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:
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();
}
}
}