57 lines
1.7 KiB
Python
57 lines
1.7 KiB
Python
 
|
"""One-off: add split-address tokens to existing messages' FTS vector.
|
||
|
|
|
||
|
|
New messages get address parts indexed via `_doc_text_blob` (so a bare "wfdif"
|
||
|
|
finds dyrektor@wfdif.com.pl). This backfills that into already-indexed rows by
|
||
|
|
appending the split-address lexemes to `body_indexed`. Idempotent — tsvector
|
||
|
|
concat merges duplicate lexemes, so re-running is harmless.
|
||
|
|
|
||
|
|
Run: python -m scripts.reindex_address_parts
|
||
|
|
"""
|
||
|
|
|
||
|
|
from __future__ import annotations
|
||
|
|
|
||
|
|
import asyncio
|
||
|
|
|
||
|
|
from sqlalchemy import func, select, update
|
||
|
|
|
||
|
|
from app.db import get_sessionmaker
|
||
|
|
from app.models import Message
|
||
|
|
from app.search.pg import _TS_CONFIG, _email_parts
|
||
|
|
|
||
|
|
|
||
|
|
def _address_parts_blob(msg: Message) -> str:
|
||
|
|
parts: list[str] = []
|
||
|
|
for field in (msg.from_addr, msg.to_addr, msg.cc_addr):
|
||
|
|
for addr in field:
|
||
|
|
email = addr.get("email", "")
|
||
|
|
if email:
|
||
|
|
parts.append(_email_parts(email))
|
||
|
|
return " ".join(parts)
|
||
|
|
|
||
|
|
|
||
|
|
async def main() -> None:
|
||
|
|
sm = get_sessionmaker()
|
||
|
|
updated = 0
|
||
|
|
async with sm() as session:
|
||
|
|
msgs = list(await session.scalars(select(Message).where(Message.body_indexed.is_not(None))))
|
||
|
|
for msg in msgs:
|
||
|
|
blob = _address_parts_blob(msg)
|
||
|
|
if not blob:
|
||
|
|
continue
|
||
|
|
await session.execute(
|
||
|
|
update(Message)
|
||
|
|
.where(Message.id == msg.id)
|
||
|
|
.values(
|
||
|
|
body_indexed=Message.body_indexed.op("||")(
|
||
|
|
func.to_tsvector(_TS_CONFIG, blob)
|
||
|
|
)
|
||
|
|
)
|
||
|
|
)
|
||
|
|
updated += 1
|
||
|
|
await session.commit()
|
||
|
|
print(f"reindexed address parts into {updated} messages")
|
||
|
|
|
||
|
|
|
||
|
|
if __name__ == "__main__":
|
||
|
|
asyncio.run(main())
|