make get_addressdata calls cachable

[nominatim.git] / nominatim / api / results.py

diff --git a/nominatim/api/results.py b/nominatim/api/results.py
index 1e77d0be5aba5b6b6c9ba7118380956adba90d7d..2fe547112b07e16932b2d5d84243bf816fb7ef30 100644 (file)
--- a/nominatim/api/results.py
+++ b/nominatim/api/results.py
@@ -11,14 +11,14 @@ Data classes are part of the public API while the functions are for
 internal use only. That's why they are implemented as free-standing functions
 instead of member functions.
 """
 internal use only. That's why they are implemented as free-standing functions
 instead of member functions.
 """

-from typing import Optional, Tuple, Dict, Sequence, TypeVar, Type, List, Any
+from typing import Optional, Tuple, Dict, Sequence, TypeVar, Type, List, Any, Union

 import enum
 import dataclasses
 import datetime as dt
 
 import sqlalchemy as sa
 
 import enum
 import dataclasses
 import datetime as dt
 
 import sqlalchemy as sa
 

-from nominatim.typing import SaSelect, SaRow
+from nominatim.typing import SaSelect, SaRow, SaColumn

 from nominatim.api.types import Point, Bbox, LookupDetails
 from nominatim.api.connection import SearchConnection
 from nominatim.api.logging import log
 from nominatim.api.types import Point, Bbox, LookupDetails
 from nominatim.api.connection import SearchConnection
 from nominatim.api.logging import log


@@ -27,6 +27,24 @@ from nominatim.api.localization import Locales
 # This file defines complex result data classes.
 # pylint: disable=too-many-instance-attributes
 
 # This file defines complex result data classes.
 # pylint: disable=too-many-instance-attributes
 

+def _mingle_name_tags(names: Optional[Dict[str, str]]) -> Optional[Dict[str, str]]:
+    """ Mix-in names from linked places, so that they show up
+        as standard names where necessary.
+    """
+    if not names:
+        return None
+
+    out = {}
+    for k, v in names.items():
+        if k.startswith('_place_'):
+            outkey = k[7:]
+            out[k if outkey in names else outkey] = v
+        else:
+            out[k] = v
+
+    return out
+
+

 class SourceTable(enum.Enum):
     """ Enumeration of kinds of results.
     """
 class SourceTable(enum.Enum):
     """ Enumeration of kinds of results.
     """


@@ -210,6 +228,12 @@ class SearchResults(List[SearchResult]):
         May be empty when no result was found.
     """
 
         May be empty when no result was found.
     """
 

+    def localize(self, locales: Locales) -> None:
+        """ Apply the given locales to all results.
+        """
+        for result in self:
+            result.localize(locales)
+

 
 def _filter_geometries(row: SaRow) -> Dict[str, str]:
     return {k[9:]: v for k, v in row._mapping.items() # pylint: disable=W0212
 
 def _filter_geometries(row: SaRow) -> Dict[str, str]:
     return {k[9:]: v for k, v in row._mapping.items() # pylint: disable=W0212


@@ -229,7 +253,7 @@ def create_from_placex_row(row: Optional[SaRow],
                       place_id=row.place_id,
                       osm_object=(row.osm_type, row.osm_id),
                       category=(row.class_, row.type),
                       place_id=row.place_id,
                       osm_object=(row.osm_type, row.osm_id),
                       category=(row.class_, row.type),

-                      names=row.name,
+                      names=_mingle_name_tags(row.name),

                       address=row.address,
                       extratags=row.extratags,
                       housenumber=row.housenumber,
                       address=row.address,
                       extratags=row.extratags,
                       housenumber=row.housenumber,


@@ -239,7 +263,7 @@ def create_from_placex_row(row: Optional[SaRow],
                       rank_search=row.rank_search,
                       importance=row.importance,
                       country_code=row.country_code,
                       rank_search=row.rank_search,
                       importance=row.importance,
                       country_code=row.country_code,

-                      centroid=Point.from_wkb(row.centroid.data),
+                      centroid=Point.from_wkb(row.centroid),

                       geometry=_filter_geometries(row))
 
 
                       geometry=_filter_geometries(row))
 
 


@@ -264,7 +288,7 @@ def create_from_osmline_row(row: Optional[SaRow],
                      address=row.address,
                      postcode=row.postcode,
                      country_code=row.country_code,
                      address=row.address,
                      postcode=row.postcode,
                      country_code=row.country_code,

-                     centroid=Point.from_wkb(row.centroid.data),
+                     centroid=Point.from_wkb(row.centroid),

                      geometry=_filter_geometries(row))
 
     if hnr is None:
                      geometry=_filter_geometries(row))
 
     if hnr is None:


@@ -297,7 +321,7 @@ def create_from_tiger_row(row: Optional[SaRow],
                      category=('place', 'houses' if hnr is None else 'house'),
                      postcode=row.postcode,
                      country_code='us',
                      category=('place', 'houses' if hnr is None else 'house'),
                      postcode=row.postcode,
                      country_code='us',

-                     centroid=Point.from_wkb(row.centroid.data),
+                     centroid=Point.from_wkb(row.centroid),

                      geometry=_filter_geometries(row))
 
     if hnr is None:
                      geometry=_filter_geometries(row))
 
     if hnr is None:


@@ -326,7 +350,7 @@ def create_from_postcode_row(row: Optional[SaRow],
                       rank_search=row.rank_search,
                       rank_address=row.rank_address,
                       country_code=row.country_code,
                       rank_search=row.rank_search,
                       rank_address=row.rank_address,
                       country_code=row.country_code,

-                      centroid=Point.from_wkb(row.centroid.data),
+                      centroid=Point.from_wkb(row.centroid),

                       geometry=_filter_geometries(row))
 
 
                       geometry=_filter_geometries(row))
 
 


@@ -341,7 +365,7 @@ def create_from_country_row(row: Optional[SaRow],
 
     return class_type(source_table=SourceTable.COUNTRY,
                       category=('place', 'country'),
 
     return class_type(source_table=SourceTable.COUNTRY,
                       category=('place', 'country'),

-                      centroid=Point.from_wkb(row.centroid.data),
+                      centroid=Point.from_wkb(row.centroid),

                       names=row.name,
                       rank_address=4, rank_search=4,
                       country_code=row.country_code)
                       names=row.name,
                       rank_address=4, rank_search=4,
                       country_code=row.country_code)


@@ -378,10 +402,8 @@ def _result_row_to_address_row(row: SaRow) -> AddressLine:
     if hasattr(row, 'place_type') and row.place_type:
         extratags['place'] = row.place_type
 
     if hasattr(row, 'place_type') and row.place_type:
         extratags['place'] = row.place_type
 

-    names = row.name
+    names = _mingle_name_tags(row.name) or {}

     if getattr(row, 'housenumber', None) is not None:
     if getattr(row, 'housenumber', None) is not None:

-        if names is None:
-            names = {}

         names['housenumber'] = row.housenumber
 
     return AddressLine(place_id=row.place_id,
         names['housenumber'] = row.housenumber
 
     return AddressLine(place_id=row.place_id,


@@ -396,46 +418,74 @@ def _result_row_to_address_row(row: SaRow) -> AddressLine:
                        distance=row.distance)
 
 
                        distance=row.distance)
 
 

+def _get_housenumber_details(results: List[BaseResultT]) -> Tuple[List[int], List[int]]:
+    places = []
+    hnrs = []
+    for result in results:
+        if result.place_id:
+            housenumber = -1
+            if result.source_table in (SourceTable.TIGER, SourceTable.OSMLINE):
+                if result.housenumber is not None:
+                    housenumber = int(result.housenumber)
+                elif result.extratags is not None and 'startnumber' in result.extratags:
+                    # details requests do not come with a specific house number
+                    housenumber = int(result.extratags['startnumber'])
+            places.append(result.place_id)
+            hnrs.append(housenumber)
+
+    return places, hnrs
+
+

 async def complete_address_details(conn: SearchConnection, results: List[BaseResultT]) -> None:
     """ Retrieve information about places that make up the address of the result.
     """
 async def complete_address_details(conn: SearchConnection, results: List[BaseResultT]) -> None:
     """ Retrieve information about places that make up the address of the result.
     """

-    def get_hnr(result: BaseResult) -> Tuple[int, int]:
-        housenumber = -1
-        if result.source_table in (SourceTable.TIGER, SourceTable.OSMLINE):
-            if result.housenumber is not None:
-                housenumber = int(result.housenumber)
-            elif result.extratags is not None and 'startnumber' in result.extratags:
-                # details requests do not come with a specific house number
-                housenumber = int(result.extratags['startnumber'])
-        assert result.place_id
-        return result.place_id, housenumber
-
-    data: List[Tuple[Any, ...]] = [get_hnr(r) for r in results if r.place_id]
-
-    if not data:
+    places, hnrs = _get_housenumber_details(results)
+
+    if not places:

         return
 
         return
 

-    values = sa.values(sa.column('place_id', type_=sa.Integer),
-                       sa.column('housenumber', type_=sa.Integer),
-                       name='places',
-                       literal_binds=True).data(data)
-
-    sfn = sa.func.get_addressdata(values.c.place_id, values.c.housenumber)\
-                .table_valued( # type: ignore[no-untyped-call]
-                    sa.column('place_id', type_=sa.Integer),
-                    'osm_type',
-                    sa.column('osm_id', type_=sa.BigInteger),
-                    sa.column('name', type_=conn.t.types.Composite),
-                    'class', 'type', 'place_type',
-                    sa.column('admin_level', type_=sa.Integer),
-                    sa.column('fromarea', type_=sa.Boolean),
-                    sa.column('isaddress', type_=sa.Boolean),
-                    sa.column('rank_address', type_=sa.SmallInteger),
-                    sa.column('distance', type_=sa.Float),
-                    joins_implicitly=True)
-
-    sql = sa.select(values.c.place_id.label('result_place_id'), sfn)\
-            .order_by(values.c.place_id,
+    def _get_addressdata(place_id: Union[int, SaColumn], hnr: Union[int, SaColumn]) -> Any:
+        return sa.func.get_addressdata(place_id, hnr)\
+                    .table_valued( # type: ignore[no-untyped-call]
+                        sa.column('place_id', type_=sa.Integer),
+                        'osm_type',
+                        sa.column('osm_id', type_=sa.BigInteger),
+                        sa.column('name', type_=conn.t.types.Composite),
+                        'class', 'type', 'place_type',
+                        sa.column('admin_level', type_=sa.Integer),
+                        sa.column('fromarea', type_=sa.Boolean),
+                        sa.column('isaddress', type_=sa.Boolean),
+                        sa.column('rank_address', type_=sa.SmallInteger),
+                        sa.column('distance', type_=sa.Float),
+                        joins_implicitly=True)
+
+
+    if len(places) == 1:
+        # Optimized case for exactly one result (reverse)
+        sql = sa.select(_get_addressdata(places[0], hnrs[0]))\
+                .order_by(sa.column('rank_address').desc(),
+                          sa.column('isaddress').desc())
+
+        alines = AddressLines()
+        for row in await conn.execute(sql):
+            alines.append(_result_row_to_address_row(row))
+
+        for result in results:
+            if result.place_id == places[0]:
+                result.address_rows = alines
+                return
+
+
+    darray = sa.func.unnest(conn.t.types.to_array(places), conn.t.types.to_array(hnrs))\
+                    .table_valued( # type: ignore[no-untyped-call]
+                       sa.column('place_id', type_= sa.Integer),
+                       sa.column('housenumber', type_= sa.Integer)
+                    ).render_derived()
+
+    sfn = _get_addressdata(darray.c.place_id, darray.c.housenumber)
+
+    sql = sa.select(darray.c.place_id.label('result_place_id'), sfn)\
+            .order_by(darray.c.place_id,

                       sa.column('rank_address').desc(),
                       sa.column('isaddress').desc())
 
                       sa.column('rank_address').desc(),
                       sa.column('isaddress').desc())