fix issue with articles without ids

pyproject.toml

@@ -13,7 +13,7 @@ dependencies = [
     "networkx~=3.0",
     "pydantic~=2.10.6",
     "requests~=2.32.3",
-    "typer[all]~=0.9.0",
+    "typer[all]~=0.16.0",
 ]
 requires-python = ">=3.9"
 classifiers = [
@@ -44,7 +44,7 @@ dev = [
 ]
 
 [project.scripts]
-bibx = "bibx.cli:app"
+bibx = "bibx.cli:main"
 
 [tool.ruff.lint]
 select = [

src/bibx/__init__.py

@@ -28,7 +28,7 @@
     "read_wos",
 ]
 
-__version__ = "0.6.3"
+__version__ = "0.7.0"
 
 
 def query_openalex(

src/bibx/builders/wos.py

@@ -261,7 +261,7 @@ def __init__(self, *isi_files: TextIO) -> None:
     def build(self) -> Collection:
         """Build a collection of articles from Web of Science (WoS) ISI files."""
         articles = self._get_articles_from_files()
-        return Collection(list(articles))
+        return Collection(Collection.deduplicate_articles(list(articles)))
 
     def _get_articles_as_str_from_files(self) -> Iterable[str]:
         for file in self._files:

src/bibx/cli.py

@@ -21,7 +21,7 @@
 
 
 @app.callback()
-def main(
+def set_verbose(
     verbose: Annotated[  # noqa: FBT002
         bool, typer.Option("--verbose", "-v", help="Enable verbose logging.")
     ] = False,
@@ -99,14 +99,8 @@ def openalex(
         help="how to handle references",
         default=EnrichReferences.BASIC,
     ),
-    verbose: bool = typer.Option(
-        help="be more verbose",
-        default=False,
-    ),
 ) -> None:
     """Run the sap algorithm on a seed file of any supported format."""
-    if verbose:
-        logging.basicConfig(level=logging.INFO)
     c = query_openalex(" ".join(query), enrich=enrich)
     s = Sap()
     graph = s.create_graph(c)
@@ -115,5 +109,10 @@ def openalex(
     rprint(graph)
 
 
+def main() -> None:
+    """Entry point for the CLI."""
+    app()
+
+
 if __name__ == "__main__":
     app()

src/bibx/collection.py

@@ -46,6 +46,8 @@ def _uniqe_articles_by_id(cls, articles: list[Article]) -> dict[str, Article]:
         graph = nx.Graph()
         id_to_article: defaultdict[str, list[Article]] = defaultdict(list)
         for article in cls._all_articles(articles):
+            if not article.ids:
+                continue
             first, *rest = article.ids
             # Add a loop edge so that the unique articles are included
             graph.add_edge(first, first)