id-scanner-lib 1.3.3 → 1.5.0

package/src/{id-recognition → modules/id-card}/ocr-processor.ts

@@ -1,20 +1,29 @@
 /**
- * @file OCR处理模块
- * @description 提供身份证文字识别和信息提取功能
- * @module OCRProcessor
- * @version 1.3.2
+ * @file OCR处理器
+ * @description 提供身份证OCR识别功能
+ * @module modules/id-card/ocr-processor
  */
 
-import { createWorker } from "tesseract.js"
-import { IDCardInfo } from "../utils/types"
-import { ImageProcessor } from "../utils/image-processing"
-import { LRUCache, calculateImageFingerprint } from "../utils/performance"
+import { EventEmitter } from '../../core/event-emitter';
+import { Logger } from '../../core/logger';
+import { IDCardType, IDCardInfo } from './types';
+import {
+  createWorker,
+  Worker as TesseractWorker,
+  LoggerMessage,
+  WorkerOptions,
+} from "tesseract.js" // 导入 Worker 和 LoggerMessage 类型
+import { ImageProcessor } from "../../utils/image-processing"
+import { LRUCache, calculateImageFingerprint } from "../../utils/performance"
 import {
   isWorkerSupported,
   createWorker as createCustomWorker,
-} from "../utils/worker"
+} from "../../utils/worker" 
 import { processOCRInWorker, OCRProcessInput } from "./ocr-worker"
-import { Disposable } from "../utils/resource-manager"
+import { Disposable } from "../../utils/resource-manager"
+
+// 自定义日志函数类型，兼容字符串和LoggerMessage
+type LoggerFunction = ((message: string | LoggerMessage) => void) | undefined;
 
 /**
  * OCR处理器选项接口
@@ -29,7 +38,7 @@ export interface OCRProcessorOptions {
   onProgress?: (progress: number) => void
   enableCache?: boolean // 添加启用缓存选项
   cacheSize?: number // 添加缓存大小选项
-  logger?: (message: any) => void // 添加日志记录器选项
+  logger?: LoggerFunction // 修改为兼容字符串的日志函数类型
 }
 
 /**
@@ -54,7 +63,7 @@ export interface OCRProcessorOptions {
  * ```
  */
 export class OCRProcessor implements Disposable {
-  private worker: any = null
+  private worker: TesseractWorker | null = null // 使用导入的 TesseractWorker 类型
   private ocrWorker: ReturnType<
     typeof createCustomWorker<
       OCRProcessInput,
@@ -99,21 +108,26 @@ export class OCRProcessor implements Disposable {
       this.ocrWorker = createCustomWorker<
         OCRProcessInput,
         { idCardInfo: IDCardInfo; processingTime: number }
-      >(processOCRInWorker)
+      >(processOCRInWorker as any) // 使用类型断言解决类型不兼容问题
       this.initialized = true
       this.options.logger?.("OCR Worker 初始化完成")
     } else {
       // 使用主线程处理OCR
       this.worker = createWorker({
         logger: this.options.logger,
-      } as any)
+      })
 
       await this.worker.load()
       await this.worker.loadLanguage("chi_sim")
       await this.worker.initialize("chi_sim")
       await this.worker.setParameters({
         tessedit_char_whitelist:
-          "0123456789X-年月日一二三四五六七八九十零壹贰叁肆伍陆柒捌玖拾ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz民族汉族满族回族维吾尔族藏族苗族彝族壮族朝鲜族侗族瑶族白族土家族哈尼族哈萨克族傣族黎族傈僳族佤族高山族拉祜族水族东乡族钠西族景颇族柯尔克孜族士族达斡尔族仫佬族羌族布朗族撒拉族毛南族仡佬族锡伯族阿昌族普米族塔吉克族怒族乌孜别克族俄罗斯族鄂温克族德昂族保安族裕固族京族塔塔尔族独龙族鄂伦春族赫哲族门巴族珞巴族基诺族男女性别住址出生公民身份号码签发机关有效期",
+          "0123456789X年月日壹贰叁肆伍陆柒捌玖拾民族汉满回维吾尔藏苗彝壮朝鲜侗瑶白土家哈尼哈萨克傣黎傈僳佤高山拉祜水东乡纳西景颇柯尔克孜达斡尔仫佬羌布朗撒拉毛南仡佬锡伯阿昌普米塔吉克怒乌孜别克俄罗斯鄂温克德昂保安裕固京塔塔尔独龙鄂伦春赫哲门巴珞巴基诺男女住址出生公民身份号码签发机关有效期省市区县乡镇街道号楼单元室ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz", // 优化字符白名单，增加常见地址字符，移除部分不常用汉字
+      })
+      // 增加一些针对性的参数，提高识别率
+      await this.worker.setParameters({
+        tessedit_pageseg_mode: 7, // PSM_SINGLE_LINE，使用数字而不是字符串
+        preserve_interword_spaces: "1", // 保留单词间的空格
       })
 
       this.initialized = true
@@ -153,9 +167,11 @@ export class OCRProcessor implements Disposable {
 
     // 提高图像质量以获得更好的OCR结果
     const enhancedImage = ImageProcessor.batchProcess(downsampledImage, {
-      brightness: this.options.brightness || 15,
-      contrast: this.options.contrast || 25,
-      sharpen: true,
+      brightness:
+        this.options.brightness !== undefined ? this.options.brightness : 10, // 调整默认亮度
+      contrast:
+        this.options.contrast !== undefined ? this.options.contrast : 20, // 调整默认对比度
+      sharpen: true, // 默认启用锐化，通常对OCR有益
     })
 
     // 转换为base64供Tesseract处理
@@ -183,9 +199,8 @@ export class OCRProcessor implements Disposable {
         // 使用Worker线程处理
         const result = await this.ocrWorker.postMessage({
           imageBase64: base64Image,
-          tessWorkerOptions: {
-            logger: this.options.logger,
-          },
+          // 不传递函数对象，避免DataCloneError
+          tessWorkerOptions: {},
         })
 
         idCardInfo = result.idCardInfo
@@ -199,7 +214,14 @@ export class OCRProcessor implements Disposable {
         // 转换ImageData为Canvas
         const canvas = ImageProcessor.imageDataToCanvas(enhancedImage)
 
-        const { data } = await this.worker.recognize(canvas)
+        // 确保worker已初始化
+        if (!this.worker) {
+          throw new Error("OCR引擎未初始化");
+        }
+
+        const { data } = (await this.worker.recognize(canvas)) as {
+          data: { text: string }
+        }
 
         // 解析身份证信息
         idCardInfo = this.parseIDCardText(data.text)
@@ -218,7 +240,16 @@ export class OCRProcessor implements Disposable {
 
       return idCardInfo
     } catch (error) {
-      this.options.logger?.(`OCR识别错误: ${error}`)
+      // 改进错误处理
+      const errorMessage = error instanceof Error 
+        ? error.message 
+        : typeof error === 'object' 
+          ? JSON.stringify(error) 
+          : String(error);
+      
+      this.options.logger?.(`OCR识别错误: ${errorMessage}`);
+      
+      // 返回空对象，避免完全失败
       return {} as IDCardInfo
     }
   }
@@ -239,24 +270,26 @@ export class OCRProcessor implements Disposable {
    */
   private formatDateString(dateStr: string): string {
     // 先尝试提取年月日
-    const dateMatch = dateStr.match(/(\d{4})[-\.\u5e74\s]*(\d{1,2})[-\.\u6708\s]*(\d{1,2})[日]*/);
+    const dateMatch = dateStr.match(
+      /(\d{4})[-\.\u5e74\s]*(\d{1,2})[-\.\u6708\s]*(\d{1,2})[日]*/
+    )
     if (dateMatch) {
-      const year = dateMatch[1];
-      const month = dateMatch[2].padStart(2, '0');
-      const day = dateMatch[3].padStart(2, '0');
-      return `${year}-${month}-${day}`;
+      const year = dateMatch[1]
+      const month = dateMatch[2].padStart(2, "0")
+      const day = dateMatch[3].padStart(2, "0")
+      return `${year}-${month}-${day}`
     }
-    
+
     // 如果是纯数字格式如 20220101
     if (/^\d{8}$/.test(dateStr)) {
-      const year = dateStr.substring(0, 4);
-      const month = dateStr.substring(4, 6);
-      const day = dateStr.substring(6, 8);
-      return `${year}-${month}-${day}`;
+      const year = dateStr.substring(0, 4)
+      const month = dateStr.substring(4, 6)
+      const day = dateStr.substring(6, 8)
+      return `${year}-${month}-${day}`
     }
-    
+
     // 如果无法格式化，返回原始字符串
-    return dateStr;
+    return dateStr
   }
 
   /**
@@ -267,32 +300,32 @@ export class OCRProcessor implements Disposable {
   private validateIDNumber(idNumber: string): boolean {
     // 基本验证，校验位有效性和长度
     if (!idNumber || idNumber.length !== 18) {
-      return false;
+      return false
     }
-    
+
     // 检查格式，前17位必须为数字，最后一位可以是数字或'X'
-    const pattern = /^\d{17}[\dX]$/;
+    const pattern = /^\d{17}[\dX]$/
     if (!pattern.test(idNumber)) {
-      return false;
+      return false
     }
-    
+
     // 检查日期部分
-    const year = parseInt(idNumber.substr(6, 4));
-    const month = parseInt(idNumber.substr(10, 2));
-    const day = parseInt(idNumber.substr(12, 2));
-    
+    const year = parseInt(idNumber.substr(6, 4))
+    const month = parseInt(idNumber.substr(10, 2))
+    const day = parseInt(idNumber.substr(12, 2))
+
     if (month < 1 || month > 12 || day < 1 || day > 31) {
-      return false;
+      return false
     }
-    
+
     // 更详细的检查可以添加校验位的验证等逻辑...
-    
-    return true;
+
+    return true
   }
-  
+
   private parseIDCardText(text: string): IDCardInfo {
     const info: IDCardInfo = {}
-    
+
     // 预处理文本，清除多余空白
     const processedText = text.replace(/\s+/g, " ").trim()
 
@@ -304,18 +337,18 @@ export class OCRProcessor implements Disposable {
     const idNumberRegex = /(\d{17}[\dX])/
     // 2. 带前缀的模式
     const idNumberWithPrefixRegex = /公民身份号码[\s\:]*(\d{17}[\dX])/
-    
+
     // 尝试所有模式
     let idNumber = null
     const basicMatch = processedText.match(idNumberRegex)
     const prefixMatch = processedText.match(idNumberWithPrefixRegex)
-    
+
     if (prefixMatch && prefixMatch[1]) {
-      idNumber = prefixMatch[1]  // 首选带前缀的匹配，因为最可靠
+      idNumber = prefixMatch[1] // 首选带前缀的匹配，因为最可靠
     } else if (basicMatch && basicMatch[1]) {
-      idNumber = basicMatch[1]   // 其次是常规匹配
+      idNumber = basicMatch[1] // 其次是常规匹配
     }
-    
+
     if (idNumber) {
       info.idNumber = idNumber
     }
@@ -324,14 +357,19 @@ export class OCRProcessor implements Disposable {
     // 1. 直接匹配姓名标签近的内容
     const nameWithLabelRegex = /姓名[\s\:]*([一-龥]{2,4})/
     const nameMatch = processedText.match(nameWithLabelRegex)
-    
+
     // 2. 分析行文本寻找姓名
     if (nameMatch && nameMatch[1]) {
       info.name = nameMatch[1].trim()
     } else {
       // 备用方案：查找短行且内容全是汉字
       for (const line of lines) {
-        if (line.length >= 2 && line.length <= 5 && /^[一-龥]+$/.test(line) && !/性别|民族|住址|公民|签发|有效/.test(line)) {
+        if (
+          line.length >= 2 &&
+          line.length <= 5 &&
+          /^[一-龥]+$/.test(line) &&
+          !/性别|民族|住址|公民|签发|有效/.test(line)
+        ) {
           info.name = line.trim()
           break
         }
@@ -340,17 +378,20 @@ export class OCRProcessor implements Disposable {
 
     // 解析性别和民族 - 多种模式匹配
     // 1. 标准格式匹配
-    const genderAndNationalityRegex = /性别[\s\:]*([男女])[\s ]*民族[\s\:]*([一-龥]+族)/
-    const genderNationalityMatch = processedText.match(genderAndNationalityRegex)
-    
+    const genderAndNationalityRegex =
+      /性别[\s\:]*([男女])[\s ]*民族[\s\:]*([一-龥]+族)/
+    const genderNationalityMatch = processedText.match(
+      genderAndNationalityRegex
+    )
+
     // 2. 只匹配性别
     const genderOnlyRegex = /性别[\s\:]*([男女])/
     const genderOnlyMatch = processedText.match(genderOnlyRegex)
-    
+
     // 3. 只匹配民族
     const nationalityOnlyRegex = /民族[\s\:]*([一-龥]+族)/
     const nationalityOnlyMatch = processedText.match(nationalityOnlyRegex)
-    
+
     if (genderNationalityMatch) {
       info.gender = genderNationalityMatch[1]
       info.nationality = genderNationalityMatch[2]
@@ -366,12 +407,14 @@ export class OCRProcessor implements Disposable {
     // 2. 美式日期格式：YYYY-MM-DD或YYYY/MM/DD
     const birthDateRegex2 = /出生[\s\:]*(\d{4})[-\/\.](\d{1,2})[-\/\.](\d{1,2})/
     // 3. 带前缀的格式
-    const birthDateRegex3 = /出生日期[\s\:]*(\d{4})[-\/\.\u5e74](\d{1,2})[-\/\.\u6708](\d{1,2})[日号]?/
-    
-    let birthDateMatch = processedText.match(birthDateRegex1) || 
-                        processedText.match(birthDateRegex2) ||
-                        processedText.match(birthDateRegex3)
-                       
+    const birthDateRegex3 =
+      /出生日期[\s\:]*(\d{4})[-\/\.\u5e74](\d{1,2})[-\/\.\u6708](\d{1,2})[日号]?/
+
+    let birthDateMatch =
+      processedText.match(birthDateRegex1) ||
+      processedText.match(birthDateRegex2) ||
+      processedText.match(birthDateRegex3)
+
     // 4. 从身份证号码中提取出生日期（如果上述方法失败）
     if (!birthDateMatch && info.idNumber && info.idNumber.length === 18) {
       const year = info.idNumber.substring(6, 10)
@@ -381,8 +424,8 @@ export class OCRProcessor implements Disposable {
     } else if (birthDateMatch) {
       // 确保月份和日期是两位数
       const year = birthDateMatch[1]
-      const month = birthDateMatch[2].padStart(2, '0')
-      const day = birthDateMatch[3].padStart(2, '0')
+      const month = birthDateMatch[2].padStart(2, "0")
+      const day = birthDateMatch[3].padStart(2, "0")
       info.birthDate = `${year}-${month}-${day}`
     }
 
@@ -391,53 +434,67 @@ export class OCRProcessor implements Disposable {
     const addressRegex1 = /住址[\s\:]*([\s\S]*?)(?=公民身份|出生|性别|签发)/
     // 2. 更宽松的模式
     const addressRegex2 = /住址[\s\:]*([一-龥a-zA-Z0-9\s\.\-]+)/
-    
-    const addressMatch = processedText.match(addressRegex1) || processedText.match(addressRegex2)
-    
+
+    const addressMatch =
+      processedText.match(addressRegex1) || processedText.match(addressRegex2)
+
     if (addressMatch && addressMatch[1]) {
       // 清理地址中的常见错误和多余空格
-      info.address = addressMatch[1].replace(/\s+/g, "").replace(/\n/g, "").trim()
-      
+      info.address = addressMatch[1]
+        .replace(/\s+/g, "")
+        .replace(/\n/g, "")
+        .trim()
+
       // 限制地址长度并判断地址合理性
       if (info.address.length > 70) {
         info.address = info.address.substring(0, 70)
       }
-      
+
       // 确保地址是合理的（不仅仅包含符号或数字）
       if (!/[一-龥]/.test(info.address)) {
-        info.address = ""; // 如果没有中文字符，可能不是有效地址
+        info.address = "" // 如果没有中文字符，可能不是有效地址
       }
     }
 
     // 解析签发机关
-    const authorityRegex1 = /签发机关[\s\:]*([\s\S]*?)(?=有效|公民|出生|\d{8}|$)/
+    const authorityRegex1 =
+      /签发机关[\s\:]*([\s\S]*?)(?=有效|公民|出生|\d{8}|$)/
     const authorityRegex2 = /签发机关[\s\:]*([一-龥\s]+)/
-    
-    const authorityMatch = processedText.match(authorityRegex1) || processedText.match(authorityRegex2)
-    
+
+    const authorityMatch =
+      processedText.match(authorityRegex1) ||
+      processedText.match(authorityRegex2)
+
     if (authorityMatch && authorityMatch[1]) {
-      info.issuingAuthority = authorityMatch[1].replace(/\s+/g, "").replace(/\n/g, "").trim()
+      info.issuingAuthority = authorityMatch[1]
+        .replace(/\s+/g, "")
+        .replace(/\n/g, "")
+        .trim()
     }
 
     // 解析有效期限 - 支持多种格式
     // 1. 常规格式：YYYY.MM.DD-YYYY.MM.DD
-    const validPeriodRegex1 = /有效期限[\s\:]*(\d{4}[-\.\u5e74\s]\d{1,2}[-\.\u6708\s]\d{1,2}[日\s]*)[-\s]*(至|-)[-\s]*(\d{4}[-\.\u5e74\s]\d{1,2}[-\.\u6708\s]\d{1,2}[日]*|[永久长期]*)/
+    const validPeriodRegex1 =
+      /有效期限[\s\:]*(\d{4}[-\.\u5e74\s]\d{1,2}[-\.\u6708\s]\d{1,2}[日\s]*)[-\s]*(至|-)[-\s]*(\d{4}[-\.\u5e74\s]\d{1,2}[-\.\u6708\s]\d{1,2}[日]*|[永久长期]*)/
     // 2. 简化格式：YYYYMMDD-YYYYMMDD
-    const validPeriodRegex2 = /有效期限[\s\:]*(\d{8})[-\s]*(至|-)[-\s]*(\d{8}|[永久长期]*)/
-    
-    const validPeriodMatch = processedText.match(validPeriodRegex1) || processedText.match(validPeriodRegex2)
-    
+    const validPeriodRegex2 =
+      /有效期限[\s\:]*(\d{8})[-\s]*(至|-)[-\s]*(\d{8}|[永久长期]*)/
+
+    const validPeriodMatch =
+      processedText.match(validPeriodRegex1) ||
+      processedText.match(validPeriodRegex2)
+
     if (validPeriodMatch) {
       // 格式化为统一的有效期限形式
       if (validPeriodMatch[1] && validPeriodMatch[3]) {
         const startDate = this.formatDateString(validPeriodMatch[1])
-        const endDate = /\d/.test(validPeriodMatch[3]) ? 
-                      this.formatDateString(validPeriodMatch[3]) : 
-                      '长期有效'
-        
+        const endDate = /\d/.test(validPeriodMatch[3])
+          ? this.formatDateString(validPeriodMatch[3])
+          : "长期有效"
+
         info.validPeriod = `${startDate}-${endDate}`
       } else {
-        info.validPeriod = validPeriodMatch[0].replace('有效期限', '').trim()
+        info.validPeriod = validPeriodMatch[0].replace("有效期限", "").trim()
       }
     }
 

package/src/modules/id-card/ocr-worker.ts

@@ -0,0 +1,259 @@
+/**
+ * @file OCR Worker
+ * @description OCR处理的Worker线程实现
+ * @module modules/id-card/ocr-worker
+ */
+
+import { IDCardInfo, IDCardType } from './types';
+import { LoggerMessage } from 'tesseract.js';
+
+/**
+ * OCR处理输入参数
+ */
+export interface OCRProcessInput {
+  /** 图像Base64数据 */
+  imageBase64: string;
+  /** Tesseract Worker选项 */
+  tessWorkerOptions?: {
+    /** 语言 */
+    language?: string;
+    /** 日志回调 */
+    logger?: (message: LoggerMessage) => void;
+  };
+}
+
+/**
+ * 在Worker中处理OCR识别
+ * @param input OCR处理输入参数
+ * @returns OCR处理结果
+ */
+export async function processOCRInWorker(
+  input: OCRProcessInput
+): Promise<{ idCardInfo: IDCardInfo; processingTime: number }> {
+  const startTime = performance.now();
+
+  try {
+    // 导入Tesseract.js
+    const { createWorker } = await import('tesseract.js');
+
+    // 创建Tesseract Worker
+    const worker = createWorker({
+      logger: input.tessWorkerOptions?.logger
+    });
+
+    // 初始化Worker
+    await worker.load();
+    await worker.loadLanguage('chi_sim');
+    await worker.initialize('chi_sim');
+
+    // 设置识别参数
+    await worker.setParameters({
+      tessedit_char_whitelist: '0123456789X年月日壹贰叁肆伍陆柒捌玖拾民族汉满回维吾尔藏苗彝壮朝鲜侗瑶白土家哈尼哈萨克傣黎傈僳佤高山拉祜水东乡纳西景颇柯尔克孜达斡尔仫佬羌布朗撒拉毛南仡佬锡伯阿昌普米塔吉克怒乌孜别克俄罗斯鄂温克德昂保安裕固京塔塔尔独龙鄂伦春赫哲门巴珞巴基诺男女住址出生公民身份号码签发机关有效期省市区县乡镇街道号楼单元室ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz',
+      tessedit_pageseg_mode: 7, // PSM_SINGLE_LINE
+      preserve_interword_spaces: '1'
+    });
+
+    // 识别图像
+    const { data } = await worker.recognize(input.imageBase64);
+
+    // 解析身份证信息
+    const idCardInfo = parseIDCardText(data.text);
+
+    // 释放Worker资源
+    await worker.terminate();
+
+    const processingTime = performance.now() - startTime;
+
+    return { idCardInfo, processingTime };
+  } catch (error) {
+    console.error('OCR处理错误:', error);
+    return {
+      idCardInfo: {} as IDCardInfo,
+      processingTime: performance.now() - startTime
+    };
+  }
+}
+
+/**
+ * 解析身份证文本
+ * @param text OCR识别的文本
+ * @returns 解析后的身份证信息
+ */
+function parseIDCardText(text: string): IDCardInfo {
+  const info: IDCardInfo = {};
+
+  // 预处理文本，清除多余空白
+  const processedText = text.replace(/\s+/g, ' ').trim();
+
+  // 解析身份证号码
+  const idNumberRegex = /(\d{17}[\dX])/;
+  const idNumberWithPrefixRegex = /公民身份号码[\s\:]*(\d{17}[\dX])/;
+
+  const basicMatch = processedText.match(idNumberRegex);
+  const prefixMatch = processedText.match(idNumberWithPrefixRegex);
+
+  if (prefixMatch && prefixMatch[1]) {
+    info.idNumber = prefixMatch[1];
+  } else if (basicMatch && basicMatch[1]) {
+    info.idNumber = basicMatch[1];
+  }
+
+  // 解析姓名
+  const nameWithLabelRegex = /姓名[\s\:]*([一-龥]{2,4})/;
+  const nameMatch = processedText.match(nameWithLabelRegex);
+
+  if (nameMatch && nameMatch[1]) {
+    info.name = nameMatch[1].trim();
+  } else {
+    // 备用方案：查找短行且内容全是汉字
+    const lines = processedText.split('\n').filter(line => line.trim());
+  for (const line of lines) {
+    if (
+        line.length >= 2 &&
+        line.length <= 5 &&
+        /^[一-龥]+$/.test(line) &&
+        !/性别|民族|住址|公民|签发|有效/.test(line)
+    ) {
+        info.name = line.trim();
+        break;
+      }
+    }
+  }
+
+  // 解析性别和民族
+  const genderAndNationalityRegex = /性别[\s\:]*([男女])[\s ]*民族[\s\:]*([一-龥]+族)/;
+  const genderOnlyRegex = /性别[\s\:]*([男女])/;
+  const nationalityOnlyRegex = /民族[\s\:]*([一-龥]+族)/;
+
+  const genderNationalityMatch = processedText.match(genderAndNationalityRegex);
+  const genderOnlyMatch = processedText.match(genderOnlyRegex);
+  const nationalityOnlyMatch = processedText.match(nationalityOnlyRegex);
+
+  if (genderNationalityMatch) {
+    info.gender = genderNationalityMatch[1];
+    info.ethnicity = genderNationalityMatch[2];
+  } else {
+    if (genderOnlyMatch) info.gender = genderOnlyMatch[1];
+    if (nationalityOnlyMatch) info.ethnicity = nationalityOnlyMatch[1];
+  }
+
+  // 根据内容判断身份证类型
+  if (processedText.includes('出生') || processedText.includes('公民身份号码')) {
+    info.type = IDCardType.FRONT; // 确保类型为枚举值而不是字符串
+  } else if (processedText.includes('签发机关') || processedText.includes('有效期')) {
+    info.type = IDCardType.BACK; // 确保类型为枚举值而不是字符串
+  }
+
+  // 解析出生日期
+  const birthDateRegex1 = /出生[\s\:]*(\d{4})年(\d{1,2})月(\d{1,2})[日号]/;
+  const birthDateRegex2 = /出生[\s\:]*(\d{4})[-\/\.](\d{1,2})[-\/\.](\d{1,2})/;
+  const birthDateRegex3 = /出生日期[\s\:]*(\d{4})[-\/\.\u5e74](\d{1,2})[-\/\.\u6708](\d{1,2})[日号]?/;
+
+  let birthDateMatch =
+    processedText.match(birthDateRegex1) ||
+    processedText.match(birthDateRegex2) ||
+    processedText.match(birthDateRegex3);
+
+  if (!birthDateMatch && info.idNumber && info.idNumber.length === 18) {
+    const year = info.idNumber.substring(6, 10);
+    const month = info.idNumber.substring(10, 12);
+    const day = info.idNumber.substring(12, 14);
+    info.birthDate = `${year}-${month}-${day}`;
+  } else if (birthDateMatch) {
+    const year = birthDateMatch[1];
+    const month = birthDateMatch[2].padStart(2, '0');
+    const day = birthDateMatch[3].padStart(2, '0');
+    info.birthDate = `${year}-${month}-${day}`;
+  }
+
+  // 解析地址
+  const addressRegex1 = /住址[\s\:]*([\s\S]*?)(?=公民身份|出生|性别|签发)/;
+  const addressRegex2 = /住址[\s\:]*([一-龥a-zA-Z0-9\s\.\-]+)/;
+
+  const addressMatch =
+    processedText.match(addressRegex1) || processedText.match(addressRegex2);
+
+  if (addressMatch && addressMatch[1]) {
+    info.address = addressMatch[1]
+      .replace(/\s+/g, '')
+      .replace(/\n/g, '')
+      .trim();
+
+    if (info.address.length > 70) {
+      info.address = info.address.substring(0, 70);
+    }
+
+    if (!/[一-龥]/.test(info.address)) {
+      info.address = '';
+    }
+  }
+
+  // 解析签发机关
+  const authorityRegex1 = /签发机关[\s\:]*([\s\S]*?)(?=有效|公民|出生|\d{8}|$)/;
+  const authorityRegex2 = /签发机关[\s\:]*([一-龥\s]+)/;
+
+  const authorityMatch =
+    processedText.match(authorityRegex1) ||
+    processedText.match(authorityRegex2);
+
+  if (authorityMatch && authorityMatch[1]) {
+    info.issueAuthority = authorityMatch[1]
+      .replace(/\s+/g, '')
+      .replace(/\n/g, '')
+      .trim();
+  }
+
+  // 解析有效期限
+  const validPeriodRegex1 = /有效期限[\s\:]*(\d{4}[-\.\u5e74\s]\d{1,2}[-\.\u6708\s]\d{1,2}[日\s]*)[-\s]*(至|-)[-\s]*(\d{4}[-\.\u5e74\s]\d{1,2}[-\.\u6708\s]\d{1,2}[日]*|[永久长期]*)/;
+  const validPeriodRegex2 = /有效期限[\s\:]*(\d{8})[-\s]*(至|-)[-\s]*(\d{8}|[永久长期]*)/;
+
+  const validPeriodMatch =
+    processedText.match(validPeriodRegex1) ||
+    processedText.match(validPeriodRegex2);
+
+  if (validPeriodMatch) {
+    if (validPeriodMatch[1] && validPeriodMatch[3]) {
+      const startDate = formatDateString(validPeriodMatch[1]);
+      const endDate = /\d/.test(validPeriodMatch[3])
+        ? formatDateString(validPeriodMatch[3])
+        : '长期有效';
+
+      info.validFrom = startDate;
+      info.validTo = endDate;
+      info.validPeriod = `${startDate}-${endDate}`;
+    } else {
+      info.validPeriod = validPeriodMatch[0].replace('有效期限', '').trim();
+    }
+  }
+
+  return info;
+}
+
+/**
+ * 格式化日期字符串
+ * @param dateStr 原始日期字符串
+ * @returns 格式化后的日期字符串
+ */
+function formatDateString(dateStr: string): string {
+  // 提取年月日
+  const dateMatch = dateStr.match(
+    /(\d{4})[-\.\u5e74\s]*(\d{1,2})[-\.\u6708\s]*(\d{1,2})[日]*/
+  );
+  if (dateMatch) {
+    const year = dateMatch[1];
+    const month = dateMatch[2].padStart(2, '0');
+    const day = dateMatch[3].padStart(2, '0');
+    return `${year}-${month}-${day}`;
+  }
+
+  // 纯数字格式如 20220101
+  if (/^\d{8}$/.test(dateStr)) {
+    const year = dateStr.substring(0, 4);
+    const month = dateStr.substring(4, 6);
+    const day = dateStr.substring(6, 8);
+    return `${year}-${month}-${day}`;
+  }
+
+  // 无法格式化，返回原始字符串
+  return dateStr;
+}