feat: update search index when course content is updated (TEMP)

openedx/core/djangoapps/content/search/documents.py

@@ -6,7 +6,7 @@
 import logging
 
 from django.utils.text import slugify
-from opaque_keys.edx.keys import UsageKey, LearningContextKey
+from opaque_keys.edx.keys import LearningContextKey, UsageKey
 
 from openedx.core.djangoapps.content_libraries import api as lib_api
 from openedx.core.djangoapps.content_tagging import api as tagging_api
@@ -62,7 +62,7 @@ class DocType:
     library_block = "library_block"
 
 
-def _meili_id_from_opaque_key(usage_key: UsageKey) -> str:
+def meili_id_from_opaque_key(usage_key: UsageKey) -> str:
     """
     Meilisearch requires each document to have a primary key that's either an
     integer or a string composed of alphanumeric characters (a-z A-Z 0-9),
@@ -88,7 +88,6 @@ class implementation returns only:
         {"content": {"display_name": "..."}, "content_type": "..."}
     """
     block_data = {
-        Fields.id: _meili_id_from_opaque_key(block.usage_key),
         Fields.usage_key: str(block.usage_key),
         Fields.block_id: str(block.usage_key.block_id),
         Fields.display_name: xblock_api.get_block_display_name(block),
@@ -196,33 +195,58 @@ def _tags_for_content_object(object_id: UsageKey | LearningContextKey) -> dict:
     return {Fields.tags: result}
 
 
-def searchable_doc_for_library_block(metadata: lib_api.LibraryXBlockMetadata) -> dict:
+def searchable_doc_for_library_block(
+    xblock_metadata: lib_api.LibraryXBlockMetadata, include_metadata: bool = True, include_tags: bool = True
+) -> dict:
     """
     Generate a dictionary document suitable for ingestion into a search engine
     like Meilisearch or Elasticsearch, so that the given library block can be
     found using faceted search.
+
+    Args:
+        xblock_metadata: The XBlock component metadata to index
+        include_metadata: If True, include the block's metadata in the doc
+        include_tags: If True, include the block's tags in the doc
     """
-    library_name = lib_api.get_library(metadata.usage_key.context_key).title
-    doc = {}
-    try:
-        block = xblock_api.load_block(metadata.usage_key, user=None)
-    except Exception as err:  # pylint: disable=broad-except
-        log.exception(f"Failed to load XBlock {metadata.usage_key}: {err}")
-    doc.update(_fields_from_block(block))
-    doc.update(_tags_for_content_object(metadata.usage_key))
-    doc[Fields.type] = DocType.library_block
-    # Add the breadcrumbs. In v2 libraries, the library itself is not a "parent" of the XBlocks so we add it here:
-    doc[Fields.breadcrumbs] = [{"display_name": library_name}]
+    library_name = lib_api.get_library(xblock_metadata.usage_key.context_key).title
+    block = xblock_api.load_block(xblock_metadata.usage_key, user=None)
+
+    doc = {
+        Fields.id: meili_id_from_opaque_key(xblock_metadata.usage_key),
+        Fields.type: DocType.library_block,
+    }
+
+    if include_metadata:
+        doc.update(_fields_from_block(block))
+        # Add the breadcrumbs. In v2 libraries, the library itself is not a "parent" of the XBlocks so we add it here:
+        doc[Fields.breadcrumbs] = [{"display_name": library_name}]
+
+    if include_tags:
+        doc.update(_tags_for_content_object(xblock_metadata.usage_key))
+
     return doc
 
 
-def searchable_doc_for_course_block(block) -> dict:
+def searchable_doc_for_course_block(block, include_metadata: bool = True, include_tags: bool = True) -> dict:
     """
     Generate a dictionary document suitable for ingestion into a search engine
     like Meilisearch or Elasticsearch, so that the given course block can be
     found using faceted search.
+
+    Args:
+        block: The XBlock instance to index
+        include_metadata: If True, include the block's metadata in the doc
+        include_tags: If True, include the block's tags in the doc
     """
-    doc = _fields_from_block(block)
-    doc.update(_tags_for_content_object(block.usage_key))
-    doc[Fields.type] = DocType.course_block
+    doc = {
+        Fields.id: meili_id_from_opaque_key(block.usage_key),
+        Fields.type: DocType.course_block,
+    }
+
+    if include_metadata:
+        doc.update(_fields_from_block(block))
+
+    if include_tags:
+        doc.update(_tags_for_content_object(block.usage_key))
+
     return doc

openedx/core/djangoapps/content/search/handlers.py

@@ -0,0 +1,106 @@
+"""
+Handlers for content indexing
+"""
+
+import logging
+
+from django.dispatch import receiver
+from openedx_events.content_authoring.data import LibraryBlockData, XBlockData
+from openedx_events.content_authoring.signals import (
+    LIBRARY_BLOCK_CREATED,
+    LIBRARY_BLOCK_DELETED,
+    LIBRARY_BLOCK_UPDATED,
+    XBLOCK_CREATED,
+    XBLOCK_DELETED,
+    XBLOCK_UPDATED
+)
+
+from .api import only_if_meilisearch_enabled
+from .tasks import (
+    delete_library_block_index_doc,
+    delete_xblock_index_doc,
+    upsert_library_block_index_doc,
+    upsert_xblock_index_doc
+)
+
+log = logging.getLogger(__name__)
+
+
+@receiver(XBLOCK_CREATED)
+@only_if_meilisearch_enabled
+def xblock_created_handler(**kwargs) -> None:
+    """
+    Create the index for the XBlock
+    """
+    xblock_info = kwargs.get("xblock_info", None)
+    if not xblock_info or not isinstance(xblock_info, XBlockData):  # pragma: no cover
+        log.error("Received null or incorrect data for event")
+        return
+
+    upsert_xblock_index_doc.delay(
+        str(xblock_info.usage_key),
+        recursive=False,
+        update_metadata=True,
+        update_tags=False,
+    )
+
+
+@receiver(XBLOCK_UPDATED)
+@only_if_meilisearch_enabled
+def xblock_updated_handler(**kwargs) -> None:
+    """
+    Update the index for the XBlock and its children
+    """
+    xblock_info = kwargs.get("xblock_info", None)
+    if not xblock_info or not isinstance(xblock_info, XBlockData):  # pragma: no cover
+        log.error("Received null or incorrect data for event")
+        return
+
+    upsert_xblock_index_doc.delay(
+        str(xblock_info.usage_key),
+        recursive=True,  # Update all children because the breadcrumb may have changed
+        update_metadata=True,
+        update_tags=False,
+    )
+
+
+@receiver(XBLOCK_DELETED)
+@only_if_meilisearch_enabled
+def xblock_deleted_handler(**kwargs) -> None:
+    """
+    Delete the index for the XBlock
+    """
+    xblock_info = kwargs.get("xblock_info", None)
+    if not xblock_info or not isinstance(xblock_info, XBlockData):  # pragma: no cover
+        log.error("Received null or incorrect data for event")
+        return
+
+    delete_xblock_index_doc.delay(str(xblock_info.usage_key))
+
+
+@receiver(LIBRARY_BLOCK_CREATED)
+@only_if_meilisearch_enabled
+def content_library_updated_handler(**kwargs) -> None:
+    """
+    Create or update the index for the content library block
+    """
+    library_block_data = kwargs.get("library_block", None)
+    if not library_block_data or not isinstance(library_block_data, LibraryBlockData):  # pragma: no cover
+        log.error("Received null or incorrect data for event")
+        return
+
+    upsert_library_block_index_doc.delay(str(library_block_data.usage_key), update_metadata=True, update_tags=False)
+
+
+@receiver(LIBRARY_BLOCK_DELETED)
+@only_if_meilisearch_enabled
+def content_library_deleted_handler(**kwargs) -> None:
+    """
+    Delete the index for the content library block
+    """
+    library_block_data = kwargs.get("library_block", None)
+    if not library_block_data or not isinstance(library_block_data, LibraryBlockData):  # pragma: no cover
+        log.error("Received null or incorrect data for event")
+        return
+
+    delete_library_block_index_doc.delay(str(library_block_data.usage_key))