diff --git a/metastore/src/java/org/apache/hadoop/hive/metastore/IExtrapolatePartStatus.java b/metastore/src/java/org/apache/hadoop/hive/metastore/IExtrapolatePartStatus.java new file mode 100644 index 0000000..86257ad --- /dev/null +++ b/metastore/src/java/org/apache/hadoop/hive/metastore/IExtrapolatePartStatus.java @@ -0,0 +1,41 @@ +package org.apache.hadoop.hive.metastore; + +import java.util.Map; + +public interface IExtrapolatePartStatus { + /** + * The sequence of colStatNames. + */ + static String[] colStatNames = new String[] { "LONG_LOW_VALUE", + "LONG_HIGH_VALUE", "DOUBLE_LOW_VALUE", "DOUBLE_HIGH_VALUE", + "BIG_DECIMAL_LOW_VALUE", "BIG_DECIMAL_HIGH_VALUE", "NUM_NULLS", + "NUM_DISTINCTS", "AVG_COL_LEN", "MAX_COL_LEN", "NUM_TRUES", "NUM_FALSES" }; + + /** + * The sequence of colStatTypes. + */ + static enum ColStatType { + Long, Double, Decimal + } + + static ColStatType[] colStatTypes = new ColStatType[] { ColStatType.Long, + ColStatType.Long, ColStatType.Double, ColStatType.Double, + ColStatType.Decimal, ColStatType.Decimal, ColStatType.Long, + ColStatType.Long, ColStatType.Double, ColStatType.Long, ColStatType.Long, + ColStatType.Long }; + + /** + * The sequence of aggregation function on colStats. + */ + static enum FuncType { + Min, Max, Sum + } + + static FuncType[] funcTypes = new FuncType[] { FuncType.Min, FuncType.Max, + FuncType.Min, FuncType.Max, FuncType.Min, FuncType.Max, FuncType.Sum, + FuncType.Max, FuncType.Max, FuncType.Max, FuncType.Sum, FuncType.Sum }; + + public Object extrapolate(Object[] min, Object[] max, int colStatIndex, + Map indexMap); + +} diff --git a/metastore/src/java/org/apache/hadoop/hive/metastore/LinearExtrapolatePartStatus.java b/metastore/src/java/org/apache/hadoop/hive/metastore/LinearExtrapolatePartStatus.java new file mode 100644 index 0000000..5c53c24 --- /dev/null +++ b/metastore/src/java/org/apache/hadoop/hive/metastore/LinearExtrapolatePartStatus.java @@ -0,0 +1,114 @@ +package org.apache.hadoop.hive.metastore; + +import java.math.BigDecimal; +import java.nio.ByteBuffer; +import java.util.Map; + +import org.apache.hadoop.hive.metastore.api.Decimal; + +public class LinearExtrapolatePartStatus implements IExtrapolatePartStatus { + + @Override + public Object extrapolate(Object[] min, Object[] max, int colStatIndex, + Map indexMap) { + int rightBorderInd = indexMap.size() - 1; + int minInd = indexMap.get((String) min[1]); + int maxInd = indexMap.get((String) max[1]); + if (minInd == maxInd) { + return min[0]; + } + if (funcTypes[colStatIndex] == FuncType.Max) { + if (minInd < maxInd) { + // right border is the max + if (colStatTypes[colStatIndex] == ColStatType.Long) { + return (Long) ((Long) min[0] + (((Long) max[0] - (Long) min[0]) + * (rightBorderInd - minInd) / (maxInd - minInd))); + } else if (colStatTypes[colStatIndex] == ColStatType.Double) { + return (Double) ((Double) min[0] + (((Double) max[0] - (Double) min[0]) + * (rightBorderInd - minInd) / (maxInd - minInd))); + } else { + Decimal dmax = (Decimal) max[0]; + BigDecimal bdmax = new BigDecimal(dmax.toString()); + double doublemax = bdmax.doubleValue(); + Decimal dmin = (Decimal) min[0]; + BigDecimal bdmin = new BigDecimal(dmin.toString()); + double doublemin = bdmin.doubleValue(); + double ret = doublemin + (doublemax - doublemin) + * (rightBorderInd - minInd) / (maxInd - minInd); + return createThriftDecimal(String.valueOf(ret)); + } + } else { + // left border is the max + if (colStatTypes[colStatIndex] == ColStatType.Long) { + return (Long) ((Long) min[0] + ((Long) max[0] - (Long) min[0]) + * minInd / (minInd - maxInd)); + } else if (colStatTypes[colStatIndex] == ColStatType.Double) { + return (Double) ((Double) min[0] + ((Double) max[0] - (Double) min[0]) + * minInd / (maxInd - minInd)); + } else { + Decimal dmax = (Decimal) max[0]; + BigDecimal bdmax = new BigDecimal(dmax.toString()); + double doublemax = bdmax.doubleValue(); + Decimal dmin = (Decimal) min[0]; + BigDecimal bdmin = new BigDecimal(dmin.toString()); + double doublemin = bdmin.doubleValue(); + double ret = doublemin + (doublemax - doublemin) * minInd + / (maxInd - minInd); + return createThriftDecimal(String.valueOf(ret)); + } + } + } else { + if (minInd < maxInd) { + // left border is the min + if (colStatTypes[colStatIndex] == ColStatType.Long) { + Long ret = (Long) max[0] - ((Long) max[0] - (Long) min[0]) * maxInd + / (maxInd - minInd); + return ret; + } else if (colStatTypes[colStatIndex] == ColStatType.Double) { + Double ret = (Double) max[0] - ((Double) max[0] - (Double) min[0]) + * maxInd / (maxInd - minInd); + return ret; + } else { + Decimal dmax = (Decimal) max[0]; + BigDecimal bdmax = new BigDecimal(dmax.toString()); + double doublemax = bdmax.doubleValue(); + Decimal dmin = (Decimal) min[0]; + BigDecimal bdmin = new BigDecimal(dmin.toString()); + double doublemin = bdmin.doubleValue(); + double ret = doublemax - (doublemax - doublemin) * maxInd + / (maxInd - minInd); + return createThriftDecimal(String.valueOf(ret)); + + } + } else { + // right border is the min + if (colStatTypes[colStatIndex] == ColStatType.Long) { + Long ret = (Long) max[0] - ((Long) max[0] - (Long) min[0]) + * (rightBorderInd - maxInd) / (minInd - maxInd); + return ret; + } else if (colStatTypes[colStatIndex] == ColStatType.Double) { + Double ret = (Double) max[0] - ((Double) max[0] - (Double) min[0]) + * (rightBorderInd - maxInd) / (minInd - maxInd); + return ret; + } else { + Decimal dmax = (Decimal) max[0]; + BigDecimal bdmax = new BigDecimal(dmax.toString()); + double doublemax = bdmax.doubleValue(); + Decimal dmin = (Decimal) min[0]; + BigDecimal bdmin = new BigDecimal(dmin.toString()); + double doublemin = bdmin.doubleValue(); + double ret = doublemax - (doublemax - doublemin) + * (rightBorderInd - maxInd) / (minInd - maxInd); + return createThriftDecimal(String.valueOf(ret)); + } + } + } + } + + private static Decimal createThriftDecimal(String s) { + BigDecimal d = new BigDecimal(s); + return new Decimal(ByteBuffer.wrap(d.unscaledValue().toByteArray()), + (short) d.scale()); + } + +} diff --git a/metastore/src/java/org/apache/hadoop/hive/metastore/MetaStoreDirectSql.java b/metastore/src/java/org/apache/hadoop/hive/metastore/MetaStoreDirectSql.java index 767cffc..7adaa7f 100644 --- a/metastore/src/java/org/apache/hadoop/hive/metastore/MetaStoreDirectSql.java +++ b/metastore/src/java/org/apache/hadoop/hive/metastore/MetaStoreDirectSql.java @@ -27,6 +27,7 @@ import java.text.ParseException; import java.text.SimpleDateFormat; import java.util.ArrayList; +import java.util.Arrays; import java.util.Date; import java.util.HashMap; import java.util.Iterator; @@ -67,6 +68,7 @@ import org.apache.hadoop.hive.metastore.parser.ExpressionTree.TreeVisitor; import org.apache.hadoop.hive.metastore.parser.FilterLexer; import org.apache.hadoop.hive.serde.serdeConstants; +import org.datanucleus.store.rdbms.query.ForwardQueryResult; import org.datanucleus.store.schema.SchemaTool; import com.google.common.collect.Lists; @@ -893,33 +895,202 @@ public ColumnStatistics getTableStats( return result; } - public List aggrColStatsForPartitions(String dbName, String tableName, - List partNames, List colNames) throws MetaException { - String qText = "select \"COLUMN_NAME\", \"COLUMN_TYPE\", " - + "min(\"LONG_LOW_VALUE\"), max(\"LONG_HIGH_VALUE\"), min(\"DOUBLE_LOW_VALUE\"), max(\"DOUBLE_HIGH_VALUE\"), " - + "min(\"BIG_DECIMAL_LOW_VALUE\"), max(\"BIG_DECIMAL_HIGH_VALUE\"), sum(\"NUM_NULLS\"), max(\"NUM_DISTINCTS\"), " - + "max(\"AVG_COL_LEN\"), max(\"MAX_COL_LEN\"), sum(\"NUM_TRUES\"), sum(\"NUM_FALSES\") from \"PART_COL_STATS\"" - + " where \"DB_NAME\" = ? and \"TABLE_NAME\" = ? and \"COLUMN_NAME\" in (" - + makeParams(colNames.size()) + ") AND \"PARTITION_NAME\" in (" - + makeParams(partNames.size()) + ") group by \"COLUMN_NAME\", \"COLUMN_TYPE\""; + public List aggrColStatsForPartitions(String dbName, + String tableName, List partNames, List colNames) + throws MetaException { + // Check if the status of all the columns of all the partitions exists + String qText = "select count(*) from \"PART_COL_STATS\"" + + " where \"DB_NAME\" = ? and \"TABLE_NAME\" = ? and \"COLUMN_NAME\" in (" + + makeParams(colNames.size()) + ") AND \"PARTITION_NAME\" in (" + + makeParams(partNames.size()) + ") "; boolean doTrace = LOG.isDebugEnabled(); long start = doTrace ? System.nanoTime() : 0; Query query = pm.newQuery("javax.jdo.query.SQL", qText); - Object qResult = query.executeWithArray(prepareParams(dbName, tableName, partNames, colNames)); + Object qResult = query.executeWithArray(prepareParams(dbName, tableName, + partNames, colNames)); if (qResult == null) { query.closeAll(); return Lists.newArrayList(); } - List list = ensureList(qResult); - List colStats = new ArrayList(list.size()); - for (Object[] row : list) { - colStats.add(prepareCSObj(row,0)); - } + ForwardQueryResult fqr = (ForwardQueryResult) qResult; + Integer total = (Integer) fqr.get(0); long end = doTrace ? System.nanoTime() : 0; timingTrace(doTrace, qText, start, end); query.closeAll(); - return colStats; + + String commonPrefix = "select \"COLUMN_NAME\", \"COLUMN_TYPE\", " + + "min(\"LONG_LOW_VALUE\"), max(\"LONG_HIGH_VALUE\"), min(\"DOUBLE_LOW_VALUE\"), max(\"DOUBLE_HIGH_VALUE\"), " + + "min(\"BIG_DECIMAL_LOW_VALUE\"), max(\"BIG_DECIMAL_HIGH_VALUE\"), sum(\"NUM_NULLS\"), max(\"NUM_DISTINCTS\"), " + + "max(\"AVG_COL_LEN\"), max(\"MAX_COL_LEN\"), sum(\"NUM_TRUES\"), sum(\"NUM_FALSES\") from \"PART_COL_STATS\"" + + " where \"DB_NAME\" = ? and \"TABLE_NAME\" = ? and \"COLUMN_NAME\" in ("; + + if (total == colNames.size() * (partNames.size() - 1)) { + // Extrapolation is not needed. + qText = commonPrefix + + makeParams(colNames.size()) + ") AND \"PARTITION_NAME\" in (" + + makeParams(partNames.size()) + + ") group by \"COLUMN_NAME\", \"COLUMN_TYPE\""; + start = doTrace ? System.nanoTime() : 0; + query = pm.newQuery("javax.jdo.query.SQL", qText); + qResult = query.executeWithArray(prepareParams(dbName, tableName, + partNames, colNames)); + if (qResult == null) { + query.closeAll(); + return Lists.newArrayList(); + } + List list = ensureList(qResult); + List colStats = new ArrayList( + list.size()); + for (Object[] row : list) { + colStats.add(prepareCSObj(row, 0)); + } + end = doTrace ? System.nanoTime() : 0; + timingTrace(doTrace, qText, start, end); + query.closeAll(); + return colStats; + } else { + // Extrapolation is needed for some columns. + // In this case, at least a column status for a partition is missing. + // We need to extrapolate this partition based on the other partitions + List colStats = new ArrayList( + colNames.size()); + for (String colname : colNames) { + qText = "select \"PARTITION_NAME\" from \"PART_COL_STATS\"" + + " where \"DB_NAME\" = ? and \"TABLE_NAME\" = ? and \"COLUMN_NAME\" in (" + + makeParams(1) + ") AND \"PARTITION_NAME\" in (" + + makeParams(partNames.size()) + ") "; + start = doTrace ? System.nanoTime() : 0; + query = pm.newQuery("javax.jdo.query.SQL", qText); + qResult = query.executeWithArray(prepareParams(dbName, tableName, + partNames, Arrays.asList(colname))); + if (qResult == null) { + query.closeAll(); + return Lists.newArrayList(); + } + fqr = (ForwardQueryResult) qResult; + List existPartNames = new ArrayList(); + existPartNames.addAll(fqr); + end = doTrace ? System.nanoTime() : 0; + timingTrace(doTrace, qText, start, end); + query.closeAll(); + + if (existPartNames.size() == (partNames.size() - 1) + || existPartNames.size() < 2) { + // Extrapolation is not needed for this column if + // existPartNames.size()==partNames.size() + // Or, extrapolation is not possible for this column if + // existPartNames.size()<2 + qText = commonPrefix + + makeParams(1) + ") AND \"PARTITION_NAME\" in (" + + makeParams(partNames.size()) + + ") group by \"COLUMN_NAME\", \"COLUMN_TYPE\""; + start = doTrace ? System.nanoTime() : 0; + query = pm.newQuery("javax.jdo.query.SQL", qText); + qResult = query.executeWithArray(prepareParams(dbName, tableName, + partNames, Arrays.asList(colname))); + if (qResult == null) { + query.closeAll(); + return Lists.newArrayList(); + } + List list = ensureList(qResult); + for (Object[] row : list) { + colStats.add(prepareCSObj(row, 0)); + } + end = doTrace ? System.nanoTime() : 0; + timingTrace(doTrace, qText, start, end); + query.closeAll(); + } else { + // Extrapolation is needed for this column. + + // give a sequence number for all the partitions + Map indexMap = new HashMap(); + for (int index = 0; index < partNames.size(); index++) { + indexMap.put(partNames.get(index), index); + } + + // fill in colname + Object[] row = new Object[IExtrapolatePartStatus.colStatNames.length + 2]; + row[0] = colname; + + // fill in coltype + qText = "select \"COLUMN_TYPE\" from \"PART_COL_STATS\" " + + " where \"COLUMN_NAME\" = \'" + colname + "\' and \"DB_NAME\" = \'" + + dbName + "\' and \"TABLE_NAME\" = \'" + tableName + "\'"; + query = pm.newQuery("javax.jdo.query.SQL", qText); + start = doTrace ? System.nanoTime() : 0; + qResult = query.execute(); + if (qResult == null) { + query.closeAll(); + return Lists.newArrayList(); + } + fqr = (ForwardQueryResult) qResult; + row[1] = (String) fqr.get(0); + + //use linear extrapolation. more complicated one can be added in the future. + IExtrapolatePartStatus extrapolateMethod = new LinearExtrapolatePartStatus(); + + // fill in colstatus + for (int colStatIndex = 0; colStatIndex < IExtrapolatePartStatus.colStatNames.length; colStatIndex++) { + String colStatName = IExtrapolatePartStatus.colStatNames[colStatIndex]; + // if the aggregation type is sum, we do a scale-up + if (IExtrapolatePartStatus.funcTypes[colStatIndex] == IExtrapolatePartStatus.FuncType.Sum) { + qText = "select " + "sum(" + colStatName + + ") from \"PART_COL_STATS\"" + " where \"COLUMN_NAME\" = \'" + + colname + "\' and \"DB_NAME\" = \'" + dbName + + "\' and \"TABLE_NAME\" = \'" + tableName + "\'"; + query = pm.newQuery("javax.jdo.query.SQL", qText); + start = doTrace ? System.nanoTime() : 0; + qResult = query.execute(); + if (qResult == null) { + query.closeAll(); + return Lists.newArrayList(); + } + end = doTrace ? System.nanoTime() : 0; + timingTrace(doTrace, qText, start, end); + fqr = (ForwardQueryResult) qResult; + if (fqr == null || fqr.isEmpty()) { + row[2 + colStatIndex] = null; + } else { + Long val = (Long) (fqr.get(0)); + row[2 + colStatIndex] = (Long) (val / existPartNames.size() * (partNames + .size() - 1)); + } + query.closeAll(); + } else { + // if the aggregation type is min/max, we extrapolate from the + // left/right borders + qText = "select " + colStatName + + ",\"PARTITION_NAME\" from \"PART_COL_STATS\"" + + " where \"COLUMN_NAME\" = \'" + colname + "\' and \"DB_NAME\" = \'" + + dbName + "\' and \"TABLE_NAME\" = \'" + tableName + "\'" + + " order by \'" + colStatName + "\'"; + query = pm.newQuery("javax.jdo.query.SQL", qText); + start = doTrace ? System.nanoTime() : 0; + qResult = query.execute(); + if (qResult == null) { + query.closeAll(); + return Lists.newArrayList(); + } + fqr = (ForwardQueryResult) qResult; + Object[] min = (Object[]) (fqr.get(0)); + Object[] max = (Object[]) (fqr.get(fqr.size() - 1)); + end = doTrace ? System.nanoTime() : 0; + timingTrace(doTrace, qText, start, end); + query.closeAll(); + if (min[0] == null || max[0] == null) { + row[2 + colStatIndex] = null; + } else { + row[2 + colStatIndex] = extrapolateMethod.extrapolate(min, max, colStatIndex, + indexMap); + } + } + } + colStats.add(prepareCSObj(row, 0)); + } + } + return colStats; + } } private ColumnStatisticsObj prepareCSObj (Object[] row, int i) throws MetaException { diff --git a/ql/src/test/queries/clientpositive/extrapolate_part_stats.q b/ql/src/test/queries/clientpositive/extrapolate_part_stats.q new file mode 100644 index 0000000..100a298 --- /dev/null +++ b/ql/src/test/queries/clientpositive/extrapolate_part_stats.q @@ -0,0 +1,51 @@ +set hive.stats.fetch.column.stats=true; +set hive.stats.autogather=false; +set hive.exec.dynamic.partition=true; +set hive.exec.dynamic.partition.mode=nonstrict; + +create table if not exists ext_loc ( + state string, + locid int, + zip int, + year string +) row format delimited fields terminated by '|' stored as textfile; + +LOAD DATA LOCAL INPATH '../../data/files/extrapolate_stats.txt' OVERWRITE INTO TABLE ext_loc; + +create table if not exists loc_orc_1d ( + state string, + locid int, + zip int +) partitioned by(year string) stored as orc; + +insert overwrite table loc_orc_1d partition(year) select * from ext_loc; + +analyze table loc_orc_1d partition(year='2001') compute statistics for columns state,locid; + +analyze table loc_orc_1d partition(year='2002') compute statistics for columns state,locid; + +describe formatted loc_orc_1d.state PARTITION(year='2001'); + +describe formatted loc_orc_1d.state PARTITION(year='2002'); + +-- basicStatState: COMPLETE colStatState: PARTIAL +explain extended select state from loc_orc_1d; + +-- column statistics for __HIVE_DEFAULT_PARTITION__ is not supported yet. Hence colStatState reports PARTIAL +-- basicStatState: COMPLETE colStatState: PARTIAL +explain extended select state,locid from loc_orc_1d; + +create table if not exists loc_orc_2d ( + state string, + locid int +) partitioned by(zip int, year string) stored as orc; + +insert overwrite table loc_orc_2d partition(zip, year) select * from ext_loc; + +analyze table loc_orc_2d partition(zip=94086, year='2001') compute statistics for columns state,locid; + +analyze table loc_orc_2d partition(zip=94087, year='2002') compute statistics for columns state,locid; + +explain extended select state from loc_orc_2d; + +explain extended select state,locid from loc_orc_2d; diff --git a/ql/src/test/results/clientpositive/extrapolate_part_stats.q.out b/ql/src/test/results/clientpositive/extrapolate_part_stats.q.out new file mode 100644 index 0000000..0dcc560 --- /dev/null +++ b/ql/src/test/results/clientpositive/extrapolate_part_stats.q.out @@ -0,0 +1,2251 @@ +PREHOOK: query: create table if not exists ext_loc ( + state string, + locid int, + zip int, + year string +) row format delimited fields terminated by '|' stored as textfile +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +POSTHOOK: query: create table if not exists ext_loc ( + state string, + locid int, + zip int, + year string +) row format delimited fields terminated by '|' stored as textfile +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@ext_loc +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/extrapolate_stats.txt' OVERWRITE INTO TABLE ext_loc +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@ext_loc +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/extrapolate_stats.txt' OVERWRITE INTO TABLE ext_loc +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@ext_loc +PREHOOK: query: create table if not exists loc_orc_1d ( + state string, + locid int, + zip int +) partitioned by(year string) stored as orc +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +POSTHOOK: query: create table if not exists loc_orc_1d ( + state string, + locid int, + zip int +) partitioned by(year string) stored as orc +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@loc_orc_1d +PREHOOK: query: insert overwrite table loc_orc_1d partition(year) select * from ext_loc +PREHOOK: type: QUERY +PREHOOK: Input: default@ext_loc +PREHOOK: Output: default@loc_orc_1d +POSTHOOK: query: insert overwrite table loc_orc_1d partition(year) select * from ext_loc +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ext_loc +POSTHOOK: Output: default@loc_orc_1d@year=2000 +POSTHOOK: Output: default@loc_orc_1d@year=2001 +POSTHOOK: Output: default@loc_orc_1d@year=2002 +POSTHOOK: Output: default@loc_orc_1d@year=2003 +POSTHOOK: Output: default@loc_orc_1d@year=__HIVE_DEFAULT_PARTITION__ +POSTHOOK: Lineage: loc_orc_1d PARTITION(year=2000).locid SIMPLE [(ext_loc)ext_loc.FieldSchema(name:locid, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc_1d PARTITION(year=2000).state SIMPLE [(ext_loc)ext_loc.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc_1d PARTITION(year=2000).zip SIMPLE [(ext_loc)ext_loc.FieldSchema(name:zip, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc_1d PARTITION(year=2001).locid SIMPLE [(ext_loc)ext_loc.FieldSchema(name:locid, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc_1d PARTITION(year=2001).state SIMPLE [(ext_loc)ext_loc.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc_1d PARTITION(year=2001).zip SIMPLE [(ext_loc)ext_loc.FieldSchema(name:zip, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc_1d PARTITION(year=2002).locid SIMPLE [(ext_loc)ext_loc.FieldSchema(name:locid, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc_1d PARTITION(year=2002).state SIMPLE [(ext_loc)ext_loc.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc_1d PARTITION(year=2002).zip SIMPLE [(ext_loc)ext_loc.FieldSchema(name:zip, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc_1d PARTITION(year=2003).locid SIMPLE [(ext_loc)ext_loc.FieldSchema(name:locid, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc_1d PARTITION(year=2003).state SIMPLE [(ext_loc)ext_loc.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc_1d PARTITION(year=2003).zip SIMPLE [(ext_loc)ext_loc.FieldSchema(name:zip, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc_1d PARTITION(year=__HIVE_DEFAULT_PARTITION__).locid SIMPLE [(ext_loc)ext_loc.FieldSchema(name:locid, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc_1d PARTITION(year=__HIVE_DEFAULT_PARTITION__).state SIMPLE [(ext_loc)ext_loc.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc_1d PARTITION(year=__HIVE_DEFAULT_PARTITION__).zip SIMPLE [(ext_loc)ext_loc.FieldSchema(name:zip, type:int, comment:null), ] +PREHOOK: query: analyze table loc_orc_1d partition(year='2001') compute statistics for columns state,locid +PREHOOK: type: QUERY +PREHOOK: Input: default@loc_orc_1d +PREHOOK: Input: default@loc_orc_1d@year=2001 +#### A masked pattern was here #### +POSTHOOK: query: analyze table loc_orc_1d partition(year='2001') compute statistics for columns state,locid +POSTHOOK: type: QUERY +POSTHOOK: Input: default@loc_orc_1d +POSTHOOK: Input: default@loc_orc_1d@year=2001 +#### A masked pattern was here #### +PREHOOK: query: analyze table loc_orc_1d partition(year='2002') compute statistics for columns state,locid +PREHOOK: type: QUERY +PREHOOK: Input: default@loc_orc_1d +PREHOOK: Input: default@loc_orc_1d@year=2002 +#### A masked pattern was here #### +POSTHOOK: query: analyze table loc_orc_1d partition(year='2002') compute statistics for columns state,locid +POSTHOOK: type: QUERY +POSTHOOK: Input: default@loc_orc_1d +POSTHOOK: Input: default@loc_orc_1d@year=2002 +#### A masked pattern was here #### +PREHOOK: query: describe formatted loc_orc_1d.state PARTITION(year='2001') +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@loc_orc_1d +POSTHOOK: query: describe formatted loc_orc_1d.state PARTITION(year='2001') +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@loc_orc_1d +# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment + +state string 0 3 0.75 2 from deserializer +PREHOOK: query: describe formatted loc_orc_1d.state PARTITION(year='2002') +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@loc_orc_1d +POSTHOOK: query: describe formatted loc_orc_1d.state PARTITION(year='2002') +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@loc_orc_1d +# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment + +state string 0 6 3.0 3 from deserializer +PREHOOK: query: -- basicStatState: COMPLETE colStatState: PARTIAL +explain extended select state from loc_orc_1d +PREHOOK: type: QUERY +POSTHOOK: query: -- basicStatState: COMPLETE colStatState: PARTIAL +explain extended select state from loc_orc_1d +POSTHOOK: type: QUERY +ABSTRACT SYNTAX TREE: + +TOK_QUERY + TOK_FROM + TOK_TABREF + TOK_TABNAME + loc_orc_1d + TOK_INSERT + TOK_DESTINATION + TOK_DIR + TOK_TMP_FILE + TOK_SELECT + TOK_SELEXPR + TOK_TABLE_OR_COL + state + + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: loc_orc_1d + Statistics: Num rows: 16 Data size: 1896 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Select Operator + expressions: state (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 16 Data size: 1472 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 16 Data size: 1472 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types string + escape.delim \ + hive.serialization.extend.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: year=2000 + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2000 + properties: + COLUMN_STATS_ACCURATE false + bucket_count -1 + columns state,locid,zip + columns.comments + columns.types string:int:int +#### A masked pattern was here #### + name default.loc_orc_1d + numFiles 1 + numRows -1 + partition_columns year + partition_columns.types string + rawDataSize -1 + serialization.ddl struct loc_orc_1d { string state, i32 locid, i32 zip} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 342 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid,zip + columns.comments + columns.types string:int:int +#### A masked pattern was here #### + name default.loc_orc_1d + partition_columns year + partition_columns.types string + serialization.ddl struct loc_orc_1d { string state, i32 locid, i32 zip} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_1d + name: default.loc_orc_1d +#### A masked pattern was here #### + Partition + base file name: year=2001 + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2001 + properties: + COLUMN_STATS_ACCURATE false + bucket_count -1 + columns state,locid,zip + columns.comments + columns.types string:int:int +#### A masked pattern was here #### + name default.loc_orc_1d + numFiles 1 + numRows -1 + partition_columns year + partition_columns.types string + rawDataSize -1 + serialization.ddl struct loc_orc_1d { string state, i32 locid, i32 zip} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 363 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid,zip + columns.comments + columns.types string:int:int +#### A masked pattern was here #### + name default.loc_orc_1d + partition_columns year + partition_columns.types string + serialization.ddl struct loc_orc_1d { string state, i32 locid, i32 zip} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_1d + name: default.loc_orc_1d +#### A masked pattern was here #### + Partition + base file name: year=2002 + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2002 + properties: + COLUMN_STATS_ACCURATE false + bucket_count -1 + columns state,locid,zip + columns.comments + columns.types string:int:int +#### A masked pattern was here #### + name default.loc_orc_1d + numFiles 1 + numRows -1 + partition_columns year + partition_columns.types string + rawDataSize -1 + serialization.ddl struct loc_orc_1d { string state, i32 locid, i32 zip} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 395 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid,zip + columns.comments + columns.types string:int:int +#### A masked pattern was here #### + name default.loc_orc_1d + partition_columns year + partition_columns.types string + serialization.ddl struct loc_orc_1d { string state, i32 locid, i32 zip} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_1d + name: default.loc_orc_1d +#### A masked pattern was here #### + Partition + base file name: year=2003 + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2003 + properties: + COLUMN_STATS_ACCURATE false + bucket_count -1 + columns state,locid,zip + columns.comments + columns.types string:int:int +#### A masked pattern was here #### + name default.loc_orc_1d + numFiles 1 + numRows -1 + partition_columns year + partition_columns.types string + rawDataSize -1 + serialization.ddl struct loc_orc_1d { string state, i32 locid, i32 zip} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 393 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid,zip + columns.comments + columns.types string:int:int +#### A masked pattern was here #### + name default.loc_orc_1d + partition_columns year + partition_columns.types string + serialization.ddl struct loc_orc_1d { string state, i32 locid, i32 zip} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_1d + name: default.loc_orc_1d +#### A masked pattern was here #### + Partition + base file name: year=__HIVE_DEFAULT_PARTITION__ + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year __HIVE_DEFAULT_PARTITION__ + properties: + COLUMN_STATS_ACCURATE false + bucket_count -1 + columns state,locid,zip + columns.comments + columns.types string:int:int +#### A masked pattern was here #### + name default.loc_orc_1d + numFiles 1 + numRows -1 + partition_columns year + partition_columns.types string + rawDataSize -1 + serialization.ddl struct loc_orc_1d { string state, i32 locid, i32 zip} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 403 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid,zip + columns.comments + columns.types string:int:int +#### A masked pattern was here #### + name default.loc_orc_1d + partition_columns year + partition_columns.types string + serialization.ddl struct loc_orc_1d { string state, i32 locid, i32 zip} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_1d + name: default.loc_orc_1d + Truncated Path -> Alias: + /loc_orc_1d/year=2000 [loc_orc_1d] + /loc_orc_1d/year=2001 [loc_orc_1d] + /loc_orc_1d/year=2002 [loc_orc_1d] + /loc_orc_1d/year=2003 [loc_orc_1d] + /loc_orc_1d/year=__HIVE_DEFAULT_PARTITION__ [loc_orc_1d] + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: -- column statistics for __HIVE_DEFAULT_PARTITION__ is not supported yet. Hence colStatState reports PARTIAL +-- basicStatState: COMPLETE colStatState: PARTIAL +explain extended select state,locid from loc_orc_1d +PREHOOK: type: QUERY +POSTHOOK: query: -- column statistics for __HIVE_DEFAULT_PARTITION__ is not supported yet. Hence colStatState reports PARTIAL +-- basicStatState: COMPLETE colStatState: PARTIAL +explain extended select state,locid from loc_orc_1d +POSTHOOK: type: QUERY +ABSTRACT SYNTAX TREE: + +TOK_QUERY + TOK_FROM + TOK_TABREF + TOK_TABNAME + loc_orc_1d + TOK_INSERT + TOK_DESTINATION + TOK_DIR + TOK_TMP_FILE + TOK_SELECT + TOK_SELEXPR + TOK_TABLE_OR_COL + state + TOK_SELEXPR + TOK_TABLE_OR_COL + locid + + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: loc_orc_1d + Statistics: Num rows: 15 Data size: 1896 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Select Operator + expressions: state (type: string), locid (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 15 Data size: 1440 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 15 Data size: 1440 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0,_col1 + columns.types string:int + escape.delim \ + hive.serialization.extend.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: year=2000 + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2000 + properties: + COLUMN_STATS_ACCURATE false + bucket_count -1 + columns state,locid,zip + columns.comments + columns.types string:int:int +#### A masked pattern was here #### + name default.loc_orc_1d + numFiles 1 + numRows -1 + partition_columns year + partition_columns.types string + rawDataSize -1 + serialization.ddl struct loc_orc_1d { string state, i32 locid, i32 zip} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 342 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid,zip + columns.comments + columns.types string:int:int +#### A masked pattern was here #### + name default.loc_orc_1d + partition_columns year + partition_columns.types string + serialization.ddl struct loc_orc_1d { string state, i32 locid, i32 zip} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_1d + name: default.loc_orc_1d +#### A masked pattern was here #### + Partition + base file name: year=2001 + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2001 + properties: + COLUMN_STATS_ACCURATE false + bucket_count -1 + columns state,locid,zip + columns.comments + columns.types string:int:int +#### A masked pattern was here #### + name default.loc_orc_1d + numFiles 1 + numRows -1 + partition_columns year + partition_columns.types string + rawDataSize -1 + serialization.ddl struct loc_orc_1d { string state, i32 locid, i32 zip} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 363 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid,zip + columns.comments + columns.types string:int:int +#### A masked pattern was here #### + name default.loc_orc_1d + partition_columns year + partition_columns.types string + serialization.ddl struct loc_orc_1d { string state, i32 locid, i32 zip} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_1d + name: default.loc_orc_1d +#### A masked pattern was here #### + Partition + base file name: year=2002 + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2002 + properties: + COLUMN_STATS_ACCURATE false + bucket_count -1 + columns state,locid,zip + columns.comments + columns.types string:int:int +#### A masked pattern was here #### + name default.loc_orc_1d + numFiles 1 + numRows -1 + partition_columns year + partition_columns.types string + rawDataSize -1 + serialization.ddl struct loc_orc_1d { string state, i32 locid, i32 zip} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 395 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid,zip + columns.comments + columns.types string:int:int +#### A masked pattern was here #### + name default.loc_orc_1d + partition_columns year + partition_columns.types string + serialization.ddl struct loc_orc_1d { string state, i32 locid, i32 zip} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_1d + name: default.loc_orc_1d +#### A masked pattern was here #### + Partition + base file name: year=2003 + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2003 + properties: + COLUMN_STATS_ACCURATE false + bucket_count -1 + columns state,locid,zip + columns.comments + columns.types string:int:int +#### A masked pattern was here #### + name default.loc_orc_1d + numFiles 1 + numRows -1 + partition_columns year + partition_columns.types string + rawDataSize -1 + serialization.ddl struct loc_orc_1d { string state, i32 locid, i32 zip} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 393 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid,zip + columns.comments + columns.types string:int:int +#### A masked pattern was here #### + name default.loc_orc_1d + partition_columns year + partition_columns.types string + serialization.ddl struct loc_orc_1d { string state, i32 locid, i32 zip} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_1d + name: default.loc_orc_1d +#### A masked pattern was here #### + Partition + base file name: year=__HIVE_DEFAULT_PARTITION__ + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year __HIVE_DEFAULT_PARTITION__ + properties: + COLUMN_STATS_ACCURATE false + bucket_count -1 + columns state,locid,zip + columns.comments + columns.types string:int:int +#### A masked pattern was here #### + name default.loc_orc_1d + numFiles 1 + numRows -1 + partition_columns year + partition_columns.types string + rawDataSize -1 + serialization.ddl struct loc_orc_1d { string state, i32 locid, i32 zip} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 403 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid,zip + columns.comments + columns.types string:int:int +#### A masked pattern was here #### + name default.loc_orc_1d + partition_columns year + partition_columns.types string + serialization.ddl struct loc_orc_1d { string state, i32 locid, i32 zip} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_1d + name: default.loc_orc_1d + Truncated Path -> Alias: + /loc_orc_1d/year=2000 [loc_orc_1d] + /loc_orc_1d/year=2001 [loc_orc_1d] + /loc_orc_1d/year=2002 [loc_orc_1d] + /loc_orc_1d/year=2003 [loc_orc_1d] + /loc_orc_1d/year=__HIVE_DEFAULT_PARTITION__ [loc_orc_1d] + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: create table if not exists loc_orc_2d ( + state string, + locid int +) partitioned by(zip int, year string) stored as orc +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +POSTHOOK: query: create table if not exists loc_orc_2d ( + state string, + locid int +) partitioned by(zip int, year string) stored as orc +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@loc_orc_2d +PREHOOK: query: insert overwrite table loc_orc_2d partition(zip, year) select * from ext_loc +PREHOOK: type: QUERY +PREHOOK: Input: default@ext_loc +PREHOOK: Output: default@loc_orc_2d +POSTHOOK: query: insert overwrite table loc_orc_2d partition(zip, year) select * from ext_loc +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ext_loc +POSTHOOK: Output: default@loc_orc_2d@zip=43201/year=2001 +POSTHOOK: Output: default@loc_orc_2d@zip=43201/year=2002 +POSTHOOK: Output: default@loc_orc_2d@zip=43201/year=2003 +POSTHOOK: Output: default@loc_orc_2d@zip=43201/year=__HIVE_DEFAULT_PARTITION__ +POSTHOOK: Output: default@loc_orc_2d@zip=94086/year=2000 +POSTHOOK: Output: default@loc_orc_2d@zip=94086/year=2001 +POSTHOOK: Output: default@loc_orc_2d@zip=94086/year=2002 +POSTHOOK: Output: default@loc_orc_2d@zip=94086/year=2003 +POSTHOOK: Output: default@loc_orc_2d@zip=94086/year=__HIVE_DEFAULT_PARTITION__ +POSTHOOK: Output: default@loc_orc_2d@zip=94087/year=2000 +POSTHOOK: Output: default@loc_orc_2d@zip=94087/year=2001 +POSTHOOK: Output: default@loc_orc_2d@zip=94087/year=2002 +POSTHOOK: Output: default@loc_orc_2d@zip=94087/year=2003 +POSTHOOK: Output: default@loc_orc_2d@zip=94087/year=__HIVE_DEFAULT_PARTITION__ +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=43201,year=2001).locid SIMPLE [(ext_loc)ext_loc.FieldSchema(name:locid, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=43201,year=2001).state SIMPLE [(ext_loc)ext_loc.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=43201,year=2002).locid SIMPLE [(ext_loc)ext_loc.FieldSchema(name:locid, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=43201,year=2002).state SIMPLE [(ext_loc)ext_loc.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=43201,year=2003).locid SIMPLE [(ext_loc)ext_loc.FieldSchema(name:locid, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=43201,year=2003).state SIMPLE [(ext_loc)ext_loc.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=43201,year=__HIVE_DEFAULT_PARTITION__).locid SIMPLE [(ext_loc)ext_loc.FieldSchema(name:locid, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=43201,year=__HIVE_DEFAULT_PARTITION__).state SIMPLE [(ext_loc)ext_loc.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=94086,year=2000).locid SIMPLE [(ext_loc)ext_loc.FieldSchema(name:locid, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=94086,year=2000).state SIMPLE [(ext_loc)ext_loc.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=94086,year=2001).locid SIMPLE [(ext_loc)ext_loc.FieldSchema(name:locid, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=94086,year=2001).state SIMPLE [(ext_loc)ext_loc.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=94086,year=2002).locid SIMPLE [(ext_loc)ext_loc.FieldSchema(name:locid, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=94086,year=2002).state SIMPLE [(ext_loc)ext_loc.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=94086,year=2003).locid SIMPLE [(ext_loc)ext_loc.FieldSchema(name:locid, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=94086,year=2003).state SIMPLE [(ext_loc)ext_loc.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=94086,year=__HIVE_DEFAULT_PARTITION__).locid SIMPLE [(ext_loc)ext_loc.FieldSchema(name:locid, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=94086,year=__HIVE_DEFAULT_PARTITION__).state SIMPLE [(ext_loc)ext_loc.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=94087,year=2000).locid SIMPLE [(ext_loc)ext_loc.FieldSchema(name:locid, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=94087,year=2000).state SIMPLE [(ext_loc)ext_loc.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=94087,year=2001).locid SIMPLE [(ext_loc)ext_loc.FieldSchema(name:locid, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=94087,year=2001).state SIMPLE [(ext_loc)ext_loc.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=94087,year=2002).locid SIMPLE [(ext_loc)ext_loc.FieldSchema(name:locid, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=94087,year=2002).state SIMPLE [(ext_loc)ext_loc.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=94087,year=2003).locid SIMPLE [(ext_loc)ext_loc.FieldSchema(name:locid, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=94087,year=2003).state SIMPLE [(ext_loc)ext_loc.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=94087,year=__HIVE_DEFAULT_PARTITION__).locid SIMPLE [(ext_loc)ext_loc.FieldSchema(name:locid, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=94087,year=__HIVE_DEFAULT_PARTITION__).state SIMPLE [(ext_loc)ext_loc.FieldSchema(name:state, type:string, comment:null), ] +PREHOOK: query: analyze table loc_orc_2d partition(zip=94086, year='2001') compute statistics for columns state,locid +PREHOOK: type: QUERY +PREHOOK: Input: default@loc_orc_2d +PREHOOK: Input: default@loc_orc_2d@zip=94086/year=2001 +#### A masked pattern was here #### +POSTHOOK: query: analyze table loc_orc_2d partition(zip=94086, year='2001') compute statistics for columns state,locid +POSTHOOK: type: QUERY +POSTHOOK: Input: default@loc_orc_2d +POSTHOOK: Input: default@loc_orc_2d@zip=94086/year=2001 +#### A masked pattern was here #### +PREHOOK: query: analyze table loc_orc_2d partition(zip=94087, year='2002') compute statistics for columns state,locid +PREHOOK: type: QUERY +PREHOOK: Input: default@loc_orc_2d +PREHOOK: Input: default@loc_orc_2d@zip=94087/year=2002 +#### A masked pattern was here #### +POSTHOOK: query: analyze table loc_orc_2d partition(zip=94087, year='2002') compute statistics for columns state,locid +POSTHOOK: type: QUERY +POSTHOOK: Input: default@loc_orc_2d +POSTHOOK: Input: default@loc_orc_2d@zip=94087/year=2002 +#### A masked pattern was here #### +PREHOOK: query: explain extended select state from loc_orc_2d +PREHOOK: type: QUERY +POSTHOOK: query: explain extended select state from loc_orc_2d +POSTHOOK: type: QUERY +ABSTRACT SYNTAX TREE: + +TOK_QUERY + TOK_FROM + TOK_TABREF + TOK_TABNAME + loc_orc_2d + TOK_INSERT + TOK_DESTINATION + TOK_DIR + TOK_TMP_FILE + TOK_SELECT + TOK_SELEXPR + TOK_TABLE_OR_COL + state + + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: loc_orc_2d + Statistics: Num rows: 28 Data size: 3773 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Select Operator + expressions: state (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 28 Data size: 2464 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 28 Data size: 2464 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types string + escape.delim \ + hive.serialization.extend.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: year=2001 + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2001 + zip 43201 + properties: + COLUMN_STATS_ACCURATE false + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + numFiles 1 + numRows -1 + partition_columns zip/year + partition_columns.types int:string + rawDataSize -1 + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 264 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + partition_columns zip/year + partition_columns.types int:string + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_2d + name: default.loc_orc_2d +#### A masked pattern was here #### + Partition + base file name: year=2002 + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2002 + zip 43201 + properties: + COLUMN_STATS_ACCURATE false + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + numFiles 1 + numRows -1 + partition_columns zip/year + partition_columns.types int:string + rawDataSize -1 + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 289 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + partition_columns zip/year + partition_columns.types int:string + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_2d + name: default.loc_orc_2d +#### A masked pattern was here #### + Partition + base file name: year=2003 + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2003 + zip 43201 + properties: + COLUMN_STATS_ACCURATE false + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + numFiles 1 + numRows -1 + partition_columns zip/year + partition_columns.types int:string + rawDataSize -1 + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 279 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + partition_columns zip/year + partition_columns.types int:string + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_2d + name: default.loc_orc_2d +#### A masked pattern was here #### + Partition + base file name: year=__HIVE_DEFAULT_PARTITION__ + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year __HIVE_DEFAULT_PARTITION__ + zip 43201 + properties: + COLUMN_STATS_ACCURATE false + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + numFiles 1 + numRows -1 + partition_columns zip/year + partition_columns.types int:string + rawDataSize -1 + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 276 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + partition_columns zip/year + partition_columns.types int:string + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_2d + name: default.loc_orc_2d +#### A masked pattern was here #### + Partition + base file name: year=2000 + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2000 + zip 94086 + properties: + COLUMN_STATS_ACCURATE false + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + numFiles 1 + numRows -1 + partition_columns zip/year + partition_columns.types int:string + rawDataSize -1 + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 260 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + partition_columns zip/year + partition_columns.types int:string + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_2d + name: default.loc_orc_2d +#### A masked pattern was here #### + Partition + base file name: year=2001 + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2001 + zip 94086 + properties: + COLUMN_STATS_ACCURATE false + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + numFiles 1 + numRows -1 + partition_columns zip/year + partition_columns.types int:string + rawDataSize -1 + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 257 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + partition_columns zip/year + partition_columns.types int:string + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_2d + name: default.loc_orc_2d +#### A masked pattern was here #### + Partition + base file name: year=2002 + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2002 + zip 94086 + properties: + COLUMN_STATS_ACCURATE false + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + numFiles 1 + numRows -1 + partition_columns zip/year + partition_columns.types int:string + rawDataSize -1 + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 269 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + partition_columns zip/year + partition_columns.types int:string + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_2d + name: default.loc_orc_2d +#### A masked pattern was here #### + Partition + base file name: year=2003 + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2003 + zip 94086 + properties: + COLUMN_STATS_ACCURATE false + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + numFiles 1 + numRows -1 + partition_columns zip/year + partition_columns.types int:string + rawDataSize -1 + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 278 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + partition_columns zip/year + partition_columns.types int:string + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_2d + name: default.loc_orc_2d +#### A masked pattern was here #### + Partition + base file name: year=__HIVE_DEFAULT_PARTITION__ + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year __HIVE_DEFAULT_PARTITION__ + zip 94086 + properties: + COLUMN_STATS_ACCURATE false + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + numFiles 1 + numRows -1 + partition_columns zip/year + partition_columns.types int:string + rawDataSize -1 + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 285 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + partition_columns zip/year + partition_columns.types int:string + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_2d + name: default.loc_orc_2d +#### A masked pattern was here #### + Partition + base file name: year=2000 + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2000 + zip 94087 + properties: + COLUMN_STATS_ACCURATE false + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + numFiles 1 + numRows -1 + partition_columns zip/year + partition_columns.types int:string + rawDataSize -1 + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 247 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + partition_columns zip/year + partition_columns.types int:string + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_2d + name: default.loc_orc_2d +#### A masked pattern was here #### + Partition + base file name: year=2001 + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2001 + zip 94087 + properties: + COLUMN_STATS_ACCURATE false + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + numFiles 1 + numRows -1 + partition_columns zip/year + partition_columns.types int:string + rawDataSize -1 + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 247 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + partition_columns zip/year + partition_columns.types int:string + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_2d + name: default.loc_orc_2d +#### A masked pattern was here #### + Partition + base file name: year=2002 + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2002 + zip 94087 + properties: + COLUMN_STATS_ACCURATE false + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + numFiles 1 + numRows -1 + partition_columns zip/year + partition_columns.types int:string + rawDataSize -1 + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 277 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + partition_columns zip/year + partition_columns.types int:string + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_2d + name: default.loc_orc_2d +#### A masked pattern was here #### + Partition + base file name: year=2003 + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2003 + zip 94087 + properties: + COLUMN_STATS_ACCURATE false + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + numFiles 1 + numRows -1 + partition_columns zip/year + partition_columns.types int:string + rawDataSize -1 + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 271 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + partition_columns zip/year + partition_columns.types int:string + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_2d + name: default.loc_orc_2d +#### A masked pattern was here #### + Partition + base file name: year=__HIVE_DEFAULT_PARTITION__ + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year __HIVE_DEFAULT_PARTITION__ + zip 94087 + properties: + COLUMN_STATS_ACCURATE false + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + numFiles 1 + numRows -1 + partition_columns zip/year + partition_columns.types int:string + rawDataSize -1 + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 274 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + partition_columns zip/year + partition_columns.types int:string + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_2d + name: default.loc_orc_2d + Truncated Path -> Alias: + /loc_orc_2d/zip=43201/year=2001 [loc_orc_2d] + /loc_orc_2d/zip=43201/year=2002 [loc_orc_2d] + /loc_orc_2d/zip=43201/year=2003 [loc_orc_2d] + /loc_orc_2d/zip=43201/year=__HIVE_DEFAULT_PARTITION__ [loc_orc_2d] + /loc_orc_2d/zip=94086/year=2000 [loc_orc_2d] + /loc_orc_2d/zip=94086/year=2001 [loc_orc_2d] + /loc_orc_2d/zip=94086/year=2002 [loc_orc_2d] + /loc_orc_2d/zip=94086/year=2003 [loc_orc_2d] + /loc_orc_2d/zip=94086/year=__HIVE_DEFAULT_PARTITION__ [loc_orc_2d] + /loc_orc_2d/zip=94087/year=2000 [loc_orc_2d] + /loc_orc_2d/zip=94087/year=2001 [loc_orc_2d] + /loc_orc_2d/zip=94087/year=2002 [loc_orc_2d] + /loc_orc_2d/zip=94087/year=2003 [loc_orc_2d] + /loc_orc_2d/zip=94087/year=__HIVE_DEFAULT_PARTITION__ [loc_orc_2d] + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain extended select state,locid from loc_orc_2d +PREHOOK: type: QUERY +POSTHOOK: query: explain extended select state,locid from loc_orc_2d +POSTHOOK: type: QUERY +ABSTRACT SYNTAX TREE: + +TOK_QUERY + TOK_FROM + TOK_TABREF + TOK_TABNAME + loc_orc_2d + TOK_INSERT + TOK_DESTINATION + TOK_DIR + TOK_TMP_FILE + TOK_SELECT + TOK_SELEXPR + TOK_TABLE_OR_COL + state + TOK_SELEXPR + TOK_TABLE_OR_COL + locid + + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: loc_orc_2d + Statistics: Num rows: 28 Data size: 3773 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Select Operator + expressions: state (type: string), locid (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 28 Data size: 2576 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 28 Data size: 2576 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0,_col1 + columns.types string:int + escape.delim \ + hive.serialization.extend.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: year=2001 + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2001 + zip 43201 + properties: + COLUMN_STATS_ACCURATE false + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + numFiles 1 + numRows -1 + partition_columns zip/year + partition_columns.types int:string + rawDataSize -1 + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 264 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + partition_columns zip/year + partition_columns.types int:string + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_2d + name: default.loc_orc_2d +#### A masked pattern was here #### + Partition + base file name: year=2002 + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2002 + zip 43201 + properties: + COLUMN_STATS_ACCURATE false + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + numFiles 1 + numRows -1 + partition_columns zip/year + partition_columns.types int:string + rawDataSize -1 + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 289 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + partition_columns zip/year + partition_columns.types int:string + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_2d + name: default.loc_orc_2d +#### A masked pattern was here #### + Partition + base file name: year=2003 + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2003 + zip 43201 + properties: + COLUMN_STATS_ACCURATE false + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + numFiles 1 + numRows -1 + partition_columns zip/year + partition_columns.types int:string + rawDataSize -1 + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 279 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + partition_columns zip/year + partition_columns.types int:string + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_2d + name: default.loc_orc_2d +#### A masked pattern was here #### + Partition + base file name: year=__HIVE_DEFAULT_PARTITION__ + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year __HIVE_DEFAULT_PARTITION__ + zip 43201 + properties: + COLUMN_STATS_ACCURATE false + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + numFiles 1 + numRows -1 + partition_columns zip/year + partition_columns.types int:string + rawDataSize -1 + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 276 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + partition_columns zip/year + partition_columns.types int:string + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_2d + name: default.loc_orc_2d +#### A masked pattern was here #### + Partition + base file name: year=2000 + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2000 + zip 94086 + properties: + COLUMN_STATS_ACCURATE false + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + numFiles 1 + numRows -1 + partition_columns zip/year + partition_columns.types int:string + rawDataSize -1 + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 260 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + partition_columns zip/year + partition_columns.types int:string + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_2d + name: default.loc_orc_2d +#### A masked pattern was here #### + Partition + base file name: year=2001 + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2001 + zip 94086 + properties: + COLUMN_STATS_ACCURATE false + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + numFiles 1 + numRows -1 + partition_columns zip/year + partition_columns.types int:string + rawDataSize -1 + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 257 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + partition_columns zip/year + partition_columns.types int:string + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_2d + name: default.loc_orc_2d +#### A masked pattern was here #### + Partition + base file name: year=2002 + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2002 + zip 94086 + properties: + COLUMN_STATS_ACCURATE false + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + numFiles 1 + numRows -1 + partition_columns zip/year + partition_columns.types int:string + rawDataSize -1 + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 269 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + partition_columns zip/year + partition_columns.types int:string + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_2d + name: default.loc_orc_2d +#### A masked pattern was here #### + Partition + base file name: year=2003 + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2003 + zip 94086 + properties: + COLUMN_STATS_ACCURATE false + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + numFiles 1 + numRows -1 + partition_columns zip/year + partition_columns.types int:string + rawDataSize -1 + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 278 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + partition_columns zip/year + partition_columns.types int:string + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_2d + name: default.loc_orc_2d +#### A masked pattern was here #### + Partition + base file name: year=__HIVE_DEFAULT_PARTITION__ + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year __HIVE_DEFAULT_PARTITION__ + zip 94086 + properties: + COLUMN_STATS_ACCURATE false + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + numFiles 1 + numRows -1 + partition_columns zip/year + partition_columns.types int:string + rawDataSize -1 + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 285 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + partition_columns zip/year + partition_columns.types int:string + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_2d + name: default.loc_orc_2d +#### A masked pattern was here #### + Partition + base file name: year=2000 + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2000 + zip 94087 + properties: + COLUMN_STATS_ACCURATE false + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + numFiles 1 + numRows -1 + partition_columns zip/year + partition_columns.types int:string + rawDataSize -1 + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 247 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + partition_columns zip/year + partition_columns.types int:string + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_2d + name: default.loc_orc_2d +#### A masked pattern was here #### + Partition + base file name: year=2001 + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2001 + zip 94087 + properties: + COLUMN_STATS_ACCURATE false + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + numFiles 1 + numRows -1 + partition_columns zip/year + partition_columns.types int:string + rawDataSize -1 + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 247 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + partition_columns zip/year + partition_columns.types int:string + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_2d + name: default.loc_orc_2d +#### A masked pattern was here #### + Partition + base file name: year=2002 + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2002 + zip 94087 + properties: + COLUMN_STATS_ACCURATE false + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + numFiles 1 + numRows -1 + partition_columns zip/year + partition_columns.types int:string + rawDataSize -1 + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 277 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + partition_columns zip/year + partition_columns.types int:string + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_2d + name: default.loc_orc_2d +#### A masked pattern was here #### + Partition + base file name: year=2003 + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2003 + zip 94087 + properties: + COLUMN_STATS_ACCURATE false + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + numFiles 1 + numRows -1 + partition_columns zip/year + partition_columns.types int:string + rawDataSize -1 + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 271 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + partition_columns zip/year + partition_columns.types int:string + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_2d + name: default.loc_orc_2d +#### A masked pattern was here #### + Partition + base file name: year=__HIVE_DEFAULT_PARTITION__ + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year __HIVE_DEFAULT_PARTITION__ + zip 94087 + properties: + COLUMN_STATS_ACCURATE false + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + numFiles 1 + numRows -1 + partition_columns zip/year + partition_columns.types int:string + rawDataSize -1 + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 274 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid + columns.comments + columns.types string:int +#### A masked pattern was here #### + name default.loc_orc_2d + partition_columns zip/year + partition_columns.types int:string + serialization.ddl struct loc_orc_2d { string state, i32 locid} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_2d + name: default.loc_orc_2d + Truncated Path -> Alias: + /loc_orc_2d/zip=43201/year=2001 [loc_orc_2d] + /loc_orc_2d/zip=43201/year=2002 [loc_orc_2d] + /loc_orc_2d/zip=43201/year=2003 [loc_orc_2d] + /loc_orc_2d/zip=43201/year=__HIVE_DEFAULT_PARTITION__ [loc_orc_2d] + /loc_orc_2d/zip=94086/year=2000 [loc_orc_2d] + /loc_orc_2d/zip=94086/year=2001 [loc_orc_2d] + /loc_orc_2d/zip=94086/year=2002 [loc_orc_2d] + /loc_orc_2d/zip=94086/year=2003 [loc_orc_2d] + /loc_orc_2d/zip=94086/year=__HIVE_DEFAULT_PARTITION__ [loc_orc_2d] + /loc_orc_2d/zip=94087/year=2000 [loc_orc_2d] + /loc_orc_2d/zip=94087/year=2001 [loc_orc_2d] + /loc_orc_2d/zip=94087/year=2002 [loc_orc_2d] + /loc_orc_2d/zip=94087/year=2003 [loc_orc_2d] + /loc_orc_2d/zip=94087/year=__HIVE_DEFAULT_PARTITION__ [loc_orc_2d] + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink +