C# 字符串文本相似度比较的两种算法 附完整源码

 

算法一：

 

    public class LevenshteinDistance
    {
        

        private static LevenshteinDistance _instance=null;
        public static LevenshteinDistance Instance
        {
            get
            {
                if (_instance == null)
                {
                    return new LevenshteinDistance();
                }
                return _instance;
            }
        }
    

        /// <summary>
        /// 取最小的一位数
        /// </summary>
        /// <param name="first"></param>
        /// <param name="second"></param>
        /// <param name="third"></param>
        /// <returns></returns>
        public int LowerOfThree(int first, int second, int third)
        {
            int min = first;
            if (second < min)
                min = second;
            if (third < min)
                min = third;
            return min;
        }

        public int Levenshtein_Distance(string str1, string str2)
        {
            int[,] Matrix;
            int n=str1.Length;
            int m=str2.Length;

            int temp = 0;
            char ch1;
            char ch2;
            int i = 0;
            int j = 0;
            if (n ==0)
            {
                return m;
            }
            if (m == 0)
            {

                return n;
            }
            Matrix=new int[n 1,m 1];

            for (i = 0; i <= n; i  )
            {
                //初始化第一列
                Matrix[i,0] = i;
            }

            for (j = 0; j <= m; j  )
            {
                //初始化第一行
                Matrix[0, j] = j;
            }

            for (i = 1; i <= n; i  )
            {
                ch1 = str1[i-1];
                for (j = 1; j <= m; j  )
                {
                    ch2 = str2[j-1];
                    if (ch1.Equals(ch2))
                    {
                        temp = 0;
                    }
                    else
                    {
                        temp = 1;
                    }
                    Matrix[i,j] = LowerOfThree(Matrix[i - 1,j]   1, Matrix[i,j - 1]   1, Matrix[i - 1,j - 1]   temp);


                }
            }

            for (i = 0; i <= n; i  )
            {
                for (j = 0; j <= m; j  )
                {
                    Console.Write(" {0} ", Matrix[i, j]);
                }
                Console.WriteLine("");
            }
            return Matrix[n, m];

        }

        /// <summary>
        /// 计算字符串相似度
        /// </summary>
        /// <param name="str1"></param>
        /// <param name="str2"></param>
        /// <returns></returns>
        public decimal LevenshteinDistancePercent(string str1,string str2)
        {
            int maxLenth = str1.Length > str2.Length ? str1.Length : str2.Length;
            int val = Levenshtein_Distance(str1, str2);
            return 1 - (decimal)val / maxLenth;
        }

    }

使用代码：

 

this.lbResult.Text = (LevenshteinDistance.Instance.LevenshteinDistancePercent(this.textBox1.Text, this.textBox2.Text) * 100).ToString();

算法二：

public  string get_semblance_By_2words(string word1, string word2)
        {
            int re = 0;
            int maxLength;
            int i, l;
            List<string> tb1 = new List<string>();
            List<string> tb2 = new List<string>();
            i = 0;
            l = 1;
            maxLength = word1.Length;
            if (word1.Length < word2.Length)
                maxLength = word2.Length;
            while (l <= word1.Length)
            {
                while (i < word1.Length - 1)
                {
                    if (i   l > word1.Length)
                        break;
                    tb1.Add(word1.Substring(i, l));
                    i  ;
                }
                i = 0;
                l  ;
            }

            i = 0;
            l = 1;

            while (l <= word2.Length)
            {
                while (i < word2.Length - 1)
                {
                    if (i   l > word2.Length)
                        break;
                    tb2.Add(word2.Substring(i, l));
                    i  ;
                }
                i = 0;
                l  ;
            }
            foreach (string subStr in tb1)
            {
                int tempRe = 0;
                if (tb2.Contains(subStr))
                {
                    tempRe = subStr.Length * 100 / maxLength;
                    if (tempRe > re)
                        re = tempRe;
                    if (tempRe == 100)
                        break;
                }
            }
            return re.ToString() "%";
        }

 

资源下载

此资源下载价格为2D币（VIP免费），请先登录

资源文件列表

Levenshtein/bin/Debug/Levenshtein.exe , 12800
Levenshtein/bin/Debug/Levenshtein.pdb , 30208
Levenshtein/bin/Debug/Levenshtein.vshost.exe , 22472
Levenshtein/bin/Debug/Levenshtein.vshost.exe.manifest , 490
Levenshtein/Form1.cs , 599
Levenshtein/Form1.Designer.cs , 4681
Levenshtein/Form1.resx , 5817
Levenshtein/Form2.cs , 2202
Levenshtein/Form2.Designer.cs , 4693
Levenshtein/Form2.resx , 5817
Levenshtein/Levenshtein.csproj , 4089
Levenshtein/Levenshtein.sln , 911
Levenshtein/Levenshtein.v11.suo , 35840
Levenshtein/LevenshteinDistance.cs , 3198
Levenshtein/obj/Debug/DesignTimeResolveAssemblyReferences.cache , 863
Levenshtein/obj/Debug/DesignTimeResolveAssemblyReferencesInput.cache , 6773
Levenshtein/obj/Debug/Levenshtein.csproj.FileListAbsolute.txt , 525
Levenshtein/obj/Debug/Levenshtein.csproj.GenerateResource.Cache , 1033
Levenshtein/obj/Debug/Levenshtein.exe , 12800
Levenshtein/obj/Debug/Levenshtein.Form1.resources , 180
Levenshtein/obj/Debug/Levenshtein.Form2.resources , 180
Levenshtein/obj/Debug/Levenshtein.pdb , 30208
Levenshtein/obj/Debug/Levenshtein.Properties.Resources.resources , 180
Levenshtein/Program.cs , 535
Levenshtein/Properties/AssemblyInfo.cs , 1360
Levenshtein/Properties/Resources.Designer.cs , 2874
Levenshtein/Properties/Resources.resx , 5612
Levenshtein/Properties/Settings.Designer.cs , 1098
Levenshtein/Properties/Settings.settings , 249