Merge pull request #2736 from lonvia/reverse-interpolation-index-order

[nominatim.git] / nominatim / indexer / indexer.py

diff --git a/nominatim/indexer/indexer.py b/nominatim/indexer/indexer.py
index 5ab0eac3dca5701562085ffecdce652e110f9cfd..555f8704a19c6796da4b97a724cd363d183f7f12 100644 (file)
--- a/nominatim/indexer/indexer.py
+++ b/nominatim/indexer/indexer.py
@@ -1,3 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# This file is part of Nominatim. (https://nominatim.org)
+#
+# Copyright (C) 2022 by the Nominatim developer community.
+# For a full list of authors see the git log.
 """
 Main work horse for indexing (computing addresses) the database.
 """
@@ -91,8 +97,19 @@ class Indexer:
         self.num_threads = num_threads
 
 
+    def has_pending(self):
+        """ Check if any data still needs indexing.
+            This function must only be used after the import has finished.
+            Otherwise it will be very expensive.
+        """
+        with connect(self.dsn) as conn:
+            with conn.cursor() as cur:
+                cur.execute("SELECT 'a' FROM placex WHERE indexed_status > 0 LIMIT 1")
+                return cur.rowcount > 0
+
+
     def index_full(self, analyse=True):
-        """ Index the complete database. This will first index boudnaries
+        """ Index the complete database. This will first index boundaries
             followed by all other objects. When `analyse` is True, then the
             database will be analysed at the appropriate places to
             ensure that database statistics are updated.
@@ -100,13 +117,10 @@ class Indexer:
         with connect(self.dsn) as conn:
             conn.autocommit = True
 
-            if analyse:
-                def _analyze():
+            def _analyze():
+                if analyse:
                     with conn.cursor() as cur:
                         cur.execute('ANALYZE')
-            else:
-                def _analyze():
-                    pass
 
             self.index_by_rank(0, 4)
             _analyze()
@@ -146,15 +160,12 @@ class Indexer:
                     minrank, maxrank, self.num_threads)
 
         with self.tokenizer.name_analyzer() as analyzer:
-            for rank in range(max(1, minrank), maxrank):
-                self._index(runners.RankRunner(rank, analyzer))
+            for rank in range(max(1, minrank), maxrank + 1):
+                self._index(runners.RankRunner(rank, analyzer), 20 if rank == 30 else 1)
 
             if maxrank == 30:
                 self._index(runners.RankRunner(0, analyzer))
                 self._index(runners.InterpolationRunner(analyzer), 20)
-                self._index(runners.RankRunner(30, analyzer), 20)
-            else:
-                self._index(runners.RankRunner(maxrank, analyzer))
 
 
     def index_postcodes(self):
@@ -206,7 +217,7 @@ class Indexer:
 
                                 # And insert the curent batch
                                 for idx in range(0, len(places), batch):
-                                    part = places[idx:idx+batch]
+                                    part = places[idx:idx + batch]
                                     LOG.debug("Processing places: %s", str(part))
                                     runner.index_places(pool.next_free_worker(), part)
                                     progress.add(len(part))