Skip to content

Commit

Permalink
#326 - We are now PDF/A1b, PDF/A2b and PDF/A2u compliant.
Browse files Browse the repository at this point in the history 
Next up is the a variants.
  • Loading branch information
@danfickle
danfickle committed Mar 3, 2019
1 parent 41d5aa8 commit 20605f2
Show file tree
Hide file tree
Showing 6 changed files with 157 additions and 37 deletions.
38 changes: 13 additions & 25 deletions openhtmltopdf-pdfa-testing/src/test/java/com/openhtmltopdf/pdfa/testing/PdfATester.java
View file
Original file line number Diff line number Diff line change
Expand Up @@ -17,8 +17,6 @@
import java.util.stream.Collectors;

import org.apache.pdfbox.io.IOUtils;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.graphics.color.PDOutputIntent;
import org.junit.BeforeClass;
import org.junit.Ignore;
import org.junit.Test;
Expand All @@ -31,7 +29,6 @@
import org.verapdf.pdfa.results.TestAssertion;
import org.verapdf.pdfa.results.ValidationResult;

import com.openhtmltopdf.pdfboxout.PdfBoxRenderer;
import com.openhtmltopdf.pdfboxout.PdfRendererBuilder;
import com.openhtmltopdf.pdfboxout.PdfRendererBuilder.PdfAConformance;

Expand Down Expand Up @@ -62,32 +59,22 @@ public boolean run(String resource, PDFAFlavour flavour, PdfAConformance conform

byte[] pdfBytes;

try (PDDocument doc = new PDDocument()) {
PdfRendererBuilder builder = new PdfRendererBuilder();
builder.usePDDocument(doc);
builder.useFastMode();
//builder.testMode(true);
builder.testMode(true);
builder.usePdfAConformance(conform);
builder.useFont(new File("target/test/artefacts/Karla-Bold.ttf"), "TestFont");
builder.withHtmlContent(html, PdfATester.class.getResource("/html/").toString());

try (PdfBoxRenderer renderer = builder.buildPdfRenderer()) {
renderer.createPDFWithoutClosing();
}

try (InputStream colorProfile = PdfATester.class.getResourceAsStream("/colorspaces/sRGB.icc")) {
PDOutputIntent oi = new PDOutputIntent(doc, colorProfile);
oi.setInfo("sRGB IEC61966-2.1");
oi.setOutputCondition("sRGB IEC61966-2.1");
oi.setOutputConditionIdentifier("sRGB IEC61966-2.1");
oi.setRegistryName("http://www.color.org");
doc.getDocumentCatalog().addOutputIntent(oi);
byte[] colorProfileBytes = IOUtils.toByteArray(colorProfile);
builder.useColorProfile(colorProfileBytes);
}

ByteArrayOutputStream baos = new ByteArrayOutputStream();
doc.save(baos);
builder.toStream(baos);
builder.run();
pdfBytes = baos.toByteArray();
}

Files.createDirectories(Paths.get("target/test/pdf/"));
Files.write(Paths.get("target/test/pdf/" + resource + "--" + flavour + ".pdf"), pdfBytes);
Expand All @@ -113,31 +100,32 @@ public boolean run(String resource, PDFAFlavour flavour, PdfAConformance conform
}
}

@Ignore // Failing, multiple. See issue number 326.
/**
* PDF/A conformance. Issue 326.
* NOTE: PDF/A1 standards do not support alpha in images.
*/
@Test
public void testAllInOnePdfA1b() throws Exception {
assertTrue(run("all-in-one", PDFAFlavour.PDFA_1_B, PdfAConformance.PDFA_1_B));
assertTrue(run("all-in-one-no-alpha", PDFAFlavour.PDFA_1_B, PdfAConformance.PDFA_1_B));
}

@Ignore
@Ignore // Failing because we haven't set up structure tagging for PDF/A1a standard.
@Test
public void testAllInOnePdfA1a() throws Exception {
assertTrue(run("all-in-one", PDFAFlavour.PDFA_1_A, PdfAConformance.PDFA_1_A));
assertTrue(run("all-in-one-no-alpha", PDFAFlavour.PDFA_1_A, PdfAConformance.PDFA_1_A));
}

@Ignore
@Test
public void testAllInOnePdfA2b() throws Exception {
assertTrue(run("all-in-one", PDFAFlavour.PDFA_2_B, PdfAConformance.PDFA_2_B));
}

@Ignore
@Ignore // Failing because we haven't set up structure tagging for PDF/A2a standard.
@Test
public void testAllInOnePdfA2a() throws Exception {
assertTrue(run("all-in-one", PDFAFlavour.PDFA_2_A, PdfAConformance.PDFA_2_A));
}

@Ignore
@Test
public void testAllInOnePdfA2u() throws Exception {
assertTrue(run("all-in-one", PDFAFlavour.PDFA_2_U, PdfAConformance.PDFA_2_U));
Expand Down
100 changes: 100 additions & 0 deletions openhtmltopdf-pdfa-testing/src/test/resources/html/all-in-one-no-alpha.html
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,100 @@
<html lang="EN-US">
<head>
<title>All-in-one PDF/UA Testcase</title>
<meta name="subject" content="PDF/UA all-in-one"/>
<meta name="author" content="openhtmltopdf.com team"/>
<meta name="description" content="An example containing everything for easy testing"/>

<bookmarks>
<bookmark name="Simple Paragraphs" href="#para"/>
<bookmark name="Lists" href="#lists">
<bookmark name="Ordered" href="#ordered"/>
<bookmark name="Unordered" href="#unordered"/>
</bookmark>
<bookmark name="Images" href="#images"/>
<bookmark name="Links" href="#links"/>
<bookmark name="Tables" href="#tables"/>
<bookmark name="Backgrounds" href="#backgrounds"/>
<bookmark name="Conclusion" href="#conclusion"/>
</bookmarks>

<style>
@page {
margin: 30px 20px;

@top-center {
font-family: 'TestFont'; /* Font provided with builder. */
font-size: 16px;
color: blue;
content: "This is PDF/UA page " counter(page) " of " counter(pages) ".";
}
}
body {
margin: 0;
font-family: 'TestFont'; /* Font provided with builder. */
font-size: 15px;
}
</style>
</head>
<body style="">
<h1 id="title">All-in-one accessible (PDF/UA, Section 508, WCAG) PDF example</h1>

<h2 id="para">Simple paragraphs</h2>

<p>Paragraph one. Some text that goes over multiple lines. OK, this is getting to the required length. Need another sentence to get there in the end.</p>
<p>Paragraph two. Some text that goes over multiple lines. OK, this is getting to the required length. Need another sentence to get there in the end.</p>
<p>Paragraph three. Some text that goes over multiple lines. OK, this is getting to the required length. Need another sentence to get there in the end.</p>

<h2 id="lists">Lists</h2>

<h3 id="ordered">Ordered</h3>
<ol>
<li>One</li>
<li>Two</li>
<li>Three</li>
</ol>

<h3 id="unordered">Unordered</h3>
<ul>
<li>Bullet item one</li>
<li>And two</li>
<li>And three</li>
</ul>

<h2 id="images">Images</h2>
<img src="../images/flyingsaucer-no-alpha.png" alt="The FlyingSaucer logo. We should get our own!"/>

<h2 id="links">Links</h2>
<p>This is an external link to the project <a title="The openhtmltopdf.com homepage" href="https://openhtmltopdf.com">homepage</a>.</p>
<p>This is an internal link to the <a title="Go to top" href="#title">top</a> of the document.</p>

<h2 id="tables">Tables</h2>
<table>
<caption>Simple table example with fake data</caption>

<thead>
<tr><th>Col One</th><th>Col Two</th></tr>
</thead>

<tbody>
<tr><td>One</td><td>Two</td></tr>
<tr><td>Three</td><td>Four</td></tr>
<tr><td>Five</td><td>Six</td></tr>
</tbody>

<tfoot>
<tr><td>Footer1</td><td>Footer2</td></tr>
<tr><td>Footer3</td><td>Footer4</td></tr>
</tfoot>
</table>

<h2 id="backgrounds">Backgrounds</h2>
<div style="background-color: red; height: 40px; border-radius: 10px; border: 1px solid gray;">
<p>Some text on a background. Remember to use a good contrast if using background colors.</p>
</div>

<h2 id="conclusion">Conclusion</h2>
<p>Remember to keep it simple for PDF/UA compliance.</p>

</body>
</html>
Binary file added openhtmltopdf-pdfa-testing/src/test/resources/images/flyingsaucer-no-alpha.png
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
5 changes: 5 additions & 0 deletions openhtmltopdf-pdfbox/src/main/java/com/openhtmltopdf/pdfboxout/PdfBoxFastLinkManager.java
View file
Original file line number Diff line number Diff line change
Expand Up @@ -254,6 +254,11 @@ private boolean placeAnnotation(AffineTransform transform, Shape linkShape, Rect
PDAnnotationLink annot) {
annot.setRectangle(new PDRectangle((float) targetArea.getMinX(), (float) targetArea.getMinY(),
(float) targetArea.getWidth(), (float) targetArea.getHeight()));

// PDF/A standard requires the print flag to be set and there shouldn't
// be any harm in setting it for other documents.
annot.setPrinted(true);

if (linkShape != null) {
float[] quadPoints = mapShapeToQuadPoints(transform, linkShape, targetArea);
/*
Expand Down
8 changes: 7 additions & 1 deletion openhtmltopdf-pdfbox/src/main/java/com/openhtmltopdf/pdfboxout/PdfBoxFastOutputDevice.java
View file
Original file line number Diff line number Diff line change
Expand Up @@ -199,10 +199,13 @@ private PageState copy() {
private PdfBoxAccessibilityHelper _pdfUa;
private final boolean _pdfUaConform;

public PdfBoxFastOutputDevice(float dotsPerPoint, boolean testMode, boolean pdfUaConform) {
private final boolean _pdfAConform;

public PdfBoxFastOutputDevice(float dotsPerPoint, boolean testMode, boolean pdfUaConform, boolean pdfAConform) {
_dotsPerPoint = dotsPerPoint;
_testMode = testMode;
_pdfUaConform = pdfUaConform;
_pdfAConform = pdfAConform;
}

@Override
Expand Down Expand Up @@ -796,7 +799,10 @@ public void drawImage(FSImage fsImage, int x, int y, boolean interpolate) {

PDImageXObject xobject = img.getXObject();
if (interpolate) {
// PDF/A does not support setting the interpolate flag to true.
if (!_pdfAConform) {
xobject.setInterpolate(true);
}
} else {
/*
* Specialcase for not interpolating an image, default is to always interpolate.
Expand Down
43 changes: 32 additions & 11 deletions openhtmltopdf-pdfbox/src/main/java/com/openhtmltopdf/pdfboxout/PdfBoxRenderer.java
View file
Original file line number Diff line number Diff line change
Expand Up @@ -58,12 +58,12 @@
import org.apache.pdfbox.pdmodel.common.PDMetadata;
import org.apache.pdfbox.pdmodel.common.PDRectangle;
import org.apache.pdfbox.pdmodel.documentinterchange.logicalstructure.PDMarkInfo;
import org.apache.pdfbox.pdmodel.documentinterchange.logicalstructure.PDStructureTreeRoot;
import org.apache.pdfbox.pdmodel.encryption.PDEncryption;
import org.apache.pdfbox.pdmodel.graphics.color.PDOutputIntent;
import org.apache.pdfbox.pdmodel.interactive.viewerpreferences.PDViewerPreferences;
import org.apache.xmpbox.XMPMetadata;
import org.apache.xmpbox.schema.AdobePDFSchema;
import org.apache.xmpbox.schema.DublinCoreSchema;
import org.apache.xmpbox.schema.PDFAIdentificationSchema;
import org.apache.xmpbox.schema.XMPBasicSchema;
import org.apache.xmpbox.schema.XMPSchema;
Expand Down Expand Up @@ -150,7 +150,9 @@ public class PdfBoxRenderer implements Closeable {
_dotsPerPoint = DEFAULT_DOTS_PER_POINT;
_testMode = state._testMode;
_useFastMode = state._useFastRenderer;
_outputDevice = state._useFastRenderer ? new PdfBoxFastOutputDevice(DEFAULT_DOTS_PER_POINT, _testMode, state._pdfUaConform) : new PdfBoxSlowOutputDevice(DEFAULT_DOTS_PER_POINT, _testMode);
_outputDevice = state._useFastRenderer ?
new PdfBoxFastOutputDevice(DEFAULT_DOTS_PER_POINT, _testMode, state._pdfUaConform, state._pdfAConformance != PdfAConformance.NONE) :
new PdfBoxSlowOutputDevice(DEFAULT_DOTS_PER_POINT, _testMode);
_outputDevice.setWriter(_pdfDoc);
_outputDevice.setStartPageNo(_pdfDoc.getNumberOfPages());

Expand Down Expand Up @@ -754,36 +756,55 @@ private void addPdfASchema(PDDocument document, int part, String conformance) {
XMPMetadata metadata = XMPMetadata.createXMPMetadata();

try {
String title = information.getTitle();
String author = information.getAuthor();
String subject = information.getSubject();
String keywords = information.getKeywords();
String producer = information.getProducer();

// NOTE: The XMP metadata MUST match up with the document information dictionary
// to be a valid PDF/A document.

PDFAIdentificationSchema pdfaid = metadata.createAndAddPFAIdentificationSchema();
pdfaid.setConformance(conformance);
pdfaid.setPart(part);

AdobePDFSchema pdfSchema = metadata.createAndAddAdobePDFSchema();
pdfSchema.setProducer(information.getProducer());

if (keywords != null) {
pdfSchema.setKeywords(keywords);
}
if (producer != null) {
pdfSchema.setProducer(producer);
}

XMPBasicSchema xmpBasicSchema = metadata.createAndAddXMPBasicSchema();
xmpBasicSchema.setCreateDate(information.getCreationDate());


DublinCoreSchema dc = metadata.createAndAddDublinCoreSchema();
if (author != null) {
dc.addCreator(author);
}
if (title != null) {
dc.setTitle(title);
}
if (subject != null) {
dc.setDescription(subject);
}

PDMetadata metadataStream = new PDMetadata(document);
PDMarkInfo markInfo = new PDMarkInfo();
markInfo.setMarked(true);

// add to catalog
PDDocumentCatalog catalog = document.getDocumentCatalog();
catalog.setMetadata(metadataStream);
// for pdf/a-1 compliance, add the StructTreeRoot that https://www.pdf-online.com/osa/validate.aspx was
// complaining. Based on https://stackoverflow.com/a/46806392
catalog.setStructureTreeRoot(new PDStructureTreeRoot());
//

catalog.setMarkInfo(markInfo);

XmpSerializer serializer = new XmpSerializer();
ByteArrayOutputStream baos = new ByteArrayOutputStream();
serializer.serialize(metadata, baos, true);
metadataStream.importXMPMetadata( baos.toByteArray() );


if (_colorProfile != null) {
ByteArrayInputStream colorProfile = new ByteArrayInputStream(_colorProfile);
PDOutputIntent oi = new PDOutputIntent(document, colorProfile);
Expand Down

0 comments on commit 20605f2

Please sign in to comment.