Initial implementation for OCRmyPDF

jablib/src/main/java/org/jabref/logic/ocr/OcrEngine.java

@@ -0,0 +1,32 @@
+package org.jabref.logic.ocr;
+
+import java.nio.file.Path;
+
+/**
+ * Interface for OCR engines.
+ * Any engine in the future can implement this interface.
+ */
+public interface OcrEngine {
+
+    /**
+     * Performs OCR on the given input file and returns the result.
+     *
+     * @param pdfPath the file to perform OCR on.
+     * @return the result of the OCR operation with the extracted text or an error message.
+     */
+    OcrResult performOcr(Path pdfPath);
+
+    /**
+     * Checks if the OCR engine is available for use.
+     *
+     * @return true if the engine is available, false otherwise.
+     */
+    boolean isAvailable();
+
+    /**
+     * Gets the name of the OCR engine.
+     *
+     * @return the name of the OCR engine (e.g., "OCRmyPDF", "Tesseract").
+     */
+    String getName();
+}

jablib/src/main/java/org/jabref/logic/ocr/OcrMyPdfEngine.java

@@ -0,0 +1,101 @@
+package org.jabref.logic.ocr;
+
+import java.io.BufferedReader;
+import java.io.IOException;
+import java.io.InputStreamReader;
+import java.nio.file.Path;
+import java.util.ArrayList;
+import java.util.List;
+import java.util.concurrent.TimeUnit;
+
+import org.jabref.logic.util.io.FileUtil;
+
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+/**
+ * Implementation of the OcrEngine interface using OCRmyPDF.
+ */
+public class OcrMyPdfEngine implements OcrEngine {
+
+    private static final Logger LOGGER = LoggerFactory.getLogger(OcrMyPdfEngine.class);
+    private static final int TIMEOUT_MINS = 10;
+
+    @Override
+    public String getName() {
+        return "OCRmyPDF";
+    }
+
+    @Override
+    public boolean isAvailable() {
+        return true;
+    }
+
+    /**
+     * OCRmyPDF writes the searchable PDF to a new file alongside the original file.
+     * <p>
+     * Example: document.pdf -> document_ocr.pdf.
+     *
+     * @param pdfPath the file to perform OCR on.
+     * @return {@link OcrResult.Success} containing the path to the searchable PDF,
+     * or {@link OcrResult.Failure} with an error message if OCR failed.
+     */
+    @Override
+    public OcrResult performOcr(Path pdfPath) {
+        if (!isAvailable()) {
+            return OcrResult.failure("OCRmyPDF is not installed. Please install it using: pip install OCRmyPDF");
+        }
+        List<String> command = new ArrayList<>();
+        command.add("ocrmypdf");
+        command.add(pdfPath.toString());
+        Path outputPath = makeOutputFilePath(pdfPath);
+        String outputFile = outputPath.toString();
+        command.add(outputFile);
+        try {
+            ProcessBuilder processBuilder = new ProcessBuilder(command);
+            processBuilder.redirectErrorStream(true);
+            Process process = processBuilder.start();
+
+            StringBuilder processOutput = new StringBuilder();
+
+            // Get the output and the errors of the process
+            try (BufferedReader reader = new BufferedReader(
+                    new InputStreamReader(process.getInputStream()))) {
+                String line;
+                while ((line = reader.readLine()) != null) {
+                    processOutput.append(line).append("\n");
+                    LOGGER.debug("OCRmyPDF: {}", line);
+                }
+            }
+
+            boolean finished = process.waitFor(TIMEOUT_MINS, TimeUnit.MINUTES);
+            if (!finished) {
+                process.destroyForcibly();
+                return OcrResult.failure("OCRmyPDF process timed out after " + TIMEOUT_MINS + " minutes.");
+            }
+
+            if (process.exitValue() == 0) {
+                String result = "A searchable PDF has been created with OCRmyPDF at: " + outputFile;
+                return OcrResult.success(result, outputPath);
+            } else {
+                return OcrResult.failure("OCRmyPDF failed with exit code " + process.exitValue() + ": " + processOutput.toString());
+            }
+        } catch (IOException | InterruptedException e) {
+            LOGGER.error("Error while running OCRmyPDF.", e);
+            return OcrResult.failure("Error while running OCRmyPDF: " + e.getMessage());
+        }
+    }
+
+    /**
+     * Generates the output path for the searchable PDF.
+     * Example: Documents/my files/document.pdf -> Documents/my files/document_ocr.pdf.
+     *
+     * @param inputPath the path of the PDF that needs to be OCRed.
+     * @return the output path of the searchable OCRed PDF.
+     */
+    private Path makeOutputFilePath(Path inputPath) {
+        String baseName = FileUtil.getBaseName(inputPath.toString());
+        Path outputPath = inputPath.resolveSibling(baseName + "_ocr.pdf");
+        return outputPath;
+    }
+}

jablib/src/main/java/org/jabref/logic/ocr/OcrResult.java

@@ -0,0 +1,66 @@
+package org.jabref.logic.ocr;
+
+import java.nio.file.Path;
+
+import org.apache.commons.lang3.StringUtils;
+
+/**
+ * Represents the result of an OCR operation.
+ * Uses sealed classes to ensure type safety and avoid null parameters.
+ */
+public sealed interface OcrResult {
+    /**
+     * Represents a successful OCR result, containing the recognized text and optional output file.
+     */
+    record Success(String text, Path outputFile) implements OcrResult {
+        public Success(String text) {
+            this(text, null);
+        }
+    }
+
+    /**
+     * Represents a failed OCR result with an error message.
+     */
+    record Failure(String errorMessage) implements OcrResult {
+        public Failure {
+            if (StringUtils.isBlank(errorMessage)) {
+                errorMessage = "Unknown error during OCR process";
+            }
+        }
+    }
+
+    /**
+     * Checks if this result is success.
+     */
+    default boolean isSuccess() {
+        return this instanceof Success;
+    }
+
+    /**
+     * Checks if this result is failure.
+     */
+    default boolean isFailure() {
+        return this instanceof Failure;
+    }
+
+    /**
+     * Factory method to create a success result with text only.
+     */
+    static OcrResult success(String text) {
+        return new Success(text);
+    }
+
+    /**
+     * Factory method to create a success result with text and output file.
+     */
+    static OcrResult success(String text, Path outputFile) {
+        return new Success(text, outputFile);
+    }
+
+    /**
+     * Factory method to create a failure result with an error message.
+     */
+    static OcrResult failure(String errorMessage) {
+        return new Failure(errorMessage);
+    }
+}