User-agent: GoodBot
Disallow: /admin/
InvalidDirective: some-value
unknown-field: test
Disallow /missing-colon
Disallow:    # empty value (should be treated as allowing all)
Allow: /public/
Crawl-delay: invalid-number
Crawl-delay: -10
Crawl-delay: 5.5
Crawl-delay:
Allow:    # empty value

# Case 3: Multiple colons in directive
User-agent: MultiColonBot
Disallow: http://example.com:8080/path
Allow: /path:with:colons

User-agent: FessCrawler
Disallow:           # allows all 

User-agent: BruteBot
Disallow: /
Allow: /foo/bar/
Crawl-delay: 1314000

# welcome!
User-agent: Googlebot
Crawl-delay: 1

User-agent: *
Disallow: /private/
Disallow: /help        # disallows /help.html, /help/index.html, etc.
Allow: /help/faq.html
Crawl-delay: 3

User-agent: Crawler
Disallow: /aaa

User-agent: Crawler/1.0
Disallow: /bbb

  ~ See the License for the specific language governing permissions and
  ~ limitations under the License.
  -->
<!DOCTYPE module PUBLIC
        "-//Puppy Crawl//DTD Check Configuration 1.2//EN"
        "http://www.puppycrawl.com/dtds/configuration_1_2.dtd">
<module name="Checker">
    <module name="SuppressionFilter">
        <property name="file" value="${config_loc}/suppressions.xml"/>

    @Size(max = 200)
    public String name;

    /** The description of the file configuration (maximum 1000 characters). */
    @Size(max = 1000)
    public String description;

    /** The file paths to crawl (required, must be valid file URIs). */
    @Required
    @UriType(protocolType = ProtocolType.FILE)
    @CustomSize(maxKey = "form.admin.max.input.size")
    public String paths;

     * command. Even though search engine crawlers may consider this information
     * when making decisions, they may crawl pages marked "hourly" less
     * frequently than that, and they may crawl pages marked "yearly" more
     * frequently than that. Crawlers may periodically crawl pages marked
     * "never" so that they can handle unexpected changes to those pages.
     */
    private String changefreq;

    /**

 * This form extends CreateForm to include fields necessary for updating existing data config entries,
 * including tracking information for optimistic locking and audit trails.
 * Data configs define how to crawl and extract data from databases, CSV files, and other data sources.
 *
 */
public class EditForm extends CreateForm {

    /**
     * Creates a new EditForm instance.
     */
    public EditForm() {

    /**
     * Default constructor.
     */
    public SearchBody() {
        super();
    }

    /** Name of the web crawling configuration */
    public String name;

    /** URLs to crawl */
    public String urls;

    /** Description of the web crawling configuration */
    public String description;

<div class="wrapper">
    <jsp:include page="/WEB-INF/view/common/admin/header.jsp"></jsp:include>
    <jsp:include page="/WEB-INF/view/common/admin/sidebar.jsp">
        <jsp:param name="menuCategoryType" value="crawl"/>
        <jsp:param name="menuType" value="relatedQuery"/>
    </jsp:include>
    <main class="content-wrapper">
        <div class="content-header">
            <div class="container-fluid">

 * This form extends CreateForm to include fields necessary for updating existing web config entries,
 * including tracking information for optimistic locking and audit trails.
 * Web configs define how to crawl and index web sites and web applications.
 *
 */
public class EditForm extends CreateForm {

    /**
     * Creates a new EditForm instance.
     */
    public EditForm() {
        super();
    }

 * This form extends CreateForm to include fields necessary for updating existing file config entries,
 * including tracking information for optimistic locking and audit trails.
 * File configs define how to crawl and index files from local file systems, SMB shares, and FTP servers.
 *
 */
public class EditForm extends CreateForm {

    /**
     * Creates a new EditForm instance.
     */
    public EditForm() {