mirror of
https://github.com/boostorg/website-v2.git
synced 2026-01-19 04:42:17 +00:00
cb25772a13
Instead of parsing out the HTML body from the full HTML document. All adoc parsing now goes through `convert_adoc_to_html`. I removed the `adoc_to_html` task because it was never `.delay`ed, probably because it doesn't necessarily work: it expects content to be passed in a temp file, which might not exist on the worker processing the task. The new function passes the content as a string instead of a temp file. This removes the `div#header` and `div#content` containers from the output. It's wrong to have IDs in embeddable html because multiple asciidoc outputs might be included on the same page, resulting in duplicate IDs. I couldn't find a place where these containers are necessary, though, because markdown output doesn't include them, resulting in a discrepancy in the output for markdown vs asciidoc that is now fixed. If we need to include the containers, I'd wrap the asciidoc output in the template where it is used rather than expecting it to be returned by `convert_adoc_to_html`. Fixes #1302
88 lines
2.8 KiB
Python
88 lines
2.8 KiB
Python
import structlog
|
|
|
|
from celery import shared_task
|
|
from dateutil.parser import parse
|
|
|
|
from django.core.cache import caches
|
|
|
|
from core.asciidoc import convert_adoc_to_html
|
|
from .boostrenderer import get_content_from_s3
|
|
from .models import RenderedContent
|
|
|
|
logger = structlog.get_logger()
|
|
|
|
|
|
@shared_task
|
|
def clear_rendered_content_cache_by_cache_key(cache_key):
|
|
"""Deletes a RenderedContent object by its cache key from redis and
|
|
database."""
|
|
cache = caches["static_content"]
|
|
cache.delete(cache_key)
|
|
RenderedContent.objects.delete_by_cache_key(cache_key)
|
|
|
|
|
|
@shared_task
|
|
def clear_rendered_content_cache_by_content_type(content_type):
|
|
"""Deletes all RenderedContent objects for a given content type from redis
|
|
and database."""
|
|
RenderedContent.objects.clear_cache_by_content_type(content_type)
|
|
RenderedContent.objects.delete_by_content_type(content_type)
|
|
|
|
|
|
@shared_task
|
|
def clear_static_content_cache():
|
|
"""Runs the manager method to clear the static content cache"""
|
|
RenderedContent.objects.clear_cache_by_cache_type_and_date(
|
|
cache_type="static_content_"
|
|
)
|
|
|
|
|
|
@shared_task
|
|
def refresh_content_from_s3(s3_key, cache_key):
|
|
"""Calls S3 with the s3_key, then saves the result to the
|
|
RenderedContent object with the given cache_key."""
|
|
content_dict = get_content_from_s3(key=s3_key)
|
|
|
|
content = content_dict.get("content")
|
|
if content_dict and content:
|
|
content_type = content_dict.get("content_type")
|
|
if content_type == "text/asciidoc":
|
|
content = convert_adoc_to_html(content)
|
|
last_updated_at_raw = content_dict.get("last_updated_at")
|
|
last_updated_at = parse(last_updated_at_raw) if last_updated_at_raw else None
|
|
# Clear the cache because we're going to update it.
|
|
clear_rendered_content_cache_by_cache_key(cache_key)
|
|
|
|
# Update the rendered content.
|
|
save_rendered_content(
|
|
cache_key, content_type, content, last_updated_at=last_updated_at
|
|
)
|
|
# Cache the refreshed rendered content
|
|
cache = caches["static_content"]
|
|
cache.set(cache_key, {"content": content, "content_type": content_type})
|
|
|
|
|
|
@shared_task
|
|
def save_rendered_content(cache_key, content_type, content_html, last_updated_at=None):
|
|
"""Saves a RenderedContent object to database."""
|
|
defaults = {
|
|
"content_type": content_type,
|
|
"content_html": content_html,
|
|
}
|
|
|
|
if last_updated_at:
|
|
defaults["last_updated_at"] = last_updated_at
|
|
|
|
obj, created = RenderedContent.objects.update_or_create(
|
|
cache_key=cache_key[:255], defaults=defaults
|
|
)
|
|
logger.info(
|
|
"content_saved_to_rendered_content",
|
|
cache_key=cache_key,
|
|
content_type=content_type,
|
|
status_code=200,
|
|
obj_id=obj.id,
|
|
obj_created=created,
|
|
)
|
|
return obj
|