D-Net

package eu.dnetlib.msro.workers.aggregation.cleaner;

import java.io.StringReader;

import java.util.Set;

import org.dom4j.Document;

import org.dom4j.Element;

import org.dom4j.io.SAXReader;

import org.springframework.beans.factory.annotation.Autowired;

import org.springframework.stereotype.Component;

import com.google.common.base.Splitter;

import com.google.common.collect.Sets;

import eu.dnetlib.clients.is.InformationServiceClient;

import eu.dnetlib.msro.exceptions.MSROException;

@Component

public class CleaningRuleFactory {

	@Autowired

	private InformationServiceClient isClient;

	public CleaningRule obtainCleaningRule(final String ruleId) throws MSROException {

		try {

			final String prof =

					isClient.findOne("/RESOURCE_PROFILE[.//RESOURCE_IDENTIFIER/@value='" + ruleId + "' or .//CLEANER_NAME='" + ruleId + "']//CONFIGURATION");

			final SAXReader reader = new SAXReader();

			final Document doc = reader.read(new StringReader(prof));

			final CleaningRule rule = new CleaningRule();

			for (final Object o : doc.selectNodes("//RULE")) {

				final Element node = (Element) o;

				final String xpath = node.valueOf("@xpath");

				final String vocabularies = node.valueOf("@vocabularies");

				final String groovyRule = node.valueOf("@groovy");

				final String strict = node.valueOf("@strict");

				final XPATHCleaningRule xpathRule;

				if ((vocabularies != null) && (vocabularies.length() > 0)) {

					final Set<String> list = Sets.newHashSet(Splitter.on(",").omitEmptyStrings().trimResults().split(vocabularies));

					xpathRule = new VocabularyRule(list, isClient);

				} else {

					xpathRule = new GroovyRule(groovyRule);

				}

				xpathRule.setXpath(xpath);

				xpathRule.setStrict("true".equals(strict));

				rule.getXpathRules().add(xpathRule);

			}

			return rule;

		} catch (final Exception e) {

			throw new MSROException("Error obtaing cleaner rule " + ruleId, e);

		}

	}

}