fix(server): update some integration tests and create 'system' user

src/bin/test_runner.rs

@@ -170,7 +170,7 @@ fn run_frontend_tests() -> Result<TestResult, Box<dyn std::error::Error>> {
 
 fn check_server_running() -> Result<(), Box<dyn std::error::Error>> {
     let output = Command::new("curl")
-        .args(&["-s", "-f", "http://localhost:8080/api/health"])
+        .args(&["-s", "-f", "http://localhost:8000/api/health"])
         .output()?;
     
     if output.status.success() {
@@ -180,7 +180,7 @@ fn check_server_running() -> Result<(), Box<dyn std::error::Error>> {
         }
     }
     
-    Err("Server not running or not healthy at http://localhost:8080".into())
+    Err("Server not running or not healthy at http://localhost:8000".into())
 }
 
 fn print_summary(results: &[TestResult]) {

src/enhanced_ocr.rs

@@ -1,4 +1,4 @@
-use anyhow::Result;
+use anyhow::{anyhow, Result};
 use tracing::{debug, info, warn};
 
 #[cfg(feature = "ocr")]
@@ -503,7 +503,26 @@ impl EnhancedOcrService {
         info!("Extracting text from PDF: {}", file_path);
         
         let bytes = std::fs::read(file_path)?;
-        let text = pdf_extract::extract_text_from_mem(&bytes)?;
+        
+        // Validate PDF header
+        if bytes.len() < 5 || !bytes.starts_with(b"%PDF-") {
+            return Err(anyhow!(
+                "Invalid PDF file: Missing or corrupted PDF header. File size: {} bytes, Header: {:?}", 
+                bytes.len(),
+                bytes.get(0..20).unwrap_or(&[]).iter().map(|&b| b as char).collect::<String>()
+            ));
+        }
+        
+        let text = match pdf_extract::extract_text_from_mem(&bytes) {
+            Ok(text) => text,
+            Err(e) => {
+                // Provide more detailed error information
+                return Err(anyhow!(
+                    "PDF text extraction failed for file '{}' (size: {} bytes): {}. This may indicate a corrupted or unsupported PDF format.",
+                    file_path, bytes.len(), e
+                ));
+            }
+        };
         
         let processing_time = start_time.elapsed().as_millis() as u64;
         let word_count = text.split_whitespace().count();

src/main.rs

@@ -133,6 +133,9 @@ async fn main() -> Result<(), Box<dyn std::error::Error>> {
     // Seed admin user
     seed::seed_admin_user(&db).await?;
     
+    // Seed system user for watcher
+    seed::seed_system_user(&db).await?;
+    
     let state = AppState { db, config: config.clone() };
     
     let app = Router::new()

src/seed.rs

@@ -46,5 +46,43 @@ pub async fn seed_admin_user(db: &Database) -> Result<()> {
         }
     }
 
+    Ok(())
+}
+
+pub async fn seed_system_user(db: &Database) -> Result<()> {
+    let system_username = "system";
+    let system_email = "system@readur.internal";
+    let system_password = "system-internal-password";
+
+    // Check if system user already exists
+    match db.get_user_by_username(system_username).await {
+        Ok(Some(_)) => {
+            info!("System user already exists");
+            return Ok(());
+        }
+        Ok(None) => {
+            // User doesn't exist, create it
+        }
+        Err(e) => {
+            info!("Error checking for system user: {}", e);
+        }
+    }
+
+    let create_user = CreateUser {
+        username: system_username.to_string(),
+        email: system_email.to_string(),
+        password: system_password.to_string(),
+    };
+
+    match db.create_user(create_user).await {
+        Ok(user) => {
+            info!("✅ SYSTEM USER CREATED SUCCESSFULLY!");
+            info!("🆔 System User ID: {}", user.id);
+        }
+        Err(e) => {
+            info!("Failed to create system user: {}", e);
+        }
+    }
+
     Ok(())
 }

src/watcher.rs

@@ -295,11 +295,25 @@ async fn process_file(
         }
     }
     
+    // Validate PDF files before processing
+    if mime_type == "application/pdf" {
+        if file_data.len() < 5 || !file_data.starts_with(b"%PDF-") {
+            warn!(
+                "Skipping invalid PDF file: {} (size: {} bytes, header: {:?})",
+                filename,
+                file_data.len(),
+                file_data.get(0..20).unwrap_or(&[]).iter().map(|&b| b as char).collect::<String>()
+            );
+            return Ok(());
+        }
+    }
+    
     let saved_file_path = file_service.save_file(&filename, &file_data).await?;
     
-    // TODO: Make this configurable or fetch from database
-    // Using admin user ID for watch folder documents
-    let system_user_id = uuid::Uuid::parse_str("c2e66705-e54b-4eff-91f5-760cb0a69b62")?;
+    // Fetch system user ID from database
+    let system_user = db.get_user_by_username("system").await?
+        .ok_or_else(|| anyhow::anyhow!("System user not found. Please ensure the system user is created."))?;
+    let system_user_id = system_user.id;
     
     let document = file_service.create_document(
         &filename,