本文介绍了如何使用Doc2Docx工具将Java文档格式转换为Docx格式，并提供了替换水印的步骤，附带相关用例下载。
Doc2Docx 主函数
import java.io.File;
import java.util.HashMap;
import java.util.Map;
import com.aspose.words.Document;
public class Doc2Docx {
public static void main(String[] args) {
String docFile = "E:\\poi\\2.doc";
String docxFile = "E:\\poi\\x2.docx";
doc2docx(docFile, docxFile);
}
public static void doc2docx(String docFile, String docxFile) {
Document doc;
try {
String tempFile = docxFile.substring(0, docxFile.lastIndexOf(".")) + "_temp"
+ docxFile.substring(docxFile.lastIndexOf("."), docxFile.length());
doc = new Document(docFile);
doc.save(tempFile);
Map<String, String> map = new HashMap<String, String>();
map.put("Evaluation Only. Created with Aspose.Words. Copyright 2003-2018 Aspose Pty Ltd.", "");
// 使用 aspose不使用license.xml会产生,替换水印的文字
DocxReplace.replaceAndGenerateWord(tempFile, docxFile, map);
// 删除临时文件
forceDelete(new File(tempFile));
} catch (Exception e1) {
e1.printStackTrace();
}
}
public static boolean forceDelete(File file) {
boolean result = file.delete();
int tryCount = 0;
while (!result && tryCount++ < 10) {
System.gc();
result = file.delete();
}
return result;
}
}
DocxReplace 替换水印
import java.io.File;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.Iterator;
import java.util.List;
import java.util.Map;
import java.util.Map.Entry;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import org.apache.commons.lang.StringUtils;
import org.apache.poi.POIXMLDocument;
import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.usermodel.Range;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.apache.poi.xwpf.usermodel.XWPFParagraph;
import org.apache.poi.xwpf.usermodel.XWPFRun;
import org.apache.poi.xwpf.usermodel.XWPFTable;
import org.apache.poi.xwpf.usermodel.XWPFTableCell;
import org.apache.poi.xwpf.usermodel.XWPFTableRow;
public class DocxReplace {
// 返回Docx中需要替换的特殊字符，没有重复项
// 推荐传入正则表达式参数"\\$\\{[^{}]+\\}"
public ArrayList<String> getReplaceElementsInWord(String filePath,
String regex) {
String[] p = filePath.split("\\.");
if (p.length > 0) {// 判断文件有无扩展名
// 比较文件扩展名
if (p[p.length - 1].equalsIgnoreCase("doc")) {
ArrayList<String> al = new ArrayList<>();
File file = new File(filePath);
HWPFDocument document = null;
try {
InputStream is = new FileInputStream(file);
document = new HWPFDocument(is);
} catch (FileNotFoundException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
Range range = document.getRange();
String rangeText = range.text();
CharSequence cs = rangeText.subSequence(0, rangeText.length());
Pattern pattern = Pattern.compile(regex);
Matcher matcher = pattern.matcher(cs);
int startPosition = 0;
while (matcher.find(startPosition)) {
if (!al.contains(matcher.group())) {
al.add(matcher.group());
}
startPosition = matcher.end();
}
return al;
} else if (p[p.length - 1].equalsIgnoreCase("docx")) {
ArrayList<String> al = new ArrayList<>();
XWPFDocument document = null;
try {
document = new XWPFDocument(
POIXMLDocument.openPackage(filePath));
} catch (IOException e) {
e.printStackTrace();
}
// 遍历段落
Iterator<XWPFParagraph> itPara = document
.getParagraphsIterator();
while (itPara.hasNext()) {
XWPFParagraph paragraph = (XWPFParagraph) itPara.next();
String paragraphString = paragraph.getText();
CharSequence cs = paragraphString.subSequence(0,
paragraphString.length());
Pattern pattern = Pattern.compile(regex);
Matcher matcher = pattern.matcher(cs);
int startPosition = 0;
while (matcher.find(startPosition)) {
if (!al.contains(matcher.group())) {
al.add(matcher.group());
}
startPosition = matcher.end();
}
}
// 遍历表
Iterator<XWPFTable> itTable = document.getTablesIterator();
while (itTable.hasNext()) {
XWPFTable table = (XWPFTable) itTable.next();
int rcount = table.getNumberOfRows();
for (int i = 0; i < rcount; i++) {
XWPFTableRow row = table.getRow(i);
List<XWPFTableCell> cells = row.getTableCells();
for (XWPFTableCell cell : cells) {
String cellText = "";
cellText = cell.getText();
CharSequence cs = cellText.subSequence(0,
cellText.length());
Pattern pattern = Pattern.compile(regex);
Matcher matcher = pattern.matcher(cs);
int startPosition = 0;
while (matcher.find(startPosition)) {
if (!al.contains(matcher.group())) {
al.add(matcher.group());
}
startPosition = matcher.end();
}
}
}
}
return al;
} else {
return null;
}
} else {
return null;
}
}
// 替换word中需要替换的特殊字符
public static boolean replaceAndGenerateWord(String srcPath,
String destPath, Map<String, String> map) {
String[] sp = srcPath.split("\\.");
String[] dp = destPath.split("\\.");
if ((sp.length > 0) && (dp.length > 0)) {// 判断文件有无扩展名
// 比较文件扩展名
if (sp[sp.length - 1].equalsIgnoreCase("docx")) {
try {
XWPFDocument document = new XWPFDocument(
POIXMLDocument.openPackage(srcPath));
// 替换段落中的指定文字
Iterator<XWPFParagraph> itPara = document
.getParagraphsIterator();
while (itPara.hasNext()) {
XWPFParagraph paragraph = (XWPFParagraph) itPara.next();
List<XWPFRun> runs = paragraph.getRuns();
for (int i = 0; i < runs.size(); i++) {
String oneparaString = runs.get(i).getText(
runs.get(i).getTextPosition());
for (Map.Entry<String, String> entry : map
.entrySet()) {
if(StringUtils.isNotBlank(oneparaString) && oneparaString.indexOf(entry.getKey())!=-1){
oneparaString = oneparaString.replace(
entry.getKey(), entry.getValue());
runs.get(i).setText(oneparaString, 0);
}
}
}
}
// 替换表格中的指定文字
Iterator<XWPFTable> itTable = document.getTablesIterator();
while (itTable.hasNext()) {
XWPFTable table = (XWPFTable) itTable.next();
int rcount = table.getNumberOfRows();
for (int i = 0; i < rcount; i++) {
XWPFTableRow row = table.getRow(i);
List<XWPFTableCell> cells = row.getTableCells();
for (XWPFTableCell cell : cells) {
String cellTextString = cell.getText();
for (Entry<String, String> e : map.entrySet()) {
if (cellTextString.contains(e.getKey())) {
cellTextString = cellTextString
.replace(e.getKey(),
e.getValue());
cell.removeParagraph(0);
cell.setText(cellTextString);
cell.setColor(cell.getColor());
}
}
}
}
}
FileOutputStream outStream = null;
outStream = new FileOutputStream(destPath);
document.write(outStream);
outStream.close();
return true;
} catch (Exception e) {
e.printStackTrace();
return false;
}
} else
// doc只能生成doc，如果生成docx会出错
if ((sp[sp.length - 1].equalsIgnoreCase("doc"))
&& (dp[dp.length - 1].equalsIgnoreCase("doc"))) {
HWPFDocument document = null;
try {
document = new HWPFDocument(new FileInputStream(srcPath));
Range range = document.getRange();
for (Map.Entry<String, String> entry : map.entrySet()) {
range.replaceText(entry.getKey(), entry.getValue());
}
FileOutputStream outStream = null;
outStream = new FileOutputStream(destPath);
document.write(outStream);
outStream.close();
return true;
} catch (FileNotFoundException e) {
e.printStackTrace();
return false;
} catch (IOException e) {
e.printStackTrace();
return false;
}
} else {
return false;
}
} else {
return false;
}
}
}
扫一扫
6959
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
