- root deno.json workspace (nodeModulesDir auto), npm versions registered once in imports, deno.lock; remove pnpm-lock/pnpm-workspace/root package.json; members keep minimal package.json (name/type/exports) - tasks: dev, typecheck (tsc 7.0.2 per member + deno check), lint/fmt (biome, useImportExtensions), test (vitest via deno), check:tokens, build (web + deno compile), ci, db:migrate/reset, gen:types - tsconfig base moved to config/ (no root tsconfig.json); deno types -> types/deno.d.ts; web drops baseUrl - server: Deno.serve entry with graceful shutdown, --role migrate|preflight|probe, WEB_ROOT static SPA hosting; drop @hono/node-server, tsx, esbuild build.mjs - logger: redact child() bindings and serialize err by message/stack; sync stdout destination; tests - relative imports get explicit extensions (sites/mp-sync paths left for follow-up) - crash-recovery tests spawn `deno run -A`; tasks tests use unique per-file schemas - single-container Dockerfile + entrypoint (migrate -> preflight -> api+worker watchdog), docker-compose.yml - docs: README, runbook, ADR-001 superseded, plan §1 validation row Co-Authored-By: Claude Fable 5.1 <[email protected]>
69 lines
2.5 KiB
TypeScript
69 lines
2.5 KiB
TypeScript
import type { FeedCursor, FeedItem } from "./types.ts";
|
|
|
|
export function emptyFeedCursor(): FeedCursor {
|
|
return { lastGuidSet: [], digests: {}, lastFetchedAt: null };
|
|
}
|
|
|
|
export interface ApplyFeedResult {
|
|
/** 窗口内首次出现的 GUID */
|
|
newItems: FeedItem[];
|
|
/** 同 GUID 摘要变化(标题修正、促销、体积、置顶变化等),视为更新 */
|
|
updatedItems: FeedItem[];
|
|
unchangedCount: number;
|
|
/**
|
|
* 疑似缺口:本次条目与上次窗口没有任何重叠,且上次窗口非空。
|
|
* 说明两次抓取之间可能有条目被挤出 Feed,需要调度有预算的列表/搜索补漏(REQ §4.3)。
|
|
*/
|
|
possibleGap: boolean;
|
|
cursor: FeedCursor;
|
|
}
|
|
|
|
export interface ApplyFeedOptions {
|
|
/** 游标保留的 GUID 数上限,默认 max(500, 本次条目数 * 3) */
|
|
windowSize?: number;
|
|
}
|
|
|
|
/**
|
|
* 重叠窗口去重:不依赖条目顺序或递增 ID,乱序/置顶/重复出现都按 GUID+摘要判定。
|
|
* 游标只是快速过滤;持久去重仍以数据库 (feed, guid) 唯一约束为准。
|
|
*/
|
|
export function applyFeedItems(cursor: FeedCursor, items: FeedItem[], opts: ApplyFeedOptions = {}): ApplyFeedResult {
|
|
const newItems: FeedItem[] = [];
|
|
const updatedItems: FeedItem[] = [];
|
|
let unchangedCount = 0;
|
|
let overlap = false;
|
|
const digests: Record<string, string> = { ...cursor.digests };
|
|
const seenThisRound = new Set<string>();
|
|
for (const item of items) {
|
|
if (seenThisRound.has(item.guid)) continue; // 同一次抓取内重复 GUID 只取首条
|
|
seenThisRound.add(item.guid);
|
|
const prev = digests[item.guid];
|
|
if (prev === undefined) {
|
|
newItems.push(item);
|
|
} else {
|
|
overlap = true;
|
|
if (prev !== item.rawDigest) updatedItems.push(item);
|
|
else unchangedCount++;
|
|
}
|
|
digests[item.guid] = item.rawDigest;
|
|
}
|
|
const windowSize = opts.windowSize ?? Math.max(500, items.length * 3);
|
|
const order = [...seenThisRound, ...cursor.lastGuidSet.filter((g) => !seenThisRound.has(g))].slice(0, windowSize);
|
|
const kept: Record<string, string> = {};
|
|
for (const g of order) {
|
|
const d = digests[g];
|
|
if (d !== undefined) kept[g] = d;
|
|
}
|
|
const lastFetchedAt = items.reduce<string | null>(
|
|
(acc, it) => (acc === null || it.fetchedAt > acc ? it.fetchedAt : acc),
|
|
cursor.lastFetchedAt,
|
|
);
|
|
return {
|
|
newItems,
|
|
updatedItems,
|
|
unchangedCount,
|
|
possibleGap: cursor.lastGuidSet.length > 0 && items.length > 0 && !overlap,
|
|
cursor: { lastGuidSet: order, digests: kept, lastFetchedAt },
|
|
};
|
|
}
|