From: Christian von Roques <roques@mti.ag>
Date: Tue, 4 Apr 2017 17:00:36 +0000 (+0200)
Subject: deduplicate words: do not look for duplicates in empty partitions
X-Git-Tag: v3.0.0~36^2^2~2
X-Git-Url: https://git.openstreetmap.org/nominatim.git/commitdiff_plain/c80637b05cb7789c4e361ff1ef4ebf895b0f89d3

deduplicate words: do not look for duplicates in empty partitions
---

diff --git a/utils/update.php b/utils/update.php
index 52577d88..d8ac134a 100755
--- a/utils/update.php
+++ b/utils/update.php
@@ -166,6 +166,15 @@ if ($aResult['deduplicate']) {
     $aPartitions = chksql($oDB->getCol($sSQL));
     $aPartitions[] = 0;
 
+    // we don't care about empty search_name_* artitions, 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";