def main()

in data_parsing.py [0:0]

• 29 lines of code
• 5 McCabe index (conditional complexity)

def main(args):
	#load wikitionary dump data file
	start_time = time.time()
	f = open(args.wiki_file, 'r')

	#track status in file
	curr_page = []
	is_page = False

	#track all info for dataset
	senses = []

	#scan through file and process pages sequentially 
	for line in f:
		line = line.strip()
		if line == '<page>': 
			is_page = True
		elif line == '</page>': 
			s = process_page(curr_page)
			if s != -1: senses.extend(s)
			is_page = False
			curr_page = []
		else:
			#drop empty lines
			if is_page and len(line)>0: curr_page.append(line)
	f.close()
	print(len(senses), '{:.2f}'.format(time.time()-start_time))

	#add post-processing to seperate out quotes, examples into seperate lists
	senses, quotations, examples = post_processing(senses)

	#make save dir if it doesn't exist
	if not os.path.exists(args.save_dir):
		os.makedirs(args.save_dir)

	#save senses
	s_path = os.path.join(args.save_dir, 'senses.txt')
	save_senses(s_path, senses)

	#save examples
	e_path = os.path.join(args.save_dir, 'examples.txt')
	save_examples(e_path, examples)

	#save quotes
	q_path = os.path.join(args.save_dir, 'quotations.txt')
	save_quotations(q_path, quotations)

	return