java-topology/defects/ray-project/test/RayProjectTest.java

import java.util.*;

/**
 * Unit test for ray-project-0001: dag_node.py _get_toplevel_child_nodes O(A²) dedup
 *
 * CWE-407 — Algorithmic Complexity
 *
 * DAGNode._get_toplevel_child_nodes() uses `if a not in children` on a list
 * for deduplication, making it O(A²) where A = number of DAG arguments.
 * Fix: maintain a parallel set for O(1) membership.
 */
public class RayProjectTest {

    /** Simulates a DAGNode with an ID for identity comparison */
    static class FakeDAGNode {
        final int nodeId;
        FakeDAGNode(int id) { this.nodeId = id; }
        @Override
        public boolean equals(Object o) {
            return o instanceof FakeDAGNode && ((FakeDAGNode) o).nodeId == this.nodeId;
        }
        @Override
        public int hashCode() { return nodeId; }
    }

    /** DEFECTIVE: linear scan on list for dedup — O(A²) */
    static List<FakeDAGNode> getChildrenDefective(List<FakeDAGNode> args) {
        List<FakeDAGNode> children = new ArrayList<>();
        for (FakeDAGNode a : args) {
            if (!children.contains(a)) {
                children.add(a);
            }
        }
        return children;
    }

    /** FIXED: set-based dedup — O(A) */
    static List<FakeDAGNode> getChildrenFixed(List<FakeDAGNode> args) {
        List<FakeDAGNode> children = new ArrayList<>();
        Set<Integer> childrenIds = new HashSet<>();
        for (FakeDAGNode a : args) {
            if (childrenIds.add(System.identityHashCode(a))) {
                children.add(a);
            }
        }
        return children;
    }

    public static void main(String[] args) {
        // Create A=500 unique DAG nodes, with ~50% duplicates
        int A = 500;
        List<FakeDAGNode> nodes = new ArrayList<>();
        for (int i = 0; i < A; i++) nodes.add(new FakeDAGNode(i));

        // Build args list with duplicates
        List<FakeDAGNode> argsList = new ArrayList<>();
        Random rng = new Random(42);
        for (int i = 0; i < A * 2; i++) {
            argsList.add(nodes.get(rng.nextInt(A)));
        }

        // Correctness
        List<FakeDAGNode> resultDefective = getChildrenDefective(argsList);
        List<FakeDAGNode> resultFixed = getChildrenFixed(argsList);
        assert resultDefective.size() == resultFixed.size() : "FAIL: sizes differ";

        // Warmup
        for (int w = 0; w < 5; w++) {
            getChildrenDefective(argsList);
            getChildrenFixed(argsList);
        }

        // Benchmark
        int iterations = 500;
        long t0 = System.nanoTime();
        for (int i = 0; i < iterations; i++) {
            getChildrenDefective(argsList);
        }
        long defectiveNs = System.nanoTime() - t0;

        t0 = System.nanoTime();
        for (int i = 0; i < iterations; i++) {
            getChildrenFixed(argsList);
        }
        long fixedNs = System.nanoTime() - t0;

        double ratio = (double) defectiveNs / fixedNs;
        System.out.printf("ray-project-0001 (_get_toplevel_child_nodes O(A²) → O(A))%n");
        System.out.printf("  A=%d args (with duplicates), %d iterations%n", A * 2, iterations);
        System.out.printf("  defective: %,d ns%n", defectiveNs);
        System.out.printf("  fixed:     %,d ns%n", fixedNs);
        System.out.printf("  ratio:     %.1fx%n", ratio);
        System.out.printf("  PASS (ratio=%.1f)%n", ratio);
    }
}