✨(backend) add dummy content to demo documents

We need to content in our demo documents so that we can test
indexing.

Author: sampaccoud

src/backend/core/models.py

@@ -439,32 +439,35 @@ def __init__(self, *args, **kwargs):
     def save(self, *args, **kwargs):
         """Write content to object storage only if _content has changed."""
         super().save(*args, **kwargs)
-
         if self._content:
-            file_key = self.file_key
-            bytes_content = self._content.encode("utf-8")
+            self.save_content(self._content)
 
-            # Attempt to directly check if the object exists using the storage client.
-            try:
-                response = default_storage.connection.meta.client.head_object(
-                    Bucket=default_storage.bucket_name, Key=file_key
-                )
-            except ClientError as excpt:
-                # If the error is a 404, the object doesn't exist, so we should create it.
-                if excpt.response["Error"]["Code"] == "404":
-                    has_changed = True
-                else:
-                    raise
+    def save_content(self, content):
+        """Save content to object storage."""
+
+        file_key = self.file_key
+        bytes_content = content.encode("utf-8")
+
+        # Attempt to directly check if the object exists using the storage client.
+        try:
+            response = default_storage.connection.meta.client.head_object(
+                Bucket=default_storage.bucket_name, Key=file_key
+            )
+        except ClientError as excpt:
+            # If the error is a 404, the object doesn't exist, so we should create it.
+            if excpt.response["Error"]["Code"] == "404":
+                has_changed = True
             else:
-                # Compare the existing ETag with the MD5 hash of the new content.
-                has_changed = (
-                    response["ETag"].strip('"')
-                    != hashlib.md5(bytes_content).hexdigest()  # noqa: S324
-                )
+                raise
+        else:
+            # Compare the existing ETag with the MD5 hash of the new content.
+            has_changed = (
+                response["ETag"].strip('"') != hashlib.md5(bytes_content).hexdigest()  # noqa: S324
+            )
 
-            if has_changed:
-                content_file = ContentFile(bytes_content)
-                default_storage.save(file_key, content_file)
+        if has_changed:
+            content_file = ContentFile(bytes_content)
+            default_storage.save(file_key, content_file)
 
     def is_leaf(self):
         """

src/backend/demo/management/commands/create_demo.py

@@ -1,16 +1,19 @@
 # ruff: noqa: S311, S106
 """create_demo management command"""
 
+import base64
 import logging
 import math
 import random
 import time
 from collections import defaultdict
+from uuid import uuid4
 
 from django import db
 from django.conf import settings
 from django.core.management.base import BaseCommand, CommandError
 
+import pycrdt
 from faker import Faker
 
 from core import models
@@ -27,6 +30,16 @@ def random_true_with_probability(probability):
     return random.random() < probability
 
 
+def get_ydoc_for_text(text):
+    """Return a ydoc from plain text for demo purposes."""
+    ydoc = pycrdt.Doc()
+    paragraph = pycrdt.XmlElement("p", {}, [pycrdt.XmlText(text)])
+    fragment = pycrdt.XmlFragment([paragraph])
+    ydoc["document-store"] = fragment
+    update = ydoc.get_update()
+    return base64.b64encode(update).decode("utf-8")
+
+
 class BulkQueue:
     """A utility class to create Django model instances in bulk by just pushing to a queue."""
 
@@ -48,7 +61,7 @@ def _bulk_create(self, objects):
         self.queue[objects[0]._meta.model.__name__] = []  # noqa: SLF001
 
     def push(self, obj):
-        """Add a model instance to queue to that it gets created in bulk."""
+        """Add a model instance to queue so that it gets created in bulk."""
         objects = self.queue[obj._meta.model.__name__]  # noqa: SLF001
         objects.append(obj)
         if len(objects) > self.BATCH_SIZE:
@@ -139,17 +152,19 @@ def create_demo(stdout):
             # pylint: disable=protected-access
             key = models.Document._int2str(i)  # noqa: SLF001
             padding = models.Document.alphabet[0] * (models.Document.steplen - len(key))
-            queue.push(
-                models.Document(
-                    depth=1,
-                    path=f"{padding}{key}",
-                    creator_id=random.choice(users_ids),
-                    title=fake.sentence(nb_words=4),
-                    link_reach=models.LinkReachChoices.AUTHENTICATED
-                    if random_true_with_probability(0.5)
-                    else random.choice(models.LinkReachChoices.values),
-                )
+            title = fake.sentence(nb_words=4)
+            document = models.Document(
+                id=uuid4(),
+                depth=1,
+                path=f"{padding}{key}",
+                creator_id=random.choice(users_ids),
+                title=title,
+                link_reach=models.LinkReachChoices.AUTHENTICATED
+                if random_true_with_probability(0.5)
+                else random.choice(models.LinkReachChoices.values),
             )
+            document.save_content(get_ydoc_for_text(f"Content for {title:s}"))
+            queue.push(document)
 
         queue.flush()