Merge branch 'main' into main

.devcontainer/devcontainer.json

@@ -119,7 +119,9 @@
                 "EditorConfig.EditorConfig", // EditorConfig support for maintaining consistent coding styles
                 "ms-azuretools.vscode-docker", // Docker extension for Visual Studio Code
                 "charliermarsh.ruff", // Ruff extension for Ruff language support
-                "github.vscode-github-actions" // GitHub Actions extension for Visual Studio Code
+                "github.vscode-github-actions", // GitHub Actions extension for Visual Studio Code
+                "stylelint.vscode-stylelint", // Stylelint extension for CSS and SCSS linting
+                "redhat.vscode-yaml" // YAML extension for Visual Studio Code
             ]
         }
     },

.github/labeler-config-srvaroa.yml

@@ -2,37 +2,46 @@ version: 1
 labels:
 
   - label: "Bugfix"
-    title: '^fix:.*'
+    title: '^fix(\([^)]*\))?:|^fix:.*'
 
   - label: "enhancement"
-    title: '^feat:.*'
+    title: '^feat(\([^)]*\))?:|^feat:.*'
 
   - label: "build"
-    title: '^build:.*'
+    title: '^build(\([^)]*\))?:|^build:.*'
 
   - label: "chore"
-    title: '^chore:.*'
+    title: '^chore(\([^)]*\))?:|^chore:.*'
 
   - label: "ci"
-    title: '^ci:.*'
+    title: '^ci(\([^)]*\))?:|^ci:.*'
+
+  - label: "ci"
+    title: '^.*\(ci\):.*'
 
   - label: "perf"
-    title: '^perf:.*'
+    title: '^perf(\([^)]*\))?:|^perf:.*'
 
   - label: "refactor"
-    title: '^refactor:.*'
+    title: '^refactor(\([^)]*\))?:|^refactor:.*'
 
   - label: "revert"
-    title: '^revert:.*'
+    title: '^revert(\([^)]*\))?:|^revert:.*'
 
   - label: "style"
-    title: '^style:.*'
+    title: '^style(\([^)]*\))?:|^style:.*'
 
   - label: "Documentation"
-    title: '^docs:.*'
+    title: '^docs(\([^)]*\))?:|^docs:.*'
+
+  - label: "dependencies"
+    title: '^deps(\([^)]*\))?:|^deps:.*'
+
+  - label: "dependencies"
+    title: '^.*\(deps\):.*'
 
   - label: 'API'
-    title: '.*openapi.*'
+    title: '.*openapi.*|.*swagger.*|.*api.*'
 
   - label: 'Translation'
     files:
@@ -81,6 +90,7 @@ labels:
       - 'stirling-pdf/src/main/java/stirling/software/SPDF/controller/web/MetricsController.java'
       - 'stirling-pdf/src/main/java/stirling/software/SPDF/controller/api/.*'
       - 'stirling-pdf/src/main/java/stirling/software/SPDF/model/api/.*'
+      - 'stirling-pdf/src/main/java/stirling/software/SPDF/service/ApiDocService.java'  
       - 'proprietary/src/main/java/stirling/software/proprietary/security/controller/api/.*'
       - 'scripts/png_to_webp.py'
       - 'split_photos.py'
@@ -116,6 +126,7 @@ labels:
       - '.pre-commit-config'
       - '.github/workflows/pre_commit.yml'
       - 'devGuide/.*'
+      - 'devTools/.*'
 
   - label: 'Test'
     files:

.github/labels.yml

@@ -175,3 +175,6 @@
   description: "This PR changes 1000+ lines ignoring generated files."
 - name: "to research"
   color: "FBCA04"
+- name: "pr-deployed"
+  color: "00FF00"
+  description: "Pull request has been deployed to a test environment"

.github/workflows/PR-Demo-Comment-with-react.yml

@@ -6,15 +6,13 @@ on:
 
 permissions:
   contents: read
-  issues: write      # Required for adding reactions to comments
+  pull-requests: read
-  pull-requests: read # Required for reading PR information
 
 jobs:
   check-comment:
     runs-on: ubuntu-latest
     permissions:
       issues: write
-      pull-requests: read
     if: |
       github.event.issue.pull_request &&
       (
@@ -47,10 +45,14 @@ jobs:
         with:
           egress-policy: audit
 
-      # Generate GitHub App token
+      - name: Checkout PR
-      - name: Generate GitHub App Token
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
-        id: generate-token
+
-        uses: actions/create-github-app-token@df432ceedc7162793a195dd1713ff69aefc7379e # v2.0.6
+      - name: Setup GitHub App Bot
+        if: github.actor != 'dependabot[bot]'
+        id: setup-bot
+        uses: ./.github/actions/setup-bot
+        continue-on-error: true
         with:
           app-id: ${{ secrets.GH_APP_ID }}
           private-key: ${{ secrets.GH_APP_PRIVATE_KEY }}
@@ -123,7 +125,7 @@ jobs:
         id: add-eyes-reaction
         uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea # v7.0.1
         with:
-          github-token: ${{ steps.generate-token.outputs.token }}
+          github-token: ${{ steps.setup-bot.outputs.token }}
           script: |
             console.log(`Adding eyes reaction to comment ID: ${context.payload.comment.id}`);
             try {
@@ -145,8 +147,8 @@ jobs:
     needs: check-comment
     runs-on: ubuntu-latest
     permissions:
-      contents: read
       issues: write
+      pull-requests: write
 
     steps:
       - name: Harden Runner
@@ -154,9 +156,14 @@ jobs:
         with:
           egress-policy: audit
 
-      - name: Generate GitHub App Token
+      - name: Checkout PR
-        id: generate-token
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
-        uses: actions/create-github-app-token@df432ceedc7162793a195dd1713ff69aefc7379e # v2.0.6
+
+      - name: Setup GitHub App Bot
+        if: github.actor != 'dependabot[bot]'
+        id: setup-bot
+        uses: ./.github/actions/setup-bot
+        continue-on-error: true
         with:
           app-id: ${{ secrets.GH_APP_ID }}
           private-key: ${{ secrets.GH_APP_PRIVATE_KEY }}
@@ -166,7 +173,7 @@ jobs:
         with:
           repository: ${{ needs.check-comment.outputs.pr_repository }}
           ref: ${{ needs.check-comment.outputs.pr_ref }}
-          token: ${{ secrets.GITHUB_TOKEN }}
+          token: ${{ steps.setup-bot.outputs.token }}
 
       - name: Set up JDK
         uses: actions/setup-java@c5195efecf7bdfc987ee8bae7a71cb8b11521c00 # v4.7.1
@@ -188,12 +195,6 @@ jobs:
       - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@e468171a9de216ec08956ac3ada2f0791b6bd435 # v3.11.1
 
-      - name: Get version number
-        id: versionNumber
-        run: |
-          VERSION=$(grep "^version =" build.gradle | awk -F'"' '{print $2}')
-          echo "versionNumber=$VERSION" >> $GITHUB_OUTPUT
-
       - name: Login to Docker Hub
         uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
         with:
@@ -297,7 +298,7 @@ jobs:
         if: success()
         uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea # v7.0.1
         with:
-          github-token: ${{ steps.generate-token.outputs.token }}
+          github-token: ${{ steps.setup-bot.outputs.token }}
           script: |
             console.log(`Adding rocket reaction to comment ID: ${{ needs.check-comment.outputs.comment_id }}`);
             try {
@@ -313,11 +314,26 @@ jobs:
               console.error(error);
             }
 
+            // add label to PR
+            const prNumber = ${{ needs.check-comment.outputs.pr_number }};
+            try {
+              await github.rest.issues.addLabels({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                issue_number: prNumber,
+                labels: ['pr-deployed']
+              });
+              console.log(`Added 'pr-deployed' label to PR #${prNumber}`);
+            } catch (error) {
+              console.error(`Failed to add label to PR: ${error.message}`);
+              console.error(error);
+            }
+
       - name: Add failure reaction to comment
         if: failure()
         uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea # v7.0.1
         with:
-          github-token: ${{ steps.generate-token.outputs.token }}
+          github-token: ${{ steps.setup-bot.outputs.token }}
           script: |
             console.log(`Adding -1 reaction to comment ID: ${{ needs.check-comment.outputs.comment_id }}`);
             try {
@@ -337,7 +353,7 @@ jobs:
         if: success()
         uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea # v7.0.1
         with:
-          github-token: ${{ steps.generate-token.outputs.token }}
+          github-token: ${{ steps.setup-bot.outputs.token }}
           script: |
             const { GITHUB_REPOSITORY } = process.env;
             const [repoOwner, repoName] = GITHUB_REPOSITORY.split('/');
@@ -357,3 +373,11 @@ jobs:
               issue_number: prNumber,
               body: commentBody
             });
+
+      - name: Cleanup temporary files
+        if: always()
+        run: |
+          echo "Cleaning up temporary files..."
+          rm -f ../private.key docker-compose.yml
+          echo "Cleanup complete."
+        continue-on-error: true

.github/workflows/PR-Demo-cleanup.yml

@@ -1,7 +1,7 @@
 name: PR Deployment cleanup
 
 on:
-  pull_request:
+  pull_request_target:
     types: [opened, synchronize, reopened, closed]
 
 permissions:
@@ -13,11 +13,11 @@ env:
 
 jobs:
   cleanup:
+    if: github.event.action == 'closed'
     runs-on: ubuntu-latest
     permissions:
-      contents: write
       pull-requests: write
-    if: github.event.action == 'closed'
+      issues: write
 
     steps:
       - name: Harden Runner
@@ -25,13 +25,84 @@ jobs:
         with:
           egress-policy: audit
 
+      - name: Checkout PR
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+
+      - name: Setup GitHub App Bot
+        if: github.actor != 'dependabot[bot]'
+        id: setup-bot
+        uses: ./.github/actions/setup-bot
+        continue-on-error: true
+        with:
+          app-id: ${{ secrets.GH_APP_ID }}
+          private-key: ${{ secrets.GH_APP_PRIVATE_KEY }}
+
+      - name: Remove 'pr-deployed' label if present
+        id: remove-label-comment
+        uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea # v7.0.1
+        with:
+          github-token: ${{ steps.setup-bot.outputs.token }}
+          script: |
+            const prNumber = ${{ github.event.pull_request.number }};
+            const owner = context.repo.owner;
+            const repo = context.repo.repo;
+
+            // Hole alle Labels auf dem PR
+            const { data: labels } = await github.rest.issues.listLabelsOnIssue({
+              owner,
+              repo,
+              issue_number: prNumber
+            });
+
+            const hasLabel = labels.some(label => label.name === 'pr-deployed');
+
+            if (hasLabel) {
+              console.log("Label 'pr-deployed' found. Removing...");
+              await github.rest.issues.removeLabel({
+                owner,
+                repo,
+                issue_number: prNumber,
+                name: 'pr-deployed'
+              });
+            } else {
+              console.log("Label 'pr-deployed' not found. Nothing to do.");
+            }
+
+            // Find existing comment
+            const comments = await github.rest.issues.listComments({
+              owner,
+              repo,
+              issue_number: prNumber
+            });
+
+            const deploymentComments = comments.data.filter(c =>
+              c.body?.includes("## 🚀 PR Test Deployment") &&
+              c.user?.type === "Bot"
+            );
+
+            if (deploymentComments.length > 0) {
+              for (const comment of deploymentComments) {
+                await github.rest.issues.deleteComment({
+                  owner,
+                  repo,
+                  comment_id: comment.id
+                });
+                console.log(`Deleted deployment comment (ID: ${comment.id})`);
+              }
+            } else {
+              console.log("No matching deployment comments found.");
+            }
+            core.setOutput('present', hasLabel || deploymentComment ? 'true' : 'false');
+
       - name: Set up SSH
+        if: steps.remove-label-comment.outputs.present == 'true'
         run: |
           mkdir -p ~/.ssh/
           echo "${{ secrets.VPS_SSH_KEY }}" > ../private.key
           sudo chmod 600 ../private.key
 
       - name: Cleanup PR deployment
+        if: steps.remove-label-comment.outputs.present == 'true'
         id: cleanup
         run: |
           ssh -i ../private.key -o StrictHostKeyChecking=no -o UserKnownHostsFile=/dev/null -T ${{ secrets.VPS_USERNAME }}@${{ secrets.VPS_HOST }} << 'ENDSSH'
@@ -57,3 +128,11 @@ jobs:
               echo "NO_CLEANUP_NEEDED"
             fi
           ENDSSH
+
+      - name: Cleanup temporary files
+        if: always()
+        run: |
+          echo "Cleaning up temporary files..."
+          rm -f ../private.key
+          echo "Cleanup complete."
+        continue-on-error: true

.github/workflows/swagger.yml

@@ -29,7 +29,7 @@ jobs:
       - uses: gradle/actions/setup-gradle@ac638b010cf58a27ee6c972d7336334ccaf61c96 # v4.4.1
 
       - name: Generate Swagger documentation
-        run: ./gradlew generateOpenApiDocs
+        run: ./gradlew :stirling-pdf:generateOpenApiDocs
 
       - name: Upload Swagger Documentation to SwaggerHub
         run: ./gradlew swaggerhubUpload

.vscode/extensions.json

@@ -17,5 +17,7 @@
     "GitHub.vscode-pull-request-github", // GitHub Pull Requests extension for Visual Studio Code
     "charliermarsh.ruff", // Ruff code formatter for Python to follow the Ruff Style Guide
     "yzhang.markdown-all-in-one", // Markdown All-in-One extension for enhanced Markdown editing
+    "stylelint.vscode-stylelint", // Stylelint extension for CSS and SCSS linting
+    "redhat.vscode-yaml", // YAML extension for Visual Studio Code
   ]
 }

.vscode/settings.json

@@ -9,6 +9,9 @@
   "[jsonc]": {
     "editor.defaultFormatter": "vscode.json-language-features"
   },
+  "[css]": {
+    "editor.defaultFormatter": "stylelint.vscode-stylelint"
+  },
   "[json]": {
     "editor.defaultFormatter": "vscode.json-language-features"
   },
@@ -27,6 +30,9 @@
   "[gradle]": {
     "editor.defaultFormatter": "vscjava.vscode-gradle"
   },
+  "[yaml]": {
+    "editor.defaultFormatter": "redhat.vscode-yaml"
+  },
   "java.compile.nullAnalysis.mode": "automatic",
   "java.configuration.updateBuildConfiguration": "interactive",
   "java.format.enabled": true,
@@ -119,6 +125,7 @@
   "html.format.indentHandlebars": true,
   "html.format.preserveNewLines": true,
   "html.format.maxPreserveNewLines": 2,
+  "stylelint.configFile": "devTools/.stylelintrc.json",
   "java.project.sourcePaths": [
     "stirling-pdf/src/main/java",
     "common/src/main/java",

README.md

@@ -135,7 +135,7 @@ Stirling-PDF currently supports 40 languages!
 | Indonesian (Bahasa Indonesia) (id_ID)        | ![63%](https://geps.dev/progress/63)   |
 | Irish (Gaeilge) (ga_IE)                      | ![70%](https://geps.dev/progress/70)   |
 | Italian (Italiano) (it_IT)                   | ![98%](https://geps.dev/progress/98)   |
-| Japanese (日本語) (ja_JP)                    | ![70%](https://geps.dev/progress/70)   |
+| Japanese (日本語) (ja_JP)                    | ![95%](https://geps.dev/progress/95)   |
 | Korean (한국어) (ko_KR)                      | ![69%](https://geps.dev/progress/69)   |
 | Norwegian (Norsk) (no_NB)                    | ![67%](https://geps.dev/progress/67)   |
 | Persian (فارسی) (fa_IR)                      | ![66%](https://geps.dev/progress/66)   |
@@ -145,7 +145,7 @@ Stirling-PDF currently supports 40 languages!
 | Romanian (Română) (ro_RO)                    | ![59%](https://geps.dev/progress/59)   |
 | Russian (Русский) (ru_RU)                    | ![70%](https://geps.dev/progress/70)   |
 | Serbian Latin alphabet (Srpski) (sr_LATN_RS) | ![97%](https://geps.dev/progress/97)   |
-| Simplified Chinese (简体中文) (zh_CN)         | ![90%](https://geps.dev/progress/90)   |
+| Simplified Chinese (简体中文) (zh_CN)         | ![95%](https://geps.dev/progress/95)   |
 | Slovakian (Slovensky) (sk_SK)                | ![53%](https://geps.dev/progress/53)   |
 | Slovenian (Slovenščina) (sl_SI)              | ![73%](https://geps.dev/progress/73)   |
 | Spanish (Español) (es_ES)                    | ![75%](https://geps.dev/progress/75)   |

build.gradle

@@ -6,7 +6,7 @@ plugins {
     id "org.springdoc.openapi-gradle-plugin" version "1.9.0"
     id "io.swagger.swaggerhub" version "1.3.2"
     id "edu.sc.seis.launch4j" version "3.0.6"
-    id "com.diffplug.spotless" version "7.0.4"
+    id "com.diffplug.spotless" version "7.1.0"
     id "com.github.jk1.dependency-license-report" version "2.9"
     //id "nebula.lint" version "19.0.3"
     id "org.panteleyev.jpackageplugin" version "1.7.3"
@@ -161,6 +161,44 @@ subprojects {
 	tasks.named("processResources") {
 	  dependsOn(rootProject.tasks.writeVersion)
 	}
+
+    if (name == 'stirling-pdf') {
+        apply plugin: 'org.springdoc.openapi-gradle-plugin'
+
+        openApi {
+            apiDocsUrl = "http://localhost:8080/v1/api-docs"
+            outputDir = file("$projectDir")
+            outputFileName = "SwaggerDoc.json"
+            waitTimeInSeconds = 60 // Increase the wait time to 60 seconds
+        }
+
+        tasks.named("forkedSpringBootRun") {
+            dependsOn(":common:jar")
+            dependsOn(":proprietary:jar")
+        }
+
+        tasks.register("copySwaggerDoc", Copy) {
+            doNotTrackState("Writes SwaggerDoc.json to project root")
+            from(layout.projectDirectory.file("SwaggerDoc.json"))
+            into(rootProject.projectDir)
+            dependsOn("generateOpenApiDocs")
+        }
+
+        tasks.register("cleanSwaggerInBuild", Delete) {
+            doNotTrackState("Cleans up SwaggerDoc.json in build directory")
+            delete(layout.projectDirectory.file("SwaggerDoc.json"))
+            dependsOn("copySwaggerDoc")
+        }
+
+        tasks.named("copySwaggerDoc") {
+            finalizedBy("cleanSwaggerInBuild")
+        }
+
+        tasks.named("generateOpenApiDocs") {
+            finalizedBy("copySwaggerDoc")
+            doNotTrackState("OpenAPI plugin writes outside build directory")
+        }
+    }
 }
 
 tasks.withType(JavaCompile).configureEach {
@@ -169,6 +207,7 @@ tasks.withType(JavaCompile).configureEach {
 }
 
 licenseReport {
+    projects = [project]
     renderers = [new JsonReportRenderer()]
     allowedLicensesFile = new File("$projectDir/allowed-licenses.json")
 }
@@ -204,13 +243,6 @@ sourceSets {
     }
 }
 
-openApi {
-    apiDocsUrl = "http://localhost:8080/v1/api-docs"
-    outputDir = file("$projectDir")
-    outputFileName = "SwaggerDoc.json"
-    waitTimeInSeconds = 60 // Increase the wait time to 60 seconds
-}
-
 // Configure the forked spring boot run task to properly delegate to the stirling-pdf module
 tasks.named('forkedSpringBootRun') {
     dependsOn ':stirling-pdf:bootRun'
@@ -565,9 +597,6 @@ tasks.register('printMacVersion') {
     }
 }
 
-tasks.named('generateOpenApiDocs') {
-    doNotTrackState("Tracking state is not supported for this task")
-}
 tasks.named('bootRun') {
     group = 'application'
     description = 'Delegates to :stirling-pdf:bootRun'

common/build.gradle

@@ -21,7 +21,7 @@ dependencies {
     api 'com.googlecode.owasp-java-html-sanitizer:owasp-java-html-sanitizer:20240325.1'
     api 'com.fathzer:javaluator:3.0.6'
     api 'com.posthog.java:posthog:1.2.0'
-    api 'org.apache.commons:commons-lang3:3.17.0'
+    api 'org.apache.commons:commons-lang3:3.18.0'
     api 'com.drewnoakes:metadata-extractor:2.19.0' // Image metadata extractor
     api 'com.vladsch.flexmark:flexmark-html2md-converter:0.64.8'
     api "org.apache.pdfbox:pdfbox:$pdfboxVersion"

common/src/main/java/stirling/software/common/aop/AutoJobAspect.java

@@ -43,6 +43,7 @@ public class AutoJobAspect {
         // This aspect will run before any audit aspects due to @Order(0)
         // Extract parameters from the request and annotation
         boolean async = Boolean.parseBoolean(request.getParameter("async"));
+        log.debug("AutoJobAspect: Processing {} {} with async={}", request.getMethod(), request.getRequestURI(), async);
         long timeout = autoJobPostMapping.timeout();
         int retryCount = autoJobPostMapping.retryCount();
         boolean trackProgress = autoJobPostMapping.trackProgress();
@@ -54,19 +55,8 @@ public class AutoJobAspect {
                 retryCount,
                 trackProgress);
 
-        // Copy and process arguments
+        // Process arguments in-place to avoid type mismatch issues
-        // In a test environment, we might need to update the original objects for verification
+        Object[] args = processArgsInPlace(joinPoint.getArgs(), async);
-        boolean isTestEnvironment = false;
-        try {
-            isTestEnvironment = Class.forName("org.junit.jupiter.api.Test") != null;
-        } catch (ClassNotFoundException e) {
-            // Not in a test environment
-        }
-
-        Object[] args =
-                isTestEnvironment
-                        ? processArgsInPlace(joinPoint.getArgs(), async)
-                        : copyAndProcessArgs(joinPoint.getArgs(), async);
 
         // Extract queueable and resourceWeight parameters and validate
         boolean queueable = autoJobPostMapping.queueable();
@@ -229,79 +219,10 @@ public class AutoJobAspect {
                 resourceWeight);
     }
 
-    /**
-     * Creates deep copies of arguments when needed to avoid mutating the original objects
-     * Particularly important for PDFFile objects that might be reused by Spring
-     *
-     * @param originalArgs The original arguments
-     * @param async Whether this is an async operation
-     * @return A new array with safely processed arguments
-     */
-    private Object[] copyAndProcessArgs(Object[] originalArgs, boolean async) {
-        if (originalArgs == null || originalArgs.length == 0) {
-            return originalArgs;
-        }
-
-        Object[] processedArgs = new Object[originalArgs.length];
-
-        // Copy all arguments
-        for (int i = 0; i < originalArgs.length; i++) {
-            Object arg = originalArgs[i];
-
-            if (arg instanceof PDFFile pdfFile) {
-                // Create a copy of PDFFile to avoid mutating the original
-                // Using direct property access instead of reflection for better performance
-                PDFFile pdfFileCopy = new PDFFile();
-                pdfFileCopy.setFileId(pdfFile.getFileId());
-                pdfFileCopy.setFileInput(pdfFile.getFileInput());
-
-                // Case 1: fileId is provided but no fileInput
-                if (pdfFileCopy.getFileInput() == null && pdfFileCopy.getFileId() != null) {
-                    try {
-                        log.debug("Using fileId {} to get file content", pdfFileCopy.getFileId());
-                        MultipartFile file = fileStorage.retrieveFile(pdfFileCopy.getFileId());
-                        pdfFileCopy.setFileInput(file);
-                    } catch (Exception e) {
-                        throw new RuntimeException(
-                                "Failed to resolve file by ID: " + pdfFileCopy.getFileId(), e);
-                    }
-                }
-                // Case 2: For async requests, we need to make a copy of the MultipartFile
-                else if (async && pdfFileCopy.getFileInput() != null) {
-                    try {
-                        log.debug("Making persistent copy of uploaded file for async processing");
-                        MultipartFile originalFile = pdfFileCopy.getFileInput();
-                        String fileId = fileStorage.storeFile(originalFile);
-
-                        // Store the fileId for later reference
-                        pdfFileCopy.setFileId(fileId);
-
-                        // Replace the original MultipartFile with our persistent copy
-                        MultipartFile persistentFile = fileStorage.retrieveFile(fileId);
-                        pdfFileCopy.setFileInput(persistentFile);
-
-                        log.debug("Created persistent file copy with fileId: {}", fileId);
-                    } catch (IOException e) {
-                        throw new RuntimeException(
-                                "Failed to create persistent copy of uploaded file", e);
-                    }
-                }
-
-                processedArgs[i] = pdfFileCopy;
-            } else {
-                // For non-PDFFile objects, just pass the original reference
-                // If other classes need copy-on-write, add them here
-                processedArgs[i] = arg;
-            }
-        }
-
-        return processedArgs;
-    }
 
     /**
-     * Processes arguments in-place for testing purposes This is similar to our original
+     * Processes arguments in-place to handle file resolution and async file persistence.
-     * implementation before introducing copy-on-write It's only used in test environments to
+     * This approach avoids type mismatch issues by modifying the original objects directly.
-     * maintain test compatibility
      *
      * @param originalArgs The original arguments
      * @param async Whether this is an async operation

common/src/main/java/stirling/software/common/model/job/JobResult.java

@@ -6,6 +6,8 @@ import java.util.Collections;
 import java.util.List;
 import java.util.concurrent.CopyOnWriteArrayList;
 
+import com.fasterxml.jackson.annotation.JsonIgnore;
+
 import lombok.AllArgsConstructor;
 import lombok.Builder;
 import lombok.Data;
@@ -28,6 +30,7 @@ public class JobResult {
     private String error;
 
     /** List of result files for jobs that produce files */
+    @JsonIgnore
     private List<ResultFile> resultFiles;
 
     /** Time when the job was created */

common/src/main/java/stirling/software/common/service/TaskManager.java

@@ -1,6 +1,5 @@
 package stirling.software.common.service;
 
-import io.github.pixee.security.ZipSecurity;
 import java.io.ByteArrayInputStream;
 import java.io.ByteArrayOutputStream;
 import java.io.IOException;
@@ -21,6 +20,8 @@ import org.springframework.http.MediaType;
 import org.springframework.stereotype.Service;
 import org.springframework.web.multipart.MultipartFile;
 
+import io.github.pixee.security.ZipSecurity;
+
 import jakarta.annotation.PreDestroy;
 
 import lombok.extern.slf4j.Slf4j;
@@ -361,7 +362,8 @@ public class TaskManager {
         MultipartFile zipFile = fileStorage.retrieveFile(zipFileId);
 
         try (ZipInputStream zipIn =
-                ZipSecurity.createHardenedInputStream(new ByteArrayInputStream(zipFile.getBytes()))) {
+                ZipSecurity.createHardenedInputStream(
+                        new ByteArrayInputStream(zipFile.getBytes()))) {
             ZipEntry entry;
             while ((entry = zipIn.getNextEntry()) != null) {
                 if (!entry.isDirectory()) {

devGuide/STYLELINT.md

@@ -0,0 +1,47 @@
+# STYLELINT.md
+
+## Usage
+
+Apply Stylelint to your project's CSS with the following steps:
+
+1. **NPM Script**
+
+   - Go to directory: `devTools/`
+
+   - Add Stylelint & stylistic/stylelint-plugin
+     ```bash
+     npm install --save-dev stylelint stylelint-config-standard
+     npm install --save-dev @stylistic/stylelint-plugin
+     ```
+   - Add a script entry to your `package.json`:
+     ```jsonc
+     {
+       "scripts": {
+          "lint:css:check": "stylelint \"../stirling-pdf/src/main/**/*.css\" \"../proprietary/src/main/resources/static/css/*.css\" --config .stylelintrc.json",
+          "lint:css:fix": "stylelint \"../stirling-pdf/src/main/**/*.css\" \"../proprietary/src/main/resources/static/css/*.css\" --config .stylelintrc.json --fix"
+       }
+     }
+     ```
+   - Run the linter:
+     ```bash
+     npm run lint:css:check
+     npm run lint:css:fix
+     ```
+
+2. **CLI Usage**
+
+   - Lint all CSS files:
+     ```bash
+     npx stylelint ../stirling-pdf/src/main/**/*.css ../proprietary/src/main/resources/static/css/*.css
+     ```
+   - Lint a single file:
+     ```bash
+     npx stylelint ../proprietary/src/main/resources/static/css/audit-dashboard.css
+     ```
+   - Apply automatic fixes:
+     ```bash
+     npx stylelint "../stirling-pdf/src/main/**/*.css" "../proprietary/src/main/resources/static/css/*.css" --fix
+     ```
+
+For full configuration options and rule customization, refer to the official documentation: [https://stylelint.io](https://stylelint.io)
+

devTools/.stylelintrc.json

@@ -0,0 +1,69 @@
+{
+  "extends": [
+    "stylelint-config-standard"
+  ],
+  "plugins": [
+    "@stylistic/stylelint-plugin"
+  ],
+  "ignoreFiles": [
+    "stirling-pdf/src/main/resources/static/css/bootstrap*.css",
+    "stirling-pdf/src/main/resources/static/css/cookieconsent.css",
+    "stirling-pdf/src/main/resources/static/css/cookieconsentCustomisation.css",
+    "stirling-pdf/src/main/resources/static/css/prism.css",
+    "stirling-pdf/src/main/resources/static/pdfjs-legacy/**/*.css"
+  ],
+  "rules": {
+    "property-no-vendor-prefix": null,
+    "value-no-vendor-prefix": null,
+    "selector-no-vendor-prefix": null,
+    "media-feature-name-no-vendor-prefix": null,
+    "value-keyword-case": null,
+    "color-function-notation": null,
+    "alpha-value-notation": null,
+    "color-function-alias-notation": null,
+    "selector-class-pattern": null,
+    "selector-id-pattern": null,
+    "declaration-block-no-redundant-longhand-properties": null,
+    "media-feature-range-notation": "prefix",
+    "selector-attribute-quotes": null,
+    "at-rule-no-vendor-prefix": null,
+    "selector-not-notation": null,
+    "no-duplicate-selectors": [
+      true,
+      {
+        "disableFix": true
+      }
+    ],
+    "comment-word-disallowed-list": null,
+    "custom-property-pattern": null,
+    "no-descending-specificity": null,
+    "keyframes-name-pattern": null,
+    "comment-empty-line-before": [
+      "always",
+      {
+        "ignore": [
+          "stylelint-commands"
+        ]
+      }
+    ],
+    "block-no-empty": true,
+    "@stylistic/declaration-bang-space-after": "never",
+    "@stylistic/declaration-bang-space-before": "always",
+    "@stylistic/declaration-block-trailing-semicolon": "always",
+    "@stylistic/function-comma-space-after": [
+      "always-single-line",
+      {
+        "disableFix": false
+      }
+    ],
+    "@stylistic/function-comma-space-before": "never",
+    "@stylistic/color-hex-case": "lower",
+    "@stylistic/declaration-block-semicolon-newline-after": "always",
+    "@stylistic/indentation": [
+      2,
+      {
+        "baseIndentLevel": 2
+      }
+    ]
+  }
+}

devTools/package.json

@@ -0,0 +1,13 @@
+{
+  "name": "stirling-pdf",
+  "version": "1.0.0",
+  "scripts": {
+    "lint:css:check": "stylelint \"../stirling-pdf/src/main/**/*.css\" \"../proprietary/src/main/resources/static/css/*.css\" --config .stylelintrc.json",
+    "lint:css:fix": "stylelint \"../stirling-pdf/src/main/**/*.css\" \"../proprietary/src/main/resources/static/css/*.css\" --config .stylelintrc.json --fix"
+  },
+  "devDependencies": {
+    "@stylistic/stylelint-plugin": "^3.1.3",
+    "stylelint": "^16.21.1",
+    "stylelint-config-standard": "^38.0.0"
+  }
+}

proprietary/build.gradle

@@ -37,7 +37,7 @@ dependencies {
 
     implementation 'org.thymeleaf.extras:thymeleaf-extras-springsecurity5:3.1.3.RELEASE'
     api 'io.micrometer:micrometer-registry-prometheus'
-    implementation 'com.unboundid.product.scim2:scim2-sdk-client:2.3.5'
+    implementation 'com.unboundid.product.scim2:scim2-sdk-client:4.0.0'
     runtimeOnly 'com.h2database:h2:2.3.232' // Don't upgrade h2database
     runtimeOnly 'org.postgresql:postgresql:42.7.7'
     constraints {

scripts/ignore_translation.toml

@@ -529,7 +529,6 @@ ignore = [
 
 [ja_JP]
 ignore = [
-    'lang.jav',
     'language.direction',
 ]
 

stirling-pdf/src/main/java/stirling/software/SPDF/config/CleanUrlInterceptor.java

@@ -29,7 +29,8 @@ public class CleanUrlInterceptor implements HandlerInterceptor {
                     "type",
                     "principal",
                     "startDate",
-                    "endDate");
+                    "endDate",
+                    "async");
 
     @Override
     public boolean preHandle(

stirling-pdf/src/main/resources/static/3rdPartyLicenses.json

@@ -165,12 +165,6 @@
             "moduleLicense": "Apache-2.0",
             "moduleLicenseUrl": "https://www.apache.org/licenses/LICENSE-2.0.txt"
         },
-        {
-            "moduleName": "com.google.errorprone:error_prone_annotations",
-            "moduleVersion": "2.11.0",
-            "moduleLicense": "Apache 2.0",
-            "moduleLicenseUrl": "http://www.apache.org/licenses/LICENSE-2.0.txt"
-        },
         {
             "moduleName": "com.google.errorprone:error_prone_annotations",
             "moduleUrl": "https://errorprone.info/error_prone_annotations",
@@ -639,13 +633,6 @@
             "moduleLicense": "Apache License, Version 2.0",
             "moduleLicenseUrl": "https://www.apache.org/licenses/LICENSE-2.0.txt"
         },
-        {
-            "moduleName": "io.swagger.core.v3:swagger-annotations-jakarta",
-            "moduleUrl": "https://github.com/swagger-api/swagger-core/modules/swagger-annotations",
-            "moduleVersion": "2.2.30",
-            "moduleLicense": "Apache License, Version 2.0",
-            "moduleLicenseUrl": "https://www.apache.org/licenses/LICENSE-2.0"
-        },
         {
             "moduleName": "io.swagger.core.v3:swagger-annotations-jakarta",
             "moduleUrl": "https://github.com/swagger-api/swagger-core/modules/swagger-annotations",
@@ -653,13 +640,6 @@
             "moduleLicense": "Apache License, Version 2.0",
             "moduleLicenseUrl": "https://www.apache.org/licenses/LICENSE-2.0"
         },
-        {
-            "moduleName": "io.swagger.core.v3:swagger-core-jakarta",
-            "moduleUrl": "https://github.com/swagger-api/swagger-core/modules/swagger-core",
-            "moduleVersion": "2.2.30",
-            "moduleLicense": "Apache License, Version 2.0",
-            "moduleLicenseUrl": "https://www.apache.org/licenses/LICENSE-2.0"
-        },
         {
             "moduleName": "io.swagger.core.v3:swagger-core-jakarta",
             "moduleUrl": "https://github.com/swagger-api/swagger-core/modules/swagger-core",
@@ -667,13 +647,6 @@
             "moduleLicense": "Apache License, Version 2.0",
             "moduleLicenseUrl": "https://www.apache.org/licenses/LICENSE-2.0"
         },
-        {
-            "moduleName": "io.swagger.core.v3:swagger-models-jakarta",
-            "moduleUrl": "https://github.com/swagger-api/swagger-core/modules/swagger-models",
-            "moduleVersion": "2.2.30",
-            "moduleLicense": "Apache License, Version 2.0",
-            "moduleLicenseUrl": "https://www.apache.org/licenses/LICENSE-2.0"
-        },
         {
             "moduleName": "io.swagger.core.v3:swagger-models-jakarta",
             "moduleUrl": "https://github.com/swagger-api/swagger-core/modules/swagger-models",
@@ -744,13 +717,6 @@
             "moduleLicense": "GPL2 w/ CPE",
             "moduleLicenseUrl": "https://www.gnu.org/software/classpath/license.html"
         },
-        {
-            "moduleName": "jakarta.servlet:jakarta.servlet-api",
-            "moduleUrl": "https://www.eclipse.org",
-            "moduleVersion": "6.1.0",
-            "moduleLicense": "GPL2 w/ CPE",
-            "moduleLicenseUrl": "https://www.gnu.org/software/classpath/license.html"
-        },
         {
             "moduleName": "jakarta.transaction:jakarta.transaction-api",
             "moduleUrl": "https://projects.eclipse.org/projects/ee4j.jta",
@@ -889,13 +855,6 @@
             "moduleLicense": "Apache-2.0",
             "moduleLicenseUrl": "https://www.apache.org/licenses/LICENSE-2.0.txt"
         },
-        {
-            "moduleName": "org.apache.commons:commons-text",
-            "moduleUrl": "https://commons.apache.org/proper/commons-text",
-            "moduleVersion": "1.10.0",
-            "moduleLicense": "Apache License, Version 2.0",
-            "moduleLicenseUrl": "https://www.apache.org/licenses/LICENSE-2.0.txt"
-        },
         {
             "moduleName": "org.apache.commons:commons-text",
             "moduleUrl": "https://commons.apache.org/proper/commons-text",
@@ -1018,13 +977,6 @@
             "moduleLicense": "The Apache Software License, Version 2.0",
             "moduleLicenseUrl": "https://www.apache.org/licenses/LICENSE-2.0.txt"
         },
-        {
-            "moduleName": "org.bouncycastle:bcpkix-jdk18on",
-            "moduleUrl": "https://www.bouncycastle.org/java.html",
-            "moduleVersion": "1.72",
-            "moduleLicense": "Bouncy Castle Licence",
-            "moduleLicenseUrl": "https://www.bouncycastle.org/licence.html"
-        },
         {
             "moduleName": "org.bouncycastle:bcpkix-jdk18on",
             "moduleUrl": "https://www.bouncycastle.org/download/bouncy-castle-java/",
@@ -1039,13 +991,6 @@
             "moduleLicense": "Bouncy Castle Licence",
             "moduleLicenseUrl": "https://www.bouncycastle.org/licence.html"
         },
-        {
-            "moduleName": "org.bouncycastle:bcutil-jdk18on",
-            "moduleUrl": "https://www.bouncycastle.org/java.html",
-            "moduleVersion": "1.72",
-            "moduleLicense": "Bouncy Castle Licence",
-            "moduleLicenseUrl": "https://www.bouncycastle.org/licence.html"
-        },
         {
             "moduleName": "org.bouncycastle:bcutil-jdk18on",
             "moduleUrl": "https://www.bouncycastle.org/download/bouncy-castle-java/",
@@ -1562,13 +1507,6 @@
             "moduleLicense": "Apache License, Version 2.0",
             "moduleLicenseUrl": "https://www.apache.org/licenses/LICENSE-2.0"
         },
-        {
-            "moduleName": "org.springframework.boot:spring-boot-devtools",
-            "moduleUrl": "https://spring.io/projects/spring-boot",
-            "moduleVersion": "3.5.3",
-            "moduleLicense": "Apache License, Version 2.0",
-            "moduleLicenseUrl": "https://www.apache.org/licenses/LICENSE-2.0"
-        },
         {
             "moduleName": "org.springframework.boot:spring-boot-starter",
             "moduleUrl": "https://spring.io/projects/spring-boot",

testing/allEndpointsRemovedSettings.yml

@@ -65,17 +65,23 @@ premium:
   key: 00000000-0000-0000-0000-000000000000
   enabled: false # Enable license key checks for pro/enterprise features
   proFeatures:
+    database: true # Enable database features
     SSOAutoLogin: false
     CustomMetadata:
-      autoUpdateMetadata: false # set to 'true' to automatically update metadata with below values
+      autoUpdateMetadata: false
-      author: username # supports text such as 'John Doe' or types such as username to autopopulate with user's username
+      author: username
-      creator: Stirling-PDF # supports text such as 'Company-PDF'
+      creator: Stirling-PDF
-      producer: Stirling-PDF # supports text such as 'Company-PDF'
+      producer: Stirling-PDF
     googleDrive:
       enabled: false
       clientId: ''
       apiKey: ''
       appId: ''
+  enterpriseFeatures:
+    audit:
+      enabled: true # Enable audit logging
+      level: 2 # Audit logging level: 0=OFF, 1=BASIC, 2=STANDARD, 3=VERBOSE
+      retentionDays: 90 # Number of days to retain audit logs
 
 mail:
   enabled: false # set to 'true' to enable sending emails
@@ -86,7 +92,7 @@ mail:
   from: '' # sender email address
 
 legal:
-  termsAndConditions: https://www.stirlingpdf.com/terms # URL to the terms and conditions of your application (e.g. https://example.com/terms). Empty string to disable or filename to load from local file in static folder
+  termsAndConditions: https://www.stirlingpdf.com/terms-and-conditions # URL to the terms and conditions of your application (e.g. https://example.com/terms). Empty string to disable or filename to load from local file in static folder
   privacyPolicy: https://www.stirlingpdf.com/privacy-policy # URL to the privacy policy of your application (e.g. https://example.com/privacy). Empty string to disable or filename to load from local file in static folder
   accessibilityStatement: '' # URL to the accessibility statement of your application (e.g. https://example.com/accessibility). Empty string to disable or filename to load from local file in static folder
   cookiePolicy: '' # URL to the cookie policy of your application (e.g. https://example.com/cookie). Empty string to disable or filename to load from local file in static folder
@@ -120,6 +126,15 @@ system:
       weasyprint: '' # Defaults to /opt/venv/bin/weasyprint
       unoconvert: '' # Defaults to /opt/venv/bin/unoconvert
   fileUploadLimit: '' # Defaults to "". No limit when string is empty. Set a number, between 0 and 999, followed by one of the following strings to set a limit. "KB", "MB", "GB".
+  tempFileManagement:
+    baseTmpDir: '' # Defaults to java.io.tmpdir/stirling-pdf
+    libreofficeDir: '' # Defaults to tempFileManagement.baseTmpDir/libreoffice
+    systemTempDir: '' # Only used if cleanupSystemTemp is true
+    prefix: stirling-pdf- # Prefix for temp file names
+    maxAgeHours: 24 # Maximum age in hours before temp files are cleaned up
+    cleanupIntervalMinutes: 30 # How often to run cleanup (in minutes)
+    startupCleanup: true # Clean up old temp files on startup
+    cleanupSystemTemp: false # Whether to clean broader system temp directory
 
 ui:
   appName: '' # application's visible name
@@ -150,6 +165,8 @@ processExecutor:
     weasyPrintSessionLimit: 16
     installAppSessionLimit: 1
     calibreSessionLimit: 1
+    ghostscriptSessionLimit: 8
+    ocrMyPdfSessionLimit: 2
   timeoutMinutes: # Process executor timeout in minutes
     libreOfficetimeoutMinutes: 30
     pdfToHtmltimeoutMinutes: 20
@@ -158,3 +175,6 @@ processExecutor:
     installApptimeoutMinutes: 60
     calibretimeoutMinutes: 30
     tesseractTimeoutMinutes: 30
+    qpdfTimeoutMinutes: 30
+    ghostscriptTimeoutMinutes: 30
+    ocrMyPdfTimeoutMinutes: 30

testing/cucumber/features/environment.py

@@ -1,21 +1,25 @@
 import os
 
+
 def before_all(context):
     context.endpoint = None
     context.request_data = None
     context.files = {}
     context.response = None
 
+
 def after_scenario(context, scenario):
-    if hasattr(context, 'files'):
+    if hasattr(context, "files"):
         for file in context.files.values():
             file.close()
-    if os.path.exists('response_file'):
+    if os.path.exists("response_file"):
-        os.remove('response_file')
+        os.remove("response_file")
-    if hasattr(context, 'file_name') and os.path.exists(context.file_name):
+    if hasattr(context, "file_name") and os.path.exists(context.file_name):
         os.remove(context.file_name)
 
     # Remove any temporary files
-    for temp_file in os.listdir('.'):
+    for temp_file in os.listdir("."):
-        if temp_file.startswith('genericNonCustomisableName') or temp_file.startswith('temp_image_'):
+        if temp_file.startswith("genericNonCustomisableName") or temp_file.startswith(
+            "temp_image_"
+        ):
             os.remove(temp_file)

testing/cucumber/features/external.feature

@@ -22,7 +22,7 @@ Feature: API Validation
             | cleanFinal        | true   |
             | ocrType           | Normal |
             | ocrRenderType     | hocr   |
-      | removeImagesAfter| false       |
+            | removeImagesAfter | false  |
         When I send the API request to the endpoint "/api/v1/misc/ocr-pdf"
         Then the response content type should be "application/pdf"
         And the response file should have size greater than 0
@@ -60,7 +60,7 @@ Feature: API Validation
             | cleanFinal        | true  |
             | ocrType           | Force |
             | ocrRenderType     | hocr  |
-      | removeImagesAfter| false       |
+            | removeImagesAfter | false |
         When I send the API request to the endpoint "/api/v1/misc/ocr-pdf"
         Then the response content type should be "application/pdf"
         And the response file should have size greater than 0
@@ -164,6 +164,27 @@ Feature: API Validation
             | presentation | odp    | .odp      |
             | html         | html   | .zip      |
 
+    @image @positive
+    Scenario Outline: Convert PDF to image
+        Given I generate a PDF file as "fileInput"
+        And the pdf contains 3 pages with random text
+        And the pdf contains 3 images of size 300x300 on 3 pages
+        And the request data includes
+            | parameter   | value    |
+            | dpi         | 300      |
+            | imageFormat | <format> |
+        When I send the API request to the endpoint "/api/v1/convert/pdf/img"
+        Then the response status code should be 200
+        And the response file should have size greater than 100
+        And the response file should have extension ".zip"
+
+        Examples:
+            | format |
+            | webp   |
+            | png    |
+            | jpeg   |
+            | jpg    |
+            | gif    |
 
     @libre @positive @topdf
     Scenario Outline: Convert PDF to various types
@@ -227,4 +248,3 @@ Feature: API Validation
         And the response file should have size greater than 200
         And the response file should have extension ".zip"
         And the response ZIP should contain 3 files
-  

testing/cucumber/features/general.feature

@@ -24,29 +24,6 @@ Feature: API Validation
             | 1                   | 2                 | 12         |
             | 2                   | 2                 | 18         |
 
-  @split-pdf-by-sections @positive
-  Scenario Outline: split-pdf-by-sections with different parameters
-    Given I generate a PDF file as "fileInput"
-    And the pdf contains 2 pages
-    And the request data includes
-      | parameter           | value       |
-      | horizontalDivisions | <horizontalDivisions> |
-      | verticalDivisions   | <verticalDivisions> |
-      | merge               | true |
-    When I send the API request to the endpoint "/api/v1/general/split-pdf-by-sections"
-    Then the response content type should be "application/pdf"
-    And the response file should have size greater than 200
-    And the response status code should be 200
-    And the response PDF should contain <page_count> pages
-
-  Examples:
-    | horizontalDivisions | verticalDivisions | page_count |
-    | 0                   | 1                 | 4          |
-    | 1                   | 1                 | 8          |
-    | 1                   | 2                 | 12          |
-    | 2                   | 2                 | 18          |
-
-
 
     @split-pdf-by-pages @positive
     Scenario Outline: split-pdf-by-pages with different parameters
@@ -70,7 +47,6 @@ Feature: API Validation
             | 3n          | 7          |
 
 
-
     @split-pdf-by-size-or-count @positive
     Scenario Outline: split-pdf-by-size-or-count with different parameters
         Given I generate a PDF file as "fileInput"

testing/cucumber/features/steps/step_definitions.py

@@ -10,67 +10,67 @@ from reportlab.lib.pagesizes import letter
 from reportlab.lib.utils import ImageReader
 from reportlab.pdfgen import canvas
 import mimetypes
-import requests
 import zipfile
-import shutil
 import re
 from PIL import Image, ImageDraw
 
-API_HEADERS = {
+API_HEADERS = {"X-API-KEY": "123456789"}
-    'X-API-KEY': '123456789'
-}
 
 #########
 # GIVEN #
 #########
 
+
 @given('I generate a PDF file as "{fileInput}"')
 def step_generate_pdf(context, fileInput):
     context.param_name = fileInput
     context.file_name = "genericNonCustomisableName.pdf"
     writer = PdfWriter()
     writer.add_blank_page(width=72, height=72)  # Single blank page
-    with open(context.file_name, 'wb') as f:
+    with open(context.file_name, "wb") as f:
         writer.write(f)
-    if not hasattr(context, 'files'):
+    if not hasattr(context, "files"):
         context.files = {}
-    context.files[context.param_name] = open(context.file_name, 'rb')
+    context.files[context.param_name] = open(context.file_name, "rb")
 
 
 @given('I use an example file at "{filePath}" as parameter "{fileInput}"')
 def step_use_example_file(context, filePath, fileInput):
     context.param_name = fileInput
-    context.file_name = filePath.split('/')[-1]
+    context.file_name = filePath.split("/")[-1]
-    if not hasattr(context, 'files'):
+    if not hasattr(context, "files"):
         context.files = {}
 
     # Ensure the file exists before opening
     try:
-        example_file = open(filePath, 'rb')
+        example_file = open(filePath, "rb")
         context.files[context.param_name] = example_file
     except FileNotFoundError:
         raise FileNotFoundError(f"The example file '{filePath}' does not exist.")
 
-@given('the pdf contains {page_count:d} pages')
+
+@given("the pdf contains {page_count:d} pages")
 def step_pdf_contains_pages(context, page_count):
     writer = PdfWriter()
     for i in range(page_count):
         writer.add_blank_page(width=72, height=72)
-    with open(context.file_name, 'wb') as f:
+    with open(context.file_name, "wb") as f:
         writer.write(f)
     context.files[context.param_name].close()
-    context.files[context.param_name] = open(context.file_name, 'rb')
+    context.files[context.param_name] = open(context.file_name, "rb")
+
 
 # Duplicate for now...
-@given('the pdf contains {page_count:d} blank pages')
+@given("the pdf contains {page_count:d} blank pages")
 def step_pdf_contains_blank_pages(context, page_count):
     writer = PdfWriter()
     for i in range(page_count):
         writer.add_blank_page(width=72, height=72)
-    with open(context.file_name, 'wb') as f:
+    with open(context.file_name, "wb") as f:
         writer.write(f)
     context.files[context.param_name].close()
-    context.files[context.param_name] = open(context.file_name, 'rb')
+    context.files[context.param_name] = open(context.file_name, "rb")
+
 
 def create_black_box_image(file_name, size):
     can = canvas.Canvas(file_name, pagesize=size)
@@ -80,14 +80,20 @@ def create_black_box_image(file_name, size):
     can.showPage()
     can.save()
 
-@given(u'the pdf contains {image_count:d} images of size {width:d}x{height:d} on {page_count:d} pages')
+
+@given(
+    "the pdf contains {image_count:d} images of size {width:d}x{height:d} on {page_count:d} pages"
+)
 def step_impl(context, image_count, width, height, page_count):
     context.param_name = "fileInput"
     context.file_name = "genericNonCustomisableName.pdf"
-    create_pdf_with_images_and_boxes(context.file_name, image_count, page_count, width, height)
+    create_pdf_with_images_and_boxes(
-    if not hasattr(context, 'files'):
+        context.file_name, image_count, page_count, width, height
+    )
+    if not hasattr(context, "files"):
         context.files = {}
-    context.files[context.param_name] = open(context.file_name, 'rb')
+    context.files[context.param_name] = open(context.file_name, "rb")
+
 
 def add_black_boxes_to_image(image):
     if isinstance(image, str):
@@ -97,9 +103,14 @@ def add_black_boxes_to_image(image):
     draw.rectangle([(0, 0), image.size], fill=(0, 0, 0))  # Fill image with black
     return image
 
-def create_pdf_with_images_and_boxes(file_name, image_count, page_count, image_width, image_height):
+
+def create_pdf_with_images_and_boxes(
+    file_name, image_count, page_count, image_width, image_height
+):
     page_width, page_height = max(letter[0], image_width), max(letter[1], image_height)
-    boxes_per_page = image_count // page_count + (1 if image_count % page_count != 0 else 0)
+    boxes_per_page = image_count // page_count + (
+        1 if image_count % page_count != 0 else 0
+    )
 
     writer = PdfWriter()
     box_counter = 0
@@ -114,12 +125,14 @@ def create_pdf_with_images_and_boxes(file_name, image_count, page_count, image_w
 
             # Simulating a dynamic image creation (replace this with your actual image creation logic)
             # For demonstration, we'll create a simple black image
-            dummy_image = Image.new('RGB', (image_width, image_height), color='white')  # Create a white image
+            dummy_image = Image.new(
+                "RGB", (image_width, image_height), color="white"
+            )  # Create a white image
             dummy_image = add_black_boxes_to_image(dummy_image)  # Add black boxes
 
             # Convert the PIL Image to bytes to pass to drawImage
             image_bytes = io.BytesIO()
-            dummy_image.save(image_bytes, format='PNG')
+            dummy_image.save(image_bytes, format="PNG")
             image_bytes.seek(0)
 
             # Check if the image fits in the current page dimensions
@@ -130,7 +143,9 @@ def create_pdf_with_images_and_boxes(file_name, image_count, page_count, image_w
                 break
 
             # Add the image to the PDF
-            can.drawImage(ImageReader(image_bytes), x, y, width=image_width, height=image_height)
+            can.drawImage(
+                ImageReader(image_bytes), x, y, width=image_width, height=image_height
+            )
             box_counter += 1
 
         can.showPage()
@@ -140,7 +155,7 @@ def create_pdf_with_images_and_boxes(file_name, image_count, page_count, image_w
         writer.add_page(new_pdf.pages[0])
 
     # Write the PDF to file
-    with open(file_name, 'wb') as f:
+    with open(file_name, "wb") as f:
         writer.write(f)
 
     # Clean up temporary image files
@@ -149,36 +164,81 @@ def create_pdf_with_images_and_boxes(file_name, image_count, page_count, image_w
         if os.path.exists(temp_image_path):
             os.remove(temp_image_path)
 
-@given('the pdf contains {image_count:d} images on {page_count:d} pages')
+
+@given("the pdf contains {image_count:d} images on {page_count:d} pages")
 def step_pdf_contains_images(context, image_count, page_count):
-    if not hasattr(context, 'param_name'):
+    if not hasattr(context, "param_name"):
         context.param_name = "default"
     context.file_name = "genericNonCustomisableName.pdf"
     create_pdf_with_black_boxes(context.file_name, image_count, page_count)
-    if not hasattr(context, 'files'):
+    if not hasattr(context, "files"):
         context.files = {}
     if context.param_name in context.files:
         context.files[context.param_name].close()
-    context.files[context.param_name] = open(context.file_name, 'rb')
+    context.files[context.param_name] = open(context.file_name, "rb")
 
-@given('the pdf contains {page_count:d} pages with random text')
+
+def create_pdf_with_black_boxes(file_name, image_count, page_count):
+
+    page_width, page_height = letter
+    writer = PdfWriter()
+    box_counter = 0
+
+    for page in range(page_count):
+        packet = io.BytesIO()
+        can = canvas.Canvas(packet, pagesize=(page_width, page_height))
+
+        boxes_per_page = image_count // page_count + (
+            1 if image_count % page_count != 0 else 0
+        )
+        for i in range(boxes_per_page):
+            if box_counter >= image_count:
+                break
+
+            # Create a black box image
+            dummy_image = Image.new("RGB", (100, 100), color="black")
+            image_bytes = io.BytesIO()
+            dummy_image.save(image_bytes, format="PNG")
+            image_bytes.seek(0)
+
+            x = (i % (page_width // 100)) * 100
+            y = page_height - (((i % (page_height // 100)) + 1) * 100)
+
+            if x + 100 > page_width or y < 0:
+                break
+
+            can.drawImage(ImageReader(image_bytes), x, y, width=100, height=100)
+            box_counter += 1
+
+        can.showPage()
+        can.save()
+        packet.seek(0)
+        new_pdf = PdfReader(packet)
+        writer.add_page(new_pdf.pages[0])
+
+    with open(file_name, "wb") as f:
+        writer.write(f)
+
+
+@given("the pdf contains {page_count:d} pages with random text")
 def step_pdf_contains_pages_with_random_text(context, page_count):
     buffer = io.BytesIO()
     c = canvas.Canvas(buffer, pagesize=letter)
     width, height = letter
 
     for _ in range(page_count):
-        text = ''.join(random.choices(string.ascii_letters + string.digits, k=100))
+        text = "".join(random.choices(string.ascii_letters + string.digits, k=100))
         c.drawString(100, height - 100, text)
         c.showPage()
 
     c.save()
 
-    with open(context.file_name, 'wb') as f:
+    with open(context.file_name, "wb") as f:
         f.write(buffer.getvalue())
 
     context.files[context.param_name].close()
-    context.files[context.param_name] = open(context.file_name, 'rb')
+    context.files[context.param_name] = open(context.file_name, "rb")
+
 
 @given('the pdf pages all contain the text "{text}"')
 def step_pdf_pages_contain_text(context, text):
@@ -192,11 +252,12 @@ def step_pdf_pages_contain_text(context, text):
 
     c.save()
 
-    with open(context.file_name, 'wb') as f:
+    with open(context.file_name, "wb") as f:
         f.write(buffer.getvalue())
 
     context.files[context.param_name].close()
-    context.files[context.param_name] = open(context.file_name, 'rb')
+    context.files[context.param_name] = open(context.file_name, "rb")
+
 
 @given('the pdf is encrypted with password "{password}"')
 def step_encrypt_pdf(context, password):
@@ -205,29 +266,34 @@ def step_encrypt_pdf(context, password):
     for i in range(len(reader.pages)):
         writer.add_page(reader.pages[i])
     writer.encrypt(password)
-    with open(context.file_name, 'wb') as f:
+    with open(context.file_name, "wb") as f:
         writer.write(f)
     context.files[context.param_name].close()
-    context.files[context.param_name] = open(context.file_name, 'rb')
+    context.files[context.param_name] = open(context.file_name, "rb")
 
-@given('the request data is')
+
+@given("the request data is")
 def step_request_data(context):
     context.request_data = eval(context.text)
 
-@given('the request data includes')
+
+@given("the request data includes")
 def step_request_data_table(context):
-    context.request_data = {row['parameter']: row['value'] for row in context.table}
+    context.request_data = {row["parameter"]: row["value"] for row in context.table}
+
 
 @given('save the generated PDF file as "{filename}" for debugging')
 def save_generated_pdf(context, filename):
-    with open(filename, 'wb') as f:
+    with open(filename, "wb") as f:
         f.write(context.files[context.param_name].read())
     print(f"Saved generated PDF content to {filename}")
 
+
 ########
 # WHEN #
 ########
 
+
 @when('I send a GET request to "{endpoint}"')
 def step_send_get_request(context, endpoint):
     base_url = "http://localhost:8080"
@@ -235,20 +301,22 @@ def step_send_get_request(context, endpoint):
     response = requests.get(full_url, headers=API_HEADERS)
     context.response = response
 
+
 @when('I send a GET request to "{endpoint}" with parameters')
 def step_send_get_request_with_params(context, endpoint):
     base_url = "http://localhost:8080"
-    params = {row['parameter']: row['value'] for row in context.table}
+    params = {row["parameter"]: row["value"] for row in context.table}
     full_url = f"{base_url}{endpoint}"
     response = requests.get(full_url, params=params, headers=API_HEADERS)
     context.response = response
 
+
 @when('I send the API request to the endpoint "{endpoint}"')
 def step_send_api_request(context, endpoint):
     url = f"http://localhost:8080{endpoint}"
-    files = context.files if hasattr(context, 'files') else {}
+    files = context.files if hasattr(context, "files") else {}
 
-    if not hasattr(context, 'request_data') or context.request_data is None:
+    if not hasattr(context, "request_data") or context.request_data is None:
         context.request_data = {}
 
     form_data = []
@@ -257,130 +325,173 @@ def step_send_api_request(context, endpoint):
 
     for key, file in files.items():
         mime_type, _ = mimetypes.guess_type(file.name)
-        mime_type = mime_type or 'application/octet-stream'
+        mime_type = mime_type or "application/octet-stream"
         print(f"form_data {file.name} with {mime_type}")
         form_data.append((key, (file.name, file, mime_type)))
 
     response = requests.post(url, files=form_data, headers=API_HEADERS)
     context.response = response
 
+
 ########
 # THEN #
 ########
 
+
 @then('the response content type should be "{content_type}"')
 def step_check_response_content_type(context, content_type):
-    actual_content_type = context.response.headers.get('Content-Type', '')
+    actual_content_type = context.response.headers.get("Content-Type", "")
-    assert actual_content_type.startswith(content_type), f"Expected {content_type} but got {actual_content_type}. Response content: {context.response.content}"
+    assert actual_content_type.startswith(
+        content_type
+    ), f"Expected {content_type} but got {actual_content_type}. Response content: {context.response.content}"
 
-@then('the response file should have size greater than {size:d}')
+
+@then("the response file should have size greater than {size:d}")
 def step_check_response_file_size(context, size):
     response_file = io.BytesIO(context.response.content)
     assert len(response_file.getvalue()) > size
 
-@then('the response PDF is not passworded')
+
+@then("the response PDF is not passworded")
 def step_check_response_pdf_not_passworded(context):
     response_file = io.BytesIO(context.response.content)
     reader = PdfReader(response_file)
     assert not reader.is_encrypted
 
-@then('the response PDF is passworded')
+
+@then("the response PDF is passworded")
 def step_check_response_pdf_passworded(context):
     response_file = io.BytesIO(context.response.content)
     try:
         reader = PdfReader(response_file)
         assert reader.is_encrypted
     except PdfReadError as e:
-        raise AssertionError(f"Failed to read PDF: {str(e)}. Response content: {context.response.content}")
+        raise AssertionError(
+            f"Failed to read PDF: {str(e)}. Response content: {context.response.content}"
+        )
     except Exception as e:
-        raise AssertionError(f"An error occurred: {str(e)}. Response content: {context.response.content}")
+        raise AssertionError(
+            f"An error occurred: {str(e)}. Response content: {context.response.content}"
+        )
 
-@then('the response status code should be {status_code:d}')
+
+@then("the response status code should be {status_code:d}")
 def step_check_response_status_code(context, status_code):
-    assert context.response.status_code == status_code, f"Expected status code {status_code} but got {context.response.status_code}"
+    assert (
+        context.response.status_code == status_code
+    ), f"Expected status code {status_code} but got {context.response.status_code}"
+
 
 @then('the response should contain error message "{message}"')
 def step_check_response_error_message(context, message):
     response_json = context.response.json()
-    assert response_json.get('error') == message, f"Expected error message '{message}' but got '{response_json.get('error')}'"
+    assert (
+        response_json.get("error") == message
+    ), f"Expected error message '{message}' but got '{response_json.get('error')}'"
 
-@then('the response PDF should contain {page_count:d} pages')
-def step_check_response_pdf_page_count(context, page_count):
-    response_file = io.BytesIO(context.response.content)
-    reader = PdfReader(response_file)
-    assert len(reader.pages) == page_count, f"Expected {page_count} pages but got {len(reader.pages)} pages"
 
 @then('the response PDF metadata should include "{metadata_key}" as "{metadata_value}"')
 def step_check_response_pdf_metadata(context, metadata_key, metadata_value):
     response_file = io.BytesIO(context.response.content)
     reader = PdfReader(response_file)
     metadata = reader.metadata
-    assert metadata.get("/" + metadata_key) == metadata_value, f"Expected {metadata_key} to be '{metadata_value}' but got '{metadata.get(metadata_key)}'"
+    assert (
+        metadata.get("/" + metadata_key) == metadata_value
+    ), f"Expected {metadata_key} to be '{metadata_value}' but got '{metadata.get(metadata_key)}'"
+
 
 @then('the response file should have extension "{extension}"')
 def step_check_response_file_extension(context, extension):
-    content_disposition = context.response.headers.get('Content-Disposition', '')
+    content_disposition = context.response.headers.get("Content-Disposition", "")
     filename = ""
     if content_disposition:
-        parts = content_disposition.split(';')
+        parts = content_disposition.split(";")
         for part in parts:
-            if part.strip().startswith('filename'):
+            if part.strip().startswith("filename"):
-                filename = part.split('=')[1].strip().strip('"')
+                filename = part.split("=")[1].strip().strip('"')
                 break
-    assert filename.endswith(extension), f"Expected file extension {extension} but got {filename}. Response content: {context.response.content}"
+    assert filename.endswith(
+        extension
+    ), f"Expected file extension {extension} but got {filename}. Response content: {context.response.content}"
+
 
 @then('save the response file as "{filename}" for debugging')
 def step_save_response_file(context, filename):
-    with open(filename, 'wb') as f:
+    with open(filename, "wb") as f:
         f.write(context.response.content)
     print(f"Saved response content to {filename}")
 
-@then('the response PDF should contain {page_count:d} pages')
+
+@then("the response PDF should contain {page_count:d} pages")
 def step_check_response_pdf_page_count(context, page_count):
     response_file = io.BytesIO(context.response.content)
     reader = PdfReader(io.BytesIO(response_file.getvalue()))
     actual_page_count = len(reader.pages)
-    assert actual_page_count == page_count, f"Expected {page_count} pages but got {actual_page_count} pages"
+    assert (
+        actual_page_count == page_count
+    ), f"Expected {page_count} pages but got {actual_page_count} pages"
 
-@then('the response ZIP should contain {file_count:d} files')
+
+@then("the response ZIP should contain {file_count:d} files")
 def step_check_response_zip_file_count(context, file_count):
     response_file = io.BytesIO(context.response.content)
     with zipfile.ZipFile(io.BytesIO(response_file.getvalue())) as zip_file:
         actual_file_count = len(zip_file.namelist())
-    assert actual_file_count == file_count, f"Expected {file_count} files but got {actual_file_count} files"
+    assert (
+        actual_file_count == file_count
+    ), f"Expected {file_count} files but got {actual_file_count} files"
 
-@then('the response ZIP file should contain {doc_count:d} documents each having {pages_per_doc:d} pages')
+
+@then(
+    "the response ZIP file should contain {doc_count:d} documents each having {pages_per_doc:d} pages"
+)
 def step_check_response_zip_doc_page_count(context, doc_count, pages_per_doc):
     response_file = io.BytesIO(context.response.content)
     with zipfile.ZipFile(io.BytesIO(response_file.getvalue())) as zip_file:
         actual_doc_count = len(zip_file.namelist())
-        assert actual_doc_count == doc_count, f"Expected {doc_count} documents but got {actual_doc_count} documents"
+        assert (
+            actual_doc_count == doc_count
+        ), f"Expected {doc_count} documents but got {actual_doc_count} documents"
 
         for file_name in zip_file.namelist():
             with zip_file.open(file_name) as pdf_file:
                 reader = PdfReader(pdf_file)
                 actual_pages_per_doc = len(reader.pages)
-                assert actual_pages_per_doc == pages_per_doc, f"Expected {pages_per_doc} pages per document but got {actual_pages_per_doc} pages in document {file_name}"
+                assert (
+                    actual_pages_per_doc == pages_per_doc
+                ), f"Expected {pages_per_doc} pages per document but got {actual_pages_per_doc} pages in document {file_name}"
+
 
 @then('the JSON value of "{key}" should be "{expected_value}"')
 def step_check_json_value(context, key, expected_value):
     actual_value = context.response.json().get(key)
-    assert actual_value == expected_value, \
+    assert (
-        f"Expected JSON value for '{key}' to be '{expected_value}' but got '{actual_value}'"
+        actual_value == expected_value
+    ), f"Expected JSON value for '{key}' to be '{expected_value}' but got '{actual_value}'"
 
-@then('JSON list entry containing "{identifier_key}" as "{identifier_value}" should have "{target_key}" as "{target_value}"')
+
-def step_check_json_list_entry(context, identifier_key, identifier_self, target_key, target_value):
+@then(
+    'JSON list entry containing "{identifier_key}" as "{identifier_value}" should have "{target_key}" as "{target_value}"'
+)
+def step_check_json_list_entry(
+    context, identifier_key, identifier_self, target_key, target_value
+):
     json_response = context.response.json()
     for entry in json_response:
         if entry.get(identifier_key) == identifier_value:
-            assert entry.get(target_key) == target_value, \
+            assert (
-                f"Expected {target_key} to be {target_value} in entry where {identifier_key} is {identifier_value}, but found {entry.get(target_key)}"
+                entry.get(target_key) == target_value
+            ), f"Expected {target_key} to be {target_value} in entry where {identifier_key} is {identifier_value}, but found {entry.get(target_key)}"
             break
     else:
-        raise AssertionError(f"No entry with {identifier_key} as {identifier_value} found")
+        raise AssertionError(
+            f"No entry with {identifier_key} as {identifier_value} found"
+        )
+
 
 @then('the response should match the regex "{pattern}"')
 def step_response_matches_regex(context, pattern):
     response_text = context.response.text
-    assert re.match(pattern, response_text), \
+    assert re.match(
-        f"Response '{response_text}' does not match the expected pattern '{pattern}'"
+        pattern, response_text
+    ), f"Response '{response_text}' does not match the expected pattern '{pattern}'"