List of usage examples for org.apache.pdfbox.pdmodel PDPage setContents
public void setContents(List<PDStream> contents)
From source file:com.santaanna.friendlyreader.pdfstod.pdfstod3.ReplaceStringStreamEngine.java
License:Apache License
/** * Sammanfatta PDF dokumentet baserat p .. * * @param inputFile The PDF to open.//www. j a va 2 s. co m * @param outputFile The PDF to write to. * @param strToFind The string to find in the PDF document. * @param message The message to write in the file. * * @throws IOException If there is an error writing the data. * @throws COSVisitorException If there is an error writing the PDF. */ public Collection<SEmening> doIt(String inputFile, String outputFile1, boolean DoHighlight, int sumslidval, int valdmening) throws IOException, COSVisitorException { // the document // doc = null; // Output dokumentet (? Kollas!) PDFOperator gop = PDFOperator.getOperator("g"); COSFloat cfloat5 = new COSFloat("0.25"); COSFloat cfloat1 = new COSFloat("0.75"); Boolean gray1 = true; outputFile = outputFile1; String meningsrest = ""; String sidtext = ""; Boolean filesaved = false; try { helaTexten = ""; SkrivUt(3, "Fre DoIt doc1 load"); doc1 = PDDocument.load(inputFile); // Indokumentet. SkrivUt(3, "Efter DoIt doc1 load"); List pages = doc1.getDocumentCatalog().getAllPages(); // SkrivUt(2, "Antal sidor: " + pages.size()); for (int i = 0; i < pages.size(); i++) { // Frsta fasen skall samla hela texten samt ev ndra relativa till absoluta. // TBVector = new Vector<SETextBlock>(); // TB vektorn fr denna sida. // PageVector.add(i, TBVector); // Lgg till TB vektorn fr denna sida. SkrivUt(4, "Ny sida helaTexten: " + i); PDPage page = (PDPage) pages.get(i); PDStream contents = page.getContents(); //AH Kod frn PageDrawer: if (contents != null) { PDResources resources = page.findResources(); SkrivUt(4, "Fre getHelaTexten."); // Fas = relativ2absolut r inte implementerad n! // PDFStreamEngine.fas = PDFStreamEngine.rel2abs; setSumcharAlla(0); // Nollstll teckenrknaren fr strings sidtext = getHelaTexten(page.getContents().getStream()); //getTextFromPDF, Robin helaTexten += sidtext; // Hmta hela texten frn dokumentet. // SkrivUt(2, "Hela texten per sida0: " + sidtext); // helaTexten = ""; // Skall inte nollstllas nu! // helaTexten = ""; // AH* >> Nollstll INTE, - fr alla sidor. SkrivUt(4, "Efter getHelaTexten."); // cosStream.getStreamToken /* // PDStream nycont = new PDStream( getTokenList()); PDFStreamEngine.fas = PDFStreamEngine.splitstrings; processStream( page, resources, page.getContents().getStream()); SkrivUt(4, "Hela texten2: " + helaTexten); SkrivUt(4, "Efter andra processStream."); meningsvektor = Hittameningarna( helaTexten ); helaTexten = ""; // AH* >> Nollstll??? * */ } } // Extrahera meningarna frn hela texten: // SkrivUt(2, "Hela texten1: " + helaTexten); meningsvektor = Hittameningarna(helaTexten); // Splittra texten i meningar. SkrivUt(1, "Meningsvektor.Size: " + meningsvektor.size()); SEmening semen = null; for (int n = 0; n < meningsvektor.size(); n++) { // Lgg till mening till meningsvektor. // semen = new SEmening(); // semen.helameningen = menvektor.get( n ); // meningsvektor.add(n, semen); // Huvudstrukturen fr meningar. SkrivUt(1, "Mening: " + meningsvektor.get(n).helameningen); } /* for (int n = 0; n < meningsvektor.size(); n++ ) { SkrivUt(4, "Mening: " + meningsvektor.get( n ).helameningen); } */ // String helaTextTemp = helaTexten; // Vid nsta bearbetning skall string och array splittras vid // meningsgrnser. mind = 0; meningsrest = meningsvektor.get(mind).helameningen; // Kvarvarande text p aktuella sidan for (int i = 0; i < pages.size(); i++) { // Borde flytta p denna om de inte skall anvndas! // TBVector = new Vector<SETextBlock>(); // TB vektorn fr denna sida. // PageVector.add(i, TBVector); // Totalstruktur. // Lgg till TB vektorn fr denna sida. SkrivUt(4, "Ny sida Split: " + i); // PDPage ndrad till lokal variabel! page1 = (PDPage) pages.get(i); PDStream contents = page1.getContents(); //AH Kod frn PageDrawer: SkrivUt(4, "Innan contents test."); if (contents != null) { PDResources resources = page1.findResources(); SkrivUt(3, "Fre splitMeningar 1."); // PDFStreamEngine.fas = PDFStreamEngine.rel2abs; setSumcharAlla(0); // Nollstll teckenrknaren fr strings SkrivUt(4, "Fre splitMeningar 2."); meningsrest = splitMeningar(meningsrest, page1.getContents().getStream()); SkrivUt(4, "*** meningsrest: " + meningsrest); SkrivUt(4, "3, Efter splitMeningar."); } } // Kolla denna kod!!! // saveAndClose( outputFile, doc1 ); // AH**** // doc1 = PDDocument.load( inputFile ); // Indokumentet. // SkrivUt(3,"Efter DoIt doc1 load"); // pages = doc1.getDocumentCatalog().getAllPages(); Nyinlagd. Kvar??? // Hr skall g operatorer lggas till fr varje TJ och Tj! mind = 0; // Behvs denna hr? meningsrest = meningsvektor.get(mind).helameningen; // Kvarvarande text p aktuella sidan. for (int i = 0; i < pages.size(); i++) { // Borde flytta p denna om de inte skall anvndas! // TBVector = new Vector<SETextBlock>(); // TB vektorn fr denna sida. // PageVector.add(i, TBVector); // Totalstruktur. // Lgg till TB vektorn fr denna sida. SkrivUt(4, "Ny sida Gray: " + i); // PDPage ndrad till lokal variabel! page1 = (PDPage) pages.get(i); PDStream contents = page1.getContents(); //AH Kod frn PageDrawer: SkrivUt(4, "Innan contents test."); if (contents != null) { PDResources resources = page1.findResources(); SkrivUt(3, "Fre GrayInsert 1."); // PDFStreamEngine.fas = PDFStreamEngine.rel2abs; setSumcharAlla(0); // Nollstll teckenrknaren fr strings // SkrivUt(4, "Fre splitMeningar 2."); meningsrest = grayInsert(meningsrest, page1.getContents().getStream(), i); //SkrivUt(4, "*** meningsrest: "+ meningsrest); SkrivUt(3, "Efter grayInsert av sida."); } } SkrivUt(3, "Efter hela grayInsert."); // Bygg TB och meningsstrukturer. // mind = 0; meningsrest = meningsvektor.get(mind).helameningen; // Kvarvarande text p aktuella sidan. for (int i = 0; i < pages.size(); i++) { TBIndex = 0; // Index i textblocks strukturen. // Hr anvnds och byggs datastrukturerna! TBVector = new Vector<SETextBlock>(); // TB vektorn fr denna sida. PageVector.add(i, TBVector); // Totalstruktur. tbpagenr = i; // Lgg till TB vektorn fr denna sida. SkrivUt(4, "Ny sida Split: " + i); // PDPage ndrad till lokal variabel! page1 = (PDPage) pages.get(i); PDStream contents = page1.getContents(); //AH Kod frn PageDrawer: SkrivUt(4, "Innan contents test."); if (contents != null) { PDResources resources = page1.findResources(); SkrivUt(3, "Fre byggStrukturer 1."); // PDFStreamEngine.fas = PDFStreamEngine.rel2abs; setSumcharAlla(0); // Nollstll teckenrknaren fr strings SkrivUt(4, "Fre byggStrukturer 2."); meningsrest = byggStrukturer(meningsrest, page1.getContents().getStream(), i); SkrivUt(4, "*** meningsrest: " + meningsrest); SkrivUt(3, "Efter byggStrukturer."); } } // Skriv ut innehllet i TB strukturen: listTextBlocks(); // Skriv ut meningarna: listMeningar(); //*/ // Sista passet skall samla in TP fontmetrics och spara dem till TB strukturer. SkrivUt(4, "Fr lngt."); mind = 0; // Behvs denna hr? for (int i = 0; i < pages.size(); i++) { // Frsta fasen skall samla hela texten samt ev ndra relativa till absoluta. // TBVector = new Vector<SETextBlock>(); // TB vektorn fr denna sida. // PageVector.add(i, TBVector); // Lgg till TB vektorn fr denna sida. tempsidnr = i; SkrivUt(4, "Ny sida A: " + i); PDPage page = (PDPage) pages.get(i); PDStream contents = page.getContents(); //AH Kod frn PageDrawer: if (contents != null) { PDResources resources = page.findResources(); SkrivUt(4, "Fre processStream."); // PDFStreamEngine.fas = PDFStreamEngine.rel2abs; setSumcharAlla(0); // Nollstll teckenrknaren fr strings // SkrivUt(4, "Hela texten2FRE: " + helaTexten); // processStream( page, resources, page.getContents().getStream()); // Hr anropas sidhanteringen! // SkrivUt(2, "Hela texten2: " + helaTexten); // helaTexten = ""; // AH* >> Nollstll INTE, - fr alla sidor. SkrivUt(4, "Efter processStream. fre nya"); // cosStream.getStreamToken /* // PDStream nycont = new PDStream( getTokenList()); PDFStreamEngine.fas = PDFStreamEngine.splitstrings; processStream( page, resources, page.getContents().getStream()); SkrivUt(4, "Hela texten2: " + helaTexten); SkrivUt(4, "Efter andra processStream."); meningsvektor = Hittameningarna( helaTexten ); helaTexten = ""; // AH* >> Nollstll??? * */ } } SkrivUt(3, "Efter processStream."); //if (DoHighlight) //{ // Hr skall texten frmedlas till EasyReader och resultatlista med // meningar som skall highlightas skall returneras! if ((DoHighlight) && !(helaTexten.equals(""))) { SkrivUt(2, "Fre sammanfatta. helaTexten = \"\""); menisammanfattningen = sammanfatta(helaTexten, sumslidval); System.out.println(menisammanfattningen); } else menisammanfattningen = null; // Hr skall g operatorernas argument modifieras fr de som skall vara // med i sammanfattningen. mind = 0; // Behvs denna hr? meningsrest = meningsvektor.get(mind).helameningen; // Kvarvarande text p aktuella sidan. cosenr = 0; // index fr COSString eller COSArray. mennr = 0; // index fr aktuell mening. mendelnr = 0; mendelantal = 0; // Antal delar som meningen bestr av. valdsida = -1; // valda sidan inte knd n. for (int i = 0; i < pages.size(); i++) { // Borde flytta p denna om de inte skall anvndas! // TBVector = new Vector<SETextBlock>(); // TB vektorn fr denna sida. // PageVector.add(i, TBVector); // Totalstruktur. // Lgg till TB vektorn fr denna sida. SkrivUt(4, "Ny sida highlight: " + i); // PDPage ndrad till lokal variabel! page1 = (PDPage) pages.get(i); PDStream contents = page1.getContents(); //AH Kod frn PageDrawer: SkrivUt(4, "Innan contents test."); if (contents != null) { PDResources resources = page1.findResources(); SkrivUt(1, "Fre highlight 1. Sida: " + i); // PDFStreamEngine.fas = PDFStreamEngine.rel2abs; setSumcharAlla(0); // Nollstll teckenrknaren fr strings // SkrivUt(4, "Fre splitMeningar 2."); // if (DoHighlight) meningsrest = highlight(meningsrest, page1.getContents().getStream(), i, DoHighlight, valdmening); //SkrivUt(4, "*** meningsrest: "+ meningsrest); SkrivUt(1, "Efter highlight av sida:" + i); } } SkrivUt(3, "Efter hela highlight."); /*} else // Spara data till pageTokens fr sparande till fil efter. { }*/ // Dags att hmta fontmetrics och spara till fil. r det samma som ovan? // Skall inte gras f.n! for (int i = 0; i < pages.size(); i++) { TBVector = new Vector<SETextBlock>(); // TB vektorn fr denna sida. PageVector.add(i, TBVector); // Lgg till TB vektorn fr denna sida. SkrivUt(4, "Ny sida X: " + i); // PDPage ndrad, inte lokal lngre! page = (PDPage) pages.get(i); PDStream contents = page.getContents(); //AH Kod frn PageDrawer: if (contents != null) { PDResources resources = page.findResources(); SkrivUt(4, "Fre processStream."); // PDFStreamEngine.fas = PDFStreamEngine.rel2abs; setSumcharAlla(0); // Nollstll teckenrknaren fr strings // AH* Nsta rad anvnds fr att hmta ut fontmetrics. /* processStream( page, resources, page.getContents().getStream()); // Hr anropas sidhanteringen! SkrivUt(4, "Hela texten1: " + helaTexten); // helaTexten = ""; // Skall inte nollstllas nu! SkrivUt(4, "Efter processStream. fre nya"); // cosStream.getStreamToken * */ // PDStream nycont = new PDStream( getTokenList()); // PDFStreamEngine.fas = PDFStreamEngine.splitstrings; // Nedanstende har anropats ovan. // processStream( page, resources, page.getContents().getStream()); // SkrivUt(4, "Hela texten3: " + helaTexten); SkrivUt(4, "Efter andra processStream."); } SkrivUt(3, "Efter hela andra processStream."); /* PDFStreamParser parser = new PDFStreamParser(contents.getStream()); parser.parse(); * */ // SkrivUt(4, "Egna loopen Sida: " + i); /* List tokens = getTokenList();// AH* parser.getTokens(); Tidigare hmtning av lista. // Dvs hmta INTE tokens frn den parsade filen. Anvnd tidigare data. LinkedList arguments = new LinkedList(); // AH* argumenten till operatorn. 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 //AH: //SkrivUt(4, "ArgumentList length: " + arguments.size()); //>> AH* SkrivUt(4, "Operator anrop:" + OperatorCall( op, arguments )); // AH: Hr borde man gra ett anrop till StreamEngine! arguments = new LinkedList(); // Mste nollstlla argumenten // efter varje operator. 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() ); // AH* Testa tillgg av kod. tokens.add(j-1, gop); if (gray1) { tokens.add(j-1,cfloat1 ); gray1 = false; } else { tokens.add(j-1, cfloat5); gray1 = true; } j = j+2; } 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() ); } } // AH: Tillagd kod! /* tokens.add(j-1, gop); if (gray1) { tokens.add(j-1,cfloat1 ); gray1 = false; } else { tokens.add(j-1, cfloat5); gray1 = true; } j = j+2; } } else // Inte PDFOperator, samla argument! { if (next instanceof COSBase) { arguments.add( next); //SkrivUt(4, "COSBase " + next.toString()); } else { SkrivUt(4, "next inte rtt typ!"); } } } */ //now that the tokens are updated we will replace the //page content stream. // Uppdatera data till filen! SkrivUt(3, ">>> Fre spara tokens i DoIt."); PDStream updatedStream = new PDStream(doc1); SkrivUt(3, ">>> Efter updated stream i DoIt."); OutputStream out = updatedStream.createOutputStream(); ContentStreamWriter tokenWriter = new ContentStreamWriter(out); tokenWriter.writeTokens(pageTokens.get(i)); page.setContents(updatedStream); SkrivUt(3, ">>> Efter spara tokens i DoIt."); } /* if (!filesaved) { doc1.save( outputFile ); filesaved = true; } doc1.close(); SkrivUt(3, "doc1 closed 1."); * */ } finally { saveAndClose(outputFile, doc1); /* SkrivUt(2, "Finally."); if( doc1 != null ) { if (!filesaved) { doc1.save( outputFile ); filesaved = true; } doc1.close(); SkrivUt(3, "doc1 closed 2."); } * */ } return meningsvektor; }
From source file:fi.nls.oskari.printout.printing.PDPageContentStream.java
License:Apache License
/** * Create a new PDPage content stream./*w ww . java 2 s . c o m*/ * * @param document * The document the page is part of. * @param sourcePage * The page to write the contents to. * @param appendContent * Indicates whether content will be overwritten. If false all * previous content is deleted. * @param compress * Tell if the content stream should compress the page contents. * @param resetContext * Tell if the graphic context should be reseted. * @throws IOException * If there is an error writing to the page contents. */ public PDPageContentStream(PDDocument document, PDPage sourcePage, boolean appendContent, boolean compress, boolean resetContext) throws IOException { page = sourcePage; resources = page.getResources(); if (resources == null) { resources = new PDResources(); page.setResources(resources); } // Get the pdstream from the source page instead of creating a new one PDStream contents = sourcePage.getContents(); boolean hasContent = contents != null; // If request specifies the need to append to the document if (appendContent && hasContent) { // Create a pdstream to append new content PDStream contentsToAppend = new PDStream(document); // This will be the resulting COSStreamArray after existing and new // streams are merged COSStreamArray compoundStream = null; // If contents is already an array, a new stream is simply appended // to it if (contents.getStream() instanceof COSStreamArray) { compoundStream = (COSStreamArray) contents.getStream(); compoundStream.appendStream(contentsToAppend.getStream()); } else { // Creates the COSStreamArray and adds the current stream plus a // new one to it COSArray newArray = new COSArray(); newArray.add(contents.getCOSObject()); newArray.add(contentsToAppend.getCOSObject()); compoundStream = new COSStreamArray(newArray); } if (compress) { List<COSName> filters = new ArrayList<COSName>(); filters.add(COSName.FLATE_DECODE); contentsToAppend.setFilters(filters); } if (resetContext) { // create a new stream to encapsulate the existing stream PDStream saveGraphics = new PDStream(document); output = saveGraphics.createOutputStream(); // save the initial/unmodified graphics context saveGraphicsState(); close(); // ? if (compress) { List<COSName> filters = new ArrayList<COSName>(); filters.add(COSName.FLATE_DECODE); saveGraphics.setFilters(filters); } // insert the new stream at the beginning compoundStream.insertCOSStream(saveGraphics); } // Sets the compoundStream as page contents sourcePage.setContents(new PDStream(compoundStream)); output = contentsToAppend.createOutputStream(); if (resetContext) { // restore the initial/unmodified graphics context restoreGraphicsState(); } } else { if (hasContent) { LOG.warn("You are overwriting an existing content, you should use the append mode"); } contents = new PDStream(document); if (compress) { List<COSName> filters = new ArrayList<COSName>(); filters.add(COSName.FLATE_DECODE); contents.setFilters(filters); } sourcePage.setContents(contents); output = contents.createOutputStream(); } formatDecimal.setMaximumFractionDigits(10); formatDecimal.setGroupingUsed(false); }
From source file:Utilities.GlobalVar.java
public static void updateSeqNum(PDDocument doc, String cycle) throws IOException { int sequenceNum = 1; 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();//from w ww . j a va 2s . c o m 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(); // System.out.println(string); // System.out.println(string.charAt(5)); if (string.contains("/0")) { String seq = cycle + "/" + GlobalVar.globalCountGenerator5Digit(sequenceNum); string = string.replaceFirst(string, seq); previous.reset(); previous.append(string.getBytes("ISO-8859-1")); sequenceNum++; break; } //Word you want to change. Currently this code changes word "Solr" to "Solr123" 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(); // System.out.println(string); if (string.contains("/00")) { String seq = cycle + "/" + GlobalVar.globalCountGenerator5Digit(sequenceNum); string = string.replaceFirst(string, seq); cosString.reset(); cosString.append(string.getBytes("ISO-8859-1")); sequenceNum++; break; } // Currently this code changes word "Solr" to "Solr123" cosString.reset(); cosString.append(string.getBytes("ISO-8859-1")); // break; } } } } } // 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); } }