#!/usr/bin/perl 
# Parse a URI (or URI) into it's parts, and describe them in RDF>
# Dan Brickley <danbri@danbri.org>
#
# 	regex from Jo Rabin, http://www.w3.org/2005/Incubator/wcl/matching.html
# 	thanks to: Kjetilk, LeeF and EliasT in #swig 
#  	  see http://chatlogs.planetrdf.com/swig/2006-06-30#T20-02-35 
#      
# note: we currently use a 404 namespace URI
 
print "<rdf:RDF xmlns:rdf='http://www.w3.org/1999/02/22-rdf-syntax-ns#'>\n\n";

foreach my $uri (<STDIN>) {
 next if ($uri =~ m/^#/);
 next unless ($uri =~ m/\w/);
 chomp $uri;
 $uri =~ m!^(([^:/?#]+):)?(//((([^/?#]*)@)?([^/?#:]*)(:([^/?#]*))?))?([^?#]*)(\?([^#]*))?(#(.*))?!;
 my ($scheme, $authority, $userinfo, $host, $port, $path, $query, $fragment)
					 = ($2, $4, $6, $7, $9, $10, $12, $14);

 print "<ID xmlns='http://www.w3.org/2004/12/q/idsyntax#'>\n";
 print "  <full>$uri</full> \n";
 print "  <nameFor rdf:resource='$uri' /> \n";
 print "  <scheme>$scheme</scheme> \n" if $scheme;
 print "  <authority>$authority</authority> \n" if $authority;
 print "  <userinfo>$userinfo</userinfo> \n" if $userinfo;
 print "  <host>$host</host> \n" if $host;
 print "  <port>$port</port> \n" if $port;
 print "  <path>$path</path> \n" if $path;
 print "  <query>$query</query> \n" if $query;
 print "  <fragment>$fragment</fragment> \n" if $fragment;
 print "</ID>\n\n";
}

print "</rdf:RDF>\n\n";


# resources:
# on IRI testing, 
#  http://www.w3.org/2001/Talks/0912-IUC-IRI/paper.html
#
# http://librdf.org/query?uri=http%3A%2F%2Fspypixel.com%2F2006%2Fwcl%2Furi%2F_data.rdf&query=PREFIX+rdf%3A+%3Chttp%3A%2F%2Fwww.w3.org%2F1999%2F02%2F22-rdf-syntax-ns%23%3E%0D%0APREFIX+u%3A+%3Chttp%3A%2F%2Fwww.w3.org%2F2004%2F12%2Fq%2Fidsyntax%23%3E%0D%0ASELECT+DISTINCT+*%0D%0AWHERE+%7B%0D%0A++%3Fid+rdf%3Atype+u%3AID+.%0D%0A++%3Fid+u%3Afull+%3Ffull+.%0D%0A++%3Fid+u%3AnameFor+%3Fres+.%0D%0A++%3Fid+u%3Ascheme+%3Fscheme+.%0D%0A++%3Fid+u%3Aauthority+%3Fauthority+.%0D%0A++OPTIONAL+%7B+%3Fid+u%3Ahost+%3Fhost+%7D+.%0D%0A++OPTIONAL+%7B+%3Fid+u%3Aport+%3Fport+%7D+.%0D%0A++OPTIONAL+%7B+%3Fid+u%3Apath+%3Fpath+%7D+.%0D%0A++OPTIONAL+%7B+%3Fid+u%3Aquery+%3Fquery+%7D+.%0D%0A++OPTIONAL+%7B+%3Fid+u%3Afragment+%3Ffragment+%7D+.+%0D%0A%7D%0D%0A&language=sparql&Run+Query=Run+Query&.cgifields=language&.cgifields=json&.cgifields=raw
#
# PREFIX u: <http://www.w3.org/2004/12/q/idsyntax#>
# SELECT DISTINCT *
# WHERE {
#   ?id a u:ID .
#   ?id u:full ?full .
#   ?id u:nameFor ?res .
#   ?id u:scheme ?scheme .
#   ?id u:authority ?authority .
#   OPTIONAL { ?id u:host ?host } .
#   OPTIONAL { ?id u:port ?port } .
#   OPTIONAL { ?id u:path ?path } .
#   OPTIONAL { ?id u:query ?query } .
#   OPTIONAL { ?id u:fragment ?fragment } . 
#  }
#
# URL testing:
# http://www.w3.org/Addressing/url_test/url_grammar.tests


# URI Test cases from Graham Klyne:
# http://www.ninebynine.org/Software/HaskellUtils/Network/URITestDescriptions.html