'commit'

src/main/java/com/dsideal/base/Tools/FillData/Area/A13.java

@@ -0,0 +1,182 @@
+package com.dsideal.base.Tools.FillData.Area;
+
+import cn.hutool.core.io.FileUtil;
+import com.dsideal.base.DataEase.Model.DataEaseModel;
+import com.dsideal.base.Tools.FillData.DataEaseKit.DsKit;
+import com.dsideal.base.Tools.Util.LocalMysqlConnectUtil;
+import com.jfinal.kit.StrKit;
+import org.apache.commons.io.FileUtils;
+import org.apache.poi.ss.usermodel.Row;
+import org.apache.poi.xssf.usermodel.XSSFCellStyle;
+import org.apache.poi.xssf.usermodel.XSSFSheet;
+import org.apache.poi.xssf.usermodel.XSSFWorkbook;
+import org.dom4j.Document;
+import org.dom4j.DocumentException;
+import org.dom4j.Element;
+import org.dom4j.io.SAXReader;
+
+import java.io.File;
+import java.io.FileInputStream;
+import java.io.FileOutputStream;
+import java.io.IOException;
+import java.util.ArrayList;
+import java.util.Arrays;
+import java.util.Collections;
+import java.util.List;
+import java.util.zip.ZipEntry;
+import java.util.zip.ZipInputStream;
+
+import static com.dsideal.base.Tools.FillData.DataEaseKit.DsKit.DocxUnzipDirectory;
+
+public class A13 {
+    //只输出四和五
+    static String[] printDx = {"一", "二", "三", "四", "五", "六", "七", "八", "九", "十"};
+    //转为 List<String>
+    static List<String> printDxList = Arrays.asList(printDx);
+    //哪些是处理不了的，就不处理了~
+    static String[] excludeCityList = {"~$", "磨憨-磨丁", "经开区", "阳宗海"};
+    //示例Excel
+    static String sampleExcelPath = "D:\\dsWork\\YunNanDsBase\\Doc\\待处理\\区\\【13】教育特征决策建议\\【云南省】教育特征-决策建议.xlsx";
+
+    /**
+     * 提取Word文档中的目录信息
+     *
+     * @param wordPath
+     * @throws DocumentException
+     * @throws IOException
+     */
+
+
+    static DataEaseModel dm = new DataEaseModel();
+
+    public static List<String> get4() throws DocumentException {
+        List<String> list = new ArrayList<>();
+        //读入XML
+        String xmlPath = DocxUnzipDirectory + "word\\document.xml";
+        SAXReader reader = new SAXReader();        // 创建 SAXReader 对象，读取 XML 文件
+        Document document = reader.read(new File(xmlPath));
+        Element root = document.getRootElement();// 获取根元素
+        List<Element> children = root.element("body").elements("p");//工作区
+        boolean out = false;
+        int parent = 0;
+        for (Element child : children) {
+            if (child.getName().equals("p")) {
+                List<Element> pChildren = child.elements();
+                String content = "";
+                for (Element pChild : pChildren) {
+                    if (!pChild.getName().equals("pPr")) {
+                        if (pChild.getName().equals("r")) {
+                            for (Element t : pChild.elements("t")) {
+                                content = content + t.getText();
+                            }
+                        }
+                    }
+                }
+                if (!StrKit.isBlank(content)) {
+                    //如果content是 "图"+数字形式的，不输出
+                    if (!content.contains("(图") && !content.contains("（图")) {
+                        //如果文字不是以上面printDx中的某一个开头，而且不是以数字+.开头，不输出
+                        if (content.startsWith("（") && printDxList.contains(String.valueOf(content.charAt(1)))) {
+                            out = true;
+                        }
+                        //太长的不要
+                        if (content.length() > 40) continue;
+                        if (printDxList.contains(content.substring(0, 1))) {
+                            if (content.charAt(0) == '四' && content.charAt(1) == '、') {
+                                parent = 4;
+                            }
+                            if (content.charAt(0) == '五' && content.charAt(1) == '、') {
+                                parent = 5;
+                            }
+                            out = true;
+                        }
+                        if (out && parent > 0) {
+                            if (!content.startsWith("（")) continue;
+                            if (parent == 4) {
+                                list.add(content.split("。")[0]);
+                            }
+//                                        if (parent == 5) {
+//                                            System.out.println("==================五===============");
+//                                            System.out.println(content.split("。")[0]);
+//                                        }
+                            out = false;
+                        }
+                    }
+                }
+            }
+        }
+        return list;
+    }
+
+    public static void main(String[] args) throws IOException, DocumentException {
+        //初始化数据库连接
+        LocalMysqlConnectUtil.Init();
+        //结果Excel
+        XSSFWorkbook outWorkbook = new XSSFWorkbook();
+        //结果Sheet
+        XSSFSheet outSheet = DsKit.createSheet(outWorkbook);
+        //样式
+        XSSFCellStyle headerStyle = DsKit.getHeaderStyle(outWorkbook);
+        XSSFCellStyle dataStyle = DsKit.getDataStyle(outWorkbook);
+        //如果样例文件是xls格式，则转化为xlsx格式
+        sampleExcelPath = DsKit.convertXlsToXlsx(sampleExcelPath);
+        //拷贝文件头
+        DsKit.copyHead(sampleExcelPath, outSheet, headerStyle);
+
+        //目标Excel,就是把文件名解析出来后，后面添加上【成果】,需要动态计算获取，不能写死
+        String excelPath = sampleExcelPath.replace(".xlsx", "【成果】.xlsx");
+        DsKit.delExcel(excelPath);
+
+        String parentPath = "D:\\dsidealDoc\\全省及州市县区人口与教育报告集20241023\\133个县区报告2022\\县区研究报告";
+        List<File> files = FileUtil.loopFiles(parentPath, file -> true);
+        int rowIndex = 0;
+        //处理这个目录
+        if (files != null) {
+            for (File file : files) {
+                //判断file是不是目录，是目录的需要跳过
+                if (file.isDirectory()) continue;
+                String fileName = file.getName();
+                //判断是否为docx文件
+                if (fileName.endsWith(".docx") && !fileName.startsWith("~")) {
+                    boolean flag = false;
+                    for (String s : excludeCityList) {
+                        if (file.getName().contains(s)) {
+                            flag = true;
+                            break;
+                        }
+                    }
+                    if (flag) continue;
+                    //县区名称
+                    String areaName = dm.getAreaName(file.getName());
+                    //市州名称
+                    String cityName = dm.getCityNameByAreaName(areaName);
+
+                    if (StrKit.isBlank(cityName) || StrKit.isBlank(areaName)) {
+                        System.out.println("发现异常数据，请人工处理：" + file.getName());
+                        continue;
+                    }
+                    //县区名称
+                    System.out.println("正在进行" + cityName + "-" + areaName + "的数据填充~");
+                    DsKit.unCompress(file.getAbsolutePath());
+
+                    List<String> list4 = get4();
+                    //如果list4的元素个数不足7个，需要补全到7个，空的用空字符串
+                    if (list4.size() < 7) {
+                        for (int i = list4.size(); i < 7; i++) {
+                            list4.add("");
+                        }
+                    }
+                    Row outRow = outSheet.createRow(++rowIndex);
+                    DsKit.putData(outRow, Arrays.asList(areaName, "教育特征","全县人口呈平稳增长趋势",
+                            list4.getFirst(), list4.get(1), list4.get(2), list4.get(3),
+                            list4.get(4), list4.get(5), list4.get(6),
+                            cityName), dataStyle);
+
+                }
+            }
+        }
+        //保存文件
+        DsKit.saveExcel(excelPath, outWorkbook);
+        System.out.println("县区所有文件处理完成！");
+    }
+}