mnote/scripts/task532-knowledge-rag-docx-ingestion-smoke.js

#!/usr/bin/env node
"use strict";

const assert = require("node:assert");
const fs = require("node:fs");
const path = require("node:path");
const JSZip = require("jszip");
const { chromium } = require("playwright");

const BASE_URL = (process.env.MNOTE_WEB_SMOKE_BASE_URL || "http://127.0.0.1:3000").replace(/\/+$/, "");
const ROOT_PATH = process.env.MNOTE_KNOWLEDGE_RAG_ROOT_PATH || "/mnt/Data1T/Mnote_data/users/mnote-e2e/workspaces/my-space";
const ROOT_URI = process.env.MNOTE_KNOWLEDGE_RAG_ROOT_URI || `file://${ROOT_PATH}`;
const WORKSPACE_ID = process.env.MNOTE_KNOWLEDGE_RAG_WORKSPACE_ID || "local-ws:mnote-e2e:my-space";
const SOURCE_DOCX = process.env.MNOTE_KNOWLEDGE_RAG_DOCX_SOURCE || path.join(process.cwd(), "tmp", "onlyoffice-direct-bridge.docx");
const FIXTURE_DIR = "knowledge-rag-fixtures-7-50";
const OUTPUT_DIR = path.join(process.cwd(), "tmp", "task532-knowledge-rag-docx-ingestion-smoke");
const RESULT_PATH = path.join(OUTPUT_DIR, "result.json");
const SCREENSHOT_PATH = path.join(OUTPUT_DIR, "docx-resource-tab.png");
const POLL_TIMEOUT_MS = Number(process.env.MNOTE_KNOWLEDGE_RAG_DOCX_TIMEOUT_MS || 10 * 60_000);
const UI_TIMEOUT_MS = Number(process.env.MNOTE_SMOKE_UI_TIMEOUT_MS || 30_000);
const CHROMIUM_EXECUTABLE_PATH = process.env.PLAYWRIGHT_CHROMIUM_EXECUTABLE_PATH
  || ["/usr/bin/google-chrome-stable", "/usr/bin/google-chrome", "/snap/bin/chromium", "/usr/bin/chromium"]
    .find((candidate) => fs.existsSync(candidate));

function sleep(ms) {
  return new Promise((resolve) => setTimeout(resolve, ms));
}

function xmlEscape(value) {
  return String(value)
    .replaceAll("&", "&")
    .replaceAll("<", "&lt;")
    .replaceAll(">", "&gt;")
    .replaceAll('"', "&quot;")
    .replaceAll("'", "&apos;");
}

async function writeDocxFixture(targetPath, marker) {
  assert(fs.existsSync(SOURCE_DOCX), `缺少 DOCX 源文件: ${SOURCE_DOCX}`);
  const zip = await JSZip.loadAsync(fs.readFileSync(SOURCE_DOCX));
  const documentFile = zip.file("word/document.xml");
  assert(documentFile, `DOCX 缺少 word/document.xml: ${SOURCE_DOCX}`);
  const originalXml = await documentFile.async("string");
  const paragraph = `<w:p><w:r><w:t>${xmlEscape(marker)}</w:t></w:r></w:p>`;
  const nextXml = originalXml.includes("</w:body>")
    ? originalXml.replace("</w:body>", `${paragraph}</w:body>`)
    : originalXml + paragraph;
  zip.file("word/document.xml", nextXml);
  fs.mkdirSync(path.dirname(targetPath), { recursive: true });
  const buffer = await zip.generateAsync({ type: "nodebuffer" });
  fs.writeFileSync(targetPath, buffer);
}

async function signIn(context) {
  const response = await context.request.post(`${BASE_URL}/api/auth`, {
    data: {
      action: "auth:signIn",
      args: {
        provider: "password",
        params: {
          email: "mnote.e2e@example.com",
          password: process.env.MNOTE_E2E_PASSWORD || "MnoteE2E123!",
          flow: "signIn",
        },
      },
    },
  });
  assert(response.ok(), `登录失败: ${response.status()} ${await response.text()}`);
}

async function apiJson(context, method, url, data) {
  const response = await context.request.fetch(url, {
    method,
    data,
    headers: {
      "x-mnote-actor-id": "mnote-e2e",
      "x-mnote-actor-type": "user",
      "accept": "application/json",
    },
    timeout: UI_TIMEOUT_MS,
  });
  const text = await response.text();
  let payload = null;
  try {
    payload = text ? JSON.parse(text) : null;
  } catch (_) {
    payload = { rawText: text };
  }
  return { ok: response.ok(), status: response.status(), payload, text };
}

async function status(context) {
  const params = new URLSearchParams({ rootUri: ROOT_URI, workspaceId: WORKSPACE_ID });
  const result = await apiJson(context, "GET", `${BASE_URL}/api/knowledge-rag/status?${params.toString()}`);
  assert(result.ok, `knowledge-rag status 失败: ${result.status} ${result.text.slice(0, 1000)}`);
  return result.payload;
}

function findRegistryEntry(payload, sourcePath) {
  const entries = payload?.registry?.entries;
  return Array.isArray(entries) ? entries.find((entry) => entry.sourceRootRelativePath === sourcePath) : null;
}

async function ingest(context, sourcePath) {
  const result = await apiJson(context, "POST", `${BASE_URL}/api/knowledge-rag/ingest`, {
    rootUri: ROOT_URI,
    workspaceId: WORKSPACE_ID,
    sources: [{ sourcePath }],
  });
  assert(result.ok, `knowledge-rag ingest 失败: ${result.status} ${result.text.slice(0, 1000)}`);
  return result.payload;
}

async function waitForIndexed(context, sourcePath) {
  const startedAt = Date.now();
  let attempts = 0;
  let lastStatus = null;
  let lastIngest = null;
  while (Date.now() - startedAt < POLL_TIMEOUT_MS) {
    attempts += 1;
    lastStatus = await status(context);
    const entry = findRegistryEntry(lastStatus, sourcePath);
    if (entry && entry.indexedAtMs && entry.lightRagDocId && !entry.stale && !entry.deletedAtMs) {
      return { entry, status: lastStatus, attempts, lastIngest };
    }
    if (!entry || attempts % 6 === 1) {
      lastIngest = await ingest(context, sourcePath);
    }
    await sleep(5_000);
  }
  throw new Error(`等待 DOCX 入库超时: ${JSON.stringify({ sourcePath, lastIngest, lastStatus }, null, 2).slice(0, 4000)}`);
}

async function queryDocx(context, marker, sourcePath) {
  const result = await apiJson(context, "POST", `${BASE_URL}/api/knowledge-rag/query`, {
    rootUri: ROOT_URI,
    workspaceId: WORKSPACE_ID,
    query: marker,
    mode: "mix",
    topK: 8,
    chunkTopK: 8,
    includeChunkContent: true,
  });
  assert(result.ok, `knowledge-rag query 失败: ${result.status} ${result.text.slice(0, 1000)}`);
  const references = Array.isArray(result.payload?.references) ? result.payload.references : [];
  const reference = references.find((item) => item.sourceRootRelativePath === sourcePath);
  assert(reference, `DOCX 查询缺少目标引用 ${sourcePath}: ${JSON.stringify(references, null, 2).slice(0, 3000)}`);
  assert(String(reference.quote || reference.content || result.text).toLowerCase().includes(marker.toLowerCase()), `DOCX 引用缺少 marker: ${JSON.stringify(reference, null, 2).slice(0, 2000)}`);
  assert(String(reference.citationUrl || "").includes("resourceTab="), `DOCX 引用缺少 resourceTab citationUrl: ${JSON.stringify(reference, null, 2)}`);
  assert(String(reference.citationMarkdown || "").includes(path.basename(sourcePath)), `DOCX 引用缺少 citationMarkdown: ${JSON.stringify(reference, null, 2)}`);
  return { payload: result.payload, reference };
}

async function openCitationInBrowser(context, reference, sourcePath) {
  const page = await context.newPage();
  await page.goto(`${BASE_URL}${reference.citationUrl}`, { waitUntil: "domcontentloaded", timeout: UI_TIMEOUT_MS });
  await page.waitForFunction(
    (expectedResource) => document.querySelector(`[data-mnote-resource-tab-panel][data-resource-path="${expectedResource}"]`),
    sourcePath,
    { timeout: UI_TIMEOUT_MS },
  );
  await page.waitForTimeout(2_000);
  const state = await page.evaluate((expectedResource) => {
    const panel = document.querySelector(`[data-mnote-resource-tab-panel][data-resource-path="${expectedResource}"]`);
    const activeTab = document.querySelector(".mnote-main-tab.is-active, [data-mnote-tab-kind].is-active");
    return {
      url: location.href,
      panelVisible: !!panel && !panel.hidden,
      panelResourcePath: panel ? panel.getAttribute("data-resource-path") : "",
      panelKind: panel ? panel.getAttribute("data-resource-kind") : "",
      activeTabText: activeTab ? activeTab.textContent.trim().slice(0, 160) : "",
      bodyText: document.body.innerText.slice(0, 1000),
    };
  }, sourcePath);
  await page.screenshot({ path: SCREENSHOT_PATH, fullPage: true });
  await page.close().catch(() => undefined);
  assert.equal(state.panelVisible, true, `DOCX citationUrl 未打开资源 tab: ${JSON.stringify(state, null, 2)}`);
  assert.equal(state.panelResourcePath, sourcePath, `DOCX resource tab path 不匹配: ${JSON.stringify(state, null, 2)}`);
  return state;
}

async function main() {
  fs.mkdirSync(OUTPUT_DIR, { recursive: true });
  const marker = process.env.MNOTE_KNOWLEDGE_RAG_DOCX_MARKER || `DOCX RAG SMOKE ${Date.now()}`;
  const fileName = `docx-rag-smoke-${Date.now()}.docx`;
  const sourcePath = `${FIXTURE_DIR}/${fileName}`;
  const targetPath = path.join(ROOT_PATH, sourcePath);
  await writeDocxFixture(targetPath, marker);

  const browser = await chromium.launch({
    headless: true,
    ...(CHROMIUM_EXECUTABLE_PATH ? { executablePath: CHROMIUM_EXECUTABLE_PATH } : {}),
  });
  const context = await browser.newContext({ viewport: { width: 1360, height: 900 } });
  try {
    await signIn(context);
    const ingestPayload = await ingest(context, sourcePath);
    const indexed = await waitForIndexed(context, sourcePath);
    const queried = await queryDocx(context, marker, sourcePath);
    const browserState = await openCitationInBrowser(context, queried.reference, sourcePath);
    const result = {
      ok: true,
      baseUrl: BASE_URL,
      rootUri: ROOT_URI,
      workspaceId: WORKSPACE_ID,
      sourcePath,
      marker,
      lightRagDocId: indexed.entry.lightRagDocId,
      lightRagFilePath: indexed.entry.lightRagFilePath,
      ingestStatus: ingestPayload?.status,
      attempts: indexed.attempts,
      citationMarkdown: queried.reference.citationMarkdown,
      citationUrl: queried.reference.citationUrl,
      locatorDegraded: queried.reference.locatorDegraded,
      browserState,
      screenshot: SCREENSHOT_PATH,
    };
    fs.writeFileSync(RESULT_PATH, `${JSON.stringify(result, null, 2)}\n`, "utf8");
    console.log(JSON.stringify(result, null, 2));
  } finally {
    await browser.close().catch(() => undefined);
  }
}

main().catch((error) => {
  fs.mkdirSync(OUTPUT_DIR, { recursive: true });
  fs.writeFileSync(
    path.join(OUTPUT_DIR, "failure.json"),
    `${JSON.stringify({ ok: false, error: error.stack || error.message || String(error) }, null, 2)}\n`,
    "utf8",
  );
  console.error(error.stack || error.message || String(error));
  process.exit(1);
});