Use Apache POI to convert Word document to PDF, PDF to image
I found a lot of online examples, but the writing was very complicated and unusable. It took me a day to sort it out. Don’t talk nonsense, just upload the code
Required dependencies
<dependency> <groupId>org.apache.pdfbox</groupId> <artifactId>pdfbox</artifactId> <version>2.0.27</version> </dependency> <dependency> <groupId>org.apache.pdfbox</groupId> <artifactId>pdfbox-tools</artifactId> <version>2.0.27</version> </dependency> <!-- fill word--> <dependency> <groupId>org.apache.poi</groupId> <artifactId>poi</artifactId> <version>3.17</version> </dependency> <dependency> <groupId>org.apache.poi</groupId> <artifactId>poi-ooxml-schemas</artifactId> <version>3.17</version> </dependency> <!--word to pdf, fill word--> <dependency> <groupId>org.apache.poi</groupId> <artifactId>poi-ooxml</artifactId> <version>3.17</version> </dependency> <!--word to pdf--> <dependency> <groupId>fr.opensagres.xdocreport</groupId> <artifactId>fr.opensagres.poi.xwpf.converter.pdf-gae</artifactId> <version>2.0.1</version> </dependency> <dependency> <groupId>com.documents4j</groupId> <artifactId>documents4j-local</artifactId> <version>1.0.3</version> </dependency> <dependency> <groupId>com.documents4j</groupId> <artifactId>documents4j-transformer-msoffice-word</artifactId> <version>1.0.3</version> </dependency> <!--pdf to picture--> <dependency> <groupId>org.apache.pdfbox</groupId> <artifactId>pdfbox</artifactId> <version>3.0.0-alpha2</version> </dependency> <dependency> <groupId>org.apache.pdfbox</groupId> <artifactId>fontbox</artifactId> <version>3.0.0-alpha2</version> </dependency>
Tool class
package com.xxx.common.utils;
import java.awt.image.BufferedImage;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import com.documents4j.api.DocumentType;
import com.documents4j.api.IConverter;
import com.documents4j.job.LocalConverter;
import lombok.extern.slf4j.Slf4j;
import org.apache.pdfbox.Loader;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.rendering.PDFRenderer;
import org.apache.poi.xwpf.usermodel.*;
import javax.imageio.ImageIO;
import java.io.*;
import java.util.Date;
import java.util.Iterator;
import java.util.List;
import java.util.Map;
/**
* @description: tool class
*/
@Slf4j
public class WordUtils {<!-- -->
/**
* @Author: RedRush
* @Date: 2023/2/20 17:42
* @param path template path
* @param outPath output path
* @param dict The collection of information that needs to be replaced
* @Return: boolean
* @description: Compile the text and tables in the template according to the dict
*/
public static void compile(String path, String outPath, Map<String, Object> dict) throws Exception{<!-- -->
FileInputStream is = new FileInputStream(path);
XWPFDocument document = new XWPFDocument(is);
if (dict != null) {<!-- -->
// Replace text outside the table (text only)
WordUtils.compileText(document, dict);
// replace the text object in the table
WordUtils.compileTable(document, dict);
}
File f = new File(outPath. substring(0, outPath. lastIndexOf(File. separator)));
if(!f.exists()){<!-- -->
f. mkdirs();
}
FileOutputStream out = new FileOutputStream(outPath);
document. write(out);
}
/***
* @Description : replace paragraph text
* @param document docx parsing object
* @param dict The collection of information that needs to be replaced
* @return void
* @Date 2022/11/17 17:22
*/
public static void compileText(XWPFDocument document, Map<String, Object> dict) {<!-- -->
// Get the collection of paragraphs
Iterator<XWPFParagraph> iterator = document. getParagraphsIterator();
XWPFParagraph paragraph = null;
while (iterator.hasNext()) {<!-- -->
paragraph = iterator. next();
// Determine whether this paragraph needs to be replaced
if (checkText(paragraph. getText())) {<!-- -->
replaceValue(paragraph, dict);
}
}
}
/***
* @Description : replace the text in the table
* @param document
* @param dict The collection of information that needs to be replaced
* @return void
* @Date 2022/11/18 11:29
*/
public static void compileTable(XWPFDocument document, Map<String, Object> dict) {<!-- -->
// Get the form of the file
Iterator<XWPFTable> tableList = document. getTablesIterator();
XWPFTable table;
List<XWPFTableRow> rows;
List<XWPFTableCell> cells;
// Loop through all the text that needs to be replaced and replace it
while (tableList.hasNext()) {<!-- -->
table = tableList. next();
if (checkText(table.getText())) {<!-- -->
rows = table. getRows();
// Traverse the table and replace the template
for (XWPFTableRow row : rows) {<!-- -->
cells = row. getTableCells();
for (XWPFTableCell cell : cells) {<!-- -->
// Determine whether the cell needs to be replaced
if (checkText(cell. getText())) {<!-- -->
List<XWPFParagraph> paragraphs = cell. getParagraphs();
for (XWPFParagraph paragraph : paragraphs) {<!-- -->
replaceValue(paragraph, dict);
}
}
}
}
}
}
}
/**
* @Author: RedRush
* @Date: 2023/2/20 17:31
* @param paragraph word text
* @param dict The collection of information that needs to be replaced
* @description: replacement string
*/
private static void replaceValue(XWPFParagraph paragraph, Map<String, Object> dict) {<!-- -->
String nextLine;
List<XWPFRun> runs = paragraph. getRuns();
for (int i = 0; i < runs. size(); i ++ ) {<!-- -->
// read current line
String readLine = runs. get(i). text();
// System.out.println("readLine:" + readLine);
// Skip if empty or does not contain the target string
if(StringUtils.isEmpty(readLine) || !readLine.contains("$")) continue;
// Initialize the result set
StringBuffer sb = new StringBuffer();
// Loop through the template string of the current row
while (readLine. contains("$")){<!-- -->
// Get the string on the left side of the template string
int left;
if(readLine. contains("${")){<!-- -->
left = readLine. indexOf("${");
} else {<!-- -->
if(runs. size() < i + 1){<!-- -->
break;
}
nextLine = runs. get(i + 1). text();
if(!nextLine.startsWith("{")) break;
readLine += nextLine;
paragraph. removeRun(i + 1);
left = readLine. indexOf("${");
}
sb.append(readLine.substring(0, left));
// Get the right side of the template string
while(runs.size() >= i + 1 & amp; & amp; !readLine.contains("}")){<!-- -->
nextLine = runs. get(i + 1). text();
readLine += nextLine;
paragraph. removeRun(i + 1);
}
int right = readLine. indexOf("}");
if(right == -1) break;
// Replace the template string [if it does not exist in the dictionary, it will be replaced with an empty string]
sb.append(dict.getOrDefault(readLine.substring(left, right + 1), ""));
if(right + 1 < readLine. length()){<!-- -->
sb. append(readLine. substring(right + 1));
}
readLine = sb. toString();
}
runs.get(i).setText(sb.toString(), 0);
}
}
/***
* @Description : Check if the text contains the specified character (here "$")
* @param text
* @return boolean
* @Date 2022/11/17 17:22
*/
private static boolean checkText(String text) {<!-- -->
return text. contains("$");
}
/**
* Convert word to pdf through documents4j
*
* @param sourcePath source file address such as /root/example.doc
* @param targetPath target file address such as /root/example.pdf
*/
public static void documents4jWordToPdf(String sourcePath, String targetPath) {<!-- -->
File inputWord = new File(sourcePath);
File outputFile = new File(targetPath);
try {<!-- -->
InputStream docxInputStream = new FileInputStream(inputWord);
OutputStream outputStream = new FileOutputStream(outputFile);
IConverter converter = LocalConverter.builder().build();
boolean execute = converter. convert(docxInputStream)
.as(DocumentType.DOCX)
.to(outputStream)
.as(DocumentType.PDF).schedule().get();
outputStream. close();
docxInputStream. close();
log.info("Conversion completed targetPath = {}", outputFile.getAbsolutePath());
System.out.println("Conversion completed targetPath = " + outputFile.getAbsolutePath());
converter. shutDown();
return;
} catch (Exception e) {<!-- -->
log.error("[documents4J] word to pdf failed: {}", e.toString());
}
}
/**
* Convert the generated Word document to PDF format
* @param wordPath Word document path
* @param pdfPath generated PDF path
*/
public static void convertToPDF(String wordPath , String pdfPath ) {<!-- -->
documents4jWordToPdf(wordPath, pdfPath);
}
/**
* Convert PDF files to pictures
* @param sourcePath PDF file address
*/
public void execute(String sourcePath) {<!-- -->
File file = new File(sourcePath);
String path = file. getAbsolutePath();
String targetPathNoExt = path.substring(0, path.lastIndexOf("."));
try {<!-- -->
PDDocument doc = Loader.loadPDF(file);
PDFRenderer renderer = new PDFRenderer(doc);
int pageCount = doc. getNumberOfPages();
for (int i = 0; i < pageCount; i ++ ) {<!-- -->
// System.out.println("Current page" + (i + 1));
BufferedImage image = renderer.renderImageWithDPI(i, 296);
// BufferedImage image = renderer. renderImage(i, 2.5f);
ImageIO.write(image, "PNG", new File(targetPathNoExt + "_" + i + ".png"));
}
} catch (IOException e) {<!-- -->
e.printStackTrace();
}
}
}
Test Code
/**
* Fill word and generate pdf
* @throws Exception
*/
@Test
public void fillTemplate() throws Exception {<!-- -->
//Fill word needs to be defined in the document: ${name}
Map<String, Object> strData = new HashMap<>();
strData.put("${name}", "xxx"); //Customer name
strData.put("${createDate}", DateUtil.format(DateUtil.date(), DatePattern.CHINESE_DATE_PATTERN));
strData.put("${openingAccountBalance}", 121);//The opening account balance (yuan)
strData.put("${rechargeAmount}", 121);//New recharge amount (yuan)
strData.put("${totalConsumptionAmount}", 121);//Consumption during this account period (yuan)
strData.put("${balanceAfterSettlement}", 121);//End account balance (yuan)
String readPath = "C:\Users\gukt\Desktop\template.docx"; //word template
String outPath = "C:\Users\gukt\Desktop\output.docx"; // output fill word path
String outPdfPath = "C:\Users\gukt\Desktop\output.pdf"; //Enter word to pdf path
WordUtils.compile(readPath, outPath, strData); //Fill in word, if you only want to convert word to pdf, you don’t need it here
// conversion operation, can be used alone
WordUtils.convertToPDF(outPath,outPdfPath); //word to pdf
WordUtils.execute(outPdfPath); //pdf to picture png
}