Example usage for org.apache.poi.hwpf.usermodel Picture suggestFileExtension

Introduction

In this page you can find the example usage for org.apache.poi.hwpf.usermodel Picture suggestFileExtension.

Prototype

public String suggestFileExtension() 

Source Link

Document

tries to suggest extension for picture's file by matching signatures of popular image formats to first bytes of picture's contents

Usage

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;// w  ww  .j a v a 2  s  .  co  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.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;/*  www. j  a va 2s  . 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);
    }
}

---