<?xml version="1.0"?>
<!-- This is the configuration file for the RegexUrlNormalize Class.
     This is intended so that users can specify substitutions to be
     done on URLs. The regex engine that is used is Perl5 compatible.
     The rules are applied to URLs in the order they occur in this file.  -->

<!-- WATCH OUT: an xml parser reads this file an ampersands must be
     expanded to &amp; -->

<!-- The following rules show how to strip out session IDs, default pages, 
     interpage anchors, etc. Order does matter!  -->
<regex-normalize>

<!-- removes session ids from urls (such as jsessionid and PHPSESSID) -->
<regex>
  <pattern>(?i)(;?\b_?(l|j|bv_)?(sid|phpsessid|sessionid)=.*?)(\?|&amp;|#|$)</pattern>
  <substitution>$4</substitution>
</regex>

<!-- changes default pages into standard for /index.html, etc. into / -->
<!-- these are commented in the default file but uncommented here for testing -->
<regex>
  <pattern>/((?i)index|default)\.((?i)js[pf]{1}?[afx]?|cgi|cfm|asp[x]?|[psx]?htm[l]?|php[3456]?)(\?|&amp;|#|$)</pattern>
  <substitution>/$3</substitution>
</regex> 

<!-- removes interpage href anchors such as site.com#location -->
<regex>
  <pattern>#.*?(\?|&amp;|$)</pattern>
  <substitution>$1</substitution>
</regex>

<!-- cleans ?&var=value into ?var=value -->
<regex>
  <pattern>\?&amp;</pattern>
  <substitution>\?</substitution>
</regex>

<!-- cleans multiple sequential ampersands into a single ampersand -->
<regex>
  <pattern>&amp;{2,}</pattern>
  <substitution>&amp;</substitution>
</regex>

<!-- removes trailing ?, ampersands, . -->
<regex>
  <pattern>[\?&amp;\.]$</pattern>
  <substitution></substitution>
</regex>

<!-- normalize file:/// protocol prefix: -->
<!--  keep one single slash (NUTCH-1483) -->
<regex>
  <pattern>^file://+</pattern>
  <substitution>file:/</substitution>
</regex>

<!-- removes duplicate slashes but -->
<!-- * allow 2 slashes after colon ':' (indicating protocol) -->
<regex>
  <pattern>(?&lt;!:)/{2,}</pattern>
  <substitution>/</substitution>
</regex>

</regex-normalize>

