importer: Update tests for normalized title matching

CERNDocumentServer · Jan 23, 2024 · 1608e0f · 1608e0f
1 parent 0de5125
commit 1608e0f
Show file tree

Hide file tree

Showing 3 changed files with 17 additions and 4 deletions.
diff --git a/cds_ils/importer/documents/api.py b/cds_ils/importer/documents/api.py
@@ -40,7 +40,9 @@ def search_document_by_title_authors(title, authors, subtitle=None):
     """Find document by title and authors."""
     document_search = current_app_ils.document_search_cls()
 
-    title = " ".join(title.lower().split()) # Normalized title search for documents
+    title = " ".join(
+        title.lower().split()
+    ).strip()  # Normalized title search for documents
     if subtitle:
         search = (
             document_search.filter("term", title__normalized_keyword=title)

diff --git a/cds_ils/importer/documents/importer.py b/cds_ils/importer/documents/importer.py
@@ -199,6 +199,12 @@ def _update_field_alternative_identifiers(self, matched_document):
 
         return existing_identifiers + new_identifiers
 
+    @staticmethod
+    def _normalize_title(title):
+        """Return a normalized title."""
+        t = " ".join(title.lower().split())
+        return t.strip()
+
     def update_document(self, matched_document):
         """Update document record."""
         for field in self.update_document_fields:
@@ -263,11 +269,13 @@ def _validate_volumes(self, existing_document):
 
         for import_serial in import_doc_serials:
             import_volume = import_serial.get("volume")
-            import_serial_title = import_serial["title"].lower()
+            import_serial_title = self._normalize_title(import_serial["title"])
 
             for serial in existing_doc_serials:
                 existing_volume = serial.get("volume")
-                existing_title = serial["record_metadata"]["title"].lower()
+                existing_title = self._normalize_title(
+                    serial["record_metadata"]["title"]
+                )
 
                 same_serial = existing_title == import_serial_title
                 both_have_volumes = import_volume and existing_volume
@@ -322,7 +330,9 @@ def validate_found_matches(self, not_validated_matches):
                 )
 
                 pub_year_not_equal = doc_pub_year != import_doc_publication_year
-                titles_not_equal = document_title.lower() != import_doc_title.lower()
+                titles_not_equal = self._normalize_title(
+                    document_title
+                ) != self._normalize_title(import_doc_title)
 
                 provider_identifiers_not_equal = (
                     not self._validate_provider_identifiers(document)

diff --git a/tests/importer/test_document_matching.py b/tests/importer/test_document_matching.py
@@ -78,6 +78,7 @@ def test_document_search_matching(importer_test_data):
     validated_matches, partial = document_importer.validate_found_matches(matches)
 
     assert validated_matches == "docid-4"
+    assert partial == ["docid-41"]
 
 
 def test_fuzzy_matching(importer_test_data):