Merge remote-tracking branch 'origin/dev' into dev

test/test_1_nonsense.py

@@ -7,12 +7,8 @@
 
 import pytest
 import os.path
-import csv
 from datetime import date
-from swesesci.scholar import SSSScholar
-from swesesci.affiliation import SSSAffiliation
 from swesesci.scholar_reader import ScholarReader
-from swesesci.scholar_miner import ScholarMiner
 
 class TestClass_NonSense:
 

test/test_3_twoscholars.py

@@ -8,8 +8,6 @@
 import pytest
 import os.path
 from datetime import date
-from swesesci.scholar import SSSScholar
-from swesesci.affiliation import SSSAffiliation
 from swesesci.scholar_reader import ScholarReader
 from swesesci.scholar_miner import ScholarMiner
 from swesesci.scholar_analyzer import ScholarAnalyzer
@@ -32,7 +30,6 @@ def setup_method(self):
         self.miner = ScholarMiner(self.filename_prefix, self.sss_scholars, self.sss_affiliations)
         self.miner.parse_scholars()
         self.sss_scholars = self.miner.get_scholars()
-        print(self.sss_scholars)
 
     def test_two_results(self):
         # TC1: Test that DBLP returns a result

test/test_4_nonasciititles.csv

@@ -0,0 +1 @@
+Affiliation,Mauro Caporuscio,-1,https://dblp.org/pid/c/MauroCaporuscio.xml

test/test_4_nonasciititles.py

@@ -5,80 +5,40 @@
 @author: Markus Borg
 """
 
-import pytest
 import os.path
 from datetime import date
-from swesesci.scholar import SSSScholar
-from swesesci.affiliation import SSSAffiliation
+from swesesci.scholar_reader import ScholarReader
 from swesesci.scholar_miner import ScholarMiner
 from swesesci.scholar_analyzer import ScholarAnalyzer
 from swesesci.scholar_tabulator import ScholarTabulator
 
-def string_splitter(scholar_string):
-    affiliation = scholar_string[0]
-    name = scholar_string[1]
-    running_number = scholar_string[2]
-    url = scholar_string[3]
-
-    try:
-        split1 = url.split("pid/")
-        split2 = split1[1].split(".xml")
-        pid = split2[0]
-    except IndexError:
-        print("Invalid format of input XML URL. (" + name + ")")
-        raise IndexError
-
-    return affiliation, name, running_number, pid, url
-
 class TestClass_NonASCIITitles:
 
     def setup_method(self):
-        self.scholars = []
-        self.affiliations = []
+        self.sss_scholars = []
+        self.sss_affiliations = []
         subdirectory = "output"
         try:
             os.mkdir(subdirectory)
         except Exception:
             pass
         self.filename_prefix = os.path.join(subdirectory, str(date.today()) + "_sss_")
-        self.test_nonascii_scholar = [("Mauro Caporuscio", "-1", "https://dblp.org/pid/c/MauroCaporuscio.xml")]
-
-    def add_sss_scholars(self, process_list, affiliation):
-        for person in process_list:
-            name = person[0]
-            running_number = person[1]
-            url = person[2]
-            # extract the pid from the url by substringing
-            try:
-                split1 = url.split("pid/")
-                split2 = split1[1].split(".xml")
-                pid = split2[0]
-            except IndexError:
-                print("Invalid format of input XML URL.")
-                return
 
-            self.scholars.append(SSSScholar(name, running_number, pid, url, affiliation, -1))
-            tmp_aff = SSSAffiliation(affiliation)
-            if tmp_aff not in self.affiliations:
-                tmp_aff.nbr_scholars += 1
-                self.affiliations.append(tmp_aff)
-            else:
-                curr = next((x for x in self.affiliations if affiliation == x.name), None)
-                curr.nbr_scholars += 1
+        reader = ScholarReader("test/test_4_nonasciititles.csv")
+        self.sss_scholars, self.sss_affiliations = reader.read_candidate_scholars()
+        self.miner = ScholarMiner(self.filename_prefix, self.sss_scholars, self.sss_affiliations)
+        self.miner.parse_scholars()
+        self.sss_scholars = self.miner.get_scholars()
 
     def test_mauro_caporuscio(self):
-        self.add_sss_scholars(self.test_nonascii_scholar, "N/A")
-        self.miner = ScholarMiner(self.filename_prefix, self.scholars, self.affiliations)
-        self.miner.parse_scholars() # This involves dealing with non-ASCII characters
-        self.scholars = self.miner.get_scholars()
         mauro = None
-        for scholar in self.scholars:
+        for scholar in self.sss_scholars:
             if scholar.name == "Mauro Caporuscio":
                 mauro = scholar
 
                 # TC1: Test that DBLP returns a result
-                assert self.scholars != None
-                assert len(self.scholars) == 1
+                assert self.sss_scholars != None
+                assert len(self.sss_scholars) == 1
 
                 # TC2: Test that Mauro has at least 40 DBLP entries
                 assert mauro.dblp_entries >= 40
@@ -108,11 +68,11 @@ def test_mauro_caporuscio(self):
                 assert file_stats_csv.st_size > 0
 
                 # TC8: Test analyzer
-                analyzer = ScholarAnalyzer(self.filename_prefix, self.scholars, self.affiliations)
+                analyzer = ScholarAnalyzer(self.filename_prefix, self.sss_scholars, self.sss_affiliations)
                 analyzer.analyze_individual_research_interests()
                 assert mauro.sss_contrib >= 1.50
                 assert mauro.sss_rating >= 1.00
 
                 # TC10: Test tabulator
-                tabulator = ScholarTabulator(self.filename_prefix, self.scholars, self.affiliations)
+                tabulator = ScholarTabulator(self.filename_prefix, self.sss_scholars, self.sss_affiliations)
                 tabulator.write_tables()