/**
 * <p>
 * {@link ESSourceReader} reads documents from Elasticsearch using the scroll API.
 * It implements the {@link DocumentReader} interface to provide a way to iterate over documents
 * in a large index without loading all of them into memory at once.
 * </p>
 *
 * <p>
 * The reader supports limiting the number of documents read based on a percentage of the total documents

        /**
         * Constructor.
         * @param reader The reader.
         */
        public TextNormalizeContext(final Reader reader) {
            this.reader = reader;
        }

        /**
         * Executes the text processing operation on the provided reader.
         *
         * This method reads characters from the reader and processes them according to the following rules:

        }
    }

    /**
     * Processes allowed SIDs (Security Identifiers) and adds them to the SID set.
     * If the SID is a group, it recursively processes all group members.
     *
     * @param file the SMB1 file
     * @param sid the SID to process
     * @param sidSet the set of SIDs to add to
     */
    protected void processAllowedSIDs(final SmbFile file, final SID sid, final Set<SID> sidSet) {

/*
 * 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,

        }
    }

    /**
     * Processes allowed SIDs (Security Identifiers) and adds them to the SID set.
     * If the SID is a group, it recursively processes all group members.
     *
     * @param file the SMB file
     * @param sid the SID to process
     * @param sidSet the set of SIDs to add to
     */
    protected void processAllowedSIDs(final SmbFile file, final SID sid, final Set<SID> sidSet) {

    }

    /**
     * Gets the appropriate crawler client for the given URL.
     * @param url The URL to get a client for.
     * @return The crawler client.
     */
    protected CrawlerClient getClient(final String url) {
        return clientFactory.getClient(url);
    }

    /**
     * Checks if the content has been updated since the last crawl.
     * @param client The crawler client.

    }

    /**
     * Gets the character set for the given file.
     *
     * @param file the file to get the character set for
     * @return the character set
     */
    protected String getCharSet(final File file) {
        return charset;
    }

    /**
     * Gets the character encoding used for files.
     *
     * @return the character encoding
     */

    /**
     * Adds an attribute to the factory.
     * @param name The name of the attribute.
     * @param value The value of the attribute.
     */
    public void addAttribute(final String name, final Object value) {
        attributeMap.put(name, value);
    }

    /**
     * Adds a feature to the factory.
     * @param key The key of the feature.
     * @param value The value of the feature.
     */

    }

    /**
     * Returns the current session ID.
     * @return The session ID.
     */
    public String getSessionId() {
        return crawlerContext.sessionId;
    }

    /**
     * Sets the session ID.
     * If the new session ID is different from the current one, it updates the session ID in the URL queue service.
     * @param sessionId The new session ID.
     */