cloud-fan commented on code in PR #54040:
URL: https://github.com/apache/spark/pull/54040#discussion_r2804886266
##########
sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedDeltaByteArrayReader.java:
##########
@@ -100,6 +102,48 @@ public void readBinary(int total, WritableColumnVector c,
int rowId) {
readValues(total, c, rowId);
}
+ @Override
+ public void readGeometry(int total, WritableColumnVector c, int rowId) {
+ assert(c.dataType() instanceof GeometryType);
+ int srid = ((GeometryType) c.dataType()).srid();
+ readGeoData(total, c, rowId, srid, WKBToGeometryConverter.INSTANCE);
+ }
+
+ @Override
+ public void readGeography(int total, WritableColumnVector c, int rowId) {
+ assert(c.dataType() instanceof GeographyType);
+ int srid = ((GeographyType) c.dataType()).srid();
+ readGeoData(total, c, rowId, srid, WKBToGeographyConverter.INSTANCE);
+ }
+
+ private void readGeoData(int total, WritableColumnVector c, int rowId, int
srid,
+ WKBConverterStrategy converter) {
+ for (int i = 0; i < total; i++) {
+ int prefixLength = prefixLengthVector.getInt(currentRow);
+ ByteBuffer suffix = suffixReader.getBytes(currentRow);
+ int suffixLength = suffix.limit() - suffix.position();
+ int length = prefixLength + suffixLength;
+
+ byte[] wkb = new byte[length];
+ if (prefixLength > 0) {
+ previous.get(wkb, 0, prefixLength);
+ }
+ suffix.get(wkb, prefixLength, suffixLength);
+
+ // Converts WKB into a physical representation of geometry/geography.
Review Comment:
what's the Spark internal physical binary format for these two types?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
