Files

encoder.src test.src
encoder.src
  • // require lst
  • Encoder = {}
  • Encoder.CELL_LEN = 14
  • char_set = []
  • char_set.push(range(48, 57)) // numbers
  • char_set.push(range(65, 90)) // capital_letters
  • char_set.push(range(97, 122)) // letters
  • char_set.push(range(128, 193)) // extended
  • char_set = char_set.flat // <- 7 bit char set
  • Encoder.CHAR_SET = char_set
  • // UTILS ------------------------------------------------------
  • Encoder.Utils = {}
  • Encoder.Utils.to_bin = function(n)
  • if n == 0 then return "0"
  • if n == 1 then return "1"
  • return self.to_bin(floor(n / 2)) + str(n % 2)
  • end function
  • Encoder.Utils.to_int = function(n)
  • n = n.values
  • n.reverse
  • r = 0
  • for i in n.indexes
  • if n[i] == "1" then
  • r = r + 2 ^ i
  • end if
  • end for
  • return r
  • end function
  • Encoder.Utils.divide = function(s, n)
  • if s.len == 0 then
  • return []
  • end if
  • if s.len < n then
  • //prepend = "0" * (n - s.len)
  • //s = prepend + s
  • return [s]
  • end if
  • return self.divide(s[n:], n).insert(0, s[0:n])
  • end function
  • // -------------------------------------------------------------
  • Encoder.encode = function(lzw)
  • l = lzw[0:]
  • CELL_SIZE = 0
  • for i in l.indexes
  • if l[i] isa string then l[i] = l[i].code
  • l[i] = self.Utils.to_bin(l[i])
  • if l[i].len > CELL_SIZE then CELL_SIZE = l[i].len
  • end for
  • for i in l.indexes
  • l[i] = "0" * (CELL_SIZE - l[i].len) + l[i]
  • end for
  • l = l.join("")
  • FAT_ADDED = l.len % 7
  • if FAT_ADDED > 0 then FAT_ADDED = 7 - FAT_ADDED
  • l = l + "0" * FAT_ADDED
  • l = self.Utils.divide(l, 7)
  • fat_bin = self.Utils.to_bin(FAT_ADDED)
  • l.insert(0, "0" * (6 - fat_bin.len) + fat_bin)
  • l.insert(0, "0" * (7 - fat_bin.len) + fat_bin)
  • cell_bin = self.Utils.to_bin(CELL_SIZE)
  • l.insert(0, "0" * (6 - cell_bin.len) + cell_bin)
  • l.insert(0, "0" * (7 - cell_bin.len) + cell_bin)
  • l = self.Utils.divide(l.join(""), 7)
  • //print l
  • for i in l.indexes
  • l[i] = char(self.CHAR_SET[self.Utils.to_int(l[i])])
  • end for
  • return l.join("")
  • end function
  • Encoder.decode = function(string)
  • l = string.values
  • for i in l.indexes
  • l[i] = self.Utils.to_bin(self.CHAR_SET.indexOf(l[i].code))
  • l[i] = "0" * (7 - l[i].len) + l[i]
  • end for
  • l[-1] = l[-1][2:]
  • //l[-1] = l[-1][2:]
  • l = l.join("")
  • CELL_SIZE = self.Utils.to_int(l[0:6])
  • FAT_ADDED = self.Utils.to_int(l[6: 12])
  • CELL_SIZE = self.Utils.to_int(l[0:7])
  • FAT_ADDED = self.Utils.to_int(l[7: 14])
  • l = self.Utils.divide(l[12:], 7)
  • l[-1] = l[-1][0:FAT_ADDED * -1]
  • l = self.Utils.divide(l[14:], 7)
  • //print l
  • if FAT_ADDED > 0 then l[-1] = l[-1][0:FAT_ADDED * -1]
  • //print l
  • l = self.Utils.divide(l.join(""), CELL_SIZE)
  • for i in l.indexes
  • l[i] = self.Utils.to_int(l[i])
  • if l[i] < 256 then l[i] = char(l[i])
  • end for
  • return l
  • end function
test.src
  • import_code("/home/me/projects/lzw/libs/lst.src")
  • import_code("/home/me/projects/lzw/lzw.src")
  • import_code("/home/me/projects/lzw/encoder.src")
  • input = user_input("in: ")
  • compressed = Lzw.compress(input)
  • //compressed = Lzw.compress("TOBEORNOTTOBEORTOBEORNOT")
  • print "compressed: " + compressed
  • //compressed = Lzw.compress("ffffffffffffffffffffffff")
  • //print "compressed: " + compressed
  • e = Encoder.encode(compressed)
  • print "encoded: " + e
  • dd = Lzw.decompress(Encoder.decode(e))
  • print "decoded and decompressed: " + dd
  • //print "decoded and decompressed: " + dd
  • if input != dd then exit("<color=red>ERROR</color>")
  • print "input len: " + input.len
  • print "encoded len: " + e.len
  • print input
  • print dd
  • print input == dd
  • print "text reduced by: " + round(100 - (e.len / input.len * 100), 2) + "%"
  • //print input
  • //print dd
  • //print input == dd