| | |
| | | package com.chinaztt.mes.docx.util; |
| | | |
| | | import cn.hutool.core.io.FileUtil; |
| | | import cn.hutool.http.HttpRequest; |
| | | import cn.hutool.json.JSONUtil; |
| | | import com.chinaztt.mes.docx.dto.GetFileDto; |
| | | import com.opencsv.CSVReader; |
| | | import com.opencsv.CSVReaderBuilder; |
| | | import com.opencsv.exceptions.CsvValidationException; |
| | | import net.sourceforge.tess4j.Tesseract; |
| | | import net.sourceforge.tess4j.TesseractException; |
| | | import org.apache.commons.lang3.ObjectUtils; |
| | | 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.ooxml.POIXMLDocument; |
| | | import org.apache.poi.ooxml.extractor.POIXMLTextExtractor; |
| | | import org.apache.poi.openxml4j.opc.OPCPackage; |
| | | import org.apache.poi.xssf.usermodel.XSSFSheet; |
| | | import org.apache.poi.xssf.usermodel.XSSFWorkbook; |
| | | import org.apache.poi.poifs.filesystem.POIFSFileSystem; |
| | | import org.apache.poi.ss.usermodel.Sheet; |
| | | import org.apache.poi.ss.usermodel.Workbook; |
| | | import org.apache.poi.ss.usermodel.WorkbookFactory; |
| | | 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; |
| | | |
| | | public class TakeWords { |
| | | |
| | | private static final String splitIdentifier = "@-@"; // 自定义唯一标识符 |
| | | |
| | | // 科学计数法正则模式 |
| | | private static final Pattern SCIENTIFIC_PATTERN = Pattern.compile( |
| | | "^[+-]?\\d+(\\.\\d+)?[eE][+-]?\\d+$" |
| | | ); |
| | | |
| | | public static Object readWordFile(File file) { |
| | | String result = ""; |
| | |
| | | return result; |
| | | } |
| | | |
| | | public static Object readExcelFile(File file) throws FileNotFoundException, IOException { |
| | | /** |
| | | * 读取excel文件,兼容.xlsx,.xls格式 |
| | | * @param file |
| | | * @return |
| | | */ |
| | | public static Object readExcelFile(File file) { |
| | | StringBuilder result = new StringBuilder(); |
| | | //创建工作簿对象 |
| | | XSSFWorkbook xssfWorkbook = new XSSFWorkbook(new FileInputStream(file)); |
| | | //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); |
| | | try ( |
| | | FileInputStream fis = new FileInputStream(file); |
| | | Workbook workbook = WorkbookFactory.create(fis) |
| | | ) { |
| | | //遍历工作簿中的所有数据 |
| | | Sheet sheet = workbook.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 = 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); |
| | | if(Objects.nonNull(sheet.getRow(row))){ |
| | | 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"); |
| | | } |
| | | result.append(aLine).append("\n"); |
| | | } |
| | | } catch (Exception e) { |
| | | e.printStackTrace(); |
| | | } |
| | | return result.toString(); |
| | | } |
| | | |
| | | /** |
| | | * 读取excel文件中的图片内容 |
| | | * @param file |
| | | * @return |
| | | * @throws IOException |
| | | */ |
| | | public static Object readPngContextInExcel(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 = ocrImageContext(tempFile.getAbsolutePath()); |
| | | } finally { |
| | | // 删除临时文件 |
| | | tempFile.delete(); |
| | | } |
| | | result = ocrResult; |
| | | } |
| | | } |
| | | return result; |
| | | |
| | | } |
| | | |
| | | 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 { |
| | |
| | | StringBuilder stringBuilder = new StringBuilder(); |
| | | String strTmp = ""; |
| | | while ((strTmp = buffReader.readLine()) != null) { |
| | | strTmp = strTmp.replaceAll("\t",","); |
| | | stringBuilder.append(strTmp).append("\n"); |
| | | } |
| | | buffReader.close(); |
| | |
| | | } |
| | | |
| | | 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; |
| | | while ((line = br.readLine()) != null) { |
| | | // 分割 |
| | | String[] columns = line.split(DELIMITER); |
| | | // 打印行 |
| | | stringBuilder.append(String.join(splitIdentifier, columns)).append("\n"); |
| | | try (FileReader fileReader = new FileReader(file); |
| | | CSVReader csvReader = new CSVReaderBuilder(fileReader).build()) { |
| | | |
| | | String[] nextLine; |
| | | while ((nextLine = csvReader.readNext()) != null) { |
| | | // 处理每一行数据 |
| | | for (String cell : nextLine) { |
| | | if(StringUtils.isNotBlank(cell)){ |
| | | stringBuilder.append(scientificToNumber(cell)).append(splitIdentifier); |
| | | } |
| | | } |
| | | stringBuilder.append("\n"); |
| | | } |
| | | } catch (IOException ex) { |
| | | ex.printStackTrace(); |
| | | } catch (IOException e) { |
| | | e.printStackTrace(); |
| | | } catch (CsvValidationException e) { |
| | | throw new RuntimeException(e); |
| | | } |
| | | return stringBuilder.toString(); |
| | | } |
| | | |
| | | /** |
| | | * 将科学计数法转换为数字 |
| | | * @param cell |
| | | * @return |
| | | */ |
| | | public static String scientificToNumber(String cell){ |
| | | if(SCIENTIFIC_PATTERN.matcher(cell).matches()){ |
| | | return String.valueOf(Double.parseDouble(cell)); |
| | | } |
| | | return cell; |
| | | } |
| | | |
| | | public static Object readMdbFile(File file, GetFileDto getFileDto) throws SQLException, ClassNotFoundException, InstantiationException, IllegalAccessException { |
| | |
| | | Properties prop = new Properties(); |
| | | //设置编码 |
| | | prop.put("charSet", "UTF-8"); |
| | | prop.put("user", ""); |
| | | prop.put("password", ""); |
| | | prop.put("user", StringUtils.isNotBlank(getFileDto.getDbUserName())?getFileDto.getDbUserName():""); |
| | | prop.put("password", StringUtils.isNotBlank(getFileDto.getDbPassword())?getFileDto.getDbPassword():""); |
| | | //数据地址 |
| | | String dbUrl = "jdbc:ucanaccess://" + file.getPath(); |
| | | //引入驱动 |
| | |
| | | try { |
| | | List<Object> list = new ArrayList<>(); |
| | | //遍历获取多张表数据 |
| | | // String s = "select * from " + getFileDto.getDbFileName() + " where 1=1" + getFileDto.getMdbEntrustCode() + " = '" + getFileDto.getEntrustCode() + |
| | | // "' and " + getFileDto.getMdbSampleCode() + " = '" + getFileDto.getSampleCode() + "'"; |
| | | String s = "select * from " + getFileDto.getDbFileName() + " where 1=1"; |
| | | if(StringUtils.isNotBlank(getFileDto.getMdbEntrustCode())){ |
| | | s+=" and " + getFileDto.getMdbEntrustCode() + " = '" + getFileDto.getEntrustCode()+ "'"; |
| | |
| | | if(StringUtils.isNotBlank(getFileDto.getMdbSampleCode())){ |
| | | s+=" and " + getFileDto.getMdbSampleCode() + " = '" + getFileDto.getSampleCode() + "'"; |
| | | } |
| | | if(StringUtils.isNotBlank(getFileDto.getBushingColorField())){ |
| | | s+=" and " + getFileDto.getBushingColorField() + " = '" + getFileDto.getBushingColor() + "'"; |
| | | } |
| | | |
| | | preparedStatement = conn.prepareStatement(s); |
| | | rs = preparedStatement.executeQuery(); |
| | | ResultSetMetaData data = rs.getMetaData(); |
| | |
| | | } |
| | | tableMap.put("data", list); |
| | | } catch (Exception e) { |
| | | e.printStackTrace(); |
| | | } finally { |
| | | closeA1l(conn, preparedStatement, rs); |
| | | } |
| | |
| | | } |
| | | } 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() + " = TRIM('" + getFileDto.getEntrustCode()+ "')"; |
| | | if(StringUtils.isNotBlank(getFileDto.getLotBatchNo())){ |
| | | sql+=" OR "+ getFileDto.getMdbEntrustCode() + " = TRIM('" + getFileDto.getLotBatchNo()+ "')"; |
| | | } |
| | | sql+=")"; |
| | | } |
| | | if(StringUtils.isNotBlank(getFileDto.getMdbSampleCode())){ |
| | | sql+=" AND " + getFileDto.getMdbSampleCode() + " = '" + getFileDto.getSampleCode() + "'"; |
| | | } |
| | | if(StringUtils.isNotBlank(getFileDto.getCableTag())){ |
| | | sql+=" AND Color = '" + getFileDto.getCableTag() + "'"; |
| | | } |
| | | // 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 { |
| | |
| | | return tableMap; |
| | | } |
| | | |
| | | /** |
| | | * ocr识别图片内容 |
| | | * @param imagePath 图片路径 |
| | | * @return |
| | | */ |
| | | public static String ocrImageContext(String imagePath){ |
| | | //调用ocr识别服务 |
| | | Map<String,Object> jsonMap = new HashMap<>(); |
| | | jsonMap.put("imagePath",imagePath); |
| | | String requestBody = JSONUtil.toJsonStr(jsonMap); |
| | | return HttpRequest.post("localhost:8080/ocr/recognize").body(requestBody).execute().body(); |
| | | } |
| | | |
| | | public static Object readPngFile(File file) throws IOException, TesseractException { |
| | | String canonicalPath32 = FileUtil.file(".", "/jre_32/tessdata").getCanonicalPath(); |
| | | String canonicalPath64 = FileUtil.file(".", "/jre_64/tessdata").getCanonicalPath(); |
| | |
| | | } 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); |