- added lookbehind support (?<=pattern), (?<!pattern).

the pattern must have a fixed width.

- got rid of array-module dependencies; the match pro-
  gram is now stored inside the pattern object, rather
  than in an extra string buffer.

- cleaned up a various of potential leaks, api abuses,
  and other minors in the engine module.

- use mal's new isalnum macro, rather than my own work-
  around.

- untabified test_sre.py.  seems like I removed a couple
  of trailing spaces in the process...
This commit is contained in:
Fredrik Lundh 2000-07-03 18:44:21 +00:00
parent 40c48685a2
commit 6f01398236
5 changed files with 138 additions and 104 deletions

View file

@ -35,20 +35,20 @@ if verbose:
try:
assert sre.sub("(?i)b+", "x", "bbbb BBBB") == 'x x'
def bump_num(matchobj):
int_value = int(matchobj.group(0))
return str(int_value + 1)
assert sre.sub(r'\d+', bump_num, '08.2 -2 23x99y') == '9.3 -3 24x100y'
assert sre.sub(r'\d+', bump_num, '08.2 -2 23x99y', 3) == '9.3 -3 23x99y'
assert sre.sub('.', lambda m: r"\n", 'x') == '\\n'
assert sre.sub('.', r"\n", 'x') == '\n'
s = r"\1\1"
assert sre.sub('(.)', s, 'x') == 'xx'
assert sre.sub('(.)', sre.escape(s), 'x') == s
assert sre.sub('(.)', sre.escape(s), 'x') == s
assert sre.sub('(.)', lambda m: s, 'x') == s
assert sre.sub('(?P<a>x)', '\g<a>\g<a>', 'xx') == 'xxxx'
@ -144,7 +144,7 @@ except AssertionError:
if verbose:
print 'Running tests on sre.split'
try:
assert sre.split(":", ":a:b::c") == ['', 'a', 'b', '', 'c']
assert sre.split(":*", ":a:b::c") == ['', 'a', 'b', 'c']
@ -164,7 +164,7 @@ try:
assert sre.split(':', 'a:b:c:d', 2) == ['a', 'b', 'c:d']
assert sre.split("(:)", ":a:b::c", 2) == ['', ':', 'a', ':', 'b::c']
assert sre.split("(:*)", ":a:b::c", 2) == ['', ':', 'a', ':', 'b::c']
assert sre.split("(:*)", ":a:b::c", 2) == ['', ':', 'a', ':', 'b::c']
except AssertionError:
raise TestFailed, "qualified sre.split"
@ -186,29 +186,29 @@ if verbose:
try:
# No groups at all
m = sre.match('a', 'a') ; assert m.groups() == ()
m = sre.match('a', 'a') ; assert m.groups() == ()
# A single group
m = sre.match('(a)', 'a') ; assert m.groups() == ('a',)
m = sre.match('(a)', 'a') ; assert m.groups() == ('a',)
pat = sre.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')
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')
except AssertionError:
raise TestFailed, "match .groups() method"
try:
# A single group
m = sre.match('(a)', 'a')
assert m.group(0) == 'a' ; assert m.group(0) == 'a'
m = sre.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 = sre.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')
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')
except AssertionError:
raise TestFailed, "match .group() method"
@ -252,10 +252,10 @@ try:
assert sre.I == sre.IGNORECASE
assert sre.L == sre.LOCALE
assert sre.M == sre.MULTILINE
assert sre.S == sre.DOTALL
assert sre.X == sre.VERBOSE
assert sre.T == sre.TEMPLATE
assert sre.U == sre.UNICODE
assert sre.S == sre.DOTALL
assert sre.X == sre.VERBOSE
assert sre.T == sre.TEMPLATE
assert sre.U == sre.UNICODE
except AssertionError:
raise TestFailed, 're module constants'
@ -272,7 +272,7 @@ if verbose:
else:
# To save time, only run the first and last 10 tests
#tests = tests[:10] + tests[-10:]
pass
pass
for t in tests:
sys.stdout.flush()
@ -280,7 +280,7 @@ for t in tests:
if len(t)==5:
pattern, s, outcome, repl, expected = t
elif len(t)==3:
pattern, s, outcome = t
pattern, s, outcome = t
else:
raise ValueError, ('Test tuples should have 3 or 5 fields',t)
@ -288,7 +288,7 @@ for t in tests:
obj=sre.compile(pattern)
except sre.error:
if outcome==SYNTAX_ERROR: pass # Expected a syntax error
else:
else:
print '=== Syntax error:', t
except KeyboardInterrupt: raise KeyboardInterrupt
except:
@ -356,7 +356,7 @@ for t in tests:
# of the match and see if it still succeeds. \B will
# break (because it won't match at the end or start of a
# string), so we'll ignore patterns that feature it.
if pattern[:2]!='\\B' and pattern[-2:]!='\\B':
obj=sre.compile(pattern)
result=obj.search(s, result.start(0), result.end(0)+1)