Skip to content

[spark] SparkFilterConverter: support AlwaysTrue/False, fix silent NaN drop #8060

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
heye1005 wants to merge 1 commit into
base: master
Choose a base branch
from
Open

[spark] SparkFilterConverter: support AlwaysTrue/False, fix silent NaN drop #8060

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
25 changes: 22 additions & 3 deletions ...spark/paimon-spark-common/src/main/java/org/apache/paimon/spark/SparkFilterConverter.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,6 +23,8 @@
import org.apache.paimon.types.DataType;
import org.apache.paimon.types.RowType;

import org.apache.spark.sql.sources.AlwaysFalse;
import org.apache.spark.sql.sources.AlwaysTrue;
import org.apache.spark.sql.sources.And;
import org.apache.spark.sql.sources.EqualNullSafe;
import org.apache.spark.sql.sources.EqualTo;
Expand Down Expand Up @@ -54,6 +56,8 @@ public class SparkFilterConverter {

public static final List<String> SUPPORT_FILTERS =
Arrays.asList(
"AlwaysTrue",
"AlwaysFalse",
"EqualTo",
"EqualNullSafe",
"GreaterThan",
Expand Down Expand Up @@ -97,10 +101,16 @@ public Predicate convert(Filter filter, boolean ignoreFailure) {
}

public Predicate convert(Filter filter) {
if (filter instanceof EqualTo) {
if (filter instanceof AlwaysTrue) {
return PredicateBuilder.alwaysTrue();
} else if (filter instanceof AlwaysFalse) {
return PredicateBuilder.alwaysFalse();
} else if (filter instanceof EqualTo) {
EqualTo eq = (EqualTo) filter;
// TODO deal with isNaN
int index = fieldIndex(eq.attribute());
if (isNaN(eq.value())) {
return builder.isNaN(index);
}
Object literal = convertLiteral(index, eq.value());
return builder.equal(index, literal);
} else if (filter instanceof EqualNullSafe) {
Expand Down Expand Up @@ -173,11 +183,20 @@ public Predicate convert(Filter filter) {
return builder.contains(index, literal);
}

// TODO: AlwaysTrue, AlwaysFalse
throw new UnsupportedOperationException(
filter + " is unsupported. Support Filters: " + SUPPORT_FILTERS);
}

private static boolean isNaN(Object value) {
if (value instanceof Float) {
return Float.isNaN((Float) value);
}
if (value instanceof Double) {
return Double.isNaN((Double) value);
}
return false;
}

public Object convertLiteral(String field, Object value) {
return convertLiteral(fieldIndex(field), value);
}
Expand Down
34 changes: 34 additions & 0 deletions ...spark/paimon-spark-ut/src/test/java/org/apache/paimon/spark/SparkFilterConverterTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,11 +26,15 @@
import org.apache.paimon.types.CharType;
import org.apache.paimon.types.DataField;
import org.apache.paimon.types.DateType;
import org.apache.paimon.types.DoubleType;
import org.apache.paimon.types.FloatType;
import org.apache.paimon.types.IntType;
import org.apache.paimon.types.RowType;
import org.apache.paimon.types.TimestampType;
import org.apache.paimon.types.VarCharType;

import org.apache.spark.sql.sources.AlwaysFalse;
import org.apache.spark.sql.sources.AlwaysTrue;
import org.apache.spark.sql.sources.EqualNullSafe;
import org.apache.spark.sql.sources.EqualTo;
import org.apache.spark.sql.sources.GreaterThan;
Expand Down Expand Up @@ -229,6 +233,36 @@ public void testDate() {
assertThat(localDateExpression).isEqualTo(rawExpression);
}

@Test
public void testAlwaysTrueFalse() {
RowType rowType =
new RowType(Collections.singletonList(new DataField(0, "id", new IntType())));
SparkFilterConverter converter = new SparkFilterConverter(rowType);

assertThat(converter.convert(new AlwaysTrue())).isEqualTo(PredicateBuilder.alwaysTrue());
assertThat(converter.convert(new AlwaysFalse())).isEqualTo(PredicateBuilder.alwaysFalse());
}

@Test
public void testEqualToNaN() {
RowType rowType =
new RowType(
Arrays.asList(
new DataField(0, "f", new FloatType()),
new DataField(1, "d", new DoubleType())));
SparkFilterConverter converter = new SparkFilterConverter(rowType);
PredicateBuilder builder = new PredicateBuilder(rowType);

EqualTo eqNaNFloat = EqualTo.apply("f", Float.NaN);
assertThat(converter.convert(eqNaNFloat)).isEqualTo(builder.isNaN(0));

EqualTo eqNaNDouble = EqualTo.apply("d", Double.NaN);
assertThat(converter.convert(eqNaNDouble)).isEqualTo(builder.isNaN(1));

EqualTo eqFloat = EqualTo.apply("f", 1.0f);
assertThat(converter.convert(eqFloat)).isEqualTo(builder.equal(0, 1.0f));
}

@Test
public void testIgnoreFailure() {
List<DataField> dataFields = new ArrayList<>();
Expand Down
Loading