huanghai
/
YunNanDsBase
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

'commit'

Browse Source
main
黄海 8 months ago
parent a7f413a28f
commit b785e66487
2 changed files with 154 additions and 147 deletions
Show Stats Download Patch File Download Diff File

152
src/main/java/com/dsideal/base/Tools/FillData/ExcelKit/ExcelKit.java
Unescape View File

@ -11,12 +11,22 @@ import org.apache.poi.xssf.usermodel.XSSFSheet;
import org.apache.poi.xssf.usermodel.XSSFWorkbook;
import org.apache.poi.xwpf.usermodel.XWPFChart;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.dom4j.Document;
import org.dom4j.DocumentException;
import org.dom4j.Element;
import org.dom4j.io.SAXReader;
import java.io.*;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import java.util.zip.ZipEntry;
import java.util.zip.ZipInputStream;
public class ExcelKit {
// docx文件解压目录
public static String DocxUnzipDirectory = "C:\\zipFile\\";
/**
* 将xls转换为xlsx
@ -527,4 +537,146 @@ public class ExcelKit {
is.close();
}
/**
* 解压缩
*
* @throws IOException
*/
public static void UnCompress(String wordPath) throws IOException {
File file = new File(wordPath);//取得word文件
FileInputStream inputStream = new FileInputStream(file);
ZipInputStream zipInputStream = new ZipInputStream(inputStream);
ZipEntry entry;
byte[] ch = new byte[256];
while ((entry = zipInputStream.getNextEntry()) != null) {
File zFile = new File(DocxUnzipDirectory + entry.getName());
if (entry.isDirectory()) {
if (!zFile.exists()) {
zFile.mkdirs();
}
zipInputStream.closeEntry();
} else {
File fpath = new File(zFile.getParent());
if (!fpath.exists()) {
fpath.mkdirs();
}
FileOutputStream outputStream = new FileOutputStream(zFile);
int i;
while ((i = zipInputStream.read(ch)) != -1) {
outputStream.write(ch, 0, i);
}
zipInputStream.closeEntry();
outputStream.close();
}
}
inputStream.close();
}
/**
* 读取指定的Chart数据
*
* @param chartNumber
*/
public static List<List<String>> readChart(int chartNumber) throws DocumentException {
List<List<String>> matrix = new ArrayList<>();
String xml = DocxUnzipDirectory + "word\\charts\\chart" + chartNumber + ".xml";
if (!(new File(xml).exists())) {
System.out.println("没有找到第" + chartNumber + "个图表");
return matrix;
}
//3、开始读取
// 创建 SAXReader 对象，读取 XML 文件
SAXReader reader = new SAXReader();
Document document = reader.read(new File(xml));
// 获取根元素
Element root = document.getRootElement();
//折线图
//将xml用IDEA打开，搜索关键的数据值，然后右键查看XPATH完整路径可以获取到下面的路径
///c:chartSpace/c:chart/c:plotArea/c:lineChart/c:ser/c:cat/c:numRef/c:numCache/c:pt/c:v
//在每个已知的图表类型中查找，找到后跳出循环
//声明一个数组,图表的所有类型
String[] CHART_TYPES = {"lineChart", "barChart"};//折线，柱状
String type = "";
for (String chartType : CHART_TYPES) {
if (root.element("chart").element("plotArea")
.element(chartType) != null) {
type = chartType;
break;
}
}
if (StrKit.isBlank(type)) {
System.out.println("没有找到图表类型,请扩充图表类型");
System.out.println(root.element("chart").element("plotArea"));
System.exit(-1);
}
List<Element> xList = root.element("chart").element("plotArea").element(type).element("ser").element("cat")
.element("numRef").element("numCache").elements("pt");
List<Object> listObject = new ArrayList<>();
///c:chartSpace/c:chart/c:plotArea/c:lineChart/c:ser/c:val/c:numRef/c:numCache
for (Element ser : root.element("chart").element("plotArea").element(type).elements("ser")) {
List<Element> yList = ser.element("val").element("numRef").element("numCache").elements("pt");
//记录都有哪些有效数值和索引号
Map<Integer, Element> map = new HashMap<>();
for (Element e : yList) {
map.put(Integer.parseInt(e.attribute("idx").getValue()), e);
}
List<Object> list = new ArrayList<>();
for (int i = 0; i < xList.size(); i++) {
list.add(map.getOrDefault(i, null));
}
listObject.add(list);
}
//数据是按行读取的
for (int i = 0; i < listObject.size(); i++) {
List<String> row = new ArrayList<>();
List<Element> lo = (List<Element>) listObject.get(i);
for (Element e : lo) {
if (e == null) {
row.add(null);
} else {
row.add(e.element("v").getText());
}
}
matrix.add(row);
}
//上面生成的数据格式需要行转列,横坐标是年份，纵坐标是数据
int rowCount = matrix.size();// 计算行数和列数
int colCount = matrix.getFirst().size();
// 创建一个一维列表，用于存储转换后的列
List<List<String>> transposed = new ArrayList<>();
// 遍历每一列
for (int col = 0; col < colCount; col++) {
// 创建一个新的内部列表，用于存储当前列的所有行
List<String> column = new ArrayList<>();
// 遍历每一行，将当前列的值添加到新的内部列表中
for (int row = 0; row < rowCount; row++) {
String x = matrix.get(row).get(col);
//如果x可以转为小数，那么需要保留两位小数，如果可以转换为整数，那么直接返回整数，如果是字符串，就不变
try {
double d = Double.parseDouble(x);
if (d == (int) d) {
x = String.valueOf((int) d);
} else {
x = String.format("%.2f", d);
}
} catch (Exception e) {
//do nothing
}
column.add(x);
}
// 将当前列添加到结果列表中
transposed.add(column);
}
// 在每一行的第一列插入年份
for (int i = 0; i < transposed.size(); i++) {
List<String> column = transposed.get(i);
column.addFirst(xList.get(i).element("v").getText()); // 在每行的开始插入序号
}
return transposed;
}
}

149
src/main/java/com/dsideal/base/Tools/Test/TestOutSideExcel.java
Unescape View File

@ -1,173 +1,28 @@
package com.dsideal.base.Tools.Test;
import com.dsideal.base.Tools.FillData.ExcelKit.ExcelKit;
import com.jfinal.kit.StrKit;
import org.apache.poi.openxml4j.exceptions.InvalidFormatException;
import org.dom4j.Document;
import org.dom4j.DocumentException;
import org.dom4j.Element;
import org.dom4j.io.SAXReader;
import org.xml.sax.SAXException;
import javax.xml.parsers.ParserConfigurationException;
import javax.xml.xpath.XPathExpressionException;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import java.util.zip.ZipEntry;
import java.util.zip.ZipInputStream;
public class TestOutSideExcel {
/**
* 解压缩
*
* @throws IOException
*/
public static void UnCompress(String wordPath, String workingPath) throws IOException {
workingPath = workingPath.replace("\\", "/");
if (!workingPath.endsWith("/")) workingPath += "/";
File file = new File(wordPath);//取得word文件
FileInputStream inputStream = new FileInputStream(file);
ZipInputStream zipInputStream = new ZipInputStream(inputStream);
ZipEntry entry;
byte[] ch = new byte[256];
while ((entry = zipInputStream.getNextEntry()) != null) {
File zFile = new File(workingPath + entry.getName());
if (entry.isDirectory()) {
if (!zFile.exists()) {
zFile.mkdirs();
}
zipInputStream.closeEntry();
} else {
File fpath = new File(zFile.getParent());
if (!fpath.exists()) {
fpath.mkdirs();
}
FileOutputStream outputStream = new FileOutputStream(zFile);
int i;
while ((i = zipInputStream.read(ch)) != -1) {
outputStream.write(ch, 0, i);
}
zipInputStream.closeEntry();
outputStream.close();
}
}
inputStream.close();
}
/**
* 读取指定的Chart数据
*
* @param workingPath
* @param chartNumber
*/
public static List<List<String>> readChart(String workingPath, int chartNumber) throws DocumentException {
List<List<String>> matrix = new ArrayList<>();
String xml = workingPath + "\\word\\charts\\chart" + chartNumber + ".xml";
if (!(new File(xml).exists())) {
System.out.println("没有找到第" + chartNumber + "个图表");
return matrix;
}
//3、开始读取
// 创建 SAXReader 对象，读取 XML 文件
SAXReader reader = new SAXReader();
Document document = reader.read(new File(xml));
// 获取根元素
Element root = document.getRootElement();
//折线图
//将xml用IDEA打开，搜索关键的数据值，然后右键查看XPATH完整路径可以获取到下面的路径
///c:chartSpace/c:chart/c:plotArea/c:lineChart/c:ser/c:cat/c:numRef/c:numCache/c:pt/c:v
//在每个已知的图表类型中查找，找到后跳出循环
//声明一个数组,图表的所有类型
String[] CHART_TYPES = {"lineChart", "barChart"};//折线，柱状
String type = "";
for (String chartType : CHART_TYPES) {
if (root.element("chart").element("plotArea")
.element(chartType) != null) {
type = chartType;
break;
}
}
if (StrKit.isBlank(type)) {
System.out.println("没有找到图表类型,请扩充图表类型");
System.out.println(root.element("chart").element("plotArea"));
System.exit(-1);
}
List<Element> xList = root.element("chart").element("plotArea").element(type).element("ser").element("cat")
.element("numRef").element("numCache").elements("pt");
List<Object> listObject = new ArrayList<>();
///c:chartSpace/c:chart/c:plotArea/c:lineChart/c:ser/c:val/c:numRef/c:numCache
for (Element ser : root.element("chart").element("plotArea").element(type).elements("ser")) {
List<Element> yList = ser.element("val").element("numRef").element("numCache").elements("pt");
//记录都有哪些有效数值和索引号
Map<Integer, Element> map = new HashMap<>();
for (Element e : yList) {
map.put(Integer.parseInt(e.attribute("idx").getValue()), e);
}
List<Object> list = new ArrayList<>();
for (int i = 0; i < xList.size(); i++) {
list.add(map.getOrDefault(i, null));
}
listObject.add(list);
}
//数据是按行读取的
for (int i = 0; i < listObject.size(); i++) {
List<String> row = new ArrayList<>();
List<Element> lo = (List<Element>) listObject.get(i);
for (Element e : lo) {
if (e == null) {
row.add(null);
} else {
row.add(e.element("v").getText());
}
}
matrix.add(row);
}
//上面生成的数据格式需要行转列,横坐标是年份，纵坐标是数据
int rowCount = matrix.size();// 计算行数和列数
int colCount = matrix.getFirst().size();
// 创建一个一维列表，用于存储转换后的列
List<List<String>> transposed = new ArrayList<>();
// 遍历每一列
for (int col = 0; col < colCount; col++) {
// 创建一个新的内部列表，用于存储当前列的所有行
List<String> column = new ArrayList<>();
// 遍历每一行，将当前列的值添加到新的内部列表中
for (int row = 0; row < rowCount; row++) {
column.add(matrix.get(row).get(col));
}
// 将当前列添加到结果列表中
transposed.add(column);
}
// 在每一行的第一列插入年份
for (int i = 0; i < transposed.size(); i++) {
List<String> column = transposed.get(i);
column.addFirst(xList.get(i).element("v").getText()); // 在每行的开始插入序号
}
return transposed;
}
public static void main(String[] args) throws IOException, InvalidFormatException, InterruptedException, ParserConfigurationException, SAXException, XPathExpressionException, DocumentException {
String sourceDoc = "c:/西双版纳州人口变化及其对教育的影响20240420.docx";
//1、将word文件解压缩
String workingPath = "C:\\zipFile";
UnCompress(sourceDoc, workingPath);
ExcelKit.UnCompress(sourceDoc);
//2、我们需要第几个图表
for (int chartNumber = 1; chartNumber <= 37; chartNumber++) {
System.out.println("正在处理第" + chartNumber + "个图表的信息~");
//读取图表
List<List<String>> list = readChart(workingPath, chartNumber);
List<List<String>> list = ExcelKit.readChart( chartNumber);
ExcelKit.printTable(list);
System.out.println("=========================================================");
}

Write Preview
Loading…
Cancel
Save