mirror of
https://github.com/ArchiveBox/ArchiveBox
synced 2024-11-14 16:37:17 +00:00
14df0cbb7c
Sonic buffer accepts 20.000 bytes not unicode characters, since the chunking here is on unicode characters, sending 20.000 characters will overflow sonic's buffer. UTF-8 can take up to 6 bytes, so sending less than (20.000 / 6) rounded minus should be ok.
28 lines
1.2 KiB
Python
28 lines
1.2 KiB
Python
from typing import List, Generator
|
|
|
|
from sonic import IngestClient, SearchClient
|
|
|
|
from archivebox.util import enforce_types
|
|
from archivebox.config import SEARCH_BACKEND_HOST_NAME, SEARCH_BACKEND_PORT, SEARCH_BACKEND_PASSWORD, SONIC_BUCKET, SONIC_COLLECTION
|
|
|
|
MAX_SONIC_TEXT_LENGTH = 2000
|
|
|
|
@enforce_types
|
|
def index(snapshot_id: str, texts: List[str]):
|
|
with IngestClient(SEARCH_BACKEND_HOST_NAME, SEARCH_BACKEND_PORT, SEARCH_BACKEND_PASSWORD) as ingestcl:
|
|
for text in texts:
|
|
chunks = [text[i:i+MAX_SONIC_TEXT_LENGTH] for i in range(0, len(text), MAX_SONIC_TEXT_LENGTH)]
|
|
for chunk in chunks:
|
|
ingestcl.push(SONIC_COLLECTION, SONIC_BUCKET, snapshot_id, str(chunk))
|
|
|
|
@enforce_types
|
|
def search(text: str) -> List[str]:
|
|
with SearchClient(SEARCH_BACKEND_HOST_NAME, SEARCH_BACKEND_PORT, SEARCH_BACKEND_PASSWORD) as querycl:
|
|
snap_ids = querycl.query(SONIC_COLLECTION, SONIC_BUCKET, text)
|
|
return snap_ids
|
|
|
|
@enforce_types
|
|
def flush(snapshot_ids: Generator[str, None, None]):
|
|
with IngestClient(SEARCH_BACKEND_HOST_NAME, SEARCH_BACKEND_PORT, SEARCH_BACKEND_PASSWORD) as ingestcl:
|
|
for id in snapshot_ids:
|
|
ingestcl.flush_object(SONIC_COLLECTION, SONIC_BUCKET, str(id))
|