Examples with ExportCache eu.transkribus.core.model.builder.ExportCache used on opensource projects

Example 1 with ExportCache

use of eu.transkribus.core.model.builder.ExportCache in project TranskribusCore by Transkribus.

the class TrpXlsxBuilder method main.

public static void main(String[] args) throws Exception {
    TrpDoc doc = LocalDocReader.load("C:/Users/Administrator/OCR_Sample_Document_-_Gothic_letter/");
    TrpXlsxBuilder txslx = new TrpXlsxBuilder();
    writeXlsxForDoc(doc, true, new File("C:/Users/Administrator/test.xlsx"), null, null, new ExportCache());
    // ExcelTest("C:/Users/Administrator/test.xlsx");
    System.out.println("finished");
}

Example 2 with ExportCache

use of eu.transkribus.core.model.builder.ExportCache in project TranskribusCore by Transkribus.

the class PdfExporter method export.

public File export(final TrpDoc doc, final String path, Set<Integer> pageIndices, final boolean useWordLevel, final boolean addTextPages, final boolean imagesOnly, final boolean highlightTags, final boolean doBlackening, boolean createTitle, ExportCache cache) throws DocumentException, MalformedURLException, IOException, JAXBException, URISyntaxException, InterruptedException {
    if (doc == null) {
        throw new IllegalArgumentException("TrpDoc is null!");
    }
    if (path == null) {
        throw new IllegalArgumentException("path is null!");
    }
    if (cache == null) {
        cache = new ExportCache();
    }
    // if(startPage == null || startPage < 1) startPage = 1;
    // final int nrOfPages = doc.getPages().size();
    // if(endPage == null || endPage > nrOfPages+1) endPage = nrOfPages;
    // 
    // if(startPage > endPage){
    // throw new IllegalArgumentException("Start page must be smaller than end page!");
    // }
    File pdfFile = new File(path);
    TrpPdfDocument pdf = new TrpPdfDocument(pdfFile, useWordLevel, highlightTags, doBlackening, createTitle);
    setChanged();
    notifyObservers("Creating PDF document...");
    boolean onePagePrinted = false;
    // for(int i = startPage-1; i <= endPage-1; i++){
    for (int i = 0; i < doc.getPages().size(); ++i) {
        if (pageIndices != null && !pageIndices.contains(i))
            continue;
        logger.info("Processing page " + (i + 1));
        TrpPage p = doc.getPages().get(i);
        URL imgUrl = p.getUrl();
        /*
			 * md is only needed for getting resolution because in the image it may be missing
			 * But if it is a local doc we have to try to get from img because md is null
			 */
        FimgStoreImgMd md = null;
        if (doc.isRemoteDoc()) {
            FimgStoreGetClient getter = new FimgStoreGetClient(p.getUrl());
            md = (FimgStoreImgMd) getter.getFileMd(p.getKey());
        }
        URL xmlUrl = p.getCurrentTranscript().getUrl();
        logger.debug("output with tags " + highlightTags);
        // PcGtsType pc = PageXmlUtils.unmarshal(xmlUrl);
        // should be the same as above
        JAXBPageTranscript pt = null;
        if (cache != null) {
            pt = cache.getPageTranscriptAtIndex(i);
        }
        PcGtsType pc;
        if (pt != null) {
            pc = pt.getPageData();
        } else {
            pc = PageXmlUtils.unmarshal(xmlUrl);
        }
        if (!onePagePrinted) {
            // add first page and previously add a title page with doc metadata and editorial declarations (if this option is set)
            pdf.addPage(imgUrl, doc, pc, addTextPages, imagesOnly, md, doBlackening, cache);
            onePagePrinted = true;
        } else {
            pdf.addPage(imgUrl, null, pc, addTextPages, imagesOnly, md, doBlackening, cache);
        }
        setChanged();
        notifyObservers(Integer.valueOf(i + 1));
        if (cancel) {
            pdf.close();
            File file = new File(path);
            if (!file.delete()) {
                throw new IOException("Could not delete the incomplete PDF file during export cancel");
            }
            throw new InterruptedException("Export canceled by the user");
        // break;
        }
    }
    if (highlightTags) {
        pdf.addTags(doc, pageIndices, useWordLevel, cache);
    }
    pdf.close();
    setChanged();
    notifyObservers("PDF written at: " + path);
    logger.info("PDF written at: " + path);
    return pdfFile;
}

Example 3 with ExportCache

use of eu.transkribus.core.model.builder.ExportCache in project TranskribusCore by Transkribus.

the class TrpTxtBuilder method main.

public static void main(String[] args) {
    // final String path = "/mnt/dea_scratch/TRP/Bentham_box_002_GT";
    final String path = "X:/TRP/Bentham_box_002_GT";
    try {
        TrpDoc doc = LocalDocReader.load(path);
        writeTxtForDoc(doc, true, false, true, new File("TxtExportTest.txt"), null, null, new ExportCache());
    } catch (JAXBException e) {
        // TODO Auto-generated catch block
        e.printStackTrace();
    } catch (IOException e) {
        // TODO Auto-generated catch block
        e.printStackTrace();
    } catch (Docx4JException e) {
        // TODO Auto-generated catch block
        e.printStackTrace();
    } catch (InterruptedException e) {
        // TODO Auto-generated catch block
        e.printStackTrace();
    }
}