java-topology/defects/open3d/unit/RansacSamplerAlgorithm.java

package unit;

import java.util.*;

/**
 * Unit test for open3d-0002: RandomSampler::operator() O(S²) → O(S)
 *
 * Simulates Open3D PointCloudSegmentation.cpp RandomSampler:
 *   Defective: std::find on growing samples vector inside rejection-sampling while loop
 *   Fixed:     unordered_set for O(1) duplicate detection
 *
 * Compile: javac -d . RansacSamplerAlgorithm.java
 * Run:     java -ea unit.RansacSamplerAlgorithm
 */
public class RansacSamplerAlgorithm {

    // ── defective implementation ──────────────────────────────────────────────

    /** Returns sampleSize unique indices in [0, totalSize), using O(S²) rejection sampling */
    static List<Integer> defectiveSample(int totalSize, int sampleSize, Random rng) {
        List<Integer> samples = new ArrayList<>(sampleSize);
        while (samples.size() < sampleSize) {
            int idx = rng.nextInt(totalSize);
            // O(valid_sample) linear scan — same as std::find in Open3D
            boolean found = false;
            for (int s : samples) if (s == idx) { found = true; break; }
            if (!found) samples.add(idx);
        }
        return samples;
    }

    // ── fixed implementation ──────────────────────────────────────────────────

    /** Returns sampleSize unique indices in [0, totalSize), using O(S) set-based sampling */
    static List<Integer> fixedSample(int totalSize, int sampleSize, Random rng) {
        List<Integer> samples = new ArrayList<>(sampleSize);
        Set<Integer> seen = new HashSet<>(sampleSize * 2);
        while (samples.size() < sampleSize) {
            int idx = rng.nextInt(totalSize);
            if (seen.add(idx)) samples.add(idx);  // O(1)
        }
        return samples;
    }

    // ── property checks ───────────────────────────────────────────────────────

    static boolean isUniqueSubset(List<Integer> sample, int totalSize) {
        Set<Integer> seen = new HashSet<>();
        for (int idx : sample) {
            if (idx < 0 || idx >= totalSize) return false;
            if (!seen.add(idx)) return false;  // duplicate
        }
        return true;
    }

    // ── tests ─────────────────────────────────────────────────────────────────

    static int pass = 0, total = 0;

    static void assertTrue(String name, boolean cond) {
        total++;
        if (cond) { pass++; System.out.println("PASS " + name); }
        else       System.out.println("FAIL " + name);
    }

    public static void main(String[] args) {
        Random rng = new Random(12345);

        // Test 1: sample_size=0 → empty result
        {
            List<Integer> d = defectiveSample(100, 0, new Random(1));
            List<Integer> f = fixedSample(100, 0, new Random(1));
            assertTrue("zero-sample-defective", d.isEmpty());
            assertTrue("zero-sample-fixed", f.isEmpty());
        }

        // Test 2: sample_size=1 → single unique index
        {
            List<Integer> d = defectiveSample(1000, 1, new Random(2));
            List<Integer> f = fixedSample(1000, 1, new Random(2));
            assertTrue("size1-defective", d.size() == 1 && isUniqueSubset(d, 1000));
            assertTrue("size1-fixed", f.size() == 1 && isUniqueSubset(f, 1000));
        }

        // Test 3: sample_size=3 (default ransac_n) → correct size, unique, valid range
        {
            for (int trial = 0; trial < 20; trial++) {
                List<Integer> d = defectiveSample(10000, 3, rng);
                List<Integer> f = fixedSample(10000, 3, rng);
                if (!isUniqueSubset(d, 10000) || d.size() != 3) {
                    assertTrue("sample3-defective-trial" + trial, false);
                    break;
                }
                if (!isUniqueSubset(f, 10000) || f.size() != 3) {
                    assertTrue("sample3-fixed-trial" + trial, false);
                    break;
                }
            }
            assertTrue("sample3-20-trials-defective", true);
            assertTrue("sample3-20-trials-fixed", true);
        }

        // Test 4: sample_size=totalSize → exactly all indices (if feasible)
        {
            int N = 20;
            List<Integer> d = defectiveSample(N, N, new Random(7));
            List<Integer> f = fixedSample(N, N, new Random(7));
            assertTrue("full-sample-defective", d.size() == N && isUniqueSubset(d, N) && new HashSet<>(d).size() == N);
            assertTrue("full-sample-fixed", f.size() == N && isUniqueSubset(f, N) && new HashSet<>(f).size() == N);
        }

        // Test 5: no duplicates across 100 calls with sample_size=10
        {
            boolean defOk = true, fixOk = true;
            for (int i = 0; i < 100; i++) {
                if (!isUniqueSubset(defectiveSample(10000, 10, rng), 10000)) defOk = false;
                if (!isUniqueSubset(fixedSample(10000, 10, rng), 10000)) fixOk = false;
            }
            assertTrue("no-duplicates-100-defective", defOk);
            assertTrue("no-duplicates-100-fixed", fixOk);
        }

        // Test 6: performance — simulate RANSAC: num_iterations=1000, ransac_n=10, totalSize=50000
        {
            int numIter = 1000, sampleSize = 10, totalSize = 50000;

            long t0 = System.nanoTime();
            Random r1 = new Random(42);
            for (int i = 0; i < numIter; i++) defectiveSample(totalSize, sampleSize, r1);
            long tDef = System.nanoTime() - t0;

            t0 = System.nanoTime();
            Random r2 = new Random(42);
            for (int i = 0; i < numIter; i++) fixedSample(totalSize, sampleSize, r2);
            long tFix = System.nanoTime() - t0;

            double ratio = (double) tDef / tFix;
            System.out.printf("  Perf RANSAC iter=%d S=%d N=%d: defective=%.1fms fixed=%.1fms ratio=%.1fx%n",
                numIter, sampleSize, totalSize, tDef / 1e6, tFix / 1e6, ratio);
            // At S=10 ratio may be modest; the defect scales as S²
            assertTrue("perf-not-slower", ratio >= 0.5);  // conservative: fixed should not be slower
        }

        // Test 7: performance at larger sample_size=100 where O(S²) hurts more
        {
            int numIter = 1000, sampleSize = 100, totalSize = 100000;

            long t0 = System.nanoTime();
            Random r1 = new Random(99);
            for (int i = 0; i < numIter; i++) defectiveSample(totalSize, sampleSize, r1);
            long tDef = System.nanoTime() - t0;

            t0 = System.nanoTime();
            Random r2 = new Random(99);
            for (int i = 0; i < numIter; i++) fixedSample(totalSize, sampleSize, r2);
            long tFix = System.nanoTime() - t0;

            double ratio = (double) tDef / tFix;
            System.out.printf("  Perf RANSAC iter=%d S=%d N=%d: defective=%.1fms fixed=%.1fms ratio=%.1fx%n",
                numIter, sampleSize, totalSize, tDef / 1e6, tFix / 1e6, ratio);
            assertTrue("perf-s100-speedup", ratio > 2.0);
        }

        System.out.println(pass + "/" + total + " PASS");
        assert pass == total : pass + "/" + total + " passed";
    }
}