Skip to content

Parquet: Guard ordered predicates on variant/nested types in metrics row group filter #17431

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
vishnuprakaz wants to merge 1 commit into
base: main
Choose a base branch
from
+84 −0
Open

Parquet: Guard ordered predicates on variant/nested types in metrics row group filter #17431

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
56 changes: 56 additions & 0 deletions data/src/test/java/org/apache/iceberg/data/TestMetricsRowGroupFilter.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1259,6 +1259,62 @@ public void testVariantFieldIn() throws IOException {
.isTrue();
}

@TestTemplate
public void testVariantFieldLt() throws IOException {
assumeThat(format).isEqualTo(FileFormat.PARQUET);

VariantMetadata md = Variants.metadata("k");
Variant v0 = createVariantWithKey(md, "v0");
List<GenericRecord> records = createVariantRecords(v0);

boolean shouldRead = shouldReadVariant(lessThan("variant_field", v0), records);
assertThat(shouldRead)
.as("Should read: variant lt filters must be evaluated post scan")
.isTrue();
}

@TestTemplate
public void testVariantFieldLtEq() throws IOException {
assumeThat(format).isEqualTo(FileFormat.PARQUET);

VariantMetadata md = Variants.metadata("k");
Variant v0 = createVariantWithKey(md, "v0");
List<GenericRecord> records = createVariantRecords(v0);

boolean shouldRead = shouldReadVariant(lessThanOrEqual("variant_field", v0), records);
assertThat(shouldRead)
.as("Should read: variant ltEq filters must be evaluated post scan")
.isTrue();
}

@TestTemplate
public void testVariantFieldGt() throws IOException {
assumeThat(format).isEqualTo(FileFormat.PARQUET);

VariantMetadata md = Variants.metadata("k");
Variant v0 = createVariantWithKey(md, "v0");
List<GenericRecord> records = createVariantRecords(v0);

boolean shouldRead = shouldReadVariant(greaterThan("variant_field", v0), records);
assertThat(shouldRead)
.as("Should read: variant gt filters must be evaluated post scan")
.isTrue();
}

@TestTemplate
public void testVariantFieldGtEq() throws IOException {
assumeThat(format).isEqualTo(FileFormat.PARQUET);

VariantMetadata md = Variants.metadata("k");
Variant v0 = createVariantWithKey(md, "v0");
List<GenericRecord> records = createVariantRecords(v0);

boolean shouldRead = shouldReadVariant(greaterThanOrEqual("variant_field", v0), records);
assertThat(shouldRead)
.as("Should read: variant gtEq filters must be evaluated post scan")
.isTrue();
}

@TestTemplate
public void testUUID() {
assumeThat(format).as("Only valid for Parquet").isEqualTo(FileFormat.PARQUET);
Expand Down
28 changes: 28 additions & 0 deletions parquet/src/main/java/org/apache/iceberg/parquet/ParquetMetricsRowGroupFilter.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -237,6 +237,13 @@ public <T> Boolean notNaN(BoundReference<T> ref) {
public <T> Boolean lt(BoundReference<T> ref, Literal<T> lit) {
int id = ref.fieldId();

// Leave all nested column type and variant type filters to be
// evaluated post scan.
Type type = schema.findType(id);
if (type instanceof Type.NestedType || type.isVariantType()) {
return ROWS_MIGHT_MATCH;
}

Long valueCount = valueCounts.get(id);
if (valueCount == null) {
// the column is not present and is all nulls
Expand Down Expand Up @@ -267,6 +274,13 @@ public <T> Boolean lt(BoundReference<T> ref, Literal<T> lit) {
public <T> Boolean ltEq(BoundReference<T> ref, Literal<T> lit) {
int id = ref.fieldId();

// Leave all nested column type and variant type filters to be
// evaluated post scan.
Type type = schema.findType(id);
if (type instanceof Type.NestedType || type.isVariantType()) {
return ROWS_MIGHT_MATCH;
}

Long valueCount = valueCounts.get(id);
if (valueCount == null) {
// the column is not present and is all nulls
Expand Down Expand Up @@ -297,6 +311,13 @@ public <T> Boolean ltEq(BoundReference<T> ref, Literal<T> lit) {
public <T> Boolean gt(BoundReference<T> ref, Literal<T> lit) {
int id = ref.fieldId();

// Leave all nested column type and variant type filters to be
// evaluated post scan.
Type type = schema.findType(id);
if (type instanceof Type.NestedType || type.isVariantType()) {
return ROWS_MIGHT_MATCH;
}

Long valueCount = valueCounts.get(id);
if (valueCount == null) {
// the column is not present and is all nulls
Expand Down Expand Up @@ -327,6 +348,13 @@ public <T> Boolean gt(BoundReference<T> ref, Literal<T> lit) {
public <T> Boolean gtEq(BoundReference<T> ref, Literal<T> lit) {
int id = ref.fieldId();

// Leave all nested column type and variant type filters to be
// evaluated post scan.
Type type = schema.findType(id);
if (type instanceof Type.NestedType || type.isVariantType()) {
return ROWS_MIGHT_MATCH;
}

Long valueCount = valueCounts.get(id);
if (valueCount == null) {
// the column is not present and is all nulls
Expand Down
Loading