Skip to content

GH-3188: Set the global configured column stats enable flag to default #3189

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

Merged
wgtmac merged 2 commits into from
Apr 12, 2025
Merged

GH-3188: Set the global configured column stats enable flag to default #3189

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
14092fd
Minor: Set the global configured column stats enable flag to default …
Apr 11, 2025
4369866
Address format complain
Apr 11, 2025
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
1 change: 1 addition & 0 deletions parquet-column/src/main/java/org/apache/parquet/column/ParquetProperties.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -708,6 +708,7 @@ public Builder withStatisticsEnabled(String columnPath, boolean enabled) {
}

public Builder withStatisticsEnabled(boolean enabled) {
this.statistics.withDefaultValue(enabled);
this.statisticsEnabled = enabled;
return this;
}
Expand Down
7 changes: 6 additions & 1 deletion parquet-hadoop/src/test/java/org/apache/parquet/hadoop/TestParquetWriter.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -543,7 +543,7 @@ private void testParquetFileNumberOfBlocks(
}

@Test
public void testSizeStatisticsControl() throws Exception {
public void testSizeStatisticsAndStatisticsControl() throws Exception {
MessageType schema = Types.buildMessage()
.required(BINARY)
.named("string_field")
Expand All @@ -568,6 +568,7 @@ public void testSizeStatisticsControl() throws Exception {
try (ParquetWriter<Group> writer = ExampleParquetWriter.builder(path)
.withType(schema)
.withSizeStatisticsEnabled(false)
.withStatisticsEnabled(false) // Disable column statistics globally
.build()) {
writer.write(group);
}
Expand All @@ -576,6 +577,7 @@ public void testSizeStatisticsControl() throws Exception {
// Verify size statistics are disabled globally
for (BlockMetaData block : reader.getFooter().getBlocks()) {
for (ColumnChunkMetaData column : block.getColumns()) {
assertTrue(column.getStatistics().isEmpty()); // Make sure there is no column statistics
assertNull(column.getSizeStatistics());
}
}
Expand All @@ -589,6 +591,7 @@ public void testSizeStatisticsControl() throws Exception {
.withType(schema)
.withSizeStatisticsEnabled(true) // enable globally
.withSizeStatisticsEnabled("boolean_field", false) // disable for specific column
.withStatisticsEnabled("boolean_field", false) // disable column statistics
.build()) {
writer.write(group);
}
Expand All @@ -599,8 +602,10 @@ public void testSizeStatisticsControl() throws Exception {
for (ColumnChunkMetaData column : block.getColumns()) {
if (column.getPath().toDotString().equals("boolean_field")) {
assertNull(column.getSizeStatistics());
assertTrue(column.getStatistics().isEmpty());
} else {
assertTrue(column.getSizeStatistics().isValid());
assertFalse(column.getStatistics().isEmpty());
}
}
}
Expand Down