def translate(bicorpus, file=sys.stdin):
"""
input: Bs, a sentence in the source language
output: list of Bt, sentences in the target language, candidate translations
data (passed as arguments):
bicorpus = list of pairs (As, At) where At is the translation of As.
bidictionary = bilingual dictionary of (a_s, a_t) where a_s is a word, and a_t its translation.
"""
# bidictionary = bicorpus
for Bs in file:
Bs = Bs.rstrip('\n')
if __verbose__:
print >> sys.stderr, '\n# Translating sentence: {}'.format(Bs)
# for As in bicorpus:
for As in bicorpus.iter(string=Bs,
strategy='by distance',
method='direct'):
a_s, b_s = single_substitution(As, Bs)
try:
a_t, b_t = bicorpus[a_s], bicorpus[b_s]
except KeyError:
continue
else:
if __verbose__:
print >> sys.stderr, '#\t{} : {} :: {} : {}\n'.format(
a_s, a_t, b_s, b_t)
print '{}\t{}'.format(Bs, bicorpus[As].replace(a_t, b_t))
def translate(bicorpus, bidictionary, file=sys.stdin):
"""
input: Bs in the source language
output: list of Bt in the target language, candidate translations
data (passed as argument):
bicorpus = list of pairs (As, At) where At is the translation of As.
bidictionary = bilingual dictionary of (a_s, a_t) where a_s is a word, and a_t its translation.
"""
# bidictionary = bicorpus
print file
for Bs in file:
Bs = Bs.rstrip('\n')
if __verbose__:
print >> sys.stderr, '\n# Translating sentence: {}'.format(Bs)
for As in bicorpus:
a_s, b_s = single_substitution(As, Bs)
try:
a_t, b_t = bidictionary[a_s], bidictionary[b_s]
except KeyError:
continue
else:
if __verbose__:
print >> sys.stderr, '\t{} <--> {}\t{} <--> {}'.format(
a_s, b_s, a_t, b_t)
print '{}\t{}'.format(Bs, bicorpus[As].replace(a_t, b_t))