be more strict what areas make up an address

Exclude boundaries that touch a line in only one point and
that touch areas only along the boundary.

Fixes #1900.

diff --git a/sql/partition-functions.src.sql b/sql/partition-functions.src.sql
index 34b4d390750798cb506f5fe11507535c0c20278e..17db9c1681060ab8f1d2fc2f667b8e595990d3d9 100644 (file)
--- a/sql/partition-functions.src.sql
+++ b/sql/partition-functions.src.sql
@@ -10,6 +10,28 @@ CREATE TYPE nearfeaturecentr AS (
   centroid GEOMETRY
 );
 
+        -- feature intersects geoemtry
+        -- for areas and linestrings they must touch at least along a line
+CREATE OR REPLACE FUNCTION is_relevant_geometry(de9im TEXT, geom_type TEXT)
+RETURNS BOOLEAN
+AS $$
+BEGIN
+  IF substring(de9im from 1 for 2) != 'FF' THEN
+    RETURN TRUE;
+  END IF;
+
+  IF geom_type = 'ST_Point' THEN
+    RETURN substring(de9im from 4 for 1) = '0';
+  END IF;
+
+  IF geom_type in ('ST_LineString', 'ST_MultiLineString') THEN
+    RETURN substring(de9im from 4 for 1) = '1';
+  END IF;
+
+  RETURN substring(de9im from 4 for 1) = '2';
+END
+$$ LANGUAGE plpgsql IMMUTABLE;
+
 create or replace function getNearFeatures(in_partition INTEGER, feature GEOMETRY, maxrank INTEGER, isin_tokens INT[]) RETURNS setof nearfeaturecentr AS $$
 DECLARE
   r nearfeaturecentr%rowtype;
@@ -20,7 +42,8 @@ BEGIN
     FOR r IN 
       SELECT place_id, keywords, rank_address, rank_search, min(ST_Distance(feature, centroid)) as distance, isguess, postcode, centroid
       FROM location_area_large_-partition-
-      WHERE ST_Intersects(geometry, feature)
+      WHERE geometry && feature
+        AND is_relevant_geometry(ST_Relate(geometry, feature), ST_GeometryType(feature))
         AND rank_search < maxrank AND rank_address < maxrank
       GROUP BY place_id, keywords, rank_address, rank_search, isguess, postcode, centroid
       ORDER BY rank_address, isin_tokens && keywords desc, isguess asc,

diff --git a/test/bdd/db/import/addressing.feature b/test/bdd/db/import/addressing.feature
index f4297f30a34deda9024edf85e58385fbd5d7454a..ddb7b438be69e1f7db5fddcdbff7c25c2d89d687 100644 (file)
--- a/test/bdd/db/import/addressing.feature
+++ b/test/bdd/db/import/addressing.feature
@@ -21,6 +21,99 @@ Feature: Address computation
             | W1     | W10     | 10                  |
             | W1     | W11     | 10                  |
 
+
+    Scenario: Roads following a boundary should contain both states
+        Given the grid
+            | 1 |   |   | 2 |   | 3 |
+            |   |   | 8 | 7 |   |   |
+            | 4 |   |   | 5 |   | 6 |
+        And the named places
+            | osm | class   | type | geometry |
+            | W1  | highway | road | 2, 7, 8  |
+        And the named places
+            | osm | class    | type           | admin | geometry      |
+            | W10 | boundary | administrative | 5     | (1, 2, 5, 4, 1) |
+            | W11 | boundary | administrative | 5     | (2, 3, 6, 5, 2) |
+        When importing
+        Then place_addressline contains
+            | object | address | cached_rank_address |
+            | W1     | W10     | 10                  |
+            | W1     | W11     | 10                  |
+
+    Scenario: Roads should not contain boundaries they touch in a end point
+        Given the grid
+            | 1 |   |   | 2 |   | 3 |
+            |   | 7 |   | 8 |   |   |
+            | 4 |   |   | 5 |   | 6 |
+        And the named places
+            | osm | class   | type | geometry |
+            | W1  | highway | road | 7, 8     |
+        And the named places
+            | osm | class    | type           | admin | geometry      |
+            | W10 | boundary | administrative | 5     | (1, 2, 8, 5, 4, 1) |
+            | W11 | boundary | administrative | 5     | (2, 3, 6, 5, 8, 2) |
+        When importing
+        Then place_addressline contains
+            | object | address | cached_rank_address |
+            | W1     | W10     | 10                  |
+        Then place_addressline doesn't contain
+            | object | address |
+            | W1     | W11     |
+
+    Scenario: Roads should not contain boundaries they touch in a end point
+        Given the grid
+            | 1 |   |   | 2 |   | 3 |
+            |   | 7 |   | 8 |   |   |
+            | 4 |   | 9 | 5 |   | 6 |
+        And the named places
+            | osm | class   | type | geometry |
+            | W1  | highway | road | 7, 8, 9     |
+        And the named places
+            | osm | class    | type           | admin | geometry      |
+            | W10 | boundary | administrative | 5     | (1, 2, 8, 5, 4, 1) |
+            | W11 | boundary | administrative | 5     | (2, 3, 6, 5, 8, 2) |
+        When importing
+        Then place_addressline contains
+            | object | address | cached_rank_address |
+            | W1     | W10     | 10                  |
+        Then place_addressline doesn't contain
+            | object | address |
+            | W1     | W11     |
+
+    Scenario: Locality points should contain all boundaries they touch
+        Given the grid
+            | 1 |   |   | 2 |   | 3 |
+            |   |   |   | 8 |   |   |
+            | 4 |   |   | 5 |   | 6 |
+        And the named places
+            | osm | class | type     | geometry |
+            | N1  | place | locality | 8        |
+        And the named places
+            | osm | class    | type           | admin | geometry      |
+            | W10 | boundary | administrative | 5     | (1, 2, 8, 5, 4, 1) |
+            | W11 | boundary | administrative | 5     | (2, 3, 6, 5, 8, 2) |
+        When importing
+        Then place_addressline contains
+            | object | address | cached_rank_address |
+            | N1     | W10     | 10                  |
+            | N1     | W11     | 10                  |
+
+    Scenario: Areas should not contain boundaries they touch
+        Given the grid
+            | 1 |   |   | 2 |   | 3 |
+            |   |   |   |   |   |   |
+            | 4 |   |   | 5 |   | 6 |
+        And the named places
+            | osm | class    | type           | geometry      |
+            | W1  | landuse  | industrial     | (1, 2, 5, 4, 1) |
+        And the named places
+            | osm | class    | type           | admin | geometry      |
+            | W10 | boundary | administrative | 5     | (2, 3, 6, 5, 2) |
+        When importing
+        Then place_addressline doesn't contain
+            | object | address |
+            | W1     | W10     |
+
     Scenario: buildings with only addr:postcodes do not appear in the address of a way
         Given the scene admin-areas
         And the named places