/// <summary>
/// Gets a Hashtable of words and integers representing the number of each word.
/// </summary>
/// <param name="input">The string to get the word frequency of.</param>
/// <param name="caseSensitive">True if words should be treated as separate if they have different casing.</param>
/// <param name="tokenizer">A instance of ITokenizer.</param>
/// <param name="stopWordProvider">An instance of IStopWordProvider.</param>
/// <returns></returns>
public static Hashtable GetWordFrequency(string input, bool caseSensitive, ITokenizer tokenizer, IStopWordProvider stopWordProvider)
{
string convertedInput = input;
if (!caseSensitive)
convertedInput = input.ToLower();
string[] words = tokenizer.Tokenize(convertedInput);
Array.Sort(words);
string[] uniqueWords = GetUniqueWords(words);
Hashtable result = new Hashtable();
for (int i = 0; i < uniqueWords.Length; i++)
{
if (stopWordProvider == null || (IsWord(uniqueWords[i]) && !stopWordProvider.IsStopWord(uniqueWords[i])))
{
if (result.ContainsKey(uniqueWords[i]))
result[uniqueWords[i]] = (int)result[uniqueWords[i]] + CountWords(uniqueWords[i], words);
else
result.Add(uniqueWords[i], CountWords(uniqueWords[i], words));
}
}
return result;
}
public Integration(
IUserInterfacePortal userInterfacePortal,
IManuscriptProvider manuscriptProvider,
IStopWordProvider stopWordProvider)
{
_userInterfacePortal = userInterfacePortal;
_manuscriptProvider = manuscriptProvider;
_stopWordProvider = stopWordProvider;
}
public IntegrationTests()
{
_userInterfacePortal = Substitute.For <IUserInterfacePortal>();
_manuscriptProvider = new ManuscriptProvider();
_stopWordProvider = new StopwordProvider(TestStopwordListPath);
_target = new Integration(
_userInterfacePortal,
_manuscriptProvider,
_stopWordProvider);
}
public BayesianClassifier(IWordsDataSource wd, ITokenizer tokenizer, IStopWordProvider swp)
{
if (wd == null)
throw new ArgumentNullException("IWordsDataSource cannot be null.");
_wordsData = wd;
if (tokenizer == null)
throw new ArgumentNullException("ITokenizer cannot be null.");
_tokenizer = tokenizer;
if (swp == null)
throw new ArgumentNullException("IStopWordProvider cannot be null.");
_stopWordProvider = swp;
}
public BayesianClassifier(IWordsDataSource wd, ITokenizer tokenizer, IStopWordProvider swp)
{
if (wd == null)
{
throw new ArgumentNullException("IWordsDataSource cannot be null.");
}
_wordsData = wd;
if (tokenizer == null)
{
throw new ArgumentNullException("ITokenizer cannot be null.");
}
_tokenizer = tokenizer;
if (swp == null)
{
throw new ArgumentNullException("IStopWordProvider cannot be null.");
}
_stopWordProvider = swp;
}
public BayesianClassifier(IWordsDataSource wordsDataSource, ITokenizer tokenizer, IStopWordProvider stopWordProvider)
{
if (wordsDataSource == null)
{
throw new ArgumentNullException("wordsDataSource");
}
_wordsData = wordsDataSource;
if (tokenizer == null)
{
throw new ArgumentNullException("tokenizer");
}
_tokenizer = tokenizer;
if (stopWordProvider == null)
{
throw new ArgumentNullException("stopWordProvider");
}
_stopWordProvider = stopWordProvider;
}
public BayesianClassifier(IWordsDataSource wordsDataSource, ITokenizer tokenizer, IStopWordProvider stopWordProvider)
{
if (wordsDataSource == null)
{
throw new ArgumentNullException("wordsDataSource");
}
_wordsData = wordsDataSource;
if (tokenizer == null)
{
throw new ArgumentNullException("tokenizer");
}
_tokenizer = tokenizer;
if (stopWordProvider == null)
{
throw new ArgumentNullException("stopWordProvider");
}
_stopWordProvider = stopWordProvider;
}
/// <summary>
/// Gets a dictionary of words and integers representing the number of each word.
/// </summary>
/// <param name="input">The string to get the word frequency of.</param>
/// <param name="caseSensitive">True if words should be treated as separate if they have different casing.</param>
/// <param name="tokenizer">A instance of ITokenizer.</param>
/// <param name="stopWordProvider">An instance of IStopWordProvider.</param>
/// <returns></returns>
public static IDictionary<string, int> GetWordFrequency(string input, bool caseSensitive, ITokenizer tokenizer, IStopWordProvider stopWordProvider)
{
var convertedInput = input;
if (!caseSensitive)
{
convertedInput = input.ToLower();
}
var words = tokenizer.Tokenize(convertedInput);
Array.Sort(words);
var uniqueWords = GetUniqueWords(words);
var result = new Dictionary<string, int>();
for (var i = 0; i < uniqueWords.Length; i++)
{
var word = uniqueWords[i];
if (stopWordProvider == null || (IsWord(word) && !stopWordProvider.IsStopWord(word)))
{
int value;
if (result.TryGetValue(word, out value))
{
result[word] = value + CountWords(word, words);
}
else
{
result.Add(word, CountWords(word, words));
}
}
}
return result;
}
public StopWordsFilter(IStopWordProvider stopwordProvider)
{
_stopwordProvider = stopwordProvider;
}
/// <summary>
/// Gets a Hashtable of words and integers representing the number of each word.
/// </summary>
/// <param name="input">The string to get the word frequency of.</param>
/// <param name="caseSensitive">True if words should be treated as separate if they have different casing.</param>
/// <param name="tokenizer">A instance of ITokenizer.</param>
/// <param name="stopWordProvider">An instance of IStopWordProvider.</param>
/// <returns></returns>
public static Hashtable GetWordFrequency(string input, bool caseSensitive, ITokenizer tokenizer, IStopWordProvider stopWordProvider)
{
string convertedInput = input;
if (!caseSensitive)
{
convertedInput = input.ToLower();
}
string[] words = tokenizer.Tokenize(convertedInput);
Array.Sort(words);
string[] uniqueWords = GetUniqueWords(words);
Hashtable result = new Hashtable();
for (int i = 0; i < uniqueWords.Length; i++)
{
if (stopWordProvider == null || (IsWord(uniqueWords[i]) && !stopWordProvider.IsStopWord(uniqueWords[i])))
{
if (result.ContainsKey(uniqueWords[i]))
{
result[uniqueWords[i]] = (int)result[uniqueWords[i]] + CountWords(uniqueWords[i], words);
}
else
{
result.Add(uniqueWords[i], CountWords(uniqueWords[i], words));
}
}
}
return(result);
}
public StopWordProviderTests()
{
_target = new StopwordProvider(TestStopWordListFilePath);
}
public StopWordService(IStopWordProvider provider)
{
_provider = provider;
}
/// <summary>
/// Gets a dictionary of words and integers representing the number of each word.
/// </summary>
/// <param name="input">The string to get the word frequency of.</param>
/// <param name="caseSensitive">True if words should be treated as separate if they have different casing.</param>
/// <param name="tokenizer">A instance of ITokenizer.</param>
/// <param name="stopWordProvider">An instance of IStopWordProvider.</param>
/// <returns></returns>
public static IDictionary<string, int> GetWordFrequency(string input, bool caseSensitive, ITokenizer tokenizer, IStopWordProvider stopWordProvider)
{
var convertedInput = input;
if (!caseSensitive)
{
convertedInput = input.ToLower();
}
var words = tokenizer.Tokenize(convertedInput);
Array.Sort(words);
var uniqueWords = GetUniqueWords(words);
var result = new Dictionary<string, int>();
for (var i = 0; i < uniqueWords.Length; i++)
{
var word = uniqueWords[i];
if (stopWordProvider == null || (IsWord(word) && !stopWordProvider.IsStopWord(word)))
{
int value;
if (result.TryGetValue(word, out value))
{
result[word] = value + CountWords(word, words);
}
else
{
result.Add(word, CountWords(word, words));
}
}
}
return result;
}
public DocumentDataProvider(IStopWordProvider stopWordProvider, IXmlService xmlService, ITextAnalyzer textAnalyzer)
{
this.stopWordProvider = stopWordProvider;
this.xmlService = xmlService;
this.textAnalyzer = textAnalyzer;
}