Merge branch 'main' into include_more_characters

PapersCited.py

@@ -43,6 +43,8 @@ class PhrasesToChange:
       "suradnicima": "sur.",
       "suradnici": "sur.",
       "suradnika": "sur.",
+      # Change possesive form to a proper noun
+      "'s" : ""
     }
     # Before adding something to excluded phrases, Google [word] surname.
     # If anything shows up, don't include that word.

tests/test_detecting_authors.py

@@ -152,4 +152,23 @@ def test_new_foreign_characters():
         ["Bø (1999", "Yø (2000", "Så (2001"]
     text_non_alphanumeric = "Bø's (1999) research cited Yø-yoma (2000)"
     assert PapersCited.get_matches_solo_author(text_non_alphanumeric).citations ==\
-        ["Bø's (1999", "Yø-yoma (2000"]
+        ["Bø's (1999", "Yø-yoma (2000"]
+
+def test_possesive_recognised_and_adjusted():
+    possesive_text = "Listen to Cohen's (1999) talk."
+    matches = PapersCited.get_matches_solo_author(possesive_text)
+    matches.cleanup()
+    assert matches.citations == ["Cohen 1999"]
+    # When both possesive and regular form are cited, this should result in a single,
+    # proper form citation.
+    possesive_and_regular = "Listen to Cohen's (1999) talk. Or read Cohen (1999)"
+    matches = PapersCited.get_matches_solo_author(possesive_and_regular)
+    matches.cleanup()
+    assert matches.citations == ["Cohen 1999"]
+
+def test_surnames_apostrophe_s_recognised():
+    text = "O'Sullivan (2000) wrote a paper. Compare it to O'Samuel's (1999) work."
+    matches = PapersCited.get_matches_solo_author(text)
+    matches.cleanup()
+    assert matches.citations == ["O'Samuel 1999", "O'Sullivan 2000"]
+