[RELEASE] iText pdfOCR 4.0.2

Author: iText-CI

pdfocr-api/pom.xml

@@ -5,7 +5,7 @@
   <parent>
     <groupId>com.itextpdf</groupId>
     <artifactId>pdfocr-root</artifactId>
-    <version>4.0.1</version>
+    <version>4.0.2</version>
   </parent>
 
   <artifactId>pdfocr-api</artifactId>

pdfocr-api/src/sharpenconfig/java/com/itextpdf/pdfocr/SharpenConfigMapping.java

@@ -0,0 +1,94 @@
+/*
+    This file is part of the iText (R) project.
+    Copyright (c) 1998-2025 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.pdfocr;
+
+import java.util.AbstractMap.SimpleImmutableEntry;
+import java.util.Collection;
+import java.util.Collections;
+import java.util.List;
+import sharpen.config.MappingConfiguration;
+import sharpen.config.MappingConfigurator;
+import sharpen.config.ModuleOption;
+import sharpen.config.ModulesConfigurator;
+import sharpen.config.OptionsConfigurator;
+
+public class SharpenConfigMapping implements MappingConfiguration {
+
+    @Override
+    public int getMappingPriority() {
+        return 6;
+    }
+
+    @Override
+    public String getModuleName() {
+        return "pdfocr-api";
+    }
+
+    @Override
+    public void applyMappingConfiguration(MappingConfigurator configurator) {
+        configurator.mapStringLiteral("com.itextpdf.pdfocr.PdfOcrFontProvider.DEFAULT_FONT_PATH", "iText.Pdfocr.Api.font.LiberationSans-Regular.ttf");
+
+        // It's fine to use System.IO.StreamWriter in this mapping instead of the iText.Commons.Utils.FormattingStreamWriter
+        // because java.io.FileWriter only works with the characters writing, so there are no locale-dependent conversions.
+        configurator.ignoreUsing("Java.IO");
+        configurator.ignoreUsing("Java.Nio");
+        // images
+        configurator.addFullName("System.Drawing.Bitmap");
+        configurator.ignoreUsing("Javax.Imageio");
+    }
+
+    @Override
+    public void applySharpenOptions(OptionsConfigurator configurator) {
+
+    }
+
+    @Override
+    public void applyConfigModuleSettings(ModulesConfigurator configurator) {
+
+    }
+
+    @Override
+    public Collection<ModuleOption> getAvailableModuleSettings() {
+        return Collections.EMPTY_SET;
+    }
+
+    @Override
+    public Collection<String> getDependencies() {
+        return Collections.EMPTY_LIST;
+    }
+
+    @Override
+    public Collection<String> getIgnoredSourceFiles() {
+        return Collections.EMPTY_LIST;
+    }
+
+    @Override
+    public Collection<String> getIgnoredResources() {
+        return Collections.EMPTY_LIST;
+    }
+
+    @Override
+    public List<SimpleImmutableEntry<String, String>> getOverwrittenResources() {
+        return Collections.EMPTY_LIST;
+    }
+}

pdfocr-api/src/sharpenconfig/resources/META-INF/services/sharpen.config.MappingConfiguration

@@ -0,0 +1 @@
+com.itextpdf.pdfocr.SharpenConfigMapping

pdfocr-tesseract4/pom.xml

@@ -5,7 +5,7 @@
   <parent>
     <groupId>com.itextpdf</groupId>
     <artifactId>pdfocr-root</artifactId>
-    <version>4.0.1</version>
+    <version>4.0.2</version>
   </parent>
 
   <artifactId>pdfocr-tesseract4</artifactId>

pdfocr-tesseract4/src/main/java/com/itextpdf/pdfocr/tesseract4/AbstractTesseract4OcrEngine.java

@@ -27,6 +27,7 @@ This file is part of the iText (R) project.
 import com.itextpdf.commons.actions.contexts.IMetaInfo;
 import com.itextpdf.commons.actions.data.ProductData;
 import com.itextpdf.commons.utils.MessageFormatUtil;
+import com.itextpdf.commons.utils.StringNormalizer;
 import com.itextpdf.io.image.ImageType;
 import com.itextpdf.pdfocr.AbstractPdfOcrEventHelper;
 import com.itextpdf.pdfocr.IOcrEngine;
@@ -315,7 +316,7 @@ public final String doImageOcr(final File input,
      * @return boolean true is current os is windows, otherwise - false
      */
     public boolean isWindows() {
-        return identifyOsType().toLowerCase().contains("win");
+        return StringNormalizer.toLowerCase(identifyOsType()).contains("win");
     }
 
     /**
@@ -326,7 +327,7 @@ public boolean isWindows() {
     public String identifyOsType() {
         String os = System.getProperty("os.name") == null
                 ? System.getProperty("OS") : System.getProperty("os.name");
-        return os.toLowerCase();
+        return StringNormalizer.toLowerCase(os);
     }
 
     /**

pdfocr-tesseract4/src/main/java/com/itextpdf/pdfocr/tesseract4/Tesseract4ExecutableOcrEngine.java

@@ -25,6 +25,12 @@ This file is part of the iText (R) project.
 import com.itextpdf.commons.actions.confirmations.ConfirmEvent;
 import com.itextpdf.commons.actions.confirmations.EventConfirmationType;
 import com.itextpdf.commons.utils.MessageFormatUtil;
+import com.itextpdf.commons.utils.StringNormalizer;
+import com.itextpdf.pdfocr.AbstractPdfOcrEventHelper;
+import com.itextpdf.pdfocr.tesseract4.actions.events.PdfOcrTesseract4ProductEvent;
+import com.itextpdf.pdfocr.tesseract4.exceptions.PdfOcrTesseract4Exception;
+import com.itextpdf.pdfocr.tesseract4.exceptions.PdfOcrTesseract4ExceptionMessageConstant;
+import com.itextpdf.pdfocr.tesseract4.logs.Tesseract4LogMessageConstant;
 
 import java.awt.image.BufferedImage;
 import java.io.File;
@@ -35,13 +41,6 @@ This file is part of the iText (R) project.
 import java.util.Collections;
 import java.util.List;
 import java.util.UUID;
-
-import com.itextpdf.pdfocr.AbstractPdfOcrEventHelper;
-import com.itextpdf.pdfocr.tesseract4.actions.events.PdfOcrTesseract4ProductEvent;
-import com.itextpdf.pdfocr.tesseract4.exceptions.PdfOcrTesseract4Exception;
-import com.itextpdf.pdfocr.tesseract4.exceptions.PdfOcrTesseract4ExceptionMessageConstant;
-import com.itextpdf.pdfocr.tesseract4.logs.Tesseract4LogMessageConstant;
-
 import net.sourceforge.lept4j.Pix;
 import org.slf4j.LoggerFactory;
 
@@ -478,7 +477,7 @@ private String getExtension(File inputImage) {
                 String extension = new String(
                         inputImage.getAbsolutePath().toCharArray(), index,
                         inputImage.getAbsolutePath().length() - index);
-                return extension.toLowerCase();
+                return StringNormalizer.toLowerCase(extension);
             }
         }
         return ".png";

pdfocr-tesseract4/src/main/java/com/itextpdf/pdfocr/tesseract4/Tesseract4OcrEngineProperties.java

@@ -24,6 +24,7 @@ This file is part of the iText (R) project.
 
 import com.itextpdf.commons.utils.FileUtil;
 import com.itextpdf.commons.utils.MessageFormatUtil;
+import com.itextpdf.commons.utils.StringNormalizer;
 import com.itextpdf.pdfocr.IOcrEngine;
 import com.itextpdf.pdfocr.OcrEngineProperties;
 import com.itextpdf.pdfocr.tesseract4.exceptions.PdfOcrTesseract4Exception;
@@ -328,7 +329,7 @@ Tesseract4OcrEngineProperties setUserWords(final String language,
             final InputStream inputStream) throws PdfOcrTesseract4Exception {
         setPathToUserWordsFile(null);
         if (!getLanguages().contains(language)) {
-            if (DEFAULT_LANGUAGE.equals(language.toLowerCase())) {
+            if (DEFAULT_LANGUAGE.equals(StringNormalizer.toLowerCase(language))) {
                 List<String> languagesList = getLanguages();
                 languagesList.add(language);
                 setLanguages(languagesList);

pdfocr-tesseract4/src/main/java/com/itextpdf/pdfocr/tesseract4/actions/data/PdfOcrTesseract4ProductData.java

@@ -30,7 +30,7 @@ This file is part of the iText (R) project.
 public class PdfOcrTesseract4ProductData {
     private static final String PDF_OCR_TESSERACT4_PRODUCT_NAME = "pdfOcr-tesseract4";
     private static final String PDF_OCR_TESSERACT4_PUBLIC_PRODUCT_NAME = "pdfOCR-Tesseract4";
-    private static final String PDF_OCR_VERSION = "4.0.1";
+    private static final String PDF_OCR_VERSION = "4.0.2";
     private static final int PDF_OCR_COPYRIGHT_SINCE = 2000;
     private static final int PDF_OCR_COPYRIGHT_TO = 2025;
 

pdfocr-tesseract4/src/test/java/com/itextpdf/pdfocr/imageformats/ImageFormatIntegrationTest.java

@@ -23,6 +23,7 @@ This file is part of the iText (R) project.
 package com.itextpdf.pdfocr.imageformats;
 
 import com.itextpdf.commons.utils.MessageFormatUtil;
+import com.itextpdf.commons.utils.StringNormalizer;
 import com.itextpdf.kernel.colors.DeviceCmyk;
 import com.itextpdf.kernel.utils.CompareTool;
 import com.itextpdf.pdfocr.IntegrationTestHelper;
@@ -49,7 +50,7 @@ public abstract class ImageFormatIntegrationTest extends IntegrationTestHelper {
 
     public ImageFormatIntegrationTest(ReaderType type) {
         tesseractReader = getTesseractReader(type);
-        this.testType = type.toString().toLowerCase();
+        this.testType = StringNormalizer.toLowerCase(type.toString());
     }
 
     @BeforeEach

pom.xml

@@ -5,12 +5,12 @@
   <parent>
     <groupId>com.itextpdf</groupId>
     <artifactId>root</artifactId>
-    <version>9.1.0</version>
+    <version>9.2.0</version>
     <relativePath />
   </parent>
 
   <artifactId>pdfocr-root</artifactId>
-  <version>4.0.1</version>
+  <version>4.0.2</version>
   <packaging>pom</packaging>
 
   <name>pdfOCR</name>
@@ -22,7 +22,7 @@
   </modules>
 
   <properties>
-    <itext.version>9.1.0</itext.version>
+    <itext.version>9.2.0</itext.version>
     <java.version>1.8</java.version>
     <jdkLevel>${java.version}</jdkLevel>
     <maven.compiler.source>${java.version}</maven.compiler.source>