pyBestGuessCaesarDecryption

# Caesar Cypher Decoding
# Decode some text by finding out what Caesar offset produces the best looking result

intext = "evmvizekyvwzvcufwyldretfewcztknrjjfdltyfnvuspjfdrepkfjfwvn"

# Read a sample file of valid English words
# This wordlist can be found here:-   https://pastebin.com/VtvPbcAd
fin = open("mywords.txt")
alltext = fin.read()            # Read the whole file in one go
wordlist = alltext.split()      # Split the total text into words

# Try decoding the input text using all possible offsets, 1 to 25, in turn
# We will keep scores of good words found, for each offset (each score will be appended to this list)
countlist = [0]

# Each good word that is found in the decoded text, will add a score equal to the length of the word
# For example: it is considered much more significant to find the word "health" than to find "he"

for off in range(1, 26):            # Try each offset (1 to 25) in turn
    otext = ""
    for ch in intext:
        x = ord(ch) - ord('a')      # compute the distance of a letter from 'a'
        x += off                    # add the current offset
        x %= 26                     # wrap around 26 letters
        otext += chr(x + ord('a'))  # build the decoded output text

    # Now find all the valid English words that exist in the decoded text
    score = 0
    for w in wordlist:          # try each word in our sample English words list
        if w in otext:          # does this word exist in the decoded text?
            score += len(w)     # - yes - the score for this word is the length of the word

    countlist.append(score)     # append the total matching words score to our list of scores per offset

# Find the best scoring offset by examining our list of scores
best = max(countlist)

# Find the offset that made that biggest score
off = countlist.index(best)

# Now decode the encypted text once more, this time using the offset that gave the best results
otext = ""
for ch in intext:
    x = ord(ch) - ord('a')      # compute the distance of a letter from 'a'
    x += off                    # add the current offset
    x %= 26                     # wrap around 26 letters
    otext += chr(x + ord('a'))  # build the decoded output text

print(otext)                    # Print out our best attempt at the decoded text