@Override
public void copyAsField(String name, MapWriter writer) {
if (writer.ok()) {
SingleMapWriter impl = (SingleMapWriter) writer.map(name);
impl.inform(impl.container.copyFromSafe(idx(), impl.idx(), vector));
}
}
@Override
public void copyAsValue(MapWriter writer) {
if (writer.ok()) {
SingleMapWriter impl = (SingleMapWriter) writer;
impl.inform(impl.container.copyFromSafe(idx(), impl.idx(), vector));
}
}
// This function assumes that the fields in the schema parameter are in the same order as the
// fields in the columns parameter. The
// columns parameter may have fields that are not present in the schema, though.
public DrillParquetGroupConverter(
OutputMutator mutator,
MapWriter mapWriter,
GroupType schema,
Collection<SchemaPath> columns,
OptionManager options) {
this.mapWriter = mapWriter;
this.mutator = mutator;
converters = Lists.newArrayList();
this.options = options;
Iterator<SchemaPath> colIterator = columns.iterator();
for (Type type : schema.getFields()) {
Repetition rep = type.getRepetition();
boolean isPrimitive = type.isPrimitive();
// Match the name of the field in the schema definition to the name of the field in the query.
String name = null;
SchemaPath col = null;
PathSegment colPath = null;
PathSegment colNextChild = null;
while (colIterator.hasNext()) {
col = colIterator.next();
colPath = col.getRootSegment();
colNextChild = colPath.getChild();
if (colPath != null
&& colPath.isNamed()
&& (!colPath.getNameSegment().getPath().equals("*"))) {
name = colPath.getNameSegment().getPath();
// We may have a field that does not exist in the schema
if (!name.equalsIgnoreCase(type.getName())) {
continue;
}
}
break;
}
if (name == null) {
name = type.getName();
}
if (!isPrimitive) {
Collection<SchemaPath> c = new ArrayList<SchemaPath>();
while (colNextChild != null) {
if (colNextChild.isNamed()) {
break;
}
colNextChild = colNextChild.getChild();
}
if (colNextChild != null) {
SchemaPath s = new SchemaPath(colNextChild.getNameSegment());
c.add(s);
}
if (rep != Repetition.REPEATED) {
DrillParquetGroupConverter converter =
new DrillParquetGroupConverter(
mutator, mapWriter.map(name), type.asGroupType(), c, options);
converters.add(converter);
} else {
DrillParquetGroupConverter converter =
new DrillParquetGroupConverter(
mutator, mapWriter.list(name).map(), type.asGroupType(), c, options);
converters.add(converter);
}
} else {
PrimitiveConverter converter = getConverterForType(name, type.asPrimitiveType());
converters.add(converter);
}
}
}
@Override
public void end() {
mapWriter.end();
}
@Override
public void start() {
mapWriter.start();
}
private PrimitiveConverter getConverterForType(String name, PrimitiveType type) {
switch (type.getPrimitiveTypeName()) {
case INT32:
{
if (type.getOriginalType() == null) {
IntWriter writer =
type.getRepetition() == Repetition.REPEATED
? mapWriter.list(name).integer()
: mapWriter.integer(name);
return new DrillIntConverter(writer);
}
switch (type.getOriginalType()) {
case DECIMAL:
{
ParquetReaderUtility.checkDecimalTypeEnabled(options);
Decimal9Writer writer =
type.getRepetition() == Repetition.REPEATED
? mapWriter.list(name).decimal9()
: mapWriter.decimal9(name);
return new DrillDecimal9Converter(
writer,
type.getDecimalMetadata().getPrecision(),
type.getDecimalMetadata().getScale());
}
case DATE:
{
DateWriter writer =
type.getRepetition() == Repetition.REPEATED
? mapWriter.list(name).date()
: mapWriter.date(name);
return new DrillDateConverter(writer);
}
case TIME_MILLIS:
{
TimeWriter writer =
type.getRepetition() == Repetition.REPEATED
? mapWriter.list(name).time()
: mapWriter.time(name);
return new DrillTimeConverter(writer);
}
default:
{
throw new UnsupportedOperationException(
"Unsupported type: " + type.getOriginalType());
}
}
}
case INT64:
{
if (type.getOriginalType() == null) {
BigIntWriter writer =
type.getRepetition() == Repetition.REPEATED
? mapWriter.list(name).bigInt()
: mapWriter.bigInt(name);
return new DrillBigIntConverter(writer);
}
switch (type.getOriginalType()) {
case DECIMAL:
{
ParquetReaderUtility.checkDecimalTypeEnabled(options);
Decimal18Writer writer =
type.getRepetition() == Repetition.REPEATED
? mapWriter.list(name).decimal18()
: mapWriter.decimal18(name);
return new DrillDecimal18Converter(
writer,
type.getDecimalMetadata().getPrecision(),
type.getDecimalMetadata().getScale());
}
case TIMESTAMP_MILLIS:
{
TimeStampWriter writer =
type.getRepetition() == Repetition.REPEATED
? mapWriter.list(name).timeStamp()
: mapWriter.timeStamp(name);
return new DrillTimeStampConverter(writer);
}
default:
{
throw new UnsupportedOperationException(
"Unsupported type " + type.getOriginalType());
}
}
}
case INT96:
{
if (type.getOriginalType() == null) {
VarBinaryWriter writer =
type.getRepetition() == Repetition.REPEATED
? mapWriter.list(name).varBinary()
: mapWriter.varBinary(name);
return new DrillFixedBinaryToVarbinaryConverter(
writer,
ParquetRecordReader.getTypeLengthInBits(type.getPrimitiveTypeName()) / 8,
mutator.getManagedBuffer());
}
}
case FLOAT:
{
Float4Writer writer =
type.getRepetition() == Repetition.REPEATED
? mapWriter.list(name).float4()
: mapWriter.float4(name);
return new DrillFloat4Converter(writer);
}
case DOUBLE:
{
Float8Writer writer =
type.getRepetition() == Repetition.REPEATED
? mapWriter.list(name).float8()
: mapWriter.float8(name);
return new DrillFloat8Converter(writer);
}
case BOOLEAN:
{
BitWriter writer =
type.getRepetition() == Repetition.REPEATED
? mapWriter.list(name).bit()
: mapWriter.bit(name);
return new DrillBoolConverter(writer);
}
case BINARY:
{
if (type.getOriginalType() == null) {
VarBinaryWriter writer =
type.getRepetition() == Repetition.REPEATED
? mapWriter.list(name).varBinary()
: mapWriter.varBinary(name);
return new DrillVarBinaryConverter(writer, mutator.getManagedBuffer());
}
switch (type.getOriginalType()) {
case UTF8:
{
VarCharWriter writer =
type.getRepetition() == Repetition.REPEATED
? mapWriter.list(name).varChar()
: mapWriter.varChar(name);
return new DrillVarCharConverter(writer, mutator.getManagedBuffer());
}
// TODO not sure if BINARY/DECIMAL is actually supported
case DECIMAL:
{
ParquetReaderUtility.checkDecimalTypeEnabled(options);
DecimalMetadata metadata = type.getDecimalMetadata();
if (metadata.getPrecision() <= 28) {
Decimal28SparseWriter writer =
type.getRepetition() == Repetition.REPEATED
? mapWriter.list(name).decimal28Sparse()
: mapWriter.decimal28Sparse(
name, metadata.getScale(), metadata.getPrecision());
return new DrillBinaryToDecimal28Converter(
writer,
metadata.getPrecision(),
metadata.getScale(),
mutator.getManagedBuffer());
} else {
Decimal38SparseWriter writer =
type.getRepetition() == Repetition.REPEATED
? mapWriter.list(name).decimal38Sparse()
: mapWriter.decimal38Sparse(
name, metadata.getScale(), metadata.getPrecision());
return new DrillBinaryToDecimal38Converter(
writer,
metadata.getPrecision(),
metadata.getScale(),
mutator.getManagedBuffer());
}
}
default:
{
throw new UnsupportedOperationException(
"Unsupported type " + type.getOriginalType());
}
}
}
case FIXED_LEN_BYTE_ARRAY:
if (type.getOriginalType() == OriginalType.DECIMAL) {
ParquetReaderUtility.checkDecimalTypeEnabled(options);
DecimalMetadata metadata = type.getDecimalMetadata();
if (metadata.getPrecision() <= 28) {
Decimal28SparseWriter writer =
type.getRepetition() == Repetition.REPEATED
? mapWriter.list(name).decimal28Sparse()
: mapWriter.decimal28Sparse(name, metadata.getScale(), metadata.getPrecision());
return new DrillBinaryToDecimal28Converter(
writer, metadata.getPrecision(), metadata.getScale(), mutator.getManagedBuffer());
} else {
Decimal38SparseWriter writer =
type.getRepetition() == Repetition.REPEATED
? mapWriter.list(name).decimal38Sparse()
: mapWriter.decimal38Sparse(name, metadata.getScale(), metadata.getPrecision());
return new DrillBinaryToDecimal38Converter(
writer, metadata.getPrecision(), metadata.getScale(), mutator.getManagedBuffer());
}
} else if (type.getOriginalType() == OriginalType.INTERVAL) {
IntervalWriter writer =
type.getRepetition() == Repetition.REPEATED
? mapWriter.list(name).interval()
: mapWriter.interval(name);
return new DrillFixedLengthByteArrayToInterval(writer);
} else {
VarBinaryWriter writer =
type.getRepetition() == Repetition.REPEATED
? mapWriter.list(name).varBinary()
: mapWriter.varBinary(name);
return new DrillFixedBinaryToVarbinaryConverter(
writer, type.getTypeLength(), mutator.getManagedBuffer());
}
default:
throw new UnsupportedOperationException("Unsupported type: " + type.getPrimitiveTypeName());
}
}