From a8608e2b796fd4f7885baddea391add5e308389a Mon Sep 17 00:00:00 2001
From: Brian Quinion <brian.quinion@mapquest.com>
Date: Tue, 19 Mar 2013 19:44:33 +0000
Subject: [PATCH] calculate the importance value

---
 utils/import_wikipedia.sh | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/utils/import_wikipedia.sh b/utils/import_wikipedia.sh
index d40578dd..0a15e2d0 100755
--- a/utils/import_wikipedia.sh
+++ b/utils/import_wikipedia.sh
@@ -39,6 +39,8 @@ do
   echo "insert into wikipedia_article select '${i}', title, count, othercount, count+othercount from ${i}pagelinkcount;" | $psqlcmd
 done
 
+echo "update wikipedia_article set importance = log(totalcount)/log((select max(totalcount) from wikipedia_article))" | $psqlcmd
+
 # precalculated lat,lon from dbpedia
 wget http://downloads.dbpedia.org/current/en/geo_coordinates_en.nq.bz2
 bzip2 -dc geo_coordinates_en.nq.bz2 | grep http://www.georss.org/georss/point | sed 's|<http://dbpedia.org/resource/[^>]*> *<http://www.georss.org/georss/point> "\(-\?[-0-9.E]\+\) \(-\?[-0-9.E]\+\)"@en <http://\([a-z][a-z]\).wikipedia.org/wiki/\([^#]\+\)#> .|update pagelinks set lat=\1, lon=\2 where language = '"'"'\3'"'"' and title = decode_url_part('"'"'\4'"'"');|g' | $psqlcmd
-- 
2.39.5