[RELEASE] iText pdfOCR 4.0.0

Author: iText-CI

SECURITY.md

@@ -0,0 +1,40 @@
+# iText Security Policy
+
+## Reporting a Vulnerability
+
+We are committed to maintaining the security of our software. If you discover a security vulnerability, we encourage you to report it to us as soon as possible.
+
+To report a vulnerability, please visit our [Vulnerability Reporting Page](https://itextpdf.com/report-vulnerability), or email [[email protected]]([email protected]). If you do not receive a response in 2 business days, please follow up as we may not have received your message.
+
+We follow the procedure of Coordinated Vulnerability Disclosure (CVD) and, to protect the ecosystem, we request that those reporting do the same. Please visit the above page for more information, and follow the steps below to ensure that your report is handled promptly and appropriately:
+
+1. **Do not disclose the vulnerability publicly** until we have had a chance to address it.
+2. **Provide a detailed description** of the vulnerability, including steps to reproduce it, if possible.
+3. **Include any relevant information** such as the version of pdfOCR you are using, your operating system, and any other pertinent details.
+
+## Security Updates and Patches
+
+ When a vulnerability is reported, we will:
+
+1. **Investigate and verify** the vulnerability.
+2. **Develop and test** a fix for the vulnerability.
+3. **Release a patch** as soon as possible.
+
+
+## Known Vulnerabilities
+
+The iText Knowledge Base has a page for known [Common Vulnerabilities and Exposures](https://kb.itextpdf.com/itext/cves) (CVEs), please check it to ensure your vulnerability has not already been disclosed or addressed.
+
+## Supported product lines
+
+See [Compatibility Matrix](https://kb.itextpdf.com/itext/compatibility-matrix)
+
+## Security Best Practices
+
+To help ensure the security of your applications using pdfOCR, we recommend the following best practices:
+
+1. **Keep pdfOCR up to date** by regularly checking for and applying updates.
+2. **Review and follow** our security guidelines for secure usage.
+3. **Monitor your applications** for any unusual activity and investigate any anomalies promptly.
+
+Thank you for helping us keep iText secure!

pdfocr-api/pom.xml

@@ -5,7 +5,7 @@
   <parent>
     <groupId>com.itextpdf</groupId>
     <artifactId>pdfocr-root</artifactId>
-    <version>3.0.2</version>
+    <version>4.0.0</version>
   </parent>
 
   <artifactId>pdfocr-api</artifactId>

pdfocr-api/src/main/java/com/itextpdf/pdfocr/IOcrEngine.java

@@ -85,4 +85,11 @@ public interface IOcrEngine {
      * @param ocrProcessContext ocr processing context
      */
     void createTxtFile(List<File> inputImages, File txtFile, OcrProcessContext ocrProcessContext);
+
+    /**
+     * Checks whether tagging is supported by the OCR engine.
+     *
+     * @return {@code true} if tagging is supported by the engine, {@code false} otherwise
+     */
+    boolean isTaggingSupported();
 }

pdfocr-api/src/main/java/com/itextpdf/pdfocr/OcrPdfCreator.java

@@ -39,7 +39,7 @@ This file is part of the iText (R) project.
 import com.itextpdf.kernel.geom.Point;
 import com.itextpdf.kernel.geom.Rectangle;
 import com.itextpdf.kernel.pdf.DocumentProperties;
-import com.itextpdf.kernel.pdf.PdfAConformanceLevel;
+import com.itextpdf.kernel.pdf.PdfAConformance;
 import com.itextpdf.kernel.pdf.PdfDocument;
 import com.itextpdf.kernel.pdf.PdfDocumentInfo;
 import com.itextpdf.kernel.pdf.PdfName;
@@ -67,8 +67,8 @@ This file is part of the iText (R) project.
 import com.itextpdf.pdfocr.logs.PdfOcrLogMessageConstant;
 import com.itextpdf.pdfocr.statistics.PdfOcrOutputType;
 import com.itextpdf.pdfocr.statistics.PdfOcrOutputTypeStatisticsEvent;
-import com.itextpdf.pdfocr.structuretree.LogicalStructureTreeItem;
 import com.itextpdf.pdfocr.structuretree.ArtifactItem;
+import com.itextpdf.pdfocr.structuretree.LogicalStructureTreeItem;
 
 import java.io.File;
 import java.io.IOException;
@@ -129,6 +129,9 @@ public OcrPdfCreator(final IOcrEngine ocrEngine) {
      */
     public OcrPdfCreator(final IOcrEngine ocrEngine,
             final OcrPdfCreatorProperties ocrPdfCreatorProperties) {
+        if (ocrPdfCreatorProperties.isTagged() && !ocrEngine.isTaggingSupported()) {
+            throw new PdfOcrException(PdfOcrExceptionMessageConstant.TAGGING_IS_NOT_SUPPORTED);
+        }
         setOcrEngine(ocrEngine);
         setOcrPdfCreatorProperties(ocrPdfCreatorProperties);
     }
@@ -471,11 +474,7 @@ private void addToCanvas(final PdfDocument pdfDocument,
                 // Logical tree, a list of top items, children can be retrieved out of them
                 List<LogicalStructureTreeItem> logicalTree = new ArrayList<>();
                 // A map of leaf LogicalStructureTreeItem's to TextInfo's attached to these leaves
-                Map<LogicalStructureTreeItem, List<TextInfo>> leavesTextInfos = new HashMap<>();
-                final boolean taggedSupported = getLogicalTree(pageText, logicalTree, leavesTextInfos);
-                if (!taggedSupported) {
-                    throw new PdfOcrException(PdfOcrExceptionMessageConstant.TAGGING_IS_NOT_SUPPORTED);
-                }
+                Map<LogicalStructureTreeItem, List<TextInfo>> leavesTextInfos = getLogicalTree(pageText, logicalTree);
                 pdfDocument.setTagged();
 
                 // Create a map of TextInfo to tag pointers meanwhile creating the required tags.
@@ -504,7 +503,7 @@ private PdfDocument createPdfDocument(final PdfWriter pdfWriter,
         boolean createPdfA3u = pdfOutputIntent != null;
         if (createPdfA3u) {
             pdfDocument = new PdfADocument(pdfWriter,
-                    PdfAConformanceLevel.PDF_A_3U, pdfOutputIntent,
+                    PdfAConformance.PDF_A_3U, pdfOutputIntent,
                     documentProperties);
         } else {
             pdfDocument = new PdfDocument(pdfWriter,
@@ -623,7 +622,7 @@ private void addImageToCanvas(final ImageData imageData,
                         ocrPdfCreatorProperties.getPageSize(), imageSize);
                 final Rectangle rect =
                         new Rectangle(
-                                (float)coordinates.x, (float)coordinates.y,
+                                (float)coordinates.getX(), (float)coordinates.getY(),
                                 imageSize.getWidth(), imageSize.getHeight());
                 pdfCanvas.addImageFittedIntoRectangle(imageData, rect, false);
             }
@@ -634,19 +633,12 @@ private void addImageToCanvas(final ImageData imageData,
         }
     }
 
-    /**
-     * @return {@code true} if tagging supported by the engine.
-     * @deprecated In next major version we need to add boolean taggingSupported() method into IOcrEngine
-     * and throw exception in OcrPdfCreator constructor if taggingSupported() returns false but
-     * OcrPdfCreatorProperties.getTagged returns true.
-     */
-    @Deprecated
-    private static boolean getLogicalTree(List<TextInfo> textInfos,
-            List<LogicalStructureTreeItem> logicalStructureTreeItems,
-            Map<LogicalStructureTreeItem, List<TextInfo>> leavesTextInfos) {
-        boolean taggedSupported = false;
+    private static Map<LogicalStructureTreeItem, List<TextInfo>> getLogicalTree(
+            List<TextInfo> textInfos, List<LogicalStructureTreeItem> logicalStructureTreeItems) {
+
+        Map<LogicalStructureTreeItem, List<TextInfo>> leavesTextInfos = new HashMap<>();
         if (textInfos == null) {
-            return taggedSupported;
+            return leavesTextInfos;
         }
 
         for (TextInfo textInfo : textInfos) {
@@ -656,7 +648,6 @@ private static boolean getLogicalTree(List<TextInfo> textInfos,
                 continue;
             } else if (structTreeItem != null) {
                 topParent = getTopParent(structTreeItem);
-                taggedSupported = true;
             } else {
                 structTreeItem = new LogicalStructureTreeItem();
                 textInfo.setLogicalStructureTreeItem(structTreeItem);
@@ -675,7 +666,7 @@ private static boolean getLogicalTree(List<TextInfo> textInfos,
             }
         }
 
-        return taggedSupported;
+        return leavesTextInfos;
     }
 
     private static LogicalStructureTreeItem getTopParent(LogicalStructureTreeItem structInfo) {
@@ -792,8 +783,8 @@ private void addTextToCanvas(
             }
 
             canvas.showTextAligned(paragraph,
-                    xOffset + (float) imageCoordinates.x,
-                    yOffset + (float) imageCoordinates.y,
+                    xOffset + (float) imageCoordinates.getX(),
+                    yOffset + (float) imageCoordinates.getY(),
                     TextAlignment.LEFT);
 
             if (ocrPdfCreatorProperties.isTagged()) {
@@ -933,7 +924,7 @@ public PdfCanvas showText(GlyphLine text) {
             // unicode of the not found glyph
             String message = PdfOcrLogMessageConstant
                     .COULD_NOT_FIND_CORRESPONDING_GLYPH_TO_UNICODE_CHARACTER;
-            for (int i = glyphLine.start; i < glyphLine.end; i++) {
+            for (int i = glyphLine.getStart(); i < glyphLine.getEnd(); i++) {
                 if (isNotDefGlyph(currentFont, glyphLine.get(i))) {
                     notDefGlyphsExists = true;
                     message = MessageFormatUtil.format(PdfOcrLogMessageConstant