forked from samuelclay/NewsBlur
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathurlnorm.py
221 lines (193 loc) · 8.24 KB
/
urlnorm.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
"""
URI Normalization function:
* Always provide the URI scheme in lowercase characters.
* Always provide the host, if any, in lowercase characters.
* Only perform percent-encoding where it is essential.
* Always use uppercase A-through-F characters when percent-encoding.
* Prevent dot-segments appearing in non-relative URI paths.
* For schemes that define a default authority, use an empty authority if the
default is desired.
* For schemes that define an empty path to be equivalent to a path of "/",
use "/".
* For schemes that define a port, use an empty port if the default is desired
* All portions of the URI must be utf-8 encoded NFC from Unicode strings
implements:
http://gbiv.com/protocols/uri/rev-2002/rfc2396bis.html#canonical-form
http://www.intertwingly.net/wiki/pie/PaceCanonicalIds
inspired by:
Tony J. Ibbs, http://starship.python.net/crew/tibs/python/tji_url.py
Mark Nottingham, http://www.mnot.net/python/urlnorm.py
"""
__license__ = "Python"
import re, unicodedata, urlparse
from urllib import quote, unquote
default_port = {
'ftp': 21,
'telnet': 23,
'http': 80,
'gopher': 70,
'news': 119,
'nntp': 119,
'prospero': 191,
'https': 443,
'snews': 563,
'snntp': 563,
}
def normalize(url):
"""Normalize a URL."""
if not isinstance(url, basestring):
return url
scheme,auth,path,query,fragment = urlparse.urlsplit(url.strip())
(userinfo,host,port)=re.search('([^@]*@)?([^:]*):?(.*)',auth).groups()
# Always provide the URI scheme in lowercase characters.
scheme = scheme.lower()
# Always provide the host, if any, in lowercase characters.
host = host.lower()
if host and host[-1] == '.': host = host[:-1]
# Only perform percent-encoding where it is essential.
# Always use uppercase A-through-F characters when percent-encoding.
# All portions of the URI must be utf-8 encoded NFC from Unicode strings
def clean(string):
try:
string=unicode(unquote(string))
return unicodedata.normalize('NFC',string).encode('utf-8')
except UnicodeDecodeError:
return string
path=quote(clean(path),"~:/?#[]@!$&'()*+,;=")
fragment=quote(clean(fragment),"~")
# note care must be taken to only encode & and = characters as values
query="&".join(["=".join([quote(clean(t) ,"~:/?#[]@!$'()*+,;=")
for t in q.split("=",1)]) for q in query.split("&")])
# Prevent dot-segments appearing in non-relative URI paths.
if scheme in ["","http","https","ftp","file"]:
output=[]
for input in path.split('/'):
if input=="":
if not output: output.append(input)
elif input==".":
pass
elif input=="..":
if len(output)>1: output.pop()
else:
output.append(input)
if input in ["",".",".."]: output.append("")
path='/'.join(output)
# For schemes that define a default authority, use an empty authority if
# the default is desired.
if userinfo in ["@",":@"]: userinfo=""
# For schemes that define an empty path to be equivalent to a path of "/",
# use "/".
if path=="" and scheme in ["http","https","ftp","file"]:
path="/"
# For schemes that define a port, use an empty port if the default is
# desired
if port and scheme in default_port.keys():
if port.isdigit():
port=str(int(port))
if int(port)==default_port[scheme]:
port = ''
# Put it all back together again
auth=(userinfo or "") + host
if port: auth+=":"+port
if url.endswith("#") and query=="" and fragment=="": path+="#"
url = urlparse.urlunsplit((scheme,auth,path,query,fragment))
if '://' not in url:
url = 'http://' + url
if url.startswith('feed://'):
url = url.replace('feed://', 'http://')
return url
if __name__ == "__main__":
import unittest
suite = unittest.TestSuite()
""" from http://www.intertwingly.net/wiki/pie/PaceCanonicalIds """
tests= [
(False, "http://:@example.com/"),
(False, "http://@example.com/"),
(False, "http://example.com"),
(False, "HTTP://example.com/"),
(False, "http://EXAMPLE.COM/"),
(False, "http://example.com/%7Ejane"),
(False, "http://example.com/?q=%C7"),
(False, "http://example.com/?q=%5c"),
(False, "http://example.com/?q=C%CC%A7"),
(False, "http://example.com/a/../a/b"),
(False, "http://example.com/a/./b"),
(False, "http://example.com:80/"),
(True, "http://example.com/"),
(True, "http://example.com/?q=%C3%87"),
(True, "http://example.com/?q=%E2%85%A0"),
(True, "http://example.com/?q=%5C"),
(True, "http://example.com/~jane"),
(True, "http://example.com/a/b"),
(True, "http://example.com:8080/"),
(True, "http://user:[email protected]/"),
# from rfc2396bis
(True, "ftp://ftp.is.co.za/rfc/rfc1808.txt"),
(True, "http://www.ietf.org/rfc/rfc2396.txt"),
(True, "ldap://[2001:db8::7]/c=GB?objectClass?one"),
(True, "mailto:[email protected]"),
(True, "news:comp.infosystems.www.servers.unix"),
(True, "tel:+1-816-555-1212"),
(True, "telnet://192.0.2.16:80/"),
(True, "urn:oasis:names:specification:docbook:dtd:xml:4.1.2"),
# other
(True, "http://127.0.0.1/"),
(False, "http://127.0.0.1:80/"),
(True, "http://www.w3.org/2000/01/rdf-schema#"),
(False, "http://example.com:081/"),
]
def testcase(expected,value):
class test(unittest.TestCase):
def runTest(self):
assert (normalize(value)==value)==expected, \
(expected, value, normalize(value))
return test()
for (expected,value) in tests:
suite.addTest(testcase(expected,value))
""" mnot test suite; three tests updated for rfc2396bis. """
tests = {
'/foo/bar/.': '/foo/bar/',
'/foo/bar/./': '/foo/bar/',
'/foo/bar/..': '/foo/',
'/foo/bar/../': '/foo/',
'/foo/bar/../baz': '/foo/baz',
'/foo/bar/../..': '/',
'/foo/bar/../../': '/',
'/foo/bar/../../baz': '/baz',
'/foo/bar/../../../baz': '/baz', #was: '/../baz',
'/foo/bar/../../../../baz': '/baz',
'/./foo': '/foo',
'/../foo': '/foo', #was: '/../foo',
'/foo.': '/foo.',
'/.foo': '/.foo',
'/foo..': '/foo..',
'/..foo': '/..foo',
'/./../foo': '/foo', #was: '/../foo',
'/./foo/.': '/foo/',
'/foo/./bar': '/foo/bar',
'/foo/../bar': '/bar',
'/foo//': '/foo/',
'/foo///bar//': '/foo/bar/',
'http://www.foo.com:80/foo': 'http://www.foo.com/foo',
'http://www.foo.com:8000/foo': 'http://www.foo.com:8000/foo',
'http://www.foo.com./foo/bar.html': 'http://www.foo.com/foo/bar.html',
'http://www.foo.com.:81/foo': 'http://www.foo.com:81/foo',
'http://www.foo.com/%7ebar': 'http://www.foo.com/~bar',
'http://www.foo.com/%7Ebar': 'http://www.foo.com/~bar',
'ftp://user:[email protected]/foo/bar':
'ftp://user:[email protected]/foo/bar',
'http://USER:[email protected]/foo/bar':
'http://USER:[email protected]/foo/bar',
'http://www.example.com./': 'http://www.example.com/',
'-': '-',
}
def testcase(original,normalized):
class test(unittest.TestCase):
def runTest(self):
assert normalize(original)==normalized, \
(original, normalized, normalize(original))
return test()
for (original,normalized) in tests.items():
suite.addTest(testcase(original,normalized))
""" execute tests """
unittest.TextTestRunner().run(suite)