loads of useful information, examples and tutorials pertaining to web development utilizing asp.net, c#, vb, css, xhtml, javascript, sql, xml, ajax and everything else...

 



Advertise Here
C-Sharpener.com - Programming is Easy!  Learn Asp.Net & C# in just days, Guaranteed!

Finding/counting Keywords out of a Text Document

by naspinski 9/18/2008 6:41:00 AM

A quick program to find keywords out of a document - great for a knowledge base or .txt file repository

I wrote this a while back and it became relevant again today.  All this does is take in a text file, go through it making a Dictionary of all the words and counting them (ignoring the words in the exclusion list) and then sorts and outputs them.  The logic is pretty straightforward and looks like this:

[code:c#]

public partial class keywords : System.Web.UI.Page
{
    Dictionary<string, int> _keywords = new Dictionary<string, int>();
    char[] delimiter = {' '}; // whatever you want to delimit the text with, I just use spaces
    string[] DEFAULT_EXCLUDE = { "a", "the", "is", "and" };//things you want excluded even if the user does not specify (you can leave it blank too)

    protected void Page_Load(object sender, EventArgs e)
    {
        lblExcluded.Text = string.Empty;
        for(int i=0;i<DEFAULT_EXCLUDE.Length;i++)
            lblExcluded.Text += i == DEFAULT_EXCLUDE.Length - 1 ? DEFAULT_EXCLUDE[i] + " " : DEFAULT_EXCLUDE[i] + ", ";
    }
    protected void submit_Click(object sender, EventArgs e)
    {
        string[] words_to_exclude = txtExclude.Text.Length<1 ? new string[] {" "} : txtExclude.Text.Split(new char[] {','});
        for (int i = 0; i < words_to_exclude.Length; i++) words_to_exclude[i] = words_to_exclude[i].Trim(); //cut off all empty space
        List<string> excluded = new List<string>();
        foreach (string s in DEFAULT_EXCLUDE)
            if (!excluded.Contains(s)) excluded.Add(s);
        foreach (string s in words_to_exclude)
            if (!excluded.Contains(s)) excluded.Add(s);

        int keyword_threshhold = Int32.Parse(txtThreshhold.Text);
        if (fu.HasFile)
        {
            try
            {
                //Save the file here
                StreamReader sr = new StreamReader(fu.FileContent);//this pulls from the user, or you can pull it from where you saved it to now
                while (!sr.EndOfStream)
                {
                    string line = sr.ReadLine();
                    string[] splitString = line.Split(delimiter);
                    foreach (string s in splitString)
                    {
                        if (!excluded.Contains(s))
                        {
                            try { _keywords[s] = _keywords[s] + 1; }
                            catch { _keywords.Add(s, 1); }
                        }
                    }
                }
                bool switcher = false;
                phKeywords.Controls.Add(new LiteralControl("<div id=\"keys\" class=\"main_area\"><h2>Keywords</h2>"));

                var query = from p in _keywords orderby p.Value descending select p;

                foreach (KeyValuePair<string, int> d in query)
                {
                    if ((int)d.Value >= keyword_threshhold)
                    {
                        string color = switcher?"blue": "white";
                        phKeywords.Controls.Add(new LiteralControl("<div class=\""+ color +"\">"+ d.Value + " - " + d.Key + "</div>"));
                        switcher = !switcher;
                    }
                }
                phKeywords.Controls.Add(new LiteralControl("</div>"));
            }

            catch (Exception ex)
            { phError.Controls.Add(new LiteralControl("<div id=\"error\" class=\"main_area\"><b>Error:</b>" + ex.Message + "</div>")); }
        }
        else
            phError.Controls.Add(new LiteralControl("<div id=\"error\" class=\"main_area\"><b>Error:</b> Can't process what you don't give me...</div>"));

    }

[/code]

 

The inputs are fu, which is a FileUpload control that holds the file you are parsing, txtExclude which is a TextBox of the words to exclude (added to default exclusions), and txtThreshhold which is a TextBox where you enter the number of words to consider before it is counted as a keyword.

 

 

 

 

 

 

Related posts


Comments are closed