Imports System
Imports System.Collections.Generic
Imports System.Text
'
' =====================================================================
' High‑Performance Reversible Text Compression Using a Word Dictionary
' ---------------------------------------------------------------------
' This program compresses text by replacing repeated words with tokens
' like @0, @1, @2... and stores each unique word in a dictionary.
'
' The compressed text is fully reversible.
'
' WHY THIS VERSION IS FAST (VB.NET):
' ---------------------------------
' • Uses Dictionary(Of String, Integer) for O(1) average lookup.
' • Uses List(Of String) for compact dictionary storage.
' • Uses StringBuilder for efficient string construction.
' • Manual scanning avoids regex overhead.
' • Clean, idiomatic, modern VB.NET design.
'
' OUTPUT EXAMPLE:
' Original: this is is a test test compression string string test
' Compressed: @0 @1 @1 @2 @3 @3 @4 @5 @5 @3
' Decompressed: this is is a test test compression string string test
' =====================================================================
'
Module WordDictionaryCompression
' -----------------------------------------------------------------
' Dictionary structure: List + Dictionary
' -----------------------------------------------------------------
Public Class WordDictionary
Public Words As New List(Of String)() ' index → word
Public IndexMap As New Dictionary(Of String, Integer)() ' word → index
End Class
' -----------------------------------------------------------------
' Find or add a word to the dictionary (O(1) average)
' -----------------------------------------------------------------
Function FindOrAdd(dict As WordDictionary, word As String) As Integer
Dim existing As Integer
If dict.IndexMap.TryGetValue(word, existing) Then
Return existing
End If
Dim newIndex As Integer = dict.Words.Count
dict.Words.Add(word)
dict.IndexMap(word) = newIndex
Return newIndex
End Function
' -----------------------------------------------------------------
' Compress text into @ID tokens
' -----------------------------------------------------------------
Function Compress(input As String, dict As WordDictionary) As String
Dim out As New StringBuilder(input.Length * 2)
Dim i As Integer = 0
While i < input.Length
Dim c As Char = input(i)
' Pass punctuation/spaces directly
If Not Char.IsLetterOrDigit(c) Then
out.Append(c)
i += 1
Continue While
End If
' Extract word
Dim start As Integer = i
While i < input.Length AndAlso Char.IsLetterOrDigit(input(i))
i += 1
End While
Dim word As String = input.Substring(start, i - start)
' Get dictionary index
Dim id As Integer = FindOrAdd(dict, word)
' Write token
out.Append("@"c)
out.Append(id)
End While
Return out.ToString()
End Function
' -----------------------------------------------------------------
' Decompress @ID tokens back into original text
' -----------------------------------------------------------------
Function Decompress(compressed As String, dict As WordDictionary) As String
Dim out As New StringBuilder(compressed.Length * 2)
Dim i As Integer = 0
While i < compressed.Length
Dim c As Char = compressed(i)
' Token?
If c = "@"c Then
i += 1
Dim id As Integer = 0
' Parse digits
While i < compressed.Length AndAlso Char.IsDigit(compressed(i))
id = id * 10 + (Convert.ToInt32(compressed(i)) - Convert.ToInt32("0"c))
i += 1
End While
If id >= 0 AndAlso id < dict.Words.Count Then
out.Append(dict.Words(id))
End If
Else
' Pass punctuation/spaces
out.Append(c)
i += 1
End If
End While
Return out.ToString()
End Function
' -----------------------------------------------------------------
' Main
' -----------------------------------------------------------------
Sub Main()
Dim original As String =
"this is is a test test compression string string test " &
"this is a test compression"
Dim dict As New WordDictionary()
Dim compressed As String = Compress(original, dict)
Dim decompressed As String = Decompress(compressed, dict)
Console.WriteLine("Original: """ & original & """")
Console.WriteLine("Compressed: """ & compressed & """")
Console.WriteLine("Decompressed: """ & decompressed & """" & Environment.NewLine)
Console.WriteLine("Dictionary:")
For i As Integer = 0 To dict.Words.Count - 1
Console.WriteLine(" @" & i & " => " & dict.Words(i))
Next
End Sub
End Module
'
' run:
'
' Original: "this is is a test test compression string string test this is a test compression"
' Compressed: "@0 @1 @1 @2 @3 @3 @4 @5 @5 @3 @0 @1 @2 @3 @4"
' Decompressed: "this is is a test test compression string string test this is a test compression"
'
' Dictionary:
' @0 => this
' @1 => is
' @2 => a
' @3 => test
' @4 => compression
' @5 => string
'
