Skip to content

use default fpp for writing in Hive connector if not provided in table metadata #16589

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
Praveen2112 merged 1 commit into from
Feb 2, 2024
Merged

use default fpp for writing in Hive connector if not provided in table metadata #16589

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
8 changes: 4 additions & 4 deletions plugin/trino-hive/src/main/java/io/trino/plugin/hive/util/HiveUtil.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -749,11 +749,11 @@ public static List<HiveType> getColumnTypes(Map<String, String> schema)
public static OrcWriterOptions getOrcWriterOptions(Map<String, String> schema, OrcWriterOptions orcWriterOptions)
{
if (schema.containsKey(ORC_BLOOM_FILTER_COLUMNS_KEY)) {
if (!schema.containsKey(ORC_BLOOM_FILTER_FPP_KEY)) {
throw new TrinoException(HIVE_INVALID_METADATA, "FPP for bloom filter is missing");
}
try {
double fpp = parseDouble(schema.get(ORC_BLOOM_FILTER_FPP_KEY));
// use default fpp DEFAULT_BLOOM_FILTER_FPP if fpp key does not exist in table metadata
double fpp = schema.containsKey(ORC_BLOOM_FILTER_FPP_KEY)
? parseDouble(schema.get(ORC_BLOOM_FILTER_FPP_KEY))
: orcWriterOptions.getBloomFilterFpp();
return orcWriterOptions
.withBloomFilterColumns(ImmutableSet.copyOf(COLUMN_NAMES_SPLITTER.splitToList(schema.get(ORC_BLOOM_FILTER_COLUMNS_KEY))))
.withBloomFilterFpp(fpp);
Expand Down
10 changes: 10 additions & 0 deletions plugin/trino-hive/src/test/java/io/trino/plugin/hive/orc/TestOrcWriterOptions.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -116,4 +116,14 @@ private static Map<String, String> createTablePropertiesWithFpp(String fpp)
.put(ORC_BLOOM_FILTER_FPP_KEY, fpp)
.buildOrThrow();
}

@Test
public void testOrcWriterOptionsWithMissingFPPValue()
{
Map<String, String> tableProperties = ImmutableMap.<String, String>builder()
.put(ORC_BLOOM_FILTER_COLUMNS_KEY, "column_with_bloom_filter")
.buildOrThrow();
OrcWriterOptions orcWriterOptions = getOrcWriterOptions(tableProperties, new OrcWriterOptions());
assertThat(orcWriterOptions.getBloomFilterFpp()).isEqualTo(0.05);
}
}
7 changes: 3 additions & 4 deletions plugin/trino-iceberg/src/main/java/io/trino/plugin/iceberg/IcebergFileWriterFactory.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -266,11 +266,10 @@ private IcebergFileWriter createOrcWriter(
public static OrcWriterOptions withBloomFilterOptions(OrcWriterOptions orcWriterOptions, Map<String, String> storageProperties)
{
if (storageProperties.containsKey(ORC_BLOOM_FILTER_COLUMNS_KEY)) {
if (!storageProperties.containsKey(ORC_BLOOM_FILTER_FPP_KEY)) {
throw new TrinoException(ICEBERG_INVALID_METADATA, "FPP for Bloom filter is missing");
}
try {
double fpp = parseDouble(storageProperties.get(ORC_BLOOM_FILTER_FPP_KEY));
double fpp = storageProperties.containsKey(ORC_BLOOM_FILTER_FPP_KEY)
? parseDouble(storageProperties.get(ORC_BLOOM_FILTER_FPP_KEY))
: orcWriterOptions.getBloomFilterFpp();
return OrcWriterOptions.builderFrom(orcWriterOptions)
.setBloomFilterColumns(ImmutableSet.copyOf(COLUMN_NAMES_SPLITTER.splitToList(storageProperties.get(ORC_BLOOM_FILTER_COLUMNS_KEY))))
.setBloomFilterFpp(fpp)
Expand Down