欢迎您访问程序员文章站本站旨在为大家提供分享程序员计算机编程知识!
您现在的位置是: 首页  >  IT编程

C#实现的字符串相似度对比类

程序员文章站 2023-12-05 23:05:28
本类适用于比较2个字符的相似度,代码如下: using system; using system.collections.generic; using sys...

本类适用于比较2个字符的相似度,代码如下:

using system;
using system.collections.generic;
using system.text;

public class stringcompute
{
  #region 私有变量
  /// <summary>
  /// 字符串1
  /// </summary>
  private char[] _arrchar1;
  /// <summary>
  /// 字符串2
  /// </summary>
  private char[] _arrchar2;
  /// <summary>
  /// 统计结果
  /// </summary>
  private result _result;
  /// <summary>
  /// 开始时间
  /// </summary>
  private datetime _begintime;
  /// <summary>
  /// 结束时间
  /// </summary>
  private datetime _endtime;
  /// <summary>
  /// 计算次数
  /// </summary>
  private int _computetimes;
  /// <summary>
  /// 算法矩阵
  /// </summary>
  private int[,] _matrix;
  /// <summary>
  /// 矩阵列数
  /// </summary>
  private int _column;
  /// <summary>
  /// 矩阵行数
  /// </summary>
  private int _row;
  #endregion
  #region 属性
  public result computeresult
  {
    get { return _result; }
  }
  #endregion
  #region 构造函数
  public stringcompute(string str1, string str2)
  {
    this.stringcomputeinit(str1, str2);
  }
  public stringcompute()
  {
  }
  #endregion
  #region 算法实现
  /// <summary>
  /// 初始化算法基本信息
  /// </summary>
  /// <param name="str1">字符串1</param>
  /// <param name="str2">字符串2</param>
  private void stringcomputeinit(string str1, string str2)
  {
    _arrchar1 = str1.tochararray();
    _arrchar2 = str2.tochararray();
    _result = new result();
    _computetimes = 0;
    _row = _arrchar1.length + 1;
    _column = _arrchar2.length + 1;
    _matrix = new int[_row, _column];
  }
  /// <summary>
  /// 计算相似度
  /// </summary>
  public void compute()
  {
    //开始时间
    _begintime = datetime.now;
    //初始化矩阵的第一行和第一列
    this.initmatrix();
    int intcost = 0;
    for (int i = 1; i < _row; i++)
    {
      for (int j = 1; j < _column; j++)
      {
        if (_arrchar1[i - 1] == _arrchar2[j - 1])
        {
          intcost = 0;
        }
        else
        {
          intcost = 1;
        }
        //关键步骤,计算当前位置值为左边+1、上面+1、左上角+intcost中的最小值 
        //循环遍历到最后_matrix[_row - 1, _column - 1]即为两个字符串的距离
        _matrix[i, j] = this.minimum(_matrix[i - 1, j] + 1, _matrix[i, j - 1] + 1, _matrix[i - 1, j - 1] + intcost);
        _computetimes++;
      }
    }
    //结束时间
    _endtime = datetime.now;
    //相似率 移动次数小于最长的字符串长度的20%算同一题
    int intlength = _row > _column ? _row : _column;

    _result.rate = (1 - (decimal)_matrix[_row - 1, _column - 1] / intlength);
    _result.usetime = (_endtime - _begintime).tostring();
    _result.computetimes = _computetimes.tostring();
    _result.difference = _matrix[_row - 1, _column - 1];
  }


  /// <summary>
  /// 计算相似度(不记录比较时间)
  /// </summary>
  public void speedycompute()
  {
    //开始时间
    //_begintime = datetime.now;
    //初始化矩阵的第一行和第一列
    this.initmatrix();
    int intcost = 0;
    for (int i = 1; i < _row; i++)
    {
      for (int j = 1; j < _column; j++)
      {
        if (_arrchar1[i - 1] == _arrchar2[j - 1])
        {
          intcost = 0;
        }
        else
        {
          intcost = 1;
        }
        //关键步骤,计算当前位置值为左边+1、上面+1、左上角+intcost中的最小值 
        //循环遍历到最后_matrix[_row - 1, _column - 1]即为两个字符串的距离
        _matrix[i, j] = this.minimum(_matrix[i - 1, j] + 1, _matrix[i, j - 1] + 1, _matrix[i - 1, j - 1] + intcost);
        _computetimes++;
      }
    }
    //结束时间
    //_endtime = datetime.now;
    //相似率 移动次数小于最长的字符串长度的20%算同一题
    int intlength = _row > _column ? _row : _column;

    _result.rate = (1 - (decimal)_matrix[_row - 1, _column - 1] / intlength);
    // _result.usetime = (_endtime - _begintime).tostring();
    _result.computetimes = _computetimes.tostring();
    _result.difference = _matrix[_row - 1, _column - 1];
  }
  /// <summary>
  /// 计算相似度
  /// </summary>
  /// <param name="str1">字符串1</param>
  /// <param name="str2">字符串2</param>
  public void compute(string str1, string str2)
  {
    this.stringcomputeinit(str1, str2);
    this.compute();
  }

  /// <summary>
  /// 计算相似度
  /// </summary>
  /// <param name="str1">字符串1</param>
  /// <param name="str2">字符串2</param>
  public void speedycompute(string str1, string str2)
  {
    this.stringcomputeinit(str1, str2);
    this.speedycompute();
  }
  /// <summary>
  /// 初始化矩阵的第一行和第一列
  /// </summary>
  private void initmatrix()
  {
    for (int i = 0; i < _column; i++)
    {
      _matrix[0, i] = i;
    }
    for (int i = 0; i < _row; i++)
    {
      _matrix[i, 0] = i;
    }
  }
  /// <summary>
  /// 取三个数中的最小值
  /// </summary>
  /// <param name="first"></param>
  /// <param name="second"></param>
  /// <param name="third"></param>
  /// <returns></returns>
  private int minimum(int first, int second, int third)
  {
    int intmin = first;
    if (second < intmin)
    {
      intmin = second;
    }
    if (third < intmin)
    {
      intmin = third;
    }
    return intmin;
  }
  #endregion
}
/// <summary>
/// 计算结果
/// </summary>
public struct result
{
  /// <summary>
  /// 相似度
  /// </summary>
  public decimal rate;
  /// <summary>
  /// 对比次数
  /// </summary>
  public string computetimes;
  /// <summary>
  /// 使用时间
  /// </summary>
  public string usetime;
  /// <summary>
  /// 差异
  /// </summary>
  public int difference;
}

调用方法:

// 方式一
stringcompute stringcompute1 = new stringcompute();
stringcompute1.speedycompute("对比字符一", "对比字符二");  // 计算相似度, 不记录比较时间
decimal rate = stringcompute1.computeresult.rate;     // 相似度百分之几,完全匹配相似度为1

// 方式二
stringcompute stringcompute2 = new stringcompute();
stringcompute2.compute();                 // 计算相似度, 记录比较时间
string usetime = stringcompute2.computeresult.usetime;   // 对比使用时间