def retrieveText(self, pn, terms):
result = {}
os.chdir(pn + '/output')
with open('output_vote_remain_Dark_Age.csv', 'rU') as csvfile:
reader = csv.reader(csvfile, delimiter='*', quotechar='|')
i = -1
try:
for row in reader:
if (i == -1):
i = i + 1
continue
if (len(row) < 2):
continue
text = row[1]
tFalse = True
for term in terms:
if (term in text) or (term.lower() in text.lower()):
tFalse = False
break
for s in result:
t = result[s]
if (text in t):
tFalse = False
break
if (tFalse == True):
result[str(i)] = text
i = i + 1
except csv.Error, e:
sys.exit('line %d: %s' % (reader.line_num, e))
return result
def parse_text(text):
text = text.strip(" ")
return GracefulList(text.lower().replace("\\", "").replace("\n", " ").split(" "))
def __tokenize(text):
return re.split(r'[^a-z0-9\-]+', text.lower())