java-topology/defects/r-lang-0001/unit/RNamespaceUsersTest.java

import java.util.*;

/**
 * Unit test: simulates R getNamespaceUsers() and namespaceImportMethods()
 * O(N^2) list-membership defect (CWE-407).
 *
 * Models:
 *   - getNamespaceUsers: outer loop N loaded namespaces, inner match() O(I)
 *     => total O(N * I), patched to O(N + I) using HashSet
 *   - namespaceImportMethods: outer loop G generics, inner %in% vars O(V)
 *     => total O(G * V), patched to O(G + V) using HashSet
 */
public class RNamespaceUsersTest {

    // --- Model: getNamespaceUsers ---

    /** Buggy: O(N * I) - linear scan of inames per namespace. */
    static List<String> getNamespaceUsersDefect(
            String nsname,
            Map<String, List<String>> loadedImports) {
        List<String> users = new ArrayList<>();
        for (Map.Entry<String, List<String>> e : loadedImports.entrySet()) {
            String n = e.getKey();
            List<String> inames = e.getValue();
            // match(nsname, inames) — O(|inames|) linear scan
            if (inames.contains(nsname)) {
                users.add(0, n);
            }
        }
        return users;
    }

    /**
     * Fixed: O(N + total_imports) - build reverse index once.
     * The R-level fix uses a pre-built hash env or converts the whole
     * import list to a set before calling getNamespaceUsers in a loop.
     * In practice the fix is to cache the reverse map.
     */
    static List<String> getNamespaceUsersFixed(
            String nsname,
            Map<String, List<String>> loadedImports) {
        // Build reverse index: importedName -> list of namespaces that import it
        // O(N * I) build cost amortized across many getNamespaceUsers() calls,
        // or O(N + total_imports) per single call when done as a flat scan + set.
        // Single-call optimization: collect all (namespace, importName) pairs
        // into a Map<importName, Set<namespace>> in one pass.
        Map<String, List<String>> reverseIndex = new HashMap<>();
        for (Map.Entry<String, List<String>> e : loadedImports.entrySet()) {
            for (String imp : e.getValue()) {
                reverseIndex.computeIfAbsent(imp, k -> new ArrayList<>()).add(e.getKey());
            }
        }
        List<String> found = reverseIndex.getOrDefault(nsname, Collections.emptyList());
        // Return in reverse order to match original semantics (prepend)
        List<String> users = new ArrayList<>(found);
        Collections.reverse(users);
        return users;
    }

    // --- Model: namespaceImportMethods ---

    /** Buggy: O(G * V) - g %in% vars is O(|vars|) per generic. */
    static List<String> importMethodsDefect(List<String> allFuns, List<String> vars) {
        List<String> imported = new ArrayList<>();
        for (String g : allFuns) {
            if (vars.contains(g)) { // O(|vars|)
                imported.add(g);
            }
        }
        return imported;
    }

    /** Fixed: O(G + V) - convert vars to HashSet once. */
    static List<String> importMethodsFixed(List<String> allFuns, List<String> vars) {
        Set<String> varsSet = new HashSet<>(vars);
        List<String> imported = new ArrayList<>();
        for (String g : allFuns) {
            if (varsSet.contains(g)) { // O(1)
                imported.add(g);
            }
        }
        return imported;
    }

    // --- Benchmark and correctness check ---

    static Map<String, List<String>> buildNamespaceImports(int numNamespaces, int importsPerNs, String target) {
        Map<String, List<String>> result = new LinkedHashMap<>();
        for (int i = 0; i < numNamespaces; i++) {
            List<String> imports = new ArrayList<>();
            for (int j = 0; j < importsPerNs; j++) {
                imports.add("pkg" + i + "_import" + j);
            }
            // Last namespace imports our target
            if (i == numNamespaces - 1) imports.add(target);
            result.put("namespace" + i, imports);
        }
        return result;
    }

    public static void main(String[] args) {
        final int N = 200;   // namespaces (CRAN session can exceed 100)
        final int I = 500;   // imports per namespace (e.g., Bioconductor packages)
        final int G = 1000;  // generics in a namespace (methods-heavy pkg like Matrix/BioConductor)
        final int V = 500;   // vars requested

        String target = "stats";
        Map<String, List<String>> loadedImports = buildNamespaceImports(N, I, target);

        // Correctness check
        List<String> r1 = getNamespaceUsersDefect(target, loadedImports);
        List<String> r2 = getNamespaceUsersFixed(target, loadedImports);
        assert r1.equals(r2) : "getNamespaceUsers: results differ";

        // Build allFuns and vars for importMethods
        List<String> allFuns = new ArrayList<>();
        for (int i = 0; i < G; i++) allFuns.add("generic" + i);
        List<String> vars = new ArrayList<>();
        for (int i = 0; i < V; i++) vars.add("generic" + (G - V + i));

        List<String> m1 = importMethodsDefect(allFuns, vars);
        List<String> m2 = importMethodsFixed(allFuns, vars);
        assert m1.equals(m2) : "importMethods: results differ";

        // --- Timing ---
        // getNamespaceUsers is called for each namespace being detached/reloaded.
        // In a session with N namespaces, it's called O(N) times total.
        // Simulate that: call getNamespaceUsers for each of N distinct targets.
        final int REPS = 10;
        List<String> targets = new ArrayList<>();
        for (int i = 0; i < N; i++) targets.add("namespace" + i);

        // getNamespaceUsers defect — O(N * I) per call, called N times = O(N^2 * I)
        long t0 = System.nanoTime();
        for (int r = 0; r < REPS; r++)
            for (String tgt : targets) getNamespaceUsersDefect(tgt, loadedImports);
        long defectNs = System.nanoTime() - t0;

        // getNamespaceUsers fixed — build reverse index once, O(N*I) build + O(1) per query
        t0 = System.nanoTime();
        for (int r = 0; r < REPS; r++) {
            // Build reverse index once per session-level batch
            Map<String, List<String>> reverseIndex = new HashMap<>();
            for (Map.Entry<String, List<String>> e : loadedImports.entrySet()) {
                for (String imp : e.getValue()) {
                    reverseIndex.computeIfAbsent(imp, k -> new ArrayList<>()).add(e.getKey());
                }
            }
            for (String tgt : targets) {
                List<String> found = reverseIndex.getOrDefault(tgt, Collections.emptyList());
            }
        }
        long fixedNs = System.nanoTime() - t0;

        // importMethods defect
        long t2 = System.nanoTime();
        for (int r = 0; r < REPS; r++) importMethodsDefect(allFuns, vars);
        long importDefectNs = System.nanoTime() - t2;

        // importMethods fixed
        t2 = System.nanoTime();
        for (int r = 0; r < REPS; r++) importMethodsFixed(allFuns, vars);
        long importFixedNs = System.nanoTime() - t2;

        System.out.printf("=== r-lang-0001: CWE-407 namespace membership O(N*I) ===%n");
        System.out.printf("getNamespaceUsers  defect: %,d ns | fixed: %,d ns | ratio: %.1fx%n",
                defectNs, fixedNs, (double) defectNs / fixedNs);
        System.out.printf("importMethods      defect: %,d ns | fixed: %,d ns | ratio: %.1fx%n",
                importDefectNs, importFixedNs, (double) importDefectNs / importFixedNs);
        System.out.printf("N=%d namespaces, I=%d imports, G=%d generics, V=%d vars%n", N, I, G, V);

        // PASS/FAIL
        double nsRatio = (double) defectNs / fixedNs;
        double imRatio = (double) importDefectNs / importFixedNs;
        if (nsRatio >= 3.0 && imRatio >= 3.0) {
            System.out.println("PASS");
        } else {
            System.out.printf("FAIL — ratios below threshold (%.1fx, %.1fx, expected >=3x)%n",
                    nsRatio, imRatio);
            System.exit(1);
        }
    }
}