Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
75 changes: 75 additions & 0 deletions api/src/main/java/org/apache/iceberg/expressions/BoundExtract.java
Original file line number Diff line number Diff line change
@@ -0,0 +1,75 @@
/*
* Licensed to the Apache Software Foundation (ASF) under one
* or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information
* regarding copyright ownership. The ASF licenses this file
* to you under the Apache License, Version 2.0 (the
* "License"); you may not use this file except in compliance
* with the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing,
* software distributed under the License is distributed on an
* "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
* KIND, either express or implied. See the License for the
* specific language governing permissions and limitations
* under the License.
*/
package org.apache.iceberg.expressions;

import org.apache.iceberg.StructLike;
import org.apache.iceberg.relocated.com.google.common.base.Joiner;
import org.apache.iceberg.types.Type;

public class BoundExtract<T> implements BoundTerm<T> {
private final BoundReference<?> ref;
private final String path;
private final String fullFieldName;
private final Type type;

BoundExtract(BoundReference<?> ref, String path, Type type) {
this.ref = ref;
this.path = path;
this.fullFieldName = Joiner.on(".").join(PathUtil.parse(path));
this.type = type;
}

@Override
public BoundReference<?> ref() {
return ref;
}

public String path() {
return path;
}

String fullFieldName() {
return fullFieldName;
}

@Override
public Type type() {
return type;
}

@Override
public boolean isEquivalentTo(BoundTerm<?> other) {
if (other instanceof BoundExtract) {
BoundExtract<?> that = (BoundExtract<?>) other;
return ref.isEquivalentTo(that.ref) && path.equals(that.path) && type.equals(that.type);
}

return false;
}

@Override
public T eval(StructLike struct) {
throw new UnsupportedOperationException("Cannot evaluate " + this);
}

@Override
public String toString() {
return "extract(" + ref + ", path=" + path + ", type=" + type + ")";
}
}
Original file line number Diff line number Diff line change
Expand Up @@ -55,6 +55,11 @@ public Type type() {
return field.type();
}

@Override
public boolean producesNull() {
return field.isOptional();
}

@Override
public String name() {
return name;
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -31,6 +31,11 @@ public interface BoundTerm<T> extends Bound<T>, Term {
/** Returns the type produced by this expression. */
Type type();

/** Returns whether values produced by this expression may be null. */
default boolean producesNull() {
return true;
}

/** Returns a {@link Comparator} for values produced by this term. */
default Comparator<T> comparator() {
return Comparators.forType(type().asPrimitiveType());
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -54,6 +54,13 @@ public Transform<S, T> transform() {
return transform;
}

@Override
public boolean producesNull() {
// transforms must produce null for null input values
// transforms may produce null for non-null inputs when not order-preserving
return ref.producesNull() || !transform.preservesOrder();
}

@Override
public Type type() {
return transform.getResultType(ref.type());
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -102,6 +102,10 @@ public static <T> UnboundTerm<T> truncate(String name, int width) {
return new UnboundTransform<>(ref(name), Transforms.truncate(width));
}

public static <T> UnboundTerm<T> extract(String name, String path, String type) {
return new UnboundExtract<>(ref(name), path, type);
}

public static <T> UnboundPredicate<T> isNull(String name) {
return new UnboundPredicate<>(Expression.Operation.IS_NULL, ref(name));
}
Expand Down
64 changes: 64 additions & 0 deletions api/src/main/java/org/apache/iceberg/expressions/PathUtil.java
Original file line number Diff line number Diff line change
@@ -0,0 +1,64 @@
/*
* Licensed to the Apache Software Foundation (ASF) under one
* or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information
* regarding copyright ownership. The ASF licenses this file
* to you under the Apache License, Version 2.0 (the
* "License"); you may not use this file except in compliance
* with the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing,
* software distributed under the License is distributed on an
* "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
* KIND, either express or implied. See the License for the
* specific language governing permissions and limitations
* under the License.
*/
package org.apache.iceberg.expressions;

import java.util.List;
import java.util.function.Predicate;
import java.util.regex.Pattern;
import org.apache.iceberg.relocated.com.google.common.base.Preconditions;
import org.apache.iceberg.relocated.com.google.common.base.Splitter;

class PathUtil {
private PathUtil() {}

private static final String RFC9535_NAME_FIRST =
"[A-Za-z_\\x{0080}-\\x{D7FF}\\x{E000}-\\x{10FFFF}]";
private static final String RFC9535_NAME_CHARS =
"[0-9A-Za-z_\\x{0080}-\\x{D7FF}\\x{E000}-\\x{10FFFF}]*";
private static final Predicate<String> RFC9535_MEMBER_NAME_SHORTHAND =
Pattern.compile(RFC9535_NAME_FIRST + RFC9535_NAME_CHARS).asMatchPredicate();

private static final Splitter DOT = Splitter.on(".");
private static final String ROOT = "$";

static List<String> parse(String path) {
Preconditions.checkArgument(path != null, "Invalid path: null");
Preconditions.checkArgument(
!path.contains("[") && !path.contains("]"), "Unsupported path, contains bracket: %s", path);
Preconditions.checkArgument(
!path.contains("*"), "Unsupported path, contains wildcard: %s", path);
Preconditions.checkArgument(
!path.contains(".."), "Unsupported path, contains recursive descent: %s", path);

List<String> parts = DOT.splitToList(path);
Preconditions.checkArgument(
ROOT.equals(parts.get(0)), "Invalid path, does not start with %s: %s", ROOT, path);

List<String> names = parts.subList(1, parts.size());
for (String name : names) {
Preconditions.checkArgument(
RFC9535_MEMBER_NAME_SHORTHAND.test(name),
"Invalid path: %s (%s has invalid characters)",
path,
name);
}

return names;
}
}
Original file line number Diff line number Diff line change
@@ -0,0 +1,67 @@
/*
* Licensed to the Apache Software Foundation (ASF) under one
* or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information
* regarding copyright ownership. The ASF licenses this file
* to you under the Apache License, Version 2.0 (the
* "License"); you may not use this file except in compliance
* with the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing,
* software distributed under the License is distributed on an
* "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
* KIND, either express or implied. See the License for the
* specific language governing permissions and limitations
* under the License.
*/
package org.apache.iceberg.expressions;

import org.apache.iceberg.exceptions.ValidationException;
import org.apache.iceberg.types.Type;
import org.apache.iceberg.types.Types;

public class UnboundExtract<T> implements UnboundTerm<T> {
private final NamedReference<?> ref;
private final String path;
private final Type.PrimitiveType type;

public UnboundExtract(NamedReference<?> ref, String path, String type) {
this.ref = ref;
this.path = path;
this.type = Types.fromPrimitiveString(type);
// verify that the path is well-formed
PathUtil.parse(path);
}

@Override
public BoundTerm<T> bind(Types.StructType struct, boolean caseSensitive) {
BoundReference<?> boundRef = ref.bind(struct, caseSensitive);
ValidationException.check(
Types.VariantType.get().equals(boundRef.type()),
"Cannot bind extract, not a variant: %s",
boundRef.name());
ValidationException.check(
!type.equals(Types.UnknownType.get()), "Invalid type to extract: unknown");
return new BoundExtract<>(boundRef, path, type);
}

@Override
public NamedReference<?> ref() {
return ref;
}

public String path() {
return path;
}

public Type type() {
return type;
}

@Override
public String toString() {
return "extract(" + ref + ", path=" + path + ", type=" + type + ")";
}
}
Original file line number Diff line number Diff line change
Expand Up @@ -27,6 +27,7 @@
import org.apache.iceberg.relocated.com.google.common.collect.Lists;
import org.apache.iceberg.relocated.com.google.common.collect.Sets;
import org.apache.iceberg.types.Type;
import org.apache.iceberg.types.Types;
import org.apache.iceberg.types.Types.StructType;
import org.apache.iceberg.util.CharSequenceSet;

Expand Down Expand Up @@ -124,13 +125,17 @@ public Expression bind(StructType struct, boolean caseSensitive) {
private Expression bindUnaryOperation(BoundTerm<T> boundTerm) {
switch (op()) {
case IS_NULL:
if (boundTerm.ref().field().isRequired()) {
if (!boundTerm.producesNull()) {
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I see this change is same as the one in BoundReference (field.isOptional()). For BoundTransform, seems we added !transform.preservesOrder() - which transforms produce nulls when not order-preserving?

// transforms must produce null for null input values
// transforms may produce null for non-null inputs when not order-preserving
return ref.producesNull() || !transform.preservesOrder();

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

A good example is VoidTransform, which maps all values to null. If a transform preserves order then it can't produce a null value for a non-null input because that would violate order preservation. If it does not preserve order, then it could map values to null so we account for that. If a field is required there are no non-null values, so the only way a null could be produced is by the transform.

return Expressions.alwaysFalse();
} else if (boundTerm.type().equals(Types.UnknownType.get())) {
return Expressions.alwaysTrue();
}
return new BoundUnaryPredicate<>(Operation.IS_NULL, boundTerm);
case NOT_NULL:
if (boundTerm.ref().field().isRequired()) {
if (!boundTerm.producesNull()) {
return Expressions.alwaysTrue();
} else if (boundTerm.type().equals(Types.UnknownType.get())) {
return Expressions.alwaysFalse();
}
return new BoundUnaryPredicate<>(Operation.NOT_NULL, boundTerm);
case IS_NAN:
Expand All @@ -155,6 +160,14 @@ private boolean floatingType(Type.TypeID typeID) {
}

private Expression bindLiteralOperation(BoundTerm<T> boundTerm) {
if (op() == Operation.STARTS_WITH || op() == Operation.NOT_STARTS_WITH) {
ValidationException.check(
boundTerm.type().equals(Types.StringType.get()),
"Term for STARTS_WITH or NOT_STARTS_WITH must produce a string: %s: %s",
boundTerm,
boundTerm.type());
}

Literal<T> lit = literal().to(boundTerm.type());

if (lit == null) {
Expand Down
Loading