* either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.suggest.request;

/**
 * The Response interface serves as a marker interface for all response types
 * in the suggestion system. Implementations of this interface are used to
 * encapsulate the results of various operations and queries within the system.
 *

 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.suggest.normalizer;

import java.util.ArrayList;
import java.util.List;

/**
 * The NormalizerChain class implements the Normalizer interface and allows chaining multiple normalizers together.
 * It applies each normalizer in the order they were added to the chain.
 *

     * which pages you deem most important for the crawlers.
     *
     * The default priority of a page is 0.5.
     *
     * Please note that the priority you assign to a page is not likely to
     * influence the position of your URLs in a search engine's result pages.
     * Search engines may use this information when selecting between URLs on
     * the same site, so you can use this tag to increase the likelihood that

/*
 * Copyright 2012-2025 CodeLibs Project and the Others.
 *
 * Licensed under the Apache License, Version 2.0 (the "License");
 * you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,

/*
 * Copyright 2012-2025 CodeLibs Project and the Others.
 *
 * Licensed under the Apache License, Version 2.0 (the "License");
 * you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,

    }

    /**
     * Adds an extractor to the factory for the specified key.
     * If an extractor already exists for the key, the new extractor is added to the array of extractors,
     * and the array is sorted by weight in descending order.
     * If no extractor exists for the key, a new array containing the extractor is created and associated with the key.
     *

/*
 * Copyright 2012-2025 CodeLibs Project and the Others.
 *
 * Licensed under the Apache License, Version 2.0 (the "License");
 * you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,

    }

    /**
     * Retrieves a single document from the OpenSearch index by session ID and URL.
     *
     * @param <T> The type of the object to retrieve.
     * @param clazz The class of the object to retrieve.
     * @param sessionId The session ID of the document.
     * @param url The URL of the document.
     * @return The retrieved object, or null if not found.

   * General magic matches which could trigger a false-positive need
     a low one
   * The priority for containers normally need to be higher than for
     the things they contain, so they don't accidently get detected
     as what's in them
   * For logic too complex to be expressed in a magic match, do the best
     you can here, then provide a Custom Detector for the rest
-->
<mime-info xmlns:tika="https://tika.apache.org/">

/**
 * A response processor implementation that handles sitemaps.
 * It parses the response body as a SitemapSet, extracts URLs from the sitemaps,
 * and adds them as child URLs to be crawled.
 *
 * <p>
 * This class uses a {@link SitemapsHelper} to parse the sitemap XML or text.
 * It then iterates through the sitemaps in the SitemapSet, extracts the URL
 * from each sitemap, and creates a new {@link RequestData} object for each URL.