scoap3-next: arxiv id parsing to str before extracting categories (#438)

SCOAP3 · May 30, 2023 · a655c70 · a655c70
1 parent 8c6afcc
commit a655c70
Show file tree

Hide file tree

Showing 2 changed files with 6 additions and 1 deletion.
diff --git a/scoap3/utils/arxiv.py b/scoap3/utils/arxiv.py
@@ -50,7 +50,7 @@ def clean_arxiv(arxiv):
     if arxiv is None:
         return None
 
-    return arxiv.split(':')[-1].split('v')[0].split(' ')[0].strip('"\'')
+    return str(arxiv.split(':')[-1].split('v')[0].split(' ')[0].strip('"\''))
 
 
 def get_arxiv_categories_from_response_xml(xml):

diff --git a/tests/unit/utils/test_arxiv.py b/tests/unit/utils/test_arxiv.py
@@ -95,3 +95,8 @@ def test_categories_without_arxiv_with_title_and_doi():
     categories = get_arxiv_categories(doi="10.1088/1674-1137/acac6c", title="Static properties and Semileptonic transitions of lowest-lying double heavy baryons")
     assert categories == ['hep-ph']
 
+@mark.vcr
+def test_categories_with_arxiv_type_unicode():
+    """Test extraction arXiv categories from arXiv api."""
+    categories =  get_arxiv_categories(arxiv_id=u'2111.13053', title="Axial Chiral Vortical Effect in a Sphere with finite size effect", doi="10.1088/1674-1137/acac6d")
+    assert categories == ['hep-th']