Skip to content

Delving Bitcoin - Add metadata tracking and post sync optimization #98

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
urvishp80 wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Delving Bitcoin - Add metadata tracking and post sync optimization #98

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 5 additions & 3 deletions .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,10 @@
.idea/
delvingbitcoin_2_elasticsearch\archive
delvingbitcoin_2_elasticsearch/archive/posts
delvingbitcoin_2_elasticsearch/archive/rendered-topics
venv/
archive

archive/posts
archive/rendered-topics

.venv

Expand Down Expand Up @@ -96,7 +99,6 @@ web_modules/
.yarn-integrity

# dotenv environment variable files
.env
.env.development.local
.env.test.local
.env.production.local
Expand Down
2 changes: 1 addition & 1 deletion delvingbitcoin_2_elasticsearch/achieve.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -165,7 +165,7 @@ def download_dumps() -> None:
# Resync over the last day to catch any post edits.
last_sync_date -= datetime.timedelta(days=1)

log.info("detected latest synced post date:{last_sync_date}")
log.info(f"detected latest synced post date: {last_sync_date}")

topics_to_get = {}
max_created_at = None
Expand Down
3 changes: 3 additions & 0 deletions delvingbitcoin_2_elasticsearch/archive/.metadata.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,3 @@
{
"last_sync_date": "2025-01-24T00:42:29.140000+00:00"
Copy link
Member

@kouloumos kouloumos Jan 25, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

where is this getting updated?

}
18 changes: 11 additions & 7 deletions delvingbitcoin_2_elasticsearch/delvingbitcoin_2_elasticsearch.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@

sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))

from common.elasticsearch_utils import document_add, document_view, create_index
from common.elasticsearch_utils import document_add, document_view, create_index, document_update

from achieve import download_dumps

Expand Down Expand Up @@ -86,10 +86,11 @@ def index_documents(files_path):
'body_type': 'html',
'body': body,
'body_formatted': strip_attributes_but_urls(document['cooked']),
'created_at': document['updated_at'],
'created_at': document['created_at'],
'domain': "https://delvingbitcoin.org/",
'url': f"https://delvingbitcoin.org/t/{document['topic_slug']}/{document['topic_id']}",
"indexed_at": datetime.utcnow().isoformat()
"indexed_at": datetime.utcnow().isoformat(),
"updated_at": document['updated_at']
}

if document['post_number'] != 1:
Expand All @@ -98,13 +99,16 @@ def index_documents(files_path):
else:
doc['type'] = 'original_post'

# Check if a document already exists
# check if document exist and update it if any changes are found
resp = document_view(index_name=INDEX, doc_id=doc['id'])
if not resp:
if resp and doc['updated_at'] != resp['_source']['updated_at']:
_ = document_update(index_name=INDEX, doc=doc, doc_id=doc['id'])
log.success(f'Updated doc with ID: {doc["id"]}, Type:{doc["type"]}')
elif not resp:
_ = document_add(index_name=INDEX, doc=doc, doc_id=doc['id'])
log.success(f'Successfully added! ID: {doc["id"]}, Type:{doc["type"]}')
log.success(f'Added doc with ID: {doc["id"]}, Type:{doc["type"]}')
else:
log.info(f"Document already exist! ID: {doc['id']}")
log.info(f"No changes - ID: {doc['id']}")


if __name__ == "__main__":
Expand Down