'''
Count the number of times each character appears in the ciphertext file
Saves counts into a file named <ciphertext filename>.counts.csv

Author: Tim Pierson, Dartmouth CS55, Winter 2021
Usage: python3 counts.py <ciphertext filename>
'''
import sys
alphabet = 'abcdefghijklmnopqrstuvwxyz' #only consider these characters

if __name__ == '__main__':
	#usage check: make sure we got a filename to read
	if len(sys.argv) != 2:
		print("Usage: python3 counts.py <ciphertext filename>")
		print("Looks like you did not provide a filename")
		exit()

	#read ciphertext file into variable named text
	f = open(sys.argv[1], "r")
	text = f.read()
	f.close()

	#get unique characters in text (sorted here for debugging)
	#use a set for efficiency!
	characters = ''.join(sorted(set(text))) #characters is a string
	print("Ciphertext is:")
	print(text)
	
	print("\nUnique characters are:")
	print(characters)

	#add missing characters from our alphabet so we get a zero count for them
	for c in alphabet:
		if not c in characters:
			characters += c #append character from alphabet not in ciphertext

	#count how many times each character found in ciphertext
	counts = {}
	for c in characters: 
		counts[c] = text.count(c)

	#print in descending sorted order
	#also save as csv for later analysis
	print("Character counts in descending order:")	
	f = open(sys.argv[1]+".counts.csv","w")
	for key, value in sorted(counts.items(), key=lambda item: item[1], reverse=True):
		if key in alphabet: #do not include punctuation here
			print(key,value)
			f.write(key+","+str(value)+"\n")
	f.close()