fabi/Mangalord
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(search): page content-search endpoint (multi-tag AND + text + warnings)

Browse Source 
New GET /v1/me/page-search surfacing the analysis worker's output:

- repo::page_analysis::page_search + PageSearchQuery: multi-tag AND across
  (user page_tags ∪ global page_auto_tags) via the unnest double-negative
  idiom, weighted OCR/scene text ranking (ts_rank over search_doc), and
  content-warning include/exclude. One row per page with is_nsfw +
  deduped content_warnings + rank.
- domain::PageSearchItem.
- api::page_tags: /me/page-search handler with CSV tag/warning parsing
  (parse_tags_csv reuses normalize_tag; parse_warnings_csv validates the
  closed vocabulary), requiring at least one positive filter (422 else).
  This is where the reserved OCR text search lands for pages.

Tests: multi-tag AND user∪auto, speech>sfx ranking, cw include/exclude
(+ row flags), text-only (no tags), missing-filter 422, unknown-warning
422, auth required.

Note: the /me/page-tags/chapters|mangas aggregations keep single-tag
behavior + the reserved text=501 for now; page-level search is the
primary text surface.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
MechaCat02
2026-06-13 18:58:07 +02:00
parent 7d80a437bf
commit af870bd157
8 changed files with 516 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

121
backend/src/repo/page_analysis.rs
View File

@@ -15,9 +15,27 @@ use sqlx::PgPool;
use uuid::Uuid;
use crate::crawler::jobs::{self, JobPayload};
use crate::domain::page_analysis::{ContentWarning, OcrKind, PageAnalysis, VisionAnalysis};
use crate::domain::page_analysis::{
ContentWarning, OcrKind, PageAnalysis, PageSearchItem, VisionAnalysis,
};
use crate::error::AppResult;
/// Filter set for [`page_search`]. `tags` are AND-ed (a page must carry
/// every one, satisfiable by EITHER the user's page tag or a global auto
/// tag); `text` ranks via the weighted tsvector; `cw_include` requires all
/// listed warnings; `cw_exclude` rejects any. All string values arrive
/// pre-normalized (tags lowercased, warnings validated) from the handler.
#[derive(Debug, Default, Clone)]
pub struct PageSearchQuery {
pub user_id: uuid::Uuid,
pub tags: Vec<String>,
pub text: Option<String>,
pub cw_include: Vec<String>,
pub cw_exclude: Vec<String>,
pub limit: i64,
pub offset: i64,
}
/// Longest tag the shared `tags` table accepts (`upsert_by_name` enforces
/// the same bound). Auto-tags over this are dropped here rather than
/// aborting the whole page's analysis on one bad model output.
@@ -245,6 +263,107 @@ pub async fn persist_analysis(
Ok(())
}
/// Content search over pages: multi-tag AND across (user page tags ∪
/// global auto tags), optional weighted text search over the OCR/scene
/// document, and content-warning include/exclude. Returns one row per
/// matching page plus the total for pagination.
///
/// Empty `tags` makes the tag clause vacuously true (text- or
/// warning-only search), mirroring the manga search's `unnest` idiom. The
/// caller is responsible for requiring at least one positive filter so
/// this never degenerates into "every page".
pub async fn page_search(
pool: &PgPool,
q: &PageSearchQuery,
) -> AppResult<(Vec<PageSearchItem>, i64)> {
// `text` participates in three places ($3): the rank, the match
// predicate, and the order key. Empty string disables text filtering.
let text = q.text.as_deref().unwrap_or("").trim();
const WHERE: &str = r#"
NOT EXISTS (
SELECT 1 FROM unnest($2::text[]) AS req(name)
WHERE NOT EXISTS (
SELECT 1 FROM page_tags ut
JOIN tags t ON t.id = ut.tag_id
WHERE ut.page_id = p.id AND ut.user_id = $1 AND lower(t.name) = req.name
UNION ALL
SELECT 1 FROM page_auto_tags at
JOIN tags t ON t.id = at.tag_id
WHERE at.page_id = p.id AND lower(t.name) = req.name
)
)
AND ($3 = '' OR pa.search_doc @@ plainto_tsquery('simple', $3))
AND NOT EXISTS (
SELECT 1 FROM unnest($4::text[]) AS req(w)
WHERE NOT EXISTS (
SELECT 1 FROM page_content_warnings pw
WHERE pw.page_id = p.id AND pw.warning = req.w
)
)
AND NOT EXISTS (
SELECT 1 FROM page_content_warnings pw
WHERE pw.page_id = p.id AND pw.warning = ANY($5::text[])
)
"#;
let rows_sql = format!(
r#"
SELECT
p.id AS page_id,
p.chapter_id AS chapter_id,
ch.manga_id AS manga_id,
p.page_number AS page_number,
ch.number AS chapter_number,
ch.title AS chapter_title,
m.title AS manga_title,
p.storage_key AS storage_key,
COALESCE(pa.is_nsfw, false) AS is_nsfw,
COALESCE(
(SELECT array_agg(pw.warning ORDER BY pw.warning)
FROM page_content_warnings pw WHERE pw.page_id = p.id),
ARRAY[]::text[]
) AS content_warnings,
COALESCE(ts_rank(pa.search_doc, plainto_tsquery('simple', $3)), 0)::real AS rank
FROM pages p
JOIN chapters ch ON ch.id = p.chapter_id
JOIN mangas m ON m.id = ch.manga_id
LEFT JOIN page_analysis pa ON pa.page_id = p.id
WHERE {WHERE}
ORDER BY (CASE WHEN $3 = '' THEN 0 ELSE 1 END) DESC, rank DESC, p.id
LIMIT $6 OFFSET $7
"#
);
let rows = sqlx::query_as::<_, PageSearchItem>(&rows_sql)
.bind(q.user_id)
.bind(&q.tags)
.bind(text)
.bind(&q.cw_include)
.bind(&q.cw_exclude)
.bind(q.limit)
.bind(q.offset)
.fetch_all(pool)
.await?;
let count_sql = format!(
"SELECT count(*) FROM pages p \
JOIN chapters ch ON ch.id = p.chapter_id \
JOIN mangas m ON m.id = ch.manga_id \
LEFT JOIN page_analysis pa ON pa.page_id = p.id \
WHERE {WHERE}"
);
let (total,): (i64,) = sqlx::query_as(&count_sql)
.bind(q.user_id)
.bind(&q.tags)
.bind(text)
.bind(&q.cw_include)
.bind(&q.cw_exclude)
.fetch_one(pool)
.await?;
Ok((rows, total))
}
/// Append a token to a tsvector text bucket with a trailing space.
fn push_token(bucket: &mut String, text: &str) {
bucket.push_str(text);