D-Net

package eu.dnetlib.data.collector.plugins.schemaorg;

import org.json.JSONArray;

import org.json.JSONObject;

import org.w3c.dom.Document;

import org.w3c.dom.NodeList;

import org.xml.sax.InputSource;

import javax.xml.parsers.DocumentBuilder;

import javax.xml.parsers.DocumentBuilderFactory;

import javax.xml.xpath.XPath;

import javax.xml.xpath.XPathConstants;

import javax.xml.xpath.XPathExpression;

import javax.xml.xpath.XPathFactory;

import java.io.File;

import java.io.FileInputStream;

import java.io.FileOutputStream;

import java.io.StringReader;

import java.nio.charset.Charset;

import java.nio.charset.UnsupportedCharsetException;

import java.util.ArrayList;

import java.util.EnumSet;

import java.util.HashMap;

import java.util.List;

import java.util.zip.GZIPInputStream;

public class Utils {

	public static List<String> collectAsStrings(String xml, String xpath) throws Exception{

		DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();

		DocumentBuilder builder = factory.newDocumentBuilder();

		Document doc = builder.parse(new InputSource(new StringReader(xml)));

		return Utils.collectAsStrings(doc, xpath);

	}

	public static List<String> collectAsStrings(File file, String xpath) throws Exception{

		DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();

		DocumentBuilder builder = factory.newDocumentBuilder();

		Document doc = builder.parse(file);

		return Utils.collectAsStrings(doc, xpath);

	}

	public static List<String> collectAsStrings(Document doc, String xpath) throws Exception{

		XPathFactory xPathfactory = XPathFactory.newInstance();

		XPath path = xPathfactory.newXPath();

		XPathExpression expr = path.compile(xpath);

		NodeList nodes = (NodeList) expr.evaluate(doc, XPathConstants.NODESET);

		List<String> values = new ArrayList<>();

		for (int i = 0; i < nodes.getLength(); i++)

			values.add(nodes.item(i).getNodeValue());

		return values;

	}

	public static void decompressGZipTo(File input, File output) throws Exception {

		try (GZIPInputStream in = new GZIPInputStream(new FileInputStream(input))){

			try (FileOutputStream out = new FileOutputStream(output)){

				byte[] buffer = new byte[1024];

				int len;

				while((len = in.read(buffer)) != -1){

					out.write(buffer, 0, len);

				}

			}

		}

	}

	public static String getAsString(HashMap<String,String> map, String key, String defaultValue)

	{

		String value = map.get(key);

		if(value == null) return defaultValue;

		return value;

	}

	public static List<String> getAsStringCsv(HashMap<String,String> map, String key, List<String> defaultValue)

	{

		String value = map.get(key);

		if(value == null) return defaultValue;

		String[] splits = value.split(",");

		List<String> curated = new ArrayList<>();

		for(String item : splits){

			if(item == null || item.trim().length() == 0) continue;

			curated.add(item.trim());

		}

		return curated;

	}

	public static int getAsInt(HashMap<String,String> map, String key, int defaultValue)

	{

		String value = map.get(key);

		if(value == null) return defaultValue;

		try {

			return Integer.parseInt(value);

		} catch (NumberFormatException e) {

			return defaultValue;

		}

	}

	public static long getAsLong(HashMap<String,String> map, String key, long defaultValue)

	{

		String value = map.get(key);

		if(value == null) return defaultValue;

		try {

			return Long.parseLong(value);

		} catch (NumberFormatException e) {

			return defaultValue;

		}

	}

	public static <E extends Enum<E>> E getAsEnum(HashMap<String,String> map, String key, E defaultValue, Class<E> clazz) {

		//EnumSet<E> values = EnumSet.allOf(defaultValue.getClass());

		EnumSet<E> values = EnumSet.allOf(clazz);

		String value = map.get(key);

		if (value == null) return defaultValue;

		for(E val : values){

			if(!val.name().equalsIgnoreCase(value)) continue;

			return val;

		}

		return defaultValue;

	}

	public static Boolean getAsBoolean(HashMap<String,String> map, String key, Boolean defaultValue) {

		String value = map.get(key);

		if (value == null) return defaultValue;

		return Boolean.parseBoolean(value);

	}

	public static Charset getAsCharset(HashMap<String,String> map, String key, Charset defaultValue)

	{

		String value = map.get(key);

		if(value == null) return defaultValue;

		try {

			return Charset.forName(value);

		} catch (UnsupportedCharsetException e) {

			return defaultValue;

		}

	}

}