mirror of
https://github.com/lrnselfreliance/wrolpi.git
synced 2026-10-26 10:51:36 -04:00
73fafcd645
The file_group.textsearch tsvector indexes all four text columns;
d_text (captions, document text, zip contents) is ~90% of the data,
making ts_rank searches take seconds on large libraries. Add a
textsearch_abc generated column (title/author/description only, ~8x
smaller) and default all searches to it, with deep=true opting into the
full column.
Database:
- Migration adds the generated column and a GIN index (rewrites the
table; a few minutes on large libraries).
Backend:
- FilesSearchRequest, VideoSearchRequest, ArchiveSearchRequest, and
DocSearchRequest accept `deep`; each search function picks the column.
- /api/search_file_estimates returns both counts in one index-bound
query (COUNT FILTER on the abc subset): `file_groups` (fast) and
`file_groups_deep`.
UI (one coherent story across the count surfaces):
- The typing dropdown always suggests the deep count (what is findable).
- The tab badge shows the active mode's count so it matches the result
list.
- The gap is reconciled by a hint offering deep search: count-aware on
the global search ("No results in fast search. N results available in
deep search." / "N more results available..."), generic on the module
pages (no deep estimate there). The hint resets pagination.
- "Search Depth" toggle in the search filter modals, persisted as
?deep=true.
Tests that relied on d_text matches now pass deep=True, with fast-mode
assertions alongside. Also skip flaky test_download_channel on
CircleCI.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
62 lines
1.8 KiB
Python
62 lines
1.8 KiB
Python
from http import HTTPStatus
|
|
|
|
from sanic import Request, Blueprint
|
|
from sanic_ext import validate
|
|
from sanic_ext.extensions.openapi import openapi
|
|
|
|
from wrolpi.api_utils import json_response
|
|
from wrolpi.common import logger, api_param_limiter
|
|
from wrolpi.schema import JSONErrorResponse
|
|
from . import schema
|
|
from .lib import get_statistics, _doc_response, _get_doc, _search_docs
|
|
|
|
NAME = 'docs'
|
|
|
|
docs_bp = Blueprint('Docs', '/api/docs')
|
|
|
|
logger = logger.getChild(__name__)
|
|
|
|
|
|
@docs_bp.get('/statistics')
|
|
@openapi.response(HTTPStatus.OK, schema.DocStatisticsResponse)
|
|
async def statistics(_: Request):
|
|
ret = get_statistics()
|
|
return json_response(ret, HTTPStatus.OK)
|
|
|
|
|
|
@docs_bp.get('/<file_group_id:int>')
|
|
@openapi.description('Get a doc by FileGroup ID')
|
|
@openapi.response(HTTPStatus.NOT_FOUND, JSONErrorResponse)
|
|
async def get_doc(request: Request, file_group_id: int):
|
|
session = request.ctx.session
|
|
doc = _get_doc(session, file_group_id)
|
|
return json_response(_doc_response(doc))
|
|
|
|
|
|
doc_limit_limiter = api_param_limiter(100)
|
|
|
|
|
|
@docs_bp.post('/search')
|
|
@openapi.definition(
|
|
summary='Search docs with filtering',
|
|
body=schema.DocSearchRequest,
|
|
)
|
|
@openapi.response(HTTPStatus.OK, schema.DocSearchResponse)
|
|
@validate(schema.DocSearchRequest)
|
|
async def search_docs(_: Request, body: schema.DocSearchRequest):
|
|
limit = doc_limit_limiter(body.limit)
|
|
offset = body.offset or 0
|
|
file_groups, total = _search_docs(
|
|
search_str=body.search_str,
|
|
author=body.author,
|
|
subject=body.subject,
|
|
language=body.language,
|
|
mimetype=body.mimetype,
|
|
limit=limit,
|
|
offset=offset,
|
|
order_by=body.order_by,
|
|
tag_names=body.tag_names,
|
|
deep=body.deep,
|
|
)
|
|
ret = dict(file_groups=file_groups, totals=dict(file_groups=total))
|
|
return json_response(ret)
|