Arbitrate-Backend/ruoyi-system/src/main/java/com/ruoyi/wisdomarbitrate/utils/OCRUtils.java

package com.ruoyi.wisdomarbitrate.utils;

import cn.hutool.core.collection.CollectionUtil;
import cn.hutool.core.util.StrUtil;
import com.ruoyi.common.constant.Constants;
import com.ruoyi.common.exception.ServiceException;
import com.ruoyi.wisdomarbitrate.domain.FatchRule;
import com.tencentcloudapi.bsca.v20210811.models.LicenseSummary;
import com.tencentcloudapi.common.Credential;
import com.tencentcloudapi.common.exception.TencentCloudSDKException;
import com.tencentcloudapi.common.profile.ClientProfile;
import com.tencentcloudapi.common.profile.HttpProfile;
import com.tencentcloudapi.ocr.v20181119.OcrClient;
import com.tencentcloudapi.ocr.v20181119.models.*;
import org.json.JSONArray;
import org.json.JSONObject;

import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.util.*;
import java.util.stream.Collectors;

public class OCRUtils {
    //API的SecretId
    private static final String SECRET_ID = "AKIDeEf2A8uX1HSainvvnXAc3X9ZlhtyvkMp";
    //API的SecretKey
    private static final String SECRET_KEY = "QjphKo8zkHZigT8j9PVtFPJyfIvO3d6V";
    // 仲裁申请书识别字段
    private static final String[] applicantName = {"申请人", "统一社会信用代码", "负责人", "住所", "联系地址"
            , "委托代理人", "联系电话", "电子邮件", "被申请人", "居民身份证号码", "仲裁请求", "事实和理由"};
    // 贷款合同识别字段
    private static final String[] contractName = {
            "合同编号","甲方(贷款人)" ,"或委托代理人签字:","本合同的初始贷款年利率为","乙方确认有效的电子信箱地址为"};
    // 调解协议识别字段
    private static final String[] accordName = {"金融消费纠纷基本情况","经调解，双方自愿达成如下协议"};
    // 授权委托书识别字段
    private static final String[] powerAttorneyName = {"职务"};
    /**
     * pdf识别成文字
     * @param imageBase64
     * @param pageNumber
     * @param fatchRules 抓取规则
     * @return
     */
    public static String pdfIdentifyText(String imageBase64, Integer pageNumber, List<FatchRule> fatchRules) {
        StringBuilder respStr=new StringBuilder();
        try {
            // 实例化一个认证对象，入参需要传入腾讯云账户 SecretId 和 SecretKey，此处还需注意密钥对的保密
            // 代码泄露可能会导致 SecretId 和 SecretKey 泄露，并威胁账号下所有资源的安全性。以下代码示例仅供参考，建议采用更安全的方式来使用密钥，请参见：https://cloud.tencent.com/document/product/1278/85305
            // 密钥可前往官网控制台 https://console.cloud.tencent.com/cam/capi 进行获取
            Credential cred = new Credential(SECRET_ID, SECRET_KEY);
            // 实例化一个http选项，可选的，没有特殊需求可以跳过
            HttpProfile httpProfile = new HttpProfile();
            httpProfile.setEndpoint("ocr.tencentcloudapi.com");
            // 实例化一个client选项，可选的，没有特殊需求可以跳过
            ClientProfile clientProfile = new ClientProfile();
            clientProfile.setHttpProfile(httpProfile);
            // 实例化要请求产品的client对象,clientProfile是可选的
            OcrClient client = new OcrClient(cred, "ap-beijing", clientProfile);
            // 实例化一个请求对象,每个接口都会对应一个request对象
            GeneralAccurateOCRRequest req = new GeneralAccurateOCRRequest();
            req.setImageBase64(imageBase64);
            req.setIsPdf(true);
            req.setPdfPageNumber(pageNumber.longValue());
            // 返回的resp是一个SmartStructuralOCRV2Response的实例，与请求对象对应
            GeneralAccurateOCRResponse resp = client.GeneralAccurateOCR(req);
            // 输出json格式的字符串回包
            System.out.println(GeneralAccurateOCRResponse.toJsonString(resp));
            // 获取响应内容
            TextDetection[] textDetections = resp.getTextDetections();
            if (textDetections == null || textDetections.length == 0) {
                return respStr.toString();
            }
            for (TextDetection textDetection : textDetections) {
                respStr.append(textDetection.getDetectedText());
            }
        }catch (TencentCloudSDKException e){
            throw new ServiceException("ocr识别失败");
        }
        if(respStr.toString().endsWith(String.valueOf(pageNumber))){
            int lastIndexOf = respStr.toString().lastIndexOf(String.valueOf(pageNumber));
            return respStr.toString().substring(0,lastIndexOf);
        }
        return respStr.toString();



//
//            //解析数据
//            String s = GeneralAccurateOCRResponse.toJsonString(resp);
//            // 解析JSON数据
//            JSONObject jsonObject = new JSONObject(s);
//            JSONArray structuralList = jsonObject.getJSONArray("TextDetections");
//            // 遍历StructuralList中的Groups，获取Key对应的AutoName和Value对应的AutoConten
//            StringBuilder stringBuilder = new StringBuilder(); // 创建一个StringBuilder对象
//            for (int i = 0; i < structuralList.length(); i++) {
//                JSONArray groups = structuralList.getJSONObject(i).getJSONArray("Groups");
//                for (int j = 0; j < groups.length(); j++) {
//                    JSONArray lines = groups.getJSONObject(j).getJSONArray("Lines");
//                    for (int k = 0; k < lines.length(); k++) {
//                        JSONObject line = lines.getJSONObject(k);
//                        JSONObject key = line.getJSONObject("Key");
//                        JSONObject value = line.getJSONObject("Value");
//                        String autoName = key.getString("AutoName");
//                        String autoContent = value.getString("AutoContent");
//                        String text = autoName + Constants.PDFSTR + autoContent;
//                        if (stringBuilder.length() > 0) {
//                            stringBuilder.append(Constants.BR); // 在已有内容的情况下添加逗号分隔符
//                        }
//                        stringBuilder.append(text); // 拼接当前的字符串
//                    }
//                }
//            }
//            return stringBuilder.toString(); // 获取最终的拼接结果
//        } catch (TencentCloudSDKException e) {
//            System.out.println(e.toString());
//        }
    }

    /**
     * pdf识别成文字
     * @param imageBase64
     * @param pageNumber
     * @param type pdf类型
     * @return
     */
    public static String pdfIdentifyText1(String imageBase64, Integer pageNumber,String type) {
        try {
            // 实例化一个认证对象，入参需要传入腾讯云账户 SecretId 和 SecretKey，此处还需注意密钥对的保密
            // 代码泄露可能会导致 SecretId 和 SecretKey 泄露，并威胁账号下所有资源的安全性。以下代码示例仅供参考，建议采用更安全的方式来使用密钥，请参见：https://cloud.tencent.com/document/product/1278/85305
            // 密钥可前往官网控制台 https://console.cloud.tencent.com/cam/capi 进行获取
            Credential cred = new Credential(SECRET_ID, SECRET_KEY);
            // 实例化一个http选项，可选的，没有特殊需求可以跳过
            HttpProfile httpProfile = new HttpProfile();
            httpProfile.setEndpoint("ocr.tencentcloudapi.com");
            // 实例化一个client选项，可选的，没有特殊需求可以跳过
            ClientProfile clientProfile = new ClientProfile();
            clientProfile.setHttpProfile(httpProfile);
            // 实例化要请求产品的client对象,clientProfile是可选的
            OcrClient client = new OcrClient(cred, "ap-beijing", clientProfile);
            // 实例化一个请求对象,每个接口都会对应一个request对象
            SmartStructuralOCRV2Request req = new SmartStructuralOCRV2Request();
            req.setImageBase64(imageBase64);
            req.setIsPdf(true);
            req.setPdfPageNumber(pageNumber.longValue());
            if(type.contains("申请书")){
                req.setItemNames(applicantName);
            }else if(type.contains("调解协议")){
                req.setItemNames(accordName);
            }else if(type.contains("合同")){
                req.setItemNames(contractName);
            }else if(type.contains("授权委托书")){
                req.setItemNames(powerAttorneyName);
            }

            // 返回的resp是一个SmartStructuralOCRV2Response的实例，与请求对象对应
            SmartStructuralOCRV2Response resp = client.SmartStructuralOCRV2(req);
            // 输出json格式的字符串回包
            System.out.println(SmartStructuralOCRV2Response.toJsonString(resp));
            //解析数据
            String s = SmartStructuralOCRV2Response.toJsonString(resp);
            // 解析JSON数据
            JSONObject jsonObject = new JSONObject(s);
            JSONArray structuralList = jsonObject.getJSONArray("StructuralList");
            // 遍历StructuralList中的Groups，获取Key对应的AutoName和Value对应的AutoConten
            StringBuilder stringBuilder = new StringBuilder(); // 创建一个StringBuilder对象
            for (int i = 0; i < structuralList.length(); i++) {
                JSONArray groups = structuralList.getJSONObject(i).getJSONArray("Groups");
                for (int j = 0; j < groups.length(); j++) {
                    JSONArray lines = groups.getJSONObject(j).getJSONArray("Lines");
                    for (int k = 0; k < lines.length(); k++) {
                        JSONObject line = lines.getJSONObject(k);
                        JSONObject key = line.getJSONObject("Key");
                        JSONObject value = line.getJSONObject("Value");
                        String autoName = key.getString("AutoName");
                        String autoContent = value.getString("AutoContent");
                        String text = autoName + Constants.PDFSTR + autoContent;
                        if (stringBuilder.length() > 0) {
                            stringBuilder.append(Constants.BR); // 在已有内容的情况下添加逗号分隔符
                        }
                        stringBuilder.append(text); // 拼接当前的字符串
                    }
                }
            }
            return stringBuilder.toString(); // 获取最终的拼接结果
        } catch (TencentCloudSDKException e) {
            System.out.println(e.toString());
        }
        return null;
    }
    public static String pdfConvertBase64(String pathUrl){
        try {
            File file = new File(pathUrl);
            FileInputStream fileInputStream = new FileInputStream(file);
            byte[] fileBytes = new byte[(int) file.length()];
            fileInputStream.read(fileBytes);
            fileInputStream.close();
            // 将字节数组转换为Base64值
            return Base64.getEncoder().encodeToString(fileBytes);
        } catch (IOException e) {
            e.printStackTrace();
        }
        return null;
    }

    /**
     * 根据抓取规则获取内容
     * @param ocrText ocr识别的text
     * @param fatchRules 抓取规则
     * @return
     */
    public static void fatchRuleGetContent(String ocrText, List<FatchRule> fatchRules, Map<String, String> fatchMap) {

        if (CollectionUtil.isNotEmpty(fatchRules)) {

            for (FatchRule fatchRule : fatchRules) {
                if (StrUtil.isEmpty(fatchRule.getStartContent())) {
                    continue;
                }
                // 开始截取字符串 申请人：赵会
                //   String[] startContentSplit = ocrText.split(fatchRule.getStartContent());
                int startFirstIndex = ocrText.indexOf(fatchRule.getStartContent()) + fatchRule.getStartContent().length();
                if(startFirstIndex<0){
                    continue;
                }
                if (ocrText.length() >= startFirstIndex) {
                    ocrText = ocrText.substring(startFirstIndex);
                }

                if (StrUtil.isNotEmpty(fatchRule.getEndContent())) {
                    if(ocrText.indexOf(fatchRule.getEndContent())>=0) {
                        int endFirstIndex = ocrText.indexOf(fatchRule.getEndContent()) + fatchRule.getEndContent().length();
                        if (ocrText.length() >= (endFirstIndex - fatchRule.getEndContent().length())) {
                            fatchMap.put(fatchRule.getColumn(), ocrText.substring(0, endFirstIndex - fatchRule.getEndContent().length()));
                            ocrText = ocrText.substring(endFirstIndex - fatchRule.getEndContent().length());
                        }
                    }
                }
            }

        }
    }
}