java-topology/defects/diesel/unit/DieselAlgorithm.java

package support;

import java.util.*;

/**
 * DieselAlgorithm — algorithmic models of Diesel (Rust) CWE-407 defects.
 *
 * Three defects modelled:
 *
 *   diesel-0001: SqliteRow Duplicated RowIndex<&str>
 *     column_names.iter().position() — O(N_cols) per named-column access.
 *     Called once per deserialized field access on a duplicated row.
 *
 *   diesel-0002: OwnedSqliteRow RowIndex<&str>
 *     Same pattern on the owned (long-lived) variant.
 *
 *   diesel-0003: MysqlRow RowIndex<&str>
 *     metadata.fields().iter().enumerate().find() — O(N_cols) linear scan.
 */
public class DieselAlgorithm {

    public static class Result {
        public final int defectiveOps;
        public final int fixedOps;
        public Result(int defectiveOps, int fixedOps) {
            this.defectiveOps = defectiveOps;
            this.fixedOps = fixedOps;
        }
    }

    // -----------------------------------------------------------------------
    // diesel-0001/0002: SQLite Duplicated row — named column lookup
    //
    // Pattern: for each row in result set, for each named-column access,
    //          scan the column_names slice for a matching name.
    //
    // Cost: O(rows × cols_accessed × total_cols)
    // Fixed: build index map once per statement; O(rows × cols_accessed × log(total_cols))
    // -----------------------------------------------------------------------

    /**
     * Defective: linear scan for column name on every access.
     *
     * @param totalCols   total columns in the result set (width of row)
     * @param colsAccessed number of named-column accesses per row
     * @param numRows     number of rows in the result set
     * @return total position-scan steps (cost metric)
     */
    public static long sqliteRowDefective(int totalCols, int colsAccessed, int numRows) {
        // Simulate column_names as a list (Rust: Rc<[Option<String>]>)
        List<String> columnNames = new ArrayList<>();
        for (int c = 0; c < totalCols; c++) {
            columnNames.add("col_" + c);
        }

        long totalScanSteps = 0;
        for (int r = 0; r < numRows; r++) {
            for (int a = 0; a < colsAccessed; a++) {
                String target = "col_" + (a % totalCols);
                // Simulate: column_names.iter().position(|n| n == target)
                for (int i = 0; i < columnNames.size(); i++) {
                    totalScanSteps++;
                    if (columnNames.get(i).equals(target)) break;
                }
            }
        }
        return totalScanSteps;
    }

    /**
     * Fixed: build a Map<String, Integer> once per statement (once, not per row),
     * then O(log N) lookup per access via TreeMap.
     *
     * @param totalCols   total columns
     * @param colsAccessed named-column accesses per row
     * @param numRows     rows in result set
     * @return total lookup steps (cost metric)
     */
    public static long sqliteRowFixed(int totalCols, int colsAccessed, int numRows) {
        List<String> columnNames = new ArrayList<>();
        for (int c = 0; c < totalCols; c++) {
            columnNames.add("col_" + c);
        }

        // Build index map ONCE (per statement / per Duplicated construction)
        Map<String, Integer> columnNameIndex = new TreeMap<>();
        for (int i = 0; i < columnNames.size(); i++) {
            columnNameIndex.put(columnNames.get(i), i);
        }

        long totalLookupOps = 0;
        for (int r = 0; r < numRows; r++) {
            for (int a = 0; a < colsAccessed; a++) {
                String target = "col_" + (a % totalCols);
                // O(log N) TreeMap lookup
                totalLookupOps++;
                columnNameIndex.get(target); // O(log totalCols)
            }
        }
        return totalLookupOps;
    }

    // -----------------------------------------------------------------------
    // diesel-0003: MySQL row — named column lookup
    // Same linear scan pattern, same fix.
    // -----------------------------------------------------------------------

    /**
     * Defective: metadata.fields().iter().enumerate().find() — O(N_cols) per access.
     */
    public static long mysqlRowDefective(int totalCols, int colsAccessed, int numRows) {
        return sqliteRowDefective(totalCols, colsAccessed, numRows);
    }

    /**
     * Fixed: build BTreeMap once per MysqlRow construction.
     */
    public static long mysqlRowFixed(int totalCols, int colsAccessed, int numRows) {
        return sqliteRowFixed(totalCols, colsAccessed, numRows);
    }

    // -----------------------------------------------------------------------
    // Complexity ratio helper
    // -----------------------------------------------------------------------

    /** Returns the ratio defective/fixed scan steps for a given configuration. */
    public static double complexityRatio(int totalCols, int colsAccessed, int numRows) {
        long def = sqliteRowDefective(totalCols, colsAccessed, numRows);
        long fix = sqliteRowFixed(totalCols, colsAccessed, numRows);
        return (double) def / fix;
    }
}