文档拆分，处理在线编辑docx文件document.xml内容问题。
This commit is contained in:
wangzhijiang
-164
@@ -12,8 +12,6 @@ import org.slf4j.LoggerFactory;
|
|||||||
import java.io.*;
|
import java.io.*;
|
||||||
import java.nio.file.*;
|
import java.nio.file.*;
|
||||||
import java.nio.file.attribute.BasicFileAttributes;
|
import java.nio.file.attribute.BasicFileAttributes;
|
||||||
import java.util.zip.ZipEntry;
|
|
||||||
import java.util.zip.ZipOutputStream;
|
|
||||||
|
|
||||||
public class FileUtils {
|
public class FileUtils {
|
||||||
|
|
||||||
@@ -51,167 +49,5 @@ public class FileUtils {
|
|||||||
e.printStackTrace();
|
e.printStackTrace();
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
/**
|
|
||||||
* 处理在线编辑文件中，拆分图片，document.xml里面标签问题。
|
|
||||||
* @return
|
|
||||||
*/
|
|
||||||
public static InputStream docxModifier(InputStream inputStream){
|
|
||||||
InputStream resultIs = null;
|
|
||||||
// 把文件流转成docx文件。存储到本地临时文件
|
|
||||||
byte[] buf = new byte[1024 * 8];
|
|
||||||
String tempFileName = UUIDUtils.randomUUID20();
|
|
||||||
LOGGER.info("处理docx文件中，document.xml文件标签开始，目录名为：" + tempFileName);
|
|
||||||
String filePath = "D:\\opt\\splitTempFile\\" + tempFileName + "\\";
|
|
||||||
String afterFilePath = "D:\\opt\\splitTempFile\\" + tempFileName;
|
|
||||||
File filePathDir = new File(filePath);
|
|
||||||
if (!filePathDir.exists()) {
|
|
||||||
filePathDir.mkdirs();
|
|
||||||
}
|
|
||||||
String tempFileUrl = filePath + tempFileName + ".docx";
|
|
||||||
String unZipFileDir = filePath;
|
|
||||||
try {
|
|
||||||
FileOutputStream fileOut = new FileOutputStream(new File(tempFileUrl));
|
|
||||||
while (true) {
|
|
||||||
int read = 0;
|
|
||||||
if (inputStream != null) {
|
|
||||||
read = inputStream.read(buf);
|
|
||||||
}
|
|
||||||
if (read == -1) {
|
|
||||||
break;
|
|
||||||
}
|
|
||||||
fileOut.write(buf, 0, read);
|
|
||||||
}
|
|
||||||
// 查看文件获取是否成功
|
|
||||||
if (fileOut.getFD().valid() == true) {
|
|
||||||
LOGGER.info("获取文件保存成功");
|
|
||||||
} else {
|
|
||||||
LOGGER.info("获取文件失败");
|
|
||||||
}
|
|
||||||
fileOut.flush();
|
|
||||||
fileOut.close();
|
|
||||||
}catch (Exception ex){
|
|
||||||
ex.printStackTrace();
|
|
||||||
LOGGER.error("文件流转成docx存储到本地失败：" + ex.getMessage());
|
|
||||||
}
|
|
||||||
|
|
||||||
// 将docx文件解压。
|
|
||||||
unpackDocx(tempFileUrl,unZipFileDir);
|
|
||||||
// 解压完，临时文件就没用了，删掉。
|
|
||||||
deleteFolders(tempFileUrl);
|
|
||||||
|
|
||||||
// 获取document.xml文件，解析该文件。
|
|
||||||
String documentXmlUrl = unZipFileDir + "\\word\\document.xml";
|
|
||||||
try {
|
|
||||||
InputStream documentXmlIs = new FileInputStream(new File(documentXmlUrl));
|
|
||||||
ByteArrayOutputStream xmlOutputStream = new ByteArrayOutputStream();
|
|
||||||
copyStream(documentXmlIs, xmlOutputStream);
|
|
||||||
String xmlContent = new String(xmlOutputStream.toByteArray(), "UTF-8");
|
|
||||||
|
|
||||||
// 将标签去掉。
|
|
||||||
xmlContent = xmlContent.replace("<mc:AlternateContent>", "")
|
|
||||||
.replace("<mc:Choice Requires=\"wpg\">", "")
|
|
||||||
.replace("</mc:Choice>", "")
|
|
||||||
.replace("</mc:AlternateContent>", "");
|
|
||||||
LOGGER.info("去掉标签后的XML内容：" + xmlContent);
|
|
||||||
// 放回原位。
|
|
||||||
// 将之前的document.xml文件删掉，创建一个新的document.xml文件。并把替换后的内容写进去。
|
|
||||||
documentXmlIs.close();
|
|
||||||
deleteFolders(documentXmlUrl);
|
|
||||||
|
|
||||||
FileWriter xmlFileWriter = new FileWriter(documentXmlUrl);
|
|
||||||
BufferedWriter bufferedWriter = new BufferedWriter(xmlFileWriter);
|
|
||||||
bufferedWriter.write(xmlContent);
|
|
||||||
bufferedWriter.close();
|
|
||||||
|
|
||||||
}catch (Exception ex){
|
|
||||||
ex.printStackTrace();
|
|
||||||
LOGGER.error("处理document.xml文件失败：" + ex.getMessage());
|
|
||||||
}
|
|
||||||
// 压缩成docx文件，转成文件流返回。
|
|
||||||
compressDocx(afterFilePath, tempFileUrl);
|
|
||||||
try {
|
|
||||||
resultIs = new FileInputStream(tempFileUrl);
|
|
||||||
// resultIs.close();
|
|
||||||
} catch (Exception ex) {
|
|
||||||
ex.printStackTrace();
|
|
||||||
LOGGER.error("获取处理完之后的docx失败：" + ex.getMessage());
|
|
||||||
}
|
|
||||||
// 删除创建的临时文件
|
|
||||||
// deleteFolders(filePath);
|
|
||||||
return resultIs;
|
|
||||||
}
|
|
||||||
|
|
||||||
/**
|
|
||||||
* 解压docx文件
|
|
||||||
* @param docxFilePath docx文件路径
|
|
||||||
* @param destDirPath 解压后的文件夹路径
|
|
||||||
*/
|
|
||||||
public static void unpackDocx(String docxFilePath,String destDirPath){
|
|
||||||
ZipUtil.unZip(new File(docxFilePath), destDirPath);
|
|
||||||
}
|
|
||||||
|
|
||||||
// 辅助方法：复制输入流到输出流
|
|
||||||
private static void copyStream(InputStream inputStream, OutputStream outputStream) throws IOException {
|
|
||||||
byte[] buffer = new byte[1024];
|
|
||||||
int length;
|
|
||||||
while ((length = inputStream.read(buffer)) > 0) {
|
|
||||||
outputStream.write(buffer, 0, length);
|
|
||||||
}
|
|
||||||
inputStream.close();
|
|
||||||
outputStream.flush();
|
|
||||||
}
|
|
||||||
|
|
||||||
|
|
||||||
/**
|
|
||||||
* 压缩docx文件
|
|
||||||
* @param folderPath 文件夹路径
|
|
||||||
* @param docxFilePath 压缩后的docx文件路径。
|
|
||||||
*/
|
|
||||||
public static void compressDocx(String folderPath, String docxFilePath) {
|
|
||||||
|
|
||||||
try {
|
|
||||||
File folder = new File(folderPath);
|
|
||||||
FileOutputStream fos = new FileOutputStream(docxFilePath);
|
|
||||||
ZipOutputStream zos = new ZipOutputStream(fos);
|
|
||||||
|
|
||||||
addFilesToZip(folder, zos, "");
|
|
||||||
|
|
||||||
zos.close();
|
|
||||||
fos.close();
|
|
||||||
} catch (Exception ex){
|
|
||||||
ex.printStackTrace();
|
|
||||||
LOGGER.error("压缩docx文件失败：" + ex.getMessage());
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
public static void addFilesToZip(File folder, ZipOutputStream zos, String parentFolderName) throws IOException {
|
|
||||||
for (File file : folder.listFiles()) {
|
|
||||||
if (file.isDirectory()) {
|
|
||||||
addFilesToZip(file, zos, parentFolderName + file.getName() + "/");
|
|
||||||
continue;
|
|
||||||
}
|
|
||||||
|
|
||||||
byte[] buffer = new byte[1024];
|
|
||||||
FileInputStream fis = new FileInputStream(file);
|
|
||||||
zos.putNextEntry(new ZipEntry(parentFolderName + file.getName()));
|
|
||||||
int length;
|
|
||||||
while ((length = fis.read(buffer)) > 0) {
|
|
||||||
zos.write(buffer, 0, length);
|
|
||||||
}
|
|
||||||
zos.closeEntry();
|
|
||||||
fis.close();
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
public static void main(String[] args) {
|
|
||||||
try {
|
|
||||||
// compressDocx("D:\\opt\\splitTempFile\\GZA688BPVSW4T3Y7YK9K\\","D:\\opt\\splitTempFile\\GZA688BPVSW4T3Y7YK9K\\GZA688BPVSW4T3Y7YK9K.docx");
|
|
||||||
compressDocx("D:\\opt\\splitTempFile\\GZA688BPVSW4T3Y7YK9K", "D:\\opt\\splitTempFile\\GZA688BPVSW4T3Y7YK9K\\output.docx");
|
|
||||||
} catch (Exception e) {
|
|
||||||
e.printStackTrace();
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|||||||
+16
-4
@@ -237,10 +237,6 @@ public class FileSpiltService {
|
|||||||
}
|
}
|
||||||
log.info("下载文档结束=========================================================");
|
log.info("下载文档结束=========================================================");
|
||||||
}
|
}
|
||||||
|
|
||||||
// 处理在线编辑文件中，图片拆分问题。
|
|
||||||
splitFileIs = com.jero.common.util.FileUtils.docxModifier(splitFileIs);
|
|
||||||
|
|
||||||
//记录公式自动编号
|
//记录公式自动编号
|
||||||
MathNumber mathNumber = new MathNumber();
|
MathNumber mathNumber = new MathNumber();
|
||||||
try (InputStream is = splitFileIs;InputStream is1 = splitFileIs1) {
|
try (InputStream is = splitFileIs;InputStream is1 = splitFileIs1) {
|
||||||
@@ -923,6 +919,22 @@ public class FileSpiltService {
|
|||||||
c.selectPath("./*");
|
c.selectPath("./*");
|
||||||
while (c.toNextSelection()) {
|
while (c.toNextSelection()) {
|
||||||
XmlObject o = c.getObject();
|
XmlObject o = c.getObject();
|
||||||
|
if(o.getDomNode().getNodeName().equals("mc:AlternateContent")){
|
||||||
|
String str = o.toString();
|
||||||
|
String imgId = "";
|
||||||
|
Pattern pattern = Pattern.compile("r:embed=\"([^\"]+)\"");
|
||||||
|
Matcher matcher = pattern.matcher(str);
|
||||||
|
// 查找匹配项
|
||||||
|
if (matcher.find()) {
|
||||||
|
// 提取捕获组中的内容
|
||||||
|
String result = matcher.group(1);
|
||||||
|
imgId = result;
|
||||||
|
}
|
||||||
|
if(StringUtils.isNotBlank(imgId)){
|
||||||
|
imageBundleList.add(imgId);
|
||||||
|
continue;
|
||||||
|
}
|
||||||
|
}
|
||||||
//如果子元素是<w:drawing>这样的形式，使用CTDrawing保存图片
|
//如果子元素是<w:drawing>这样的形式，使用CTDrawing保存图片
|
||||||
if (o instanceof CTDrawing) {
|
if (o instanceof CTDrawing) {
|
||||||
CTDrawing drawing = (CTDrawing) o;
|
CTDrawing drawing = (CTDrawing) o;
|
||||||
|
|||||||
Reference in New Issue
Block a user