statoolinfosweb/src/fr/devinsy/statoolinfos/core/CrawlCache.java

/*
 * Copyright (C) 2020 Christian Pierre MOMON <christian@momon.org>
 * 
 * This file is part of StatoolInfos, simple service statistics tool.
 * 
 * StatoolInfos is free software: you can redistribute it and/or modify
 * it under the terms of the GNU Affero General Public License as
 * published by the Free Software Foundation, either version 3 of the
 * License, or (at your option) any later version.
 * 
 * StatoolInfos is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU Affero General Public License for more details.
 * 
 * You should have received a copy of the GNU Affero General Public License
 * along with StatoolInfos.  If not, see <http://www.gnu.org/licenses/>.
 */
package fr.devinsy.statoolinfos.core;

import java.io.File;
import java.io.IOException;

import org.apache.commons.codec.digest.DigestUtils;
import org.apache.commons.lang3.StringUtils;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

import fr.devinsy.statoolinfos.properties.PathPropertyList;
import fr.devinsy.statoolinfos.properties.PathPropertyUtils;

/**
 * The Class CrawlCache.
 */
public class CrawlCache
{
    private static Logger logger = LoggerFactory.getLogger(CrawlCache.class);

    private File directory;

    /**
     * Instantiates a new crawl cache.
     *
     * @param directory
     *            the directory
     * @throws StatoolInfosException
     *             the statool infos exception
     */
    public CrawlCache(final File directory) throws StatoolInfosException
    {
        if (directory == null)
        {
            throw new IllegalArgumentException("Null parameter.");
        }
        else if (StringUtils.isBlank(directory.getName()))
        {
            throw new IllegalArgumentException("Blank directory.");
        }
        else if (!directory.exists())
        {
            throw new IllegalArgumentException("Directory does not exist.");
        }
        else
        {
            this.directory = directory;
        }
    }

    private File buildFile(final String url, final String additionalName)
    {
        File result;

        result = new File(this.directory, DigestUtils.md5Hex(url) + additionalName);

        // result = new File(this.directory, DigestUtils.sha1Hex(url));
        // String normalizeUrl = StringUtils.removeAll(url,
        // "^https*://").replace('/', '+');
        // result = new File(this.directory, normalizeUrl);

        //
        return result;
    }

    /**
     * Clear file in cache. Only files ending with ".property" are deleted.
     */
    public void clear()
    {
        for (File file : this.directory.listFiles())
        {
            if ((file.isFile()) && (file.getName().endsWith(".properties")))
            {
                logger.info("Deleting " + file.getName());
                file.delete();
            }
        }
    }

    /**
     * Load.
     *
     * @param url
     *            the url
     * @return the path property list
     * @throws IOException
     *             Signals that an I/O exception has occurred.
     */
    public PathPropertyList load(final String url) throws IOException
    {
        PathPropertyList result;

        File file = buildFile(url, ".properties");

        result = PathPropertyUtils.load(file);

        //
        return result;
    }

    /**
     * Store.
     *
     * @param url
     *            the url
     * @param properties
     *            the properties
     * @return the file
     * @throws IOException
     *             Signals that an I/O exception has occurred.
     */
    public File store(final String url, final PathPropertyList properties) throws IOException
    {
        File result;

        if (StringUtils.startsWith(url, "http"))
        {
            result = buildFile(url, ".properties");

            PathPropertyUtils.save(result, properties);
        }
        else
        {
            result = null;
        }

        //
        return result;
    }
}