notebook_filename = 'T & C Message Decode 1623_v33.ipynb' 
from google.colab import drive
drive.mount('/content/drive')

import os
import csv
import pandas as pd
import shutil
import datetime

# Project Purpose:
#
# Decoding the message secretly embedded in the text of the Shakespearen play,
#'Trolious and Cressida'
# by Sir Francis Bacon, using his Biliteral Cipher (Binary Code) as described 
# in his 1623 book, The Advancement of Learning.
project_name = 'T & C Prologue Decode 1623'
# Derive input and output directories:
# Root Directory for project content on Google Drive:
content_dir = '/content/drive/MyDrive'
project_dir = content_dir + '/' + project_name 
data_upload_dir = project_dir + '/text data to upload - tsv/upload/'

#Input File path (1 total):
input_filename = 'v21.tsv'
data_upload_file = os.path.join(data_upload_dir, input_filename)

#Output File Directory paths (5 total):
original_text_dir = project_dir + '/original text - csv/' 
biliterals_dir = project_dir + '/biliterals - csv/' 
output_data_table_dir = project_dir + '/output data table - csv/' 
decoded_message_dir = project_dir + '/decoded message - csv/'
notebook_dir = project_dir + '/notebook - ipynb/'
archive_dir = project_dir + '/archive - zip/'

if os.path.isfile(data_upload_file):
  print(data_upload_file)
if os.path.isdir(original_text_dir):
  print(original_text_dir)
if os.path.isdir(biliterals_dir):
  print(biliterals_dir)
if os.path.isdir(output_data_table_dir):
  print(output_data_table_dir)
if os.path.isdir(decoded_message_dir):
  print(decoded_message_dir)
if os.path.isdir(notebook_dir):
  print(notebook_dir)  
if os.path.isdir(archive_dir):
  print(archive_dir)

import datetime
now = datetime.datetime.now()
output_filename = now.strftime("%Y-%m-%d_%H-%M-%S")
#print (output_filename)

# Decode a five bit binary word into an English Alphabet letter.
# There were 22 letters in the Elizabethan English Alphabet:
#   'I' = 'J'
#   'U' = 'V'
# therefore 5 binary digits are more than enough, 2 (exp) 5 = 32
def decode_biliteral(which):
  decode = {
  'aaaaa': 'a',
  'aaaab': 'b',
  'aaaba': 'c',
  'aaabb': 'd',
  'aabaa': 'e',
  'aabab': 'f',
  'aabba': 'g',
  'aabbb': 'h',
  'abaaa': 'i',
  'abaab': 'k',
  'ababa': 'l',
  'ababb': 'm',
  'abbaa': 'n',
  'abbab': 'o',
  'abbba': 'p',
  'abbbb': 'q',
  'baaaa': 'r',
  'baaab': 's',
  'baaba': 't',
  'baabb': 'v',
  'babaa': 'w',
  'babab': 'x',
  'babba': 'y',
  'babbb': 'z'
  }
  which_letter = decode[which]
  return which_letter

# Read the input text data from the .tsv file:
print(data_upload_file)
input_data_table = pd.read_csv(data_upload_file, sep='t', header=None)

# De-interlace the original text from the book page text, and store it separately:
original_text = input_data_table.iloc[0::3, :]
ot_path = original_text_dir + output_filename + '.csv'
original_text.to_csv (ot_path, index = None, header=True) 
#original_text

# De-interlace the biliterals (an 'a' or 'b' quintet) from the book page text, and store it separately:
biliterals = input_data_table.iloc[1::3, :]
blt_path = biliterals_dir + output_filename + '.csv'
biliterals.to_csv (blt_path, index = None, header=True) 
#biliterals

# Make a copy of the input data frame, and write rows of decoded biliterals into it:
output_encoded_dataframe = input_data_table.copy(deep=True)
encoded_text_size = 0
original_text_letters = ''
for row in range(2,45,3):
  for column in range(14):
    letter = output_encoded_dataframe.loc[row - 2,column] 
    biliteral = output_encoded_dataframe.loc[row - 1,column] 
    which_letter = decode_biliteral(biliteral)
    output_encoded_dataframe.loc[row,column] = which_letter
    encoded_text_size += 5
    original_text_letters += letter
odt_path = output_data_table_dir + output_filename + '.csv'
output_encoded_dataframe.to_csv (odt_path, index = None, header=True) 
output_encoded_dataframe

decoded_message = ''
biliteral_values = ''
with open(decoded_message_dir + '.csv', 'w') as new_f:
  for row in range(0,15,1):
    for column in range(14):
      biliteral = biliterals.iloc[row, column]
      which_letter = decode_biliteral(biliteral)
      decoded_message += which_letter
      biliteral_values += biliteral 
print('Encoded Text Size: ' + str(encoded_text_size))
print('Biliterals Text Size: ' + str (len(biliteral_values)))
print('Decoded Text Size: ' + str(len(decoded_message)))
print('n')
print('Raw Decoded Message: ' + decoded_message)

!jupyter nbconvert --to html '/content/drive/MyDrive/Colab Notebooks/T_&_C_Message_Decode_1623_v33.ipynb'