import java.io.Serializable;
import java.util.Arrays;
import java.util.HashSet;
import java.util.Set;

import org.apache.commons.validator.util.Flags;
import org.apache.oro.text.perl.Perl5Util;

/**
 * <p>Validates URLs.</p>
 * Behavour of validation is modified by passing in options:
 * <li>ALLOW_2_SLASHES - [FALSE]  Allows double '/' characters in the path
 * component.</li>
 * <li>NO_FRAGMENT- [FALSE]  By default fragments are allowed, if this option is
 * included then fragments are flagged as illegal.</li>
 * <li>ALLOW_ALL_SCHEMES - [FALSE] By default only http, https, and ftp are
 * considered valid schemes.  Enabling this option will let any scheme pass validation.</li>
 *
 * <p>Originally based in on php script by Debbie Dyer, validation.php v1.2b, Date: 03/07/02,
 * http://javascript.internet.com. However, this validation now bears little resemblance
 * to the php original.</p>
 * <pre>
 *   Example of usage:
 *   Construct a UrlValidator with valid schemes of "http", and "https".
 *
 *    String[] schemes = {"http","https"}.
 *    UrlValidator urlValidator = new UrlValidator(schemes);
 *    if (urlValidator.isValid("ftp://foo.bar.com/")) {
 *       System.out.println("url is valid");
 *    } else {
 *       System.out.println("url is invalid");
 *    }
 *
 *    prints "url is invalid"
 *   If instead the default constructor is used.
 *
 *    UrlValidator urlValidator = new UrlValidator();
 *    if (urlValidator.isValid("ftp://foo.bar.com/")) {
 *       System.out.println("url is valid");
 *    } else {
 *       System.out.println("url is invalid");
 *    }
 *
 *   prints out "url is valid"
 *  </pre>
 *
 * @see
 * <a href='http://www.ietf.org/rfc/rfc2396.txt' >
 *  Uniform Resource Identifiers (URI): Generic Syntax
 * </a>
 *
 * @version $Revision: 478334 $ $Date: 2006-11-22 21:31:54 +0000 (Wed, 22 Nov 2006) $
 * @since Validator 1.1
 */
public class UrlValidator implements Serializable {

    /**
     * Allows all validly formatted schemes to pass validation instead of 
     * supplying a set of valid schemes.
     */
    public static final int ALLOW_ALL_SCHEMES = 1 << 0;

    /**
     * Allow two slashes in the path component of the URL.
     */
    public static final int ALLOW_2_SLASHES = 1 << 1;

    /**
     * Enabling this options disallows any URL fragments.
     */
    public static final int NO_FRAGMENTS = 1 << 2;

    private static final String ALPHA_CHARS = "a-zA-Z";

    private static final String ALPHA_NUMERIC_CHARS = ALPHA_CHARS + "\\d";

    private static final String SPECIAL_CHARS = ";/@&=,.?:+$";

    private static final String VALID_CHARS = "[^\\s" + SPECIAL_CHARS + "]";

    private static final String SCHEME_CHARS = ALPHA_CHARS;

    // Drop numeric, and  "+-." for now
    private static final String AUTHORITY_CHARS = ALPHA_NUMERIC_CHARS + "\\-\\.";

    private static final String ATOM = VALID_CHARS + '+';

    /**
     * This expression derived/taken from the BNF for URI (RFC2396).
     */
    private static final String URL_PATTERN =
            "/^(([^:/?#]+):)?(//([^/?#]*))?([^?#]*)(\\?([^#]*))?(#(.*))?/";
    //                                                                      12            3  4          5       6   7        8 9

    /**
     * Schema/Protocol (ie. http:, ftp:, file:, etc).
     */
    private static final int PARSE_URL_SCHEME = 2;

    /**
     * Includes hostname/ip and port number.
     */
    private static final int PARSE_URL_AUTHORITY = 4;

    private static final int PARSE_URL_PATH = 5;

    private static final int PARSE_URL_QUERY = 7;

    private static final int PARSE_URL_FRAGMENT = 9;

    /**
     * Protocol (ie. http:, ftp:,https:).
     */
    private static final String SCHEME_PATTERN = "/^[" + SCHEME_CHARS + "]/";

    private static final String AUTHORITY_PATTERN =
            "/^([" + AUTHORITY_CHARS + "]*)(:\\d*)?(.*)?/";
    //                                                                            1                          2  3       4

    private static final int PARSE_AUTHORITY_HOST_IP = 1;

    private static final int PARSE_AUTHORITY_PORT = 2;

    /**
     * Should always be empty.
     */
    private static final int PARSE_AUTHORITY_EXTRA = 3;

    private static final String PATH_PATTERN = "/^(/[-\\w:@&?=+,.!/~*'%$_;]*)?$/";

    private static final String QUERY_PATTERN = "/^(.*)$/";

    private static final String LEGAL_ASCII_PATTERN = "/^[\\000-\\177]+$/";

    private static final String IP_V4_DOMAIN_PATTERN =
            "/^(\\d{1,3})[.](\\d{1,3})[.](\\d{1,3})[.](\\d{1,3})$/";

    private static final String DOMAIN_PATTERN =
            "/^" + ATOM + "(\\." + ATOM + ")*$/";

    private static final String PORT_PATTERN = "/^:(\\d{1,5})$/";

    private static final String ATOM_PATTERN = "/(" + ATOM + ")/";

    private static final String ALPHA_PATTERN = "/^[" + ALPHA_CHARS + "]/";

    /**
     * Holds the set of current validation options.
     */
    private Flags options = null;

    /**
     * The set of schemes that are allowed to be in a URL.
     */
    private Set allowedSchemes = new HashSet();

    /**
     * If no schemes are provided, default to this set.
     */
    protected String[] defaultSchemes = {"http", "https", "ftp"};

    /**
     * Create a UrlValidator with default properties.
     */
    public UrlValidator() {
        this(null);
    }

    /**
     * Behavior of validation is modified by passing in several strings options:
     * @param schemes Pass in one or more url schemes to consider valid, passing in
     *        a null will default to "http,https,ftp" being valid.
     *        If a non-null schemes is specified then all valid schemes must
     *        be specified. Setting the ALLOW_ALL_SCHEMES option will
     *        ignore the contents of schemes.
     */
    public UrlValidator(String[] schemes) {
        this(schemes, 0);
    }

    /**
     * Initialize a UrlValidator with the given validation options.
     * @param options The options should be set using the public constants declared in
     * this class.  To set multiple options you simply add them together.  For example,
     * ALLOW_2_SLASHES + NO_FRAGMENTS enables both of those options.
     */
    public UrlValidator(int options) {
        this(null, options);
    }

    /**
     * Behavour of validation is modified by passing in options:
     * @param schemes The set of valid schemes.
     * @param options The options should be set using the public constants declared in
     * this class.  To set multiple options you simply add them together.  For example,
     * ALLOW_2_SLASHES + NO_FRAGMENTS enables both of those options.
     */
    public UrlValidator(String[] schemes, int options) {
        this.options = new Flags(options);

        if (this.options.isOn(ALLOW_ALL_SCHEMES)) {
            return;
        }

        if (schemes == null) {
            schemes = this.defaultSchemes;
        }

        this.allowedSchemes.addAll(Arrays.asList(schemes));
    }