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

Core: Use CharSequenceMap for writing unordered deletes #9365

Merged
merged 1 commit into from
Dec 24, 2023
+9 −19
Merged

Core: Use CharSequenceMap for writing unordered deletes #9365

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
28 changes: 9 additions & 19 deletions core/src/main/java/org/apache/iceberg/deletes/SortingPositionOnlyDeleteWriter.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,13 +20,11 @@

import java.io.IOException;
import java.util.List;
import java.util.Map;
import org.apache.iceberg.io.DeleteWriteResult;
import org.apache.iceberg.io.FileWriter;
import org.apache.iceberg.relocated.com.google.common.collect.Lists;
import org.apache.iceberg.relocated.com.google.common.collect.Maps;
import org.apache.iceberg.types.Comparators;
import org.apache.iceberg.util.CharSequenceWrapper;
import org.apache.iceberg.util.CharSequenceMap;
import org.roaringbitmap.longlong.PeekableLongIterator;
import org.roaringbitmap.longlong.Roaring64Bitmap;

Expand All @@ -44,28 +42,20 @@ public class SortingPositionOnlyDeleteWriter<T>
implements FileWriter<PositionDelete<T>, DeleteWriteResult> {

private final FileWriter<PositionDelete<T>, DeleteWriteResult> writer;
private final Map<CharSequenceWrapper, Roaring64Bitmap> positionsByPath;
private final CharSequenceWrapper pathWrapper;
private final CharSequenceMap<Roaring64Bitmap> positionsByPath;
private DeleteWriteResult result = null;

public SortingPositionOnlyDeleteWriter(FileWriter<PositionDelete<T>, DeleteWriteResult> writer) {
this.writer = writer;
this.positionsByPath = Maps.newHashMap();
this.pathWrapper = CharSequenceWrapper.wrap(null);
this.positionsByPath = CharSequenceMap.create();
}

@Override
public void write(PositionDelete<T> positionDelete) {
CharSequence path = positionDelete.path();
long position = positionDelete.pos();
Roaring64Bitmap positions = positionsByPath.get(pathWrapper.set(path));
if (positions != null) {
positions.add(position);
} else {
positions = new Roaring64Bitmap();
positions.add(position);
positionsByPath.put(CharSequenceWrapper.wrap(path), positions);
}
Roaring64Bitmap positions = positionsByPath.computeIfAbsent(path, Roaring64Bitmap::new);
positions.add(position);
}

@Override
Expand All @@ -88,12 +78,12 @@ public void close() throws IOException {
private DeleteWriteResult writeDeletes() throws IOException {
try {
PositionDelete<T> positionDelete = PositionDelete.create();
for (CharSequenceWrapper path : sortedPaths()) {
for (CharSequence path : sortedPaths()) {
// the iterator provides values in ascending sorted order
PeekableLongIterator positions = positionsByPath.get(path).getLongIterator();
while (positions.hasNext()) {
long position = positions.next();
writer.write(positionDelete.set(path.get(), position, null /* no row */));
writer.write(positionDelete.set(path, position, null /* no row */));
}
}
} finally {
Expand All @@ -103,8 +93,8 @@ private DeleteWriteResult writeDeletes() throws IOException {
return writer.result();
}

private List<CharSequenceWrapper> sortedPaths() {
List<CharSequenceWrapper> paths = Lists.newArrayList(positionsByPath.keySet());
private List<CharSequence> sortedPaths() {
List<CharSequence> paths = Lists.newArrayList(positionsByPath.keySet());
paths.sort(Comparators.charSequences());
return paths;
}
Expand Down