org.apache.commons.lang3.stream.Streams Maven / Gradle / Ivy
Show all versions of commons-lang3 Show documentation
/*
* 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.commons.lang3.stream;
import java.lang.reflect.Array;
import java.util.ArrayList;
import java.util.Collection;
import java.util.Collections;
import java.util.List;
import java.util.Set;
import java.util.function.BiConsumer;
import java.util.function.BinaryOperator;
import java.util.function.Consumer;
import java.util.function.Function;
import java.util.function.Predicate;
import java.util.function.Supplier;
import java.util.stream.Collector;
import java.util.stream.Collectors;
import java.util.stream.Stream;
import org.apache.commons.lang3.function.Failable;
import org.apache.commons.lang3.function.FailableConsumer;
import org.apache.commons.lang3.function.FailableFunction;
import org.apache.commons.lang3.function.FailablePredicate;
/**
* Provides utility functions, and classes for working with the
* {@code java.util.stream} package, or more generally, with Java 8 lambdas. More
* specifically, it attempts to address the fact that lambdas are supposed
* not to throw Exceptions, at least not checked Exceptions, AKA instances
* of {@link Exception}. This enforces the use of constructs like
*
* Consumer<java.lang.reflect.Method> consumer = (m) -> {
* try {
* m.invoke(o, args);
* } catch (Throwable t) {
* throw Failable.rethrow(t);
* }
* };
* stream.forEach(consumer);
*
* Using a {@link FailableStream}, this can be rewritten as follows:
*
* Streams.failable(stream).forEach((m) -> m.invoke(o, args));
*
* Obviously, the second version is much more concise and the spirit of
* Lambda expressions is met better than in the first version.
*
* @see Stream
* @see Failable
* @since 3.11
*/
public class Streams {
public static class ArrayCollector implements Collector, O[]> {
private static final Set characteristics = Collections.emptySet();
private final Class elementType;
public ArrayCollector(final Class elementType) {
this.elementType = elementType;
}
@Override
public BiConsumer, O> accumulator() {
return List::add;
}
@Override
public Set characteristics() {
return characteristics;
}
@Override
public BinaryOperator> combiner() {
return (left, right) -> {
left.addAll(right);
return left;
};
}
@Override
public Function, O[]> finisher() {
return list -> {
@SuppressWarnings("unchecked")
final O[] array = (O[]) Array.newInstance(elementType, list.size());
return list.toArray(array);
};
}
@Override
public Supplier> supplier() {
return ArrayList::new;
}
}
/**
* A reduced, and simplified version of a {@link Stream} with failable method signatures.
*
* @param The streams element type.
*/
public static class FailableStream {
private Stream stream;
private boolean terminated;
/**
* Constructs a new instance with the given {@code stream}.
*
* @param stream The stream.
*/
public FailableStream(final Stream stream) {
this.stream = stream;
}
/**
* Returns whether all elements of this stream match the provided predicate. May not evaluate the predicate on
* all elements if not necessary for determining the result. If the stream is empty then {@code true} is
* returned and the predicate is not evaluated.
*
*
* This is a short-circuiting terminal operation.
*
* Note This method evaluates the universal quantification of the predicate over the elements of
* the stream (for all x P(x)). If the stream is empty, the quantification is said to be vacuously
* satisfied and is always {@code true} (regardless of P(x)).
*
* @param predicate A non-interfering, stateless predicate to apply to elements of this stream
* @return {@code true} If either all elements of the stream match the provided predicate or the stream is
* empty, otherwise {@code false}.
*/
public boolean allMatch(final FailablePredicate predicate) {
assertNotTerminated();
return stream().allMatch(Failable.asPredicate(predicate));
}
/**
* Returns whether any elements of this stream match the provided predicate. May not evaluate the predicate on
* all elements if not necessary for determining the result. If the stream is empty then {@code false} is
* returned and the predicate is not evaluated.
*
*
* This is a short-circuiting terminal operation.
*
* Note This method evaluates the existential quantification of the predicate over the elements of
* the stream (for some x P(x)).
*
* @param predicate A non-interfering, stateless predicate to apply to elements of this stream
* @return {@code true} if any elements of the stream match the provided predicate, otherwise {@code false}
*/
public boolean anyMatch(final FailablePredicate predicate) {
assertNotTerminated();
return stream().anyMatch(Failable.asPredicate(predicate));
}
protected void assertNotTerminated() {
if (terminated) {
throw new IllegalStateException("This stream is already terminated.");
}
}
/**
* Performs a mutable reduction operation on the elements of this stream using a {@code Collector}. A
* {@code Collector} encapsulates the functions used as arguments to
* {@link #collect(Supplier, BiConsumer, BiConsumer)}, allowing for reuse of collection strategies and
* composition of collect operations such as multiple-level grouping or partitioning.
*
*
* If the underlying stream is parallel, and the {@code Collector} is concurrent, and either the stream is
* unordered or the collector is unordered, then a concurrent reduction will be performed (see {@link Collector}
* for details on concurrent reduction.)
*
*
* This is a terminal operation.
*
*
* When executed in parallel, multiple intermediate results may be instantiated, populated, and merged so as to
* maintain isolation of mutable data structures. Therefore, even when executed in parallel with non-thread-safe
* data structures (such as {@code ArrayList}), no additional synchronization is needed for a parallel
* reduction.
*
* Note The following will accumulate strings into an ArrayList:
*
*
* {@code
* List asList = stringStream.collect(Collectors.toList());
* }
*
*
*
* The following will classify {@code Person} objects by city:
*
*
* {@code
* Map> peopleByCity = personStream.collect(Collectors.groupingBy(Person::getCity));
* }
*
*
*
* The following will classify {@code Person} objects by state and city, cascading two {@code Collector}s
* together:
*
*
* {@code
* Map>> peopleByStateAndCity = personStream
* .collect(Collectors.groupingBy(Person::getState, Collectors.groupingBy(Person::getCity)));
* }
*
*
* @param the type of the result
* @param the intermediate accumulation type of the {@code Collector}
* @param collector the {@code Collector} describing the reduction
* @return the result of the reduction
* @see #collect(Supplier, BiConsumer, BiConsumer)
* @see Collectors
*/
public R collect(final Collector collector) {
makeTerminated();
return stream().collect(collector);
}
/**
* Performs a mutable reduction operation on the elements of this FailableStream. A mutable reduction is one in
* which the reduced value is a mutable result container, such as an {@code ArrayList}, and elements are
* incorporated by updating the state of the result rather than by replacing the result. This produces a result
* equivalent to:
*
*
* {@code
* R result = supplier.get();
* for (T element : this stream)
* accumulator.accept(result, element);
* return result;
* }
*
*
*
* Like {@link #reduce(Object, BinaryOperator)}, {@code collect} operations can be parallelized without
* requiring additional synchronization.
*
*
* This is a terminal operation.
*
* Note There are many existing classes in the JDK whose signatures are well-suited for use with method
* references as arguments to {@code collect()}. For example, the following will accumulate strings into an
* {@code ArrayList}:
*
*
* {@code
* List asList = stringStream.collect(ArrayList::new, ArrayList::add, ArrayList::addAll);
* }
*
*
*
* The following will take a stream of strings and concatenates them into a single string:
*
*
* {@code
* String concat = stringStream.collect(StringBuilder::new, StringBuilder::append, StringBuilder::append)
* .toString();
* }
*
*
* @param type of the result
* @param Type of the accumulator.
* @param pupplier a function that creates a new result container. For a parallel execution, this function may
* be called multiple times and must return a fresh value each time.
* @param accumulator An associative, non-interfering, stateless function for incorporating an additional
* element into a result
* @param combiner An associative, non-interfering, stateless function for combining two values, which must be
* compatible with the accumulator function
* @return The result of the reduction
*/
public R collect(final Supplier pupplier, final BiConsumer accumulator,
final BiConsumer combiner) {
makeTerminated();
return stream().collect(pupplier, accumulator, combiner);
}
/**
* Returns a FailableStream consisting of the elements of this stream that match the given FailablePredicate.
*
*
* This is an intermediate operation.
*
* @param predicate a non-interfering, stateless predicate to apply to each element to determine if it should be
* included.
* @return the new stream
*/
public FailableStream filter(final FailablePredicate predicate) {
assertNotTerminated();
stream = stream.filter(Failable.asPredicate(predicate));
return this;
}
/**
* Performs an action for each element of this stream.
*
*
* This is a terminal operation.
*
*
* The behavior of this operation is explicitly nondeterministic. For parallel stream pipelines, this operation
* does not guarantee to respect the encounter order of the stream, as doing so would sacrifice the
* benefit of parallelism. For any given element, the action may be performed at whatever time and in whatever
* thread the library chooses. If the action accesses shared state, it is responsible for providing the required
* synchronization.
*
* @param action a non-interfering action to perform on the elements
*/
public void forEach(final FailableConsumer action) {
makeTerminated();
stream().forEach(Failable.asConsumer(action));
}
protected void makeTerminated() {
assertNotTerminated();
terminated = true;
}
/**
* Returns a stream consisting of the results of applying the given function to the elements of this stream.
*
*
* This is an intermediate operation.
*
* @param The element type of the new stream
* @param mapper A non-interfering, stateless function to apply to each element
* @return the new stream
*/
public FailableStream map(final FailableFunction mapper) {
assertNotTerminated();
return new FailableStream<>(stream.map(Failable.asFunction(mapper)));
}
/**
* Performs a reduction on the elements of this stream, using the provided identity value and an associative
* accumulation function, and returns the reduced value. This is equivalent to:
*
*
* {@code
* T result = identity;
* for (T element : this stream)
* result = accumulator.apply(result, element)
* return result;
* }
*
*
* but is not constrained to execute sequentially.
*
*
* The {@code identity} value must be an identity for the accumulator function. This means that for all
* {@code t}, {@code accumulator.apply(identity, t)} is equal to {@code t}. The {@code accumulator} function
* must be an associative function.
*
*
* This is a terminal operation.
*
* Note Sum, min, max, average, and string concatenation are all special cases of reduction. Summing a
* stream of numbers can be expressed as:
*
*
* {@code
* Integer sum = integers.reduce(0, (a, b) -> a + b);
* }
*
*
* or:
*
*
* {@code
* Integer sum = integers.reduce(0, Integer::sum);
* }
*
*
*
* While this may seem a more roundabout way to perform an aggregation compared to simply mutating a running
* total in a loop, reduction operations parallelize more gracefully, without needing additional synchronization
* and with greatly reduced risk of data races.
*
* @param identity the identity value for the accumulating function
* @param accumulator an associative, non-interfering, stateless function for combining two values
* @return the result of the reduction
*/
public O reduce(final O identity, final BinaryOperator accumulator) {
makeTerminated();
return stream().reduce(identity, accumulator);
}
/**
* Converts the FailableStream into an equivalent stream.
*
* @return A stream, which will return the same elements, which this FailableStream would return.
*/
public Stream stream() {
return stream;
}
}
/**
* Converts the given {@link Collection} into a {@link FailableStream}. This is basically a simplified, reduced
* version of the {@link Stream} class, with the same underlying element stream, except that failable objects, like
* {@link FailablePredicate}, {@link FailableFunction}, or {@link FailableConsumer} may be applied, instead of
* {@link Predicate}, {@link Function}, or {@link Consumer}. The idea is to rewrite a code snippet like this:
*
*
* final List<O> list;
* final Method m;
* final Function<O, String> mapper = (o) -> {
* try {
* return (String) m.invoke(o);
* } catch (Throwable t) {
* throw Failable.rethrow(t);
* }
* };
* final List<String> strList = list.stream().map(mapper).collect(Collectors.toList());
*
*
* as follows:
*
*
* final List<O> list;
* final Method m;
* final List<String> strList = Failable.stream(list.stream()).map((o) -> (String) m.invoke(o))
* .collect(Collectors.toList());
*
*
* While the second version may not be quite as efficient (because it depends on the creation of
* additional, intermediate objects, of type FailableStream), it is much more concise, and readable, and meets the
* spirit of Lambdas better than the first version.
*
* @param The streams element type.
* @param stream The stream, which is being converted.
* @return The {@link FailableStream}, which has been created by converting the stream.
*/
public static FailableStream stream(final Collection stream) {
return stream(stream.stream());
}
/**
* Converts the given {@link Stream stream} into a {@link FailableStream}. This is basically a simplified, reduced
* version of the {@link Stream} class, with the same underlying element stream, except that failable objects, like
* {@link FailablePredicate}, {@link FailableFunction}, or {@link FailableConsumer} may be applied, instead of
* {@link Predicate}, {@link Function}, or {@link Consumer}. The idea is to rewrite a code snippet like this:
*
*
* final List<O> list;
* final Method m;
* final Function<O, String> mapper = (o) -> {
* try {
* return (String) m.invoke(o);
* } catch (Throwable t) {
* throw Failable.rethrow(t);
* }
* };
* final List<String> strList = list.stream().map(mapper).collect(Collectors.toList());
*
*
* as follows:
*
*
* final List<O> list;
* final Method m;
* final List<String> strList = Failable.stream(list.stream()).map((o) -> (String) m.invoke(o))
* .collect(Collectors.toList());
*
*
* While the second version may not be quite as efficient (because it depends on the creation of
* additional, intermediate objects, of type FailableStream), it is much more concise, and readable, and meets the
* spirit of Lambdas better than the first version.
*
* @param The streams element type.
* @param stream The stream, which is being converted.
* @return The {@link FailableStream}, which has been created by converting the stream.
*/
public static FailableStream stream(final Stream stream) {
return new FailableStream<>(stream);
}
/**
* Returns a {@code Collector} that accumulates the input elements into a new array.
*
* @param pElementType Type of an element in the array.
* @param the type of the input elements
* @return a {@code Collector} which collects all the input elements into an array, in encounter order
*/
public static Collector toArray(final Class pElementType) {
return new ArrayCollector<>(pElementType);
}
}