321 lines
17 KiB
Java
321 lines
17 KiB
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.common.utils.StringUtils;
|
|
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) {
|
|
String text = ocrText;
|
|
if (CollectionUtil.isNotEmpty(fatchRules)) {
|
|
|
|
for (FatchRule fatchRule : fatchRules) {
|
|
// 从后往前抓取
|
|
if (fatchRule.getFatchOrder() != null && fatchRule.getFatchOrder() == 1) {
|
|
// String reverseText = StrUtil.reverse(ocrText);
|
|
// if (StrUtil.isEmpty(fatchRule.getStartContent()) && StrUtil.isEmpty(fatchRule.getEndContent())) {
|
|
// fatchMap.put(fatchRule.getColumnName(), trimStr(text));
|
|
// } else if(StrUtil.isEmpty(fatchRule.getStartContent())&&StrUtil.isNotEmpty(fatchRule.getEndContent())){
|
|
// // 开始字段为空，结束字段不为空
|
|
// String endReverseText = StrUtil.reverse(fatchRule.getEndContent());
|
|
// int endContIndex = StrUtil.ordinalIndexOf(reverseText, endReverseText, fatchRule.getEndContentRepeatOrder());
|
|
// if (endContIndex != -1) {
|
|
// String substring = text.substring(0, endContIndex);
|
|
// fatchMap.put(fatchRule.getColumnName(), trimStr(StrUtil.reverse(substring)));
|
|
// }
|
|
//
|
|
//
|
|
// }else if(StrUtil.isNotEmpty(fatchRule.getStartContent())&&StrUtil.isEmpty(fatchRule.getEndContent())){
|
|
// // 开始字段不为空，结束字段为空
|
|
// // 开始字段为空，结束字段不为空
|
|
// String startReverseText = StrUtil.reverse(fatchRule.getStartContent());
|
|
// int startContIndex = StrUtil.ordinalIndexOf(reverseText, startReverseText, fatchRule.getStartContentRepeatOrder());
|
|
// if (startContIndex != -1) {
|
|
// String substring = text.substring(0, startContIndex);
|
|
// fatchMap.put(fatchRule.getColumnName(), trimStr(StrUtil.reverse(substring)));
|
|
// }
|
|
//
|
|
// }else if(StrUtil.isNotEmpty(fatchRule.getStartContent())&&StrUtil.isNotEmpty(fatchRule.getEndContent())){
|
|
// String startReverseText = StrUtil.reverse(fatchRule.getStartContent());
|
|
// String endReverseText = StrUtil.reverse(fatchRule.getEndContent());
|
|
// int startContIndex = StrUtil.ordinalIndexOf(reverseText, startReverseText, fatchRule.getStartContentRepeatOrder());
|
|
// if (startContIndex != -1) {
|
|
// // 结束字段不为空
|
|
// int endContIndex = StrUtil.ordinalIndexOf(reverseText, endReverseText, fatchRule.getEndContentRepeatOrder());
|
|
// if (endContIndex != -1 && (startContIndex + fatchRule.getStartContent().length()) <= text.length()) {
|
|
// String substring = text.substring(startContIndex + fatchRule.getStartContent().length(), endContIndex);
|
|
// // 去除\n
|
|
// fatchMap.put(fatchRule.getColumnName(),trimStr(StrUtil.reverse(substring)));
|
|
// }
|
|
// }
|
|
// }
|
|
} else {
|
|
// 开始为空结束为空
|
|
if (StrUtil.isEmpty(fatchRule.getStartContent()) && StrUtil.isEmpty(fatchRule.getEndContent())) {
|
|
fatchMap.put(fatchRule.getColumnName(), trimStr(text));
|
|
} else if (StrUtil.isNotEmpty(fatchRule.getStartContent())) {
|
|
int startContIndex = StrUtil.ordinalIndexOf(text, fatchRule.getStartContent(), fatchRule.getStartContentRepeatOrder());
|
|
if (startContIndex != -1) {
|
|
// 开始不为空结束为空
|
|
if (StrUtil.isEmpty(fatchRule.getEndContent())) {
|
|
if ((startContIndex + fatchRule.getStartContent().length()) <= text.length()) {
|
|
String substring = text.substring(startContIndex + fatchRule.getStartContent().length());
|
|
// 去除\n
|
|
fatchMap.put(fatchRule.getColumnName(), trimStr(substring));
|
|
}
|
|
|
|
} else {
|
|
// 开始不为空结束不为空
|
|
int endContIndex = StrUtil.ordinalIndexOf(text, fatchRule.getEndContent(), fatchRule.getEndContentRepeatOrder());
|
|
if (endContIndex != -1 && (startContIndex + fatchRule.getStartContent().length()) <= text.length()) {
|
|
String substring = text.substring(startContIndex + fatchRule.getStartContent().length(), endContIndex);
|
|
// 去除\n
|
|
fatchMap.put(fatchRule.getColumnName(), trimStr(substring));
|
|
}
|
|
|
|
}
|
|
//
|
|
}
|
|
|
|
} else if (StrUtil.isEmpty(fatchRule.getStartContent()) && StrUtil.isNotEmpty(fatchRule.getEndContent())) {
|
|
// 开始为空结束不为空
|
|
int endContIndex = StrUtil.ordinalIndexOf(text, fatchRule.getEndContent(), fatchRule.getEndContentRepeatOrder());
|
|
if (endContIndex != -1) {
|
|
String substring = text.substring(0, endContIndex);
|
|
fatchMap.put(fatchRule.getColumnName(), trimStr(substring));
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
|
|
}
|
|
|
|
/**
|
|
* 去除末尾空格
|
|
*
|
|
* @param substring
|
|
* @return
|
|
*/
|
|
private static String trimStr(String substring) {
|
|
if (StrUtil.isNotEmpty(substring)) {
|
|
return StrUtil.trim(substring);
|
|
} else {
|
|
return "";
|
|
}
|
|
|
|
}
|
|
|
|
}
|