From 04a3d4237a4fb811da9e6009ba9c926bf7dbc408 Mon Sep 17 00:00:00 2001 From: Mzaxd Date: Thu, 25 May 2023 14:57:50 +0800 Subject: [PATCH] =?UTF-8?q?fix:=E4=BF=AE=E5=A4=8D=E6=8A=BD=E5=8F=96?= =?UTF-8?q?=E7=A9=BA=E6=96=87=E4=BB=B6=E5=86=85=E5=AE=B9=E6=8A=A5=E9=94=99?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- .../adc/da/report/util/FileContentUtil.java | 95 ++++++++++--------- 1 file changed, 49 insertions(+), 46 deletions(-) diff --git a/adc-da-report/src/main/java/com/adc/da/report/util/FileContentUtil.java b/adc-da-report/src/main/java/com/adc/da/report/util/FileContentUtil.java index 1ba8074..cff0fa3 100644 --- a/adc-da-report/src/main/java/com/adc/da/report/util/FileContentUtil.java +++ b/adc-da-report/src/main/java/com/adc/da/report/util/FileContentUtil.java @@ -5,11 +5,11 @@ import java.io.FileInputStream; import java.io.IOException; import com.adc.da.report.constant.ReportConstants; +import lombok.extern.slf4j.Slf4j; 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; @@ -22,7 +22,6 @@ 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; @@ -31,6 +30,7 @@ import org.apache.pdfbox.text.PDFTextStripper; * * @author caihaohan */ +@Slf4j public class FileContentUtil { public static String readFileContent(File file) throws IOException { @@ -39,55 +39,58 @@ public class FileContentUtil { 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"); + try { + 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_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: + break; + case ReportConstants.FILE_EXTENSIONS_PDF: + PDDocument document = PDDocument.load(fis); + PDFTextStripper stripper = new PDFTextStripper(); + content = new StringBuilder(stripper.getText(document)); + default: + } + } catch (Exception e) { + fis.close(); + log.info("文件内容抽取失败，原因可能是上传的文件为空文件"); } - fis.close(); return content.toString(); }