Update duckdb query examples

docs/getting-data/duckdb.mdx

@@ -9,7 +9,8 @@ import Peaks from '!!raw-loader!@site/src/queries/duckdb/mountain_peaks.sql';
 import DetroitBuildings from '!!raw-loader!@site/src/queries/duckdb/buildings_detroit.sql';
 import CountyGeometries from '!!raw-loader!@site/src/queries/duckdb/county_level_geometries.sql';
 import NewYorkPizza from '!!raw-loader!@site/src/queries/duckdb/new_york_pizza.sql';
-import ParisRoads from '!!raw-loader!@site/src/queries/duckdb/paris_roads.sql';
+import ParisRoadsContained from '!!raw-loader!@site/src/queries/duckdb/paris_roads_contained.sql';
+import ParisRoadsIntersecting from '!!raw-loader!@site/src/queries/duckdb/paris_roads_intersecting.sql';
 import WriteGeoparquet from '!!raw-loader!@site/src/queries/duckdb/write_geoparquet.sql';
 import BuildingsInDivision from '!!raw-loader!@site/src/queries/duckdb/buildings_in_division_area.sql';
 
@@ -46,9 +47,13 @@ Access Overture buildings data hosted on Azure to download named buildings aroun
 
 <TabItem value="Roads" label="Roads">
 
-Download roads in Paris around the _Arc de Triomphe_ and save as GeoJSON.
+Download all roads intersecting a given bounding box around the Arc de Triomphe in Paris and save as GeoJSON.
 
-<QueryBuilder query={ParisRoads}></QueryBuilder>
+<QueryBuilder query={ParisRoadsIntersecting}></QueryBuilder>
+_Note: This will result in a GeoJSON file that contains all road segments that intersect the bounding box, not just road segments contained within the bounding box._
+
+To download only roads contained within that bounding box around the Arc de Triomphe in Paris, use the following:
+<QueryBuilder query={ParisRoadsContained}></QueryBuilder>
 </TabItem>
 
 <TabItem value="Mountains" label="Mountains">

src/queries/duckdb/buildings_detroit.sql

@@ -1,14 +1,18 @@
-LOAD spatial; --noqa
+LOAD spatial; -- noqa
+
+SET s3_region='us-west-2';
 
 COPY(
   SELECT
     id,
     names.primary as primary_name,
     height,
     geometry
-  FROM read_parquet('az://overturemapswestus2.blob.core.windows.net/release/__OVERTURE_RELEASE/theme=buildings/type=building/*', filename=true, hive_partitioning=1)
-  WHERE names.primary IS NOT NULL
-  AND bbox.xmin BETWEEN -84.36 AND -82.42
-  AND bbox.ymin BETWEEN 41.71 AND 43.33
+  FROM
+    read_parquet('az://overturemapswestus2.blob.core.windows.net/release/__OVERTURE_RELEASE/theme=buildings/type=building/*', filename=true, hive_partitioning=1)
+  WHERE
+    names.primary IS NOT NULL
+    AND bbox.xmin BETWEEN -84.36 AND -82.42
+    AND bbox.ymin BETWEEN 41.71 AND 43.33
   LIMIT 100
 ) TO 'detroit_buildings.geojsonseq' WITH (FORMAT GDAL, DRIVER 'GeoJSONSeq');

src/queries/duckdb/county_level_geometries.sql

@@ -1,16 +1,17 @@
 LOAD spatial; -- noqa
+
 SET s3_region='us-west-2';
 
 COPY(
-    SELECT
-        id,
-        division_id,
-        names.primary,
-        geometry  -- DuckDB v.1.1.0 will autoload this as a `geometry` type
-        FROM
-            read_parquet('s3://overturemaps-us-west-2/release/__OVERTURE_RELEASE/theme=divisions/type=division_area/*', hive_partitioning=1)
-        WHERE
-            subtype = 'county'
-            AND country = 'US'
-            AND region = 'US-PA'
+  SELECT
+    id,
+    division_id,
+    names.primary,
+    geometry  -- DuckDB v.1.1.0 will autoload this as a `geometry` type
+  FROM
+    read_parquet('s3://overturemaps-us-west-2/release/__OVERTURE_RELEASE/theme=divisions/type=division_area/*', hive_partitioning=1)
+  WHERE
+    subtype = 'county'
+    AND country = 'US'
+    AND region = 'US-PA'
 ) TO 'pennsylvania_counties.gpkg' WITH (FORMAT GDAL, DRIVER 'GPKG');

src/queries/duckdb/mountain_peaks.sql

@@ -3,14 +3,17 @@ LOAD spatial; -- noqa
 SET s3_region='us-west-2';
 
 COPY(
-    SELECT
-       id,
-       names.primary as name,
-       CAST(elevation * 3.28084 AS INT) AS elevation_ft,
-       geometry -- DuckDB v.1.1.0 will autoload this as a `geometry` type
-    FROM read_parquet('s3://overturemaps-us-west-2/release/__OVERTURE_RELEASE/theme=base/type=land/*', filename=true, hive_partitioning=1)
-    WHERE subtype = 'physical' AND class IN ('peak','volcano') AND elevation IS NOT NULL
+  SELECT
+    id,
+    names.primary as name,
+    CAST(elevation * 3.28084 AS INT) AS elevation_ft,
+    geometry -- DuckDB v.1.1.0 will autoload this as a `geometry` type
+  FROM
+    read_parquet('s3://overturemaps-us-west-2/release/__OVERTURE_RELEASE/theme=base/type=land/*', filename=true, hive_partitioning=1)
+  WHERE
+    subtype = 'physical'
+    AND class IN ('peak','volcano')
+    AND elevation IS NOT NULL
     AND bbox.xmin BETWEEN -124.71 AND -116.47
     AND bbox.ymin BETWEEN 41.99 AND 46.30
-) TO 'oregon_peaks.geojson'
-WITH (FORMAT GDAL, DRIVER 'GeoJSON');
+) TO 'oregon_peaks.geojson' WITH (FORMAT GDAL, DRIVER 'GeoJSON');

src/queries/duckdb/new_york_pizza.sql

@@ -3,15 +3,16 @@ LOAD spatial; -- noqa
 SET s3_region='us-west-2';
 
 COPY(                                       -- COPY <query> TO <output> saves the results to disk.
-    SELECT
-       id,
-       names.primary as name,
-       confidence AS confidence,
-       CAST(socials AS JSON) as socials,    -- Ensure each attribute can be serialized to JSON
-       geometry                             -- DuckDB understands this to be a geometry type
-    FROM read_parquet('s3://overturemaps-us-west-2/release/__OVERTURE_RELEASE/theme=places/type=place/*', filename=true, hive_partitioning=1)
-    WHERE categories.primary = 'pizza_restaurant'
+  SELECT
+    id,
+    names.primary as name,
+    confidence AS confidence,
+    CAST(socials AS JSON) as socials,    -- Ensure each attribute can be serialized to JSON
+    geometry                             -- DuckDB understands this to be a geometry type
+  FROM
+    read_parquet('s3://overturemaps-us-west-2/release/__OVERTURE_RELEASE/theme=places/type=place/*', filename=true, hive_partitioning=1)
+  WHERE
+    categories.primary = 'pizza_restaurant'
     AND bbox.xmin BETWEEN -75 AND -73       -- Only use the bbox min values
     AND bbox.ymin BETWEEN 40 AND 41         -- because they are point geometries.
-
 ) TO 'nyc_pizza.geojson' WITH (FORMAT GDAL, DRIVER 'GeoJSON');

src/queries/duckdb/paris_roads_contained.sql

@@ -0,0 +1,18 @@
+LOAD spatial; -- noqa
+
+SET s3_region='us-west-2';
+
+COPY(
+  SELECT
+    id,
+    names.primary as name,
+    class,
+    geometry   -- DuckDB v.1.1.0 will autoload this as a `geometry` type
+  FROM
+    read_parquet('s3://overturemaps-us-west-2/release/__OVERTURE_RELEASE/theme=transportation/type=segment/*', filename=true, hive_partitioning=1)
+  WHERE
+    bbox.xmin > 2.276
+    AND bbox.ymin > 48.865
+    AND bbox.xmax < 2.314
+    AND bbox.ymax < 48.882
+) TO 'paris_roads_contained.geojson' WITH (FORMAT GDAL, DRIVER 'GeoJSON');

src/queries/duckdb/paris_roads_intersecting.sql

@@ -0,0 +1,18 @@
+LOAD spatial; -- noqa
+
+SET s3_region='us-west-2';
+
+COPY(
+  SELECT
+    id,
+    names.primary as name,
+    class,
+    geometry   -- DuckDB v.1.1.0 will autoload this as a `geometry` type
+  FROM
+    read_parquet('s3://overturemaps-us-west-2/release/__OVERTURE_RELEASE/theme=transportation/type=segment/*', filename=true, hive_partitioning=1)
+  WHERE
+    bbox.xmin < 2.314 
+    AND bbox.ymin < 48.882 
+    AND bbox.xmax > 2.276 
+    AND bbox.ymax > 48.865
+) TO 'paris_roads_intersecting.geojson' WITH (FORMAT GDAL, DRIVER 'GeoJSON');

src/queries/duckdb/write_geoparquet.sql

@@ -1,8 +1,11 @@
 LOAD spatial; -- noqa
 
+SET s3_region='us-west-2';
+
 COPY(
   SELECT
     *
-  FROM read_parquet('s3://overturemaps-us-west-2/release/__OVERTURE_RELEASE/theme=places/type=place/*')
+  FROM
+    read_parquet('s3://overturemaps-us-west-2/release/__OVERTURE_RELEASE/theme=places/type=place/*')
   LIMIT 100000
 ) TO 'places.parquet';