Files
gerbeur/api/services/backlink-service.ts
khannurien d392be7cb8
All checks were successful
Build and Publish Docker Image / build-and-push (push) Successful in 50s
v3: api/ gets one layout rule and keeps to it, and whatever crosses the wire is defined once, in shared/ — api/model/interfaces.ts and src/model.ts declared the same 40 types by hand and had drifted: the error envelope, email required on one side and optional on the other, Invitee/InviteTreeEntry and LinkPreview/UrlPreviewResponse for one shape each. The validation limits, the role permissions, the chat length cap, the @mention pattern and the Bandcamp and YouTube player responses were copied too, behind "keep in sync" comments. shared/ now holds them once, one file per domain (api, category, chat, comment, dump, follow, mention, notification, permissions, player, playlist, search, user, validation, ws), and imports nothing from either half. The server sends Dates; the client reads Wire<T>, the same type with every Date an ISO string, and turns it back with src/utils/shared/deserialize.ts. APIErrorCode becomes a const object, since the frontend's erasableSyntaxOnly rejects an enum. The shared types showed two real gaps: the avatar upload and GET /api/users/me return the full self user and the frontend read them as public users, and a stored session may predate media tokens, so the client keeps it as its own Session type. The backend rule: each folder holds one kind of module, each file is named after its domain. routes/ parse and answer; services/ hold the logic and every SQL query (lib/auth.ts's token check moves to user-service); remote/ is the only place that fetches from other sites — the guarded fetch and the HTML scraping out of rich-content-service, public-address, the Bandcamp and YouTube resolvers, the link providers, the image proxy (fetch, checks and cache, out of routes/preview.ts) and the Twemoji glyphs (out of lib/site-icons.ts). model/ holds per table a row type, its guard and its mappers; validators/ the request guards; db/connection.ts the handle and transaction(), db/startup.ts the purges and default admin that db.ts ran on import, called at the same moment. Tests mirror the source one file per module, test/<layer>/<module>.test.ts, with shared/'s under shared/test/ (deno task test runs both); the test that covered the bandcamp and soundcloud providers together is two now, and the backend can() has its own, so 202 tests. deno lint src/ is clean too: window.* becomes globalThis.*, and test bodies and act() callbacks that never awaited lose their async. The README states the rule. No behaviour changes; the catalogues only move their source references.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-27 20:19:48 +00:00

112 lines
3.8 KiB
TypeScript

import type { Dump } from "../../shared/dump.ts";
import { db, transaction } from "../db/connection.ts";
import {
DUMP_SELECT_COLUMNS as SELECT_COLS,
dumpRowToApi,
isDumpRow,
} from "../model/dump.ts";
import { UUID_RE } from "../lib/slugify.ts";
// Matches http(s) URLs in free text — stops at whitespace or markdown-link
// delimiters (so `[text](url)` and `<url>` don't swallow the closing char).
const URL_RE = /https?:\/\/[^\s)\]<>"']+/g;
// A link to another dump's page on this same site (e.g. pasted from the
// address bar) — host-agnostic, since the configured public URL can differ
// between dev/prod/reverse-proxy setups. Matches `/dumps/{slug-or-id}`,
// ignoring any trailing path/query/hash (so `/edit` or `#comment-x` links
// still resolve to the same target dump).
const DUMP_PATH_RE = /^\/dumps\/([^/?#]+)/;
function canonicalize(url: string): string | null {
try {
return new URL(url).toString();
} catch {
return null;
}
}
/** Resolves a same-site `/dumps/{slug-or-id}` path segment to a dump id. */
function resolveDumpPathId(idOrSlug: string): string | null {
const row = UUID_RE.test(idOrSlug)
? db.prepare(`SELECT id FROM dumps WHERE id = ?;`).get(idOrSlug)
: db.prepare(`SELECT id FROM dumps WHERE slug = ?;`).get(idOrSlug);
return (row as { id: string } | undefined)?.id ?? null;
}
/**
* Re-derive the backlinks contributed by one text source (a dump's own
* `comment` field, or a single comment's `body`) and persist them. Always
* deletes the source's previous contribution first, so editing/clearing the
* text correctly removes stale links — unlike `linkAttachments`/`notifyMentions`,
* which are purely additive.
*/
export function relinkBacklinks(
sourceType: "dump_comment" | "comment",
sourceId: string,
fromDumpId: string,
text: string,
): void {
const targetIds = new Set<string>();
const externalUrls = new Set<string>();
for (const match of text.matchAll(URL_RE)) {
const canonical = canonicalize(match[0]);
if (!canonical) continue;
let parsed: URL;
try {
parsed = new URL(canonical);
} catch {
continue;
}
const pathMatch = DUMP_PATH_RE.exec(parsed.pathname);
if (pathMatch) {
const resolved = resolveDumpPathId(decodeURIComponent(pathMatch[1]));
if (resolved) targetIds.add(resolved);
} else {
externalUrls.add(canonical);
}
}
if (externalUrls.size > 0) {
const placeholders = [...externalUrls].map(() => "?").join(", ");
const rows = db.prepare(
`SELECT id FROM dumps WHERE url IN (${placeholders});`,
).all(...externalUrls) as { id: string }[];
for (const row of rows) targetIds.add(row.id);
}
targetIds.delete(fromDumpId); // no self-links
transaction(() => {
db.prepare(
`DELETE FROM dump_backlinks WHERE source_type = ? AND source_id = ?;`,
).run(sourceType, sourceId);
const createdAt = new Date().toISOString();
const insert = db.prepare(
`INSERT INTO dump_backlinks (source_type, source_id, from_dump_id, to_dump_id, created_at)
VALUES (?, ?, ?, ?, ?);`,
);
for (const toDumpId of targetIds) {
insert.run(sourceType, sourceId, fromDumpId, toDumpId, createdAt);
}
});
}
/** Bidirectional, privacy-filtered, capped at 20 — backlinks are a small, bounded list. */
export function getRelatedDumps(
dumpId: string,
requestingUserId?: string,
): Dump[] {
const rows = db.prepare(
`SELECT ${SELECT_COLS} FROM dumps WHERE id IN (
SELECT to_dump_id FROM dump_backlinks WHERE from_dump_id = ?
UNION
SELECT from_dump_id FROM dump_backlinks WHERE to_dump_id = ?
) AND (is_private = 0 OR user_id = ?)
ORDER BY created_at DESC LIMIT 20;`,
).all(dumpId, dumpId, requestingUserId ?? "");
return rows.filter(isDumpRow).map(dumpRowToApi);
}