use of com.tutego.jrtf.RtfText in project TranskribusCore by Transkribus.
the class TrpRtfBuilder method writeRtfForDoc.
public static void writeRtfForDoc(TrpDoc doc, boolean wordBased, boolean writeTags, boolean doBlackening, File file, Set<Integer> pageIndices, IProgressMonitor monitor, ExportCache cache) throws JAXBException, IOException {
exportTags = writeTags;
tagnames = cache.getSelectedTags();
TrpRtfBuilder.doBlackening = doBlackening;
/*
* get all names of tags
*/
// tagnames = CustomTagFactory.getRegisteredTagNames();
Rtf rtf = Rtf.rtf();
List<TrpPage> pages = doc.getPages();
int totalPages = pageIndices == null ? pages.size() : pageIndices.size();
if (monitor != null) {
monitor.beginTask("Exporting to RTF", totalPages);
}
int c = 0;
for (int i = 0; i < pages.size(); ++i) {
if (pageIndices != null && !pageIndices.contains(i))
continue;
if (monitor != null) {
if (monitor.isCanceled()) {
logger.debug("RTF 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();
TrpPageType trpPage = tr.getPage();
logger.debug("writing rtf for page " + (i + 1) + "/" + doc.getNPages());
// rtf().header(color( 204, 0, 0 ).at( 0 ),
// color( 0, 0xff, 0 ).at( 1 ),
// color( 0, 0, 0xff ).at( 2 ),
// font( "Calibri" ).at( 0 ) );
// RtfHeaderColor color = RtfHeaderColor.color(0xff, 0, 0);
rtf.header(color(204, 0, 0).at(0), color(0, 0xff, 0).at(1)).section(getRtfParagraphsForTranscript(trpPage, wordBased));
++c;
if (monitor != null) {
monitor.worked(c);
}
}
// write tags at end of last page
if (exportTags) {
// RtfText headline = RtfText.text("Person names in this document (amount of found persons: " + persons.size() + ")", "\n");
/*
* for all different tagnames:
* find all custom tags in doc
* create list and
*/
ArrayList<RtfPara> tagParas = new ArrayList<RtfPara>();
// 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);
if (allTagsOfThisTagname.size() > 0) {
tagParas.add(RtfPara.p(RtfText.text(RtfText.underline(currTagname + " tags in this document: " + allTagsOfThisTagname.size()))));
// ArrayList<RtfText> tagTexts = new ArrayList<RtfText>();
Collection<String> valueSet = allTagsOfThisTagname.values();
RtfText[] tagTexts = new RtfText[valueSet.size()];
int l = 0;
for (String currEntry : valueSet) {
tagTexts[l++] = RtfText.text(currEntry.concat("\n"));
// logger.debug("tag value is " + currEntry);
}
tagParas.add(RtfPara.p(tagTexts));
}
}
// int parSize = getParsNumber();
// int k = 0;
//
// if (persons.size() > 0){
// logger.debug("k is " + k);
// List<String> newPersonList = new ArrayList<String>(new HashSet<String>(persons));
// tagParas[k++]=RtfPara.p(RtfText.text("Person names in this document (amount of found persons: " + newPersonList.size() + ")", "\n"));
// logger.debug("k is " + k);
// //rtf.p("Person names in this document (amount of found persons: " + persons.size() + ")", "\n");
// //to make the list contain only unique values
//
// RtfText[] personTexts = new RtfText[newPersonList.size()];
// for (int j=0; j<newPersonList.size(); ++j) {
// personTexts[j] = RtfText.text(newPersonList.get(j), "\n");
// logger.debug("person is " + newPersonList.get(j));
// }
// tagParas[k++] = RtfPara.p(personTexts);
// }
//
// if (places.size() > 0){
// List<String> newPlaceList = new ArrayList<String>(new HashSet<String>(places));
// tagParas[k++]=RtfPara.p(RtfText.text("Places in this document (amount of found places " + newPlaceList.size() + ")", "\n"));
//
// RtfText[] placeTexts = new RtfText[newPlaceList.size()];
// for (int j=0; j<newPlaceList.size(); ++j) {
// //RtfText.color(0, "red");
// placeTexts[j] = RtfText.color(0, newPlaceList.get(j).concat("\n"));
// logger.debug("place is " + newPlaceList.get(j));
// }
// RtfPara par2 = RtfPara.p(placeTexts);
// tagParas[k++] = par2;
// }
//
// if(addresses.size() > 0){
// List<String> newAddressList = new ArrayList<String>(new HashSet<String>(addresses));
// tagParas[k++]=RtfPara.p(RtfText.text("Addresses in this document (amount of found addresses " + newAddressList.size() + ")", "\n"));
//
// RtfText[] addresseTexts = new RtfText[newAddressList.size()];
// for (int j=0; j<newAddressList.size(); ++j) {
// addresseTexts[j] = RtfText.text(newAddressList.get(j), "\n");
// logger.debug("addresse is " + newAddressList.get(j));
// }
// RtfPara par3 = RtfPara.p(addresseTexts);
// tagParas[k++] = par3;
// }
// rtf.section(par3);
rtf.header(color(204, 0, 0).at(0)).section(tagParas);
}
rtf.out(new FileWriter(file));
logger.info("wrote rtf to: " + file.getAbsolutePath());
}
use of com.tutego.jrtf.RtfText in project TranskribusCore by Transkribus.
the class TrpRtfBuilder method getRtfParagraphsForTranscript.
// public static void writeRtfForElement(Rtf rtf, ITrpShapeType element, boolean wordBased, File file, boolean append) throws IOException, JAXBException {
// element.getUnicodeText();
// CustomTagList cl = element.getCustomTagList();
//
// RtfText text = RtfText.text(element.getUnicodeText());
// text = formatRtfText(text, element.getTextStyle());
//
//
//
// if (element instanceof TextLineType || element instanceof TextRegionType) {// TODO words vs lines and regions
// rtf.p(text);
// } else if (element instanceof TrpWordType) {
// // rtf.p(texts);
// }
//
//
// // cl.getCustomTagAndContinuations(tag)
//
//
//
// }
public static RtfPara[] getRtfParagraphsForTranscript(TrpPageType trpPage, boolean wordBased) throws IOException, JAXBException {
boolean rtl = false;
List<TrpTextRegionType> textRegions = trpPage.getTextRegions(true);
// List<TrpTextRegionType> textRegions = trpPage.getTextRegionsAndTextRegionsFromTableRegions(true);
RtfPara[] paras = new RtfPara[textRegions.size()];
for (int j = 0; j < textRegions.size(); ++j) {
TrpTextRegionType r = textRegions.get(j);
// if (exportTags){
// getTagsForShapeElement(r);
// }
List<TextLineType> lines = r.getTextLine();
RtfText[] linesTexts = new RtfText[lines.size()];
for (int i = 0; i < lines.size(); ++i) {
TrpTextLineType trpL = (TrpTextLineType) lines.get(i);
linesTexts[i] = (wordBased && trpL.getWord().size() > 0) ? getRtfTextForLineFromWords(trpL) : getRtfTextForShapeElement(trpL);
linesTexts[i] = RtfText.text(linesTexts[i], "\n");
}
// read from right to left -> alignment is right
if (rtl) {
// paras[j] = RtfPara.p(linesTexts).footnote("Test").alignRight();
} else {
String test = "test";
paras[j] = RtfPara.p(linesTexts);
// paras[j] = RtfPara.p(linesTexts, RtfText.footnote("Test")).alignLeft();
}
}
return paras;
// Rtf rtf = Rtf.rtf().section(paras);
// return rtf;
// for (RegionType r : trpPage.getTextRegionOrImageRegionOrLineDrawingRegion()) {
// if (r instanceof GraphicRegionType) {
// GraphicRegionType gr = (GraphicRegionType) r;
// // TODO: how to export images in pdf??
// r.getTextRegions(recursive);
// }
// }
// tr.getPage().getTextRegions(recursive);
// Rtf.rtf();
// RtfWriter;
}
use of com.tutego.jrtf.RtfText in project TranskribusCore by Transkribus.
the class TrpRtfBuilder method getRtfTextForLineFromWords.
// private static void getTagsForShapeElement(ITrpShapeType element) throws IOException{
//
// String textStr = element.getUnicodeText();
// CustomTagList cl = element.getCustomTagList();
// if (textStr == null || cl == null)
// throw new IOException("Element has no text or custom tag list: "+element+", class: "+element.getClass().getName());
//
// for (CustomTag nonIndexedTag : cl.getNonIndexedTags()) {
//
// logger.debug("nonindexed tag found ");
// storeCustomTag(nonIndexedTag, textStr);
//
// }
// for (CustomTag indexedTag : cl.getIndexedTags()) {
//
// logger.debug("indexed tag found ");
// storeCustomTag(indexedTag, textStr);
//
// }
//
// }
//
// private static void storeCustomTag(CustomTag currTag, String textStr) {
// if (!currTag.getTagName().equals("textStyle")){
//
// if (currTag.getOffset() != -1 && currTag.getLength() != -1 && (currTag.getOffset()+currTag.getLength() <= textStr.length())){
// tags.put(currTag, textStr.substring(currTag.getOffset(), currTag.getOffset()+currTag.getLength()));
// }
// else{
// tags.put(currTag, textStr);
// }
// logger.debug("++tag name is " + currTag.getTagName());
// logger.debug("text " + tags.get(currTag));
// }
//
// if (currTag.getTagName().equals("Person")){
// if (currTag.getOffset() != -1 && currTag.getLength() != -1 && (currTag.getOffset()+currTag.getLength() <= textStr.length())){
// persons.add(textStr.substring(currTag.getOffset(), currTag.getOffset()+currTag.getLength()));
// }
// else{
// logger.debug("with index is something wrong: offset " + currTag.getOffset() + " length " + currTag.getLength()) ;
// //throw new Exception("Something wrong with indexed tag for text: " + textStr);
// }
// }
// else if (currTag.getTagName().equals("Place")){
// if (currTag.getOffset() != -1 && currTag.getLength() != -1 && (currTag.getOffset()+currTag.getLength() <= textStr.length())){
// places.add(textStr.substring(currTag.getOffset(), currTag.getOffset()+currTag.getLength()));
// }
// }
//
// }
private static RtfText getRtfTextForLineFromWords(TrpTextLineType line) throws IOException {
List<WordType> words = line.getWord();
RtfText[] wordTexts = new RtfText[words.size()];
for (int i = 0; i < wordTexts.length; ++i) {
TrpWordType w = (TrpWordType) words.get(i);
wordTexts[i] = getRtfTextForShapeElement(w);
}
RtfText totalText = RtfText.text(true, wordTexts);
return totalText;
}
use of com.tutego.jrtf.RtfText in project TranskribusCore by Transkribus.
the class TrpRtfBuilder method getRtfTextForShapeElement.
private static RtfText getRtfTextForShapeElement(ITrpShapeType element) throws IOException {
String textStr = element.getUnicodeText();
CustomTagList cl = element.getCustomTagList();
if (textStr == null || cl == null)
throw new IOException("Element has no text or custom tag list: " + element + ", class: " + element.getClass().getName());
if (doBlackening) {
// format according to tags:CustomTagList
for (CustomTag nonIndexedTag : cl.getNonIndexedTags()) {
if (nonIndexedTag.getTagName().equals(RegionTypeUtil.BLACKENING_REGION.toLowerCase())) {
// logger.debug("nonindexed tag found ");
textStr = ExportUtils.blackenString(nonIndexedTag, textStr);
}
}
for (CustomTag indexedTag : cl.getIndexedTags()) {
if (indexedTag.getTagName().equals(RegionTypeUtil.BLACKENING_REGION.toLowerCase())) {
// logger.debug("nonindexed tag found ");
textStr = ExportUtils.blackenString(indexedTag, textStr);
}
}
}
List<TextStyleTag> textStylesTags = element.getTextStyleTags();
// if (exportTags){
// getTagsForShapeElement(element);
// }
RtfText[] chars = new RtfText[textStr.length()];
for (int i = 0; i < textStr.length(); ++i) {
chars[i] = RtfText.text(textStr.substring(i, i + 1));
// format according to "global" text style
chars[i] = formatRtfText(chars[i], element.getTextStyle());
/*
* format according to custom style tag - check for each char in the text if a special style should be set
*/
for (TextStyleTag styleTag : textStylesTags) {
if (i >= styleTag.getOffset() && i < (styleTag.getOffset() + styleTag.getLength())) {
chars[i] = formatRtfText(chars[i], styleTag.getTextStyle());
}
}
// // format according to tags:
// for (String nonIndexedTag : cl.getNonIndexedTagNames()) {
// charText = formatRtfText(charText, element);
// // TODO
// }
// for (String indexedTag : cl.getIndexedTagNames()) {
// // TODO
// }
// TODO: include structure types!! (also possible in custom tags!!)
// TODO: include reading order!!!
}
RtfText totalText = RtfText.text(false, (Object[]) chars);
return totalText;
}
use of com.tutego.jrtf.RtfText in project ddf by codice.
the class RtfTemplate method appendProperty.
private RtfRow appendProperty(String metacardId, Map.Entry<String, ExportCategory.ExportValue> entry) {
if (ExportCategory.ValueType.MEDIA.equals(entry.getValue().getType())) {
ExportCategory.ExportValue<byte[], ExportCategory.ValueType> value = entry.getValue();
Function<byte[], InputStream> fromByteArrayFunction = memoizeForImageData.apply(metacardId);
RtfText picture = Optional.of(value.getValue()).map(fromByteArrayFunction).map(this::imageFromStream).orElse(text(EMPTY_VALUE));
return row(entry.getKey(), picture);
}
return row(entry.getKey(), entry.getValue().getValue());
}
Aggregations