kazuyukitanimura commented on a change in pull request #34611:
URL: https://github.com/apache/spark/pull/34611#discussion_r754552760
##########
File path:
sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedPlainValuesReader.java
##########
@@ -53,19 +53,47 @@ public void skip() {
throw new UnsupportedOperationException();
}
+ private void updateCurrentByte() {
Review comment:
Thanks, I would keep `updateCurrentByte` for now. Because public methods
are using `read***` prefix, I chose `updateCurrentByte` to distinguish this
private method.
##########
File path:
sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/WritableColumnVector.java
##########
@@ -470,6 +493,18 @@ public final int appendBooleans(int count, boolean v) {
return result;
}
+ /**
+ * Append bits from [src[offset], src[offset + count])
+ * src must contain bit-packed 8 Booleans in the byte.
Review comment:
Updated
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/execution/vectorized/ColumnarBatchSuite.scala
##########
@@ -130,6 +133,89 @@ class ColumnarBatchSuite extends SparkFunSuite {
}
}
+ testVector("Boolean APIs", 1024, BooleanType) {
+ column =>
+ val reference = mutable.ArrayBuffer.empty[Boolean]
+
+ var values = Array(true, false, true, false, false)
+ var bits = values.foldRight(0)((b, i) => i << 1 | (if (b) 1 else
0)).toByte
+ column.appendBooleans(2, bits, 0)
+ reference ++= values.slice(0, 2)
+
+ column.appendBooleans(3, bits, 2)
+ reference ++= values.slice(2, 5)
+
+ column.appendBooleans(6, true)
+ reference ++= Array.fill(6)(true)
+
+ column.appendBoolean(false)
+ reference += false
+
+ var idx = column.elementsAppended
+
+ values = Array(true, true, false, true, false, true, false, true)
+ bits = values.foldRight(0)((b, i) => i << 1 | (if (b) 1 else 0)).toByte
+ column.putBooleans(idx, 2, bits, 0)
+ reference ++= values.slice(0, 2)
+ idx += 2
+
+ column.putBooleans(idx, 3, bits, 2)
+ reference ++= values.slice(2, 5)
+ idx += 3
+
+ column.putBooleans(idx, bits)
+ reference ++= values
+ idx += 8
+
+ column.putBoolean(idx, false)
+ reference += false
+ idx += 1
+
+ column.putBooleans(idx, 3, true)
+ reference ++= Array.fill(3)(true)
+ idx += 3
+
+ implicit def intToByte(i: Int): Byte = i.toByte
+ val buf = ByteBuffer.wrap(Array(0x33, 0x5A, 0xA5, 0xCC, 0x0F, 0xF0,
0xEE))
+ val reader = new VectorizedPlainValuesReader()
+ reader.initFromPage(0, ByteBufferInputStream.wrap(buf))
+ column.putBoolean(idx, reader.readBoolean) // bit index 0
+ reference += true
+ idx += 1
+
+ reader.skipBooleans(1)
+
+ column.putBoolean(idx, reader.readBoolean) // bit index 2
+ reference += false
+ idx += 1
+
+ reader.skipBooleans(5)
+
+ column.putBoolean(idx, reader.readBoolean) // bit index 8
+ reference += false
+ idx += 1
+
+ reader.skipBooleans(8)
Review comment:
Updated
##########
File path:
sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedPlainValuesReader.java
##########
@@ -53,19 +53,47 @@ public void skip() {
throw new UnsupportedOperationException();
}
+ private void updateCurrentByte() {
+ try {
+ currentByte = (byte) in.read();
+ } catch (IOException e) {
+ throw new ParquetDecodingException("Failed to read a byte", e);
+ }
+ }
+
@Override
public final void readBooleans(int total, WritableColumnVector c, int rowId)
{
- // TODO: properly vectorize this
- for (int i = 0; i < total; i++) {
- c.putBoolean(rowId + i, readBoolean());
+ int i = 0;
+ if (bitOffset > 0) {
+ i = Math.min(8 - bitOffset, total);
Review comment:
I don't think we need to update the `total` here. Only the `I` gets
updated.
Any particular examples that you are worried?
--
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]
