[COMMIT LOGREPORT] service/www/lib/Lire/DlfAnalysers ReferrerCategoriser.pm,1.2,1.3

Joost van Baal vanbaal at users.sourceforge.net
Sun Jul 16 14:02:54 CEST 2006


Update of /cvsroot/logreport/service/www/lib/Lire/DlfAnalysers
In directory sc8-pr-cvs6.sourceforge.net:/tmp/cvs-serv833

Modified Files:
	ReferrerCategoriser.pm 
Log Message:
cosmetics

Index: ReferrerCategoriser.pm
===================================================================
RCS file: /cvsroot/logreport/service/www/lib/Lire/DlfAnalysers/ReferrerCategoriser.pm,v
retrieving revision 1.2
retrieving revision 1.3
diff -u -r1.2 -r1.3
--- ReferrerCategoriser.pm	29 Jul 2005 20:53:39 -0000	1.2
+++ ReferrerCategoriser.pm	16 Jul 2006 12:02:52 -0000	1.3
@@ -62,31 +62,31 @@
 # Because google.yahoo.com isn't the same as www.google.com
 my @Engine2Keywords = 
   (
-   ["yahoo.com",    'p',	"Yahoo!"],
-   ["altavista.com",'q',	"AltaVista"],
-   ["google",	    'q',	"Google"],
-   ["google",	    'query',	"Google"],
-   ["www.google",   'q',	"Google"],
-   ["aol.com",	    'query',	"AOL NetFind"],
-   ["eureka.com",   'q',	"Eureka"],
-   ["lycos.com",    'query',	"Lycos"],
-   ["hotbot.com",   'MT',	"HotBot"],
-   ["msn.com",	    'MT',	"Microsoft Network"],
-   ["infoseek.com", 'qt',	"InfoSeek"],
-   ["webcrawler",   'searchText', "WebCrawler"],
-   [ "excite",	    'search',	"Excite"],
-   ["netscape.com", 'search',	"Netscape"],
-   ["mamma.com",    'query',	"Mamma"],
-   ["alltheweb.com", 'query',	"All The Web"],
-   ["northernlight.com", 'qr',	"Northern Light"],
-   ["askjeeves.com", 'ask',	"Ask Jeeves"],
-   ["looksmart.com", 'key',	"Look Smart"],
-   ["goto.com",	     'key',	"Look Smart"],
-   ["overture.com",  'Keywords',"Overture"],
-   ["about.com",     'terms',	"About.COM"],
-   ["metacrawler.com", 'general', "Meta Crawler"],
-   ["about.com",     'terms',	"About.COM"],
-   ["iwon.com",     'searchfor', "iWon"],
+   ["yahoo.com",         'p',          "Yahoo!"],
+   ["altavista.com",     'q',          "AltaVista"],
+   ["google",            'q',          "Google"],
+   ["google",            'query',      "Google"],
+   ["www.google",        'q',          "Google"],
+   ["aol.com",           'query',      "AOL NetFind"],
+   ["eureka.com",        'q',          "Eureka"],
+   ["lycos.com",         'query',      "Lycos"],
+   ["hotbot.com",        'MT',         "HotBot"],
+   ["msn.com",           'MT',         "Microsoft Network"],
+   ["infoseek.com",      'qt',         "InfoSeek"],
+   ["webcrawler",        'searchText', "WebCrawler"],
+   [ "excite",           'search',     "Excite"],
+   ["netscape.com",      'search',     "Netscape"],
+   ["mamma.com",         'query',      "Mamma"],
+   ["alltheweb.com",     'query',      "All The Web"],
+   ["northernlight.com", 'qr',         "Northern Light"],
+   ["askjeeves.com",     'ask',        "Ask Jeeves"],
+   ["looksmart.com",     'key',        "Look Smart"],
+   ["goto.com",          'key',        "Look Smart"],
+   ["overture.com",      'Keywords',   "Overture"],
+   ["about.com",         'terms',      "About.COM"],
+   ["metacrawler.com",   'general',    "Meta Crawler"],
+   ["about.com",         'terms',      "About.COM"],
+   ["iwon.com",          'searchfor',  "iWon"],
   );
 
 sub categorise {
@@ -114,13 +114,13 @@
 	next unless $parsed_url->{'query'} =~ /$param=(.*?)([;&]|$)/;
 	my $keywords = $1;
 	$keywords =~ tr/+/ /s;
-	$keywords =~ s/%([0-9a-fA-F]{2})/chr(hex $1)/eg;
+	$keywords =~ s/%([0-9a-fA-F]{2})/chr(hex $1)/eg;  # FIXME: take &ie=ISO-8859-1& into account here!  We wrongly assume anything is UTF8-encoded here.
+        $dlf->{'search_engine'} = $engine;
         # we've seen
         # http://www.google.com/search?as_q=&num=10&btnG=Google+Search&\
         #  as_epq=Trippin+Smurfs&as_oq=&as_eq=&lr=&as_ft=i&as_filetype=&\
         #  as_qdr=all&as_occt=any&as_dt=i&as_sitesearch=&safe=off
         # so: deal with empty search requests.
-        $dlf->{'search_engine'} = $engine;
         $dlf->{'keywords'} = $keywords
           if $keywords;
         return;

-- 
To UNSUBSCRIBE, email to commit-request at logreport.org with a subject of 
"unsubscribe". Trouble? Send an email with subject "help" to 
commit-request at logreport.org



More information about the Commit mailing list