Manipulate PDF Documents in Java

Aspose.PDF for Java includes document-structure operations that go beyond simple page editing.

Validate PDF/A-1a compliance

Use this example when you need to check whether a document meets the PDF/A-1a archival standard.

  1. Open the source PDF Document.
  2. Run validation against the required PdfFormat target.
  3. Save the validation report to the specified output path.
public static void validatePdfaStandardA1a(Path inputFile, Path outputFile) {
    try (Document document = new Document(inputFile.toString())) {
        document.validate(outputFile.toString(), PdfFormat.PDF_A_1A);
    }
}

Validate PDF/A-1b compliance

This variation validates the same source document against the PDF/A-1b conformance level.

  1. Open the source PDF Document.
  2. Call the validation method with the PdfFormat value for PDF/A-1b.
  3. Write the validation result to the output report file.
public static void validatePdfaStandardA1b(Path inputFile, Path outputFile) {
    try (Document document = new Document(inputFile.toString())) {
        document.validate(outputFile.toString(), PdfFormat.PDF_A_1B);
    }
}

Add a table of contents

Use this approach when the document should include a generated TOC page with links to content pages.

  1. Open the source PDF Document.
  2. Insert a new TOC Page and configure its TocInfo.
  3. Create Heading entries that point to the destination pages.
  4. Save the updated document.
public static void addTableOfContents(Path inputFile, Path outputFile) {
    try (Document document = new Document(inputFile.toString())) {
        Page tocPage = document.getPages().insert(1);
        TocInfo tocInfo = new TocInfo();
        TextFragment title = new TextFragment("Table Of Contents");
        title.getTextState().setFontSize(20);
        title.getTextState().setFontStyle(FontStyles.Bold);
        tocInfo.setTitle(title);
        tocPage.setTocInfo(tocInfo);

        String[] titles = {"First page", "Second page"};
        for (int index = 0; index < titles.length && index + 2 <= document.getPages().size(); index++) {
            Heading heading = new Heading(1);
            TextSegment segment = new TextSegment(titles[index]);
            heading.setTocPage(tocPage);
            heading.getSegments().add(segment);
            Page destinationPage = document.getPages().get_Item(index + 2);
            heading.setDestinationPage(destinationPage);
            heading.setTop(destinationPage.getRect().getHeight());
            tocPage.getParagraphs().add(heading);
        }

        document.save(outputFile.toString());
    }
}

Customize TOC levels and formatting

This example shows how to assign different visual settings to multiple table-of-contents levels.

  1. Open the source PDF Document.
  2. Add a TOC Page and configure the TocInfo format array.
  3. Create sample Heading entries with different levels.
  4. Save the document with the formatted TOC.
public static void setTocLevels(Path inputFile, Path outputFile) {
    try (Document document = new Document(inputFile.toString())) {
        Page tocPage = document.getPages().add();
        TocInfo tocInfo = new TocInfo();
        tocInfo.setLineDash(TabLeaderType.Solid);
        TextFragment title = new TextFragment("Table Of Contents");
        title.getTextState().setFontSize(30);
        tocInfo.setTitle(title);
        tocPage.setTocInfo(tocInfo);

        tocInfo.setFormatArrayLength(4);
        tocInfo.getFormatArray()[0].getMargin().setLeft(0);
        tocInfo.getFormatArray()[0].getMargin().setRight(30);
        tocInfo.getFormatArray()[0].setLineDash(TabLeaderType.Dot);
        tocInfo.getFormatArray()[0].getTextState().setFontStyle(FontStyles.Bold | FontStyles.Italic);
        tocInfo.getFormatArray()[1].getMargin().setLeft(10);
        tocInfo.getFormatArray()[1].getMargin().setRight(30);
        tocInfo.getFormatArray()[1].setLineDash(3);
        tocInfo.getFormatArray()[1].getTextState().setFontSize(10);
        tocInfo.getFormatArray()[2].getMargin().setLeft(20);
        tocInfo.getFormatArray()[2].getMargin().setRight(30);
        tocInfo.getFormatArray()[2].getTextState().setFontStyle(FontStyles.Bold);
        tocInfo.getFormatArray()[3].setLineDash(TabLeaderType.Solid);
        tocInfo.getFormatArray()[3].getMargin().setLeft(30);
        tocInfo.getFormatArray()[3].getMargin().setRight(30);
        tocInfo.getFormatArray()[3].getTextState().setFontStyle(FontStyles.Bold);

        try (Page page = document.getPages().add()) {
            for (int level = 1; level < 5; level++) {
                Heading heading = new Heading(level);
                heading.setAutoSequence(true);
                heading.setTocPage(tocPage);
                heading.getTextState().setFont(FontRepository.findFont("Arial"));
                heading.getSegments().add(new TextSegment("Sample Heading" + level));
                heading.setInList(true);
                page.getParagraphs().add(heading);
            }
        }

        document.save(outputFile.toString());
    }
}

Hide page numbers in the TOC

Use this example when the table of contents should show entry titles without page numbers.

  1. Open the source PDF Document.
  2. Add a TOC Page and disable page numbers in TocInfo.
  3. Create the required Heading entry and add it to the content page.
  4. Save the updated document.
public static void hidePageNumbersInToc(Path inputFile, Path outputFile) {
    try (Document document = new Document(inputFile.toString())) {
        Page page;
        Heading heading;
        try (Page tocPage = document.getPages().add()) {
            TocInfo tocInfo = new TocInfo();
            TextFragment title = new TextFragment("Table Of Contents");
            title.getTextState().setFontSize(20);
            title.getTextState().setFontStyle(FontStyles.Bold);
            tocInfo.setTitle(title);
            tocInfo.setShowPageNumbers(false);
            tocPage.setTocInfo(tocInfo);

            tocInfo.setFormatArrayLength(4);
            tocInfo.getFormatArray()[0].getMargin().setRight(0);
            tocInfo.getFormatArray()[0].getTextState().setFontStyle(FontStyles.Bold | FontStyles.Italic);
            tocInfo.getFormatArray()[1].getMargin().setLeft(30);
            tocInfo.getFormatArray()[1].getTextState().setUnderline(true);
            tocInfo.getFormatArray()[1].getTextState().setFontSize(10);
            tocInfo.getFormatArray()[2].getTextState().setFontStyle(FontStyles.Bold);
            tocInfo.getFormatArray()[3].getTextState().setFontStyle(FontStyles.Bold);

            page = document.getPages().add();
            heading = new Heading(1);
            heading.setTocPage(tocPage);
        }
        heading.setAutoSequence(true);
        heading.setInList(true);
        heading.getSegments().add(new TextSegment("this is heading of level 1"));
        page.getParagraphs().add(heading);

        document.save(outputFile.toString());
    }
}

Customize TOC page number prefixes

This example adds a custom prefix to the page numbers displayed in the generated table of contents.

  1. Open the source PDF Document.
  2. Insert a TOC Page and set the desired page number prefix in TocInfo.
  3. Create Heading entries that point to each page.
  4. Save the updated document.
public static void customizePageNumbersInToc(Path inputFile, Path outputFile) {
    try (Document document = new Document(inputFile.toString())) {
        Page tocPage = document.getPages().insert(1);
        TocInfo tocInfo = new TocInfo();
        TextFragment title = new TextFragment("Table Of Contents");
        title.getTextState().setFontSize(20);
        title.getTextState().setFontStyle(FontStyles.Bold);
        tocInfo.setTitle(title);
        tocInfo.setPageNumbersPrefix("P");
        tocPage.setTocInfo(tocInfo);

        for (int index = 1; index <= document.getPages().size(); index++) {
            Page page = document.getPages().get_Item(index);
            Heading heading = new Heading(1);
            heading.setTocPage(tocPage);
            heading.setDestinationPage(page);
            heading.setTop(page.getRect().getHeight());
            heading.getSegments().add(new TextSegment("Page " + index));
            tocPage.getParagraphs().add(heading);
        }

        document.save(outputFile.toString());
    }
}

Add a PDF expiry script

Use this approach when the document should run JavaScript on open and show an expiry warning after a specific date.

  1. Open the source PDF Document and add any required content.
  2. Create a JavascriptAction with the expiry logic.
  3. Assign the script as the document open action and save the output file.
public static void setPdfExpiryDate(Path inputFile, Path outputFile) {
    try (Document document = new Document(inputFile.toString())) {
        try (Page page = document.getPages().add()) {
            page.getParagraphs().add(new TextFragment("Hello World..."));
        }
        JavascriptAction script = new JavascriptAction(
                "var year=2017;"
                        + "var month=5;"
                        + "today = new Date(); today = new Date(today.getFullYear(), today.getMonth());"
                        + "expiry = new Date(year, month);"
                        + "if (today.getTime() > expiry.getTime())"
                        + "app.alert('The file is expired. You need a new one.');");
        document.setOpenAction(script);
        document.save(outputFile.toString());
    }
}

Flatten a fillable PDF form

This example converts interactive form fields into static page content so the resulting document is no longer editable as a form.

  1. Open the source PDF Document.
  2. Check whether the document contains form widgets.
  3. Flatten each Field represented by a WidgetAnnotation.
  4. Save the flattened document.
public static void flattenFillablePdf(Path inputFile, Path outputFile) {
    try (Document document = new Document(inputFile.toString())) {
        if (document.getForm() != null && document.getForm().size() > 0) {
            for (WidgetAnnotation annotation : document.getForm()) {
                if (annotation instanceof Field field) {
                    field.flatten();
                }
            }
        }
        document.save(outputFile.toString());
    }
}
Format PDF Documents in Java Optimize PDF Files in Java