Add decoding script

huffman-coding.py

@@ -18,63 +18,88 @@ def find_node(nodes, target_character):
 	# if desired character not found, return empty list
     return []
 
-# retrieve text to encode
+def encode(txt):
-txt = input("Text: ")
+	# create list of tuples in descending order of frequency: (character, frequency)
+	info = Counter(txt).most_common()
+	# change the list into ascending order
+	info.reverse()
+	# create list for character tuples
+	nodes = []
+	# create list for node usage frequencies
+	frequencies = []
 
-# create list of tuples in descending order of frequency: (character, frequency)
+	# copy nodes and their usage frequencies to the dedicated lists
-info = Counter(txt).most_common()
+	for item in info:
-# change the list into ascending order
+		nodes.append(item[0])
-info.reverse()
+		frequencies.append(item[1])
-# create list for character tuples
-nodes = []
-# create list for node usage frequencies
-frequencies = []
 
-# copy nodes and their usage frequencies to the dedicated lists
+	# repeat until only one top-level node exists
-for item in info:
+	while len(nodes) > 2:
-	nodes.append(item[0])
+		# combine two least frequent characters' nodes into a new tuple node, containing the old nodes (old_node_1, old_node_2)
-	frequencies.append(item[1])
+		new_node = (nodes[0], nodes[1])
+		# combine two least frequent characters' frequencies into a total frequency, to be used at the top level of the list of nodes
+		new_frequency = frequencies[0] + frequencies[1]
+		#  remove nodes that have been nested inside the new node
+		del nodes[0:2]
+		#  remove frequencies that have been summed and added to the new frequency
+		del frequencies[0:2]
 		
-# repeat until only one top-level node exists
+		# find index of last node with frequency below that of the new node
-while len(nodes) > 2:
+		# if the largest frequency is smaller than the new one, place the new node at the end of the list
-	# combine two least frequent characters' nodes into a new tuple node, containing the old nodes (old_node_1, old_node_2)
+		if (frequencies[-1] < new_frequency):
-	new_node = (nodes[0], nodes[1])
+			i = -1
-	# combine two least frequent characters' frequencies into a total frequency, to be used at the top level of the list of nodes
+		else:
-	new_frequency = frequencies[0] + frequencies[1]
+			# else, loop over every frequency
-	#  remove nodes that have been nested inside the new node
+			for index, item in enumerate(frequencies):
-	del nodes[0:2]
+				# if the frequency is greater than or equal to the new frequency
-	#  remove frequencies that have been summed and added to the new frequency
+				if (item >= new_frequency):
-	del frequencies[0:2]
+					# record the index to insert the frequency at
+					i = index
+					# stop looping
+					break
 		
-	# find index of last node with frequency below that of the new node
+		# insert the new node in its rightful position, maintaining ascending order of frequency
-	# if the largest frequency is smaller than the new one, place the new node at the end of the list
+		nodes.insert(i, new_node)
-	if (frequencies[-1] < new_frequency):
+		# insert the new frequency in its rightful position, maintaining ascending order of frequency
-		i = -1
+		frequencies.insert(i, new_frequency)
-	else:
-		# else, loop over every frequency
-		for index, item in enumerate(frequencies):
-			# if the frequency is greater than or equal to the new frequency
-			if (item >= new_frequency):
-				# record the index to insert the frequency at
-				i = index
-				# stop looping
-				break
 
-	# insert the new node in its rightful position, maintaining ascending order of frequency
+	# print all nodes
-	nodes.insert(i, new_node)
+	print("Nodes: %s" % nodes)
-	# insert the new frequency in its rightful position, maintaining ascending order of frequency
-	frequencies.insert(i, new_frequency)
 
-# print all nodes
+	# encrypted text
-print("Nodes: %s" % nodes)
+	output = ""
 
-# encrypted text
+	# for every character in the text to be encrypted
-output = ""
+	for char in txt:
+		# find its path and add it to the encrypted text
+		output += "".join(find_node(nodes, char))
 
-# for every character in the text to be encrypted
+	# print encoded message
-for char in txt:
+	print("Encoded message: %s" % output)
-	# find its path and add it to the encrypted text
-	output += "".join(find_node(nodes, char))
 	
-# print encrypted message
+	# return encoded message
-print("Encrypted message: %s" % output)
+	return [output, nodes]
+
+def decode(txt, nodes):
+	# string to hold decoded message
+	output = ""
+	# replicate nodes, for looping over and editing with the first part of the code
+	node = nodes
+	# for each digit
+	for digit in txt:
+			# get the node with the corresponding index
+			node = node[int(digit)]
+			# if the retrieved node isn't a tuple (i.e. it isn't a parent node)
+			if (not isinstance(node, tuple)):
+				# add the node's content to the output
+				output += node
+				# replace the retrieved node with the whole tree again, for looping over and editing with the next part of the code
+				node = nodes
+
+	# print decoded message
+	print("Decoded message: %s" % output)
+	# return decoded message
+	return output
+
+encoding = encode(input("Text: "))
+decode(encoding[0], encoding[1])