Mercurial > cpython-lru_cache-weakref
annotate Lib/urlparse.py @ 25838:8540887bcec6 2.2
Backport of 2.183:
Fix memory leak in add_subclass() found by NealN with valgrind.
| author | Guido van Rossum <guido@python.org> |
|---|---|
| date | Fri, 18 Oct 2002 13:42:21 +0000 |
| parents | b8cbdb735cf2 |
| children | a16bc64f1145 |
| rev | line source |
|---|---|
|
11707
6f4146846337
The third and final doc-string sweep by Ka-Ping Yee.
Guido van Rossum <guido@python.org>
parents:
10830
diff
changeset
|
1 """Parse (absolute and relative) URLs. |
|
6f4146846337
The third and final doc-string sweep by Ka-Ping Yee.
Guido van Rossum <guido@python.org>
parents:
10830
diff
changeset
|
2 |
|
6f4146846337
The third and final doc-string sweep by Ka-Ping Yee.
Guido van Rossum <guido@python.org>
parents:
10830
diff
changeset
|
3 See RFC 1808: "Relative Uniform Resource Locators", by R. Fielding, |
|
6f4146846337
The third and final doc-string sweep by Ka-Ping Yee.
Guido van Rossum <guido@python.org>
parents:
10830
diff
changeset
|
4 UC Irvine, June 1995. |
|
6f4146846337
The third and final doc-string sweep by Ka-Ping Yee.
Guido van Rossum <guido@python.org>
parents:
10830
diff
changeset
|
5 """ |
|
1875
8c9cc054c5ed
New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
6 |
|
25814
b8cbdb735cf2
Added missing entries to __all__.
Fred Drake <fdrake@acm.org>
parents:
25787
diff
changeset
|
7 __all__ = ["urlparse", "urlunparse", "urljoin", "urldefrag", |
|
b8cbdb735cf2
Added missing entries to __all__.
Fred Drake <fdrake@acm.org>
parents:
25787
diff
changeset
|
8 "urlsplit", "urlunsplit"] |
|
16889
0feb63490093
final round of __all__ lists (I hope) - skipped urllib2 because Moshe may be
Skip Montanaro <skip@pobox.com>
parents:
15874
diff
changeset
|
9 |
|
1875
8c9cc054c5ed
New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
10 # 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
|
11 uses_relative = ['ftp', 'http', 'gopher', 'nntp', 'wais', 'file', |
|
15874
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
12 'https', 'shttp', |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
13 'prospero', 'rtsp', 'rtspu', ''] |
|
1875
8c9cc054c5ed
New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
14 uses_netloc = ['ftp', 'http', 'gopher', 'nntp', 'telnet', 'wais', |
|
15874
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
15 'file', |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
16 'https', 'shttp', 'snews', |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
17 'prospero', 'rtsp', 'rtspu', ''] |
|
4853
cf90745381bf
Added characteristics of shttp, https, and snews.
Guido van Rossum <guido@python.org>
parents:
4831
diff
changeset
|
18 non_hierarchical = ['gopher', 'hdl', 'mailto', 'news', 'telnet', 'wais', |
|
15874
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
19 'snews', 'sip', |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
20 ] |
|
4853
cf90745381bf
Added characteristics of shttp, https, and snews.
Guido van Rossum <guido@python.org>
parents:
4831
diff
changeset
|
21 uses_params = ['ftp', 'hdl', 'prospero', 'http', |
|
15874
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
22 'https', 'shttp', 'rtsp', 'rtspu', 'sip', |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
23 ''] |
|
4853
cf90745381bf
Added characteristics of shttp, https, and snews.
Guido van Rossum <guido@python.org>
parents:
4831
diff
changeset
|
24 uses_query = ['http', 'wais', |
|
15874
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
25 'https', 'shttp', |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
26 'gopher', 'rtsp', 'rtspu', 'sip', |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
27 ''] |
|
3641
e4faadb4abe2
added hdl protocol properties
Guido van Rossum <guido@python.org>
parents:
3482
diff
changeset
|
28 uses_fragment = ['ftp', 'hdl', 'http', 'gopher', 'news', 'nntp', 'wais', |
|
15874
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
29 'https', 'shttp', 'snews', |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
30 'file', 'prospero', ''] |
|
1875
8c9cc054c5ed
New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
31 |
|
8c9cc054c5ed
New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
32 # Characters valid in scheme names |
|
15623
db69c092c906
Be explicit about scheme_chars -- string.letters is locale dependent
Guido van Rossum <guido@python.org>
parents:
12967
diff
changeset
|
33 scheme_chars = ('abcdefghijklmnopqrstuvwxyz' |
|
db69c092c906
Be explicit about scheme_chars -- string.letters is locale dependent
Guido van Rossum <guido@python.org>
parents:
12967
diff
changeset
|
34 'ABCDEFGHIJKLMNOPQRSTUVWXYZ' |
|
db69c092c906
Be explicit about scheme_chars -- string.letters is locale dependent
Guido van Rossum <guido@python.org>
parents:
12967
diff
changeset
|
35 '0123456789' |
|
db69c092c906
Be explicit about scheme_chars -- string.letters is locale dependent
Guido van Rossum <guido@python.org>
parents:
12967
diff
changeset
|
36 '+-.') |
|
1875
8c9cc054c5ed
New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
37 |
|
5785
b247297be9a0
After some discussion with Jeremy and Fred, decided to limit the
Guido van Rossum <guido@python.org>
parents:
5776
diff
changeset
|
38 MAX_CACHE_SIZE = 20 |
|
3652
728a39a3e0d5
optimizations due to Fred Drake; added urldefrag() function
Guido van Rossum <guido@python.org>
parents:
3641
diff
changeset
|
39 _parse_cache = {} |
|
728a39a3e0d5
optimizations due to Fred Drake; added urldefrag() function
Guido van Rossum <guido@python.org>
parents:
3641
diff
changeset
|
40 |
|
728a39a3e0d5
optimizations due to Fred Drake; added urldefrag() function
Guido van Rossum <guido@python.org>
parents:
3641
diff
changeset
|
41 def clear_cache(): |
|
15874
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
42 """Clear the parse cache.""" |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
43 global _parse_cache |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
44 _parse_cache = {} |
|
3652
728a39a3e0d5
optimizations due to Fred Drake; added urldefrag() function
Guido van Rossum <guido@python.org>
parents:
3641
diff
changeset
|
45 |
|
728a39a3e0d5
optimizations due to Fred Drake; added urldefrag() function
Guido van Rossum <guido@python.org>
parents:
3641
diff
changeset
|
46 |
|
20995
174ccb035b3d
Fix parsing of parameters from a URL; urlparse() did not check that it only
Fred Drake <fdrake@acm.org>
parents:
19209
diff
changeset
|
47 def urlparse(url, scheme='', allow_fragments=1): |
|
15874
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
48 """Parse a URL into 6 components: |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
49 <scheme>://<netloc>/<path>;<params>?<query>#<fragment> |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
50 Return a 6-tuple: (scheme, netloc, path, params, query, fragment). |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
51 Note that we don't break the components up in smaller bits |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
52 (e.g. netloc is a single string) and we don't expand % escapes.""" |
|
20995
174ccb035b3d
Fix parsing of parameters from a URL; urlparse() did not check that it only
Fred Drake <fdrake@acm.org>
parents:
19209
diff
changeset
|
53 tuple = urlsplit(url, scheme, allow_fragments) |
|
174ccb035b3d
Fix parsing of parameters from a URL; urlparse() did not check that it only
Fred Drake <fdrake@acm.org>
parents:
19209
diff
changeset
|
54 scheme, netloc, url, query, fragment = tuple |
|
174ccb035b3d
Fix parsing of parameters from a URL; urlparse() did not check that it only
Fred Drake <fdrake@acm.org>
parents:
19209
diff
changeset
|
55 if scheme in uses_params and ';' in url: |
|
174ccb035b3d
Fix parsing of parameters from a URL; urlparse() did not check that it only
Fred Drake <fdrake@acm.org>
parents:
19209
diff
changeset
|
56 url, params = _splitparams(url) |
|
174ccb035b3d
Fix parsing of parameters from a URL; urlparse() did not check that it only
Fred Drake <fdrake@acm.org>
parents:
19209
diff
changeset
|
57 else: |
|
174ccb035b3d
Fix parsing of parameters from a URL; urlparse() did not check that it only
Fred Drake <fdrake@acm.org>
parents:
19209
diff
changeset
|
58 params = '' |
|
174ccb035b3d
Fix parsing of parameters from a URL; urlparse() did not check that it only
Fred Drake <fdrake@acm.org>
parents:
19209
diff
changeset
|
59 return scheme, netloc, url, params, query, fragment |
|
174ccb035b3d
Fix parsing of parameters from a URL; urlparse() did not check that it only
Fred Drake <fdrake@acm.org>
parents:
19209
diff
changeset
|
60 |
|
174ccb035b3d
Fix parsing of parameters from a URL; urlparse() did not check that it only
Fred Drake <fdrake@acm.org>
parents:
19209
diff
changeset
|
61 def _splitparams(url): |
|
174ccb035b3d
Fix parsing of parameters from a URL; urlparse() did not check that it only
Fred Drake <fdrake@acm.org>
parents:
19209
diff
changeset
|
62 if '/' in url: |
|
174ccb035b3d
Fix parsing of parameters from a URL; urlparse() did not check that it only
Fred Drake <fdrake@acm.org>
parents:
19209
diff
changeset
|
63 i = url.find(';', url.rfind('/')) |
|
174ccb035b3d
Fix parsing of parameters from a URL; urlparse() did not check that it only
Fred Drake <fdrake@acm.org>
parents:
19209
diff
changeset
|
64 if i < 0: |
|
174ccb035b3d
Fix parsing of parameters from a URL; urlparse() did not check that it only
Fred Drake <fdrake@acm.org>
parents:
19209
diff
changeset
|
65 return url, '' |
|
174ccb035b3d
Fix parsing of parameters from a URL; urlparse() did not check that it only
Fred Drake <fdrake@acm.org>
parents:
19209
diff
changeset
|
66 else: |
|
174ccb035b3d
Fix parsing of parameters from a URL; urlparse() did not check that it only
Fred Drake <fdrake@acm.org>
parents:
19209
diff
changeset
|
67 i = url.find(';') |
|
174ccb035b3d
Fix parsing of parameters from a URL; urlparse() did not check that it only
Fred Drake <fdrake@acm.org>
parents:
19209
diff
changeset
|
68 return url[:i], url[i+1:] |
|
174ccb035b3d
Fix parsing of parameters from a URL; urlparse() did not check that it only
Fred Drake <fdrake@acm.org>
parents:
19209
diff
changeset
|
69 |
|
174ccb035b3d
Fix parsing of parameters from a URL; urlparse() did not check that it only
Fred Drake <fdrake@acm.org>
parents:
19209
diff
changeset
|
70 def urlsplit(url, scheme='', allow_fragments=1): |
|
174ccb035b3d
Fix parsing of parameters from a URL; urlparse() did not check that it only
Fred Drake <fdrake@acm.org>
parents:
19209
diff
changeset
|
71 """Parse a URL into 5 components: |
|
174ccb035b3d
Fix parsing of parameters from a URL; urlparse() did not check that it only
Fred Drake <fdrake@acm.org>
parents:
19209
diff
changeset
|
72 <scheme>://<netloc>/<path>?<query>#<fragment> |
|
174ccb035b3d
Fix parsing of parameters from a URL; urlparse() did not check that it only
Fred Drake <fdrake@acm.org>
parents:
19209
diff
changeset
|
73 Return a 5-tuple: (scheme, netloc, path, query, fragment). |
|
174ccb035b3d
Fix parsing of parameters from a URL; urlparse() did not check that it only
Fred Drake <fdrake@acm.org>
parents:
19209
diff
changeset
|
74 Note that we don't break the components up in smaller bits |
|
174ccb035b3d
Fix parsing of parameters from a URL; urlparse() did not check that it only
Fred Drake <fdrake@acm.org>
parents:
19209
diff
changeset
|
75 (e.g. netloc is a single string) and we don't expand % escapes.""" |
|
15874
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
76 key = url, scheme, allow_fragments |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
77 cached = _parse_cache.get(key, None) |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
78 if cached: |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
79 return cached |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
80 if len(_parse_cache) >= MAX_CACHE_SIZE: # avoid runaway growth |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
81 clear_cache() |
|
20995
174ccb035b3d
Fix parsing of parameters from a URL; urlparse() did not check that it only
Fred Drake <fdrake@acm.org>
parents:
19209
diff
changeset
|
82 netloc = query = fragment = '' |
|
15874
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
83 i = url.find(':') |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
84 if i > 0: |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
85 if url[:i] == 'http': # optimize the common case |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
86 scheme = url[:i].lower() |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
87 url = url[i+1:] |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
88 if url[:2] == '//': |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
89 i = url.find('/', 2) |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
90 if i < 0: |
| 22378 | 91 i = url.find('#') |
| 92 if i < 0: | |
| 93 i = len(url) | |
|
15874
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
94 netloc = url[2:i] |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
95 url = url[i:] |
|
20995
174ccb035b3d
Fix parsing of parameters from a URL; urlparse() did not check that it only
Fred Drake <fdrake@acm.org>
parents:
19209
diff
changeset
|
96 if allow_fragments and '#' in url: |
|
174ccb035b3d
Fix parsing of parameters from a URL; urlparse() did not check that it only
Fred Drake <fdrake@acm.org>
parents:
19209
diff
changeset
|
97 url, fragment = url.split('#', 1) |
|
174ccb035b3d
Fix parsing of parameters from a URL; urlparse() did not check that it only
Fred Drake <fdrake@acm.org>
parents:
19209
diff
changeset
|
98 if '?' in url: |
|
174ccb035b3d
Fix parsing of parameters from a URL; urlparse() did not check that it only
Fred Drake <fdrake@acm.org>
parents:
19209
diff
changeset
|
99 url, query = url.split('?', 1) |
|
174ccb035b3d
Fix parsing of parameters from a URL; urlparse() did not check that it only
Fred Drake <fdrake@acm.org>
parents:
19209
diff
changeset
|
100 tuple = scheme, netloc, url, query, fragment |
|
15874
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
101 _parse_cache[key] = tuple |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
102 return tuple |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
103 for c in url[:i]: |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
104 if c not in scheme_chars: |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
105 break |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
106 else: |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
107 scheme, url = url[:i].lower(), url[i+1:] |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
108 if scheme in uses_netloc: |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
109 if url[:2] == '//': |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
110 i = url.find('/', 2) |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
111 if i < 0: |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
112 i = len(url) |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
113 netloc, url = url[2:i], url[i:] |
|
20995
174ccb035b3d
Fix parsing of parameters from a URL; urlparse() did not check that it only
Fred Drake <fdrake@acm.org>
parents:
19209
diff
changeset
|
114 if allow_fragments and scheme in uses_fragment and '#' in url: |
|
174ccb035b3d
Fix parsing of parameters from a URL; urlparse() did not check that it only
Fred Drake <fdrake@acm.org>
parents:
19209
diff
changeset
|
115 url, fragment = url.split('#', 1) |
|
174ccb035b3d
Fix parsing of parameters from a URL; urlparse() did not check that it only
Fred Drake <fdrake@acm.org>
parents:
19209
diff
changeset
|
116 if scheme in uses_query and '?' in url: |
|
174ccb035b3d
Fix parsing of parameters from a URL; urlparse() did not check that it only
Fred Drake <fdrake@acm.org>
parents:
19209
diff
changeset
|
117 url, query = url.split('?', 1) |
|
174ccb035b3d
Fix parsing of parameters from a URL; urlparse() did not check that it only
Fred Drake <fdrake@acm.org>
parents:
19209
diff
changeset
|
118 tuple = scheme, netloc, url, query, fragment |
|
15874
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
119 _parse_cache[key] = tuple |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
120 return tuple |
|
1875
8c9cc054c5ed
New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
121 |
|
8c9cc054c5ed
New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
122 def urlunparse((scheme, netloc, url, params, query, fragment)): |
|
15874
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
123 """Put a parsed URL back together again. This may result in a |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
124 slightly different, but equivalent URL, if the URL that was parsed |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
125 originally had redundant delimiters, e.g. a ? with an empty query |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
126 (the draft states that these are equivalent).""" |
|
20995
174ccb035b3d
Fix parsing of parameters from a URL; urlparse() did not check that it only
Fred Drake <fdrake@acm.org>
parents:
19209
diff
changeset
|
127 if params: |
|
174ccb035b3d
Fix parsing of parameters from a URL; urlparse() did not check that it only
Fred Drake <fdrake@acm.org>
parents:
19209
diff
changeset
|
128 url = "%s;%s" % (url, params) |
|
174ccb035b3d
Fix parsing of parameters from a URL; urlparse() did not check that it only
Fred Drake <fdrake@acm.org>
parents:
19209
diff
changeset
|
129 return urlunsplit((scheme, netloc, url, query, fragment)) |
|
174ccb035b3d
Fix parsing of parameters from a URL; urlparse() did not check that it only
Fred Drake <fdrake@acm.org>
parents:
19209
diff
changeset
|
130 |
|
174ccb035b3d
Fix parsing of parameters from a URL; urlparse() did not check that it only
Fred Drake <fdrake@acm.org>
parents:
19209
diff
changeset
|
131 def urlunsplit((scheme, netloc, url, query, fragment)): |
|
25787
bf384111b3b3
Backporting urlparse.py:1.34, test_urlparse.py:1.8:
Guido van Rossum <guido@python.org>
parents:
25426
diff
changeset
|
132 if netloc or (scheme and scheme in uses_netloc and url[:2] != '//'): |
|
15874
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
133 if url and url[:1] != '/': url = '/' + url |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
134 url = '//' + (netloc or '') + url |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
135 if scheme: |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
136 url = scheme + ':' + url |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
137 if query: |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
138 url = url + '?' + query |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
139 if fragment: |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
140 url = url + '#' + fragment |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
141 return url |
|
1875
8c9cc054c5ed
New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
142 |
|
9051
839c6622d15a
fix typo in keyword argument 'allow_frament' should be 'allow_fragment'
Jeremy Hylton <jeremy@alum.mit.edu>
parents:
7125
diff
changeset
|
143 def urljoin(base, url, allow_fragments = 1): |
|
15874
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
144 """Join a base URL and a possibly relative URL to form an absolute |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
145 interpretation of the latter.""" |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
146 if not base: |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
147 return url |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
148 if not url: |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
149 return base |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
150 bscheme, bnetloc, bpath, bparams, bquery, bfragment = \ |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
151 urlparse(base, '', allow_fragments) |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
152 scheme, netloc, path, params, query, fragment = \ |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
153 urlparse(url, bscheme, allow_fragments) |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
154 if scheme != bscheme or scheme not in uses_relative: |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
155 return url |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
156 if scheme in uses_netloc: |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
157 if netloc: |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
158 return urlunparse((scheme, netloc, path, |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
159 params, query, fragment)) |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
160 netloc = bnetloc |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
161 if path[:1] == '/': |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
162 return urlunparse((scheme, netloc, path, |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
163 params, query, fragment)) |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
164 if not path: |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
165 if not params: |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
166 params = bparams |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
167 if not query: |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
168 query = bquery |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
169 return urlunparse((scheme, netloc, bpath, |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
170 params, query, fragment)) |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
171 segments = bpath.split('/')[:-1] + path.split('/') |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
172 # XXX The stuff below is bogus in various ways... |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
173 if segments[-1] == '.': |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
174 segments[-1] = '' |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
175 while '.' in segments: |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
176 segments.remove('.') |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
177 while 1: |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
178 i = 1 |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
179 n = len(segments) - 1 |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
180 while i < n: |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
181 if (segments[i] == '..' |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
182 and segments[i-1] not in ('', '..')): |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
183 del segments[i-1:i+1] |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
184 break |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
185 i = i+1 |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
186 else: |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
187 break |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
188 if segments == ['', '..']: |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
189 segments[-1] = '' |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
190 elif len(segments) >= 2 and segments[-1] == '..': |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
191 segments[-2:] = [''] |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
192 return urlunparse((scheme, netloc, '/'.join(segments), |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
193 params, query, fragment)) |
|
1875
8c9cc054c5ed
New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
194 |
|
3652
728a39a3e0d5
optimizations due to Fred Drake; added urldefrag() function
Guido van Rossum <guido@python.org>
parents:
3641
diff
changeset
|
195 def urldefrag(url): |
|
15874
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
196 """Removes any existing fragment from URL. |
|
3652
728a39a3e0d5
optimizations due to Fred Drake; added urldefrag() function
Guido van Rossum <guido@python.org>
parents:
3641
diff
changeset
|
197 |
|
15874
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
198 Returns a tuple of the defragmented URL and the fragment. If |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
199 the URL contained no fragments, the second element is the |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
200 empty string. |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
201 """ |
|
20995
174ccb035b3d
Fix parsing of parameters from a URL; urlparse() did not check that it only
Fred Drake <fdrake@acm.org>
parents:
19209
diff
changeset
|
202 if '#' in url: |
|
174ccb035b3d
Fix parsing of parameters from a URL; urlparse() did not check that it only
Fred Drake <fdrake@acm.org>
parents:
19209
diff
changeset
|
203 s, n, p, a, q, frag = urlparse(url) |
|
174ccb035b3d
Fix parsing of parameters from a URL; urlparse() did not check that it only
Fred Drake <fdrake@acm.org>
parents:
19209
diff
changeset
|
204 defrag = urlunparse((s, n, p, a, q, '')) |
|
174ccb035b3d
Fix parsing of parameters from a URL; urlparse() did not check that it only
Fred Drake <fdrake@acm.org>
parents:
19209
diff
changeset
|
205 return defrag, frag |
|
174ccb035b3d
Fix parsing of parameters from a URL; urlparse() did not check that it only
Fred Drake <fdrake@acm.org>
parents:
19209
diff
changeset
|
206 else: |
|
174ccb035b3d
Fix parsing of parameters from a URL; urlparse() did not check that it only
Fred Drake <fdrake@acm.org>
parents:
19209
diff
changeset
|
207 return url, '' |
|
3652
728a39a3e0d5
optimizations due to Fred Drake; added urldefrag() function
Guido van Rossum <guido@python.org>
parents:
3641
diff
changeset
|
208 |
|
728a39a3e0d5
optimizations due to Fred Drake; added urldefrag() function
Guido van Rossum <guido@python.org>
parents:
3641
diff
changeset
|
209 |
|
1875
8c9cc054c5ed
New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
210 test_input = """ |
|
8c9cc054c5ed
New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
211 http://a/b/c/d |
|
8c9cc054c5ed
New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
212 |
|
8c9cc054c5ed
New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
213 g:h = <URL:g:h> |
|
8c9cc054c5ed
New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
214 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
|
215 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
|
216 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
|
217 ./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
|
218 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
|
219 /g = <URL:http://a/g> |
|
8c9cc054c5ed
New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
220 //g = <URL:http://g> |
|
8c9cc054c5ed
New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
221 ?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
|
222 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
|
223 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
|
224 . = <URL:http://a/b/c/> |
|
8c9cc054c5ed
New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
225 ./ = <URL:http://a/b/c/> |
|
8c9cc054c5ed
New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
226 .. = <URL:http://a/b/> |
|
8c9cc054c5ed
New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
227 ../ = <URL:http://a/b/> |
|
8c9cc054c5ed
New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
228 ../g = <URL:http://a/b/g> |
|
8c9cc054c5ed
New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
229 ../.. = <URL:http://a/> |
|
8c9cc054c5ed
New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
230 ../../g = <URL:http://a/g> |
|
8c9cc054c5ed
New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
231 ../../../g = <URL:http://a/../g> |
|
8c9cc054c5ed
New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
232 ./../g = <URL:http://a/b/g> |
|
8c9cc054c5ed
New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
233 ./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
|
234 /./g = <URL:http://a/./g> |
|
8c9cc054c5ed
New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
235 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
|
236 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
|
237 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
|
238 http: = <URL:http://a/b/c/d> |
|
9793
737d05a9bb5e
Fixed bug in the common-case code for HTTP URLs; it would lose the query,
Andrew M. Kuchling <amk@amk.ca>
parents:
9665
diff
changeset
|
239 http:?y = <URL:http://a/b/c/d?y> |
|
737d05a9bb5e
Fixed bug in the common-case code for HTTP URLs; it would lose the query,
Andrew M. Kuchling <amk@amk.ca>
parents:
9665
diff
changeset
|
240 http:g?y = <URL:http://a/b/c/g?y> |
|
737d05a9bb5e
Fixed bug in the common-case code for HTTP URLs; it would lose the query,
Andrew M. Kuchling <amk@amk.ca>
parents:
9665
diff
changeset
|
241 http:g?y/./x = <URL:http://a/b/c/g?y/./x> |
|
1875
8c9cc054c5ed
New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
242 """ |
|
9665
e11d75005a5a
Add XXX comment about a test that doesn't seem right -- no time to
Guido van Rossum <guido@python.org>
parents:
9068
diff
changeset
|
243 # XXX The result for //g is actually http://g/; is this a problem? |
|
1875
8c9cc054c5ed
New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
244 |
|
8c9cc054c5ed
New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
245 def test(): |
|
15874
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
246 import sys |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
247 base = '' |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
248 if sys.argv[1:]: |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
249 fn = sys.argv[1] |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
250 if fn == '-': |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
251 fp = sys.stdin |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
252 else: |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
253 fp = open(fn) |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
254 else: |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
255 import StringIO |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
256 fp = StringIO.StringIO(test_input) |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
257 while 1: |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
258 line = fp.readline() |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
259 if not line: break |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
260 words = line.split() |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
261 if not words: |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
262 continue |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
263 url = words[0] |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
264 parts = urlparse(url) |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
265 print '%-10s : %s' % (url, parts) |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
266 abs = urljoin(base, url) |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
267 if not base: |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
268 base = abs |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
269 wrapped = '<URL:%s>' % abs |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
270 print '%-10s = %s' % (url, wrapped) |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
271 if len(words) == 3 and words[1] == '=': |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
272 if wrapped != words[2]: |
|
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
273 print 'EXPECTED', words[2], '!!!!!!!!!!' |
|
1875
8c9cc054c5ed
New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
274 |
|
8c9cc054c5ed
New tty/pty modules by Steen; new urlparser.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
275 if __name__ == '__main__': |
|
15874
4c01ee0a8073
Whitespace normalization. Top level of Lib now fixed-point for reindent.py!
Tim Peters <tim.peters@gmail.com>
parents:
15741
diff
changeset
|
276 test() |
