def test_empty_array(self):
# SF buf 1647541
import array
for typecode in 'cbBuhHiIlLfd':
a = array.array(typecode)
assert re.compile("bla").match(a) == None
assert re.compile("").match(a).groups() == ()
def test_empty_array(self):
# SF buf 1647541
import array
for typecode in 'cbBuhHiIlLfd':
a = array.array(typecode)
assert re.compile("bla").match(a) == None
assert re.compile("").match(a).groups() == ()
def test_bug_926075(self):
try:
unicode
except NameError:
return # no problem if we have no unicode
assert (re.compile('bug_926075') is not
re.compile(eval("u'bug_926075'")))
def test_re_match(self):
assert re.match('a', 'a').groups() == ()
assert re.match('(a)', 'a').groups() == ('a',)
assert re.match(r'(a)', 'a').group(0) == 'a'
assert re.match(r'(a)', 'a').group(1) == 'a'
assert re.match(r'(a)', 'a').group(1, 1) == ('a', 'a')
pat = re.compile('((a)|(b))(c)?')
assert pat.match('a').groups() == ('a', 'a', None, None)
assert pat.match('b').groups() == ('b', None, 'b', None)
assert pat.match('ac').groups() == ('a', 'a', None, 'c')
assert pat.match('bc').groups() == ('b', None, 'b', 'c')
assert pat.match('bc').groups("") == ('b', "", 'b', 'c')
# A single group
m = re.match('(a)', 'a')
assert m.group(0) == 'a'
assert m.group(0) == 'a'
assert m.group(1) == 'a'
assert m.group(1, 1) == ('a', 'a')
pat = re.compile('(?:(?P<a1>a)|(?P<b2>b))(?P<c3>c)?')
assert pat.match('a').group(1, 2, 3) == ('a', None, None)
assert pat.match('b').group('a1', 'b2', 'c3') == (
(None, 'b', None))
assert pat.match('ac').group(1, 'b2', 3) == ('a', None, 'c')
def test_bug_926075(self):
try:
unicode
except NameError:
return # no problem if we have no unicode
assert (re.compile('bug_926075')
is not re.compile(eval("u'bug_926075'")))
def test_re_match(self):
assert re.match('a', 'a').groups() == ()
assert re.match('(a)', 'a').groups() == ('a', )
assert re.match(r'(a)', 'a').group(0) == 'a'
assert re.match(r'(a)', 'a').group(1) == 'a'
assert re.match(r'(a)', 'a').group(1, 1) == ('a', 'a')
pat = re.compile('((a)|(b))(c)?')
assert pat.match('a').groups() == ('a', 'a', None, None)
assert pat.match('b').groups() == ('b', None, 'b', None)
assert pat.match('ac').groups() == ('a', 'a', None, 'c')
assert pat.match('bc').groups() == ('b', None, 'b', 'c')
assert pat.match('bc').groups("") == ('b', "", 'b', 'c')
# A single group
m = re.match('(a)', 'a')
assert m.group(0) == 'a'
assert m.group(0) == 'a'
assert m.group(1) == 'a'
assert m.group(1, 1) == ('a', 'a')
pat = re.compile('(?:(?P<a1>a)|(?P<b2>b))(?P<c3>c)?')
assert pat.match('a').group(1, 2, 3) == ('a', None, None)
assert pat.match('b').group('a1', 'b2', 'c3') == ((None, 'b', None))
assert pat.match('ac').group(1, 'b2', 3) == ('a', None, 'c')
def test_bug_931848(self):
try:
unicode
except NameError:
pass
pattern = eval('u"[\u002E\u3002\uFF0E\uFF61]"')
assert re.compile(pattern).split("a.b.c") == (['a', 'b', 'c'])
def test_bug_931848(self):
try:
unicode
except NameError:
pass
pattern = eval('u"[\u002E\u3002\uFF0E\uFF61]"')
assert re.compile(pattern).split("a.b.c") == (
['a','b','c'])
def test_bug_764548(self):
# bug 764548, re.compile() barfs on str/unicode subclasses
try:
unicode
except NameError:
return # no problem if we have no unicode
class my_unicode(unicode): pass
pat = re.compile(my_unicode("abc"))
assert pat.match("xyz") == None
def pickle_test(self, pickle):
oldpat = re.compile('a(?:b|(c|e){1,2}?|d)+?(.)')
s = pickle.dumps(oldpat)
newpat = pickle.loads(s)
# Not using object identity for _sre.py, since some Python builds do
# not seem to preserve that in all cases (observed on an UCS-4 build
# of 2.4.1).
#self.assertEqual(oldpat, newpat)
assert oldpat.__dict__ == newpat.__dict__
def test_bug_581080(self):
iter = re.finditer(r"\s", "a b")
assert iter.next().span() == (1,2)
raises(StopIteration, iter.next)
if 0: # XXX
scanner = re.compile(r"\s").scanner("a b")
assert scanner.search().span() == (1, 2)
assert scanner.search() == None
def test_bug_581080(self):
iter = re.finditer(r"\s", "a b")
assert iter.next().span() == (1, 2)
raises(StopIteration, iter.next)
if 0: # XXX
scanner = re.compile(r"\s").scanner("a b")
assert scanner.search().span() == (1, 2)
assert scanner.search() == None
def pickle_test(self, pickle):
oldpat = re.compile('a(?:b|(c|e){1,2}?|d)+?(.)')
s = pickle.dumps(oldpat)
newpat = pickle.loads(s)
# Not using object identity for _sre.py, since some Python builds do
# not seem to preserve that in all cases (observed on an UCS-4 build
# of 2.4.1).
#self.assertEqual(oldpat, newpat)
assert oldpat.__dict__ == newpat.__dict__
def test_re_escape(self):
p=""
for i in range(0, 256):
p = p + chr(i)
assert re.match(re.escape(chr(i)), chr(i)) is not None
assert re.match(re.escape(chr(i)), chr(i)).span() == (0,1)
pat=re.compile(re.escape(p))
assert pat.match(p) is not None
assert pat.match(p).span() == (0,256)
def test_re_escape(self):
p = ""
for i in range(0, 256):
p = p + chr(i)
assert re.match(re.escape(chr(i)), chr(i)) is not None
assert re.match(re.escape(chr(i)), chr(i)).span() == (0, 1)
pat = re.compile(re.escape(p))
assert pat.match(p) is not None
assert pat.match(p).span() == (0, 256)
def test_bug_764548(self):
# bug 764548, re.compile() barfs on str/unicode subclasses
try:
unicode
except NameError:
return # no problem if we have no unicode
class my_unicode(unicode):
pass
pat = re.compile(my_unicode("abc"))
assert pat.match("xyz") == None
def test_inline_flags(self):
# Bug #1700
upper_char = unichr(0x1ea0) # Latin Capital Letter A with Dot Bellow
lower_char = unichr(0x1ea1) # Latin Small Letter A with Dot Bellow
p = re.compile(upper_char, re.I | re.U)
q = p.match(lower_char)
assert q != None
p = re.compile(lower_char, re.I | re.U)
q = p.match(upper_char)
assert q != None
p = re.compile('(?i)' + upper_char, re.U)
q = p.match(lower_char)
assert q != None
p = re.compile('(?i)' + lower_char, re.U)
q = p.match(upper_char)
assert q != None
p = re.compile('(?iu)' + upper_char)
q = p.match(lower_char)
assert q != None
p = re.compile('(?iu)' + lower_char)
q = p.match(upper_char)
assert q != None
def test_inline_flags(self):
# Bug #1700
upper_char = unichr(0x1ea0) # Latin Capital Letter A with Dot Bellow
lower_char = unichr(0x1ea1) # Latin Small Letter A with Dot Bellow
p = re.compile(upper_char, re.I | re.U)
q = p.match(lower_char)
assert q != None
p = re.compile(lower_char, re.I | re.U)
q = p.match(upper_char)
assert q != None
p = re.compile('(?i)' + upper_char, re.U)
q = p.match(lower_char)
assert q != None
p = re.compile('(?i)' + lower_char, re.U)
q = p.match(upper_char)
assert q != None
p = re.compile('(?iu)' + upper_char)
q = p.match(lower_char)
assert q != None
p = re.compile('(?iu)' + lower_char)
q = p.match(upper_char)
assert q != None
def test_re_groupref_exists(self):
assert re.match('^(\()?([^()]+)(?(1)\))$',
'(a)').groups() == (('(', 'a'))
assert re.match('^(\()?([^()]+)(?(1)\))$',
'a').groups() == ((None, 'a'))
assert re.match('^(\()?([^()]+)(?(1)\))$', 'a)') == None
assert re.match('^(\()?([^()]+)(?(1)\))$', '(a') == None
assert re.match('^(?:(a)|c)((?(1)b|d))$',
'ab').groups() == (('a', 'b'))
assert re.match('^(?:(a)|c)((?(1)b|d))$',
'cd').groups() == ((None, 'd'))
assert re.match('^(?:(a)|c)((?(1)|d))$',
'cd').groups() == ((None, 'd'))
assert 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))')
assert p.match('abc').groups() == (('a', 'b', 'c'))
assert p.match('ad').groups() == (('a', None, 'd'))
assert p.match('abd') == None
assert p.match('ac') == None
def test_re_groupref_exists(self):
assert re.match('^(\()?([^()]+)(?(1)\))$', '(a)').groups() == (
('(', 'a'))
assert re.match('^(\()?([^()]+)(?(1)\))$', 'a').groups() == (
(None, 'a'))
assert re.match('^(\()?([^()]+)(?(1)\))$', 'a)') == None
assert re.match('^(\()?([^()]+)(?(1)\))$', '(a') == None
assert re.match('^(?:(a)|c)((?(1)b|d))$', 'ab').groups() == (
('a', 'b'))
assert re.match('^(?:(a)|c)((?(1)b|d))$', 'cd').groups() == (
(None, 'd'))
assert re.match('^(?:(a)|c)((?(1)|d))$', 'cd').groups() == (
(None, 'd'))
assert re.match('^(?:(a)|c)((?(1)|d))$', 'a').groups() == (
('a', ''))
# Tests for bug #1177831: exercise groups other than the first group
p = re.compile('(?P<g1>a)(?P<g2>b)?((?(g2)c|d))')
assert p.match('abc').groups() == (
('a', 'b', 'c'))
assert p.match('ad').groups() == (
('a', None, 'd'))
assert p.match('abd') == None
assert p.match('ac') == None
string = chr(n) * n
rsre_core.search(pattern, string)
#
unicodestr = unichr(n) * n
ctx = rsre_core.UnicodeMatchContext(pattern, unicodestr, 0,
len(unicodestr), 0)
rsre_core.search_context(ctx)
#
return 0
def test_gengraph():
t, typer, graph = gengraph(main, [int])
m = compile("(a|b)aaaaa")
def test_match():
def f(i):
if i:
s = "aaaaaa"
else:
s = "caaaaa"
g = m.match(s)
if g is None:
return 3
return int("aaaaaa" == g.group(0))
assert interpret(f, [3]) == 1
assert interpret(f, [0]) == 3
def test_flags(self):
for flag in [re.I, re.M, re.X, re.S, re.L]:
assert re.compile('^pattern$', flag) != None
def test_bug_612074(self):
pat = u"[" + re.escape(u"\u2039") + u"]"
assert re.compile(pat) and 1 == 1
pattern = [n] * n
string = chr(n) * n
rsre_core.search(pattern, string)
#
unicodestr = unichr(n) * n
ctx = rsre_core.UnicodeMatchContext(pattern, unicodestr, 0, len(unicodestr), 0)
rsre_core.search_context(ctx)
#
return 0
def test_gengraph():
t, typer, graph = gengraph(main, [int])
m = compile("(a|b)aaaaa")
def test_match():
def f(i):
if i:
s = "aaaaaa"
else:
s = "caaaaa"
g = m.match(s)
if g is None:
return 3
return int("aaaaaa" == g.group(0))
assert interpret(f, [3]) == 1
assert interpret(f, [0]) == 3
def test_bug_612074(self):
pat=u"["+re.escape(u"\u2039")+u"]"
assert re.compile(pat) and 1 == 1
def test_flags(self):
for flag in [re.I, re.M, re.X, re.S, re.L]:
assert re.compile('^pattern$', flag) != None
