PARQUET-1328: Add Bloom filter reader and writer #521
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -21,6 +21,7 @@ | |
| import static org.apache.parquet.bytes.BytesInput.concat; | ||
|
|
||
| import java.io.IOException; | ||
| import java.util.HashMap; | ||
|
|
||
| import org.apache.parquet.column.ColumnDescriptor; | ||
| import org.apache.parquet.column.ColumnWriter; | ||
|
|
@@ -29,6 +30,8 @@ | |
| import org.apache.parquet.column.page.PageWriter; | ||
| import org.apache.parquet.column.statistics.Statistics; | ||
| import org.apache.parquet.column.values.ValuesWriter; | ||
| import org.apache.parquet.column.values.bloomfilter.BloomFilter; | ||
| import org.apache.parquet.column.values.bloomfilter.BloomFilterWriter; | ||
| import org.apache.parquet.io.ParquetEncodingException; | ||
| import org.apache.parquet.io.api.Binary; | ||
| import org.slf4j.Logger; | ||
|
|
@@ -55,6 +58,23 @@ final class ColumnWriterV1 implements ColumnWriter { | |
| private int valueCountForNextSizeCheck; | ||
|
|
||
| private Statistics statistics; | ||
| private BloomFilterWriter bloomFilterWriter; | ||
| private BloomFilter bloomFilter; | ||
|
|
||
| public ColumnWriterV1(ColumnDescriptor path, PageWriter pageWriter, | ||
| BloomFilterWriter bloomFilterWriter, ParquetProperties props) { | ||
|
||
| this(path, pageWriter, props); | ||
|
|
||
| // Current not support nested column. | ||
| if (path.getPath().length == 1) { | ||
|
||
| this.bloomFilterWriter = bloomFilterWriter; | ||
| HashMap<String, Long> bloomFilterInfo = props.getBloomFilterInfo(); | ||
| String column = path.getPath()[0]; | ||
| if (bloomFilterInfo.keySet().contains(column)) { | ||
| this.bloomFilter = new BloomFilter(bloomFilterInfo.get(column).intValue()); | ||
|
||
| } | ||
| } | ||
| } | ||
|
|
||
| public ColumnWriterV1(ColumnDescriptor path, PageWriter pageWriter, | ||
| ParquetProperties props) { | ||
|
|
@@ -177,6 +197,9 @@ public void write(double value, int repetitionLevel, int definitionLevel) { | |
| definitionLevelColumn.writeInteger(definitionLevel); | ||
|
||
| dataColumn.writeDouble(value); | ||
| updateStatistics(value); | ||
| if (bloomFilter != null) { | ||
| bloomFilter.insert(bloomFilter.hash(value)); | ||
| } | ||
| accountForValueWritten(); | ||
| } | ||
|
|
||
|
|
@@ -187,6 +210,9 @@ public void write(float value, int repetitionLevel, int definitionLevel) { | |
| definitionLevelColumn.writeInteger(definitionLevel); | ||
| dataColumn.writeFloat(value); | ||
| updateStatistics(value); | ||
| if (bloomFilter != null) { | ||
| bloomFilter.insert(bloomFilter.hash(value)); | ||
| } | ||
| accountForValueWritten(); | ||
| } | ||
|
|
||
|
|
@@ -197,6 +223,9 @@ public void write(Binary value, int repetitionLevel, int definitionLevel) { | |
| definitionLevelColumn.writeInteger(definitionLevel); | ||
| dataColumn.writeBytes(value); | ||
| updateStatistics(value); | ||
| if (bloomFilter != null) { | ||
| bloomFilter.insert(bloomFilter.hash(value)); | ||
| } | ||
| accountForValueWritten(); | ||
| } | ||
|
|
||
|
|
@@ -217,6 +246,9 @@ public void write(int value, int repetitionLevel, int definitionLevel) { | |
| definitionLevelColumn.writeInteger(definitionLevel); | ||
| dataColumn.writeInteger(value); | ||
| updateStatistics(value); | ||
| if (bloomFilter != null) { | ||
| bloomFilter.insert(bloomFilter.hash(value)); | ||
| } | ||
| accountForValueWritten(); | ||
| } | ||
|
|
||
|
|
@@ -227,6 +259,9 @@ public void write(long value, int repetitionLevel, int definitionLevel) { | |
| definitionLevelColumn.writeInteger(definitionLevel); | ||
| dataColumn.writeLong(value); | ||
| updateStatistics(value); | ||
| if (bloomFilter != null) { | ||
| bloomFilter.insert(bloomFilter.hash(value)); | ||
| } | ||
| accountForValueWritten(); | ||
| } | ||
|
|
||
|
|
@@ -244,6 +279,10 @@ public void flush() { | |
| } | ||
| dataColumn.resetDictionary(); | ||
| } | ||
|
|
||
| if (bloomFilterWriter != null && bloomFilter != null) { | ||
|
||
| bloomFilterWriter.writeBloomFilter(bloomFilter); | ||
| } | ||
| } | ||
|
|
||
| @Override | ||
|
|
@@ -257,17 +296,21 @@ public void close() { | |
|
|
||
| @Override | ||
| public long getBufferedSizeInMemory() { | ||
| long bloomBufferSize = bloomFilter == null ? 0 : bloomFilter.getBufferedSize(); | ||
| return repetitionLevelColumn.getBufferedSize() | ||
| + definitionLevelColumn.getBufferedSize() | ||
| + dataColumn.getBufferedSize() | ||
| + pageWriter.getMemSize() | ||
| + bloomBufferSize; | ||
| } | ||
|
|
||
| public long allocatedSize() { | ||
| long bloomAllocatedSize = bloomFilter == null ? 0 : bloomFilter.getBufferedSize(); | ||
| return repetitionLevelColumn.getAllocatedSize() | ||
| + definitionLevelColumn.getAllocatedSize() | ||
| + dataColumn.getAllocatedSize() | ||
| + pageWriter.allocatedSize() | ||
| + bloomAllocatedSize; | ||
| } | ||
|
|
||
| public String memUsageString(String indent) { | ||
|
|
||
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Please keep changes like this in a different patch. Every patch should have a single purpose.