List of usage examples for org.apache.poi.hwpf.usermodel Picture getMimeType
public String getMimeType()
From source file:mj.ocraptor.extraction.tika.parser.microsoft.WordExtractor.java
License:Apache License
private void handlePictureCharacterRun(CharacterRun cr, Picture picture, PicturesSource pictures, XHTMLContentHandler xhtml) throws SAXException, IOException, TikaException { if (!isRendered(cr) || picture == null) { // Oh dear, we've run out... // Probably caused by multiple \u0008 images referencing // the same real image return;// ww w . ja va2 s . c om } // Which one is it? String extension = picture.suggestFileExtension(); int pictureNumber = pictures.pictureNumber(picture); // Make up a name for the picture // There isn't one in the file, but we need to be able to reference // the picture from the img tag and the embedded resource String filename = "image" + pictureNumber + (extension.length() > 0 ? "." + extension : ""); // Grab the mime type for the picture String mimeType = picture.getMimeType(); // Output the img tag AttributesImpl attr = new AttributesImpl(); attr.addAttribute("", "src", "src", "CDATA", "embedded:" + filename); attr.addAttribute("", "alt", "alt", "CDATA", filename); xhtml.startElement("img", attr); xhtml.endElement("img"); // Have we already output this one? // (Only expose each individual image once) if (!pictures.hasOutput(picture)) { TikaInputStream stream = TikaInputStream.get(picture.getContent()); handleEmbeddedResource(stream, filename, null, mimeType, xhtml, false); pictures.recordOutput(picture); } }
From source file:org.apache.tika.parser.microsoft.WordExtractor.java
License:Apache License
private void handlePictureCharacterRun(CharacterRun cr, Picture picture, PicturesSource pictures, XHTMLContentHandler xhtml) throws SAXException, IOException, TikaException { if (!isRendered(cr) || picture == null) { // Oh dear, we've run out... // Probably caused by multiple \u0008 images referencing // the same real image return;/*from w w w . jav a 2s . c o m*/ } // Which one is it? String extension = picture.suggestFileExtension(); int pictureNumber = pictures.pictureNumber(picture); // Make up a name for the picture // There isn't one in the file, but we need to be able to reference // the picture from the img tag and the embedded resource String filename = "image" + pictureNumber + (extension.length() > 0 ? "." + extension : ""); // Grab the mime type for the picture String mimeType = picture.getMimeType(); // Output the img tag AttributesImpl attr = new AttributesImpl(); attr.addAttribute("", "src", "src", "CDATA", "embedded:" + filename); attr.addAttribute("", "alt", "alt", "CDATA", filename); xhtml.startElement("img", attr); xhtml.endElement("img"); // Have we already output this one? // (Only expose each individual image once) if (!pictures.hasOutput(picture)) { TikaInputStream stream = TikaInputStream.get(picture.getContent()); handleEmbeddedResource(stream, filename, null, mimeType, xhtml, false); pictures.recordOutput(picture); } }
From source file:org.opf_labs.aqua.OfficeAnalyser.java
License:Apache License
public static void main(String[] args) throws Exception { //import org.apache.poi.poifs.dev.POIFSDump; //POIFSDump.main(args); SMOutputDocument xmldoc = SMOutputFactory.createOutputDocument( SMOutputFactory.getGlobalXMLOutputFactory().createXMLStreamWriter(System.out, "UTF-8"), "1.1", "UTF-8", true); xmldoc.setIndentation("\n ", 1, 2); // for unix linefeed, 2 spaces per level SMOutputElement xmlroot = xmldoc.addElement("properties"); // Loop through arguments: for (int i = 0; i < args.length; i++) { SMOutputElement xd = xmlroot.addElement("document"); xd.addAttribute("href", args[i]); HWPFDocument doc = new HWPFDocument(new FileInputStream(args[i])); // SummaryInformation SMOutputElement sie = xd.addElement("SummaryInformation"); sie.addElement("ApplicationName").addCharacters(doc.getSummaryInformation().getApplicationName()); sie.addElement("OSVersion").addCharacters("" + doc.getSummaryInformation().getOSVersion()); sie.addElement("Author").addCharacters("" + doc.getSummaryInformation().getAuthor()); sie.addElement("CharCount").addCharacters("" + doc.getSummaryInformation().getCharCount()); sie.addElement("Comments").addCharacters("" + doc.getSummaryInformation().getComments()); sie.addElement("EditTime").addCharacters("" + doc.getSummaryInformation().getEditTime()); sie.addElement("Format").addCharacters("" + doc.getSummaryInformation().getFormat()); sie.addElement("Keywords").addCharacters("" + doc.getSummaryInformation().getKeywords()); sie.addElement("LastAuthor").addCharacters("" + doc.getSummaryInformation().getLastAuthor()); sie.addElement("PageCount").addCharacters("" + doc.getSummaryInformation().getPageCount()); sie.addElement("RevNumber").addCharacters("" + doc.getSummaryInformation().getRevNumber()); sie.addElement("SectionCount").addCharacters("" + doc.getSummaryInformation().getSectionCount()); sie.addElement("Security").addCharacters("" + doc.getSummaryInformation().getSecurity()); sie.addElement("Subject").addCharacters("" + doc.getSummaryInformation().getSubject()); sie.addElement("Template").addCharacters("" + doc.getSummaryInformation().getTemplate()); sie.addElement("Title").addCharacters("" + doc.getSummaryInformation().getTitle()); sie.addElement("WordCount").addCharacters("" + doc.getSummaryInformation().getWordCount()); sie.addElement("CreatedDateTime").addCharacters("" + doc.getSummaryInformation().getCreateDateTime()); sie.addElement("LastPrinted").addCharacters("" + doc.getSummaryInformation().getLastPrinted()); sie.addElement("LastSaveDateTime") .addCharacters("" + doc.getSummaryInformation().getLastSaveDateTime()); sie.addElement("Thumbnail").addCharacters("" + doc.getSummaryInformation().getThumbnail()); // TextTable SMOutputElement tte = xd.addElement("TextTable"); for (TextPiece tp : doc.getTextTable().getTextPieces()) { SMOutputElement tpe = tte.addElement("TextPiece"); tpe.addAttribute("isUnicode", "" + tp.getPieceDescriptor().isUnicode()); tpe.addCharacters(tp.getStringBuilder().toString()); }/*from w w w .java 2 s . c o m*/ // DocumentSummaryInformation SMOutputElement dsie = xd.addElement("DocumentSummaryInformation"); dsie.addElement("ParCount").addCharacters("" + doc.getDocumentSummaryInformation().getParCount()); dsie.addElement("ByteCount").addCharacters("" + doc.getDocumentSummaryInformation().getByteCount()); dsie.addElement("HiddenCount").addCharacters("" + doc.getDocumentSummaryInformation().getHiddenCount()); dsie.addElement("LineCount").addCharacters("" + doc.getDocumentSummaryInformation().getLineCount()); dsie.addElement("MMClipCount").addCharacters("" + doc.getDocumentSummaryInformation().getMMClipCount()); dsie.addElement("NoteCount").addCharacters("" + doc.getDocumentSummaryInformation().getNoteCount()); dsie.addElement("SectionCount") .addCharacters("" + doc.getDocumentSummaryInformation().getSectionCount()); dsie.addElement("SlideCount").addCharacters("" + doc.getDocumentSummaryInformation().getSlideCount()); dsie.addElement("Format").addCharacters("" + doc.getDocumentSummaryInformation().getFormat()); dsie.addElement("PresentationFormat") .addCharacters("" + doc.getDocumentSummaryInformation().getPresentationFormat()); dsie.addElement("Company").addCharacters("" + doc.getDocumentSummaryInformation().getCompany()); dsie.addElement("Category").addCharacters("" + doc.getDocumentSummaryInformation().getCategory()); // Sections for (Object os : doc.getDocumentSummaryInformation().getSections()) { Section s = (Section) os; SMOutputElement se = dsie.addElement("Section"); se.addElement("FormatID").addCharacters("" + s.getFormatID()); se.addElement("CodePage").addCharacters("" + s.getCodepage()); se.addElement("PropertyCount").addCharacters("" + s.getPropertyCount()); for (Property sp : s.getProperties()) { SMOutputElement pe = se.addElement("Property"); pe.addAttribute("class", sp.getValue().getClass().getCanonicalName()); pe.addCharacters(sp.getValue().toString()); } } SMOutputElement fte = xd.addElement("FontTable"); for (Ffn f : doc.getFontTable().getFontNames()) { SMOutputElement fe = fte.addElement("Font"); fe.addElement("MainFontName").addCharacters(f.getMainFontName()); try { fe.addElement("AltFontName").addCharacters(f.getAltFontName()); } catch (Exception e) { // Seems to fail, and no safe test found as yet. } fe.addElement("Size").addCharacters("" + f.getSize()); fe.addElement("Weight").addCharacters("" + f.getWeight()); } SMOutputElement pte = xd.addElement("PicturesTable"); for (Picture p : doc.getPicturesTable().getAllPictures()) { SMOutputElement pe = pte.addElement("Picture"); pe.addElement("MimeType").addCharacters(p.getMimeType()); pe.addElement("Width").addCharacters("" + p.getWidth()); pe.addElement("Height").addCharacters("" + p.getHeight()); pe.addElement("HorizontalScalingFactor").addCharacters("" + p.getHorizontalScalingFactor()); pe.addElement("VerticalScalingFactor").addCharacters("" + p.getVerticalScalingFactor()); pe.addElement("Content").addCharacters("" + p.getContent()); } //parseCompObj( new File(args[i]) ); // This //System.out.println("Dumping " + args[i]); FileInputStream is = new FileInputStream(args[i]); POIFSFileSystem fs = new POIFSFileSystem(is); is.close(); DirectoryEntry root = fs.getRoot(); //dump(root); xmldoc.closeRoot(); // important, flushes, closes output } }