#20 - Fix listterms test

Author: patkyn

src/dwcahandler/dwca/terms.py

@@ -139,6 +139,8 @@ def update_dwc_terms(self):
         if len(dwc_class_df) > 0:
             self.class_df = self._update_class_df(NsPrefix.DWC, dwc_class_df)
 
+        return self.terms_df, self.class_df
+
     @staticmethod
     def extract_term(term_string, add_underscore: bool = False):
         """
@@ -173,30 +175,21 @@ def update_gbif_ext(self):
         """
         Update the class row type and terms specified by GBIF_REGISTERED_EXTENSION and update by prefix
         """
-        def _get_latest(identifier: str):
-            d = requests.get(Terms.GBIF_EXT).json()
-            gbif_ext_df = pd.DataFrame.from_dict(d["extensions"])
-            ext_df = gbif_ext_df[(gbif_ext_df["identifier"] == identifier) & (gbif_ext_df["isLatest"])]
-            url: str = ""
-            if len(ext_df) > 0 and "url" in ext_df.columns.tolist():
-                url = ext_df["url"].values[0]
-            return url
-
-        def _extract_term_info(every_term: tuple) -> list:
+        def _extract_term_info(current_term: tuple) -> list:
             def _extract_value(text: str):
                 return text.replace("\\n", "").replace('\\', ""). \
                             replace('"', "").replace("'", "").split("=")[1]
 
-            term_name = _extract_value(every_term[0])
-            namespace = _extract_value(every_term[1])
-            uri = _extract_value(every_term[2])
+            term_name = _extract_value(current_term[0])
+            namespace = _extract_value(current_term[1])
+            uri = _extract_value(current_term[2])
 
             return [term_name, namespace, uri]
 
-        def _get_NsPrefix(val: str):
-            prefix = [p for p in NsPrefix if p.value == val]
-            if len(prefix) > 0:
-                return prefix[0]
+        def _get_ns_prefix(val: str):
+            ns_prefix = [p for p in NsPrefix if p.value == val]
+            if len(ns_prefix) > 0:
+                return ns_prefix[0]
             else:
                 return None
 
@@ -207,7 +200,7 @@ def _get_NsPrefix(val: str):
 
         for index, supported_ext in gbif_registered_ext.iterrows():
             url = supported_ext["url"]
-            prefix = _get_NsPrefix(supported_ext["prefix"])
+            prefix = _get_ns_prefix(supported_ext["prefix"])
             if url:
                 update_class = pd.DataFrame([supported_ext["identifier"]], columns=["class_uri"])
                 self.class_df = self._update_class_df(prefix, update_class)
@@ -234,6 +227,8 @@ def _get_NsPrefix(val: str):
                         new_terms.loc[:, "prefix"] = prefix.value
                         self.terms_df = self._update_df(prefix, new_terms, self.terms_df)
 
+        return self.terms_df, self.class_df
+
     @staticmethod
     def update_terms():
         """

tests/test_listterms.py

@@ -21,10 +21,14 @@ def test_list_dwc_terms(self):
         assert df.query('term == "eventDate"').shape[0] == 1
         assert len(class_df[class_df["class"] == "OCCURRENCE"]) == 1
 
-    def test_update_list_terms(self, mocker):
+    def test_update_dwc_list_terms(self, mocker):
         """
         Test that the terms are stored in expected format and deprecated terms are not brought over
         """
+        expected_uri_list = ["http://rs.tdwg.org/dwc/terms/basisOfRecord",
+                             "http://rs.tdwg.org/dwc/terms/occurrenceID",
+                             "http://rs.tdwg.org/dwc/terms/scientificName"]
+        expected_class_list = ["http://rs.tdwg.org/dwc/terms/Occurrence"]
         mocker.patch.object(Terms,
                             attribute="get_dwc_source_data",
                             return_value=pd.DataFrame
@@ -39,21 +43,20 @@ def test_update_list_terms(self, mocker):
                                                                "http://rs.tdwg.org/dwc/terms/Occurrence",
                                                                "http://rs.tdwg.org/dwc/terms/Occurrence"]}))
         mocker.patch('pandas.DataFrame.to_csv')
+        mocker.patch('dwcahandler.dwca.terms.Terms.update_gbif_ext')
         return_terms_df, return_class_df = Terms.update_terms()
-        return_dwc_terms_df = return_terms_df[return_terms_df.prefix.isin(['dwc'])].copy().reset_index(drop=True)
-        return_dwc_class_df = return_class_df[return_class_df.prefix.isin(['dwc'])].copy().reset_index(drop=True)
+        return_dwc_terms_df = return_terms_df[return_terms_df.prefix.isin(['dwc']) & return_terms_df["uri"].isin(expected_uri_list)].copy().reset_index(drop=True)
+        return_dwc_class_df = return_class_df[return_class_df.prefix.isin(['dwc']) & return_class_df["class_uri"].isin(expected_class_list)].copy().reset_index(drop=True)
         pd.testing.assert_frame_equal(left=return_dwc_terms_df,
                                       right=pd.DataFrame(
                                           {"prefix": [NsPrefix.DWC.value, NsPrefix.DWC.value, NsPrefix.DWC.value],
                                            "term": ["basisOfRecord", "occurrenceID", "scientificName"],
-                                           "uri": ["http://rs.tdwg.org/dwc/terms/basisOfRecord",
-                                                   "http://rs.tdwg.org/dwc/terms/occurrenceID",
-                                                   "http://rs.tdwg.org/dwc/terms/scientificName"]}),
+                                           "uri": expected_uri_list}),
                                       check_index_type=False,
                                       check_dtype=False)
         pd.testing.assert_frame_equal(left=return_dwc_class_df,
                                       right=pd.DataFrame({"prefix": [NsPrefix.DWC.value],
                                                           "class": ["OCCURRENCE"],
-                                                          "class_uri": ["http://rs.tdwg.org/dwc/terms/Occurrence"]}),
+                                                          "class_uri": expected_class_list}),
                                       check_index_type=False,
                                       check_dtype=False)