peoplemanager.java

这是一个matlab的java实现。里面有许多内容。请大家慢慢捉摸。

/* Copyright (C) 2003 Univ. of Massachusetts Amherst, Computer Science Dept.
   This file is part of "MALLET" (MAchine Learning for LanguagE Toolkit).
   http://www.cs.umass.edu/~mccallum/mallet
   This software is provided under the terms of the Common Public License,
   version 1.0, as published by http://www.opensource.org.  For further
   information, see the file `LICENSE' included with this distribution. */

/**  Manages the extraction and linkage of a set of people found in email.
 *   @author Aron Culotta <A HREF="mailto:[e-mail]">[e-mail]</A>
*/

package edu.umass.cs.mallet.projects.dex.types;

import edu.umass.cs.mallet.projects.dex.ie.*;
import edu.umass.cs.mallet.projects.dex.web.*;
import edu.umass.cs.mallet.base.util.MalletLogger;

import java.util.logging.*;
import java.util.*;
import java.io.*;

public class PeopleManager {
	private static Logger logger = MalletLogger.getLogger(PeopleManager.class.getName());
	
	People people;
	HashSet stopWords;
	String userName;
	File inputDir;
	File outputDir;
	File vcfFile;
	File htmlFile;
	
	protected PeopleManager () { }

	public PeopleManager (File inputDir, File outputDir, File stopListFile, String userName) {
		this.inputDir = inputDir;
		this.outputDir = outputDir;
		this.userName = userName;
		this.vcfFile = new File (userName + ".vcf");
		this.htmlFile = new File (userName + ".html");
		setStopWords (stopListFile);
		readPeopleFromDir (inputDir);		
	}

	public PeopleManager (File inputDir, File outputDir, File stopListFile, String userName,
												File personObjectFile, File vcfFile, File htmlFile) {
		this.inputDir = inputDir;
		this.outputDir = outputDir;
		this.userName = userName;
		this.vcfFile = vcfFile;
		this.htmlFile = htmlFile;
		setStopWords (stopListFile);
		if (personObjectFile != null) {
			System.err.println ("Reading people from file " + personObjectFile);
			people = People.read (personObjectFile);
		}
		else {
			System.out.println ("Reading people from " + inputDir);
			readPeopleFromDir (inputDir);
		}
	}

	public void readPeopleFromDir (File inputDir) {
		EmailPeopleExtractor epe = new EmailPeopleExtractor (inputDir, stopWords);
		people = epe.getPeople();
		logger.info ("Read " + people.size() + " people from email directory " + inputDir);		
	}
	
	public void setStopWords(File f) {
		stopWords = new HashSet ();
		try {
			BufferedReader reader = new BufferedReader (new FileReader (f));
			String line;
			while ((line = reader.readLine()) != null) {
				stopWords.add (line.toLowerCase().trim());
			}
		} catch (IOException e) {System.err.println ("Exception reading stop list " + e);}
	}

	public void expandSocialNetwork (int numHops, File crfFile) {
		ContactRecordExtractor cre = new ContactRecordExtractor (crfFile, vcfFile, htmlFile, stopWords);
		HomePageFinder hpf = new HomePageFinder (outputDir, userName, stopWords);
		for (int i=0; i < numHops; i++) {
			logger.info ("Iteration " + i + ", " + people.size() + " people.");
			hpf.findHomePagesFor (people);
			cre.extractContactRecordsFor (people);
			people.expand();
		}
		hpf.findHomePagesFor (people);
		logger.info ("Final network has " + people.size() + " people.");
	}


	public People getPeople () { return people; }
	
	public void writePeople (File f) {
		people.write (f);
	}
	
	public void writeTXT (File f) {
		people.writeTXT(f);
 	}

	public void writeHTML (File f) {
		people.writeHTML (f);
 	}

	public void writeCSV (File f) {
		people.writeCSV (f);
	}

	public void writeVCF (File f) {
		people.writeVCF (f);
	}
	
}