Last active
April 21, 2025 23:48
-
-
Save DanielThomas/f74d8937a5440685ceef07a70df6433c to your computer and use it in GitHub Desktop.
Tests for HashIndex.java
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
/* | |
* Copyright 2024 Netflix Inc. | |
* | |
* Licensed 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 com.netflix.index; | |
import org.junit.jupiter.api.Disabled; | |
import org.junit.jupiter.api.Test; | |
import org.junit.jupiter.params.ParameterizedTest; | |
import org.junit.jupiter.params.provider.ValueSource; | |
import org.springframework.core.io.ClassPathResource; | |
import java.io.*; | |
import java.util.*; | |
import java.util.function.ToLongFunction; | |
import java.util.stream.Collectors; | |
import java.util.stream.IntStream; | |
import java.util.stream.LongStream; | |
import java.util.zip.GZIPInputStream; | |
import static org.junit.jupiter.api.Assertions.*; | |
class HashIndexTest { | |
private static HashIndex<String> single() { | |
Spliterator<String> source = Collections.singletonList("").spliterator(); | |
return HashIndex.ofLong(source, input -> 0, input -> 0); | |
} | |
private static HashIndex<String> singleWithMaxBytes(long value, int maxBytes) { | |
Spliterator<String> source = Collections.singletonList("").spliterator(); | |
return ofBytes(source, input -> 0, input -> value, maxBytes); | |
} | |
private static <T> HashIndex<T> ofBytes(Spliterator<T> source, ToLongFunction<T> keyMapper, ToLongFunction<T> valueMapper, int maxBytes) { | |
switch(maxBytes) { | |
case Byte.BYTES: return HashIndex.ofByte(source, keyMapper, valueMapper); | |
case Short.BYTES: return HashIndex.ofShort(source, keyMapper, valueMapper); | |
case Integer.BYTES: return HashIndex.ofInt(source, keyMapper, valueMapper); | |
case Long.BYTES: return HashIndex.ofLong(source, keyMapper, valueMapper); | |
} | |
throw new IllegalArgumentException(); | |
} | |
@Test | |
public void mapMissing() { | |
HashIndex<String> index = single(); | |
String actual = index.map(0, value -> null); | |
assertNull(actual); | |
} | |
@Test | |
public void mapMaxKey() { | |
HashIndex<String> index = single(); | |
String actual = index.map(Long.MAX_VALUE, value -> "value"); | |
assertNull(actual); | |
} | |
@Test | |
public void mapPresent() { | |
HashIndex<String> index = single(); | |
String actual = index.map(0, value -> "value"); | |
assertEquals("value", actual); | |
} | |
@Test | |
public void mapNotEqual() { | |
HashIndex<String> index = single(); | |
String actual = index.map(0, value -> null); | |
assertNull(actual); | |
} | |
@Test | |
public void mapDuplicateKeys() { | |
Spliterator<Integer> source = IntStream.rangeClosed(1, 5).boxed().spliterator(); | |
HashIndex<Integer> index = HashIndex.ofInt(source, input -> 1, input -> input); | |
List<Long> values = new ArrayList<>(); | |
Integer actual = index.map(1, value -> { | |
values.add(value); | |
if (value == 5) { | |
return 5; | |
} | |
return null; | |
}); | |
assertEquals(5, actual); | |
assertEquals(5, values.size()); | |
} | |
@Test | |
public void indexMaxTableSize() { | |
Spliterator<Integer> source = Spliterators.spliterator(Collections.<Integer>emptyList().iterator(), Integer.MAX_VALUE, Spliterator.SIZED); | |
assertThrows(ArithmeticException.class, () -> HashIndex.ofInt(source, input -> 1, input -> input)); | |
} | |
@ParameterizedTest | |
@ValueSource(longs = {(long) Byte.MAX_VALUE, (long) Short.MAX_VALUE, (long) Integer.MAX_VALUE, Long.MAX_VALUE}) | |
public void indexMaxValueDisallowed(long expected) { | |
int maxBytes = (Long.SIZE - Long.numberOfLeadingZeros(expected) + 1) / Byte.SIZE; | |
IllegalArgumentException exception = assertThrows(IllegalArgumentException.class, () -> singleWithMaxBytes(expected, maxBytes)); | |
assertEquals("max value is reserved", exception.getMessage()); | |
} | |
@ParameterizedTest | |
@ValueSource(longs = {(long) Byte.MAX_VALUE, (long) Short.MAX_VALUE, (long) Integer.MAX_VALUE, Long.MAX_VALUE}) | |
public void indexMaxValueMinusOne(long expected) { | |
int maxBytes = (Long.SIZE - Long.numberOfLeadingZeros(expected) + 1) / Byte.SIZE; | |
expected = expected - 1; | |
HashIndex<String> index = singleWithMaxBytes(expected, maxBytes); | |
String actual = index.map(0, String::valueOf); | |
assertEquals(expected, Long.valueOf(actual)); | |
} | |
@ParameterizedTest | |
@ValueSource(longs = {(long) Byte.MIN_VALUE, (long) Short.MIN_VALUE, (long) Integer.MIN_VALUE, Long.MIN_VALUE}) | |
public void indexMinValue(long expected) { | |
int maxBytes = (Long.SIZE - Long.numberOfLeadingZeros(~expected) + 1) / Byte.SIZE; | |
HashIndex<String> index = singleWithMaxBytes(expected, maxBytes); | |
String actual = index.map(0, String::valueOf); | |
assertEquals(expected, Long.valueOf(actual)); | |
} | |
@ParameterizedTest | |
@ValueSource(ints = {Byte.BYTES, Short.BYTES, Integer.BYTES}) | |
public void indexNarrowingDisallowed(int maxBytes) { | |
Exception exception = assertThrows(IllegalArgumentException.class, () -> singleWithMaxBytes(1L << maxBytes * Byte.SIZE, maxBytes)); | |
assertEquals("value out of range", exception.getMessage()); | |
} | |
@Test | |
public void indexLargeKeySet() throws IOException { | |
ClassPathResource resource = new ClassPathResource("keys-sorted.txt.gz"); | |
try (BufferedReader reader = new BufferedReader(new InputStreamReader(new GZIPInputStream(resource.getInputStream())))) { | |
List<Long> lines = reader.lines().map(Long::parseLong).collect(Collectors.toList()); | |
HashIndex<Long> index = HashIndex.ofInt(lines.spliterator(), input -> input, input -> input); | |
lines.forEach(key -> assertEquals(key, index.map(key, candidate -> candidate == key ? candidate : null))); | |
} | |
} | |
@Disabled | |
@ParameterizedTest | |
@ValueSource(ints = {Byte.BYTES, Short.BYTES, Integer.BYTES, Long.BYTES}) | |
public void indexAndGetAllValues(int maxBytes) { | |
int numBits = maxBytes * Byte.SIZE; | |
long minValue = -(1L << numBits - 1); | |
long maxValue = ~minValue; | |
int batch = 10000000; | |
long start = minValue + 1; | |
while (true) { | |
long end = Math.min(maxValue, start + batch); | |
Spliterator<Long> source = LongStream.range(start, end).boxed().spliterator(); | |
HashIndex<Long> index = ofBytes(source, value -> value, value -> value, maxBytes); | |
LongStream.range(start, end).forEach(value -> index.map(value, candidate -> candidate == value ? candidate : null)); | |
start = end; | |
if (end == maxValue) break; | |
} | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment