Count words, unique words, and their occurrence count in Java

readme.md

Related blog post: Count Words and Occurrences of Each Word in a Document using Java

CountWordInDocuments.java

// Count Words in PDF document using Java
// Count Unique Words and their occurrences in PDF document using Java
try (Parser parser = new Parser("path/document.pdf")) {

	TextReader reader = parser.getText();
	String text = reader.readToEnd();

	String[] words = text.split("\\s+|\\.|\\,|\\?|\\:|\\;");
	System.out.println("Length:" + words.length);
}

CountWordOccurrences.java

// Count Unique Words and their occurrences in PDF document using Java
try (Parser parser = new Parser("path/document.pdf")) {

	TextReader reader = parser.getText();
	String text = reader.readToEnd();

	String[] words = text.split("\\s+|\\.|\\,|\\?|\\:|\\;");
	Hashtable<String, Integer> wordCountTable = new Hashtable<String, Integer>();

	int minWordLength = 2;
	for (String word : words) 
	{
		String uniqueWord = word.toLowerCase();
		if (uniqueWord.length() > minWordLength) 
		{
			if (wordCountTable.containsKey(uniqueWord))	{
				wordCountTable.replace(uniqueWord, wordCountTable.get(uniqueWord),
						wordCountTable.get(uniqueWord).intValue() + 1);
			} else {
				wordCountTable.put(uniqueWord, 1);
			}

		}
	}
	wordCountTable.entrySet().forEach(entry -> {
		System.out.println(entry.getKey() + ": " + entry.getValue());
	});
}