package com.chinaztt.mes.docx.util;
|
|
import cn.hutool.core.io.FileUtil;
|
import com.chinaztt.mes.docx.dto.GetFileDto;
|
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.hwpf.extractor.WordExtractor;
|
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.xwpf.extractor.XWPFWordExtractor;
|
|
import java.io.*;
|
import java.nio.file.Files;
|
import java.sql.*;
|
import java.util.*;
|
|
public class TakeWords {
|
|
private static final String splitIdentifier = "@-@"; // 自定义唯一标识符
|
|
public static Object readWordFile(File file) {
|
String result = "";
|
//首先判断文件中的是doc/docx
|
try {
|
if (file.getName().endsWith(".doc")) {
|
InputStream is = new FileInputStream(file);
|
WordExtractor re = new WordExtractor(is);
|
result = re.getText();
|
re.close();
|
} else if (file.getName().endsWith(".docx")) {
|
OPCPackage opcPackage = POIXMLDocument.openPackage(file.getPath());
|
POIXMLTextExtractor extractor = new XWPFWordExtractor(opcPackage);
|
result = extractor.getText();
|
extractor.close();
|
}
|
} catch (Exception e) {
|
e.printStackTrace();
|
}
|
return result;
|
}
|
|
public static Object readExcelFile(File file) throws FileNotFoundException, IOException {
|
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);
|
//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");
|
}
|
}
|
return result.toString();
|
}
|
|
public static Object readTxtFile(File file) throws IOException {
|
FileInputStream fin = new FileInputStream(file);
|
InputStreamReader reader = new InputStreamReader(fin);
|
BufferedReader buffReader = new BufferedReader(reader);
|
StringBuilder stringBuilder = new StringBuilder();
|
String strTmp = "";
|
while ((strTmp = buffReader.readLine()) != null) {
|
stringBuilder.append(strTmp).append("\n");
|
}
|
buffReader.close();
|
return stringBuilder.toString();
|
}
|
|
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");
|
}
|
} catch (IOException ex) {
|
ex.printStackTrace();
|
}
|
return stringBuilder.toString();
|
}
|
|
public static Object readMdbFile(File file, GetFileDto getFileDto) throws SQLException, ClassNotFoundException, InstantiationException, IllegalAccessException {
|
Map<String, Object> tableMap = new HashMap<>(16);
|
Properties prop = new Properties();
|
//设置编码
|
prop.put("charSet", "UTF-8");
|
prop.put("user", "");
|
prop.put("password", "");
|
//数据地址
|
String dbUrl = "jdbc:ucanaccess://" + file.getPath();
|
//引入驱动
|
Class.forName("net.ucanaccess.jdbc.UcanaccessDriver").newInstance();
|
Connection conn = null;
|
PreparedStatement preparedStatement = null;
|
ResultSet rs = null;
|
|
//连接数据库资源
|
conn = DriverManager.getConnection(dbUrl, prop);
|
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() + "'";
|
}
|
preparedStatement = conn.prepareStatement(s);
|
rs = preparedStatement.executeQuery();
|
ResultSetMetaData data = rs.getMetaData();
|
while (rs.next()) {
|
Map<String, String> map = new HashMap<>();
|
for (int i = 1; i <= data.getColumnCount(); i++) {
|
//列名
|
String columnName = data.getColumnName(i);
|
map.put(columnName, rs.getString(i));
|
}
|
list.add(map);
|
}
|
tableMap.put("data", list);
|
} catch (Exception e) {
|
} finally {
|
closeA1l(conn, preparedStatement, rs);
|
}
|
return tableMap;
|
}
|
|
private static void closeA1l(Connection conn, PreparedStatement preparedStatement, ResultSet rs) {
|
try {
|
if (null != rs) {
|
rs.close();
|
}
|
if (null != preparedStatement) {
|
preparedStatement.close();
|
}
|
if (null != conn) {
|
conn.close();
|
}
|
} catch (Exception ignore) {
|
}
|
}
|
|
public static Object readDbFile(File file, GetFileDto getFileDto) throws SQLException, ClassNotFoundException, InstantiationException, IllegalAccessException {
|
Map<String, Object> tableMap = new HashMap<>(16);
|
Properties prop = new Properties();
|
//设置编码
|
prop.put("charSet", "GBK");
|
prop.put("user", "");
|
prop.put("password", "");
|
//数据地址
|
String dbUrl = "jdbc:sqlite:" + file.getPath();
|
//引入驱动
|
Class.forName("org.sqlite.JDBC").newInstance();
|
Connection conn = null;
|
PreparedStatement preparedStatement = null;
|
ResultSet rs = null;
|
//连接数据库资源
|
conn = DriverManager.getConnection(dbUrl, prop);
|
try {
|
List<Object> list = new ArrayList<>();
|
//转义中文
|
String sampleCode = changeCharset(getFileDto.getSampleCode(), "GBK");
|
String sql = "select * from " + getFileDto.getDbFileName() +
|
" where " + getFileDto.getMdbEntrustCode() + " = '" + getFileDto.getEntrustCode() +
|
"' and " + getFileDto.getMdbSampleCode() + " = '" + sampleCode + "'";
|
if (ObjectUtils.allNotNull(getFileDto.getFiberOpticRibbonCode(), getFileDto.getFiberOpticRibbon()) && !getFileDto.getFiberOpticRibbonCode().equals("null")) {
|
sql = sql + " and " + getFileDto.getFiberOpticRibbonCode() + " = '" + getFileDto.getFiberOpticRibbon() + "'";
|
}
|
//遍历获取多张表数据
|
preparedStatement = conn.prepareStatement(sql);
|
rs = preparedStatement.executeQuery();
|
ResultSetMetaData data = rs.getMetaData();
|
while (rs.next()) {
|
Map<String, String> map = new HashMap<>();
|
for (int i = 1; i <= data.getColumnCount(); i++) {
|
//列名
|
String columnName = data.getColumnName(i);
|
//将返回的结果转换从utf-8编码
|
map.put(columnName, changeCharset(rs.getString(i),"UTF-8"));
|
}
|
list.add(map);
|
}
|
tableMap.put("data", list);
|
} catch (Exception e) {
|
} finally {
|
closeA1l(conn, preparedStatement, rs);
|
}
|
return tableMap;
|
}
|
|
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();
|
String path;
|
// 判断电脑是32位还是64位
|
String arch = System.getProperty("sun.arch.data.model");
|
if (arch.contains("32")) {
|
path = canonicalPath32.replaceAll("/chi_sim.traineddata", "").replaceAll("\\\\", "/");
|
} else {
|
path = canonicalPath64.replaceAll("/chi_sim.traineddata", "").replaceAll("\\\\", "/");
|
}
|
//设置配置文件夹微视、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，（如果要设置为英文可改为"eng"）
|
tesseract.setLanguage("chi_sim");
|
//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);
|
}
|
|
/**
|
* 字符串编码转换
|
*
|
* @param str 要转换的字符串
|
* @param unicode 字符编码
|
* @return
|
*/
|
public static String changeCharset(String str, String unicode) {
|
if(Objects.isNull(str)){
|
return "";
|
}
|
try {
|
return new String(str.getBytes(), unicode);
|
} catch (UnsupportedEncodingException e) {
|
throw new RuntimeException(e);
|
}
|
}
|
|
}
|
