Daan MeijerandClaude Opus 5.5
be8a3d4580
Spotnet (CONCEPT D29): - Index free.pt fully and import spots with their descriptions, categories and NZBs; a spot renames its release, since Spotnet names are more trustworthy than names derived from subjects. - Find passwords in spot descriptions too, and tell "needs a password we have" from "needs a password we don't have". Content inspection: - List the contents of 7z (.7z.001) archives, SFV sets, nicovideo uploads and other archive-like files; mark yEncBin .bin containers as encrypted. - Take real names from yEnc headers for randomly named files, and merge uploads that were split across posts. Storage (D31, D32): - Store segment lists zstd-compressed behind the FileStore accessor. - group:backfill indexes older headers at low priority and pauses when the NVMe or HDD part of the database gets too large. Grouping (D35, D36): - Lone header segments wait in staged_segments until a second segment of their file arrives, which drops the per-article junk binaries. - Counter grouping joins random-subject uploads by poster, [i/M] counter, part count and day. Search and maintenance (D33, D34): - A trigram-indexed search_text column, smaller indexes, estimated stats. - Passes that clean up nonsense names; weekly index maintenance; GC budgets per kind. - Web UI: grey out stale results while a search runs and cancel superseded requests. Count only up to 1,000 matches for the page, which made filter clicks take seconds (Newznab keeps the 10,000 cap). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
56 lines
2.1 KiB
TypeScript
56 lines
2.1 KiB
TypeScript
import db from '@adonisjs/lucid/services/db'
|
|
import type { QueryClientContract } from '@adonisjs/lucid/types/database'
|
|
import { packSegments, unpackSegments, type Segment } from '#lib/nzb/segments'
|
|
|
|
/**
|
|
* The only code that knows how `files` keeps its segment lists (CONCEPT.md
|
|
* D31): compressed in `files.segments`, with the first segment's message-id
|
|
* in the indexed `first_message_id` for lookups. Read them with
|
|
* `segmentsOf(file)`; write new files with `FileStore.insert`.
|
|
*/
|
|
|
|
/** A new `files` row, with its segments as a list. */
|
|
export type NewFile = Record<string, unknown> & { segments: Segment[] }
|
|
|
|
const unpacked = new WeakMap<object, Segment[]>()
|
|
|
|
/** The segments of a `files` row (a row from `db.from('files')`), in order. */
|
|
export function segmentsOf(file: { segments?: Buffer | Segment[] | null }): Segment[] {
|
|
const { segments } = file
|
|
if (!segments) return []
|
|
if (Array.isArray(segments)) return segments
|
|
let list = unpacked.get(file)
|
|
if (!list) {
|
|
list = unpackSegments(segments)
|
|
unpacked.set(file, list)
|
|
}
|
|
return list
|
|
}
|
|
|
|
/** Stored form of a segment list, for the File model's column. */
|
|
export function storedSegments(segments: Segment[]) {
|
|
return packSegments(segments)
|
|
}
|
|
|
|
export function loadedSegments(stored: Buffer | null): Segment[] {
|
|
return stored ? unpackSegments(stored) : []
|
|
}
|
|
|
|
class FileStore {
|
|
/**
|
|
* Inserts files, skipping those whose `file_key` exists. Returns the rows
|
|
* that were inserted (id and filename).
|
|
*/
|
|
async insert(files: NewFile[], client: Pick<QueryClientContract, 'knexQuery'> = db): Promise<{ id: number; filename: string }[]> {
|
|
if (files.length === 0) return []
|
|
const rows = files.map(({ segments, ...file }) => {
|
|
const sorted = [...segments].sort((a, b) => a.number - b.number)
|
|
return { ...file, segments: packSegments(sorted), first_message_id: sorted[0]?.id ?? null }
|
|
})
|
|
const inserted = await client.knexQuery().table('files').insert(rows).onConflict('file_key').ignore().returning(['id', 'filename'])
|
|
return inserted.map((row: any) => ({ id: Number(row.id), filename: row.filename }))
|
|
}
|
|
}
|
|
|
|
export default new FileStore()
|