字符相似度比较

最近项目有个问题，客户重复，比如**市A有限公司，**A有限公司，少了一个市，或者有限什么的，这样导致本来一个客户在系统中就出现多条记录，现在利用字符相似度比较找出差不多的客户给业务部门确认。

引用原文地址

http://darkmasky.iteye.com/blog/1115039

 

程序代码如下,由于只是一次使用，并没有写的很规范，Main.java中被注释的一段如果加上去，准确率高但是范围小了，所以做参考。

 

package com.shine.db;

import java.sql.Connection;
import java.sql.DriverManager;
import java.sql.ResultSet;
import java.sql.Statement;
import java.util.ArrayList;
import java.util.List;

import a.Customer;

public class JDBC {
	public static List<Customer> getData() {
		String sql = "select t.fnumber,t.fname_l2, length(t.fname_l2) s from t_bd_customer t order by s";
		String driver = "oracle.jdbc.driver.OracleDriver";
		String connStr = "jdbc:oracle:thin:@192.168.0.5:1521:test";
		Connection conn = null;
		ArrayList<Customer> l = new ArrayList<Customer>();
		try {

			Class.forName(driver);
			conn = DriverManager.getConnection(connStr, "user", "***");
			Statement stmt = conn.createStatement();
			ResultSet rs = stmt.executeQuery(sql);
			while (rs.next()) {
				Customer c = new Customer();
				c.setName(rs.getString("fname_l2"));
				c.setNumber(rs.getString("fnumber"));
				c.setLen(rs.getInt("s"));
				l.add(c);
			}
			rs.close();
			stmt.close();
			conn.close();
		} catch (Exception e) {
			e.printStackTrace();
		}
		return l;
	}
}

 

package a;
public class Customer {
	String number;
	String name;
	int len;
	public int getLen() {
		return len;
	}
	public void setLen(int l) {
		this.len = l;
	}
	public String getNumber() {
		return number;
	}
	public void setNumber(String numner) {
		this.number = numner;
	}
	public String getName() {
		return name;
	}
	public void setName(String name) {
		this.name = name;
	}
}

 

package a;

import java.util.List;

import com.shine.db.JDBC;

public class Main {

	public static void main(String[] args) {
		List<Customer> data = JDBC.getData();
		for (int i = 0; i < data.size(); i++) {
			Customer c1 = (Customer) data.get(i);
			String s1 = c1.getName();
			int l1 = c1.getLen();
			for (int j = i + 1; j < data.size(); j++) {
				Customer c2 = (Customer) data.get(j);
				String s2 = c2.getName();
				int l2 = c2.getLen();
				double similarDegree = getSimilarityRatio(s1, s2);
				if (similarDegree >= 0.85) {
					System.out.println(s1 + "(" + c1.getNumber() + "),"
							+ s2 + "(" + c2.getNumber() + ")");
				}
//				if (l1 != l2) {
//					double similarDegree = getSimilarityRatio(s1, s2);
//					if (similarDegree >= 0.9) {
//						System.out.println(s1 + "(" + c1.getNumber() + "),"
//								+ s2 + "(" + c2.getNumber() + ")");
//					}
//				}
			}
		}

	}

	private static int compare(String str, String target) {

		int d[][]; // 矩阵

		int n = str.length();

		int m = target.length();

		int i; // 遍历str的

		int j; // 遍历target的

		char ch1; // str的

		char ch2; // target的

		int temp; // 记录相同字符,在某个矩阵位置值的增量,不是0就是1

		if (n == 0) {

			return m;

		}

		if (m == 0) {

			return n;

		}

		d = new int[n + 1][m + 1];

		for (i = 0; i <= n; i++) { // 初始化第一列

			d[i][0] = i;

		}

		for (j = 0; j <= m; j++) { // 初始化第一行

			d[0][j] = j;

		}

		for (i = 1; i <= n; i++) { // 遍历str

			ch1 = str.charAt(i - 1);

			// 去匹配target

			for (j = 1; j <= m; j++) {

				ch2 = target.charAt(j - 1);

				if (ch1 == ch2) {

					temp = 0;

				} else {

					temp = 1;

				}

				// 左边+1,上边+1, 左上角+temp取最小

				d[i][j] = min(d[i - 1][j] + 1, d[i][j - 1] + 1, d[i - 1][j - 1]

				+ temp);

			}

		}

		return d[n][m];

	}

	private static int min(int one, int two, int three) {

		return (one = one < two ? one : two) < three ? one : three;

	}

	/**
	 * 
	 * 获取两字符串的相似度
	 * 
	 * 
	 * 
	 * @param str
	 * 
	 * @param target
	 * 
	 * @return
	 */

	public static float getSimilarityRatio(String str, String target) {

		return 1 - (float) compare(str, target)

		/ Math.max(str.length(), target.length());

	}
}