min_fms = float(args.min_fms)
min_len = int(args.min_len)
max_len = int(args.max_len) if args.max_len else max(len(s_sentence.split()), len(s1_sentence.split()))
#Calculate FMS between S and S1.
fms = FMS(s_sentence, s1_sentence).calculate()
#Exit if low FMS.
assertion(fms >= min_fms, "Sentences have low fuzzy match score of %.02f." %fms)
#Get A set
phrase_extractor = PhraseExtractor(s_sentence, s1_sentence, min_len, max_len)
a_set = phrase_extractor.extract_pairs()
#Initiate and check Apertium
apertium = Apertium(lps[0], lps[1])
(out, err) = apertium.check_installations(lp_dir)
assertion(out, err)
# Prepare to Generate D set.
S = s_sentence.split()
S1 = s1_sentence.split()
src = ""
src1 = ""
for a,b,c,d in a_set:
str1 = ' '.join(S[a: b+1])
str2 = ' '.join(S1[c: d+1])
print('("{0}", "{1}")'.format(str1, str2))
assertion(mode in ['all', 'cam', 'compare'], "Mode couldn't be identified.") grounded = args.go best_only = args.bo min_fms = float(args.min_fms) min_len = int(args.min_len) max_len = int(args.max_len) warning(min_len > 1 & grounded, "min_len should be greater than 1") cache_db_file = None if cache != '': cache_db_file = cache use_caching = True if cache_db_file else False apertium = Apertium(lps[0], lps[1]) (out, err) = apertium.check_installations(lp_dir) assertion(out, err) #Reopen new file file1 = open(args.out) #Global values gl_wer = [] best_wer = [] gl_up_wer = [] gl_no_of_patches = 0.0 if mode == 'compare': gl_wer2 = [] best_wer2 = []
