Initial implementation for OCRmyPDF #15712
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -48,6 +48,7 @@ public enum KeyBinding { | |
| // We have to put Entry Editor Previous before, because otherwise the decrease font size is found first | ||
| ENTRY_EDITOR_PREVIOUS_PANEL_2("Entry editor, previous panel 2", Localization.lang("Entry editor, previous panel 2"), "shortcut+MINUS", KeyBindingCategory.VIEW), | ||
| DELETE_ENTRY("Delete entry", Localization.lang("Delete entry"), "DELETE", KeyBindingCategory.BIBTEX), | ||
| PERFORM_OCR("Perform OCR", Localization.lang("Perform OCR"), "", KeyBindingCategory.FILE), | ||
|
Member
There was a problem hiding this comment. I think this should have an appropriate shortcut. Pinging @Siedlerchr for suggestions. |
||
| DEFAULT_DIALOG_ACTION("Execute default action in dialog", Localization.lang("Execute default action in dialog"), "shortcut+ENTER", KeyBindingCategory.VIEW), | ||
| DOWNLOAD_FULL_TEXT("Download full text documents", Localization.lang("Download full text documents"), "alt+F7", KeyBindingCategory.QUALITY), | ||
| OPEN_CLOSE_ENTRY_EDITOR("Open / close entry editor", Localization.lang("Open / close entry editor"), "shortcut+E", KeyBindingCategory.VIEW), | ||
|
|
||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,114 @@ | ||
| package org.jabref.gui.linkedfile; | ||
|
|
||
| import java.nio.file.Path; | ||
| import java.util.List; | ||
| import java.util.Optional; | ||
|
|
||
| import javax.swing.undo.UndoManager; | ||
|
|
||
| import org.jabref.gui.DialogService; | ||
| import org.jabref.gui.StateManager; | ||
| import org.jabref.gui.actions.SimpleCommand; | ||
| import org.jabref.gui.externalfiles.ImportHandler; | ||
| import org.jabref.gui.preferences.GuiPreferences; | ||
| import org.jabref.logic.l10n.Localization; | ||
| import org.jabref.logic.ocr.OcrEngine; | ||
| import org.jabref.logic.ocr.OcrMyPdfEngine; | ||
| import org.jabref.logic.ocr.OcrResult; | ||
| import org.jabref.logic.util.BackgroundTask; | ||
| import org.jabref.logic.util.TaskExecutor; | ||
| import org.jabref.model.database.BibDatabaseContext; | ||
| import org.jabref.model.entry.BibEntry; | ||
| import org.jabref.model.entry.LinkedFile; | ||
| import org.jabref.model.util.FileUpdateMonitor; | ||
|
|
||
| import org.slf4j.Logger; | ||
| import org.slf4j.LoggerFactory; | ||
|
|
||
| public class OcrLinkedFileAction extends SimpleCommand { | ||
| private static final Logger LOGGER = LoggerFactory.getLogger(OcrLinkedFileAction.class); | ||
|
|
||
| private final LinkedFile linkedFile; | ||
| private final BibDatabaseContext databaseContext; | ||
| private final DialogService dialogService; | ||
| private final GuiPreferences preferences; | ||
| private final TaskExecutor taskExecutor; | ||
| private final OcrEngine ocrEngine; | ||
| private final List<BibEntry> linkedEntries; | ||
| private final ImportHandler importHandler; | ||
|
|
||
| public OcrLinkedFileAction(LinkedFile linkedFile, | ||
| List<BibEntry> bibEntries, | ||
|
InAnYan marked this conversation as resolved.
|
||
| BibDatabaseContext databaseContext, | ||
| DialogService dialogService, | ||
| GuiPreferences preferences, | ||
| TaskExecutor taskExecutor, | ||
| FileUpdateMonitor fileUpdateMonitor, | ||
| UndoManager undoManager, | ||
| StateManager stateManager) { | ||
| this.linkedFile = linkedFile; | ||
| this.linkedEntries = bibEntries; | ||
| this.databaseContext = databaseContext; | ||
| this.dialogService = dialogService; | ||
| this.preferences = preferences; | ||
| this.taskExecutor = taskExecutor; | ||
| this.ocrEngine = new OcrMyPdfEngine(); | ||
| this.importHandler = new ImportHandler( | ||
| databaseContext, | ||
| preferences, | ||
| fileUpdateMonitor, | ||
| undoManager, | ||
| stateManager, | ||
| dialogService, | ||
| taskExecutor | ||
| ); | ||
| } | ||
|
|
||
| @Override | ||
| public void execute() { | ||
| Optional<Path> pdfPath = linkedFile.findIn(databaseContext, preferences.getFilePreferences()); | ||
| if (pdfPath.isEmpty()) { | ||
| dialogService.showErrorDialogAndWait(Localization.lang("Could not find a file to OCR")); | ||
| return; | ||
| } | ||
| BackgroundTask<OcrResult> ocrTask = BackgroundTask.wrap(() -> ocrEngine.performOcrAndEmbedText(pdfPath.get())); | ||
|
qodo-free-for-open-source-projects[bot] marked this conversation as resolved.
|
||
|
|
||
| ocrTask.titleProperty().set(Localization.lang("Performing OCR")); | ||
| ocrTask.showToUser(true); | ||
| ocrTask.onSuccess(result -> { | ||
| switch (result) { | ||
| case OcrResult.Success success -> { | ||
| dialogService.notify(Localization.lang("OCR succeeded")); | ||
| Path ocredPdf = success.outputFile(); | ||
| for (BibEntry entry : linkedEntries) { | ||
| importHandler.getFileLinker().linkFilesToEntry(entry, List.of(ocredPdf)); | ||
| } | ||
| } | ||
|
qodo-free-for-open-source-projects[bot] marked this conversation as resolved.
|
||
| case OcrResult.Failure failure -> { | ||
| String failureReason = getFailureResult(failure); | ||
| dialogService.showErrorDialogAndWait(Localization.lang("OCR failed"), failureReason); | ||
| } | ||
| } | ||
| }); | ||
| ocrTask.onFailure(exception -> { | ||
| LOGGER.error("Unexpected error during OCR", exception); | ||
| dialogService.notify(Localization.lang("OCR failed. See the logs for the details")); | ||
| }); | ||
| taskExecutor.execute(ocrTask); | ||
| } | ||
|
|
||
| String getFailureResult(OcrResult.Failure failure) { | ||
| return switch (failure.reason()) { | ||
| case NOT_AVAILABLE -> | ||
| Localization.lang("OCRmyPDF is not available"); | ||
| case TIMEOUT -> | ||
| Localization.lang("OCR timed out"); | ||
| case NON_ZERO_EXIT -> | ||
| Localization.lang("OCR process failed"); | ||
| case IO_ERROR -> | ||
| Localization.lang("Could not start OCR process"); | ||
| case INTERRUPTED -> | ||
| Localization.lang("OCR was cancelled"); | ||
| }; | ||
| } | ||
| } | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,25 @@ | ||
| 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, whether the path of the OCRed with searchable text file or the error message. | ||
| /// | ||
| /// @param pdfPath the file to perform OCR on. | ||
| /// @return the result of the OCR operation with the extracted text or an error message. | ||
| OcrResult performOcrAndEmbedText(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(); | ||
| } |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,6 @@ | ||
| package org.jabref.logic.ocr; | ||
|
|
||
| /// Enums for the reasons that can lead the OCR process to fail. | ||
| public enum OcrFailureReason { | ||
| NOT_AVAILABLE, TIMEOUT, NON_ZERO_EXIT, IO_ERROR, INTERRUPTED | ||
| } |
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I think we should change "Perform OCR" in the message shown to the user. I think most of the users don't know what OCR is.
I think "Make the PDF searchable" or something like this would be better.