import edu.stanford.nlp.ling.CoreAnnotations;
import edu.stanford.nlp.ling.CoreLabel;
import edu.stanford.nlp.pipeline.Annotation;
import edu.stanford.nlp.pipeline.StanfordCoreNLP;
import edu.stanford.nlp.util.CoreMap;
import java.io.BufferedInputStream;
import java.io.BufferedWriter;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.nio.file.Files;
import java.nio.file.Path;
import java.nio.file.Paths;
import java.util.Arrays;


import java.util.List;
import java.util.Properties;
import org.apache.commons.csv.CSVFormat;
import org.apache.commons.csv.CSVPrinter;
import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.parser.AutoDetectParser;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.Parser;
import org.apache.tika.sax.BodyContentHandler;
import org.xml.sax.SAXException;

public class runner {

        private static final String SAMPLE_CSV_FILE = "./sample.csv";

        public static BodyContentHandler process() throws Exception {
     FileInputStream mypdfstream = new FileInputStream(new File("C:\\Users\\jonat\\Documents\\resume\\Dave.docx"));
         BodyContentHandler handler = new BodyContentHandler();
         AutoDetectParser parser = new AutoDetectParser();
        Metadata metadata = new Metadata();
        ParseContext context = new ParseContext();
        parser.parse(mypdfstream,handler,metadata,context);
        return handler;
        }


    public static void main(String[] args) throws Exception {

        // creates a StanfordCoreNLP object, with POS tagging, lemmatization, NER, parsing, and coreference resolution
        Properties props = new Properties();
        props.setProperty("annotators", "tokenize, ssplit, pos, lemma, ner, parse, dcoref");
        StanfordCoreNLP pipeline = new StanfordCoreNLP(props);

        // read some text in the text variable
        String text = process().toString();
        //"What is the Weather in Bangalore right now?";

        // create an empty Annotation just with the given text
        Annotation document = new Annotation(text);

        // run all Annotators on this text
        pipeline.annotate(document);

        List<CoreMap> sentences = document.get(CoreAnnotations.SentencesAnnotation.class);

        for (CoreMap sentence : sentences) {
            // traversing the words in the current sentence
            // a CoreLabel is a CoreMap with additional token-specific methods
            for (CoreLabel token : sentence.get(CoreAnnotations.TokensAnnotation.class)) {
                // this is the text of the token
                String word = token.get(CoreAnnotations.TextAnnotation.class);
                // this is the POS tag of the token
                String pos = token.get(CoreAnnotations.PartOfSpeechAnnotation.class);
                // this is the NER label of the token
                String ne = token.get(CoreAnnotations.NamedEntityTagAnnotation.class);




            BufferedWriter writer = Files.newBufferedWriter(Paths.get(SAMPLE_CSV_FILE));

            CSVPrinter csvPrinter = new CSVPrinter(writer, CSVFormat.DEFAULT
                    .withHeader("Print"));
        {
            csvPrinter.printRecord(String.format("Print: word: [%s] pos: [%s] ne: [%s]", word, pos, ne));

            csvPrinter.flush();

            //check https://www.programcreek.com/java-api-examples/?class=org.apache.commons.csv.CSVPrinter&method=printRecord
        }


            }
        }
    }
}