FT/foton-slrs-system-rest
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: There is no way the,

Browse Source
This commit is contained in:
super_liu
2022-05-03 12:30:23 +08:00
parent a2cf5bbd77
commit f287e7c52b
1 changed files with 68 additions and 62 deletions
Download Patch File Download Diff File Expand all files Collapse all files
adc-da-slrs/src/main/java/com/adc/da/slrs/sarStandardsInfo/service/impl/SarStandardsInfoServiceImpl.java
+68 -62
View File
@@ -2971,42 +2971,45 @@ public class SarStandardsInfoServiceImpl extends ServiceImpl<SarStandardsInfoDao
String readFilePath = filePath + "/" + attFileEO.getFilePath() + attFileEO.getFileName(); String readFilePath = filePath + "/" + attFileEO.getFilePath() + attFileEO.getFileName();
// String readFilePath = "E:\\上汽企标流程总览.pdf"; // String readFilePath = "E:\\上汽企标流程总览.pdf";
try { try {
// 判断文件是docx还是PDF File existsFile = new File(readFilePath);
if (null != attFileEO.getFileSuffix() && (attFileEO.getFileSuffix().equals("docx") || attFileEO.getFileSuffix().equals("doc") || attFileEO.getFileSuffix().equals("DOC") || attFileEO.getFileSuffix().equals("DOCX") || attFileEO.getFileSuffix().equals("ppt") || attFileEO.getFileSuffix().equals("pptx"))) { if(existsFile.exists()){
if (attFileEO.getFileSuffix().equals("doc") || attFileEO.getFileSuffix().equals("docx") || attFileEO.getFileSuffix().equals("DOC") || attFileEO.getFileSuffix().equals("DOCX")) { // 判断文件是docx还是PDF
BufferedInputStream bis = new BufferedInputStream(new FileInputStream(new File(readFilePath))); if (null != attFileEO.getFileSuffix() && (attFileEO.getFileSuffix().equals("docx") || attFileEO.getFileSuffix().equals("doc") || attFileEO.getFileSuffix().equals("DOC") || attFileEO.getFileSuffix().equals("DOCX") || attFileEO.getFileSuffix().equals("ppt") || attFileEO.getFileSuffix().equals("pptx"))) {
if (FileMagic.valueOf(bis) == FileMagic.OOXML) { if (attFileEO.getFileSuffix().equals("doc") || attFileEO.getFileSuffix().equals("docx") || attFileEO.getFileSuffix().equals("DOC") || attFileEO.getFileSuffix().equals("DOCX")) {
XWPFDocument doc = new XWPFDocument(bis); BufferedInputStream bis = new BufferedInputStream(new FileInputStream(new File(readFilePath)));
XWPFWordExtractor extractor = new XWPFWordExtractor(doc); if (FileMagic.valueOf(bis) == FileMagic.OOXML) {
XWPFDocument doc = new XWPFDocument(bis);
XWPFWordExtractor extractor = new XWPFWordExtractor(doc);
String txt = extractor.getText();
content.append(txt);
extractor.close();
}else {
WordExtractor wordExtractor = new WordExtractor(bis);
String txt = wordExtractor.getText();
content.append(txt);
wordExtractor.close();
}
bis.close();
} else {
OPCPackage opcPackage = XWPFDocument.openPackage(readFilePath);
XWPFWordExtractor extractor = new XWPFWordExtractor(opcPackage);
String txt = extractor.getText(); String txt = extractor.getText();
content.append(txt); content.append(txt);
extractor.close(); opcPackage.close();
}else {
WordExtractor wordExtractor = new WordExtractor(bis);
String txt = wordExtractor.getText();
content.append(txt);
wordExtractor.close();
} }
bis.close();
} else { } else {
OPCPackage opcPackage = XWPFDocument.openPackage(readFilePath); PDDocument document = PDDocument.load(new File(readFilePath));
XWPFWordExtractor extractor = new XWPFWordExtractor(opcPackage); document.getClass();
String txt = extractor.getText(); if (!document.isEncrypted()) {
content.append(txt); PDFTextStripperByArea stripper = new PDFTextStripperByArea();
opcPackage.close(); stripper.setSortByPosition(true);
PDFTextStripper tStripper = new PDFTextStripper();
String pdfFileInText = tStripper.getText(document);
// String[] lines = pdfFileInText.split("\\r?\\n");
content.append(pdfFileInText);
}
document.close();
} }
} else {
PDDocument document = PDDocument.load(new File(readFilePath));
document.getClass();
if (!document.isEncrypted()) {
PDFTextStripperByArea stripper = new PDFTextStripperByArea();
stripper.setSortByPosition(true);
PDFTextStripper tStripper = new PDFTextStripper();
String pdfFileInText = tStripper.getText(document);
// String[] lines = pdfFileInText.split("\\r?\\n");
content.append(pdfFileInText);
}
document.close();
} }
} catch (Exception e) { } catch (Exception e) {
logger.error("搜索中心新增数据读取文档内容时失败"); logger.error("搜索中心新增数据读取文档内容时失败");
@@ -3044,42 +3047,45 @@ public class SarStandardsInfoServiceImpl extends ServiceImpl<SarStandardsInfoDao
} }
String readFilePath = filePath + "/" + attFileEO.getFilePath() + attFileEO.getFileName(); String readFilePath = filePath + "/" + attFileEO.getFilePath() + attFileEO.getFileName();
try { try {
// 判断文件是docx还是PDF File existsFile = new File(readFilePath);
if (null != attFileEO.getFileSuffix() && (attFileEO.getFileSuffix().equals("docx") || attFileEO.getFileSuffix().equals("doc") || attFileEO.getFileSuffix().equals("DOC") || attFileEO.getFileSuffix().equals("DOCX") || attFileEO.getFileSuffix().equals("ppt") || attFileEO.getFileSuffix().equals("pptx"))) { if(existsFile.exists()){
if (attFileEO.getFileSuffix().equals("doc") || attFileEO.getFileSuffix().equals("docx") || attFileEO.getFileSuffix().equals("DOC") || attFileEO.getFileSuffix().equals("DOCX")) { // 判断文件是docx还是PDF
BufferedInputStream bis = new BufferedInputStream(new FileInputStream(new File(readFilePath))); if (null != attFileEO.getFileSuffix() && (attFileEO.getFileSuffix().equals("docx") || attFileEO.getFileSuffix().equals("doc") || attFileEO.getFileSuffix().equals("DOC") || attFileEO.getFileSuffix().equals("DOCX") || attFileEO.getFileSuffix().equals("ppt") || attFileEO.getFileSuffix().equals("pptx"))) {
if (FileMagic.valueOf(bis) == FileMagic.OOXML) { if (attFileEO.getFileSuffix().equals("doc") || attFileEO.getFileSuffix().equals("docx") || attFileEO.getFileSuffix().equals("DOC") || attFileEO.getFileSuffix().equals("DOCX")) {
XWPFDocument doc = new XWPFDocument(bis); BufferedInputStream bis = new BufferedInputStream(new FileInputStream(new File(readFilePath)));
XWPFWordExtractor extractor = new XWPFWordExtractor(doc); if (FileMagic.valueOf(bis) == FileMagic.OOXML) {
XWPFDocument doc = new XWPFDocument(bis);
XWPFWordExtractor extractor = new XWPFWordExtractor(doc);
String txt = extractor.getText();
content.append(txt);
extractor.close();
}else {
WordExtractor wordExtractor = new WordExtractor(bis);
String txt = wordExtractor.getText();
content.append(txt);
wordExtractor.close();
}
bis.close();
} else {
OPCPackage opcPackage = XWPFDocument.openPackage(readFilePath);
XWPFWordExtractor extractor = new XWPFWordExtractor(opcPackage);
String txt = extractor.getText(); String txt = extractor.getText();
content.append(txt); content.append(txt);
extractor.close(); opcPackage.close();
}else {
WordExtractor wordExtractor = new WordExtractor(bis);
String txt = wordExtractor.getText();
content.append(txt);
wordExtractor.close();
} }
bis.close();
} else { } else {
OPCPackage opcPackage = XWPFDocument.openPackage(readFilePath); PDDocument document = PDDocument.load(new File(readFilePath));
XWPFWordExtractor extractor = new XWPFWordExtractor(opcPackage); document.getClass();
String txt = extractor.getText(); if (!document.isEncrypted()) {
content.append(txt); PDFTextStripperByArea stripper = new PDFTextStripperByArea();
opcPackage.close(); stripper.setSortByPosition(true);
PDFTextStripper tStripper = new PDFTextStripper();
String pdfFileInText = tStripper.getText(document);
// String[] lines = pdfFileInText.split("\\r?\\n");
content.append(pdfFileInText);
}
document.close();
} }
} else {
PDDocument document = PDDocument.load(new File(readFilePath));
document.getClass();
if (!document.isEncrypted()) {
PDFTextStripperByArea stripper = new PDFTextStripperByArea();
stripper.setSortByPosition(true);
PDFTextStripper tStripper = new PDFTextStripper();
String pdfFileInText = tStripper.getText(document);
// String[] lines = pdfFileInText.split("\\r?\\n");
content.append(pdfFileInText);
}
document.close();
} }
} catch (Exception e) { } catch (Exception e) {
logger.error("搜索中心修改数据读取文档内容时失败"); logger.error("搜索中心修改数据读取文档内容时失败");