上传备份

.gitignore

@@ -0,0 +1,21 @@
+target/
+pom.xml.tag
+pom.xml.releaseBackup
+pom.xml.versionsBackup
+pom.xml.next
+release.properties
+/.idea
+*.iml
+/.settings
+/bin
+/gen
+/build
+/gradle
+/classes
+.classpath
+.project
+*.gradle
+gradlew
+local.properties
+node_modules/
+data/

pom.xml

@@ -0,0 +1,70 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project xmlns="http://maven.apache.org/POM/4.0.0"
+         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
+    <modelVersion>4.0.0</modelVersion>
+    <groupId>xyz.wbsite</groupId>
+    <artifactId>starter-pdf2doc</artifactId>
+    <version>0.0.1-SNAPSHOT</version>
+    <packaging>jar</packaging>
+
+    <properties>
+        <java.version>8</java.version>
+    </properties>
+
+    <repositories>
+        <!-- 将中央仓库地址指向阿里云聚合仓库,提高下载速度 -->
+        <repository>
+            <id>central</id>
+            <name>Central Repository</name>
+            <layout>default</layout>
+            <url>https://maven.aliyun.com/repository/public</url>
+        </repository>
+    </repositories>
+    <pluginRepositories>
+        <!-- 将插件的仓库指向阿里云聚合仓库，解决低版本maven下载插件异常或提高下载速度 -->
+        <pluginRepository>
+            <id>central</id>
+            <name>Central Repository</name>
+            <url>https://maven.aliyun.com/repository/public</url>
+            <layout>default</layout>
+        </pluginRepository>
+    </pluginRepositories>
+
+    <build>
+        <plugins>
+            <plugin>
+                <groupId>org.apache.maven.plugins</groupId>
+                <artifactId>maven-compiler-plugin</artifactId>
+                <configuration>
+                    <source>8</source>
+                    <target>8</target>
+                </configuration>
+            </plugin>
+        </plugins>
+    </build>
+
+    <dependencies>
+        <!-- 糊涂工具，包含常用API，避免重复造轮子 -->
+        <dependency>
+            <groupId>cn.hutool</groupId>
+            <artifactId>hutool-all</artifactId>
+            <version>5.8.24</version>
+        </dependency>
+
+        <dependency>
+            <groupId>spire</groupId>
+            <artifactId>doc</artifactId>
+            <version>1.0</version>
+            <scope>system</scope>
+            <systemPath>${project.basedir}/src/main/resources/lib/Spire.Doc.jar</systemPath>
+        </dependency>
+        <dependency>
+            <groupId>spire</groupId>
+            <artifactId>pdf</artifactId>
+            <version>1.0</version>
+            <scope>system</scope>
+            <systemPath>${project.basedir}/src/main/resources/lib/Spire.Pdf.jar</systemPath>
+        </dependency>
+    </dependencies>
+</project>

src/main/java/xyz/wbsite/pdf2doc/Demo.java

@@ -0,0 +1,9 @@
+package xyz.wbsite.pdf2doc;
+
+public class Demo {
+	public static void main(String[] args) {
+		String res = new PdfToWord().pdftoword("D:\\材料\\8、相关标准\\GB6944-2012 危险货物分类和品名编号.pdf");
+		System.out.println(res);
+	}
+	
+}

src/main/java/xyz/wbsite/pdf2doc/FileDeleteTest.java

@@ -0,0 +1,22 @@
+package xyz.wbsite.pdf2doc;
+
+import java.io.File;
+
+public class FileDeleteTest {
+	//删除文件和目录
+	public void clearFiles(String workspaceRootPath){
+	     File file = new File(workspaceRootPath);
+	     if(file.exists()){
+	          deleteFile(file);
+	     }
+	}
+	public void deleteFile(File file){
+	     if(file.isDirectory()){
+	          File[] files = file.listFiles();
+	          for(int i=0; i<files.length; i++){
+	               deleteFile(files[i]);
+	          }
+	     }
+	     file.delete();
+	}
+}

src/main/java/xyz/wbsite/pdf2doc/MergeWordDocument.java

@@ -0,0 +1,33 @@
+package xyz.wbsite.pdf2doc;
+
+import com.spire.doc.Document;
+import com.spire.doc.FileFormat;
+
+import java.io.File;
+
+public class MergeWordDocument {
+	
+    public static boolean merge(String docPath,String desPath){
+
+    	File[] fs = getSplitFiles(docPath);
+    	System.out.println(docPath);
+		Document document = new Document(docPath+"test0.docx");
+		
+		for(int i=1;i<fs.length;i++) {
+			 document.insertTextFromFile(docPath+"test"+i+".docx",FileFormat.Docx_2013);
+		}
+		//第四步：对合并的doc进行保存2
+		document.saveToFile(desPath);
+		return true;       
+    }
+	// 取得某一路径下所有的pdf
+	private static File[] getSplitFiles(String path) {
+		File f = new File(path);
+		File[] fs = f.listFiles();
+		if (fs == null) {
+			return null;
+		}
+		return fs;
+	}
+
+}

src/main/java/xyz/wbsite/pdf2doc/PdfToWord.java

@@ -0,0 +1,112 @@
+package xyz.wbsite.pdf2doc;
+
+import com.spire.pdf.FileFormat;
+import com.spire.pdf.PdfDocument;
+import com.spire.pdf.widget.PdfPageCollection;
+
+import java.io.File;
+
+
+public class PdfToWord {
+
+    // 涉及到的路径
+    // 1、pdf所在的路径，真实测试种是从外部引入的
+
+    // 2、如果是大文件，需要进行切分，保存的子pdf路径
+    String splitPath = "./split/";
+
+    // 3、如果是大文件，需要对子pdf文件一个一个进行转化
+    String docPath = "./doc/";
+
+    public String pdftoword(String srcPath) {
+        // 4、最终生成的doc所在的目录，默认是和引入的一个地方，开源时对外提供下载的接口。
+        String desPath = srcPath.substring(0, srcPath.length() - 4) + ".docx";
+        boolean result = false;
+        try {
+            // 0、判断输入的是否是pdf文件
+            //第一步：判断输入的是否合法
+            boolean flag = isPDFFile(srcPath);
+            //第二步：在输入的路径下新建文件夹
+            boolean flag1 = create();
+
+            if (flag && flag1) {
+                // 1、加载pdf
+                PdfDocument pdf = new PdfDocument();
+                pdf.loadFromFile(srcPath);
+                PdfPageCollection num = pdf.getPages();
+
+                // 2、如果pdf的页数小于11，那么直接进行转化
+                if (num.getCount() <= 10) {
+                    pdf.saveToFile(desPath, FileFormat.DOCX);
+                }
+                // 3、否则输入的页数比较多，就开始进行切分再转化
+                else {
+                    // 第一步：将其进行切分,每页一张pdf
+                    pdf.split(splitPath + "test{0}.pdf", 0);
+
+                    // 第二步：将切分的pdf，一个一个进行转换
+                    File[] fs = getSplitFiles(splitPath);
+                    for (int i = 0; i < fs.length; i++) {
+                        PdfDocument sonpdf = new PdfDocument();
+                        sonpdf.loadFromFile(fs[i].getAbsolutePath());
+                        sonpdf.saveToFile(docPath + fs[i].getName().substring(0, fs[i].getName().length() - 4) + ".docx", FileFormat.DOCX);
+                    }
+                    //第三步：对转化的doc文档进行合并，合并成一个大的word
+                    try {
+                        result = MergeWordDocument.merge(docPath, desPath);
+                        System.out.println(result);
+                    } catch (Exception e) {
+                        e.printStackTrace();
+                    }
+
+                }
+            } else {
+                System.out.println("输入的不是pdf文件");
+                return "输入的不是pdf文件";
+            }
+        } catch (Exception e) {
+            e.printStackTrace();
+        } finally {
+            //4、把刚刚缓存的split和doc删除
+            if (result == true) {
+                new FileDeleteTest().clearFiles(splitPath);
+                new FileDeleteTest().clearFiles(docPath);
+            }
+        }
+        return "转换成功";
+    }
+
+
+    private boolean create() {
+        File f = new File(splitPath);
+        File f1 = new File(docPath);
+        if (!f.exists()) {
+            f.mkdirs();
+        }
+        if (!f.exists()) {
+            f1.mkdirs();
+        }
+        return true;
+    }
+
+    // 判断是否是pdf文件
+    private boolean isPDFFile(String srcPath2) {
+        File file = new File(srcPath2);
+        String filename = file.getName();
+        if (filename.endsWith(".pdf")) {
+            return true;
+        }
+        return false;
+    }
+
+    // 取得某一路径下所有的pdf
+    private File[] getSplitFiles(String path) {
+        File f = new File(path);
+        File[] fs = f.listFiles();
+        if (fs == null) {
+            return null;
+        }
+        return fs;
+    }
+
+}