- if (getPostgresVersion($oDB) < 9.3) {
- fail('ERROR: deduplicate is only currently supported in postgresql 9.3');
- }
-
- $sSQL = 'select partition from country_name order by country_code';
- $aPartitions = chksql($oDB->getCol($sSQL));
- $aPartitions[] = 0;
-
- // we don't care about empty search_name_* partitions, they can't contain mentions of duplicates
- foreach ($aPartitions as $i => $sPartition) {
- $sSQL = 'select count(*) from search_name_'.$sPartition;
- $nEntries = chksql($oDB->getOne($sSQL));
- if ($nEntries == 0) {
- unset($aPartitions[$i]);
- }
- }
-
- $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,';
- $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);
- $iKeepID = $aKeep['word_id'];
-
- foreach ($aTokenSet as $aRemove) {
- $sSQL = 'update search_name set';
- $sSQL .= ' name_vector = array_replace(name_vector,'.$aRemove['word_id'].','.$iKeepID.'),';
- $sSQL .= ' nameaddress_vector = array_replace(nameaddress_vector,'.$aRemove['word_id'].','.$iKeepID.')';
- $sSQL .= ' where name_vector @> ARRAY['.$aRemove['word_id'].']';
- chksql($oDB->query($sSQL));
-
- $sSQL = 'update search_name set';
- $sSQL .= ' nameaddress_vector = array_replace(nameaddress_vector,'.$aRemove['word_id'].','.$iKeepID.')';
- $sSQL .= ' where nameaddress_vector @> ARRAY['.$aRemove['word_id'].']';
- chksql($oDB->query($sSQL));
-
- $sSQL = 'update location_area_country set';
- $sSQL .= ' keywords = array_replace(keywords,'.$aRemove['word_id'].','.$iKeepID.')';
- $sSQL .= ' where keywords @> ARRAY['.$aRemove['word_id'].']';
- chksql($oDB->query($sSQL));
-
- foreach ($aPartitions as $sPartition) {
- $sSQL = 'update search_name_'.$sPartition.' set';
- $sSQL .= ' name_vector = array_replace(name_vector,'.$aRemove['word_id'].','.$iKeepID.')';
- $sSQL .= ' where name_vector @> ARRAY['.$aRemove['word_id'].']';
- chksql($oDB->query($sSQL));
-
- $sSQL = 'update location_area_country set';
- $sSQL .= ' keywords = array_replace(keywords,'.$aRemove['word_id'].','.$iKeepID.')';
- $sSQL .= ' where keywords @> ARRAY['.$aRemove['word_id'].']';
- chksql($oDB->query($sSQL));
- }
-
- $sSQL = 'delete from word where word_id = '.$aRemove['word_id'];
- chksql($oDB->query($sSQL));
- }