def check_wrd(index, length, word, f_wrd):
lst = []
lst.append(f_wrd)
for i in range(1, length):
k = return_key(str(index + i), h_wrd_dict)
lst.append(k)
w = ' '.join(lst)
if w == word:
return index
def return_id(word):
lst = word.split()
length = len(lst)
if lst[0] in h_wrd_dict.values():
w = []
out = return_key(lst[0], h_wrd_dict)
if out != None:
w.append(lst[0])
for i in range(1,length):
w.append(h_wrd_dict[out+i])
wrd = ' '.join(w)
if wrd == word:
return(out)
def check_for_kriyA_mUla(start_id, length, anu_vb_word):
k_m_wrd = []
ids = []
for i in range(length):
if start_id + i not in v_rt_dic.keys():
val = return_key(str(start_id + i), h_wrd_dict)
if val != None and val != 'nahIM':
k_m_wrd.append(val) #bAwa
ids.append(str(start_id + i))
elif val == 'nahIM':
v = return_key(str(start_id + i + 1), h_wrd_dict)
k_m_wrd.append(v) #Bexa_nahIM_kara
ids.append(str(start_id + i + 1))
else:
if v_rt_dic[start_id + i] != 'nahIM':
k_m_wrd.append(v_rt_dic[start_id + i]) #kara
ids.append(str(start_id + i))
else:
k_m_wrd.append(v_rt_dic[start_id + i + 1])
ids.append(str(start_id + i + 1))
if anu_vb_word == '_'.join(k_m_wrd):
return ' '.join(ids)
mngs = kriyA_mula_dic[eng_rt].split('/')
for each in mngs:
wrd = each.split('_')
if wrd[0] in h_wrd_dict.keys():
if '/' not in h_wrd_dict[wrd[0]]:
out = check_for_kriyA_mUla(int(h_wrd_dict[wrd[0]]),
len(wrd), each)
if out != None:
# print(each, h_wrd_dict[wrd[0]])
print('(anu_id-manu_verb_root-ids', key, each, out,
')')
else:
if eng_rt in verb_dic.keys():
mngs = verb_dic[eng_rt].split('/')
for each in mngs:
v_id = return_key(each, v_rt_dic)
if v_id != None:
print('(anu_id-manu_verb_root-ids', key,
each, v_id, ')') #ai1E, 2.50, pA
else:
#print('&&', wrd[0], h_wrd_dict[wrd[0]], each)
l = h_wrd_dict[wrd[0]].split('/')
for item in l:
out = check_for_kriyA_mUla(int(item), len(wrd), each)
if out != None:
# print(each, h_wrd_dict[wrd[0]])
print('(anu_id-manu_verb_root-ids', key, each, out,
')')
else:
if eng_rt in verb_dic.keys():
mngs = verb_dic[eng_rt].split('/')
#################################
#Creating domain dic:
for line in open(sys.argv[1]):
if(line[0]!= '#'):
lst = line.strip().split('\t')
wrd = lst[0].split('_')
add_data_in_dic(domain_dic, wrd[0], lst[1])
#for key in sorted(domain_dic):
# print(str(key) + '\t' + domain_dic[key])
#Checking collected capital words in domain dic:
for key in sorted(domain_dic):
if(key in cap_dic.values()):
key_id = return_key(key, cap_dic)
# if(key_id not in cap_dom_dic.keys()): #If neccessary uncomment this loop
cap_dom_dic[key_id] = domain_dic[key]
# print(str(key_id) + '\t' + domain_dic[key])
#################################
#Creating default dic:
for line in open(sys.argv[2]):
if(line[0]!= '#' and line[0] != '\t'):
lst = line.strip().split('\t')
add_data_in_dic(default_dic, lst[0], lst[1])
#Checking collected capital words in domain dic:
for key in sorted(default_dic):
if(key in cap_dic.values()):
lst = line[:-2].split()
man_rt_dic[lst[1]] = '+'.join(lst[2:])
if 'verb_root-tam-gnp-v_id' in line:
lst = line[:-2].split()
key = '+'.join(lst[4:])
gnp_dic[key] = lst[3]
#############################################
#Aligning with tam if anu root and manual root are different:
for key in sorted(anu_tam_dic):
# print(anu_tam_dic[key], man_tam_dic.values())
if anu_tam_dic[key] in man_tam_dic.keys():
k = anu_tam_dic[key]
val = man_tam_dic[k]
print(val, man_rt_dic)
man_rt = return_key('+'.join(val), man_rt_dic)
if man_rt == None:
man_rt = return_key(val[0], man_rt_dic)
if anu_rt_dic[key] != man_rt:
k_tam_dic[key] = ' '.join(val)
k_v_t_gnp_dic[key] = man_rt + '+' + k + gnp_dic[val[0]]
# print(key, man_rt, man_rt_dic, k)
#############################################
fw = open("word.dat", "r").readlines()
word_len = len(fw) - 1
for i in range(len(fw)):
list_K_tam.append('-')
list_K_tam_v.append('-')
print('(anu_id-manu_verb_root-ids', key, each, out, ')')
#Get kriyA_mUla info:
f3 = open(sys.argv[4], 'r').readlines()
kriyA_mUla_lst = []
for each in f3:
lst = each.strip().split('\t')
if lst[0] not in kriyA_mUla_lst:
kriyA_mUla_lst.append(lst[0])
#print(kriyA_mUla_lst, len(kriyA_mUla_lst))
for key in sorted(v_rt_dic):
k = key - 1
wrd = return_key(str(k), h_wrd_dict)
k_m_w = wrd + '_' + v_rt_dic[key]
# print(wrd, k_m_w)
if k_m_w in kriyA_mUla_lst:
# print('&&', k , k_m_w)
del v_rt_dic[key]
if k_m_w not in v_rt_dic:
v_rt_dic[k_m_w] = str(k) + ' ' + str(key)
else:
v_rt_dic[k_m_w] = v_rt_dic[k_m_w] + '/' + str(k) + ' ' + str(key)
new_key = str(k) + ' ' + str(key)
tam_dic[new_key] = tam_dic[key]
del tam_dic[key]
else:
val = v_rt_dic[key]
del v_rt_dic[key]
#print expr
expr_lst = expr.split()
h_ids = []
for i in range(0, len(expr_lst)):
item = expr_lst[i]
if item.split(':')[1] in h_wrd_dic.keys():
val = item.split(':')[1]
h_ids.append(
h_wrd_dic[val]
) # Ex: item.split(':')[1] = 'parimiwa' , h_wrd_dic['item.split(':')[1]] = 4 (Ex: 2.98, ai2E)
k_mwe_dic[ids[i]] = h_wrd_dic[val]
#print h_wrd_dic[val]
else:
last_id = h_ids[-1]
cur_id = int(last_id) + 1
o = return_key(str(cur_id), h_wrd_dic)
if o != None:
#print item.split(':')[1] + '<>' + o
k_mwe_dic[ids[i]] = '<< ' + str(cur_id) + ' >>'
#################################
for key in sorted(k_mwe_dic):
print(str(key) + '\t' + k_mwe_dic[key])
for i in range(len(fw) - 1):
list_K_exact_word_align.append('-')
#Store data in list_K_alignment
for i in range(1, len(fw)):
if str(i) in k_mwe_dic.keys():
list_K_exact_word_align[i] = k_mwe_dic[str(i)]