Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

ORC-236: Support UNION type in Java Convert tool #1025

Merged
merged 4 commits into from
Feb 16, 2022
Merged

ORC-236: Support UNION type in Java Convert tool #1025

Changes from 1 commit
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
635102e
ORC-236: Support UNION type in Java Convert tool
rizaon Jan 24, 2022
572a7f4
Add union-tag and union-value options.
rizaon Feb 3, 2022
e73fc3f
Fix checkstyle errors
rizaon Feb 3, 2022
d171029
Add third constructor for JsonReader.java
rizaon Feb 13, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
29 changes: 29 additions & 0 deletions java/tools/src/java/org/apache/orc/tools/convert/JsonReader.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,6 +34,7 @@
import org.apache.hadoop.hive.ql.exec.vector.MapColumnVector;
import org.apache.hadoop.hive.ql.exec.vector.StructColumnVector;
import org.apache.hadoop.hive.ql.exec.vector.TimestampColumnVector;
import org.apache.hadoop.hive.ql.exec.vector.UnionColumnVector;
import org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch;
import org.apache.orc.RecordReader;
import org.apache.orc.TypeDescription;
Expand Down Expand Up @@ -293,6 +294,32 @@ public void convert(JsonElement value, ColumnVector vect, int row) {
}
}

class UnionColumnConverter implements JsonConverter {
private JsonConverter[] childConverter;

UnionColumnConverter(TypeDescription schema) {
int size = schema.getChildren().size();
childConverter = new JsonConverter[size];
for (int i = 0; i < size; i++) {
childConverter[i] = createConverter(schema.getChildren().get(i));
}
}

@Override
public void convert(JsonElement value, ColumnVector vect, int row) {
if (value == null || value.isJsonNull()) {
vect.noNulls = false;
vect.isNull[row] = true;
} else {
UnionColumnVector vector = (UnionColumnVector) vect;
JsonObject obj = value.getAsJsonObject();
int tag = obj.get("tag").getAsInt();
vector.tags[row] = tag;
childConverter[tag].convert(obj.get("value"), vector.fields[tag], row);
}
}
}

JsonConverter createConverter(TypeDescription schema) {
switch (schema.getCategory()) {
case BYTE:
Expand Down Expand Up @@ -324,6 +351,8 @@ JsonConverter createConverter(TypeDescription schema) {
return new ListColumnConverter(schema);
case MAP:
return new MapColumnConverter(schema);
case UNION:
return new UnionColumnConverter(schema);
default:
throw new IllegalArgumentException("Unhandled type " + schema);
}
Expand Down