fix: doc 文件加载

pom.xml

@@ -107,12 +107,6 @@
             <version>8.0.28</version>
         </dependency>
 
-        <dependency>
-            <groupId>org.apache.poi</groupId>
-            <artifactId>poi-ooxml</artifactId>
-            <version>4.1.2</version>
-        </dependency>
-
         <!-- ES       -->
         <dependency>
             <groupId>org.elasticsearch.client</groupId>
@@ -245,11 +239,14 @@
                 </exclusion>
             </exclusions>
         </dependency>
+
+        <!-- https://mvnrepository.com/artifact/org.apache.poi/poi-ooxml -->
         <dependency>
             <groupId>org.apache.poi</groupId>
             <artifactId>poi-ooxml</artifactId>
             <version>4.1.2</version>
         </dependency>
+        <!-- https://mvnrepository.com/artifact/org.apache.poi/poi-ooxml-schemas -->
         <dependency>
             <groupId>org.apache.poi</groupId>
             <artifactId>poi-ooxml-schemas</artifactId>
@@ -260,6 +257,13 @@
             <artifactId>ooxml-schemas</artifactId>
             <version>1.1</version>
         </dependency>
+        <!-- https://mvnrepository.com/artifact/org.apache.poi/poi-scratchpad -->
+        <dependency>
+            <groupId>org.apache.poi</groupId>
+            <artifactId>poi-scratchpad</artifactId>
+            <version>4.1.2</version>
+        </dependency>
+
         <dependency>
             <groupId>org.apache.logging.log4j</groupId>
             <artifactId>log4j-core</artifactId>
@@ -277,11 +281,6 @@
             <version>3.6.0</version>
         </dependency>
 
-        <dependency>
-            <groupId>org.apache.poi</groupId>
-            <artifactId>poi-ooxml</artifactId>
-            <version>4.1.2</version>
-        </dependency>
 
         <!-- https://mvnrepository.com/artifact/cn.hutool/hutool-http -->
         <dependency>

src/main/java/cn/com/poc/common/utils/DocumentLoad.java

@@ -6,7 +6,7 @@ import org.apache.pdfbox.io.RandomAccessBufferedFileInputStream;
 import org.apache.pdfbox.pdfparser.PDFParser;
 import org.apache.pdfbox.pdmodel.PDDocument;
 import org.apache.pdfbox.text.PDFTextStripper;
-//import org.apache.poi.hwpf.HWPFDocument;
+import org.apache.poi.hwpf.extractor.WordExtractor;
 import org.apache.poi.xwpf.extractor.XWPFWordExtractor;
 import org.apache.poi.xwpf.usermodel.XWPFDocument;
 import org.springframework.util.Assert;
@@ -31,7 +31,7 @@ public class DocumentLoad {
                 case "docx":
                     return loadWordDocx(file);
                 case "doc":
-                    return loadWordDocx(file);
+                    return loadWordDoc(file);
                 case "md":
                     return loadMarkDown(file);
                 case "pdf":
@@ -62,12 +62,12 @@ public class DocumentLoad {
         return xwpfWordExtractor.getText();
     }
 
-//    public static String loadWordDoc(File file) throws IOException {
-//        FileInputStream fis = new FileInputStream(file);
-//        HWPFDocument doc = new HWPFDocument(fis);
-//        fis.close();
-//        return doc.getText().toString();
-//    }
+    public static String loadWordDoc(File file) throws IOException {
+        FileInputStream fis = new FileInputStream(file);
+        WordExtractor wordExtractor = new WordExtractor(fis);
+        fis.close();
+        return wordExtractor.getText().toString();
+    }
 
     public static String loadTxt(File file) throws IOException {
         BufferedReader bufferedReader = new BufferedReader(new FileReader(file));