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

Introduction

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

Prototype

public String[] getParagraphText() 

Source Link

Document

Get the text from the word file, as an array with one String per paragraph

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();/*from  ww  w .ja  va  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 {//  w  ww .j a va2  s  .c  om
        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:br.com.schumaker.beta.doc.ReadDocMaster.java

public static void main(String[] args) {
    try {//from   w ww.j a  v  a  2  s  .  co m

        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.jaeksoft.searchlib.parser.DocParser.java

License:Open Source License

private void currentWordExtraction(ParserResultItem result, InputStream inputStream) throws IOException {
    WordExtractor word = null;

    try {//from  w w w. j av  a  2s.  c  o m
        word = new WordExtractor(inputStream);

        SummaryInformation info = word.getSummaryInformation();
        if (info != null) {
            result.addField(ParserFieldEnum.title, info.getTitle());
            result.addField(ParserFieldEnum.author, info.getAuthor());
            result.addField(ParserFieldEnum.subject, info.getSubject());
        }

        String[] paragraphes = word.getParagraphText();
        for (String paragraph : paragraphes) {
            String[] frags = paragraph.split("\\n");
            for (String frag : frags)
                result.addField(ParserFieldEnum.content, StringUtils.replaceConsecutiveSpaces(frag, " "));
        }
    } finally {
        IOUtils.close(word);
    }
}

---

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

License:Apache License

private void currentWordExtraction(InputStream inputStream) throws IOException {
    WordExtractor word = null;

    try {//from www  . java  2  s  .co  m
        word = new WordExtractor(inputStream);

        SummaryInformation info = word.getSummaryInformation();
        if (info != null) {
            metas.add(TITLE, info.getTitle());
            metas.add(AUTHOR, info.getAuthor());
            metas.add(SUBJECT, info.getSubject());
            metas.add(CREATION_DATE, info.getCreateDateTime());
            metas.add(MODIFICATION_DATE, info.getLastSaveDateTime());
            metas.add(KEYWORDS, info.getKeywords());
        }

        ParserDocument document = getNewParserDocument();
        String[] paragraphes = word.getParagraphText();
        for (String paragraph : paragraphes)
            document.add(CONTENT, paragraph);
        document.add(LANG_DETECTION, languageDetection(CONTENT, 10000));
    } finally {
        IOUtils.closeQuietly(word);
    }
}

---

From source file:com.pdf.GetPdf.java

public static void docConvert(Document document, String url, String type)
        throws IOException, DocumentException {
    WordExtractor we;

    if (type.equals("doc")) {
        HWPFDocument wordDoc = new HWPFDocument(new URL(url).openStream());
        we = new WordExtractor(wordDoc);
        String[] paragraphs = we.getParagraphText();
        for (int i = 0; i < paragraphs.length; i++) {
            paragraphs[i] = paragraphs[i].replaceAll("\\cM?\r?\n", "");
            document.add(new Paragraph(paragraphs[i]));
        }/*from  ww  w  . j a va  2s.  com*/
    } else {
        XWPFDocument wordDoc = new XWPFDocument(new URL(url).openStream());
        List<IBodyElement> contents = wordDoc.getBodyElements();

        for (IBodyElement content : contents) {
            if (content.getElementType() == BodyElementType.PARAGRAPH) {
                List<XWPFParagraph> paras = content.getBody().getParagraphs();
                for (XWPFParagraph para : paras) {
                    document.add(new Paragraph(para.getParagraphText()));
                }

            } else if (content.getElementType() == BodyElementType.TABLE) {
                List<XWPFTable> tables = content.getBody().getTables();
                for (XWPFTable table : tables) {
                    List<XWPFTableRow> rows = table.getRows();
                    for (XWPFTableRow row : rows) {
                        List<XWPFTableCell> tablecells = row.getTableCells();
                    }
                }
            }

        }
    }

}

---

From source file:com.unsa.view.MainView.java

License:Creative Commons License

private void DocConverterPDF(File file1) {
    NPOIFSFileSystem fs = null;/* www. j a v  a2  s  . com*/
    com.lowagie.text.Document document = new com.lowagie.text.Document();

    try {
        System.out.println(file1.getAbsolutePath());
        fs = new NPOIFSFileSystem(new FileInputStream(file1.getAbsolutePath()));
        HWPFDocument doc = new HWPFDocument(fs.getRoot());
        WordExtractor we = new WordExtractor(doc);
        String output = file1.getAbsolutePath().substring(0, file1.getAbsolutePath().length() - 3);
        OutputStream fileout = new FileOutputStream(new File(output + "pdf"));

        PdfWriter writer = PdfWriter.getInstance(document, fileout);

        Range range = doc.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);
            paragraphs[i] = paragraphs[i].replaceAll("\\cM?\r?\n", "");
            document.add(new Paragraph(paragraphs[i]));
        }

    } catch (Exception e) {

        e.printStackTrace();
    } finally {

        document.close();
    }

}

---

From source file:cv_extractor.DocReader.java

protected static void readDocFile(File localFile) {
    try {//w ww .  j a  va2 s .  c om
        //Create a input stream to read file
        FileInputStream fis = new FileInputStream(localFile.getAbsolutePath());

        //For reading docx files
        HWPFDocument doc = new HWPFDocument(fis);

        WordExtractor we = new WordExtractor(doc);

        String[] paragraphs = we.getParagraphText();

        System.out.println("Total no of paragraph " + paragraphs.length);

        for (String para : paragraphs) {
            //Compile the regex defined above
            Pattern r = Pattern.compile(pattern);

            //Check if any string matches the compiled pattern
            Matcher m = r.matcher(para);

            if (m.find()) {
                //m.group() Returns the input subsequence matched by the previous match
                data.add(m.group());
            }
        }

        fis.close();
    }

    catch (Exception e) {
        e.printStackTrace();
    }
}

---

From source file:File.DOC.ReadDoc.java

public void Read(String path, String namafile) {
    try {//  ww  w  .j av a 2 s. c  o  m
        File file = new File(path + namafile + ".doc");
        FileInputStream fis = new FileInputStream(file.getAbsolutePath());

        HWPFDocument doc = new HWPFDocument(fis);

        WordExtractor we = new WordExtractor(doc);

        String[] paragraphs = we.getParagraphText();

        System.out.println("Total no of paragraph " + paragraphs.length);
        for (String para : paragraphs) {
            System.out.println(para.toString());
        }
        fis.close();
    } catch (Exception ex) {
        ex.printStackTrace();
    }
}

---

From source file:insight.masters.policyanalytics.services.BranchingOriginStanfordKeywords.java

public static String readfromdoc(String datsetspath, String Document) {
    File file = null;//from  w  w w.  ja v  a 2s  .c  o m
    WordExtractor extractor = null;
    String extractedtext = "";
    try {

        file = new File(datsetspath + Document);
        FileInputStream fis = new FileInputStream(file.getAbsolutePath());
        HWPFDocument document = new HWPFDocument(fis);
        extractor = new WordExtractor(document);
        String[] fileData = extractor.getParagraphText();
        for (int i = 0; i < fileData.length; i++) {
            if (fileData[i] != null)
                //                       System.out.print("{\"text\":\"");
                System.out.print(fileData[i].replace("\n", "").replace("\r", ""));
            extractedtext += fileData[i].replace("\n", "").replace("\r", "");
            //                System.out.print("\"}");

        }
    } catch (Exception exep) {
        exep.printStackTrace();
    }
    return extractedtext;
}

---

• «
• 1
• 2
• 3
• »