public void SetUp()
{
defaultWords = new List <string> {
"di", "solid", "mocking", "unit", "to"
};
defaultHeights = Enumerable.Repeat(30, defaultWords.Count).ToList();
wordsPreprocessor1 = A.Fake <IWordsPreprocessor>();
wordsPreprocessor2 = A.Fake <IWordsPreprocessor>();
wordsFilter1 = A.Fake <IWordsFilter>();
wordsFilter2 = A.Fake <IWordsFilter>();
wordsFramer = A.Fake <IWordsHeighter>();
layouter = A.Fake <ICloudLayouter>();
writer = A.Fake <IWordsBitmapWriter>();
A.CallTo(() => wordsPreprocessor1.Process(null)).WithAnyArguments().Returns(defaultWords);
A.CallTo(() => wordsPreprocessor2.Process(null)).WithAnyArguments().Returns(defaultWords);
A.CallTo(() => wordsFilter1.GetFiltered(null)).WithAnyArguments().Returns(defaultWords);
A.CallTo(() => wordsFilter2.GetFiltered(null)).WithAnyArguments().Returns(defaultWords);
A.CallTo(() => wordsFramer.GetWithHeights(null)).WithAnyArguments().Returns(defaultWords.Zip(defaultHeights, Tuple.Create));
A.CallTo(() => layouter.PutNextRectangle(Size.Empty)).WithAnyArguments().Returns(Rectangle.Empty);
A.CallTo(() => writer.Write(null)).WithAnyArguments().Returns(bitmapResult);
container = new CloudContainer(
new [] { wordsPreprocessor1, wordsPreprocessor2 },
new [] { wordsFilter1, wordsFilter2 },
wordsFramer,
layouter,
writer, ImageFormat.Bmp);
}
public TextProcessor(
IWordsPreprocessor wordsPreprocessor,
IDictionaryUpdater dictionaryUpdater,
ITextProvider textProvider)
{
this.wordsPreprocessor = wordsPreprocessor;
this.dictionaryUpdater = dictionaryUpdater;
this.textProvider = textProvider;
}
public DataProvider(ICloudSettings cloudSettings, ISourceTextReader textReader, IWordsPreprocessor wordsPreprocessor,
IAlgorithm algorithm, ILogger logger)
{
this.cloudSettings = cloudSettings;
this.textReader = textReader;
this.wordsPreprocessor = wordsPreprocessor;
this.algorithm = algorithm;
this.logger = logger;
}
public SimpleCloudConfigurator(IWordsPreprocessor preprocessor)
{
wordsWithFrequency = preprocessor.GetWordsFrequency();
}
private static Dictionary <string, int> ReadWords(IWordsDirectoryProvider wordsDirectoryProvider, IWordsPreprocessor preprocessor)
{
var words = File.ReadLines(wordsDirectoryProvider.WordsDirectory);
return(preprocessor
.PreprocessWords(words)
.GroupBy(word => word)
.ToDictionary(wordGroup => wordGroup.Key, wordGroup => wordGroup.Count()));
}
public WordsProvider(IWordsDirectoryProvider wordsDirectoryProvider, IWordsPreprocessor preprocessor)
{
wordToFrequency = ReadWords(wordsDirectoryProvider, preprocessor);
}
public BayesianSpamFilter(IProbabilityProvider probabilityProvider, IWordsExtractor wordsExtractor, IWordsPreprocessor wordsPreprocessor)
{
this.probabilityProvider = probabilityProvider;
this.wordsExtractor = wordsExtractor;
this.wordsPreprocessor = wordsPreprocessor;
}
private static Dictionary <string, int> CalculateWordsCount(IEnumerable <FileInfo> msgFiles, IWordsExtractor wordsExtractor, IWordsPreprocessor wordsPreprocessor)
{
var wordToCountMessagesWithThisWord = new Dictionary <string, int>();
foreach (var messageFile in msgFiles)
{
var rawWords = wordsExtractor.ExtractWords(messageFile.OpenRead());
var preprocessedWords = wordsPreprocessor.PreprocessWords(rawWords);
foreach (var word in preprocessedWords.Distinct())
{
if (!wordToCountMessagesWithThisWord.ContainsKey(word))
{
wordToCountMessagesWithThisWord[word] = 0;
}
wordToCountMessagesWithThisWord[word]++;
}
}
return(wordToCountMessagesWithThisWord);
}
public ProbabilityProvider(ITrainingSample trainingSample, IWordsExtractor wordsExtractor, IWordsPreprocessor wordsPreprocessor)
{
spamCountWithWord = CalculateWordsCount(trainingSample.SpamFiles, wordsExtractor, wordsPreprocessor);
totalSpamCount = trainingSample.SpamFiles.Count();
hamCountWithWord = CalculateWordsCount(trainingSample.HamFiles, wordsExtractor, wordsPreprocessor);
totalHamCount = trainingSample.HamFiles.Count();
}
