A simple utility to verify the downloaded CIA Factbook file for the Huffman assignment.

FactbookValidator.java

import java.io.BufferedInputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.security.DigestInputStream;
import java.security.MessageDigest;
import java.security.NoSuchAlgorithmException;
import java.util.Arrays;

import javax.swing.JFileChooser;
import javax.swing.filechooser.FileNameExtensionFilter;

/**
 * A simple utility to validate that the 2008 CIA Factbook text file used for
 * the CS 314 Huffman Coding assignment was downloaded correctly without being
 * improperly transcoded.
 * 
 * License: GNU GPLv3 or later (https://www.gnu.org/licenses/gpl-3.0.en.html)
 * 
 * @author Andrew Smith ([email protected])
 */
public class FactbookValidator {
    /** A URL for the cumulative archive of Huffman files. */
    private static final String ARCHIVE_URL =
            "https://www.cs.utexas.edu/~scottm/cs314/javacode/A10_Huffman/A10_Huffman_All_Files.zip";

    private static final String REDOWNLOAD_REQUEST =
            "Please use only the version of the CIA Factbook provided in the cumulative Huffman archive: "
                + ARCHIVE_URL;

    /** The number of bytes in the correct CIA Factbook file. */
    private static final long FACTBOOK_FILE_SIZE = 9637228;

    /** The MD5 checksum of the correct CIA Factbook file. */
    private static final byte[] FACTBOOK_FILE_CHECKSUM = {
        -63, 60, 77, 5, -91, -125, 16, 93, 125, 20, 19, -72, 97, -111, 37, 96
    };

    public static void main(String[] args) throws IOException {
        // Request the Factbook file from the user.
        File factbook = getUserFile();
        if (factbook == null) {
            System.err.println("You must select a CIA Factbook file to validate.");
            System.exit(-1);
        }

        // Ensure that the file does not contain any carriage returns and compute its MD5 checksum.
        byte[] checksum = computeChecksum(factbook);
        if (checksum == null) {
            System.err.println("Your CIA Factbook file contains Windows-style (CRLF) line endings.  "
                    + REDOWNLOAD_REQUEST);
            System.exit(-1);
        }

        // Ensure that the file is the correct size.
        long factbookSize = factbook.length();
        if (factbookSize != FACTBOOK_FILE_SIZE) {
            System.err.printf("Your CIA Factbook file contains the wrong number of bytes (expected %d, actual %d), "
                    + "indicating that it was truncated when it was downloaded.  " + REDOWNLOAD_REQUEST + "\n",
                    FACTBOOK_FILE_SIZE, factbookSize);
            System.exit(-1);
        }

        // Ensure that the checksum of the factbook file is correct.
        if (!Arrays.equals(checksum, FACTBOOK_FILE_CHECKSUM)) {
            System.err.println("The checksum of your CIA Factbook file is incorrect, indicating that the file could "
                    + "have been mangled while you were downloading it.  " + REDOWNLOAD_REQUEST);
            System.exit(-1);
        }

        System.out.println("Your CIA Factbook file is correct!");
    }

    /**
     * Request a text file from the user using a graphical dialog.
     *
     * @return A handle to the file selected by the user, or null if the user
     *         closed the dialog without selecting a file.
     */
    private static File getUserFile() {
        JFileChooser fc = new JFileChooser();
        fc.setDialogTitle("Select your CIA Factbook text file");
        // Only allow the user to select files with the .txt extension.
        fc.setFileFilter(new FileNameExtensionFilter("Text files", "txt"));

        if (fc.showOpenDialog(null) == JFileChooser.APPROVE_OPTION) {
            return fc.getSelectedFile();
        } else {
            return null;
        }
    }

    /**
     * Compute the MD5 checksum for the specified CIA Factbook file, provided
     * that the file does not contain carriage returns.
     * 
     * @param factbook The CIA Factbook file for which to generate a checksum.
     * @return An array of bytes constituting the MD5sum of the factbook, or
     *         null if the file contained any carriage returns.
     */
    private static byte[] computeChecksum(File factbook) throws IOException {
        // Attempt to instantiate an MD5 checksum generator.
        MessageDigest md5;
        try {
            md5 = MessageDigest.getInstance("MD5");
        } catch (NoSuchAlgorithmException e) {
            System.err.println("Unable to instantiate an MD5 checksum generator.");
            return null;
        }

        BufferedInputStream is = new BufferedInputStream(new FileInputStream(factbook));
        DigestInputStream digestStream = new DigestInputStream(is, md5);

        // Read the file's contents using the MD5 digest input stream.
        int read;
        boolean foundCarriageReturn = false;
        while ((read = digestStream.read()) != -1 && !foundCarriageReturn) {
            foundCarriageReturn = read == '\r';
        }

        digestStream.close();
        // If a carriage return was found, we could not compute the checksum.
        return foundCarriageReturn ? null : md5.digest();
    }
}