Skip to content

AP-24057-Remove-unused-Arrow-dictionary-writing-from-Arrow-Writer #75

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

Open
tpietzsch wants to merge 1 commit into
base: master
Choose a base branch
from
Open

AP-24057-Remove-unused-Arrow-dictionary-writing-from-Arrow-Writer #75

Show file tree
Hide file tree
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
12 changes: 0 additions & 12 deletions org.knime.python3.arrow/src/main/java/org/knime/python3/arrow/PythonArrowDataSource.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48,8 +48,6 @@
*/
package org.knime.python3.arrow;

import java.util.List;

import org.knime.python3.PythonTableDataSource;

/**
Expand Down Expand Up @@ -86,16 +84,6 @@ default String getIdentifier() {
*/
long getRecordBatchOffset(int index);

/**
* Get the offsets of the dictionary batches relating to the record batch at the given index. This method can lock
* if the dictionary batches are not yet written to the file. When it returns it guarantees that the dictionary
* batches can be read at the returned offsets from the file.
*
* @param index the index of the dictionary batches
* @return the offsets of all dictionary batches for the given index
*/
List<Long> getDictionaryBatchOffsets(int index);

/**
* @return the total number of batches
*/
Expand Down
14 changes: 0 additions & 14 deletions org.knime.python3.arrow/src/main/java/org/knime/python3/arrow/PythonArrowDataUtils.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -52,10 +52,8 @@
import java.nio.file.Files;
import java.nio.file.Path;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.List;
import java.util.function.Supplier;
import java.util.stream.Collectors;

import org.knime.core.columnar.arrow.ArrowBatchReadStore;
import org.knime.core.columnar.arrow.ArrowBatchStore;
Expand Down Expand Up @@ -484,12 +482,6 @@ private static OffsetProvider getOffsetProvider(final DefaultPythonArrowDataSink
public long getRecordBatchOffset(final int index) {
return dataSink.getRecordBatchOffsets().get(index);
}

@Override
public long[] getDictionaryBatchOffsets(final int index) {
// TODO support dictionary batches
return new long[0];
}
};
}

Expand Down Expand Up @@ -549,12 +541,6 @@ public long getRecordBatchOffset(final int index) {
return m_offsetProvider.getRecordBatchOffset(index);
}

@Override
public List<Long> getDictionaryBatchOffsets(final int index) {
return Arrays.stream(m_offsetProvider.getDictionaryBatchOffsets(index)).boxed()
.collect(Collectors.toList());
}

@Override
public String[] getColumnNames() {
return m_columnNames;
Expand Down
1 change: 0 additions & 1 deletion org.knime.python3.arrow/src/main/python/knime/_arrow/_backend.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -194,7 +194,6 @@ def num_record_batches(self):
return self._java_data_source.numBatches()

def get_batch(self, index: int) -> pa.RecordBatch:
# TODO(dictionary) handle dictionaries
offset = self._java_data_source.getRecordBatchOffset(index)
self._source_file.seek(offset)
# TODO do we need to map columns somehow (in Java we have the factory versions)
Expand Down
Loading