SYS-1574 and SYS-1575: Updated TEI and image OAI feed to match public…

… site display assumptions (#117)

* Fixes for PR, function naming and additional test
* Added release notes and tag
* Remove unused import and wrap long comments

charts/prod-ohstaff-values.yaml

@@ -6,7 +6,7 @@ replicaCount: 1
 
 image:
   repository: uclalibrary/oral-history-staff-ui
-  tag: v1.0.11
+  tag: v1.0.12
   pullPolicy: Always
 
 nameOverride: ""

oh_staff_ui/classes/OralHistoryMods.py

@@ -41,7 +41,7 @@ def populate_fields(self):
         self._populate_rights()
         self._populate_subjects()
         self._populate_constituent_audio()
-        self._populate_narrator_image()
+        self._populate_interviewee_image()
         self._populate_interview_content()
         self._populate_series_content()
 
@@ -177,21 +177,21 @@ def _create_relateditem_audio(self, mi: MediaFile) -> MODSv34:
             ri.toc = TableOfContents(text=toc.value)
 
         for ts in MediaFile.objects.filter(
-            item=pi, file_type__file_code="text_master_index"
+            item=pi, file_type__file_code="text_master_transcript"
         ):
-            if ts.file_url != "":
-                ri.locations.append(
-                    LocationOH(url=ts.file_url, usage="primary display")
-                )
+            if ts.file_url != "" and ts.file_url.endswith(".xml"):
+                # Due to legacy design the text_master_transcript can have 2 file types
+                # associated with it, we only want to show xml (TEI), and ignore html files
+                ri.locations.append(LocationOH(url=ts.file_url, usage="timed log"))
 
         return ri
 
-    def _populate_narrator_image(self):
+    def _populate_interviewee_image(self):
         for img in MediaFile.objects.filter(
             item=self._item, file_type__file_code="image_submaster"
         ).order_by("sequence"):
             self.locations.append(
-                LocationOH(url=img.file_url, label="Image of Narrator")
+                LocationOH(url=img.file_url, label="Image of Interviewee")
             )
 
     def _populate_interview_content(self):

oh_staff_ui/templates/oh_staff_ui/release_notes.html

@@ -4,6 +4,13 @@
 <h3>Release Notes</h3>
 <hr/>
 
+<h4>1.0.12</h4>
+<p><i>April 26, 2024</i></p>
+<ul>
+    <li>Display value associated with images changed from Narrator to Interviewee in OAI feed</li>
+    <li>TEI documents are now presented as mods:location/mods:url[@="timed_log"] inside mods:relatedItem</li>
+</ul>
+
 <h4>1.0.11</h4>
 <p><i>April 26, 2024</i></p>
 <ul>

oh_staff_ui/tests.py

@@ -1150,6 +1150,12 @@ def setUpTestData(cls):
             file="oh_static/text/submasters/fake-abcdef-2-master-tei.xml",
         )
 
+    # Utility methods to pretty print xml
+    def prettify_xml(self, xml: str) -> str:
+        root = etree.fromstring(xml.serializeDocument())
+        pretty_xml = etree.tostring(root, pretty_print=True, encoding="unicode")
+        return pretty_xml
+
     # Utility methods to return MODS specific to item type
     def get_mods_from_audio_item(self):
         return self.get_mods_from_item_type(type="audio")
@@ -1322,7 +1328,7 @@ def test_valid_timing_log(self):
     def test_valid_mods_image(self):
         ohmods = self.get_mods_from_interview_item()
         self.assertTrue(
-            b'<mods:location displayLabel="Image of Narrator">'
+            b'<mods:location displayLabel="Image of Interviewee">'
             in ohmods.serializeDocument()
         )
 
@@ -1356,7 +1362,8 @@ def test_series_relateditem_on_items(self):
         )
 
     def test_timed_log_attribute_is_added(self):
-        # If an item contains a TEI/XML transcript, it should have a usage attribute with value "timed_log"
+        # If an item contains a TEI/XML transcript, it should have a usage attribute
+        # with value "timed_log"
         if MediaFile(
             item=self.audio_item,
             file_type=MediaFileType.objects.get(file_code="text_master_transcript"),
@@ -1366,6 +1373,35 @@ def test_timed_log_attribute_is_added(self):
                 b'<mods:url usage="timed log">' in ohmods.serializeDocument()
             )
 
+    def test_absence_of_timed_log_with_text_master_index(self):
+        # If an item does not contain a file_code of text_master_transcript,
+        # mods:url[@usage="timed log"] should not be present.
+
+        # Delete MediaFile associated with "text_master_transcript" file_code
+        media_file = MediaFile.objects.get(
+            item__id=self.audio_item.id, file_type__file_code="text_master_transcript"
+        )
+        media_file.delete()
+
+        ohmods = self.get_mods_from_audio_item()
+
+        # At this point we should only have "text_master_index" file_code MediaFile
+        if MediaFile.objects.get(
+            item__id=self.audio_item.id, file_type__file_code="text_master_index"
+        ):
+            self.assertFalse(
+                b'<mods:url usage="timed log">' in ohmods.serializeDocument()
+            )
+
+        # Add "text_master_transcript" back in case future tests rely on it
+        MediaFile.objects.create(
+            created_by=self.user,
+            file_type=MediaFileType.objects.get(file_code="text_master_transcript"),
+            item=self.audio_item,
+            original_file_name="FAKE_TEI_TIMED_LOG",
+            file="oh_static/text/submasters/fake-abcdef-2-master-tei.xml",
+        )
+
     def test_writing_single_mods(self):
         ohmods = self.get_mods_from_interview_item()
         ohmods.write_mods_record()