def test_sampa2uni():
seq = 'tʰɔxtər'
sampa = eval('"'+sampa2uni('t_hOxt@r')+'"')
assert sampa == seq #or sampa2 == seq
def test_sampa2uni(self):
seq = 'tʰɔxtər'
sampa = eval('"' + sampa2uni('t_hOxt@r') + '"')
assert sampa == seq # or sampa2 == seq
for i, line in enumerate(csv[i+1:]):
if len(line) != 4:
print('error in line {0} in file {1}'.format(i,'ss'))
_, concept, language, sampa = line
if sampa.strip() and sampa.strip() != '-':
sampa_o = sampa
sampas = sampa.split(',')
for sampa in sampas:
sampa = sampa.strip()
for s, t in reps:
sampa = sampa.replace(s, t)
print(sampa)
if sampa:
ipa = sampa2uni(sampa)
ipa = ipa.replace(' ', '_')
tks = ipa2tokens(ipa, merge_vowels=False, semi_diacritics='')
D[idx] = [concept, language, sampa_o, sampa, ipa, tks]
idx += 1
wl = Wordlist(D)
wl.output('tsv', filename='an-data-wordlist', prettify=False, ignore='all')
lex = LexStat(wl)
print(lex.height, lex.width)
#lex.cluster(method=_method,cluster_method=_cluster_method, threshold=0.45)
lex.cluster(method='sca', threshold=0.45)
alm = Alignments(lex, ref='scaid')
alm.align()
alm.output('tsv', filename='an-data-aligned', prettify=False, ignore='all')
alm.output('html',filename='result')