mirror of
https://github.com/python/cpython
synced 2024-09-04 15:56:13 +00:00
![Georg Brandl](/assets/img/avatar_default.png)
svn+ssh://pythondev@svn.python.org/python/trunk ........ r60151 | christian.heimes | 2008-01-21 14:11:15 +0100 (Mon, 21 Jan 2008) | 1 line A bunch of header files were not listed as dependencies for object files. Changes to files like Parser/parser.h weren't picked up by make. ........ r60152 | georg.brandl | 2008-01-21 15:16:46 +0100 (Mon, 21 Jan 2008) | 3 lines #1087741: make mmap.mmap the type of mmap objects, not a factory function. Allow it to be subclassed. ........ r60153 | georg.brandl | 2008-01-21 15:18:14 +0100 (Mon, 21 Jan 2008) | 2 lines mmap is an extension module. ........ r60154 | georg.brandl | 2008-01-21 17:28:13 +0100 (Mon, 21 Jan 2008) | 2 lines Fix example. ........ r60155 | georg.brandl | 2008-01-21 17:34:07 +0100 (Mon, 21 Jan 2008) | 2 lines #1555501: document plistlib and move it to the general library. ........ r60156 | georg.brandl | 2008-01-21 17:36:00 +0100 (Mon, 21 Jan 2008) | 2 lines Add a stub for bundlebuilder documentation. ........ r60157 | georg.brandl | 2008-01-21 17:46:58 +0100 (Mon, 21 Jan 2008) | 2 lines Removing bundlebuilder docs again -- it's not to be used anymore (see #779825). ........ r60158 | georg.brandl | 2008-01-21 17:51:51 +0100 (Mon, 21 Jan 2008) | 2 lines #997912: acknowledge nested scopes in tutorial. ........ r60159 | vinay.sajip | 2008-01-21 18:02:26 +0100 (Mon, 21 Jan 2008) | 1 line Fix: #1836: Off-by-one bug in TimedRotatingFileHandler rollover calculation. Patch thanks to Kathryn M. Kowalski. ........ r60161 | georg.brandl | 2008-01-21 18:13:03 +0100 (Mon, 21 Jan 2008) | 2 lines Adapt pydoc to new doc URLs. ........ r60162 | georg.brandl | 2008-01-21 18:17:00 +0100 (Mon, 21 Jan 2008) | 2 lines Fix old link. ........ r60163 | georg.brandl | 2008-01-21 18:22:06 +0100 (Mon, 21 Jan 2008) | 2 lines #1726198: replace while 1: fp.readline() with file iteration. ........ r60164 | georg.brandl | 2008-01-21 18:29:23 +0100 (Mon, 21 Jan 2008) | 2 lines Clarify $ behavior in re docstring. #1631394. ........ r60165 | vinay.sajip | 2008-01-21 18:39:22 +0100 (Mon, 21 Jan 2008) | 1 line Minor documentation change - hyperlink tidied up. ........ r60166 | georg.brandl | 2008-01-21 18:42:40 +0100 (Mon, 21 Jan 2008) | 2 lines #1530959: change distutils build dir for --with-pydebug python builds. ........ r60167 | vinay.sajip | 2008-01-21 19:16:05 +0100 (Mon, 21 Jan 2008) | 1 line Updated to include news on recent logging fixes and documentation changes. ........ r60168 | georg.brandl | 2008-01-21 19:35:49 +0100 (Mon, 21 Jan 2008) | 3 lines Issue #1882: when compiling code from a string, encoding cookies in the second line of code were not always recognized correctly. ........ r60170 | georg.brandl | 2008-01-21 19:36:51 +0100 (Mon, 21 Jan 2008) | 2 lines Add NEWS entry for #1882. ........ r60172 | georg.brandl | 2008-01-21 19:41:24 +0100 (Mon, 21 Jan 2008) | 2 lines Use original location of document, which has translations. ........ r60173 | walter.doerwald | 2008-01-21 21:18:04 +0100 (Mon, 21 Jan 2008) | 2 lines Follow PEP 8 in module docstring. ........ r60175 | georg.brandl | 2008-01-21 21:20:53 +0100 (Mon, 21 Jan 2008) | 2 lines Adapt to latest doctools refactoring. ........
326 lines
11 KiB
Python
326 lines
11 KiB
Python
"""Parse (absolute and relative) URLs.
|
|
|
|
See RFC 1808: "Relative Uniform Resource Locators", by R. Fielding,
|
|
UC Irvine, June 1995.
|
|
"""
|
|
|
|
__all__ = ["urlparse", "urlunparse", "urljoin", "urldefrag",
|
|
"urlsplit", "urlunsplit"]
|
|
|
|
# A classification of schemes ('' means apply by default)
|
|
uses_relative = ['ftp', 'http', 'gopher', 'nntp', 'imap',
|
|
'wais', 'file', 'https', 'shttp', 'mms',
|
|
'prospero', 'rtsp', 'rtspu', '', 'sftp']
|
|
uses_netloc = ['ftp', 'http', 'gopher', 'nntp', 'telnet',
|
|
'imap', 'wais', 'file', 'mms', 'https', 'shttp',
|
|
'snews', 'prospero', 'rtsp', 'rtspu', 'rsync', '',
|
|
'svn', 'svn+ssh', 'sftp']
|
|
non_hierarchical = ['gopher', 'hdl', 'mailto', 'news',
|
|
'telnet', 'wais', 'imap', 'snews', 'sip', 'sips']
|
|
uses_params = ['ftp', 'hdl', 'prospero', 'http', 'imap',
|
|
'https', 'shttp', 'rtsp', 'rtspu', 'sip', 'sips',
|
|
'mms', '', 'sftp']
|
|
uses_query = ['http', 'wais', 'imap', 'https', 'shttp', 'mms',
|
|
'gopher', 'rtsp', 'rtspu', 'sip', 'sips', '']
|
|
uses_fragment = ['ftp', 'hdl', 'http', 'gopher', 'news',
|
|
'nntp', 'wais', 'https', 'shttp', 'snews',
|
|
'file', 'prospero', '']
|
|
|
|
# Characters valid in scheme names
|
|
scheme_chars = ('abcdefghijklmnopqrstuvwxyz'
|
|
'ABCDEFGHIJKLMNOPQRSTUVWXYZ'
|
|
'0123456789'
|
|
'+-.')
|
|
|
|
MAX_CACHE_SIZE = 20
|
|
_parse_cache = {}
|
|
|
|
def clear_cache():
|
|
"""Clear the parse cache."""
|
|
_parse_cache.clear()
|
|
|
|
|
|
class ResultMixin(object):
|
|
"""Shared methods for the parsed result objects."""
|
|
|
|
@property
|
|
def username(self):
|
|
netloc = self.netloc
|
|
if "@" in netloc:
|
|
userinfo = netloc.rsplit("@", 1)[0]
|
|
if ":" in userinfo:
|
|
userinfo = userinfo.split(":", 1)[0]
|
|
return userinfo
|
|
return None
|
|
|
|
@property
|
|
def password(self):
|
|
netloc = self.netloc
|
|
if "@" in netloc:
|
|
userinfo = netloc.rsplit("@", 1)[0]
|
|
if ":" in userinfo:
|
|
return userinfo.split(":", 1)[1]
|
|
return None
|
|
|
|
@property
|
|
def hostname(self):
|
|
netloc = self.netloc
|
|
if "@" in netloc:
|
|
netloc = netloc.rsplit("@", 1)[1]
|
|
if ":" in netloc:
|
|
netloc = netloc.split(":", 1)[0]
|
|
return netloc.lower() or None
|
|
|
|
@property
|
|
def port(self):
|
|
netloc = self.netloc
|
|
if "@" in netloc:
|
|
netloc = netloc.rsplit("@", 1)[1]
|
|
if ":" in netloc:
|
|
port = netloc.split(":", 1)[1]
|
|
return int(port, 10)
|
|
return None
|
|
|
|
from collections import namedtuple
|
|
|
|
class SplitResult(namedtuple('SplitResult', 'scheme netloc path query fragment'), ResultMixin):
|
|
|
|
__slots__ = ()
|
|
|
|
def geturl(self):
|
|
return urlunsplit(self)
|
|
|
|
|
|
class ParseResult(namedtuple('ParseResult', 'scheme netloc path params query fragment'), ResultMixin):
|
|
|
|
__slots__ = ()
|
|
|
|
def geturl(self):
|
|
return urlunparse(self)
|
|
|
|
|
|
def urlparse(url, scheme='', allow_fragments=True):
|
|
"""Parse a URL into 6 components:
|
|
<scheme>://<netloc>/<path>;<params>?<query>#<fragment>
|
|
Return a 6-tuple: (scheme, netloc, path, params, query, fragment).
|
|
Note that we don't break the components up in smaller bits
|
|
(e.g. netloc is a single string) and we don't expand % escapes."""
|
|
tuple = urlsplit(url, scheme, allow_fragments)
|
|
scheme, netloc, url, query, fragment = tuple
|
|
if scheme in uses_params and ';' in url:
|
|
url, params = _splitparams(url)
|
|
else:
|
|
params = ''
|
|
return ParseResult(scheme, netloc, url, params, query, fragment)
|
|
|
|
def _splitparams(url):
|
|
if '/' in url:
|
|
i = url.find(';', url.rfind('/'))
|
|
if i < 0:
|
|
return url, ''
|
|
else:
|
|
i = url.find(';')
|
|
return url[:i], url[i+1:]
|
|
|
|
def _splitnetloc(url, start=0):
|
|
delim = len(url) # position of end of domain part of url, default is end
|
|
for c in '/?#': # look for delimiters; the order is NOT important
|
|
wdelim = url.find(c, start) # find first of this delim
|
|
if wdelim >= 0: # if found
|
|
delim = min(delim, wdelim) # use earliest delim position
|
|
return url[start:delim], url[delim:] # return (domain, rest)
|
|
|
|
def urlsplit(url, scheme='', allow_fragments=True):
|
|
"""Parse a URL into 5 components:
|
|
<scheme>://<netloc>/<path>?<query>#<fragment>
|
|
Return a 5-tuple: (scheme, netloc, path, query, fragment).
|
|
Note that we don't break the components up in smaller bits
|
|
(e.g. netloc is a single string) and we don't expand % escapes."""
|
|
allow_fragments = bool(allow_fragments)
|
|
key = url, scheme, allow_fragments, type(url), type(scheme)
|
|
cached = _parse_cache.get(key, None)
|
|
if cached:
|
|
return cached
|
|
if len(_parse_cache) >= MAX_CACHE_SIZE: # avoid runaway growth
|
|
clear_cache()
|
|
netloc = query = fragment = ''
|
|
i = url.find(':')
|
|
if i > 0:
|
|
if url[:i] == 'http': # optimize the common case
|
|
scheme = url[:i].lower()
|
|
url = url[i+1:]
|
|
if url[:2] == '//':
|
|
netloc, url = _splitnetloc(url, 2)
|
|
if allow_fragments and '#' in url:
|
|
url, fragment = url.split('#', 1)
|
|
if '?' in url:
|
|
url, query = url.split('?', 1)
|
|
v = SplitResult(scheme, netloc, url, query, fragment)
|
|
_parse_cache[key] = v
|
|
return v
|
|
for c in url[:i]:
|
|
if c not in scheme_chars:
|
|
break
|
|
else:
|
|
scheme, url = url[:i].lower(), url[i+1:]
|
|
if scheme in uses_netloc and url[:2] == '//':
|
|
netloc, url = _splitnetloc(url, 2)
|
|
if allow_fragments and scheme in uses_fragment and '#' in url:
|
|
url, fragment = url.split('#', 1)
|
|
if scheme in uses_query and '?' in url:
|
|
url, query = url.split('?', 1)
|
|
v = SplitResult(scheme, netloc, url, query, fragment)
|
|
_parse_cache[key] = v
|
|
return v
|
|
|
|
def urlunparse(components):
|
|
"""Put a parsed URL back together again. This may result in a
|
|
slightly different, but equivalent URL, if the URL that was parsed
|
|
originally had redundant delimiters, e.g. a ? with an empty query
|
|
(the draft states that these are equivalent)."""
|
|
scheme, netloc, url, params, query, fragment = components
|
|
if params:
|
|
url = "%s;%s" % (url, params)
|
|
return urlunsplit((scheme, netloc, url, query, fragment))
|
|
|
|
def urlunsplit(components):
|
|
scheme, netloc, url, query, fragment = components
|
|
if netloc or (scheme and scheme in uses_netloc and url[:2] != '//'):
|
|
if url and url[:1] != '/': url = '/' + url
|
|
url = '//' + (netloc or '') + url
|
|
if scheme:
|
|
url = scheme + ':' + url
|
|
if query:
|
|
url = url + '?' + query
|
|
if fragment:
|
|
url = url + '#' + fragment
|
|
return url
|
|
|
|
def urljoin(base, url, allow_fragments=True):
|
|
"""Join a base URL and a possibly relative URL to form an absolute
|
|
interpretation of the latter."""
|
|
if not base:
|
|
return url
|
|
if not url:
|
|
return base
|
|
bscheme, bnetloc, bpath, bparams, bquery, bfragment = \
|
|
urlparse(base, '', allow_fragments)
|
|
scheme, netloc, path, params, query, fragment = \
|
|
urlparse(url, bscheme, allow_fragments)
|
|
if scheme != bscheme or scheme not in uses_relative:
|
|
return url
|
|
if scheme in uses_netloc:
|
|
if netloc:
|
|
return urlunparse((scheme, netloc, path,
|
|
params, query, fragment))
|
|
netloc = bnetloc
|
|
if path[:1] == '/':
|
|
return urlunparse((scheme, netloc, path,
|
|
params, query, fragment))
|
|
if not (path or params or query):
|
|
return urlunparse((scheme, netloc, bpath,
|
|
bparams, bquery, fragment))
|
|
segments = bpath.split('/')[:-1] + path.split('/')
|
|
# XXX The stuff below is bogus in various ways...
|
|
if segments[-1] == '.':
|
|
segments[-1] = ''
|
|
while '.' in segments:
|
|
segments.remove('.')
|
|
while 1:
|
|
i = 1
|
|
n = len(segments) - 1
|
|
while i < n:
|
|
if (segments[i] == '..'
|
|
and segments[i-1] not in ('', '..')):
|
|
del segments[i-1:i+1]
|
|
break
|
|
i = i+1
|
|
else:
|
|
break
|
|
if segments == ['', '..']:
|
|
segments[-1] = ''
|
|
elif len(segments) >= 2 and segments[-1] == '..':
|
|
segments[-2:] = ['']
|
|
return urlunparse((scheme, netloc, '/'.join(segments),
|
|
params, query, fragment))
|
|
|
|
def urldefrag(url):
|
|
"""Removes any existing fragment from URL.
|
|
|
|
Returns a tuple of the defragmented URL and the fragment. If
|
|
the URL contained no fragments, the second element is the
|
|
empty string.
|
|
"""
|
|
if '#' in url:
|
|
s, n, p, a, q, frag = urlparse(url)
|
|
defrag = urlunparse((s, n, p, a, q, ''))
|
|
return defrag, frag
|
|
else:
|
|
return url, ''
|
|
|
|
|
|
test_input = """
|
|
http://a/b/c/d
|
|
|
|
g:h = <URL:g:h>
|
|
http:g = <URL:http://a/b/c/g>
|
|
http: = <URL:http://a/b/c/d>
|
|
g = <URL:http://a/b/c/g>
|
|
./g = <URL:http://a/b/c/g>
|
|
g/ = <URL:http://a/b/c/g/>
|
|
/g = <URL:http://a/g>
|
|
//g = <URL:http://g>
|
|
?y = <URL:http://a/b/c/d?y>
|
|
g?y = <URL:http://a/b/c/g?y>
|
|
g?y/./x = <URL:http://a/b/c/g?y/./x>
|
|
. = <URL:http://a/b/c/>
|
|
./ = <URL:http://a/b/c/>
|
|
.. = <URL:http://a/b/>
|
|
../ = <URL:http://a/b/>
|
|
../g = <URL:http://a/b/g>
|
|
../.. = <URL:http://a/>
|
|
../../g = <URL:http://a/g>
|
|
../../../g = <URL:http://a/../g>
|
|
./../g = <URL:http://a/b/g>
|
|
./g/. = <URL:http://a/b/c/g/>
|
|
/./g = <URL:http://a/./g>
|
|
g/./h = <URL:http://a/b/c/g/h>
|
|
g/../h = <URL:http://a/b/c/h>
|
|
http:g = <URL:http://a/b/c/g>
|
|
http: = <URL:http://a/b/c/d>
|
|
http:?y = <URL:http://a/b/c/d?y>
|
|
http:g?y = <URL:http://a/b/c/g?y>
|
|
http:g?y/./x = <URL:http://a/b/c/g?y/./x>
|
|
"""
|
|
|
|
def test():
|
|
import sys
|
|
base = ''
|
|
if sys.argv[1:]:
|
|
fn = sys.argv[1]
|
|
if fn == '-':
|
|
fp = sys.stdin
|
|
else:
|
|
fp = open(fn)
|
|
else:
|
|
from io import StringIO
|
|
fp = StringIO(test_input)
|
|
for line in fp:
|
|
words = line.split()
|
|
if not words:
|
|
continue
|
|
url = words[0]
|
|
parts = urlparse(url)
|
|
print('%-10s : %s' % (url, parts))
|
|
abs = urljoin(base, url)
|
|
if not base:
|
|
base = abs
|
|
wrapped = '<URL:%s>' % abs
|
|
print('%-10s = %s' % (url, wrapped))
|
|
if len(words) == 3 and words[1] == '=':
|
|
if wrapped != words[2]:
|
|
print('EXPECTED', words[2], '!!!!!!!!!!')
|
|
|
|
if __name__ == '__main__':
|
|
test()
|