def test_foo(self):
dawg = make_dawg(('foo', 'bar'))
found = set(Iterator('baz', 1, dawg))
self.assertEqual({'bar'}, found)
found = set(Iterator('baz', 2, dawg))
self.assertEqual({'bar'}, found)
def test_tolerance(self):
dictionary = ('meter', 'otter', 'potter')
dawg = make_dawg(dictionary)
found = set(Iterator('mutter', 1, dawg))
self.assertEqual(set(), found)
found = set(Iterator('mutter', 2, dawg))
self.assertEqual(set(dictionary), found)
def test_this(self):
dictionary = ('this', 'that', 'other')
dawg = make_dawg(dictionary)
found = set(Iterator('the', 1, dawg))
self.assertEqual(set(), found)
found = set(Iterator('the', 2, dawg))
self.assertEqual(set(dictionary), found)
def main():
if len(sys.argv) != 2:
raise Exception("usage: %s input-file" % sys.argv[0])
input_path = os.path.abspath(sys.argv[1])
dictionary = make_test_dict(input_path)
dawg = make_dawg(dictionary)
totals = []
count_children(dawg.root, totals)
i = 0
l = len(totals)
while i < l:
if totals[i] > 0:
print("%d: %d" % (i, totals[i]))
i += 1
def test_initial_final(self):
dawg = make_dawg(('', 'a'))
found = set(Iterator('b', 1, dawg))
self.assertEqual({'', 'a'}, found)
def test_binary(self):
dictionary = ('ababa', 'babab')
dawg = make_dawg(dictionary)
found = set(Iterator('abba', 3, dawg))
self.assertEqual(set(dictionary), found)
def test_long_head(self):
found = set(Iterator('abtrtz', 1, make_dawg(('abtrbtz', ))))
self.assertEqual({'abtrbtz'}, found)
def main():
parser = argparse.ArgumentParser(
description='MUlti-word EDit DIstance test')
parser.add_argument('--tolerance',
'-t',
type=int,
default=1,
help='max allowed number of edits')
parser.add_argument('input', nargs=1, help='input file path')
parser.add_argument('--result',
'-r',
type=str,
default='result.tsv',
help='input file path')
parser.add_argument('--single-dict',
'-s',
action='store_true',
help='include tested word in the dictionary')
args = parser.parse_args()
n = args.tolerance
if n <= 0:
raise Exception("max allowed number of edits must be positive")
input_path = os.path.abspath(args.input[0])
result_path = args.result
single_mode = args.single_dict
dictionary = make_test_dict(input_path)
dd = copy.copy(dictionary) if single_mode else dictionary
dawg = make_dawg(dd) if single_mode else None
if not os.path.isfile(result_path):
with open(result_path, 'w', newline='') as f:
writer = csv.writer(f, delimiter='\t')
writer.writerow([input_path, str(n), int(single_mode)])
last_word = None
first = True
for tword in sorted(dictionary):
print("%s..." % tword)
if not single_mode:
dd.remove(tword)
if (first):
first = False
else:
dd.add(last_word)
dawg = make_dawg(dd)
last_word = tword
test_independent(tword, n, dd, dawg, writer)
else:
with open(result_path, newline='') as f:
reader = csv.reader(f, delimiter='\t')
first_row = next(reader)
if len(first_row) != 3:
raise Exception("three-column header expected")
if (first_row[0] != input_path) or (int(first_row[1]) != n) or (
int(first_row[2]) != int(single_mode)):
raise Exception("inputs changed")
last_word = None
first = True
for tword in sorted(dictionary):
print("%s..." % tword)
if not single_mode:
dd.remove(tword)
if (first):
first = False
else:
dd.add(last_word)
dawg = make_dawg(dd)
last_word = tword
test_repeat(tword, n, dawg, reader)
