List of usage examples for org.apache.poi.xslf.usermodel XSLFComments getCTCommentsList
public CTCommentList getCTCommentsList()
From source file:com.opensearchserver.extractor.parser.Pptx.java
License:Apache License
/** * Declined from XSLFPowerPointExtractor.java * //from w w w . j a v a 2s . c om * @param pptSlideShow */ private void extractSides(XMLSlideShow slideshow) { XSLFSlide[] slides = (XSLFSlide[]) slideshow.getSlides(); XSLFCommentAuthors commentAuthors = slideshow.getCommentAuthors(); for (XSLFSlide slide : slides) { // One document per slide ParserDocument result = getNewParserDocument(); XSLFNotes notes = slide.getNotes(); XSLFComments comments = slide.getComments(); XSLFSlideLayout layout = slide.getSlideLayout(); XSLFSlideMaster master = layout.getSlideMaster(); // TODO Do the slide's name // (Stored in docProps/app.xml) // Do the slide's text result.add(SLIDES, extractText(slide.getCommonSlideData(), false)); result.add(LANG_DETECTION, languageDetection(SLIDES, 10000)); // If requested, get text from the master and it's layout if (layout != null) { result.add(MASTER, extractText(layout.getCommonSlideData(), true)); } if (master != null) { result.add(MASTER, extractText(master.getCommonSlideData(), true)); } // If the slide has comments, do those too if (comments != null) { for (CTComment comment : comments.getCTCommentsList().getCmList()) { StringBuilder sbComment = new StringBuilder(); // Do the author if we can if (commentAuthors != null) { CTCommentAuthor author = commentAuthors.getAuthorById(comment.getAuthorId()); if (author != null) { sbComment.append(author.getName()); sbComment.append(": "); } } // Then the comment text, with a new line afterwards sbComment.append(comment.getText()); sbComment.append("\n"); if (sbComment.length() > 0) result.add(COMMENTS, sbComment.toString()); } } // Do the notes if requested if (notes != null) { result.add(NOTES, extractText(notes.getCommonSlideData(), false)); } } }
From source file:com.qwazr.extractor.parser.Pptx.java
License:Apache License
/** * Declined from XSLFPowerPointExtractor.java * * @param slideshow/* ww w . j av a 2 s. c o m*/ */ private void extractSides(XMLSlideShow slideshow) { List<XSLFSlide> slides = slideshow.getSlides(); XSLFCommentAuthors commentAuthors = slideshow.getCommentAuthors(); for (XSLFSlide slide : slides) { // One document per slide ParserDocument result = getNewParserDocument(); XSLFNotes notes = slide.getNotes(); XSLFComments comments = slide.getComments(); XSLFSlideLayout layout = slide.getSlideLayout(); XSLFSlideMaster master = layout.getSlideMaster(); // TODO Do the slide's name // (Stored in docProps/app.xml) // Do the slide's text result.add(SLIDES, extractText(slide.getCommonSlideData(), false)); result.add(LANG_DETECTION, languageDetection(SLIDES, 10000)); // If requested, get text from the master and it's layout if (layout != null) { result.add(MASTER, extractText(layout.getCommonSlideData(), true)); } if (master != null) { result.add(MASTER, extractText(master.getCommonSlideData(), true)); } // If the slide has comments, do those too if (comments != null) { for (CTComment comment : comments.getCTCommentsList().getCmList()) { StringBuilder sbComment = new StringBuilder(); // Do the author if we can if (commentAuthors != null) { CTCommentAuthor author = commentAuthors.getAuthorById(comment.getAuthorId()); if (author != null) { sbComment.append(author.getName()); sbComment.append(": "); } } // Then the comment text, with a new line afterwards sbComment.append(comment.getText()); sbComment.append("\n"); if (sbComment.length() > 0) result.add(COMMENTS, sbComment.toString()); } } // Do the notes if requested if (notes != null) { result.add(NOTES, extractText(notes.getCommonSlideData(), false)); } } }
From source file:com.qwazr.library.poi.PptxParser.java
License:Apache License
/** * Declined from XSLFPowerPointExtractor.java * * @param slideshow/*from w w w .j ava 2s. c om*/ * @param resultBuilder */ private void extractSides(final XMLSlideShow slideshow, final ParserResultBuilder resultBuilder) { final List<XSLFSlide> slides = slideshow.getSlides(); final XSLFCommentAuthors commentAuthors = slideshow.getCommentAuthors(); for (XSLFSlide slide : slides) { // One document per slide final ParserFieldsBuilder result = resultBuilder.newDocument(); final XSLFNotes notes = slide.getNotes(); final XSLFComments comments = slide.getComments(); final XSLFSlideLayout layout = slide.getSlideLayout(); final XSLFSlideMaster master = layout.getSlideMaster(); // TODO Do the slide's name // (Stored in docProps/app.xml) // Do the slide's text final String slideText = extractText(slide.getCommonSlideData(), false); result.add(SLIDES, slideText); result.add(CONTENT, slideText); // If requested, get text from the master and it's layout if (layout != null) { final String text = extractText(layout.getCommonSlideData(), true); result.add(MASTER, text); result.add(CONTENT, text); } if (master != null) { final String text = extractText(master.getCommonSlideData(), true); result.add(MASTER, text); result.add(CONTENT, text); } // If the slide has comments, do those too if (comments != null) { for (CTComment comment : comments.getCTCommentsList().getCmList()) { final StringBuilder sbComment = new StringBuilder(); // Do the author if we can if (commentAuthors != null) { CTCommentAuthor author = commentAuthors.getAuthorById(comment.getAuthorId()); if (author != null) { sbComment.append(author.getName()); sbComment.append(": "); } } // Then the comment text, with a new line afterwards sbComment.append(comment.getText()); sbComment.append("\n"); if (sbComment.length() > 0) { final String text = sbComment.toString(); result.add(COMMENTS, text); result.add(CONTENT, text); } } } // Do the notes if requested if (notes != null) { final String text = extractText(notes.getCommonSlideData(), false); result.add(NOTES, text); result.add(CONTENT, text); } result.add(LANG_DETECTION, languageDetection(result, CONTENT, 10000)); } }
From source file:mj.ocraptor.extraction.tika.parser.microsoft.ooxml.XSLFPowerPointExtractorDecorator.java
License:Apache License
/** * @see org.apache.poi.xslf.extractor.XSLFPowerPointExtractor#getText() *///from ww w . j a v a2 s.co m protected void buildXHTML(XHTMLContentHandler xhtml) throws SAXException, IOException { XMLSlideShow slideShow = (XMLSlideShow) extractor.getDocument(); XSLFSlide[] slides = slideShow.getSlides(); for (XSLFSlide slide : slides) { String slideDesc; if (slide.getPackagePart() != null && slide.getPackagePart().getPartName() != null) { slideDesc = getJustFileName(slide.getPackagePart().getPartName().toString()); slideDesc += "_"; } else { slideDesc = null; } // slide extractContent(slide.getShapes(), false, xhtml, slideDesc); // slide layout which is the master sheet for this slide XSLFSheet slideLayout = slide.getMasterSheet(); extractContent(slideLayout.getShapes(), true, xhtml, null); // slide master which is the master sheet for all text layouts XSLFSheet slideMaster = slideLayout.getMasterSheet(); extractContent(slideMaster.getShapes(), true, xhtml, null); // notes (if present) XSLFSheet slideNotes = slide.getNotes(); if (slideNotes != null) { extractContent(slideNotes.getShapes(), false, xhtml, slideDesc); // master sheet for this notes XSLFSheet notesMaster = slideNotes.getMasterSheet(); extractContent(notesMaster.getShapes(), true, xhtml, null); } // comments (if present) XSLFComments comments = slide.getComments(); if (comments != null) { for (CTComment comment : comments.getCTCommentsList().getCmList()) { xhtml.element("p", comment.getText()); } } } if (Config.inst().getProp(ConfigBool.ENABLE_IMAGE_OCR)) { TikaImageHelper helper = new TikaImageHelper(metadata); try { List<XSLFPictureData> pictures = slideShow.getAllPictures(); for (XSLFPictureData picture : pictures) { ByteArrayInputStream imageData = new ByteArrayInputStream(picture.getData()); BufferedImage image = ImageIO.read(imageData); helper.addImage(image); helper.addTextToHandler(xhtml); } } catch (Exception e) { e.printStackTrace(); } finally { if (extractor != null) { extractor.close(); } if (helper != null) { helper.close(); } } } }