Label current version to prevent expiry of original (#271)

* Label current version to prevent expiry of original

* Cleanup & Add tests for feature "keep original version"

---------

Co-authored-by: Robin Windey <[email protected]>

README.md

@@ -136,6 +136,7 @@ OCR language | The languages to be used for OCR processing. The languages can be
 Assign tags after OCR | These tags will be assigned to the file after it has been successfully processed. |
 Remove tags after OCR | These tags will be removed from the file after it has been successfully processed. If the file does not have the tag, it will just be skipped. |
 OCR mode | Controls the way files are processed, which already have OCR content. For PDF files this setting corresponds to the `--skip-text`, `--redo-ocr` and `--force-ocr` parameters of `ocrmypdf`. See [official docs](https://ocrmypdf.readthedocs.io/en/latest/advanced.html#when-ocr-is-skipped) for additional information.<br>**Skip text:** skip pages completely that already contain text. Such a page will not be touched and just be copied to the final output.<br>**Redo OCR:** perform a detailed text analysis to split up pages into areas with and without text.<br>**Force OCR:** all pages will be rasterized to images and OCR will be performed on every page. |
+Keep original file version | If the switch is set, the original file (before applying OCR) will be kept. This is done by giving the file version the label `Before OC`. This version will be excluded from the automatic expiration process (see [here](https://docs.nextcloud.com/server/latest/user_manual/en/files/version_control.html#naming-a-version) for details) |
 Remove background\* | If the switch is set, the OCR processor will try to remove the background of the document before processing and instead set a white background. For PDF files this setting corresponds to the [`--remove-background`](https://ocrmypdf.readthedocs.io/en/latest/cookbook.html?highlight=remove-background#image-processing) parameter of `ocrmypdf`.<br/>:warning: Please note that this flag will currently only work with **`ocrmypdf` versions prior to 13**. It might be added in future versions again. See [here](https://github.com/ocrmypdf/OCRmyPDF/issues/884) for details. :warning:|
 
 

jest.config.js

@@ -4,15 +4,18 @@ const ignorePatterns = [
 	'@mdi/svg',
 	'bail',
 	'comma-separated-tokens',
+	'ccount',
 	'char-regex',
 	'decode-named-character-reference',
 	'devlop',
 	'escape-string-regexp',
 	'hast-.*',
 	'is-.*',
+	'longest-streak',
 	'mdast-.*',
 	'micromark',
 	'micromark-.*',
+	'markdown-table',
 	'property-information',
 	'rehype-.*',
 	'remark-.*',
@@ -28,6 +31,7 @@ const ignorePatterns = [
 	'vfile-.*',
 	'vue-material-design-icons',
 	'web-namespaces',
+	'zwitch',
 ]
 
 module.exports = {

lib/Model/WorkflowSettings.php

@@ -49,6 +49,9 @@ class WorkflowSettings {
 	/** @var array string */
 	private $tagsToAddAfterOcr = [];
 
+	/** @var bool */
+	private $keepOriginalFileVersion = false;
+
 	/**
 	 * @param string $json The serialized JSON string used in frontend as input for the Vue component
 	 */
@@ -91,6 +94,13 @@ public function getTagsToAddAfterOcr(): array {
 		return $this->tagsToAddAfterOcr;
 	}
 
+	/**
+	 * @return bool
+	 */
+	public function getKeepOriginalFileVersion(): bool {
+		return $this->keepOriginalFileVersion;
+	}
+
 	/**
 	 * Checks if a new WorkflowSettings object can be constructed from the given JSON string
 	 * @param string $json The serialized JSON string used in frontend as input for the Vue component
@@ -132,5 +142,8 @@ private function setJson(?string $json = null) {
 		if (array_key_exists('tagsToAddAfterOcr', $data) && is_array($data['tagsToAddAfterOcr'])) {
 			$this->tagsToAddAfterOcr = $data['tagsToAddAfterOcr'];
 		}
+		if (array_key_exists('keepOriginalFileVersion', $data) && is_bool($data['keepOriginalFileVersion'])) {
+			$this->keepOriginalFileVersion = $data['keepOriginalFileVersion'];
+		}
 	}
 }

lib/Service/OcrService.php

@@ -27,6 +27,9 @@
 namespace OCA\WorkflowOcr\Service;
 
 use OC\User\NoUserException;
+use OCA\Files_Versions\Versions\IMetadataVersion;
+use OCA\Files_Versions\Versions\IMetadataVersionBackend;
+use OCA\Files_Versions\Versions\IVersionManager;
 use OCA\WorkflowOcr\Exception\OcrResultEmptyException;
 use OCA\WorkflowOcr\Helper\IProcessingFileAccessor;
 use OCA\WorkflowOcr\Model\WorkflowSettings;
@@ -46,12 +49,18 @@
 use Psr\Log\LoggerInterface;
 
 class OcrService implements IOcrService {
+	private const FILE_VERSION_LABEL_KEY = 'label';
+	private const FILE_VERSION_LABEL_VALUE = 'Before OCR';
+
 	/** @var IOcrProcessorFactory */
 	private $ocrProcessorFactory;
 
 	/** @var IGlobalSettingsService */
 	private $globalSettingsService;
 
+	/** @var IVersionManager */
+	private $versionManager;
+
 	/** @var ISystemTagObjectMapper */
 	private $systemTagObjectMapper;
 
@@ -82,6 +91,7 @@ class OcrService implements IOcrService {
 	public function __construct(
 		IOcrProcessorFactory $ocrProcessorFactory,
 		IGlobalSettingsService $globalSettingsService,
+		IVersionManager $versionManager,
 		ISystemTagObjectMapper $systemTagObjectMapper,
 		IUserManager $userManager,
 		IFilesystem $filesystem,
@@ -93,6 +103,7 @@ public function __construct(
 		LoggerInterface $logger) {
 		$this->ocrProcessorFactory = $ocrProcessorFactory;
 		$this->globalSettingsService = $globalSettingsService;
+		$this->versionManager = $versionManager;
 		$this->systemTagObjectMapper = $systemTagObjectMapper;
 		$this->userManager = $userManager;
 		$this->filesystem = $filesystem;
@@ -133,6 +144,11 @@ public function runOcrProcess(int $fileId, string $uid, WorkflowSettings $settin
 
 			// Only create a new file version if the file OCR result was not empty #130
 			if ($result->getRecognizedText() !== '') {
+				if ($settings->getKeepOriginalFileVersion()) {
+					// Add label to original file to prevent its expiry
+					$this->setFileVersionsLabel($file, $uid, self::FILE_VERSION_LABEL_VALUE);
+				}
+
 				$newFilePath = $originalFileExtension === $newFileExtension ?
 					$filePath :
 					$filePath . '.pdf';
@@ -225,4 +241,37 @@ private function createNewFileVersion(string $filePath, string $ocrContent, int
 			$this->processingFileAccessor->setCurrentlyProcessedFileId(null);
 		}
 	}
+
+	/**
+	 * @param File $file The file to set the label for
+	 * @param string $uid The userId of the file owner
+	 * @param string $label The label to set
+	 */
+	private function setFileVersionsLabel(File $file, string $uid, string $label): void {
+		$fileMTime = $file->getMTime();
+		$user = $this->userManager->get($uid);
+		$versions = $this->versionManager->getVersionsForFile($user, $file);
+
+		foreach ($versions as $version) {
+			$revisionId = $version->getRevisionId();
+			if (!$version instanceof IMetadataVersion) {
+				$this->logger->debug('Skipping version with revision id {versionId} because "{versionClass}" is not an IMetadataVersion', ['versionId' => $revisionId, 'versionClass' => get_class($version)]);
+				continue;
+			}
+
+			$versionBackend = $version->getBackend();
+			if (!$versionBackend instanceof IMetadataVersionBackend) {
+				$this->logger->debug('Skipping version with revision id {versionId} because its backend "{versionBackendClass}" does not implement IMetadataVersionBackend', ['versionId' => $revisionId, 'versionBackendClass' => get_class($versionBackend)]);
+				continue;
+			}
+
+			$versionTimestamp = $version->getTimestamp();
+			$versionLabel = $version->getMetadataValue(self::FILE_VERSION_LABEL_KEY);
+
+			if ($fileMTime === $versionTimestamp && empty($versionLabel)) {
+				$this->logger->debug('Setting pre OCR label for version with revision id {versionId} on file {fileId}', ['versionId' => $revisionId, 'fileId' => $file->getId()]);
+				$versionBackend->setMetadataValue($file, $revisionId, self::FILE_VERSION_LABEL_KEY, $label);
+			}
+		}
+	}
 }