Merge pull request 'redirection of non active ror ids' (#1) from main into openaire-workflow-ready

Reviewed-on: #1

affro_cluster.py

@@ -15,7 +15,7 @@ def affro(raw_aff_string):
     try:
         result = Aff_Ids(create_df_algorithm(raw_aff_string), dix_org, dix_mult, dix_city, dix_country,  0.65, 0.82)
         if len(result)>0:
-            result_dict =  [json.dumps({'Origin': 'affRo', 'RORid':x[2], 'Confidence':x[1]}) for x in result]
+            result_dict =  [json.dumps({'Origin': 'affRo', 'RORid':x[2], 'Confidence':x[1], 'Status':x[3]}) for x in result]
         else:
             result_dict =  []
 
@@ -25,7 +25,6 @@ def affro(raw_aff_string):
         print(f"Error: {str(e)}")
         print(raw_aff_string)
         pass
-#raw_aff = 'university of california, los angeles, university of athens, university of california, san diego, university of athens, greece'
 
 
 if __name__ == "__main__":

matching_cluster.py

@@ -9,6 +9,9 @@ from sklearn.metrics.pairwise import cosine_similarity
 from functions_cluster import *
 from create_input_cluster import *
 
+with open('/Users/myrto/Documents/openAIRE/3. ror/dictionaries/dix_status.json', 'rb') as f:
+    dix_status = json.load(f)
+    
 def best_sim_score(light_raw, candidate_num, pairs_list, m, simU, simG):
     """
     Finds the best match between a 'key word' and several legal names from the OpenAIRE database.
@@ -259,39 +262,37 @@ def Aff_Ids(input, dix_org, dix_mult, dix_city_ror, dix_country_ror, simU, simG)
        # id_list = []
         if dix_mult[x] != 'unique':
             if x in list(dix_city_ror.keys()):
-                match_found0 = False
                 match_found = False
 
                 for city in dix_city_ror[x]:
                     if city[0] in light_aff:
                         if city[0] not in x: 
                             ids[i] = city[1]                            
-                            
-                            match_found0 = True
                             match_found = True
                             break
+                        else:
+                            if light_aff.count(city[0]) >1:
+                                ids[i] = city[1]
+                                match_found = True
+                                break
+                            
                 if not match_found:
                     for city in dix_city_ror[x]:
                         if city[0] in   light_aff and city[0] not in x:
                             ids[i] = city[1]
-                            match_found0 = True
-                            print('ok')
                             break  
                     
                 if not match_found:
-                    match_found2 = False
                     match_found3 = False
 
                     for country in dix_country_ror[x]:
                         if country[0] == 'united states' and (country[0] in light_aff or 'usa'  in light_aff):
                             ids[i] = country[1]
-                            match_found2 = True
                             match_found3 = True
                             break
                         
                         if country[0] == 'united kingdom' and (country[0] in light_aff or 'uk'  in light_aff):
                             ids[i] = country[1]
-                            match_found2 = True
                             match_found3 = True
                             break
 
@@ -299,7 +300,6 @@ def Aff_Ids(input, dix_org, dix_mult, dix_city_ror, dix_country_ror, simU, simG)
 
                             if country[0] not in x:
                                 ids[i] = country[1]
-                                match_found2 = True
                                 match_found3 = True
                                 break
 
@@ -307,13 +307,25 @@ def Aff_Ids(input, dix_org, dix_mult, dix_city_ror, dix_country_ror, simU, simG)
                         for country in dix_country_ror[x]:
                             if country[0] in light_aff and country[0] in x:
                                 ids[i] = country[1]
-                                match_found2 = True
                                 break  
                         
 
 
-            
-
     results = [[x[0],x[1], ids[i]] for i,x in enumerate(best)]
+    results_upd = []
 
-    return  results #[[result[to_check[i]] for i in ready] + [to_check[2]], best[0]]
+    for r in results:
+        if  dix_status[r[2]][0] == 'active':
+            r.append('active')
+            results_upd.append(r)
+        else:
+            if dix_status[r[2]][1] == '':
+                r.append(dix_status[r[2]][0])
+                results_upd.append(r)
+            else:
+                r.append(dix_status[r[2]][0])
+                results_upd.append(r)
+                results_upd.append([r[0],r[1], dix_status[r[2]][1], 'active'])
+            
+        
+    return  results_upd