ZQ/laws-sinotruk-server
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update 文档拆分回滚

Browse Source
This commit is contained in:
lijiarao
2023-11-09 15:38:01 +08:00
parent 88f9ac8211
commit 23caf9f334
15 changed files with 4702 additions and 42 deletions
Download Patch File Download Diff File Expand all files Collapse all files
laws-modules/src/main/java/com/jero/modules/split/service/impl/FileSpiltService.java
+17 -39
View File
@@ -18,6 +18,7 @@ import com.jero.modules.split.vo.TitleNumberVO;
import lombok.extern.slf4j.Slf4j;
import org.apache.commons.collections4.CollectionUtils;
import org.apache.commons.lang3.StringUtils;
import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.openxml4j.opc.PackagePart;
import org.apache.poi.openxml4j.util.ZipSecureFile;
import org.apache.poi.xwpf.usermodel.*;
@@ -128,22 +129,22 @@ public class FileSpiltService {
// nowStart.add(String.valueOf(sarFileSplitInfoEO.getStartNumber()));
// }
// 获取文件地址
// String fileId = sarFileSplitInfoEO.getFileId();
// LambdaQueryWrapper<OSSFile> queryWrapper = new LambdaQueryWrapper();
// queryWrapper.eq(OSSFile::getId, fileId);
// queryWrapper.orderByDesc(OSSFile::getCreateTime);
// List<OSSFile> ossFileList = iossFileService.list(queryWrapper);
// if (CollectionUtils.isEmpty(ossFileList)) {
// throw new JeroBootException("当前文件未找到，请重新选择！");
// }
// OSSFile ossFile = ossFileList.get(0);
// String readFilePath = ossFile.getUrl();
// if (StringUtils.isEmpty(readFilePath) || !MinioUtil.doesObjectExist(readFilePath)) {
// throw new JeroBootException("当前文件未找到，请重新选择！");
// }
// try (InputStream is = MinioUtil.download(readFilePath);InputStream is1 = MinioUtil.download(readFilePath)) {
String readFilePath = "E:\\Data\\Downloads\\wordtest\\GB7258标准修订test - 表格测试 - 副本.docx";
try (InputStream is = new FileInputStream(readFilePath); InputStream is1 = new FileInputStream(readFilePath)) {//需要将文件路更改为word文档所在路径。
String fileId = sarFileSplitInfoEO.getFileId();
LambdaQueryWrapper<OSSFile> queryWrapper = new LambdaQueryWrapper();
queryWrapper.eq(OSSFile::getId, fileId);
queryWrapper.orderByDesc(OSSFile::getCreateTime);
List<OSSFile> ossFileList = iossFileService.list(queryWrapper);
if (CollectionUtils.isEmpty(ossFileList)) {
throw new JeroBootException("当前文件未找到，请重新选择！");
}
OSSFile ossFile = ossFileList.get(0);
String readFilePath = ossFile.getUrl();
if (StringUtils.isEmpty(readFilePath) || !MinioUtil.doesObjectExist(readFilePath)) {
throw new JeroBootException("当前文件未找到，请重新选择！");
}
try (InputStream is = MinioUtil.download(readFilePath);InputStream is1 = MinioUtil.download(readFilePath)) {
//String readFilePath = "E:\\Data\\Downloads\\wordtest\\GB7258标准修订test - 表格测试 - 副本.docx";
//try (InputStream is = new FileInputStream(readFilePath); InputStream is1 = new FileInputStream(readFilePath)) {//需要将文件路更改为word文档所在路径。
ZipSecureFile.setMinInflateRatio(-1.0d);
XWPFDocument doc = new XWPFDocument(is);
@@ -173,29 +174,6 @@ public class FileSpiltService {
XWPFParagraph p = (XWPFParagraph) element;
StringBuilder stringBuilder = new StringBuilder();
ParagraphChildOrderManager runOrMaths = new ParagraphChildOrderManager(p);
List<Object> childList = runOrMaths.getChildList();
for (Object child : childList) {
//if (child instanceof XWPFRun) {
// //处理段落中的文本以及图片
// handleParagraphRun(content, (XWPFRun) child, imageParser);
//} else
if (child instanceof CTOMath) {
// 处理word中存在的公式成mathML格式
handleParagraphOMath(stringBuilder, (CTOMath) child);
if (messageList.size() > 0) {
addItermsConditionsMath(messageList.get(messageList.size() - 1), itemValList, stringBuilder.toString());
}
} else if (child instanceof CTOMathPara) {
//处理word中存在的公式
handleParagraphOMath(stringBuilder, (CTOMathPara) child);
if (messageList.size() > 0) {
addItermsConditionsMath(messageList.get(messageList.size() - 1), itemValList, stringBuilder.toString());
}
}
}
for (XWPFRun xwrun : p.getRuns()) {
VerticalAlign subscript = xwrun.getSubscript();
String smalltext = xwrun.getText(0);
laws-modules/src/main/java/com/jero/modules/split/service/impl/SarFileSplitInfoServiceImpl.java
+1 -1
View File
@@ -97,7 +97,7 @@ public class SarFileSplitInfoServiceImpl extends ServiceImpl<SarFileSplitInfoMap
@Override
public void add(SarFileSplitInfoEO sarFileSplitInfoEO) {
// 唯一校验
uniqueCheck(sarFileSplitInfoEO);
//uniqueCheck(sarFileSplitInfoEO);
LoginUser sysUser = (LoginUser) SecurityUtils.getSubject().getPrincipal();
Date now = new Date();
laws-modules/src/main/java/com/jero/modules/split/util/OmmlUtils.java
+8 -2
View File
@@ -1,5 +1,8 @@
package com.jero.modules.split.util;
import cn.hutool.poi.word.WordUtil;
import org.apache.xmlbeans.impl.jam.provider.ResourcePath;
import javax.xml.transform.Source;
import javax.xml.transform.Transformer;
import javax.xml.transform.TransformerException;
@@ -10,6 +13,7 @@ import java.io.File;
import java.io.IOException;
import java.io.StringReader;
import java.io.StringWriter;
import java.net.URL;
/**
* @author liJiaRao
@@ -23,10 +27,12 @@ public class OmmlUtils {
*/
public static String getMathMLFromNode(String omML) {
//通过word中的xsl转成器解析omml公式格式
//StreamSource xslSource = new StreamSource(new File("src/main/resources/OMML2MML.XSL"));
URL resourceUrl = ResourcePath.class.getClassLoader().getResource("OMML2MML.XSL");
File file = new File(resourceUrl.getPath());
StreamSource xslSource = new StreamSource(WordUtil.class.getResourceAsStream("conventer/OMML2MML.XSL"));
StringWriter writer = new StringWriter();
try {
Transformer t = TransformerFactory.newInstance().newTransformer();
Transformer t = TransformerFactory.newInstance().newTransformer(xslSource);
Source sources = new StreamSource(new StringReader(omML));
StreamResult result = new StreamResult(writer);
t.transform(sources, result);
laws-modules/src/main/java/com/jero/modules/split/util/ParagraphChildOrderManager.java
+112
View File
@@ -1,11 +1,23 @@
package com.jero.modules.split.util;
import cn.hutool.poi.word.WordUtil;
import lombok.extern.slf4j.Slf4j;
import org.apache.poi.xwpf.usermodel.XWPFParagraph;
import org.apache.poi.xwpf.usermodel.XWPFRun;
import org.apache.xmlbeans.XmlCursor;
import org.dom4j.Document;
import org.dom4j.DocumentException;
import org.dom4j.Element;
import org.dom4j.Node;
import org.dom4j.io.SAXReader;
import org.openxmlformats.schemas.officeDocument.x2006.math.CTOMath;
import org.openxmlformats.schemas.officeDocument.x2006.math.CTOMathPara;
import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTP;
import javax.xml.transform.*;
import javax.xml.transform.stream.StreamResult;
import javax.xml.transform.stream.StreamSource;
import java.io.*;
import java.util.ArrayList;
import java.util.LinkedList;
import java.util.List;
@@ -19,6 +31,7 @@ import java.util.Queue;
* @author liJiaRao
* @date 2023-11-09 9:24
*/
@Slf4j
public class ParagraphChildOrderManager {
public static int TYPE_RUN = 1;
public static int TYPE_OMATH = 2;
@@ -84,4 +97,103 @@ public class ParagraphChildOrderManager {
return runsOrMathList;
}
}
public static String parseParagraph(XWPFParagraph xwpfParagraph) {
CTP ctp = xwpfParagraph.getCTP();
String xmlText = ctp.xmlText();
StringBuilder sb = new StringBuilder();
// if (xmlText.contains("<m:oMath>")) {
//段落文本内容
sb.append(xwpfParagraph.getParagraphText());
//段落公式解析
//得到根节点的值
SAXReader saxReader = new SAXReader();
//将String类型的字符串转换成XML文本对象
Document doc = null;
try {
doc = saxReader.read(new ByteArrayInputStream(xmlText.getBytes()));
} catch (DocumentException e) {
e.printStackTrace();
}
Element root = doc.getRootElement();
// 一个段落多个表达式解析
//用xpath得到OMML节点
List<Node> nodes = root.selectNodes("//m:oMath");
if (nodes != null && !nodes.isEmpty()) {
for (Node node : nodes) {
/**
* OMML -> MathML -> LaTex
* Office在安装目录中提供了将OMML转为MathML的xsl工具：MML2OMML.XSL
* MathML转LaTex使用网上找到另一个xsl工具mmltex.xsl。
*/
String xml = node.asXML();
//xml转 mathml
String mathml = convertOMML2MML(xml);
//mathml转latx
String latex = convertMML2Latex(mathml);
sb.append(latex);
log.info("latex表达式：{}",latex);
}
}
log.info("公式个数：{},解析内容：{}",nodes.size(),sb.toString());
return sb.toString();
}
/**
* <p>Description: 将mathml转为latx </p>
* @param mml mathml字符串
* @return
*/
public static String convertMML2Latex(String mml){
mml = mml.substring(mml.indexOf("?>")+2, mml.length()); //去掉xml的头节点
URIResolver r = new URIResolver(){ //设置xls依赖文件的路径
@Override
public Source resolve(String href, String base) throws TransformerException {
File f = new File("/conventer/mml2tex/" + href);
InputStream inputStream = WordUtil.class.getResourceAsStream("/conventer/mml2tex/" + href);
return new StreamSource(inputStream);
}
};
String latex = xslConvert(mml, "/conventer/mml2tex/mmltex.xsl", r);
if(latex != null && latex.length() > 1){
latex = latex.substring(1, latex.length() - 1);
}
return latex;
}
/**
* <p>Description: office xml转为mathml </p>
* @param xml 公式xml
* @return
*/
public static String convertOMML2MML(String xml){
// 进行转换的过程中需要借助这个文件,一般来说本机安装office就会有这个文件,找到就可以
String result = xslConvert(xml, "/conventer/OMML2MML.XSL", null);
return result;
}
/**
* Description: xsl转换器</p>
* @param s 公式xml字符串
* @param xslpath 转换器路径
* @param uriResolver xls依赖文件
* @return
*/
public static String xslConvert(String s, String xslpath, URIResolver uriResolver){
TransformerFactory tFac = TransformerFactory.newInstance();
if(uriResolver != null) {
tFac.setURIResolver(uriResolver);
}
StreamSource xslSource = new StreamSource(WordUtil.class.getResourceAsStream(xslpath));
StringWriter writer = new StringWriter();
try {
Transformer t = tFac.newTransformer(xslSource);
Source source = new StreamSource(new StringReader(s));
Result result = new StreamResult(writer);
t.transform(source, result);
} catch (TransformerException e) {
log.error(e.getMessage(), e);
}
return writer.getBuffer().toString();
}
}