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

Merge branch 'develop_master' into FOTON

Browse Source
This commit is contained in:
super_liu
2022-05-03 13:22:52 +08:00
parent 9e344f00bd 984c9d645c
commit ad21d53503
1 changed files with 70 additions and 64 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
+70 -64
View File
@@ -3001,47 +3001,50 @@ public class SarStandardsInfoServiceImpl extends ServiceImpl<SarStandardsInfoDao
String[] attidlist = String.valueOf(attrInfoMap.get("content")).split(" , "); String[] attidlist = String.valueOf(attrInfoMap.get("content")).split(" , ");
StringBuilder content = new StringBuilder(""); StringBuilder content = new StringBuilder("");
for (int i = 0; i < attidlist.length; i++) { for (int i = 0; i < attidlist.length; i++) {
if (org.apache.commons.lang.StringUtils.isNotEmpty(attidlist[i])) { if (StringUtils.isNotEmpty(attidlist[i]) && !"null".equals(attidlist[i]) && attidlist[i].contains("att_file")) {
AttFileEO attFileEO = attFileEOService.getFileInfo(attidlist[i]); AttFileEO attFileEO = attFileEOService.getFileInfo(attidlist[i]);
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");
@@ -3072,49 +3075,52 @@ public class SarStandardsInfoServiceImpl extends ServiceImpl<SarStandardsInfoDao
String[] attidlist = String.valueOf(attrInfoMap.get("content")).split(","); String[] attidlist = String.valueOf(attrInfoMap.get("content")).split(",");
StringBuilder content = new StringBuilder(""); StringBuilder content = new StringBuilder("");
for (int i = 0; i < attidlist.length; i++) { for (int i = 0; i < attidlist.length; i++) {
if (StringUtils.isNotEmpty(attidlist[i]) && !"null".equals(attidlist[i])) { if (StringUtils.isNotEmpty(attidlist[i]) && !"null".equals(attidlist[i]) && attidlist[i].contains("att_file")) {
AttFileEO attFileEO = attFileEOService.getFileInfo(attidlist[i]); AttFileEO attFileEO = attFileEOService.getFileInfo(attidlist[i]);
if (null == attFileEO) { if (null == attFileEO) {
continue; continue;
} }
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");