video-workflow/scripts/validation/ip-operator-cleanup-dry-run.mjs

import fs from 'node:fs';
import path from 'node:path';
import { fileURLToPath } from 'node:url';

const FN_URL = process.env.SMOKE_FN_URL || 'https://server.fmode.cn/api/functions';
const APP_ID = process.env.SMOKE_PARSE_APP_ID || 'ncloudmaster';
const SESSION_TOKEN = process.env.SMOKE_SESSION_TOKEN || '';
const ACCOUNT_FILTER = String(process.env.IP_CLEANUP_ACCOUNT_ID || '').trim();
const INCLUDE_ALL_ACTIVE = /^(1|true|yes)$/i.test(String(process.env.IP_CLEANUP_INCLUDE_ALL_ACTIVE || ''));
const PRINT_CANDIDATES = /^(1|true|yes)$/i.test(String(process.env.IP_CLEANUP_PRINT_CANDIDATES || ''));
const OUTPUT_DIR = process.env.IP_CLEANUP_OUTPUT_DIR
  ? path.resolve(process.env.IP_CLEANUP_OUTPUT_DIR)
  : path.join(process.cwd(), 'tmp');

const __dirname = path.dirname(fileURLToPath(import.meta.url));
const rootDir = path.resolve(__dirname, '..', '..');
const cloudFunctionsPath = path.join(rootDir, 'src', 'app', 'services', 'cloud-functions.ts');
const fn = readCloudFunctionIds(cloudFunctionsPath);

const entityTypes = [
  'ipOperator.account',
  'ipOperator.profile',
  'ipOperator.plan',
  'ipOperator.accountSnapshot',
  'ipOperator.accountSnapshotWork',
  'ipOperator.accountSnapshotComment',
  'ipOperator.accountDiagnosis',
  'ipOperator.positioningProposal',
  'ipOperator.positioningVersion',
  'ipOperator.contentDirection',
  'ipOperator.operationTask',
  'ipOperator.publishBinding',
  'ipOperator.planEvidenceItem',
  'ipOperator.planCommentPainInsight',
  'ipOperator.planContentCalendarItem',
  'ipOperator.planPublishPackage',
  'ipOperator.planScriptBody',
  'ipOperator.planGenerationPreview',
];

if (!SESSION_TOKEN) {
  console.error('Missing SMOKE_SESSION_TOKEN. This dry-run only reads the current Parse user namespace.');
  process.exit(1);
}
if (!fn.systemStorage) {
  console.error('CLOUD_FN.systemStorage is empty. Check src/app/services/cloud-functions.ts.');
  process.exit(1);
}

const startedAt = new Date().toISOString();
const rowsByType = new Map();
const allRows = [];

for (const entityType of entityTypes) {
  const rows = await listRows(entityType);
  rowsByType.set(entityType, rows);
  allRows.push(...rows);
}

const stats = await call(fn.systemStorage, { action: 'stats' }).catch(() => null);
const accounts = rowsByType.get('ipOperator.account') || [];
const plans = rowsByType.get('ipOperator.plan') || [];
const snapshots = rowsByType.get('ipOperator.accountSnapshot') || [];
const works = rowsByType.get('ipOperator.accountSnapshotWork') || [];
const comments = rowsByType.get('ipOperator.accountSnapshotComment') || [];
const evidenceRows = rowsByType.get('ipOperator.planEvidenceItem') || [];
const painRows = rowsByType.get('ipOperator.planCommentPainInsight') || [];

const accountIds = new Set();
for (const account of accounts) accountIds.add(account.entityId);
for (const row of [...snapshots, ...works, ...comments, ...evidenceRows, ...painRows]) {
  const accountId = row.data?.accountId || parseAccountIdFromSnapshotId(row.data?.snapshotId || row.entityId);
  if (accountId) accountIds.add(accountId);
}
const targetAccountIds = [...accountIds].filter((id) => !ACCOUNT_FILTER || id === ACCOUNT_FILTER);

const candidates = [];
for (const accountId of targetAccountIds) {
  collectAccountCandidates(accountId, candidates);
}

const typeStatus = summarizeByTypeAndStatus(allRows);
const candidateSummary = summarizeByTypeAndStatus(candidates);
const reportBase = `ip-operator-cleanup-dry-run-${safeTimestamp(startedAt)}`;
const jsonPath = path.join(OUTPUT_DIR, `${reportBase}.json`);
const mdPath = path.join(OUTPUT_DIR, `${reportBase}.md`);
const report = buildReport({
  generatedAt: startedAt,
  accountFilter: ACCOUNT_FILTER || '',
  stats: stats?.success ? stats.data : null,
  fetchedSummary: summaryToObject(typeStatus),
  candidateSummary: summaryToObject(candidateSummary),
  fetchedRowCount: allRows.length,
  candidateCount: candidates.length,
  candidates,
});
fs.mkdirSync(OUTPUT_DIR, { recursive: true });
fs.writeFileSync(jsonPath, `${JSON.stringify(report, null, 2)}\n`, 'utf8');
fs.writeFileSync(mdPath, renderMarkdownReport(report), 'utf8');

console.log(`IP operator cleanup dry-run generatedAt=${startedAt}`);
console.log(`scope=current Parse user; accountFilter=${ACCOUNT_FILTER || '(all detected accounts)'}`);
console.log('');
console.log('Current fetched rows by entityType/status:');
printSummary(typeStatus);
if (stats?.success && stats.data?.totalEntities !== undefined) {
  console.log('');
  console.log(`systemStorage.stats totalEntities=${stats.data.totalEntities}`);
}
console.log('');
console.log('Cleanup candidates by entityType/status:');
printSummary(candidateSummary);
console.log('');
console.log(`Cleanup candidate rows: ${candidates.length}`);
console.log('');
console.log(`Full JSON report: ${jsonPath}`);
console.log(`Full Markdown report: ${mdPath}`);
if (PRINT_CANDIDATES) {
  console.log('');
  printCandidates(candidates);
}
console.log('');
console.log('DRY-RUN ONLY: no delete/purge/physical removal was executed.');
console.log('Next step: review candidate reasons. Only after confirmation should a separate execution script be used.');

async function listRows(entityType) {
  const statuses = INCLUDE_ALL_ACTIVE
    ? ['active', 'deleted', 'purged', 'archived']
    : ['active', 'deleted', 'purged'];
  const merged = [];
  const seen = new Set();
  for (const status of statuses) {
    const result = await call(fn.systemStorage, { action: 'list', entityType, status, limit: 1000 });
    if (!result?.success) {
      console.warn(`WARN list failed entityType=${entityType} status=${status}: ${result?.error || JSON.stringify(result)}`);
      continue;
    }
    for (const row of result.data || []) {
      const key = row.objectId || `${row.entityType}:${row.entityId}:${row.status}`;
      if (seen.has(key)) continue;
      seen.add(key);
      merged.push(normalizeRow(row));
    }
  }
  return merged;
}

function collectAccountCandidates(accountId, output) {
  const currentSnapshotId = `snapshot_${accountId}_current`;
  const currentPlanId = `ip_account_plan_${accountId}`;
  const plan = plans.find((row) => row.entityId === currentPlanId || row.data?.id === currentPlanId);
  const currentRefs = new Set([
    ...toArray(plan?.data?.externalizedCollections?.evidenceItems),
    ...toArray(plan?.data?.evidenceItems).map((item) => item?.id).filter(Boolean),
  ]);
  const currentPainRefs = new Set([
    ...toArray(plan?.data?.externalizedCollections?.commentPainInsights),
    ...toArray(plan?.data?.commentPainInsights).map((item) => item?.id).filter(Boolean),
  ]);

  const staleSnapshotIds = new Set();
  for (const row of snapshots) {
    const rowAccountId = row.data?.accountId || parseAccountIdFromSnapshotId(row.entityId);
    if (rowAccountId !== accountId) continue;
    if (row.entityId === currentSnapshotId) continue;
    if (/^snapshot_.+_(current)$/.test(row.entityId)) continue;
    staleSnapshotIds.add(row.entityId);
    pushCandidate(output, row, accountId, `old account snapshot; keep ${currentSnapshotId}`);
  }

  for (const row of works) {
    const snapshotId = row.data?.snapshotId || parseSnapshotIdFromChildId(row.entityId);
    const rowAccountId = row.data?.accountId || parseAccountIdFromSnapshotId(snapshotId);
    if (rowAccountId !== accountId) continue;
    if (staleSnapshotIds.has(snapshotId)) {
      pushCandidate(output, row, accountId, `work belongs to old snapshot ${snapshotId}`);
    }
  }

  for (const row of comments) {
    const snapshotId = row.data?.snapshotId || parseSnapshotIdFromChildId(row.entityId);
    const rowAccountId = row.data?.accountId || parseAccountIdFromSnapshotId(snapshotId);
    if (rowAccountId !== accountId) continue;
    if (staleSnapshotIds.has(snapshotId)) {
      pushCandidate(output, row, accountId, `comment belongs to old snapshot ${snapshotId}`);
    }
  }

  for (const row of evidenceRows) {
    const data = row.data || {};
    if (data.accountId !== accountId) continue;
    const evidenceId = data.id || row.entityId.split('__').pop();
    const snapshotId = data.snapshotId || '';
    if (staleSnapshotIds.has(snapshotId)) {
      pushCandidate(output, row, accountId, `evidence belongs to old snapshot ${snapshotId}`);
      continue;
    }
    if (plan && currentRefs.size && !currentRefs.has(evidenceId)) {
      pushCandidate(output, row, accountId, `evidence is not referenced by current plan ${currentPlanId}`);
    }
  }

  for (const row of painRows) {
    const data = row.data || {};
    const planId = data.planId || row.entityId.split('__')[0];
    if (planId !== currentPlanId) continue;
    const painId = data.id || row.entityId.split('__').pop();
    const evidenceIds = toArray(data.evidenceItemIds);
    const referencesStaleEvidence = evidenceIds.some((id) => candidatesEvidenceIdsForAccount(output, accountId).has(id));
    if (referencesStaleEvidence) {
      pushCandidate(output, row, accountId, 'pain insight references stale evidence');
      continue;
    }
    if (plan && currentPainRefs.size && !currentPainRefs.has(painId)) {
      pushCandidate(output, row, accountId, `pain insight is not referenced by current plan ${currentPlanId}`);
    }
  }

  for (const row of allRows) {
    if ((row.status === 'deleted' || row.status === 'purged') && row.entityType.startsWith('ipOperator.')) {
      const rowAccountId = row.data?.accountId || parseAccountIdFromSnapshotId(row.data?.snapshotId || row.entityId);
      if (rowAccountId === accountId) pushCandidate(output, row, accountId, `already ${row.status}; physical cleanup candidate only after review`);
    }
  }
}

function candidatesEvidenceIdsForAccount(output, accountId) {
  return new Set(output
    .filter((row) => row.accountId === accountId && row.entityType === 'ipOperator.planEvidenceItem')
    .map((row) => row.data?.id || row.entityId.split('__').pop())
    .filter(Boolean));
}

function pushCandidate(output, row, accountId, reason) {
  const key = row.objectId || `${row.entityType}:${row.entityId}`;
  if (output.some((item) => (item.objectId || `${item.entityType}:${item.entityId}`) === key)) return;
  output.push({ ...row, accountId, reason });
}

async function call(id, body) {
  let lastResult = null;
  let lastError = null;
  for (let attempt = 1; attempt <= 4; attempt += 1) {
    try {
      const response = await fetch(FN_URL, {
        method: 'POST',
        headers: {
          'Content-Type': 'application/json',
          'X-Parse-Application-Id': APP_ID,
        },
        body: JSON.stringify({ id, _ApplicationId: APP_ID, sessionToken: SESSION_TOKEN, ...body }),
      });
      const text = await response.text();
      let result;
      try {
        result = JSON.parse(text);
      } catch {
        result = { code: response.status, success: false, error: text };
      }
      lastResult = result;
      if (attempt < 4 && isRetryableResult(result)) {
        await sleep(600 * attempt);
        continue;
      }
      return result;
    } catch (error) {
      lastError = error;
      const message = `${error?.message || ''} ${error?.cause?.code || ''}`;
      if (attempt < 4 && isRetryableMessage(message)) {
        await sleep(600 * attempt);
        continue;
      }
      return { code: 500, success: false, error: error?.message || 'fetch failed' };
    }
  }
  if (lastResult) return lastResult;
  return { code: 500, success: false, error: lastError?.message || 'fetch failed' };
}

function isRetryableResult(result) {
  const message = `${result?.error || ''} ${result?.message || ''}`;
  return Number(result?.code || 0) >= 500 || isRetryableMessage(message);
}

function isRetryableMessage(message) {
  return /fetch failed|Failed to fetch|NetworkError|Load failed|ECONNRESET|ETIMEDOUT|EAI_AGAIN/i.test(message || '');
}

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

function readCloudFunctionIds(filePath) {
  const text = fs.readFileSync(filePath, 'utf8');
  const ids = {};
  const re = /(\w+):\s*'([^']*)'/g;
  let match;
  while ((match = re.exec(text))) ids[match[1]] = match[2];
  return ids;
}

function normalizeRow(row) {
  return {
    objectId: row.objectId || '',
    entityType: row.entityType || row.type || '',
    entityId: row.entityId || row.id || '',
    status: row.status || 'active',
    createdAt: row.createdAt || '',
    updatedAt: row.updatedAt || '',
    data: row.data && typeof row.data === 'object' ? row.data : {},
  };
}

function summarizeByTypeAndStatus(rows) {
  const summary = new Map();
  for (const row of rows) {
    const type = row.entityType || '(unknown)';
    const status = row.status || '(unknown)';
    if (!summary.has(type)) summary.set(type, {});
    summary.get(type)[status] = (summary.get(type)[status] || 0) + 1;
  }
  return summary;
}

function printSummary(summary) {
  const types = [...summary.keys()].sort();
  if (!types.length) {
    console.log('  (none)');
    return;
  }
  for (const type of types) {
    const statuses = Object.entries(summary.get(type))
      .sort(([a], [b]) => a.localeCompare(b))
      .map(([status, count]) => `${status}:${count}`)
      .join(', ');
    console.log(`  ${type} -> ${statuses}`);
  }
}

function printCandidates(rows) {
  if (!rows.length) {
    console.log('  (none)');
    return;
  }
  const sorted = [...rows].sort((a, b) =>
    a.accountId.localeCompare(b.accountId)
    || a.entityType.localeCompare(b.entityType)
    || a.entityId.localeCompare(b.entityId));
  for (const row of sorted) {
    console.log([
      `  account=${row.accountId}`,
      `type=${row.entityType}`,
      `status=${row.status}`,
      `entityId=${row.entityId}`,
      row.objectId ? `objectId=${row.objectId}` : '',
      `reason=${row.reason}`,
    ].filter(Boolean).join(' | '));
  }
}

function buildReport(input) {
  return {
    generatedAt: input.generatedAt,
    scope: {
      parseUser: 'current sessionToken user',
      accountFilter: input.accountFilter,
      includeArchived: INCLUDE_ALL_ACTIVE,
    },
    stats: input.stats,
    fetchedRowCount: input.fetchedRowCount,
    fetchedSummary: input.fetchedSummary,
    candidateCount: input.candidateCount,
    candidateSummary: input.candidateSummary,
    candidates: input.candidates.map((row) => ({
      accountId: row.accountId,
      objectId: row.objectId,
      entityType: row.entityType,
      entityId: row.entityId,
      status: row.status,
      createdAt: row.createdAt,
      updatedAt: row.updatedAt,
      reason: row.reason,
      dataId: row.data?.id || '',
      snapshotId: row.data?.snapshotId || '',
      planId: row.data?.planId || '',
      workId: row.data?.workId || '',
    })),
  };
}

function renderMarkdownReport(report) {
  const lines = [
    '# IP Operator Cleanup Dry Run',
    '',
    `- generatedAt: ${report.generatedAt}`,
    `- scope: ${report.scope.parseUser}`,
    `- accountFilter: ${report.scope.accountFilter || '(all detected accounts)'}`,
    `- fetchedRowCount: ${report.fetchedRowCount}`,
    `- candidateCount: ${report.candidateCount}`,
  ];
  if (report.stats?.totalEntities !== undefined) {
    lines.push(`- systemStorage.stats totalEntities: ${report.stats.totalEntities}`);
  }
  lines.push('', '## Current fetched rows by entityType/status', '');
  lines.push(...summaryMarkdownLines(report.fetchedSummary));
  lines.push('', '## Cleanup candidates by entityType/status', '');
  lines.push(...summaryMarkdownLines(report.candidateSummary));
  lines.push('', '## Candidate rows', '');
  if (!report.candidates.length) {
    lines.push('(none)');
  } else {
    lines.push('| accountId | entityType | status | entityId | objectId | reason |');
    lines.push('|---|---|---|---|---|---|');
    for (const row of report.candidates) {
      lines.push(`| ${escapeMd(row.accountId)} | ${escapeMd(row.entityType)} | ${escapeMd(row.status)} | ${escapeMd(row.entityId)} | ${escapeMd(row.objectId)} | ${escapeMd(row.reason)} |`);
    }
  }
  lines.push('', '> DRY-RUN ONLY: no delete/purge/physical removal was executed.', '');
  return `${lines.join('\n')}\n`;
}

function summaryMarkdownLines(summary) {
  const types = Object.keys(summary).sort();
  if (!types.length) return ['(none)'];
  return types.map((type) => {
    const statuses = Object.entries(summary[type])
      .sort(([a], [b]) => a.localeCompare(b))
      .map(([status, count]) => `${status}:${count}`)
      .join(', ');
    return `- ${type}: ${statuses}`;
  });
}

function summaryToObject(summary) {
  const result = {};
  for (const [type, statuses] of summary.entries()) {
    result[type] = { ...statuses };
  }
  return result;
}

function safeTimestamp(value) {
  return String(value).replace(/[:.]/g, '-');
}

function escapeMd(value) {
  return String(value ?? '').replace(/\|/g, '\\|').replace(/\r?\n/g, '<br>');
}

function parseSnapshotIdFromChildId(value) {
  const text = String(value || '');
  const index = text.indexOf('__');
  return index >= 0 ? text.slice(0, index) : '';
}

function parseAccountIdFromSnapshotId(value) {
  const text = String(value || '');
  const match = text.match(/^snapshot_(.+?)_(?:current|\d{10,}.*)$/);
  return match?.[1] || '';
}

function toArray(value) {
  return Array.isArray(value) ? value : [];
}