[RELEASE] iText pdfHtml 5.0.3

pom.xml

@@ -5,12 +5,12 @@
   <parent>
     <groupId>com.itextpdf</groupId>
     <artifactId>root</artifactId>
-    <version>8.0.2</version>
+    <version>8.0.3</version>
     <relativePath />
   </parent>
 
   <artifactId>html2pdf</artifactId>
-  <version>5.0.2</version>
+  <version>5.0.3</version>
 
   <name>pdfHTML</name>
   <description>pdfHTML is an iText add-on that lets you to parse (X)HTML snippets and the associated CSS and converts
@@ -70,7 +70,6 @@
       <groupId>com.itextpdf</groupId>
       <artifactId>pdfa</artifactId>
       <version>${itext.version}</version>
-      <scope>test</scope>
     </dependency>
     <dependency>
       <groupId>com.itextpdf</groupId>

src/main/java/com/itextpdf/html2pdf/ConverterProperties.java

@@ -1,6 +1,6 @@
 /*
     This file is part of the iText (R) project.
-    Copyright (c) 1998-2023 Apryse Group NV
+    Copyright (c) 1998-2024 Apryse Group NV
     Authors: Apryse Software.
 
     This program is offered under a commercial and under the AGPL license.
@@ -26,10 +26,14 @@ This file is part of the iText (R) project.
 import com.itextpdf.html2pdf.attach.ITagWorkerFactory;
 import com.itextpdf.html2pdf.attach.impl.OutlineHandler;
 import com.itextpdf.html2pdf.css.apply.ICssApplierFactory;
+import com.itextpdf.kernel.pdf.PdfAConformanceLevel;
+import com.itextpdf.kernel.pdf.PdfOutputIntent;
 import com.itextpdf.layout.font.FontProvider;
 import com.itextpdf.styledxmlparser.css.media.MediaDeviceDescription;
 import com.itextpdf.styledxmlparser.resolver.resource.IResourceRetriever;
 
+import java.io.InputStream;
+
 /**
  * Properties that will be used by the {@link com.itextpdf.html2pdf.HtmlConverter}.
  */
@@ -105,6 +109,16 @@ public class ConverterProperties {
      */
     private boolean continuousContainerEnabled;
 
+    /**
+     * Output intent for final destination device.
+     */
+    private PdfOutputIntent outputIntent;
+
+    /**
+     * Conformance level for conversion to pdf/a.
+     */
+    private PdfAConformanceLevel conformanceLevel;
+
     /**
      * Instantiates a new {@link ConverterProperties} instance.
      */
@@ -396,6 +410,58 @@ public ConverterProperties setCharset(String charset) {
         return this;
     }
 
+    /**
+     * Sets pdf document output intent (final destination device) to reproduce the color in the PDF.
+     * Required parameter, when converting to pdf/a one have to specify an explicit output intent.
+     *
+     * <p>
+     * Note, output intent isn't applicable for HtmlConverter#convertToElements methods
+     * (e.g. {@link HtmlConverter#convertToElements(InputStream, ConverterProperties)})
+     *
+     * @param outputIntent a {@link PdfOutputIntent} instance
+     *
+     * @return the {@link ConverterProperties} instance
+     */
+    public ConverterProperties setDocumentOutputIntent(PdfOutputIntent outputIntent) {
+        this.outputIntent = outputIntent;
+        return this;
+    }
+
+    /**
+     * Sets the generation and strictness level of the PDF/A that must be followed.
+     * Required parameter, when converting to pdf/a one have to specify an explicit pdf/a conformance level.
+     *
+     * @param conformanceLevel a {@link PdfAConformanceLevel} constant
+     *
+     * @return the {@link ConverterProperties} instance
+     */
+    public ConverterProperties setPdfAConformanceLevel(PdfAConformanceLevel conformanceLevel) {
+        this.conformanceLevel = conformanceLevel;
+        return this;
+    }
+
+    /**
+     * Gets pdf document output intent (final destination device) to reproduce the color in the PDF.
+     *
+     * <p>
+     * Note, output intent isn't applicable for HtmlConverter#convertToElements methods
+     * (e.g. {@link HtmlConverter#convertToElements(InputStream, ConverterProperties)})
+     *
+     * @return pdf output intent
+     */
+    public PdfOutputIntent getDocumentOutputIntent() {
+        return outputIntent;
+    }
+
+    /**
+     * Gets the generation and strictness level of the PDF/A that must be followed.
+     *
+     * @return pdf/a conformance level
+     */
+    public PdfAConformanceLevel getConformanceLevel() {
+        return conformanceLevel;
+    }
+
     /**
      * Checks if immediateFlush is set.
      * <p>

src/main/java/com/itextpdf/html2pdf/HtmlConverter.java

@@ -1,6 +1,6 @@
 /*
     This file is part of the iText (R) project.
-    Copyright (c) 1998-2023 Apryse Group NV
+    Copyright (c) 1998-2024 Apryse Group NV
     Authors: Apryse Software.
 
     This program is offered under a commercial and under the AGPL license.
@@ -22,17 +22,22 @@ This file is part of the iText (R) project.
  */
 package com.itextpdf.html2pdf;
 
+import com.itextpdf.commons.actions.contexts.IMetaInfo;
+import com.itextpdf.commons.utils.FileUtil;
 import com.itextpdf.html2pdf.attach.Attacher;
 import com.itextpdf.html2pdf.exceptions.Html2PdfException;
-import com.itextpdf.commons.utils.FileUtil;
-import com.itextpdf.commons.actions.contexts.IMetaInfo;
+import com.itextpdf.html2pdf.resolver.font.DefaultFontProvider;
 import com.itextpdf.kernel.pdf.DocumentProperties;
+import com.itextpdf.kernel.pdf.PdfAConformanceLevel;
 import com.itextpdf.kernel.pdf.PdfDocument;
+import com.itextpdf.kernel.pdf.PdfVersion;
 import com.itextpdf.kernel.pdf.PdfWriter;
+import com.itextpdf.kernel.pdf.WriterProperties;
 import com.itextpdf.layout.Document;
 import com.itextpdf.layout.element.IElement;
 import com.itextpdf.layout.properties.Property;
 import com.itextpdf.layout.renderer.MetaInfoContainer;
+import com.itextpdf.pdfa.PdfADocument;
 import com.itextpdf.styledxmlparser.IXmlParser;
 import com.itextpdf.styledxmlparser.node.IDocumentNode;
 import com.itextpdf.styledxmlparser.node.impl.jsoup.JsoupHtmlParser;
@@ -43,6 +48,8 @@ This file is part of the iText (R) project.
 import java.io.IOException;
 import java.io.InputStream;
 import java.io.OutputStream;
+import java.util.ArrayList;
+import java.util.Arrays;
 import java.util.List;
 
 /**
@@ -55,6 +62,8 @@ This file is part of the iText (R) project.
  */
 public class HtmlConverter {
 
+    private static final List<PdfAConformanceLevel> pdf2ConformanceLevels = new ArrayList<>(Arrays. asList(PdfAConformanceLevel.PDF_A_4, PdfAConformanceLevel.PDF_A_4E, PdfAConformanceLevel.PDF_A_4F));
+
     /**
      * Instantiates a new HtmlConverter instance.
      */
@@ -81,6 +90,10 @@ public static void convertToPdf(String html, OutputStream pdfStream) {
      * @param converterProperties a {@link ConverterProperties} instance
      */
     public static void convertToPdf(String html, OutputStream pdfStream, ConverterProperties converterProperties) {
+        if (converterProperties != null && pdf2ConformanceLevels.contains(converterProperties.getConformanceLevel())) {
+            convertToPdf(html, new PdfWriter(pdfStream, new WriterProperties().setPdfVersion(PdfVersion.PDF_2_0)), converterProperties);
+            return;
+        }
         convertToPdf(html, new PdfWriter(pdfStream), converterProperties);
     }
 
@@ -104,8 +117,19 @@ public static void convertToPdf(String html, PdfWriter pdfWriter) {
      * @param converterProperties a {@link ConverterProperties} instance
      */
     public static void convertToPdf(String html, PdfWriter pdfWriter, ConverterProperties converterProperties) {
-        convertToPdf(html, new PdfDocument(pdfWriter, new DocumentProperties()
-                .setEventCountingMetaInfo(resolveMetaInfo(converterProperties))), converterProperties);
+        if (converterProperties == null || converterProperties.getConformanceLevel() == null) {
+            convertToPdf(html, new PdfDocument(pdfWriter, new DocumentProperties()
+                    .setEventCountingMetaInfo(resolveMetaInfo(converterProperties))), converterProperties);
+            return;
+        }
+        PdfDocument document = new PdfADocument(pdfWriter, converterProperties.getConformanceLevel(),
+                converterProperties.getDocumentOutputIntent(), new DocumentProperties()
+                .setEventCountingMetaInfo(resolveMetaInfo(converterProperties)));
+        converterProperties = setDefaultFontProviderForPdfA(document, converterProperties);
+        if ("A".equals(converterProperties.getConformanceLevel().getConformance())) {
+            document.setTagged();
+        }
+        convertToPdf(html, document, converterProperties);
     }
 
     /**
@@ -178,6 +202,10 @@ public static void convertToPdf(InputStream htmlStream, OutputStream pdfStream)
      * @throws IOException Signals that an I/O exception has occurred.
      */
     public static void convertToPdf(InputStream htmlStream, OutputStream pdfStream, ConverterProperties converterProperties) throws IOException {
+        if (converterProperties != null && pdf2ConformanceLevels.contains(converterProperties.getConformanceLevel())) {
+            convertToPdf(htmlStream, new PdfWriter(pdfStream, new WriterProperties().setPdfVersion(PdfVersion.PDF_2_0)), converterProperties);
+            return;
+        }
         convertToPdf(htmlStream, new PdfWriter(pdfStream), converterProperties);
     }
 
@@ -217,8 +245,19 @@ public static void convertToPdf(InputStream htmlStream, PdfWriter pdfWriter) thr
      * @throws IOException Signals that an I/O exception has occurred.
      */
     public static void convertToPdf(InputStream htmlStream, PdfWriter pdfWriter, ConverterProperties converterProperties) throws IOException {
-        convertToPdf(htmlStream, new PdfDocument(pdfWriter, new DocumentProperties().setEventCountingMetaInfo(
-                resolveMetaInfo(converterProperties))), converterProperties);
+        if (converterProperties == null || converterProperties.getConformanceLevel() == null) {
+            convertToPdf(htmlStream, new PdfDocument(pdfWriter, new DocumentProperties().setEventCountingMetaInfo(
+                    resolveMetaInfo(converterProperties))), converterProperties);
+            return;
+        }
+        PdfDocument document = new PdfADocument(pdfWriter, converterProperties.getConformanceLevel(),
+                converterProperties.getDocumentOutputIntent(), new DocumentProperties()
+                .setEventCountingMetaInfo(resolveMetaInfo(converterProperties)));
+        converterProperties = setDefaultFontProviderForPdfA(document, converterProperties);
+        if ("A".equals(converterProperties.getConformanceLevel().getConformance())) {
+            document.setTagged();
+        }
+        convertToPdf(htmlStream, document, converterProperties);
     }
 
     /**
@@ -231,6 +270,7 @@ public static void convertToPdf(InputStream htmlStream, PdfWriter pdfWriter, Con
      * @throws IOException Signals that an I/O exception has occurred.
      */
     public static void convertToPdf(InputStream htmlStream, PdfDocument pdfDocument, ConverterProperties converterProperties) throws IOException {
+        converterProperties = setDefaultFontProviderForPdfA(pdfDocument, converterProperties);
         final Document document = convertToDocument(htmlStream, pdfDocument, converterProperties);
         IMetaInfo metaInfo = resolveMetaInfo(converterProperties);
         document.setProperty(Property.META_INFO, new MetaInfoContainer(metaInfo));
@@ -305,6 +345,7 @@ public static Document convertToDocument(String html, PdfDocument pdfDocument, C
         if (pdfDocument.getReader() != null) {
             throw new Html2PdfException(Html2PdfException.PDF_DOCUMENT_SHOULD_BE_IN_WRITING_MODE);
         }
+        converterProperties = setDefaultFontProviderForPdfA(pdfDocument, converterProperties);
         IXmlParser parser = new JsoupHtmlParser();
         IDocumentNode doc = parser.parse(html);
         return Attacher.attach(doc, pdfDocument, converterProperties);
@@ -325,6 +366,7 @@ public static Document convertToDocument(InputStream htmlStream, PdfDocument pdf
         if (pdfDocument.getReader() != null) {
             throw new Html2PdfException(Html2PdfException.PDF_DOCUMENT_SHOULD_BE_IN_WRITING_MODE);
         }
+        converterProperties = setDefaultFontProviderForPdfA(pdfDocument, converterProperties);
         IXmlParser parser = new JsoupHtmlParser();
         IDocumentNode doc = parser.parse(htmlStream, converterProperties != null ? converterProperties.getCharset() : null);
         return Attacher.attach(doc, pdfDocument, converterProperties);
@@ -363,6 +405,7 @@ public static List<IElement> convertToElements(InputStream htmlStream) throws IO
      * @return a list of iText building blocks
      */
     public static List<IElement> convertToElements(String html, ConverterProperties converterProperties) {
+        converterProperties = setDefaultFontProviderForPdfA(null, converterProperties);
         IXmlParser parser = new JsoupHtmlParser();
         IDocumentNode doc = parser.parse(html);
         return Attacher.attach(doc, converterProperties);
@@ -379,6 +422,7 @@ public static List<IElement> convertToElements(String html, ConverterProperties
      * @throws IOException Signals that an I/O exception has occurred.
      */
     public static List<IElement> convertToElements(InputStream htmlStream, ConverterProperties converterProperties) throws IOException {
+        converterProperties = setDefaultFontProviderForPdfA(null, converterProperties);
         IXmlParser parser = new JsoupHtmlParser();
         IDocumentNode doc = parser.parse(htmlStream, converterProperties != null ? converterProperties.getCharset() : null);
         return Attacher.attach(doc, converterProperties);
@@ -394,6 +438,22 @@ private static IMetaInfo resolveMetaInfo(ConverterProperties converterProperties
                 : converterProperties.getEventMetaInfo();
     }
 
+    private static ConverterProperties setDefaultFontProviderForPdfA(PdfDocument document, ConverterProperties properties) {
+        if (document instanceof PdfADocument) {
+            if (properties == null) {
+                properties = new ConverterProperties();
+            }
+            if (properties.getFontProvider() == null) {
+                properties.setFontProvider(new DefaultFontProvider(false, true, false));
+            }
+        } else if (document == null && properties != null && properties.getConformanceLevel() != null) {
+            if (properties.getFontProvider() == null) {
+                properties.setFontProvider(new DefaultFontProvider(false, true, false));
+            }
+        }
+        return properties;
+    }
+
     private static class HtmlMetaInfo implements IMetaInfo {
     }
 }

src/main/java/com/itextpdf/html2pdf/ProcessorContextCreator.java

@@ -1,6 +1,6 @@
 /*
     This file is part of the iText (R) project.
-    Copyright (c) 1998-2023 Apryse Group NV
+    Copyright (c) 1998-2024 Apryse Group NV
     Authors: Apryse Software.
 
     This program is offered under a commercial and under the AGPL license.

src/main/java/com/itextpdf/html2pdf/actions/data/PdfHtmlProductData.java

@@ -1,6 +1,6 @@
 /*
     This file is part of the iText (R) project.
-    Copyright (c) 1998-2023 Apryse Group NV
+    Copyright (c) 1998-2024 Apryse Group NV
     Authors: Apryse Software.
 
     This program is offered under a commercial and under the AGPL license.
@@ -30,9 +30,9 @@ This file is part of the iText (R) project.
  */
 public final class PdfHtmlProductData {
     private static final String PDF_HTML_PUBLIC_PRODUCT_NAME = "pdfHTML";
-    private static final String PDF_HTML_VERSION = "5.0.2";
+    private static final String PDF_HTML_VERSION = "5.0.3";
     private static final int PDF_HTML_COPYRIGHT_SINCE = 2000;
-    private static final int PDF_HTML_COPYRIGHT_TO = 2023;
+    private static final int PDF_HTML_COPYRIGHT_TO = 2024;
 
     private static final ProductData PDF_HTML_PRODUCT_DATA = new ProductData(PDF_HTML_PUBLIC_PRODUCT_NAME,
             ProductNameConstant.PDF_HTML, PDF_HTML_VERSION, PDF_HTML_COPYRIGHT_SINCE, PDF_HTML_COPYRIGHT_TO);

src/main/java/com/itextpdf/html2pdf/actions/events/PdfHtmlProductEvent.java

@@ -1,6 +1,6 @@
 /*
     This file is part of the iText (R) project.
-    Copyright (c) 1998-2023 Apryse Group NV
+    Copyright (c) 1998-2024 Apryse Group NV
     Authors: Apryse Software.
 
     This program is offered under a commercial and under the AGPL license.

src/main/java/com/itextpdf/html2pdf/attach/Attacher.java

@@ -1,6 +1,6 @@
 /*
     This file is part of the iText (R) project.
-    Copyright (c) 1998-2023 Apryse Group NV
+    Copyright (c) 1998-2024 Apryse Group NV
     Authors: Apryse Software.
 
     This program is offered under a commercial and under the AGPL license.

src/main/java/com/itextpdf/html2pdf/attach/IHtmlProcessor.java

@@ -1,6 +1,6 @@
 /*
     This file is part of the iText (R) project.
-    Copyright (c) 1998-2023 Apryse Group NV
+    Copyright (c) 1998-2024 Apryse Group NV
     Authors: Apryse Software.
 
     This program is offered under a commercial and under the AGPL license.

src/main/java/com/itextpdf/html2pdf/attach/ITagWorker.java

@@ -1,6 +1,6 @@
 /*
     This file is part of the iText (R) project.
-    Copyright (c) 1998-2023 Apryse Group NV
+    Copyright (c) 1998-2024 Apryse Group NV
     Authors: Apryse Software.
 
     This program is offered under a commercial and under the AGPL license.

src/main/java/com/itextpdf/html2pdf/attach/ITagWorkerFactory.java

@@ -1,6 +1,6 @@
 /*
     This file is part of the iText (R) project.
-    Copyright (c) 1998-2023 Apryse Group NV
+    Copyright (c) 1998-2024 Apryse Group NV
     Authors: Apryse Software.
 
     This program is offered under a commercial and under the AGPL license.