Merge pull request #3356 from lonvia/use-date-from-osm2pgsql-prop

[nominatim.git] / nominatim / db / sql_preprocessor.py

diff --git a/nominatim/db/sql_preprocessor.py b/nominatim/db/sql_preprocessor.py
index b450422da09396cb687cfe50750490311f82a31d..af5bc3357959abf52b9518e83144403e2150564b 100644 (file)
--- a/nominatim/db/sql_preprocessor.py
+++ b/nominatim/db/sql_preprocessor.py
@@ -7,10 +7,11 @@
 """
 Preprocessing of SQL files.
 """
-from typing import Set, Dict, Any
+from typing import Set, Dict, Any, cast
 import jinja2
 
 from nominatim.db.connection import Connection
+from nominatim.db.async_connection import WorkerPool
 from nominatim.config import Configuration
 
 def _get_partitions(conn: Connection) -> Set[int]:
@@ -27,13 +28,24 @@ def _get_partitions(conn: Connection) -> Set[int]:
 
 def _get_tables(conn: Connection) -> Set[str]:
     """ Return the set of tables currently in use.
-        Only includes non-partitioned
     """
     with conn.cursor() as cur:
         cur.execute("SELECT tablename FROM pg_tables WHERE schemaname = 'public'")
 
         return set((row[0] for row in list(cur)))
 
+def _get_middle_db_format(conn: Connection, tables: Set[str]) -> str:
+    """ Returns the version of the slim middle tables.
+    """
+    if 'osm2pgsql_properties' not in tables:
+        return '1'
+
+    with conn.cursor() as cur:
+        cur.execute("SELECT value FROM osm2pgsql_properties WHERE property = 'db_format'")
+        row = cur.fetchone()
+
+        return cast(str, row[0]) if row is not None else '1'
+
 
 def _setup_tablespace_sql(config: Configuration) -> Dict[str, str]:
     """ Returns a dict with tablespace expressions for the different tablespace
@@ -56,9 +68,11 @@ def _setup_postgresql_features(conn: Connection) -> Dict[str, Any]:
     """
     pg_version = conn.server_version_tuple()
     postgis_version = conn.postgis_version_tuple()
+    pg11plus = pg_version >= (11, 0, 0)
+    ps3 = postgis_version >= (3, 0)
     return {
-        'has_index_non_key_column': pg_version >= (11, 0, 0),
-        'spgist_geom' : 'SPGIST' if postgis_version >= (3, 0) else 'GIST'
+        'has_index_non_key_column': pg11plus,
+        'spgist_geom' : 'SPGIST' if pg11plus and ps3 else 'GIST'
     }
 
 class SQLPreprocessor:
@@ -81,12 +95,25 @@ class SQLPreprocessor:
         db_info['tables'] = _get_tables(conn)
         db_info['reverse_only'] = 'search_name' not in db_info['tables']
         db_info['tablespace'] = _setup_tablespace_sql(config)
+        db_info['middle_db_format'] = _get_middle_db_format(conn, db_info['tables'])
 
         self.env.globals['config'] = config
         self.env.globals['db'] = db_info
         self.env.globals['postgres'] = _setup_postgresql_features(conn)
 
 
+    def run_string(self, conn: Connection, template: str, **kwargs: Any) -> None:
+        """ Execute the given SQL template string on the connection.
+            The keyword arguments may supply additional parameters
+            for preprocessing.
+        """
+        sql = self.env.from_string(template).render(**kwargs)
+
+        with conn.cursor() as cur:
+            cur.execute(sql)
+        conn.commit()
+
+
     def run_sql_file(self, conn: Connection, name: str, **kwargs: Any) -> None:
         """ Execute the given SQL file on the connection. The keyword arguments
             may supply additional parameters for preprocessing.
@@ -96,3 +123,21 @@ class SQLPreprocessor:
         with conn.cursor() as cur:
             cur.execute(sql)
         conn.commit()
+
+
+    def run_parallel_sql_file(self, dsn: str, name: str, num_threads: int = 1,
+                              **kwargs: Any) -> None:
+        """ Execute the given SQL files using parallel asynchronous connections.
+            The keyword arguments may supply additional parameters for
+            preprocessing.
+
+            After preprocessing the SQL code is cut at lines containing only
+            '---'. Each chunk is sent to one of the `num_threads` workers.
+        """
+        sql = self.env.get_template(name).render(**kwargs)
+
+        parts = sql.split('\n---\n')
+
+        with WorkerPool(dsn, num_threads) as pool:
+            for part in parts:
+                pool.next_free_worker().perform(part)