数采调整2

zouyu

2025-10-21 b1ff3475c44738107398f4e502d9b54aac97fc48

 src/main/java/com/chinaztt/mes/docx/util/TakeWords.java

@@ -11,13 +11,18 @@
import org.apache.commons.lang3.StringUtils;
import org.apache.poi.POIXMLDocument;
import org.apache.poi.POIXMLTextExtractor;
import org.apache.poi.hssf.usermodel.HSSFPictureData;
import org.apache.poi.hssf.usermodel.HSSFWorkbook;
import org.apache.poi.hwpf.extractor.WordExtractor;
import org.apache.poi.openxml4j.opc.OPCPackage;
import org.apache.poi.ss.usermodel.Sheet;
import org.apache.poi.ss.usermodel.Workbook;
import org.apache.poi.xssf.usermodel.XSSFSheet;
import org.apache.poi.xssf.usermodel.XSSFWorkbook;
import org.apache.poi.xwpf.extractor.XWPFWordExtractor;

import java.io.*;
import java.nio.file.Files;
import java.sql.*;
import java.util.*;
import java.util.regex.Pattern;
@@ -52,28 +57,171 @@
        return result;
    }

    public static Object readExcelFile(File file) throws FileNotFoundException, IOException {
    public static Object readExcelFile(File file) throws IOException {
        StringBuilder result = new StringBuilder();
        //创建工作簿对象
        XSSFWorkbook xssfWorkbook = new XSSFWorkbook(new FileInputStream(file));
        XSSFWorkbook xssfWorkbook = new XSSFWorkbook(Files.newInputStream(file.toPath()));
        //获取工作簿下sheet的个数 只读取第一个sheet
//            int sheetNum = xssfWorkbook.getNumberOfSheets();
        //遍历工作簿中的所有数据
        for (int i = 0; i < 1; i++) {
            XSSFSheet sheet = xssfWorkbook.getSheetAt(i);
            //获取最后一行的num，即总行数。此处从0开始
            int maxRow = sheet.getLastRowNum();
            for (int row = 0; row <= maxRow; row++) {
                //获取最后单元格num，即总单元格数 ***注意：此处从1开始计数***
                int maxRol = sheet.getRow(row).getLastCellNum();
                StringBuilder aLine = new StringBuilder();
                for (int rol = 0; rol < maxRol; rol++) {
                    aLine.append(sheet.getRow(row).getCell(rol)).append(splitIdentifier);
                }
                result.append(aLine).append("\n");
        XSSFSheet sheet = xssfWorkbook.getSheetAt(0);
        //获取最后一行的num，即总行数。此处从0开始
        int maxRow = sheet.getLastRowNum();
        for (int row = 1; row <= maxRow; row++) {
            //获取最后单元格num，即总单元格数 ***注意：此处从1开始计数***
            int maxRol = sheet.getRow(row).getLastCellNum();
            StringBuilder aLine = new StringBuilder();
            for (int rol = 0; rol < maxRol; rol++) {
                aLine.append(sheet.getRow(row).getCell(rol)).append(splitIdentifier);
            }
            result.append(aLine).append("\n");
        }
        return result.toString();
    }

    public static Object readExcelxlsFile(File file) throws IOException {
        String result = "";
        try (FileInputStream fis = new FileInputStream(file);
             Workbook workbook = new HSSFWorkbook(fis)) {
            // 获取第一个工作表
            Sheet sheet = workbook.getSheetAt(0);
            // 读取图片信息
            if (workbook instanceof HSSFWorkbook) {
                HSSFWorkbook hssfWorkbook = (HSSFWorkbook) workbook;
                List<HSSFPictureData> pictures = hssfWorkbook.getAllPictures();
                //处理最后一张图片数据
                HSSFPictureData lastPicture = pictures.get(pictures.size()-1);
                // 获取图片类型
                String pictureType = lastPicture.suggestFileExtension();
                // 获取图片数据
                byte[] pictureData = lastPicture.getData();
                // 创建临时文件
                File tempFile = File.createTempFile(UUID.randomUUID().toString(), "." + pictureType);
                try (FileOutputStream fos = new FileOutputStream(tempFile)) {
                    fos.write(pictureData);
                }
                String ocrResult = "";
                try {
                    ocrResult = (String) readPngFile(tempFile);
                } catch (TesseractException e) {
                    ocrResult = "OCR识别失败: " + e.getMessage();
                } finally {
                    // 删除临时文件
                    tempFile.delete();
                }
                result = ocrResult;
//                String ocrText = fixOcrText(ocrResult);
//                result.append("OCR Result:").append(ocrText).append(",");


//                for (HSSFPictureData picture : pictures) {
//                    // 获取图片类型
//                    String pictureType = picture.suggestFileExtension();
//                    // 获取图片数据
//                    byte[] pictureData = picture.getData();
//                    // 创建临时文件
//                    File tempFile = File.createTempFile(UUID.randomUUID().toString(), "." + pictureType);
//                    try (FileOutputStream fos = new FileOutputStream(tempFile)) {
//                        fos.write(pictureData);
//                    }
//                    // 图片预处理
////                    File processedFile = preprocessImage(tempFile, pictureType);
//                    // 调用 readPngFile1 方法读取图片文字信息
//                    String ocrResult = "";
//                    try {
//                        ocrResult = (String) readPngFile(tempFile);
////                        ocrResult = (String) readPngFile(tempFile);
////                        ocrResult = (String) readPngFile(processedFile);
//                    } catch (TesseractException e) {
//                        ocrResult = "OCR识别失败: " + e.getMessage();
//                    } finally {
//                        // 删除临时文件
////                        tempFile.delete();
////                        processedFile.delete();
//                    }
//
//                    // 将图片信息添加到结果中
////                    result.append("Picture Type: ").append(pictureType)
////                            .append(", Picture Size: ").append(pictureData.length)
////                            .append(" bytes")
////                            .append(", OCR Result: ").append(ocrResult)
////                            .append(",");
//                    String ocrText = fixOcrText(ocrResult);
//                    result.append("OCR Result:").append(ocrText).append(",");
//                }
            }
//
//            // 遍历每一行
//            for (Row row : sheet) {
//                // 遍历每一列
//                for (Cell cell : row) {
//                    CellType cellType = CellType.forInt(cell.getCellType());
//                    switch (cellType) {
//                        case STRING:
//                            result.append(cell.getStringCellValue());
//                            break;
//                        case NUMERIC:
//                            if (DateUtil.isCellDateFormatted(cell)) {
//                                result.append(cell.getDateCellValue());
//                            } else {
//                                result.append(cell.getNumericCellValue());
//                            }
//                            break;
//                        case BOOLEAN:
//                            result.append(cell.getBooleanCellValue());
//                            break;
//                        case FORMULA:
//                            result.append(cell.getCellFormula());
//                            break;
//                        default:
//                            result.append("");
//                    }
//                    result.append("\t");
//                }
//                result.append("\n");
//            }
        }
        return result;

    }

    // 修正 OCR 识别文本中的错误关键词
    public static String fixOcrText(String ocrText) {
        // 定义错误关键词和正确内容的映射，这里处理“击 宇 强 庞”修正为“击穿强度”
        // 考虑到可能有空格分隔，用正则匹配包含这些字的内容
        ocrText = ocrText.replaceAll("击\\s*宇\\s*强\\s*庞", "击穿强度");
        // 还可以继续添加其他错误修正，比如下面假设“电 压 \\(HV\\)”里的空格影响，也修正下
        ocrText = ocrText.replaceAll("电\\s*压\\s*\\(HV\\)", "电压(KV)");
        ocrText = ocrText.replaceAll("电\\s*流\\s*\\(nt\\)", "电流(mA)");
        return ocrText;
    }

    public static Object readPngFile1(File file) throws IOException, TesseractException {
        // 获取 tessdata 目录的绝对路径
        String arch = System.getProperty("sun.arch.data.model");
        File tessDataDir;
        if (arch.contains("32")) {
            tessDataDir = FileUtil.file(".", "/jre_32/tessdata");
        } else {
            tessDataDir = FileUtil.file(".", "/jre_64/tessdata");
        }
        String path = tessDataDir.getCanonicalPath();
        // 检查 chi_sim.traineddata 文件是否存在
        File chiSimFile = new File(path, "chi_sim.traineddata");
        if (!chiSimFile.exists()) {
            throw new FileNotFoundException("chi_sim.traineddata 文件未找到，请检查路径: " + chiSimFile.getAbsolutePath());
        }
        // 设置配置文件夹、识别语言、识别模式
        Tesseract tesseract = new Tesseract();
        tesseract.setDatapath(path);
        // 设置识别语言为中文简体和英文（如果要设置为英文可改为 "eng"）
        tesseract.setLanguage("chi_sim+eng");
        // 使用 OSD 进行自动页面分割以进行图像处理
        tesseract.setPageSegMode(1);
        // 设置引擎模式是神经网络 LSTM 引擎
        tesseract.setOcrEngineMode(1);
        // 开始识别整张图片中的文字
        return tesseract.doOCR(file);
    }

    public static Object readTxtFile(File file) throws IOException {
@@ -90,23 +238,9 @@
    }

    public static Object readCsvFile(File file) {

        StringBuilder stringBuilder = new StringBuilder();
        // 创建 reader
//        try (BufferedReader br = Files.newBufferedReader(file.toPath())) {
//            // CSV文件的分隔符
//            String DELIMITER = ",";
//            // 按行读取
//            String line;
//            System.out.println(br.readLine());
//            while ((line = br.readLine()) != null) {
//                // 分割
//                String[] columns = line.split(DELIMITER);
//                // 打印行
//                stringBuilder.append(String.join(splitIdentifier, columns)).append("\n");
//            }
//        } catch (IOException ex) {
//            ex.printStackTrace();
//        }
        try (FileReader fileReader = new FileReader(file);
             CSVReader csvReader = new CSVReaderBuilder(fileReader).build()) {

@@ -183,6 +317,7 @@
            }
            tableMap.put("data", list);
        } catch (Exception e) {
            e.printStackTrace();
        } finally {
            closeA1l(conn, preparedStatement, rs);
        }
@@ -202,6 +337,74 @@
            }
        } catch (Exception ignore) {
        }
    }

    public static Object getMysqlFile(GetFileDto getFileDto){
        Map<String, Object> tableMap = new HashMap<>(16);
        // 从 GetFileDto 获取数据库名，对应【文件名称】字段
        String dbName = getFileDto.getDbFileName();
        String user = getFileDto.getDbUserName();
        String password = getFileDto.getDbPassword();
        // 从 GetFileDto 获取数据表名，对应【数据库表名】字段
        String table = getFileDto.getDbTable();
        // 检查数据库名和表名是否为空
        if (dbName == null || dbName.isEmpty() || table == null || table.isEmpty()) {
            return R.failed("数据库名或表名不能为空");
        }
        // 数据库连接信息
        String url = "jdbc:mysql://localhost:3306/"+dbName+"?useSSL=false&serverTimezone=GMT%2B8&allowPublicKeyRetrieval=true&characterEncoding=utf8";
        Connection connection = null;
        PreparedStatement preparedStatement = null;
        ResultSet resultSet = null;
        List<Map<String, Object>> dataList = new ArrayList<>();

        try {
            // 建立连接
            connection = DriverManager.getConnection(url, user, password);
            // 构建基础 SQL

            String sql = "SELECT * FROM "+table+" WHERE 1=1";
            if(StringUtils.isNotBlank(getFileDto.getMdbEntrustCode())){
                sql+=" AND " + getFileDto.getMdbEntrustCode() + " = '" + getFileDto.getEntrustCode()+ "'";
            }
            if(StringUtils.isNotBlank(getFileDto.getMdbSampleCode())){
                sql+=" AND " + getFileDto.getMdbSampleCode() + " = '" + getFileDto.getSampleCode() + "'";
            }
            // 创建 PreparedStatement 对象执行 SQL
            preparedStatement = connection.prepareStatement(sql);
            resultSet = preparedStatement.executeQuery();
            ResultSetMetaData metaData = resultSet.getMetaData();
            int columnCount = metaData.getColumnCount();
            // 遍历结果集获取数据
            while (resultSet.next()) {
                Map<String, Object> rowData = new HashMap<>();
                for (int i = 1; i <= columnCount; i++) {
                    String columnName = metaData.getColumnName(i);
                    rowData.put(columnName, resultSet.getObject(i));
                }
                dataList.add(rowData);
            }
            tableMap.put("data", dataList);
        } catch (Exception e) {
            e.printStackTrace();
            // 假设 R 类有 failed 方法，若没有需补充实现
            return R.failed("数据库查询出错: " + e.getMessage());
        } finally {
            try {
                if (resultSet != null) {
                    resultSet.close();
                }
                if (preparedStatement != null) {
                    preparedStatement.close();
                }
                if (connection != null) {
                    connection.close();
                }
            } catch (SQLException e) {
                e.printStackTrace();
            }
        }
        return tableMap;
    }

    public static Object readDbFile(File file, GetFileDto getFileDto) throws SQLException, ClassNotFoundException, InstantiationException, IllegalAccessException {
@@ -263,6 +466,8 @@
        } else {
            path = canonicalPath64.replaceAll("/chi_sim.traineddata", "").replaceAll("\\\\", "/");
        }
        // 设置 TESSDATA_PREFIX 环境变量
//        System.setProperty("TESSDATA_PREFIX", path);
        //设置配置文件夹微视、识别语言、识别模式
        Tesseract tesseract = new Tesseract();
        tesseract.setDatapath(path);