Count words, unique words, and their occurrence count using C#

readme.md

Related blog post: Count Words and Occurrences of each Word in a Document using C#

CountWordInDocuments.cs

// Count Words in PDF document using C#
using (Parser parser = new Parser("path/document.pdf"))
{                
	// Extract a text into the reader
	using (TextReader reader = parser.GetText())
	{
		string text = reader.ReadToEnd();
		char[] chars = { ' ', '.', ',', ';', ':', '?', '\n', '\r' };
		// split words
		string[] words = text.Split(chars);
		// print total word count
		Console.WriteLine("Total word count: {0}", stats.Count);
	}
}

CountWordOccurrences.cs

// Count Unique Words and their occurrences in PDF document using C#
using (Parser parser = new Parser("path/document.pdf"))
{                
	// Extract text into TextReader
	using (TextReader reader = parser.GetText())
	{
		Dictionary<string, int> stats = new Dictionary<string, int>();
		string text = reader.ReadToEnd();
		char[] chars = { ' ', '.', ',', ';', ':', '?', '\n', '\r' };
		// split words
		string[] words = text.Split(chars);
		int minWordLength = 2; // Consider a word having more than 2 characters

		// iterate over the words collection to count occurrences
		foreach (string word in words)
		{
			string w = word.Trim().ToLower();
			if (w.Length > minWordLength)
			{
				if (!stats.ContainsKey(w))
				{
					stats.Add(w, 1); // add new word to collection
				}
				else
				{
					stats[w] += 1; // update word occurrence count
				}
			}
		}
		// order the collection by word count
		var orderedStats = stats.OrderByDescending(x => x.Value);
		
    		// Print word count Results
		Console.WriteLine("Total word count: {0}", stats.Count);

    		foreach (var pair in orderedStats)
		{
			Console.WriteLine("Total occurrences of {0}: {1}", pair.Key, pair.Value);
		}
	}
}

GetText.cs

using (TextReader reader = parser.GetText())
{

}

GroupDocsParserNamespaces.cs

using GroupDocs.Parser;
using System;
using System.Collections.Generic;
using System.IO;
using System.Linq; 

LoadDocumentForParsing.cs

using (Parser parser = new Parser("sample.pdf"))
{
  // your code goes here.
}

PrintWordCount.cs

// order the list by word count
var orderedStats = stats.OrderByDescending(x => x.Value);
// print total word count
Console.WriteLine("Total word count: {0}", stats.Count);
// print occurrence of each word
foreach (var pair in orderedStats)
{
	Console.WriteLine("Total occurrences of {0}: {1}", pair.Key, pair.Value);
}

SplitTextAndCountWords.cs

Dictionary<string, int> stats = new Dictionary<string, int>();
string text = reader.ReadToEnd();
char[] chars = { ' ', '.', ',', ';', ':', '?', '\n', '\r' };
// split words
string[] words = text.Split(chars);
int minWordLength = 2;// to count words having more than 2  characters

// iterate over the word collection to count occurrences
foreach (string word in words)
{
	string w = word.Trim().ToLower();
	if (w.Length > minWordLength)
	{
		if (!stats.ContainsKey(w))
		{
			// add new word to collection
			stats.Add(w, 1);
		}
		else
		{
			// update word occurrence count
			stats[w] += 1;
		}
	}
}