完成[抽取七种文件格式内容]工具类

adc-da-report/src/main/java/com/adc/da/report/constant/ReportConstants.java

@@ -0,0 +1,16 @@
+package com.adc.da.report.constant;
+
+/**
+ * @author ThinkBook
+ */
+public class ReportConstants {
+
+    public static final String FILE_EXTENSIONS_DOC = "doc";
+    public static final String FILE_EXTENSIONS_DOCX = "docx";
+    public static final String FILE_EXTENSIONS_XLS = "xls";
+    public static final String FILE_EXTENSIONS_XLSX = "xlsx";
+    public static final String FILE_EXTENSIONS_PPT = "ppt";
+    public static final String FILE_EXTENSIONS_PPTX = "pptx";
+    public static final String FILE_EXTENSIONS_PDF = "pdf";
+
+}

adc-da-report/src/main/java/com/adc/da/report/util/FileContentUtil.java

@@ -0,0 +1,120 @@
+package com.adc.da.report.util;
+
+import java.io.File;
+import java.io.FileInputStream;
+import java.io.IOException;
+
+import com.adc.da.report.constant.ReportConstants;
+import org.apache.poi.hslf.usermodel.HSLFShape;
+import org.apache.poi.hslf.usermodel.HSLFSlide;
+import org.apache.poi.hslf.usermodel.HSLFTextShape;
+import org.apache.poi.hssf.usermodel.HSSFWorkbook;
+import org.apache.poi.openxml4j.exceptions.InvalidFormatException;
+import org.apache.poi.ss.usermodel.Cell;
+import org.apache.poi.ss.usermodel.Row;
+import org.apache.poi.xslf.usermodel.XMLSlideShow;
+import org.apache.poi.xslf.usermodel.XSLFShape;
+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.hwpf.HWPFDocument;
+import org.apache.poi.hwpf.extractor.WordExtractor;
+import org.apache.poi.xwpf.usermodel.XWPFDocument;
+import org.apache.poi.xwpf.extractor.XWPFWordExtractor;
+import org.apache.poi.hslf.usermodel.HSLFSlideShow;
+import org.apache.poi.hslf.extractor.PowerPointExtractor;
+import org.apache.pdfbox.pdmodel.PDDocument;
+import org.apache.pdfbox.text.PDFTextStripper;
+
+/**
+ * 提取文件中的内容
+ *
+ * @author caihaohan
+ */
+public class FileContentUtil {
+
+    public static String readFileContent(File file) throws IOException {
+        String fileName = file.getName();
+        String fileExtension = fileName.substring(fileName.lastIndexOf(".") + 1);
+        StringBuilder content = new StringBuilder();
+
+        FileInputStream fis = new FileInputStream(file);
+
+        switch (fileExtension) {
+            case ReportConstants.FILE_EXTENSIONS_XLS:
+                HSSFWorkbook workbookXls = new HSSFWorkbook(fis);
+                content = new StringBuilder(readExcelContent(workbookXls));
+                break;
+            case ReportConstants.FILE_EXTENSIONS_XLSX:
+                XSSFWorkbook workbookXlsx = new XSSFWorkbook(fis);
+                content = new StringBuilder(readExcelContent(workbookXlsx));
+                break;
+            case ReportConstants.FILE_EXTENSIONS_DOC:
+                HWPFDocument documentDoc = new HWPFDocument(fis);
+                WordExtractor extractorDoc = new WordExtractor(documentDoc);
+                content = new StringBuilder(extractorDoc.getText());
+                break;
+            case ReportConstants.FILE_EXTENSIONS_DOCX:
+                XWPFDocument documentDocx = new XWPFDocument(fis);
+                XWPFWordExtractor extractorDocx = new XWPFWordExtractor(documentDocx);
+                content = new StringBuilder(extractorDocx.getText());
+                break;
+            case ReportConstants.FILE_EXTENSIONS_PPT:
+                HSLFSlideShow ppt = new HSLFSlideShow(fis);
+                for (HSLFSlide slide : ppt.getSlides()) {
+                    for (HSLFShape shape : slide.getShapes()) {
+                        if (shape instanceof HSLFTextShape) {
+                            HSLFTextShape textShape = (HSLFTextShape) shape;
+                            content.append(textShape.getText()).append("\n");
+                        }
+                    }
+                }
+                break;
+            case ReportConstants.FILE_EXTENSIONS_PPTX:
+                XMLSlideShow pptx = new XMLSlideShow(fis);
+                for (XSLFSlide slide : pptx.getSlides()) {
+                    for (XSLFShape shape : slide.getShapes()) {
+                        if (shape instanceof XSLFTextShape) {
+                            XSLFTextShape textShape = (XSLFTextShape) shape;
+                            content.append(textShape.getText()).append("\n");
+                        }
+                    }
+                }
+                break;
+            case ReportConstants.FILE_EXTENSIONS_PDF:
+                PDDocument document = PDDocument.load(fis);
+                PDFTextStripper stripper = new PDFTextStripper();
+                content = new StringBuilder(stripper.getText(document));
+            default:
+        }
+        fis.close();
+        return content.toString();
+    }
+
+    private static String readExcelContent(org.apache.poi.ss.usermodel.Workbook workbook) {
+        StringBuilder sb = new StringBuilder();
+        int numberOfSheets = workbook.getNumberOfSheets();
+        for (int i = 0; i < numberOfSheets; i++) {
+            org.apache.poi.ss.usermodel.Sheet sheet = workbook.getSheetAt(i);
+            for (Row row : sheet) {
+                for (Cell cell : row) {
+                    sb.append(cell.toString());
+                    sb.append("\t");
+                }
+                sb.append("\n");
+            }
+        }
+        return sb.toString();
+    }
+
+    public static void main(String[] args) {
+        File file = new File("C:\\Users\\ThinkBook\\Desktop\\hzwl-projcets\\测试文件\\testppt.ppt");
+        try {
+            String content = FileContentUtil.readFileContent(file);
+            System.out.println("File content: " + content);
+        } catch (IOException e) {
+            e.printStackTrace();
+        }
+    }
+
+}