Skip to content

Use safe XML parser for rich text in PdfUA2AnnotationChecker #318

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
netliomax25-code wants to merge 1 commit into
base: develop
Choose a base branch
from
+25 −2
Open

Use safe XML parser for rich text in PdfUA2AnnotationChecker #318

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 4 additions & 2 deletions pdfua/src/main/java/com/itextpdf/pdfua/checkers/utils/ua2/PdfUA2AnnotationChecker.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,6 @@ This file is part of the iText (R) project.

import com.itextpdf.commons.utils.MessageFormatUtil;
import com.itextpdf.forms.fields.PdfFormField;
import com.itextpdf.io.util.XmlUtil;
import com.itextpdf.kernel.exceptions.PdfException;
import com.itextpdf.kernel.pdf.PdfDictionary;
import com.itextpdf.kernel.pdf.PdfDocument;
Expand All @@ -37,6 +36,7 @@ This file is part of the iText (R) project.
import com.itextpdf.kernel.pdf.tagging.IStructureNode;
import com.itextpdf.kernel.pdf.tagging.PdfObjRef;
import com.itextpdf.kernel.pdf.tagging.PdfStructElem;
import com.itextpdf.kernel.utils.XmlProcessorCreator;
import com.itextpdf.kernel.utils.checkers.PdfCheckersUtil;
import com.itextpdf.pdfua.checkers.utils.ContextAwareTagTreeIteratorHandler;
import com.itextpdf.pdfua.checkers.utils.PdfUAValidationContext;
Expand All @@ -49,6 +49,7 @@ This file is part of the iText (R) project.
import java.util.HashSet;
import java.util.List;
import java.util.Set;
import javax.xml.parsers.DocumentBuilder;
import org.w3c.dom.Node;
import org.w3c.dom.NodeList;

Expand Down Expand Up @@ -164,7 +165,8 @@ static String getRichTextStringValue(PdfObject rv) {
return richText;
}
try {
return parseRichText(XmlUtil.initXmlDocument(new ByteArrayInputStream(
DocumentBuilder db = XmlProcessorCreator.createSafeDocumentBuilder(false, false);
return parseRichText(db.parse(new ByteArrayInputStream(
richText.getBytes(StandardCharsets.UTF_8))));
} catch (Exception e) {
throw new PdfException(e.getMessage(), e);
Expand Down
21 changes: 21 additions & 0 deletions .../src/test/java/com/itextpdf/pdfua/checkers/utils/ua2/PdfUA2AnnotationCheckerUnitTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,11 +24,13 @@ This file is part of the iText (R) project.

import com.itextpdf.commons.utils.MessageFormatUtil;
import com.itextpdf.io.source.ByteArrayOutputStream;
import com.itextpdf.kernel.exceptions.PdfException;
import com.itextpdf.kernel.geom.Rectangle;
import com.itextpdf.kernel.pdf.PdfArray;
import com.itextpdf.kernel.pdf.PdfDictionary;
import com.itextpdf.kernel.pdf.PdfName;
import com.itextpdf.kernel.pdf.PdfPage;
import com.itextpdf.kernel.pdf.PdfString;
import com.itextpdf.kernel.pdf.PdfUAConformance;
import com.itextpdf.kernel.pdf.PdfVersion;
import com.itextpdf.kernel.pdf.PdfWriter;
Expand All @@ -47,19 +49,38 @@ This file is part of the iText (R) project.
import com.itextpdf.kernel.pdf.tagging.PdfStructElem;
import com.itextpdf.kernel.pdf.tagging.StandardRoles;
import com.itextpdf.kernel.pdf.tagutils.TagTreePointer;
import com.itextpdf.kernel.utils.XmlProcessorCreator;
import com.itextpdf.pdfua.PdfUAConfig;
import com.itextpdf.pdfua.PdfUADocument;
import com.itextpdf.pdfua.exceptions.PdfUAConformanceException;
import com.itextpdf.pdfua.exceptions.PdfUAExceptionMessageConstants;
import com.itextpdf.test.ExceptionTestUtil;
import com.itextpdf.test.ExtendedITextTest;

import org.junit.jupiter.api.Assertions;
import org.junit.jupiter.api.BeforeEach;
import org.junit.jupiter.api.Tag;
import org.junit.jupiter.api.Test;

@Tag("UnitTest")
public class PdfUA2AnnotationCheckerUnitTest extends ExtendedITextTest {

private static final String RICH_TEXT_WITH_XXE = "<?xml version=\"1.0\"?>\n"
+ "<!DOCTYPE r [ <!ENTITY xxe SYSTEM \"xxe-data.txt\"> ]>\n"
+ "<body xmlns=\"http://www.w3.org/1999/xhtml\"><p>&xxe;</p></body>";

@BeforeEach
public void resetXmlParserFactoryToDefault() {
XmlProcessorCreator.setXmlParserFactory(null);
}

@Test
public void richTextWithXxeIsRejected() {
Exception e = Assertions.assertThrows(PdfException.class,
() -> PdfUA2AnnotationChecker.getRichTextStringValue(new PdfString(RICH_TEXT_WITH_XXE)));
Assertions.assertEquals(ExceptionTestUtil.getDoctypeIsDisallowedExceptionMessage(), e.getMessage());
}

@Test
public void basicAnnotationBadParent() {
PdfLineAnnotation lineAnnotation = new PdfLineAnnotation(new Rectangle(0, 0, 100, 100), new float[]{2, 3});
Expand Down