improve handling of multi-word partials in SearchDescription

Multi-word partial terms had an undue advantage over separate partial
terms because they only need to pay the penalty once. This changes
the behaviour by setting the penalty according to the number of
words in the token. This should get rid of search interpretations
with low chance of matching.

This also fixes handling of exact term matching. We now match against
all exact terms of the query, not just a couple of them collected
while building the interpretations.

Also adds a penalty to very short postcodes.

lib/TokenList.php

@@ -80,6 +80,21 @@ class TokenList
         return isset($this->aTokens[$sWord]) ? $this->aTokens[$sWord] : array();
     }
 
+    public function getFullWordIDs()
+    {
+        $ids = array();
+
+        foreach($this->aTokens as $aTokenList) {
+            foreach($aTokenList as $oToken) {
+                if (is_a($oToken, '\Nominatim\Token\Word') && !$oToken->bPartial) {
+                    $ids[$oToken->iId] = $oToken->iId;
+                }
+            }
+        }
+
+        return $ids;
+    }
+
     /**
      * Add token information from the word table in the database.
      *
@@ -151,7 +166,8 @@ class TokenList
                 $oToken = new Token\Word(
                     $iId,
                     $aWord['word_token'][0] != ' ',
-                    (int) $aWord['count']
+                    (int) $aWord['count'],
+                    substr_count($aWord['word_token'], ' ')
                 );
             }