X-Git-Url: https://git.openstreetmap.org./nominatim.git/blobdiff_plain/4a321487f3d44241242a1729ab4d137df1f57bfb..d18bd14045ef31342a8af5834f760532ef9d7487:/utils/update.php diff --git a/utils/update.php b/utils/update.php index 95e99b9f..232a23c9 100755 --- a/utils/update.php +++ b/utils/update.php @@ -166,12 +166,17 @@ if ($aResult['deduplicate']) { $aPartitions = chksql($oDB->getCol($sSQL)); $aPartitions[] = 0; - $sSQL = "select word_token,count(*) from word where substr(word_token, 1, 1) = ' ' and class is null and type is null and country_code is null group by word_token having count(*) > 1 order by word_token"; + $sSQL = "select word_token,count(*) from word where substr(word_token, 1, 1) = ' '"; + $sSQL .= " and class is null and type is null and country_code is null"; + $sSQL .= " group by word_token having count(*) > 1 order by word_token"; $aDuplicateTokens = chksql($oDB->getAll($sSQL)); foreach ($aDuplicateTokens as $aToken) { if (trim($aToken['word_token']) == '' || trim($aToken['word_token']) == '-') continue; echo "Deduping ".$aToken['word_token']."\n"; - $sSQL = "select word_id,(select count(*) from search_name where nameaddress_vector @> ARRAY[word_id]) as num from word where word_token = '".$aToken['word_token']."' and class is null and type is null and country_code is null order by num desc"; + $sSQL = "select word_id,"; + $sSQL .= " (select count(*) from search_name where nameaddress_vector @> ARRAY[word_id]) as num"; + $sSQL .= " from word where word_token = '".$aToken['word_token']; + $sSQL .= "' and class is null and type is null and country_code is null order by num desc"; $aTokenSet = chksql($oDB->getAll($sSQL)); $aKeep = array_shift($aTokenSet);