use of org.docx4j.model.fields.FieldUpdater 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());
}
use of org.docx4j.model.fields.FieldUpdater in project docx4j-template by vindell.
the class WordprocessingMLPackageWriter method writeToPDFWhithFo.
/**
* 将 {@link org.docx4j.openpackaging.packages.WordprocessingMLPackage} 存为 pdf
*/
public void writeToPDFWhithFo(WordprocessingMLPackage wmlPackage, OutputStream output) throws IOException, Docx4JException {
Assert.notNull(wmlPackage, " wmlPackage is not specified!");
Assert.notNull(output, " output is not specified!");
try {
// Font regex (optional)
// Set regex if you want to restrict to some defined subset of fonts
// Here we have to do this before calling createContent,
// since that discovers fonts
// String regex = null;
// Refresh the values of DOCPROPERTY fields
FieldUpdater updater = new FieldUpdater(wmlPackage);
updater.update(true);
// .. example of mapping font Times New Roman which doesn't have certain Arabic glyphs
// eg Glyph "ي" (0x64a, afii57450) not available in font "TimesNewRomanPS-ItalicMT".
// eg Glyph "ج" (0x62c, afii57420) not available in font "TimesNewRomanPS-ItalicMT".
// to a font which does
PhysicalFonts.get("Arial Unicode MS");
// FO exporter setup (required)
// .. the FOSettings object
FOSettings foSettings = Docx4J.createFOSettings();
foSettings.setWmlPackage(wmlPackage);
foSettings.setApacheFopMime("application/pdf");
// Document format:
// The default implementation of the FORenderer that uses Apache Fop will output
// a PDF document if nothing is passed via
// foSettings.setApacheFopMime(apacheFopMime)
// apacheFopMime can be any of the output formats defined in org.apache.fop.apps.MimeConstants eg org.apache.fop.apps.MimeConstants.MIME_FOP_IF or
// FOSettings.INTERNAL_FO_MIME if you want the fo document as the result.
// foSettings.setApacheFopMime(FOSettings.INTERNAL_FO_MIME);
// Specify whether PDF export uses XSLT or not to create the FO
// (XSLT takes longer, but is more complete).
// Don't care what type of exporter you use
Docx4J.toFO(foSettings, output, Docx4J.FLAG_EXPORT_PREFER_XSL);
// Prefer the exporter, that uses a xsl transformation
// Docx4J.toFO(foSettings, os, Docx4J.FLAG_EXPORT_PREFER_XSL);
// Prefer the exporter, that doesn't use a xsl transformation (= uses a visitor)
// faster, but not yet at feature parity
// Docx4J.toFO(foSettings, os, Docx4J.FLAG_EXPORT_PREFER_NONXSL);
// Clean up, so any ObfuscatedFontPart temp files can be deleted
// if (wordMLPackage.getMainDocumentPart().getFontTablePart()!=null) {
// wordMLPackage.getMainDocumentPart().getFontTablePart().deleteEmbeddedFontTempFiles();
// }
// This would also do it, via finalize() methods
updater = null;
foSettings = null;
wmlPackage = null;
} finally {
IOUtils.closeQuietly(output);
}
}
Aggregations