Mercurial > hg > urlmatch
annotate urlmatch.py @ 3:00266c7a7c3c
since there is only one module, dont bother with the whole directory thing
| author | Jeff Hammel <jhammel@mozilla.com> |
|---|---|
| date | Fri, 17 Jun 2011 10:39:37 -0700 |
| parents | urlmatch/__init__.py@750dc780d3d8 |
| children | 23be092e6099 |
| rev | line source |
|---|---|
| 0 | 1 import urlparse |
| 2 | |
| 3 class UrlMatcher(object): | |
| 4 | |
| 5 def __init__(self, *urls): | |
| 6 match_order=('domain', 'scheme', 'path') | |
| 7 self.order = match_order | |
| 8 self.urls = {} | |
| 9 for url in urls: | |
| 10 self.add(url) | |
| 11 | |
| 12 def decompose(self, url): | |
| 13 | |
| 14 # break it down | |
| 15 (scheme, netloc, path, query, fragment) = urlparse.urlsplit(url) | |
| 16 urldict = {} | |
| 17 | |
| 18 # domain | |
| 19 netloc = netloc.split('.') | |
| 20 if len(netloc) == 1: | |
| 21 urldict['domain'] = netloc | |
| 22 else: | |
| 23 # assert a TLD | |
| 24 urldict['domain'] = [netloc[-2], netloc[-1]] + list(reversed(netloc[0:-2])) | |
| 25 | |
| 26 # path | |
| 27 path = path.strip('/').split('/') | |
| 28 if path == ['']: | |
| 29 path = [] | |
| 30 urldict['path'] = path | |
| 31 | |
| 32 # scheme | |
| 33 urldict['scheme'] = scheme | |
| 34 | |
| 35 # could do others | |
| 36 | |
| 37 return urldict | |
| 38 | |
| 39 def add(self, url): | |
| 40 if url not in self.urls: | |
| 41 self.urls[url] = self.decompose(url) | |
| 42 | |
|
1
750dc780d3d8
stub a diff method; really, i have no idea what im doing
Jeff Hammel <jhammel@mozilla.com>
parents:
0
diff
changeset
|
43 def diff(self, url1, url2): |
|
750dc780d3d8
stub a diff method; really, i have no idea what im doing
Jeff Hammel <jhammel@mozilla.com>
parents:
0
diff
changeset
|
44 |
|
750dc780d3d8
stub a diff method; really, i have no idea what im doing
Jeff Hammel <jhammel@mozilla.com>
parents:
0
diff
changeset
|
45 # decompose the urls if necessary |
|
750dc780d3d8
stub a diff method; really, i have no idea what im doing
Jeff Hammel <jhammel@mozilla.com>
parents:
0
diff
changeset
|
46 if isinstance(url1, basestring): |
|
750dc780d3d8
stub a diff method; really, i have no idea what im doing
Jeff Hammel <jhammel@mozilla.com>
parents:
0
diff
changeset
|
47 url1 = self.decompose(url) |
|
750dc780d3d8
stub a diff method; really, i have no idea what im doing
Jeff Hammel <jhammel@mozilla.com>
parents:
0
diff
changeset
|
48 if isinstance(url2, basestring): |
|
750dc780d3d8
stub a diff method; really, i have no idea what im doing
Jeff Hammel <jhammel@mozilla.com>
parents:
0
diff
changeset
|
49 url2 = self.decompose(url) |
|
750dc780d3d8
stub a diff method; really, i have no idea what im doing
Jeff Hammel <jhammel@mozilla.com>
parents:
0
diff
changeset
|
50 |
|
750dc780d3d8
stub a diff method; really, i have no idea what im doing
Jeff Hammel <jhammel@mozilla.com>
parents:
0
diff
changeset
|
51 # TODO: finish |
|
750dc780d3d8
stub a diff method; really, i have no idea what im doing
Jeff Hammel <jhammel@mozilla.com>
parents:
0
diff
changeset
|
52 raise NotImplementedError |
|
750dc780d3d8
stub a diff method; really, i have no idea what im doing
Jeff Hammel <jhammel@mozilla.com>
parents:
0
diff
changeset
|
53 |
| 0 | 54 def match(self, url): |
| 55 if '://' not in url: | |
| 56 # give a bogus scheme for urlparse. boo! | |
| 57 urldict = self.decompose('bogus://' + url) | |
| 58 urldict.pop('scheme') | |
| 59 else: | |
| 60 urldict = self.decompose(url) | |
| 61 | |
| 62 order = self.order | |
| 63 urls = set(self.urls.keys()) | |
| 64 for field in order: | |
| 65 value = urldict.get(field) | |
| 66 if not value: | |
| 67 # don't match trivial fields | |
| 68 continue | |
| 69 length = len(value) | |
| 70 deleted = set() | |
| 71 for key in list(urls)[:]: | |
| 72 compare_value = self.urls[key].get(field) | |
| 73 if not compare_value: | |
| 74 urls.discard(key) | |
| 75 continue | |
| 76 if isinstance(value, basestring) and value != compare_value: | |
| 77 urls.discard(key) | |
| 78 continue | |
| 79 if len(compare_value) < length: | |
| 80 urls.discard(key) | |
| 81 continue | |
| 82 if compare_value[:len(value)] != value: | |
| 83 urls.discard(key) | |
| 84 if not urls: | |
| 85 return [] | |
| 86 return urls | |
| 87 | |
| 88 if __name__ == '__main__': | |
| 89 matcher = UrlMatcher('http://www.example.com/foo/bar/fleem') | |
| 90 matcher.add('http://www.example.com/foo/blah') | |
| 91 matcher.add('https://www.example.com/foo/') | |
| 92 matcher.add('https://www.example.net/foo/') | |
| 93 print matcher.match('example.com/foo/bar') | |
| 94 print matcher.match('http://example.com/foo') | |
| 95 print matcher.match('example.com') | |
| 96 print matcher.match('example') |