feat(file): 新增文件哈希去重与文本提取功能- 在多个模块中引入 FileHashUtil 并用于文件上传前的哈希计算

- 优化文件上传逻辑，实现基于哈希的秒传机制
- 新增音频服务中的文本提取方法，支持 txt 和 docx 格式
- 使用流式解析技术处理大文件内容，避免内存溢出
-为 AppVideoController 添加 /extract 接口用于文本内容提取
- 完善文件哈希工具类，增强线程安全性与异常处理
- 调整 SysOssService 的 updateHash 方法以支持复用逻辑- 统一构建 SysOssVo 实体时的哈希字段设置逻辑

fys-admin/src/main/java/com/fuyuanshen/app/controller/AppVideoController.java

@@ -1,5 +1,6 @@
 package com.fuyuanshen.app.controller;
 
+import cn.dev33.satoken.annotation.SaIgnore;
 import com.fuyuanshen.app.service.AudioProcessService;
 import com.fuyuanshen.app.service.VideoProcessService;
 import com.fuyuanshen.common.core.domain.R;
@@ -51,4 +52,13 @@ public class AppVideoController extends BaseController {
     public R<List<String>> uploadAudioTTS(@RequestParam String text) throws IOException {
         return R.ok(audioProcessService.generateStandardPcmData(text));
     }
+
+    /**
+     * 提取文本内容（只支持txt/docx）
+     */
+    @PostMapping(value = "/extract", consumes = MediaType.MULTIPART_FORM_DATA_VALUE)
+    @RepeatSubmit(interval = 2, timeUnit = TimeUnit.SECONDS,message = "请勿重复提交！")
+    public R<String> extract(@RequestParam("file") MultipartFile file) throws Exception {
+        return R.ok("Success",audioProcessService.extract(file));
+    }
 }

fys-admin/src/main/java/com/fuyuanshen/app/service/AudioProcessService.java

@@ -7,11 +7,17 @@ import lombok.extern.slf4j.Slf4j;
 import org.springframework.stereotype.Service;
 import org.springframework.web.multipart.MultipartFile;
 
-import java.io.File;
-import java.io.IOException;
+import javax.xml.stream.XMLInputFactory;
+import javax.xml.stream.XMLStreamConstants;
+import javax.xml.stream.XMLStreamException;
+import javax.xml.stream.XMLStreamReader;
+import java.io.*;
+import java.nio.charset.StandardCharsets;
 import java.nio.file.Files;
 import java.util.Arrays;
 import java.util.List;
+import java.util.zip.ZipEntry;
+import java.util.zip.ZipInputStream;
 
 /**
  * 音频处理服务
@@ -170,5 +176,75 @@ public class AudioProcessService {
         }
     }
 
+    /**
+     * 提取文本
+     */
+    public String extract(MultipartFile file) throws Exception {
+        String name = file.getOriginalFilename();
+        if (name == null ||
+                (!name.endsWith(".txt") && !name.endsWith(".docx"))) {
+            throw new IllegalArgumentException("仅支持 .txt 或 .docx");
+        }
+        if (file.getSize() > MAX_AUDIO_SIZE) {
+            throw new IllegalArgumentException("文件超过5MB");
+        }
+
+        String text;
+        /* 全程流式，不落地磁盘，不一次性读字节数组 */
+        try (InputStream in = file.getInputStream()) {
+            if (name.endsWith(".txt")) {
+                text = readTxt(in);
+            } else {
+                text = readDocx(in);
+            }
+        }
+        return text;
+    }
+
+    /* ---------- txt：按行读，StringBuilder 复用 ---------- */
+    private String readTxt(InputStream in) throws IOException {
+        BufferedReader br = new BufferedReader(new InputStreamReader(in, StandardCharsets.UTF_8));
+        StringBuilder sb = new StringBuilder(4096);
+        String line;
+        while ((line = br.readLine()) != null) {
+            sb.append(line).append('\n');
+        }
+        return sb.toString();
+    }
+
+    /* ---------- docx：ZipInputStream 只扫 document.xml ---------- */
+    private String readDocx(InputStream in) throws IOException {
+        ZipInputStream zin = new ZipInputStream(in);
+        ZipEntry e;
+        while ((e = zin.getNextEntry()) != null) {
+            if ("word/document.xml".equals(e.getName())) {
+                return staxExtract(zin);   // 流式读 XML
+            }
+        }
+        return "";
+    }
+
+    /* ---------- StAX 流式提取 <w:t> ---------- */
+    private String staxExtract(InputStream xml) throws IOException {
+        XMLStreamReader r = null;
+        StringBuilder sb = new StringBuilder(4096);
+        try {
+            //System.out.println(new String(xml.readAllBytes()));
+            r = XMLInputFactory.newInstance().createXMLStreamReader(xml);
+            while (r.hasNext()) {
+                if (r.next() == XMLStreamConstants.START_ELEMENT &&
+                        "t".equals(r.getLocalName())) {
+                    String elementText = r.getElementText();
+                    sb.append(elementText);
+                }
+            }
+        } catch (XMLStreamException ex) {
+            throw new IOException(ex);
+        } finally {
+            if (r != null) try { r.close(); } catch (XMLStreamException ignore) {}
+        }
+        return sb.toString();
+    }
+
 
 }