def process_gloss()

in data_parsing.py [0:0]

• 13 lines of code
• 3 McCabe index (conditional complexity)

def process_gloss(line):
	depth = len(line)-len(line.lstrip('#')) #to get number of # at beginning of line
	line = line.strip('#').strip()

	#strip out tags, comments
	gloss = re.sub(r'{{lb.*?}}', '', line).strip()
	gloss = re.sub(r'<!--.*?-->', '', gloss).strip()
	gloss = clean_text(gloss)

	#ignore senses with no gloss or only tags in gloss (not text)
	if len(gloss) == 0 or len(re.sub(r'\(.*?\)\.?', '', gloss.strip())) == 0: 
		return -1, -1, -1 
	
	#parse tags
	tags = []
	t = re.search(r'{{lb(.*?)}}', line)
	if t: 
		tags = t.group(1).strip().split('|')[1:]

	return gloss, depth, tags