feat:添加PPT读取方法

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

@@ -7,11 +7,26 @@ 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.hslf.usermodel.HSLFSlide;
+import org.apache.poi.hslf.usermodel.HSLFSlideShow;
 import org.apache.poi.hwpf.extractor.WordExtractor;
+import org.apache.poi.poifs.filesystem.OfficeXmlFileException;
+import org.apache.poi.sl.extractor.SlideShowExtractor;
+import org.apache.poi.sl.usermodel.Slide;
+import org.apache.poi.sl.usermodel.SlideShow;
 import org.apache.poi.ss.usermodel.*;
+import org.apache.poi.xslf.usermodel.XMLSlideShow;
+import org.apache.poi.xslf.usermodel.XSLFSlide;
+import org.apache.poi.xslf.usermodel.XSLFTextShape;
 import org.apache.poi.xssf.usermodel.XSSFWorkbook;
 import org.apache.poi.xwpf.extractor.XWPFWordExtractor;
 import org.apache.poi.xwpf.usermodel.XWPFDocument;
+import org.openxmlformats.schemas.drawingml.x2006.main.CTRegularTextRun;
+import org.openxmlformats.schemas.drawingml.x2006.main.CTTextBody;
+import org.openxmlformats.schemas.drawingml.x2006.main.CTTextParagraph;
+import org.openxmlformats.schemas.presentationml.x2006.main.CTGroupShape;
+import org.openxmlformats.schemas.presentationml.x2006.main.CTShape;
+import org.openxmlformats.schemas.presentationml.x2006.main.CTSlide;
 import org.springframework.util.Assert;
 
 import java.io.*;
@@ -19,6 +34,7 @@ import java.net.URL;
 import java.net.URLConnection;
 import java.nio.file.Files;
 import java.util.Iterator;
+import java.util.List;
 
 public class DocumentLoad {
 
@@ -66,6 +82,52 @@ public class DocumentLoad {
         }
     }
 
+    public static String loadPPT(File file) {
+        StringBuilder sb = new StringBuilder();
+        try {
+            InputStream is = FileUtil.getInputStream(file);
+            HSLFSlideShow hslfSlideShow = new HSLFSlideShow(is);
+            List<HSLFSlide> slides = hslfSlideShow.getSlides();
+            SlideShowExtractor slideShowExtractor = new SlideShowExtractor(hslfSlideShow);
+            for (HSLFSlide slide : slides) {
+                sb.append("Page:").append(slide.getSlideNumber()).append(StringUtils.LF).append(slideShowExtractor.getText(slide)).append(StringUtils.LF);
+            }
+            slideShowExtractor.close();
+            is.close();
+        } catch (IOException e) {
+            throw new I18nMessageException("exception/file.load.error");
+        } catch (OfficeXmlFileException e) {
+            try {
+                InputStream is = FileUtil.getInputStream(file);
+                XMLSlideShow xmlSlideShow = new XMLSlideShow(is);
+                List<XSLFSlide> slides = xmlSlideShow.getSlides();
+                for (XSLFSlide slide : slides) {
+                    CTSlide rawSlide = slide.getXmlObject();
+                    CTGroupShape spTree = rawSlide.getCSld().getSpTree();
+                    List<CTShape> spList = spTree.getSpList();
+                    for (CTShape shape : spList) {
+                        CTTextBody txBody = shape.getTxBody();
+                        if (null == txBody) {
+                            continue;
+                        }
+                        List<CTTextParagraph> pList = txBody.getPList();
+                        for (CTTextParagraph textParagraph : pList) {
+                            List<CTRegularTextRun> textRuns = textParagraph.getRList();
+                            for (CTRegularTextRun textRun : textRuns) {
+                                sb.append("Page:").append(slide.getSlideNumber()).append(StringUtils.LF).append(textRun.getT()).append(StringUtils.LF);
+                            }
+                        }
+                    }
+                }
+                xmlSlideShow.close();
+                is.close();
+            } catch (IOException e1) {
+                throw new I18nMessageException("exception/file.load.error");
+            }
+        }
+        return sb.toString();
+    }
+
     /**
      * Html To Markdown
      */
@@ -121,6 +183,9 @@ public class DocumentLoad {
                     return loadPDF(file);
                 case "txt":
                     return loadTxt(file);
+                case "ppt":
+                case "pptx":
+                    return loadPPT(file);
                 case "xlsx":
                 case "xls":
                 case "csv":

src/test/java/cn/com/poc/thirdparty/resource/demand/ai/function/ImageOCRFunctionTest.java

@@ -53,4 +53,10 @@ public class ImageOCRFunctionTest {
         File file = new File("C:\\Users\\52747\\Desktop\\List of Question Intents and Standard Answers (IDP&DL) (Dec2024).xlsx");
         System.out.println(DocumentLoad.excelToMarkdown(file));
     }
+
+    @Test
+    public void loadPPT() {
+        System.out.println(DocumentLoad.loadPPT(new File("C:\\Users\\52747\\Documents\\dataset\\中国风.pptx")));
+    }
+
 }