当前季度和当月招聘会详情

ruoyi-common/pom.xml

@@ -77,6 +77,13 @@
             <artifactId>poi-ooxml</artifactId>
         </dependency>
 
+        <!-- doc文件支持 -->
+        <dependency>
+            <groupId>org.apache.poi</groupId>
+            <artifactId>poi-scratchpad</artifactId>
+            <version>4.1.2</version>
+        </dependency>
+
         <!-- yml解析器 -->
         <dependency>
             <groupId>org.yaml</groupId>

ruoyi-common/src/main/java/com/ruoyi/common/utils/file/DocConverter.java

@@ -0,0 +1,107 @@
+package com.ruoyi.common.utils.file;
+
+import org.apache.poi.hwpf.HWPFDocument;
+import org.apache.poi.hwpf.extractor.WordExtractor;
+import org.apache.poi.xwpf.usermodel.XWPFDocument;
+import org.apache.poi.xwpf.usermodel.XWPFParagraph;
+
+import java.io.*;
+import java.nio.charset.StandardCharsets;
+import java.nio.file.*;
+
+/**
+ * Doc/Docx 文件转换工具
+ * 将 doc/docx 文件批量转换为 txt 文件
+ */
+public class DocConverter {
+
+    /**
+     * 批量转换目录下的 doc/docx 文件为 txt
+     * @param inputDir 输入目录
+     * @param outputDir 输出目录
+     */
+    public static void convertDir(String inputDir, String outputDir) {
+        File outDir = new File(outputDir);
+        if (!outDir.exists()) {
+            outDir.mkdirs();
+        }
+
+        File dir = new File(inputDir);
+        File[] files = dir.listFiles((d, name) ->
+                name.toLowerCase().endsWith(".doc") || name.toLowerCase().endsWith(".docx"));
+
+        if (files == null || files.length == 0) {
+            System.out.println("No doc/docx files found in: " + inputDir);
+            return;
+        }
+
+        System.out.println("Found " + files.length + " files to convert");
+
+        int success = 0;
+        int fail = 0;
+        for (File file : files) {
+            try {
+                String content;
+                if (file.getName().toLowerCase().endsWith(".docx")) {
+                    content = readDocx(file);
+                } else {
+                    content = readDoc(file);
+                }
+
+                String outputName = file.getName().replaceAll("\\.(doc|docx)$", ".txt");
+                Path outputPath = Paths.get(outputDir, outputName);
+                Files.write(outputPath, content.getBytes(StandardCharsets.UTF_8));
+                System.out.println("OK: " + file.getName());
+                success++;
+            } catch (Exception e) {
+                System.out.println("FAIL: " + file.getName() + " - " + e.getMessage());
+                fail++;
+            }
+        }
+        System.out.println("Done! Success: " + success + ", Failed: " + fail);
+    }
+
+    /**
+     * 读取 docx 文件内容
+     */
+    public static String readDocx(File file) throws IOException {
+        try (FileInputStream fis = new FileInputStream(file);
+             XWPFDocument doc = new XWPFDocument(fis)) {
+            StringBuilder sb = new StringBuilder();
+            for (XWPFParagraph para : doc.getParagraphs()) {
+                sb.append(para.getText()).append("\n");
+            }
+            return sb.toString();
+        }
+    }
+
+    /**
+     * 读取 doc 文件内容
+     */
+    public static String readDoc(File file) throws IOException {
+        try (FileInputStream fis = new FileInputStream(file);
+             HWPFDocument doc = new HWPFDocument(fis);
+             WordExtractor extractor = new WordExtractor(doc)) {
+            return extractor.getText();
+        }
+    }
+
+    /**
+     * 读取 doc 或 docx 文件内容
+     */
+    public static String readWord(File file) throws IOException {
+        if (file.getName().toLowerCase().endsWith(".docx")) {
+            return readDocx(file);
+        } else {
+            return readDoc(file);
+        }
+    }
+
+    /**
+     * 命令行入口
+     * 用法: java -cp xxx.jar com.ruoyi.common.utils.file.DocConverter <inputDir> [outputDir]
+     */
+    public static void main(String[] args) {
+        convertDir("D:\\new_to_here\\code\\shz-backend\\政策文件1", "D:\\new_to_here\\code\\shz-backend\\政策文件1\\outputDir");
+    }
+}