############################################
#Declarations:
v_rt_dic = {}
tam_dic = {}
anu_rt_dic = {}
anu_tam_dic = {}
k_v_rt_dic = {}
k_v_rt_par_dic = {}
anu_km_dic_match = {}
k_exact_tam_dic = {}
############################################
#storing verb rt and tam info in dics:
for line in open(sys.argv[1]):
lst = line.strip().split()
if 'verb_root-id' in lst[0]:
add_data_in_dic(v_rt_dic, lst[1], ' '.join(lst[2:-1])) #vApasa_A 8 9
if 'tam-id' in lst[0]:
add_data_in_dic(tam_dic, lst[1], ' '.join(lst[2:-1]))
if 'anu_id-manu_verb_root-ids' in lst[0]:
add_data_in_dic(anu_km_dic_match, int(lst[1]), ' '.join(lst[3:-1])) #bAwa_kara 7 8
##############################################
#storing K layer root info in dic:
for line in open(sys.argv[2]):
lst = line.strip().split()
if 'id-anu_root' in lst[0]:
anu_rt_dic[int(lst[1])] = lst[2]
if 'id-anu_tam' in lst[0]:
anu_tam_dic[int(lst[1])] = lst[2]
##############################
#Declarations:
h_wrd_dict = {}
v_rt_dic = {}
tam_dic = {}
anu_eng_rt_dic = {}
kriyA_mula_dic = {}
anu_rt_dic = {}
anu_tam_dic = {}
verb_dic = {}
man_tam_dic = {}
gnp_dic = {}
##############################
for line in fhw:
lst = line[:-2].split()
add_data_in_dic(h_wrd_dict, lst[2], lst[1])
##############################
#storing single mng verb dic
for line in open(sys.argv[3]):
lst = line.strip().split('\t')
add_data_in_dic(verb_dic, lst[0], lst[1])
##############################
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)
from functions import add_data_in_dic
from functions import return_key
############################################
#Declarations:
v_rt_dic = {}
tam_dic = {}
anu_rt_dic = {}
k_v_rt_dic = {}
k_v_rt_par_dic = {}
############################################
#storing verb rt and tam info in dics:
for line in open(sys.argv[1]):
lst = line.strip().split()
if 'verb_root-id' in lst[0]:
add_data_in_dic(v_rt_dic, lst[1],
' '.join(lst[2:-1])) #vApasa_A 8 9
if 'tam-id' in lst[0]:
add_data_in_dic(tam_dic, lst[1], ' '.join(lst[2:-1]))
##############################################
#storing K layer root info in dic:
for line in open(sys.argv[2]):
lst = line.strip().split()
anu_rt_dic[int(lst[1])] = lst[2]
##############################################
#aligning verb root
for key in sorted(anu_rt_dic):
anu_rt = anu_rt_dic[key]
print(anu_rt)
domain_dic = {}
default_dic = {}
cap_dom_dic = {}
cap_def_dic = {}
man_mng_dic = {}
k_align_dic = {}
list_K_alignment=['K_1st_letter_capital_word']
#################################
#Collecting first word Capital from original_word.dat
for line in fo:
lst = line[:-2].split()
if (lst[2].lower() not in weak_choice):#ai1E/2.67: Condition added by Kishori 9 nov to remove 1_In = 3_meM/10_meM in K_1st_letter_capital_word
if(lst[2][0].isupper()): #and lst[1] != '1'):
#print(lst[2])
add_data_in_dic(cap_dic, int(lst[1]), lst[2].lower())
#for key in sorted(cap_dic):
# print(str(key) + '\t' + cap_dic[key])
#################################
#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])
import sys
from functions import unique_val
from functions import add_data_in_dic
from functions import return_key
hrt_dic = {}
hid_dic = {}
kriyA_mUla = []
for line in open(sys.argv[1]):
lst = line[:-2].split()
add_data_in_dic(hrt_dic, lst[2], lst[1])
add_data_in_dic(hid_dic, int(lst[1]), lst[2])
for line in open(sys.argv[2]):
lst = line.strip().split('\t')
mngs = lst[1].split('/')
for each in mngs:
if each not in kriyA_mUla:
kriyA_mUla.append(each)
#print(kriyA_mUla)
def check_substring(lst, sub):
sub_lst = []
for each in lst:
if sub in each:
sub_lst.append(each)
return sub_lst
list_K_exact_word_align = ['K_exact_word_align']
############################################################
#Creating wrd_dic, nwe_dic, h_wrd_dic
for line in fw:
lst = line[:-2].split()
wrd_dic[lst[1]] = lst[2]
for line in open(sys.argv[2]):
lst = line.strip().split('\t')
mwe_dic[lst[0]] = lst[1]
for line in fr:
lst = line[:-2].split('\t')
add_data_in_dic(h_wrd_dic, lst[2], lst[1])
############################################################
#Checking multi_word_expressions.dat
mwe_list = []
for line in open(sys.argv[1]):
mwe_mng = ''
lst = line[:-2].split()
if 'compound' in lst[3]:
mwe_mng = lst[2]
ids = lst[4:]
print(ids, mwe_mng)
mwe_lst = []
for each in ids:
mwe_lst.append(wrd_dic[each])
#print each, wrd_dic[each], h_wrd_dic.keys()
mwe = '_'.join(mwe_lst) #finite_state_machine
