Compression Program

-- This is eniallator's Compression program that takes an input file and then you can choose to either compress it or decompress it.
-- The way compression works is by making a table of all the different words that come up in the file.
-- It will then instead of putting the word in the actual body of the file, it will just put the index of the table that the program has to search for.
-- The index is in the form of a byte and i use string.char() and string.byte() to convert between the 2.
--
-- ================================================================================
--
-- Im currently using the following numbers for special cases:
-- 0 = bigger than 255, 1 = new line, 2 = multiple spaces, 3 = 1 space
--
-- I also don't use 13 because when LUA converts character 13 back to it's number, it will be the same result as byte 10.
-- Aparts from that, every other byte i just use to index the words.

local tArgs = { ... }

-- Function to return a table of the lines of a file
function fileToLines(file)

  local read = fs.open(file,"r")
  local lines = {}

  -- While loop to keep on adding the current line to a table and if theres no current line, it will break
  while true do

    local currLine = read.readLine()

    if currLine then

      table.insert(lines, currLine)
    else

      break
    end
  end

  read.close()
  return lines
end

-- Function to split a string up at its spaces
local function wordSplit(string)

  local out = {}

  -- For loop to iterate over the words in the string
  for word in string:gmatch("%S+") do

    table.insert(out, word)
  end

  return out
end

-- Function that compression uses, if the number given in the arguments is bigger than 254 it will keep on adding the byte 0 to the return
local function checkNum(num)

  local out = ""

  -- While to iterate when num is bigger than 254
  while num > 254 do

    out = out .. string.char(0)
    num = num - 254
  end

  -- Making sure num isn't byte 13
  if num >= 13 then num = num + 1 end

  -- Returning the bytes instead of the number.
  return out .. string.char(num)
end


-- Function to add any new words to the index
local function sortWord(word,outTbl,line)
  if #word > 0 then

    local wordFound = false

    -- Iterating over the first index of outTable
    for i=1,#outTbl[1] do

      -- Checking if the word already exists or not
      if outTbl[1][i] == word then

        table.insert(outTbl[line+1],i+3)
        wordFound = true
        break
      end
    end

    -- Adding the word to the index if it hasn't been found
    if not wordFound then

      table.insert(outTbl[1],word)
      table.insert(outTbl[line+1],#outTbl[1]+3)
    end
  end

  return outTbl
end

-- Function to handle spaces in the file
local function sortSpaces(spaces,outTbl,line)
  if spaces > 0 then

    -- Checking if the number of spaces is bigger than 1 so it can add a different byte depending on if it is or not
    if spaces > 1 then

      table.insert(outTbl[line+1],2)
      table.insert(outTbl[line+1],spaces)
    else

      table.insert(outTbl[line+1],3)
    end
  end

  return outTbl
end

-- The compression function
function compress(lines)

  local outTable = {{}}

  for line=1,#lines do

    local spaces = 0
    local word = ""
    outTable[line+1] = {}

    -- For to handle the entire compression to convert the file into bytes
    for i=1,#lines[line] do

      local currChar = lines[line]:sub(i,i)

      -- A crude way to split up the lines into words and spaces
      if currChar == " " then

        spaces = spaces + 1
        outTable = sortWord(word,outTable,line)
        word = ""
      else

        word = word .. currChar
        outTable = sortSpaces(spaces,outTable,line)
        spaces = 0
      end
    end

    outTable = sortWord(word,outTable,line)
    outTable = sortSpaces(spaces,outTable,line)
  end

  local outString = ""

  -- For loop to combine the outTable into an output string
  for i=1,#outTable do
    for j=1,#outTable[i] do
      if i == 1 then
        if #outString > 0 then outString = outString .. " " end

        outString = outString .. outTable[i][j]
      else

        outString = outString .. checkNum(outTable[i][j])
      end
    end

    -- Adding the new line character to the end of the line. The index is always at line 1 so i choose to add a \n to the end of line 1
    if i == 1 then

      outString = outString .. "\n"
    else

      outString = outString .. string.char(1)
    end
  end

  return outString
end

-- The decompression function
function decompress(lines)

  -- Seperating the index table from the body table
  local index = wordSplit(lines[1])
  local body = {}
  table.remove(lines,1)

  -- For to convert the compressed file into it's original lines and where the indexes should go
  for line=1,#lines do

    -- Inserting the character 10 every time the file goes onto a new line. This is because character 10 actually is the new line character
    if line > 1 then

      table.insert(body,10)
    end

    -- For loop to convert the bytes into the corresponding indexes
    for i=1,#lines[line] do

      local indexNum = string.byte(lines[line]:sub(i))

      if indexNum >= 13 then

        indexNum = indexNum - 1
      end

      table.insert(body,indexNum)
    end
  end

  local counter = 1
  local fullFile = ""

  -- While loop to convert the indexes into the corresponding words (aparts from the special characters)
  while counter < #body do

    -- Checking if the current index is 0 and then converting it into it's actual index (because 0 means it's bigger than 254)
    if body[counter] == 0 then

      local multiples = 0

      -- Adding up the multiples of 254
      while body[counter] == 0 do

        counter = counter + 1
        multiples = multiples + 254
      end

      -- Inserting the corresponding word with the full index from adding the multiples and the current index
      fullFile = fullFile .. index[body[counter] + multiples-3]

    -- Seeing if the current index is 1 which is the new line character
    elseif body[counter] == 1 then

      fullFile = fullFile .. "\n"

    -- Seeing if the current index is 2 and then seeing what the next index is to make that next index * spaces.
    elseif body[counter] == 2 then

      counter = counter + 1

      -- Iterating for the amount of spaces that should be in and adding them
      for i=1,body[counter] do

        fullFile = fullFile .. " "
      end

    -- Seeing if the current index is 3 and inserting a space into the file
    elseif body[counter] == 3 then

      fullFile = fullFile .. " "

    -- If nothing before has caught the index, the corresponding word to that index will be inserted into the file.
    else

      fullFile = fullFile .. index[body[counter]-3]
    end

    counter = counter + 1
  end

  return fullFile
end

-- Handling program arguments
if tArgs[1] == "com" then
  if tArgs[2] and fs.exists(tArgs[2]) then
    if tArgs[3] then

      comString = compress(fileToLines(tArgs[2]))

      openFile = assert(fs.open(tArgs[3],"w"),"Something went wrong when trying to open the output file")
      openFile.write(comString)
      openFile.close()
    else

      print("Error: Compression requires a third argument")
    end
  else

    print("Error: Compression requires a valid file name as the second argument.")
  end
elseif tArgs[1] == "decom" then
  if tArgs[2] and fs.exists(tArgs[2]) and tArgs[3] then
    if tArgs[3] then

      comString = decompress(fileToLines(tArgs[2]))

      openFile = assert(fs.open(tArgs[3],"w"),"Something went wrong when trying to open the output file")
      openFile.write(comString)
      openFile.close()
    else

      print("Error: Decompression requires a third argument")
    end
  else

    print("Error: Decompression requires a valid file name as the second argument.")
  end
else

  print('Error: Invalid syntax. Correct syntax is: "compress [com/decom] [input file name] [output file name]"')
end