Example usage for org.apache.poi.xwpf.extractor XWPFWordExtractor getText

List of usage examples for org.apache.poi.xwpf.extractor XWPFWordExtractor getText

  1. HOME
  2. Java
  3. org.apache.poi
  4. org.apache.poi.xwpf.extractor.*
  5. XWPFWordExtractor
  6. getText

Introduction

In this page you can find the example usage for org.apache.poi.xwpf.extractor XWPFWordExtractor getText.

Prototype

public String getText()

Source Link

Usage

From source file:com.opensearchserver.extractor.parser.Docx.java

License:Apache License

@Override
protected void parseContent(InputStream inputStream, String extension, String mimeType) throws IOException {

    XWPFDocument document = new XWPFDocument(inputStream);
    XWPFWordExtractor word = null;
    try {//from  www. j a v a  2  s  .c o m
        word = new XWPFWordExtractor(document);

        CoreProperties info = word.getCoreProperties();
        if (info != null) {
            metas.add(TITLE, info.getTitle());
            metas.add(CREATOR, info.getCreator());
            metas.add(CREATION_DATE, info.getCreated());
            metas.add(MODIFICATION_DATE, info.getModified());
            metas.add(SUBJECT, info.getSubject());
            metas.add(DESCRIPTION, info.getDescription());
            metas.add(KEYWORDS, info.getKeywords());
        }
        ParserDocument parserDocument = getNewParserDocument();
        parserDocument.add(CONTENT, word.getText());
        parserDocument.add(LANG_DETECTION, languageDetection(CONTENT, 10000));
    } finally {
        IOUtils.closeQuietly(word);
    }
}

From source file:com.opensearchserver.textextractor.parser.Docx.java

License:Apache License

@Override
protected void parseContent(InputStream inputStream) throws IOException {

    XWPFDocument document = new XWPFDocument(inputStream);
    XWPFWordExtractor word = null;
    try {//from  ww  w .ja va  2  s.  com
        word = new XWPFWordExtractor(document);

        CoreProperties info = word.getCoreProperties();
        if (info != null) {
            metas.add(TITLE, info.getTitle());
            metas.add(CREATOR, info.getCreator());
            metas.add(CREATION_DATE, info.getCreated());
            metas.add(MODIFICATION_DATE, info.getModified());
            metas.add(SUBJECT, info.getSubject());
            metas.add(DESCRIPTION, info.getDescription());
            metas.add(KEYWORDS, info.getKeywords());
        }
        ParserDocument parserDocument = getNewParserDocument();
        parserDocument.add(CONTENT, word.getText());
        parserDocument.add(LANG_DETECTION, languageDetection(CONTENT, 10000));
    } finally {
        IOUtils.closeQuietly(word);
    }
}

From source file:com.swg.parse.docx.MSDocConvTest.java

/***
 * @return String containing the content of the .docx file from POI apache
 * @throws FileNotFoundException//w w w  . ja  va2s. co m
 * @throws IOException 
 */
private String getPOI() throws FileNotFoundException, IOException {

    FileInputStream inputTest = new FileInputStream(path + "SCD_2009_E-04 2009.08.21.docx");
    XWPFDocument docxTest = new XWPFDocument(inputTest);
    XWPFWordExtractor ContentTest = new XWPFWordExtractor(docxTest);
    String contentIn = ContentTest.getText();
    return contentIn;
}

From source file:com.swg.parse.docx.MSDocConvTest2.java

/***
 * @return String containing the content of the .docx file from POI apache
 * @throws FileNotFoundException/*from  w w w.j  av a 2 s . c o m*/
 * @throws IOException 
 */
private String getPOI() throws FileNotFoundException, IOException {

    FileInputStream inputTest = new FileInputStream(path + "CAD_2013_RE-06.docx");
    XWPFDocument docxTest = new XWPFDocument(inputTest);
    XWPFWordExtractor ContentTest = new XWPFWordExtractor(docxTest);
    String contentIn = ContentTest.getText();
    return contentIn;
}

From source file:com.swg.parse.docx.OpenFolderAction.java

/***
 * Simply grab the content of a .docx file using Apache POI and put it into a string
 * This String may have missing part due to POI library
 * @param f the .dox file/*from   w  ww.  jav a 2 s. com*/
 * @return POI content of .docx
 * @throws FileNotFoundException
 * @throws IOException 
 */
private String getPOI(File f) throws FileNotFoundException, IOException {

    FileInputStream inputTest = new FileInputStream(f.getAbsolutePath());
    XWPFDocument docxTest = new XWPFDocument(inputTest);
    XWPFWordExtractor ContentTest = new XWPFWordExtractor(docxTest);
    String contentIn = ContentTest.getText();
    return contentIn;
}

From source file:com.swg.parse.docx.OpenWord.java

/***
 * Simply grab the content of a .docx file using Apache POI and put it into a string
 * This String may have missing part due to POI library
 * @param f the .dox file/* w  w w.ja va2 s  .c o m*/
 * @return POI content of .docx
 * @throws FileNotFoundException
 * @throws IOException 
 */
private String getPOI() throws FileNotFoundException, IOException {

    FileInputStream inputTest = new FileInputStream(selectedFile.getAbsolutePath());
    XWPFDocument docxTest = new XWPFDocument(inputTest);
    XWPFWordExtractor ContentTest = new XWPFWordExtractor(docxTest);
    String contentIn = ContentTest.getText();
    return contentIn;
}

From source file:com.swg.parse.docx.V2Test.java

/***
 * @return String containing the content of the .docx file from POI apache
 * @throws FileNotFoundException//  w  w  w  . j  a v a 2 s.c o  m
 * @throws IOException 
 */
private String getPOI() throws FileNotFoundException, IOException {

    FileInputStream inputTest = new FileInputStream(path + "CAD_2013_RE-02.docx");
    XWPFDocument docxTest = new XWPFDocument(inputTest);
    XWPFWordExtractor ContentTest = new XWPFWordExtractor(docxTest);
    String contentIn = ContentTest.getText();
    return contentIn;
}

From source file:de.catma.document.source.contenthandler.DOCXContentHandler.java

License:Open Source License

@Override
public void load(InputStream is) throws IOException {
    XWPFDocument doc = new XWPFDocument(is);
    XWPFWordExtractor wordExtractor = new XWPFWordExtractor(doc);
    String buf = wordExtractor.getText();

    //it's still microsoft after all
    if (FileOSType.getFileOSType(buf).equals(FileOSType.UNIX)) {
        buf = FileOSType.convertUnixToDos(buf);
    }//from   w w  w  .  java 2s  . c o m

    setContent(buf);
}

From source file:de.iisys.schub.processMining.similarity.parsing.DocxParser.java

License:Apache License

/**
 * Only use this method if you don't want to get chapters sometimes.
 * Otherwise use 'parseDocxAndChapters' and 'getFullText' methods.
 * //from  www .  jav a2  s . c  o  m
 * Parses a .docx Word file and returns its text.
 * @return
 *       Returns the full text (incl. tables) as string.
 */
public String parseDocxSimple() {
    if (theDoc != null) {
        XWPFWordExtractor extr = new XWPFWordExtractor(theDoc);
        this.fullText = extr.getText();
        try {
            extr.close();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
    return this.fullText;
}

From source file:de.powerstaff.business.service.impl.reader.msword.DOCXWordDocumentReader.java

License:Open Source License

public ReadResult getContent(File inputFile) throws Exception {

    XWPFDocument theDocument = new XWPFDocument(new FileInputStream(inputFile));
    XWPFWordExtractor theExtractor = new XWPFWordExtractor(theDocument);
    String theText = theExtractor.getText();
    theText = theText.replace('|', ' ');
    return new ReadResult(toFlatString(theText));
}