1. add geo_value validator in _params

2. modified test_covidcast and test_delphi_epidata for server geo_value validation passing
3. add TODO for patch and mock part

Author: LeonLu2

integrations/client/test_delphi_epidata.py

@@ -19,6 +19,14 @@
 from delphi.epidata.acquisition.covidcast.test_utils import CovidcastBase
 import delphi.operations.secrets as secrets
 
+# TODO replace these real geo_values with fake values, and use patch and mock to mock the return values of 
+# delphi_utils.geomap.GeoMapper().get_geo_values(geo_type) in parse_geo_sets() of _params.py
+
+global fips, msa # add two global lists of valid geo_values of these types to pass the validation in parse_geo_sets() of _params.py
+
+fips = ['04019', '19143', '29063'] # Example list of valid FIPS codes as strings
+msa = ['40660', '44180', '48620'] # Example list of valid MSAs as strings
+
 # py3tester coverage target
 __test_target__ = 'delphi.epidata.client.delphi_epidata'
 
@@ -54,12 +62,12 @@ def test_covidcast(self):
 
     # insert placeholder data: three issues of one signal, one issue of another
     rows = [
-      self._make_placeholder_row(issue=self.DEFAULT_ISSUE + i, value=i, lag=i)[0]
+      self._make_placeholder_row(geo_type='msa', geo_value=msa[0], issue=self.DEFAULT_ISSUE + i, value=i, lag=i)[0]
       for i in range(3)
     ]
     row_latest_issue = rows[-1]
     rows.append(
-      self._make_placeholder_row(signal="sig2")[0]
+      self._make_placeholder_row(geo_type='msa', geo_value=msa[0], signal="sig2")[0]
     )
     self._insert_rows(rows)
 
@@ -74,6 +82,7 @@ def test_covidcast(self):
         self.expected_from_row(rows[-1])
       ]
 
+      self.maxDiff = None
       # check result
       self.assertEqual(response, {
         'result': 1,
@@ -223,10 +232,10 @@ def test_geo_value(self):
     # insert placeholder data: three counties, three MSAs
     N = 3
     rows = [
-      self._make_placeholder_row(geo_type="county", geo_value=str(i)*5, value=i)[0]
+      self._make_placeholder_row(geo_type="fips", geo_value=fips[i], value=i)[0]
       for i in range(N)
     ] + [
-      self._make_placeholder_row(geo_type="msa", geo_value=str(i)*5, value=i*10)[0]
+      self._make_placeholder_row(geo_type="msa", geo_value=msa[i], value=i*10)[0]
       for i in range(N)
     ]
     self._insert_rows(rows)
@@ -240,32 +249,32 @@ def fetch(geo):
         **self.params_from_row(rows[0], geo_value=geo)
       )
 
+    self.maxDiff = None
     # test fetch all
     r = fetch('*')
     self.assertEqual(r['message'], 'success')
     self.assertEqual(r['epidata'], counties)
     # test fetch a specific region
-    r = fetch('11111')
+    r = fetch('{}'.format(fips[0]))
     self.assertEqual(r['message'], 'success')
-    self.assertEqual(r['epidata'], [counties[1]])
+    self.assertEqual(r['epidata'], [counties[0]])
     # test fetch a specific yet not existing region
     r = fetch('55555')
-    self.assertEqual(r['message'], 'no results')
+    self.assertEqual(r['message'], 'invalid geo_value for the requested geo_type')
     # test fetch a multiple regions
-    r = fetch(['11111', '22222'])
+    r = fetch(['{}'.format(fips[0]), '{}'.format(fips[1])])
     self.assertEqual(r['message'], 'success')
-    self.assertEqual(r['epidata'], [counties[1], counties[2]])
+    self.assertEqual(r['epidata'], [counties[0], counties[1]])
     # test fetch a multiple regions in another variant
-    r = fetch(['00000', '22222'])
+    r = fetch(['{}'.format(fips[0]), '{}'.format(fips[2])])
     self.assertEqual(r['message'], 'success')
     self.assertEqual(r['epidata'], [counties[0], counties[2]])
     # test fetch a multiple regions but one is not existing
-    r = fetch(['11111', '55555'])
-    self.assertEqual(r['message'], 'success')
-    self.assertEqual(r['epidata'], [counties[1]])
+    r = fetch(['{}'.format(fips[0]), '55555'])
+    self.assertEqual(r['message'], 'invalid geo_value for the requested geo_type')
     # test fetch a multiple regions but specify no region
     r = fetch([])
-    self.assertEqual(r['message'], 'no results')
+    self.assertEqual(r['message'], 'invalid geo_value for the requested geo_type')
 
   def test_covidcast_meta(self):
     """Test that the covidcast_meta endpoint returns expected data."""
@@ -322,10 +331,10 @@ def test_async_epidata(self):
     # insert placeholder data: three counties, three MSAs
     N = 3
     rows = [
-      self._make_placeholder_row(geo_type="county", geo_value=str(i)*5, value=i)[0]
+      self._make_placeholder_row(geo_type="fips", geo_value=fips[i-1], value=i)[0]
       for i in range(N)
     ] + [
-      self._make_placeholder_row(geo_type="msa", geo_value=str(i)*5, value=i*10)[0]
+      self._make_placeholder_row(geo_type="msa", geo_value=msa[i-1], value=i*10)[0]
       for i in range(N)
     ]
     self._insert_rows(rows)

integrations/server/test_covidcast.py

@@ -3,6 +3,8 @@
 # standard library
 import json
 import unittest
+# from unittest.mock import MagicMock
+# from unittest.mock import patch
 
 # third party
 import mysql.connector
@@ -15,6 +17,13 @@
 # use the local instance of the Epidata API
 BASE_URL = 'http://delphi_web_epidata/epidata/api.php'
 
+# TODO replace these real geo_values with fake values, and use patch and mock to mock the return values of 
+# delphi_utils.geomap.GeoMapper().get_geo_values(geo_type) in parse_geo_sets() of _params.py
+
+global fips, msa # add two global lists of valid geo_values of these types to pass the validation in parse_geo_sets() of _params.py
+
+fips = ['04019', '19143', '29063'] # Example list of valid FIPS codes as strings
+msa = ['40660', '44180', '48620'] # Example list of valid MSAs as strings
 
 
 class CovidcastTests(CovidcastBase):
@@ -35,53 +44,52 @@ def request_based_on_row(self, row, extract_response=lambda x: x.json(), **kwarg
     return response, expected
 
   def _insert_placeholder_set_one(self):
-    row, settings = self._make_placeholder_row()
+    row, settings = self._make_placeholder_row(geo_type='msa', geo_value=msa[0])
     self._insert_rows([row])
     return row
 
   def _insert_placeholder_set_two(self):
     rows = [
-      self._make_placeholder_row(geo_type='county', geo_value=str(i)*5, value=i*1., stderr=i*10., sample_size=i*100.)[0]
+      self._make_placeholder_row(geo_type='msa', geo_value=msa[i-1], value=i*1., stderr=i*10., sample_size=i*100.)[0]
       for i in [1, 2, 3]
     ] + [
-      # geo value intended to overlap with counties above
-      self._make_placeholder_row(geo_type='msa', geo_value=str(i-3)*5, value=i*1., stderr=i*10., sample_size=i*100.)[0]
+      self._make_placeholder_row(geo_type='fips', geo_value=fips[i-4], value=i*1., stderr=i*10., sample_size=i*100.)[0]
       for i in [4, 5, 6]
     ]
     self._insert_rows(rows)
     return rows
 
   def _insert_placeholder_set_three(self):
     rows = [
-      self._make_placeholder_row(geo_type='county', geo_value='11111', time_value=2000_01_01+i, value=i*1., stderr=i*10., sample_size=i*100., issue=2000_01_03, lag=2-i)[0]
+      self._make_placeholder_row(geo_type='msa', geo_value=msa[0], time_value=2000_01_01+i, value=i*1., stderr=i*10., sample_size=i*100., issue=2000_01_03, lag=2-i)[0]
       for i in [1, 2, 3]
     ] + [
       # time value intended to overlap with 11111 above, with disjoint geo values
-      self._make_placeholder_row(geo_type='county', geo_value=str(i)*5, time_value=2000_01_01+i-3, value=i*1., stderr=i*10., sample_size=i*100., issue=2000_01_03, lag=5-i)[0]
+      self._make_placeholder_row(geo_type='msa', geo_value=str(i)*5, time_value=2000_01_01+i-3, value=i*1., stderr=i*10., sample_size=i*100., issue=2000_01_03, lag=5-i)[0]
       for i in [4, 5, 6]
     ]
     self._insert_rows(rows)
     return rows
 
   def _insert_placeholder_set_four(self):
     rows = [
-      self._make_placeholder_row(source='src1', signal=str(i)*5, value=i*1., stderr=i*10., sample_size=i*100.)[0]
+      self._make_placeholder_row(geo_type='msa', geo_value=msa[0], source='src1', signal=str(i)*5, value=i*1., stderr=i*10., sample_size=i*100.)[0]
       for i in [1, 2, 3]
     ] + [
       # signal intended to overlap with the signal above
-      self._make_placeholder_row(source='src2', signal=str(i-3)*5, value=i*1., stderr=i*10., sample_size=i*100.)[0]
+      self._make_placeholder_row(geo_type='msa', geo_value=msa[0], source='src2', signal=str(i-3)*5, value=i*1., stderr=i*10., sample_size=i*100.)[0]
       for i in [4, 5, 6]
     ]
     self._insert_rows(rows)
     return rows
 
   def _insert_placeholder_set_five(self):
     rows = [
-      self._make_placeholder_row(time_value=2000_01_01, value=i*1., stderr=i*10., sample_size=i*100., issue=2000_01_03+i)[0]
+      self._make_placeholder_row(geo_type='msa', geo_value=msa[0], time_value=2000_01_01, value=i*1., stderr=i*10., sample_size=i*100., issue=2000_01_03+i)[0]
       for i in [1, 2, 3]
     ] + [
       # different time_values, same issues
-      self._make_placeholder_row(time_value=2000_01_01+i-3, value=i*1., stderr=i*10., sample_size=i*100., issue=2000_01_03+i-3)[0]
+      self._make_placeholder_row(geo_type='msa', geo_value=msa[0], time_value=2000_01_01+i-3, value=i*1., stderr=i*10., sample_size=i*100., issue=2000_01_03+i-3)[0]
       for i in [4, 5, 6]
     ]
     self._insert_rows(rows)
@@ -310,7 +318,7 @@ def test_signal_wildcard(self):
     })
 
   def test_geo_value(self):
-    """test different variants of geo types: single, *, multi."""
+    """test whether geo values are valid for specific geo types"""
 
     # insert placeholder data
     rows = self._insert_placeholder_set_two()
@@ -324,28 +332,33 @@ def fetch(geo_value):
 
       return response
 
+    self.maxDiff = None
     # test fetch a specific region
-    r = fetch('11111')
+    r = fetch(msa[0])
     self.assertEqual(r['message'], 'success')
     self.assertEqual(r['epidata'], [expected_counties[0]])
+
     # test fetch a specific yet not existing region
-    r = fetch('55555')
-    self.assertEqual(r['message'], 'no results')
+    r = fetch('11111')
+    self.assertEqual(r['message'], 'invalid geo_value for the requested geo_type')
+
     # test fetch multiple regions
-    r = fetch('11111,22222')
+    r = fetch('{},{}'.format(msa[0], msa[1]))
     self.assertEqual(r['message'], 'success')
     self.assertEqual(r['epidata'], [expected_counties[0], expected_counties[1]])
+
     # test fetch multiple noncontiguous regions
-    r = fetch('11111,33333')
+    r = fetch('{},{}'.format(msa[0], msa[2]))
     self.assertEqual(r['message'], 'success')
     self.assertEqual(r['epidata'], [expected_counties[0], expected_counties[2]])
+
     # test fetch multiple regions but one is not existing
-    r = fetch('11111,55555')
-    self.assertEqual(r['message'], 'success')
-    self.assertEqual(r['epidata'], [expected_counties[0]])
+    r = fetch('{},11111'.format(msa[0]))
+    self.assertEqual(r['message'], 'invalid geo_value for the requested geo_type')
+
     # test fetch empty region
     r = fetch('')
-    self.assertEqual(r['message'], 'no results')
+    self.assertEqual(r['message'], 'invalid geo_value for the requested geo_type')
 
   def test_location_timeline(self):
     """Select a timeline for a particular location."""
@@ -384,7 +397,7 @@ def test_nullable_columns(self):
     """Missing values should be surfaced as null."""
 
     row, _ = self._make_placeholder_row(
-      stderr=None, sample_size=None,
+      geo_type='msa', geo_value=msa[0], stderr=None, sample_size=None,
       missing_stderr=Nans.OTHER.value, missing_sample_size=Nans.OTHER.value
     )
     self._insert_rows([row])
@@ -405,7 +418,7 @@ def test_temporal_partitioning(self):
 
     # insert placeholder data
     rows = [
-      self._make_placeholder_row(time_type=tt)[0]
+      self._make_placeholder_row(geo_type='msa', geo_value=msa[0], time_type=tt)[0]
       for tt in "hour day week month year".split()
     ]
     self._insert_rows(rows)

requirements.api.txt

@@ -1,3 +1,4 @@
+delphi_utils==0.3.6
 epiweeks==2.1.2
 Flask==2.2.2
 itsdangerous<2.1

src/server/_params.py

@@ -2,6 +2,7 @@
 import re
 from dataclasses import dataclass
 from typing import List, Optional, Sequence, Tuple, Union
+import delphi_utils    
 
 from flask import request
 
@@ -460,14 +461,21 @@ def parse_source_signal_sets() -> List[SourceSignalSet]:
 
 def parse_geo_sets() -> List[GeoSet]:
     geo_type = request.values.get("geo_type")
+
     if geo_type:
         # old version
         require_any(request, "geo_value", "geo_values", empty=True)
         geo_values = extract_strings(("geo_values", "geo_value"))
         if len(geo_values) == 1 and geo_values[0] == "*":
             return [GeoSet(geo_type, True)]
+
+        for geo_value in geo_values:
+            if geo_value not in delphi_utils.geomap.GeoMapper().get_geo_values(geo_type):
+                raise ValidationFailedException("invalid geo_value for the requested geo_type")
+
         return [GeoSet(geo_type, geo_values)]
 
+
     if ":" not in request.values.get("geo", ""):
         raise ValidationFailedException("missing parameter: geo or (geo_type and geo_value[s])")