一个文本文件（c:\test.txt）的内容由英文单词及分隔符组成（分隔符包括英文的空格、逗号、分号、点号、问号。分隔符可能连续出现，如空格），请用C#编写一个程序实现如下功能：
1）  统计文件中的所有不同单词，不区分大小写，并通过界面显示。
2）  统计每个单词在文件中出现的次数，并按照次数进行排序。
注意：文本文件可能很大，请考虑使用高效的数据结构。测试文件自行设计，请考虑通用性，评卷时会根据测试用例进行测试。

[[italic] 本帖最后由 simpson 于 2008-1-15 13:29 编辑 [/italic]]

顶 至今23：00结帖

性能全部损耗在排序上,由于hashtable不能排序,所以只能借助其他来排序,  不过还好  一本60000字的书10几秒就能统计完.

using
using System.Collections;//use hashtable
using System.Text.RegularExpressions;

namespace WindowsApplication1
{
    public partial class Form1 : Form
    {
        public Form1()
        {
            InitializeComponent();
        }
        private void cmdStart_Click(object sender, EventArgs e)
        {
            string Pattern = @"\,|\.|\ |\n|\r|\?|\;|\:|\!|\(|\)|\042|\“|\”|\-|[\u4e00-\u9fa5]|[0-9]";   //匹配正值表达式 逗号，点号，空格，换行符，回车符，问号，,分号，，冒号，感叹号，，左括号，又括号，双引号，左双引号，右双引号，中文字符,数字
            string textstring = "";
            int j;
            Hashtable ht = new Hashtable();      //创建一个Hashtable实例
            //Hashtable ht = new Hashtable();      //创建一个Hashtable实例
            Regex regex = new Regex(Pattern);    //创建Regex实类
            textBox2.Text = "";
            //读取文件
            try
            {
                StreamReader sr = new StreamReader(@textBox1.Text,System.Text.Encoding.GetEncoding("GB2312"));
                textstring = sr.ReadToEnd();
                sr.Close();
            }
            catch
            {
                MessageBox.Show("请把test.txt文件拷贝到C:/");
            }
            //根据匹配正值表达式分割字符串
            string[] words = regex.Split(textstring);
            //单词加入哈希表
            foreach (string word in words)
            {
                //textBox2.Text = textBox2.Text + "   " + i;
                if (word != null && word != "")
                {
                    if (ht.Contains(word))
                    {
                        j = Convert.ToInt32(ht[word]) + 1;
                        //ht.Remove(word);
                        //ht.Add(word, j);
                        ht[word]=j;
                    }
                    else
                    {
                        ht.Add(word, 1);
                    }
                }
            }
            ////对哈希表排序
            ArrayList akeys = new ArrayList(ht.Keys);
                //按字母顺序进行排序
                //akeys.Sort() ;
                //按字单词次数进行排序
                string[] keyarray = new string[akeys.Count];
                int[] valuearray = new int[akeys.Count];
                int index=0;
                //将key/value分别赋给数祖
                foreach (string skey in akeys)
                {
                    keyarray[index] = Convert.ToString(skey);
                    valuearray[index] = Convert.ToInt32(ht[skey]);
                    index++;
                }
                for(int a=0;a<akeys.Count;a++)
                {
                    for (int b = a+1; b < akeys.Count; b++)
                    {
                        if (valuearray[a]>valuearray[b])
                        {
                            valuearray[a] ^= valuearray[b];
                            valuearray[b] ^= valuearray[a];
                            valuearray[a] ^= valuearray[b];
                            string tempstr = keyarray[a];
                            keyarray[a] = keyarray[b];
                            keyarray[b] = tempstr;
                        }
                    }
                }
            //显示
                //按字母顺序进行排序显示
                //foreach(string skey in akeys)
                //{
                //    textBox2.Text = textBox2.Text + skey + "\t" + ht[skey] + "\r\n";
                //}
                //按字单词次数进行排序显示
                for (int a = 0; a < akeys.Count; a++)
                {
                    textBox2.Text = textBox2.Text + keyarray[a] + "\t" + valuearray[a] + "\r\n";
                }
        }
    }
}

[[italic] 本帖最后由 simpson 于 2008-1-12 00:13 编辑 [/italic]]

求更高效的实现方法。。。

:victory