Revert [7849] and [7850]. Brain failure on my part.

git-svn-id: http://code.djangoproject.com/svn/django/trunk@7851 bcc190cf-cafb-0310-a4f2-bffc1f526a37
This commit is contained in:
Malcolm Tredinnick 2008-07-06 14:20:30 +00:00
parent c2f753a8ba
commit 5deb4fcbb9
2 changed files with 6 additions and 156 deletions

View File

@ -1,123 +0,0 @@
"""
Functions for reversing a regular expression (used in reverse URL resolving).
This is not, and is not intended to be, a complete reg-exp decompiler. It
should be good enough for almost all sane URLs.
"""
import re
from bisect import bisect
GROUP_CLASS = re.compile(r'''\((?:
(?P<positional>[^?])| # Unnamed (positional) capturing group.
\?(?:
P<(?P<named>[\w]+)>(?P<contents>.*)| # Named capturing group.
P=(?P<repeat>.+)| # Repeat of a previous named group.
(?P<grouping>:)| # Non-capturing grouping parens.
(?P<comment>\#)| # Comment group
(?P<illegal>.) # Anything else (which will be an error)
)
).*\)''', re.VERBOSE)
def normalize(pattern):
"""
Given a reg-exp pattern, normalizes it to a list of forms that suffice for
reverse matching. This does the following:
(1) For any repeating sections, keeps the minimum number of occurrences
permitted (this means zero for optional groups).
(2) If an optional group includes parameters, include one occurrence of
that group (along with the zero occurrence case from step (1)).
(3) Select the first (essentially an arbitrary) element from any character
class. Select an arbitrary character for any unordered class (e.g. '.' or
'\w') in the pattern.
(4) Take the first alternative in any '|' division, unless other
alternatives would involve different parameters.
(5) Ignore comments. Error on all other non-capturing (?...) forms (e.g.
look-ahead and look-behind matches).
Returns a list of tuples, each tuple containing (a) a pattern, (b) the
number of parameters, (c) the names of the parameters. Any unnamed
parameters are called '_0', '_1', etc.
"""
# Do a linear scan to work out the special features of this pattern. The
# idea is that we scan once here and collect all the information we need to
# make future decisions.
groups = [] # (start, end)
quantifiers = [] # start pos
ranges = [] # (start, end)
eols = [] # pos
disjunctions = [] # pos
unclosed_groups = []
unclosed_ranges = []
escaped = False
quantify = False
in_range = False
for pos, c in enumerate(pattern):
if in_range and c != ']' or (c == ']' and
unclosed_ranges[-1] == pos - 1):
continue
elif c == '[':
unclosed_ranges.append(pos)
elif c == ']':
ranges.append((unclosed_ranges.pop(), pos + 1))
in_range = False
elif c == '.':
# Treat this as a one-character long range:
ranges.append((pos, pos + 1))
elif escaped or c == '\\':
escaped = not escaped
elif c == '(':
unclosed_groups.append(pos)
elif c == ')':
groups.append((unclosed_groups.pop(), pos + 1))
elif quantify and c == '?':
quantify = False
elif c in '?*+{':
quantifiers.append(pos)
quantify = True
elif c == '$':
eols.append(pos)
elif c == '|':
disjunctions.append(pos)
# Now classify each of the parenthetical groups to work out which ones take
# parameters. Only the outer-most of a set of nested capturing groups is
# important.
groups.sort()
params = []
comments = []
last_end = 0
for start, end in groups:
if start < last_end:
# Skip over inner nested capturing groups.
continue
m = GROUP_CLASS.match(pattern, start)
if m.group('positional'):
params.append((start, end, '_%d' % len(params), start + 1))
elif m.group('named'):
params.append((start, end, m.group('named'), m.start('contents')))
elif m.group('repeat'):
params.append((start, end, m.group('repeat'), start + 1))
elif m.group('illegal'):
raise ValueError('The pattern construct %r is not valid here.'
% pattern[start:end])
elif m.group('comment'):
comments.extend([start, end])
else:
# This is a non-capturing set, so nesting prohibitions don't apply
# to any inner groups.
continue
last_end = end
# XXX: Got to here!
results = []
end = groups[0][0]
# The first bit, before the first group starts.
if end == 0:
# FIXME: don't want to handle this case just yet.
raise Exception
quant_end = bisect(quantifiers, end)
range_end = bisect(ranges, end)
dis_end = bisect(disjunctions, end)

View File

@ -1,32 +1,19 @@
"""
Unit tests for reverse URL lookups.
"""
import re
import unittest
"Unit tests for reverse URL lookup"
from django.core.urlresolvers import reverse_helper, NoReverseMatch
import re, unittest
test_data = (
('^places/(\d+)/$', 'places/3/', [3], {}),
('^places/(\d+)/$', 'places/3/', ['3'], {}),
('^places/(\d+)/$', NoReverseMatch, ['a'], {}),
('^places/(\d+)/$', NoReverseMatch, [], {}),
('^places?/$', '/', [], {}),
('^places+/$', 'places/', [], {}),
('^places*/$', '/', [], {}),
(r'^places/(\d+|[a-z_]+)/', 'places/4/', [4], {}),
(r'^places/(\d+|[a-z_]+)/', 'places/harlem/', ['harlem'], {}),
(r'^places/(\d+|[a-z_]+)/', NoReverseMatch, ['harlem64'], {}),
('^places/(?P<id>\d+)/$', 'places/3/', [], {'id': 3}),
('^people/(?P<name>\w+)/$', NoReverseMatch, [], {}),
('^people/(?P<name>\w+)/$', 'people/adrian/', ['adrian'], {}),
('^people/(?P<name>\w+)/$', 'people/adrian/', [], {'name': 'adrian'}),
('^people/(?P<name>\w+)/$', NoReverseMatch, ['name with spaces'], {}),
('^people/(?P<name>\w+)/$', NoReverseMatch, [], {'name': 'name with spaces'}),
('^people/(?:name/)', 'people/name/', [], {}),
('^people/(?:name/)?', 'people/', [], {}),
('^people/(?:name/(\w+)/)?', 'people/name/fred/', ['fred'], {}),
('^people/(?P<name>\w+)/$', NoReverseMatch, [], {}),
('^hardcoded/$', 'hardcoded/', [], {}),
('^hardcoded/$', 'hardcoded/', ['any arg'], {}),
('^hardcoded/$', 'hardcoded/', [], {'kwarg': 'foo'}),
@ -37,31 +24,17 @@ test_data = (
('^people/(?P<state>\w\w)/(?P<name>\w+)/$', NoReverseMatch, [], {'name': 'adrian'}),
('^people/(?P<state>\w\w)/(\w+)/$', NoReverseMatch, ['il'], {'name': 'adrian'}),
('^people/(?P<state>\w\w)/(\w+)/$', 'people/il/adrian/', ['adrian'], {'state': 'il'}),
(r'^people/((?P<state>\w\w)/test)?/(\w+)/$', 'people/il/test/adrian/', ['adrian'], {'state': 'il'}),
(r'^people/((?P<state>\w\w)/test)?/(\w+)/$', NoReverseMatch, ['adrian'], {}),
('^character_set/[abcdef0-9]/$', 'character_set/a/', [], {}),
('^character_set/[\w]/$', 'character_set/a/', [], {}),
(r'^price/\$(\d+)/$', 'price/$10/', ['10'], {}),
(r'^price/[$](\d+)/$', 'price/$10/', ['10'], {}),
(r'^price/[\$](\d+)/$', 'price/$10/', ['10'], {}),
(r'^product/(?P<product>\w+)\+\(\$(?P<price>\d+(\.\d+)?)\)/$', 'product/chocolate+($2.00)/', ['2.00'], {'product': 'chocolate'}),
(r'^headlines/(?P<year>\d+)\.(?P<month>\d+)\.(?P<day>\d+)/$', 'headlines/2007.5.21/', [], dict(year=2007, month=5, day=21)),
(r'^windows_path/(?P<drive_name>[A-Z]):\\(?P<path>.+)/$', r'windows_path/C:\Documents and Settings\spam/', [], dict(drive_name='C', path=r'Documents and Settings\spam')),
(r'^special_chars/(.+)/$', r'special_chars/+\$*/', [r'+\$*'], {}),
(r'^special_chars/(.+)/$', NoReverseMatch, [''], {}),
(r'^(?P<name>.+)/\d+/$', NoReverseMatch, [], {'name': 'john'}),
(r'^repeats/a{1,2}/$', 'repeats/a/', [], {}),
(r'^repeats/a{2,4}/$', 'repeats/aa/', [], {}),
(r'^people/(?:(?:wilma|fred)/)$', '/people/wilma', [], {}),
)
class URLPatternReverse(unittest.TestCase):
def test_urlpattern_reverse(self):
for regex, expected, args, kwargs in test_data:
try:
got = reverse_helper(regex, *args, **kwargs)
got = reverse_helper(re.compile(regex), *args, **kwargs)
except NoReverseMatch, e:
self.assertEqual(expected, NoReverseMatch)
else:
self.assertEquals(got, expected)
if __name__ == "__main__":
run_tests(1)