first_prototype_grammar_checker.py

import re 
import os.path
import time 

# start = time. time()


def MeSH_DB(data_folder): 

# Source: https://www.nlm.nih.gov/mesh/2019/download/2019New_Mesh_Tree_Hierarchy.txt
# can we invoke this through API 

     # Import the MeSH to be checked against
     data_file = os.path.join(data_folder, "MeSH_keywords.txt")
     
     # finding the keyword in the file 
     with open (data_file, "r+") as f:
          
         
     
          for line in f:
               if line.startswith("TREE_NUMBER") == True or line.startswith("----") == True or not line.strip():
               # Skipping title line , -----grid and empty lines 
                      next(f)
    
               else:
                      MeSH_term = "" # create an empty term to store the MeSH item in each line
               
                      MeSH_entry = {} # empty dictionary to store the final indexed entry 
                
                      split_result = re.split(" ", line)
               
                      split_result = list(filter(None, split_result)) # remove all the empty strings " "
               
                      MeSH_index = split_result.pop(0) # store the first item as index
               
                      if split_result[-1] == "\n": # remove the last item 
                             split_result.pop(-1)
               
                      MeSH_term = str.join(" ", split_result) # join every term left into a single string
               
                      MeSH_entry = {"MeSH_index" : MeSH_index, "MeSH_term": MeSH_term} # store the index and term
                      
                      yield MeSH_term
               
                      
          # print (MeSH_list) # takes around 1.5s slower than the generator function 
                      
generator = MeSH_DB("/Users/annatswater/Desktop/ChallengeCup_2019")

x = (list(generator)) # must be a list or else cannot search for the word


# end = time. time()
# print(end - start)


# Multiline input in GUI: https://stackoverflow.com/questions/9661854/how-to-create-a-multiline-entry-with-tkinter
# Iteration through list and file: https://stackoverflow.com/questions/51297805/in-python-searching-a-text-file-for-multiple-words-and-printing-the-correspondi


# The next function needs to accept a chunk of text in a textbox 
# set the size to be big 
# if matches value of "MeSH_Term" in the dictionary (a list of dictionary) 
# change color into red
# or at least count the times the term occurs 

with open ("/Users/annatswater/Desktop/ChallengeCup_2019/new_text_file.txt", "r+") as input_file:
      for line in input_file:
           if any(word in line for word in x): 
              print(line) # cannot print the word; undefined
        
         
         # or highlight each word, and then count numbers of highlighted words and then do cluster counts 
         # but how can i do this now that I have ruined the formatting 
         
         
# take each line as a string 
# find the keyword in each line

#for line in fruit_list:
    #if any(word in line for word in search_words):
        #print(line)


     
            
# https://stackoverflow.com/questions/18366554/how-to-search-for-word-in-text-file-and-print-part-of-line-with-python