cloud-fan commented on a change in pull request #33006:
URL: https://github.com/apache/spark/pull/33006#discussion_r656777628
##########
File path:
sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedColumnReader.java
##########
@@ -216,53 +195,49 @@ void readBatch(int total, WritableColumnVector column)
throws IOException {
boolean needTransform = castLongToInt || isUnsignedInt32 ||
isUnsignedInt64;
column.setDictionary(new ParquetDictionary(dictionary,
needTransform));
} else {
- updater.decodeDictionaryIds(num, rowId, column, dictionaryIds,
dictionary);
+ updater.decodeDictionaryIds(readState.offset - startOffset,
startOffset, column,
+ dictionaryIds, dictionary);
}
} else {
- if (column.hasDictionary() && rowId != 0) {
+ if (column.hasDictionary() && readState.offset != 0) {
// This batch already has dictionary encoded values but this new
page is not. The batch
// does not support a mix of dictionary and not so we will decode
the dictionary.
- updater.decodeDictionaryIds(rowId, 0, column, dictionaryIds,
dictionary);
+ updater.decodeDictionaryIds(readState.offset, 0, column,
dictionaryIds, dictionary);
}
column.setDictionary(null);
VectorizedValuesReader valuesReader = (VectorizedValuesReader)
dataColumn;
- defColumn.readBatch(num, rowId, column, maxDefLevel, valuesReader,
updater);
+ defColumn.readBatch(readState, column, valuesReader, updater);
}
-
- valuesRead += num;
- rowId += num;
- total -= num;
}
}
- private void readPage() {
+ private int readPage() {
DataPage page = pageReader.readPage();
- // TODO: Why is this a visitor?
- page.accept(new DataPage.Visitor<Void>() {
+ return page.accept(new DataPage.Visitor<Integer>() {
@Override
- public Void visit(DataPageV1 dataPageV1) {
+ public Integer visit(DataPageV1 dataPageV1) {
Review comment:
ah I see, let's leave it then.
--
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.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
