def test_re_findall(self):
self.assertEqual(re.findall(":+", "abc"), [])
self.assertEqual(re.findall(":+", "a:b::c:::d"), [":", "::", ":::"])
self.assertEqual(re.findall("(:+)", "a:b::c:::d"), [":", "::", ":::"])
self.assertEqual(re.findall("(:)(:*)", "a:b::c:::d"), [(":", ""),
(":", ":"),
(":", "::")])
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_re_escape_non_ascii_bytes(self):
b = u'y\u2620y\u2620y'.encode('utf-8')
b_escaped = re.escape(b)
self.assertEqual(b_escaped, b'y\\\xe2\\\x98\\\xa0y\\\xe2\\\x98\\\xa0y')
self.assertMatch(b_escaped, b)
res = re.findall(re.escape(u'\u2620'.encode('utf-8')), b)
self.assertEqual(len(res), 2)
def test_bug_117612(self):
self.assertEqual(re.findall(r"(a|(b))", "aba"),
[("a", ""),("b", "b"),("a", "")])