java-topology/defects/opensearch/unit/CacheStatsLevelsContains.java

package unit;

import java.util.ArrayList;
import java.util.Arrays;
import java.util.HashSet;
import java.util.List;
import java.util.Set;

/**
 * CWE-407 unit test: opensearch-001
 * ImmutableCacheStatsHolder.java:232-235 — Arrays.asList(levels).contains() inside
 * a loop over dimensionNames — O(n²) level filtering.
 *
 * Slow path: Arrays.asList().contains() — O(L) per iteration.
 * Fast path: HashSet.contains() — O(1) per iteration.
 *
 * Compile: javac -d . CacheStatsLevelsContains.java
 * Run:     java -ea unit.CacheStatsLevelsContains
 */
public class CacheStatsLevelsContains {

    /**
     * Simulates the defective filterLevels().
     * Returns the number of element comparisons performed.
     */
    static long slowFilterLevels(String[] levels, List<String> dimensionNames) {
        if (levels == null) return 0;

        List<String> levelsList = Arrays.asList(levels);  // O(n) contains() scan
        List<String> result = new ArrayList<>();
        long comparisons = 0;

        for (String dimensionName : dimensionNames) {
            // charge the linear scan cost
            comparisons += levelsList.size();
            if (levelsList.contains(dimensionName)) {
                result.add(dimensionName);
            }
        }
        return comparisons;
    }

    /**
     * Simulates the fixed filterLevels() using HashSet.
     * Returns the number of hash lookups performed.
     */
    static long fastFilterLevels(String[] levels, List<String> dimensionNames) {
        if (levels == null) return 0;

        Set<String> levelsSet = new HashSet<>(Arrays.asList(levels));
        List<String> result = new ArrayList<>();
        long operations = 0;

        for (String dimensionName : dimensionNames) {
            operations++;  // O(1) hash lookup
            if (levelsSet.contains(dimensionName)) {
                result.add(dimensionName);
            }
        }
        return operations;
    }

    /** Run both paths and return filtered list (for correctness check). */
    static List<String> filterSlow(String[] levels, List<String> dimensionNames) {
        if (levels == null) return new ArrayList<>(dimensionNames);
        List<String> levelsList = Arrays.asList(levels);
        List<String> result = new ArrayList<>();
        for (String d : dimensionNames) {
            if (levelsList.contains(d)) result.add(d);
        }
        return result;
    }

    static List<String> filterFast(String[] levels, List<String> dimensionNames) {
        if (levels == null) return new ArrayList<>(dimensionNames);
        Set<String> levelsSet = new HashSet<>(Arrays.asList(levels));
        List<String> result = new ArrayList<>();
        for (String d : dimensionNames) {
            if (levelsSet.contains(d)) result.add(d);
        }
        return result;
    }

    public static void main(String[] args) {
        int passed = 0;
        int total = 0;

        // Test 1: correctness — same output from both paths
        {
            total++;
            String[] levels = {"shard", "node"};
            List<String> dims = new ArrayList<>(Arrays.asList("index", "shard", "node", "tier"));

            List<String> slowResult = filterSlow(levels, dims);
            List<String> fastResult = filterFast(levels, dims);

            assert slowResult.equals(fastResult) :
                "Results differ: slow=" + slowResult + " fast=" + fastResult;
            assert slowResult.size() == 2 : "Expected 2, got " + slowResult.size();
            System.out.printf("Test 1 (correctness): both = %s%n", slowResult);
            passed++;
        }

        // Test 2: null levels — pass-through
        {
            total++;
            List<String> dims = new ArrayList<>(Arrays.asList("a", "b", "c"));
            long slowCost = slowFilterLevels(null, dims);
            long fastCost = fastFilterLevels(null, dims);
            assert slowCost == 0 && fastCost == 0;
            System.out.printf("Test 2 (null levels): slow=%d fast=%d%n", slowCost, fastCost);
            passed++;
        }

        // Test 3: cost ratio — medium scale
        {
            total++;
            int D = 100; // dimension names (like cache dimension keys in a large cluster)
            int L = 50;  // levels requested

            List<String> dimensionNames = new ArrayList<>();
            for (int i = 0; i < D; i++) dimensionNames.add("dim" + i);

            String[] levels = new String[L];
            for (int i = 0; i < L; i++) levels[i] = "dim" + (i * 2); // every other dim

            long slowCost = slowFilterLevels(levels, dimensionNames);
            long fastCost = fastFilterLevels(levels, dimensionNames);

            assert slowCost > fastCost :
                String.format("Expected slow > fast: slow=%d fast=%d", slowCost, fastCost);
            System.out.printf("Test 3 (D=%d L=%d): slow=%d, fast=%d, ratio=%.1fx%n",
                D, L, slowCost, fastCost, (double) slowCost / fastCost);
            passed++;
        }

        // Test 4: large scale — verify significant speedup
        {
            total++;
            int D = 500;
            int L = 200;

            List<String> dimensionNames = new ArrayList<>();
            for (int i = 0; i < D; i++) dimensionNames.add("dim" + i);

            String[] levels = new String[L];
            for (int i = 0; i < L; i++) levels[i] = "dim" + i;

            long slowCost = slowFilterLevels(levels, dimensionNames);
            long fastCost = fastFilterLevels(levels, dimensionNames);

            double ratio = (double) slowCost / fastCost;
            assert ratio > 10.0 :
                String.format("Expected >10x speedup at D=%d L=%d, got %.1fx", D, L, ratio);
            System.out.printf("Test 4 (D=%d L=%d): slow=%d, fast=%d, speedup=%.1fx%n",
                D, L, slowCost, fastCost, ratio);
            passed++;
        }

        System.out.printf("%n%d/%d PASS%n", passed, total);
    }
}