/**
 * 文档解析脚本
 *
 * @description 扫描 docs/to-parse 文件夹中的文档，调用 AI 服务解析，自动更新配置
 * @module scripts/parse-docs
 * @author Claude Code
 * @created 2026-02-13
 *
 * @usage
 * # 解析所有待处理文档
 * npm run parse:docs
 *
 * # 解析指定文档
 * npm run parse:docs -- --file=产品说明书.pdf
 *
 * # 查看待处理文档
 * npm run parse:docs -- --list
 */
import crypto from 'crypto'
import fs from 'fs'
import path from 'path'
import { PDFParse } from 'pdf-parse'
import mammoth from 'mammoth'
import Ajv from 'ajv'
import { spawn } from 'child_process'
import {
  checkMarkitdownAvailable,
  checkAIServiceConfigured,
  printConfigStatus,
  MARKITDOWN_CONFIG,
  AI_SERVICE_CONFIG
} from './parse-config.js'

// ========== 配置区 ==========

const DOCS_DIR = path.resolve(process.cwd(), 'docs/to-parse')
const CONFIG_FILE = path.resolve(process.cwd(), 'src/config/plan-templates.js')
const BACKUP_DIR = path.resolve(process.cwd(), 'docs/parsed-backup')

// 支持的文档格式
const SUPPORTED_EXTENSIONS = ['.pdf', '.doc', '.docx', '.txt', '.md']

const ajv = new Ajv({ allErrors: true, strict: false })
const parseConfigSchema = {
    type: 'object',
    required: ['product_name', 'product_type', 'currency', 'form_schema', 'submit_mapping'],
    properties: {
        product_name: { type: 'string', minLength: 1 },
        product_type: { type: 'string', enum: ['savings', 'life-insurance', 'critical-illness'] },
        currency: { type: 'string', minLength: 1 },
        form_schema: { type: 'object' },
        submit_mapping: { type: 'object' }
    },
    additionalProperties: true
}
const validateParsedConfigSchema = ajv.compile(parseConfigSchema)

// ========== 工具函数 ==========

/**
 * 确保目录存在
 */
function ensureDir(dirPath) {
  if (!fs.existsSync(dirPath)) {
    fs.mkdirSync(dirPath, { recursive: true })
    console.log(`📁 创建目录: ${dirPath}`)
  }
}

/**
 * 读取文件内容
 */
function readFile(filePath) {
  return fs.readFileSync(filePath, 'utf-8')
}

function getFileMeta(filePath, extraMeta = {}) {
  const stats = fs.existsSync(filePath) ? fs.statSync(filePath) : { size: 0 }
  return {
    file_name: path.basename(filePath),
    ext: path.extname(filePath).toLowerCase(),
    size: stats.size,
    ocr: {
      enabled: false,
      provider: null,
      reason: 'not_configured'
    },
    ...extraMeta
  }
}

function buildExtractResult(filePath, text, warnings = [], extraMeta = {}) {
  return {
    text,
    warnings,
    meta: getFileMeta(filePath, extraMeta)
  }
}

async function extractTextFromPdf(filePath) {
  const buffer = fs.readFileSync(filePath)
  const parser = new PDFParse({ data: buffer })
  let result
  try {
    result = await parser.getText()
  } finally {
    await parser.destroy()
  }
  return buildExtractResult(filePath, result?.text || '', [], {
    total_pages: result?.total || 0
  })
}

async function extractTextFromDocx(filePath) {
  const buffer = fs.readFileSync(filePath)
  const result = await mammoth.extractRawText({ buffer })
  const warnings = (result.messages || []).map(item => `${item.type || 'warning'}:${item.message}`)
  return buildExtractResult(filePath, result.value || '', warnings)
}

function extractTextFromDoc(filePath) {
  return buildExtractResult(filePath, '', ['暂不支持 .doc，请转换为 .docx'])
}

function extractTextFromPlainFile(filePath) {
  return buildExtractResult(filePath, readFile(filePath), [])
}

export async function extractDocumentText(filePath) {
  const ext = path.extname(filePath).toLowerCase()
  let result

  if (ext === '.pdf') {
    result = await extractTextFromPdf(filePath)
  } else if (ext === '.docx') {
    result = await extractTextFromDocx(filePath)
  } else if (ext === '.doc') {
    result = extractTextFromDoc(filePath)
  } else if (ext === '.txt' || ext === '.md') {
    result = extractTextFromPlainFile(filePath)
  } else {
    result = buildExtractResult(filePath, '', [`不支持的文件类型: ${ext}`])
  }

  if (!result.text || !result.text.trim()) {
    result.warnings.push('抽取文本为空，可能是扫描件')
    result.meta.ocr = {
      enabled: false,
      provider: null,
      reason: 'text_empty'
    }
  }

  return result
}

export function validateParsedConfig(config) {
    const valid = validateParsedConfigSchema(config)
    if (valid) {
        return { valid: true, errors: [] }
    }

    const errors = (validateParsedConfigSchema.errors || []).map(error => {
        if (error.keyword === 'required' && error.params?.missingProperty) {
            return `${error.instancePath || '/'} 缺少字段 ${error.params.missingProperty}`
        }
        if (error.message) {
            return `${error.instancePath || '/'} ${error.message}`.trim()
        }
        return `${error.instancePath || '/'} 校验失败`
    })

    return { valid: false, errors }
}

/**
 * 写入文件内容
 */
function writeFile(filePath, content) {
  fs.writeFileSync(filePath, content, 'utf-8')
}

/**
 * 获取所有待处理的文档
 */
function getDocsToParse() {
  if (!fs.existsSync(DOCS_DIR)) {
    console.log('📂 文档夹不存在:', DOCS_DIR)
    return []
  }

  const files = fs.readdirSync(DOCS_DIR)
  return files
    .filter(file => SUPPORTED_EXTENSIONS.includes(path.extname(file).toLowerCase()))
    .filter(file => file !== 'README.md')
    .map(file => ({
      name: file,
      fullPath: path.join(DOCS_DIR, file),
      ext: path.extname(file).toLowerCase(),
      size: fs.statSync(path.join(DOCS_DIR, file)).size
    }))
}

/**
 * 生成 form_sn
 */
export function generateFormSn(config) {
    if (config?.form_sn) {
        return config.form_sn
    }

    const product_type = config?.product_type || 'product'
    const raw_name = (config?.product_name || '').trim()
    const name_slug = raw_name
        .toLowerCase()
        .replace(/[^a-z0-9]+/g, '-')
        .replace(/^-+|-+$/g, '')
    const base_value = `${product_type}|${name_slug || 'product'}|${raw_name}`
    const hash = crypto.createHash('sha1').update(base_value).digest('hex').slice(0, 8)

    return `${product_type}-${name_slug || 'product'}-${hash}`
}

/**
 * 生成配置代码
 */
export function generateConfigCode(config) {
    const formSn = generateFormSn(config)
    const isSavings = config.is_savings || config.product_type === 'savings'
    const productType = config.product_type || 'life-insurance'
    const componentName = isSavings
        ? 'SavingsTemplate'
        : (productType === 'critical-illness' ? 'CriticalIllnessTemplate' : 'LifeInsuranceTemplate')
    const { form_schema_ref, submit_mapping_ref } = resolveSchemaRefs(config)
    const form_schema_code = buildSchemaCode(config.form_schema, form_schema_ref)
    const submit_mapping_code = buildSchemaCode(config.submit_mapping, submit_mapping_ref)

    let code = "  /**\n"
    code += "   * " + config.product_name + "\n"
    code += "   * @added " + new Date().toISOString() + "\n"
    code += "   * @source docs/to-parse/" + config.source_file + "\n"
    code += "   */\n"
    code += "  '" + formSn + "': {\n"
    code += "    name: '" + config.product_name + "',\n"
    code += "    component: '" + componentName + "',\n"
    if (isSavings) {
        code += "    category: 'savings',\n"
    }
    code += "    config: {\n"

    if (isSavings) {
        code += "      currency: '" + config.currency + "',\n"
        code += "      payment_periods: " + JSON.stringify(config.payment_periods || []) + ",\n"
        code += "      age_range: { min: " + (config.age_range?.min || 0) + ", max: " + (config.age_range?.max || 75) + " },\n"
        code += "      insurance_period: '" + (config.insurance_period || '终身') + "',\n"
        code += "      withdrawal_plan: {\n"
        code += "        enabled: true,\n"
        code += "        currencies: ['HKD', 'USD', 'CNY'],\n"
        code += "        default_currency: '" + config.currency + "',\n"
        code += "        withdrawal_modes: " + JSON.stringify(config.withdrawal_modes || []) + ",\n"
        code += "        withdrawal_periods: " + JSON.stringify(config.withdrawal_periods || []) + "\n"
        code += "      },\n"
        code += "      form_schema: " + form_schema_code + ",\n"
        code += "      submit_mapping: " + submit_mapping_code + "\n"
    } else {
        code += "      currency: '" + config.currency + "',\n"
        code += "      payment_periods: " + JSON.stringify(config.payment_periods || []) + ",\n"
        code += "      age_range: { min: " + (config.age_range?.min || 0) + ", max: " + (config.age_range?.max || 75) + " },\n"
        code += "      insurance_period: '" + (config.insurance_period || '终身') + "',\n"
        code += "      form_schema: " + form_schema_code + ",\n"
        code += "      submit_mapping: " + submit_mapping_code + "\n"
    }

    code += "    }\n"
    code += "  }\n\n"

    return { formSn, code }
}

function resolveSchemaRefs(config) {
    const isSavings = config?.is_savings || config?.product_type === 'savings'
    if (isSavings) {
        return {
            form_schema_ref: 'savingsFormSchema',
            submit_mapping_ref: 'savingsSubmitMapping'
        }
    }
    return {
        form_schema_ref: 'protectionFormSchema',
        submit_mapping_ref: 'baseSubmitMapping'
    }
}

function buildSchemaCode(value, fallbackRef) {
    if (!value || isEmptyObject(value)) {
        return fallbackRef
    }
    if (value && typeof value === 'object' && !Array.isArray(value)) {
        const baseFields = value.base_fields
        const withdrawalFields = value.withdrawal_fields
        const resetMap = value.reset_map
        const baseFieldsEmpty = Array.isArray(baseFields) && baseFields.length === 0
        const withdrawalFieldsEmpty = !Array.isArray(withdrawalFields) || withdrawalFields.length === 0
        const resetMapEmpty = !resetMap || (typeof resetMap === 'object' && !Array.isArray(resetMap) && Object.keys(resetMap).length === 0)
        if (baseFieldsEmpty && withdrawalFieldsEmpty && resetMapEmpty) {
            return fallbackRef
        }
    }
    if (typeof value === 'string') {
        return value
    }
    return JSON.stringify(value, null, 2).replace(/\n/g, '\n      ')
}

function isEmptyObject(value) {
    if (!value || typeof value !== 'object' || Array.isArray(value)) {
        return false
    }
    return Object.keys(value).length === 0
}

function formatSize(size) {
    if (size < 1024) return `${size} B`
    if (size < 1024 * 1024) return `${(size / 1024).toFixed(1)} KB`
    if (size < 1024 * 1024 * 1024) return `${(size / (1024 * 1024)).toFixed(1)} MB`
    return `${(size / (1024 * 1024 * 1024)).toFixed(1)} GB`
}

/**
 * 调用 markitdown 服务解析文档
 *
 * @description 使用 markitdown CLI 将 PDF/DOCX 转换为 Markdown/文本
 * @param {string} docPath - 文档路径
 * @returns {Promise<{text: string, warnings: string[]}>} 解析结果
 */
async function parseDocumentWithMarkitdown(docPath) {
  const ext = path.extname(docPath).toLowerCase()

  // MD 和 TXT 文件直接读取，不需要 markitdown
  if (ext === '.md' || ext === '.txt') {
    console.log(`📄 直接读取文本文件: ${path.basename(docPath)}`)
    return buildExtractResult(docPath, fs.readFileSync(docPath, 'utf-8'), [])
  }

  console.log(`\n📄 使用 markitdown 解析: ${path.basename(docPath)}`)

  try {
    if (MARKITDOWN_CONFIG.type === 'cli') {
      // .docx 文件使用 mammoth 库（markitdown 兼容性问题）
      if (ext === '.docx') {
        console.log('⚠️  .docx 文件使用 mammoth 库解析（避免 markitdown 兼容性问题）')
        return await extractTextFromDocx(docPath)
      }
      // 只对 PDF 使用 markitdown
      if (ext === '.pdf') {
        return await parseWithMarkitdownCLI(docPath)
      } else {
        console.log(`⚠️  文件类型 ${ext} 不支持 markitdown，使用本地库解析`)
        return await extractDocumentText(docPath)
      }
    }

    // 其他类型暂未实现，fallback 到本地库
    console.log('⚚️  markitdown 未启用，使用本地库解析')
    return await extractDocumentText(docPath)
  } catch (error) {
    console.error(`❌ markitdown 解析失败 (${docPath}):`, error.message)
    // fallback 到本地库
    console.log('🔄 回退到本地库解析...')
    return await extractDocumentText(docPath)
  }
}

/**
 * 使用 markitdown CLI 解析文档
 *
 * @description 使用 spawn 调用 markitdown CLI 工具（从 stdin 读取）
 * @param {string} docPath - 文档路径
 * @returns {Promise<{text: string, warnings: string[]}>} 解析结果
 */
async function parseWithMarkitdownCLI(docPath) {
  const tmpDir = path.resolve(process.cwd(), 'docs/tmp')
  ensureDir(tmpDir)

  const outputPath = path.join(tmpDir, path.basename(docPath, path.extname(docPath)) + '.md')
  const timeout = MARKITDOWN_CONFIG.cli.timeout || 30000

  console.log(`   命令: cat "${docPath}" | markitdown > "${outputPath}"`)

  return new Promise((resolve, reject) => {
    const timer = setTimeout(() => {
      spawn.kill(0, 'SIGTERM') // 尝试优雅终止
      reject(new Error('markitdown 执行超时'))
    }, timeout)

    // 使用 cat 读取文件并通过管道传递给 markitdown
    const cat = spawn('cat', [docPath])
    const markitdown = spawn('markitdown', [], {
      stdio: ['ignore', 'pipe', 'pipe']
    })

    let stdout = ''
    let stderr = ''

    markitdown.stdout.on('data', (data) => { stdout += data })
    markitdown.stderr.on('data', (data) => { stderr += data })

    markitdown.on('close', (code) => {
      clearTimeout(timer)

      if (code !== 0) {
        reject(new Error(`markitdown 退出码: ${code}\n${stderr}`))
        return
      }

      // 写入输出文件
      try {
        fs.writeFileSync(outputPath, stdout, 'utf-8')

        console.log(`✅ markitdown 解析成功，提取 ${stdout.length} 字符`)
        resolve({ text: stdout, warnings: [] })
      } catch (writeError) {
        reject(writeError)
      }
    })

    markitdown.on('error', (error) => {
      clearTimeout(timer)
      reject(error)
    })

    cat.on('error', (error) => {
      clearTimeout(timer)
      reject(error)
    })

    // 将 cat 的输出连接到 markitdown 的输入
    cat.stdout.pipe(markitdown.stdin)
  })
}

/**
 * AI 解析提示词模板
 *
 * @description 用于指导 AI 从文档内容中提取产品配置
 */
const AI_PARSE_PROMPT = `你是一个保险产品配置专家。请从以下文档内容中提取产品配置信息。

请按以下 JSON 格式返回配置：
{
  "product_name": "产品名称",
  "product_type": "产品类型 (savings/life-insurance/critical-illness)",
  "currency": "币种 (USD/CNY/HKD)",
  "payment_periods": ["缴费年期1", "缴费年期2"],
  "age_range": { "min": 最小年龄, "max": 最大年龄 },
  "insurance_period": "保险期间",
  "is_savings": true/false (是否为储蓄型产品),
  "withdrawal_modes": ["提取模式1", "提取模式2"],
  "withdrawal_periods": ["提取期1", "提取期2"]
}

文档内容：
{CONTENT}

请只返回 JSON，不要包含其他内容。`

/**
 * 调用 AI 服务解析文档
 *
 * @description 使用 markitdown + AI 智能解析文档并提取配置
 * @param {string} docPath - 文档路径
 * @returns {Promise<Object>} 解析后的配置对象
 */
async function parseDocumentWithAI(docPath) {
  console.log(`\n🤖 正在智能解析: ${path.basename(docPath)}`)

  try {
    // 步骤 1: 使用 markitdown 将文档转换为 Markdown/文本
    const parse_result = await parseDocumentWithMarkitdown(docPath)

    if (parse_result.warnings.length > 0) {
      parse_result.warnings.forEach(message => {
        console.log(`⚠️  解析警告: ${message}`)
      })
    }

    if (!parse_result.text || !parse_result.text.trim()) {
      console.error(`❌ 文档解析失败，文本为空 (${docPath})`)
      return null
    }

    const content = parse_result.text

    // 步骤 2: 调用 AI 服务从文档内容中提取配置
    // TODO(human): 集成 AI 服务（OpenAI/Anthropic）
    // 需要配置 API Key 和服务端点
    console.log('📝 AI 配置提取: 待集成 AI 服务')

    // 临时方案：生成基础配置（基于文件名和内容启发式推断）
    const fileName = path.basename(docPath, path.extname(docPath))
    const config = {
      product_name: fileName,
      product_type: inferProductType(fileName, content),
      currency: inferCurrency(content),
      payment_periods: ['整付', '3年', '5年'],
      age_range: { min: 0, max: 75 },
      insurance_period: '终身',
      is_savings: true,
      withdrawal_modes: ['年龄指定金额', '最高固定金额'],
      withdrawal_periods: ['1年', '3年', '5年', '10年'],
      form_schema: { base_fields: [], withdrawal_fields: [], reset_map: {} },
      submit_mapping: {}
    }

    console.log('✅ 解析成功 (启发式推断)')
    console.log(`   产品类型: ${config.product_type}`)
    console.log(`   币种: ${config.currency}`)
    return config
  } catch (error) {
    console.error(`❌ 解析失败 (${docPath}):`, error.message)
    return null
  }
}

/**
 * 启发式推断产品类型
 *
 * @description 从文件名和内容推断产品类型
 * @param {string} fileName - 文件名
 * @param {string} content - 文档内容
 * @returns {string} 产品类型
 */
function inferProductType(fileName, content) {
  const lowerName = fileName.toLowerCase()

  if (lowerName.includes('储蓄') || lowerName.includes('saving') || lowerName.includes('传承') || lowerName.includes('家传')) {
    return 'savings'
  }
  if (lowerName.includes('重疾') || lowerName.includes('critical') || lowerName.includes('守护')) {
    return 'critical-illness'
  }
  if (lowerName.includes('人寿') || lowerName.includes('life') || lowerName.includes('创富')) {
    return 'life-insurance'
  }

  // 从内容中推断
  const contentLower = content.toLowerCase()
  if (contentLower.includes('储蓄') || contentLower.includes('红利') || contentLower.includes('提取')) {
    return 'savings'
  }
  if (contentLower.includes('重疾') || contentLower.includes('早期严重疾病')) {
    return 'critical-illness'
  }
  if (contentLower.includes('寿险') || contentLower.includes('身故保障')) {
    return 'life-insurance'
  }

  // 默认为储蓄型
  return 'savings'
}

/**
 * 启发式推断币种
 *
 * @description 从文档内容推断币种
 * @param {string} content - 文档内容
 * @returns {string} 币种代码
 */
function inferCurrency(content) {
  // 统计各种币种符号的出现次数
  const usdCount = (content.match(/\$/g) || []).length
  const cnyCount = (content.match(/¥|人民币/g) || []).length
  const hkdCount = (content.match(/HK\$/g) || []).length

  if (usdCount > cnyCount && usdCount > hkdCount) return 'USD'
  if (hkdCount > usdCount && hkdCount > cnyCount) return 'HKD'
  if (cnyCount > usdCount && cnyCount > hkdCount) return 'CNY'

  // 默认美元
  return 'USD'
}

/**
 * 解析单个文档
 */
async function parseSingleFile(filePath) {
  const fileName = path.basename(filePath)
  console.log("\n" + "=".repeat(60))
  console.log("📄 处理文件: " + fileName)
  console.log("=".repeat(60))

  // 解析文档
  const config = await parseDocumentWithAI(filePath)

  if (!config) {
    console.log("⏭️  跳过文件: " + fileName + " (解析失败)")
    return { success: false, file: fileName, reason: 'parse_failed' }
  }

  const validation = validateParsedConfig(config)
  if (!validation.valid) {
    console.error("❌ 校验失败: " + fileName)
    validation.errors.forEach(message => {
      console.error(" - " + message)
    })
    return { success: false, file: fileName, reason: 'validation_failed', errors: validation.errors }
  }

  // 添加源文件信息
  config.source_file = fileName

  // 生成配置代码
  const { formSn, code } = generateConfigCode(config)

  console.log("\n📝 生成 form_sn: " + formSn)
  console.log("📋 生成配置代码:\n" + code)

  // ✨ 新增：生成待审核文件（不直接写入正式配置）
  const auditFile = await generateAuditFile(fileName, config, code)
  if (auditFile) {
    console.log("\n✅ 已生成待审核文件: " + auditFile)
    console.log("📋 请审核后手动移动到 src/config/plan-templates.js")
    return { success: true, formSn, code, file: fileName, config, auditFile }
  }

  return { success: true, formSn, code, file: fileName, config, auditFile }
}

/**
 * 生成待审核文件
 *
 * @description 生成人类可读的 markdown 审核文件
 * @param {string} fileName - 原始文件名
 * @param {Object} config - 解析的配置对象
 * @param {string} code - 生成的配置代码
 * @returns {Promise<string|null>} 审核文件路径
 */
async function generateAuditFile(fileName, config, code) {
  const AUDIT_DIR = path.resolve(process.cwd(), 'docs/parse-audit/pending')
  ensureDir(AUDIT_DIR)

  const date = new Date().toISOString().split('T')[0]
  const auditFileName = `${date}-${fileName.replace(/\.[^/.]+$/, '')}.md`
  const auditFilePath = path.join(AUDIT_DIR, auditFileName)

  const content = `# ${config.product_name || fileName}

## 解析信息

- **原始文件**: ${fileName}
- **解析时间**: ${new Date().toLocaleString('zh-CN')}
- **数据来源**: docs/to-parse/${fileName}

---

## 配置预览

\`\`\`javascript
const config = \\${JSON.stringify(config, null, 2)}
\`\`

---

## 审核检查清单

- [ ] 产品名称是否正确
- [ ] 产品类型是否正确（${config.product_type || '未知'}）
- [ ] 币种是否正确（${config.currency || '未知'}）
- [ ] age_range 是否合理（${config.age_range?.min || 0} - ${config.age_range?.max || 75}岁）
- [ ] form_schema 字段是否完整
- [ ] submit_mapping 逻辑是否正确

---

## 下一步

1. 审核以上配置是否正确
2. 确核通过后，执行以下操作：

\`\`\`bash
# 1. 移动到 approved 目录
mv docs/parse-audit/pending/${auditFileName} docs/parse-audit/approved/

# 2. 手动添加配置到 src/config/plan-templates.js
# 3. 运行 pnpm lint 检
\`\`

---

## 审核状态

- [ ] 待审核
- [ ] 已通过
- [ ] 已拒绝

## 审核意见

<!-- 审核时请填写 -->

**生成时间**: ${new Date().toLocaleString('zh-CN')}
`

<!-- 审核通过后，请执行以下步骤：-->
1. 将此文件移动到 \`docs/parse-audit/approved/\`
2. 手动将配置添加到 \`src/config/plan-templates.js\`
3. 运行 \`pnpm lint\` �查
`

---

**注意**:
- 请仔细核对配置的每个字段
- 确认产品类型和币种是否符合业务需求
- �查 form_schema 中的字段定义是否完整
`

`

  try {
    fs.writeFileSync(auditFilePath, content, 'utf-8')
    return auditFilePath
  } catch (error) {
    console.error(\`❌ 写入审核文件失败: \${error.message}`)
    return null
  }
}

/**
 * 生成待审核文件
 *
 * @description 生成人类可读的 markdown 审核文件，保存到 docs/parse-audit/pending/
 * @param {string} fileName - 原始文件名
 * @param {Object} config - 解析的配置对象
 * @param {string} code - 生成的配置代码
 * @returns {Promise<string|null>} 审核文件路径
 */
async function generateAuditFile(fileName, config, code) {
  const AUDIT_DIR = path.resolve(process.cwd(), 'docs/parse-audit/pending')
  ensureDir(AUDIT_DIR)

  const date = new Date().toISOString().split('T')[0]
  const auditFileName = `${date}-${fileName.replace(/\.[^/.]+$/, '')}.md`
  const auditFilePath = path.join(AUDIT_DIR, auditFileName)

  const content = `# ${config.product_name || fileName}

## 解析信息

- **原始文件**: ${fileName}
- **解析时间**: ${new Date().toLocaleString('zh-CN')}
- **数据来源**: docs/to-parse/${fileName}

---

## 配置预览

\`\`\`javascript
{
  "product_name": "${config.product_name || ''}",
  "product_type": "${config.product_type || ''}",
  "currency": "${config.currency || ''}",
${Object.entries(config).filter(([k]) =>
!['source_file', 'form_schema', 'submit_mapping'].includes(k)
).map(([k, v]) =>
  `  "${k}": ${JSON.stringify(v, null, 2)}`
).join(',\n  ')}
\`\`\`

---

## 审核检查清单

- [ ] 产品名称是否正确
- [ ] 产品类型是否正确
- [ ] 币种是否正确
- [ ] age_range 是否合理
- [ ] payment_periods / withdrawal_periods 是否完整
- [ ] form_schema 字段是否完整
- [ ] 提取逻辑是否符合需求

---

## 审核状态

- [ ] 待审核
- [ ] 已通过
- [ ] 已拒绝

## 审核意见

\`\`\`

<!-- 审核通过后，请执行以下步骤：

1. 将此文件移动到 docs/parse-audit/approved/
2. 手动将配置添加到 src/config/plan-templates.js
3. 提交变更

-->

  try {
    fs.writeFileSync(auditFilePath, content, 'utf-8')
    return auditFilePath
  } catch (error) {
    console.error(`❌ 写入审核文件失败: ${error.message}`)
    return null
  }
}

/**
 * 更新配置文件
 * @description 使用简单的字符串搜索找到正确的插入位置
 */
export function updateConfigContent(existingContent, newConfigs) {
    const range = getPlanTemplatesRange(existingContent)
    if (!range) {
        return null
    }

    const insertContent = newConfigs.map((item, index) => {
        const code = item.code.trimEnd()
        return index === newConfigs.length - 1 ? code : code + ','
    }).join('\n\n')

    const before = existingContent.substring(0, range.endIndex)
    const after = existingContent.substring(range.endIndex)
    const beforeTrimmed = before.replace(/\s+$/, '')
    const needsComma = !beforeTrimmed.endsWith(',')
    const comma = needsComma ? ',' : ''

    return `${beforeTrimmed}${comma}\n\n${insertContent}${after}`
}

function getPlanTemplatesRange(content) {
    const startToken = 'export const PLAN_TEMPLATES = {'
    const startIndex = content.indexOf(startToken)
    if (startIndex === -1) {
        return null
    }

    const openIndex = startIndex + startToken.length - 1
    let depth = 1
    let inSingle = false
    let inDouble = false
    let inTemplate = false
    let escape = false

    for (let i = openIndex + 1; i < content.length; i += 1) {
        const ch = content[i]
        if (escape) {
            escape = false
            continue
        }
        if (ch === '\\') {
            if (inSingle || inDouble || inTemplate) {
                escape = true
            }
            continue
        }
        if (inSingle) {
            if (ch === "'") {
                inSingle = false
            }
            continue
        }
        if (inDouble) {
            if (ch === '"') {
                inDouble = false
            }
            continue
        }
        if (inTemplate) {
            if (ch === '`') {
                inTemplate = false
            }
            continue
        }
        if (ch === "'") {
            inSingle = true
            continue
        }
        if (ch === '"') {
            inDouble = true
            continue
        }
        if (ch === '`') {
            inTemplate = true
            continue
        }
        if (ch === '{') {
            depth += 1
            continue
        }
        if (ch === '}') {
            depth -= 1
            if (depth === 0) {
                return { startIndex, endIndex: i }
            }
        }
    }

    return null
}

function readQuotedKey(content, startIndex) {
    const quote = content[startIndex]
    let value = ''
    let escape = false
    for (let i = startIndex + 1; i < content.length; i += 1) {
        const ch = content[i]
        if (escape) {
            value += ch
            escape = false
            continue
        }
        if (ch === '\\') {
            escape = true
            continue
        }
        if (ch === quote) {
            return { value, endIndex: i }
        }
        value += ch
    }
    return null
}

function extractPlanTemplateKeys(content) {
    const range = getPlanTemplatesRange(content)
    if (!range) {
        return []
    }
    const block = content.slice(range.startIndex, range.endIndex + 1)
    const blockStart = block.indexOf('{') + 1
    const blockContent = block.slice(blockStart, block.length - 1)

    const keys = []
    let depth = 0
    let inSingle = false
    let inDouble = false
    let inTemplate = false
    let escape = false

    for (let i = 0; i < blockContent.length; i += 1) {
        const ch = blockContent[i]
        if (escape) {
            escape = false
            continue
        }
        if (ch === '\\') {
            if (inSingle || inDouble || inTemplate) {
                escape = true
            }
            continue
        }
        if (inSingle) {
            if (ch === "'") {
                inSingle = false
            }
            continue
        }
        if (inDouble) {
            if (ch === '"') {
                inDouble = false
            }
            continue
        }
        if (inTemplate) {
            if (ch === '`') {
                inTemplate = false
            }
            continue
        }
        if (ch === "'") {
            inSingle = true
            if (depth === 0) {
                const keyResult = readQuotedKey(blockContent, i)
                if (keyResult) {
                    const nextIndex = keyResult.endIndex + 1
                    const rest = blockContent.slice(nextIndex)
                    const match = rest.match(/^\s*:/)
                    if (match) {
                        keys.push(keyResult.value)
                    }
                    i = keyResult.endIndex
                    inSingle = false
                }
            }
            continue
        }
        if (ch === '"') {
            inDouble = true
            if (depth === 0) {
                const keyResult = readQuotedKey(blockContent, i)
                if (keyResult) {
                    const nextIndex = keyResult.endIndex + 1
                    const rest = blockContent.slice(nextIndex)
                    const match = rest.match(/^\s*:/)
                    if (match) {
                        keys.push(keyResult.value)
                    }
                    i = keyResult.endIndex
                    inDouble = false
                }
            }
            continue
        }
        if (ch === '`') {
            inTemplate = true
            continue
        }
        if (ch === '{') {
            depth += 1
            continue
        }
        if (ch === '}') {
            depth -= 1
        }
    }

    return keys
}

export function detectFormSnConflicts(existingContent, newConfigs) {
    const existingKeys = extractPlanTemplateKeys(existingContent)
    const existingSet = new Set(existingKeys)
    const conflicts = []
    newConfigs.forEach(item => {
        if (existingSet.has(item.formSn)) {
            conflicts.push(item.formSn)
        }
    })
    return conflicts
}

export function buildDryRunDiff(newConfigs) {
    const insertContent = newConfigs.map((item, index) => {
        const code = item.code.trimEnd()
        return index === newConfigs.length - 1 ? code : code + ','
    }).join('\n\n')
    const lines = insertContent.split('\n').map(line => `+ ${line}`)
    return ['--- plan-templates.js', '+++ plan-templates.js', ...lines].join('\n')
}

export function buildConfigUpdateResult(existingContent, newConfigs, options = {}) {
    const conflicts = detectFormSnConflicts(existingContent, newConfigs)
    if (conflicts.length > 0) {
        return { ok: false, conflicts, updatedContent: null, diff: null }
    }

    const updatedContent = updateConfigContent(existingContent, newConfigs)
    if (!updatedContent) {
        return { ok: false, conflicts: [], updatedContent: null, diff: null }
    }

    const diff = options.dry_run ? buildDryRunDiff(newConfigs) : null
    return { ok: true, conflicts: [], updatedContent, diff }
}

export function buildParseSummary(results, duration_ms) {
    const summary = {
        total: results.length,
        success: 0,
        failed: 0,
        duration_ms,
        success_list: [],
        failed_list: []
    }

    results.forEach(result => {
        if (result.success) {
            summary.success += 1
            summary.success_list.push({
                form_sn: result.formSn,
                product_name: result.config?.product_name,
                file: result.file
            })
        } else {
            summary.failed += 1
            summary.failed_list.push({
                file: result.file,
                reason: result.reason || 'unknown',
                errors: result.errors || []
            })
        }
    })

    return summary
}

function buildChangeSummary(update_result) {
    if (!update_result) {
        return null
    }
    const summary = {
        ok: update_result.ok,
        dry_run: update_result.dry_run || false,
        updated_count: update_result.updated_count || 0,
        form_sn_list: update_result.form_sn_list || [],
        conflicts: update_result.conflicts || [],
        reason: update_result.reason || null
    }

    if (update_result.diff) {
        summary.diff_preview = update_result.diff.split('\n').slice(0, 60).join('\n')
    }

    return summary
}

function buildAuditRecord(summary, options = {}, update_result = null, mode = 'batch') {
    return {
        at: new Date().toISOString(),
        mode,
        options: {
            dry_run: !!options.dry_run
        },
        summary,
        change_summary: buildChangeSummary(update_result)
    }
}

function writeBackupLog(record) {
    ensureDir(BACKUP_DIR)
    const logFile = path.join(BACKUP_DIR, 'backup-log.jsonl')
    const line = JSON.stringify(record)
    fs.appendFileSync(logFile, `${line}\n`, 'utf-8')
}

function writeAuditLog(record) {
    ensureDir(BACKUP_DIR)
    const logFile = path.join(BACKUP_DIR, 'parse-audit.jsonl')
    const line = JSON.stringify(record)
    fs.appendFileSync(logFile, `${line}\n`, 'utf-8')
}

function rollbackConfigFile(backupFile) {
    if (!backupFile || !fs.existsSync(backupFile)) {
        console.error("❌ 找不到备份文件: " + backupFile)
        return false
    }
    fs.copyFileSync(backupFile, CONFIG_FILE)
    writeBackupLog({
        action: 'rollback',
        backup_file: backupFile,
        target_file: CONFIG_FILE,
        at: new Date().toISOString()
    })
    console.log("✅ 已回滚配置文件: " + backupFile)
    return true
}

function updateConfigFile(newConfigs, options = {}) {
  console.log("\n" + "=".repeat(60))
  console.log("📝 更新配置文件: " + CONFIG_FILE)
  console.log("=".repeat(60))

  const existingContent = fs.readFileSync(CONFIG_FILE, 'utf-8')
  const updateResult = buildConfigUpdateResult(existingContent, newConfigs, options)
  if (!updateResult.ok && updateResult.conflicts.length > 0) {
    console.error("❌ 检测到重复 form_sn: " + updateResult.conflicts.join(', '))
    return { ok: false, reason: 'conflict', conflicts: updateResult.conflicts }
  }

  if (!updateResult.ok) {
    console.error('❌ 无法定位 PLAN_TEMPLATES 插入位置')
    return { ok: false, reason: 'insert_not_found', conflicts: [] }
  }

  if (options.dry_run) {
    console.log("\n🧪 dry-run 变更预览:\n" + updateResult.diff)
    return {
        ok: true,
        dry_run: true,
        diff: updateResult.diff,
        form_sn_list: newConfigs.map(item => item.formSn),
        updated_count: newConfigs.length
    }
  }

  let backupFile = null
  if (fs.existsSync(CONFIG_FILE)) {
    ensureDir(BACKUP_DIR)
    backupFile = path.join(BACKUP_DIR, `plan-templates.backup.${Date.now()}.js`)
    fs.copyFileSync(CONFIG_FILE, backupFile)
    console.log("💾 已备份到: " + backupFile)
  }

  writeFile(CONFIG_FILE, updateResult.updatedContent)
  writeBackupLog({
    action: 'update',
    backup_file: backupFile,
    target_file: CONFIG_FILE,
    form_sn_list: newConfigs.map(item => item.formSn),
    at: new Date().toISOString()
  })
  console.log("✅ 已更新配置文件，新增 " + newConfigs.length + " 个产品")
  return {
      ok: true,
      dry_run: false,
      backup_file: backupFile,
      form_sn_list: newConfigs.map(item => item.formSn),
      updated_count: newConfigs.length
  }
}

/**
 * 处理所有文档
 */
async function parseAllDocs(docs, options = {}) {
  if (docs.length === 0) {
    console.log('📭 没有待处理的文档')
    return
  }

  const start_time = Date.now()
  console.log("\n" + "=".repeat(60))
  console.log("📚 发现 " + docs.length + " 个待处理文档")
  console.log("=".repeat(60))

  const results = []
  const successResults = []

  for (const doc of docs) {
    const result = await parseSingleFile(doc.fullPath)
    results.push(result)
    if (result.success) {
      successResults.push(result)
    }
  }

  // 汇总
  console.log("\n" + "=".repeat(60))
  console.log("📊 解析结果汇总")
  console.log("=".repeat(60))
  console.log("总计: " + docs.length + " 个文档")
  console.log("成功: " + successResults.length + " 个")
  console.log("失败: " + (results.length - successResults.length) + " 个")
  const summary = buildParseSummary(results, Date.now() - start_time)
  console.log("耗时: " + summary.duration_ms + "ms")

  // 显示成功的产品
  if (successResults.length > 0) {
    console.log("\n✅ 成功解析的产品:")
    successResults.forEach(r => {
      console.log("   - " + r.formSn + ": " + r.config.product_name)
    })
  }
  if (summary.failed_list.length > 0) {
    console.log("\n⚠️ 失败明细:")
    summary.failed_list.forEach(item => {
      console.log("   - " + item.file + " (" + item.reason + ")")
    })
  }

  // 更新配置文件
  let update_result = null
  if (successResults.length > 0) {
    update_result = updateConfigFile(successResults, options)
  } else {
    console.log("\n❌ 没有成功解析的文档，配置文件未更新")
  }
  const audit_record = buildAuditRecord(summary, options, update_result, 'batch')
  writeAuditLog(audit_record)
}

/**
 * CLI 入口
 */
async function main() {
  const args = process.argv.slice(2)
  const docs = getDocsToParse()

  // 检查模式
  const listMode = args.includes('--list')
  const fileMode = args.find(arg => arg.startsWith('--file='))
  const dryRunMode = args.includes('--dry-run')
  const rollbackMode = args.find(arg => arg.startsWith('--rollback='))
  const statusMode = args.includes('--status')

  // 检查解析器选择
  const parserModeArg = args.find(arg => arg.startsWith('--parser='))
  const parserMode = parserModeArg ? parserModeArg.split('=')[1].toLowerCase() : 'mammoth'

  console.log('\n🚀 文档解析工具 v2.0')
  console.log("   文档目录: " + DOCS_DIR)
  console.log("   配置文件: " + CONFIG_FILE)

  // 显示配置状态
  printConfigStatus()

  if (statusMode) {
    // 只显示状态，不执行解析
    return
  }

  if (rollbackMode) {
    const backupFile = rollbackMode.split('=')[1]
    rollbackConfigFile(backupFile)
  } else if (listMode) {
    // 列出模式
    const docs = getDocsToParse()
    console.log("\n📋 待处理文档列表:")
    if (docs.length === 0) {
      console.log('  (无文档)')
    } else {
      docs.forEach((doc, index) => {
        console.log(" " + (index + 1) + ". " + doc.name + " (" + formatSize(doc.size) + ")")
      })
    }
  } else if (fileMode) {
    // 单文件模式
    const fileName = fileMode.split('=')[1]
    // 更宽松的匹配：支持模糊匹配（移除特殊字符后比较）
    const normalize = (str) => str.toLowerCase().replace(/[\s\-_版]/g, '')
    const normalizedFileName = normalize(fileName)
    const targetDoc = docs.find(d => {
      const normalizedName = normalize(d.name)
      return normalizedName === normalizedFileName || normalizedName.includes(normalizedFileName)
    })

    if (targetDoc) {
      const start_time = Date.now()
      const result = await parseSingleFile(targetDoc.fullPath, parserMode)
      const summary = buildParseSummary([result], Date.now() - start_time)
      console.log("\n📊 解析结果汇总")
      console.log("总计: " + summary.total + " 个文档")
      console.log("成功: " + summary.success + " 个")
      console.log("失败: " + summary.failed + " 个")
      console.log("耗时: " + summary.duration_ms + "ms")
      if (result.success) {
        const update_result = updateConfigFile([result], { dry_run: dryRunMode })
        const audit_record = buildAuditRecord(summary, { dry_run: dryRunMode }, update_result, 'single')
        writeAuditLog(audit_record)
      } else {
        const audit_record = buildAuditRecord(summary, { dry_run: dryRunMode }, null, 'single')
        writeAuditLog(audit_record)
      }
    } else {
      console.log("❌ 找不到文件: " + fileName)
    }
  } else {
    // 批量处理模式
    await parseAllDocs(docs, { dry_run: dryRunMode })
  }

  console.log('\n✨ 处理完成!')
}

const isDirectRun = import.meta.url === `file://${process.argv[1]}`
if (isDirectRun) {
    main().catch(error => {
        console.error('❌ 执行失败:', error)
        process.exit(1)
    })
}