""" definition of the phones to be used. """

# phonese in {FAME}/lexicon/lex.asr
phoneset = [
	# vowels
	'a',
	'a:',
	'e',
	'e:',
	'i',
	'i:',
	'i̯',
	'o',
	'o:',
	'ö',
	'ö:',
	'u',
	'u:',
	'ü',
	'ü:',
	#'ú', # only appears in word 'feeste'(út) and 'gaste'(út) which are 'f e: s t ə' and 'yn' in lex_asr. The pronunciation in Fries may be mistakes so I removed this phone. 
	'ṷ',
	'y',
	'ɔ',
	'ɔ:',
	'ɔ̈', 
	'ɔ̈:',
	'ə',
	'ɛ',
	'ɛ:',
	'ɪ',
	'ɪ:',

	# plosives
	'p', 
	'b', 
	't',
	'd', 
	'k',
	'g',
	'ɡ', # = 'g'

	# nasals
	'm',
	'n',
	'ŋ',
	
	# fricatives
	'f',
	'v',
	's',
	's:',
	'z',
	'x',
	'h',
	
	# tap and flip
	'r',
	'r:',

	# approximant
	'j',
	'l'
	]


## reduce the number of phones.
# the phones which seldom occur are replaced with another more popular phones.
# replacements are based on the advice from Martijn Wieling.
reduction_key = {
	'y':'i:', 'e':'e:', 'ə:':'ɛ:', 'r:':'r', 'ɡ':'g',
	# aki added because this is used in stimmen_project.
	'ɔ̈:':'ɔ:'
	}
# already removed beforehand in phoneset. Just to be sure.
phones_to_be_removed = ['ú', 's:']

def phone_reduction(phones):
	""" 
	Args:
		phones (list): list of phones.
	"""
	if sum([phone in phones for phone in phones_to_be_removed]) != 0:
		print('input includes phone(s) which is not defined in fame_asr.')
		print('those phone(s) are removed.')		
	return [reduction_key.get(i, i) for i in phones
		 if i not in phones_to_be_removed]

phoneset_short = list(set(phone_reduction(phoneset)))
phoneset_short.sort()



## translation_key to htk format (ascii).
# phones which gives UnicodeEncodeError when phone.encode("ascii")
# are replaced with other characters.
translation_key_asr2htk = {
	'i̯': 'i_',
	'ṷ': 'u_',

	# on the analogy of German umlaut, 'e' is used.
	'ö': 'oe', 'ö:': 'oe:', ''
	'ü': 'ue', 'ü:': 'ue:',

	# on the analogy of Chinese...
	'ŋ': 'ng',
				
	# refer to Xsampa. 
	'ɔ': 'O', 'ɔ:': 'O:', 'ɔ̈': 'Oe', 
	#'ɔ̈:': 'O:', # does not appear in FAME, but used in stimmen.
	'ɛ': 'E', 'ɛ:': 'E:',
	'ɪ': 'I', 'ɪ:': 'I:', 

	# it is @ in Xsampa, but that is not handy on HTK.
	'ə': 'A'
	}
phoneset_htk = [translation_key_asr2htk.get(i, i) for i in phoneset_short]

#not_in_ascii = [
#	'\'', 
#	'â', 'ê', 'ô', 'û', 'č', 
#	'à', 'í', 'é', 'è', 'ú', 'ć', 
#	'ä', 'ë', 'ï', 'ö', 'ü'
#]
translation_key_word2htk = {
	#'\'': '\\\'',
	'í':'i1', 'é':'e1', 'ú':'u1', 'ć':'c1',
	'à':'a2', 'è':'e2', 	
	'â':'a3', 'ê':'e3', 'ô':'o3', 'û':'u3', 
	'č':'c4',
	'ä': 'ao', 'ë': 'ee', 'ï': 'ie', 'ö': 'oe', 'ü': 'ue',
}
#[translation_key_word2htk.get(i, i) for i in not_in_ascii]
#Stop: p, b, t, d, k, g  
#Nasal: m, n, ng(ŋ)
#Fricative: s, z, f, v, h, x
#Liquid: l, r
#Vowel: a, a:, e:, i, i:, i_(i̯), o, o:, u, u:, u_(ṷ), oe(ö), oe:(ö:), ue(ü), ue:(ü:), O(ɔ), O:(ɔ:), Oe(ɔ̈), A(ə), E(ɛ), E:(ɛ:), I(ɪ), I:(ɪ:)


## the list of multi character phones. 
# for example, the length of 'a:' is 3, but in the codes it is treated as one letter.

# original.
multi_character_phones = [i for i in phoneset if len(i) > 1]
multi_character_phones.sort(key=len, reverse=True)

# phonset reduced.
multi_character_phones_short = [i for i in phoneset_short if len(i) > 1]
multi_character_phones_short.sort(key=len, reverse=True)

# htk compatible.
multi_character_phones_htk = [i for i in phoneset_htk if len(i) > 1]
multi_character_phones_htk.sort(key=len, reverse=True)