fix issue with articles with no author or year (#40)

* Skip articles that don't have authors or year

* Prepare release

Author: odarbelaeze

src/bibx/__init__.py

@@ -27,7 +27,7 @@
     "read_wos",
 ]
 
-__version__ = "0.6.0"
+__version__ = "0.6.1"
 
 
 def query_openalex(

src/bibx/article.py

@@ -87,10 +87,10 @@ def permalink(self) -> Optional[str]:
     @property
     def simple_id(self) -> Optional[str]:
         """Return a simple ID for the article."""
-        if self.authors and self.year is not None:
-            author = self.authors[0].split(" ")[0].replace(",", "")
-            return f"{author}{self.year}".lower()
-        return None
+        if not self.authors or self.year is None:
+            return None
+        author = self.authors[0].split(" ")[0].replace(",", "")
+        return f"{author}{self.year}".lower()
 
     def __repr__(self) -> str:
         """Return a string representation of the article."""

src/bibx/builders/scopus_csv.py

@@ -99,6 +99,12 @@ def _parse_file(self, file: TextIO) -> Generator[Article]:
         reader = csv.DictReader(file)
         for row in reader:
             datum = Row.model_validate(row)
+            if not datum.authors or not datum.year:
+                logger.info(
+                    "skipping row with missing authors or year: %s",
+                    datum.model_dump_json(indent=2),
+                )
+                continue
             yield (
                 Article(
                     label="",
@@ -131,6 +137,9 @@ def _parse_file(self, file: TextIO) -> Generator[Article]:
     def _article_from_reference(self, reference: str) -> Optional[Article]:
         try:
             *authors, journal, issue, year = reference.split(", ")
+            if not authors:
+                message = "a minimum of one author is required"
+                raise ValueError(message)
             _year = int(year.lstrip("(").rstrip(")"))
             return Article(
                 label=reference,