Prepare release of server v0.24.1

366 fix empty table case

NEWS.md

@@ -1,3 +1,8 @@
+May 16th, 2017
+=============
+* Version `0.24.1` of the server
+    * Fixed an interface mismatch between DS API and OBS backend, when returning no data. See #366
+
 May 9th, 2017
 =============
 * Version `0.17.0` of the client and version `0.24.0` of the server

server/extension/cdb_dataservices_server--0.24.0--0.24.1.sql

@@ -0,0 +1,100 @@
+--DO NOT MODIFY THIS FILE, IT IS GENERATED AUTOMATICALLY FROM SOURCES
+-- Complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "ALTER EXTENSION cdb_dataservices_server UPDATE TO '0.24.1'" to load this file. \quit
+
+
+CREATE OR REPLACE FUNCTION cdb_dataservices_server.OBS_GetData(
+  username TEXT,
+  orgname TEXT,
+  geomvals geomval[],
+  params JSON,
+  merge BOOLEAN DEFAULT True)
+RETURNS TABLE (
+  id INT,
+  data JSON
+) AS $$
+  from cartodb_services.metrics import metrics
+  from cartodb_services.metrics import QuotaService
+  from cartodb_services.tools import Logger,LoggerConfig
+
+  plpy.execute("SELECT cdb_dataservices_server._connect_to_redis('{0}')".format(username))
+  redis_conn = GD["redis_connection_{0}".format(username)]['redis_metrics_connection']
+  plpy.execute("SELECT cdb_dataservices_server._get_obs_config({0}, {1})".format(plpy.quote_nullable(username), plpy.quote_nullable(orgname)))
+  user_obs_config = GD["user_obs_config_{0}".format(username)]
+
+  plpy.execute("SELECT cdb_dataservices_server._get_logger_config()")
+  logger_config = GD["logger_config"]
+  logger = Logger(logger_config)
+  quota_service = QuotaService(user_obs_config, redis_conn)
+  if not quota_service.check_user_quota():
+    raise Exception('You have reached the limit of your quota')
+
+  with metrics('obs_getdata', user_obs_config, logger):
+    try:
+        obs_plan = plpy.prepare("SELECT * FROM cdb_dataservices_server._OBS_GetData($1, $2, $3, $4, $5);", ["text", "text", "geomval[]", "json", "boolean"])
+        result = plpy.execute(obs_plan, [username, orgname, geomvals, params, merge])
+        empty_results = len(geomvals) - len(result)
+        if empty_results > 0:
+          quota_service.increment_empty_service_use(empty_results)
+        if result:
+          quota_service.increment_success_service_use(len(result))
+          return result
+        else:
+          return []
+    except BaseException as e:
+        import sys
+        quota_service.increment_failed_service_use(len(geomvals))
+        logger.error('Error trying to OBS_GetData', sys.exc_info(), data={"username": username, "orgname": orgname})
+        raise Exception('Error trying to OBS_GetData')
+    finally:
+        quota_service.increment_total_service_use(len(geomvals))
+$$ LANGUAGE plpythonu;
+
+
+CREATE OR REPLACE FUNCTION cdb_dataservices_server.OBS_GetData(
+  username TEXT,
+  orgname TEXT,
+  geomrefs TEXT[],
+  params JSON)
+RETURNS TABLE (
+  id TEXT,
+  data JSON
+) AS $$
+  from cartodb_services.metrics import metrics
+  from cartodb_services.metrics import QuotaService
+  from cartodb_services.tools import Logger,LoggerConfig
+
+  plpy.execute("SELECT cdb_dataservices_server._connect_to_redis('{0}')".format(username))
+  redis_conn = GD["redis_connection_{0}".format(username)]['redis_metrics_connection']
+  plpy.execute("SELECT cdb_dataservices_server._get_obs_config({0}, {1})".format(plpy.quote_nullable(username), plpy.quote_nullable(orgname)))
+  user_obs_config = GD["user_obs_config_{0}".format(username)]
+
+  plpy.execute("SELECT cdb_dataservices_server._get_logger_config()")
+  logger_config = GD["logger_config"]
+  logger = Logger(logger_config)
+  quota_service = QuotaService(user_obs_config, redis_conn)
+  if not quota_service.check_user_quota():
+    raise Exception('You have reached the limit of your quota')
+
+  with metrics('obs_getdata', user_obs_config, logger):
+    try:
+        obs_plan = plpy.prepare("SELECT * FROM cdb_dataservices_server._OBS_GetData($1, $2, $3, $4);", ["text", "text", "text[]", "json"])
+        result = plpy.execute(obs_plan, [username, orgname, geomrefs, params])
+        empty_results = len(geomrefs) - len(result)
+        if empty_results > 0:
+          quota_service.increment_empty_service_use(empty_results)
+        if result:
+          quota_service.increment_success_service_use(len(result))
+          return result
+        else:
+          return []
+    except BaseException as e:
+        import sys
+        quota_service.increment_failed_service_use(len(geomrefs))
+        exc_info = sys.exc_info()
+        logger.error('%s, %s, %s' % (exc_info[0], exc_info[1], exc_info[2]))
+        logger.error('Error trying to OBS_GetData', exc_info, data={"username": username, "orgname": orgname})
+        raise Exception('Error trying to OBS_GetData')
+    finally:
+        quota_service.increment_total_service_use(len(geomrefs))
+$$ LANGUAGE plpythonu;

server/extension/cdb_dataservices_server--0.24.1--0.24.0.sql

@@ -0,0 +1,100 @@
+--DO NOT MODIFY THIS FILE, IT IS GENERATED AUTOMATICALLY FROM SOURCES
+-- Complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "ALTER EXTENSION cdb_dataservices_server UPDATE TO '0.24.0'" to load this file. \quit
+
+
+CREATE OR REPLACE FUNCTION cdb_dataservices_server.OBS_GetData(
+  username TEXT,
+  orgname TEXT,
+  geomvals geomval[],
+  params JSON,
+  merge BOOLEAN DEFAULT True)
+RETURNS TABLE (
+  id INT,
+  data JSON
+) AS $$
+  from cartodb_services.metrics import metrics
+  from cartodb_services.metrics import QuotaService
+  from cartodb_services.tools import Logger,LoggerConfig
+
+  plpy.execute("SELECT cdb_dataservices_server._connect_to_redis('{0}')".format(username))
+  redis_conn = GD["redis_connection_{0}".format(username)]['redis_metrics_connection']
+  plpy.execute("SELECT cdb_dataservices_server._get_obs_config({0}, {1})".format(plpy.quote_nullable(username), plpy.quote_nullable(orgname)))
+  user_obs_config = GD["user_obs_config_{0}".format(username)]
+
+  plpy.execute("SELECT cdb_dataservices_server._get_logger_config()")
+  logger_config = GD["logger_config"]
+  logger = Logger(logger_config)
+  quota_service = QuotaService(user_obs_config, redis_conn)
+  if not quota_service.check_user_quota():
+    raise Exception('You have reached the limit of your quota')
+
+  with metrics('obs_getdata', user_obs_config, logger):
+    try:
+        obs_plan = plpy.prepare("SELECT * FROM cdb_dataservices_server._OBS_GetData($1, $2, $3, $4, $5);", ["text", "text", "geomval[]", "json", "boolean"])
+        result = plpy.execute(obs_plan, [username, orgname, geomvals, params, merge])
+        empty_results = len(geomvals) - len(result)
+        if empty_results > 0:
+          quota_service.increment_empty_service_use(empty_results)
+        if result:
+          quota_service.increment_success_service_use(len(result))
+          return result
+        else:
+          return None
+    except BaseException as e:
+        import sys
+        quota_service.increment_failed_service_use(len(geomvals))
+        logger.error('Error trying to OBS_GetData', sys.exc_info(), data={"username": username, "orgname": orgname})
+        raise Exception('Error trying to OBS_GetData')
+    finally:
+        quota_service.increment_total_service_use(len(geomvals))
+$$ LANGUAGE plpythonu;
+
+
+CREATE OR REPLACE FUNCTION cdb_dataservices_server.OBS_GetData(
+  username TEXT,
+  orgname TEXT,
+  geomrefs TEXT[],
+  params JSON)
+RETURNS TABLE (
+  id TEXT,
+  data JSON
+) AS $$
+  from cartodb_services.metrics import metrics
+  from cartodb_services.metrics import QuotaService
+  from cartodb_services.tools import Logger,LoggerConfig
+
+  plpy.execute("SELECT cdb_dataservices_server._connect_to_redis('{0}')".format(username))
+  redis_conn = GD["redis_connection_{0}".format(username)]['redis_metrics_connection']
+  plpy.execute("SELECT cdb_dataservices_server._get_obs_config({0}, {1})".format(plpy.quote_nullable(username), plpy.quote_nullable(orgname)))
+  user_obs_config = GD["user_obs_config_{0}".format(username)]
+
+  plpy.execute("SELECT cdb_dataservices_server._get_logger_config()")
+  logger_config = GD["logger_config"]
+  logger = Logger(logger_config)
+  quota_service = QuotaService(user_obs_config, redis_conn)
+  if not quota_service.check_user_quota():
+    raise Exception('You have reached the limit of your quota')
+
+  with metrics('obs_getdata', user_obs_config, logger):
+    try:
+        obs_plan = plpy.prepare("SELECT * FROM cdb_dataservices_server._OBS_GetData($1, $2, $3, $4);", ["text", "text", "text[]", "json"])
+        result = plpy.execute(obs_plan, [username, orgname, geomrefs, params])
+        empty_results = len(geomrefs) - len(result)
+        if empty_results > 0:
+          quota_service.increment_empty_service_use(empty_results)
+        if result:
+          quota_service.increment_success_service_use(len(result))
+          return result
+        else:
+          return None
+    except BaseException as e:
+        import sys
+        quota_service.increment_failed_service_use(len(geomrefs))
+        exc_info = sys.exc_info()
+        logger.error('%s, %s, %s' % (exc_info[0], exc_info[1], exc_info[2]))
+        logger.error('Error trying to OBS_GetData', exc_info, data={"username": username, "orgname": orgname})
+        raise Exception('Error trying to OBS_GetData')
+    finally:
+        quota_service.increment_total_service_use(len(geomrefs))
+$$ LANGUAGE plpythonu;

server/extension/cdb_dataservices_server.control

@@ -1,5 +1,5 @@
 comment = 'CartoDB dataservices server extension'
-default_version = '0.24.0'
+default_version = '0.24.1'
 requires = 'plpythonu, plproxy, postgis, cdb_geocoder'
 superuser = true
 schema = cdb_dataservices_server

server/extension/sql/110_data_observatory_augmentation.sql

@@ -619,7 +619,7 @@ RETURNS TABLE (
           quota_service.increment_success_service_use(len(result))
           return result
         else:
-          return None
+          return []
     except BaseException as e:
         import sys
         quota_service.increment_failed_service_use(len(geomvals))
@@ -678,7 +678,7 @@ RETURNS TABLE (
           quota_service.increment_success_service_use(len(result))
           return result
         else:
-          return None
+          return []
     except BaseException as e:
         import sys
         quota_service.increment_failed_service_use(len(geomrefs))

server/extension/test/expected/00_install_test.out

@@ -37,7 +37,7 @@ SELECT cartodb.cdb_conf_setconf('logger_conf', '{"geocoder_log_path": "/dev/null
  
 (1 row)
 
-SELECT cartodb.cdb_conf_setconf('data_observatory_conf', '{"connection": {"whitelist": ["ethervoid"], "production": "host=localhost port=5432 dbname=dataservices_db user=geocoder_api", "staging": "host=localhost port=5432 dbname=dataservices_db user=geocoder_api"}, "monthly_quota": 100000}');
+SELECT cartodb.cdb_conf_setconf('data_observatory_conf', '{"connection": {"whitelist": ["ethervoid"], "production": "host=localhost port=5432 dbname=contrib_regression user=geocoder_api", "staging": "host=localhost port=5432 dbname=dataservices_db user=geocoder_api"}, "monthly_quota": 100000}');
  cdb_conf_setconf 
 ------------------
  

server/extension/test/expected/366_empty_table_test.out

@@ -0,0 +1,9 @@
+\set ECHO none
+ id | data 
+----+------
+(0 rows)
+
+ id | data 
+----+------
+(0 rows)
+

server/extension/test/sql/00_install_test.sql

@@ -14,7 +14,7 @@ SELECT cartodb.cdb_conf_setconf('redis_metadata_config', '{"redis_host": "localh
 SELECT cartodb.cdb_conf_setconf('heremaps_conf', '{"geocoder": {"app_id": "dummy_id", "app_code": "dummy_code", "geocoder_cost_per_hit": 1}, "isolines": {"app_id": "dummy_id", "app_code": "dummy_code"}}');
 SELECT cartodb.cdb_conf_setconf('mapzen_conf', '{"routing": {"api_key": "routing_dummy_api_key", "monthly_quota": 1500000}, "geocoder": {"api_key": "geocoder_dummy_api_key", "monthly_quota": 1500000}, "matrix": {"api_key": "matrix_dummy_api_key", "monthly_quota": 1500000}}');
 SELECT cartodb.cdb_conf_setconf('logger_conf', '{"geocoder_log_path": "/dev/null"}');
-SELECT cartodb.cdb_conf_setconf('data_observatory_conf', '{"connection": {"whitelist": ["ethervoid"], "production": "host=localhost port=5432 dbname=dataservices_db user=geocoder_api", "staging": "host=localhost port=5432 dbname=dataservices_db user=geocoder_api"}, "monthly_quota": 100000}');
+SELECT cartodb.cdb_conf_setconf('data_observatory_conf', '{"connection": {"whitelist": ["ethervoid"], "production": "host=localhost port=5432 dbname=contrib_regression user=geocoder_api", "staging": "host=localhost port=5432 dbname=dataservices_db user=geocoder_api"}, "monthly_quota": 100000}');
 
 -- Mock the varnish invalidation function
 -- (used by cdb_geocoder tests)

server/extension/test/sql/366_empty_table_test.sql

@@ -0,0 +1,65 @@
+\set ECHO none
+\set VERBOSITY verbose
+SET client_min_messages TO error;
+
+-- Set configuration for a user 'foo'
+DO $$
+  import json
+  from cartodb_services.config import ServiceConfiguration
+
+  import cartodb_services
+  cartodb_services.init(plpy, GD)
+
+  service_config = ServiceConfiguration('observatory', 'foo', None)
+  service_config.user.set('soft_obs_general_limit', True)
+  service_config.user.set('period_end_date', '20170516')
+
+$$ LANGUAGE plpythonu;
+
+
+-- Mock Observatory backend function
+CREATE SCHEMA cdb_observatory;
+CREATE OR REPLACE FUNCTION cdb_observatory.OBS_GetData(geomvals geomval[], params JSON, merge BOOLEAN DEFAULT TRUE)
+RETURNS TABLE (
+  id INT,
+  data JSON
+) AS $$
+BEGIN
+  -- this will return an empty set
+  RAISE NOTICE 'Mocked OBS_GetData()';
+END;
+$$ LANGUAGE plpgsql;
+GRANT USAGE ON SCHEMA cdb_observatory TO geocoder_api;
+GRANT EXECUTE ON ALL FUNCTIONS IN SCHEMA cdb_observatory TO geocoder_api;
+
+
+-- Test it
+SELECT * FROM cdb_dataservices_server.OBS_GetData(
+    'foo',
+    NULL,
+    '{"(0103000020E61000000100000005000000010000E0F67F52C096D88AE6B25F4440010000E0238052C0BF6D8A1A8D5D4440010000D0DA7E52C05F03F3CC265D444001000020F47E52C0F2DD78AB5D5F4440010000E0F67F52C096D88AE6B25F4440,1)"}'::public._geomval,
+    '[{"id": 1, "score": 52.7515548093083898758340051256007949661290516400338, "geom_id": "us.census.tiger.census_tract", "denom_id": "us.census.acs.B01003001", "numer_id": "us.census.acs.B03002003", "geom_name": "US Census Tracts", "geom_type": "Geometry", "num_geoms": 2.86483076549783307739486952736, "denom_name": "Total Population", "denom_type": "Numeric", "numer_name": "White Population", "numer_type": "Numeric", "score_rank": 1, "target_area": 0.000307374806576033, "geom_colname": "the_geom", "score_rownum": 1, "target_geoms": null, "denom_colname": "total_pop", "denom_reltype": '
+         '"denominator", "geom_timespan": "2015", "normalization": "prenormalized", "numer_colname": "white_pop", "timespan_rank": 1, "geom_tablename": "obs_87a814e485deabe3b12545a537f693d16ca702c2", "max_score_rank": null, "numer_timespan": "2010 - 2014", "suggested_name": "white_pop_2010_2014", "denom_aggregate": "sum", "denom_tablename": "obs_b393b5b88c6adda634b2071a8005b03c551b609a", "numer_aggregate": "sum", "numer_tablename": "obs_b393b5b88c6adda634b2071a8005b03c551b609a", "timespan_rownum": 1, "geom_description": "Census tracts are small, relatively permanent statistical subdivisions of a county or equivalent entity that are updated by local participants prior to each decennial census as part of the Census Bureau’s Participant Statistical Areas Program. The Census Bureau delineates census tracts in situations where no local participant existed or where state, local, or tribal governments'
+         'declined to participate. The primary purpose of census tracts is to provide a stable set of geographic units for the presentation of statistical data.\r\n\r\nCensus tracts generally have a population size between 1,200 and 8,000 people, with an optimum size of 4,000 people. A census tract usually covers a contiguous area; however, the spatial size of census tracts varies widely depending on the density of settlement. Census tract boundaries are delineated with the intention of being maintained over a long time so that statistical comparisons can be made from census to census. Census tracts occasionally are split due to population growth or merged as a result of substantial population decline.\r\n\r\nCensus tract boundaries generally follow visible and identifiable features. They may follow nonvisible legal boundaries, such as minor civil division (MCD) or incorporated place boundaries'
+         'in some states and situations, to allow for census-tract-to-governmental-unit relationships where the governmental boundaries tend to remain unchanged between censuses. State and county boundaries always are census tract boundaries in the standard census geographic hierarchy. Tribal census tracts are a unique geographic entity defined within federally recognized American Indian reservations and off-reservation trust lands and can cross state and county boundaries. Tribal census tracts may be completely different from the census tracts and block groups defined by state and county (see “Tribal Census Tract”).", "denom_description": "The total number of all people living in a given geographic area.  This is a very useful catch-all denominator when calculating rates.", "max_timespan_rank": null, "numer_description": "The number of people identifying as white, non-Hispanic in each'
+         'geography.", "geom_t_description": null, "denom_t_description": null, "numer_t_description": null, "geom_geomref_colname": "geoid", "denom_geomref_colname": "geoid", "numer_geomref_colname": "geoid"}]'::json,
+     true);
+
+
+
+-- Mock another observatory backend function (overloaded, different params)
+CREATE OR REPLACE FUNCTION cdb_observatory.OBS_GetData(geomrefs TEXT[], params JSON)
+RETURNS TABLE (
+  id INT,
+  data JSON
+) AS $$
+BEGIN
+  -- this will return an empty set
+  RAISE NOTICE 'Mocked OBS_GetData()';
+END;
+$$ LANGUAGE plpgsql;
+GRANT USAGE ON SCHEMA cdb_observatory TO geocoder_api;
+GRANT EXECUTE ON ALL FUNCTIONS IN SCHEMA cdb_observatory TO geocoder_api;
+
+-- Test it
+SELECT * FROM cdb_dataservices_server.OBS_GetData('foo', NULL, '{bar, baz}'::TEXT[], '[]'::JSON);