def search
for query in fileinput.input():
query_tokens = query[:-1].split(' ')
print (green('QUERY: ') + query)
for quote in quotes:
good = True
for tok in query_tokens :
good_tok = False
for quot_tok in quote :
if match_tokens(tok, quot_tok) :
good_tok = True
if good_tok == False:
good = False
break
if good :
#print (quote)
print (' ', my_highlight(query_tokens, quote))
#print(lemtas)
good_token = False
else:
good_token = False
if good_token :
good = True
break
if good:
for j in range(len(q)):
r.append(Fore.RED + Style.BRIGHT + L[i+j]+ Fore.BLACK + Style.RESET_ALL)
i+=len(q)
else:
r.append(w)
return ' '.join(r)
print("Ready for input\n")
for query in fileinput.input():
query_tokens = []
split_res = query[:-1].split('\"')
for i in range(len(split_res)):
if i%2 == 0:
query_tokens+= [[w] for w in split_res[i].split(' ') if w != '']
else:
query_tokens+= [[w for w in split_res[i].split(' ') if w != '']]
print(query_tokens)
print (green('QUERY: ') + query)
good_documents = sorted([get_dokument(f) for f in find_quotes( query_tokens )], key = lambda x : rank_document(query_tokens, x), reverse = True)
good_documents = [word_tokenize(x)for x in good_documents]
for quote in good_documents:
print (' ', my_highlight(query_tokens, quote))
lines = []
tokens = []
def match(query, line):
return all(w in line for w in query)
def search(q):
return [line for line in tokens if match(q, line)]
for line in open('tokenized_quotes.txt'):
L = line.split()
tokens.append(L)
print('No, dalej!')
t0 = time.time()
for x in sys.stdin:
L = x.split()
print(green('QUERY: ') + ' '.join(L))
search(L)
for res in search(L):
print(' ', highlight(L, res))
yellow_line()
print()
print(time.time() - t0)