#!/usr/bin/env python
# coding: utf-8

# # Check feature monad

# In the context of a corpus, the term "monad" refers to a unit of textual analysis or a discrete linguistic unit. Specifically, in this Text-Fabric dataset, it is employed to denote the sequence number of an individual word within the entire corpus, specifically the New Testament.
# 
# Hence, in the tf file the value for monad should nicely increment by one. This script checks this.

# In[9]:


import os
# Following variable should contain the relative path to the 'monad' tf file to check 
FileToCheck = "..//tf//0.4//monad.tf"

def process_file(file_path):
    LinesToPrint=10
    PrintedLines=0
    PreviousMonadValue=0
    Result ="Filecontent is OK (i.e. sequential)"
    with open(file_path, "r") as file:
       print("Analyzing: ", end='', flush=True)
       for line in file:
            if line.startswith("@"):
                continue  # Skip lines that start with "@"
            if line.startswith("\n"):
                continue  # Skip lines that start with " "
            CurrentMonadValue=int(line.replace("\n", ""))
            if CurrentMonadValue % 10000 == 0:
                print(".", end='', flush=True)  # Print a dot without a new line for every 10000th monad value
            if CurrentMonadValue-1==PreviousMonadValue:
                PreviousMonadValue=CurrentMonadValue
            else:
                Result="Found something wrong. Monad"+CurrentMonadValue+"after"+PreviousMonadValue
                break
    print ("\n",Result)   
         
# Main part
#First check if the file exist, then check its content
if os.path.exists(FileToCheck):
    print(f"The file {FileToCheck} exist and will be checked")
    process_file(FileToCheck)
else:
    print(f"Could not find file {FileToCheck}.")


# In[ ]: