使用C#和Jieba.NET实现中英文混合文本关键词的提取功能

Install-Package jieba.NET

using System;
using System.Collections.Generic;
using System.Linq;
using System.Windows.Forms;
using JiebaNet.Segmenter;
using System.Text.RegularExpressions;

public partial class MainForm : Form
{
    private TextBox inputBox;
    private Button analyzeButton;
    private ListBox resultList;
    private HashSet<string> stopWords;

    public MainForm()
    {
        InitializeComponent();
        InitializeStopWords(); // 初始化停用词表
    }

    private void InitializeStopWords()
    {
        // 中英文停用词表（示例）
        stopWords = new HashSet<string>
        {
            // 中文停用词
            "的", "了", "在", "是", "我", "和", "有", "就", "不", "人",
            // 英文停用词
            "a", "an", "the", "is", "are", "and", "in", "on", "at"
        };
    }

    private void AnalyzeButton_Click(object sender, EventArgs e)
    {
        string inputText = inputBox.Text.Trim();
        if (string.IsNullOrEmpty(inputText))
        {
            MessageBox.Show("请输入文本！");
            return;
        }

        // 使用Jieba进行分词（处理中文和英文混合）
        var segmenter = new JiebaSegmenter();
        var segments = segmenter.Cut(inputText);

        // 提取英文单词（通过正则表达式补充处理）
        var allWords = new List<string>();
        foreach (var seg in segments)
        {
            // 处理中英文混合词（如 "C#编程" -> ["C#", "编程"]）
            var words = Regex.Matches(seg, @"([A-Za-z0-9#+]+)|([\u4e00-\u9fa5]+)")
                .Cast<Match>()
                .Select(m => m.Value.ToLower());
            allWords.AddRange(words);
        }

        // 过滤停用词和单字词
        var filteredWords = allWords
            .Where(word => !stopWords.Contains(word) && word.Length >= 2);

        // 统计词频并排序
        var keywordCounts = filteredWords
            .GroupBy(word => word)
            .OrderByDescending(g => g.Count())
            .Select(g => $"{g.Key} ({g.Count()})")
            .ToList();

        // 显示结果
        resultList.DataSource = keywordCounts;
    }

    // 初始化窗体控件
    private void InitializeComponent()
    {
        this.inputBox = new TextBox();
        this.analyzeButton = new Button();
        this.resultList = new ListBox();

        // 布局控件
        this.inputBox.Multiline = true;
        this.inputBox.Location = new System.Drawing.Point(20, 20);
        this.inputBox.Size = new System.Drawing.Size(400, 150);

        this.analyzeButton.Text = "提取关键词";
        this.analyzeButton.Location = new System.Drawing.Point(20, 180);
        this.analyzeButton.Click += AnalyzeButton_Click;

        this.resultList.Location = new System.Drawing.Point(20, 220);
        this.resultList.Size = new System.Drawing.Size(400, 200);

        this.ClientSize = new System.Drawing.Size(440, 440);
        this.Controls.Add(inputBox);
        this.Controls.Add(analyzeButton);
        this.Controls.Add(resultList);
    }
}

private void LoadStopWordsFromFile(string path)
{
    stopWords = new HashSet<string>(File.ReadAllLines(path));
}

var posSegmenter = new PosSegmenter();
var posTags = posSegmenter.Cut(inputText);
var nouns = posTags.Where(tag => tag.Flag.StartsWith("n"));

using JiebaNet.Segmenter;
using System;
 
class Program
{
    static void Main(string[] args)
    {
        var segmenter = new JiebaSegmenter();
        string text = "我爱北京天安门";
        var words = segmenter.Cut(text);
        foreach (var word in words)
        {
            Console.WriteLine(word);
        }
    }
}

var words = segmenter.Cut(text, cutMode: CutMode.Full); // 使用全模式进行分词

segmenter.AddWord("天安门广场"); // 将“天安门广场”添加到词典中