fix: PDF乱码替换

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

@@ -244,7 +244,7 @@ public class DocumentLoad {
         textStripper.setSortByPosition(true);
         stringBuilder.append(textStripper.getText(doc));
         doc.close();
-        return stringBuilder.toString();
+        return stringBuilder.toString().replaceAll("�", StringUtils.EMPTY);
     }
 
 

src/test/java/cn/com/poc/utils/FileUtilsTest.java

@@ -61,4 +61,11 @@ public class FileUtilsTest {
         }
     }
 
+    @Test
+    public void test_pdf() {
+        File file = new File("C:\\Users\\52747\\Documents\\dataset\\迎向AI新纪元：2025企业转型的关键时刻-从2024产业案例看今年生成式AI.pdf");
+        String pdfResult = DocumentLoad.documentToText(file);
+        System.out.println(pdfResult);
+    }
+
 }