I am trying to write a program in python which searches for user specified words in a txt file and copies the selected lines containing that word into another file.
Also the user will have an option to exclude any word.
(e.g Suppose the user searches for the word "exception" and want to exclude the word "abc", then the code will only copy the lines which has "exception" in it but not "abc").
Now all the work will be done from the command prompt.
The input would be:
file.py test.txt(input file) test_mod.txt(output file) -e abc(exclude word denoted by -e)-s exception(search word denoted by -s)
Now the user will have an option to enter multiple exclude words and multiple search words.
I have done the program using the argparse module and it runs.
My problem is it only takes lower case words as search or exclude words. That is if I type "exception" as search word, it does not find "Exception" or "EXCEPTION". How do I solve this prob? I want to ignore case on both search and exclude words.
Here's my code as of now:
import sys
import os
import argparse
import tempfile
import re
def main(): #main method
try:
parser = argparse.ArgumentParser(description='Copies selected lines from files') #Defining the parser
parser.add_argument('input_file') #Adds the command line arguments to be given
parser.add_argument('output_file')
parser.add_argument('-e',action="append")
parser.add_argument('-s',action="append")
args = parser.parse_args() #Parses the Arguments
user_input1 = (args.e) #takes the word which is to be excluded.
user_input2 = (args.s) #takes the word which is to be included.
def include_exclude(input_file, output_file, exclusion_list=[], inclusion_list=[]): #Function which actually does the file writing and also handles exceptions
if input_file == output_file:
sys.exit("ERROR! Two file names cannot be the same.")
else:
try:
found_s = False #These 3 boolean variables will be used later to handle different exceptions.
found_e = False
found_e1 = True
with open(output_file, 'w') as fo: #opens the output file
with open(input_file, 'r') as fi: #opens the input file
for line in fi: #reads all the line in the input file
if user_input2 != None:
inclusion_words_in_line = map(lambda x: x in line, inclusion_list)#Mapping the inclusion and the exclusion list in a new list in the namespace
if user_input1 != None and user_input2 != None: #This list is defined as a single variable as condition operators cannot be applied to lists
exclusion_words_in_line = map(lambda x: x in line, exclusion_list)
if any(inclusion_words_in_line) and not any(exclusion_words_in_line): #Main argument which includes the search word and excludes the exclusion words
fo.write(line) #writes in the output file
found_s = True
elif user_input1 == None and user_input2 != None: #This portion executes if no exclude word is given,only the search word
if any(inclusion_words_in_line):
fo.write(line)
found_e = True
found_s = True
found_e1 = False
if user_input2 == None and user_input1 != None: #No search word entered
print("No search word entered.")
if not found_s and found_e: #If the search word is not found
print("The search word couldn't be found.")
fo.close()
os.remove(output_file)
elif not found_e and not found_s: #If both are not found
print("\nNOTE: \nCopy error.")
fo.close()
os.remove(output_file)
elif not found_e1: #If only the search word is entered
print("\nNOTE: \nThe exclusion word was not entered! \nWriting only the lines containing search words")
except IOError:
print("IO error or wrong file name.")
fo.close()
os.remove(output_file)
if user_input1 != user_input2 : #this part prevents the output file creation if someone inputs 2 same words creating an anomaly.
include_exclude(args.input_file, args.output_file, user_input1, user_input2);
if user_input1 == user_input2 : #This part prevents the program from running further if both of the words are same
sys.exit('\nERROR!!\nThe word to be excluded and the word to be included cannot be the same.')
except SystemExit as e: #Exception handles sys.exit()
sys.exit(e)
if __name__ == '__main__':
main()