Skip to content

Y
yn-health-science
Commit 142c18f6 authored by 徐俊's avatar 徐俊
Browse files
Options

xujun

parent f0ff946b
Hide whitespace changes
Inline Side-by-side
Showing with 0 additions and 237 deletions
science-admin/src/main/java/com/yiboshi/science/utils/WordToPdfConverter.java deleted 100644 → 0
View file @ f0ff946b
package com.yiboshi.science.utils;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.apache.poi.hwpf.HWPFDocument;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDPage;
import org.apache.pdfbox.pdmodel.PDPageContentStream;
import org.apache.pdfbox.pdmodel.font.PDType0Font;
import org.apache.poi.xwpf.usermodel.XWPFParagraph;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import java.io.*;
import java.util.List;
public class WordToPdfConverter {
private static final Logger logger = LoggerFactory.getLogger(WordToPdfConverter.class);
/**
* 将Word文档转换为PDF
* @param wordPath Word文档路径
* @param pdfPath 输出PDF路径
* @return 转换是否成功
*/
public static boolean convertToPdf(String wordPath, String pdfPath) {
// 检查文件是否存在
File wordFile = new File(wordPath);
if (!wordFile.exists()) {
logger.error("Word文件不存在: {}", wordPath);
return false;
}
// 检查输出目录是否存在
File pdfFile = new File(pdfPath);
File parentDir = pdfFile.getParentFile();
if (!parentDir.exists()) {
parentDir.mkdirs();
}
try {
if (wordPath.toLowerCase().endsWith(".docx")) {
return convertDocxToPdf(wordPath, pdfPath);
} else if (wordPath.toLowerCase().endsWith(".doc")) {
return convertDocToPdf(wordPath, pdfPath);
} else {
logger.error("不支持的文件格式: {}", wordPath);
return false;
}
} catch (Exception e) {
logger.error("Word转PDF失败", e);
return false;
}
}
/**
* 将Word文档转换为PDF（字节数组版本）
* @param wordBytes Word文档的字节数组
* @param pdfPath 输出PDF路径
* @return 转换是否成功
*/
public static boolean convertToPdf(byte[] wordBytes, String pdfPath) {
if (wordBytes == null || wordBytes.length == 0) {
logger.error("Word文档字节数组为空");
return false;
}
// 检查输出目录是否存在
File pdfFile = new File(pdfPath);
File parentDir = pdfFile.getParentFile();
if (!parentDir.exists()) {
parentDir.mkdirs();
}
try {
// 创建临时文件
File tempFile = File.createTempFile("temp", ".docx");
try (FileOutputStream fos = new FileOutputStream(tempFile)) {
fos.write(wordBytes);
}
// 转换文件
boolean result = convertToPdf(tempFile.getAbsolutePath(), pdfPath);
// 删除临时文件
tempFile.delete();
return result;
} catch (Exception e) {
logger.error("Word转PDF失败", e);
return false;
}
}
/**
* 转换DOCX文件到PDF
*/
private static boolean convertDocxToPdf(String docxPath, String pdfPath) throws IOException {
try (FileInputStream fis = new FileInputStream(docxPath);
XWPFDocument document = new XWPFDocument(fis);
PDDocument pdfDocument = new PDDocument()) {
// 获取文档内容
List<XWPFParagraph> paragraphs = document.getParagraphs();
// 创建PDF页面
PDPage page = new PDPage();
pdfDocument.addPage(page);
// 加载字体
PDType0Font font = PDType0Font.load(pdfDocument,
WordToPdfConverter.class.getResourceAsStream("/fonts/simsun.ttc"));
// 创建内容流
try (PDPageContentStream contentStream =
new PDPageContentStream(pdfDocument, page)) {
float y = page.getMediaBox().getHeight() - 50;
// 写入段落
for (XWPFParagraph para : paragraphs) {
String text = para.getText();
contentStream.beginText();
contentStream.setFont(font, 12);
contentStream.newLineAtOffset(50, y);
contentStream.showText(text);
contentStream.endText();
y -= 15;
}
}
// 保存PDF
pdfDocument.save(pdfPath);
return true;
}
}
/**
* 转换DOC文件到PDF
*/
private static boolean convertDocToPdf(String docPath, String pdfPath) throws IOException {
try (FileInputStream fis = new FileInputStream(docPath);
HWPFDocument document = new HWPFDocument(fis);
PDDocument pdfDocument = new PDDocument()) {
// 获取文档内容
String text = document.getDocumentText();
// 创建PDF页面
PDPage page = new PDPage();
pdfDocument.addPage(page);
// 加载字体
PDType0Font font = PDType0Font.load(pdfDocument,
WordToPdfConverter.class.getResourceAsStream("/fonts/simsun.ttc"));
// 创建内容流
try (PDPageContentStream contentStream =
new PDPageContentStream(pdfDocument, page)) {
contentStream.beginText();
contentStream.setFont(font, 12);
contentStream.newLineAtOffset(50, page.getMediaBox().getHeight() - 50);
contentStream.showText(text);
contentStream.endText();
}
// 保存PDF
pdfDocument.save(pdfPath);
return true;
}
}
/**
* 检查文件是否为Word文档
*/
public static boolean isWordFile(String fileName) {
if (fileName == null || fileName.trim().isEmpty()) {
return false;
}
String lowerFileName = fileName.toLowerCase();
return lowerFileName.endsWith(".doc") || lowerFileName.endsWith(".docx");
}
/**
* 从远程URL下载Word文档并转换为PDF
* @param wordUrl Word文档的URL地址
* @param pdfPath 输出PDF路径
* @return 转换是否成功
*/
public static boolean convertUrlToPdf(String wordUrl, String pdfPath) {
if (wordUrl == null || wordUrl.trim().isEmpty()) {
logger.error("Word文档URL为空");
return false;
}
InputStream inputStream = null;
try {
// 创建URL连接
java.net.URL url = new java.net.URL(wordUrl);
java.net.HttpURLConnection conn = (java.net.HttpURLConnection) url.openConnection();
conn.setRequestMethod("GET");
conn.setConnectTimeout(5000);
conn.setReadTimeout(5000);
// 检查响应码
if (conn.getResponseCode() != java.net.HttpURLConnection.HTTP_OK) {
logger.error("下载Word文档失败，HTTP响应码: {}", conn.getResponseCode());
return false;
}
// 读取文件内容
inputStream = conn.getInputStream();
ByteArrayOutputStream outputStream = new ByteArrayOutputStream();
byte[] buffer = new byte[4096];
int bytesRead;
while ((bytesRead = inputStream.read(buffer)) != -1) {
outputStream.write(buffer, 0, bytesRead);
}
// 转换为PDF
byte[] wordBytes = outputStream.toByteArray();
return convertToPdf(wordBytes, pdfPath);
} catch (Exception e) {
logger.error("从URL下载Word文档失败: {}", wordUrl, e);
return false;
} finally {
if (inputStream != null) {
try {
inputStream.close();
} catch (IOException e) {
logger.error("关闭输入流失败", e);
}
}
}
}
}
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment