HTML column on comments for storing tiptap editor data

src/researchhub_comment/constants/rh_comment_content_types.py

@@ -1,9 +1,11 @@
 CK_EDITOR = "CK_EDITOR"
 QUILL_EDITOR = "QUILL_EDITOR"
 TEXT = "TEXT"
+HTML = "HTML"
 
 RH_COMMENT_CONTENT_TYPES = (
     (CK_EDITOR, CK_EDITOR),
     (QUILL_EDITOR, QUILL_EDITOR),
     (TEXT, TEXT),
+    (HTML, HTML),
 )

src/researchhub_comment/migrations/0009_alter_rhcommentthreadmodel_thread_type.py

@@ -19,7 +19,12 @@ class Migration(migrations.Migration):
                     ("INNER_CONTENT_COMMENT", "INNER_CONTENT_COMMENT"),
                 ],
                 default="GENERIC_COMMENT",
-                max_length=144,
+                max_length=255,
             ),
         ),
+        migrations.AddField(
+            model_name="rhcommentmodel",
+            name="html",
+            field=models.TextField(blank=True, null=True),
+        ),
     ]

src/researchhub_comment/migrations/0020_alter_rhcommentmodel_html.py

@@ -0,0 +1,22 @@
+# Generated by Django 5.1.4 on 2025-02-02 20:05
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("researchhub_comment", "0019_alter_rhcommentmodel_comment_type_and_more"),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="rhcommentmodel",
+            name="html",
+            field=models.TextField(
+                blank=True,
+                help_text="HTML representation of the comment content",
+                null=True,
+            ),
+        ),
+    ]

src/researchhub_comment/related_models/rh_comment_model.py

@@ -14,6 +14,7 @@
 from discussion.reaction_models import AbstractGenericReactionModel
 from purchase.models import Purchase
 from researchhub_comment.constants.rh_comment_content_types import (
+    HTML,
     QUILL_EDITOR,
     RH_COMMENT_CONTENT_TYPES,
 )
@@ -57,6 +58,11 @@ class RhCommentModel(
         default=QUILL_EDITOR,
         max_length=144,
     )
+    html = TextField(
+        blank=True,
+        null=True,
+        help_text="HTML representation of the comment content",
+    )
     is_accepted_answer = BooleanField(null=True)
     parent = ForeignKey(
         "self",
@@ -167,9 +173,11 @@ def get_total_children_count(self):
         return total_count
 
     def update_comment_content(self):
-        celery_create_comment_content_src.apply_async(
-            (self.id, self.comment_content_json), countdown=2
-        )
+        # Only create content source for QUILL format
+        if self.comment_content_type != HTML:
+            celery_create_comment_content_src.apply_async(
+                (self.id, self.comment_content_json), countdown=2
+            )
 
     def _update_related_discussion_count(self, amount):
         from citation.models import CitationEntry
@@ -207,11 +215,25 @@ def decrement_discussion_count(self):
     def create_from_data(cls, data):
         from researchhub_comment.serializers import RhCommentSerializer
 
+        content_format = data.get("content_format", QUILL_EDITOR)
+
+        if content_format == QUILL_EDITOR:
+            # For QUILL format, content is already in comment_content_json
+            data["html"] = None
+        else:
+            # For HTML format, use comment_content directly
+            data["html"] = data.get("comment_content")
+            data["comment_content_json"] = None
+
         rh_comment_serializer = RhCommentSerializer(data=data)
         rh_comment_serializer.is_valid(raise_exception=True)
         rh_comment = rh_comment_serializer.save()
-        celery_create_comment_content_src.apply_async(
-            (rh_comment.id, data.get("comment_content_json")), countdown=2
-        )
+
+        if content_format == QUILL_EDITOR:
+            # Only create content source for QUILL format
+            celery_create_comment_content_src.apply_async(
+                (rh_comment.id, rh_comment.comment_content_json), countdown=2
+            )
+
         rh_comment.increment_discussion_count()
         return rh_comment, rh_comment_serializer.data

src/researchhub_comment/serializers/constants/rh_comment_serializer_contants.py

@@ -6,6 +6,7 @@
     "context_title",
     "created_date",
     "created_by",
+    "html",
     "updated_by",
     "id",
     "is_accepted_answer",

src/researchhub_comment/tests/test_comments.py

@@ -199,6 +199,37 @@ def test_filter_by_bounties(self):
         self.assertEqual(regular_res.status_code, 200)
         self.assertEqual(regular_res.data["count"], 4)
 
+    def test_html_content_format(self):
+        """Test that HTML format comments store content in html field and not in comment_content_json"""
+        html_content = "<p>This is a test HTML comment</p>"
+        res = self._create_paper_comment(
+            self.paper.id,
+            self.user_1,
+            content_format="HTML",
+            comment_content=html_content,
+        )
+
+        self.assertEqual(res.status_code, 200)
+        comment_data = res.data
+
+        # Verify html field is set and comment_content_json is null
+        self.assertEqual(comment_data["html"], html_content)
+        self.assertIsNone(comment_data["comment_content_json"])
+
+    def test_quill_content_format(self):
+        """Test that QUILL_EDITOR format comments store content in comment_content_json field and not in html"""
+        quill_content = {"ops": [{"insert": "This is a test Quill comment"}]}
+        res = self._create_paper_comment(
+            self.paper.id, self.user_1, comment_content_json=quill_content
+        )
+
+        self.assertEqual(res.status_code, 200)
+        comment_data = res.data
+
+        # Verify comment_content_json is set and html is null
+        self.assertEqual(comment_data["comment_content_json"], quill_content)
+        self.assertIsNone(comment_data["html"])
+
     def test_comment_mentions(self):
         creator = self.user_1
         recipient = self.user_2