Apache's POI project can be used to process MS Office documents, and there is also a .net version of it on codeplex. POI projects can create and maintain various Java APIs based on OOXML and OLE2 file formats. Most MS Offices are in OLE2 format. POI supports Outlook through the HSMF sub-project, supports Visio through the HDGF sub-project, and supports Publisher through the HPBF sub-project.
Simple example of using POI to extract Word:
We need to introduce the two packages: poi-3.7.jat and poi-scratchpad-3.7.ajr.
The code copy is as follows:
package msoffice;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;
import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.extractor.WordExtractor;
import org.apache.poi.hwpf.usermodel.CharacterRun;
import org.apache.poi.hwpf.usermodel.Paragraph;
import org.apache.poi.hwpf.usermodel.Range;
import org.apache.poi.hwpf.usermodel.Section;
public class Word {
// Directly extract all content
public static String readDoc1(InputStream is) throws IOException {
WordExtractor extractor = new WordExtractor(is);
return extractor.getText();
}
//Extract by section section, paragraph Paragraph, string CharacterRun
public static void readDoc2(InputStream is) throws IOException {
HWPFDocument doc=new HWPFDocument(is);
Range r=doc.getRange();
for(int x=0;x<r.numSections();x++){
Section s=r.getSection(x);
for(int y=0;y<s.numParagraphs();y++){
Paragraph p=s.getParagraph(y);
for(int z=0;z<p.numCharacterRuns();z++){
CharacterRun run=p.getCharacterRun(z);
String text=run.text();
System.out.print(text);
}
}
}
}
public static void main(String[] args) {
File file = new File("/home/orisun/1.doc");
try {
FileInputStream fin = new FileInputStream(file);
String cont = readDoc1(fin);
System.out.println(cont);
fin.close();
fin = new FileInputStream(file);
readDoc2(fin);
fin.close();
} catch (IOException e) {
e.printStackTrace();
}
}
}
Example of POI extraction PPT:
The code copy is as follows:
package msoffice;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;
import org.apache.poi.hslf.HSLFSlideShow;
import org.apache.poi.hslf.extractor.PowerPointExtractor;
import org.apache.poi.hslf.model.Slide;
import org.apache.poi.hslf.model.TextRun;
import org.apache.poi.hslf.usermodel.SlideShow;
public class PPT {
//Directly extract all the contents of the slide
public static String readDoc1(InputStream is) throws IOException{
PowerPointExtractor extractor=new PowerPointExtractor(is);
return extractor.getText();
}
//Read one slide one slide one slide
public static void readDoc2(InputStream is) throws IOException{
SlideShow ss=new SlideShow(new HSLFSlideShow(is));
Slide[] slides=ss.getSlides();
for(int i=0;i<slides.length;i++){
//Read the title of a slide
String title=slides[i].getTitle();
System.out.println("Title:"+title);
//Read the content of a slide (including the title)
TextRun[] runs=slides[i].getTextRuns();
for(int j=0;j<runs.length;j++){
System.out.println(runs[j].getText());
}
}
}
public static void main(String[] args){
File file = new File("/home/orisun/2.ppt");
try{
FileInputStream fin=new FileInputStream(file);
String cont=readDoc1(fin);
System.out.println(cont);
fin.close();
fin=new FileInputStream(file);
readDoc2(fin);
fin.close();
}catch(IOException e){
e.printStackTrace();
}
}
}
Excel files are composed of multiple Workbooks, and a Workbook consists of multiple Sheets.
Simple example of POI extraction Excel:
The code copy is as follows:
package msoffice;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.util.Iterator;
import org.apache.poi.hssf.usermodel.HSSFCell;
import org.apache.poi.hssf.usermodel.HSSFRow;
import org.apache.poi.hssf.usermodel.HSSFSheet;
import org.apache.poi.hssf.usermodel.HSSFWorkbook;
import org.apache.poi.hssf.extractor.ExcelExtractor;
import org.apache.poi.poifs.filesystem.POIFSFileSystem;
import org.apache.poi.ss.usermodel.Row;
public class Excel {
//Read all the contents of Excel directly
public static String readDoc1(InputStream is)throws IOException{
HSSFWorkbook wb=new HSSFWorkbook(new POIFSFileSystem(is));
ExcelExtractor extractor=new ExcelExtractor(wb);
extractor.setFormulasNotResults(false);
extractor.setIncludeSheetNames(true);
return extractor.getText();
}
//Refine to Sheet, row or even cells when reading
public static double getAvg(InputStream is)throws IOException{
HSSFWorkbook wb=new HSSFWorkbook(new POIFSFileSystem(is));
//Get the first sheet
HSSFSheet sheet=wb.getSheetAt(0);
double molecule=0.0;
double denominator=0.0;
//Transfer sheet by line
Iterator<Row> riter=sheet.rowIterator();
while(riter.hasNext()){
HSSFRow row=(HSSFRow)riter.next();
HSSFCell cell1=row.getCell(4);
HSSFCell cell2=row.getCell(4);
if(cell1.getCellType()!=HSSFCell.CELL_TYPE_NUMERIC){
System.err.println("Number type error!");
System.exit(-2);
}
if(cell2.getCellType()!=HSSFCell.CELL_TYPE_NUMERIC){
System.err.println("Number type error!");
System.exit(-2);
}
denominator+=Double.parseDouble(cell2.toString().trim());
molecule+=Double.parseDouble(cell2.toString().trim())*Float.parseFloat(cell1.toString().trim());
}
return molecule/denominator;
}
public static void main(String[] args){
File file = new File("/home/orisun/3.xls");
try{
FileInputStream fin=new FileInputStream(file);
String cont=readDoc1(fin);
System.out.println(cont);
fin.close();
fin=new FileInputStream(file);
System.out.println("weighted average score" + getAvg(fin));
fin.close();
}catch(IOException e){
e.printStackTrace();
}
}
}