ignore postcodes with colons

[nominatim.git] / utils / update.php

diff --git a/utils/update.php b/utils/update.php
index 9bb3388a1598a24ced032b8a03aa0607aeef3fa4..f0b45b428cf4b866c624ea5717272337bc3e1b7a 100644 (file)
--- a/utils/update.php
+++ b/utils/update.php
@@ -39,11 +39,9 @@ $aCMDOptions
    array('index-rank', '', 0, 1, 1, 1, 'int', 'Rank to start indexing from'),
    array('index-instances', '', 0, 1, 1, 1, 'int', 'Number of indexing instances (threads)'),
 
-   array('deduplicate', '', 0, 1, 0, 0, 'bool', 'Deduplicate tokens'),
    array('recompute-word-counts', '', 0, 1, 0, 0, 'bool', 'Compute frequency of full-word search terms'),
    array('update-address-levels', '', 0, 1, 0, 0, 'bool', 'Reimport address level configuration (EXPERT)'),
-   array('recompute-importance', '', 0, 1, 0, 0, 'bool', 'Recompute place importances'),
-   array('no-npi', '', 0, 1, 0, 0, 'bool', '(obsolete)'),
+   array('recompute-importance', '', 0, 1, 0, 0, 'bool', 'Recompute place importances')
   );
 
 getCmdOpt($_SERVER['argv'], $aCMDOptions, $aResult, true, true);
@@ -92,8 +90,10 @@ if (!is_null(CONST_Osm2pgsql_Flatnode_File) && CONST_Osm2pgsql_Flatnode_File) {
     $oOsm2pgsqlCmd->addParams('--flat-nodes', CONST_Osm2pgsql_Flatnode_File);
 }
 if ($fPostgresVersion >= 11.0) {
-    $oOsm2pgsqlCmd->addEnvPair('PGOPTIONS',
-                               '-c jit=off -c max_parallel_workers_per_gather=0');
+    $oOsm2pgsqlCmd->addEnvPair(
+        'PGOPTIONS',
+        '-c jit=off -c max_parallel_workers_per_gather=0'
+    );
 }
 
 
@@ -101,7 +101,9 @@ $oIndexCmd = (new \Nominatim\Shell(CONST_BasePath.'/nominatim/nominatim.py'))
              ->addParams('--database', $aDSNInfo['database'])
              ->addParams('--port', $aDSNInfo['port'])
              ->addParams('--threads', $aResult['index-instances']);
-
+if (!$aResult['quiet']) {
+    $oIndexCmd->addParams('--verbose');
+}
 if ($aResult['verbose']) {
     $oIndexCmd->addParams('--verbose');
 }
@@ -149,7 +151,6 @@ if ($aResult['init-updates']) {
                                       'enable-diff-updates' => true,
                                       'verbose' => $aResult['verbose']
                                      ));
-        $cSetup->connect();
         $cSetup->createFunctions();
     }
 
@@ -269,78 +270,6 @@ if ($bHaveDiff) {
     }
 }
 
-if ($aResult['deduplicate']) {
-    $oDB = new Nominatim\DB();
-    $oDB->connect();
-
-    if ($oDB->getPostgresVersion() < 9.3) {
-        fail('ERROR: deduplicate is only currently supported in postgresql 9.3');
-    }
-
-    $sSQL = 'select partition from country_name order by country_code';
-    $aPartitions = $oDB->getCol($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 = $oDB->getOne($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 = $oDB->getAll($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 = $oDB->getAll($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'].']';
-            $oDB->exec($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'].']';
-            $oDB->exec($sSQL);
-
-            $sSQL = 'update location_area_country set';
-            $sSQL .= ' keywords = array_replace(keywords,'.$aRemove['word_id'].','.$iKeepID.')';
-            $sSQL .= ' where keywords @> ARRAY['.$aRemove['word_id'].']';
-            $oDB->exec($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'].']';
-                $oDB->exec($sSQL);
-
-                $sSQL = 'update location_area_country set';
-                $sSQL .= ' keywords = array_replace(keywords,'.$aRemove['word_id'].','.$iKeepID.')';
-                $sSQL .= ' where keywords @> ARRAY['.$aRemove['word_id'].']';
-                $oDB->exec($sSQL);
-            }
-
-            $sSQL = 'delete from word where word_id = '.$aRemove['word_id'];
-            $oDB->exec($sSQL);
-        }
-    }
-}
-
 if ($aResult['recompute-word-counts']) {
     info('Recompute frequency of full-word search terms');
     $sTemplate = file_get_contents(CONST_BasePath.'/sql/words_from_search_name.sql');
@@ -349,9 +278,11 @@ if ($aResult['recompute-word-counts']) {
 
 if ($aResult['index']) {
     $oCmd = (clone $oIndexCmd)
-            ->addParams('--minrank', $aResult['index-rank']);
+            ->addParams('--minrank', $aResult['index-rank'], '-b');
+    $oCmd->run();
 
-    // echo $oCmd->escapedCmd()."\n";
+    $oCmd = (clone $oIndexCmd)
+            ->addParams('--minrank', $aResult['index-rank']);
     $oCmd->run();
 
     $oDB->exec('update import_status set indexed = true');
@@ -492,9 +423,18 @@ if ($aResult['import-osmosis'] || $aResult['import-osmosis-all']) {
 
         // Index file
         if (!$aResult['no-index']) {
-            $oThisIndexCmd = clone($oIndexCmd);
             $fCMDStartTime = time();
 
+            $oThisIndexCmd = clone($oIndexCmd);
+            $oThisIndexCmd->addParams('-b');
+            echo $oThisIndexCmd->escapedCmd()."\n";
+            $iErrorLevel = $oThisIndexCmd->run();
+            if ($iErrorLevel) {
+                echo "Error: $iErrorLevel\n";
+                exit($iErrorLevel);
+            }
+
+            $oThisIndexCmd = clone($oIndexCmd);
             echo $oThisIndexCmd->escapedCmd()."\n";
             $iErrorLevel = $oThisIndexCmd->run();
             if ($iErrorLevel) {