[COST-4333] Fix OCP on Azure matching by resource-ids (#4824)

Co-authored-by: maskarb <[email protected]>

koku/masu/test/util/aws/test_common.py

@@ -13,7 +13,6 @@
 from uuid import uuid4
 
 import boto3
-import numpy as np
 import pandas as pd
 from botocore.exceptions import ClientError
 from dateutil.relativedelta import relativedelta
@@ -755,7 +754,7 @@ def test_match_openshift_labels_with_nan_resources(self):
 
         matched_tags = [{"key": "value"}]
         data = [
-            {"lineitem_resourceid": np.nan, "lineitem_unblendedcost": 1, "resourcetags": '{"key": "value"}'},
+            {"lineitem_resourceid": "", "lineitem_unblendedcost": 1, "resourcetags": '{"key": "value"}'},
         ]
 
         df = pd.DataFrame(data)
@@ -779,7 +778,7 @@ def test_match_openshift_resource_with_nan_labels(self):
 
         matched_tags = [{"key": "value"}]
         data = [
-            {"lineitem_resourceid": "id1", "lineitem_unblendedcost": 1, "resourcetags": np.nan},
+            {"lineitem_resourceid": "id1", "lineitem_unblendedcost": 1, "resourcetags": ""},
         ]
 
         df = pd.DataFrame(data)

koku/masu/test/util/azure/test_common.py

@@ -3,7 +3,6 @@
 # Copyright 2021 Red Hat Inc.
 # SPDX-License-Identifier: Apache-2.0
 #
-import numpy as np
 import pandas as pd
 from django_tenants.utils import schema_context
 
@@ -116,9 +115,9 @@ def test_match_openshift_resources_and_labels_resource_nan(self):
         ]
         matched_tags = []
         data = [
-            {"resourceid": np.nan, "instanceid": "id1", "pretaxcost": 1, "tags": '{"key": "value"}'},
-            {"resourceid": np.nan, "instanceid": "id2", "pretaxcost": 1, "tags": '{"key": "other_value"}'},
-            {"resourceid": np.nan, "instanceid": "id3", "pretaxcost": 1, "tags": '{"keyz": "value"}'},
+            {"resourceid": "", "instanceid": "id1", "pretaxcost": 1, "tags": '{"key": "value"}'},
+            {"resourceid": "", "instanceid": "id2", "pretaxcost": 1, "tags": '{"key": "other_value"}'},
+            {"resourceid": "", "instanceid": "id3", "pretaxcost": 1, "tags": '{"keyz": "value"}'},
         ]
 
         df = pd.DataFrame(data)
@@ -148,7 +147,7 @@ def test_match_openshift_resource_with_nan_labels(self):
 
         matched_tags = [{"key": "value"}]
         data = [
-            {"resourceid": "id1", "pretaxcost": 1, "tags": np.nan},
+            {"resourceid": "id1", "pretaxcost": 1, "tags": ""},
         ]
 
         df = pd.DataFrame(data)

koku/masu/util/aws/common.py

@@ -880,14 +880,14 @@ def match_openshift_resources_and_labels(data_frame, cluster_topologies, matched
     resource_ids = tuple(resource_ids)
     data_frame["resource_id_matched"] = False
     resource_id_df = data_frame["lineitem_resourceid"]
-    if not resource_id_df.isna().values.all():
+    if not resource_id_df.eq("").all():
         LOG.info("Matching OpenShift on AWS by resource ID.")
         resource_id_matched = resource_id_df.str.endswith(resource_ids)
         data_frame["resource_id_matched"] = resource_id_matched
 
     data_frame["special_case_tag_matched"] = False
     tags = data_frame["resourcetags"]
-    if not tags.isna().values.all():
+    if not tags.eq("").all():
         tags = tags.str.lower()
         LOG.info("Matching OpenShift on AWS by tags.")
         special_case_tag_matched = tags.str.contains(
@@ -903,7 +903,7 @@ def match_openshift_resources_and_labels(data_frame, cluster_topologies, matched
             tag_values.extend(list(tag.values()))
 
         any_tag_matched = None
-        if not tags.isna().values.all():
+        if not tags.eq("").all():
             tag_matched = tags.str.contains("|".join(tag_keys)) & tags.str.contains("|".join(tag_values))
             data_frame["tag_matched"] = tag_matched
             any_tag_matched = tag_matched.any()

koku/masu/util/azure/common.py

@@ -181,17 +181,17 @@ def match_openshift_resources_and_labels(data_frame, cluster_topologies, matched
     matchable_resources = list(nodes) + list(volumes)
     data_frame["resource_id_matched"] = False
     resource_id_df = data_frame["resourceid"]
-    if resource_id_df.isna().values.all():
+    if resource_id_df.eq("").all():
         resource_id_df = data_frame["instanceid"]
 
-    if not resource_id_df.isna().values.all():
+    if not resource_id_df.eq("").all():
         LOG.info("Matching OpenShift on Azure by resource ID.")
         resource_id_matched = resource_id_df.str.contains("|".join(matchable_resources))
         data_frame["resource_id_matched"] = resource_id_matched
 
     data_frame["special_case_tag_matched"] = False
     tags = data_frame["tags"]
-    if not tags.isna().values.all():
+    if not tags.eq("").all():
         tags = tags.str.lower()
         LOG.info("Matching OpenShift on Azure by tags.")
         special_case_tag_matched = tags.str.contains(
@@ -207,7 +207,7 @@ def match_openshift_resources_and_labels(data_frame, cluster_topologies, matched
             tag_values.extend(list(tag.values()))
 
         any_tag_matched = None
-        if not tags.isna().values.all():
+        if not tags.eq("").all():
             tag_matched = tags.str.contains("|".join(tag_keys)) & tags.str.contains("|".join(tag_values))
             data_frame["tag_matched"] = tag_matched
             any_tag_matched = tag_matched.any()