[RELEASE] iText pdfHtml 5.0.4

Author: iText-CI

pom.xml

@@ -5,12 +5,12 @@
   <parent>
     <groupId>com.itextpdf</groupId>
     <artifactId>root</artifactId>
-    <version>8.0.3</version>
+    <version>8.0.4</version>
     <relativePath />
   </parent>
 
   <artifactId>html2pdf</artifactId>
-  <version>5.0.3</version>
+  <version>5.0.4</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

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

@@ -30,7 +30,7 @@ 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 = "5.0.3";
+    private static final String PDF_HTML_VERSION = "5.0.4";
     private static final int PDF_HTML_COPYRIGHT_SINCE = 2000;
     private static final int PDF_HTML_COPYRIGHT_TO = 2024;
 

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

@@ -0,0 +1,39 @@
+/*
+    This file is part of the iText (R) project.
+    Copyright (c) 1998-2024 Apryse Group NV
+    Authors: Apryse Software.
+
+    This program is offered under a commercial and under the AGPL license.
+    For commercial licensing, contact us at https://itextpdf.com/sales.  For AGPL licensing, see below.
+
+    AGPL licensing:
+    This program is free software: you can redistribute it and/or modify
+    it under the terms of the GNU Affero General Public License as published by
+    the Free Software Foundation, either version 3 of the License, or
+    (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Affero General Public License for more details.
+
+    You should have received a copy of the GNU Affero General Public License
+    along with this program.  If not, see <https://www.gnu.org/licenses/>.
+ */
+package com.itextpdf.html2pdf.attach;
+
+import com.itextpdf.styledxmlparser.node.IElementNode;
+
+/**
+ * {@link IOutlineMarkExtractor} interface is used to control what part of element will be a mark
+ * witch will be used to create outline in {@link com.itextpdf.html2pdf.attach.impl.OutlineHandler}
+ */
+public interface IOutlineMarkExtractor {
+    /**
+     * Get element mark.
+     *
+     * @param element the element
+     * @return returns string mark of the element
+     */
+    String getMark(IElementNode element);
+}

src/main/java/com/itextpdf/html2pdf/attach/impl/ClassOutlineMarkExtractor.java

@@ -0,0 +1,36 @@
+/*
+    This file is part of the iText (R) project.
+    Copyright (c) 1998-2024 Apryse Group NV
+    Authors: Apryse Software.
+
+    This program is offered under a commercial and under the AGPL license.
+    For commercial licensing, contact us at https://itextpdf.com/sales.  For AGPL licensing, see below.
+
+    AGPL licensing:
+    This program is free software: you can redistribute it and/or modify
+    it under the terms of the GNU Affero General Public License as published by
+    the Free Software Foundation, either version 3 of the License, or
+    (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Affero General Public License for more details.
+
+    You should have received a copy of the GNU Affero General Public License
+    along with this program.  If not, see <https://www.gnu.org/licenses/>.
+ */
+package com.itextpdf.html2pdf.attach.impl;
+
+import com.itextpdf.html2pdf.attach.IOutlineMarkExtractor;
+import com.itextpdf.styledxmlparser.node.IElementNode;
+
+/**
+ * {@link ClassOutlineMarkExtractor} class is used to get class of element as a mark for {@link OutlineHandler}
+ */
+public class ClassOutlineMarkExtractor implements IOutlineMarkExtractor {
+    @Override
+    public String getMark(IElementNode element) {
+        return element.getAttribute("class");
+    }
+}

src/main/java/com/itextpdf/html2pdf/attach/impl/OutlineHandler.java

@@ -23,6 +23,7 @@ This file is part of the iText (R) project.
 package com.itextpdf.html2pdf.attach.impl;
 
 import com.itextpdf.commons.datastructures.Tuple2;
+import com.itextpdf.html2pdf.attach.IOutlineMarkExtractor;
 import com.itextpdf.html2pdf.html.TagConstants;
 import com.itextpdf.html2pdf.logs.Html2PdfLogMessageConstant;
 import com.itextpdf.html2pdf.attach.ITagWorker;
@@ -45,7 +46,8 @@ This file is part of the iText (R) project.
 import java.util.Map;
 
 /**
- * A {@link OutlineHandler} handles creating outlines for tags.
+ * A {@link OutlineHandler} handles creating outlines for marks.
+ * Marks are extracted via interface {@link IOutlineMarkExtractor}.
  * <p>
  * This class is not reusable and a new instance shall be created for every new conversion process.
  */
@@ -68,86 +70,182 @@ public class OutlineHandler {
     /**
      * The current outline.
      */
-    private PdfOutline currentOutline;
+    protected PdfOutline currentOutline;
 
     /**
      * The destinations in process.
      */
-    private Deque<Tuple2<String, PdfDictionary>> destinationsInProcess = new LinkedList<Tuple2<String, PdfDictionary>>();
+    protected Deque<Tuple2<String, PdfDictionary>> destinationsInProcess = new LinkedList<Tuple2<String, PdfDictionary>>();
 
     /**
      * The levels in process.
      */
-    private Deque<Integer> levelsInProcess = new LinkedList<Integer>();
+    protected Deque<Integer> levelsInProcess = new LinkedList<Integer>();
 
     /**
-     * The tag priorities mapping.
+     * The mark priorities mapping.
      */
-    private Map<String, Integer> tagPrioritiesMapping = new HashMap<String, Integer>();
+    private Map<String, Integer> markPrioritiesMapping = new HashMap<String, Integer>();
 
     /**
      * The destination prefix.
      */
     private String destinationNamePrefix = DEFAULT_DESTINATION_NAME_PREFIX;
 
+    /**
+     *The mark extractor defines what part of element will be used to create outline
+     */
+    protected IOutlineMarkExtractor markExtractor;
 
     /**
-     * Creates an OutlineHandler with standard predefined mappings.
+     * Creates an OutlineHandler with standard {@link TagOutlineMarkExtractor}.
+     */
+    public OutlineHandler(){
+        markExtractor = new TagOutlineMarkExtractor();
+    }
+    /**
+     * Creates an OutlineHandler with standard {@link TagOutlineMarkExtractor} and predefined mappings.
      *
      * @return the outline handler
      */
     public static OutlineHandler createStandardHandler() {
         OutlineHandler handler = new OutlineHandler();
-        handler.putTagPriorityMapping(TagConstants.H1, 1);
-        handler.putTagPriorityMapping(TagConstants.H2, 2);
-        handler.putTagPriorityMapping(TagConstants.H3, 3);
-        handler.putTagPriorityMapping(TagConstants.H4, 4);
-        handler.putTagPriorityMapping(TagConstants.H5, 5);
-        handler.putTagPriorityMapping(TagConstants.H6, 6);
+        handler.putMarkPriorityMapping(TagConstants.H1, 1);
+        handler.putMarkPriorityMapping(TagConstants.H2, 2);
+        handler.putMarkPriorityMapping(TagConstants.H3, 3);
+        handler.putMarkPriorityMapping(TagConstants.H4, 4);
+        handler.putMarkPriorityMapping(TagConstants.H5, 5);
+        handler.putMarkPriorityMapping(TagConstants.H6, 6);
+        return handler;
+    }
+
+    /**
+     * Creates an OutlineHandler with custom {@link IOutlineMarkExtractor}
+     *
+     * @param extractor the mark extractor
+     * @return the outline handler
+     */
+    public static OutlineHandler createHandler(IOutlineMarkExtractor extractor) {
+        OutlineHandler handler = new OutlineHandler();
+        handler.markExtractor = extractor;
         return handler;
     }
 
     /**
-     * Put tag priority mapping.
+     * Get mark extractor.
+     *
+     * @return the mark extractor
+     */
+    public IOutlineMarkExtractor getMarkExtractor(){
+        return markExtractor;
+    }
+
+    /**
+     * Set mark extractor.
+     *
+     * @param extractor the mark extractor
+     * @return the outline handler
+     */
+    public OutlineHandler setMarkExtractor(IOutlineMarkExtractor extractor){
+        markExtractor = extractor;
+        return this;
+    }
+    /**
+     * Put tag into priority mapping.
      *
      * @param tagName  the tag name
      * @param priority the priority
      * @return the outline handler
+     * @deprecated use {@link #putMarkPriorityMapping(String, Integer)} instead
      */
+    @Deprecated
     public OutlineHandler putTagPriorityMapping(String tagName, Integer priority) {
-        tagPrioritiesMapping.put(tagName, priority);
+        putMarkPriorityMapping(tagName, priority);
         return this;
     }
 
     /**
-     * Put all tag priority mappings.
+     * Put mark into priority mapping.
+     *
+     * @param markName  the mark name
+     * @param priority the priority
+     * @return the outline handler
+     */
+    public OutlineHandler putMarkPriorityMapping(String markName, Integer priority) {
+        markPrioritiesMapping.put(markName, priority);
+        return this;
+    }
+
+    /**
+     * Put all tags into priority mappings.
      *
      * @param mappings the mappings
      * @return the outline handler
+     * @deprecated ue {@link #putAllMarksPriorityMappings(Map)} instead
      */
+    @Deprecated
     public OutlineHandler putAllTagPriorityMappings(Map<String, Integer> mappings) {
-        tagPrioritiesMapping.putAll(mappings);
+        putAllMarksPriorityMappings(mappings);
+        return this;
+    }
+
+    /**
+     * Put all marks into priority mappings.
+     *
+     * @param mappings the mappings
+     * @return the outline handler
+     */
+    public OutlineHandler putAllMarksPriorityMappings(Map<String, Integer> mappings) {
+        markPrioritiesMapping.putAll(mappings);
         return this;
     }
 
     /**
-     * Gets the tag priority mapping.
+     * Gets the marks from priority mapping.
      *
      * @param tagName the tag name
      * @return the tag priority mapping
+     * @deprecated use {@link #getMarkPriorityMapping(String)} instead
      */
+    @Deprecated
     public Integer getTagPriorityMapping(String tagName) {
-        return tagPrioritiesMapping.get(tagName);
+        return getMarkPriorityMapping(tagName);
     }
 
     /**
-     * Checks for tag priority mapping.
+     * Gets the mark from priority mapping.
+     *
+     * @param markName the mark name
+     * @return the tag priority mapping
+     */
+    public Integer getMarkPriorityMapping(String markName) {
+        return markPrioritiesMapping.get(markName);
+    }
+
+    /**
+     * Checks for tag in priority mapping.
      *
      * @param tagName the tag name
      * @return true, if the tag name is listed in the tag priorities mapping
+     * @deprecated use {@link #hasMarkPriorityMapping(String)} instead
      */
+    @Deprecated
     public boolean hasTagPriorityMapping(String tagName) {
-        return tagPrioritiesMapping.containsKey(tagName);
+        return hasMarkPriorityMapping(tagName);
+    }
+
+    /**
+     * Checks for tag in priority mapping.
+     *
+     * @param markName the mark name
+     * @return true, if the tag name is listed in the tag priorities mapping
+     */
+    public boolean hasMarkPriorityMapping(String markName) {
+        if (markName == null){
+            return false;
+        } else {
+            return markPrioritiesMapping.containsKey(markName);
+        }
     }
 
     /**
@@ -209,10 +307,10 @@ protected String generateUniqueDestinationName(IElementNode element) {
      * @return the unique destination name
      */
     protected String generateOutlineName(IElementNode element) {
-        String tagName = element.name();
+        String markName = markExtractor.getMark(element);
         String content = ((JsoupElementNode) element).text();
         if (content.isEmpty()) {
-            content = getUniqueID(tagName);
+            content = getUniqueID(markName);
         }
         return content;
     }
@@ -228,10 +326,11 @@ protected String generateOutlineName(IElementNode element) {
      * @param context   the processor context
      * @return the outline handler
      */
-    OutlineHandler addOutlineAndDestToDocument(ITagWorker tagWorker, IElementNode element, ProcessorContext context) {
-        String tagName = element.name();
-        if (null != tagWorker && hasTagPriorityMapping(tagName) && context.getPdfDocument() != null) {
-            int level = (int) getTagPriorityMapping(tagName);
+    protected OutlineHandler addOutlineAndDestToDocument(ITagWorker tagWorker, IElementNode element,
+                                                         ProcessorContext context) {
+        String markName = markExtractor.getMark(element);
+        if (null != tagWorker && hasMarkPriorityMapping(markName) && context.getPdfDocument() != null) {
+            int level = (int) getMarkPriorityMapping(markName);
             if (null == currentOutline) {
                 currentOutline = context.getPdfDocument().getOutlines(false);
             }
@@ -262,16 +361,16 @@ OutlineHandler addOutlineAndDestToDocument(ITagWorker tagWorker, IElementNode el
      * @param element   the element
      * @return the outline handler
      */
-    OutlineHandler setDestinationToElement(ITagWorker tagWorker, IElementNode element) {
-        String tagName = element.name();
-        if (null != tagWorker && hasTagPriorityMapping(tagName) && destinationsInProcess.size() > 0) {
+    protected OutlineHandler setDestinationToElement(ITagWorker tagWorker, IElementNode element) {
+        String markName = markExtractor.getMark(element);
+        if (null != tagWorker && hasMarkPriorityMapping(markName) && destinationsInProcess.size() > 0) {
             Tuple2<String, PdfDictionary> content = destinationsInProcess.pop();
             if (tagWorker.getElementResult() instanceof IElement) {
                 tagWorker.getElementResult().setProperty(Property.DESTINATION, content);
             } else {
                 Logger logger = LoggerFactory.getLogger(OutlineHandler.class);
                 logger.warn(MessageFormatUtil.format(
-                        Html2PdfLogMessageConstant.NO_IPROPERTYCONTAINER_RESULT_FOR_THE_TAG, tagName));
+                        Html2PdfLogMessageConstant.NO_IPROPERTYCONTAINER_RESULT_FOR_THE_TAG, markName));
             }
         }
         return this;