Merge remote-tracking branch 'upstream/master'

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

diff --git a/src/nominatim_db/indexer/indexer.py b/src/nominatim_db/indexer/indexer.py
index 9d42922b8e4f09372bc395dbcf209b41e7890030..d467efbd6e27b7dbaa207ee042d2ea3ac2cadcf9 100644 (file)
--- a/src/nominatim_db/indexer/indexer.py
+++ b/src/nominatim_db/indexer/indexer.py
@@ -21,6 +21,7 @@ from . import runners
 
 LOG = logging.getLogger()
 
 
 LOG = logging.getLogger()
 

+

 class Indexer:
     """ Main indexing routine.
     """
 class Indexer:
     """ Main indexing routine.
     """


@@ -30,7 +31,6 @@ class Indexer:
         self.tokenizer = tokenizer
         self.num_threads = num_threads
 
         self.tokenizer = tokenizer
         self.num_threads = num_threads
 

-

     def has_pending(self) -> bool:
         """ Check if any data still needs indexing.
             This function must only be used after the import has finished.
     def has_pending(self) -> bool:
         """ Check if any data still needs indexing.
             This function must only be used after the import has finished.


@@ -41,7 +41,6 @@ class Indexer:
                 cur.execute("SELECT 'a' FROM placex WHERE indexed_status > 0 LIMIT 1")
                 return cur.rowcount > 0
 
                 cur.execute("SELECT 'a' FROM placex WHERE indexed_status > 0 LIMIT 1")
                 return cur.rowcount > 0
 

-

     async def index_full(self, analyse: bool = True) -> None:
         """ Index the complete database. This will first index boundaries
             followed by all other objects. When `analyse` is True, then the
     async def index_full(self, analyse: bool = True) -> None:
         """ Index the complete database. This will first index boundaries
             followed by all other objects. When `analyse` is True, then the


@@ -75,7 +74,6 @@ class Indexer:
                 if not self.has_pending():
                     break
 
                 if not self.has_pending():
                     break
 

-

     async def index_boundaries(self, minrank: int, maxrank: int) -> int:
         """ Index only administrative boundaries within the given rank range.
         """
     async def index_boundaries(self, minrank: int, maxrank: int) -> int:
         """ Index only administrative boundaries within the given rank range.
         """


@@ -138,7 +136,6 @@ class Indexer:
                                    (minrank, maxrank))
                 total_tuples = {row.rank_address: row.count for row in cur}
 
                                    (minrank, maxrank))
                 total_tuples = {row.rank_address: row.count for row in cur}
 

-

         with self.tokenizer.name_analyzer() as analyzer:
             for rank in range(max(1, minrank), maxrank + 1):
                 if rank >= 30:
         with self.tokenizer.name_analyzer() as analyzer:
             for rank in range(max(1, minrank), maxrank + 1):
                 if rank >= 30:


@@ -156,7 +153,6 @@ class Indexer:
 
         return total
 
 
         return total
 

-

     async def index_postcodes(self) -> int:
         """Index the entries of the location_postcode table.
         """
     async def index_postcodes(self) -> int:
         """Index the entries of the location_postcode table.
         """


@@ -164,7 +160,6 @@ class Indexer:
 
         return await self._index(runners.PostcodeRunner(), batch=20)
 
 
         return await self._index(runners.PostcodeRunner(), batch=20)
 

-

     def update_status_table(self) -> None:
         """ Update the status in the status table to 'indexed'.
         """
     def update_status_table(self) -> None:
         """ Update the status in the status table to 'indexed'.
         """


@@ -193,7 +188,7 @@ class Indexer:
 
         if total_tuples > 0:
             async with await psycopg.AsyncConnection.connect(
 
         if total_tuples > 0:
             async with await psycopg.AsyncConnection.connect(

-                                 self.dsn, row_factory=psycopg.rows.dict_row) as aconn,\
+                                 self.dsn, row_factory=psycopg.rows.dict_row) as aconn, \

                        QueryPool(self.dsn, self.num_threads, autocommit=True) as pool:
                 fetcher_time = 0.0
                 tstart = time.time()
                        QueryPool(self.dsn, self.num_threads, autocommit=True) as pool:
                 fetcher_time = 0.0
                 tstart = time.time()


@@ -224,7 +219,6 @@ class Indexer:
 
         return progress.done()
 
 
         return progress.done()
 

-

     def _prepare_indexing(self, runner: runners.Runner) -> int:
         with connect(self.dsn) as conn:
             hstore_info = psycopg.types.TypeInfo.fetch(conn, "hstore")
     def _prepare_indexing(self, runner: runners.Runner) -> int:
         with connect(self.dsn) as conn:
             hstore_info = psycopg.types.TypeInfo.fetch(conn, "hstore")