Merge pull request #3328 from lonvia/word-count-into-new-table

[nominatim.git] / nominatim / tokenizer / legacy_tokenizer.py

diff --git a/nominatim/tokenizer/legacy_tokenizer.py b/nominatim/tokenizer/legacy_tokenizer.py
index e09700d9ddb8856a8d52fc6f7de1e9b748b9bbd7..2d28a8b29891623e72e7f8c2f0f7b7c9cafbd160 100644 (file)
--- a/nominatim/tokenizer/legacy_tokenizer.py
+++ b/nominatim/tokenizer/legacy_tokenizer.py
@@ -210,7 +210,7 @@ class LegacyTokenizer(AbstractTokenizer):
             self._save_config(conn, config)
 
 
-    def update_statistics(self) -> None:
+    def update_statistics(self, _: Configuration) -> None:
         """ Recompute the frequency of full words.
         """
         with connect(self.dsn) as conn:
@@ -256,6 +256,16 @@ class LegacyTokenizer(AbstractTokenizer):
         return LegacyNameAnalyzer(self.dsn, normalizer)
 
 
+    def most_frequent_words(self, conn: Connection, num: int) -> List[str]:
+        """ Return a list of the `num` most frequent full words
+            in the database.
+        """
+        with conn.cursor() as cur:
+            cur.execute(""" SELECT word FROM word WHERE word is not null
+                              ORDER BY search_name_count DESC LIMIT %s""", (num,))
+            return list(s[0] for s in cur)
+
+
     def _install_php(self, config: Configuration, overwrite: bool = True) -> None:
         """ Install the php script for the tokenizer.
         """