pig_latin_translator.py

# Pig Latin Translator in Python
# Jonah Lawrence
# January 2020

import re


def translate(message: str) -> str:
	"""translate a message to pig latin"""

	# common English digraphs
	digraphs = {"bh", "bl", "br", "bw", "ch", "chr", "cl", "cr", "cz",
				"dh", "dr", "dw", "fl", "fr", "fw", "gh", "gl", "gn",
				"gr", "kh", "kl", "kn", "kr", "kw", "lh", "ll", "ph",
				"pl", "pr", "ps", "pw", "qu", "rh", "sc", "sch", "schm",
				"schw", "scr", "sh", "shl", "shm", "shn", "shqu", "shr",
				"shw", "sk", "sl", "sm", "sn", "sp", "sph", "spr", 
				"squ", "st", "str", "sw", "szch", "tch", "th", "thr", 
				"tr", "ts", "tw", "vh", "vh", "vlwh", "wr", "xh", "zh"}

	def translate_word(word: str) -> str:
		"""translate an individual word to pig latin"""
		# starts with a vowel
		if word[0].lower() in {"a", "e", "i", "o", "u"}:
			return word + "way"
		# starts with a digraph, checking lengths largest to smallest
		digraph_length = max(len(x) for x in digraphs)
		while digraph_length >= 2:
			if word[:digraph_length].lower() in digraphs:
				# move digraph to the end
				return word[digraph_length:] + word[:digraph_length] + "ay"
		# otherwise, just shift the first letter
		return word[1:] + word[0] + "ay"

	# split sentence at spaces
	sentence = message.split()
	num_words = len(sentence)
	# loop through words
	for i in range(num_words):
		# split non-alpha characters on ends into separate groups
		nonAlphaOnEnds = r"^([^a-zA-Z]*)([a-zA-Z]+)([^a-zA-Z]*)$"
		match = re.match(nonAlphaOnEnds, sentence[i])
		# if alpha characters were found
		if match is not None:
			# translate the alpha character section
			translation = translate_word(match[2])
			# put back the non-alpha characters on the ends
			sentence[i] = match[1] + translation + match[3]
	# insert the spaces back into the text
	return " ".join(sentence)