aiagents4pharma 1.44.0__py3-none-any.whl → 1.45.1__py3-none-any.whl

aiagents4pharma/talk2scholars/tests/{test_s2_multi.py → test_tools_s2_multi.py}

@@ -4,11 +4,13 @@ Unit tests for S2 tools functionality.
 
 import json
 from types import SimpleNamespace
+
+import hydra
 import pytest
 import requests
-from langgraph.types import Command
 from langchain_core.messages import ToolMessage
-import hydra
+from langgraph.types import Command
+
 from aiagents4pharma.talk2scholars.tools.s2.multi_paper_rec import (
     get_multi_paper_recommendations,
 )
@@ -162,9 +164,7 @@ def dummy_requests_post_exception(url, headers, params, data, timeout):
 def patch_hydra(monkeypatch):
     """Patch Hydra's initialize and compose functions to return dummy objects."""
     # Patch hydra.initialize to return our dummy context manager.
-    monkeypatch.setattr(
-        hydra, "initialize", lambda version_base, config_path: DummyHydraContext()
-    )
+    monkeypatch.setattr(hydra, "initialize", lambda version_base, config_path: DummyHydraContext())
     # Patch hydra.compose to return our dummy config.
     monkeypatch.setattr(hydra, "compose", lambda config_name, overrides: dummy_config)
 

aiagents4pharma/talk2scholars/tests/{test_s2_retrieve.py → test_tools_s2_retrieve.py}

@@ -3,13 +3,14 @@ Unit tests for S2 tools functionality.
 """
 
 from unittest.mock import patch
+
 import pytest
 from langgraph.types import Command
+
 from ..tools.s2.retrieve_semantic_scholar_paper_id import (
     retrieve_semantic_scholar_paper_id,
 )
 
-
 # Fixed test data for deterministic results
 MOCK_SEARCH_RESPONSE = {
     "data": [

aiagents4pharma/talk2scholars/tests/{test_s2_search.py → test_tools_s2_search.py}

@@ -3,11 +3,13 @@ Unit tests for S2 tools functionality.
 """
 
 from types import SimpleNamespace
-import pytest
+
 import hydra
+import pytest
 import requests
-from langgraph.types import Command
 from langchain_core.messages import ToolMessage
+from langgraph.types import Command
+
 from aiagents4pharma.talk2scholars.tools.s2.search import search_tool
 from aiagents4pharma.talk2scholars.tools.s2.utils import search_helper
 
@@ -147,9 +149,7 @@ def dummy_requests_get_exception(url, params, timeout):
 def patch_hydra(monkeypatch):
     """hydra patch to mock initialize and compose functions."""
     # Patch hydra.initialize to return our dummy context manager.
-    monkeypatch.setattr(
-        hydra, "initialize", lambda version_base, config_path: DummyHydraContext()
-    )
+    monkeypatch.setattr(hydra, "initialize", lambda version_base, config_path: DummyHydraContext())
     # Patch hydra.compose to return our dummy config.
     monkeypatch.setattr(hydra, "compose", lambda config_name, overrides: dummy_config)
 

aiagents4pharma/talk2scholars/tests/{test_s2_single.py → test_tools_s2_single.py}

@@ -3,11 +3,13 @@ Unit tests for S2 tools functionality.
 """
 
 from types import SimpleNamespace
+
+import hydra
 import pytest
 import requests
-import hydra
-from langgraph.types import Command
 from langchain_core.messages import ToolMessage
+from langgraph.types import Command
+
 from aiagents4pharma.talk2scholars.tools.s2.single_paper_rec import (
     get_single_paper_recommendations,
 )
@@ -156,9 +158,7 @@ def dummy_requests_get_exception(url, params, timeout):
 @pytest.fixture(autouse=True)
 def patch_hydra(monkeypatch):
     """Patch Hydra's initialize and compose functions with dummy implementations."""
-    monkeypatch.setattr(
-        hydra, "initialize", lambda version_base, config_path: DummyHydraContext()
-    )
+    monkeypatch.setattr(hydra, "initialize", lambda version_base, config_path: DummyHydraContext())
     # Patch hydra.compose to return our dummy config.
     monkeypatch.setattr(hydra, "compose", lambda config_name, overrides: dummy_config)
 

aiagents4pharma/talk2scholars/tests/{test_arxiv_downloader.py → test_utils_arxiv_downloader.py}

@@ -81,7 +81,10 @@ class TestArxivDownloader(unittest.TestCase):
                     <name>Jane Smith</name>
                 </author>
                 <link href="http://arxiv.org/abs/1234.5678v1" rel="alternate" type="text/html"/>
-                <link href="http://arxiv.org/pdf/1234.5678v1.pdf" rel="related" type="application/pdf" title="pdf"/>
+                <link href="http://arxiv.org/pdf/1234.5678v1.pdf"
+                    rel="related"
+                    type="application/pdf"
+                    title="pdf"/>
             </entry>
         </feed>"""
 
@@ -104,8 +107,7 @@ class TestArxivDownloader(unittest.TestCase):
 
         # Verify API call - it uses query string format, not params
         expected_url = (
-            "http://export.arxiv.org/api/query?search_query="
-            "id:1234.5678&start=0&max_results=1"
+            "http://export.arxiv.org/api/query?search_query=id:1234.5678&start=0&max_results=1"
         )
         mock_get.assert_called_once_with(expected_url, timeout=30)
         mock_response.raise_for_status.assert_called_once()
@@ -201,9 +203,7 @@ class TestArxivDownloader(unittest.TestCase):
         metadata = ET.fromstring(self.sample_xml)
         pdf_result = ("/tmp/test.pdf", "test_paper.pdf")
 
-        result = self.downloader.extract_paper_metadata(
-            metadata, "1234.5678", pdf_result
-        )
+        result = self.downloader.extract_paper_metadata(metadata, "1234.5678", pdf_result)
 
         # Verify extracted metadata
         expected_metadata = {
@@ -226,9 +226,7 @@ class TestArxivDownloader(unittest.TestCase):
         """Test metadata extraction without PDF download."""
         metadata = ET.fromstring(self.sample_xml)
 
-        with patch.object(
-            self.downloader, "get_default_filename", return_value="1234.5678.pdf"
-        ):
+        with patch.object(self.downloader, "get_default_filename", return_value="1234.5678.pdf"):
             result = self.downloader.extract_paper_metadata(metadata, "1234.5678", None)
 
         # Verify metadata without PDF
@@ -275,9 +273,7 @@ class TestArxivDownloader(unittest.TestCase):
         # Case 1: Title present
         metadata1 = ET.fromstring(self.sample_xml)
         entry1 = metadata1.find("atom:entry", ns)
-        self.assertEqual(
-            self.downloader.extract_title_public(entry1, ns), "Test Paper Title"
-        )
+        self.assertEqual(self.downloader.extract_title_public(entry1, ns), "Test Paper Title")
 
         # Case 2: Title missing
         xml_no_title = """<?xml version="1.0" encoding="UTF-8"?>
@@ -346,9 +342,7 @@ class TestArxivDownloader(unittest.TestCase):
         )
 
         # Without result
-        with patch.object(
-            self.downloader, "get_default_filename", return_value="default.pdf"
-        ):
+        with patch.object(self.downloader, "get_default_filename", return_value="default.pdf"):
             expected_without = {
                 "URL": "",
                 "pdf_url": "",
@@ -365,9 +359,7 @@ class TestArxivDownloader(unittest.TestCase):
         """Service name, identifier name, and default filename helpers."""
         self.assertEqual(self.downloader.get_service_name(), "arXiv")
         self.assertEqual(self.downloader.get_identifier_name(), "arXiv ID")
-        self.assertEqual(
-            self.downloader.get_default_filename("1234.5678"), "1234.5678.pdf"
-        )
+        self.assertEqual(self.downloader.get_default_filename("1234.5678"), "1234.5678.pdf")
 
     def test_get_paper_identifier_info(self):
         """Test _get_paper_identifier_info method."""
@@ -411,7 +403,10 @@ class TestArxivDownloaderIntegration(unittest.TestCase):
                 <author>
                     <name>Test Author</name>
                 </author>
-                <link href="http://arxiv.org/pdf/1234.5678v1.pdf" rel="related" type="application/pdf" title="pdf"/>
+                <link href="http://arxiv.org/pdf/1234.5678v1.pdf"
+                    rel="related"
+                    type="application/pdf"
+                    title="pdf"/>
             </entry>
         </feed>"""
 
@@ -446,9 +441,7 @@ class TestArxivDownloaderIntegration(unittest.TestCase):
             pdf_result = self.downloader.download_pdf_to_temp(pdf_url, identifier)
 
             # Step 4: Extract metadata
-            paper_data = self.downloader.extract_paper_metadata(
-                metadata, identifier, pdf_result
-            )
+            paper_data = self.downloader.extract_paper_metadata(metadata, identifier, pdf_result)
 
             results[identifier] = paper_data
 
@@ -464,9 +457,7 @@ class TestArxivDownloaderIntegration(unittest.TestCase):
 
         # Verify method calls
         mock_get.assert_called_once()
-        mock_download.assert_called_once_with(
-            "http://arxiv.org/pdf/1234.5678v1.pdf", "1234.5678"
-        )
+        mock_download.assert_called_once_with("http://arxiv.org/pdf/1234.5678v1.pdf", "1234.5678")
 
     @patch("requests.get")
     def test_error_handling_workflow(self, mock_get):

aiagents4pharma/talk2scholars/tests/{test_base_paper_downloader.py → test_utils_base_paper_downloader.py}

@@ -3,11 +3,11 @@ Unit tests for BasePaperDownloader.
 Tests the abstract base class functionality and common methods.
 """
 
+import inspect
 import unittest
-from typing import Any, Dict, Optional, Tuple
+from typing import Any
 from unittest.mock import Mock, patch
 
-import inspect
 import requests
 
 from aiagents4pharma.talk2scholars.tools.paper_download.utils.base_paper_downloader import (
@@ -31,8 +31,8 @@ class ConcretePaperDownloader(BasePaperDownloader):
         return f"https://test.com/{identifier}.pdf"
 
     def extract_paper_metadata(
-        self, metadata: Any, identifier: str, pdf_result: Optional[Tuple[str, str]]
-    ) -> Dict[str, Any]:
+        self, metadata: Any, identifier: str, pdf_result: tuple[str, str] | None
+    ) -> dict[str, Any]:
         """Concrete implementation for testing."""
         return {
             "Title": f"Test Paper {identifier}",
@@ -53,21 +53,19 @@ class ConcretePaperDownloader(BasePaperDownloader):
         """Concrete implementation for testing."""
         return f"test_{identifier}.pdf"
 
-    def _get_paper_identifier_info(self, paper: Dict[str, Any]) -> str:
+    def _get_paper_identifier_info(self, paper: dict[str, Any]) -> str:
         """Concrete implementation for testing."""
         return f" ({paper.get('identifier', 'unknown')})"
 
-    def _add_service_identifier(self, entry: Dict[str, Any], identifier: str) -> None:
+    def _add_service_identifier(self, entry: dict[str, Any], identifier: str) -> None:
         """Concrete implementation for testing."""
         entry["test_id"] = identifier
 
-    def get_paper_identifier_info_public(self, paper: Dict[str, Any]) -> str:
+    def get_paper_identifier_info_public(self, paper: dict[str, Any]) -> str:
         """Public wrapper to access protected identifier info for tests."""
         return self._get_paper_identifier_info(paper)
 
-    def add_service_identifier_public(
-        self, entry: Dict[str, Any], identifier: str
-    ) -> None:
+    def add_service_identifier_public(self, entry: dict[str, Any], identifier: str) -> None:
         """Public wrapper to access protected service identifier for tests."""
         self._add_service_identifier(entry, identifier)
 
@@ -109,9 +107,7 @@ class TestBasePaperDownloader(unittest.TestCase):
         mock_response = Mock()
         mock_response.raise_for_status = Mock()
         mock_response.iter_content.return_value = [b"PDF chunk 1", b"PDF chunk 2"]
-        mock_response.headers = {
-            "Content-Disposition": 'attachment; filename="paper.pdf"'
-        }
+        mock_response.headers = {"Content-Disposition": 'attachment; filename="paper.pdf"'}
         mock_get.return_value = mock_response
 
         # Mock temporary file
@@ -121,9 +117,7 @@ class TestBasePaperDownloader(unittest.TestCase):
         mock_temp_file.__exit__ = Mock(return_value=None)
         mock_tempfile.return_value = mock_temp_file
 
-        result = self.downloader.download_pdf_to_temp(
-            "https://test.com/paper.pdf", "12345"
-        )
+        result = self.downloader.download_pdf_to_temp("https://test.com/paper.pdf", "12345")
 
         # Verify result
         self.assertEqual(result, ("/tmp/test.pdf", "paper.pdf"))
@@ -153,9 +147,7 @@ class TestBasePaperDownloader(unittest.TestCase):
         """Test PDF download with network error."""
         mock_get.side_effect = requests.RequestException("Network error")
 
-        result = self.downloader.download_pdf_to_temp(
-            "https://test.com/paper.pdf", "12345"
-        )
+        result = self.downloader.download_pdf_to_temp("https://test.com/paper.pdf", "12345")
 
         self.assertIsNone(result)
 
@@ -235,12 +227,8 @@ class TestBasePaperDownloader(unittest.TestCase):
                 raise requests.RequestException("Fetch failed")
             return {"test": identifier}
 
-        with patch.object(
-            self.downloader, "fetch_metadata", side_effect=mock_fetch_metadata
-        ):
-            with patch.object(
-                self.downloader, "download_pdf_to_temp", return_value=None
-            ):
+        with patch.object(self.downloader, "fetch_metadata", side_effect=mock_fetch_metadata):
+            with patch.object(self.downloader, "download_pdf_to_temp", return_value=None):
                 result = self.downloader.process_identifiers(identifiers)
 
         # Valid identifier should succeed
@@ -316,11 +304,11 @@ class TestBasePaperDownloader(unittest.TestCase):
         """Test building summary with long list (should show only top 3)."""
         article_data = {}
         for i in range(5):  # More than 3
-            article_data[f"{i+1}"] = {
-                "Title": f"Paper {i+1}",
-                "identifier": f"{i+1}",
+            article_data[f"{i + 1}"] = {
+                "Title": f"Paper {i + 1}",
+                "identifier": f"{i + 1}",
                 "access_type": "open_access_downloaded",
-                "Abstract": f"Abstract {i+1}",
+                "Abstract": f"Abstract {i + 1}",
             }
 
         result = self.downloader.build_summary(article_data)
@@ -388,9 +376,7 @@ class TestBasePaperDownloader(unittest.TestCase):
             BasePaperDownloader.construct_pdf_url(self.downloader, {}, "test")
 
         with self.assertRaises(NotImplementedError):
-            BasePaperDownloader.extract_paper_metadata(
-                self.downloader, {}, "test", None
-            )
+            BasePaperDownloader.extract_paper_metadata(self.downloader, {}, "test", None)
 
         with self.assertRaises(NotImplementedError):
             BasePaperDownloader.get_service_name(self.downloader)
@@ -402,15 +388,13 @@ class TestBasePaperDownloader(unittest.TestCase):
             BasePaperDownloader.get_default_filename(self.downloader, "test")
 
         # Protected abstract methods: call via getattr to avoid W0212 while still executing code.
+        method_name_1 = "_get_paper_identifier_info"
         with self.assertRaises(NotImplementedError):
-            getattr(BasePaperDownloader, "_get_paper_identifier_info")(
-                self.downloader, {}
-            )
+            getattr(BasePaperDownloader, method_name_1)(self.downloader, {})
 
+        method_name_2 = "_add_service_identifier"
         with self.assertRaises(NotImplementedError):
-            getattr(BasePaperDownloader, "_add_service_identifier")(
-                self.downloader, {}, "test"
-            )
+            getattr(BasePaperDownloader, method_name_2)(self.downloader, {}, "test")
 
     @patch("tempfile.NamedTemporaryFile")
     @patch("requests.get")
@@ -420,9 +404,7 @@ class TestBasePaperDownloader(unittest.TestCase):
         mock_response = Mock()
         mock_response.raise_for_status = Mock()
         mock_response.iter_content.return_value = [b"PDF data"]
-        mock_response.headers = {
-            "Content-Disposition": 'attachment; filename="paper.pdf"'
-        }
+        mock_response.headers = {"Content-Disposition": 'attachment; filename="paper.pdf"'}
         mock_get.return_value = mock_response
 
         # Mock temporary file
@@ -434,9 +416,7 @@ class TestBasePaperDownloader(unittest.TestCase):
 
         # Patch re.search to raise an exception during filename extraction
         with patch("re.search", side_effect=requests.RequestException("Regex error")):
-            result = self.downloader.download_pdf_to_temp(
-                "https://test.com/paper.pdf", "12345"
-            )
+            result = self.downloader.download_pdf_to_temp("https://test.com/paper.pdf", "12345")
 
         # Should still succeed but use default filename due to exception
         self.assertEqual(result, ("/tmp/test.pdf", "test_12345.pdf"))
@@ -507,9 +487,7 @@ class TestBasePaperDownloaderEdgeCases(unittest.TestCase):
         mock_temp_file.__exit__ = Mock(return_value=None)
         mock_tempfile.return_value = mock_temp_file
 
-        with patch.object(
-            self.downloader, "get_default_filename", return_value="default.pdf"
-        ):
+        with patch.object(self.downloader, "get_default_filename", return_value="default.pdf"):
             # Call without assigning to avoid 'unused-variable'
             self.downloader.download_pdf_to_temp("https://test.com/paper.pdf", "12345")
 

aiagents4pharma/talk2scholars/tests/{test_biorxiv_downloader.py → test_utils_biorxiv_downloader.py}

@@ -122,9 +122,7 @@ class TestBiorxivDownloader(unittest.TestCase):
         result = self.downloader.fetch_metadata("10.1101/2023.01.01.123456")
 
         # Verify API call
-        expected_url = (
-            "https://api.biorxiv.org/details/biorxiv/10.1101/2023.01.01.123456/na/json"
-        )
+        expected_url = "https://api.biorxiv.org/details/biorxiv/10.1101/2023.01.01.123456/na/json"
         mock_scraper.get.assert_called_once_with(expected_url, timeout=30)
         mock_response.raise_for_status.assert_called_once()
 
@@ -171,9 +169,7 @@ class TestBiorxivDownloader(unittest.TestCase):
         # Default version
         meta_default = {"collection": [{"title": "Test Paper"}]}
         self.assertEqual(
-            self.downloader.construct_pdf_url(
-                meta_default, "10.1101/2023.01.01.123456"
-            ),
+            self.downloader.construct_pdf_url(meta_default, "10.1101/2023.01.01.123456"),
             "https://www.biorxiv.org/content/10.1101/2023.01.01.123456v1.full.pdf",
         )
 
@@ -195,9 +191,7 @@ class TestBiorxivDownloader(unittest.TestCase):
             b"PDF content chunk 1",
             b"PDF content chunk 2",
         ]
-        mock_pdf_response.headers = {
-            "Content-Disposition": 'attachment; filename="paper.pdf"'
-        }
+        mock_pdf_response.headers = {"Content-Disposition": 'attachment; filename="paper.pdf"'}
 
         mock_scraper.get.side_effect = [mock_landing_response, mock_pdf_response]
 
@@ -209,9 +203,7 @@ class TestBiorxivDownloader(unittest.TestCase):
         mock_tempfile.return_value = mock_temp_file
 
         pdf_url = "https://www.biorxiv.org/content/10.1101/2023.01.01.123456v1.full.pdf"
-        result = self.downloader.download_pdf_to_temp(
-            pdf_url, "10.1101/2023.01.01.123456"
-        )
+        result = self.downloader.download_pdf_to_temp(pdf_url, "10.1101/2023.01.01.123456")
 
         # Verify result
         self.assertEqual(result, ("/tmp/test.pdf", "paper.pdf"))
@@ -263,9 +255,7 @@ class TestBiorxivDownloader(unittest.TestCase):
         mock_scraper.get.return_value = ok
 
         # Case 1: with .full.pdf -> should visit landing
-        pdf_url_full = (
-            "https://www.biorxiv.org/content/10.1101/2023.01.01.123456v1.full.pdf"
-        )
+        pdf_url_full = "https://www.biorxiv.org/content/10.1101/2023.01.01.123456v1.full.pdf"
         self.downloader.visit_landing_page_public(
             mock_scraper, pdf_url_full, "10.1101/2023.01.01.123456"
         )
@@ -324,9 +314,7 @@ class TestBiorxivDownloader(unittest.TestCase):
             ),  # trigger exception path
         ]
         for headers, expected, raise_regex in cases:
-            with self.subTest(
-                headers=headers, expected=expected, raise_regex=raise_regex
-            ):
+            with self.subTest(headers=headers, expected=expected, raise_regex=raise_regex):
                 resp = Mock()
                 resp.headers = headers
                 if raise_regex:
@@ -339,18 +327,14 @@ class TestBiorxivDownloader(unittest.TestCase):
                             "get_default_filename",
                             return_value="default.pdf",
                         ):
-                            got = self.downloader.extract_filename_public(
-                                resp, "10.1101/test"
-                            )
+                            got = self.downloader.extract_filename_public(resp, "10.1101/test")
                 else:
                     with patch.object(
                         self.downloader,
                         "get_default_filename",
                         return_value="default.pdf",
                     ):
-                        got = self.downloader.extract_filename_public(
-                            resp, "10.1101/test"
-                        )
+                        got = self.downloader.extract_filename_public(resp, "10.1101/test")
                 self.assertEqual(got, expected)
 
     def test_extract_paper_metadata_success(self):
@@ -396,18 +380,14 @@ class TestBiorxivDownloader(unittest.TestCase):
         self.assertEqual(result["URL"], "")
         self.assertEqual(result["pdf_url"], "")
         self.assertEqual(result["temp_file_path"], "")
-        self.assertEqual(
-            result["filename"], "10_1101_2023_01_01_123456.pdf"
-        )  # Default filename
+        self.assertEqual(result["filename"], "10_1101_2023_01_01_123456.pdf")  # Default filename
 
     def test_extract_paper_metadata_no_collection(self):
         """Test metadata extraction with missing collection."""
         metadata = {}
 
         with self.assertRaises(RuntimeError) as context:
-            self.downloader.extract_paper_metadata(
-                metadata, "10.1101/2023.01.01.123456", None
-            )
+            self.downloader.extract_paper_metadata(metadata, "10.1101/2023.01.01.123456", None)
 
         self.assertIn("No collection data found", str(context.exception))
 
@@ -415,9 +395,7 @@ class TestBiorxivDownloader(unittest.TestCase):
         """Test basic metadata extraction helper method."""
         paper = self.sample_json_response["collection"][0]
 
-        result = self.downloader.extract_basic_metadata_public(
-            paper, "10.1101/2023.01.01.123456"
-        )
+        result = self.downloader.extract_basic_metadata_public(paper, "10.1101/2023.01.01.123456")
 
         expected = {
             "Title": "Test BioRxiv Paper",
@@ -468,9 +446,7 @@ class TestBiorxivDownloader(unittest.TestCase):
         """Test _add_service_identifier method."""
         entry = {}
 
-        self.downloader.add_service_identifier_public(
-            entry, "10.1101/2023.01.01.123456"
-        )
+        self.downloader.add_service_identifier_public(entry, "10.1101/2023.01.01.123456")
 
         self.assertEqual(entry["DOI"], "10.1101/2023.01.01.123456")
         self.assertEqual(entry["server"], "biorxiv")
@@ -561,9 +537,7 @@ class TestBiorxivDownloaderIntegration(unittest.TestCase):
         pdf_result = self.downloader.download_pdf_to_temp(pdf_url, identifier)
 
         # Step 4: Extract metadata
-        paper_data = self.downloader.extract_paper_metadata(
-            metadata, identifier, pdf_result
-        )
+        paper_data = self.downloader.extract_paper_metadata(metadata, identifier, pdf_result)
 
         # Verify the complete workflow
         self.assertEqual(paper_data["Title"], "Integration Test Paper")
@@ -571,9 +545,7 @@ class TestBiorxivDownloaderIntegration(unittest.TestCase):
         self.assertEqual(paper_data["access_type"], "open_access_downloaded")
         self.assertEqual(paper_data["temp_file_path"], "/tmp/integration.pdf")
 
-        expected_pdf_url = (
-            "https://www.biorxiv.org/content/10.1101/2023.01.01.123456v1.full.pdf"
-        )
+        expected_pdf_url = "https://www.biorxiv.org/content/10.1101/2023.01.01.123456v1.full.pdf"
         self.assertEqual(pdf_url, expected_pdf_url)
 
         # Verify 3 calls: metadata, landing page, PDF