Merge pull request #303 from CartoDB/precheck_metadata

OBS_MetadataValidation

.travis.yml

@@ -0,0 +1,42 @@
+language: c
+
+env:
+  global:
+    - PAGER=cat
+
+before_install:
+  - sudo add-apt-repository -y ppa:cartodb/postgresql-9.5
+  - sudo add-apt-repository -y ppa:cartodb/gis
+  - sudo add-apt-repository -y ppa:cartodb/gis-testing
+  - sudo apt-get update
+
+  # Install postgres db and build deps
+  - sudo /etc/init.d/postgresql stop # stop travis default instance
+  - sudo apt-get -y remove --purge postgresql-9.1
+  - sudo apt-get -y remove --purge postgresql-9.2
+  - sudo apt-get -y remove --purge postgresql-9.3
+  - sudo apt-get -y remove --purge postgresql-9.4
+  - sudo apt-get -y remove --purge postgresql-9.5
+  - sudo rm -rf /var/lib/postgresql/
+  - sudo rm -rf /var/log/postgresql/
+  - sudo rm -rf /etc/postgresql/
+  - sudo apt-get -y remove --purge postgis-2.2
+  - sudo apt-get -y autoremove
+
+  - sudo apt-get -y install postgresql-9.5=9.5.2-3cdb3
+  - sudo apt-get -y install postgresql-server-dev-9.5=9.5.2-3cdb3
+  - sudo apt-get -y install postgresql-plpython-9.5=9.5.2-3cdb3
+  - sudo apt-get -y install postgresql-9.5-postgis-scripts=2.2.2.0-cdb2
+  - sudo apt-get -y install postgresql-9.5-postgis-2.2=2.2.2.0-cdb2
+
+  # configure it to accept local connections from postgres
+  - echo -e "# TYPE  DATABASE        USER            ADDRESS                 METHOD \nlocal   all             postgres                                trust\nlocal   all             all                                     trust\nhost    all             all             127.0.0.1/32            trust" \
+    | sudo tee /etc/postgresql/9.5/main/pg_hba.conf
+  - sudo /etc/init.d/postgresql restart 9.5
+
+install:
+  - sudo make install
+
+script:
+  - cd src/pg
+  - make test || { cat src/pg/test/regression.diffs; false; }

scripts/generate_fixtures.py

@@ -52,8 +52,8 @@ def get_tablename_query(column_id, boundary_id, timespan):
 METADATA_TABLES = ['obs_table', 'obs_column_table', 'obs_column', 'obs_column_tag',
                    'obs_tag', 'obs_column_to_column', 'obs_dump_version', 'obs_meta',
                    'obs_meta_numer', 'obs_meta_denom', 'obs_meta_geom',
-                   'obs_meta_timespan', 'obs_column_table_tile',
+                   'obs_meta_timespan', 'obs_meta_geom_numer_timespan',
-                   'obs_column_table_tile_simple']
+                   'obs_column_table_tile', 'obs_column_table_tile_simple']
 
 FIXTURES = [
     ('us.census.acs.B01003001_quantile', 'us.census.tiger.census_tract', '2010 - 2014'),

scripts/requirements.txt

@@ -1,3 +1,4 @@
 requests
 nose
 nose_parameterized
+psycopg2

src/pg/sql/41_observatory_augmentation.sql

@@ -1076,3 +1076,46 @@ BEGIN
   RETURN result;
 END;
 $$ LANGUAGE plpgsql STABLE;
+
+-- MetadataValidation checks the metadata parameters and the geometry type
+-- of the data in order to find possible wrong cases
+CREATE OR REPLACE FUNCTION cdb_observatory.obs_metadatavalidation(
+  geometry_extent geometry(Geometry, 4326),
+  geometry_type text,
+  params JSON,
+  target_geoms INTEGER DEFAULT NULL
+)
+RETURNS TABLE(valid boolean, errors text[]) AS $$
+DECLARE
+  meta json;
+  errors text[];
+BEGIN
+  errors := (ARRAY[])::TEXT[];
+  IF geometry_type IN ('ST_Polygon', 'ST_MultiPolygon') THEN
+      FOR meta IN EXECUTE 'SELECT json_array_elements(cdb_observatory.OBS_GetMeta($1, $2, 1, 1, $3))' USING geometry_extent, params, target_geoms
+      LOOP
+          IF (meta->>'normalization' = 'denominated' AND meta->>'denom_id' is NULL) THEN
+              errors := array_append(errors, 'Normalizated measure should have a numerator and a denominator. Please review the provided options.');
+          END IF;
+          IF (meta->>'numer_aggregate' IS NULL) THEN
+              errors := array_append(errors, 'For polygon geometries, aggregation is mandatory. Please review the provided options');
+          END IF;
+          IF (meta->>'numer_aggregate' IN ('median', 'average') AND meta->>'denom_id' IS NULL) THEN
+              errors := array_append(errors, 'Median or average aggregation for polygons requires a denominator to provide weights. Please review the provided options');
+          END IF;
+          IF (meta->>'numer_aggregate' IN ('median', 'average') AND meta->>'normalization' NOT LIKE 'pre%') THEN
+              errors := array_append(errors, format('Median or average aggregation only supports prenormalized normalization, %s passed. Please review the provided options', meta->>'normalization'));
+          END IF;
+      END LOOP;
+
+      IF CARDINALITY(errors) > 0 THEN
+          RETURN QUERY EXECUTE 'SELECT FALSE, $1' USING errors;
+      ELSE
+          RETURN QUERY SELECT TRUE, ARRAY[]::TEXT[];
+      END IF;
+  ELSE
+    RETURN QUERY SELECT TRUE, ARRAY[]::TEXT[];
+  END IF;
+  RETURN;
+END;
+$$ LANGUAGE plpgsql STABLE;

src/pg/test/expected/41_observatory_augmentation_test.out

@@ -304,3 +304,12 @@ tract_sample|tract_max_error|tract_avg_error|tract_min_error
 no_bg_point_error
 t
 (1 row)
+valid|errors
+t|{}
+(1 row)
+valid|errors
+f|{"Median or average aggregation only supports prenormalized normalization, denominated passed. Please review the provided options"}
+(1 row)
+valid|errors
+f|{"Normalizated measure should have a numerator and a denominator. Please review the provided options."}
+(1 row)

src/pg/test/fixtures/drop_fixtures.sql

@@ -12,6 +12,7 @@ DROP TABLE IF EXISTS observatory.obs_meta_numer;
 DROP TABLE IF EXISTS observatory.obs_meta_denom;
 DROP TABLE IF EXISTS observatory.obs_meta_geom;
 DROP TABLE IF EXISTS observatory.obs_meta_timespan;
+DROP TABLE IF EXISTS observatory.obs_meta_geom_numer_timespan;
 DROP TABLE IF EXISTS observatory.obs_column_table_tile;
 DROP TABLE IF EXISTS observatory.obs_column_table_tile_simple;
 DROP TABLE IF EXISTS observatory.obs_78fb6c1d6ff6505225175922c2c389ce48d7632c;

src/pg/test/sql/41_observatory_augmentation_test.sql

@@ -973,3 +973,9 @@ WITH _geoms AS (
 FROM geoms, results
 WHERE cartodb_id = id
 ;
+
+-- OBS_MetadataValidation
+
+SELECT * FROM cdb_observatory.OBS_MetadataValidation(NULL, 'ST_Polygon', '[{"numer_id": "us.census.acs.B01003001","denom_id": null,"normalization": "prenormalized","geom_id": null,"numer_timespan": "2010 - 2014"}]'::json, 500);
+SELECT * FROM cdb_observatory.OBS_MetadataValidation(NULL, 'ST_Polygon', '[{"numer_id": "us.census.acs.B25058001","denom_id": null,"normalization": "denominated","geom_id": null,"numer_timespan": "2010 - 2014"}]'::json, 500);
+SELECT * FROM cdb_observatory.OBS_MetadataValidation(NULL, 'ST_Polygon', '[{"numer_id": "us.census.acs.B15003001","denom_id": null,"normalization": "denominated","geom_id": null,"numer_timespan": "2010 - 2014"}]'::json, 500);