Category

Imports System.Text.RegularExpressions

Namespace BayesClassifier

    Public Class Category
        Implements ICategory

        Protected m_Phrases As System.Collections.Generic.SortedDictionary(Of String, PhraseCount)
        Private m_TotalWords As Integer
        Private m_Name As String
        Private m_Excluded As ExcludedWords

        Public ReadOnly Property Name() As String Implements ICategory.Name
            Get
                Return m_Name
            End Get
        End Property

        Public ReadOnly Property TotalWords() As Integer Implements ICategory.TotalWords
            Get
                Return m_TotalWords
            End Get
        End Property

        Public Sub New(ByVal cat As String, ByVal excluded As ExcludedWords)
            m_Phrases = New SortedDictionary(Of String, PhraseCount)()
            m_Excluded = excluded
            m_Name = cat
        End Sub

        Public Function GetPhraseCount(ByVal phrase As String) As Integer Implements ICategory.GetPhraseCount
            Dim pc As PhraseCount = New PhraseCount()
            If m_Phrases.TryGetValue(phrase, pc) Then
                Return pc.Count
            Else
                Return 0
            End If
        End Function

        Public Sub Reset() Implements ICategory.Reset
            m_TotalWords = 0
            m_Phrases.Clear()
        End Sub

        Private ReadOnly Property Phrases() As System.Collections.Generic.SortedDictionary(Of String, PhraseCount)
            Get
                Return m_Phrases
            End Get
        End Property

        Public Sub TeachCategory(ByVal reader As System.IO.TextReader) Implements ICategory.TeachCategory
            Dim re As New Regex("(\w+)\W*", RegexOptions.Compiled)
            Dim line As String = String.Empty
            While (InlineAssignHelper(line, reader.ReadLine())) IsNot Nothing
                Dim m As Match = re.Match(line)
                While m.Success
                    Dim word As String = m.Groups(1).Value
                    TeachPhrase(word)
                    m = m.NextMatch()
                End While
            End While
        End Sub

        Public Sub TeachPhrases(ByVal words As String()) Implements ICategory.TeachPhrases
            For Each word As String In words
                TeachPhrase(word)
            Next
        End Sub

        Public Sub TeachPhrase(ByVal rawPhrase As String) Implements ICategory.TeachPhrase
            If (m_Excluded IsNot Nothing) AndAlso (m_Excluded.IsExcluded(rawPhrase)) Then
                Exit Sub
            End If

            Dim pc As PhraseCount = New PhraseCount()
            Dim Phrase As String = DePhrase(rawPhrase)
            If Not m_Phrases.TryGetValue(Phrase, pc) Then
                pc = New PhraseCount(rawPhrase)
                m_Phrases.Add(Phrase, pc)
            End If

            pc.Count += 1
            m_TotalWords += 1
        End Sub

        Shared ms_PhraseRegEx As New Regex("\W", RegexOptions.Compiled)

        Public Shared Function CheckIsPhrase(ByVal s As String) As Boolean
            Return ms_PhraseRegEx.IsMatch(s)
        End Function

        Public Shared Function DePhrase(ByVal s As String) As String
            Return ms_PhraseRegEx.Replace(s, "")
        End Function

        Private Shared Function InlineAssignHelper(Of T)(ByRef target As T, ByVal value As T) As T
            target = value
            Return value
        End Function
    End Class

End Namespace