def main():
seq = stdin.read()
write = stdout.write
ilen = len(seq)
seq = sub('>.*\n|\n', '', seq)
clen = len(seq)
variants = (
'agggtaaa|tttaccct',
'[cgt]gggtaaa|tttaccc[acg]',
'a[act]ggtaaa|tttacc[agt]t',
'ag[act]gtaaa|tttac[agt]ct',
'agg[act]taaa|ttta[agt]cct',
'aggg[acg]aaa|ttt[cgt]ccct',
'agggt[cgt]aa|tt[acg]accct',
'agggta[cgt]a|t[acg]taccct',
'agggtaa[cgt]|[acg]ttaccct')
for f in variants:
write(f + ' ' +str(len(findall(f, seq))).encode('latin1') + '\n')
subst = {
'B' : '(c|g|t)', 'D' : '(a|g|t)', 'H' : '(a|c|t)', 'K' : '(g|t)',
'M' : '(a|c)', 'N' : '(a|c|g|t)', 'R' : '(a|g)', 'S' : '(c|g)',
'V' : '(a|c|g)', 'W' : '(a|t)', 'Y' : '(c|t)'}
for f, r in subst.items():
seq = sub(f, r, seq)
write('\n')
write(str(ilen).encode('latin1') + '\n')
write(str(clen).encode('latin1') + '\n')
write(str(len(seq)).encode('latin1') + '\n')
def test_bug_449000(self):
# Test for sub() on escaped characters
self.assertEqual(re.sub(r'\r\n', r'\n', 'abc\r\ndef\r\n'),
'abc\ndef\n')
self.assertEqual(re.sub('\r\n', r'\n', 'abc\r\ndef\r\n'),
'abc\ndef\n')
self.assertEqual(re.sub(r'\r\n', '\n', 'abc\r\ndef\r\n'),
'abc\ndef\n')
self.assertEqual(re.sub('\r\n', '\n', 'abc\r\ndef\r\n'),
'abc\ndef\n')
def test_bug_1140(self):
# re.sub(x, y, u'') should return u'', not '', and
# re.sub(x, y, '') should return '', not u''.
# Also:
# re.sub(x, y, unicode(x)) should return unicode(y), and
# re.sub(x, y, str(x)) should return
# str(y) if isinstance(y, str) else unicode(y).
for x in 'x', u'x':
for y in 'y', u'y':
z = re.sub(x, y, u'')
self.assertEqual(z, u'')
self.assertEqual(type(z), unicode)
#
z = re.sub(x, y, '')
self.assertEqual(z, '')
self.assertEqual(type(z), str)
#
z = re.sub(x, y, unicode(x))
self.assertEqual(z, y)
self.assertEqual(type(z), unicode)
#
z = re.sub(x, y, str(x))
self.assertEqual(z, y)
self.assertEqual(type(z), type(y))
def test_bug_449964(self):
# fails for group followed by other escape
self.assertEqual(re.sub(r'(?P<unk>x)', '\g<1>\g<1>\\b', 'xx'),
'xx\bxx\b')
def test_basic_re_sub(self):
self.assertEqual(re.sub("(?i)b+", "x", "bbbb BBBB"), 'x x')
self.assertEqual(re.sub(r'\d+', self.bump_num, '08.2 -2 23x99y'),
'9.3 -3 24x100y')
self.assertEqual(re.sub(r'\d+', self.bump_num, '08.2 -2 23x99y', 3),
'9.3 -3 23x99y')
self.assertEqual(re.sub('.', lambda m: r"\n", 'x'), '\\n')
self.assertEqual(re.sub('.', r"\n", 'x'), '\n')
s = r"\1\1"
self.assertEqual(re.sub('(.)', s, 'x'), 'xx')
self.assertEqual(re.sub('(.)', re.escape(s), 'x'), s)
self.assertEqual(re.sub('(.)', lambda m: s, 'x'), s)
self.assertEqual(re.sub('(?P<a>x)', '\g<a>\g<a>', 'xx'), 'xxxx')
self.assertEqual(re.sub('(?P<a>x)', '\g<a>\g<1>', 'xx'), 'xxxx')
self.assertEqual(re.sub('(?P<unk>x)', '\g<unk>\g<unk>', 'xx'), 'xxxx')
self.assertEqual(re.sub('(?P<unk>x)', '\g<1>\g<1>', 'xx'), 'xxxx')
self.assertEqual(re.sub('a',r'\t\n\v\r\f\a\b\B\Z\a\A\w\W\s\S\d\D','a'),
'\t\n\v\r\f\a\b\\B\\Z\a\\A\\w\\W\\s\\S\\d\\D')
self.assertEqual(re.sub('a', '\t\n\v\r\f\a', 'a'), '\t\n\v\r\f\a')
self.assertEqual(re.sub('a', '\t\n\v\r\f\a', 'a'),
(chr(9)+chr(10)+chr(11)+chr(13)+chr(12)+chr(7)))
self.assertEqual(re.sub('^\s*', 'X', 'test'), 'Xtest')
def test_bug_462270(self):
# Test for empty sub() behaviour, see SF bug #462270
self.assertEqual(re.sub('x*', '-', 'abxd'), '-a-b-d-')
self.assertEqual(re.sub('x+', '-', 'abxd'), 'ab-d')
def test_bug_114660(self):
self.assertEqual(re.sub(r'(\S)\s+(\S)', r'\1 \2', 'hello there'),
'hello there')
def test_qualified_re_sub(self):
self.assertEqual(re.sub('a', 'b', 'aaaaa'), 'bbbbb')
self.assertEqual(re.sub('a', 'b', 'aaaaa', 1), 'baaaa')
def test_sub_template_numeric_escape(self):
# bug 776311 and friends
self.assertEqual(re.sub('x', r'\0', 'x'), '\0')
self.assertEqual(re.sub('x', r'\000', 'x'), '\000')
self.assertEqual(re.sub('x', r'\001', 'x'), '\001')
self.assertEqual(re.sub('x', r'\008', 'x'), '\0' + '8')
self.assertEqual(re.sub('x', r'\009', 'x'), '\0' + '9')
self.assertEqual(re.sub('x', r'\111', 'x'), '\111')
self.assertEqual(re.sub('x', r'\117', 'x'), '\117')
self.assertEqual(re.sub('x', r'\1111', 'x'), '\1111')
self.assertEqual(re.sub('x', r'\1111', 'x'), '\111' + '1')
self.assertEqual(re.sub('x', r'\00', 'x'), '\x00')
self.assertEqual(re.sub('x', r'\07', 'x'), '\x07')
self.assertEqual(re.sub('x', r'\08', 'x'), '\0' + '8')
self.assertEqual(re.sub('x', r'\09', 'x'), '\0' + '9')
self.assertEqual(re.sub('x', r'\0a', 'x'), '\0' + 'a')
self.assertEqual(re.sub('x', r'\400', 'x'), '\0')
self.assertEqual(re.sub('x', r'\777', 'x'), '\377')
self.assertRaises(re.error, re.sub, 'x', r'\1', 'x')
self.assertRaises(re.error, re.sub, 'x', r'\8', 'x')
self.assertRaises(re.error, re.sub, 'x', r'\9', 'x')
self.assertRaises(re.error, re.sub, 'x', r'\11', 'x')
self.assertRaises(re.error, re.sub, 'x', r'\18', 'x')
self.assertRaises(re.error, re.sub, 'x', r'\1a', 'x')
self.assertRaises(re.error, re.sub, 'x', r'\90', 'x')
self.assertRaises(re.error, re.sub, 'x', r'\99', 'x')
self.assertRaises(re.error, re.sub, 'x', r'\118', 'x') # r'\11' + '8'
self.assertRaises(re.error, re.sub, 'x', r'\11a', 'x')
self.assertRaises(re.error, re.sub, 'x', r'\181', 'x') # r'\18' + '1'
self.assertRaises(re.error, re.sub, 'x', r'\800', 'x') # r'\80' + '0'
# in python2.3 (etc), these loop endlessly in sre_parser.py
self.assertEqual(re.sub('(((((((((((x)))))))))))', r'\11', 'x'), 'x')
self.assertEqual(re.sub('((((((((((y))))))))))(.)', r'\118', 'xyz'),
'xz8')
self.assertEqual(re.sub('((((((((((y))))))))))(.)', r'\11a', 'xyz'),
'xza')
