def getlkpitem(items):
match_rgx1 = "\s*[\'\"](.+?)[\'\"]\s*:\s*[\'\"](.*)[\'\"]\s*,\s*(.*)"
match_rgx2 = "\s*[\'\"](.+?)[\'\"]\s*:\s*[\'\"](.*)[\'\"]\s*"
matched = match(match_rgx, items)
if not matched:
matched = match(match_rgx2, items)
return matched
def test_bigcharset(self):
self.assertEqual(re.match(u"([\u2222\u2223])",
u"\u2222").group(1), u"\u2222")
self.assertEqual(re.match(u"([\u2222\u2223])",
u"\u2222", re.UNICODE).group(1), u"\u2222")
r = u'[%s]' % u''.join(map(unichr, range(256, 2**16, 255)))
self.assertEqual(re.match(r, u"\uff01", re.UNICODE).group(), u"\uff01")
def test_bug_527371(self):
# bug described in patches 527371/672491
self.assertEqual(re.match(r'(a)?a','a').lastindex, None)
self.assertEqual(re.match(r'(a)(b)?b','ab').lastindex, 1)
self.assertEqual(re.match(r'(?P<a>a)(?P<b>b)?b','ab').lastgroup, 'a')
self.assertEqual(re.match("(?P<a>a(b))", "ab").lastgroup, 'a')
self.assertEqual(re.match("((a))", "a").lastindex, 1)
def test_string_boundaries(self):
# See http://bugs.python.org/issue10713
self.assertEqual(re.search(r"\b(abc)\b", "abc").group(1),
"abc")
# There's a word boundary at the start of a string.
self.assertTrue(re.match(r"\b", "abc"))
# A non-empty string includes a non-boundary zero-length match.
self.assertTrue(re.search(r"\B", "abc"))
# There is no non-boundary match at the start of a string.
self.assertFalse(re.match(r"\B", "abc"))
# However, an empty string contains no word boundaries, and also no
# non-boundaries.
self.assertEqual(re.search(r"\B", ""), None)
# This one is questionable and different from the perlre behaviour,
# but describes current behavior.
self.assertEqual(re.search(r"\b", ""), None)
# A single word-character string has two boundaries, but no
# non-boundary gaps.
self.assertEqual(len(re.findall(r"\b", "a")), 2)
self.assertEqual(len(re.findall(r"\B", "a")), 0)
# If there are no words, there are no boundaries
self.assertEqual(len(re.findall(r"\b", " ")), 0)
self.assertEqual(len(re.findall(r"\b", " ")), 0)
# Can match around the whitespace.
self.assertEqual(len(re.findall(r"\B", " ")), 2)
def apply(self, pos, tokens):
if pos + self.offset < 0:
return False, []
if pos + self.offset >= len(tokens):
return False, []
if self.rgxname not in self.norm.rgxs:
return False, []
if self.src == 'lcase':
val = tokens[pos + self.offset].get('tknorm')
if val is None:
return False, []
matched = match(self.norm.rgxs[self.rgxname], val)
if matched:
if not len(matched.groups()):
return True, [matched.group(0)]
else:
return True, matched.groups()
else:
return False, []
else:
if tokens[pos + self.offset].text:
matched = match(self.norm.rgxs[self.rgxname],
(tokens[pos + self.offset].text).strip())
else:
return False, []
if matched:
if not len(matched.groups()):
return True, [matched.group(0)]
else:
return True, matched.groups()
else:
return False, []
def test_bug_448951(self):
# bug 448951 (similar to 429357, but with single char match)
# (Also test greedy matches.)
for op in '','?','*':
self.assertEqual(re.match(r'((.%s):)?z'%op, 'z').groups(),
(None, None))
self.assertEqual(re.match(r'((.%s):)?z'%op, 'a:z').groups(),
('a:', 'a'))
def test_getlower(self):
# PCRE: disabled, we're not testing _sre here
#import _sre
#self.assertEqual(_sre.getlower(ord('A'), 0), ord('a'))
#self.assertEqual(_sre.getlower(ord('A'), re.LOCALE), ord('a'))
#self.assertEqual(_sre.getlower(ord('A'), re.UNICODE), ord('a'))
self.assertEqual(re.match("abc", "ABC", re.I).group(0), "ABC")
self.assertEqual(re.match("abc", u"ABC", re.I).group(0), "ABC")
def test_search_star_plus(self):
self.assertEqual(re.search('x*', 'axx').span(0), (0, 0))
self.assertEqual(re.search('x*', 'axx').span(), (0, 0))
self.assertEqual(re.search('x+', 'axx').span(0), (1, 3))
self.assertEqual(re.search('x+', 'axx').span(), (1, 3))
self.assertEqual(re.search('x', 'aaa'), None)
self.assertEqual(re.match('a*', 'xxx').span(0), (0, 0))
self.assertEqual(re.match('a*', 'xxx').span(), (0, 0))
self.assertEqual(re.match('x*', 'xxxa').span(0), (0, 3))
self.assertEqual(re.match('x*', 'xxxa').span(), (0, 3))
self.assertEqual(re.match('a+', 'xxx'), None)
def test_ignore_case(self):
self.assertEqual(re.match("abc", "ABC", re.I).group(0), "ABC")
self.assertEqual(re.match("abc", u"ABC", re.I).group(0), "ABC")
self.assertEqual(re.match(r"(a\s[^a])", "a b", re.I).group(1), "a b")
self.assertEqual(re.match(r"(a\s[^a]*)", "a bb", re.I).group(1), "a bb")
self.assertEqual(re.match(r"(a\s[abc])", "a b", re.I).group(1), "a b")
self.assertEqual(re.match(r"(a\s[abc]*)", "a bb", re.I).group(1), "a bb")
self.assertEqual(re.match(r"((a)\s\2)", "a a", re.I).group(1), "a a")
self.assertEqual(re.match(r"((a)\s\2*)", "a aa", re.I).group(1), "a aa")
self.assertEqual(re.match(r"((a)\s(abc|a))", "a a", re.I).group(1), "a a")
self.assertEqual(re.match(r"((a)\s(abc|a)*)", "a aa", re.I).group(1), "a aa")
def test_bug_418626(self):
# bugs 418626 at al. -- Testing Greg Chapman's addition of op code
# SRE_OP_MIN_REPEAT_ONE for eliminating recursion on simple uses of
# pattern '*?' on a long string.
self.assertEqual(re.match('.*?c', 10000*'ab'+'cd').end(0), 20001)
self.assertEqual(re.match('.*?cd', 5000*'ab'+'c'+5000*'ab'+'cde').end(0),
20003)
self.assertEqual(re.match('.*?cd', 20000*'abc'+'de').end(0), 60001)
# non-simple '*?' still used to hit the recursion limit, before the
# non-recursive scheme was implemented.
self.assertEqual(re.search('(a|b)*?c', 10000*'ab'+'cd').end(0), 20001)
def test_repeat_minmax_overflow_maxrepeat(self):
try:
# PCRE: this is defined in pcre module
#from _sre import MAXREPEAT
from pcre import MAXREPEAT
except ImportError:
self.skipTest('requires _sre.MAXREPEAT constant')
string = "x" * 100000
self.assertIsNone(re.match(r".{%d}" % (MAXREPEAT - 1), string))
self.assertEqual(re.match(r".{,%d}" % (MAXREPEAT - 1), string).span(),
(0, 100000))
self.assertIsNone(re.match(r".{%d,}?" % (MAXREPEAT - 1), string))
self.assertRaises(OverflowError, re.compile, r".{%d}" % MAXREPEAT)
self.assertRaises(OverflowError, re.compile, r".{,%d}" % MAXREPEAT)
self.assertRaises(OverflowError, re.compile, r".{%d,}?" % MAXREPEAT)
def check_whitelist(rule, nxlog):
"""
:param dict rule:
:param dict nxlog:
:return bool: Did the `rule` whitelisted the `nxlog`?
"""
negative_id = any(i < 0 for i in rule['wl'])
for mz in rule['mz']:
for nb in itertools.count():
matched = False
nxlog_zone = nxlog.get('zone%d' % nb, '')
if not nxlog_zone:
break
if mz.startswith('$'): # named argument
mz_zone, mz_var = mz.split(':', 1)
if mz_zone.endswith('_X'): # regexp named argument
if pcre.match(mz_var, nxlog['var_name%d' % nb], pcre.I) and nxlog_zone == mz_zone[1:-6]:
matched = True
elif nxlog['var_name%d' % nb] == mz_var and nxlog_zone == mz_zone[1:-4]:
matched = True
elif nxlog_zone in mz: # zone without argument
matched = True
if not matched: # We didn't manage to match the nxlog zone `nxlog_zone` with anything in our `rule`
return False
if negative_id:
if int(nxlog['id%d' % nb]) in rule['wl']:
return False
elif int(nxlog['id%d' % nb]) not in rule['wl']:
return False
return True
def test_groupdict(self):
self.assertEqual(
re.match('(?P<first>first) (?P<second>second)',
'first second').groupdict(), {
'first': 'first',
'second': 'second'
})
def run(self):
if not HAVE_PCRE:
return False
ret = False
pcres = list()
kits = [
"angler",
"dotcachef",
"fiesta",
"goon",
"magnitude",
"neutrino",
"nuclear",
"orange",
"rig",
]
office = [
"doc",
"xls",
"ppt",
]
if "feeds" in self.results and self.results["feeds"]:
if "Punch_Plus_Plus_PCREs" in self.results["feeds"]:
with open(self.results["feeds"]["Punch_Plus_Plus_PCREs"], "r") as feedfile:
data = feedfile.read().splitlines()
if data:
for item in data:
regex = item.split()[0]
desc = " ".join(item.split()[1:])
pcres.append((regex, desc))
if "network" in self.results and self.results["network"]:
if "http" in self.results["network"] and self.results["network"]["http"]:
for req in self.results["network"]["http"]:
for regex in pcres:
if pcre.match(regex[0], req["uri"]):
ret = True
add = {"URL": req["uri"]}
if add not in self.data:
self.data.append(add)
self.data.append({"Desc": regex[1]})
self.data.append({"PCRE": regex[0]})
for ek in kits:
check1 = " {0} ek".format(ek)
check2 = " {0} exploit kit".format(ek)
desc = regex[1].lower()
if check1 in desc or check2 in desc:
if ek not in self.families:
self.families = [ek]
if self.results["info"]["package"] in office:
if "dridex" in regex[1].lower() and "dridex" not in self.families:
if not self.families:
self.families = ["dridex"]
if ret:
return True
return False
def extract(fingerprint):
pattern_compiled = pcre.compile(REGEX, flags=parse_compile_flags(RESULT['rule']['pattern']['flags']))
matched = pcre.match(pattern_compiled, fingerprint)
if not matched:
return None
result = copy.deepcopy(RESULT)
result['rule']['portinfo'] = substitute_portinfo_template(result['rule']['portinfo'], matched.groups())
return result
def test_bug_6561(self):
# '\d' should match characters in Unicode category 'Nd'
# (Number, Decimal Digit), but not those in 'Nl' (Number,
# Letter) or 'No' (Number, Other).
decimal_digits = [
u'\u0037', # '\N{DIGIT SEVEN}', category 'Nd'
u'\u0e58', # '\N{THAI DIGIT SIX}', category 'Nd'
u'\uff10', # '\N{FULLWIDTH DIGIT ZERO}', category 'Nd'
]
for x in decimal_digits:
self.assertEqual(re.match('^\d$', x, re.UNICODE).group(0), x)
not_decimal_digits = [
u'\u2165', # '\N{ROMAN NUMERAL SIX}', category 'Nl'
u'\u3039', # '\N{HANGZHOU NUMERAL TWENTY}', category 'Nl'
u'\u2082', # '\N{SUBSCRIPT TWO}', category 'No'
u'\u32b4', # '\N{CIRCLED NUMBER THIRTY NINE}', category 'No'
]
for x in not_decimal_digits:
self.assertIsNone(re.match('^\d$', x, re.UNICODE))
def test_re_match(self):
self.assertEqual(re.match('a', 'a').groups(), ())
self.assertEqual(re.match('(a)', 'a').groups(), ('a',))
self.assertEqual(re.match(r'(a)', 'a').group(0), 'a')
self.assertEqual(re.match(r'(a)', 'a').group(1), 'a')
self.assertEqual(re.match(r'(a)', 'a').group(1, 1), ('a', 'a'))
pat = re.compile('((a)|(b))(c)?')
self.assertEqual(pat.match('a').groups(), ('a', 'a', None, None))
self.assertEqual(pat.match('b').groups(), ('b', None, 'b', None))
self.assertEqual(pat.match('ac').groups(), ('a', 'a', None, 'c'))
self.assertEqual(pat.match('bc').groups(), ('b', None, 'b', 'c'))
self.assertEqual(pat.match('bc').groups(""), ('b', "", 'b', 'c'))
# A single group
m = re.match('(a)', 'a')
self.assertEqual(m.group(0), 'a')
self.assertEqual(m.group(0), 'a')
self.assertEqual(m.group(1), 'a')
self.assertEqual(m.group(1, 1), ('a', 'a'))
pat = re.compile('(?:(?P<a1>a)|(?P<b2>b))(?P<c3>c)?')
self.assertEqual(pat.match('a').group(1, 2, 3), ('a', None, None))
self.assertEqual(pat.match('b').group('a1', 'b2', 'c3'),
(None, 'b', None))
self.assertEqual(pat.match('ac').group(1, 'b2', 3), ('a', None, 'c'))
def test_bug_725106(self):
# capturing groups in alternatives in repeats
self.assertEqual(re.match('^((a)|b)*', 'abc').groups(), ('b', 'a'))
self.assertEqual(re.match('^(([ab])|c)*', 'abc').groups(), ('c', 'b'))
self.assertEqual(re.match('^((d)|[ab])*', 'abc').groups(), ('b', None))
self.assertEqual(
re.match('^((a)c|[ab])*', 'abc').groups(), ('b', None))
self.assertEqual(re.match('^((a)|b)*?c', 'abc').groups(), ('b', 'a'))
self.assertEqual(
re.match('^(([ab])|c)*?d', 'abcd').groups(), ('c', 'b'))
self.assertEqual(
re.match('^((d)|[ab])*?c', 'abc').groups(), ('b', None))
self.assertEqual(
re.match('^((a)c|[ab])*?c', 'abc').groups(), ('b', None))
def test_unlimited_zero_width_repeat(self):
# Issue #9669
self.assertIsNone(re.match(r'(?:a?)*y', 'z'))
self.assertIsNone(re.match(r'(?:a?)+y', 'z'))
self.assertIsNone(re.match(r'(?:a?){2,}y', 'z'))
self.assertIsNone(re.match(r'(?:a?)*?y', 'z'))
self.assertIsNone(re.match(r'(?:a?)+?y', 'z'))
self.assertIsNone(re.match(r'(?:a?){2,}?y', 'z'))
def loads(cls, input_str: str):
null = None
pcre.enable_re_template_mode()
json = pcre.match(cls.__pattern, input_str)
if input_str.isdigit() or (input_str.startswith('-') and input_str[1:].isdigit()):
return input_str
if json is None:
if input_str.startswith('"') and input_str.endswith('"'):
return leval(input_str)
raise SyntaxError('Invalid json format')
else:
json = json.group(0)
res: dict = eval(json, {}, {'null': null})
return res
def test_sre_character_literals(self):
for i in [0, 8, 16, 32, 64, 127, 128, 255]:
self.assertNotEqual(re.match(r"\%03o" % i, chr(i)), None)
self.assertNotEqual(re.match(r"\%03o0" % i, chr(i)+"0"), None)
self.assertNotEqual(re.match(r"\%03o8" % i, chr(i)+"8"), None)
self.assertNotEqual(re.match(r"\x%02x" % i, chr(i)), None)
self.assertNotEqual(re.match(r"\x%02x0" % i, chr(i)+"0"), None)
self.assertNotEqual(re.match(r"\x%02xz" % i, chr(i)+"z"), None)
self.assertRaises(re.error, re.match, "\911", "")
def test_sre_character_class_literals(self):
for i in [0, 8, 16, 32, 64, 127, 128, 255]:
self.assertNotEqual(re.match(r"[\%03o]" % i, chr(i)), None)
self.assertNotEqual(re.match(r"[\%03o0]" % i, chr(i)), None)
self.assertNotEqual(re.match(r"[\%03o8]" % i, chr(i)), None)
self.assertNotEqual(re.match(r"[\x%02x]" % i, chr(i)), None)
self.assertNotEqual(re.match(r"[\x%02x0]" % i, chr(i)), None)
self.assertNotEqual(re.match(r"[\x%02xz]" % i, chr(i)), None)
self.assertRaises(re.error, re.match, "[\911]", "")
def test_bug_725106(self):
# capturing groups in alternatives in repeats
self.assertEqual(re.match('^((a)|b)*', 'abc').groups(),
('b', 'a'))
self.assertEqual(re.match('^(([ab])|c)*', 'abc').groups(),
('c', 'b'))
self.assertEqual(re.match('^((d)|[ab])*', 'abc').groups(),
('b', None))
self.assertEqual(re.match('^((a)c|[ab])*', 'abc').groups(),
('b', None))
self.assertEqual(re.match('^((a)|b)*?c', 'abc').groups(),
('b', 'a'))
self.assertEqual(re.match('^(([ab])|c)*?d', 'abcd').groups(),
('c', 'b'))
self.assertEqual(re.match('^((d)|[ab])*?c', 'abc').groups(),
('b', None))
self.assertEqual(re.match('^((a)c|[ab])*?c', 'abc').groups(),
('b', None))
def test_re_groupref(self):
self.assertEqual(re.match(r'^(\|)?([^()]+)\1$', '|a|').groups(),
('|', 'a'))
self.assertEqual(re.match(r'^(\|)?([^()]+)\1?$', 'a').groups(),
(None, 'a'))
self.assertEqual(re.match(r'^(\|)?([^()]+)\1$', 'a|'), None)
self.assertEqual(re.match(r'^(\|)?([^()]+)\1$', '|a'), None)
self.assertEqual(re.match(r'^(?:(a)|c)(\1)$', 'aa').groups(),
('a', 'a'))
self.assertEqual(re.match(r'^(?:(a)|c)(\1)?$', 'c').groups(),
(None, None))
def runrulesets(self, tokens):
if self.verboselvl:
sys.stderr.write('\tRunning normaliser rules\n')
for ridx, ruleset in enumerate(self.rulesequence):
if self.verboselvl > 1:
sys.stderr.write('\t\tRunning normaliser rule set {0} of {1}\n'.format(ridx+1, len(self.rulesequence)))
if self.verboselvl > 2:
debugnosteps = 20
debugline = '\t\t\t0% [{0:' + str(debugnosteps) + '}] 100%\r'
debugoutline = ''
for i, tk in enumerate(tokens):
if self.verboselvl > 2:
if len(tokens)//debugnosteps:
if i % (len(tokens)//debugnosteps) == 0:
progress = i // (len(tokens)//debugnosteps)
debugoutline = debugline.format('*'*progress)
sys.stderr.write(debugoutline)
sys.stderr.flush()
else:
debugoutline = debugline.format('*'*debugnosteps)
sys.stderr.write(debugoutline)
sys.stderr.flush()
norm_empty = (tk.get('norm') is None or
not match('^[a-z ]*$', tk.get('norm')) or
ruleset[:4] == 'ssml')
if tk.tag == 'tk' and norm_empty:
for rule in self.rules[ruleset]:
tokensxml = []
for tk in tokens:
tokensxml.append(etree.tostring(tk,
pretty_print=True,
encoding='UTF-8')
.strip())
matched = rule.apply(i, tokens)
if matched:
newtokensxml = []
for tk in tokens:
ntkstr = etree.tostring(tk,
pretty_print=True,
encoding='UTF-8')
newtokensxml.append(ntkstr.strip())
break
if self.verboselvl > 2:
sys.stderr.write('\n')
def posnumbersonly(lkp, string, args, output):
n = ''
leading = True
for i, c in enumerate(string):
# minus handled by rule and should be tokenised separately
# one result is single '-' in filter returns nothing.
if i == 0 and c == '-':
pass
#output.append(lkp['-'])
elif c == args['separator']:
pass
elif c == '0' and leading and args['leadingzeros'] == 't':
output.append(lkp['0'])
elif match('[0-9]', c):
leading = False
n = n + c
else:
break
return n
def test_repeat_minmax_overflow(self):
# Issue #13169
string = "x" * 100000
self.assertEqual(re.match(r".{65535}", string).span(), (0, 65535))
self.assertEqual(re.match(r".{,65535}", string).span(), (0, 65535))
self.assertEqual(re.match(r".{65535,}?", string).span(), (0, 65535))
self.assertEqual(re.match(r".{65536}", string).span(), (0, 65536))
self.assertEqual(re.match(r".{,65536}", string).span(), (0, 65536))
self.assertEqual(re.match(r".{65536,}?", string).span(), (0, 65536))
# 2**128 should be big enough to overflow both SRE_CODE and Py_ssize_t.
self.assertRaises(OverflowError, re.compile, r".{%d}" % 2**128)
self.assertRaises(OverflowError, re.compile, r".{,%d}" % 2**128)
self.assertRaises(OverflowError, re.compile, r".{%d,}?" % 2**128)
self.assertRaises(OverflowError, re.compile, r".{%d,%d}" % (2**129, 2**128))
def test_re_groupref_exists(self):
self.assertEqual(
re.match('^(\()?([^()]+)(?(1)\))$', '(a)').groups(), ('(', 'a'))
self.assertEqual(
re.match('^(\()?([^()]+)(?(1)\))$', 'a').groups(), (None, 'a'))
self.assertEqual(re.match('^(\()?([^()]+)(?(1)\))$', 'a)'), None)
self.assertEqual(re.match('^(\()?([^()]+)(?(1)\))$', '(a'), None)
self.assertEqual(
re.match('^(?:(a)|c)((?(1)b|d))$', 'ab').groups(), ('a', 'b'))
self.assertEqual(
re.match('^(?:(a)|c)((?(1)b|d))$', 'cd').groups(), (None, 'd'))
self.assertEqual(
re.match('^(?:(a)|c)((?(1)|d))$', 'cd').groups(), (None, 'd'))
self.assertEqual(
re.match('^(?:(a)|c)((?(1)|d))$', 'a').groups(), ('a', ''))
# Tests for bug #1177831: exercise groups other than the first group
p = re.compile('(?P<g1>a)(?P<g2>b)?((?(g2)c|d))')
self.assertEqual(p.match('abc').groups(), ('a', 'b', 'c'))
self.assertEqual(p.match('ad').groups(), ('a', None, 'd'))
self.assertEqual(p.match('abd'), None)
self.assertEqual(p.match('ac'), None)
def test_re_groupref_exists(self):
self.assertEqual(re.match('^(\()?([^()]+)(?(1)\))$', '(a)').groups(),
('(', 'a'))
self.assertEqual(re.match('^(\()?([^()]+)(?(1)\))$', 'a').groups(),
(None, 'a'))
self.assertEqual(re.match('^(\()?([^()]+)(?(1)\))$', 'a)'), None)
self.assertEqual(re.match('^(\()?([^()]+)(?(1)\))$', '(a'), None)
self.assertEqual(re.match('^(?:(a)|c)((?(1)b|d))$', 'ab').groups(),
('a', 'b'))
self.assertEqual(re.match('^(?:(a)|c)((?(1)b|d))$', 'cd').groups(),
(None, 'd'))
self.assertEqual(re.match('^(?:(a)|c)((?(1)|d))$', 'cd').groups(),
(None, 'd'))
self.assertEqual(re.match('^(?:(a)|c)((?(1)|d))$', 'a').groups(),
('a', ''))
# Tests for bug #1177831: exercise groups other than the first group
p = re.compile('(?P<g1>a)(?P<g2>b)?((?(g2)c|d))')
self.assertEqual(p.match('abc').groups(),
('a', 'b', 'c'))
self.assertEqual(p.match('ad').groups(),
('a', None, 'd'))
self.assertEqual(p.match('abd'), None)
self.assertEqual(p.match('ac'), None)
def test_bug_725149(self):
# mark_stack_base restoring before restoring marks
self.assertEqual(re.match('(a)(?:(?=(b)*)c)*', 'abb').groups(),
('a', None))
self.assertEqual(re.match('(a)((?!(b)*))*', 'abb').groups(),
('a', None, None))
def test_getattr(self):
self.assertEqual(re.match("(a)", "a").pos, 0)
self.assertEqual(re.match("(a)", "a").endpos, 1)
self.assertEqual(re.match("(a)", "a").string, "a")
self.assertEqual(re.match("(a)", "a").regs, ((0, 1), (0, 1)))
self.assertNotEqual(re.match("(a)", "a").re, None)
def test_stack_overflow(self):
# nasty cases that used to overflow the straightforward recursive
# implementation of repeated groups.
self.assertEqual(re.match('(x)*', 50000*'x').group(1), 'x')
self.assertEqual(re.match('(x)*y', 50000*'x'+'y').group(1), 'x')
self.assertEqual(re.match('(x)*?y', 50000*'x'+'y').group(1), 'x')
def test_bug_113254(self):
self.assertEqual(re.match(r'(a)|(b)', 'b').start(1), -1)
self.assertEqual(re.match(r'(a)|(b)', 'b').end(1), -1)
self.assertEqual(re.match(r'(a)|(b)', 'b').span(1), (-1, -1))
def test_repeat_minmax(self):
self.assertEqual(re.match("^(\w){1}$", "abc"), None)
self.assertEqual(re.match("^(\w){1}?$", "abc"), None)
self.assertEqual(re.match("^(\w){1,2}$", "abc"), None)
self.assertEqual(re.match("^(\w){1,2}?$", "abc"), None)
self.assertEqual(re.match("^(\w){3}$", "abc").group(1), "c")
self.assertEqual(re.match("^(\w){1,3}$", "abc").group(1), "c")
self.assertEqual(re.match("^(\w){1,4}$", "abc").group(1), "c")
self.assertEqual(re.match("^(\w){3,4}?$", "abc").group(1), "c")
self.assertEqual(re.match("^(\w){3}?$", "abc").group(1), "c")
self.assertEqual(re.match("^(\w){1,3}?$", "abc").group(1), "c")
self.assertEqual(re.match("^(\w){1,4}?$", "abc").group(1), "c")
self.assertEqual(re.match("^(\w){3,4}?$", "abc").group(1), "c")
self.assertEqual(re.match("^x{1}$", "xxx"), None)
self.assertEqual(re.match("^x{1}?$", "xxx"), None)
self.assertEqual(re.match("^x{1,2}$", "xxx"), None)
self.assertEqual(re.match("^x{1,2}?$", "xxx"), None)
self.assertNotEqual(re.match("^x{3}$", "xxx"), None)
self.assertNotEqual(re.match("^x{1,3}$", "xxx"), None)
self.assertNotEqual(re.match("^x{1,4}$", "xxx"), None)
self.assertNotEqual(re.match("^x{3,4}?$", "xxx"), None)
self.assertNotEqual(re.match("^x{3}?$", "xxx"), None)
self.assertNotEqual(re.match("^x{1,3}?$", "xxx"), None)
self.assertNotEqual(re.match("^x{1,4}?$", "xxx"), None)
self.assertNotEqual(re.match("^x{3,4}?$", "xxx"), None)
self.assertEqual(re.match("^x{}$", "xxx"), None)
self.assertNotEqual(re.match("^x{}$", "x{}"), None)
def test_anyall(self):
self.assertEqual(re.match("a.b", "a\nb", re.DOTALL).group(0),
"a\nb")
self.assertEqual(re.match("a.*b", "a\n\nb", re.DOTALL).group(0),
"a\n\nb")
def test_non_consuming(self):
self.assertEqual(re.match("(a(?=\s[^a]))", "a b").group(1), "a")
self.assertEqual(re.match("(a(?=\s[^a]*))", "a b").group(1), "a")
self.assertEqual(re.match("(a(?=\s[abc]))", "a b").group(1), "a")
self.assertEqual(re.match("(a(?=\s[abc]*))", "a bc").group(1), "a")
self.assertEqual(re.match(r"(a)(?=\s\1)", "a a").group(1), "a")
self.assertEqual(re.match(r"(a)(?=\s\1*)", "a aa").group(1), "a")
self.assertEqual(re.match(r"(a)(?=\s(abc|a))", "a a").group(1), "a")
self.assertEqual(re.match(r"(a(?!\s[^a]))", "a a").group(1), "a")
self.assertEqual(re.match(r"(a(?!\s[abc]))", "a d").group(1), "a")
self.assertEqual(re.match(r"(a)(?!\s\1)", "a b").group(1), "a")
self.assertEqual(re.match(r"(a)(?!\s(abc|a))", "a b").group(1), "a")
def test_category(self):
self.assertEqual(re.match(r"(\s)", " ").group(1), " ")
def test_expand(self):
self.assertEqual(re.match("(?P<first>first) (?P<second>second)",
"first second")
.expand(r"\2 \1 \g<second> \g<first>"),
"second first second first")
