+

+tde_add_check_executable( testlibrss AUTOMOC

+ SOURCES testlibrss.cpp

+ LINK rsslocal-static ${TQT_LIBRARIES} tdeio-shared

+)

+

+set( TEST_DATA "${CMAKE_CURRENT_SOURCE_DIR}/test_data")

+

+add_test( NAME TestLibRSS_0.91

+ COMMAND testlibrss ${TEST_DATA}/rss091.xml

+)

+

+add_test( NAME TestLibRSS_CommentAPI

+ COMMAND testlibrss ${TEST_DATA}/comment_api.xml

+)

+

+add_test( NAME TestLibRSS_DublinCore

+ COMMAND testlibrss ${TEST_DATA}/dublincore.xml

+)

+

+add_test( NAME TestLibRSS_RDF

+ COMMAND testlibrss ${TEST_DATA}/rdf.xml

+)

+

+add_test( NAME TestLibRSS_AtomSpec

+ COMMAND testlibrss ${TEST_DATA}/atom_spec.xml

+)

+<?xml version="1.0" encoding="utf-8"?>

+<feed xmlns="http://www.w3.org/2005/Atom" xml:lang="en-us">

+ <title type="text">dive into mark</title>

+ <subtitle type="html">

+ A &lt;em&gt;lot&lt;/em&gt; of effort

+ went into making this effortless

+ </subtitle>

+ <updated>2005-07-31T12:29:29Z</updated>

+ <id>tag:example.org,2003:3</id>

+ <link rel="alternate" type="text/html" hreflang="en" href="http://example.org/"/>

+ <link rel="self" type="application/atom+xml" href="http://example.org/feed.atom"/>

+ <rights>Copyright (c) 2003, Mark Pilgrim</rights>

+ <generator uri="http://www.example.com/" version="1.0">

+ Example Toolkit

+ </generator>

+ <entry>

+ <title>Atom draft-07 snapshot</title>

+ <link rel="alternate" type="text/html" href="http://example.org/2005/04/02/atom"/>

+ <link rel="enclosure" type="audio/mpeg" length="1337" href="http://example.org/audio/ph34r_my_podcast.mp3"/>

+ <id>tag:example.org,2003:3.2397</id>

+ <updated>2005-07-31T12:29:29Z</updated>

+ <published>2003-12-13T08:29:29-04:00</published>

+ <author>

+ <name>Mark Pilgrim</name>

+ <uri>http://example.org/</uri>

+ <email>f8dy@example.com</email>

+ </author>

+ <contributor>

+ <name>Sam Ruby</name>

+ </contributor>

+ <contributor>

+ <name>Joe Gregorio</name>

+ </contributor>

+ <content type="xhtml" xml:lang="en" xml:base="http://diveintomark.org/">

+ <div xmlns="http://www.w3.org/1999/xhtml">

+ <p>

+ <i>[Update: The Atom draft is finished.]</i>

+ </p>

+ </div>

+ </content>

+ </entry>

+</feed>

+<?xml version="1.0" encoding="iso-8859-1"?>

+<rss version="2.0" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:wfw='http://wellformedweb.org/CommentAPI/' xmlns:dc='http://purl.org/dc/elements/1.1/' xmlns:rl='http://www.purl.org/RESTLog/'>

+ <channel>

+ <title>The Well-Formed Web</title>

+ <link>http://wellformedweb.org/news/</link>

+ <description>Exploring the limits of XML and HTTP</description>

+ <dc:creator>BitWorking, Inc</dc:creator>

+ <item>

+ <title>Should you use Content Negotiation in your Web Services?</title>

+ <link>http://bitworking.org/news/WebServicesAndContentNegotiation</link>

+ <description>

+ &lt;p&gt;Should you use Content Negotiation when building your web service?

+The short answer is no. There are definite problems with &lt;abbrev title="Content Negotiation"&gt;conneg&lt;/abbrev&gt;

+and I can give some examples of problems I have run into and also point to problems

+other have run into.&lt;/p&gt;

+

+

+&lt;p&gt;First let's back up and explain Content Negotiation. Your browser is

+ a generic display program and can take in various kinds of media, such

+ as HTML, JPEGs, CSS, Flash, etc. and display it for you. The first thing to

+ note is that each of those kinds of media have different mime types.

+ Each format has it's own registered mime type and when a client

+ does a GET on a URL it gets back not only the content but the response

+ also includes a &lt;code&gt;Content-Type:&lt;/code&gt; header which lists

+ the mime-type of what is in the body.

+&lt;/p&gt;

+

+&lt;p&gt;One of the interesting things about HTTP is that it allows

+ the same URI to have multiple representations. For example I

+ could have a URL that had both &lt;code&gt;plain/text&lt;/code&gt; and &lt;code&gt;text/html&lt;/code&gt;

+ representations. Now that leads to two obvious questions.&lt;/p&gt;

+

+&lt;ol&gt;

+ &lt;li&gt;How does the server know which represenation to serve?&lt;/li&gt;

+ &lt;li&gt;How can the browser influence the servers choice to get something it can handle?&lt;/li&gt;

+&lt;/ol&gt;

+

+&lt;p&gt;Let's start by answering question two first. The browser uses the &lt;code&gt;Accept:&lt;/code&gt;

+ header to list out the mime-types that it is willing to accept. There is also a weighting

+ scheme that allows the client to specify a preference for one media type

+ over another. For example, here is the capture of some of the headers, including the &lt;code&gt;Accept:&lt;/code&gt; header,

+ sent by Mozilla when it does a GET on a URI:&lt;/p&gt;

+

+&lt;pre class="example"&gt;&lt;code&gt;Accept: text/xml,application/xml,application/xhtml+xml,\

+ text/html;q=0.9,text/plain;q=0.8,video/x-mng,\

+ image/png,image/jpeg,image/gif;q=0.2,*/*;q=0.1

+Accept-Language: en-us,en;q=0.5

+Accept-Encoding: gzip,deflate,compress;q=0.9

+Accept-Charset: ISO-8859-1,utf-8;q=0.7,*;q=0.7

+&lt;/code&gt;&lt;/pre&gt;

+

+&lt;p&gt;The &lt;code&gt;Accept:&lt;/code&gt; header list the mime-types that the browser can

+ handle along with weights of the form &lt;code&gt;q=&lt;/code&gt; where the argument

+ is a floating point number between 0 and 1. The weights indicate a preference

+ for that media type, with a higher number inidicating a higher preference. Note that

+ there are several bits of complexity I am going to ignore for now. The first is the last

+ type the Mozilla browser says in can accept, */*;q=0.1. This is a wild card

+ match, which will match any mime-type that the server could want to serve up. The second

+ is that there are multiple Accept headers, one for language, one for encoding, another

+ for charset. How these over-lap and influence the response sent won't be covered here.

+&lt;/p&gt;

+

+&lt;p&gt;Now to answer the first question. The server looks at the available representations

+ is has and servers up the one with the highest preference to the client.

+ Based on the &lt;code&gt;Accept:&lt;/code&gt;

+ header it sends an appropriate representation back and indicates the type it

+ chose using the &lt;code&gt;Content-Type:&lt;/code&gt; header.&lt;/p&gt;

+

+&lt;p&gt;This seems like a really cool and vastly under utilized feature of HTTP. It also

+ seems particularly intriguing for web services. You could return

+ JPEGs from that mapping service for the older client platforms, but also

+ serve up SVG for the newer clients so they can scale and rotate their maps.

+ What could possibly go wrong?&lt;/p&gt;

+

+&lt;p&gt;The first thing that could go wrong is a bug or mis-configuration on the client or the server.

+ This has happened to me in the

+ past. The W3C does conneg on some of their recommendations, returning either HTML or plain

+ text based on the clients capabilities. This is fine, but one day their server was

+ either confused or mis-configured because it would only serve the recommendation in &lt;code&gt;plain/text&lt;/code&gt;.

+ I really needed the HTML form, but after trying multiple browsers from multipe locations I could only retrieve the text

+ format. I ended up pulling the HTML version out of the Google cache.&lt;/p&gt;

+

+&lt;p&gt;The second problem that I ran across highlights the real core problem with conneg. I was

+ trying to use the W3C XSLT service to do some transformations on my web pages. Now the server side

+ software I use to run Well-Formed Web does conneg and can return either HTML or an RSS item

+ fragment for each URI. At the time I was serving up XHTML 1.0, which is valid XML and

+ thus good input into an XSLT service. So the way the XSLT service works is that you enter two URIs, one

+ for the source content and the other for the XSLT sheet to apply to the source content.

+ My transformation kept failing and it was because of the

+ Accept headers that the XSLT service sent when it went to retrieve the source content.

+ My server kept returning the RSS item fragment and not

+ the XHTML. Now this would have been fine if I wanted to apply an XSLT sheet to my RSS item fragment, but in this

+ case I wanted it to apply to the XHTML. Note that the problem could have been completely reversed, I could have

+ been trying to apply the XSLT to the RSS item and not to the XHTML and my server could have returned

+ the XHTML all the time. The crux of the problem is that when I gave the URI to the XSLT transformation

+ service I have no way of specifying what mime-type to request. I get no chance to tweak the

+ services &lt;code&gt;Accept:&lt;/code&gt; header.

+&lt;/p&gt;

+

+&lt;p&gt;Let's cover that again to clarify. If I hand you a URI only, and that URI supports conneg,

+ then I get no control over which representation you retrieve. In the cases where you are

+ passing a URI into a service that is later going to retrieve a represenation from that URI, you

+ really have no idea which representation it's going to get. That could mean that you end up

+ passing your RSS feed to the W3C HTML validator, or you end up passing XHTML instead of RSS into

+ an XSLT translator service, or you end up passing a 12MB PNG to a handheld instead of

+ that 20KB SVG file. You end up with a problem that is hard to debug and

+ one that wouldn't exist if each URI had only one mime-type.&lt;/p&gt;

+

+&lt;h3&gt;Further Reading&lt;/h3&gt;

+&lt;p&gt;&lt;a href="http://norman.walsh.name/2003/07/02/conneg"&gt;Norman Walsh has also run into problems&lt;/a&gt; with Content Negotiation.&lt;/p&gt;

+&lt;p&gt;The issue of using fragment identifiers with conneg has not only come up but was important enough to

+ merit mention in the W3C document &lt;a href="http://www.w3.org/TR/webarch/#frag-conneg"&gt;Architecture of the World Wide Web&lt;/a&gt;.&lt;/p&gt;

+

+

+ </description>

+

+ <dc:date>2003-09-06T21:54:43-05:00</dc:date>

+ <wfw:comment>http://bitworking.org/news/comments/WebServicesAndContentNegotiation</wfw:comment>

+ <wfw:commentRss>http://bitworking.org/news/WebServicesAndContentNegotiation?crss</wfw:commentRss>

+ </item>

+ <item>

+ <title>Google2Atom</title>

+ <link>http://wellformedweb.org/news/Google2Atom</link>

+ <description>

+&lt;p&gt;Welcome to the Google2Atom web service. Just enter your

+ search and your &lt;a href="http://www.google.com/apis/"&gt;Google key&lt;/a&gt;

+ below. Once you press "Search" you will get an &lt;a href="http://www.mnot.net/drafts/draft-nottingham-atom-format-00.html"&gt;

+ Atom&lt;/a&gt; feed of the search results.

+&lt;/p&gt;

+

+&lt;form method="get" action="http://wellformedweb.org/cgi-bin/google2atom.cgi"&gt;

+&lt;p&gt;&lt;input size="50" name="q"/&gt;&lt;/p&gt;

+&lt;p&gt;Google Key: &lt;input size="20" name="license_key"/&gt;&lt;/p&gt;

+&lt;p&gt;&lt;input type="submit" value=" Search "/&gt;&lt;/p&gt;

+&lt;/form&gt;

+

+&lt;hr /&gt;

+

+&lt;p&gt;&lt;strong&gt;Note:&lt;/strong&gt; The Google Key is no longer mandatory, if it's not

+ supplied it will use my own key. In light of that please feel free to

+ use my key for experimentation, but if you start making heavy use

+ of this service please get your own Google API Key to avoid

+ limiting others use of this service.&lt;/p&gt;

+

+&lt;p&gt;This is a REST based reformulation of the Google API. As such it uses

+ query parameters in a GET based HTTP request to do the search. That is, it works

+ just like the regular google web page, but this form returns

+ a well-formed XML document instead of a web page. Why is this better?&lt;/p&gt;

+

+&lt;dl&gt;

+ &lt;dt&gt;Simplicity&lt;/dt&gt;

+ &lt;dd&gt;

+ It works just like the google web page, so it is

+ conceptually easier to understand.

+ &lt;/dd&gt;

+

+ &lt;dt&gt;Composability&lt;/dt&gt;

+ &lt;dd&gt;Since the request is just a simple GET the results of a query can be composed

+ with other web services. For example, the results could be transformed using

+ XSLT or fed into a validator.

+ &lt;/dd&gt;

+&lt;/dl&gt;

+

+&lt;h3&gt;Bonus Features&lt;/h3&gt;

+

+&lt;p&gt;One feature found in this interface that is not found

+ in the original Google API is the well-formedness of the

+ results content.

+ &lt;a href="http://bitworking.org/news/Announcing_pyTidy"&gt;PyTidy&lt;/a&gt;

+ is used to transform the HTML

+ snippets from the Google API into well-formed XML and place

+ those into 'content' elements with type='text/html' and

+ mode='xml'.

+&lt;/p&gt;

+

+&lt;h3&gt;Colophon&lt;/h3&gt;

+

+&lt;p&gt;Google2Atom is written in &lt;a href="http://www.python.org"&gt;Python&lt;/a&gt; and uses

+ both the &lt;a href="http://bitworking.org/news/Announcing_pyTidy"&gt;

+ pyTidy&lt;/a&gt; and &lt;a href="http://www.diveintomark.org/projects/pygoogle/"&gt;

+ pyGoogle&lt;/a&gt; libraries.&lt;/p&gt;

+

+ </description>

+

+ <dc:date>2003-11-22T01:18:42-05:00</dc:date>

+ <wfw:comment>http://wellformedweb.org/news/comments/Google2Atom</wfw:comment>

+ <wfw:commentRss>http://wellformedweb.org/news/Google2Atom?crss</wfw:commentRss>

+ </item>

+ <item>

+ <title>wfw namespace elements</title>

+ <link>http://wellformedweb.org/news/wfw_namespace_elements</link>

+ <description>

+ &lt;p&gt;The &lt;code&gt;wfw&lt;/code&gt; namespace, http://wellformedweb.org/CommentAPI/

+contains multiple elements. As more are added in various places I will

+endeavor to keep the list here updated.&lt;/p&gt;

+

+&lt;dl&gt;

+ &lt;dt&gt;wfw:comment&lt;/dt&gt;

+ &lt;dd&gt;The first element to appear in this namespace is &lt;code&gt;comment&lt;/code&gt;. This element appears

+ in RSS feeds and contains the URI that comment entries are to be POSTed to. The details

+ of this are outlined in the &lt;a href="http://wellformedweb.org/story/9"&gt;CommentAPI Specification&lt;/a&gt;.&lt;dd&gt;

+

+ &lt;dt&gt;wfw:commentRss&lt;/dt&gt;

+ &lt;dd&gt;The second element to appear in the wfw namespace is &lt;code&gt;commentRss&lt;/code&gt;. This element

+ also appears in RSS feeds and contains the URI of the RSS feed for comments on that Item.

+ This is documented in &lt;a href="http://www.sellsbrothers.com/spout/default.aspx?content=archive.htm#exposingRssComments"&gt;Chris Sells' Specification&lt;/a&gt;. Note that for quite a while this page has had a typo and erroneously referred to

+ this element as 'commentRSS' as opposed to the correct 'commentRss'. Feed consumers should be aware

+ that they may run into both spellings in the wild. Please see

+ &lt;a href="http://www.intertwingly.net/blog/2006/04/16/commentRss"&gt;this page&lt;/a&gt; for

+ more information.

+ &lt;/dd&gt;

+&lt;/dl&gt;

+ </description>

+

+ <dc:date>2003-10-10T13:11:46-05:00</dc:date>

+ <wfw:comment>http://wellformedweb.org/news/comments/wfw_namespace_elements</wfw:comment>

+ <wfw:commentRss>http://wellformedweb.org/news/wfw_namespace_elements?crss</wfw:commentRss>

+ </item>

+ <item>

+ <title>The HTTP verb PUT under Apache: Safe or Dangerous?</title>

+ <link>http://wellformedweb.org/news/PUT_SaferOrDangerous</link>

+ <description>

+ &lt;p&gt;"Is the HTTP verb PUT under Apache safe or dangerous?" This is a question I come across often, and have now

+ run into it twice in the work on Atom. So is it safe? The answer is maybe.&lt;/p&gt;

+&lt;p&gt;Here are two such examples:&lt;/p&gt;

+

+&lt;blockquote&gt;&lt;p&gt;

+ Using DELETE and PUT may be the "right thing to do"

+ in an ideal world, but the fact of the matter is that a

+ lot -- if not the vast majority -- of webservers do not allow these

+ operations. &lt;/p&gt;&lt;/blockquote&gt;

+

+&lt;blockquote&gt;&lt;p&gt;If anyone knows of a newer article describing

+ HTTP PUT with apache, I would be very interested in seeing it. Because,

+ due to my experience with PUT, you have to define a single PUTScript in

+ httpd.conf, and if you PUT something to an apache server at the URI

+ www.example.com/blog/entries/1 or something similar, apache passes all

+ of the information to the PUTScript, not to anything else.&lt;/p&gt;&lt;/blockquote&gt;

+

+&lt;p&gt;Both of the above quotes are from the &lt;a href="http://www.intertwingly.net/wiki/pie/RestEchoApiPutAndDelete"&gt;Atom Wiki discussion

+ of the use of PUT&lt;/a&gt;. A little digging reveals that the ApacheWeek article

+ &lt;a href="http://www.apacheweek.com/features/put"&gt;Publishing Pages with PUT&lt;/a&gt;

+ is referenced most often when the danger of PUT is raised. &lt;p&gt;

+

+&lt;p&gt;That ApacheWeek article does talk about the dangers of PUT and

+ the cautions you need to follow when writing a script that

+ does content publishing via PUT. That key part of that phrase

+ is &lt;strong&gt;content publishing&lt;/strong&gt;. That means that PUT is being

+ used to upload arbitrary content to the server and the client

+ is determining via the URI where the content should be stored.

+ Now you can imagine how this might be dangerous, for example

+ not correctly checking URI paths that include &lt;code&gt;../..&lt;/code&gt; could

+ let a malicious agent re-write your &lt;code&gt;.bashrc&lt;/code&gt;.&lt;/p&gt;

+

+&lt;p&gt;Implementing a PUT script can be difficult and a security hazard

+ in the context of content publishing, but that's the case because

+ the client is choosing the target URI and the client could upload

+ any content type. In the case of Web Services in general, and

+ the AtomAPI in particular, PUT is used in a much narrower manner

+ and avoids those potential security problems.&lt;/p&gt;

+

+&lt;p&gt;In the case of the AtomAPI PUT is only allowed on URIs that point

+ to a pre-existing resource. The

+ AtomAPI follows a general idiom for editing resources of doing

+ a GET to retrieve the original XML, then a PUT on the same URI

+ to upate that resource with the edited XML. No URIs are created

+ by doing a PUT. PUT is not accepted on arbitrary URIs. This makes

+ the use of PUT in the context of the AtomAPI just as safe as POST.&lt;/p&gt;

+

+&lt;p&gt;There are quite a few ways to configure Apache to process

+ incoming requests. In particular it is possible to have a single

+ script that handles all PUT requests below a chosen directory. This

+ strategy, and all of the associated security concerns associated with

+ it, are covered fully in the &lt;a href="http://www.apacheweek.com/features/put"&gt;Publishing Pages with PUT&lt;/a&gt;.&lt;/p&gt;

+

+&lt;p&gt;When processing request with a CGI script all the PUT requests

+ will come through. The verb is passed to the CGI program via the REQUEST_METHOD environment

+ variable, and the program decides what to do with the content.&lt;/p&gt;

+

+&lt;p&gt;Using PUT propoerly has advantages in Web Service development. First,

+ Apache lets you control security based on the verb using the

+ &lt;a href="http://httpd.apache.org/docs-2.0/mod/core.html#limit"&gt;Limit&lt;/a&gt;

+ and &lt;a href="http://httpd.apache.org/docs-2.0/mod/core.html#limitexcept"&gt;LimitExcept&lt;/a&gt;

+ directives, which

+ let you restrict access controls based on the verb. Here is a sample

+ of one of my &lt;code&gt;.htaccess&lt;/code&gt; files that restricts the use of

+ all verbs except GET to the CGI program &lt;code&gt;Bulu.cgi.&lt;/code&gt;&lt;/p&gt;

+

+&lt;pre class="example"&gt;&lt;code&gt;&amp;lt;Files Bulu.cgi&gt;

+AuthType Basic

+AuthName myrealm

+AuthUserFile /path/to/my/password/file

+ &amp;lt;LimitExcept GET&gt;

+ Require valid-user

+ &amp;lt;/LimitExcept&gt;

+&amp;lt;/Files&gt;

+&lt;/code&gt;&lt;/pre&gt;

+

+&lt;p&gt;In addition, the &lt;a href="http://httpd.apache.org/docs-2.0/mod/mod_actions.html#script"&gt;Script&lt;/a&gt;

+ directive can be used to dispatch to a CGI program based on the verb used:&lt;/p&gt;

+

+&lt;pre class="example"&gt;&lt;code&gt;Script PUT /cgi-bin/put.cgi&lt;/code&gt;&lt;/pre&gt;

+

+&lt;p&gt;The second advantage using PUT brings is clarity. Given the idiom

+ of using GET/PUT in tandem on a URI to edit resources PUT

+ clearly signals what the interface is doing.&lt;/p&gt;

+

+&lt;h4&gt;Resources&lt;/h4&gt;

+

+&lt;p&gt;&lt;a href="http://www.apacheweek.com"&gt;ApacheWeek&lt;/a&gt;: &lt;a href="http://www.apacheweek.com/features/put"&gt;Publishing Pages with PUT&lt;/a&gt;&lt;/p&gt;

+&lt;p&gt;&lt;a href="http://www.intertwingly.net/wiki/pie/RestEchoApiPutAndDelete"&gt;RestEchoApiPutAndDelete&lt;/a&gt;: Discussion on the use of PUT

+ and DELETE in the AtomAPI.&lt;/p&gt;

+&lt;p&gt;&lt;a href="http://httpd.apache.org/docs-2.0/mod/mod_actions.html"&gt;mod_actions&lt;/a&gt;: An Apache module for

+ controlling dispatching based on verb or content-type.&lt;/p&gt;

+&lt;p&gt;&lt;a href="http://www.w3.org/Amaya/User/Put.html"&gt;Configuring your WWW server to understand the PUT method&lt;/a&gt;, from the W3Cs Amaya project documentation.&lt;/p&gt;

+&lt;p&gt;&lt;a href="http://www.webdav.org/"&gt;WebDAV&lt;/a&gt; is also something you may be interested in if you

+ are looking for ways to publish your content using HTTP. WebDAV stands for

+ "Web-based Distributed Authoring and Versioning". It is a set of extensions to the HTTP

+ protocol which allows users to collaboratively edit and manage files on remote web servers.

+ &lt;a href="http://httpd.apache.org/docs-2.0/mod/mod_dav.html"&gt;

+ Mod_dav&lt;/a&gt; in an Apache module that implements WebDAV.&lt;/p&gt;

+

+

+

+ </description>

+

+ <dc:date>2003-08-23T00:45:25-05:00</dc:date>

+ <wfw:comment>http://wellformedweb.org/news/comments/PUT_SaferOrDangerous</wfw:comment>

+ <wfw:commentRss>http://wellformedweb.org/news/PUT_SaferOrDangerous?crss</wfw:commentRss>

+ </item>

+ <item>

+ <title>Six Plus One</title>

+ <link>http://wellformedweb.org/news/SixPlusOne</link>

+ <description>

+ &lt;p&gt;Previously I talked about the &lt;a href="http://bitworking.org/news/Six_Places"&gt;six different places&lt;/a&gt; there are to

+ store information in an HTTP transaction. This is slightly misleading.

+&lt;/p&gt;

+

+&lt;p&gt; To review, the six places are:&lt;/p&gt;

+&lt;ol&gt;

+ &lt;li&gt;Request URI&lt;/li&gt;

+ &lt;li&gt;Request Headers&lt;/li&gt;

+ &lt;li&gt;Request Content&lt;/li&gt;

+ &lt;li&gt;Response Status Code&lt;/li&gt;

+ &lt;li&gt;Response Headers&lt;/li&gt;

+ &lt;li&gt;Response Content&lt;/li&gt;

+&lt;/ol&gt;

+

+&lt;p&gt;This is slightly misleading because the URI is listed as a single

+ storage location. This isn't the best characterization, as it really

+ contains two different sets of information: the path, and the query parameters.&lt;/p&gt;

+

+&lt;p&gt;Now the path part of a URI usually corresponds to the directory structure on the server.

+ But remember that the path structure of a server is completely controlled

+ by that server and it need not corresponse to any file or directory strucure.

+ While it is at times convenient to map it to a directory structure, this isn't required,

+ and it is possible to pass path information to a

+ CGI program. For example, if you do a GET on the following URL:&lt;/p&gt;

+

+&lt;pre class="example"&gt;&lt;code&gt;http://example.org/cgi-bin/test.py/fred/12

+&lt;/code&gt;&lt;/pre&gt;

+

+&lt;p&gt;and there exists a program named &lt;code&gt;test.py&lt;/code&gt; in the &lt;code&gt;cgi-bin&lt;/code&gt; directory

+ then that program will be executed. The remaining path after the program is passed

+ to the CGI program in the PATH_INFO environment variable. In contrast, if query

+ parameters are passed in, they are passed to the CGI program

+ via the QUERY_STRING environment variable.&lt;/p&gt;

+

+&lt;p&gt;For example, if this is the script &lt;code&gt;test.py&lt;/code&gt;:&lt;/p&gt;

+

+&lt;pre class="example"&gt;&lt;code&gt;import os

+print "Content-type: text/plain\n\n"

+print "PATH_INFO = %s" % os.environ['PATH_INFO']

+print "QUERY_STRING = %s" % os.environ['QUERY_STRING']&lt;/code&gt;&lt;/pre&gt;

+

+&lt;p&gt;And it handles the GET for this URI:&lt;/p&gt;

+

+&lt;pre class="example"&gt;&lt;code&gt;http://localhost/cgi-bin/test.py/reilly/12?id=234454&lt;/code&gt;&lt;/pre&gt;

+

+&lt;p&gt;It will display:&lt;/p&gt;

+

+&lt;pre class="example"&gt;&lt;code&gt;PATH_INFO = /reilly/12

+QUERY_STRING = id=234454

+&lt;/code&gt;&lt;/pre&gt;

+

+&lt;p&gt;Note how the piece of the path below test.py has been stripped off and made

+ available via &lt;code&gt;PATH_INFO&lt;/code&gt;, while the query parameters are

+ stored in the QUERY_STRING environment variable.

+&lt;/p&gt;

+

+&lt;p&gt;So HTTP, via the structure of a URI, gives you two distinct places

+ to store information, one in the path and the second in the query parameters.

+ This isn't even the full story, because if you are running Apache and have

+ the ability to use .htaccess files you can use

+ &lt;a href="http://httpd.apache.org/docs/mod/mod_rewrite.html"&gt;mod_rewrite&lt;/a&gt; and map URIs so that they appear

+ as paths but show up in the CGI as query parameters, but we won't cover that

+ now.

+&lt;/p&gt;

+

+

+ </description>

+

+ <dc:date>2003-08-03T01:34:49-05:00</dc:date>

+ <wfw:comment>http://wellformedweb.org/news/comments/SixPlusOne</wfw:comment>

+ <wfw:commentRss>http://wellformedweb.org/news/SixPlusOne?crss</wfw:commentRss>

+ </item>

+ </channel>

+</rss>

+

+

+

+<?xml version="1.0" encoding="utf-8"?>

+<rss xmlns:media="http://search.yahoo.com/mrss/" xmlns:dc="http://purl.org/dc/elements/1.1/" version="2.0">

+ <channel>

+ <title>The Guardian</title>

+ <link>https://www.theguardian.com/us</link>

+ <description>Latest US news, world news, sports, business, opinion, analysis and reviews from the Guardian, the world's leading liberal voice</description>

+ <copyright>Guardian News and Media Limited or its affiliated companies. All rights reserved. 2025</copyright>

+ <language>en-gb</language>

+ <!-- pubDate has been modified so we can assure dc:date is chosen. -->

+ <pubDate>Thu, 13 Mar 2020 10:38:39 GMT</pubDate>

+ <dc:date>2025-03-13T07:28:39Z</dc:date>

+ <dc:language>en-gb</dc:language>

+ <dc:rights>Guardian News and Media Limited or its affiliated companies. All rights reserved. 2025</dc:rights>

+ <image>

+ <title>The Guardian</title>

+ <url>https://assets.guim.co.uk/images/guardian-logo-rss.c45beb1bafa34b347ac333af2e6fe23f.png</url>

+ <link>https://www.theguardian.com</link>

+ </image>

+ <item>

+ <title>Judge orders Elon Musk and Doge to produce records about cost-cutting operations</title>

+ <link>https://www.theguardian.com/us-news/2025/mar/13/elon-musk-doge-court-ruling-records</link>

+ <description>&lt;p&gt;The documents would ultimately inform whether Musk has been operating unconstitutionally to the extent Doge’s activities should be halted&lt;/p&gt;&lt;p&gt;Elon Musk and his so-called “department of government efficiency”, or Doge, have been ordered by &lt;a href="https://www.theguardian.com/us-news/2025/mar/12/judge-blocks-trump-order-perkins-coie"&gt;a federal judge&lt;/a&gt; to turn over a wide array of records that would reveal the identities of staffers and internal records related to efforts to aggressively cut federal government spending and programs.&lt;/p&gt;&lt;p&gt;US district judge Tanya Chutkan’s order forces Musk to produce documents related to Doge’s activities &lt;a href="https://storage.courtlistener.com/recap/gov.uscourts.dcd.277463/gov.uscourts.dcd.277463.61.0_1.pdf"&gt;as part of a lawsuit&lt;/a&gt; brought by 14 Democratic state attorneys general that alleges Musk violated the constitution by wielding powers that only Senate-confirmed officials should possess.&lt;/p&gt; &lt;a href="https://www.theguardian.com/us-news/2025/mar/13/elon-musk-doge-court-ruling-records"&gt;Continue reading...&lt;/a&gt;</description>

+ <category domain="https://www.theguardian.com/us-news/trump-administration">Trump administration</category>

+ <category domain="https://www.theguardian.com/us-news/donaldtrump">Donald Trump</category>

+ <category domain="https://www.theguardian.com/law/law-us">Law (US)</category>

+ <category domain="https://www.theguardian.com/us-news/us-politics">US politics</category>

+ <category domain="https://www.theguardian.com/us-news/us-news">US news</category>

+ <!-- pubDate has been modified so we can assure dc:date is chosen. -->

+ <pubDate>Thu, 13 Mar 2020 10:38:39 GMT</pubDate>

+ <guid>https://www.theguardian.com/us-news/2025/mar/13/elon-musk-doge-court-ruling-records</guid>

+ <media:content width="140" url="https://i.guim.co.uk/img/media/8570e3094dfad7e268555097158aa8085221d48f/0_72_5221_3132/master/5221.jpg?width=140&amp;quality=85&amp;auto=format&amp;fit=max&amp;s=8677942b4c15d93e73d6bd18a13a12c0">

+ <media:credit scheme="urn:ebu">Photograph: Alex Brandon/AP</media:credit>

+ </media:content>

+ <media:content width="460" url="https://i.guim.co.uk/img/media/8570e3094dfad7e268555097158aa8085221d48f/0_72_5221_3132/master/5221.jpg?width=460&amp;quality=85&amp;auto=format&amp;fit=max&amp;s=bcd596d741b8c9e4be82c602e5105122">

+ <media:credit scheme="urn:ebu">Photograph: Alex Brandon/AP</media:credit>

+ </media:content>

+ <dc:creator>Hugo Lowell in Washington</dc:creator>

+ <dc:date>2025-03-13T05:22:00Z</dc:date>

+ </item>

+ </channel>

+</rss>

+

+<?xml version="1.0"?>

+<rdf:RDF

+ xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"

+ xmlns="http://purl.org/rss/1.0/"

+>

+

+ <channel rdf:about="http://www.xml.com/xml/news.rss">

+ <title>XML.com</title>

+ <link>http://xml.com/pub</link>

+

+ <description>

+ XML.com features a rich mix of information and services

+ for the XML community.

+ </description>

+

+ <image rdf:resource="http://xml.com/universal/images/xml_tiny.gif" />

+

+ <items>

+ <rdf:Seq>

+

+ <rdf:li resource="http://xml.com/pub/2000/08/09/xslt/xslt.html" />

+ <rdf:li resource="http://xml.com/pub/2000/08/09/rdfdb/index.html" />

+ </rdf:Seq>

+ </items>

+

+ <textinput rdf:resource="http://search.xml.com" />

+

+ </channel>

+ <image rdf:about="http://xml.com/universal/images/xml_tiny.gif">

+ <title>XML.com</title>

+ <link>http://www.xml.com</link>

+ <url>http://xml.com/universal/images/xml_tiny.gif</url>

+

+ </image>

+ <item rdf:about="http://xml.com/pub/2000/08/09/xslt/xslt.html">

+ <title>Processing Inclusions with XSLT</title>

+ <link>http://xml.com/pub/2000/08/09/xslt/xslt.html</link>

+ <description>

+

+ Processing document inclusions with general XML tools can be

+ problematic. This article proposes a way of preserving inclusion

+ information through SAX-based processing.

+ </description>

+ </item>

+ <item rdf:about="http://xml.com/pub/2000/08/09/rdfdb/index.html">

+ <title>Putting RDF to Work</title>

+ <link>http://xml.com/pub/2000/08/09/rdfdb/index.html</link>

+

+ <description>

+ Tool and API support for the Resource Description Framework

+ is slowly coming of age. Edd Dumbill takes a look at RDFDB,

+ one of the most exciting new RDF toolkits.

+ </description>

+ </item>

+

+ <textinput rdf:about="http://search.xml.com">

+ <title>Search XML.com</title>

+

+ <description>Search XML.com's XML collection</description>

+ <name>s</name>

+ <link>http://search.xml.com</link>

+ </textinput>

+

+</rdf:RDF>

+<?xml version="1.0" encoding="ISO-8859-1" ?>

+<rss version="0.91">

+ <channel>

+ <title>WriteTheWeb</title>

+ <link>http://writetheweb.com</link>

+ <description>News for web users that write back</description>

+ <language>en-us</language>

+ <copyright>Copyright 2000, WriteTheWeb team.</copyright>

+ <managingEditor>editor@writetheweb.com</managingEditor>

+ <webMaster>webmaster@writetheweb.com</webMaster>

+ <image>

+ <title>WriteTheWeb</title>

+ <url>http://writetheweb.com/images/mynetscape88.gif</url>

+ <link>http://writetheweb.com</link>

+ <width>88</width>

+ <height>31</height>

+ <description>News for web users that write back</description>

+ </image>

+ <item>

+ <title>Giving the world a pluggable Gnutella</title>

+ <link>http://writetheweb.com/read.php?item=24</link>

+ <description>WorldOS is a framework on which to build programs that work like Freenet or Gnutella -allowing distributed applications using peer-to-peer routing.</description>

+ </item>

+ <item>

+ <title>Syndication discussions hot up</title>

+ <link>http://writetheweb.com/read.php?item=23</link>

+ <description>After a period of dormancy, the Syndication mailing list has become active again, with contributions from leaders in traditional media and Web syndication.</description>

+ </item>

+ <item>

+ <title>Personal web server integrates file sharing and messaging</title>

+ <link>http://writetheweb.com/read.php?item=22</link>

+ <description>The Magi Project is an innovative project to create a combined personal web server and messaging system that enables the sharing and synchronization of information across desktop, laptop and palmtop devices.</description>

+ </item>

+ <item>

+ <title>Syndication and Metadata</title>

+ <link>http://writetheweb.com/read.php?item=21</link>

+ <description>RSS is probably the best known metadata format around. RDF is probably one of the least understood. In this essay, published on my O'Reilly Network weblog, I argue that the next generation of RSS should be based on RDF.</description>

+ </item>

+ <item>

+ <title>UK bloggers get organised</title>

+ <link>http://writetheweb.com/read.php?item=20</link>

+ <description>Looks like the weblogs scene is gathering pace beyond the shores of the US. There's now a UK-specific page on weblogs.com, and a mailing list at egroups.</description>

+ </item>

+ <item>

+ <title>Yournamehere.com more important than anything</title>

+ <link>http://writetheweb.com/read.php?item=19</link>

+ <description>Whatever you're publishing on the web, your site name is the most valuable asset you have, according to Carl Steadman.</description>

+ </item>

+ </channel>

+ </rss>

+#include <tqdatetime.h>

+#include <krfcdate.h>

+

+#include "image.h"

+#include "enclosure.h"

+template<typename ActualType, typename ExpectedType>

+static void assertEquals(const ActualType& actual, const ExpectedType& expected)

+{

+ if (actual != expected)

+ {

+ kdError() << "Assertion failed: actual == expected\n"

+ << " actual: " << actual << "\n"

+ << " expected: " << expected << endl;

+ tdeApp->exit(1);

+ }

+}

+

+static void checkRSS091(const Document& document)

+{

+ assertEquals(document.title(), "WriteTheWeb");

+ assertEquals(document.link().url(), "http://writetheweb.com");

+ assertEquals(document.description(), "News for web users that write back");

+ assertEquals(document.language(), Language::en_us);

+ assertEquals(document.copyright(), "Copyright 2000, WriteTheWeb team.");

+ assertEquals(document.managingEditor(), "editor@writetheweb.com");

+ assertEquals(document.webMaster(), "webmaster@writetheweb.com");

+

+ const Image* image = document.image();

+ if (!image)

+ {

+ kdError() << "Expected an <image> element to be found" << endl;

+ tdeApp->exit(1);

+ }

+

+ assertEquals(image->title(), "WriteTheWeb");

+ assertEquals(image->url().url(), "http://writetheweb.com/images/mynetscape88.gif");

+ assertEquals(image->link().url(), "http://writetheweb.com");

+ assertEquals(image->description(), "News for web users that write back");

+ assertEquals(image->width(), 88);

+ assertEquals(image->height(), 31);

+

+ assertEquals(document.articles().count(), 6);

+

+ Article article = document.articles().first();

+ assertEquals(article.title(), "Giving the world a pluggable Gnutella");

+ assertEquals(article.link().url(), "http://writetheweb.com/read.php?item=24");

+ assertEquals(article.description(), "WorldOS is a framework on which to build programs that work like Freenet or Gnutella -allowing distributed applications using peer-to-peer routing.");

+}

+

+static void checkWFW(const Document& document)

+{

+ assertEquals(document.link().url(), "http://wellformedweb.org/news/");

+ assertEquals(document.description(), "Exploring the limits of XML and HTTP");

+

+ assertEquals(document.articles().count(), 5);

+

+ Article article = document.articles().front();

+ assertEquals(article.title(), "Should you use Content Negotiation in your Web Services?");

+ assertEquals(article.commentsLink().url(), "http://bitworking.org/news/comments/WebServicesAndContentNegotiation");

+}

+

+static void checkDC(const Document& document)

+{

+ // librss will use dc:date if it is provided, otherwise it will use pubDate

+ assertEquals(document.link().url(), "https://www.theguardian.com/us");

+

+ TQDateTime expectedTime;

+ time_t time = KRFCDate::parseDateISO8601("2025-03-13T07:28:39Z");

+ expectedTime.setTime_t(time);

+ assertEquals(document.pubDate(), expectedTime);

+

+ assertEquals(document.articles().count(), 1);

+

+ Article article = document.articles().first();

+ time = KRFCDate::parseDateISO8601("2025-03-13T05:22:00Z");

+ expectedTime.setTime_t(time);

+ assertEquals(article.pubDate(), expectedTime);

+

+ assertEquals(article.author(), "Hugo Lowell in Washington");

+}

+

+static void checkRDF(const Document& document)

+{

+ assertEquals(document.title(), "XML.com");

+ assertEquals(document.link().url(), "http://xml.com/pub");

+

+ assertEquals(document.articles().count(), 2);

+

+ Article article = document.articles().first();

+

+ assertEquals(article.title(), "Processing Inclusions with XSLT");

+ assertEquals(article.link().url(), "http://xml.com/pub/2000/08/09/xslt/xslt.html");

+ assertEquals(article.guid(), "http://xml.com/pub/2000/08/09/xslt/xslt.html");

+ assertEquals(article.guidIsPermaLink(), false);

+}

+

+static void checkAtom10(const Document& document)

+{

+ assertEquals(document.title(), "dive into mark");

+ assertEquals(document.description(), "A <em>lot</em> of effort went into making this effortless");

+ kdWarning() << "Skipping check for Atom \"rights\" (Document::copyright) -- not implemented." << endl;

+ // assertEquals(document.copyright(), "Copyright (c) 2003, Mark Pilgrim");

+ assertEquals(document.language(), Language::en_us);

+

+ // 2005-07-31T12:29:29Z

+ // TQDateTime compTime;

+ // time_t time = KRFCDate::parseDateISO8601("2005-07-31T12:29:29Z");

+ // compTime.setTime_t(time);

+ // assertEquals(document.pubDate(), compTime);

+ kdWarning() << "Skipping check for Atom \"updated\" (Document::pubDate/lastBuildDate) -- not implemented." << endl;

+

+ assertEquals(document.link().url(), "http://example.org/");

+

+ assertEquals(document.articles().count(), 1);

+

+ Article article = document.articles().first();

+

+ assertEquals(article.title(), "Atom draft-07 snapshot");

+ assertEquals(article.link().url(), "http://example.org/2005/04/02/atom");

+

+ if (article.description().isNull())

+ {

+ kdError() << "Empty Atom article description." << endl;

+ tdeApp->exit(1);

+ }

+

+ // Enclosure enclosure = article.enclosure();

+ // assertEquals(enclosure.url(), "http://example.org/audio/ph34r_my_podcast.mp3");

+ // assertEquals(enclosure.length(), 1337);

+ // assertEquals(enclosure.type(), "audio/mpeg");

+ kdWarning() << "Skipping check for Atom \"enclosure\" links -- not implemented." << endl;

+

+ assertEquals(article.guid(), "tag:example.org,2003:3.2397");

+

+ // 2005-07-31T12:29:29Z

+ // Need a little workaround since librss converts the timestamp to local time.

+ // NOTE: Atom provides both 'published' and 'updated'; librss uses 'updated'.

+ TQDateTime articlePublishedDate;

+ time_t publishedTime = KRFCDate::parseDateISO8601("2005-07-31T12:29:29Z");

+ articlePublishedDate.setTime_t(publishedTime);

+ assertEquals(article.pubDate(), articlePublishedDate);

+

+ assertEquals(article.author(), "<a href=\"mailto:f8dy@example.com\">Mark Pilgrim</a>");

+}

+ if (status != Success)

+ {

+ kdError() << "Failed to load Document " << loader->errorCode() << endl;

+ tdeApp->exit(1);

+ }

+

+ switch (doc.version())

+ case RSS::v0_91:

+ checkRSS091(doc);

+ break;

+ }

+ case RSS::v2_0:

+ {

+ if (doc.title() == "The Well-Formed Web")

+ {

+ checkWFW(doc);

+ break;

+ }

+ else if (doc.title() == "The Guardian")

+ {

+ checkDC(doc);

+ break;

+ }

+ else if (doc.title() == "XML.com")

+ {

+ checkRDF(doc);

+ break;

+ }

+ kdError() << "Unknown RSS 2.0 document '" << doc.title() << "'" << endl;

+ tqApp->exit(1);

+ }

+ case RSS::vAtom_1_0:

+ {

+ checkAtom10(doc);

+ break;

+ }

+ default:

+ {

+ break;

+ TDECmdLineArgs::addCmdLineOptions( options );

+ TDEApplication app(false, false);