[
https://issues.apache.org/jira/browse/IMPALA-6503?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16704047#comment-16704047
]
Tim Armstrong commented on IMPALA-6503:
---------------------------------------
Yeah I believe that's a valid assumption. I'm not 100% sure but I couldn't find
a case where that wouldn't be true. . You might already know but the top-level
tuple descriptor can refer to a nested collection, but I believe each level of
nesting within a slot can only add one level to the path.
{noformat}
select o_orderkey from tpch_nested_parquet.customer.c_orders limit 5
I1129 15:54:23.728154 8024 TupleDescriptor.java:236] Tuple:
TupleDescriptor{id=0, name=CollectionTableRef c_orders,
tbl=tpch_nested_parquet.customer, path=tpch_nested_parquet.customer.c_orders,
byte_size=9, is_materialized=true, slots=[SlotDescriptor{id=0,
path=c_orders.o_orderkey, type=BIGINT, materialized=true, byteSize=8,
byteOffset=0, nullable=true, nullIndicatorByte=8, nullIndicatorBit=0,
slotIdx=0, stats=ColumnStats{avgSerializedSize_=8.0, maxSize_=8,
numDistinct_=-1, numNulls_=-1}}]}
{noformat}
{noformat}
$ git diff
diff --git a/fe/src/main/java/org/apache/impala/analysis/TupleDescriptor.java
b/fe/src/main/java/org/apache/impala/analysis/TupleDescriptor.java
index 98621ef..0f94f69 100644
--- a/fe/src/main/java/org/apache/impala/analysis/TupleDescriptor.java
+++ b/fe/src/main/java/org/apache/impala/analysis/TupleDescriptor.java
@@ -31,6 +31,8 @@ import org.apache.impala.catalog.FeKuduTable;
import org.apache.impala.catalog.FeTable;
import org.apache.impala.catalog.StructType;
import org.apache.impala.thrift.TTupleDescriptor;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
import com.google.common.base.Joiner;
import com.google.common.base.Objects;
@@ -73,6 +75,7 @@ import com.google.common.collect.Lists;
* Offsets: 0 12 16 18 19
*/
public class TupleDescriptor {
+ private final static Logger LOG =
LoggerFactory.getLogger(TupleDescriptor.class);
// Padding size in bytes for Kudu string slots.
private static final int KUDU_STRING_PADDING = 4;
@@ -191,6 +194,8 @@ public class TupleDescriptor {
}
public String debugString() {
+ String pathStr = (path_ == null) ? "null" : path_.toString();
+
String tblStr = (getTable() == null ? "null" : getTable().getFullName());
List<String> slotStrings = Lists.newArrayList();
for (SlotDescriptor slot : slots_) {
@@ -200,6 +205,7 @@ public class TupleDescriptor {
.add("id", id_.asInt())
.add("name", debugName_)
.add("tbl", tblStr)
+ .add("path", pathStr)
.add("byte_size", byteSize_)
.add("is_materialized", isMaterialized_)
.add("slots", "[" + Joiner.on(", ").join(slotStrings) + "]")
@@ -227,6 +233,7 @@ public class TupleDescriptor {
}
public TTupleDescriptor toThrift(Integer tableId) {
+ LOG.info("Tuple: " + debugString());
TTupleDescriptor ttupleDesc =
new TTupleDescriptor(id_.asInt(), byteSize_, numNullBytes_);
if (tableId == null) return ttupleDesc;
{noformat
{code}
$ git diff
diff --git a/fe/src/main/java/org/apache/impala/analysis/TupleDescriptor.java
b/fe/src/main/java/org/apache/impala/analysis/TupleDescriptor.java
index 98621ef..0f94f69 100644
--- a/fe/src/main/java/org/apache/impala/analysis/TupleDescriptor.java
+++ b/fe/src/main/java/org/apache/impala/analysis/TupleDescriptor.java
@@ -31,6 +31,8 @@ import org.apache.impala.catalog.FeKuduTable;
import org.apache.impala.catalog.FeTable;
import org.apache.impala.catalog.StructType;
import org.apache.impala.thrift.TTupleDescriptor;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
import com.google.common.base.Joiner;
import com.google.common.base.Objects;
@@ -73,6 +75,7 @@ import com.google.common.collect.Lists;
* Offsets: 0 12 16 18 19
*/
public class TupleDescriptor {
+ private final static Logger LOG =
LoggerFactory.getLogger(TupleDescriptor.class);
// Padding size in bytes for Kudu string slots.
private static final int KUDU_STRING_PADDING = 4;
@@ -191,6 +194,8 @@ public class TupleDescriptor {
}
public String debugString() {
+ String pathStr = (path_ == null) ? "null" : path_.toString();
+
String tblStr = (getTable() == null ? "null" : getTable().getFullName());
List<String> slotStrings = Lists.newArrayList();
for (SlotDescriptor slot : slots_) {
@@ -200,6 +205,7 @@ public class TupleDescriptor {
.add("id", id_.asInt())
.add("name", debugName_)
.add("tbl", tblStr)
+ .add("path", pathStr)
.add("byte_size", byteSize_)
.add("is_materialized", isMaterialized_)
.add("slots", "[" + Joiner.on(", ").join(slotStrings) + "]")
@@ -227,6 +233,7 @@ public class TupleDescriptor {
}
public TTupleDescriptor toThrift(Integer tableId) {
+ LOG.info("Tuple: " + debugString());
TTupleDescriptor ttupleDesc =
new TTupleDescriptor(id_.asInt(), byteSize_, numNullBytes_);
if (tableId == null) return ttupleDesc;
{code}
> Support reading complex types from ORC format files
> ---------------------------------------------------
>
> Key: IMPALA-6503
> URL: https://issues.apache.org/jira/browse/IMPALA-6503
> Project: IMPALA
> Issue Type: New Feature
> Components: Backend, Frontend
> Reporter: Quanlong Huang
> Assignee: Quanlong Huang
> Priority: Major
>
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
