Example usage for org.apache.poi.hwpf.extractor WordExtractor WordExtractor

Introduction

In this page you can find the example usage for org.apache.poi.hwpf.extractor WordExtractor WordExtractor.

Prototype

public WordExtractor(HWPFDocument doc) 

Source Link

Document

Create a new Word Extractor

Usage

From source file:at.tugraz.sss.serv.SSFileU.java

License:Apache License

public static void writePDFFromDoc(final String docFilePath, final String pdfFilePath) throws Exception {

    final Document document = new Document();
    final POIFSFileSystem fs = new POIFSFileSystem(openFileForRead(docFilePath));
    final HWPFDocument word = new HWPFDocument(fs);
    final WordExtractor we = new WordExtractor(word);
    final OutputStream out = openOrCreateFileWithPathForWrite(pdfFilePath);
    final PdfWriter writer = PdfWriter.getInstance(document, out);
    final Range range = word.getRange();

    document.open();/* ww w .  ja v  a  2s  .co m*/
    writer.setPageEmpty(true);
    document.newPage();
    writer.setPageEmpty(true);

    String[] paragraphs = we.getParagraphText();

    for (int i = 0; i < paragraphs.length; i++) {

        org.apache.poi.hwpf.usermodel.Paragraph pr = range.getParagraph(i);
        // CharacterRun run = pr.getCharacterRun(i);
        // run.setBold(true);
        // run.setCapitalized(true);
        // run.setItalic(true);
        paragraphs[i] = paragraphs[i].replaceAll("\\cM?\r?\n", "");
        System.out.println("Length:" + paragraphs[i].length());
        System.out.println("Paragraph" + i + ": " + paragraphs[i].toString());

        // add the paragraph to the document
        document.add(new Paragraph(paragraphs[i]));
    }

    document.close();
}

---

From source file:at.tugraz.sss.serv.util.SSFileU.java

License:Apache License

public static void writePDFFromDoc(final String docFilePath, final String pdfFilePath) throws SSErr {

    try {/*from www  . ja  va 2  s.co  m*/
        final Document document = new Document();
        final POIFSFileSystem fs = new POIFSFileSystem(openFileForRead(docFilePath));
        final HWPFDocument word = new HWPFDocument(fs);
        final WordExtractor we = new WordExtractor(word);
        final OutputStream out = openOrCreateFileWithPathForWrite(pdfFilePath);
        final PdfWriter writer = PdfWriter.getInstance(document, out);
        final Range range = word.getRange();

        document.open();
        writer.setPageEmpty(true);
        document.newPage();
        writer.setPageEmpty(true);

        String[] paragraphs = we.getParagraphText();

        for (int i = 0; i < paragraphs.length; i++) {

            org.apache.poi.hwpf.usermodel.Paragraph pr = range.getParagraph(i);
            // CharacterRun run = pr.getCharacterRun(i);
            // run.setBold(true);
            // run.setCapitalized(true);
            // run.setItalic(true);
            paragraphs[i] = paragraphs[i].replaceAll("\\cM?\r?\n", "");
            System.out.println("Length:" + paragraphs[i].length());
            System.out.println("Paragraph" + i + ": " + paragraphs[i].toString());

            // add the paragraph to the document
            document.add(new Paragraph(paragraphs[i]));
        }

        document.close();
    } catch (Exception error) {
        SSServErrReg.regErrThrow(error);
    }
}

---

From source file:avoking.com.documentos.scheduler.core.Core.java

private String leerDoc(InputStream doc) throws IOException {
    POIFSFileSystem fs = new POIFSFileSystem(doc);
    WordExtractor we = new WordExtractor(fs);
    return we.getText();
}

---

From source file:axiom.util.TextExtractor.java

License:Open Source License

public static String msWordExtractor(InputStream is) throws Exception {
    WordExtractor we = new WordExtractor(is);
    return we.getText();
}

---

From source file:br.com.schumaker.beta.doc.ReadDocMaster.java

public static void main(String[] args) {
    try {//  w  w w .  j a v a2  s. c om

        File file = new File(
                "/users/hudsonschumaker/downloads/Guisi01206us - Jira Guide for P3 PECB enhancement requests.doc");
        FileInputStream fis = new FileInputStream(file.getAbsolutePath());
        HWPFDocument doc = new HWPFDocument(fis);
        WordExtractor extractor = new WordExtractor(doc);

        for (String rawText : extractor.getParagraphText()) {
            String text = extractor.stripFields(rawText);
            if (text.length() > 10)
                System.out.println(text.trim());
        }
    } catch (Exception exep) {
    }
}

---

From source file:com.artech.prototype2.bardakov.utils.impl.MultiParserImpl.java

/**
 *      doc/docx//from  w ww . j a  va 2 s  . c o m
 * @param FilePath -   
 * @return ?? ?
 */
private ArrayList<String> getListOfWordsFromDoc(String FilePath) {
    FileInputStream fis;
    List<String> result = new ArrayList<String>();
    if (FilePath.substring(FilePath.length() - 1).equals("x")) { //is a docx
        try {
            fis = new FileInputStream(new File(FilePath));
            XWPFDocument doc = new XWPFDocument(fis);
            XWPFWordExtractor extract = new XWPFWordExtractor(doc);
            // System.out.println(extract.getText());
            StringBuilder builder = new StringBuilder();
            builder.append(extract.getText());
            String[] words = builder.toString().split(" ");
            for (String s : words) {
                result.add(s);
            }
        } catch (IOException e) {

            e.printStackTrace();
        }
    } else { //is not a docx
        try {
            fis = new FileInputStream(new File(FilePath));
            HWPFDocument doc = new HWPFDocument(fis);
            WordExtractor extractor = new WordExtractor(doc);
            StringBuilder builder = new StringBuilder();
            builder.append(extractor.getText());
            String[] words = builder.toString().split(" ");
            for (String s : words) {
                result.add(s);
            }

        } catch (IOException e) {
            e.printStackTrace();
        }
    }
    return (ArrayList<String>) result;
}

---

From source file:com.docdoku.server.esindexer.ESTools.java

License:Open Source License

private static String microsoftWordDocumentToString(InputStream inputStream) throws IOException {
    String strRet;/*from w  w w.jav  a  2 s.  c om*/
    try (InputStream wordStream = new BufferedInputStream(inputStream)) {
        if (POIFSFileSystem.hasPOIFSHeader(wordStream)) {
            WordExtractor wordExtractor = new WordExtractor(wordStream);
            strRet = wordExtractor.getText();
        } else {
            XWPFWordExtractor wordXExtractor = new XWPFWordExtractor(new XWPFDocument(wordStream));
            strRet = wordXExtractor.getText();
        }
    }
    return strRet;
}

---

From source file:com.docdoku.server.IndexerBean.java

License:Open Source License

@Asynchronous
@Lock(LockType.WRITE)//w  w  w. j a v a 2s  . c  o  m
public void addToIndex(String fullName, String pathName) {
    IndexWriter indexWriter = null;
    Directory indexDir = null;
    try {
        indexDir = FSDirectory.open(new File(indexPath));
        indexWriter = new IndexWriter(indexDir, new StandardAnalyzer(Version.LUCENE_30),
                IndexWriter.MaxFieldLength.LIMITED);
        int ext = pathName.lastIndexOf('.');
        String extension = "";
        if (ext != -1) {
            extension = pathName.substring(ext);
        }

        if (extension.equals(".odt") || extension.equals(".ods") || extension.equals(".odp")
                || extension.equals(".odg") || extension.equals(".odc") || extension.equals(".odf")
                || extension.equals(".odb") || extension.equals(".odi") || extension.equals(".odm")) {
            final StringBuilder text = new StringBuilder();
            ZipInputStream zipOpenDoc = new ZipInputStream(
                    new BufferedInputStream(new FileInputStream(pathName)));
            ZipEntry zipEntry;
            while ((zipEntry = zipOpenDoc.getNextEntry()) != null) {
                if (zipEntry.getName().equals("content.xml")) {
                    SAXParserFactory saxParserFactory = SAXParserFactory.newInstance();
                    SAXParser parser = saxParserFactory.newSAXParser();
                    parser.parse(zipOpenDoc, new DefaultHandler() {

                        @Override
                        public void characters(char[] ch, int start, int length) throws SAXException {
                            for (int i = start; i < start + length; i++) {
                                text.append(ch[i]);
                            }
                            text.append("\r\n");
                        }
                    });
                    break;
                }
            }
            zipOpenDoc.close();
            Reader contentReader = new StringReader(text.toString());
            addDoc(indexWriter, contentReader, fullName);
            contentReader.close();
        } else if (extension.equals(".doc")) {
            //MSWord Document
            InputStream wordStream = new BufferedInputStream(new FileInputStream(pathName));
            WordExtractor wordExtractor = new WordExtractor(wordStream);
            Reader contentReader = new StringReader(wordExtractor.getText());
            wordStream.close();
            addDoc(indexWriter, contentReader, fullName);
            contentReader.close();
        } else if (extension.equals(".ppt") || extension.equals(".pps")) {
            //MSPowerPoint Document
            InputStream pptStream = new BufferedInputStream(new FileInputStream(pathName));
            PowerPointExtractor pptExtractor = new PowerPointExtractor(pptStream);
            Reader contentReader = new StringReader(pptExtractor.getText(true, true));
            pptStream.close();
            addDoc(indexWriter, contentReader, fullName);
            pptExtractor.close();
            contentReader.close();
        } else if (extension.equals(".txt")) {
            //Text Document
            Reader contentReader = new BufferedReader(new FileReader(pathName));
            addDoc(indexWriter, contentReader, fullName);
            contentReader.close();
        } else if (extension.equals(".xls")) {
            //MSExcelExtractor Document
            //InputStream excelStream=new BufferedInputStream(new FileInputStream(pathName));
            //ExcelExtractor excelExtractor= new ExcelExtractor(excelStream);
            //Reader contentReader=new StringReader(excelExtractor.getText());
            //excelStream.close();
            //addDoc(indexWriter,contentReader,fullName);
            //excelExtractor.close();
            //contentReader.close();
        } else if (extension.equals(".html") || extension.equals(".htm")) {
        } else if (extension.equals(".csv")) {
        } else if (extension.equals(".xml")) {
        } else if (extension.equals(".rtf")) {
        } else if (extension.equals(".pdf")) {
        } else if (extension.equals(".msg")) {
        }
    } catch (CorruptIndexException ex) {
        throw new EJBException(ex);
    } catch (LockObtainFailedException ex) {
        try {
            if (IndexWriter.isLocked(indexDir)) {
                IndexWriter.unlock(indexDir);
            }
        } catch (IOException pIOEx) {
            throw new EJBException(pIOEx);
        }
        throw new EJBException(ex);
    } catch (ParserConfigurationException ex) {
        throw new EJBException(ex);
    } catch (SAXException ex) {
        throw new EJBException(ex);
    } catch (IOException ex) {
        throw new EJBException(ex);
    } finally {
        try {
            if (indexWriter != null) {
                indexWriter.close();
            }
        } catch (IOException ex) {
            throw new EJBException(ex);
        }
    }
}

---

From source file:com.frameworkset.platform.cms.searchmanager.extractors.CmsExtractorMsWord.java

License:Open Source License

/** 
 * @see org.opencms.search.extractors.I_CmsTextExtractor#extractText(java.io.InputStream, java.lang.String)
 *///from   ww  w  .  j a  v  a 2s.com
public I_CmsExtractionResult extractText(InputStream in, String encoding) throws Exception {

    // first extract the text using the text actraction libary
    //       WordTextExtractorFactory factory = new WordTextExtractorFactory();

    //        TextExtractor wordExtractor = factory.textExtractor(getStreamCopy(in));

    //        String result = wordExtractor.getText();
    //        String result = wordExtractor.extractText(getStreamCopy(in));
    StringBuffer content = new StringBuffer();
    //       org.apache.poi.hwpf

    //        HWPFDocument doc = new HWPFDocument(in);
    //         Range range = doc.getRange();
    //         int paragraphCount = range.numParagraphs();// ?
    //         for (int i = 0; i < paragraphCount; i++) {// ?????
    //             Paragraph pp = range.getParagraph(i);
    //             content.append(pp.text());
    //         }
    String result = null;
    Map metaInfo = null;
    if (version.equals(ContentHandler.VERSION_2003)) {
        WordExtractor ex = new WordExtractor(in);
        result = ex.getText();
        SummaryInformation info = ex.getSummaryInformation();
        this.m_summary = info;
        this.m_documentSummary = ex.getDocSummaryInformation();
        metaInfo = extractMetaInformation();
    } else {
        XWPFDocument doc = new XWPFDocument(in);
        XWPFWordExtractor ex = new XWPFWordExtractor(doc);
        result = ex.getText();
        cp = ex.getCoreProperties();
        metaInfo = extractMetaInformation();
        //           SummaryInformation info = doc.getSummaryInformation();
        //             this.m_summary = info;
        //             this.m_documentSummary = doc.getDocSummaryInformation();
    }

    //        result = removeControlChars(result);

    //     String result = content.toString();
    // now extract the meta information using POI 
    //        POIFSReader reader = new POIFSReader();
    //        reader.registerListener(this);
    //        reader.read(getStreamCopy(getStreamCopy(in)));

    // free some memory
    cleanup();

    // return the final result
    return new CmsExtractionResult(result, metaInfo);
}

---

From source file:com.isotrol.impe3.idx.oc.extractors.ExtractorMsWord.java

License:Open Source License

/**
 * Extrae el texto de un fichero word./*from   www  .j  a v a 2  s.c  om*/
 * @param in
 * @return String. Devuelve el texto crudo
 * @throws Exception
 */
public static String extractText(InputStream in) throws Exception {

    String result = "";

    HWPFDocument doc = new HWPFDocument(in);

    WordExtractor we = new WordExtractor(doc);
    result = we.getText();

    // Eliminamos los caracteres que no nos sirven para indexar.
    result = ExtractorUtil.removeControlChars(result);

    return result;
}

---

• «
• 1
• 2
• 3
• 4
• 5
• 6
• 7
• 8
• 9
• »