We Keep Coding

I'm using PDFBox to replace text, strange characters

I'm using PDFBox to replace text in a template and there are characters (e.g. a simple J) that the tool recognizes as a special character. Any help to solve this problem?
public static PDDocument replaceText(PDDocument document, Map<String, String> mapVars) throws IOException {
for (PDPage page : document.getPages()) {
PDFStreamParser parser = new PDFStreamParser(page);
parser.parse();
List<?> tokens = parser.getTokens();
for (int j = 0; j < tokens.size(); j++) {
Object next = tokens.get(j);
if (next instanceof Operator) {
Operator op = (Operator) next;
String pstring = "";
int prej = 0;
if (op.getName().equals("TJ")) {
COSArray previous = (COSArray) tokens.get(j - 1);
for (int k = 0; k < previous.size(); k++) {
Object arrElement = previous.getObject(k);
if (arrElement instanceof COSString) {
COSString cosString = (COSString) arrElement;
String string = cosString.getString();
if (j == prej) {
pstring += string;
} else {
prej = j;
pstring = string;
}
}
}
if (mapVars.containsKey(pstring.trim())) {
String replacement = mapVars.get(pstring.trim());
COSString sx = new COSString(replacement);
sx.setValue(replacement.getBytes());
previous.clear();
previous.add(0, sx);
}
}
}
}
PDStream updatedStream = new PDStream(document);
OutputStream out = updatedStream.createOutputStream(COSName.FLATE_DECODE);
ContentStreamWriter tokenWriter = new ContentStreamWriter(out);
tokenWriter.writeTokens(tokens);
out.close();
page.setContents(updatedStream);
}
return document;
}

How to keep the order of words while reading a right to left text pdf

I am trying to parse a text from a pdf file
(with right to left language)
using java (code below)
sometimes because it's a right to
left language -
the order of the words
changes after my try to break the lines.
For example:
טלפון: טלפון1 דואר:דואר1
Became:
דואר1 : דואר טלפון1 טלפון:
public void test(){
PDFParser parser = null;
PDDocument pdDoc = null;
COSDocument cosDoc = null;
PDFTextStripper pdfStripper;
String parsedText = "";
try {
parser = new PDFParser(new RandomAccessFile(new File(file1), "r"));
parser.parse();
cosDoc = parser.getDocument();
pdfStripper = new PDFTextStripper();
pdfStripper.setSortByPosition(true);
//separator
pdfStripper.setWordSeparator(" ");
pdDoc = new PDDocument(cosDoc);
//get count of pages
int pages = pdDoc.getPages().getCount();
pdfStripper.setStartPage(1);
pdfStripper.setEndPage(1);
parsedText = parsedText + pdfStripper.getText(pdDoc);
if(pages>1){
//
}
StringTokenizer lines = new StringTokenizer(parsedText, "\n");
return lines.getTokenList();
} catch (){
}
}

Try to use simple invert:
public String invert(String s){
String arr[] = s.split(" ");
int len = arr.length;
for (int i = 0; i < len / 2; i++) {
String temp = arr[i];
arr[i] = arr[len - i - 1];
arr[len - i - 1] = temp;
}
return Arrays.stream(arr)
.collect(Collectors.joining(" "));
}
Using example:
System.out.println(invert("1 2 3 4 5");
Result:
5 4 3 2 1
Also, you should be considering another delimiter signs (enter, tabulation, comma...)

Bad characters when replacing text in pdf using pdfbox

I'm trying to replace text in pdf and it's kind of replaced, this is my code
PDDocument doc = null;
int occurrences = 0;
try {
doc = PDDocument.load("test.pdf"); //Input PDF File Name
List pages = doc.getDocumentCatalog().getAllPages();
for (int i = 0; i < pages.size(); i++) {
PDPage page = (PDPage) pages.get(i);
PDStream contents = page.getContents();
PDFStreamParser parser = new PDFStreamParser(contents.getStream());
parser.parse();
List tokens = parser.getTokens();
for (int j = 0; j < tokens.size(); j++) {
Object next = tokens.get(j);
if (next instanceof PDFOperator) {
PDFOperator op = (PDFOperator) next;
// Tj and TJ are the two operators that display strings in a PDF
if (op.getOperation().equals("Tj")) {
// Tj takes one operator and that is the string
// to display so lets update that operator
COSString previous = (COSString) tokens.get(j - 1);
String string = previous.getString();
if (string.contains("Good")) {
string = string.replace("Good", "Bad");
occurrences++;
}
//Word you want to change. Currently this code changes word "Good" to "Bad"
previous.reset();
previous.append(string.getBytes("ISO-8859-1"));
} else if (op.getOperation().equals("TJ")) {
COSArray previous = (COSArray) tokens.get(j - 1);
COSString temp = new COSString();
String tempString = "";
for (int t = 0; t < previous.size(); t++) {
if (previous.get(t) instanceof COSString) {
tempString += ((COSString) previous.get(t)).getString();
}
}
temp.append(tempString.getBytes("ISO-8859-1"));
tempString = "";
tempString = temp.getString();
if (tempString.contains("Good")) {
tempString = tempString.replace("Good", "Bad");
occurrences++;
}
previous.clear();
String[] stringArray = tempString.split(" ");
for (String string : stringArray) {
COSString cosString = new COSString();
string = string + " ";
cosString.append(string.getBytes("ISO-8859-1"));
previous.add(cosString);
}
}
}
}
// now that the tokens are updated we will replace the page content stream.
PDStream updatedStream = new PDStream(doc);
OutputStream out = updatedStream.createOutputStream();
ContentStreamWriter tokenWriter = new ContentStreamWriter(out);
tokenWriter.writeTokens(tokens);
page.setContents(updatedStream);
}
System.out.println("number of matches found: " + occurrences);
doc.save("a.pdf"); //Output file name
} catch (IOException ex) {
Logger.getLogger(ReplaceTextInPDF.class.getName()).log(Level.SEVERE, null, ex);
} catch (COSVisitorException ex) {
Logger.getLogger(ReplaceTextInPDF.class.getName()).log(Level.SEVERE, null, ex);
} finally {
if (doc != null) {
try {
doc.close();
} catch (IOException ex) {
Logger.getLogger(ReplaceTextInPDF.class.getName()).log(Level.SEVERE, null, ex);
}
}
}
the issue that it's replaced in a bad characters or hidden shape ( as example the bad word becomes only d character), but if i copy and paste it in another place it paste the expected word correctly,
also when i search the generated pdf for the new word it doesn't find it, but when i search with the old word it finds it in the replaced places

I found aspose, this link shows how to use it to replace text in pdfs, it's easy and works perfect except that it's not free, so the free version is printing copyrights line on the head of pdf file pages
http://www.aspose.com/docs/display/pdfjava/Replace+Text+in+Pages+of+a+PDF+Document

How to replace centered text in a PDF with PDFBox

I use the PDFTextReplacement example.
It does the replacement as expected, In case my text is left aligned.
But if my input pdf has a text centered, it replaces the text as a left aligned.
Ok, so I have to recalculate the right starting point.
For that reason I have two targets or questions:
How to determine the alignment?
How to calculate the right starting point?
Here is my code:
public PDDocument doIt(String inputFile, Map<String, String> text)
throws IOException, COSVisitorException {
// the document
PDDocument doc = null;
doc = PDDocument.load(inputFile);
List pages = doc.getDocumentCatalog().getAllPages();
for (int i = 0; i < pages.size(); i++) {
PDPage page = (PDPage) pages.get(i);
PDStream contents = page.getContents();
PDFStreamParser parser = new PDFStreamParser(contents.getStream());
parser.parse();
List tokens = parser.getTokens();
for (int j = 0; j < tokens.size(); j++) {
Object next = tokens.get(j);
if (next instanceof PDFOperator) {
PDFOperator op = (PDFOperator) next;
// Tj and TJ are the two operators that display
// strings in a PDF
String pstring = "";
int prej = 0;
if (op.getOperation().equals("Tj")) {
// Tj takes one operator and that is the string
// to display so lets update that operator
COSString previous = (COSString) tokens.get(j - 1);
String string = previous.getString();
// System.out.println(j + " " + string);
if (j == prej) {
pstring += string;
} else {
prej = j;
pstring = string;
}
previous.reset();
previous.append(string.getBytes("ISO-8859-1"));
} else if (op.getOperation().equals("TJ")) {
COSArray previous = (COSArray) tokens.get(j - 1);
for (int k = 0; k < previous.size(); k++) {
Object arrElement = previous.getObject(k);
if (arrElement instanceof COSString) {
COSString cosString = (COSString) arrElement;
String string = cosString.getString();
if (j == prej) {
pstring += string;
} else {
prej = j;
pstring = string;
}
cosString.reset();
// cosString.append(string
// .getBytes("ISO-8859-1"));
}
}
COSString cosString2 = (COSString) previous
.getObject(0);
for (int t = 1; t < previous.size(); t++)
previous.remove(t);
// cosString2.setNeedToBeUpdate(true);
if (text.containsKey(pstring.trim())) {
String textValue = text.get(pstring.trim());
cosString2.append(textValue.getBytes("ISO-8859-1"));
for (int k = 1; k < previous.size(); k++) {
previous.remove(k);
}
}
}
}
}
// now that the tokens are updated we will replace the
// page content stream.
PDStream updatedStream = new PDStream(doc);
OutputStream out = updatedStream.createOutputStream();
ContentStreamWriter tokenWriter = new ContentStreamWriter(out);
tokenWriter.writeTokens(tokens);
page.setContents(updatedStream);
}
return doc;
}

you can use this function:
public void doIt( String inputFile, String outputFile, String strToFind, String message)
throws IOException, COSVisitorException
{
// the document
PDDocument doc = null;
try
{
doc = PDDocument.load( inputFile );
List pages = doc.getDocumentCatalog().getAllPages();
for( int i=0; i<pages.size(); i++ )
{
PDPage page = (PDPage)pages.get( i );
PDStream contents = page.getContents();
PDFStreamParser parser = new PDFStreamParser(contents.getStream() );
parser.parse();
List tokens = parser.getTokens();
for( int j=0; j<tokens.size(); j++ )
{
Object next = tokens.get( j );
if( next instanceof PDFOperator )
{
PDFOperator op = (PDFOperator)next;
//Tj and TJ are the two operators that display
//strings in a PDF
if( op.getOperation().equals( "Tj" ) )
{
//Tj takes one operator and that is the string
//to display so lets update that operator
COSString previous = (COSString)tokens.get( j-1 );
String string = previous.getString();
string = string.replaceFirst( strToFind, message );
previous.reset();
previous.append( string.getBytes() );
}
else if( op.getOperation().equals( "TJ" ) )
{
COSArray previous = (COSArray)tokens.get( j-1 );
for( int k=0; k<previous.size(); k++ )
{
Object arrElement = previous.getObject( k );
if( arrElement instanceof COSString )
{
COSString cosString = (COSString)arrElement;
String string = cosString.getString();
string = string.replaceFirst( strToFind, message );
cosString.reset();
cosString.append( string.getBytes() );
}
}
}
}
}
//now that the tokens are updated we will replace the
//page content stream.
PDStream updatedStream = new PDStream(doc);
OutputStream out = updatedStream.createOutputStream();
ContentStreamWriter tokenWriter = new ContentStreamWriter(out);
tokenWriter.writeTokens( tokens );
page.setContents( updatedStream );
}
doc.save( outputFile );
}
finally
{
if( doc != null )
{
doc.close();
}
}
}

How to read bookmarks in PDF using itext at multi level?

I am using iText-Java to split PDFs at bookmark level.
Does anybody know or have any examples for splitting a PDF at bookmarks that exist at a level 2 or 3?
For ex: I have the bookmarks in the following levels:
Father
|-Son
|-Son
|-Daughter
|-|-Grand son
|-|-Grand daughter
Right now I have below code to read the bookmark which reads the base bookmark(Father). Basically SimpleBookmark.getBookmark(reader) line did all the work.
But I want to read the level 2 and level 3 bookmarks to split the content present between those inner level bookmarks.
public static void splitPDFByBookmarks(String pdf, String outputFolder){
try
{
PdfReader reader = new PdfReader(pdf);
//List of bookmarks: each bookmark is a map with values for title, page, etc
List<HashMap> bookmarks = SimpleBookmark.getBookmark(reader);
for(int i=0; i<bookmarks.size(); i++){
HashMap bm = bookmarks.get(i);
HashMap nextBM = i==bookmarks.size()-1 ? null : bookmarks.get(i+1);
//In my case I needed to split the title string
String title = ((String)bm.get("Title")).split(" ")[2];
log.debug("Titel: " + title);
String startPage = ((String)bm.get("Page")).split(" ")[0];
String startPageNextBM = nextBM==null ? "" + (reader.getNumberOfPages() + 1) : ((String)nextBM.get("Page")).split(" ")[0];
log.debug("Page: " + startPage);
log.debug("------------------");
extractBookmarkToPDF(reader, Integer.valueOf(startPage), Integer.valueOf(startPageNextBM), title + ".pdf",outputFolder);
}
}
catch (IOException e)
{
log.error(e.getMessage());
}
}
private static void extractBookmarkToPDF(PdfReader reader, int pageFrom, int pageTo, String outputName, String outputFolder){
Document document = new Document();
OutputStream os = null;
try{
os = new FileOutputStream(outputFolder + outputName);
// Create a writer for the outputstream
PdfWriter writer = PdfWriter.getInstance(document, os);
document.open();
PdfContentByte cb = writer.getDirectContent(); // Holds the PDF data
PdfImportedPage page;
while(pageFrom < pageTo) {
document.newPage();
page = writer.getImportedPage(reader, pageFrom);
cb.addTemplate(page, 0, 0);
pageFrom++;
}
os.flush();
document.close();
os.close();
}catch(Exception ex){
log.error(ex.getMessage());
}finally {
if (document.isOpen())
document.close();
try {
if (os != null)
os.close();
} catch (IOException ioe) {
log.error(ioe.getMessage());
}
}
}
Your help is much appreciated.
Thanks in advance! :)

You get an ArrayList<HashMap> when you call SimpleBookmark.getBookmark(reader); (do the cast if you need it). Try to iterate through that Arraylist and see its structure. If a bookmarks have sons (as you call it), it will contains another list with the same structure.
A recursive method could be the solution.

Reference for those who are looking at this using itext7
public void walkOutlines(PdfOutline outline, Map<String, PdfObject> names, PdfDocument pdfDocument,List<String>titles,List<Integer>pageNum) { //----------loop traversing all paths
for (PdfOutline child : outline.getAllChildren()){
if(child.getDestination() != null) {
prepareIndexFile(child,names,pdfDocument,titles,pageNum,list);
}
}
}
//-----Getting pageNumbers from outlines
public void prepareIndexFile(PdfOutline outline, Map<String, PdfObject> names, PdfDocument pdfDocument,List<String>titles,List<Integer>pageNum) {
String title = outline.getTitle();
PdfDestination pdfDestination = outline.getDestination();
String pdfStr = ((PdfString)pdfDestination.getPdfObject()).toUnicodeString();
PdfArray array = (PdfArray) names.get(pdfStr);
PdfObject pdfObj = array != null ? array.get(0) : null;
Integer pageNumber = pdfDocument.getPageNumber((PdfDictionary)pdfObj);
titles.add(title);
pageNum.add(pageNumber);
if(outline.getAllChildren().size() > 0) {
for (PdfOutline child : outline.getAllChildren()){
prepareIndexFile(child,names,pdfDocument,titles,pageNum);
}
}
}
public boolean splitPdf(String inputFile, final String outputFolder) {
boolean splitSuccess = true;
PdfDocument pdfDoc = null;
try {
PdfReader pdfReaderNew = new PdfReader(inputFile);
pdfDoc = new PdfDocument(pdfReaderNew);
final List<String> titles = new ArrayList<String>();
List<Integer> pageNum = new ArrayList<Integer>();
PdfNameTree destsTree = pdfDoc.getCatalog().getNameTree(PdfName.Dests);
Map<String, PdfObject> names = destsTree.getNames();//--------------------------------------Core logic for getting names
PdfOutline root = pdfDoc.getOutlines(false);//--------------------------------------Core logic for getting outlines
walkOutlines(root,names, pdfDoc, titles, pageNum,content); //------Logic to get bookmarks and pageNumbers
if (titles == null || titles.size()==0) {
splitSuccess = false;
}else { //------Proceed if it has bookmarks
for(int i=0;i<titles.size();i++) {
String title = titles.get(i);
String startPageNmStr =""+pageNum.get(i);
int startPage = Integer.parseInt(startPageNmStr);
int endPage = startPage;
if(i == titles.size() - 1) {
endPage = pdfDoc.getNumberOfPages();
}else {
int nextPage = pageNum.get(i+1);
if(nextPage > startPage) {
endPage = nextPage - 1;
}else {
endPage = nextPage;
}
}
String outFileName = outputFolder + File.separator + getFileName(title) + ".pdf";
PdfWriter pdfWriter = new PdfWriter(outFileName);
PdfDocument newDocument = new PdfDocument(pdfWriter, new DocumentProperties().setEventCountingMetaInfo(null));
pdfDoc.copyPagesTo(startPage, endPage, newDocument);
newDocument.close();
pdfWriter.close();
}
}
}catch(Exception e){
//---log
}
}