DOCS_PATH = dict()
#directory = "C:/Users/ualis/Desktop/REV/"
directory = sys.argv[1]
H = dict()
N = len(os.listdir(directory))
for i, filename in enumerate(os.listdir(directory)):
if filename.endswith(".txt") or filename.endswith(".html") or filename.endswith(".story"):
path = os.path.join(directory, filename)
print('Documentos Indexados: ', i)
doc = Document(i+1, filename, directory)
HashTableVector = doc.to_vector()
for token in HashTableVector:
idDoc = 'D'+str(doc.getID())
DOCS_PATH[idDoc] = path
if token not in H:
TokenInfo = list()
TokenInfo.append(0)
tupla = (idDoc, HashTableVector[token])
TokenInfo.append(tupla)
H[token] = TokenInfo
DOC_REFERENCE[idDoc] = 0
else:
DOC_REFERENCE[idDoc] = 0
tupla = (idDoc, HashTableVector[token])
TokenInfo = H[token]
TokenInfo.append(tupla)
H[token] = TokenInfo
print('ÍNDICE INVERTIDO')