Mercurial > cpython-lru_cache-weakref

annotate Lib/urlparse.py @ 2047:f18c1915c722 legacy-trunk

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Add hacks for switching protocol and path but leaving host unchanged
author Guido van Rossum <guido@python.org>
date Fri, 30 Dec 1994 17:18:59 +0000
parents 8c9cc054c5ed
children 0acbd85bcdba
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
1875
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
1 # Parse (absolute and relative) URLs according to latest internet draft:
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
2
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
3 # Uniform Resource Identifiers Working Group R. Fielding
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
4 # INTERNET-DRAFT UC Irvine
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
5 # Expires February 24, 1995 August 24, 1994
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
6 #
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
7 # Relative Uniform Resource Locators
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
8 # <draft-ietf-uri-relative-url-00.txt>
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
9
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
10 # Standard/builtin Python modules
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
11 import string
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
12
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
13 # A classification of schemes ('' means apply by default)
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
14 uses_relative = ['ftp', 'http', 'gopher', 'nntp', 'wais', 'file',
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
15 'prospero', '']
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
16 uses_netloc = ['ftp', 'http', 'gopher', 'nntp', 'telnet', 'wais',
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
17 'file', 'prospero', '']
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
18 non_hierarchical = ['gopher', 'mailto', 'news', 'telnet', 'wais']
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
19 uses_params = ['ftp', 'prospero', '']
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
20 uses_query = ['http', 'wais', '']
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
21 uses_fragment = ['ftp', 'http', 'gopher', 'news', 'nntp', 'wais',
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
22 'file', 'prospero', '']
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
23
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
24 # Characters valid in scheme names
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
25 scheme_chars = string.letters + string.digits + '+-.'
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
26
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
27 # Parse a URL into 6 components:
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
28 # <scheme>://<netloc>/<path>;<params>?<query>#<fragment>
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
29 # Return a 6-tuple: (scheme, netloc, path, params, query, fragment).
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
30 # Note that we don't break the components up in smaller bits
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
31 # (e.g. netloc is a single string) and we don't expand % escapes.
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
32 def urlparse(url, scheme = '', allow_framents = 1):
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
33 netloc = ''
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
34 path = ''
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
35 params = ''
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
36 query = ''
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
37 fragment = ''
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
38 i = string.find(url, ':')
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
39 if i > 0:
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
40 for c in url[:i]:
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
41 if c not in scheme_chars:
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
42 break
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
43 else:
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
44 scheme, url = string.lower(url[:i]), url[i+1:]
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
45 if scheme in uses_netloc:
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
46 if url[:2] == '//':
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
47 i = string.find(url, '/', 2)
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
48 if i < 0:
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
49 i = len(url)
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
50 netloc, url = url[2:i], url[i:]
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
51 if allow_framents and scheme in uses_fragment:
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
52 i = string.rfind(url, '#')
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
53 if i >= 0:
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
54 url, fragment = url[:i], url[i+1:]
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
55 if scheme in uses_query:
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
56 i = string.find(url, '?')
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
57 if i >= 0:
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
58 url, query = url[:i], url[i+1:]
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
59 if scheme in uses_params:
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
60 i = string.find(url, ';')
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
61 if i >= 0:
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
62 url, params = url[:i], url[i+1:]
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
63 return scheme, netloc, url, params, query, fragment
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
64
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
65 # Put a parsed URL back together again. This may result in a slightly
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
66 # different, but equivalent URL, if the URL that was parsed originally
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
67 # had redundant delimiters, e.g. a ? with an empty query (the draft
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
68 # states that these are equivalent).
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
69 def urlunparse((scheme, netloc, url, params, query, fragment)):
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
70 if netloc:
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
71 url = '//' + netloc + url
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
72 if scheme:
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
73 url = scheme + ':' + url
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
74 if params:
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
75 url = url + ';' + params
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
76 if query:
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
77 url = url + '?' + query
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
78 if fragment:
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
79 url = url + '#' + fragment
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
80 return url
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
81
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
82 # Join a base URL and a possibly relative URL to form an absolute
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
83 # interpretation of the latter.
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
84 def urljoin(base, url, allow_framents = 1):
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
85 if not base:
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
86 return url
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
87 bscheme, bnetloc, bpath, bparams, bquery, bfragment = \
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
88 urlparse(base, '', allow_framents)
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
89 scheme, netloc, path, params, query, fragment = \
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
90 urlparse(url, bscheme, allow_framents)
2047
f18c1915c722 Add hacks for switching protocol and path but leaving host unchanged
Guido van Rossum <guido@python.org>
parents: 1875
diff changeset
91 # XXX Unofficial hack: default netloc to bnetloc even if
f18c1915c722 Add hacks for switching protocol and path but leaving host unchanged
Guido van Rossum <guido@python.org>
parents: 1875
diff changeset
92 # schemes differ
f18c1915c722 Add hacks for switching protocol and path but leaving host unchanged
Guido van Rossum <guido@python.org>
parents: 1875
diff changeset
93 if scheme != bscheme and not netloc and \
f18c1915c722 Add hacks for switching protocol and path but leaving host unchanged
Guido van Rossum <guido@python.org>
parents: 1875
diff changeset
94 scheme in uses_relative and bscheme in uses_relative and \
f18c1915c722 Add hacks for switching protocol and path but leaving host unchanged
Guido van Rossum <guido@python.org>
parents: 1875
diff changeset
95 scheme in uses_netloc and bscheme in uses_netloc:
f18c1915c722 Add hacks for switching protocol and path but leaving host unchanged
Guido van Rossum <guido@python.org>
parents: 1875
diff changeset
96 netloc = bnetloc
f18c1915c722 Add hacks for switching protocol and path but leaving host unchanged
Guido van Rossum <guido@python.org>
parents: 1875
diff changeset
97 # Strip the port number
f18c1915c722 Add hacks for switching protocol and path but leaving host unchanged
Guido van Rossum <guido@python.org>
parents: 1875
diff changeset
98 i = string.find(netloc, '@')
f18c1915c722 Add hacks for switching protocol and path but leaving host unchanged
Guido van Rossum <guido@python.org>
parents: 1875
diff changeset
99 if i < 0: i = 0
f18c1915c722 Add hacks for switching protocol and path but leaving host unchanged
Guido van Rossum <guido@python.org>
parents: 1875
diff changeset
100 i = string.find(netloc, ':', i)
f18c1915c722 Add hacks for switching protocol and path but leaving host unchanged
Guido van Rossum <guido@python.org>
parents: 1875
diff changeset
101 if i >= 0:
f18c1915c722 Add hacks for switching protocol and path but leaving host unchanged
Guido van Rossum <guido@python.org>
parents: 1875
diff changeset
102 netloc = netloc[:i]
1875
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
103 if scheme != bscheme or scheme not in uses_relative:
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
104 return urlunparse((scheme, netloc, path,
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
105 params, query, fragment))
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
106 if scheme in uses_netloc:
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
107 if netloc:
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
108 return urlunparse((scheme, netloc, path,
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
109 params, query, fragment))
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
110 netloc = bnetloc
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
111 if path[:1] == '/':
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
112 return urlunparse((scheme, netloc, path,
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
113 params, query, fragment))
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
114 if not path:
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
115 path = bpath
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
116 if not query:
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
117 query = bquery
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
118 return urlunparse((scheme, netloc, path,
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
119 params, query, fragment))
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
120 i = string.rfind(bpath, '/')
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
121 if i < 0:
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
122 i = len(bpath)
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
123 path = bpath[:i] + '/' + path
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
124 segments = string.splitfields(path, '/')
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
125 if segments[-1] == '.':
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
126 segments[-1] = ''
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
127 while '.' in segments:
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
128 segments.remove('.')
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
129 while 1:
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
130 i = 1
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
131 n = len(segments) - 1
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
132 while i < n:
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
133 if segments[i] == '..' and segments[i-1]:
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
134 del segments[i-1:i+1]
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
135 break
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
136 i = i+1
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
137 else:
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
138 break
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
139 if len(segments) >= 2 and segments[-1] == '..':
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
140 segments[-2:] = ['']
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
141 path = string.joinfields(segments, '/')
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
142 return urlunparse((scheme, netloc, path,
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
143 params, query, fragment))
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
144
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
145 test_input = """
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
146 http://a/b/c/d
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
147
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
148 g:h = <URL:g:h>
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
149 http:g = <URL:http://a/b/c/g>
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
150 http: = <URL:http://a/b/c/d>
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
151 g = <URL:http://a/b/c/g>
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
152 ./g = <URL:http://a/b/c/g>
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
153 g/ = <URL:http://a/b/c/g/>
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
154 /g = <URL:http://a/g>
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
155 //g = <URL:http://g>
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
156 ?y = <URL:http://a/b/c/d?y>
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
157 g?y = <URL:http://a/b/c/g?y>
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
158 g?y/./x = <URL:http://a/b/c/g?y/./x>
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
159 . = <URL:http://a/b/c/>
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
160 ./ = <URL:http://a/b/c/>
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
161 .. = <URL:http://a/b/>
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
162 ../ = <URL:http://a/b/>
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
163 ../g = <URL:http://a/b/g>
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
164 ../.. = <URL:http://a/>
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
165 ../../g = <URL:http://a/g>
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
166 ../../../g = <URL:http://a/../g>
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
167 ./../g = <URL:http://a/b/g>
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
168 ./g/. = <URL:http://a/b/c/g/>
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
169 /./g = <URL:http://a/./g>
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
170 g/./h = <URL:http://a/b/c/g/h>
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
171 g/../h = <URL:http://a/b/c/h>
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
172 http:g = <URL:http://a/b/c/g>
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
173 http: = <URL:http://a/b/c/d>
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
174 """
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
175
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
176 def test():
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
177 import sys
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
178 base = ''
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
179 if sys.argv[1:]:
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
180 fn = sys.argv[1]
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
181 if fn == '-':
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
182 fp = sys.stdin
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
183 else:
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
184 fp = open(fn)
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
185 else:
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
186 import StringIO
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
187 fp = StringIO.StringIO(test_input)
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
188 while 1:
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
189 line = fp.readline()
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
190 if not line: break
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
191 words = string.split(line)
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
192 if not words:
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
193 continue
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
194 url = words[0]
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
195 parts = urlparse(url)
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
196 print '%-10s : %s' % (url, parts)
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
197 abs = urljoin(base, url)
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
198 if not base:
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
199 base = abs
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
200 wrapped = '<URL:%s>' % abs
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
201 print '%-10s = %s' % (url, wrapped)
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
202 if len(words) == 3 and words[1] == '=':
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
203 if wrapped != words[2]:
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
204 print 'EXPECTED', words[2], '!!!!!!!!!!'
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
205
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
206 if __name__ == '__main__':
8c9cc054c5ed New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff changeset
207 test()