Support "Forms" rules for PDF/UA-2

DEVSIX-9022

Author: AnhelinaM

forms/src/main/java/com/itextpdf/forms/fields/PdfFormField.java

@@ -333,6 +333,27 @@ public static PdfName getFormType(PdfDictionary fieldDict) {
         return formType;
     }
 
+    /**
+     * Retrieves string value from {@link PdfObject} representing text string or text stream.
+     *
+     * @param value {@link PdfObject} representing text string or text stream
+     *
+     * @return {@link String} value
+     */
+    public static String getStringValue(PdfObject value) {
+        if (value == null) {
+            return "";
+        } else if (value instanceof PdfStream) {
+            return new String(((PdfStream) value).getBytes(), StandardCharsets.UTF_8);
+        } else if (value instanceof PdfName) {
+            return ((PdfName) value).getValue();
+        } else if (value instanceof PdfString) {
+            return ((PdfString) value).toUnicodeString();
+        } else {
+            return "";
+        }
+    }
+
     /**
      * Returns the type of the parent form field, or of the wrapped
      * <PdfDictionary> object.
@@ -775,17 +796,7 @@ public PdfObject getValue() {
      */
     public String getValueAsString() {
         PdfObject value = getValue();
-        if (value == null) {
-            return "";
-        } else if (value instanceof PdfStream) {
-            return new String(((PdfStream) value).getBytes(), StandardCharsets.UTF_8);
-        } else if (value instanceof PdfName) {
-            return ((PdfName) value).getValue();
-        } else if (value instanceof PdfString) {
-            return ((PdfString) value).toUnicodeString();
-        } else {
-            return "";
-        }
+        return getStringValue(value);
     }
 
     /**
@@ -1044,10 +1055,11 @@ public PdfObject getRichText() {
 
     /**
      * Sets a rich text string, as described in "Rich Text Strings" section of Pdf spec.
-     * May be either {@link PdfStream} or {@link PdfString}.
+     * It may be either {@link PdfStream} or {@link PdfString}.
      *
-     * @param richText a new rich text value.
-     * @return the edited {@link PdfFormField}.
+     * @param richText a new rich text value
+     *
+     * @return the edited {@link PdfFormField}
      */
     public PdfFormField setRichText(PdfObject richText) {
         put(PdfName.RV, richText);

io/src/main/java/com/itextpdf/io/util/XmlUtil.java

@@ -26,10 +26,13 @@ This file is part of the iText (R) project.
 // Android-Conversion-Replace import org.apache.xerces.jaxp.DocumentBuilderFactoryImpl;
 // Android-Conversion-Replace import org.apache.xerces.jaxp.SAXParserFactoryImpl;
 import org.w3c.dom.Document;
+import org.xml.sax.SAXException;
 
 import javax.xml.parsers.DocumentBuilderFactory;
 import javax.xml.parsers.ParserConfigurationException;
 import javax.xml.parsers.SAXParserFactory;
+import java.io.IOException;
+import java.io.InputStream;
 
 /**
  * This file is a helper class for internal usage only.
@@ -70,4 +73,20 @@ public static Document initNewXmlDocument() throws ParserConfigurationException
         return DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument();
     }
 
+    /**
+     * This method creates new Xml document from input stream.
+     *
+     * @param inputStream to parse
+     *
+     * @return parsed Xml document
+     *
+     * @throws ParserConfigurationException if an error occurs while creating the document
+     * @throws SAXException if any parse errors occur
+     * @throws IOException if any IO errors occur
+     */
+    public static Document initXmlDocument(InputStream inputStream)
+            throws ParserConfigurationException, IOException, SAXException {
+        return DocumentBuilderFactory.newInstance().newDocumentBuilder().parse(inputStream);
+    }
+
 }

kernel/src/main/java/com/itextpdf/kernel/utils/checkers/PdfCheckersUtil.java

@@ -25,9 +25,11 @@ This file is part of the iText (R) project.
 import com.itextpdf.commons.utils.MessageFormatUtil;
 import com.itextpdf.kernel.exceptions.KernelExceptionMessageConstant;
 import com.itextpdf.kernel.exceptions.PdfException;
+import com.itextpdf.kernel.pdf.PdfArray;
 import com.itextpdf.kernel.pdf.PdfConformance;
 import com.itextpdf.kernel.pdf.PdfDictionary;
 import com.itextpdf.kernel.pdf.PdfName;
+import com.itextpdf.kernel.pdf.PdfObject;
 import com.itextpdf.kernel.pdf.PdfStream;
 import com.itextpdf.kernel.xmp.XMPConst;
 import com.itextpdf.kernel.xmp.XMPException;
@@ -111,6 +113,25 @@ public static void checkMetadata(PdfDictionary catalog, PdfConformance conforman
         }
     }
 
+    /**
+     * Gets all the descending kids including widgets for a given {@link PdfArray} representing array of form fields.
+     *
+     * @param array the {@link PdfArray} of form fields {@link PdfDictionary} objects
+     *
+     * @return the {@link PdfArray} of all form fields
+     */
+    public static PdfArray getFormFields(PdfArray array) {
+        PdfArray fields = new PdfArray();
+        for (PdfObject field : array) {
+            PdfArray kids = ((PdfDictionary) field).getAsArray(PdfName.Kids);
+            fields.add(field);
+            if (kids != null) {
+                fields.addAll(getFormFields(kids));
+            }
+        }
+        return fields;
+    }
+
     /**
      * Validates {@code pdfuaid:rev} value which is four-digit year of the date of publication or revision.
      *

pdfa/src/main/java/com/itextpdf/pdfa/checker/PdfA1Checker.java

@@ -53,9 +53,12 @@ This file is part of the iText (R) project.
 import com.itextpdf.kernel.pdf.colorspace.PdfPattern;
 import com.itextpdf.kernel.pdf.colorspace.PdfSpecialCs;
 import com.itextpdf.kernel.utils.checkers.FontCheckUtil;
+import com.itextpdf.kernel.utils.checkers.PdfCheckersUtil;
 import com.itextpdf.pdfa.exceptions.PdfAConformanceException;
 import com.itextpdf.pdfa.exceptions.PdfaExceptionMessageConstant;
 import com.itextpdf.pdfa.logs.PdfAConformanceLogMessageConstant;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
 
 import java.io.IOException;
 import java.util.ArrayList;
@@ -64,8 +67,6 @@ This file is part of the iText (R) project.
 import java.util.HashSet;
 import java.util.List;
 import java.util.Set;
-import org.slf4j.Logger;
-import org.slf4j.LoggerFactory;
 
 /**
  * PdfA1Checker defines the requirements of the PDF/A-1 standard and contains
@@ -704,7 +705,7 @@ protected void checkForm(PdfDictionary form) {
 
         PdfArray fields = form.getAsArray(PdfName.Fields);
         if (fields != null) {
-            fields = getFormFields(fields);
+            fields = PdfCheckersUtil.getFormFields(fields);
             for (PdfObject field : fields) {
                 PdfDictionary fieldDic = (PdfDictionary) field;
                 if (fieldDic.containsKey(PdfName.A) || fieldDic.containsKey(PdfName.AA)) {
@@ -785,7 +786,10 @@ protected void checkTrailer(PdfDictionary trailer) {
      * @param array the {@link PdfArray} of form fields {@link PdfDictionary} objects
      *
      * @return the {@link PdfArray} of form fields
+     *
+     * @deprecated in favour of {@link PdfCheckersUtil#getFormFields(PdfArray)}
      */
+    @Deprecated
     protected PdfArray getFormFields(PdfArray array) {
         PdfArray fields = new PdfArray();
         for (PdfObject field : array) {

pdfa/src/main/java/com/itextpdf/pdfa/checker/PdfA2Checker.java

@@ -53,6 +53,7 @@ This file is part of the iText (R) project.
 import com.itextpdf.kernel.pdf.colorspace.PdfPattern;
 import com.itextpdf.kernel.pdf.colorspace.PdfSpecialCs;
 import com.itextpdf.kernel.pdf.extgstate.PdfExtGState;
+import com.itextpdf.kernel.utils.checkers.PdfCheckersUtil;
 import com.itextpdf.pdfa.exceptions.PdfAConformanceException;
 import com.itextpdf.pdfa.exceptions.PdfaExceptionMessageConstant;
 import com.itextpdf.pdfa.logs.PdfAConformanceLogMessageConstant;
@@ -583,7 +584,7 @@ protected void checkForm(PdfDictionary form) {
 
             PdfArray fields = form.getAsArray(PdfName.Fields);
             if (fields != null) {
-                fields = getFormFields(fields);
+                fields = PdfCheckersUtil.getFormFields(fields);
                 for (PdfObject field : fields) {
                     PdfDictionary fieldDic = (PdfDictionary) field;
                     checkResources(fieldDic.getAsDictionary(PdfName.DR), fieldDic);

pdfua/src/main/java/com/itextpdf/pdfua/checkers/PdfUA1Checker.java

@@ -54,11 +54,11 @@ This file is part of the iText (R) project.
 import com.itextpdf.kernel.xmp.XMPMeta;
 import com.itextpdf.layout.validation.context.LayoutValidationContext;
 import com.itextpdf.pdfua.checkers.utils.AnnotationCheckUtil;
-import com.itextpdf.pdfua.checkers.utils.FormCheckUtil;
 import com.itextpdf.pdfua.checkers.utils.GraphicsCheckUtil;
 import com.itextpdf.pdfua.checkers.utils.LayoutCheckUtil;
 import com.itextpdf.pdfua.checkers.utils.PdfUAValidationContext;
 import com.itextpdf.pdfua.checkers.utils.tables.TableCheckUtil;
+import com.itextpdf.pdfua.checkers.utils.ua1.PdfUA1FormChecker;
 import com.itextpdf.pdfua.checkers.utils.ua1.PdfUA1FormulaChecker;
 import com.itextpdf.pdfua.checkers.utils.ua1.PdfUA1HeadingsChecker;
 import com.itextpdf.pdfua.checkers.utils.ua1.PdfUA1ListChecker;
@@ -271,7 +271,7 @@ private void checkStructureTreeRoot(PdfStructTreeRoot structTreeRoot) {
         tagTreeIterator.addHandler(new PdfUA1HeadingsChecker.PdfUA1HeadingHandler(context));
         tagTreeIterator.addHandler(new TableCheckUtil.TableHandler(context));
         tagTreeIterator.addHandler(new AnnotationCheckUtil.AnnotationHandler(context));
-        tagTreeIterator.addHandler(new FormCheckUtil.FormTagHandler(context));
+        tagTreeIterator.addHandler(new PdfUA1FormChecker.PdfUA1FormTagHandler(context));
         tagTreeIterator.addHandler(new PdfUA1ListChecker.PdfUA1ListHandler(context));
         tagTreeIterator.traverse();
     }

pdfua/src/main/java/com/itextpdf/pdfua/checkers/PdfUA2Checker.java

@@ -47,6 +47,7 @@ This file is part of the iText (R) project.
 import com.itextpdf.pdfua.checkers.utils.LayoutCheckUtil;
 import com.itextpdf.pdfua.checkers.utils.PdfUAValidationContext;
 import com.itextpdf.pdfua.checkers.utils.tables.TableCheckUtil;
+import com.itextpdf.pdfua.checkers.utils.ua2.PdfUA2FormChecker;
 import com.itextpdf.pdfua.checkers.utils.ua2.PdfUA2FormulaChecker;
 import com.itextpdf.pdfua.checkers.utils.ua2.PdfUA2HeadingsChecker;
 import com.itextpdf.pdfua.checkers.utils.ua2.PdfUA2ListChecker;
@@ -158,6 +159,9 @@ private void checkCatalog(PdfCatalog catalog) {
         checkMetadata(catalog);
         checkViewerPreferences(catalog);
         checkOCProperties(catalog.getPdfObject().getAsDictionary(PdfName.OCProperties));
+        PdfUA2FormChecker formChecker = new PdfUA2FormChecker(context);
+        formChecker.checkFormFields(catalog.getPdfObject().getAsDictionary(PdfName.AcroForm));
+        formChecker.checkWidgetAnnotations(this.pdfDocument);
     }
 
     /**
@@ -209,6 +213,7 @@ private void checkStructureTreeRoot(PdfStructTreeRoot structTreeRoot) {
         tagTreeIterator.addHandler(new PdfUA2HeadingsChecker.PdfUA2HeadingHandler(context));
         tagTreeIterator.addHandler(new TableCheckUtil.TableHandler(context));
         // TODO DEVSIX-9016 Support PDF/UA-2 rules for annotation types
+        tagTreeIterator.addHandler(new PdfUA2FormChecker.PdfUA2FormTagHandler(context));
         tagTreeIterator.addHandler(new PdfUA2ListChecker.PdfUA2ListHandler(context));
         tagTreeIterator.addHandler(new PdfUA2NotesChecker.PdfUA2NotesHandler(context));
         tagTreeIterator.addHandler(new PdfUA2TableOfContentsChecker.PdfUA2TableOfContentsHandler(context));

pdfua/src/main/java/com/itextpdf/pdfua/checkers/utils/FormCheckUtil.java

@@ -26,12 +26,16 @@ This file is part of the iText (R) project.
 import com.itextpdf.kernel.pdf.PdfName;
 import com.itextpdf.kernel.pdf.tagging.IStructureNode;
 import com.itextpdf.kernel.pdf.tagging.PdfStructElem;
+import com.itextpdf.pdfua.checkers.utils.ua1.PdfUA1FormChecker;
 import com.itextpdf.pdfua.exceptions.PdfUAConformanceException;
 import com.itextpdf.pdfua.exceptions.PdfUAExceptionMessageConstants;
 
 /**
  * Class that provides methods for checking PDF/UA compliance of interactive form fields.
+ *
+ * @deprecated in favour of {@link PdfUA1FormChecker}
  */
+@Deprecated
 public class FormCheckUtil {
 
     /**
@@ -43,11 +47,14 @@ private FormCheckUtil() {
 
     /**
      * Handler for checking form field elements in the tag tree.
+     *
+     * @deprecated in favour of {@link PdfUA1FormChecker.PdfUA1FormTagHandler}
      */
+    @Deprecated
     public static class FormTagHandler extends ContextAwareTagTreeIteratorHandler {
 
         /**
-         * Creates a new {@link  FormulaCheckUtil.FormulaTagHandler} instance.
+         * Creates a new {@link FormCheckUtil.FormTagHandler} instance.
          *
          * @param context The validation context.
          */

pdfua/src/main/java/com/itextpdf/pdfua/checkers/utils/NoteCheckUtil.java

@@ -38,7 +38,10 @@ This file is part of the iText (R) project.
 public class NoteCheckUtil {
     /**
      * Handler for checking Note elements in the TagTree.
+     *
+     * @deprecated in favor of {@link com.itextpdf.pdfua.checkers.utils.ua1.PdfUA1NotesChecker.PdfUA1NotesTagHandler}
      */
+    @Deprecated
     public static class NoteTagHandler extends ContextAwareTagTreeIteratorHandler {
 
         /**

pdfua/src/main/java/com/itextpdf/pdfua/checkers/utils/PdfUAValidationContext.java

@@ -22,11 +22,13 @@ This file is part of the iText (R) project.
  */
 package com.itextpdf.pdfua.checkers.utils;
 
+import com.itextpdf.kernel.pdf.PdfDictionary;
 import com.itextpdf.kernel.pdf.PdfDocument;
 import com.itextpdf.kernel.pdf.PdfName;
 import com.itextpdf.kernel.pdf.PdfUAConformance;
 import com.itextpdf.kernel.pdf.tagging.IStructureNode;
 import com.itextpdf.kernel.pdf.tagging.PdfNamespace;
+import com.itextpdf.kernel.pdf.tagging.PdfObjRef;
 import com.itextpdf.kernel.pdf.tagging.PdfStructElem;
 import com.itextpdf.kernel.pdf.tagutils.IRoleMappingResolver;
 
@@ -124,6 +126,18 @@ public PdfStructElem getElementIfRoleMatches(PdfName role, IStructureNode struct
         return null;
     }
 
+    /**
+     * Retrieves object reference instance by provided structure parent index.
+     *
+     * @param i index of the structure parent
+     * @param pageDict {@link PdfDictionary} of the page that {@link PdfObjRef} belong to
+     *
+     * @return {@link PdfObjRef} instance
+     */
+    public PdfObjRef findObjRefByStructParentIndex(int i, PdfDictionary pageDict) {
+        return pdfDocument.getStructTreeRoot().findObjRefByStructParentIndex(pageDict, i);
+    }
+
     /**
      * Retrieves the PDF/UA conformance of the {@link PdfDocument}.
      *