fix: remove hardcoded well_known_papers (#19) and add string/stdin input (#36)

- Remove well_known_papers dict and shortcut lookup from IdentifierModule
- 'attention is all you need' now resolved via normal arXiv/Crossref search
- CLI process command accepts: file path, '-' for stdin, or inline string
- Update examples in --help text to show new usage patterns
- Update tests: replace well_known_paper_shortcut test, add string/stdin tests

Closes #19
Closes #36

Author: Ang

onecite/cli.py

@@ -47,8 +47,11 @@ def create_parser() -> argparse.ArgumentParser:
         epilog="""
 Examples:
   onecite process references.txt --output-format bibtex
-  onecite process references.bib --input-type bib --template conference_paper 
+  onecite process references.bib --input-type bib --template conference_paper
   onecite process references.txt --interactive --output results.bib
+  onecite process "10.1038/nature14539"
+  onecite process "attention is all you need, Vaswani et al., NIPS 2017"
+  echo "10.1038/nature14539" | onecite process -
         """
     )
 
@@ -67,7 +70,7 @@ def create_parser() -> argparse.ArgumentParser:
     )
     process_parser.add_argument(
         'input_file',
-        help='Input file containing references'
+        help='Input file, "-" for stdin, or a reference string (e.g. a DOI or title)'
     )
     process_parser.add_argument(
         '--input-type',
@@ -117,12 +120,13 @@ def process_command(args: "argparse.Namespace") -> int:
         Exit code — ``0`` on success, ``1`` on failure.
     """
     try:
-        if not os.path.exists(args.input_file):
-            print(f"Error: Input file not found: {args.input_file}", file=sys.stderr)
-            return 1
-            
-        with open(args.input_file, 'r', encoding='utf-8') as f:
-            input_content = f.read()
+        if args.input_file == '-':
+            input_content = sys.stdin.read()
+        elif os.path.exists(args.input_file):
+            with open(args.input_file, 'r', encoding='utf-8') as f:
+                input_content = f.read()
+        else:
+            input_content = args.input_file
 
         def interactive_callback(candidates: List[Dict]) -> int:
             if not args.interactive:

onecite/pipeline.py

@@ -189,19 +189,6 @@ def __init__(self, use_google_scholar: bool = False):
         self.pubmed_base = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils"
         self.datacite_base = "https://api.datacite.org"
 
-        # Well-known papers that might not have DOIs
-        self.well_known_papers = {
-            'attention is all you need': {
-                'title': 'Attention Is All You Need',
-                'authors': ['Vaswani, Ashish', 'Shazeer, Noam', 'Parmar, Niki', 'Uszkoreit, Jakob', 
-                           'Jones, Llion', 'Gomez, Aidan N', 'Kaiser, Lukasz', 'Polosukhin, Illia'],
-                'year': '2017',
-                'journal': 'Advances in Neural Information Processing Systems',
-                'arxiv_id': '1706.03762',
-                'url': 'https://arxiv.org/abs/1706.03762',
-                'type': 'conference'
-            }
-        }
 
     def identify(self, raw_entries: List[RawEntry], 
                 interactive_callback: Callable[[List[Dict]], int]) -> List[IdentifiedEntry]:
@@ -1349,21 +1336,6 @@ def _fuzzy_search(self, raw_entry: RawEntry,
         """Perform fuzzy search"""
         query_string = raw_entry['query_string']
 
-        # Check if it's a well-known paper first
-        query_lower = query_string.lower()
-        for key, paper_data in self.well_known_papers.items():
-            if key in query_lower or fuzz.ratio(key, query_lower) > 85:
-                self.logger.info(f"Entry {raw_entry['id']} matched well-known paper: {paper_data['title']}")
-                return {
-                    'id': raw_entry['id'],
-                    'raw_text': raw_entry['raw_text'],
-                    'doi': None,
-                    'arxiv_id': paper_data.get('arxiv_id'),
-                    'url': paper_data.get('url'),
-                    'metadata': paper_data,
-                    'status': 'identified'
-                }
-        
         # Multi-source query with fallback
         candidates = []
         semantic_results = []  # Initialize to avoid UnboundLocalError

tests/test_cli.py

@@ -58,9 +58,10 @@ def test_input_type_and_output_format_choices(self):
         assert "{txt,bib}" in out
         assert "{bibtex,apa,mla}" in out
 
-    def test_nonexistent_file(self):
-        code, _, _ = self._run(["process", "no_such_file.txt"])
-        assert code != 0
+    def test_nonexistent_file_treated_as_string_input(self):
+        """fix #36: non-file argument is treated as inline reference string, not an error."""
+        code, out, err = self._run(["process", "no_such_file.txt", "--quiet"])
+        assert code in (0, 1)
 
     def test_invalid_output_format(self, create_test_file, sample_references):
         path = create_test_file(sample_references["doi_only"])
@@ -92,10 +93,35 @@ def _ns(**overrides):
 
     # -- Missing / bad input --------------------------------------------------
 
-    def test_missing_input_file(self, capsys):
-        code = cli.process_command(self._ns(input_file="nope.txt"))
-        assert code == 1
-        assert "Input file not found" in capsys.readouterr().err
+    def test_string_input_passed_directly(self, capsys):
+        """fix #36: non-file argument is treated as inline reference content."""
+        captured = {}
+
+        def _fake(*, input_content, **kw):
+            captured['content'] = input_content
+            return {"results": ["OK"], "report": {"total": 1, "succeeded": 1, "failed_entries": []}}
+
+        with patch("onecite.cli.process_references", side_effect=_fake):
+            code = cli.process_command(self._ns(input_file="10.1038/nature14539", quiet=True))
+
+        assert code == 0
+        assert captured['content'] == "10.1038/nature14539"
+
+    def test_stdin_input(self, capsys, monkeypatch):
+        """fix #36: '-' reads from stdin."""
+        import io
+        monkeypatch.setattr("sys.stdin", io.StringIO("10.1038/nature14539\n"))
+        captured = {}
+
+        def _fake(*, input_content, **kw):
+            captured['content'] = input_content
+            return {"results": ["OK"], "report": {"total": 1, "succeeded": 1, "failed_entries": []}}
+
+        with patch("onecite.cli.process_references", side_effect=_fake):
+            code = cli.process_command(self._ns(input_file="-", quiet=True))
+
+        assert code == 0
+        assert "10.1038/nature14539" in captured['content']
 
     # -- quiet + output file --------------------------------------------------
 

tests/test_pipeline_unit.py

@@ -487,14 +487,24 @@ def test_timeout_returns_empty(self):
 
 class TestIdentifierFuzzySearch:
 
-    def test_well_known_paper_shortcut(self):
-        """Papers in the built-in lookup table should be resolved instantly."""
+    def test_no_hardcoded_well_known_papers(self):
+        """fix #19: IdentifierModule must not have a well_known_papers shortcut."""
+        ident = IdentifierModule()
+        assert not hasattr(ident, 'well_known_papers'), (
+            "well_known_papers shortcut should have been removed (#19)")
+
+    def test_attention_query_goes_through_normal_search(self):
+        """fix #19: 'attention is all you need' must go through normal multi-source search."""
         ident = IdentifierModule()
         entry = {"id": 1, "raw_text": "Attention is all you need",
                  "query_string": "Attention is all you need"}
-        r = ident._fuzzy_search(entry, lambda _: -1)
+        arxiv_result = {"source": "arxiv", "arxiv_id": "1706.03762",
+                        "doi": "10.48550/arXiv.1706.03762",
+                        "title": "Attention Is All You Need",
+                        "url": "https://arxiv.org/abs/1706.03762"}
+        with patch.object(ident, "_search_crossref", return_value=[arxiv_result]):
+            r = ident._fuzzy_search(entry, lambda _: -1)
         assert r["status"] == "identified"
-        assert r["arxiv_id"] == "1706.03762"
 
     def test_pmid_shortcut(self):
         ident = IdentifierModule()