Merge branch 'release_branch_DEVSIX-5576' into master-rc

pdfocr-api/pom.xml

@@ -5,7 +5,7 @@
   <parent>
     <groupId>com.itextpdf</groupId>
     <artifactId>pdfocr-root</artifactId>
-    <version>1.0.3</version>
+    <version>2.0.0</version>
   </parent>
 
   <artifactId>pdfocr-api</artifactId>
@@ -47,4 +47,4 @@
       </resource>
     </resources>
   </build>
-</project>
+</project>

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

@@ -0,0 +1,55 @@
+/*
+    This file is part of the iText (R) project.
+    Copyright (c) 1998-2021 iText Group NV
+    Authors: iText 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 com.itextpdf.commons.actions.AbstractITextEvent;
+import com.itextpdf.commons.actions.AbstractProductITextEvent;
+import com.itextpdf.commons.actions.confirmations.EventConfirmationType;
+import com.itextpdf.commons.actions.sequence.SequenceId;
+
+/**
+ * Helper class for working with events. This class is for internal usage.
+ */
+public abstract class AbstractPdfOcrEventHelper extends AbstractITextEvent {
+
+    /**
+     * Handles the event.
+     *
+     * @param event event
+     */
+    public abstract void onEvent(AbstractProductITextEvent event);
+
+    /**
+     * Returns the sequence id
+     *
+     * @return sequence id
+     */
+    public abstract SequenceId getSequenceId();
+
+    /**
+     * Returns the confirmation type of event.
+     *
+     * @return event confirmation type
+     */
+    public abstract EventConfirmationType getConfirmationType();
+}

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

@@ -48,6 +48,21 @@ public interface IOcrEngine {
      */
     Map<Integer, List<TextInfo>> doImageOcr(File input);
 
+    /**
+     * Reads data from the provided input image file and returns retrieved data
+     * in the format described below.
+     *
+     * @param input input image {@link java.io.File}
+     * @param ocrProcessContext ocr processing context
+     *
+     * @return {@link java.util.Map} where key is {@link java.lang.Integer}
+     * representing the number of the page and value is
+     * {@link java.util.List} of {@link TextInfo} elements where each
+     * {@link TextInfo} element contains a word or a line and its 4
+     * coordinates(bbox)
+     */
+    Map<Integer, List<TextInfo>> doImageOcr(File input, OcrProcessContext ocrProcessContext);
+
     /**
      * Performs OCR using provided {@link IOcrEngine} for the given list of
      * input images and saves output to a text file using provided path.
@@ -58,4 +73,16 @@ public interface IOcrEngine {
      * @param txtFile file to be created
      */
     void createTxtFile(List<File> inputImages, File txtFile);
+
+    /**
+     * Performs OCR using provided {@link IOcrEngine} for the given list of
+     * input images and saves output to a text file using provided path.
+     * Note that a human reading order is not guaranteed
+     * due to possible specifics of input images (multi column layout, tables etc)
+     *
+     * @param inputImages {@link java.util.List} of images to be OCRed
+     * @param txtFile file to be created
+     * @param ocrProcessContext ocr processing context
+     */
+    void createTxtFile(List<File> inputImages, File txtFile, OcrProcessContext ocrProcessContext);
 }

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

@@ -0,0 +1,45 @@
+/*
+    This file is part of the iText (R) project.
+    Copyright (c) 1998-2021 iText Group NV
+    Authors: iText 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 com.itextpdf.commons.actions.data.ProductData;
+
+/**
+ * The interface that holds information about product data and meta info.
+ */
+public interface IProductAware {
+
+    /**
+     * Gets the container with meta info.
+     *
+     * @return the held meta info container
+     */
+    PdfOcrMetaInfoContainer getMetaInfoContainer();
+
+    /**
+     * Gets object containing information about the product.
+     *
+     * @return product data
+     */
+    ProductData getProductData();
+}