• Home
• uk.ac.shef.dcs
• sti-main
• 1.0alpha
• source code
• TableParserHTML.java

×

Project download

Many resources are needed to download a project. Please understand that we have to compensate our server costs. Thank you in advance.
Project price only 1 $

You can buy this project and download/modify it how often you want.

uk.ac.shef.dcs.sti.parser.table.TableParserHTML Maven / Gradle / Ivy

package uk.ac.shef.dcs.sti.parser.table;

import org.apache.any23.extractor.html.DomUtils;
import org.apache.any23.extractor.html.TagSoupParser;
import org.apache.commons.io.FileUtils;
import org.w3c.dom.Document;
import org.w3c.dom.Node;
import uk.ac.shef.dcs.sti.STIException;
import uk.ac.shef.dcs.sti.core.model.TContext;
import uk.ac.shef.dcs.sti.core.model.Table;
import uk.ac.shef.dcs.sti.parser.table.hodetector.TableHODetector;
import uk.ac.shef.dcs.sti.parser.table.normalizer.TableNormalizer;
import uk.ac.shef.dcs.sti.parser.table.creator.TableObjCreator;
import uk.ac.shef.dcs.sti.parser.table.validator.TableValidator;

import java.io.ByteArrayInputStream;
import java.io.File;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;

/**
 * Author: Ziqi Zhang ([email protected])
 * Date: 03/10/12
 * Time: 12:07
 */
public class TableParserHTML extends TableParser {


    public TableParserHTML(TableNormalizer normalizer, TableHODetector detector, TableObjCreator creator, TableValidator... validators) {
        super(normalizer, detector, creator,validators);
    }


    @Override
    public List extract(String inFile, String sourceId) throws STIException {
        String input;
        try {
            input = FileUtils.readFileToString(new File(inFile));
        } catch (IOException e) {
            throw new STIException(e);
        }

        List rs = new ArrayList<>();
        parser = new TagSoupParser(new ByteArrayInputStream(input.getBytes()), sourceId,"UTF-8");
        Document doc = null; try {
            doc = parser.getDOM();
        } catch (IOException e) {
            return rs;
        }

        List tables = DomUtils.findAll(doc, "//TABLE");

        int tableCount=0;
        for(Node n: tables){
            tableCount++;
            //todo: extract contexts for table
            TContext[] contexts = new TContext[0];
            Table table =extractTable(n, String.valueOf(tableCount),
                    sourceId,contexts);
            if(table!=null)
                rs.add(table);
        }
        return rs;
    }


}
    

    

    

            
    

            

    
    






    
© 2015 - 2024 Weber Informatics LLC | Privacy Policy