#region Copyright (c) 2004, Ryan Whitaker
/*********************************************************************************
'
' Copyright (c) 2004 Ryan Whitaker
'
' This software is provided 'as-is', without any express or implied warranty. In no
' event will the authors be held liable for any damages arising from the use of this
' software.
'
' Permission is granted to anyone to use this software for any purpose, including
' commercial applications, and to alter it and redistribute it freely, subject to the
' following restrictions:
'
' 1. The origin of this software must not be misrepresented; you must not claim that
' you wrote the original software. If you use this software in a product, an
' acknowledgment (see the following) in the product documentation is required.
'
' This product uses software written by the developers of NClassifier
' (http://nclassifier.sourceforge.net). NClassifier is a .NET port of the Nick
' Lothian's Java text classification engine, Classifier4J
' (http://classifier4j.sourceforge.net).
'
' 2. Altered source versions must be plainly marked as such, and must not be
' misrepresented as being the original software.
'
' 3. This notice may not be removed or altered from any source distribution.
'
'********************************************************************************/
#endregion
using System;
using System.Collections;
using System.Text.RegularExpressions;
namespace NClassifier
{
public class Utilities
{
///
/// Count how many times a word appears in an array of words.
///
/// The word to count.
/// A non-null array of words.
public static int CountWords(string word, string[] words)
{
// find the index of one of the items in the array
int itemIndex = Array.BinarySearch(words, word);
// iterate backwards until we find the first match
if (itemIndex > 0)
while (itemIndex > 0 && words[itemIndex] == word)
itemIndex--;
// now itemIndex is one item before the start of the words
int count = 0;
while (itemIndex < words.Length && itemIndex >= 0)
{
if (words[itemIndex] == word)
count++;
itemIndex++;
if (itemIndex < words.Length)
if (words[itemIndex] != word)
break;
}
return count;
}
}
}