Add image conversion (#111)

* Add image conversion capability for JPEG and PNG images. This conversion uses ImageMagick's "convert" command to create a new PDF file. It does not OCR the file during the conversion, but requires a separate flow for the newly created PDF file. * Implement optional image conversion before PDF processing * Add optional png/jpg conversion via Imagick * Closing #107 tmp test * Fix Psalm errors * Use api packages from vendor * Update Psalm baseline * Apply Psalm autofix * Move OCR processors to different classes * Code- & docs cleanup * Fix code smells & psalm errors Co-authored-by: lbdroid <[email protected]>
R0Wi-DEV · May 21, 2022 · 4d8e820 · 4d8e820
1 parent 8db58f9
commit 4d8e820
Show file tree

Hide file tree

Showing 24 changed files with 502 additions and 264 deletions.
diff --git a/.github/workflows/codecov.yml b/.github/workflows/codecov.yml
@@ -37,6 +37,7 @@ jobs:
           auth_header="$(git config --local --get http.https://github.com/.extraheader)"
           git submodule sync --recursive
           git -c "http.extraheader=$auth_header" -c protocol.version=2 submodule update --init --force --recursive --depth=1
+
       - name: Checkout app
         uses: actions/checkout@v2
         with:
@@ -47,7 +48,7 @@ jobs:
         with:
           php-version: ${{ matrix.php-versions }}
           tools: phpunit
-          extensions: mbstring, iconv, fileinfo, intl, sqlite, pdo_sqlite, gd, zip
+          extensions: mbstring, iconv, fileinfo, intl, sqlite, pdo_sqlite, gd, zip, imagick
           coverage: xdebug
 
       - name: Set up PHPUnit

diff --git a/.github/workflows/phpunit.yml b/.github/workflows/phpunit.yml
@@ -11,7 +11,7 @@ env:
   APP_NAME: workflow_ocr
 
 jobs:
-  php:
+  sqlite:
     runs-on: ubuntu-20.04
 
     strategy:
@@ -37,17 +37,18 @@ jobs:
           auth_header="$(git config --local --get http.https://github.com/.extraheader)"
           git submodule sync --recursive
           git -c "http.extraheader=$auth_header" -c protocol.version=2 submodule update --init --force --recursive --depth=1
+      
       - name: Checkout app
         uses: actions/checkout@v2
         with:
           path: apps/${{ env.APP_NAME }}
-
+      
       - name: Set up php ${{ matrix.php-versions }}
         uses: shivammathur/setup-php@v2
         with:
           php-version: ${{ matrix.php-versions }}
           tools: phpunit
-          extensions: mbstring, iconv, fileinfo, intl, sqlite, pdo_sqlite, gd, zip
+          extensions: mbstring, iconv, fileinfo, intl, sqlite, pdo_sqlite, gd, zip, imagick
           coverage: none
 
       - name: Set up PHPUnit
@@ -64,11 +65,7 @@ jobs:
           php -S localhost:8080 &
       - name: PHPUnit
         working-directory: apps/${{ env.APP_NAME }}
-        run: ./vendor/phpunit/phpunit/phpunit -c phpunit.xml
-
-      - name: PHPUnit integration
-        working-directory: apps/${{ env.APP_NAME }}
-        run: ./vendor/phpunit/phpunit/phpunit -c phpunit.integration.xml
+        run: make test
 
   mysql:
     runs-on: ubuntu-20.04
@@ -105,6 +102,7 @@ jobs:
           auth_header="$(git config --local --get http.https://github.com/.extraheader)"
           git submodule sync --recursive
           git -c "http.extraheader=$auth_header" -c protocol.version=2 submodule update --init --force --recursive --depth=1
+
       - name: Checkout app
         uses: actions/checkout@v2
         with:
@@ -115,7 +113,7 @@ jobs:
         with:
           php-version: ${{ matrix.php-versions }}
           tools: phpunit
-          extensions: mbstring, iconv, fileinfo, intl, mysql, pdo_mysql, gd, zip
+          extensions: mbstring, iconv, fileinfo, intl, mysql, pdo_mysql, gd, zip, imagick
           coverage: none
 
       - name: Set up PHPUnit
@@ -132,11 +130,7 @@ jobs:
           php -S localhost:8080 &
       - name: PHPUnit
         working-directory: apps/${{ env.APP_NAME }}
-        run: ./vendor/phpunit/phpunit/phpunit -c phpunit.xml
-
-      - name: PHPUnit integration
-        working-directory: apps/${{ env.APP_NAME }}
-        run: ./vendor/phpunit/phpunit/phpunit -c phpunit.integration.xml
+        run: make test
 
   pgsql:
     runs-on: ubuntu-20.04
@@ -175,6 +169,7 @@ jobs:
           auth_header="$(git config --local --get http.https://github.com/.extraheader)"
           git submodule sync --recursive
           git -c "http.extraheader=$auth_header" -c protocol.version=2 submodule update --init --force --recursive --depth=1
+
       - name: Checkout app
         uses: actions/checkout@v2
         with:
@@ -185,7 +180,7 @@ jobs:
         with:
           php-version: ${{ matrix.php-versions }}
           tools: phpunit
-          extensions: mbstring, iconv, fileinfo, intl, pgsql, pdo_pgsql, gd, zip
+          extensions: mbstring, iconv, fileinfo, intl, pgsql, pdo_pgsql, gd, zip, imagick
           coverage: none
 
       - name: Set up PHPUnit
@@ -202,8 +197,4 @@ jobs:
           php -S localhost:8080 &
       - name: PHPUnit
         working-directory: apps/${{ env.APP_NAME }}
-        run: ./vendor/phpunit/phpunit/phpunit -c phpunit.xml
-
-      - name: PHPUnit integration
-        working-directory: apps/${{ env.APP_NAME }}
-        run: ./vendor/phpunit/phpunit/phpunit -c phpunit.integration.xml
+        run: make test
diff --git a/README.md b/README.md
@@ -25,6 +25,7 @@
 - [How it works](#how-it-works)
   - [General](#general)
   - [PDF](#pdf)
+  - [Images](#images)
 - [Development](#development)
   - [Dev setup](#dev-setup)
   - [Debugging](#debugging)
@@ -52,13 +53,15 @@ Since the actual processing of the files is done asynchronously via Nextcloud's
 ### Backend
 > :warning: Since `v1.20.1` you'll have to install `OCRmyPDF`.
 
-In the backend [`OCRmyPDF`](https://github.com/jbarlow83/OCRmyPDF) is used for processing PDF files. Make sure you have this commandline tool installed. Make sure you have the appropriate version (see below, Used libraries').  
+In the backend [`OCRmyPDF`](https://github.com/jbarlow83/OCRmyPDF) is used for processing PDF files. Make sure you have this commandline tool installed. Make sure you have the appropriate version (see below, Used libraries').
 
 ```bash
 apt-get install ocrmypdf
 ``` 
 
-Also if you want to use specific language settings please install the corresponding `tesseract` packages.
+The `ocrmypdf` CLI can also convert single image files (`jpg`/`png`) to PDF before processing it via OCR. This mode is also supported by this app. You can read more about it in the [official docs](https://ocrmypdf.readthedocs.io/en/latest/cookbook.html#option-use-ocrmypdf-single-images-only).
+
+Also if you want to use specific **language settings** please install the corresponding `tesseract` packages.
 
 ```bash
 # English
@@ -159,7 +162,11 @@ To **test** if your file gets processed properly you can do the following steps:
 ### PDF
 For processing PDF files, the external command line tool [`OCRmyPDF`](https://github.com/jbarlow83/OCRmyPDF) is used. The tool is invoked with the [`--redo-ocr`](https://ocrmypdf.readthedocs.io/en/latest/advanced.html#when-ocr-is-skipped) parameter so that it will perform a detailed text analysis. The detailed analysis masks out visible text and sends the image of each page to the OCR processor. After processing, additional text is inserted as OCR, whereas existing text in a mixed file document (images embedded into text pages) is not disrupted.
 
+### Images
+For processing single images (currently `jpg` and `png` are supported), `ocrmypdf` converts the image to a PDF. The converted PDF file will then be OCR processed and saved as a new file with the original filename and the extension `.pdf` (for example `myImage.jpg` will be saved to `myImage.jpg.pdf`). The original image fill will remain untouched.
+
 ## Development
+
 ### Dev setup
 Tools and packages you need for development:
 * `make`
@@ -342,4 +349,4 @@ That's all. If you now create a new workflow based on your added mimetype, your
 | OCRmyPDF (commandline) | >= 9.6.0 | https://github.com/jbarlow83/OCRmyPDF On Debian, you might need to manually install a more recent version as described in https://ocrmypdf.readthedocs.io/en/latest/installation.html#ubuntu-18-04-lts; see https://github.com/R0Wi/workflow_ocr/issues/46 |
 | php-shellcommand | >= 1.6 | https://github.com/mikehaertl/php-shellcommand |
 | chain | >= 0.9.0 | https://packagist.org/packages/cocur/chain |
-| PHPUnit | >= 8.0 | https://phpunit.de/ |
+| PHPUnit | >= 8.0 | https://phpunit.de/ |
diff --git a/composer.json b/composer.json
@@ -8,7 +8,7 @@
         "phpunit/php-code-coverage": "9.2.5",
         "phpunit/phpcov": "8.2.*",
         "nextcloud/coding-standard": "^1.0",
-        "vimeo/psalm": "^4.22",
+        "vimeo/psalm": "^4.23",
         "christophwurst/nextcloud": "dev-master"
     },
     "config": {
@@ -25,6 +25,7 @@
         "psalm": "psalm --threads=1",
 		"psalm:update-baseline": "psalm --threads=1 --update-baseline",
 		"psalm:clear": "psalm --clear-cache && psalm --clear-global-cache",
-		"psalm:fix": "psalm --alter --issues=InvalidReturnType,InvalidNullableReturnType,MissingParamType,InvalidFalsableReturnType"
+		"psalm:fix": "psalm --alter --issues=InvalidReturnType,InvalidNullableReturnType,MissingParamType,InvalidFalsableReturnType",
+        "psalm:write-baseline": "psalm --threads=1 --set-baseline=./tests/psalm-baseline.xml"
     }	
 }
diff --git a/composer.lock b/composer.lock
diff --git a/lib/AppInfo/Application.php b/lib/AppInfo/Application.php
@@ -90,7 +90,7 @@ public function boot(IBootContext $context): void {
 		$this->requireAutoload();
 	}
 
-	private function requireAutoload() {
+	private function requireAutoload(): void {
 		if (is_dir(self::COMPOSER_DIR) && file_exists(self::COMPOSER_DIR . 'autoload.php')) {
 			require_once self::COMPOSER_DIR . 'autoload.php';
 		} else {

diff --git a/lib/BackgroundJobs/ProcessFileJob.php b/lib/BackgroundJobs/ProcessFileJob.php
@@ -170,7 +170,7 @@ private function processFile(string $filePath, WorkflowSettings $settings) : voi
 		}
 
 		try {
-			$ocrFile = $this->ocrFile($node, $settings);
+			$ocrFile = $this->ocrService->ocrFile($node, $settings);
 		} catch (OcrNotPossibleException $ocrNpEx) {
 			$this->logger->error('OCR for file ' . $node->getPath() . ' not possible. Message: ' . $ocrNpEx->getMessage());
 			return;
@@ -179,7 +179,16 @@ private function processFile(string $filePath, WorkflowSettings $settings) : voi
 			return;
 		}
 
-		$this->createNewFileVersion($filePath, $ocrFile, $node->getId());
+		$fileContent = $ocrFile->getFileContent();
+		$nodeId = $node->getId();
+		$originalFileExtension = $node->getExtension();
+		$newFileExtension = $ocrFile->getFileExtension();
+
+		if ($originalFileExtension === $newFileExtension) {
+			$this->createNewFileVersion($filePath, $fileContent, $nodeId);
+		} else {
+			$this->createNewFileVersion($filePath.".pdf", $fileContent, $nodeId);
+		}
 	}
 
 	private function getNode(string $filePath) : ?Node {
@@ -213,14 +222,6 @@ private function initUserEnvironment(string $uid) : void {
 		$this->filesystem->init($uid, '/' . $uid . '/files');
 	}
 
-	/**
-	 * @param File $file
-	 * @param WorkflowSettings $settings
-	 */
-	private function ocrFile(File $file, WorkflowSettings $settings) : string {
-		return $this->ocrService->ocrFile($file->getMimeType(), $file->getContent(), $settings);
-	}
-
 	private function shutdownUserEnvironment() : void {
 		$this->userSession->setUser(null);
 	}

diff --git a/lib/OcrProcessors/IOcrProcessor.php b/lib/OcrProcessors/IOcrProcessor.php
@@ -26,15 +26,16 @@
 use OCA\WorkflowOcr\Exception\OcrNotPossibleException;
 use OCA\WorkflowOcr\Model\GlobalSettings;
 use OCA\WorkflowOcr\Model\WorkflowSettings;
+use OCP\Files\File;
 
 interface IOcrProcessor {
 	/**
 	 * Processes OCR on the given file
-	 * @param string 			$fileContent  		The file to be processed
+	 * @param File 				$file  				The file to be processed
 	 * @param WorkflowSettings 	$settings 			The settings to be used for this specific workflow
 	 * @param GlobalSettings 	$globalSettings 	The global settings configured for all OCR workflows on this system
-	 * @return string   							The processed file as byte string
+	 * @return OcrProcessorResult
 	 * @throws OcrNotPossibleException
 	 */
-	public function ocrFile(string $fileContent, WorkflowSettings $settings, GlobalSettings $globalSettings) : string;
+	public function ocrFile(File $file, WorkflowSettings $settings, GlobalSettings $globalSettings) : OcrProcessorResult;
 }
diff --git a/lib/OcrProcessors/IOcrProcessorFactory.php b/lib/OcrProcessors/IOcrProcessorFactory.php
@@ -28,4 +28,11 @@ interface IOcrProcessorFactory {
 	 * Creates a IOcrProcessor object for the given mimetype
 	 */
 	public function create(string $mimeType) : IOcrProcessor;
+
+	/**
+	 * Returns true, if an OCR processor for the given mimetype
+	 * can be constructed.
+	 * @return bool
+	 */
+	public function canCreate(string $mimeType) : bool;
 }
diff --git a/lib/OcrProcessors/ImageOcrProcessor.php b/lib/OcrProcessors/ImageOcrProcessor.php
@@ -0,0 +1,33 @@
+<?php
+
+declare(strict_types=1);
+
+/**
+ * @copyright Copyright (c) 2022 Robin Windey <[email protected]>
+ *
+ *  @license GNU AGPL version 3 or any later version
+ *
+ * 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 <http://www.gnu.org/licenses/>.
+ */
+
+namespace OCA\WorkflowOcr\OcrProcessors;
+
+use OCA\WorkflowOcr\Model\WorkflowSettings;
+use OCA\WorkflowOcr\Model\GlobalSettings;
+
+class ImageOcrProcessor extends OcrMyPdfBasedProcessor {
+	protected function getAdditionalCommandlineArgs(WorkflowSettings $settings, GlobalSettings $globalSettings): string {
+		return '--image-dpi 300';
+	}
+}