Files
gongxue-base/scripts/export-worker-integration-test.js
2026-06-29 17:40:10 +08:00

317 lines
15 KiB
JavaScript

import assert from 'node:assert/strict';
import fs from 'node:fs/promises';
import path from 'node:path';
import pg from 'pg';
import { spawn } from 'node:child_process';
import JSZip from 'jszip';
const databaseUrl = process.env.DATABASE_URL || 'postgresql://postgres:postgres@127.0.0.1:54322/postgres';
const tenantId = '00000000-0000-0000-0000-000000000001';
const tenantAdminUserId = '00000000-0000-0000-0000-000000000102';
const collectionId = '00000000-0000-0000-0000-000000000615';
const localStorageRoot = '.local-storage-test';
const ids = {
pdfJob: '21000000-0000-0000-0000-000000000901',
docxJob: '21000000-0000-0000-0000-000000000902',
noAnswerDocxJob: '21000000-0000-0000-0000-000000000903',
dailyPdfJob: '21000000-0000-0000-0000-000000000904',
dailyZipJob: '21000000-0000-0000-0000-000000000905',
};
const jobIds = [ids.pdfJob, ids.docxJob, ids.noAnswerDocxJob, ids.dailyPdfJob, ids.dailyZipJob];
async function runWorkerOnce() {
const child = spawn(process.execPath, ['apps/worker/dist/apps/worker/src/index.js', '--once', '--job', 'exports'], {
cwd: process.cwd(),
env: {
...process.env,
DATABASE_URL: databaseUrl,
WORKER_EXPORT_BATCH_SIZE: '20',
WORKER_EXPORT_ID: 'export-worker-test',
STORAGE_DEFAULT_PROVIDER: 'local_dev',
STORAGE_DEFAULT_BUCKET: 'tenant-assets',
EXPORT_LOCAL_STORAGE_ROOT: localStorageRoot,
STORAGE_REQUIRE_TENANT_PREFIX: 'true',
},
stdio: ['ignore', 'pipe', 'pipe'],
windowsHide: true,
});
let output = '';
child.stdout.on('data', chunk => {
output += chunk.toString();
});
child.stderr.on('data', chunk => {
output += chunk.toString();
});
const code = await new Promise(resolve => child.on('exit', resolve));
assert.equal(code, 0, `worker should exit 0\n${output}`);
assert.match(output, /exports batch processed=\d+/, 'worker output should include exports summary');
return output;
}
async function cleanup(pool) {
await pool.query(
`
delete from public.audit_logs
where tenant_id = $1
and (
(target_type = 'content_export_job' and target_id = any($2::text[]))
or (target_type = 'content_asset' and details->>'exportJobId' = any($2::text[]))
)
`,
[tenantId, jobIds],
);
await pool.query(
`
delete from public.content_assets
where tenant_id = $1
and metadata->>'exportJobId' = any($2::text[])
`,
[tenantId, jobIds],
);
await pool.query(
`
delete from public.content_export_jobs
where tenant_id = $1 and id = any($2::uuid[])
`,
[tenantId, jobIds],
);
await fs.rm(path.resolve(process.cwd(), localStorageRoot), { recursive: true, force: true });
}
async function seed(pool) {
await pool.query(
`
insert into public.content_export_jobs (
id, tenant_id, created_by, export_type, format, scope_type, scope_id,
status, include_answers, include_explanations, include_video_refs,
question_count, summary, options, output_metadata, created_at, updated_at
)
values
(
$1, $4, $5, 'paper', 'pdf', 'collection', $6,
'pending', false, false, false,
0, '{"source":"export-worker-test"}'::jsonb,
'{"title":"导出测试无答案试卷","watermarkText":"内部水印","publishToAssets":true,"assetVisibility":"tenant","limit":50}'::jsonb,
'{"delivery":"content_asset_pending","maxQuestionLimit":50}'::jsonb,
now() - interval '1 minute', now() - interval '1 minute'
),
(
$2, $4, $5, 'paper', 'docx', 'collection', $6,
'pending', true, true, false,
0, '{"source":"export-worker-test"}'::jsonb,
'{"title":"导出测试含答案文档","watermarkText":"内部水印","publishToAssets":false,"assetVisibility":"private","limit":50}'::jsonb,
'{"delivery":"content_asset_pending","maxQuestionLimit":50}'::jsonb,
now() - interval '1 minute', now() - interval '1 minute'
),
(
$3, $4, $5, 'paper', 'docx', 'collection', $6,
'pending', false, false, false,
0, '{"source":"export-worker-test"}'::jsonb,
'{"title":"导出测试无答案文档","watermarkText":"内部水印","publishToAssets":false,"assetVisibility":"private","limit":50}'::jsonb,
'{"delivery":"content_asset_pending","maxQuestionLimit":50}'::jsonb,
now() - interval '1 minute', now() - interval '1 minute'
),
(
$7, $4, $5, 'daily_practice', 'pdf', 'collection', $6,
'pending', true, false, false,
0, '{"source":"export-worker-test"}'::jsonb,
'{"title":"每日一练测试","issue":"每日一练 第 1 期","date":"2026-06-29","watermarkText":"每日一练水印","publishToAssets":true,"assetVisibility":"tenant","limit":99,"brand":{"name":"恭学教育","english":"GONGXUE EDU","slogan":"专注高职升本","ctaLine":"每日一练 · 稳步上岸"}}'::jsonb,
'{"delivery":"content_asset_pending","maxQuestionLimit":8}'::jsonb,
now() - interval '1 minute', now() - interval '1 minute'
),
(
$8, $4, $5, 'daily_practice', 'daily_practice_zip', 'collection', $6,
'pending', false, false, false,
0, '{"source":"export-worker-test"}'::jsonb,
'{"title":"每日一练图片包测试","issue":"每日一练 第 2 期","date":"2026-06-29","theme":"ink","cardFormat":"1:1","watermarkText":"每日一练水印","publishToAssets":true,"assetVisibility":"tenant","limit":99,"brand":{"name":"恭学教育","english":"GONGXUE EDU","slogan":"专注高职升本","ctaLine":"每日一练 · 稳步上岸"}}'::jsonb,
'{"delivery":"content_asset_pending","maxQuestionLimit":8}'::jsonb,
now() - interval '1 minute', now() - interval '1 minute'
)
`,
[ids.pdfJob, ids.docxJob, ids.noAnswerDocxJob, tenantId, tenantAdminUserId, collectionId, ids.dailyPdfJob, ids.dailyZipJob],
);
}
function countFromWorkerOutput(output, name) {
const match = output.match(new RegExp(`${name}=(\\d+)`));
return match ? Number(match[1]) : 0;
}
async function generatedFileBody(asset) {
const fullPath = path.resolve(process.cwd(), localStorageRoot, asset.bucket, asset.object_key);
return fs.readFile(fullPath);
}
async function assertGeneratedFile(asset) {
const body = await generatedFileBody(asset);
assert.equal(body.length, Number(asset.file_size_bytes), 'generated file size should match content_assets');
assert.ok(body.length > 500, 'generated binary export should not be empty');
if (asset.mime_type === 'application/pdf') {
assert.equal(body.subarray(0, 4).toString('utf8'), '%PDF', 'PDF export should have PDF header');
} else if (asset.mime_type === 'application/zip') {
assert.equal(body.subarray(0, 2).toString('hex'), '504b', 'ZIP export should have ZIP header');
} else {
assert.equal(body.subarray(0, 2).toString('hex'), '504b', 'DOCX export should be a zipped Office file');
}
}
async function docxText(asset) {
const zip = await JSZip.loadAsync(await generatedFileBody(asset));
const xml = await zip.file('word/document.xml')?.async('string');
assert.ok(xml, 'DOCX should contain word/document.xml');
return xml
.replace(/<[^>]+>/g, '')
.replace(/&lt;/g, '<')
.replace(/&gt;/g, '>')
.replace(/&amp;/g, '&');
}
async function zipEntries(asset) {
const zip = await JSZip.loadAsync(await generatedFileBody(asset));
const manifestText = await zip.file('manifest.json')?.async('string');
const payloadText = await zip.file('payload.json')?.async('string');
assert.ok(manifestText, 'daily practice ZIP should contain manifest.json');
assert.ok(payloadText, 'daily practice ZIP should contain payload.json');
return {
manifest: JSON.parse(manifestText),
payload: JSON.parse(payloadText),
names: Object.keys(zip.files).filter(name => !zip.files[name].dir),
};
}
async function main() {
const pool = new pg.Pool({ connectionString: databaseUrl });
let seeded = false;
try {
await pool.query('begin');
await cleanup(pool);
await seed(pool);
await pool.query('commit');
seeded = true;
const output = await runWorkerOnce();
assert.ok(countFromWorkerOutput(output, 'completed') >= 5, 'worker should complete all binary export jobs');
const jobs = await pool.query(
`
select id, status, asset_id, question_count, output_metadata
from public.content_export_jobs
where tenant_id = $1 and id = any($2::uuid[])
order by id
`,
[tenantId, jobIds],
);
assert.equal(jobs.rowCount, 5, 'all export jobs should still exist');
for (const job of jobs.rows) {
assert.equal(job.status, 'completed', 'export job should be completed');
assert.ok(job.asset_id, 'completed export job should reference a content asset');
assert.equal(job.output_metadata?.delivery, 'content_asset', 'export job should switch delivery to content_asset');
assert.ok(job.output_metadata?.checksumSha256, 'export job should record output checksum');
assert.ok(Number(job.question_count) >= 1, 'export job should record question count');
}
const assets = await pool.query(
`
select id, asset_type, title, file_name, storage_provider, bucket,
object_key, mime_type, file_size_bytes, checksum_sha256,
upload_status, visibility, status, metadata
from public.content_assets
where tenant_id = $1 and metadata->>'exportJobId' = any($2::text[])
order by file_name
`,
[tenantId, jobIds],
);
assert.equal(assets.rowCount, 5, 'worker should create five export assets');
const pdfAsset = assets.rows.find(asset => asset.metadata?.exportJobId === ids.pdfJob);
const docxAsset = assets.rows.find(asset => asset.metadata?.exportJobId === ids.docxJob);
const noAnswerDocxAsset = assets.rows.find(asset => asset.metadata?.exportJobId === ids.noAnswerDocxJob);
const dailyPdfAsset = assets.rows.find(asset => asset.metadata?.exportJobId === ids.dailyPdfJob);
const dailyZipAsset = assets.rows.find(asset => asset.metadata?.exportJobId === ids.dailyZipJob);
assert.ok(pdfAsset, 'PDF export should create a PDF content asset');
assert.ok(docxAsset, 'DOCX export should create a Word content asset');
assert.ok(noAnswerDocxAsset, 'no-answer DOCX export should create a Word content asset');
assert.ok(dailyPdfAsset, 'daily practice PDF export should create a PDF content asset');
assert.ok(dailyZipAsset, 'daily practice ZIP export should create a package content asset');
assert.equal(pdfAsset.mime_type, 'application/pdf', 'PDF asset should use application/pdf');
assert.ok(docxAsset.mime_type?.includes('wordprocessingml'), 'DOCX asset should use Word MIME type');
assert.equal(dailyZipAsset.mime_type, 'application/zip', 'daily practice package should use application/zip');
assert.equal(dailyZipAsset.asset_type, 'package', 'daily practice ZIP should use package asset type');
assert.equal(pdfAsset.upload_status, 'verified', 'PDF asset should be verified');
assert.equal(docxAsset.upload_status, 'verified', 'DOCX asset should be verified');
assert.equal(noAnswerDocxAsset.upload_status, 'verified', 'no-answer DOCX asset should be verified');
assert.equal(dailyPdfAsset.upload_status, 'verified', 'daily practice PDF asset should be verified');
assert.equal(dailyZipAsset.upload_status, 'verified', 'daily practice ZIP asset should be verified');
assert.equal(pdfAsset.visibility, 'tenant', 'published PDF export should use requested asset visibility');
assert.equal(docxAsset.visibility, 'private', 'non-published DOCX export should remain private');
assert.equal(noAnswerDocxAsset.visibility, 'private', 'no-answer DOCX export should remain private');
assert.equal(dailyPdfAsset.visibility, 'tenant', 'daily practice PDF export should use requested asset visibility');
assert.equal(dailyZipAsset.visibility, 'tenant', 'daily practice ZIP export should use requested asset visibility');
assert.equal(dailyPdfAsset.metadata?.exportType, 'daily_practice', 'daily practice asset should keep export type metadata');
assert.equal(dailyZipAsset.metadata?.format, 'daily_practice_zip', 'daily practice package should keep export format metadata');
await assertGeneratedFile(pdfAsset);
await assertGeneratedFile(docxAsset);
await assertGeneratedFile(noAnswerDocxAsset);
await assertGeneratedFile(dailyPdfAsset);
await assertGeneratedFile(dailyZipAsset);
const answeredDocxText = await docxText(docxAsset);
assert.match(answeredDocxText, /答案/, 'DOCX with answers should include answer labels');
assert.match(answeredDocxText, /后端需要统一校验租户/, 'DOCX with answers should include subjective answer text');
const noAnswerDocxText = await docxText(noAnswerDocxAsset);
assert.doesNotMatch(noAnswerDocxText, /后端需要统一校验租户/, 'DOCX without answers should not leak subjective answer text');
assert.doesNotMatch(noAnswerDocxText, /基础加法。/, 'DOCX without explanations should not leak explanations');
const dailyZip = await zipEntries(dailyZipAsset);
assert.equal(dailyZip.manifest.exportType, 'daily_practice', 'daily practice package manifest should keep export type');
assert.equal(dailyZip.manifest.format, 'daily_practice_zip', 'daily practice package manifest should keep format');
assert.equal(dailyZip.manifest.safety?.includeAnswers, false, 'daily practice package should record answer redaction');
assert.ok(dailyZip.names.includes('collage.png'), 'daily practice package should include collage PNG');
assert.ok(dailyZip.names.includes('collage.svg'), 'daily practice package should include collage SVG source');
assert.equal(dailyZip.names.filter(name => /^cards\/card-\d{2}\.png$/.test(name)).length, 9, 'daily practice package should include nine PNG cards');
assert.equal(dailyZip.names.filter(name => /^cards\/card-\d{2}\.svg$/.test(name)).length, 9, 'daily practice package should include nine SVG card sources');
assert.equal(dailyZip.payload.questions?.[0]?.answerText, undefined, 'daily practice package payload should omit answer text when disabled');
assert.equal(dailyZip.payload.questions?.[0]?.explanation, undefined, 'daily practice package payload should omit explanations when disabled');
assert.ok(
dailyZip.payload.summary?.cardCount >= 1 && dailyZip.payload.summary?.cardCount <= 8,
'daily practice package payload should cap card count to the nine-grid question slots',
);
assert.equal(
dailyZip.payload.summary?.cardCount,
dailyZip.manifest.summary?.cardCount,
'daily practice package manifest and payload should agree on card count',
);
const audits = await pool.query(
`
select action, details
from public.audit_logs
where tenant_id = $1
and target_type = 'content_export_job'
and target_id = any($2::text[])
`,
[tenantId, jobIds],
);
assert.ok(
audits.rows.some(row => row.action === 'content.questions.export_rendered' && row.details?.assetId),
'worker should write rendered audit log',
);
console.log('Export worker integration test complete.');
} catch (error) {
await pool.query('rollback').catch(() => {});
throw error;
} finally {
if (seeded) {
await cleanup(pool).catch(() => {});
}
await pool.end();
}
}
main().catch(error => {
console.error(error);
process.exit(1);
});