Merge lp:~igraph/igraph/0.5-sf into lp:igraph/0.5-main

[Gábor Csárdi]

[Gábor Csárdi (gabor.csardi)]

review: Approve

=== added file 'doc/homepage/bugs.html.in'
--- doc/homepage/bugs.html.in	1970-01-01 00:00:00 +0000
+++ doc/homepage/bugs.html.in	2009-03-07 23:41:52 +0000
@@ -0,0 +1,18 @@
+<h2>Bug reports, questions, comments</h2>
+
+<h3>Reporting bugs at Launchpad</h3>
+
+<p>We suggest to report igraph bugs on the Launchpad website by
+  clicking on the first button in the menu on the bottom of the page. This
+  allows you to follow up on your bug report, e.g. get an email
+  notification when it is fixed. Please check the
+  <a href="https://bugs.launchpad.net/igraph/+bugs">list of bugs</a>
+  before clicking on the button below to report a new bug.
+</p>
+
+<h3>Sending bug reports in email</h3>
+
+If you prefer not to use Launchpad, you can report bugs on
+the <code>igraph-help</code> mailing list. You can find more
+information on <code>igraph-help</code> 
+<a href="support.html">here.</a> 

=== modified file 'doc/homepage/documentation.html.in'
--- doc/homepage/documentation.html.in	2008-02-14 10:57:48 +0000
+++ doc/homepage/documentation.html.in	2009-03-01 19:20:34 +0000
@@ -84,9 +84,9 @@
   <div>The original XML DocBook format of the
   manual can be obtained by downloading the latest igraph
   development version from
- <a href="http://cneurocvs.rmki.kfki.hu/arch/[e-mail]--2004-public"
-    onClick="javascript:urchinTracker ('/archrepo'); ">
-  our repository</a>.</div>
+ <a href="https://launchpad.net/igraph"
+    onClick="javascript:urchinTracker ('/launchpad'); ">
+  Launchpad</a>.</div>
   </div>
 </li>
 
@@ -101,4 +101,16 @@
   
 </li>
 
+<li class="download download-wiki">
+  <span class="name">igraph wiki at wikidot (external site)</span>
+  <span class="comment">&mdash; a collaborative effort of the community</span>
+  <ul class="download-links">
+    <li class="download-external">
+      <a href="http://igraph.wikidot.com">Browse online</a>
+    </li>
+  </ul>
+  
+</li>
+
+
 </ul>

=== modified file 'doc/homepage/download.html.in'
--- doc/homepage/download.html.in	2008-06-26 12:49:44 +0000
+++ doc/homepage/download.html.in	2009-03-01 19:20:34 +0000
@@ -13,19 +13,19 @@
         please try this before downloading from here.</span><br/>
     </li>
     <li class="download-windows">
-       <a href="download/igraph_${VERSION}.zip"
+       <a href="http://switch.dl.sourceforge.net/sourceforge/igraph/igraph_${VERSION}.zip"
           onClick="javascript:urchinTracker ('/downloads/rwindowsbinary'); ">
           Windows binary</a> 
     </li>
     <li class="download-osx">
-       <a href="download/igraph_${VERSION}.tgz"
+       <a href="http://switch.dl.sourceforge.net/sourceforge/igraph/igraph_${VERSION}.tgz"
           onClick="javascript:urchinTracker ('/downloads/rosxbinary'); "> 
           Mac OSX universal binary</a>
     </li>
     <li class="download-source">
-       <a href="download/igraph_${VERSION}.tar.gz"
+       <a href="http://switch.dl.sourceforge.net/sourceforge/igraph/igraph_${VERSION}.tar.gz"
        onClick="javascript:urchinTracker ('/downloads/rsource'); "> 
-        Source package (for Linux and similar)</a><br/>
+        Source package (for Linux and similar)</a>
     </li>
   </ul>
 </li>
@@ -58,7 +58,7 @@
     <li class="download-external">
        <a href="http://python.org/pypi/python-igraph" 
           onClick="javascript:urchinTracker ('/outgoing/pythoncheeseshop'); "> 
-          Python Package Index page</a>  
+          Python Package Index page</a>
     </li>
   </ul>
 </li>
@@ -74,7 +74,7 @@
     <li class="download-external">
        <a href="http://rubyforge.org/projects/igraph" 
           onClick="javascript:urchinTracker ('/outgoing/rubyforge'); "> 
- 	 External homepage</a> 
+ 	 External homepage</a>
     </li>
   </ul>
 </li>
@@ -86,10 +86,24 @@
   <ul class="download-links">
     <li class="download-source">
        <a onClick="javascript:urchinTracker ('/downloads/library'); " 
- 	 href="download/igraph-${VERSION}.tar.gz">Source code</a>
-    </li>
-  </ul>
-</li>
+ 	 href="http://switch.dl.sourceforge.net/sourceforge/igraph/igraph-${VERSION}.tar.gz">Source code</a>
+    </li>
+  </ul>
+</li>
+
+<li class="download download-sf">
+  <span class="name">Browse all igraph releases</span>
+  <span class="comment">&mdash; All file releases at
+  SourceForge</span>
+  <ul class="download-links">
+    <li class="download-external">
+       <a onClick="javascript:urchinTracker ('/downloads/sourceforge'); " 
+ 	 href="https://sourceforge.net/project/showfiles.php?group_id=160289">Go to SourceForge</a>
+    </li>
+  </ul>
+</li>
+  
+  
 
 </ul>
 
@@ -121,10 +135,6 @@
 <a name="dev"></a><h3>Obtaining the development version</h3>
 
 <p>You can get the latest development version of igraph (including the
-C core and the wrappers for R and Python) with the <code>tla</code> arch
-revision control system from the following URL:
- <a href="http://cneurocvs.rmki.kfki.hu/arch/[e-mail]--2004-public"
-    onClick="javascript:urchinTracker ('/archrepo'); "> 
-<a href="http://cneurocvs.rmki.kfki.hu/arch/[e-mail]--2004-public">
-<code>http://cneurocvs.rmki.kfki.hu/arch/[e-mail]--2004-public</code>.</a>
+C core and the wrappers for R and Python)
+  from <a href="https://launchpad.net/igraph">Launchpad</a>.
 </p>

=== added file 'doc/homepage/features.html.in'
--- doc/homepage/features.html.in	1970-01-01 00:00:00 +0000
+++ doc/homepage/features.html.in	2009-03-08 09:52:02 +0000
@@ -0,0 +1,36 @@
+<h2>Features</h2>
+
+<p>Here are some features of <b>igraph</b>, a subset of the functionality,
+see <i>The igraph reference manual</i> under <a
+href="documentation.html">Documentation</a> for more details.</p>
+
+<ul>
+<li><b>igraph</b> contains functions for generating regular and random graphs
+according to many algorithms and models from the network theory
+literature.</li>
+<li><b>igraph</b> provides routines for manipulating graphs, adding and removing
+    edges and vertices.</li>
+<li>You can assign numeric or textual attribute to the vertices or edges 
+    of the graph, like edge weights or textual vertex ids.</li>
+<li>A rich set of functions calculating various structural properties,
+    eg. betweenness, PageRank, k-cores, network motifs, 
+    etc. are also included.</li>
+<li>Force based layout generators for small and large graphs</li>
+<li>The R package and the Python module can visualize graphs many ways, 
+    in 2D and 3D, interactively or non-interactively.</li>
+<li><b>igraph</b> provides data types for implementing your own algorithm in 
+    C, R, Python or Ruby.</li>
+<li>Community structure detection algorithms using many recently developed
+    heuristics.</li>
+<li><b>igraph</b> can read and write many file formats, e.g., GraphML, GML or Pajek.
+    </li>
+<li><b>igraph</b> contains efficient functions for deciding graph isomorphism and
+    subgraph isomorphism</li>
+<li>It also contains an implementation of the push/relabel algorithm
+     for calculating maximum network flow, and this way minimum cuts,
+     vertex and edge connectivity.</li>
+<li><b>igraph</b> is well documented both for users and developers.</li>
+<li><b>igraph</b> is open source and distributed under GNU GPL.</li>
+</ul>
+
+<div class="back"><a href="index.html">&laquo; Back to main page</a></div>

=== modified file 'doc/homepage/generate.py'
--- doc/homepage/generate.py	2007-11-01 15:20:16 +0000
+++ doc/homepage/generate.py	2009-03-08 03:10:40 +0000
@@ -73,6 +73,7 @@
     f = open(file[:-3], "w")
     content = open(file).read()
     tokens["CONTENT"] = string.Template(content).safe_substitute(tokens)
+    tokens["PAGENAME"] = file[:-8]
     for tmpl in template:
 	print >>f, tmpl.safe_substitute(tokens),
 	

=== modified file 'doc/homepage/images/header_blue.png'
Binary files doc/homepage/images/header_blue.png	2007-10-25 15:09:54 +0000 and doc/homepage/images/header_blue.png	2009-03-02 09:02:13 +0000 differ
=== added file 'doc/homepage/images/icon_bug.png'
Binary files doc/homepage/images/icon_bug.png	1970-01-01 00:00:00 +0000 and doc/homepage/images/icon_bug.png	2009-03-01 18:56:34 +0000 differ
=== added file 'doc/homepage/images/icon_sf.png'
Binary files doc/homepage/images/icon_sf.png	1970-01-01 00:00:00 +0000 and doc/homepage/images/icon_sf.png	2009-03-01 17:58:12 +0000 differ
=== added file 'doc/homepage/images/icon_wiki.png'
Binary files doc/homepage/images/icon_wiki.png	1970-01-01 00:00:00 +0000 and doc/homepage/images/icon_wiki.png	2009-03-01 16:31:05 +0000 differ
=== added file 'doc/homepage/images/igraph2.png'
Binary files doc/homepage/images/igraph2.png	1970-01-01 00:00:00 +0000 and doc/homepage/images/igraph2.png	2009-03-01 18:56:34 +0000 differ
=== added file 'doc/homepage/images/igraph3.png'
Binary files doc/homepage/images/igraph3.png	1970-01-01 00:00:00 +0000 and doc/homepage/images/igraph3.png	2009-03-01 14:40:26 +0000 differ
=== modified file 'doc/homepage/index.html.in'
--- doc/homepage/index.html.in	2008-02-06 15:59:48 +0000
+++ doc/homepage/index.html.in	2009-03-08 09:52:02 +0000
@@ -1,174 +1,93 @@
-<h2>Introduction</h2>
-
-<img align="right" src="images/screenshots/fastgreedy.png" alt=""/>
+<table class="intro"><tr><td>
+<h2 class="th">Introduction</h2>
+
+<hr/>
+
 <p><b>igraph</b> is a free software package for creating and manipulating undirected and 
 directed graphs. It includes implementations for classic graph theory
 problems like minimum spanning trees and network flow, and also
 implements algorithms for some recent network analysis methods, like 
 community structure search.</p>
-<div class="more"><a href="#introduction2">Read more &raquo;</a></div>
-
-<h2>Features</h2>
+<div class="more"><a href="introduction.html">Read more &raquo;</a></div>
+
+</td><td>
+<h2 class="th">Features</h2>
+
+<hr/>
 
 <p><b>igraph</b> contains functions for generating regular and random graphs,
 manipulating graphs, assigning attributes to vertices and edges. It can
-calculate various structural properties, includes heuristics for 
-community structure detection, supports many file formats.</p>
-<div class="more"><a href="#features">Read more &raquo;</a></div>
-
-<h2>Requirements</h2>
-
-<p>The software you need for installing <b>igraph</b> depends on
+calculate various structural properties, graph isomorphism, 
+includes heuristics for community structure detection, supports many
+  file formats. The R and Python interfaces support visualization.</p> 
+<div class="more"><a href="features.html">Read more &raquo;</a></div>
+
+</td><td>
+<h2 class="th">Requirements</h2>
+
+<hr/>
+
+<p>
+igraph runs on most modern machines and operating systems, and it is
+tested on MS Windows, Mac OSX and various Linux versions.
+</p>
+
+<p>
+The software you need for installing <b>igraph</b> depends on
 whether you want to use the C library, the R package or the Python
-extension.</p>
-<div class="more"><a href="#requirements">Read more &raquo;</a></div>
-
-<hr/>
-
-<a name="introduction"></a>
-<h2>Introduction</h2>
-
-<p><b>igraph</b> is a free software package for creating and manipulating undirected and 
-directed graphs. It includes implementations for classic graph theory
-problems like minimum spanning trees and network flow, and also
-implements algorithms for some recent network analysis methods, like 
-community structure search.</p>
-
-<a name="introduction2"></a>
-<p>The efficient implementation of <b>igraph</b> allows it to handle graphs
-with millions of vertices and edges. The rule of thumb is that if your graph
-fits into the physical memory then <b>igraph</b> can handle it.</p>
-
-<p><b>igraph</b> can be installed in several forms:</p>
-
-<ul>
-<li><b>igraph</b> as a <i>C library</i> is useful if you want to use
-    it in your C/C++ projects, or want to implement your own network analysis
-    or model in C/C++ using the data structures and functions <b>igraph</b> provides.
-    </li>
-<li><b>igraph</b> as an <i>R package</i>. You can use <b>igraph</b> as an extension 
-    package to <a href="http://www.r-project.org">The GNU R project for
-    Statistical Computing.</a> The flexibility of the R language and its 
-    richness in statistical methods add a great deal of productivity to 
-    <b>igraph</b>, with a very small speed penalty.</li>
-<li><b>igraph</b> as a <a href="http://www.python.org">Python</a> extension module.
-    This way you can combine <b>igraph</b> with the huge set of Python functions
-    and modules available, and the ease of the Python language,
-    with a small speed penalty.</li>
-<li><b>igraph</b> as a <a href="http://www.ruby-lang.org">Ruby</a> extension. 
-    If you like the Ruby language, then this might be the right choice for you.
-    </li>
-</ul>
-
-<p>Every form of <b>igraph</b> contain the same code at the very heart, written in ANSI C.</p>
-
-<p>Please note that the ways of installing <b>igraph</b> depends on which its 
-forms you actually want to use. Eg. for using <b>igraph</b> as an R package,
-you don't need to download the C library at all. See the <a
-href="download.html">download page</a> for details.</p>
-
-<hr/>
-
-<a name="features"></a>
-<h2>Features</h2>
-
-<p>Here are some features of <b>igraph</b>, a subset of the functionality,
-see <i>The igraph reference manual</i> under <a
-href="documentation.html">Documentation</a> for more details.</p>
-
-<ul>
-<li><b>igraph</b> contains functions for generating regular and random graphs
-according to many algorithms and models from the network theory
-literature.</li>
-<li><b>igraph</b> provides routines for manipulating graphs, adding and removing
-    edges and vertices.</li>
-<li>You can assign numeric or textual attribute to the vertices or edges 
-    of the graph, like edge weights or textual vertex ids.</li>
-<li>A rich set of functions calculating various structural properties,
-    eg. betweenness, PageRank, k-cores, network motifs, 
-    etc. are also included.</li>
-<li>Force based layout generators for small and large graphs</li>
-<li>The R package and the Python module can visualize graphs many ways, 
-    in 2D and 3D, interactively or non-interactively.</li>
-<li><b>igraph</b> provides data types for implementing your own algorithm in 
-    C, R, Python or Ruby.</li>
-<li>Community structure detection algorithms using many recently developed
-    heuristics.</li>
-<li><b>igraph</b> can read and write many file formats, e.g., GraphML, GML or Pajek.
-    </li>
-<li><b>igraph</b> contains efficient functions for deciding graph isomorphism and
-    subgraph isomorphism</li>
-<li>It also contains an implementation of the push/relabel algorithm
-     for calculating maximum network flow, and this way minimum cuts,
-     vertex and edge connectivity.</li>
-<li><b>igraph</b> is well documented both for users and developers.</li>
-<li><b>igraph</b> is open source and distributed under GNU GPL.</li>
-</ul>
-
-<hr/>
-
-<a name="requirements"></a>
-<h2>Requirements</h2>
-
-<h3>The C library</h3>
-    <p>For using the <i><b>igraph</b> C library</i> only a fairly recent C
-    and C++ library is needed. For supporting the GraphML format
-    you'll need the <a href="http://xmlsoft.org"><code>libxml2</code>
-    library</a>.</p>
-
-    <p>For compiling the <i><b>igraph</b> C library</i> from source you'll
-    need a fairly modern C and C++ compiler and some standard UNIX
-    tools like <code>make</code>, <code>chmod</code>, <code>touch</code>, etc.</p>
-
-    <p>Most often we use the <a href="http://gcc.gnu.org">GNU Compiler
-    Collection</a> for compiling. Theoretically it is possible to compile
-    <b>igraph</b> using the Microsoft Visual C Compiler as well, but we
-    recommend the <a href="http://www.cygwin.com">Cygwin</a> or
-    <a href="http://www.mingw.org">MinGW</a> environments for compiling
-    <b>igraph</b> under Windows.</p>
-
-<h3>The GNU R package</h3>
-    <p>For using the <i><b>igraph</b> R package</i> you obviously need 
-    GNU R, a recent version like 2.6.0 is recommended, since earlier
-    versions contain bugs which affect <b>igraph</b>. If you would like to
-    compile the R package from source (this is the usual way for Linux
-    systems), you'll need a C and C++ compiler and optionally the
-    <a href="http://xmlsoft.org"><code>libxml2</code> library</a>.</p>
-
-    <p>For installing the <i><b>igraph</b> R package</i> on Windows, you 
-    don't need anything else, just GNU R and the binary <b>igraph</b> R
-    package of course</p>
-
-<h3>The Python extension module</h3>
-
-    <p>For installing the <i>Python extension module</i>, you'll
-    need Python version 2.4 or later. Binary versions of the module
-    are available for Python 2.4 and Python 2.5 on the Windows platform,
-    so you don't have to compile anything in this case. OS X Leopard
-	users can download an installer as well. If you are using
-    Linux or Mac OS X Tiger, you'll have to compile the extension by yourself.
-    Compilation requires a recent C compiler (e.g. <code>gcc</code>, which
-    is usually available as a separate package in Linux and as part of
-    <a href="http://developer.apple.com/tools/xcode/">XCode</a> on Mac
-    OS X. You'll also need the compiled form of the <b>igraph</b> C
-	core, as the Python interface will link to that during compilation.</p>
-    <p>If you have the <a href="http://peak.telecommunity.com/DevCenter/EasyInstall">EasyInstall</a>
-    Python script installed, you can simply type <code>easy_install igraph</code>
-    to download, compile and install <b>igraph</b> as a Python Egg. This
-	method assumes that you installed the C core somewhere in the
-	default include and library path of your system.</p>
-
-<h3>The Ruby extension</h3>
-    <p>For installing the <i>Ruby extension</i> please consult 
-    <a href="http://rubyforge.org/projects/igraph/">the homepage of
-    this extension</a>.</p>
-
-<h3>Compiling the development version</h3>
-    <p>For compiling the development version of <b>igraph</b>, you'll need
-    quite a large set of tools: <code>autoconf</code>, <code>automake</code>,
-    GNU <code>bison</code> version 1.35 or newer, GNU <code>make</code>,
-    maybe more. For compiling the documentation you'll need even more tools:
-    Python, Docbook schemas and tools, <code>xmlto</code>, <code>makeinfo</code>,
-    <code>patch</code>, <code>docbook2x</code>, maybe more. We're sure you
-    know how to get these if you want to compile the development version :)</p>
+extension; and may vary depending on your platform.</p>
+
+<div class="more"><a href="requirements.html">Read more &raquo;</a></div>
+</td></tr></table>
+
+<hr/>
+
+<div class="feed">
+<script src="http://feeds2.feedburner.com/IgraphAnnouncements?format=sigpro"
+	type="text/javascript" ></script><noscript><p>Subscribe to RSS
+    headline updates
+    from: <a href="http://feeds2.feedburner.com/IgraphAnnouncements"></a><br/>Powered
+    by FeedBurner</p> </noscript> 
+<p class="comment">View <a href="https://launchpad.net/igraph/+announcements">more
+    announcements.</a></p>
+</div>
+
+<div class="feed">
+<script src="http://feeds2.feedburner.com/BugsInIgraph?format=sigpro&nItems=5"
+	type="text/javascript" ></script><noscript><p>Subscribe to RSS
+    headline updates
+    from: <a href="http://feeds2.feedburner.com/BugsInIgraph"></a><br/>Powered
+    by FeedBurner</p> </noscript> 
+<p class="comment">View <a href="https://launchpad.net/igraph/+bugs">more
+    bugs.</a></p>
+</div>
+
+<div class="feed">
+<script src="http://feeds2.feedburner.com/LatestRevisionsForBranchigraph/igraph/06-main?format=sigpro&nItems=5"
+	type="text/javascript" ></script><noscript><p>Subscribe to RSS
+    headline updates
+    from: <a href="http://feeds2.feedburner.com/LatestRevisionsForBranchigraph/igraph/06-main"></a><br/>Powered
+    by FeedBurner</p> </noscript>
+<p class="comment"><a href="https://code.launchpad.net/~igraph/igraph/0.6-main">Browse
+    commits.</a></p>
+</div>
+
+<div class="feed">
+<script src="http://feeds2.feedburner.com/LatestRevisionsForBranchigraph/igraph/05-main?format=sigpro&nItems=5"
+	type="text/javascript" ></script><noscript><p>Subscribe to RSS
+    headline updates
+    from: <a href="http://feeds2.feedburner.com/LatestRevisionsForBranchigraph/igraph/05-main"></a><br/>Powered
+    by FeedBurner</p> </noscript> 
+<p class="comment"><a href="https://code.launchpad.net/~igraph/igraph/0.5-main">Browse
+    commits.</a></p>
+</div>
+
+<div class="feed">
+<script src="http://feeds2.feedburner.com/RecentPageChangesFromSiteigraphaWikidotSite?format=sigpro&nItems=5"
+	type="text/javascript" ></script><noscript><p>Subscribe to RSS
+    headline updates
+    from: <a href="http://feeds2.feedburner.com/RecentPageChangesFromSiteigraphaWikidotSite"></a><br/>Powered
+    by FeedBurner</p> </noscript>
+<p class="comment">See <a href="http://igraph.wikidot.com/system:recent-changes">more changes.</a></p>
+</div>
 

=== added file 'doc/homepage/introduction.html.in'
--- doc/homepage/introduction.html.in	1970-01-01 00:00:00 +0000
+++ doc/homepage/introduction.html.in	2009-03-08 09:52:02 +0000
@@ -0,0 +1,42 @@
+<h2>Introduction</h2>
+
+<p><b>igraph</b> is a free software package for creating and manipulating undirected and 
+directed graphs. It includes implementations for classic graph theory
+problems like minimum spanning trees and network flow, and also
+implements algorithms for some recent network analysis methods, like 
+community structure search.</p>
+
+<a name="introduction2"></a>
+<p>The efficient implementation of <b>igraph</b> allows it to handle graphs
+with millions of vertices and edges. The rule of thumb is that if your graph
+fits into the physical memory then <b>igraph</b> can handle it.</p>
+
+<p><b>igraph</b> can be installed in several forms:</p>
+
+<ul>
+<li><b>igraph</b> as a <i>C library</i> is useful if you want to use
+    it in your C/C++ projects, or want to implement your own network analysis
+    or model in C/C++ using the data structures and functions <b>igraph</b> provides.
+    </li>
+<li><b>igraph</b> as an <i>R package</i>. You can use <b>igraph</b> as an extension 
+    package to <a href="http://www.r-project.org">The GNU R project for
+    Statistical Computing.</a> The flexibility of the R language and its 
+    richness in statistical methods add a great deal of productivity to 
+    <b>igraph</b>, with a very small speed penalty.</li>
+<li><b>igraph</b> as a <a href="http://www.python.org">Python</a> extension module.
+    This way you can combine <b>igraph</b> with the huge set of Python functions
+    and modules available, and the ease of the Python language,
+    with a small speed penalty.</li>
+<li><b>igraph</b> as a <a href="http://www.ruby-lang.org">Ruby</a> extension. 
+    If you like the Ruby language, then this might be the right choice for you.
+    </li>
+</ul>
+
+<p>Every form of <b>igraph</b> contain the same code at the very heart, written in ANSI C.</p>
+
+<p>Please note that the ways of installing <b>igraph</b> depends on which its 
+forms you actually want to use. Eg. for using <b>igraph</b> as an R package,
+you don't need to download the C library at all. See the <a
+href="download.html">download page</a> for details.</p>
+
+<div class="back"><a href="index.html">&laquo; Back to main page</a></div>

=== modified file 'doc/homepage/license.html.in'
--- doc/homepage/license.html.in	2008-02-14 17:38:13 +0000
+++ doc/homepage/license.html.in	2009-03-01 18:56:34 +0000
@@ -1,8 +1,9 @@
 <h2>License</h2>
 
-<p>igraph library. Copyright (C) 2003-2008 Gábor Csárdi and Tamás Nepusz
-&lt;[e-mail]&gt; MTA RMKI, Konkoly-Thege Miklós st. 29-33.,
-Budapest 1121, Hungary.</p>
+<p>igraph library. Copyright (C) 2003-2009 Gábor Csárdi
+  &lt;[e-mail]&gt; and Tamás Nepusz
+  &lt;[e-mail]&gt; MTA RMKI, Konkoly-Thege Miklós
+  st. 29-33., Budapest 1121, Hungary.</p>
 
 <p> This program is free software; you can redistribute it and/or modify it
 under the terms of the GNU General Public License as published by the Free

=== added file 'doc/homepage/pngfix.js'
--- doc/homepage/pngfix.js	1970-01-01 00:00:00 +0000
+++ doc/homepage/pngfix.js	2009-03-01 23:45:06 +0000
@@ -0,0 +1,39 @@
+/*
+ 
+Correctly handle PNG transparency in Win IE 5.5 & 6.
+http://homepage.ntlworld.com/bobosola. Updated 18-Jan-2006.
+
+Use in <HEAD> with DEFER keyword wrapped in conditional comments:
+<!--[if lt IE 7]>
+<script defer type="text/javascript" src="pngfix.js"></script>
+<![endif]-->
+
+*/
+
+var arVersion = navigator.appVersion.split("MSIE")
+var version = parseFloat(arVersion[1])
+
+if ((version >= 5.5) && (document.body.filters)) 
+{
+   for(var i=0; i<document.images.length; i++)
+   {
+      var img = document.images[i]
+      var imgName = img.src.toUpperCase()
+      if (imgName.substring(imgName.length-3, imgName.length) == "PNG")
+      {
+         var imgID = (img.id) ? "id='" + img.id + "' " : ""
+         var imgClass = (img.className) ? "class='" + img.className + "' " : ""
+         var imgTitle = (img.title) ? "title='" + img.title + "' " : "title='" + img.alt + "' "
+         var imgStyle = "display:inline-block;" + img.style.cssText 
+         if (img.align == "left") imgStyle = "float:left;" + imgStyle
+         if (img.align == "right") imgStyle = "float:right;" + imgStyle
+         if (img.parentElement.href) imgStyle = "cursor:hand;" + imgStyle
+         var strNewHTML = "<span " + imgID + imgClass + imgTitle
+         + " style=\"" + "width:" + img.width + "px; height:" + img.height + "px;" + imgStyle + ";"
+         + "filter:progid:DXImageTransform.Microsoft.AlphaImageLoader"
+         + "(src=\'" + img.src + "\', sizingMethod='scale');\"></span>" 
+         img.outerHTML = strNewHTML
+         i = i-1
+      }
+   }
+}

=== added file 'doc/homepage/requirements.html.in'
--- doc/homepage/requirements.html.in	1970-01-01 00:00:00 +0000
+++ doc/homepage/requirements.html.in	2009-03-08 09:52:02 +0000
@@ -0,0 +1,65 @@
+<h2>Requirements</h2>
+
+<h3>The C library</h3>
+    <p>For using the <i><b>igraph</b> C library</i> only a fairly recent C
+    and C++ library is needed. For supporting the GraphML format
+    you'll need the <a href="http://xmlsoft.org"><code>libxml2</code>
+    library</a>.</p>
+
+    <p>For compiling the <i><b>igraph</b> C library</i> from source you'll
+    need a fairly modern C and C++ compiler and some standard UNIX
+    tools like <code>make</code>, <code>chmod</code>, <code>touch</code>, etc.</p>
+
+    <p>Most often we use the <a href="http://gcc.gnu.org">GNU Compiler
+    Collection</a> for compiling. Theoretically it is possible to compile
+    <b>igraph</b> using the Microsoft Visual C Compiler as well, but we
+    recommend the <a href="http://www.cygwin.com">Cygwin</a> or
+    <a href="http://www.mingw.org">MinGW</a> environments for compiling
+    <b>igraph</b> under Windows.</p>
+
+<h3>The GNU R package</h3>
+    <p>For using the <i><b>igraph</b> R package</i> you obviously need 
+    GNU R, a recent version like 2.6.0 is recommended, since earlier
+    versions contain bugs which affect <b>igraph</b>. If you would like to
+    compile the R package from source (this is the usual way for Linux
+    systems), you'll need a C and C++ compiler and optionally the
+    <a href="http://xmlsoft.org"><code>libxml2</code> library</a>.</p>
+
+    <p>For installing the <i><b>igraph</b> R package</i> on Windows, you 
+    don't need anything else, just GNU R and the binary <b>igraph</b> R
+    package of course</p>
+
+<h3>The Python extension module</h3>
+
+    <p>For installing the <i>Python extension module</i>, you'll
+    need Python version 2.4 or later. Binary versions of the module
+    are available for Python 2.4 and Python 2.5 on the Windows platform,
+    so you don't have to compile anything in this case. OS X Leopard
+	users can download an installer as well. If you are using
+    Linux or Mac OS X Tiger, you'll have to compile the extension by yourself.
+    Compilation requires a recent C compiler (e.g. <code>gcc</code>, which
+    is usually available as a separate package in Linux and as part of
+    <a href="http://developer.apple.com/tools/xcode/">XCode</a> on Mac
+    OS X. You'll also need the compiled form of the <b>igraph</b> C
+	core, as the Python interface will link to that during compilation.</p>
+    <p>If you have the <a href="http://peak.telecommunity.com/DevCenter/EasyInstall">EasyInstall</a>
+    Python script installed, you can simply type <code>easy_install igraph</code>
+    to download, compile and install <b>igraph</b> as a Python Egg. This
+	method assumes that you installed the C core somewhere in the
+	default include and library path of your system.</p>
+
+<h3>The Ruby extension</h3>
+    <p>For installing the <i>Ruby extension</i> please consult 
+    <a href="http://rubyforge.org/projects/igraph/">the homepage of
+    this extension</a>.</p>
+
+<h3>Compiling the development version</h3>
+    <p>For compiling the development version of <b>igraph</b>, you'll need
+    quite a large set of tools: <code>autoconf</code>, <code>automake</code>,
+    GNU <code>bison</code> version 1.35 or newer, GNU <code>make</code>,
+    maybe more. For compiling the documentation you'll need even more tools:
+    Python, Docbook schemas and tools, <code>xmlto</code>, <code>makeinfo</code>,
+    <code>patch</code>, <code>docbook2x</code>, maybe more. We're sure you
+    know how to get these if you want to compile the development version :)</p>
+
+<div class="back"><a href="index.html">&laquo; Back to main page</a></div>

=== modified file 'doc/homepage/style.css'
--- doc/homepage/style.css	2008-02-12 17:49:44 +0000
+++ doc/homepage/style.css	2009-03-08 11:22:36 +0000
@@ -8,17 +8,26 @@
 h1 {
     color: #fff;
     margin: 0;
-    padding: 7px 0 7px 15px;
+    height: 40px;
+    line-height: 40px;
     text-shadow: 0px 1px 2px #000;
-    background: #005fd7 url(images/header_blue.png) repeat-x;
+    background: #1872ce url(images/header_blue.png) repeat-x;
+    border-top: 1px solid #1872ce;
     border-bottom: 1px solid #1c477f;
     font-size: large;
+    padding-left: 10px;
 }
 h2 {
-    font-size: 1.2em;
+    font-size: 1.5em;
+    text-indent: -40px;
+}
+h2.th {
+    font-size: 1.5em;
+    text-indent: 0px;
 }
 h3 {
     font-size: 1em;
+    text-indent: -20px;
 }
 h4 {
     font-size: 0.8em;
@@ -37,13 +46,26 @@
 img.float_left { float: left }
 pre.condensed { font-size: 0.8em; line-height: 1.5em; }
 
-.main {
-    padding: 7px 15px;
+.igraphlogo {
+    float: right;
+    padding-left: 40px;
+    padding-right: 40px;
+    padding-top:30px;
+}
+
+div.main {
+    max-width:900px;
+    padding-left: 50px;
+    padding-bottom: 50px;
+    margin-right: 0;
 }
 .more {
     text-align: right;
     margin-top: -1em;
 }
+.back {
+    text-align: left;
+}
 
 ul.no-bullet {
   list-style-type: none;
@@ -80,6 +102,9 @@
 li.download-c {
   background: url(images/icon_c.png) no-repeat 0px 0px;
 }
+li.download-sf {
+  background: url(images/icon_sf.png) no-repeat 0px 0px;
+}
 li.download-r {
   background: url(images/icon_r.png) no-repeat 0px 0px;
 }
@@ -92,6 +117,9 @@
 li.download-doc {
   background: url(images/icon_documentation.png) no-repeat 0px 0px;
 }
+li.download-wiki {
+  background: url(images/icon_wiki.png) no-repeat 0px 0px;
+}
 ul.download-links {
   list-style-type: none;
   padding: 2px 0 0 20px; margin: 0;
@@ -99,13 +127,16 @@
 }
 ul.download-links li {
   padding: 0px 10px 0px 0px; margin: 0;
-  display: inline;
   padding-bottom: 5px !important;
 }
 ul.download-links li.download-source {
   background: url(images/icon_source.png) no-repeat 0px 0px;
   padding-left: 18px;
 }
+ul.download-links li.download-sf {
+  background: url(images/icon_sf.png) no-repeat 0px 0px;
+  padding-left: 18px;
+}
 ul.download-links li.download-windows {
   background: url(images/icon_windows.png) no-repeat 0px 0px;
   padding-left: 18px;
@@ -126,6 +157,10 @@
   background: url(images/icon_links.png) no-repeat 0px 0px;
   padding-left: 18px;
 }
+ul.download-links li.download-wiki {
+  background: url(images/icon_wiki.png) no-repeat 0px 0px;
+  padding-left: 18px;
+}
 ul.download-links li.download-pdf {
   background: url(images/icon_pdf.png) no-repeat 0px 0px;
   padding-left: 18px;
@@ -146,11 +181,8 @@
 h2 a, h2 a:visited, h2 a:hover { color: #000; text-decoration: none }
 h3 a, h3 a:visited, h3 a:hover { color: #000; text-decoration: none }
 
-/* Version info */
-#version_info {
+#sourceforge_logo {
   float: right;
-  font-size: 0.8em;
-  color: #888;
   padding: 3px 15px 0px 0px;
 }
 
@@ -162,41 +194,89 @@
 ul.menu-upper {
   list-style-type: none;
   padding: 0px 0px 0px 15px; margin: 0;
+  margin-top: 10px;
+  width: 95%;
+  border-bottom: 1px solid;
+  text-align: left;
 }
-
 ul.menu li {
-  padding: 0px 0px 10px 20px;
+  padding: 0px 10px 10px 20px;
   margin: 0px;
 }
 ul.menu-upper li {
-  padding: 3px 10px 10px 20px;
+  padding: 8px 10px 4px 25px;
   font-size: 0.8em;
-  margin: 0px;
+  border: solid;
+  border-width: 1px 1px 1px 1px;
+  margin: 0px 0px 0px 0px;
   display: inline;
 }
+ul.menu-upper li:hover {
+  border-top: solid 2px #0000ff;
+  border-left: solid 2px #0000ff;
+  border-right: solid 2px #0000ff;  
+}
 ul li.item-introduction {
-  background: url(images/icon_info.png) no-repeat 0px 3px;
+  background: #dadaff url(images/icon_info.png) no-repeat 5px 6px;
 }
 ul li.item-download {
-  background: url(images/icon_download.png) no-repeat 0px 3px;
+  background: #dadaff url(images/icon_download.png) no-repeat 5px 6px;
 }
 ul li.item-news {
-  background: url(images/icon_news.png) no-repeat 0px 3px;
+  background: #dadaff url(images/icon_news.png) no-repeat 5px 6px;
 }
 ul li.item-documentation {
-  background: url(images/icon_documentation.png) no-repeat 0px 3px;
+  background: #dadaff url(images/icon_documentation.png) no-repeat 5px 6px;
+}
+ul li.item-wiki {
+  background: #dadaff url(images/icon_wiki.png) no-repeat 5px 6px;
 }
 ul li.item-screenshots {
-  background: url(images/icon_screenshots.png) no-repeat 0px 3px;
+  background: #dadaff url(images/icon_screenshots.png) no-repeat 5px 6px;
 }
 ul li.item-community {
-  background: url(images/icon_community.png) no-repeat 0px 3px;
+  background: #dadaff url(images/icon_community.png) no-repeat 5px 6px;
+}
+ul li.item-bug {
+  background: #dadaff url(images/icon_bug.png) no-repeat 5px 6px;
 }
 ul li.item-links {
-  background: url(images/icon_links.png) no-repeat 0px 3px;
+  background: #dadaff url(images/icon_links.png) no-repeat 5px 6px;
 }
 ul li.item-license {
-  background: url(images/icon_license.png) no-repeat 0px 3px;
+  background: #dadaff url(images/icon_license.png) no-repeat 5px 6px;
+}
+body#index li#n-index {
+    background: #ffffff url(images/icon_info.png) no-repeat 5px 6px;
+    border-bottom: 1px solid #ffffff;
+}
+body#news li#n-news {
+    background: #ffffff url(images/icon_news.png) no-repeat 5px 6px;
+    border-bottom: 1px solid #ffffff;
+}
+body#download li#n-download{
+    background: #ffffff url(images/icon_download.png) no-repeat 5px 6px;
+    border-bottom: 1px solid #ffffff;
+}
+body#documentation li#n-documentation{
+    background: #ffffff url(images/icon_documentation.png) no-repeat 5px 6px;
+    border-bottom: 1px solid #ffffff;
+}
+body#screenshots li#n-screenshots{
+    background: #ffffff url(images/icon_screenshots.png) no-repeat 5px 6px;
+    border-bottom: 1px solid #ffffff;
+}
+body#support li#n-support{
+    background: #ffffff url(images/icon_community.png) no-repeat 5px 6px;
+    border-bottom: 1px solid #ffffff;
+}
+body#bugs li#n-bugs{
+    background: #ffffff url(images/icon_bug.png) no-repeat 5px 6px;
+    border-bottom: 1px solid #ffffff;
+}
+body#license li#n-license {
+    background: #ffffff url(images/icon_license.png) no-repeat 5px 6px;
+    border-bottom: 1px solid #ffffff;
 }
 
 /* Forms */
@@ -232,3 +312,80 @@
 {
   padding: 0px 60px 0px;
 }
+table.intro td {
+  vertical-align: top;
+  width: 33.3%;
+  padding: 20px;
+}
+div.feed {
+  width: 100%;
+  padding: 20px;
+}
+div.feedburnerFeedBlock p.feedTitle { 
+    font-size: 1em;
+}
+div.feedburnerFeedBlock a { 
+    color: black;
+}
+div.feedburnerFeedBlock ul a { 
+    color: #00f; text-decoration: none
+}
+div.feedburnerFeedBlock { 
+    font-size: 1em;
+}
+div.feedburnerFeedBlock ul { 
+  list-style-type: none;
+}
+div.feedburnerFeedBlock ul li { 
+    margin-top: 10px;
+}
+div.feedburnerFeedBlock p.date {
+    font-style: italic;
+    font-size: 0.8em;
+    margin: 5px;    
+}
+div.feedburnerFeedBlock p.date:before {
+    content: "(";
+}
+div.feedburnerFeedBlock p.date:after {
+    content: ")";
+}
+div.feedburnerFeedBlock span, span+p {display:inline}
+div.feed span.headline {
+    font-size: 1.25em;
+}
+#creditfooter {
+    float: right;
+}
+div.feedburnerFeedBlock table {
+    table-layout: fixed;
+    width: 100%;
+}
+div.quick-menu {
+    position:fixed;
+    bottom:0;
+    width: 100%;
+}
+div.quick-menu ul.menu-bottom {
+    padding: 5px;
+    border-top: 1px solid #0000a0;
+    text-align: center;
+    background: #dadaff;
+}
+ul.menu-bottom {
+  list-style-type: none;
+  padding: 0px 0px 0px 15px; margin: 0;
+}
+ul.menu-bottom li {
+  padding: 8px 10px 10px 25px;
+  font-size: 0.8em;
+  margin: 0px;
+  display: inline;
+}
+div.copyright {
+    border-top: 1px solid #8e8e8e;
+    text-align: center;
+    color: #8e8e8e;
+    padding-top: 10px;
+    padding-bottom: 50px;
+}
\ No newline at end of file

=== modified file 'doc/homepage/support.html.in'
--- doc/homepage/support.html.in	2008-02-14 10:57:48 +0000
+++ doc/homepage/support.html.in	2009-03-01 18:56:34 +0000
@@ -1,29 +1,35 @@
-<h2>Getting help</h2>
-
-<h3>Mailing lists</h3>
+<h2>Mailing lists</h2>
 
 <p>There are two <b>igraph</b> mailing lists: <code>igraph-help</code>
-and <code>igraph-announce</code>.</p>
+  and <code>igraph-announce</code>.
+</p>
+
+<h3><code>igraph-help</code></h3>
 
 <p><code>igraph-help</code> is for general discussion and questions,
-help, suggestions, etc. See
-<a href="http://lists.nongnu.org/mailman/listinfo/igraph-help"
-onClick="javascript:urchinTracker ('/outgoing/mailinglist-help'); ">
-its page at Savannah</a> for subscription and archives.</p>
-
-<p><code>igraph-announce</code> is a very low-traffic mailing (about one email per month) list for
-important announcements only, such as a new <b>igraph</b> release for
-example. <code>igraph-announce</code> is a read-only list, you can not
-post any messages to it. See
-<a href="http://lists.nongnu.org/mailman/listinfo/igraph-announce"
-onClick="javascript:urchinTracker ('/outgoing/mailinglist-announce'); ">
-its page at Savannah</a> for subscription and archives.</p>
-
-<h3>Bug reports, questions, comments</h3>
-
-<p>Please send questions, comments and bug reports to the
-<a href="mailto:[e-mail]"><code>igraph-help</code>
-mailing list</a> or to <a href="mailto:[e-mail]">Gábor
-Csárdi</a>. The mailing list is preferred. In order to receive
-responses to your comments, please consider subscribing to the
-mailing list.</p>
+  help, suggestions, etc. See
+  <a href="http://lists.nongnu.org/mailman/listinfo/igraph-help"
+     onClick="javascript:urchinTracker ('/outgoing/mailinglist-help'); ">
+    its page at Savannah</a> for subscription and archives.
+</p>
+
+<h3><code>igraph-announce</code></h3>
+
+<p><code>igraph-announce</code> is a very low-traffic mailing (about
+  two emails per year) list for important announcements only, such as
+  a new <b>igraph</b> release for example. These announcements are
+  also sent to <code>igraph-help</code>, so you don't need to sign up
+  to both mailing lists.
+</p>
+
+<p><code>igraph-announce</code> is a read-only list, you can 
+  not post any messages to it.
+</p>
+
+<p>See <a href="http://lists.nongnu.org/mailman/listinfo/igraph-announce"
+	  onClick="javascript:urchinTracker
+	  ('/outgoing/mailinglist-announce'); "> 
+    <code>igraph-announce</code> at Savannah</a> for subscription and
+    archives.
+</p>
+

=== modified file 'doc/homepage/template.html'
--- doc/homepage/template.html	2008-02-14 10:57:48 +0000
+++ doc/homepage/template.html	2009-03-08 11:22:36 +0000
@@ -6,9 +6,13 @@
 <head>
   <title>The igraph library for complex network research</title>
   <link rel="stylesheet" type="text/css" href="style.css"></link>
+  <link rel="shortcut icon" href="images/igraph3.png" type="image/x-icon" />
+  <!--[if lt IE 7.]>
+      <script defer type="text/javascript" src="pngfix.js"></script>
+  <![endif]-->
 </head>
 
-<body>
+<body id="$PAGENAME">
 
 <script src="http://www.google-analytics.com/urchin.js" type="text/javascript">
 </script>
@@ -17,26 +21,68 @@
   urchinTracker();
 </script> 
 
-<h1><a href="index.html">The <b>igraph</b> library</a></h1>
-
-<div id="version_info">Latest version: <b>$VERSION</b><br/>
+<div id="sourceforge_logo">
+<a href="http://sourceforge.net/projects/igraph"><img src="http://sflogo.sourceforge.net/sflogo.php?group_id=160289&type=12" width="120" height="30" border="0" alt="Get The igraph library at SourceForge.net. Fast, secure and Free Open Source software downloads" /></a>
+</div>
+
+<h1><a href="index.html">The <b>igraph</b> library</a>
+</h1>
+
+<ul class="menu-upper">
+  <li class="item-introduction" id="n-index"><a href="index.html">Home</a></li>
+  <li class="item-news" id="n-news"><a href="news.html">News</a></li>
+  <li class="item-download" id="n-download"><a href="download.html">Download</a></li>
+  <li class="item-documentation" id="n-documentation"><a href="documentation.html">Documentation</a></li>
+  <li class="item-wiki"><a href="http://igraph.wikidot.com">Wiki</a></li>
+  <li class="item-screenshots" id="n-screenshots"><a href="screenshots.html">Screenshots</a></li>
+  <li class="item-community" id="n-support"><a href="support.html">Mailing lists</a></li>
+  <li class="item-bug" id="n-bugs"><a href="bugs.html">Bugs</a></li>
+<!--   <li class="item-links" id="n-links"><a href="links.html">Links</a></li> -->
+  <li class="item-license" id="n-license"><a href="license.html">License</a></li>
+</ul>
+
+<div class="igraphlogo">
+<img src="images/igraph2.png" alt="" /><br/>
+Latest version: <b>$VERSION</b><br/>
 <a href="relnotes-$VERSION.html">Release notes</a>
 </div>
 
-<ul class="menu-upper">
-  <li class="item-introduction"><a href="index.html">Introduction</a></li>
-  <li class="item-news"><a href="news.html">News</a></li>
-  <li class="item-download"><a href="download.html">Download</a></li>
-  <li class="item-documentation"><a href="documentation.html">Documentation</a></li>
-  <li class="item-screenshots"><a href="screenshots.html">Screenshots</a></li>
-  <li class="item-community"><a href="support.html">Community</a></li>
-  <li class="item-links"><a href="links.html">Links</a></li>
-  <li class="item-license"><a href="license.html">License</a></li>
-</ul>
-
 <div class="main">
 $CONTENT
 </div>
 
+<div class="quick-menu">
+<ul class="menu-bottom">
+    <li class="item-bug"><a id="qm-reportbug"
+	 href="https://bugs.launchpad.net/igraph/+filebug">
+      <span>Report a bug</span></a></li>
+<!--   <li><a href="https://bugs.launchpad.net/igraph/+filebug"> -->
+<!--       <span>Request a feature</span></a></li> -->
+  <li class="item-bug"><a id="qm-listbugs"
+	 href="https://bugs.launchpad.net/igraph/+bugs">
+      <span>List open bugs</span></a></li>
+  <li class="item-community"><a id="qm-searcharchive"
+	 href="http://lists.gnu.org/archive/html/igraph-help/">
+      <span>Search mailing list</span></a></li>
+  <li class="item-community"><a id="qm-subscribe"
+	 href="http://lists.nongnu.org/mailman/listinfo/igraph-help">
+      <span>Subscribe to mailing list</span></a></li>
+  <li class="item-license"><a id="qm-browsesource"
+	 href="http://bazaar.launchpad.net/~igraph/igraph/0.5-main/files/1139.1.143">
+      <span>Browse source code</span></a></li>
+  <li class="item-documentation"><a id="qm-searchdocs"
+	 href="http://www.google.com/coop/cse?cx=006731217555358536053:yeszjk2wr6q">
+      <span>Search documentation</span></a></li>
+</ul>
+</div>
+
+<div class="copyright">
+    Copyright &copy;
+    2005-2009 <a href="http://igraph.sourceforge.net/">The igraph
+    Project</a>.<br><a href="http://validator.w3.org/check/referer">Optimised</a>
+    for <a href="http://www.w3.org/">standards</a>. Hosted
+    by <a href="http://www.sourceforge.net/">SourceForge</a>. 
+</div>
+
 </body>
 </html>

=== added file 'doc/sitemap_gen.py'
--- doc/sitemap_gen.py	1970-01-01 00:00:00 +0000
+++ doc/sitemap_gen.py	2009-03-03 11:01:42 +0000
@@ -0,0 +1,2094 @@
+#!/usr/bin/env python
+#
+# Copyright (c) 2004, 2005 Google Inc.
+# All rights reserved.
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions
+# are met:
+#
+# * Redistributions of source code must retain the above copyright
+#   notice, this list of conditions and the following disclaimer.
+#
+# * Redistributions in binary form must reproduce the above copyright
+#   notice, this list of conditions and the following disclaimer in
+#   the documentation and/or other materials provided with the
+#   distribution.
+#
+# * Neither the name of Google nor the names of its contributors may
+#   be used to endorse or promote products derived from this software
+#   without specific prior written permission.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+# "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+# LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+# FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
+# COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+# INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+# BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+# LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+# CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+# LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+# ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+# POSSIBILITY OF SUCH DAMAGE.
+#
+#
+# The sitemap_gen.py script is written in Python 2.2 and released to
+# the open source community for continuous improvements under the BSD
+# 2.0 new license, which can be found at:
+#
+#   http://www.opensource.org/licenses/bsd-license.php
+#
+
+__usage__ = \
+"""A simple script to automatically produce sitemaps for a webserver,
+in the Google Sitemap Protocol (GSP).
+
+Usage: python sitemap_gen.py --config=config.xml [--help] [--testing]
+            --config=config.xml, specifies config file location
+            --help, displays usage message
+            --testing, specified when user is experimenting
+"""
+
+# Please be careful that all syntax used in this file can be parsed on
+# Python 1.5 -- this version check is not evaluated until after the
+# entire file has been parsed.
+import sys
+if sys.hexversion < 0x02020000:
+  print 'This script requires Python 2.2 or later.'
+  print 'Currently run with version: %s' % sys.version
+  sys.exit(1)
+
+import fnmatch
+import glob
+import gzip
+import md5
+import os
+import re
+import stat
+import time
+import types
+import urllib
+import urlparse
+import xml.sax
+
+# True and False were introduced in Python2.2.2
+try:
+  testTrue=True
+  del testTrue
+except NameError:
+  True=1
+  False=0
+
+# Text encodings
+ENC_ASCII = 'ASCII'
+ENC_UTF8  = 'UTF-8'
+ENC_IDNA  = 'IDNA'
+ENC_ASCII_LIST = ['ASCII', 'US-ASCII', 'US', 'IBM367', 'CP367', 'ISO646-US'
+                  'ISO_646.IRV:1991', 'ISO-IR-6', 'ANSI_X3.4-1968',
+                  'ANSI_X3.4-1986', 'CPASCII' ]
+ENC_DEFAULT_LIST = ['ISO-8859-1', 'ISO-8859-2', 'ISO-8859-5']
+
+# Available Sitemap types
+SITEMAP_TYPES = ['web', 'mobile', 'news']
+
+# General Sitemap tags
+GENERAL_SITEMAP_TAGS = ['loc', 'changefreq', 'priority', 'lastmod']
+
+# News specific tags
+NEWS_SPECIFIC_TAGS = ['keywords', 'publication_date', 'stock_tickers']
+
+# News Sitemap tags
+NEWS_SITEMAP_TAGS = GENERAL_SITEMAP_TAGS + NEWS_SPECIFIC_TAGS
+
+# Maximum number of urls in each sitemap, before next Sitemap is created
+MAXURLS_PER_SITEMAP = 50000
+
+# Suffix on a Sitemap index file
+SITEINDEX_SUFFIX = '_index.xml'
+
+# Regular expressions tried for extracting URLs from access logs.
+ACCESSLOG_CLF_PATTERN = re.compile(
+  r'.+\s+"([^\s]+)\s+([^\s]+)\s+HTTP/\d+\.\d+"\s+200\s+.*'
+  )
+
+# Match patterns for lastmod attributes
+DATE_PATTERNS = map(re.compile, [
+  r'^\d\d\d\d$',
+  r'^\d\d\d\d-\d\d$',
+  r'^\d\d\d\d-\d\d-\d\d$',
+  r'^\d\d\d\d-\d\d-\d\dT\d\d:\d\dZ$',
+  r'^\d\d\d\d-\d\d-\d\dT\d\d:\d\d[+-]\d\d:\d\d$',
+  r'^\d\d\d\d-\d\d-\d\dT\d\d:\d\d:\d\d(\.\d+)?Z$',
+  r'^\d\d\d\d-\d\d-\d\dT\d\d:\d\d:\d\d(\.\d+)?[+-]\d\d:\d\d$',
+  ])
+
+# Match patterns for changefreq attributes
+CHANGEFREQ_PATTERNS = [
+  'always', 'hourly', 'daily', 'weekly', 'monthly', 'yearly', 'never'
+  ]
+
+# XML formats
+GENERAL_SITEINDEX_HEADER   = \
+  '<?xml version="1.0" encoding="UTF-8"?>\n' \
+  '<sitemapindex\n' \
+  '  xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"\n' \
+  '  xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"\n' \
+  '  xsi:schemaLocation="http://www.sitemaps.org/schemas/sitemap/0.9\n' \
+  '                      http://www.sitemaps.org/schemas/sitemap/0.9/' \
+  'siteindex.xsd">\n'
+
+NEWS_SITEINDEX_HEADER   = \
+  '<?xml version="1.0" encoding="UTF-8"?>\n' \
+  '<sitemapindex\n' \
+  '  xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"\n' \
+  '  xmlns:news="http://www.google.com/schemas/sitemap-news/0.9"\n' \
+  '  xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"\n' \
+  '  xsi:schemaLocation="http://www.sitemaps.org/schemas/sitemap/0.9\n' \
+  '                      http://www.sitemaps.org/schemas/sitemap/0.9/' \
+  'siteindex.xsd">\n'
+
+SITEINDEX_FOOTER   = '</sitemapindex>\n'
+SITEINDEX_ENTRY    = \
+  ' <sitemap>\n' \
+  '  <loc>%(loc)s</loc>\n' \
+  '  <lastmod>%(lastmod)s</lastmod>\n' \
+  ' </sitemap>\n'
+GENERAL_SITEMAP_HEADER     = \
+  '<?xml version="1.0" encoding="UTF-8"?>\n' \
+  '<urlset\n' \
+  '  xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"\n' \
+  '  xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"\n' \
+  '  xsi:schemaLocation="http://www.sitemaps.org/schemas/sitemap/0.9\n' \
+  '                      http://www.sitemaps.org/schemas/sitemap/0.9/' \
+  'sitemap.xsd">\n'
+
+NEWS_SITEMAP_HEADER	= \
+  '<?xml version="1.0" encoding="UTF-8"?>\n' \
+  '<urlset\n' \
+  '  xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"\n' \
+  '  xmlns:news="http://www.google.com/schemas/sitemap-news/0.9"\n' \
+  '  xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"\n' \
+  '  xsi:schemaLocation="http://www.sitemaps.org/schemas/sitemap/0.9\n' \
+  '                      http://www.sitemaps.org/schemas/sitemap/0.9/' \
+  'sitemap.xsd">\n'
+
+SITEMAP_FOOTER     = '</urlset>\n'
+SITEURL_XML_PREFIX = ' <url>\n'
+SITEURL_XML_SUFFIX = ' </url>\n'
+
+NEWS_TAG_XML_PREFIX	= '  <news:news>\n'
+NEWS_TAG_XML_SUFFIX	= '  </news:news>\n'
+
+# Search engines to notify with the updated sitemaps
+#
+# This list is very non-obvious in what's going on.  Here's the gist:
+# Each item in the list is a 6-tuple of items.  The first 5 are "almost"
+# the same as the input arguments to urlparse.urlunsplit():
+#   0 - schema
+#   1 - netloc
+#   2 - path
+#   3 - query    <-- EXCEPTION: specify a query map rather than a string
+#   4 - fragment
+# Additionally, add item 5:
+#   5 - query attribute that should be set to the new Sitemap URL
+# Clear as mud, I know.
+NOTIFICATION_SITES = [
+  ('http', 'www.google.com', 'webmasters/sitemaps/ping', {}, '', 'sitemap'),
+  ]
+
+
+class Error(Exception):
+  """
+  Base exception class.  In this module we tend not to use our own exception
+  types for very much, but they come in very handy on XML parsing with SAX.
+  """
+  pass
+#end class Error
+
+
+class SchemaError(Error):
+  """Failure to process an XML file according to the schema we know."""
+  pass
+#end class SchemeError
+
+
+class Encoder:
+  """
+  Manages wide-character/narrow-character conversions for just about all
+  text that flows into or out of the script.
+
+  You should always use this class for string coercion, as opposed to
+  letting Python handle coercions automatically.  Reason: Python
+  usually assumes ASCII (7-bit) as a default narrow character encoding,
+  which is not the kind of data we generally deal with.
+
+  General high-level methodologies used in sitemap_gen:
+
+  [PATHS]
+  File system paths may be wide or narrow, depending on platform.
+  This works fine, just be aware of it and be very careful to not
+  mix them.  That is, if you have to pass several file path arguments
+  into a library call, make sure they are all narrow or all wide.
+  This class has MaybeNarrowPath() which should be called on every
+  file system path you deal with.
+
+  [URLS]
+  URL locations are stored in Narrow form, already escaped.  This has the
+  benefit of keeping escaping and encoding as close as possible to the format
+  we read them in.  The downside is we may end up with URLs that have
+  intermingled encodings -- the root path may be encoded in one way
+  while the filename is encoded in another.  This is obviously wrong, but
+  it should hopefully be an issue hit by very few users.  The workaround
+  from the user level (assuming they notice) is to specify a default_encoding
+  parameter in their config file.
+
+  [OTHER]
+  Other text, such as attributes of the URL class, configuration options,
+  etc, are generally stored in Unicode for simplicity.
+  """
+
+  def __init__(self):
+    self._user      = None                  # User-specified default encoding
+    self._learned   = []                    # Learned default encodings
+    self._widefiles = False                 # File system can be wide
+
+    # Can the file system be Unicode?
+    try:
+      self._widefiles = os.path.supports_unicode_filenames
+    except AttributeError:
+      try:
+        self._widefiles = sys.getwindowsversion() == os.VER_PLATFORM_WIN32_NT
+      except AttributeError:
+        pass
+
+    # Try to guess a working default
+    try:
+      encoding = sys.getfilesystemencoding()
+      if encoding and not (encoding.upper() in ENC_ASCII_LIST):
+        self._learned = [ encoding ]
+    except AttributeError:
+      pass
+
+    if not self._learned:
+      encoding = sys.getdefaultencoding()
+      if encoding and not (encoding.upper() in ENC_ASCII_LIST):
+        self._learned = [ encoding ]
+
+    # If we had no guesses, start with some European defaults
+    if not self._learned:
+      self._learned = ENC_DEFAULT_LIST
+  #end def __init__
+
+  def SetUserEncoding(self, encoding):
+    self._user = encoding
+  #end def SetUserEncoding
+
+  def NarrowText(self, text, encoding):
+    """ Narrow a piece of arbitrary text """
+    if type(text) != types.UnicodeType:
+      return text
+
+    # Try the passed in preference
+    if encoding:
+      try:
+        result = text.encode(encoding)
+        if not encoding in self._learned:
+          self._learned.append(encoding)
+        return result
+      except UnicodeError:
+        pass
+      except LookupError:
+        output.Warn('Unknown encoding: %s' % encoding)
+
+    # Try the user preference
+    if self._user:
+      try:
+        return text.encode(self._user)
+      except UnicodeError:
+        pass
+      except LookupError:
+        temp = self._user
+        self._user = None
+        output.Warn('Unknown default_encoding: %s' % temp)
+
+    # Look through learned defaults, knock any failing ones out of the list
+    while self._learned:
+      try:
+        return text.encode(self._learned[0])
+      except:
+        del self._learned[0]
+
+    # When all other defaults are exhausted, use UTF-8
+    try:
+      return text.encode(ENC_UTF8)
+    except UnicodeError:
+      pass
+
+    # Something is seriously wrong if we get to here
+    return text.encode(ENC_ASCII, 'ignore')
+  #end def NarrowText
+  
+  def MaybeNarrowPath(self, text):
+    """ Paths may be allowed to stay wide """
+    if self._widefiles:
+      return text
+    return self.NarrowText(text, None)
+  #end def MaybeNarrowPath
+
+  def WidenText(self, text, encoding):
+    """ Widen a piece of arbitrary text """
+    if type(text) != types.StringType:
+      return text
+
+    # Try the passed in preference
+    if encoding:
+      try:
+        result = unicode(text, encoding)
+        if not encoding in self._learned:
+          self._learned.append(encoding)
+        return result
+      except UnicodeError:
+        pass
+      except LookupError:
+        output.Warn('Unknown encoding: %s' % encoding)
+
+    # Try the user preference
+    if self._user:
+      try:
+        return unicode(text, self._user)
+      except UnicodeError:
+        pass
+      except LookupError:
+        temp = self._user
+        self._user = None
+        output.Warn('Unknown default_encoding: %s' % temp)
+
+    # Look through learned defaults, knock any failing ones out of the list
+    while self._learned:
+      try:
+        return unicode(text, self._learned[0])
+      except:
+        del self._learned[0]
+
+    # When all other defaults are exhausted, use UTF-8
+    try:
+      return unicode(text, ENC_UTF8)
+    except UnicodeError:
+      pass
+
+    # Getting here means it wasn't UTF-8 and we had no working default.
+    # We really don't have anything "right" we can do anymore.
+    output.Warn('Unrecognized encoding in text: %s' % text)
+    if not self._user:
+      output.Warn('You may need to set a default_encoding in your '
+                  'configuration file.')
+    return text.decode(ENC_ASCII, 'ignore')
+  #end def WidenText
+#end class Encoder
+encoder = Encoder()
+
+
+class Output:
+  """
+  Exposes logging functionality, and tracks how many errors
+  we have thus output.
+
+  Logging levels should be used as thus:
+    Fatal     -- extremely sparingly
+    Error     -- config errors, entire blocks of user 'intention' lost
+    Warn      -- individual URLs lost
+    Log(,0)   -- Un-suppressable text that's not an error
+    Log(,1)   -- touched files, major actions
+    Log(,2)   -- parsing notes, filtered or duplicated URLs
+    Log(,3)   -- each accepted URL
+  """
+
+  def __init__(self):
+    self.num_errors    = 0                   # Count of errors
+    self.num_warns     = 0                   # Count of warnings
+
+    self._errors_shown = {}                  # Shown errors
+    self._warns_shown  = {}                  # Shown warnings
+    self._verbose      = 0                   # Level of verbosity
+  #end def __init__
+
+  def Log(self, text, level):
+    """ Output a blurb of diagnostic text, if the verbose level allows it """
+    if text:
+      text = encoder.NarrowText(text, None)
+      if self._verbose >= level:
+        print text
+  #end def Log
+
+  def Warn(self, text):
+    """ Output and count a warning.  Suppress duplicate warnings. """
+    if text:
+      text = encoder.NarrowText(text, None)
+      hash = md5.new(text).digest()
+      if not self._warns_shown.has_key(hash):
+        self._warns_shown[hash] = 1
+        print '[WARNING] ' + text
+      else:
+        self.Log('(suppressed) [WARNING] ' + text, 3)
+      self.num_warns = self.num_warns + 1
+  #end def Warn
+
+  def Error(self, text):
+    """ Output and count an error.  Suppress duplicate errors. """
+    if text:
+      text = encoder.NarrowText(text, None)
+      hash = md5.new(text).digest()
+      if not self._errors_shown.has_key(hash):
+        self._errors_shown[hash] = 1
+        print '[ERROR] ' + text
+      else:
+        self.Log('(suppressed) [ERROR] ' + text, 3)
+      self.num_errors = self.num_errors + 1
+  #end def Error
+
+  def Fatal(self, text):
+    """ Output an error and terminate the program. """
+    if text:
+      text = encoder.NarrowText(text, None)
+      print '[FATAL] ' + text
+    else:
+      print 'Fatal error.'
+    sys.exit(1)
+  #end def Fatal
+
+  def SetVerbose(self, level):
+    """ Sets the verbose level. """
+    try:
+      if type(level) != types.IntType:
+        level = int(level)
+      if (level >= 0) and (level <= 3):
+        self._verbose = level
+        return
+    except ValueError:
+      pass
+    self.Error('Verbose level (%s) must be between 0 and 3 inclusive.' % level)
+  #end def SetVerbose
+#end class Output
+output = Output()
+
+
+class URL(object):
+  """ URL is a smart structure grouping together the properties we
+  care about for a single web reference. """
+  __slots__ = 'loc', 'lastmod', 'changefreq', 'priority'
+
+  def __init__(self):
+    self.loc        = None                  # URL -- in Narrow characters
+    self.lastmod    = None                  # ISO8601 timestamp of last modify
+    self.changefreq = None                  # Text term for update frequency
+    self.priority   = None                  # Float between 0 and 1 (inc)
+  #end def __init__
+
+  def __cmp__(self, other):
+    if self.loc < other.loc:
+      return -1
+    if self.loc > other.loc:
+      return 1
+    return 0
+  #end def __cmp__
+
+  def TrySetAttribute(self, attribute, value):
+    """ Attempt to set the attribute to the value, with a pretty try
+    block around it.  """
+    if attribute == 'loc':
+      self.loc = self.Canonicalize(value)
+    else:
+      try:
+        setattr(self, attribute, value)
+      except AttributeError:
+        output.Warn('Unknown URL attribute: %s' % attribute)
+  #end def TrySetAttribute
+
+  def IsAbsolute(loc):
+    """ Decide if the URL is absolute or not """
+    if not loc:
+      return False
+    narrow = encoder.NarrowText(loc, None)
+    (scheme, netloc, path, query, frag) = urlparse.urlsplit(narrow)
+    if (not scheme) or (not netloc):
+      return False
+    return True
+  #end def IsAbsolute
+  IsAbsolute = staticmethod(IsAbsolute)
+
+  def Canonicalize(loc):
+    """ Do encoding and canonicalization on a URL string """
+    if not loc:
+      return loc
+    
+    # Let the encoder try to narrow it
+    narrow = encoder.NarrowText(loc, None)
+
+    # Escape components individually
+    (scheme, netloc, path, query, frag) = urlparse.urlsplit(narrow)
+    unr    = '-._~'
+    sub    = '!$&\'()*+,;='
+    netloc = urllib.quote(netloc, unr + sub + '%:@/[]')
+    path   = urllib.quote(path,   unr + sub + '%:@/')
+    query  = urllib.quote(query,  unr + sub + '%:@/?')
+    frag   = urllib.quote(frag,   unr + sub + '%:@/?')
+
+    # Try built-in IDNA encoding on the netloc
+    try:
+      (ignore, widenetloc, ignore, ignore, ignore) = urlparse.urlsplit(loc)
+      for c in widenetloc:
+        if c >= unichr(128):
+          netloc = widenetloc.encode(ENC_IDNA)
+          netloc = urllib.quote(netloc, unr + sub + '%:@/[]')
+          break
+    except UnicodeError:
+      # urlsplit must have failed, based on implementation differences in the
+      # library.  There is not much we can do here, except ignore it.
+      pass
+    except LookupError:
+      output.Warn('An International Domain Name (IDN) is being used, but this '
+                  'version of Python does not have support for IDNA encoding. '
+                  ' (IDNA support was introduced in Python 2.3)  The encoding '
+                  'we have used instead is wrong and will probably not yield '
+                  'valid URLs.')
+    bad_netloc = False
+    if '%' in netloc:
+      bad_netloc = True
+
+    # Put it all back together
+    narrow = urlparse.urlunsplit((scheme, netloc, path, query, frag))
+
+    # I let '%' through.  Fix any that aren't pre-existing escapes.
+    HEXDIG = '0123456789abcdefABCDEF'
+    list   = narrow.split('%')
+    narrow = list[0]
+    del list[0]
+    for item in list:
+      if (len(item) >= 2) and (item[0] in HEXDIG) and (item[1] in HEXDIG):
+        narrow = narrow + '%' + item
+      else:
+        narrow = narrow + '%25' + item
+
+    # Issue a warning if this is a bad URL
+    if bad_netloc:
+      output.Warn('Invalid characters in the host or domain portion of a URL: '
+                  + narrow)
+
+    return narrow
+  #end def Canonicalize
+  Canonicalize = staticmethod(Canonicalize)
+
+  def VerifyDate(self, date, metatag):
+    """Verify the date format is valid"""
+    match = False
+    if date:
+      date = date.upper()
+      for pattern in DATE_PATTERNS:
+        match = pattern.match(date)
+        if match:
+          return True
+      if not match:
+        output.Warn('The value for %s does not appear to be in ISO8601 '
+		    'format on URL: %s' % (metatag, self.loc))
+        return False
+  #end of VerifyDate
+
+  def Validate(self, base_url, allow_fragment):
+    """ Verify the data in this URL is well-formed, and override if not. """
+    assert type(base_url) == types.StringType
+    
+    # Test (and normalize) the ref
+    if not self.loc:
+      output.Warn('Empty URL')
+      return False
+    if allow_fragment:
+      self.loc = urlparse.urljoin(base_url, self.loc)
+    if not self.loc.startswith(base_url):
+      output.Warn('Discarded URL for not starting with the base_url: %s' %
+                  self.loc)
+      self.loc = None
+      return False
+
+    # Test the lastmod
+    if self.lastmod:
+      if not self.VerifyDate(self.lastmod, "lastmod"):
+        self.lastmod = None
+
+    # Test the changefreq
+    if self.changefreq:
+      match = False
+      self.changefreq = self.changefreq.lower()
+      for pattern in CHANGEFREQ_PATTERNS:
+        if self.changefreq == pattern:
+          match = True
+          break
+      if not match:
+        output.Warn('Changefreq "%s" is not a valid change frequency on URL '
+                    ': %s' % (self.changefreq, self.loc))
+        self.changefreq = None
+
+    # Test the priority
+    if self.priority:
+      priority = -1.0
+      try:
+        priority = float(self.priority)
+      except ValueError:
+        pass
+      if (priority < 0.0) or (priority > 1.0):
+        output.Warn('Priority "%s" is not a number between 0 and 1 inclusive '
+                    'on URL: %s' % (self.priority, self.loc))
+        self.priority = None
+
+    return True
+  #end def Validate
+
+  def MakeHash(self):
+    """ Provides a uniform way of hashing URLs """
+    if not self.loc:
+      return None
+    if self.loc.endswith('/'):
+      return md5.new(self.loc[:-1]).digest()
+    return md5.new(self.loc).digest()
+  #end def MakeHash
+
+  def Log(self, prefix='URL', level=3):
+    """ Dump the contents, empty or not, to the log. """
+    out = prefix + ':'
+    
+    for attribute in self.__slots__:
+      value = getattr(self, attribute)
+      if not value:
+        value = ''
+      out = out + ('  %s=[%s]' % (attribute, value))
+
+    output.Log('%s' % encoder.NarrowText(out, None), level)
+  #end def Log
+
+  def WriteXML(self, file):
+    """ Dump non-empty contents to the output file, in XML format. """
+    if not self.loc:
+      return
+    out = SITEURL_XML_PREFIX
+
+    for attribute in self.__slots__:
+      value = getattr(self, attribute)
+      if value:
+        if type(value) == types.UnicodeType:
+          value = encoder.NarrowText(value, None)
+        elif type(value) != types.StringType:
+          value = str(value)
+        value = xml.sax.saxutils.escape(value)
+        out = out + ('  <%s>%s</%s>\n' % (attribute, value, attribute))
+    
+    out = out + SITEURL_XML_SUFFIX
+    file.write(out)
+  #end def WriteXML
+#end class URL
+
+class NewsURL(URL):
+  """ NewsURL is a subclass of URL with News-Sitemap specific properties. """
+  __slots__ = 'loc', 'lastmod', 'changefreq', 'priority', 'publication_date', \
+	      'keywords', 'stock_tickers'
+
+  def __init__(self):
+    URL.__init__(self)
+    self.publication_date	= None	# ISO8601 timestamp of publication date
+    self.keywords 		= None  # Text keywords
+    self.stock_tickers   	= None  # Text stock
+  #end def __init__
+
+  def Validate(self, base_url, allow_fragment):
+    """ Verify the data in this News URL is well-formed, and override if not. """
+    assert type(base_url) == types.StringType
+
+    if not URL.Validate(self, base_url, allow_fragment):
+      return False
+ 
+    if not URL.VerifyDate(self, self.publication_date, "publication_date"):
+      self.publication_date = None
+ 
+    return True
+  #end def Validate
+
+  def WriteXML(self, file):
+    """ Dump non-empty contents to the output file, in XML format. """
+    if not self.loc:
+      return
+    out = SITEURL_XML_PREFIX
+ 
+    # printed_news_tag indicates if news-specific metatags are present
+    printed_news_tag = False
+    for attribute in self.__slots__:
+      value = getattr(self, attribute)
+      if value:
+        if type(value) == types.UnicodeType:
+          value = encoder.NarrowText(value, None)
+        elif type(value) != types.StringType:
+          value = str(value)
+          value = xml.sax.saxutils.escape(value)
+        if attribute in NEWS_SPECIFIC_TAGS:
+          if not printed_news_tag:
+	    printed_news_tag = True
+	    out = out + NEWS_TAG_XML_PREFIX
+	  out = out + ('    <news:%s>%s</news:%s>\n' % (attribute, value, attribute))
+        else:
+	  out = out + ('  <%s>%s</%s>\n' % (attribute, value, attribute))
+ 
+    if printed_news_tag:
+      out = out + NEWS_TAG_XML_SUFFIX
+    out = out + SITEURL_XML_SUFFIX
+    file.write(out)
+  #end def WriteXML
+#end class NewsURL
+
+
+class Filter:
+  """
+  A filter on the stream of URLs we find.  A filter is, in essence,
+  a wildcard applied to the stream.  You can think of this as an
+  operator that returns a tri-state when given a URL:
+
+    True  -- this URL is to be included in the sitemap
+    None  -- this URL is undecided
+    False -- this URL is to be dropped from the sitemap
+  """
+
+  def __init__(self, attributes):
+    self._wildcard  = None                  # Pattern for wildcard match
+    self._regexp    = None                  # Pattern for regexp match
+    self._pass      = False                 # "Drop" filter vs. "Pass" filter
+
+    if not ValidateAttributes('FILTER', attributes,
+                              ('pattern', 'type', 'action')):
+      return
+
+    # Check error count on the way in
+    num_errors = output.num_errors
+
+    # Fetch the attributes
+    pattern = attributes.get('pattern')
+    type    = attributes.get('type', 'wildcard')
+    action  = attributes.get('action', 'drop')
+    if type:
+      type = type.lower()
+    if action:
+      action = action.lower()
+
+    # Verify the attributes
+    if not pattern:
+      output.Error('On a filter you must specify a "pattern" to match')
+    elif (not type) or ((type != 'wildcard') and (type != 'regexp')):
+      output.Error('On a filter you must specify either \'type="wildcard"\' '
+                   'or \'type="regexp"\'')
+    elif (action != 'pass') and (action != 'drop'):
+      output.Error('If you specify a filter action, it must be either '
+                   '\'action="pass"\' or \'action="drop"\'')
+
+    # Set the rule
+    if action == 'drop':
+      self._pass = False
+    elif action == 'pass':
+      self._pass = True
+
+    if type == 'wildcard':
+      self._wildcard = pattern
+    elif type == 'regexp':
+      try:
+        self._regexp = re.compile(pattern)
+      except re.error:
+        output.Error('Bad regular expression: %s' %  pattern)
+
+    # Log the final results iff we didn't add any errors
+    if num_errors == output.num_errors:
+      output.Log('Filter: %s any URL that matches %s "%s"' %
+                 (action, type, pattern), 2)
+  #end def __init__
+
+  def Apply(self, url):
+    """ Process the URL, as above. """
+    if (not url) or (not url.loc):
+      return None
+    
+    if self._wildcard:
+      if fnmatch.fnmatchcase(url.loc, self._wildcard):
+        return self._pass
+      return None
+
+    if self._regexp:
+      if self._regexp.search(url.loc):
+        return self._pass
+      return None
+
+    assert False # unreachable
+  #end def Apply
+#end class Filter
+
+
+class InputURL:
+  """
+  Each Input class knows how to yield a set of URLs from a data source.
+
+  This one handles a single URL, manually specified in the config file.
+  """
+
+  def __init__(self, attributes):
+    self._url = None                        # The lonely URL
+
+    if not ValidateAttributes('URL', attributes,
+                                ('href', 'lastmod', 'changefreq', 'priority')):
+      return
+    
+    url = URL()
+    for attr in attributes.keys():
+      if attr == 'href':
+        url.TrySetAttribute('loc', attributes[attr])
+      else:
+        url.TrySetAttribute(attr, attributes[attr])
+
+    if not url.loc:
+      output.Error('Url entries must have an href attribute.')
+      return
+    
+    self._url = url
+    output.Log('Input: From URL "%s"' % self._url.loc, 2)
+  #end def __init__
+
+  def ProduceURLs(self, consumer):
+    """ Produces URLs from our data source, hands them in to the consumer. """
+    if self._url:
+      consumer(self._url, True)
+  #end def ProduceURLs
+#end class InputURL
+
+
+class InputURLList:
+  """
+  Each Input class knows how to yield a set of URLs from a data source.
+
+  This one handles a text file with a list of URLs
+  """
+
+  def __init__(self, attributes):
+    self._path      = None                  # The file path
+    self._encoding  = None                  # Encoding of that file
+
+    if not ValidateAttributes('URLLIST', attributes, ('path', 'encoding')):
+      return
+    
+    self._path      = attributes.get('path')
+    self._encoding  = attributes.get('encoding', ENC_UTF8)
+    if self._path:
+      self._path    = encoder.MaybeNarrowPath(self._path)
+      if os.path.isfile(self._path):
+        output.Log('Input: From URLLIST "%s"' % self._path, 2)
+      else:
+        output.Error('Can not locate file: %s' % self._path)
+        self._path = None
+    else:
+      output.Error('Urllist entries must have a "path" attribute.')
+  #end def __init__
+
+  def ProduceURLs(self, consumer):
+    """ Produces URLs from our data source, hands them in to the consumer. """
+
+    # Open the file
+    (frame, file) = OpenFileForRead(self._path, 'URLLIST')
+    if not file:
+      return
+
+    # Iterate lines
+    linenum = 0
+    for line in file.readlines():
+      linenum = linenum + 1
+
+      # Strip comments and empty lines
+      if self._encoding:
+        line = encoder.WidenText(line, self._encoding)
+      line = line.strip()
+      if (not line) or line[0] == '#':
+        continue
+      
+      # Split the line on space
+      url = URL()
+      cols = line.split(' ')
+      for i in range(0,len(cols)):
+        cols[i] = cols[i].strip()
+      url.TrySetAttribute('loc', cols[0])
+
+      # Extract attributes from the other columns
+      for i in range(1,len(cols)):
+        if cols[i]:
+          try:
+            (attr_name, attr_val) = cols[i].split('=', 1)
+            url.TrySetAttribute(attr_name, attr_val)
+          except ValueError:
+            output.Warn('Line %d: Unable to parse attribute: %s' %
+                        (linenum, cols[i]))
+
+      # Pass it on
+      consumer(url, False)
+
+    file.close()
+    if frame:
+      frame.close()
+  #end def ProduceURLs
+#end class InputURLList
+
+
+class InputNewsURLList:
+  """
+  Each Input class knows how to yield a set of URLs from a data source.
+
+  This one handles a text file with a list of News URLs and their metadata
+  """
+
+  def __init__(self, attributes):
+    self._path      = None                  # The file path
+    self._encoding  = None                  # Encoding of that file
+    self._tag_order = []                    # Order of URL metadata
+ 
+    if not ValidateAttributes('URLLIST', attributes, ('path', 'encoding', \
+		              'tag_order')):
+      return
+ 
+    self._path      = attributes.get('path')
+    self._encoding  = attributes.get('encoding', ENC_UTF8)
+    self._tag_order = attributes.get('tag_order')
+ 
+    if self._path:
+      self._path    = encoder.MaybeNarrowPath(self._path)
+      if os.path.isfile(self._path):
+        output.Log('Input: From URLLIST "%s"' % self._path, 2)
+      else:
+        output.Error('Can not locate file: %s' % self._path)
+        self._path = None
+    else:
+      output.Error('Urllist entries must have a "path" attribute.')
+
+    # parse tag_order into an array
+    # tag_order_ascii created for more readable logging
+    tag_order_ascii = []
+    if self._tag_order:
+      self._tag_order = self._tag_order.split(",")
+      for i in range(0, len(self._tag_order)):
+        element = self._tag_order[i].strip().lower()
+	self._tag_order[i]= element
+	tag_order_ascii.append(element.encode('ascii'))
+      output.Log('Input: From URLLIST tag order is "%s"' % tag_order_ascii, 0)
+    else:
+      output.Error('News Urllist configuration file must contain tag_order '
+		   'to define Sitemap metatags.')
+
+    # verify all tag_order inputs are valid
+    tag_order_dict = {}
+    for tag in self._tag_order:
+      tag_order_dict[tag] = ""
+    if not ValidateAttributes('URLLIST', tag_order_dict, \
+		    NEWS_SITEMAP_TAGS): 
+      return
+
+    # loc tag must be present
+    loc_tag = False
+    for tag in self._tag_order:
+      if tag == 'loc':
+        loc_tag = True
+        break
+    if not loc_tag:
+      output.Error('News Urllist tag_order in configuration file '
+		   'does not contain "loc" value: %s' % tag_order_ascii)
+  #end def __init__
+
+  def ProduceURLs(self, consumer):
+    """ Produces URLs from our data source, hands them in to the consumer. """
+
+    # Open the file
+    (frame, file) = OpenFileForRead(self._path, 'URLLIST')
+    if not file:
+      return
+
+    # Iterate lines
+    linenum = 0
+    for line in file.readlines():
+      linenum = linenum + 1
+
+      # Strip comments and empty lines
+      if self._encoding:
+        line = encoder.WidenText(line, self._encoding)
+      line = line.strip()
+      if (not line) or line[0] == '#':
+        continue
+      
+      # Split the line on tabs
+      url = NewsURL()
+      cols = line.split('\t')
+      for i in range(0,len(cols)):
+        cols[i] = cols[i].strip()
+
+      for i in range(0,len(cols)):
+        if cols[i]:
+          attr_value = cols[i]
+	  if i < len(self._tag_order):
+            attr_name = self._tag_order[i]
+            try:
+              url.TrySetAttribute(attr_name, attr_value)
+            except ValueError:
+              output.Warn('Line %d: Unable to parse attribute: %s' %
+                        (linenum, cols[i]))
+
+      # Pass it on
+      consumer(url, False)
+
+    file.close()
+    if frame:
+      frame.close()
+  #end def ProduceURLs
+#end class InputNewsURLList
+
+
+class InputDirectory:
+  """
+  Each Input class knows how to yield a set of URLs from a data source.
+
+  This one handles a directory that acts as base for walking the filesystem.
+  """
+
+  def __init__(self, attributes, base_url):
+    self._path         = None               # The directory
+    self._url          = None               # The URL equivalent
+    self._default_file = None
+    self._remove_empty_directories = False 
+
+    if not ValidateAttributes('DIRECTORY', attributes, ('path', 'url',
+                              'default_file', 'remove_empty_directories')):
+      return
+
+    # Prep the path -- it MUST end in a sep
+    path = attributes.get('path')
+    if not path:
+      output.Error('Directory entries must have both "path" and "url" '
+                  'attributes')
+      return
+    path = encoder.MaybeNarrowPath(path)
+    if not path.endswith(os.sep):
+      path = path + os.sep
+    if not os.path.isdir(path):
+      output.Error('Can not locate directory: %s' % path)
+      return
+    
+    # Prep the URL -- it MUST end in a sep
+    url = attributes.get('url')
+    if not url:
+      output.Error('Directory entries must have both "path" and "url" '
+                  'attributes')
+      return
+    url = URL.Canonicalize(url)
+    if not url.endswith('/'):
+      url = url + '/'
+    if not url.startswith(base_url):
+      url = urlparse.urljoin(base_url, url)
+      if not url.startswith(base_url):
+        output.Error('The directory URL "%s" is not relative to the '
+                    'base_url: %s' % (url, base_url))
+        return
+
+    # Prep the default file -- it MUST be just a filename
+    file = attributes.get('default_file')
+    if file:
+      file = encoder.MaybeNarrowPath(file)
+      if os.sep in file:
+        output.Error('The default_file "%s" can not include path information.'
+                     % file)
+        file = None
+
+    # Prep the remove_empty_directories -- default is false
+    remove_empty_directories = attributes.get('remove_empty_directories')
+    if remove_empty_directories:
+      if (remove_empty_directories == '1') or \
+         (remove_empty_directories.lower() == 'true'):
+        remove_empty_directories = True
+      elif (remove_empty_directories == '0') or \
+	   (remove_empty_directories.lower() == 'false'):
+        remove_empty_directories = False
+      # otherwise the user set a non-default value
+      else:
+        output.Error('Configuration file remove_empty_directories '
+		     'value is not recognized.  Value must be true or false.')
+        return
+    else:
+      remove_empty_directories = False
+
+    self._path         = path
+    self._url          = url
+    self._default_file = file
+    self._remove_empty_directories = remove_empty_directories
+
+    if file:
+      output.Log('Input: From DIRECTORY "%s" (%s) with default file "%s"'
+                 % (path, url, file), 2)
+    else:
+      output.Log('Input: From DIRECTORY "%s" (%s) with no default file'
+                 % (path, url), 2)
+  #end def __init__
+  
+     
+  def ProduceURLs(self, consumer):
+    """ Produces URLs from our data source, hands them in to the consumer. """
+    if not self._path:
+      return
+
+    root_path = self._path
+    root_URL  = self._url
+    root_file = self._default_file
+    remove_empty_directories = self._remove_empty_directories
+
+    def HasReadPermissions(path):
+      """ Verifies a given path has read permissions. """  
+      stat_info = os.stat(path)
+      mode = stat_info[stat.ST_MODE]
+      if mode & stat.S_IREAD:
+        return True
+      else:
+        return None
+
+    def PerFile(dirpath, name):
+      """
+      Called once per file.
+      Note that 'name' will occasionally be None -- for a directory itself
+      """
+      # Pull a timestamp
+      url           = URL()
+      isdir         = False
+      try:
+        if name:
+          path      = os.path.join(dirpath, name)
+        else:
+          path      = dirpath
+        isdir       = os.path.isdir(path)
+        time        = None
+        if isdir and root_file:
+          file      = os.path.join(path, root_file)
+          try:
+            time    = os.stat(file)[stat.ST_MTIME];
+          except OSError:
+            pass
+        if not time:
+          time      = os.stat(path)[stat.ST_MTIME];
+        url.lastmod = TimestampISO8601(time)
+      except OSError:
+        pass
+      except ValueError:
+        pass
+
+      # Build a URL
+      middle        = dirpath[len(root_path):]
+      if os.sep != '/':
+        middle = middle.replace(os.sep, '/')
+      if middle:
+        middle      = middle + '/'
+      if name:
+        middle      = middle + name
+        if isdir:
+          middle    = middle + '/'
+      url.TrySetAttribute('loc', root_URL + encoder.WidenText(middle, None))
+
+      # Suppress default files.  (All the way down here so we can log it.)
+      if name and (root_file == name):
+        url.Log(prefix='IGNORED (default file)', level=2)
+        return
+  
+      # Suppress directories when remove_empty_directories="true"
+      try:
+        if isdir:
+	  if HasReadPermissions(path):
+            if remove_empty_directories == 'true' and \
+	       len(os.listdir(path)) == 0:
+              output.Log('IGNORED empty directory %s' % str(path), level=1)
+              return
+          elif path == self._path:
+            output.Error('IGNORED configuration file directory input %s due '
+			 'to file permissions' % self._path)
+          else:
+            output.Log('IGNORED files within directory %s due to file '
+		       'permissions' % str(path), level=0)
+      except OSError:
+        pass
+      except ValueError:
+        pass
+ 
+      consumer(url, False)
+    #end def PerFile
+
+    def PerDirectory(ignore, dirpath, namelist):
+      """
+      Called once per directory with a list of all the contained files/dirs.
+      """
+      ignore = ignore  # Avoid warnings of an unused parameter
+
+      if not dirpath.startswith(root_path):
+        output.Warn('Unable to decide what the root path is for directory: '
+                    '%s' % dirpath)
+        return
+
+      for name in namelist:
+        PerFile(dirpath, name)
+    #end def PerDirectory
+
+    output.Log('Walking DIRECTORY "%s"' % self._path, 1)
+    PerFile(self._path, None)
+    os.path.walk(self._path, PerDirectory, None)
+  #end def ProduceURLs
+#end class InputDirectory
+
+
+class InputAccessLog:
+  """
+  Each Input class knows how to yield a set of URLs from a data source.
+
+  This one handles access logs.  It's non-trivial in that we want to
+  auto-detect log files in the Common Logfile Format (as used by Apache,
+  for instance) and the Extended Log File Format (as used by IIS, for
+  instance).
+  """
+
+  def __init__(self, attributes):
+    self._path         = None               # The file path
+    self._encoding     = None               # Encoding of that file
+    self._is_elf       = False              # Extended Log File Format?
+    self._is_clf       = False              # Common Logfile Format?
+    self._elf_status   = -1                 # ELF field: '200'
+    self._elf_method   = -1                 # ELF field: 'HEAD'
+    self._elf_uri      = -1                 # ELF field: '/foo?bar=1'
+    self._elf_urifrag1 = -1                 # ELF field: '/foo'
+    self._elf_urifrag2 = -1                 # ELF field: 'bar=1'
+
+    if not ValidateAttributes('ACCESSLOG', attributes, ('path', 'encoding')):
+      return
+
+    self._path      = attributes.get('path')
+    self._encoding  = attributes.get('encoding', ENC_UTF8)
+    if self._path:
+      self._path    = encoder.MaybeNarrowPath(self._path)
+      if os.path.isfile(self._path):
+        output.Log('Input: From ACCESSLOG "%s"' % self._path, 2)
+      else:
+        output.Error('Can not locate file: %s' % self._path)
+        self._path = None
+    else:
+      output.Error('Accesslog entries must have a "path" attribute.')
+  #end def __init__
+
+  def RecognizeELFLine(self, line):
+    """ Recognize the Fields directive that heads an ELF file """
+    if not line.startswith('#Fields:'):
+      return False
+    fields = line.split(' ')
+    del fields[0]
+    for i in range(0, len(fields)):
+      field = fields[i].strip()
+      if field == 'sc-status':
+        self._elf_status   = i
+      elif field == 'cs-method':
+        self._elf_method   = i
+      elif field == 'cs-uri':
+        self._elf_uri      = i
+      elif field == 'cs-uri-stem':
+        self._elf_urifrag1 = i
+      elif field == 'cs-uri-query':
+        self._elf_urifrag2 = i
+    output.Log('Recognized an Extended Log File Format file.', 2)
+    return True
+  #end def RecognizeELFLine
+
+  def GetELFLine(self, line):
+    """ Fetch the requested URL from an ELF line """
+    fields = line.split(' ')
+    count  = len(fields)
+
+    # Verify status was Ok
+    if self._elf_status >= 0:
+      if self._elf_status >= count:
+        return None
+      if not fields[self._elf_status].strip() == '200':
+        return None
+
+    # Verify method was HEAD or GET
+    if self._elf_method >= 0:
+      if self._elf_method >= count:
+        return None
+      if not fields[self._elf_method].strip() in ('HEAD', 'GET'):
+        return None
+
+    # Pull the full URL if we can
+    if self._elf_uri >= 0:
+      if self._elf_uri >= count:
+        return None
+      url = fields[self._elf_uri].strip()
+      if url != '-':
+        return url
+
+    # Put together a fragmentary URL
+    if self._elf_urifrag1 >= 0:
+      if self._elf_urifrag1 >= count or self._elf_urifrag2 >= count:
+        return None
+      urlfrag1 = fields[self._elf_urifrag1].strip()
+      urlfrag2 = None
+      if self._elf_urifrag2 >= 0:
+        urlfrag2 = fields[self._elf_urifrag2]
+      if urlfrag1 and (urlfrag1 != '-'):
+        if urlfrag2 and (urlfrag2 != '-'):
+          urlfrag1 = urlfrag1 + '?' + urlfrag2
+        return urlfrag1
+
+    return None
+  #end def GetELFLine
+
+  def RecognizeCLFLine(self, line):
+    """ Try to tokenize a logfile line according to CLF pattern and see if
+    it works. """
+    match = ACCESSLOG_CLF_PATTERN.match(line)
+    recognize = match and (match.group(1) in ('HEAD', 'GET'))
+    if recognize:
+      output.Log('Recognized a Common Logfile Format file.', 2)
+    return recognize
+  #end def RecognizeCLFLine
+
+  def GetCLFLine(self, line):
+    """ Fetch the requested URL from a CLF line """
+    match = ACCESSLOG_CLF_PATTERN.match(line)
+    if match:
+      request = match.group(1)
+      if request in ('HEAD', 'GET'):
+        return match.group(2)
+    return None
+  #end def GetCLFLine
+
+  def ProduceURLs(self, consumer):
+    """ Produces URLs from our data source, hands them in to the consumer. """
+
+    # Open the file
+    (frame, file) = OpenFileForRead(self._path, 'ACCESSLOG')
+    if not file:
+      return
+
+    # Iterate lines
+    for line in file.readlines():
+      if self._encoding:
+        line = encoder.WidenText(line, self._encoding)
+      line = line.strip()
+
+      # If we don't know the format yet, try them both
+      if (not self._is_clf) and (not self._is_elf):
+        self._is_elf = self.RecognizeELFLine(line)
+        self._is_clf = self.RecognizeCLFLine(line)
+
+      # Digest the line
+      match = None
+      if self._is_elf:
+        match = self.GetELFLine(line)
+      elif self._is_clf:
+        match = self.GetCLFLine(line)
+      if not match:
+        continue
+
+      # Pass it on
+      url = URL()
+      url.TrySetAttribute('loc', match)
+      consumer(url, True)
+
+    file.close()
+    if frame:
+      frame.close()
+  #end def ProduceURLs
+#end class InputAccessLog
+
+
+class FilePathGenerator:
+  """
+  This class generates filenames in a series, upon request.
+  You can request any iteration number at any time, you don't
+  have to go in order.
+
+  Example of iterations for '/path/foo.xml.gz':
+    0           --> /path/foo.xml.gz
+    1           --> /path/foo1.xml.gz
+    2           --> /path/foo2.xml.gz
+    _index.xml  --> /path/foo_index.xml
+  """
+
+  def __init__(self):
+    self.is_gzip     = False                 # Is this a  GZIP file?
+
+    self._path       = None                  # '/path/'
+    self._prefix     = None                  # 'foo'
+    self._suffix     = None                  # '.xml.gz'
+  #end def __init__
+
+  def Preload(self, path):
+    """ Splits up a path into forms ready for recombination. """
+    path = encoder.MaybeNarrowPath(path)
+
+    # Get down to a base name
+    path = os.path.normpath(path)
+    base = os.path.basename(path).lower()
+    if not base:
+      output.Error('Couldn\'t parse the file path: %s' % path)
+      return False
+    lenbase = len(base)
+
+    # Recognize extension
+    lensuffix = 0
+    compare_suffix = ['.xml', '.xml.gz', '.gz']
+    for suffix in compare_suffix:
+      if base.endswith(suffix):
+        lensuffix = len(suffix)
+        break
+    if not lensuffix:
+      output.Error('The path "%s" doesn\'t end in a supported file '
+                   'extension.' % path)
+      return False
+    self.is_gzip = suffix.endswith('.gz')
+
+    # Split the original path
+    lenpath = len(path)
+    self._path   = path[:lenpath-lenbase]
+    self._prefix = path[lenpath-lenbase:lenpath-lensuffix]
+    self._suffix = path[lenpath-lensuffix:]
+
+    return True
+  #end def Preload
+
+  def GeneratePath(self, instance):
+    """ Generates the iterations, as described above. """
+    prefix = self._path + self._prefix
+    if type(instance) == types.IntType:
+      if instance:
+        return '%s%d%s' % (prefix, instance, self._suffix)
+      return prefix + self._suffix
+    return prefix + instance
+  #end def GeneratePath
+
+  def GenerateURL(self, instance, root_url):
+    """ Generates iterations, but as a URL instead of a path. """
+    prefix = root_url + self._prefix
+    retval = None
+    if type(instance) == types.IntType:
+      if instance:
+        retval = '%s%d%s' % (prefix, instance, self._suffix)
+      else:
+        retval = prefix + self._suffix
+    else:
+      retval = prefix + instance
+    return URL.Canonicalize(retval)
+  #end def GenerateURL
+
+  def GenerateWildURL(self, root_url):
+    """ Generates a wildcard that should match all our iterations """
+    prefix = URL.Canonicalize(root_url + self._prefix)
+    temp   = URL.Canonicalize(prefix + self._suffix)
+    suffix = temp[len(prefix):]
+    return prefix + '*' + suffix
+  #end def GenerateURL
+#end class FilePathGenerator
+
+
+class PerURLStatistics:
+  """ Keep track of some simple per-URL statistics, like file extension. """
+
+  def __init__(self):
+    self._extensions  = {}                  # Count of extension instances
+  #end def __init__
+
+  def Consume(self, url):
+    """ Log some stats for the URL.  At the moment, that means extension. """
+    if url and url.loc:
+      (scheme, netloc, path, query, frag) = urlparse.urlsplit(url.loc)
+      if not path:
+        return
+
+      # Recognize directories
+      if path.endswith('/'):
+        if self._extensions.has_key('/'):
+          self._extensions['/'] = self._extensions['/'] + 1
+        else:
+          self._extensions['/'] = 1
+        return
+
+      # Strip to a filename
+      i = path.rfind('/')
+      if i >= 0:
+        assert i < len(path)
+        path = path[i:]
+
+      # Find extension
+      i = path.rfind('.')
+      if i > 0:
+        assert i < len(path)
+        ext = path[i:].lower()
+        if self._extensions.has_key(ext):
+          self._extensions[ext] = self._extensions[ext] + 1
+        else:
+          self._extensions[ext] = 1
+      else:
+        if self._extensions.has_key('(no extension)'):
+          self._extensions['(no extension)'] = self._extensions[
+            '(no extension)'] + 1
+        else:
+          self._extensions['(no extension)'] = 1
+  #end def Consume
+
+  def Log(self):
+    """ Dump out stats to the output. """
+    if len(self._extensions):
+      output.Log('Count of file extensions on URLs:', 1)
+      set = self._extensions.keys()
+      set.sort()
+      for ext in set:
+        output.Log(' %7d  %s' % (self._extensions[ext], ext), 1)
+  #end def Log
+
+class Sitemap(xml.sax.handler.ContentHandler):
+  """
+  This is the big workhorse class that processes your inputs and spits
+  out sitemap files.  It is built as a SAX handler for set up purposes.
+  That is, it processes an XML stream to bring itself up.
+  """
+
+  def __init__(self, suppress_notify):
+    xml.sax.handler.ContentHandler.__init__(self)
+    self._filters      = []                  # Filter objects
+    self._inputs       = []                  # Input objects
+    self._urls         = {}                  # Maps URLs to count of dups
+    self._set          = []                  # Current set of URLs
+    self._filegen      = None                # Path generator for output files
+    self._wildurl1     = None                # Sitemap URLs to filter out
+    self._wildurl2     = None                # Sitemap URLs to filter out
+    self._sitemaps     = 0                   # Number of output files
+    # We init _dup_max to 2 so the default priority is 0.5 instead of 1.0
+    self._dup_max      = 2                   # Max number of duplicate URLs
+    self._stat         = PerURLStatistics()  # Some simple stats
+    self._in_site      = False               # SAX: are we in a Site node?
+    self._in_Site_ever = False               # SAX: were we ever in a Site?
+
+    self._default_enc  = None                # Best encoding to try on URLs
+    self._base_url     = None                # Prefix to all valid URLs
+    self._store_into   = None                # Output filepath
+    self._sitemap_type = None		     # Sitemap type (web, mobile or news)
+    self._suppress     = suppress_notify     # Suppress notify of servers
+  #end def __init__
+
+  def ValidateBasicConfig(self):
+    """ Verifies (and cleans up) the basic user-configurable options. """
+    all_good = True
+
+    if self._default_enc:
+      encoder.SetUserEncoding(self._default_enc)
+
+    # Canonicalize the base_url
+    if all_good and not self._base_url:
+      output.Error('A site needs a "base_url" attribute.')
+      all_good = False
+    if all_good and not URL.IsAbsolute(self._base_url):
+        output.Error('The "base_url" must be absolute, not relative: %s' %
+                     self._base_url)
+        all_good = False
+    if all_good:
+      self._base_url = URL.Canonicalize(self._base_url)
+      if not self._base_url.endswith('/'):
+        self._base_url = self._base_url + '/'
+      output.Log('BaseURL is set to: %s' % self._base_url, 2)
+
+    # Load store_into into a generator
+    if all_good:
+      if self._store_into:
+        self._filegen = FilePathGenerator()
+        if not self._filegen.Preload(self._store_into):
+          all_good = False
+      else:
+        output.Error('A site needs a "store_into" attribute.')
+        all_good = False
+
+    # Ask the generator for patterns on what its output will look like
+    if all_good:
+      self._wildurl1 = self._filegen.GenerateWildURL(self._base_url)
+      self._wildurl2 = self._filegen.GenerateURL(SITEINDEX_SUFFIX,
+                                                 self._base_url)
+
+    # Unify various forms of False
+    if all_good:
+      if self._suppress:
+        if (type(self._suppress) == types.StringType) or (type(self._suppress)
+                                 == types.UnicodeType):
+          if (self._suppress == '0') or (self._suppress.lower() == 'false'):
+            self._suppress = False
+
+    # Clean up the sitemap_type
+    if all_good:
+      match = False
+      # If sitemap_type is not specified, default to web sitemap
+      if not self._sitemap_type:
+        self._sitemap_type = 'web'
+      else:
+	self._sitemap_type = self._sitemap_type.lower()
+        for pattern in SITEMAP_TYPES:
+          if self._sitemap_type == pattern:
+            match = True
+            break
+        if not match:
+          output.Error('The "sitemap_type" value must be "web", "mobile" '
+		       'or "news": %s' % self._sitemap_type)
+          all_good = False
+      output.Log('The Sitemap type is %s Sitemap.' % \
+		        self._sitemap_type.upper(), 0)
+
+    # Done
+    if not all_good:
+      output.Log('See "example_config.xml" for more information.', 0)
+    return all_good
+  #end def ValidateBasicConfig
+
+  def Generate(self):
+    """ Run over all the Inputs and ask them to Produce """
+    # Run the inputs
+    for input in self._inputs:
+      input.ProduceURLs(self.ConsumeURL)
+
+    # Do last flushes
+    if len(self._set):
+      self.FlushSet()
+    if not self._sitemaps:
+      output.Warn('No URLs were recorded, writing an empty sitemap.')
+      self.FlushSet()
+
+    # Write an index as needed
+    if self._sitemaps > 1:
+      self.WriteIndex()
+
+    # Notify
+    self.NotifySearch()
+
+    # Dump stats
+    self._stat.Log()
+  #end def Generate
+
+  def ConsumeURL(self, url, allow_fragment):
+    """
+    All per-URL processing comes together here, regardless of Input.
+    Here we run filters, remove duplicates, spill to disk as needed, etc.
+    
+    """
+    if not url:
+      return
+
+    # Validate
+    if not url.Validate(self._base_url, allow_fragment):
+      return
+
+    # Run filters
+    accept = None
+    for filter in self._filters:
+      accept = filter.Apply(url)
+      if accept != None:
+        break
+    if not (accept or (accept == None)):
+      url.Log(prefix='FILTERED', level=2)
+      return
+
+    # Ignore our out output URLs
+    if fnmatch.fnmatchcase(url.loc, self._wildurl1) or fnmatch.fnmatchcase(
+      url.loc, self._wildurl2):
+      url.Log(prefix='IGNORED (output file)', level=2)
+      return
+
+    # Note the sighting
+    hash = url.MakeHash()
+    if self._urls.has_key(hash):
+      dup = self._urls[hash]
+      if dup > 0:
+        dup = dup + 1
+        self._urls[hash] = dup
+        if self._dup_max < dup:
+          self._dup_max = dup
+      url.Log(prefix='DUPLICATE')
+      return
+
+    # Acceptance -- add to set
+    self._urls[hash] = 1
+    self._set.append(url)
+    self._stat.Consume(url)
+    url.Log()
+
+    # Flush the set if needed
+    if len(self._set) >= MAXURLS_PER_SITEMAP:
+      self.FlushSet()
+  #end def ConsumeURL
+
+  def FlushSet(self):
+    """
+    Flush the current set of URLs to the output.  This is a little
+    slow because we like to sort them all and normalize the priorities
+    before dumping.
+    """
+    
+    # Determine what Sitemap header to use (News or General)
+    if self._sitemap_type == 'news':
+      sitemap_header = NEWS_SITEMAP_HEADER
+    else:
+      sitemap_header = GENERAL_SITEMAP_HEADER
+      
+    # Sort and normalize
+    output.Log('Sorting and normalizing collected URLs.', 1)
+    self._set.sort()
+    for url in self._set:
+      hash = url.MakeHash()
+      dup = self._urls[hash]
+      if dup > 0:
+        self._urls[hash] = -1
+        if not url.priority:
+          url.priority = '%.4f' % (float(dup) / float(self._dup_max))
+
+    # Get the filename we're going to write to
+    filename = self._filegen.GeneratePath(self._sitemaps)
+    if not filename:
+      output.Fatal('Unexpected: Couldn\'t generate output filename.')
+    self._sitemaps = self._sitemaps + 1
+    output.Log('Writing Sitemap file "%s" with %d URLs' %
+        (filename, len(self._set)), 1)
+
+    # Write to it
+    frame = None
+    file  = None
+
+    try:
+      if self._filegen.is_gzip:
+        basename = os.path.basename(filename);
+        frame = open(filename, 'wb')
+        file = gzip.GzipFile(fileobj=frame, filename=basename, mode='wt')
+      else:
+        file = open(filename, 'wt')
+
+      file.write(sitemap_header)
+      for url in self._set:
+        url.WriteXML(file)
+      file.write(SITEMAP_FOOTER)
+
+      file.close()
+      if frame:
+        frame.close()
+
+      frame = None
+      file  = None
+    except IOError:
+      output.Fatal('Couldn\'t write out to file: %s' % filename)
+    os.chmod(filename, 0644)
+
+    # Flush
+    self._set = []
+  #end def FlushSet
+
+  def WriteIndex(self):
+    """ Write the master index of all Sitemap files """
+    # Make a filename
+    filename = self._filegen.GeneratePath(SITEINDEX_SUFFIX)
+    if not filename:
+      output.Fatal('Unexpected: Couldn\'t generate output index filename.')
+    output.Log('Writing index file "%s" with %d Sitemaps' %
+        (filename, self._sitemaps), 1)
+
+   # Determine what Sitemap index header to use (News or General)
+    if self._sitemap_type == 'news':
+      sitemap_index_header = NEWS_SITEMAP_HEADER
+    else:
+      sitemap__index_header = GENERAL_SITEMAP_HEADER
+ 
+    # Make a lastmod time
+    lastmod = TimestampISO8601(time.time())
+
+    # Write to it
+    try:
+      fd = open(filename, 'wt')
+      fd.write(sitemap_index_header)
+
+      for mapnumber in range(0,self._sitemaps):
+        # Write the entry
+        mapurl = self._filegen.GenerateURL(mapnumber, self._base_url)
+        mapattributes = { 'loc' : mapurl, 'lastmod' : lastmod }
+        fd.write(SITEINDEX_ENTRY % mapattributes)
+
+      fd.write(SITEINDEX_FOOTER)
+
+      fd.close()
+      fd = None
+    except IOError:
+      output.Fatal('Couldn\'t write out to file: %s' % filename)
+    os.chmod(filename, 0644)
+  #end def WriteIndex
+
+  def NotifySearch(self):
+    """ Send notification of the new Sitemap(s) to the search engines. """
+    if self._suppress:
+      output.Log('Search engine notification is suppressed.', 1)
+      return
+
+    output.Log('Notifying search engines.', 1)
+
+    # Override the urllib's opener class with one that doesn't ignore 404s
+    class ExceptionURLopener(urllib.FancyURLopener):
+      def http_error_default(self, url, fp, errcode, errmsg, headers):
+        output.Log('HTTP error %d: %s' % (errcode, errmsg), 2)
+        raise IOError
+      #end def http_error_default
+    #end class ExceptionURLOpener
+    old_opener = urllib._urlopener
+    urllib._urlopener = ExceptionURLopener()
+
+    # Build the URL we want to send in
+    if self._sitemaps > 1:
+      url = self._filegen.GenerateURL(SITEINDEX_SUFFIX, self._base_url)
+    else:
+      url = self._filegen.GenerateURL(0, self._base_url)
+
+    # Test if we can hit it ourselves
+    try:
+      u = urllib.urlopen(url)
+      u.close()
+    except IOError:
+      output.Error('When attempting to access our generated Sitemap at the '
+                   'following URL:\n    %s\n  we failed to read it.  Please '
+                   'verify the store_into path you specified in\n'
+                   '  your configuration file is web-accessable.  Consult '
+                   'the FAQ for more\n  information.' % url)
+      output.Warn('Proceeding to notify with an unverifyable URL.')
+
+    # Cycle through notifications
+    # To understand this, see the comment near the NOTIFICATION_SITES comment
+    for ping in NOTIFICATION_SITES:
+      query_map             = ping[3]
+      query_attr            = ping[5]
+      query_map[query_attr] = url
+      query = urllib.urlencode(query_map)
+      notify = urlparse.urlunsplit((ping[0], ping[1], ping[2], query, ping[4]))
+
+      # Send the notification
+      output.Log('Notifying: %s' % ping[1], 0)
+      output.Log('Notification URL: %s' % notify, 2)
+      try:
+        u = urllib.urlopen(notify)
+        u.read()
+        u.close()
+      except IOError:
+        output.Warn('Cannot contact: %s' % ping[1])
+
+    if old_opener:
+      urllib._urlopener = old_opener
+  #end def NotifySearch
+
+  def startElement(self, tag, attributes):
+    """ SAX processing, called per node in the config stream. """
+    if tag == 'site':
+      if self._in_site:
+        output.Error('Can not nest Site entries in the configuration.')
+      else:
+        self._in_site     = True
+
+        if not ValidateAttributes('SITE', attributes,
+          ('verbose', 'default_encoding', 'base_url', 'store_into',
+           'suppress_search_engine_notify', 'sitemap_type')):
+          return
+
+        verbose           = attributes.get('verbose', 0)
+        if verbose:
+          output.SetVerbose(verbose)
+
+        self._default_enc = attributes.get('default_encoding')
+        self._base_url    = attributes.get('base_url')
+        self._store_into  = attributes.get('store_into')
+	self._sitemap_type= attributes.get('sitemap_type')
+        if not self._suppress:
+          self._suppress  = attributes.get('suppress_search_engine_notify',
+                                            False)
+        self.ValidateBasicConfig()
+    elif tag == 'filter':
+      self._filters.append(Filter(attributes))
+
+    elif tag == 'url':
+     print type(attributes)
+     self._inputs.append(InputURL(attributes))
+
+    elif tag == 'urllist':
+      for attributeset in ExpandPathAttribute(attributes, 'path'):
+        if self._sitemap_type == 'news':
+          self._inputs.append(InputNewsURLList(attributeset))
+        else:
+	  self._inputs.append(InputURLList(attributeset))
+
+    elif tag == 'directory':
+      self._inputs.append(InputDirectory(attributes, self._base_url))
+
+    elif tag == 'accesslog':
+      for attributeset in ExpandPathAttribute(attributes, 'path'):
+        self._inputs.append(InputAccessLog(attributeset))
+    else:
+      output.Error('Unrecognized tag in the configuration: %s' % tag)
+  #end def startElement
+
+  def endElement(self, tag):
+    """ SAX processing, called per node in the config stream. """
+    if tag == 'site':
+      assert self._in_site
+      self._in_site      = False
+      self._in_site_ever = True
+  #end def endElement
+
+  def endDocument(self):
+    """ End of SAX, verify we can proceed. """
+    if not self._in_site_ever:
+      output.Error('The configuration must specify a "site" element.')
+    else:
+      if not self._inputs:
+        output.Warn('There were no inputs to generate a sitemap from.')
+  #end def endDocument
+#end class Sitemap
+
+
+def ValidateAttributes(tag, attributes, goodattributes):
+  """ Makes sure 'attributes' does not contain any attribute not
+      listed in 'goodattributes' """
+  all_good = True
+  for attr in attributes.keys():
+    if not attr in goodattributes:
+      output.Error('Unknown %s attribute: %s' % (tag, attr))
+      all_good = False
+  return all_good
+#end def ValidateAttributes
+
+def ExpandPathAttribute(src, attrib):
+  """ Given a dictionary of attributes, return a list of dictionaries
+      with all the same attributes except for the one named attrib.
+      That one, we treat as a file path and expand into all its possible
+      variations. """
+  # Do the path expansion.  On any error, just return the source dictionary.
+  path = src.get(attrib)
+  if not path:
+    return [src]
+  path = encoder.MaybeNarrowPath(path);
+  pathlist = glob.glob(path)
+  if not pathlist:
+    return [src]
+
+  # If this isn't actually a dictionary, make it one
+  if type(src) != types.DictionaryType:
+    tmp = {}
+    for key in src.keys():
+      tmp[key] = src[key]
+    src = tmp
+  # Create N new dictionaries
+  retval = []
+  for path in pathlist:
+    dst = src.copy()
+    dst[attrib] = path
+    retval.append(dst)
+
+  return retval
+#end def ExpandPathAttribute
+
+def OpenFileForRead(path, logtext):
+  """ Opens a text file, be it GZip or plain """
+
+  frame = None
+  file  = None
+
+  if not path:
+    return (frame, file)
+
+  try:
+    if path.endswith('.gz'):
+      frame = open(path, 'rb')
+      file = gzip.GzipFile(fileobj=frame, mode='rt')
+    else:
+      file = open(path, 'rt')
+
+    if logtext:
+      output.Log('Opened %s file: %s' % (logtext, path), 1)
+    else:
+      output.Log('Opened file: %s' % path, 1)
+  except IOError:
+    output.Error('Can not open file: %s' % path)
+
+  return (frame, file)
+#end def OpenFileForRead
+
+def TimestampISO8601(t):
+  """Seconds since epoch (1970-01-01) --> ISO 8601 time string."""
+  return time.strftime('%Y-%m-%dT%H:%M:%SZ', time.gmtime(t))
+#end def TimestampISO8601
+
+def CreateSitemapFromFile(configpath, suppress_notify):
+  """ Sets up a new Sitemap object from the specified configuration file.  """
+
+  # Remember error count on the way in
+  num_errors = output.num_errors
+
+  # Rev up SAX to parse the config
+  sitemap = Sitemap(suppress_notify)
+  try:
+    output.Log('Reading configuration file: %s' % configpath, 0)
+    xml.sax.parse(configpath, sitemap)
+  except IOError:
+    output.Error('Cannot read configuration file: %s' % configpath)
+  except xml.sax._exceptions.SAXParseException, e:
+    output.Error('XML error in the config file (line %d, column %d): %s' %
+                 (e._linenum, e._colnum, e.getMessage()))
+  except xml.sax._exceptions.SAXReaderNotAvailable:
+    output.Error('Some installs of Python 2.2 did not include complete support'
+                 ' for XML.\n  Please try upgrading your version of Python'
+                 ' and re-running the script.')
+
+  # If we added any errors, return no sitemap
+  if num_errors == output.num_errors:
+    return sitemap
+  return None
+#end def CreateSitemapFromFile
+
+def ProcessCommandFlags(args):
+  """
+  Parse command line flags per specified usage, pick off key, value pairs
+  All flags of type "--key=value" will be processed as __flags[key] = value,
+                    "--option" will be processed as __flags[option] = option
+  """
+
+  flags   = {}
+  rkeyval = '--(?P<key>\S*)[=](?P<value>\S*)' # --key=val
+  roption = '--(?P<option>\S*)'               # --key
+  r = '(' + rkeyval + ')|(' + roption + ')'
+  rc = re.compile(r)
+  for a in args:
+    try:
+      rcg = rc.search(a).groupdict()
+      if rcg.has_key('key'):
+        flags[rcg['key']] = rcg['value']
+      if rcg.has_key('option'):
+        flags[rcg['option']] = rcg['option']
+    except AttributeError:
+      return None
+  return flags
+#end def ProcessCommandFlags
+
+
+#
+# __main__
+#
+
+if __name__ == '__main__':
+  flags = ProcessCommandFlags(sys.argv[1:])
+  if not flags or not flags.has_key('config') or flags.has_key('help'):
+    output.Log(__usage__, 0)
+  else:
+    suppress_notify = flags.has_key('testing')
+    sitemap = CreateSitemapFromFile(flags['config'], suppress_notify)
+    if not sitemap:
+      output.Log('Configuration file errors -- exiting.', 0)
+    else:
+      sitemap.Generate()
+      output.Log('Number of errors: %d' % output.num_errors, 1)
+      output.Log('Number of warnings: %d' % output.num_warns, 1)

=== added file 'doc/sitemap_gen_config.xml'
--- doc/sitemap_gen_config.xml	1970-01-01 00:00:00 +0000
+++ doc/sitemap_gen_config.xml	2009-03-03 11:01:42 +0000
@@ -0,0 +1,14 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<site
+    base_url="http://igraph.sourceforge.net/"
+    store_into="sitemap.xml"
+    verbose="1"
+    sitemap_type="web">
+  <directory path="homepage" url="http://igraph.sourceforge.net/" />
+  <directory path="html" url="http://igraph.sourceforge.net/doc/" />
+  <directory path="book/html" url="http://igraph.sourceforge.net/igraphbook/" />
+  <filter action="drop" type="wildcard" pattern="*~" />
+  <filter action="drop" type="wildcard" pattern="*.html.in" />
+  <filter action="drop" type="wildcard" pattern="*.py" />
+  <filter action="drop" type="regexp"   pattern="/\.[^/]*"     />
+</site>