Added return value for indicating success of add

paperqa/docs.py

@@ -117,7 +117,7 @@ def add_file(
         docname: Optional[str] = None,
         dockey: Optional[DocKey] = None,
         chunk_chars: int = 3000,
-    ) -> str:
+    ) -> Optional[str]:
         """Add a document to the collection."""
         # just put in temp file and use existing method
         suffix = ".txt"
@@ -144,7 +144,7 @@ def add_url(
         docname: Optional[str] = None,
         dockey: Optional[DocKey] = None,
         chunk_chars: int = 3000,
-    ) -> str:
+    ) -> Optional[str]:
         """Add a document to the collection."""
         import urllib.request
 
@@ -167,7 +167,7 @@ def add(
         disable_check: bool = False,
         dockey: Optional[DocKey] = None,
         chunk_chars: int = 3000,
-    ) -> str:
+    ) -> Optional[str]:
         """Add a document to the collection."""
         if dockey is None:
             dockey = md5sum(path)
@@ -216,17 +216,21 @@ def add(
             raise ValueError(
                 f"This does not look like a text document: {path}. Path disable_check to ignore this error."
             )
-        self.add_texts(texts, doc)
-        return docname
+        if self.add_texts(texts, doc):
+            return docname
+        return None
 
     def add_texts(
         self,
         texts: List[Text],
         doc: Doc,
-    ):
-        """Add chunked texts to the collection. This is useful if you have already chunked the texts yourself."""
+    ) -> bool:
+        """Add chunked texts to the collection. This is useful if you have already chunked the texts yourself.
+
+        Returns True if the document was added, False if it was already in the collection.
+        """
         if doc.dockey in self.docs:
-            raise ValueError(f"Document {doc.dockey} already in collection.")
+            return False
         if len(texts) == 0:
             raise ValueError("No texts to add.")
         if doc.docname in self.docnames:
@@ -255,6 +259,7 @@ def add_texts(
         self.docs[doc.dockey] = doc
         self.texts += texts
         self.docnames.add(doc.docname)
+        return True
 
     def delete(
         self, name: Optional[str] = None, dockey: Optional[DocKey] = None

paperqa/version.py

@@ -1 +1 @@
-__version__ = "3.0.0"
+__version__ = "3.1.0"

tests/test_paperqa.py

@@ -105,7 +105,7 @@ def test_evidence():
     docs = Docs()
     docs.add(doc_path, "WikiMedia Foundation, 2023, Accessed now")
     evidence = docs.get_evidence(
-        Answer(question="For which state was he a governor"), k=1, max_sources=1
+        Answer(question="For which state was Bates a governor?"), k=1, max_sources=1
     )
     assert "Missouri" in evidence.context
     os.remove(doc_path)
@@ -121,6 +121,23 @@ def test_query():
     docs.query("What is Frederick Bates's greatest accomplishment?")
 
 
+def test_duplicate():
+    docs = Docs()
+    assert docs.add_url(
+        "https://en.wikipedia.org/wiki/Frederick_Bates_(politician)",
+        citation="WikiMedia Foundation, 2023, Accessed now",
+        dockey="test",
+    )
+    assert (
+        docs.add_url(
+            "https://en.wikipedia.org/wiki/Frederick_Bates_(politician)",
+            citation="WikiMedia Foundation, 2023, Accessed now",
+            dockey="test",
+        )
+        is None
+    )
+
+
 class Test(IsolatedAsyncioTestCase):
     async def test_aquery(self):
         docs = Docs()