package org.apache.nutch.parse.java;

import japa.parser.ast.Comment;
import japa.parser.ast.CompilationUnit;
import japa.parser.ast.ImportDeclaration;
import japa.parser.ast.PackageDeclaration;
import japa.parser.ast.body.TypeDeclaration;
import japa.parser.JavaParser;

import java.io.*;
import java.util.List;

import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;

import org.apache.hadoop.conf.Configuration;
import org.apache.nutch.metadata.Metadata;
import org.apache.nutch.parse.*;
import org.apache.nutch.protocol.Content;
import org.apache.nutch.util.LogUtil;
import org.apache.nutch.util.NutchConfiguration;


public class JavaCodeParser implements Parser{
	public static final Log LOG = LogFactory.getLog(JavaCodeParser.class);
	  
	private Configuration conf;
	
	public JavaCodeParser () {
	}
	
	public Configuration getConf() {
		return conf;
	}

	public void setConf(Configuration conf) {
		this.conf = conf;
	}
	
	public ParseResult getParse(Content content) {	
		PackageDeclaration pakage;
	    List<ImportDeclaration> imports;
	    List<TypeDeclaration> types;
	    List<Comment> comments;
	
        CompilationUnit cu;
       
        try {
            byte[] raw = content.getContent();
            
            //parse the inputstream and get a CompilationUnit instance..
            cu = JavaParser.parse(new ByteArrayInputStream(raw));
            
            //get all code data
            pakage = cu.getPackage();
            imports = cu.getImports();
            types = cu.getTypes();
            comments = cu.getComments();

        } catch (Exception e) { // run time exception
            if (LOG.isWarnEnabled()) {
              e.printStackTrace(LogUtil.getWarnStream(LOG));
              LOG.warn("nutch:parse-java:JavaCodeParser Exception: " + e.getMessage());
            }
            return new ParseStatus(ParseStatus.FAILED,
                    "Can't be handled as java document. " + e).getEmptyParseResult(content.getUrl(), getConf());
        }
        
        StringBuffer indexText = new StringBuffer();
        Metadata metadata = content.getMetadata();
        
        indexText.append(pakage.getName());
        for (int i = 0; i < imports.size(); i++) {
        	ImportDeclaration id = imports.get(i);
            indexText.append(id.getName());
            indexText.append(" ");
            metadata.add("import", id.getName().toString());
        }
        for (int i = 0; i < types.size(); i++) {
        	TypeDeclaration td = types.get(i);
            indexText.append(td.getName());
            indexText.append(" ");
            metadata.add("type", td.getName().toString());
        }
        for (int i = 0; i < comments.size(); i++) {
        	Comment c = comments.get(i);
            indexText.append(c.getContent().replaceAll("[/*\n]", ""));
            indexText.append(" ");
            metadata.add("comment", c.getContent().replaceAll("[/*\n]", ""));
        }

        ParseData parseData = new ParseData(ParseStatus.STATUS_SUCCESS,"",
                OutlinkExtractor.getOutlinks(indexText.toString(), getConf()), content.getMetadata());
        
        return ParseResult.createParseResult(content.getUrl(), new ParseImpl(indexText.toString(), parseData));
	}

}