fix: Crossref User-Agent/mailto headers (#21) and author name field (#22)

- EnricherModule: add _crossref_headers with proper User-Agent and mailto
- _get_crossref_metadata: use shared headers/mailto for all requests
- _format_authors: handle name field (org authors) and given-only authors
- Add regression tests for both fixes

Closes #21
Closes #22

Author: Ang

onecite/pipeline.py

@@ -2359,6 +2359,11 @@ def __init__(self, use_google_scholar: bool = False):
         self.pubmed_base = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils"
         self.use_google_scholar = use_google_scholar
         self._used_keys: set = set()
+        self._crossref_headers = {
+            'Accept': 'application/json',
+            'User-Agent': f'OneCite/0.1.0 (https://github.com/HzaCode/OneCite; mailto:onecite@users.noreply.github.com)',
+        }
+        self._crossref_mailto = 'onecite@users.noreply.github.com'
 
     def enrich(self, identified_entries: List[IdentifiedEntry], 
                template: Dict, raw_entries: List[RawEntry] = None) -> List[CompletedEntry]:
@@ -2584,9 +2589,8 @@ def _get_crossref_metadata(self, doi: str) -> Optional[Dict]:
         """Get metadata from the Crossref API"""
         try:
             url = f"{self.crossref_base_url}/{doi}"
-            headers = {'Accept': 'application/json'}
-            
-            response = requests.get(url, headers=headers, timeout=10)
+            params = {'mailto': self._crossref_mailto}
+            response = requests.get(url, headers=self._crossref_headers, params=params, timeout=10)
             response.raise_for_status()
 
             data = response.json()
@@ -2800,13 +2804,17 @@ def _format_authors(self, authors: List[Dict]) -> str:
         """Format the author list"""
         formatted_authors = []
         for author in authors:
-            given = author.get('given', '')
-            family = author.get('family', '')
-            if family:
-                if given:
+            if author.get('name'):
+                formatted_authors.append(author['name'])
+            else:
+                given = author.get('given', '')
+                family = author.get('family', '')
+                if family and given:
                     formatted_authors.append(f"{family}, {given}")
-                else:
+                elif family:
                     formatted_authors.append(family)
+                elif given:
+                    formatted_authors.append(given)
 
         return ' and '.join(formatted_authors)
 

tests/test_pipeline_unit.py

@@ -681,6 +681,41 @@ def test_strip_html(self):
         assert e._strip_html_tags("Human-level <i>control</i> &amp; learning") == \
                "Human-level control & learning"
 
+    def test_crossref_request_has_user_agent_and_mailto(self):
+        """fix #21: _get_crossref_metadata must send User-Agent and mailto."""
+        e = EnricherModule(use_google_scholar=False)
+        captured = {}
+
+        def fake_get(url, *a, **kw):
+            captured['headers'] = kw.get('headers', {})
+            captured['params'] = kw.get('params', {})
+            return DummyResponse(json_data={"message": {
+                "DOI": "10.1234/x", "title": ["T"],
+                "published-print": {"date-parts": [[2020]]},
+            }})
+
+        with patch("onecite.pipeline.requests.get", side_effect=fake_get):
+            e._get_crossref_metadata("10.1234/x")
+
+        assert "User-Agent" in captured["headers"], "User-Agent header missing"
+        assert "OneCite" in captured["headers"]["User-Agent"]
+        assert captured["params"].get("mailto"), "mailto param missing"
+
+    def test_format_authors_name_field(self):
+        """fix #22: org authors with 'name' field must not be dropped."""
+        e = EnricherModule(use_google_scholar=False)
+        authors = [
+            {"given": "John", "family": "Doe"},
+            {"name": "World Health Organization"},
+            {"family": "Smith"},
+            {"given": "Alice"},
+        ]
+        result = e._format_authors(authors)
+        assert "Doe, John" in result
+        assert "World Health Organization" in result
+        assert "Smith" in result
+        assert "Alice" in result
+
     def test_google_scholar_disabled_returns_none(self):
         e = EnricherModule(use_google_scholar=False)
         assert e._fetch_missing_field("pages", ["google_scholar_scraper"], {"title": "T"}) is None