Test cleanup, JVM GC and api (#2787)

# Description of Changes

Please provide a summary of the changes, including:

- What was changed
- Why the change was made
- Any challenges encountered

Closes #(issue_number)

---

## Checklist

### General

- [ ] I have read the [Contribution
Guidelines](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/CONTRIBUTING.md)
- [ ] I have read the [Stirling-PDF Developer
Guide](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/DeveloperGuide.md)
(if applicable)
- [ ] I have read the [How to add new languages to
Stirling-PDF](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/HowToAddNewLanguage.md)
(if applicable)
- [ ] I have performed a self-review of my own code
- [ ] My changes generate no new warnings

### Documentation

- [ ] I have updated relevant docs on [Stirling-PDF's doc
repo](https://github.com/Stirling-Tools/Stirling-Tools.github.io/blob/main/docs/)
(if functionality has heavily changed)
- [ ] I have read the section [Add New Translation
Tags](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/HowToAddNewLanguage.md#add-new-translation-tags)
(for new translation tags only)

### UI Changes (if applicable)

- [ ] Screenshots or videos demonstrating the UI changes are attached
(e.g., as comments or direct attachments in the PR)

### Testing (if applicable)

- [ ] I have tested my changes locally. Refer to the [Testing
Guide](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/DeveloperGuide.md#6-testing)
for more details.

---------

Co-authored-by: a <a>

.github/workflows/build.yml

@@ -112,10 +112,10 @@ jobs:
 
       - name: Pip requirements
         run: |
-          pip install --require-hashes -r ./cucumber/requirements.txt
+          pip install --require-hashes -r ./testing/cucumber/requirements.txt
 
       - name: Run Docker Compose Tests
         run: |
-          chmod +x ./cucumber/test_webpages.sh
-          chmod +x ./test.sh
-          ./test.sh "${{ github.event.pull_request.user.login == 'dependabot[bot]' }}"
+          chmod +x ./testing/test_webpages.sh
+          chmod +x ./testing/test.sh
+          ./testing/test.sh "${{ github.event.pull_request.user.login == 'dependabot[bot]' }}"

.github/workflows/testdriver.yml

@@ -122,7 +122,7 @@ jobs:
             Start-Process "C:/Program Files/Google/Chrome/Application/chrome.exe" -ArgumentList "--start-maximized", "--load-extension=$(pwd)/node_modules/dashcam-chrome/build", "http://${{ secrets.VPS_HOST }}:1337"
             Start-Sleep -Seconds 20
           prompt: |
-            1. /run testdriver/test.yml
+            1. /run testing/testdriver/test.yml
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
           FORCE_COLOR: "3"

.gitignore

@@ -25,6 +25,7 @@ clientWebUI/
 !cucumber/
 !cucumber/exampleFiles/
 !cucumber/exampleFiles/example_html.zip
+exampleYmlFiles/stirling/
 
 # Gradle
 .gradle

Dockerfile

@@ -25,7 +25,13 @@ LABEL org.opencontainers.image.keywords="PDF, manipulation, merge, split, conver
 # Set Environment Variables
 ENV DOCKER_ENABLE_SECURITY=false \
     VERSION_TAG=$VERSION_TAG \
-    JAVA_TOOL_OPTIONS="$JAVA_TOOL_OPTIONS -XX:MaxRAMPercentage=75" \
+    JAVA_TOOL_OPTIONS="-XX:+UnlockExperimentalVMOptions \
+    -XX:MaxRAMPercentage=75 \
+    -XX:InitiatingHeapOccupancyPercent=20 \
+    -XX:+G1PeriodicGCInvokesConcurrent \
+    -XX:G1PeriodicGCInterval=10000 \
+    -XX:+UseStringDeduplication \
+    -XX:G1PeriodicGCSystemLoadThreshold=70" \
     HOME=/home/stirlingpdfuser \
     PUID=1000 \
     PGID=1000 \

Dockerfile.fat

@@ -25,7 +25,13 @@ ARG VERSION_TAG
 # Set Environment Variables
 ENV DOCKER_ENABLE_SECURITY=false \
     VERSION_TAG=$VERSION_TAG \
-    JAVA_TOOL_OPTIONS="$JAVA_TOOL_OPTIONS -XX:MaxRAMPercentage=75" \
+    JAVA_TOOL_OPTIONS="-XX:+UnlockExperimentalVMOptions \
+    -XX:MaxRAMPercentage=75 \
+    -XX:InitiatingHeapOccupancyPercent=20 \
+    -XX:+G1PeriodicGCInvokesConcurrent \
+    -XX:G1PeriodicGCInterval=10000 \
+    -XX:+UseStringDeduplication \
+    -XX:G1PeriodicGCSystemLoadThreshold=70" \
     HOME=/home/stirlingpdfuser \
     PUID=1000 \
     PGID=1000 \

Dockerfile.ultra-lite

@@ -7,7 +7,13 @@ ARG VERSION_TAG
 ENV DOCKER_ENABLE_SECURITY=false \
     HOME=/home/stirlingpdfuser \
     VERSION_TAG=$VERSION_TAG \
-    JAVA_TOOL_OPTIONS="$JAVA_TOOL_OPTIONS -XX:MaxRAMPercentage=75" \
+    JAVA_TOOL_OPTIONS="-XX:+UnlockExperimentalVMOptions \
+    -XX:MaxRAMPercentage=75 \
+    -XX:InitiatingHeapOccupancyPercent=20 \
+    -XX:+G1PeriodicGCInvokesConcurrent \
+    -XX:G1PeriodicGCInterval=10000 \
+    -XX:+UseStringDeduplication \
+    -XX:G1PeriodicGCSystemLoadThreshold=70" \
     PUID=1000 \
     PGID=1000 \
     UMASK=022

build.gradle

@@ -25,7 +25,7 @@ ext {
 }
 
 group = "stirling.software"
-version = "0.38.0"
+version = "0.39.0"
 
 
 java {
@@ -370,6 +370,8 @@ dependencies {
     implementation ("org.apache.pdfbox:pdfbox:$pdfboxVersion") {
         exclude group: "commons-logging", module: "commons-logging"
     }
+    implementation "org.apache.pdfbox:preflight:$pdfboxVersion"
+    
 
     implementation ("org.apache.pdfbox:xmpbox:$pdfboxVersion") {
         exclude group: "commons-logging", module: "commons-logging"

exampleYmlFiles/test_cicd.yml

@@ -1,6 +1,6 @@
 services:
   stirling-pdf:
-    container_name: Stirling-PDF-Security-Fat
+    container_name: Stirling-PDF-Security-Fat-with-login
     image: stirlingtools/stirling-pdf:latest-fat
     deploy:
       resources:

src/main/java/stirling/software/SPDF/controller/api/AnalysisController.java

@@ -0,0 +1,180 @@
+package stirling.software.SPDF.controller.api;
+
+import org.apache.pdfbox.Loader;
+import org.apache.pdfbox.cos.COSName;
+import org.apache.pdfbox.pdmodel.PDDocument;
+import org.apache.pdfbox.pdmodel.PDPage;
+import org.apache.pdfbox.pdmodel.PDPageTree;
+import org.apache.pdfbox.pdmodel.PDDocumentInformation;
+import org.apache.pdfbox.pdmodel.interactive.form.PDAcroForm;
+import org.apache.pdfbox.pdmodel.interactive.annotation.PDAnnotation;
+import org.apache.pdfbox.pdmodel.encryption.PDEncryption;
+import org.springframework.web.bind.annotation.*;
+import org.springframework.web.multipart.MultipartFile;
+import io.swagger.v3.oas.annotations.Operation;
+import io.swagger.v3.oas.annotations.tags.Tag;
+import stirling.software.SPDF.model.api.PDFFile;
+
+import java.io.IOException;
+import java.util.*;
+
+@RestController
+@RequestMapping("/api/v1/analysis")
+@Tag(name = "Analysis", description = "Analysis APIs")
+public class AnalysisController {
+
+	
+	@PostMapping(value = "/page-count", consumes = "multipart/form-data")
+	@Operation(summary = "Get PDF page count", 
+	          description = "Returns total number of pages in PDF. Input:PDF Output:JSON Type:SISO")
+	public Map<String, Integer> getPageCount(@ModelAttribute PDFFile file) throws IOException {
+		try (PDDocument document = Loader.loadPDF(file.getFileInput().getBytes())) {
+	       return Map.of("pageCount", document.getNumberOfPages());
+	   }
+	}
+	
+    @PostMapping(value ="/basic-info", consumes = "multipart/form-data")
+    @Operation(summary = "Get basic PDF information", 
+               description = "Returns page count, version, file size. Input:PDF Output:JSON Type:SISO")
+    public Map<String, Object> getBasicInfo(@ModelAttribute PDFFile file) throws IOException {
+        try (PDDocument document = Loader.loadPDF(file.getFileInput().getBytes())) {
+            Map<String, Object> info = new HashMap<>();
+            info.put("pageCount", document.getNumberOfPages());
+            info.put("pdfVersion", document.getVersion());
+            info.put("fileSize", file.getFileInput().getSize());
+            return info;
+        }
+    }
+
+    @PostMapping(value ="/document-properties", consumes = "multipart/form-data")
+    @Operation(summary = "Get PDF document properties", 
+               description = "Returns title, author, subject, etc. Input:PDF Output:JSON Type:SISO")
+    public Map<String, String> getDocumentProperties(@ModelAttribute PDFFile file) throws IOException {
+        try (PDDocument document = Loader.loadPDF(file.getFileInput().getBytes())) {
+            PDDocumentInformation info = document.getDocumentInformation();
+            Map<String, String> properties = new HashMap<>();
+            properties.put("title", info.getTitle());
+            properties.put("author", info.getAuthor());
+            properties.put("subject", info.getSubject());
+            properties.put("keywords", info.getKeywords());
+            properties.put("creator", info.getCreator());
+            properties.put("producer", info.getProducer());
+            properties.put("creationDate", info.getCreationDate().toString());
+            properties.put("modificationDate", info.getModificationDate().toString());
+            return properties;
+        }
+    }
+
+    @PostMapping(value ="/page-dimensions", consumes = "multipart/form-data")
+    @Operation(summary = "Get page dimensions for all pages", 
+               description = "Returns width and height of each page. Input:PDF Output:JSON Type:SISO")
+    public List<Map<String, Float>> getPageDimensions(@ModelAttribute PDFFile file) throws IOException {
+        try (PDDocument document = Loader.loadPDF(file.getFileInput().getBytes())) {
+            List<Map<String, Float>> dimensions = new ArrayList<>();
+            PDPageTree pages = document.getPages();
+            
+            for (PDPage page : pages) {
+                Map<String, Float> pageDim = new HashMap<>();
+                pageDim.put("width", page.getBBox().getWidth());
+                pageDim.put("height", page.getBBox().getHeight());
+                dimensions.add(pageDim);
+            }
+            return dimensions;
+        }
+    }
+
+    @PostMapping(value ="/form-fields", consumes = "multipart/form-data")
+    @Operation(summary = "Get form field information", 
+               description = "Returns count and details of form fields. Input:PDF Output:JSON Type:SISO")
+    public Map<String, Object> getFormFields(@ModelAttribute PDFFile file) throws IOException {
+        try (PDDocument document = Loader.loadPDF(file.getFileInput().getBytes())) {
+            Map<String, Object> formInfo = new HashMap<>();
+            PDAcroForm form = document.getDocumentCatalog().getAcroForm();
+            
+            if (form != null) {
+                formInfo.put("fieldCount", form.getFields().size());
+                formInfo.put("hasXFA", form.hasXFA());
+                formInfo.put("isSignaturesExist", form.isSignaturesExist());
+            } else {
+                formInfo.put("fieldCount", 0);
+                formInfo.put("hasXFA", false);
+                formInfo.put("isSignaturesExist", false);
+            }
+            return formInfo;
+        }
+    }
+
+    @PostMapping(value ="/annotation-info", consumes = "multipart/form-data")
+    @Operation(summary = "Get annotation information", 
+               description = "Returns count and types of annotations. Input:PDF Output:JSON Type:SISO")
+    public Map<String, Object> getAnnotationInfo(@ModelAttribute PDFFile file) throws IOException {
+        try (PDDocument document = Loader.loadPDF(file.getFileInput().getBytes())) {
+            Map<String, Object> annotInfo = new HashMap<>();
+            int totalAnnotations = 0;
+            Map<String, Integer> annotationTypes = new HashMap<>();
+
+            for (PDPage page : document.getPages()) {
+                for (PDAnnotation annot : page.getAnnotations()) {
+                    totalAnnotations++;
+                    String subType = annot.getSubtype();
+                    annotationTypes.merge(subType, 1, Integer::sum);
+                }
+            }
+
+            annotInfo.put("totalCount", totalAnnotations);
+            annotInfo.put("typeBreakdown", annotationTypes);
+            return annotInfo;
+        }
+    }
+
+    @PostMapping(value ="/font-info", consumes = "multipart/form-data")
+    @Operation(summary = "Get font information", 
+               description = "Returns list of fonts used in the document. Input:PDF Output:JSON Type:SISO")
+    public Map<String, Object> getFontInfo(@ModelAttribute PDFFile file) throws IOException {
+        try (PDDocument document = Loader.loadPDF(file.getFileInput().getBytes())) {
+            Map<String, Object> fontInfo = new HashMap<>();
+            Set<String> fontNames = new HashSet<>();
+
+            for (PDPage page : document.getPages()) {
+                for (COSName font : page.getResources().getFontNames()) {
+                    fontNames.add(font.getName());
+                }
+            }
+
+            fontInfo.put("fontCount", fontNames.size());
+            fontInfo.put("fonts", fontNames);
+            return fontInfo;
+        }
+    }
+
+    @PostMapping(value ="/security-info", consumes = "multipart/form-data")
+    @Operation(summary = "Get security information", 
+               description = "Returns encryption and permission details. Input:PDF Output:JSON Type:SISO")
+    public Map<String, Object> getSecurityInfo(@ModelAttribute PDFFile file) throws IOException {
+        try (PDDocument document = Loader.loadPDF(file.getFileInput().getBytes())) {
+            Map<String, Object> securityInfo = new HashMap<>();
+            PDEncryption encryption = document.getEncryption();
+            
+            if (encryption != null) {
+                securityInfo.put("isEncrypted", true);
+                securityInfo.put("keyLength", encryption.getLength());
+                
+                // Get permissions
+                Map<String, Boolean> permissions = new HashMap<>();
+                permissions.put("canPrint", document.getCurrentAccessPermission().canPrint());
+                permissions.put("canModify", document.getCurrentAccessPermission().canModify());
+                permissions.put("canExtractContent", document.getCurrentAccessPermission().canExtractContent());
+                permissions.put("canModifyAnnotations", document.getCurrentAccessPermission().canModifyAnnotations());
+                
+                securityInfo.put("permissions", permissions);
+            } else {
+                securityInfo.put("isEncrypted", false);
+            }
+            
+            return securityInfo;
+        }
+    }
+    
+
+
+}

src/main/resources/templates/misc/remove-blanks.html

@@ -5,6 +5,7 @@
   </head>
 
   <body>
+    <th:block th:insert="~{fragments/common :: game}"></th:block>
     <div id="page-container">
       <div id="content-wrap">
         <th:block th:insert="~{fragments/navbar.html :: navbar}"></th:block>

testing/test.sh

@@ -3,6 +3,22 @@
 # Default value for the Boolean parameter
 VERIFICATION=${1:-false}  # Default is "false" if no parameter is passed
 
+# Find project root by locating build.gradle
+find_root() {
+    local dir="$PWD"
+    while [[ "$dir" != "/" ]]; do
+        if [[ -f "$dir/build.gradle" ]]; then
+            echo "$dir"
+            return 0
+        fi
+        dir="$(dirname "$dir")"
+    done
+    echo "Error: build.gradle not found" >&2
+    exit 1
+}
+
+PROJECT_ROOT=$(find_root)
+
 # Function to check the health of the service with a timeout of 80 seconds
 check_health() {
     local service_name=$1
@@ -67,13 +83,16 @@ run_tests() {
 main() {
 	SECONDS=0
 
+    cd "$PROJECT_ROOT"
+    
     # Run the gradlew build command and check if it fails
     if [[ "$VERIFICATION" == "true" ]]; then
         ./gradlew clean dependencies buildEnvironment spotlessApply --write-verification-metadata sha256 --refresh-dependencies help
         ./gradlew clean dependencies buildEnvironment spotlessApply --write-verification-metadata sha256,pgp --refresh-keys --export-keys --refresh-dependencies help
     fi
-
+   
     export DOCKER_ENABLE_SECURITY=false
+    # Run the gradlew build command and check if it fails
     if ! ./gradlew clean build; then
         echo "Gradle build failed with security disabled, exiting script."
         exit 1
@@ -83,19 +102,21 @@ main() {
     # Building Docker images
     # docker build --no-cache --pull --build-arg VERSION_TAG=alpha -t stirlingtools/stirling-pdf:latest -f ./Dockerfile .
     docker build --no-cache --pull --build-arg VERSION_TAG=alpha -t stirlingtools/stirling-pdf:latest-ultra-lite -f ./Dockerfile.ultra-lite .
-
+	
     # Test each configuration
     run_tests "Stirling-PDF-Ultra-Lite" "./exampleYmlFiles/docker-compose-latest-ultra-lite.yml"
-
+	
 	echo "Testing webpage accessibility..."
-	if ./cucumber/test_webpages.sh; then
-		passed_tests+=("Webpage-Accessibility")
+	cd "testing"
+	if ./test_webpages.sh -f webpage_urls.txt -b http://localhost:8080; then
+		passed_tests+=("Webpage-Accessibility-lite")
 	else
-		failed_tests+=("Webpage-Accessibility")
-		echo "Webpage accessibility tests failed"
+		failed_tests+=("Webpage-Accessibility-lite")
+		echo "Webpage accessibility lite tests failed"
 	fi
-
+	cd "$PROJECT_ROOT"
 	docker-compose -f "./exampleYmlFiles/docker-compose-latest-ultra-lite.yml" down
+	
 
     #run_tests "Stirling-PDF" "./exampleYmlFiles/docker-compose-latest.yml"
 	#docker-compose -f "./exampleYmlFiles/docker-compose-latest.yml" down
@@ -107,32 +128,52 @@ main() {
         exit 1
     fi
 
+
     # Building Docker images with security enabled
-    # docker build --no-cache --pull --build-arg VERSION_TAG=alpha -t stirlingtools/stirling-pdf:latest -f ./Dockerfile .
-    # docker build --no-cache --pull --build-arg VERSION_TAG=alpha -t stirlingtools/stirling-pdf:latest-ultra-lite -f ./Dockerfile.ultra-lite .
+   # docker build --no-cache --pull --build-arg VERSION_TAG=alpha -t stirlingtools/stirling-pdf:latest -f ./Dockerfile .
+ #   docker build --no-cache --pull --build-arg VERSION_TAG=alpha -t stirlingtools/stirling-pdf:latest-ultra-lite -f ./Dockerfile.ultra-lite .
     docker build --no-cache --pull --build-arg VERSION_TAG=alpha -t stirlingtools/stirling-pdf:latest-fat -f ./Dockerfile.fat .
-
+    
+    
     # Test each configuration with security
-    # run_tests "Stirling-PDF-Ultra-Lite-Security" "./exampleYmlFiles/docker-compose-latest-ultra-lite-security.yml"
-	# docker-compose -f "./exampleYmlFiles/docker-compose-latest-ultra-lite-security.yml" down
-    # run_tests "Stirling-PDF-Security" "./exampleYmlFiles/docker-compose-latest-security.yml"
-	# docker-compose -f "./exampleYmlFiles/docker-compose-latest-security.yml" down
+  #  run_tests "Stirling-PDF-Ultra-Lite-Security" "./exampleYmlFiles/docker-compose-latest-ultra-lite-security.yml"
+	#docker-compose -f "./exampleYmlFiles/docker-compose-latest-ultra-lite-security.yml" down
+  #  run_tests "Stirling-PDF-Security" "./exampleYmlFiles/docker-compose-latest-security.yml"
+#	docker-compose -f "./exampleYmlFiles/docker-compose-latest-security.yml" down
+
+
+	run_tests "Stirling-PDF-Security-Fat" "./exampleYmlFiles/docker-compose-latest-fat-security.yml"
+	
+	echo "Testing webpage accessibility..."
+	cd "testing"
+	if ./test_webpages.sh -f webpage_urls_full.txt -b http://localhost:8080; then
+		passed_tests+=("Webpage-Accessibility-full")
+	else
+		failed_tests+=("Webpage-Accessibility-full")
+		echo "Webpage accessibility full tests failed"
+	fi
+	cd "$PROJECT_ROOT"
+	
+	docker-compose -f "./exampleYmlFiles/docker-compose-latest-fat-security.yml" down
+
+
+	run_tests "Stirling-PDF-Security-Fat-with-login" "./exampleYmlFiles/test_cicd.yml"
 
-	run_tests "Stirling-PDF-Security-Fat" "./exampleYmlFiles/test_cicd.yml"
 	if [ $? -eq 0 ]; then
-		cd cucumber
+		cd "testing/cucumber"
 		if python -m behave; then
 			passed_tests+=("Stirling-PDF-Regression")
 		else
 			failed_tests+=("Stirling-PDF-Regression")
 			echo "Printing docker logs of failed regression"
-			docker logs "Stirling-PDF-Security-Fat"
+			docker logs "Stirling-PDF-Security-Fat-with-login"
 			echo "Printed docker logs of failed regression"
 		fi
-		cd ..
+		cd "$PROJECT_ROOT"
 	fi
-	docker-compose -f "./exampleYmlFiles/docker-compose-latest-fat-security.yml" down
-
+	
+	docker-compose -f "./exampleYmlFiles/test_cicd.yml" down
+	
     # Report results
     echo "All tests completed in $SECONDS seconds."
 
@@ -151,6 +192,8 @@ main() {
         echo -e "\e[31m$test\e[0m"  # Red color for failed tests
     done
 
+
+
     # Check if there are any failed tests and exit with an error code if so
     if [ ${#failed_tests[@]} -ne 0 ]; then
         echo "Some tests failed."
@@ -159,6 +202,7 @@ main() {
         echo "All tests passed successfully."
         exit 0
     fi
+
 }
 
-main
+main

testing/test_webpages.sh

@@ -2,17 +2,16 @@
 
 # Function to check a single webpage
 check_webpage() {
-    local url=$1
-    local base_url=${2:-"http://localhost:8080"}
+    local url=$(echo "$1" | tr -d '\r')  # Remove carriage returns
+    local base_url=$(echo "$2" | tr -d '\r')
     local full_url="${base_url}${url}"
     local timeout=10
-
     echo -n "Testing $full_url ... "
     
     # Use curl to fetch the page with timeout
     response=$(curl -s -w "\n%{http_code}" --max-time $timeout "$full_url")
     if [ $? -ne 0 ]; then
-        echo "FAILED - Connection error or timeout"
+        echo "FAILED - Connection error or timeout $full_url "
         return 1
     fi
 
@@ -27,7 +26,7 @@ check_webpage() {
     fi
 
     # Check if response contains HTML
-    if ! echo "$BODY" | grep -q "<!DOCTYPE html>\|<html"; then
+    if ! printf '%s' "$BODY" | grep -q "<!DOCTYPE html>\|<html"; then
         echo "FAILED - Response is not HTML"
         return 1
     fi
@@ -46,11 +45,12 @@ test_all_urls() {
 
     echo "Starting webpage tests..."
     echo "Base URL: $base_url"
+	echo "Number of lines: $(wc -l < "$url_file")"
     echo "----------------------------------------"
-
+	
     while IFS= read -r url || [ -n "$url" ]; do
-        # Skip empty lines
-        [ -z "$url" ] && continue
+        # Skip empty lines and comments
+        [[ -z "$url" || "$url" =~ ^#.*$ ]] && continue
         
         ((total_count++))
         if ! check_webpage "$url" "$base_url"; then
@@ -60,7 +60,7 @@ test_all_urls() {
 
     local end_time=$(date +%s)
     local duration=$((end_time - start_time))
-
+    
     echo "----------------------------------------"
     echo "Test Summary:"
     echo "Total tests: $total_count"
@@ -71,18 +71,44 @@ test_all_urls() {
     return $failed_count
 }
 
+# Print usage information
+usage() {
+    echo "Usage: $0 [-f url_file] [-b base_url]"
+    echo "Options:"
+    echo "  -f url_file   Path to file containing URLs to test (required)"
+    echo "  -b base_url   Base URL to prepend to test URLs (default: http://localhost:8080)"
+    exit 1
+}
+
 # Main execution
 main() {
-    local script_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-    local url_file="${script_dir}/webpage_urls.txt"
+    local url_file=""
+    local base_url="http://localhost:8080"
 
+    # Parse command line options
+    while getopts ":f:b:h" opt; do
+        case $opt in
+            f) url_file="$OPTARG" ;;
+            b) base_url="$OPTARG" ;;
+            h) usage ;;
+            \?) echo "Invalid option -$OPTARG" >&2; usage ;;
+        esac
+    done
+
+    # Check if URL file is provided
+    if [ -z "$url_file" ]; then
+        echo "Error: URL file is required"
+        usage
+    fi
+
+    # Check if URL file exists
     if [ ! -f "$url_file" ]; then
         echo "Error: URL list file not found: $url_file"
         exit 1
     fi
     
     # Run tests using the URL list
-    if test_all_urls "$url_file"; then
+    if test_all_urls "$url_file" "$base_url"; then
         echo "All webpage tests passed!"
         exit 0
     else

testing/webpage_urls_full.txt

@@ -0,0 +1,66 @@
+
+/
+/add-image
+/add-page-numbers
+/add-password
+/add-watermark
+/adjust-contrast
+/auto-redact
+/auto-rename
+/auto-split-pdf
+/cert-sign
+/change-metadata
+/change-permissions
+/compare
+/compress-pdf
+/crop
+/extract-image-scans
+/extract-images
+/extract-page
+/file-to-pdf
+/flatten
+/get-info-on-pdf
+/html-to-pdf
+/img-to-pdf
+/licenses
+/markdown-to-pdf
+/merge-pdfs
+/multi-page-layout
+/multi-tool
+/ocr-pdf
+/overlay-pdf
+/pdf-organizer
+/pdf-to-csv
+/pdf-to-html
+/pdf-to-img
+/pdf-to-markdown
+/pdf-to-presentation
+/pdf-to-single-page
+/pdf-to-text
+/pdf-to-word
+/pdf-to-xml
+/pipeline
+/redact
+/releases
+/remove-annotations
+/remove-blanks
+/remove-cert-sign
+/remove-image-pdf
+/remove-pages
+/remove-password
+/repair
+/replace-and-invert-color-pdf
+/rotate-pdf
+/sanitize-pdf
+/scale-pages
+/show-javascript
+/sign
+/split-by-size-or-count
+/split-pdf-by-chapters
+/split-pdf-by-sections
+/split-pdfs
+/stamp
+/url-to-pdf
+/validate-signature
+/view-pdf
+/swagger-ui/index.html