uses: actions/checkout@v5

      - name: Check links
        uses: lycheeverse/lychee-action@v2.6.1
        with:
          # excluded:
          # - notes.md and notes-templates.md - because they are a part of user guide
          # - Kotlin's Module.md - because it's a part of the Kotlin DSL docs
          args: >
            --no-progress --offline '**/*.md' --include-fragments

/**
 * NullResponseProcessor is a class that implements the ResponseProcessor interface.
 * It provides a no-op implementation for processing response data.
 * This class can be used when you want to skip the response processing step in a crawler.
 *
 * @author kuma
 */
public class NullResponseProcessor implements ResponseProcessor {

    /**
     * Creates a new NullResponseProcessor instance.

        } catch (final Exception e) {
            throw new ExtractException(e);
        }
    }

    /**
     * Returns the encoding used for text extraction.
     * @return the encoding
     */
    public String getEncoding() {
        return encoding;
    }

    /**
     * Sets the encoding.
     * @param encoding The encoding to set.

 */
public interface Extractor {

    /**
     * Extracts text data from the given input stream.
     *
     * @param in the input stream to extract text from
     * @param params a map of parameters to be used during extraction
     * @return an ExtractData object containing the extracted text
     */
    ExtractData getText(InputStream in, Map<String, String> params);

    /**
     * Returns the weight of the extractor.

 * </p>
 *
 * <p>
 * The {@code loc} attribute specifies the URL of the Sitemap, while the {@code lastmod} attribute
 * indicates the last time the Sitemap file was modified.  The {@code lastmod} attribute is used by crawlers
 * to incrementally fetch sitemaps that have been updated since a certain date.
 * </p>
 *
 * <p>
 * This class also provides implementations for {@code equals}, {@code hashCode}, and {@code toString} methods

# limitations under the License.
# ==============================================================================
#
# Changes the behavior in pycpp.sh from "run all tests" to "verify that all
# tests can compile." Used in some CI jobs (macOS and Linux Arm64) where test
# execution is too expensive.
TFCI_PYCPP_SWAP_TO_BUILD_ENABLE=1

     */
    public FilenameExtractor() {
        // Default constructor
    }

    /**
     * Extracts the filename from the parameters.
     * @param in The input stream (not used).
     * @param params The parameters, expected to contain ExtractData.RESOURCE_NAME_KEY.
     * @return An ExtractData object containing the filename as content.
     */
    @Override

#     src = "build_cleaner_spec.textproto",
# )
#
# exports_files(srcs = ["METADATA"])
# copybara:uncomment_end

licenses(["notice"])

exports_files([
    "LICENSE",
    # The leakr files are used by //third_party/cloud_tpu and
    # //third_party/tensorboard/google:copybara_config_test.
    "leakr_badwords.dic",
    "leakr_badfiles.dic",
    "leakr_file_type_recipe.ftrcp",
])

 * </ul>
 *
 * <p>Dependencies:</p>
 * <ul>
 *   <li>{@code ArraySettings} - Used to manage the array settings for elevate words.</li>
 *   <li>{@code SuggestSettings} - The suggestion settings.</li>
 *   <li>{@code Client} - The client used for accessing the settings.</li>
 * </ul>
 *
 * <p>Logging:</p>
 * <ul>

 * </a></li>
 * </ul>
 *
 * @author bowez
 * @author shinsuke
 *
 */
public class RobotsTxtHelper {

    /** Pattern for parsing user-agent records. */
    protected static final Pattern USER_AGENT_RECORD =
            Pattern.compile("^user-agent:\\s*([^\\t\\n\\x0B\\f\\r]+)\\s*$", Pattern.CASE_INSENSITIVE);

    /** Pattern for parsing disallow records. */