd6fb3..641b812 100644 --- ql/src/java/org/apache/hadoop/hive/ql/io/parquet/timestamp/NanoTimeUtils.java +++ ql/src/java/org/apache/hadoop/hive/ql/io/parquet/timestamp/NanoTimeUtils.java @@ -68,7 +68,7 @@ public static NanoTime getNanoTime(Timestamp ts, boolean skipConversion) { * If the timezone of the calendar is different from the current local * timezone, then the timestamp value will be adjusted. * Possible adjustments: - * - UTC Ts -> Local Ts copied to TableTZ Calendar -> UTC Ts -> JD + * - UTC Ts -> Local Ts copied to TableTZ Calendar -> UTC Ts -> JD * @param ts floating time timestamp to store * @param calendar timezone used to adjust the timestamp for parquet * @return adjusted julian date @@ -112,7 +112,7 @@ public static Timestamp getTimestamp(NanoTime nt, boolean skipConversion) { * If the timezone of the calendar is different from the current local * timezone, then the timestamp value will be adjusted. * Possible adjustments: - * - JD -> UTC Ts -> TableTZ Calendar copied to LocalTZ Calendar -> UTC Ts + * - JD -> UTC Ts -> TableTZ Calendar copied to LocalTZ Calendar -> UTC Ts * @param nt stored julian date * @param calendar timezone used to adjust the timestamp for parquet * @return floating time represented as a timestamp. Guaranteed to display diff --git ql/src/java/org/apache/hadoop/hive/ql/lib/Node.java ql/src/java/org/apache/hadoop/hive/ql/lib/Node.java index 55f0b39..7a1dd7d 100644 --- ql/src/java/org/apache/hadoop/hive/ql/lib/Node.java +++ ql/src/java/org/apache/hadoop/hive/ql/lib/Node.java @@ -30,7 +30,7 @@ * Gets the vector of children nodes. This is used in the graph walker * algorithms. * - * @return List + * @return List<? extends Node> */ List getChildren(); diff --git ql/src/java/org/apache/hadoop/hive/ql/lib/RuleExactMatch.java ql/src/java/org/apache/hadoop/hive/ql/lib/RuleExactMatch.java index 6f7962e..efabb17 100644 --- ql/src/java/org/apache/hadoop/hive/ql/lib/RuleExactMatch.java +++ ql/src/java/org/apache/hadoop/hive/ql/lib/RuleExactMatch.java @@ -36,13 +36,13 @@ * The rule specified as operator names separated by % symbols, the left side represents the * bottom of the stack. * - * E.g. TS%FIL%RS -> means + * E.g. TS%FIL%RS -> means * TableScan Node followed by Filter followed by ReduceSink in the tree, or, in terms of the * stack, ReduceSink on top followed by Filter followed by TableScan * * @param ruleName * name of the rule - * @param regExp + * @param pattern * string specification of the rule **/ public RuleExactMatch(String ruleName, String[] pattern) { diff --git ql/src/java/org/apache/hadoop/hive/ql/lib/RuleRegExp.java ql/src/java/org/apache/hadoop/hive/ql/lib/RuleRegExp.java index 1e850d6..7b74920 100644 --- ql/src/java/org/apache/hadoop/hive/ql/lib/RuleRegExp.java +++ ql/src/java/org/apache/hadoop/hive/ql/lib/RuleRegExp.java @@ -87,7 +87,7 @@ private static boolean patternHasOnlyWildCardChar(String pattern, char wcc) { /** * The rule specified by the regular expression. Note that, the regular - * expression is specified in terms of Node name. For eg: TS.*RS -> means + * expression is specified in terms of Node name. For eg: TS.*RS -> means * TableScan Node followed by anything any number of times followed by * ReduceSink * diff --git ql/src/java/org/apache/hadoop/hive/ql/log/PidFilePatternConverter.java ql/src/java/org/apache/hadoop/hive/ql/log/PidFilePatternConverter.java index 4db10bb..235e621 100644 --- ql/src/java/org/apache/hadoop/hive/ql/log/PidFilePatternConverter.java +++ ql/src/java/org/apache/hadoop/hive/ql/log/PidFilePatternConverter.java @@ -26,13 +26,13 @@ import org.apache.logging.log4j.core.pattern.ConverterKeys; /** - * FilePattern converter that converts %pid pattern to @ information + * FilePattern converter that converts %pid pattern to <process-id>@<hostname> information * obtained at runtime. * * Example usage: - * + * <RollingFile name="Rolling-default" fileName="test.log" filePattern="test.log.%pid.gz"> * - * Will generate output file with name containing @ like below + * Will generate output file with name containing <process-id>@<hostname> like below * test.log.95232@localhost.gz */ @Plugin(name = "PidFilePatternConverter", category = "FileConverter") diff --git ql/src/java/org/apache/hadoop/hive/ql/metadata/Hive.java ql/src/java/org/apache/hadoop/hive/ql/metadata/Hive.java index 5b908e8..c5fee3b 100644 --- ql/src/java/org/apache/hadoop/hive/ql/metadata/Hive.java +++ ql/src/java/org/apache/hadoop/hive/ql/metadata/Hive.java @@ -598,7 +598,7 @@ public void createTable(String tableName, List columns, List par * new name of the table. could be the old name * @throws InvalidOperationException * if the changes in metadata is not acceptable - * @throws TException + * @throws HiveException */ public void alterTable(String tblName, Table newTbl, EnvironmentContext environmentContext) throws InvalidOperationException, HiveException { @@ -643,7 +643,7 @@ public void alterIndex(String baseTableName, String indexName, Index newIdx) * new name of the index. could be the old name * @throws InvalidOperationException * if the changes in metadata is not acceptable - * @throws TException + * @throws HiveException */ public void alterIndex(String dbName, String baseTblName, String idxName, Index newIdx) throws InvalidOperationException, HiveException { @@ -665,7 +665,7 @@ public void alterIndex(String dbName, String baseTblName, String idxName, Index * new partition * @throws InvalidOperationException * if the changes in metadata is not acceptable - * @throws TException + * @throws HiveException */ public void alterPartition(String tblName, Partition newPart, EnvironmentContext environmentContext) throws InvalidOperationException, HiveException { @@ -684,7 +684,7 @@ public void alterPartition(String tblName, Partition newPart, EnvironmentContext * new partition * @throws InvalidOperationException * if the changes in metadata is not acceptable - * @throws TException + * @throws HiveException */ public void alterPartition(String dbName, String tblName, Partition newPart, EnvironmentContext environmentContext) throws InvalidOperationException, HiveException { @@ -721,7 +721,7 @@ private void validatePartition(Partition newPart) throws HiveException { * new partitions * @throws InvalidOperationException * if the changes in metadata is not acceptable - * @throws TException + * @throws HiveException */ public void alterPartitions(String tblName, List newParts, EnvironmentContext environmentContext) throws InvalidOperationException, HiveException { @@ -757,9 +757,7 @@ public void alterPartitions(String tblName, List newParts, Environmen * spec of old partition * @param newPart * new partition - * @throws InvalidOperationException - * if the changes in metadata is not acceptable - * @throws TException + * @throws HiveException */ public void renamePartition(Table tbl, Map oldPartSpec, Partition newPart) throws HiveException { @@ -1611,7 +1609,6 @@ public Database getDatabaseCurrent() throws HiveException { * @param isSrcLocal * @param isAcid * @param hasFollowingStatsTask - * @return * @throws HiveException */ public void loadPartition(Path loadPath, String tableName, diff --git ql/src/java/org/apache/hadoop/hive/ql/metadata/HiveStorageHandler.java ql/src/java/org/apache/hadoop/hive/ql/metadata/HiveStorageHandler.java index 5975d0c..f590295 100644 --- ql/src/java/org/apache/hadoop/hive/ql/metadata/HiveStorageHandler.java +++ ql/src/java/org/apache/hadoop/hive/ql/metadata/HiveStorageHandler.java @@ -139,7 +139,7 @@ public void configureTableJobProperties( * Called just before submitting MapReduce job. * * @param tableDesc descriptor for the table being accessed - * @param JobConf jobConf for MapReduce job + * @param jobConf jobConf for MapReduce job */ public void configureJobConf(TableDesc tableDesc, JobConf jobConf); } diff --git ql/src/java/org/apache/hadoop/hive/ql/metadata/PartitionIterable.java ql/src/java/org/apache/hadoop/hive/ql/metadata/PartitionIterable.java index b00044a..1f8d554 100644 --- ql/src/java/org/apache/hadoop/hive/ql/metadata/PartitionIterable.java +++ ql/src/java/org/apache/hadoop/hive/ql/metadata/PartitionIterable.java @@ -26,11 +26,11 @@ /** - * PartitionIterable - effectively a lazy Iterable + * PartitionIterable - effectively a lazy Iterable<Partition> * * Sometimes, we have a need for iterating through a list of partitions, * but the list of partitions can be too big to fetch as a single object. - * Thus, the goal of PartitionIterable is to act as an Iterable + * Thus, the goal of PartitionIterable is to act as an Iterable<Partition> * while lazily fetching each relevant partition, one after the other as * independent metadata calls. * @@ -134,7 +134,7 @@ public void remove() { /** * Dummy constructor, which simply acts as an iterator on an already-present * list of partitions, allows for easy drop-in replacement for other methods - * that already have a List + * that already have a List<Partition> */ public PartitionIterable(Collection ptnsProvided){ this.currType = Type.LIST_PROVIDED; diff --git ql/src/java/org/apache/hadoop/hive/ql/metadata/Table.java ql/src/java/org/apache/hadoop/hive/ql/metadata/Table.java index a53f774..11571db 100644 --- ql/src/java/org/apache/hadoop/hive/ql/metadata/Table.java +++ ql/src/java/org/apache/hadoop/hive/ql/metadata/Table.java @@ -654,7 +654,7 @@ private boolean isField(String col) { * Returns a list of all the columns of the table (data columns + partition * columns in that order. * - * @return List + * @return List<FieldSchema> */ public List getAllCols() { ArrayList f_list = new ArrayList(); @@ -866,7 +866,7 @@ public boolean isIndexTable() { } /** - * Creates a partition name -> value spec map object + * Creates a partition name -> value spec map object * * @param tp * Use the information from this partition. diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/ColumnPrunerProcFactory.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/ColumnPrunerProcFactory.java index 45839ad..73765d6 100644 --- ql/src/java/org/apache/hadoop/hive/ql/optimizer/ColumnPrunerProcFactory.java +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/ColumnPrunerProcFactory.java @@ -302,7 +302,7 @@ public static ColumnPrunerScriptProc getScriptProc() { * - add column names referenced in WindowFn args and in WindowFn expressions * to the pruned list of the child Select Op. * - finally we set the prunedColList on the ColumnPrunerContx; - * and update the RR & signature on the PTFOp. + * and update the RR & signature on the PTFOp. */ public static class ColumnPrunerPTFProc extends ColumnPrunerScriptProc { @Override diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/ConstantPropagateProcCtx.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/ConstantPropagateProcCtx.java index 5102d81..eb78471 100644 --- ql/src/java/org/apache/hadoop/hive/ql/optimizer/ConstantPropagateProcCtx.java +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/ConstantPropagateProcCtx.java @@ -47,7 +47,7 @@ /** * This class implements the processor context for Constant Propagate. * - * ConstantPropagateProcCtx keeps track of propagated constants in a column->const map for each + * ConstantPropagateProcCtx keeps track of propagated constants in a column->const map for each * operator, enabling constants to be revolved across operators. */ public class ConstantPropagateProcCtx implements NodeProcessorCtx { diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/ConstantPropagateProcFactory.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/ConstantPropagateProcFactory.java index 517ce31..4e16c80 100644 --- ql/src/java/org/apache/hadoop/hive/ql/optimizer/ConstantPropagateProcFactory.java +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/ConstantPropagateProcFactory.java @@ -121,7 +121,7 @@ private ConstantPropagateProcFactory() { /** * Get ColumnInfo from column expression. * - * @param rr + * @param rs * @param desc * @return */ diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/GenMRProcContext.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/GenMRProcContext.java index 4387c42..130e159 100644 --- ql/src/java/org/apache/hadoop/hive/ql/optimizer/GenMRProcContext.java +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/GenMRProcContext.java @@ -176,8 +176,6 @@ public GenMRProcContext() { * hive configuration * @param opTaskMap * reducer to task mapping - * @param seenOps - * operator already visited * @param parseCtx * current parse context * @param rootTasks diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/GenMapRedUtils.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/GenMapRedUtils.java index 88bf829..c18bd01 100644 --- ql/src/java/org/apache/hadoop/hive/ql/optimizer/GenMapRedUtils.java +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/GenMapRedUtils.java @@ -432,8 +432,8 @@ static void splitPlan(ReduceSinkOperator cRS, GenMRProcContext opProcCtx) * current alias * @param topOp * the top operator of the stack - * @param plan - * current plan + * @param task + * current task * @param local * whether you need to add to map-reduce or local work * @param opProcCtx @@ -452,8 +452,8 @@ public static void setTaskPlan(String alias_id, * current alias * @param topOp * the top operator of the stack - * @param plan - * current plan + * @param task + * current task * @param local * whether you need to add to map-reduce or local work * @param opProcCtx @@ -474,13 +474,11 @@ public static void setTaskPlan(String alias_id, * * @param alias_id * current alias - * @param topOp - * the top operator of the stack * @param plan * map work to initialize * @param local * whether you need to add to map-reduce or local work - * @param pList + * @param partsList * pruned partition list. If it is null it will be computed on-the-fly. * @param inputs * read entities for the map work @@ -758,7 +756,7 @@ public static void setMapWork(MapWork plan, ParseContext parseCtx, Set topOp, MapWork plan, boolean local, @@ -1220,7 +1218,6 @@ public static void replaceMapWork(String sourceAlias, String targetAlias, /** * @param fsInput The FileSink operator. - * @param ctx The MR processing context. * @param finalName the final destination path the merge job should output. * @param dependencyTask * @param mvTasks @@ -1245,11 +1242,11 @@ public static void replaceMapWork(String sourceAlias, String targetAlias, * v * FileSinkOperator (fsMerge) * - * Here the pathToPartitionInfo & pathToAlias will remain the same, which means the paths + * Here the pathToPartitionInfo & pathToAlias will remain the same, which means the paths * do * not contain the dynamic partitions (their parent). So after the dynamic partitions are * created (after the first job finished before the moveTask or ConditionalTask start), - * we need to change the pathToPartitionInfo & pathToAlias to include the dynamic + * we need to change the pathToPartitionInfo & pathToAlias to include the dynamic * partition * directories. * @@ -1564,8 +1561,8 @@ private static MapWork createMRWorkForMergingFiles (HiveConf conf, * * @param fsInputDesc * @param finalName + * @param hasDynamicPartitions * @param ctx - * @param inputFormatClass * @return MergeWork if table is stored as RCFile or ORCFile, * null otherwise */ diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/GlobalLimitOptimizer.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/GlobalLimitOptimizer.java index 4ddb545..e34f3e5 100644 --- ql/src/java/org/apache/hadoop/hive/ql/optimizer/GlobalLimitOptimizer.java +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/GlobalLimitOptimizer.java @@ -50,11 +50,11 @@ /** * This optimizer is used to reduce the input size for the query for queries which are * specifying a limit. - *

    + *
    * For eg. for a query of type: - *

    - * select expr from T where limit 100; - *

    + *
    + * select expr from T where <filter< limit 100; + *
    * Most probably, the whole table T need not be scanned. * Chances are that even if we scan the first file of T, we would get the 100 rows * needed by this query. diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/IdentityProjectRemover.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/IdentityProjectRemover.java index 48021cb..6475945 100644 --- ql/src/java/org/apache/hadoop/hive/ql/optimizer/IdentityProjectRemover.java +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/IdentityProjectRemover.java @@ -55,15 +55,15 @@ * * Without this optimization: * - * TS -> FIL -> SEL -> RS -> - * JOIN -> SEL -> FS - * TS -> FIL -> SEL -> RS -> + * TS -> FIL -> SEL -> RS -> + * JOIN -> SEL -> FS + * TS -> FIL -> SEL -> RS -> * * With this optimization * - * TS -> FIL -> RS -> - * JOIN -> FS - * TS -> FIL -> RS -> + * TS -> FIL -> RS -> + * JOIN -> FS + * TS -> FIL -> RS -> * * Note absence of select operator after filter and after join operator. * Also, see : identity_proj_remove.q diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/LimitPushdownOptimizer.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/LimitPushdownOptimizer.java index 9bf197b..64f7975 100644 --- ql/src/java/org/apache/hadoop/hive/ql/optimizer/LimitPushdownOptimizer.java +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/LimitPushdownOptimizer.java @@ -54,7 +54,7 @@ * If RS is only for limiting rows, RSHash counts row with same key separately. * But if RS is for GBY, RSHash should forward all the rows with the same key. * - * Legend : A(a) --> key A, value a, row A(a) + * Legend : A(a) --> key A, value a, row A(a) * * If each RS in mapper tasks is forwarded rows like this * diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/MapJoinProcessor.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/MapJoinProcessor.java index 85d46f3..0c799bb 100644 --- ql/src/java/org/apache/hadoop/hive/ql/optimizer/MapJoinProcessor.java +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/MapJoinProcessor.java @@ -273,11 +273,8 @@ private static void validateMapJoinTypes(Operator op) /** * convert a regular join to a a map-side join. * - * @param opParseCtxMap * @param op * join operator - * @param joinTree - * qb join tree * @param mapJoinPos * position of the source to be read as part of map-reduce framework. All other sources * are cached in memory @@ -408,11 +405,8 @@ private static boolean needValueIndex(int[] valueIndex) { /** * convert a sortmerge join to a a map-side join. * - * @param opParseCtxMap * @param smbJoinOp * join operator - * @param joinTree - * qb join tree * @param bigTablePos * position of the source to be read as part of map-reduce framework. All other sources * are cached in memory @@ -560,7 +554,6 @@ public MapJoinOperator generateMapJoinOperator(ParseContext pctx, JoinOperator o * @param mapJoinPos the position of big table as determined by either hints or auto conversion. * @param condns the join conditions * @return if given mapjoin position is a feasible big table position return same else -1. - * @throws SemanticException if given position is not in the big table candidates. */ public static int checkMapJoin(int mapJoinPos, JoinCondDesc[] condns) { Set bigTableCandidates = MapJoinProcessor.getBigTableCandidates(condns); diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/PrunerOperatorFactory.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/PrunerOperatorFactory.java index 51464e5..f3b4687 100644 --- ql/src/java/org/apache/hadoop/hive/ql/optimizer/PrunerOperatorFactory.java +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/PrunerOperatorFactory.java @@ -92,7 +92,7 @@ public Object process(Node nd, Stack stack, NodeProcessorCtx procCtx, /** * Generate predicate. * - * Subclass should implement the function. Please refer to {@link OpProcFactory.FilterPPR} + * Subclass should implement the function. Please refer to {@link org.apache.hadoop.hive.ql.optimizer.ppr.OpProcFactory.FilterPPR} * * @param procCtx * @param fop diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/SparkMapJoinProcessor.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/SparkMapJoinProcessor.java index 23ee3ae..75892e5 100644 --- ql/src/java/org/apache/hadoop/hive/ql/optimizer/SparkMapJoinProcessor.java +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/SparkMapJoinProcessor.java @@ -37,9 +37,7 @@ * convert a regular join to a a map-side join. * * @param conf - * @param opParseCtxMap * @param op join operator - * @param joinTree qb join tree * @param bigTablePos position of the source to be read as part of * map-reduce framework. All other sources are cached in memory * @param noCheckOuterJoin diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/HiveCalciteUtil.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/HiveCalciteUtil.java index e339d0a..b525e82 100644 --- ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/HiveCalciteUtil.java +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/HiveCalciteUtil.java @@ -612,7 +612,7 @@ public static boolean orderRelNode(RelNode rel) { /** * Get top level select starting from root. Assumption here is root can only - * be Sort & Project. Also the top project should be at most 2 levels below + * be Sort & Project. Also the top project should be at most 2 levels below * Sort; i.e Sort(Limit)-Sort(OB)-Select * * @param rootRel diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/reloperators/HiveProject.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/reloperators/HiveProject.java index a0dfbb1..ef73487 100644 --- ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/reloperators/HiveProject.java +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/reloperators/HiveProject.java @@ -120,7 +120,7 @@ public static HiveProject create(RelOptCluster cluster, RelNode child, List - * This method could optimize the result as {@link #permute} does, but does + * This method could optimize the result as permute does, but does * not at present. * * @param rel diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveExceptRewriteRule.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveExceptRewriteRule.java index b63ea02..6fab3d7 100644 --- ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveExceptRewriteRule.java +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveExceptRewriteRule.java @@ -78,8 +78,8 @@ * have m+n=a, 2m+n=b where m is the #row in R1 and n is the #row in R2 then * m=b-a, n=2a-b, m-n=2b-3a * if it is except (distinct) - * then R5 = Fil (b-a>0 && 2a-b=0) R6 = select only keys from R5 - * else R5 = Fil (2b-3a>0) R6 = UDTF (R5) which will explode the tuples based on 2b-3a. + * then R5 = Fil (b-a>0 && 2a-b=0) R6 = select only keys from R5 + * else R5 = Fil (2b-3a> 0) R6 = UDTF (R5) which will explode the tuples based on 2b-3a. * Note that NULLs are handled the same as other values. Please refer to the test cases. */ public class HiveExceptRewriteRule extends RelOptRule { diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveInsertExchange4JoinRule.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveInsertExchange4JoinRule.java index c9cf396..175bbb4 100644 --- ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveInsertExchange4JoinRule.java +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveInsertExchange4JoinRule.java @@ -46,10 +46,10 @@ import com.google.common.collect.Sets; /** Not an optimization rule. - * Rule to aid in translation from Calcite tree -> Hive tree. + * Rule to aid in translation from Calcite tree -> Hive tree. * Transforms : * Left Right Left Right - * \ / -> \ / + * \ / -> \ / * Join HashExchange HashExchange * \ / * Join diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveReduceExpressionsWithStatsRule.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveReduceExpressionsWithStatsRule.java index 0644f0c..96a2db1 100644 --- ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveReduceExpressionsWithStatsRule.java +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveReduceExpressionsWithStatsRule.java @@ -52,11 +52,11 @@ * column statistics (if available). * * For instance, given the following predicate: - * a > 5 + * a > 5 * we can infer that the predicate will evaluate to false if the max * value for column a is 4. * - * Currently we support the simplification of =, >=, <=, >, <, and + * Currently we support the simplification of =, >=, >=, >, >, and * IN operations. */ public class HiveReduceExpressionsWithStatsRule extends RelOptRule { diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveSubQueryRemoveRule.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveSubQueryRemoveRule.java index c692cc0..ff533be 100644 --- ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveSubQueryRemoveRule.java +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveSubQueryRemoveRule.java @@ -69,9 +69,9 @@ *

    Sub-queries are represented by {@link RexSubQuery} expressions. * *

    A sub-query may or may not be correlated. If a sub-query is correlated, - * the wrapped {@link RelNode} will contain a {@link RexCorrelVariable} before - * the rewrite, and the product of the rewrite will be a {@link Correlate}. - * The Correlate can be removed using {@link RelDecorrelator}. + * the wrapped {@link RelNode} will contain a RexCorrelVariable before + * the rewrite, and the product of the rewrite will be a Correlate. + * The Correlate can be removed using RelDecorrelator. */ public abstract class HiveSubQueryRemoveRule extends RelOptRule{ diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/translator/HiveGBOpConvUtil.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/translator/HiveGBOpConvUtil.java index 0f6c5b5..fa6fb18 100644 --- ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/translator/HiveGBOpConvUtil.java +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/translator/HiveGBOpConvUtil.java @@ -68,7 +68,7 @@ * 1. Change the output col/ExprNodeColumn names to external names.
    * 2. Verify if we need to use the "KEY."/"VALUE." in RS cols; switch to * external names if possible.
    - * 3. In ExprNode & in ColumnInfo the tableAlias/VirtualColumn is specified + * 3. In ExprNode & in ColumnInfo the tableAlias/VirtualColumn is specified * differently for different GB/RS in pipeline. Remove the different treatments. * 4. VirtualColMap needs to be maintained * diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/correlation/CorrelationOptimizer.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/correlation/CorrelationOptimizer.java index e1927e9..a5a9d2c 100644 --- ql/src/java/org/apache/hadoop/hive/ql/optimizer/correlation/CorrelationOptimizer.java +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/correlation/CorrelationOptimizer.java @@ -203,7 +203,7 @@ private void findPossibleAutoConvertedJoinOperators() throws SemanticException { /** * Detect correlations and transform the query tree. * - * @param pactx + * @param pctx * current parse context * @throws SemanticException */ diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/correlation/CorrelationUtilities.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/correlation/CorrelationUtilities.java index 388399c..42a364e 100644 --- ql/src/java/org/apache/hadoop/hive/ql/optimizer/correlation/CorrelationUtilities.java +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/correlation/CorrelationUtilities.java @@ -98,7 +98,7 @@ protected static boolean hasGroupingSet(ReduceSinkOperator cRS) throws SemanticE * @param throwException if throw a exception when the input operator has multiple parents * @return the single parent or null when the input operator has multiple parents and * throwException is false; - * @throws HiveException + * @throws SemanticException */ protected static Operator getSingleParent(Operator operator, boolean throwException) throws SemanticException { @@ -128,7 +128,7 @@ protected static boolean hasGroupingSet(ReduceSinkOperator cRS) throws SemanticE * @param throwException if throw a exception when the input operator has multiple children * @return the single child or null when the input operator has multiple children and * throwException is false; - * @throws HiveException + * @throws SemanticException */ protected static Operator getSingleChild(Operator operator, boolean throwException) throws SemanticException { @@ -432,8 +432,7 @@ protected static void isNullOperator(Operator operator) throws SemanticExcept * @param newOperator the operator will be inserted between child and parent * @param child * @param parent - * @param context - * @throws HiveException + * @throws SemanticException */ protected static void insertOperatorBetween( Operator newOperator, Operator parent, Operator child) diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/index/RewriteGBUsingIndex.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/index/RewriteGBUsingIndex.java index d709e21..4db3e79 100644 --- ql/src/java/org/apache/hadoop/hive/ql/optimizer/index/RewriteGBUsingIndex.java +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/index/RewriteGBUsingIndex.java @@ -83,7 +83,6 @@ * @see RewriteCanApplyProcFactory * @see RewriteParseContextGenerator * @see RewriteQueryUsingAggregateIndexCtx - * @see RewriteQueryUsingAggregateIndex * For test cases, @see ql_rewrite_gbtoidx.q */ diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/index/RewriteParseContextGenerator.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/index/RewriteParseContextGenerator.java index 5659a72..66ce1bf 100644 --- ql/src/java/org/apache/hadoop/hive/ql/optimizer/index/RewriteParseContextGenerator.java +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/index/RewriteParseContextGenerator.java @@ -53,7 +53,7 @@ /** * Parse the input {@link String} command and generate an operator tree. - * @param conf + * @param queryState * @param command * @throws SemanticException */ diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/index/RewriteQueryUsingAggregateIndexCtx.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/index/RewriteQueryUsingAggregateIndexCtx.java index dcea0e5..637fa76 100644 --- ql/src/java/org/apache/hadoop/hive/ql/optimizer/index/RewriteQueryUsingAggregateIndexCtx.java +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/index/RewriteQueryUsingAggregateIndexCtx.java @@ -59,7 +59,7 @@ /** * RewriteQueryUsingAggregateIndexCtx class stores the - * context for the {@link RewriteQueryUsingAggregateIndex} + * context for the RewriteQueryUsingAggregateIndex * used to rewrite operator plan with index table instead of base table. */ diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/listbucketingpruner/ListBucketingPruner.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/listbucketingpruner/ListBucketingPruner.java index 1965120..256bdfc 100644 --- ql/src/java/org/apache/hadoop/hive/ql/optimizer/listbucketingpruner/ListBucketingPruner.java +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/listbucketingpruner/ListBucketingPruner.java @@ -119,18 +119,18 @@ public ParseContext transform(ParseContext pctx) throws SemanticException { * * Complete dynamic-multi-dimension collection * - * (0,0) (1,a) * -> T - * (0,1) (1,b) -> T - * (0,2) (1,c) *-> F - * (0,3) (1,other)-> F - * (1,0) (2,a)-> F - * (1,1) (2,b) * -> T - * (1,2) (2,c)-> F - * (1,3) (2,other)-> F - * (2,0) (other,a) -> T - * (2,1) (other,b) -> T - * (2,2) (other,c) -> T - * (2,3) (other,other) -> T + * (0,0) (1,a) * -> T + * (0,1) (1,b) -> T + * (0,2) (1,c) *-> F + * (0,3) (1,other)-> F + * (1,0) (2,a)-> F + * (1,1) (2,b) * -> T + * (1,2) (2,c)-> F + * (1,3) (2,other)-> F + * (2,0) (other,a) -> T + * (2,1) (other,b) -> T + * (2,2) (other,c) -> T + * (2,3) (other,other) -> T * * is skewed value entry * * Expression Tree : ((c1=1) and (c2=a)) or ( (c1=3) or (c2=b)) @@ -171,7 +171,7 @@ public ParseContext transform(ParseContext pctx) throws SemanticException { * *

        *     child_nd instanceof ExprNodeConstantDesc
    -   *               && ((ExprNodeConstantDesc) child_nd).getValue() == null)
    +   *               && ((ExprNodeConstantDesc) child_nd).getValue() == null)
        * 
    * * @@ -410,7 +410,7 @@ private static void decideDefaultDirSelection(Partition part, List selecte * 2. all other cases, select the directory * Use case #2: * Multiple dimension collection represents skewed elements so that walk through tree one by one. - * Cell is a List representing the value mapping from index path and skewed value. + * Cell is a List<String> representing the value mapping from index path and skewed value. * skewed column: C1, C2, C3 * skewed value: (1,a,x), (2,b,x), (1,c,x), (2,a,y) * Other: represent value for the column which is not part of skewed value. @@ -428,8 +428,8 @@ private static void decideDefaultDirSelection(Partition part, List selecte * ============== * please see another example in {@link ListBucketingPruner#prune} * We will use a HasMap to represent the Dynamic-Multiple-Dimension collection: - * 1. Key is List representing the index path to the cell - * 2. value represents the cell (Boolean for use case #1, List for case #2) + * 1. Key is List<Integer> representing the index path to the cell + * 2. value represents the cell (Boolean for use case #1, List<String> for case #2) * For example: * 1. skewed column (list): C1, C2, C3 * 2. skewed value (list of list): (1,a,x), (2,b,x), (1,c,x), (2,a,y) @@ -446,7 +446,7 @@ private static void decideDefaultDirSelection(Partition part, List selecte * * We use the index,starting at 0. to construct hashmap representing dynamic-multi-dimension * collection: - * key (what skewed value key represents) -> value (Boolean for use case #1, List for case + * key (what skewed value key represents) -> value (Boolean for use case #1, List<String> for case * #2). * (0,0,0) (1,a,x) * (0,0,1) (1,a,y) @@ -572,18 +572,18 @@ private static void decideDefaultDirSelection(Partition part, List selecte * Index: (0,1,2) (0,1,2,3) * * Complete dynamic-multi-dimension collection - * (0,0) (1,a) * -> T - * (0,1) (1,b) -> T - * (0,2) (1,c) *-> F - * (0,3) (1,other)-> F - * (1,0) (2,a)-> F - * (1,1) (2,b) * -> T - * (1,2) (2,c)-> F - * (1,3) (2,other)-> F - * (2,0) (other,a) -> T - * (2,1) (other,b) -> T - * (2,2) (other,c) -> T - * (2,3) (other,other) -> T + * (0,0) (1,a) * -> T + * (0,1) (1,b) -> T + * (0,2) (1,c) *-> F + * (0,3) (1,other)-> F + * (1,0) (2,a)-> F + * (1,1) (2,b) * -> T + * (1,2) (2,c)-> F + * (1,3) (2,other)-> F + * (2,0) (other,a) -> T + * (2,1) (other,b) -> T + * (2,2) (other,c) -> T + * (2,3) (other,other) -> T * * is skewed value entry * * @param uniqSkewedElements diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/physical/PhysicalOptimizer.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/physical/PhysicalOptimizer.java index 9377563..65d64e8 100644 --- ql/src/java/org/apache/hadoop/hive/ql/optimizer/physical/PhysicalOptimizer.java +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/physical/PhysicalOptimizer.java @@ -105,7 +105,7 @@ private void initialize(HiveConf hiveConf) { * invoke all the resolvers one-by-one, and alter the physical plan. * * @return PhysicalContext - * @throws HiveException + * @throws SemanticException */ public PhysicalContext optimize() throws SemanticException { for (PhysicalPlanResolver r : resolvers) { diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/ppr/PartExprEvalUtils.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/ppr/PartExprEvalUtils.java index 1103d35..2afcb22 100644 --- ql/src/java/org/apache/hadoop/hive/ql/optimizer/ppr/PartExprEvalUtils.java +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/ppr/PartExprEvalUtils.java @@ -47,7 +47,6 @@ * Evaluate expression with partition columns * * @param expr - * @param partSpec * @param rowObjectInspector * @return value returned by the expression * @throws HiveException diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/stats/annotation/StatsRulesProcFactory.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/stats/annotation/StatsRulesProcFactory.java index 6844713..c6700e5 100644 --- ql/src/java/org/apache/hadoop/hive/ql/optimizer/stats/annotation/StatsRulesProcFactory.java +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/stats/annotation/StatsRulesProcFactory.java @@ -217,45 +217,32 @@ public Object process(Node nd, Stack stack, NodeProcessorCtx procCtx, /** * FILTER operator does not change the average row size but it does change the number of rows * emitted. The reduction in the number of rows emitted is dependent on the filter expression. - *
      * Notations: + *
        *
      • T(S) - Number of tuples in relations S
      • *
      • V(S,A) - Number of distinct values of attribute A in relation S
      • *
      + * Rules: *
        - * Rules: - *
      • Column equals a constant
      • T(S) = T(R) / V(R,A) - *

        - * - *

      • Inequality conditions
      • T(S) = T(R) / 3 - *

        - * - *

      • Not equals comparison
      • - Simple formula T(S) = T(R) - *

        - * - Alternate formula T(S) = T(R) (V(R,A) - 1) / V(R,A) - *

        - * - *

      • NOT condition
      • T(S) = 1 - T(S'), where T(S') is the satisfying condition - *

        - * - *

      • Multiple AND conditions
      • Cascadingly apply the rules 1 to 3 (order doesn't matter) - *

        - * - *

      • Multiple OR conditions
      • - Simple formula is to evaluate conditions independently - * and sum the results T(S) = m1 + m2 - *

        - * - Alternate formula T(S) = T(R) * ( 1 - ( 1 - m1/T(R) ) * ( 1 - m2/T(R) )) - *

        + *

      • Column equals a constant T(S) = T(R) / V(R,A)
      • + *
      • Inequality conditions T(S) = T(R) / 3
      • + *
      • Not equals comparison - Simple formula T(S) = T(R)
      • + *
      • - Alternate formula T(S) = T(R) (V(R,A) - 1) / V(R,A)
      • + *
      • NOT condition T(S) = 1 - T(S'), where T(S') is the satisfying condition
      • + *
      • Multiple AND conditions Cascadingly apply the rules 1 to 3 (order doesn't matter)
      • + *
      • Multiple OR conditions - Simple formula is to evaluate conditions independently + * and sum the results T(S) = m1 + m2
      • + *
      • - Alternate formula T(S) = T(R) * ( 1 - ( 1 - m1/T(R) ) * ( 1 - m2/T(R) )) + *
        * where, m1 is the number of tuples that satisfy condition1 and m2 is the number of tuples that - * satisfy condition2 + * satisfy condition2
      • *
      - *

      * Worst case: If no column statistics are available, then evaluation of predicate * expression will assume worst case (i.e; half the input rows) for each of predicate expression. - *

      + *
      * For more information, refer 'Estimating The Cost Of Operations' chapter in * "Database Systems: The Complete Book" by Garcia-Molina et. al. - *

      + *
      */ public static class FilterStatsRule extends DefaultStatsRule implements NodeProcessor { @@ -951,7 +938,7 @@ private long evaluateChildExpr(Statistics stats, ExprNodeDesc child, * available then a better estimate can be found by taking the smaller of product of V(R,[A,B,C]) * (product of distinct cardinalities of A,B,C) and T(R)/2. *

      - * T(R) = min (T(R)/2 , V(R,[A,B,C]) ---> [1] + * T(R) = min (T(R)/2 , V(R,[A,B,C]) ---> [1] *

      * In the presence of grouping sets, map-side GBY will emit more rows depending on the size of * grouping set (input rows * size of grouping set). These rows will get reduced because of @@ -1371,12 +1358,12 @@ private boolean checkMapSideAggregation(GroupByOperator gop, } /** - * JOIN operator can yield any of the following three cases

    • The values of join keys are + * JOIN operator can yield any of the following three cases
      • The values of join keys are * disjoint in both relations in which case T(RXS) = 0 (we need histograms for this)
      • Join * key is primary key on relation R and foreign key on relation S in which case every tuple in S - * will have a tuple in R T(RXS) = T(S) (we need histograms for this)
      • Both R & S relation + * will have a tuple in R T(RXS) = T(S) (we need histograms for this)
      • Both R & S relation * have same value for join-key. Ex: bool column with all true values T(RXS) = T(R) * T(S) (we - * need histograms for this. counDistinct = 1 and same value)
      • + * need histograms for this. counDistinct = 1 and same value)
      *

      * In the absence of histograms, we can use the following general case *

      diff --git ql/src/java/org/apache/hadoop/hive/ql/parse/ASTNode.java ql/src/java/org/apache/hadoop/hive/ql/parse/ASTNode.java index fb1a309..e728100 100644 --- ql/src/java/org/apache/hadoop/hive/ql/parse/ASTNode.java +++ ql/src/java/org/apache/hadoop/hive/ql/parse/ASTNode.java @@ -98,7 +98,7 @@ public String getName() { /** * For every node in this subtree, make sure it's start/stop token's * are set. Walk depth first, visit bottom up. Only updates nodes - * with at least one token index < 0. + * with at least one token index < 0. * * In contrast to the method in the parent class, this method is * iterative. diff --git ql/src/java/org/apache/hadoop/hive/ql/parse/ColumnStatsSemanticAnalyzer.java ql/src/java/org/apache/hadoop/hive/ql/parse/ColumnStatsSemanticAnalyzer.java index 0a5cf00..06c58d3 100644 --- ql/src/java/org/apache/hadoop/hive/ql/parse/ColumnStatsSemanticAnalyzer.java +++ ql/src/java/org/apache/hadoop/hive/ql/parse/ColumnStatsSemanticAnalyzer.java @@ -417,10 +417,6 @@ public void analyze(ASTNode ast, Context origCtx) throws SemanticException { /** * @param ast * is the original analyze ast - * @param qb - * is the qb that calls this function - * @param sem - * is the semantic analyzer that calls this function * @return * @throws SemanticException */ diff --git ql/src/java/org/apache/hadoop/hive/ql/parse/PTFInvocationSpec.java ql/src/java/org/apache/hadoop/hive/ql/parse/PTFInvocationSpec.java index ecf3cfc..9b7421e 100644 --- ql/src/java/org/apache/hadoop/hive/ql/parse/PTFInvocationSpec.java +++ ql/src/java/org/apache/hadoop/hive/ql/parse/PTFInvocationSpec.java @@ -413,7 +413,7 @@ public void setExpressions(ArrayList columns) /** * Add order expressions from the list of expressions in the format of ASTNode - * @param args + * @param nodes */ public void addExpressions(ArrayList nodes) { for (int i = 0; i < nodes.size(); i++) { diff --git ql/src/java/org/apache/hadoop/hive/ql/parse/ParseContext.java ql/src/java/org/apache/hadoop/hive/ql/parse/ParseContext.java index 6de4bcd..8b26aa9 100644 --- ql/src/java/org/apache/hadoop/hive/ql/parse/ParseContext.java +++ ql/src/java/org/apache/hadoop/hive/ql/parse/ParseContext.java @@ -128,7 +128,6 @@ public ParseContext() { } /** - * @param conf * @param opToPartPruner * map from table scan operator to partition pruner * @param opToPartList diff --git ql/src/java/org/apache/hadoop/hive/ql/parse/ReplicationSpec.java ql/src/java/org/apache/hadoop/hive/ql/parse/ReplicationSpec.java index 1ea608b..bb4bcec 100644 --- ql/src/java/org/apache/hadoop/hive/ql/parse/ReplicationSpec.java +++ ql/src/java/org/apache/hadoop/hive/ql/parse/ReplicationSpec.java @@ -244,7 +244,7 @@ public boolean allowEventReplacementInto(Table table) { } /** - * Returns a predicate filter to filter an Iterable to return all partitions + * Returns a predicate filter to filter an Iterable<Partition> to return all partitions * that the current replication event specification is allowed to replicate-replace-into */ public Predicate allowEventReplacementInto() { diff --git ql/src/java/org/apache/hadoop/hive/ql/parse/TableSample.java ql/src/java/org/apache/hadoop/hive/ql/parse/TableSample.java index ac71565..9d68bf0 100644 --- ql/src/java/org/apache/hadoop/hive/ql/parse/TableSample.java +++ ql/src/java/org/apache/hadoop/hive/ql/parse/TableSample.java @@ -120,7 +120,7 @@ public void setDenominator(int den) { /** * Gets the ON part's expression list. * - * @return ArrayList + * @return ArrayList<ASTNode> */ public ArrayList getExprs() { return exprs; diff --git ql/src/java/org/apache/hadoop/hive/ql/parse/TaskCompiler.java ql/src/java/org/apache/hadoop/hive/ql/parse/TaskCompiler.java index 08a8f00..13d3726 100644 --- ql/src/java/org/apache/hadoop/hive/ql/parse/TaskCompiler.java +++ ql/src/java/org/apache/hadoop/hive/ql/parse/TaskCompiler.java @@ -412,9 +412,7 @@ private void patchUpAfterCTASorMaterializedView(final List cur /** * Join keys are expressions based on the select operator. Resolve the expressions so they * are based on the ReduceSink operator - * SEL -> RS -> JOIN + * SEL -> RS -> JOIN * @param source * @param reduceSinkOp * @return @@ -569,10 +569,10 @@ public static PrimitiveTypeInfo deriveMinArgumentCast( * @param inputOp * Input Hive Operator * @param startPos - * starting position in the input operator schema; must be >=0 and <= + * starting position in the input operator schema; must be >=0 and <= * endPos * @param endPos - * end position in the input operator schema; must be >=0. + * end position in the input operator schema; must be >=0. * @return List of ExprNodeDesc */ public static ArrayList genExprNodeDesc(Operator inputOp, int startPos, int endPos, diff --git ql/src/java/org/apache/hadoop/hive/ql/plan/ListBucketingCtx.java ql/src/java/org/apache/hadoop/hive/ql/plan/ListBucketingCtx.java index 31fcaeb..ef06f48 100644 --- ql/src/java/org/apache/hadoop/hive/ql/plan/ListBucketingCtx.java +++ ql/src/java/org/apache/hadoop/hive/ql/plan/ListBucketingCtx.java @@ -184,7 +184,6 @@ public void setDefaultDirName(String defaultDirName) { /** * check if list bucketing is enabled. * - * @param ctx * @return */ public boolean isSkewedStoredAsDir() { @@ -201,7 +200,6 @@ public boolean isSkewedStoredAsDir() { * 0: not list bucketing * int: no. of skewed columns * - * @param ctx * @return */ public int calculateListBucketingLevel() { diff --git ql/src/java/org/apache/hadoop/hive/ql/plan/MapWork.java ql/src/java/org/apache/hadoop/hive/ql/plan/MapWork.java index 2120400..4c7529c 100644 --- ql/src/java/org/apache/hadoop/hive/ql/plan/MapWork.java +++ ql/src/java/org/apache/hadoop/hive/ql/plan/MapWork.java @@ -195,10 +195,10 @@ public void removePathToAlias(Path path){ } /** - * This is used to display and verify output of "Path -> Alias" in test framework. + * This is used to display and verify output of "Path -> Alias" in test framework. * - * QTestUtil masks "Path -> Alias" and makes verification impossible. - * By keeping "Path -> Alias" intact and adding a new display name which is not + * QTestUtil masks "Path -> Alias" and makes verification impossible. + * By keeping "Path -> Alias" intact and adding a new display name which is not * masked by QTestUtil by removing prefix. * * Notes: we would still be masking for intermediate directories. diff --git ql/src/java/org/apache/hadoop/hive/ql/plan/PlanUtils.java ql/src/java/org/apache/hadoop/hive/ql/plan/PlanUtils.java index 14f2a12..ecd57f3 100644 --- ql/src/java/org/apache/hadoop/hive/ql/plan/PlanUtils.java +++ ql/src/java/org/apache/hadoop/hive/ql/plan/PlanUtils.java @@ -450,7 +450,7 @@ public static TableDesc getTableDesc(CreateViewDesc crtViewDesc, String cols, St * Generate the table descriptor of MetadataTypedColumnsetSerDe with the * separatorCode. MetaDataTypedColumnsetSerDe is used because LazySimpleSerDe * does not support a table with a single column "col" with type - * "array". + * "array<string>". */ public static TableDesc getDefaultTableDesc(String separatorCode) { return new TableDesc( @@ -952,7 +952,7 @@ public static String stripQuotes(String val) { } /** - * Remove prefix from "Path -> Alias" + * Remove prefix from "Path -> Alias" * This is required for testing. * In order to verify that path is right, we need to display it in expected test result. * But, mask pattern masks path with some patterns. diff --git ql/src/java/org/apache/hadoop/hive/ql/plan/RenamePartitionDesc.java ql/src/java/org/apache/hadoop/hive/ql/plan/RenamePartitionDesc.java index 7523d01..def16a7 100644 --- ql/src/java/org/apache/hadoop/hive/ql/plan/RenamePartitionDesc.java +++ ql/src/java/org/apache/hadoop/hive/ql/plan/RenamePartitionDesc.java @@ -39,9 +39,7 @@ public RenamePartitionDesc() { } - /** - * @param dbName - * database to add to. + /** * @param tableName * table to add to. * @param oldPartSpec diff --git ql/src/java/org/apache/hadoop/hive/ql/plan/ShowCreateDatabaseDesc.java ql/src/java/org/apache/hadoop/hive/ql/plan/ShowCreateDatabaseDesc.java index 2b12691..1e026aa 100644 --- ql/src/java/org/apache/hadoop/hive/ql/plan/ShowCreateDatabaseDesc.java +++ ql/src/java/org/apache/hadoop/hive/ql/plan/ShowCreateDatabaseDesc.java @@ -85,7 +85,7 @@ public String getDatabaseName() { } /** - * @param databaseName + * @param dbName * the dbName to set */ public void setDatabaseName(String dbName) { diff --git ql/src/java/org/apache/hadoop/hive/ql/plan/ShowFunctionsDesc.java ql/src/java/org/apache/hadoop/hive/ql/plan/ShowFunctionsDesc.java index 48522c5..c963211 100644 --- ql/src/java/org/apache/hadoop/hive/ql/plan/ShowFunctionsDesc.java +++ ql/src/java/org/apache/hadoop/hive/ql/plan/ShowFunctionsDesc.java @@ -77,7 +77,7 @@ public ShowFunctionsDesc(Path resFile, String pattern) { /** * @param pattern * names of tables to show - * @param like + * @param isLikePattern * is like keyword used */ public ShowFunctionsDesc(Path resFile, String pattern, boolean isLikePattern) { diff --git ql/src/java/org/apache/hadoop/hive/ql/plan/SkewedColumnPositionPair.java ql/src/java/org/apache/hadoop/hive/ql/plan/SkewedColumnPositionPair.java index 0fa50f1..2e0059c 100644 --- ql/src/java/org/apache/hadoop/hive/ql/plan/SkewedColumnPositionPair.java +++ ql/src/java/org/apache/hadoop/hive/ql/plan/SkewedColumnPositionPair.java @@ -32,7 +32,7 @@ * 1. It's position in table column is 1. * 2. It's position in skewed column list is 0. * - * This information will be used in {@FileSinkOperator} generateListBucketingDirName + * This information will be used in {@link org.apache.hadoop.hive.ql.exec.FileSinkOperator} generateListBucketingDirName */ public class SkewedColumnPositionPair { private int tblColPosition; diff --git ql/src/java/org/apache/hadoop/hive/ql/plan/SparkWork.java ql/src/java/org/apache/hadoop/hive/ql/plan/SparkWork.java index 9d46cac..d5d593b 100644 --- ql/src/java/org/apache/hadoop/hive/ql/plan/SparkWork.java +++ ql/src/java/org/apache/hadoop/hive/ql/plan/SparkWork.java @@ -272,7 +272,6 @@ public SparkEdgeProperty getEdgeProperty(BaseWork a, BaseWork b) { /** * connect adds an edge between a and b. Both nodes have * to be added prior to calling connect. - * @param */ public void connect(BaseWork a, BaseWork b, SparkEdgeProperty edgeProp) { workGraph.get(a).add(b); diff --git ql/src/java/org/apache/hadoop/hive/ql/plan/TezWork.java ql/src/java/org/apache/hadoop/hive/ql/plan/TezWork.java index a037ea3..15c0b7d 100644 --- ql/src/java/org/apache/hadoop/hive/ql/plan/TezWork.java +++ ql/src/java/org/apache/hadoop/hive/ql/plan/TezWork.java @@ -370,7 +370,6 @@ public int compareTo(Dependency o) { /** * connect adds an edge between a and b. Both nodes have * to be added prior to calling connect. - * @param */ public void connect(BaseWork a, BaseWork b, TezEdgeProperty edgeProp) { diff --git ql/src/java/org/apache/hadoop/hive/ql/plan/UDTFDesc.java ql/src/java/org/apache/hadoop/hive/ql/plan/UDTFDesc.java index 68f289e..a5bb24c 100644 --- ql/src/java/org/apache/hadoop/hive/ql/plan/UDTFDesc.java +++ ql/src/java/org/apache/hadoop/hive/ql/plan/UDTFDesc.java @@ -23,8 +23,8 @@ /** - * All member variables should have a setters and getters of the form get and set or else they won't be recreated properly at run + * All member variables should have a setters and getters of the form get<member + * name> and set<member name> or else they won't be recreated properly at run * time. * */ diff --git ql/src/java/org/apache/hadoop/hive/ql/plan/VectorGroupByDesc.java ql/src/java/org/apache/hadoop/hive/ql/plan/VectorGroupByDesc.java index f9a8725..96c3401 100644 --- ql/src/java/org/apache/hadoop/hive/ql/plan/VectorGroupByDesc.java +++ ql/src/java/org/apache/hadoop/hive/ql/plan/VectorGroupByDesc.java @@ -34,17 +34,17 @@ private static final long serialVersionUID = 1L; /** - * GLOBAL No key. All rows --> 1 full aggregation on end of input + * GLOBAL No key. All rows --> 1 full aggregation on end of input * - * HASH Rows aggregated in to hash table on group key --> + * HASH Rows aggregated in to hash table on group key --> * 1 partial aggregation per key (normally, unless there is spilling) * * MERGE_PARTIAL As first operator in a REDUCER, partial aggregations come grouped from - * reduce-shuffle --> + * reduce-shuffle --> * aggregate the partial aggregations and emit full aggregation on * endGroup / closeOp * - * STREAMING Rows come from PARENT operator already grouped --> + * STREAMING Rows come from PARENT operator already grouped --> * aggregate the rows and emit full aggregation on key change / closeOp * * NOTE: Hash can spill partial result rows prematurely if it runs low on memory. @@ -115,16 +115,16 @@ public void setProjectedOutputColumns(int[] projectedOutputColumns) { * * Decides using GroupByDesc.Mode and whether there are keys. * - * Mode.COMPLETE --> (numKeys == 0 ? ProcessingMode.GLOBAL : ProcessingMode.STREAMING) + * Mode.COMPLETE --> (numKeys == 0 ? ProcessingMode.GLOBAL : ProcessingMode.STREAMING) * - * Mode.HASH --> ProcessingMode.HASH + * Mode.HASH --> ProcessingMode.HASH * - * Mode.MERGEPARTIAL --> (numKeys == 0 ? ProcessingMode.GLOBAL : ProcessingMode.MERGE_PARTIAL) + * Mode.MERGEPARTIAL --> (numKeys == 0 ? ProcessingMode.GLOBAL : ProcessingMode.MERGE_PARTIAL) * * Mode.PARTIAL1, * Mode.PARTIAL2, * Mode.PARTIALS, - * Mode.FINAL --> ProcessingMode.STREAMING + * Mode.FINAL --> ProcessingMode.STREAMING * */ public static ProcessingMode groupByDescModeToVectorProcessingMode(GroupByDesc.Mode mode, diff --git ql/src/java/org/apache/hadoop/hive/ql/ppd/PredicatePushDown.java ql/src/java/org/apache/hadoop/hive/ql/ppd/PredicatePushDown.java index a0c4008..a6514ca 100644 --- ql/src/java/org/apache/hadoop/hive/ql/ppd/PredicatePushDown.java +++ ql/src/java/org/apache/hadoop/hive/ql/ppd/PredicatePushDown.java @@ -53,9 +53,9 @@ * plan generation adds filters where they are seen but in some instances some * of the filter expressions can be pushed nearer to the operator that sees this * particular data for the first time. e.g. select a.*, b.* from a join b on - * (a.col1 = b.col1) where a.col1 > 20 and b.col2 > 40 + * (a.col1 = b.col1) where a.col1 > 20 and b.col2 > 40 * - * For the above query, the predicates (a.col1 > 20) and (b.col2 > 40), without + * For the above query, the predicates (a.col1 > 20) and (b.col2 > 40), without * predicate pushdown, would be evaluated after the join processing has been * done. Suppose the two predicates filter out most of the rows from a and b, * the join is unnecessarily processing these rows. With predicate pushdown, diff --git ql/src/java/org/apache/hadoop/hive/ql/processors/CommandProcessorResponse.java ql/src/java/org/apache/hadoop/hive/ql/processors/CommandProcessorResponse.java index e78ea45..c9fd64c 100644 --- ql/src/java/org/apache/hadoop/hive/ql/processors/CommandProcessorResponse.java +++ ql/src/java/org/apache/hadoop/hive/ql/processors/CommandProcessorResponse.java @@ -28,7 +28,7 @@ * CommandProcessor interface. Typically errorMessage * and SQLState will only be set if the responseCode * is not 0. Note that often {@code responseCode} ends up the exit value of - * command shell process so should keep it to < 127. + * command shell process so should keep it to < 127. */ public class CommandProcessorResponse { private final int responseCode; diff --git ql/src/java/org/apache/hadoop/hive/ql/processors/CryptoProcessor.java ql/src/java/org/apache/hadoop/hive/ql/processors/CryptoProcessor.java index 1acdc95..d0225bf 100644 --- ql/src/java/org/apache/hadoop/hive/ql/processors/CryptoProcessor.java +++ ql/src/java/org/apache/hadoop/hive/ql/processors/CryptoProcessor.java @@ -37,7 +37,7 @@ /** * This class processes HADOOP commands used for HDFS encryption. It is meant to be run - * only by Hive unit & queries tests. + * only by Hive unit & queries tests. */ public class CryptoProcessor implements CommandProcessor { public static final Logger LOG = LoggerFactory.getLogger(CryptoProcessor.class.getName()); diff --git ql/src/java/org/apache/hadoop/hive/ql/security/authorization/AuthorizationUtils.java ql/src/java/org/apache/hadoop/hive/ql/security/authorization/AuthorizationUtils.java index 04e5565..b8d938a 100644 --- ql/src/java/org/apache/hadoop/hive/ql/security/authorization/AuthorizationUtils.java +++ ql/src/java/org/apache/hadoop/hive/ql/security/authorization/AuthorizationUtils.java @@ -167,7 +167,6 @@ public static HivePrivilegeObject getHiveObjectRef(HiveObjectRef privObj) throws * Convert authorization plugin principal type to thrift principal type * @param type * @return - * @throws HiveException */ public static PrincipalType getThriftPrincipalType(HivePrincipalType type) { if(type == null){ diff --git ql/src/java/org/apache/hadoop/hive/ql/security/authorization/PrivilegeType.java ql/src/java/org/apache/hadoop/hive/ql/security/authorization/PrivilegeType.java index 5c2f389..40884c4 100644 --- ql/src/java/org/apache/hadoop/hive/ql/security/authorization/PrivilegeType.java +++ ql/src/java/org/apache/hadoop/hive/ql/security/authorization/PrivilegeType.java @@ -63,7 +63,7 @@ public Integer getToken() { /** * Do case lookup of PrivilegeType associated with this antlr token - * @param privilegeName + * @param token * @return corresponding PrivilegeType */ public static PrivilegeType getPrivTypeByToken(int token) { diff --git ql/src/java/org/apache/hadoop/hive/ql/security/authorization/plugin/HiveAuthorizer.java ql/src/java/org/apache/hadoop/hive/ql/security/authorization/plugin/HiveAuthorizer.java index 4814fc1..25e0a88 100644 --- ql/src/java/org/apache/hadoop/hive/ql/security/authorization/plugin/HiveAuthorizer.java +++ ql/src/java/org/apache/hadoop/hive/ql/security/authorization/plugin/HiveAuthorizer.java @@ -87,7 +87,7 @@ void revokePrivileges(List hivePrincipals, List hi /** * Create role * @param roleName - * @param adminGrantor - The user in "[ WITH ADMIN ]" clause of "create role" + * @param adminGrantor - The user in "[ WITH ADMIN <user> ]" clause of "create role" * @throws HiveAuthzPluginException * @throws HiveAccessControlException */ @@ -232,7 +232,7 @@ void checkPrivileges(HiveOperationType hiveOpType, List inp * returned, the Object has to be of type HiveAuthorizationTranslator * * @return - * @throws HiveException + * @throws HiveAuthzPluginException */ Object getHiveAuthorizationTranslator() throws HiveAuthzPluginException; @@ -246,19 +246,19 @@ void checkPrivileges(HiveOperationType hiveOpType, List inp * (part 1) It expects a valid filter condition to be returned. Null indicates no filtering is * required. * - * Example: table foo(c int) -> "c > 0 && c % 2 = 0" + * Example: table foo(c int) -> "c > 0 && c % 2 = 0" * * (part 2) It expects a valid expression as used in a select clause. Null * is NOT a valid option. If no transformation is needed simply return the * column name. * - * Example: column a -> "a" (no transform) + * Example: column a -> "a" (no transform) * - * Example: column a -> "reverse(a)" (call the reverse function on a) + * Example: column a -> "reverse(a)" (call the reverse function on a) * - * Example: column a -> "5" (replace column a with the constant 5) + * Example: column a -> "5" (replace column a with the constant 5) * - * @return List + * @return List<HivePrivilegeObject> * please return the list of HivePrivilegeObjects that need to be rewritten. * * @throws SemanticException @@ -271,7 +271,6 @@ void checkPrivileges(HiveOperationType hiveOpType, List inp * Returning false short-circuits the generation of row/column transforms. * * @return - * @throws SemanticException */ public boolean needTransform(); diff --git ql/src/java/org/apache/hadoop/hive/ql/security/authorization/plugin/HivePrivilegeObject.java ql/src/java/org/apache/hadoop/hive/ql/security/authorization/plugin/HivePrivilegeObject.java index 41983f1..414004a 100644 --- ql/src/java/org/apache/hadoop/hive/ql/security/authorization/plugin/HivePrivilegeObject.java +++ ql/src/java/org/apache/hadoop/hive/ql/security/authorization/plugin/HivePrivilegeObject.java @@ -136,7 +136,7 @@ public HivePrivilegeObject(HivePrivilegeObjectType type, String dbname, String o } /** - * Create HivePrivilegeObject of type {@link HivePrivilegeObjectType.COMMAND_PARAMS} + * Create HivePrivilegeObject of type {@link HivePrivilegeObject.HivePrivilegeObjectType#COMMAND_PARAMS} * @param cmdParams * @return */ @@ -204,7 +204,7 @@ public HivePrivObjectActionType getActionType() { } /** - * Applicable columns in this object, when the type is {@link HivePrivilegeObjectType.TABLE} + * Applicable columns in this object, when the type is {@link HivePrivilegeObject.HivePrivilegeObjectType#TABLE_OR_VIEW} * In case of DML read operations, this is the set of columns being used. * Column information is not set for DDL operations and for tables being written into * @return list of applicable columns diff --git ql/src/java/org/apache/hadoop/hive/ql/stats/StatsAggregator.java ql/src/java/org/apache/hadoop/hive/ql/stats/StatsAggregator.java index dacf7a9..394852f 100644 --- ql/src/java/org/apache/hadoop/hive/ql/stats/StatsAggregator.java +++ ql/src/java/org/apache/hadoop/hive/ql/stats/StatsAggregator.java @@ -27,9 +27,6 @@ /** * This method connects to the temporary storage. * - * @param hconf - * HiveConf that contains the connection parameters. - * @param sourceTask * @return true if connection is successful, false otherwise. */ public boolean connect(StatsCollectionContext scc); diff --git ql/src/java/org/apache/hadoop/hive/ql/stats/StatsPublisher.java ql/src/java/org/apache/hadoop/hive/ql/stats/StatsPublisher.java index 3631b83..797096c 100644 --- ql/src/java/org/apache/hadoop/hive/ql/stats/StatsPublisher.java +++ ql/src/java/org/apache/hadoop/hive/ql/stats/StatsPublisher.java @@ -31,15 +31,12 @@ * database (if not exist). * This method is usually called in the Hive client side rather than by the mappers/reducers * so that it is initialized only once. - * @param hconf HiveConf that contains the configurations parameters used to connect to - * intermediate stats database. * @return true if initialization is successful, false otherwise. */ public boolean init(StatsCollectionContext context); /** * This method connects to the intermediate statistics database. - * @param hconf HiveConf that contains the connection parameters. * @return true if connection is successful, false otherwise. */ public boolean connect(StatsCollectionContext context); diff --git ql/src/java/org/apache/hadoop/hive/ql/stats/StatsUtils.java ql/src/java/org/apache/hadoop/hive/ql/stats/StatsUtils.java index bda2050..df2012b 100644 --- ql/src/java/org/apache/hadoop/hive/ql/stats/StatsUtils.java +++ ql/src/java/org/apache/hadoop/hive/ql/stats/StatsUtils.java @@ -654,7 +654,7 @@ private static boolean containsNonPositives(List vals) { } /** - * Get sum of all values in the list that are >0 + * Get sum of all values in the list that are >0 * @param vals * - list of values * @return sum diff --git ql/src/java/org/apache/hadoop/hive/ql/udf/SettableUDF.java ql/src/java/org/apache/hadoop/hive/ql/udf/SettableUDF.java index e8f7e15..621405c 100644 --- ql/src/java/org/apache/hadoop/hive/ql/udf/SettableUDF.java +++ ql/src/java/org/apache/hadoop/hive/ql/udf/SettableUDF.java @@ -30,7 +30,6 @@ /** * Add data to UDF prior to initialization. * An exception may be thrown if the UDF doesn't know what to do with this data. - * @param params UDF-specific data to add to the UDF */ void setTypeInfo(TypeInfo typeInfo) throws UDFArgumentException; diff --git ql/src/java/org/apache/hadoop/hive/ql/udf/UDFConv.java ql/src/java/org/apache/hadoop/hive/ql/udf/UDFConv.java index 624afd1..e14c59a 100644 --- ql/src/java/org/apache/hadoop/hive/ql/udf/UDFConv.java +++ ql/src/java/org/apache/hadoop/hive/ql/udf/UDFConv.java @@ -139,7 +139,7 @@ private void char2byte(int radix, int fromPos) { } /** - * Convert numbers between different number bases. If toBase>0 the result is + * Convert numbers between different number bases. If toBase>0 the result is * unsigned, otherwise it is signed. * */ diff --git ql/src/java/org/apache/hadoop/hive/ql/udf/UDFParseUrl.java ql/src/java/org/apache/hadoop/hive/ql/udf/UDFParseUrl.java index fa0fe53..9d44001 100644 --- ql/src/java/org/apache/hadoop/hive/ql/udf/UDFParseUrl.java +++ ql/src/java/org/apache/hadoop/hive/ql/udf/UDFParseUrl.java @@ -36,7 +36,7 @@ * 'Ref' parse_url('http://facebook.com/path/p1.php?query=1#Ref', 'PROTOCOL') * will return 'http' Possible values are * HOST,PATH,QUERY,REF,PROTOCOL,AUTHORITY,FILE,USERINFO Also you can get a value - * of particular key in QUERY, using syntax QUERY: eg: QUERY:k1. + * of particular key in QUERY, using syntax QUERY:<KEY_NAME> eg: QUERY:k1. */ @Description(name = "parse_url", value = "_FUNC_(url, partToExtract[, key]) - extracts a part from a URL", diff --git ql/src/java/org/apache/hadoop/hive/ql/udf/UDFSign.java ql/src/java/org/apache/hadoop/hive/ql/udf/UDFSign.java index 449848a..12a5b5d 100644 --- ql/src/java/org/apache/hadoop/hive/ql/udf/UDFSign.java +++ ql/src/java/org/apache/hadoop/hive/ql/udf/UDFSign.java @@ -75,7 +75,7 @@ public DoubleWritable evaluate(LongWritable a) { /** * Get the sign of the decimal input * - * @param dec decimal input + * @param decWritable decimal input * * @return -1, 0, or 1 representing the sign of the input decimal */ diff --git ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDAFCorrelation.java ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDAFCorrelation.java index 61b777a..633c7d7 100644 --- ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDAFCorrelation.java +++ ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDAFCorrelation.java @@ -47,12 +47,12 @@ * Donald Knuth. * * Incremental: - * n : - * mx_n = mx_(n-1) + [x_n - mx_(n-1)]/n : - * my_n = my_(n-1) + [y_n - my_(n-1)]/n : - * c_n = c_(n-1) + (x_n - mx_(n-1))*(y_n - my_n) : - * vx_n = vx_(n-1) + (x_n - mx_n)(x_n - mx_(n-1)): - * vy_n = vy_(n-1) + (y_n - my_n)(y_n - my_(n-1)): + * n : <count> + * mx_n = mx_(n-1) + [x_n - mx_(n-1)]/n : <xavg> + * my_n = my_(n-1) + [y_n - my_(n-1)]/n : <yavg> + * c_n = c_(n-1) + (x_n - mx_(n-1))*(y_n - my_n) : <covariance * n> + * vx_n = vx_(n-1) + (x_n - mx_n)(x_n - mx_(n-1)): <variance * n> + * vy_n = vy_(n-1) + (y_n - my_n)(y_n - my_(n-1)): <variance * n> * * Merge: * c_(A,B) = c_A + c_B + (mx_A - mx_B)*(my_A - my_B)*n_A*n_B/(n_A+n_B) @@ -136,12 +136,12 @@ public GenericUDAFEvaluator getEvaluator(TypeInfo[] parameters) throws SemanticE * algorithm, based on work by Philippe Pébay and Donald Knuth. * * Incremental: - * n : - * mx_n = mx_(n-1) + [x_n - mx_(n-1)]/n : - * my_n = my_(n-1) + [y_n - my_(n-1)]/n : - * c_n = c_(n-1) + (x_n - mx_(n-1))*(y_n - my_n) : - * vx_n = vx_(n-1) + (x_n - mx_n)(x_n - mx_(n-1)): - * vy_n = vy_(n-1) + (y_n - my_n)(y_n - my_(n-1)): + * n : <count> + * mx_n = mx_(n-1) + [x_n - mx_(n-1)]/n : <xavg> + * my_n = my_(n-1) + [y_n - my_(n-1)]/n : <yavg> + * c_n = c_(n-1) + (x_n - mx_(n-1))*(y_n - my_n) : <covariance * n> + * vx_n = vx_(n-1) + (x_n - mx_n)(x_n - mx_(n-1)): <variance * n> + * vy_n = vy_(n-1) + (y_n - my_n)(y_n - my_(n-1)): <variance * n> * * Merge: * c_X = c_A + c_B + (mx_A - mx_B)*(my_A - my_B)*n_A*n_B/n_X diff --git ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDAFCovariance.java ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDAFCovariance.java index 8221c1b..fb62487 100644 --- ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDAFCovariance.java +++ ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDAFCovariance.java @@ -44,10 +44,10 @@ * Arbitrary-Order Statistical Moments", Philippe Pebay, Sandia Labs): * * Incremental: - * n : - * mx_n = mx_(n-1) + [x_n - mx_(n-1)]/n : - * my_n = my_(n-1) + [y_n - my_(n-1)]/n : - * c_n = c_(n-1) + (x_n - mx_(n-1))*(y_n - my_n) : + * n : <count> + * mx_n = mx_(n-1) + [x_n - mx_(n-1)]/n : <xavg> + * my_n = my_(n-1) + [y_n - my_(n-1)]/n : <yavg> + * c_n = c_(n-1) + (x_n - mx_(n-1))*(y_n - my_n) : <covariance * n> * * Merge: * c_X = c_A + c_B + (mx_A - mx_B)*(my_A - my_B)*n_A*n_B/n_X @@ -128,10 +128,10 @@ public GenericUDAFEvaluator getEvaluator(TypeInfo[] parameters) throws SemanticE * http://infoserve.sandia.gov/sand_doc/2008/086212.pdf * * Incremental: - * n : - * mx_n = mx_(n-1) + [x_n - mx_(n-1)]/n : - * my_n = my_(n-1) + [y_n - my_(n-1)]/n : - * c_n = c_(n-1) + (x_n - mx_(n-1))*(y_n - my_n) : + * n : <count> + * mx_n = mx_(n-1) + [x_n - mx_(n-1)]/n : <xavg> + * my_n = my_(n-1) + [y_n - my_(n-1)]/n : <yavg> + * c_n = c_(n-1) + (x_n - mx_(n-1))*(y_n - my_n) : <covariance * n> * * Merge: * c_X = c_A + c_B + (mx_A - mx_B)*(my_A - my_B)*n_A*n_B/n_X diff --git ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDAFEvaluator.java ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDAFEvaluator.java index 3a98276..2acd7ff 100644 --- ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDAFEvaluator.java +++ ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDAFEvaluator.java @@ -44,7 +44,7 @@ * accept arguments of complex types, and return complex types. 2. It can accept * variable length of arguments. 3. It can accept an infinite number of function * signature - for example, it's easy to write a GenericUDAF that accepts - * array, array> and so on (arbitrary levels of nesting). + * array<int>, array<array<int>> and so on (arbitrary levels of nesting). */ @UDFType(deterministic = true) public abstract class GenericUDAFEvaluator implements Closeable { diff --git ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDAFLeadLag.java ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDAFLeadLag.java index 376b73e..544f7ab 100644 --- ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDAFLeadLag.java +++ ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDAFLeadLag.java @@ -33,7 +33,7 @@ import org.apache.hadoop.io.IntWritable; /** - * abstract class for Lead & lag UDAFs GenericUDAFLeadLag. + * abstract class for Lead & lag UDAFs GenericUDAFLeadLag. * */ public abstract class GenericUDAFLeadLag extends AbstractGenericUDAFResolver { diff --git ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDF.java ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDF.java index 68d98f5..9fb4cc7 100644 --- ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDF.java +++ ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDF.java @@ -61,7 +61,7 @@ * accept arguments of complex types, and return complex types. 2. It can accept * variable length of arguments. 3. It can accept an infinite number of function * signature - for example, it's easy to write a GenericUDF that accepts - * array, array> and so on (arbitrary levels of nesting). 4. It + * array<int>, array<array<int>> and so on (arbitrary levels of nesting). 4. It * can do short-circuit evaluations using DeferedObject. */ @UDFType(deterministic = true) @@ -216,7 +216,7 @@ public void close() throws IOException { /** * Some functions like comparisons may be affected by appearing order of arguments. - * This is to convert a function, such as 3 > x to x < 3. The flip function of + * This is to convert a function, such as 3 > x to x < 3. The flip function of * GenericUDFOPGreaterThan is GenericUDFOPLessThan. */ public GenericUDF flip() { @@ -227,7 +227,6 @@ public GenericUDF flip() { * Gets the negative function of the current one. E.g., GenericUDFOPNotEqual for * GenericUDFOPEqual, or GenericUDFOPNull for GenericUDFOPNotNull. * @return Negative function - * @throws UDFArgumentException */ public GenericUDF negative() { throw new UnsupportedOperationException("Negative function doesn't exist for " + getFuncName()); diff --git ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDFConcatWS.java ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDFConcatWS.java index 606cb22..e415ad6 100644 --- ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDFConcatWS.java +++ ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDFConcatWS.java @@ -37,7 +37,7 @@ /** * Generic UDF for string function - * CONCAT_WS(sep, [string | array(string)]+). + * CONCAT_WS(sep, [string | array(string)]+). * This mimics the function from * MySQL http://dev.mysql.com/doc/refman/5.0/en/string-functions.html# * function_concat-ws diff --git ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDFIf.java ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDFIf.java index e1fdc41..7667301 100644 --- ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDFIf.java +++ ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDFIf.java @@ -67,7 +67,7 @@ /** * IF(expr1,expr2,expr3)
      - * If expr1 is TRUE (expr1 <> 0 and expr1 <> NULL) then IF() returns expr2; + * If expr1 is TRUE (expr1 <> 0 and expr1 <> NULL) then IF() returns expr2; * otherwise it returns expr3. IF() returns a numeric or string value, depending * on the context in which it is used. */ diff --git ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDFTimestamp.java ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDFTimestamp.java index 4d9691e..b6de9e9 100644 --- ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDFTimestamp.java +++ ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDFTimestamp.java @@ -40,7 +40,7 @@ * GenericUDFTimestamp * * Example usage: - * ... CAST( as TIMESTAMP) ... + * ... CAST(<Timestamp string> as TIMESTAMP) ... * * Creates a TimestampWritable object using PrimitiveObjectInspectorConverter * diff --git ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDFToIntervalDayTime.java ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDFToIntervalDayTime.java index e644320..5e0a33c 100644 --- ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDFToIntervalDayTime.java +++ ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDFToIntervalDayTime.java @@ -34,7 +34,7 @@ * GenericUDFIntervalDayTime * * Example usage: -* ... CAST( as INTERVAL DAY TO SECOND) ... +* ... CAST(<Interval string> as INTERVAL DAY TO SECOND) ... * * Creates a HiveIntervalDayTimeWritable object using PrimitiveObjectInspectorConverter * diff --git ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDFToIntervalYearMonth.java ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDFToIntervalYearMonth.java index 92a40f8..0008008 100644 --- ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDFToIntervalYearMonth.java +++ ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDFToIntervalYearMonth.java @@ -34,7 +34,7 @@ * GenericUDFIntervalYearMonth * * Example usage: -* ... CAST( as INTERVAL YEAR TO MONTH) ... +* ... CAST(<Interval string> as INTERVAL YEAR TO MONTH) ... * * Creates a HiveIntervalYearMonthWritable object using PrimitiveObjectInspectorConverter * diff --git ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDTF.java ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDTF.java index a93a264..987df50 100644 --- ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDTF.java +++ ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDTF.java @@ -41,7 +41,7 @@ * Additionally setup GenericUDTF with MapredContext before initializing. * This is only called in runtime of MapRedTask. * - * @param context context + * @param mapredContext context */ public void configure(MapredContext mapredContext) { } diff --git ql/src/java/org/apache/hadoop/hive/ql/udf/ptf/MatchPath.java ql/src/java/org/apache/hadoop/hive/ql/udf/ptf/MatchPath.java index cc2b77b..7611404 100644 --- ql/src/java/org/apache/hadoop/hive/ql/udf/ptf/MatchPath.java +++ ql/src/java/org/apache/hadoop/hive/ql/udf/ptf/MatchPath.java @@ -70,7 +70,7 @@ * where the first occurrence was LATE, followed by zero or more EARLY flights, * followed by a ONTIME or EARLY flight. *

    • symbols specify a list of name, expression pairs. For e.g. - * 'LATE', arrival_delay > 0, 'EARLY', arrival_delay < 0 , 'ONTIME', arrival_delay == 0. + * 'LATE', arrival_delay > 0, 'EARLY', arrival_delay < 0 , 'ONTIME', arrival_delay == 0. * These symbols can be used in the Pattern defined above. *
    • resultSelectList specified as a select list. * The expressions in the selectList are evaluated in the context where all the diff --git ql/src/java/org/apache/hadoop/hive/ql/udf/ptf/TableFunctionEvaluator.java ql/src/java/org/apache/hadoop/hive/ql/udf/ptf/TableFunctionEvaluator.java index 7b30838..0da1e19 100644 --- ql/src/java/org/apache/hadoop/hive/ql/udf/ptf/TableFunctionEvaluator.java +++ ql/src/java/org/apache/hadoop/hive/ql/udf/ptf/TableFunctionEvaluator.java @@ -62,7 +62,7 @@ * Based on Hive {@link GenericUDAFEvaluator}. Break up the responsibility of the old AbstractTableFunction * class into a Resolver and Evaluator. *

      - * The Evaluator also holds onto the {@link TableFunctionDef}. This provides information + * The Evaluator also holds onto the {@link PartitionedTableFunctionDef}. This provides information * about the arguments to the function, the shape of the Input partition and the Partitioning details. * The Evaluator is responsible for providing the 2 execute methods: *

        diff --git ql/src/java/org/apache/hadoop/hive/ql/udf/ptf/TableFunctionResolver.java ql/src/java/org/apache/hadoop/hive/ql/udf/ptf/TableFunctionResolver.java index 71034d7..c953710 100644 --- ql/src/java/org/apache/hadoop/hive/ql/udf/ptf/TableFunctionResolver.java +++ ql/src/java/org/apache/hadoop/hive/ql/udf/ptf/TableFunctionResolver.java @@ -36,15 +36,15 @@ * old AbstractTableFunction class into a Resolver and Evaluator. * The Resolver is responsible for: *
          - *
        1. setting up the {@link tableFunctionEvaluator} + *
        2. setting up the {@link TableFunctionEvaluator} *
        3. Setting up the The raw and output ObjectInspectors of the Evaluator. - *
        4. The Evaluator also holds onto the {@link TableFunctionDef}. This provides information + *
        5. The Evaluator also holds onto the {@link PartitionedTableFunctionDef}. This provides information * about the arguments to the function, the shape of the Input partition and the Partitioning details. *
        * The Resolver for a function is obtained from the {@link FunctionRegistry}. The Resolver is initialized * by the following 4 step process: *
          - *
        1. The initialize method is called; which is passed the {@link PTFDesc} and the {@link TableFunctionDef}. + *
        2. The initialize method is called; which is passed the {@link PTFDesc} and the {@link PartitionedTableFunctionDef}. *
        3. The resolver is then asked to setup the Raw ObjectInspector. This is only required if the Function reshapes * the raw input. *
        4. Once the Resolver has had a chance to compute the shape of the Raw Input that is fed to the partitioning @@ -110,8 +110,6 @@ public TableFunctionEvaluator getEvaluator() { * exist for all the Def (ArgDef, ColumnDef, WindowDef..). It is the responsibility of * the TableFunction to construct the {@link ExprNodeEvaluator evaluators} and setup the OI. * - * @param tblFuncDef - * @param ptfDesc * @throws HiveException */ public abstract void initializeOutputOI() throws HiveException;