JsonTransformer.java

package io.monokkel.core;

import com.google.common.collect.Lists;
import com.google.common.collect.Sets;
import io.monokkel.core.api.ResponseParser;
import io.monokkel.domain.PageData;
import io.monokkel.exceptions.ParseException;
import org.apache.commons.lang.StringUtils;
import org.json.simple.JSONObject;
import org.json.simple.parser.ContainerFactory;
import org.json.simple.parser.JSONParser;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

import java.util.*;
import java.util.stream.Collectors;

import static io.monokkel.core.utils.ParserUtils.doesTheListHaveHeader;
import static java.lang.String.format;

/**
 * Created by Tarjei on 25/06/14.
 * <p/>
 * This class is a JSON parser that receives a json string and returns extracted content
 * based on a simple expression path. The returned extracted content is always wrapped as a json object.
 * The path is added as a array in the constructor.
 * <p/>
 * A few examples (json is unescaped):
 * <p/>
 * ===== Example 1 =====
 * <p/>
 * String json = "{
 *      "data": {
 *               "field": "This is a field"
 *              },
 *      "list":[
 *                  {
 *                      "element": "element"
 *                  }
 *              ]
 *       }";
 * <p/>
 * ArrayList<String> path = new ArrayList<String>();
 * path.add("data");
 * path.add("field");
 * <p/>
 * JsonTransformer jsonParser = new JsonTransformer(path,..);
 * ParseOutput parseOutput = jsonParser.parse("http://url",json,1L);
 * parseOutput.getExtractedContent(); // Returns the string {"field":"This is a field"}
 * <p/>
 * ===== Example 2 =====
 * <p/>
 * ArrayList<String> path = new ArrayList<String>();
 * path.add("list");
 * path.add("0"); // Index of the list
 * <p/>
 * JsonTransformer jsonParser = new JsonTransformer(path,..);
 * ParseOutput parseOutput = jsonParser.parse("http://url",json,1L);
 * parseOutput.getExtractedContent(); // Returns the string "{ element: "element" }"
 * <p/>
 * ===== Example 3 =====
 * <p/>
 * ArrayList<String> path = new ArrayList<String>();
 * path.add("list");
 * <p/>
 * JsonTransformer jsonParser = new JsonTransformer(path,..);
 * ParseOutput parseOutput = jsonParser.parse("http://url",json,1L);
 * parseOutput.getExtractedContent(); // Returns the string "{"list":[{ element: "element" }]}"
 * <p/>
 * The second parameter in the constructor do the exact same but is intended to return urls to the crawler
 *
 */
public class JsonTransformer extends JsonSupport implements ResponseParser {

    private final Map<String, List<String>> fieldPathsToRetrieve;


    public JsonTransformer(final Map<String, List<String>> fieldsPathsToRetrieve, final List<String> fieldToFiendNextUrl) {
        super(fieldToFiendNextUrl);
        if (fieldsPathsToRetrieve.size() < 1) {
            throw new IllegalArgumentException("You need a json path longer than 1 hop");
        }

        this.fieldPathsToRetrieve = fieldsPathsToRetrieve;
    }

    @Override
    protected Map<String, Object> transformContent(final Map<String, Object> parse, final String url, final Long timeStamp) {
        return fieldPathsToRetrieve.entrySet().stream().collect(Collectors.toMap(Map.Entry::getKey, entry -> extractContent(parse, 0, url, entry.getValue(), true)));
    }



}