Question

我有一个包含不同文章的smg文件。现在，我想使用前缀树数据结构来为整个文档集建立基线字数。该文件的示例可以在下面找到：

<REUTERS TOPICS="YES" LEWISSPLIT="TRAIN" CGISPLIT="TRAINING-SET" 
OLDID="5544" NEWID="1">
<DATE>26-FEB-1987 15:01:01.79</DATE>
<TOPICS><D>cocoa</D></TOPICS>
<PLACES><D>el-salvador</D><D>usa</D><D>uruguay</D></PLACES>
<PEOPLE></PEOPLE>
<ORGS></ORGS>
<EXCHANGES></EXCHANGES>
<COMPANIES></COMPANIES>
<UNKNOWN> 
&#5;&#5;&#5;C T
&#22;&#22;&#1;f0704&#31;reute
u f BC-BAHIA-COCOA-REVIEW   02-26 0105</UNKNOWN>
<TEXT>&#2;
<TITLE>BAHIA COCOA REVIEW</TITLE>
<DATELINE>    SALVADOR, Feb 26 - </DATELINE><BODY>
Some text here.
 Reuter
&#3;</BODY></TEXT>
</REUTERS>

关于如何建立基准字数的任何建议？

Answer 1

使用trie数据结构更快地加载字符串和检索建议

public class Trie
    {
        public struct Letter
        {
            public const string Chars = "ABCDEFGHIJKLMNOPQRSTUVWXYZ";
            public static implicit operator Letter(char c)
            {
                c = c.ToString().ToUpper().ToCharArray().First();

                return new Letter() { Index = Chars.IndexOf(c) };
            }
            public int Index;
            public char ToChar()
            {
                return Chars[Index];
            }
            public override string ToString()
            {
                return Chars[Index].ToString();
            }
        }

        public class Node
        {
            public string Word;
            public bool IsTerminal { get { return Word != null; } }
            public Dictionary<Letter, Node> Edges = new Dictionary<Letter, Node>();


        }

        public Node Root = new Node();

        public Trie(string[] words)
        {
            for (int w = 0; w < words.Length; w++)
            {
                var word = words[w];
                var node = Root;
                for (int len = 1; len <= word.Length; len++)
                {
                    var letter = word[len - 1];
                    Node next;
                    if (!node.Edges.TryGetValue(letter, out next))
                    {
                        next = new Node();
                        if (len == word.Length)
                        {
                            next.Word = word;
                        }
                        node.Edges.Add(letter, next);
                    }
                    node = next;
                }
            }
        }


        public List<string> GetSuggestions(string word, int max)
        {
            List<string> outPut = new List<string>();

            var node = Root;
            int i = 0;
            foreach (var l in word)
            {
                Node cNode;
                if (node.Edges.TryGetValue(l, out cNode))
                {
                    node = cNode;
                }
                else
                {
                    if (i == word.Length - 1)
                        return outPut;
                }
                i++;
            }

            GetChildWords(node, ref outPut, max);

            return outPut;
        }


        public void GetChildWords(Node n, ref List<string> outWords, int Max)
        {
            if (n.IsTerminal && outWords.Count < Max)
                outWords.Add(n.Word);

            foreach (var item in n.Edges)
            {
                GetChildWords(item.Value, ref outWords, Max);
            }
        }

    }

如何使用前缀树数据结构

1 个答案: