Java实现SimHash算法：高效网页去重与文档相似性检测

package textCluster234;
import java.math.BigInteger;
import java.util.ArrayList;
import java.util.List;
import java.util.StringTokenizer;

public class SimHash {

    private String tokens;

    private BigInteger intSimHash;
    
    private String strSimHash;

    private int hashbits = 64;

    public SimHash(String tokens) {
        this.tokens = tokens;
        //看错了，这个和类SimHash比较相似，看花眼了
        this.intSimHash = this.simHash();
    }

    public SimHash(String tokens, int hashbits) {
        this.tokens = tokens;
        this.hashbits = hashbits;
        this.intSimHash = this.simHash();
    }

    public BigInteger simHash() {
        int[] v = new int[this.hashbits];

        StringTokenizer stringTokens = new StringTokenizer(this.tokens);
        while (stringTokens.hasMoreTokens()) {
            String temp = stringTokens.nextToken();
            BigInteger t = this.hash(temp);
            for (int i = 0; i < this.hashbits; i++) {
                BigInteger bitmask = new BigInteger("1").shiftLeft(i);
                 if (t.and(bitmask).signum() != 0) {
                    v[i] += 1;
                } else {
                    v[i] -= 1;
                }
            }
        }
        BigInteger fingerprint = new BigInteger("0");
        StringBuffer simHashBuffer = new StringBuffer();
        for (int i = 0; i < this.hashbits; i++) {
            if (v[i] >= 0) {
                fingerprint = fingerprint.add(new BigInteger("1").shiftLeft(i));
                simHashBuffer.append("1");
            }else{
                simHashBuffer.append("0");
            }
        }
        this.strSimHash = simHashBuffer.toString();
        System.out.println(this.strSimHash + " length " + this.strSimHash.length());
        return fingerprint;
    }

    private BigInteger hash(String source) {
        if (source == null || source.length() == 0) {