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

GH-3133: Fix SizeStatistics to handle omitted histogram #3134

Merged
merged 1 commit into from
Jan 21, 2025
+28 −4
Merged

GH-3133: Fix SizeStatistics to handle omitted histogram #3134

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
6 changes: 4 additions & 2 deletions parquet-column/src/main/java/org/apache/parquet/column/statistics/SizeStatistics.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -148,8 +148,10 @@ public SizeStatistics(
List<Long> definitionLevelHistogram) {
this.type = type;
this.unencodedByteArrayDataBytes = unencodedByteArrayDataBytes;
this.repetitionLevelHistogram = repetitionLevelHistogram;
this.definitionLevelHistogram = definitionLevelHistogram;
this.repetitionLevelHistogram =
repetitionLevelHistogram == null ? Collections.emptyList() : repetitionLevelHistogram;
this.definitionLevelHistogram =
definitionLevelHistogram == null ? Collections.emptyList() : definitionLevelHistogram;
}

/**
Expand Down
16 changes: 16 additions & 0 deletions parquet-column/src/test/java/org/apache/parquet/column/statistics/TestSizeStatistics.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -125,4 +125,20 @@ public void testCopyStatistics() {
Assert.assertEquals(Arrays.asList(1L, 1L, 1L), copy.getRepetitionLevelHistogram());
Assert.assertEquals(Arrays.asList(1L, 1L, 1L), copy.getDefinitionLevelHistogram());
}

@Test
public void testOmittedHistogram() {
PrimitiveType type = Types.optional(PrimitiveType.PrimitiveTypeName.BINARY)
.as(LogicalTypeAnnotation.stringType())
.named("a");
SizeStatistics statistics = new SizeStatistics(type, 1024L, null, null);
Assert.assertEquals(Optional.of(1024L), statistics.getUnencodedByteArrayDataBytes());
Assert.assertEquals(Collections.emptyList(), statistics.getRepetitionLevelHistogram());
Assert.assertEquals(Collections.emptyList(), statistics.getDefinitionLevelHistogram());

SizeStatistics copy = statistics.copy();
Assert.assertEquals(Optional.of(1024L), copy.getUnencodedByteArrayDataBytes());
Assert.assertEquals(Collections.emptyList(), copy.getRepetitionLevelHistogram());
Assert.assertEquals(Collections.emptyList(), copy.getDefinitionLevelHistogram());
}
}
10 changes: 8 additions & 2 deletions ...et-hadoop/src/main/java/org/apache/parquet/format/converter/ParquetMetadataConverter.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2382,8 +2382,14 @@ public static SizeStatistics toParquetSizeStatistics(org.apache.parquet.column.s
formatStats.setUnencoded_byte_array_data_bytes(
stats.getUnencodedByteArrayDataBytes().get());
}
formatStats.setRepetition_level_histogram(stats.getRepetitionLevelHistogram());
formatStats.setDefinition_level_histogram(stats.getDefinitionLevelHistogram());
List<Long> repLevelHistogram = stats.getRepetitionLevelHistogram();
if (repLevelHistogram != null && !repLevelHistogram.isEmpty()) {
formatStats.setRepetition_level_histogram(repLevelHistogram);
}
List<Long> defLevelHistogram = stats.getDefinitionLevelHistogram();
if (defLevelHistogram != null && !defLevelHistogram.isEmpty()) {
formatStats.setDefinition_level_histogram(defLevelHistogram);
}
return formatStats;
}
}
Loading