Search in sources :

Example 6 with Br

use of org.docx4j.wml.Br in project TranskribusCore by Transkribus.

the class DocxBuilder method writeDocxForTranscriptWithTables.

private static void writeDocxForTranscriptWithTables(MainDocumentPart mdp, TrpPageType trpPage, boolean wordBased, boolean preserveLineBreaks) {
    boolean rtl = false;
    // TrpTableRegionType is contained in the regions too
    List<TrpRegionType> regions = trpPage.getRegions();
    Collections.sort(regions, new TrpElementReadingOrderComparator<RegionType>(true));
    for (int j = 0; j < regions.size(); ++j) {
        TrpRegionType r = regions.get(j);
        if (r instanceof TrpTableRegionType) {
            logger.debug("is table");
            TrpTableRegionType table = (TrpTableRegionType) r;
            int cols = table.getNCols();
            int rows = table.getNRows();
            // PageXmlUtils.buildPolygon(table.getCoords().getPoints()).getBounds().getMaxX();
            double maxX = table.getBoundingBox().getMaxX();
            // PageXmlUtils.buildPolygon(table.getCoords().getPoints()).getBounds().getMinX();
            double minX = table.getBoundingBox().getMinX();
            int tablesize = (int) (maxX - minX);
            List<List<TrpTableCellType>> allRowCells = new ArrayList<List<TrpTableCellType>>();
            for (int k = 0; k < rows; k++) {
                allRowCells.add(table.getRowCells(k));
            }
            List<HashMap<Integer, TrpTableCellType>> allRows = new ArrayList<HashMap<Integer, TrpTableCellType>>();
            HashMap<Integer, TrpTableCellType> nextRowMap = new HashMap<Integer, TrpTableCellType>();
            for (List<TrpTableCellType> rowCells : allRowCells) {
                HashMap<Integer, TrpTableCellType> currRowMap = new HashMap<Integer, TrpTableCellType>();
                /*
	            	 * fill up all cells which are not set in TRP (needed for vertical cell merge)
	            	 * the nextRowMap contains already all cells which span vertically with the cells above - means they got merged 
	            	 * in the table but have to be considered here 
	            	 */
                currRowMap.putAll(nextRowMap);
                nextRowMap.clear();
                for (TrpTableCellType cell : rowCells) {
                    // logger.debug("table cell text " + cell.getUnicodeTextFromLines());
                    currRowMap.put(cell.getCol(), cell);
                    if (cell.getRowSpan() > 1) {
                        nextRowMap.put(cell.getCol(), null);
                    }
                }
                allRows.add(currRowMap);
            }
            Tbl thisTable;
            try {
                thisTable = getDocxTable(wordMLPackage, wordBased, rows, cols, allRows, tablesize, mdp);
                mdp.addObject(thisTable);
            } catch (Exception e) {
                // TODO Auto-generated catch block
                e.printStackTrace();
            }
            // this Br element is used break the current and go for next line
            Br br = factory.createBr();
            org.docx4j.wml.P p = factory.createP();
            mdp.addObject(p);
            p.getContent().add(br);
        } else if (r instanceof TrpTextRegionType) {
            TrpTextRegionType tr = (TrpTextRegionType) r;
            /*
				 * create one paragraph for each text region
				 * but only if there is some text in it
				 */
            String helper = tr.getUnicodeText().replaceAll("\n", "");
            if (!helper.equals("")) {
                exportTextRegion(tr, wordBased, null, mdp);
            }
        }
    }
}
Also used : TrpTextRegionType(eu.transkribus.core.model.beans.pagecontent_trp.TrpTextRegionType) TrpRegionType(eu.transkribus.core.model.beans.pagecontent_trp.TrpRegionType) TrpTableRegionType(eu.transkribus.core.model.beans.pagecontent_trp.TrpTableRegionType) RegionType(eu.transkribus.core.model.beans.pagecontent.RegionType) HashMap(java.util.HashMap) LinkedHashMap(java.util.LinkedHashMap) ArrayList(java.util.ArrayList) TrpTableRegionType(eu.transkribus.core.model.beans.pagecontent_trp.TrpTableRegionType) TrpRegionType(eu.transkribus.core.model.beans.pagecontent_trp.TrpRegionType) CustomTagList(eu.transkribus.core.model.beans.customtags.CustomTagList) List(java.util.List) ArrayList(java.util.ArrayList) Tbl(org.docx4j.wml.Tbl) P(org.docx4j.wml.P) TrpTableCellType(eu.transkribus.core.model.beans.pagecontent_trp.TrpTableCellType) JAXBException(javax.xml.bind.JAXBException) IOException(java.io.IOException) Docx4JException(org.docx4j.openpackaging.exceptions.Docx4JException) BigInteger(java.math.BigInteger) Br(org.docx4j.wml.Br) TrpTextRegionType(eu.transkribus.core.model.beans.pagecontent_trp.TrpTextRegionType)

Example 7 with Br

use of org.docx4j.wml.Br in project TranskribusCore by Transkribus.

the class DocxBuilder method writeDocxForDoc.

public static void writeDocxForDoc(TrpDoc doc, boolean wordBased, boolean writeTags, boolean doBlackeningSensibleData, File file, Set<Integer> pageIndices, IProgressMonitor monitor, boolean createTitle, boolean markUnclear, boolean expandAbbreviations, boolean replaceAbbrevs, boolean keepLineBreaks, boolean showSuppliedInBrackets, boolean ignoreSuppliedTags, ExportCache cache) throws JAXBException, IOException, Docx4JException, InterruptedException {
    // ch.qos.logback.classic.Logger root = logger.getClass().get(ch.qos.logback.classic.Logger) org.slf4j.LoggerFactory.getLogger(ch.qos.logback.classic.Logger.ROOT_LOGGER_NAME);
    ((ch.qos.logback.classic.Logger) logger).setLevel(ch.qos.logback.classic.Level.DEBUG);
    exportTags = writeTags;
    doBlackening = doBlackeningSensibleData;
    tagnames = cache.getOnlySelectedTagnames(ExportUtils.getOnlyWantedTagnames(CustomTagFactory.getRegisteredTagNames()));
    markUnclearWords = markUnclear;
    expandAbbrevs = expandAbbreviations;
    preserveLineBreaks = keepLineBreaks;
    substituteAbbrevs = replaceAbbrevs;
    showSuppliedWithBrackets = showSuppliedInBrackets;
    ignoreSupplied = ignoreSuppliedTags;
    /*
		 * get all names of tags
		 */
    // tagnames = CustomTagFactory.getRegisteredTagNames();
    // main document part
    wordMLPackage = WordprocessingMLPackage.createPackage();
    MainDocumentPart mdp = wordMLPackage.getMainDocumentPart();
    org.docx4j.wml.ObjectFactory factory = Context.getWmlObjectFactory();
    List<TrpPage> pages = doc.getPages();
    int totalPages = pageIndices == null ? pages.size() : pageIndices.size();
    if (monitor != null) {
        monitor.beginTask("Exporting to docx", totalPages);
    }
    int c = 0;
    boolean atLeastOnePageWritten = false;
    // can be used as page break every time we need one
    Br objBr = new Br();
    objBr.setType(STBrType.PAGE);
    P pageBreakP = factory.createP();
    pageBreakP.getContent().add(objBr);
    for (int i = 0; i < pages.size(); ++i) {
        if (pageIndices != null && !pageIndices.contains(i))
            continue;
        if (!atLeastOnePageWritten && createTitle) {
            addTitlePage(doc, mdp);
            // add page break
            mdp.addObject(pageBreakP);
        }
        if (monitor != null) {
            if (monitor.isCanceled()) {
                throw new InterruptedException("Export canceled by the user");
            // logger.debug("docx export cancelled!");
            // return;
            }
            monitor.subTask("Processing page " + (c + 1));
        }
        // TrpPage page = pages.get(i);
        // TrpTranscriptMetadata md = page.getCurrentTranscript();
        // JAXBPageTranscript tr = new JAXBPageTranscript(md);
        // tr.build();
        JAXBPageTranscript tr = null;
        if (cache != null) {
            tr = cache.getPageTranscriptAtIndex(i);
        }
        if (tr == null) {
            TrpPage page = pages.get(i);
            TrpTranscriptMetadata md = page.getCurrentTranscript();
            // md.getStatus().equals("Done");
            tr = new JAXBPageTranscript(md);
            tr.build();
        }
        TrpPageType trpPage = tr.getPage();
        logger.debug("writing docx for the page " + (i + 1) + "/" + doc.getNPages());
        writeDocxForTranscriptWithTables(mdp, trpPage, wordBased, preserveLineBreaks);
        atLeastOnePageWritten = true;
        ++c;
        if (monitor != null) {
            monitor.worked(c);
        }
    }
    P p = factory.createP();
    mdp.getContent().add(p);
    addComplexField(p, " INDEX \\e \"", "\" \\c \"1\" \\z \"1031\"");
    FieldUpdater updater = new FieldUpdater(wordMLPackage);
    updater.update(true);
    // write tags at end of last page
    if (false) {
        // RtfText headline = RtfText.text("Person names in this document (amount of found persons: " + persons.size() + ")", "\n");
        logger.debug("export tags ");
        boolean firstExport = true;
        // tagnames = all user choosen tags via export dialog
        for (String currTagname : tagnames) {
            // logger.debug("curr tagname " + currTagname);
            // get all custom tags with currTagname and text
            HashMap<CustomTag, String> allTagsOfThisTagname = cache.getTags(currTagname);
            // one paragraph for each tagname
            org.docx4j.wml.P p4Tag = factory.createP();
            if (allTagsOfThisTagname.size() > 0 && !currTagname.equals("textStyle") && !currTagname.equals("gap") && !currTagname.equals("comment")) {
                // new page if tag export starts
                if (firstExport) {
                    // Br objBr = new Br();
                    // objBr.setType(STBrType.PAGE);
                    p4Tag.getContent().add(objBr);
                    firstExport = false;
                }
                // logger.debug("allTagsOfThisTagname " + allTagsOfThisTagname.size());
                // one run for headline and thanfor each entry
                org.docx4j.wml.Text t = factory.createText();
                t.setValue(currTagname + " tags in this document: " + allTagsOfThisTagname.size());
                t.setSpace("preserve");
                org.docx4j.wml.R run = factory.createR();
                run.getContent().add(t);
                org.docx4j.wml.RPr rpr = factory.createRPr();
                org.docx4j.wml.BooleanDefaultTrue b = new org.docx4j.wml.BooleanDefaultTrue();
                b.setVal(true);
                U u = factory.createU();
                u.setVal(UnderlineEnumeration.SINGLE);
                rpr.setB(b);
                rpr.setU(u);
                run.setRPr(rpr);
                // this Br element is used break the current and go for next line
                Br br = factory.createBr();
                run.getContent().add(br);
                p4Tag.getContent().add(run);
                // ArrayList<RtfText> tagTexts = new ArrayList<RtfText>();
                Collection<String> valueSet = allTagsOfThisTagname.values();
                int l = 0;
                for (String currEntry : valueSet) {
                    org.docx4j.wml.R currRun = factory.createR();
                    org.docx4j.wml.Text currText = factory.createText();
                    currText.setValue(currEntry);
                    currText.setSpace("preserve");
                    currRun.getContent().add(currText);
                    // reuse linebreak
                    currRun.getContent().add(br);
                    p4Tag.getContent().add(currRun);
                }
            }
            mdp.getContent().add(p4Tag);
        }
    }
    // finally save the file
    wordMLPackage.save(file);
    logger.info("Saved " + file.getAbsolutePath());
}
Also used : JAXBPageTranscript(eu.transkribus.core.model.beans.JAXBPageTranscript) TrpTranscriptMetadata(eu.transkribus.core.model.beans.TrpTranscriptMetadata) CustomTag(eu.transkribus.core.model.beans.customtags.CustomTag) Logger(org.slf4j.Logger) RPr(org.docx4j.wml.RPr) P(org.docx4j.wml.P) U(org.docx4j.wml.U) R(org.docx4j.wml.R) Text(org.docx4j.wml.Text) TrpPageType(eu.transkribus.core.model.beans.pagecontent_trp.TrpPageType) P(org.docx4j.wml.P) FieldUpdater(org.docx4j.model.fields.FieldUpdater) TrpPage(eu.transkribus.core.model.beans.TrpPage) MainDocumentPart(org.docx4j.openpackaging.parts.WordprocessingML.MainDocumentPart) Br(org.docx4j.wml.Br)

Example 8 with Br

use of org.docx4j.wml.Br in project TranskribusCore by Transkribus.

the class DocxBuilder method exportTextRegion.

private static void exportTextRegion(TrpTextRegionType tr, boolean wordBased, P p, MainDocumentPart mdp) {
    if (p == null) {
        p = factory.createP();
        mdp.addObject(p);
    }
    List<TextLineType> lines = tr.getTextLine();
    for (int i = 0; i < lines.size(); ++i) {
        TrpTextLineType trpL = (TrpTextLineType) lines.get(i);
        try {
            if (wordBased && trpL.getWord().size() > 0) {
                getFormattedTextForLineElement(trpL.getWord(), p, mdp);
            } else {
                getFormattedTextForShapeElement(trpL, p, mdp);
            }
        } catch (Exception e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        }
        /* with ¶ the user can mark a new paragraph inside a text region
			 * unicode is \u00B6
			 */
        if (trpL.getCustomTagList().containsParagraphTag()) {
            // then new paragraph should be used;
            p = factory.createP();
            mdp.addObject(p);
        } else /*add line break after each text line
			 * or omit this if explicitely wished to have dense lines
			 * No line break at end of paragraph
			 */
        if (preserveLineBreaks && !(i + 1 == lines.size())) {
            // this Br element is used break the current and go for next line
            Br br = factory.createBr();
            p.getContent().add(br);
        }
    }
}
Also used : TrpTextLineType(eu.transkribus.core.model.beans.pagecontent_trp.TrpTextLineType) Br(org.docx4j.wml.Br) TextLineType(eu.transkribus.core.model.beans.pagecontent.TextLineType) TrpTextLineType(eu.transkribus.core.model.beans.pagecontent_trp.TrpTextLineType) JAXBException(javax.xml.bind.JAXBException) IOException(java.io.IOException) Docx4JException(org.docx4j.openpackaging.exceptions.Docx4JException)

Example 9 with Br

use of org.docx4j.wml.Br in project docx4j-template by vindell.

the class Docx4J_简单例子 method addPageBreak.

// 分页
public void addPageBreak(WordprocessingMLPackage wordMLPackage, ObjectFactory factory) {
    MainDocumentPart documentPart = wordMLPackage.getMainDocumentPart();
    Br breakObj = new Br();
    breakObj.setType(STBrType.PAGE);
    P paragraph = factory.createP();
    paragraph.getContent().add(breakObj);
    documentPart.addObject(paragraph);
}
Also used : Br(org.docx4j.wml.Br) P(org.docx4j.wml.P) MainDocumentPart(org.docx4j.openpackaging.parts.WordprocessingML.MainDocumentPart)

Example 10 with Br

use of org.docx4j.wml.Br in project docx4j-template by vindell.

the class Docx4j_工具类_S3_Test method setTcContent.

/**
 * @Description:设置单元格内容,content为null则清除单元格内容
 */
public void setTcContent(Tc tc, RPr rpr, String content) {
    List<Object> pList = tc.getContent();
    P p = null;
    if (pList != null && pList.size() > 0) {
        if (pList.get(0) instanceof P) {
            p = (P) pList.get(0);
        }
    } else {
        p = new P();
        tc.getContent().add(p);
    }
    R run = null;
    List<Object> rList = p.getContent();
    if (rList != null && rList.size() > 0) {
        for (int i = 0, len = rList.size(); i < len; i++) {
            // 清除内容(所有的r
            p.getContent().remove(0);
        }
    }
    run = new R();
    p.getContent().add(run);
    if (content != null) {
        String[] contentArr = content.split("\n");
        Text text = new Text();
        text.setSpace("preserve");
        text.setValue(contentArr[0]);
        run.setRPr(rpr);
        run.getContent().add(text);
        for (int i = 1, len = contentArr.length; i < len; i++) {
            Br br = new Br();
            // 换行
            run.getContent().add(br);
            text = new Text();
            text.setSpace("preserve");
            text.setValue(contentArr[i]);
            run.setRPr(rpr);
            run.getContent().add(text);
        }
    }
}
Also used : P(org.docx4j.wml.P) Br(org.docx4j.wml.Br) R(org.docx4j.wml.R) Text(org.docx4j.wml.Text)

Aggregations

Br (org.docx4j.wml.Br)13 P (org.docx4j.wml.P)9 MainDocumentPart (org.docx4j.openpackaging.parts.WordprocessingML.MainDocumentPart)5 R (org.docx4j.wml.R)5 Text (org.docx4j.wml.Text)5 IOException (java.io.IOException)2 JAXBException (javax.xml.bind.JAXBException)2 Docx4JException (org.docx4j.openpackaging.exceptions.Docx4JException)2 JAXBPageTranscript (eu.transkribus.core.model.beans.JAXBPageTranscript)1 TrpPage (eu.transkribus.core.model.beans.TrpPage)1 TrpTranscriptMetadata (eu.transkribus.core.model.beans.TrpTranscriptMetadata)1 CustomTag (eu.transkribus.core.model.beans.customtags.CustomTag)1 CustomTagList (eu.transkribus.core.model.beans.customtags.CustomTagList)1 RegionType (eu.transkribus.core.model.beans.pagecontent.RegionType)1 TextLineType (eu.transkribus.core.model.beans.pagecontent.TextLineType)1 TrpPageType (eu.transkribus.core.model.beans.pagecontent_trp.TrpPageType)1 TrpRegionType (eu.transkribus.core.model.beans.pagecontent_trp.TrpRegionType)1 TrpTableCellType (eu.transkribus.core.model.beans.pagecontent_trp.TrpTableCellType)1 TrpTableRegionType (eu.transkribus.core.model.beans.pagecontent_trp.TrpTableRegionType)1 TrpTextLineType (eu.transkribus.core.model.beans.pagecontent_trp.TrpTextLineType)1