diff options
| -rw-r--r-- | Doc/lib/liburlparse.tex | 172 | ||||
| -rw-r--r-- | Lib/test/test_urlparse.py | 101 | ||||
| -rw-r--r-- | Lib/urlparse.py | 125 | ||||
| -rw-r--r-- | Misc/NEWS | 3 |
4 files changed, 357 insertions, 44 deletions
diff --git a/Doc/lib/liburlparse.tex b/Doc/lib/liburlparse.tex index 730d468..f18efe9 100644 --- a/Doc/lib/liburlparse.tex +++ b/Doc/lib/liburlparse.tex @@ -25,48 +25,74 @@ draft!). It supports the following URL schemes: \code{nntp}, \code{prospero}, \code{rsync}, \code{rtsp}, \code{rtspu}, \code{sftp}, \code{shttp}, \code{sip}, \code{sips}, \code{snews}, \code{svn}, \code{svn+ssh}, \code{telnet}, \code{wais}. + \versionadded[Support for the \code{sftp} and \code{sips} schemes]{2.5} The \module{urlparse} module defines the following functions: -\begin{funcdesc}{urlparse}{urlstring\optional{, default_scheme\optional{, allow_fragments}}} -Parse a URL into 6 components, returning a 6-tuple: (addressing -scheme, network location, path, parameters, query, fragment -identifier). This corresponds to the general structure of a URL: +\begin{funcdesc}{urlparse}{urlstring\optional{, + default_scheme\optional{, allow_fragments}}} +Parse a URL into six components, returning a 6-tuple. This +corresponds to the general structure of a URL: \code{\var{scheme}://\var{netloc}/\var{path};\var{parameters}?\var{query}\#\var{fragment}}. Each tuple item is a string, possibly empty. -The components are not broken up in smaller parts (e.g. the network +The components are not broken up in smaller parts (for example, the network location is a single string), and \% escapes are not expanded. -The delimiters as shown above are not part of the tuple items, +The delimiters as shown above are not part of the result, except for a leading slash in the \var{path} component, which is -retained if present. - -Example: - -\begin{verbatim} -urlparse('http://www.cwi.nl:80/%7Eguido/Python.html') -\end{verbatim} - -yields the tuple +retained if present. For example: \begin{verbatim} +>>> from urlparse import urlparse +>>> o = urlparse('http://www.cwi.nl:80/%7Eguido/Python.html') +>>> o ('http', 'www.cwi.nl:80', '/%7Eguido/Python.html', '', '', '') +>>> o.scheme +'http' +>>> o.port +80 +>>> o.geturl() +'http://www.cwi.nl:80/%7Eguido/Python.html' \end{verbatim} If the \var{default_scheme} argument is specified, it gives the -default addressing scheme, to be used only if the URL string does not +default addressing scheme, to be used only if the URL does not specify one. The default value for this argument is the empty string. -If the \var{allow_fragments} argument is zero, fragment identifiers +If the \var{allow_fragments} argument is false, fragment identifiers are not allowed, even if the URL's addressing scheme normally does -support them. The default value for this argument is \code{1}. +support them. The default value for this argument is \constant{True}. + +The return value is actually an instance of a subclass of +\pytype{tuple}. This class has the following additional read-only +convenience attributes: + +\begin{tableiv}{l|c|l|c}{member}{Attribute}{Index}{Value}{Value if not present} + \lineiv{scheme} {0} {URL scheme specifier} {empty string} + \lineiv{netloc} {1} {Network location part} {empty string} + \lineiv{path} {2} {Hierarchical path} {empty string} + \lineiv{params} {3} {Parameters for last path element} {empty string} + \lineiv{query} {4} {Query component} {empty string} + \lineiv{fragment}{5} {Fragment identifier} {empty string} + \lineiv{username}{ } {User name} {\constant{None}} + \lineiv{password}{ } {Password} {\constant{None}} + \lineiv{hostname}{ } {Host name (lower case)} {\constant{None}} + \lineiv{port} { } {Port number as integer, if present} {\constant{None}} +\end{tableiv} + +See section~\ref{urlparse-result-object}, ``Results of +\function{urlparse()} and \function{urlsplit()},'' for more +information on the result object. + +\versionchanged[Added attributes to return value]{2.5} \end{funcdesc} -\begin{funcdesc}{urlunparse}{tuple} -Construct a URL string from a tuple as returned by \code{urlparse()}. +\begin{funcdesc}{urlunparse}{parts} +Construct a URL from a tuple as returned by \code{urlparse()}. +The \var{parts} argument be any six-item iterable. 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). +URL that was parsed originally had unnecessary delimiters (for example, +a ? with an empty query; the RFC states that these are equivalent). \end{funcdesc} \begin{funcdesc}{urlsplit}{urlstring\optional{, @@ -79,12 +105,38 @@ the URL (see \rfc{2396}) is wanted. A separate function is needed to separate the path segments and parameters. This function returns a 5-tuple: (addressing scheme, network location, path, query, fragment identifier). + +The return value is actually an instance of a subclass of +\pytype{tuple}. This class has the following additional read-only +convenience attributes: + +\begin{tableiv}{l|c|l|c}{member}{Attribute}{Index}{Value}{Value if not present} + \lineiv{scheme} {0} {URL scheme specifier} {empty string} + \lineiv{netloc} {1} {Network location part} {empty string} + \lineiv{path} {2} {Hierarchical path} {empty string} + \lineiv{query} {3} {Query component} {empty string} + \lineiv{fragment} {4} {Fragment identifier} {empty string} + \lineiv{username} { } {User name} {\constant{None}} + \lineiv{password} { } {Password} {\constant{None}} + \lineiv{hostname} { } {Host name (lower case)} {\constant{None}} + \lineiv{port} { } {Port number as integer, if present} {\constant{None}} +\end{tableiv} + +See section~\ref{urlparse-result-object}, ``Results of +\function{urlparse()} and \function{urlsplit()},'' for more +information on the result object. + \versionadded{2.2} +\versionchanged[Added attributes to return value]{2.5} \end{funcdesc} -\begin{funcdesc}{urlunsplit}{tuple} +\begin{funcdesc}{urlunsplit}{parts} Combine the elements of a tuple as returned by \function{urlsplit()} into a complete URL as a string. +The \var{parts} argument be any five-item iterable. +This may result in a slightly different, but equivalent URL, if the +URL that was parsed originally had unnecessary delimiters (for example, +a ? with an empty query; the RFC states that these are equivalent). \versionadded{2.2} \end{funcdesc} @@ -93,22 +145,16 @@ Construct a full (``absolute'') URL by combining a ``base URL'' (\var{base}) with a ``relative URL'' (\var{url}). Informally, this uses components of the base URL, in particular the addressing scheme, the network location and (part of) the path, to provide missing -components in the relative URL. - -Example: - -\begin{verbatim} -urljoin('http://www.cwi.nl/%7Eguido/Python.html', 'FAQ.html') -\end{verbatim} - -yields the string +components in the relative URL. For example: \begin{verbatim} +>>> from urlparse import urljoin +>>> urljoin('http://www.cwi.nl/%7Eguido/Python.html', 'FAQ.html') 'http://www.cwi.nl/%7Eguido/FAQ.html' \end{verbatim} -The \var{allow_fragments} argument has the same meaning as for -\code{urlparse()}. +The \var{allow_fragments} argument has the same meaning and default as +for \function{urlparse()}. \end{funcdesc} \begin{funcdesc}{urldefrag}{url} @@ -133,3 +179,61 @@ in \var{url}, returns \var{url} unmodified and an empty string. both Uniform Resource Names (URNs) and Uniform Resource Locators (URLs).} \end{seealso} + + +\subsection{Results of \function{urlparse()} and \function{urlsplit()} + \label{urlparse-result-object}} + +The result objects from the \function{urlparse()} and +\function{urlsplit()} functions are subclasses of the \pytype{tuple} +type. These subclasses add the attributes described in those +functions, as well as provide an additional method: + +\begin{methoddesc}[ParseResult]{geturl}{} + Return the re-combined version of the original URL as a string. + This may differ from the original URL in that the scheme will always + be normalized to lower case and empty components may be dropped. + Specifically, empty parameters, queries, and fragment identifiers + will be removed. + + The result of this method is a fixpoint if passed back through the + original parsing function: + +\begin{verbatim} +>>> import urlparse +>>> url = 'HTTP://www.Python.org/doc/#' + +>>> r1 = urlparse.urlsplit(url) +>>> r1.geturl() +'http://www.Python.org/doc/' + +>>> r2 = urlparse.urlsplit(r1.geturl()) +>>> r2.geturl() +'http://www.Python.org/doc/' +\end{verbatim} + +\versionadded{2.5} +\end{methoddesc} + +The following classes provide the implementations of the parse results:: + +\begin{classdesc*}{BaseResult} + Base class for the concrete result classes. This provides most of + the attribute definitions. It does not provide a \method{geturl()} + method. It is derived from \class{tuple}, but does not override the + \method{__init__()} or \method{__new__()} methods. +\end{classdesc*} + + +\begin{classdesc}{ParseResult}{scheme, netloc, path, params, query, fragment} + Concrete class for \function{urlparse()} results. The + \method{__new__()} method is overridden to support checking that the + right number of arguments are passed. +\end{classdesc} + + +\begin{classdesc}{SplitResult}{scheme, netloc, path, query, fragment} + Concrete class for \function{urlsplit()} results. The + \method{__new__()} method is overridden to support checking that the + right number of arguments are passed. +\end{classdesc} diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py index 39ada06..5cee458 100644 --- a/Lib/test/test_urlparse.py +++ b/Lib/test/test_urlparse.py @@ -12,15 +12,53 @@ class UrlParseTestCase(unittest.TestCase): def checkRoundtrips(self, url, parsed, split): result = urlparse.urlparse(url) self.assertEqual(result, parsed) + t = (result.scheme, result.netloc, result.path, + result.params, result.query, result.fragment) + self.assertEqual(t, parsed) # put it back together and it should be the same result2 = urlparse.urlunparse(result) self.assertEqual(result2, url) + self.assertEqual(result2, result.geturl()) + + # the result of geturl() is a fixpoint; we can always parse it + # again to get the same result: + result3 = urlparse.urlparse(result.geturl()) + self.assertEqual(result3.geturl(), result.geturl()) + self.assertEqual(result3, result) + self.assertEqual(result3.scheme, result.scheme) + self.assertEqual(result3.netloc, result.netloc) + self.assertEqual(result3.path, result.path) + self.assertEqual(result3.params, result.params) + self.assertEqual(result3.query, result.query) + self.assertEqual(result3.fragment, result.fragment) + self.assertEqual(result3.username, result.username) + self.assertEqual(result3.password, result.password) + self.assertEqual(result3.hostname, result.hostname) + self.assertEqual(result3.port, result.port) # check the roundtrip using urlsplit() as well result = urlparse.urlsplit(url) self.assertEqual(result, split) + t = (result.scheme, result.netloc, result.path, + result.query, result.fragment) + self.assertEqual(t, split) result2 = urlparse.urlunsplit(result) self.assertEqual(result2, url) + self.assertEqual(result2, result.geturl()) + + # check the fixpoint property of re-parsing the result of geturl() + result3 = urlparse.urlsplit(result.geturl()) + self.assertEqual(result3.geturl(), result.geturl()) + self.assertEqual(result3, result) + self.assertEqual(result3.scheme, result.scheme) + self.assertEqual(result3.netloc, result.netloc) + self.assertEqual(result3.path, result.path) + self.assertEqual(result3.query, result.query) + self.assertEqual(result3.fragment, result.fragment) + self.assertEqual(result3.username, result.username) + self.assertEqual(result3.password, result.password) + self.assertEqual(result3.hostname, result.hostname) + self.assertEqual(result3.port, result.port) def test_roundtrips(self): testcases = [ @@ -187,6 +225,69 @@ class UrlParseTestCase(unittest.TestCase): ]: self.assertEqual(urlparse.urldefrag(url), (defrag, frag)) + def test_urlsplit_attributes(self): + url = "HTTP://WWW.PYTHON.ORG/doc/#frag" + p = urlparse.urlsplit(url) + self.assertEqual(p.scheme, "http") + self.assertEqual(p.netloc, "WWW.PYTHON.ORG") + self.assertEqual(p.path, "/doc/") + self.assertEqual(p.query, "") + self.assertEqual(p.fragment, "frag") + self.assertEqual(p.username, None) + self.assertEqual(p.password, None) + self.assertEqual(p.hostname, "www.python.org") + self.assertEqual(p.port, None) + # geturl() won't return exactly the original URL in this case + # since the scheme is always case-normalized + #self.assertEqual(p.geturl(), url) + + url = "http://User:Pass@www.python.org:080/doc/?query=yes#frag" + p = urlparse.urlsplit(url) + self.assertEqual(p.scheme, "http") + self.assertEqual(p.netloc, "User:Pass@www.python.org:080") + self.assertEqual(p.path, "/doc/") + self.assertEqual(p.query, "query=yes") + self.assertEqual(p.fragment, "frag") + self.assertEqual(p.username, "User") + self.assertEqual(p.password, "Pass") + self.assertEqual(p.hostname, "www.python.org") + self.assertEqual(p.port, 80) + self.assertEqual(p.geturl(), url) + + def test_attributes_bad_port(self): + """Check handling of non-integer ports.""" + p = urlparse.urlsplit("http://www.example.net:foo") + self.assertEqual(p.netloc, "www.example.net:foo") + self.assertRaises(ValueError, lambda: p.port) + + p = urlparse.urlparse("http://www.example.net:foo") + self.assertEqual(p.netloc, "www.example.net:foo") + self.assertRaises(ValueError, lambda: p.port) + + def test_attributes_without_netloc(self): + # This example is straight from RFC 3261. It looks like it + # should allow the username, hostname, and port to be filled + # in, but doesn't. Since it's a URI and doesn't use the + # scheme://netloc syntax, the netloc and related attributes + # should be left empty. + uri = "sip:alice@atlanta.com;maddr=239.255.255.1;ttl=15" + p = urlparse.urlsplit(uri) + self.assertEqual(p.netloc, "") + self.assertEqual(p.username, None) + self.assertEqual(p.password, None) + self.assertEqual(p.hostname, None) + self.assertEqual(p.port, None) + self.assertEqual(p.geturl(), uri) + + p = urlparse.urlparse(uri) + self.assertEqual(p.netloc, "") + self.assertEqual(p.username, None) + self.assertEqual(p.password, None) + self.assertEqual(p.hostname, None) + self.assertEqual(p.port, None) + self.assertEqual(p.geturl(), uri) + + def test_main(): test_support.run_unittest(UrlParseTestCase) diff --git a/Lib/urlparse.py b/Lib/urlparse.py index 8d44853..eade040 100644 --- a/Lib/urlparse.py +++ b/Lib/urlparse.py @@ -41,7 +41,111 @@ def clear_cache(): _parse_cache = {} -def urlparse(url, scheme='', allow_fragments=1): +class BaseResult(tuple): + """Base class for the parsed result objects. + + This provides the attributes shared by the two derived result + objects as read-only properties. The derived classes are + responsible for checking the right number of arguments were + supplied to the constructor. + + """ + + __slots__ = () + + # Attributes that access the basic components of the URL: + + @property + def scheme(self): + return self[0] + + @property + def netloc(self): + return self[1] + + @property + def path(self): + return self[2] + + @property + def query(self): + return self[-2] + + @property + def fragment(self): + return self[-1] + + # Additional attributes that provide access to parsed-out portions + # of the netloc: + + @property + def username(self): + netloc = self.netloc + if "@" in netloc: + userinfo = netloc.split("@", 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.split("@", 1)[0] + if ":" in userinfo: + return userinfo.split(":", 1)[1] + return None + + @property + def hostname(self): + netloc = self.netloc + if "@" in netloc: + netloc = netloc.split("@", 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.split("@", 1)[1] + if ":" in netloc: + port = netloc.split(":", 1)[1] + return int(port, 10) + return None + + +class SplitResult(BaseResult): + + __slots__ = () + + def __new__(cls, scheme, netloc, path, query, fragment): + return BaseResult.__new__( + cls, (scheme, netloc, path, query, fragment)) + + def geturl(self): + return urlunsplit(self) + + +class ParseResult(BaseResult): + + __slots__ = () + + def __new__(cls, scheme, netloc, path, params, query, fragment): + return BaseResult.__new__( + cls, (scheme, netloc, path, params, query, fragment)) + + @property + def params(self): + return self[3] + + 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). @@ -53,7 +157,7 @@ def urlparse(url, scheme='', allow_fragments=1): url, params = _splitparams(url) else: params = '' - return scheme, netloc, url, params, query, fragment + return ParseResult(scheme, netloc, url, params, query, fragment) def _splitparams(url): if '/' in url: @@ -73,12 +177,13 @@ def _splitnetloc(url, start=0): delim = len(url) return url[start:delim], url[delim:] -def urlsplit(url, scheme='', allow_fragments=1): +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 cached = _parse_cache.get(key, None) if cached: @@ -97,9 +202,9 @@ def urlsplit(url, scheme='', allow_fragments=1): url, fragment = url.split('#', 1) if '?' in url: url, query = url.split('?', 1) - tuple = scheme, netloc, url, query, fragment - _parse_cache[key] = tuple - return tuple + 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 @@ -111,9 +216,9 @@ def urlsplit(url, scheme='', allow_fragments=1): url, fragment = url.split('#', 1) if scheme in uses_query and '?' in url: url, query = url.split('?', 1) - tuple = scheme, netloc, url, query, fragment - _parse_cache[key] = tuple - return tuple + v = SplitResult(scheme, netloc, url, query, fragment) + _parse_cache[key] = v + return v def urlunparse((scheme, netloc, url, params, query, fragment)): """Put a parsed URL back together again. This may result in a @@ -136,7 +241,7 @@ def urlunsplit((scheme, netloc, url, query, fragment)): url = url + '#' + fragment return url -def urljoin(base, url, allow_fragments = 1): +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: @@ -489,6 +489,9 @@ Extension Modules Library ------- +- Patch #624325: urlparse.urlparse() and urlparse.urlsplit() results + now sport attributes that provide access to the parts of the result. + - Patch #1462498: sgmllib now handles entity and character references in attribute values. |