feat(dev): also break up the large webdav_service.rs file into smaller ones

src/db/documents/management.rs

@@ -1,5 +1,5 @@
 use anyhow::Result;
-use sqlx::{QueryBuilder, Postgres};
+use sqlx::{QueryBuilder, Postgres, Row};
 use uuid::Uuid;
 
 use crate::models::{Document, UserRole, FacetItem};
@@ -53,11 +53,16 @@ impl Database {
             let doc_id: Uuid = row.get("document_id");
             let label = Label {
                 id: row.get("label_id"),
-                user_id: row.get("user_id"),
+                user_id: Some(row.get("user_id")),
                 name: row.get("name"),
+                description: None,
                 color: row.get("color"),
+                background_color: None,
+                icon: None,
+                is_system: false,
                 created_at: row.get("created_at"),
                 updated_at: row.get("updated_at"),
+                document_count: 0,
             };
 
             if Some(doc_id) != current_doc_id {

src/db/documents/search.rs

@@ -1,5 +1,5 @@
 use anyhow::Result;
-use sqlx::{QueryBuilder, Postgres};
+use sqlx::{QueryBuilder, Postgres, Row};
 use uuid::Uuid;
 
 use crate::models::{Document, UserRole, SearchRequest, SearchMode, SearchSnippet, HighlightRange, EnhancedDocumentResponse};

src/routes/sources.rs

@@ -443,7 +443,7 @@ async fn trigger_deep_scan(
                 })?;
 
             // Create WebDAV service
-            let webdav_config = crate::services::webdav_service::WebDAVConfig {
+            let webdav_config = crate::services::webdav::WebDAVConfig {
                 server_url: config.server_url.clone(),
                 username: config.username.clone(),
                 password: config.password.clone(),
@@ -453,7 +453,7 @@ async fn trigger_deep_scan(
                 server_type: config.server_type.clone(),
             };
 
-            let webdav_service = crate::services::webdav_service::WebDAVService::new(webdav_config.clone())
+            let webdav_service = crate::services::webdav::WebDAVService::new(webdav_config.clone())
                 .map_err(|e| {
                     error!("Failed to create WebDAV service for deep scan: {}", e);
                     StatusCode::INTERNAL_SERVER_ERROR
@@ -795,7 +795,7 @@ async fn test_connection(
             let config: crate::models::WebDAVSourceConfig = serde_json::from_value(source.config)
                 .map_err(|_| StatusCode::INTERNAL_SERVER_ERROR)?;
 
-            match crate::services::webdav_service::test_webdav_connection(
+            match crate::services::webdav::test_webdav_connection(
                 &config.server_url,
                 &config.username,
                 &config.password,
@@ -963,7 +963,7 @@ async fn estimate_webdav_crawl_internal(
     config: &crate::models::WebDAVSourceConfig,
 ) -> Result<Json<serde_json::Value>, StatusCode> {
     // Create WebDAV service config
-    let webdav_config = crate::services::webdav_service::WebDAVConfig {
+    let webdav_config = crate::services::webdav::WebDAVConfig {
         server_url: config.server_url.clone(),
         username: config.username.clone(),
         password: config.password.clone(),
@@ -974,7 +974,7 @@ async fn estimate_webdav_crawl_internal(
     };
 
     // Create WebDAV service and estimate crawl
-    match crate::services::webdav_service::WebDAVService::new(webdav_config) {
+    match crate::services::webdav::WebDAVService::new(webdav_config) {
         Ok(webdav_service) => {
             match webdav_service.estimate_crawl(&config.watch_folders).await {
                 Ok(estimate) => Ok(Json(serde_json::to_value(estimate).unwrap())),
@@ -1031,7 +1031,7 @@ async fn test_connection_with_config(
             let config: crate::models::WebDAVSourceConfig = serde_json::from_value(request.config)
                 .map_err(|_| StatusCode::BAD_REQUEST)?;
 
-            match crate::services::webdav_service::test_webdav_connection(
+            match crate::services::webdav::test_webdav_connection(
                 &config.server_url,
                 &config.username,
                 &config.password,

src/routes/webdav.rs

@@ -17,8 +17,8 @@ use crate::{
     },
     AppState,
 };
-use crate::services::webdav_service::WebDAVConfig;
-use crate::services::webdav_service::WebDAVService;
+use crate::services::webdav::WebDAVConfig;
+use crate::services::webdav::WebDAVService;
 
 pub mod webdav_sync;
 use webdav_sync::perform_webdav_sync_with_tracking;

src/routes/webdav/webdav_sync.rs

@@ -10,7 +10,7 @@ use crate::{
     models::{CreateWebDAVFile, UpdateWebDAVSyncState},
     services::file_service::FileService,
     ingestion::document_ingestion::{DocumentIngestionService, IngestionResult},
-    services::webdav_service::{WebDAVConfig, WebDAVService},
+    services::webdav::{WebDAVConfig, WebDAVService},
 };
 
 pub async fn perform_webdav_sync_with_tracking(

src/scheduling/source_scheduler.rs

@@ -662,8 +662,8 @@ impl SourceScheduler {
             // Trigger the deep scan via the API endpoint
             // We'll reuse the existing deep scan logic from the sources route
             let webdav_config: WebDAVSourceConfig = serde_json::from_value(source.config.clone())?;
-            let webdav_service = crate::services::webdav_service::WebDAVService::new(
-                crate::services::webdav_service::WebDAVConfig {
+            let webdav_service = crate::services::webdav::WebDAVService::new(
+                crate::services::webdav::WebDAVConfig {
                     server_url: webdav_config.server_url.clone(),
                     username: webdav_config.username.clone(),
                     password: webdav_config.password.clone(),
@@ -950,7 +950,7 @@ impl SourceScheduler {
         let config: WebDAVSourceConfig = serde_json::from_value(source.config.clone())
             .map_err(|e| format!("Config parse error: {}", e))?;
 
-        let webdav_config = crate::services::webdav_service::WebDAVConfig {
+        let webdav_config = crate::services::webdav::WebDAVConfig {
             server_url: config.server_url.clone(),
             username: config.username.clone(),
             password: config.password.clone(),
@@ -960,7 +960,7 @@ impl SourceScheduler {
             server_type: config.server_type.clone(),
         };
 
-        let webdav_service = crate::services::webdav_service::WebDAVService::new(webdav_config)
+        let webdav_service = crate::services::webdav::WebDAVService::new(webdav_config)
             .map_err(|e| format!("Service creation failed: {}", e))?;
 
         let test_config = crate::models::WebDAVTestConnection {

src/scheduling/source_sync.rs

@@ -15,7 +15,7 @@ use crate::{
     ingestion::document_ingestion::{DocumentIngestionService, IngestionResult},
     services::local_folder_service::LocalFolderService,
     services::s3_service::S3Service,
-    services::webdav_service::{WebDAVService, WebDAVConfig},
+    services::webdav::{WebDAVService, WebDAVConfig},
 };
 
 #[derive(Clone)]

src/scheduling/webdav_scheduler.rs

@@ -9,7 +9,7 @@ use crate::{
     services::file_service::FileService,
     AppState,
 };
-use crate::services::webdav_service::{WebDAVConfig, WebDAVService};
+use crate::services::webdav::{WebDAVConfig, WebDAVService};
 use crate::routes::webdav::webdav_sync::perform_webdav_sync_with_tracking;
 
 pub struct WebDAVScheduler {

src/services/mod.rs

@@ -3,4 +3,4 @@ pub mod local_folder_service;
 pub mod ocr_retry_service;
 pub mod s3_service;
 pub mod s3_service_stub;
-pub mod webdav_service;
+pub mod webdav;

src/services/webdav/config.rs

@@ -0,0 +1,141 @@
+use serde::{Deserialize, Serialize};
+
+/// WebDAV server configuration
+#[derive(Debug, Clone)]
+pub struct WebDAVConfig {
+    pub server_url: String,
+    pub username: String,
+    pub password: String,
+    pub watch_folders: Vec<String>,
+    pub file_extensions: Vec<String>,
+    pub timeout_seconds: u64,
+    pub server_type: Option<String>, // "nextcloud", "owncloud", "generic"
+}
+
+/// Retry configuration for WebDAV operations
+#[derive(Debug, Clone)]
+pub struct RetryConfig {
+    pub max_retries: u32,
+    pub initial_delay_ms: u64,
+    pub max_delay_ms: u64,
+    pub backoff_multiplier: f64,
+    pub timeout_seconds: u64,
+    pub rate_limit_backoff_ms: u64, // Additional backoff for 429 responses
+}
+
+/// Concurrency configuration for WebDAV operations
+#[derive(Debug, Clone)]
+pub struct ConcurrencyConfig {
+    pub max_concurrent_scans: usize,
+    pub max_concurrent_downloads: usize,
+    pub adaptive_rate_limiting: bool,
+}
+
+impl Default for RetryConfig {
+    fn default() -> Self {
+        Self {
+            max_retries: 3,
+            initial_delay_ms: 1000, // 1 second
+            max_delay_ms: 30000,    // 30 seconds
+            backoff_multiplier: 2.0,
+            timeout_seconds: 30,
+            rate_limit_backoff_ms: 5000, // 5 seconds
+        }
+    }
+}
+
+impl Default for ConcurrencyConfig {
+    fn default() -> Self {
+        Self {
+            max_concurrent_scans: 4,
+            max_concurrent_downloads: 8,
+            adaptive_rate_limiting: true,
+        }
+    }
+}
+
+impl WebDAVConfig {
+    /// Creates a new WebDAV configuration
+    pub fn new(
+        server_url: String,
+        username: String,
+        password: String,
+        watch_folders: Vec<String>,
+        file_extensions: Vec<String>,
+    ) -> Self {
+        Self {
+            server_url,
+            username,
+            password,
+            watch_folders,
+            file_extensions,
+            timeout_seconds: 30,
+            server_type: None,
+        }
+    }
+
+    /// Validates the configuration
+    pub fn validate(&self) -> anyhow::Result<()> {
+        if self.server_url.is_empty() {
+            return Err(anyhow::anyhow!("Server URL cannot be empty"));
+        }
+
+        if self.username.is_empty() {
+            return Err(anyhow::anyhow!("Username cannot be empty"));
+        }
+
+        if self.password.is_empty() {
+            return Err(anyhow::anyhow!("Password cannot be empty"));
+        }
+
+        if self.watch_folders.is_empty() {
+            return Err(anyhow::anyhow!("At least one watch folder must be specified"));
+        }
+
+        // Validate URL format
+        if !self.server_url.starts_with("http://") && !self.server_url.starts_with("https://") {
+            return Err(anyhow::anyhow!("Server URL must start with http:// or https://"));
+        }
+
+        Ok(())
+    }
+
+    /// Returns the base URL for WebDAV operations
+    pub fn webdav_url(&self) -> String {
+        let mut url = self.server_url.trim_end_matches('/').to_string();
+        
+        // Add WebDAV path based on server type
+        match self.server_type.as_deref() {
+            Some("nextcloud") => {
+                if !url.contains("/remote.php/dav/files/") {
+                    url.push_str(&format!("/remote.php/dav/files/{}", self.username));
+                }
+            }
+            Some("owncloud") => {
+                if !url.contains("/remote.php/webdav") {
+                    url.push_str("/remote.php/webdav");
+                }
+            }
+            _ => {
+                // Generic WebDAV - use the URL as provided
+            }
+        }
+        
+        url
+    }
+
+    /// Checks if a file extension is supported
+    pub fn is_supported_extension(&self, filename: &str) -> bool {
+        if self.file_extensions.is_empty() {
+            return true; // If no extensions specified, support all
+        }
+
+        let extension = filename.split('.').last().unwrap_or("");
+        self.file_extensions.iter().any(|ext| ext.eq_ignore_ascii_case(extension))
+    }
+
+    /// Gets the timeout duration
+    pub fn timeout(&self) -> std::time::Duration {
+        std::time::Duration::from_secs(self.timeout_seconds)
+    }
+}

src/services/webdav/connection.rs

@@ -0,0 +1,307 @@
+use anyhow::{anyhow, Result};
+use reqwest::{Client, Method};
+use std::time::Duration;
+use tokio::time::sleep;
+use tracing::{debug, error, info, warn};
+
+use crate::models::{WebDAVConnectionResult, WebDAVTestConnection};
+use super::config::{WebDAVConfig, RetryConfig};
+
+pub struct WebDAVConnection {
+    client: Client,
+    config: WebDAVConfig,
+    retry_config: RetryConfig,
+}
+
+impl WebDAVConnection {
+    pub fn new(config: WebDAVConfig, retry_config: RetryConfig) -> Result<Self> {
+        // Validate configuration first
+        config.validate()?;
+        let client = Client::builder()
+            .timeout(config.timeout())
+            .build()?;
+
+        Ok(Self {
+            client,
+            config,
+            retry_config,
+        })
+    }
+
+    /// Tests WebDAV connection with the provided configuration
+    pub async fn test_connection(&self) -> Result<WebDAVConnectionResult> {
+        info!("🔍 Testing WebDAV connection to: {}", self.config.server_url);
+
+        // Validate configuration first
+        if let Err(e) = self.config.validate() {
+            return Ok(WebDAVConnectionResult {
+                success: false,
+                message: format!("Configuration error: {}", e),
+                server_version: None,
+                server_type: None,
+            });
+        }
+
+        // Test basic connectivity with OPTIONS request
+        match self.test_options_request().await {
+            Ok((server_version, server_type)) => {
+                info!("✅ WebDAV connection successful");
+                Ok(WebDAVConnectionResult {
+                    success: true,
+                    message: "Connection successful".to_string(),
+                    server_version,
+                    server_type,
+                })
+            }
+            Err(e) => {
+                error!("❌ WebDAV connection failed: {}", e);
+                Ok(WebDAVConnectionResult {
+                    success: false,
+                    message: format!("Connection failed: {}", e),
+                    server_version: None,
+                    server_type: None,
+                })
+            }
+        }
+    }
+
+    /// Tests connection with provided credentials (for configuration testing)
+    pub async fn test_connection_with_config(test_config: &WebDAVTestConnection) -> Result<WebDAVConnectionResult> {
+        let config = WebDAVConfig {
+            server_url: test_config.server_url.clone(),
+            username: test_config.username.clone(),
+            password: test_config.password.clone(),
+            watch_folders: vec!["/".to_string()],
+            file_extensions: vec![],
+            timeout_seconds: 30,
+            server_type: test_config.server_type.clone(),
+        };
+
+        let connection = Self::new(config, RetryConfig::default())?;
+        connection.test_connection().await
+    }
+
+    /// Performs OPTIONS request to test basic connectivity
+    async fn test_options_request(&self) -> Result<(Option<String>, Option<String>)> {
+        let webdav_url = self.config.webdav_url();
+        
+        let response = self.client
+            .request(Method::OPTIONS, &webdav_url)
+            .basic_auth(&self.config.username, Some(&self.config.password))
+            .send()
+            .await?;
+
+        if !response.status().is_success() {
+            return Err(anyhow!(
+                "OPTIONS request failed with status: {} - {}",
+                response.status(),
+                response.text().await.unwrap_or_default()
+            ));
+        }
+
+        // Extract server information from headers
+        let server_version = response
+            .headers()
+            .get("server")
+            .and_then(|v| v.to_str().ok())
+            .map(|s| s.to_string());
+
+        let server_type = self.detect_server_type(&response, &server_version).await;
+
+        Ok((server_version, server_type))
+    }
+
+    /// Detects the WebDAV server type based on response headers and capabilities
+    async fn detect_server_type(
+        &self,
+        response: &reqwest::Response,
+        server_version: &Option<String>,
+    ) -> Option<String> {
+        // Check server header first
+        if let Some(ref server) = server_version {
+            let server_lower = server.to_lowercase();
+            if server_lower.contains("nextcloud") {
+                return Some("nextcloud".to_string());
+            }
+            if server_lower.contains("owncloud") {
+                return Some("owncloud".to_string());
+            }
+            if server_lower.contains("apache") || server_lower.contains("nginx") {
+                // Could be generic WebDAV
+            }
+        }
+
+        // Check DAV capabilities
+        if let Some(dav_header) = response.headers().get("dav") {
+            if let Ok(dav_str) = dav_header.to_str() {
+                debug!("DAV capabilities: {}", dav_str);
+                // Different servers expose different DAV levels
+                if dav_str.contains("3") {
+                    return Some("webdav_level_3".to_string());
+                }
+            }
+        }
+
+        // Test for Nextcloud/ownCloud specific endpoints
+        if self.test_nextcloud_capabilities().await.is_ok() {
+            return Some("nextcloud".to_string());
+        }
+
+        Some("generic".to_string())
+    }
+
+    /// Tests for Nextcloud-specific capabilities
+    async fn test_nextcloud_capabilities(&self) -> Result<()> {
+        let capabilities_url = format!("{}/ocs/v1.php/cloud/capabilities", 
+            self.config.server_url.trim_end_matches('/'));
+
+        let response = self.client
+            .get(&capabilities_url)
+            .basic_auth(&self.config.username, Some(&self.config.password))
+            .header("OCS-APIRequest", "true")
+            .send()
+            .await?;
+
+        if response.status().is_success() {
+            debug!("Nextcloud capabilities endpoint accessible");
+            Ok(())
+        } else {
+            Err(anyhow!("Nextcloud capabilities not accessible"))
+        }
+    }
+
+    /// Tests PROPFIND request on root directory
+    pub async fn test_propfind(&self, path: &str) -> Result<()> {
+        let url = format!("{}{}", self.config.webdav_url(), path);
+        
+        let propfind_body = r#"<?xml version="1.0" encoding="utf-8"?>
+            <D:propfind xmlns:D="DAV:">
+                <D:prop>
+                    <D:displayname/>
+                    <D:getcontentlength/>
+                    <D:getlastmodified/>
+                    <D:getetag/>
+                    <D:resourcetype/>
+                </D:prop>
+            </D:propfind>"#;
+
+        let response = self.client
+            .request(Method::from_bytes(b"PROPFIND")?)
+            .url(&url)
+            .basic_auth(&self.config.username, Some(&self.config.password))
+            .header("Depth", "1")
+            .header("Content-Type", "application/xml")
+            .body(propfind_body)
+            .send()
+            .await?;
+
+        if response.status().as_u16() == 207 {
+            debug!("PROPFIND successful for path: {}", path);
+            Ok(())
+        } else {
+            Err(anyhow!(
+                "PROPFIND failed for path '{}' with status: {} - {}",
+                path,
+                response.status(),
+                response.text().await.unwrap_or_default()
+            ))
+        }
+    }
+
+    /// Performs authenticated request with retry logic
+    pub async fn authenticated_request(
+        &self,
+        method: Method,
+        url: &str,
+        body: Option<String>,
+        headers: Option<Vec<(&str, &str)>>,
+    ) -> Result<reqwest::Response> {
+        let mut attempt = 0;
+        let mut delay = self.retry_config.initial_delay_ms;
+
+        loop {
+            let mut request = self.client
+                .request(method.clone(), url)
+                .basic_auth(&self.config.username, Some(&self.config.password));
+
+            if let Some(ref body_content) = body {
+                request = request.body(body_content.clone());
+            }
+
+            if let Some(ref headers_list) = headers {
+                for (key, value) in headers_list {
+                    request = request.header(*key, *value);
+                }
+            }
+
+            match request.send().await {
+                Ok(response) => {
+                    let status = response.status();
+                    
+                    if status.is_success() || status.as_u16() == 207 {
+                        return Ok(response);
+                    }
+
+                    // Handle rate limiting
+                    if status.as_u16() == 429 {
+                        warn!("Rate limited, backing off for {}ms", self.retry_config.rate_limit_backoff_ms);
+                        sleep(Duration::from_millis(self.retry_config.rate_limit_backoff_ms)).await;
+                        continue;
+                    }
+
+                    // Handle client errors (don't retry)
+                    if status.is_client_error() && status.as_u16() != 429 {
+                        return Err(anyhow!("Client error: {} - {}", status, 
+                            response.text().await.unwrap_or_default()));
+                    }
+
+                    // Handle server errors (retry)
+                    if status.is_server_error() && attempt < self.retry_config.max_retries {
+                        warn!("Server error {}, retrying in {}ms (attempt {}/{})", 
+                            status, delay, attempt + 1, self.retry_config.max_retries);
+                        
+                        sleep(Duration::from_millis(delay)).await;
+                        delay = std::cmp::min(
+                            (delay as f64 * self.retry_config.backoff_multiplier) as u64,
+                            self.retry_config.max_delay_ms
+                        );
+                        attempt += 1;
+                        continue;
+                    }
+
+                    return Err(anyhow!("Request failed: {} - {}", status,
+                        response.text().await.unwrap_or_default()));
+                }
+                Err(e) => {
+                    if attempt < self.retry_config.max_retries {
+                        warn!("Request error: {}, retrying in {}ms (attempt {}/{})", 
+                            e, delay, attempt + 1, self.retry_config.max_retries);
+                        
+                        sleep(Duration::from_millis(delay)).await;
+                        delay = std::cmp::min(
+                            (delay as f64 * self.retry_config.backoff_multiplier) as u64,
+                            self.retry_config.max_delay_ms
+                        );
+                        attempt += 1;
+                        continue;
+                    }
+
+                    return Err(anyhow!("Request failed after {} attempts: {}", 
+                        self.retry_config.max_retries, e));
+                }
+            }
+        }
+    }
+
+    /// Gets the WebDAV URL for a specific path
+    pub fn get_url_for_path(&self, path: &str) -> String {
+        let base_url = self.config.webdav_url();
+        let clean_path = path.trim_start_matches('/');
+        
+        if clean_path.is_empty() {
+            base_url
+        } else {
+            format!("{}/{}", base_url.trim_end_matches('/'), clean_path)
+        }
+    }
+}

src/services/webdav/discovery.rs

@@ -0,0 +1,349 @@
+use anyhow::{anyhow, Result};
+use reqwest::Method;
+use std::collections::HashSet;
+use tokio::sync::Semaphore;
+use futures_util::stream::{self, StreamExt};
+use tracing::{debug, error, info, warn};
+
+use crate::models::{FileInfo, WebDAVCrawlEstimate, WebDAVFolderInfo};
+use crate::webdav_xml_parser::{parse_propfind_response, parse_propfind_response_with_directories};
+use super::config::{WebDAVConfig, ConcurrencyConfig};
+use super::connection::WebDAVConnection;
+
+pub struct WebDAVDiscovery {
+    connection: WebDAVConnection,
+    config: WebDAVConfig,
+    concurrency_config: ConcurrencyConfig,
+}
+
+impl WebDAVDiscovery {
+    pub fn new(
+        connection: WebDAVConnection, 
+        config: WebDAVConfig, 
+        concurrency_config: ConcurrencyConfig
+    ) -> Self {
+        Self { 
+            connection, 
+            config, 
+            concurrency_config 
+        }
+    }
+
+    /// Discovers files in a directory with support for pagination and filtering
+    pub async fn discover_files(&self, directory_path: &str, recursive: bool) -> Result<Vec<FileInfo>> {
+        info!("🔍 Discovering files in directory: {}", directory_path);
+        
+        if recursive {
+            self.discover_files_recursive(directory_path).await
+        } else {
+            self.discover_files_single_directory(directory_path).await
+        }
+    }
+
+    /// Discovers files in a single directory (non-recursive)
+    async fn discover_files_single_directory(&self, directory_path: &str) -> Result<Vec<FileInfo>> {
+        let url = self.connection.get_url_for_path(directory_path);
+        
+        let propfind_body = r#"<?xml version="1.0" encoding="utf-8"?>
+            <D:propfind xmlns:D="DAV:">
+                <D:prop>
+                    <D:displayname/>
+                    <D:getcontentlength/>
+                    <D:getlastmodified/>
+                    <D:getetag/>
+                    <D:resourcetype/>
+                    <D:creationdate/>
+                </D:prop>
+            </D:propfind>"#;
+
+        let response = self.connection
+            .authenticated_request(
+                Method::from_bytes(b"PROPFIND")?,
+                &url,
+                Some(propfind_body.to_string()),
+                Some(vec![
+                    ("Depth", "1"),
+                    ("Content-Type", "application/xml"),
+                ]),
+            )
+            .await?;
+
+        let body = response.text().await?;
+        let files = parse_propfind_response(&body)?;
+        
+        // Filter files based on supported extensions
+        let filtered_files: Vec<FileInfo> = files
+            .into_iter()
+            .filter(|file| {
+                !file.is_directory && self.config.is_supported_extension(&file.name)
+            })
+            .collect();
+
+        debug!("Found {} supported files in directory: {}", filtered_files.len(), directory_path);
+        Ok(filtered_files)
+    }
+
+    /// Discovers files recursively in directory tree
+    async fn discover_files_recursive(&self, root_directory: &str) -> Result<Vec<FileInfo>> {
+        let mut all_files = Vec::new();
+        let mut directories_to_scan = vec![root_directory.to_string()];
+        let semaphore = Semaphore::new(self.concurrency_config.max_concurrent_scans);
+
+        while !directories_to_scan.is_empty() {
+            let current_batch: Vec<String> = directories_to_scan
+                .drain(..)
+                .take(self.concurrency_config.max_concurrent_scans)
+                .collect();
+
+            let tasks = current_batch.into_iter().map(|dir| {
+                let semaphore = &semaphore;
+                async move {
+                    let _permit = semaphore.acquire().await.unwrap();
+                    self.scan_directory_with_subdirs(&dir).await
+                }
+            });
+
+            let results = stream::iter(tasks)
+                .buffer_unordered(self.concurrency_config.max_concurrent_scans)
+                .collect::<Vec<_>>()
+                .await;
+
+            for result in results {
+                match result {
+                    Ok((files, subdirs)) => {
+                        all_files.extend(files);
+                        directories_to_scan.extend(subdirs);
+                    }
+                    Err(e) => {
+                        warn!("Failed to scan directory: {}", e);
+                    }
+                }
+            }
+        }
+
+        info!("Recursive discovery found {} total files", all_files.len());
+        Ok(all_files)
+    }
+
+    /// Scans a directory and returns both files and subdirectories
+    async fn scan_directory_with_subdirs(&self, directory_path: &str) -> Result<(Vec<FileInfo>, Vec<String>)> {
+        let url = self.connection.get_url_for_path(directory_path);
+        
+        let propfind_body = r#"<?xml version="1.0" encoding="utf-8"?>
+            <D:propfind xmlns:D="DAV:">
+                <D:prop>
+                    <D:displayname/>
+                    <D:getcontentlength/>
+                    <D:getlastmodified/>
+                    <D:getetag/>
+                    <D:resourcetype/>
+                    <D:creationdate/>
+                </D:prop>
+            </D:propfind>"#;
+
+        let response = self.connection
+            .authenticated_request(
+                Method::from_bytes(b"PROPFIND")?,
+                &url,
+                Some(propfind_body.to_string()),
+                Some(vec![
+                    ("Depth", "1"),
+                    ("Content-Type", "application/xml"),
+                ]),
+            )
+            .await?;
+
+        let body = response.text().await?;
+        let (files, directories) = parse_propfind_response_with_directories(&body)?;
+        
+        // Filter files by supported extensions
+        let filtered_files: Vec<FileInfo> = files
+            .into_iter()
+            .filter(|file| self.config.is_supported_extension(&file.name))
+            .collect();
+
+        // Convert directory paths to full paths
+        let full_dir_paths: Vec<String> = directories
+            .into_iter()
+            .map(|dir| {
+                if directory_path == "/" {
+                    format!("/{}", dir.trim_start_matches('/'))
+                } else {
+                    format!("{}/{}", directory_path.trim_end_matches('/'), dir.trim_start_matches('/'))
+                }
+            })
+            .collect();
+
+        debug!("Directory '{}': {} files, {} subdirectories", 
+            directory_path, filtered_files.len(), full_dir_paths.len());
+            
+        Ok((filtered_files, full_dir_paths))
+    }
+
+    /// Estimates crawl time and file counts for watch folders
+    pub async fn estimate_crawl(&self) -> Result<WebDAVCrawlEstimate> {
+        info!("📊 Estimating crawl for WebDAV watch folders");
+        
+        let mut folders = Vec::new();
+        let mut total_files = 0;
+        let mut total_supported_files = 0;
+        let mut total_size_mb = 0.0;
+
+        for watch_folder in &self.config.watch_folders {
+            match self.estimate_folder(watch_folder).await {
+                Ok(folder_info) => {
+                    total_files += folder_info.total_files;
+                    total_supported_files += folder_info.supported_files;
+                    total_size_mb += folder_info.total_size_mb;
+                    folders.push(folder_info);
+                }
+                Err(e) => {
+                    warn!("Failed to estimate folder '{}': {}", watch_folder, e);
+                    // Add empty folder info for failed estimates
+                    folders.push(WebDAVFolderInfo {
+                        path: watch_folder.clone(),
+                        total_files: 0,
+                        supported_files: 0,
+                        estimated_time_hours: 0.0,
+                        total_size_mb: 0.0,
+                    });
+                }
+            }
+        }
+
+        // Estimate total time based on file count and average processing time
+        let avg_time_per_file_seconds = 2.0; // Conservative estimate
+        let total_estimated_time_hours = (total_supported_files as f32 * avg_time_per_file_seconds) / 3600.0;
+
+        Ok(WebDAVCrawlEstimate {
+            folders,
+            total_files,
+            total_supported_files,
+            total_estimated_time_hours,
+            total_size_mb,
+        })
+    }
+
+    /// Estimates file count and size for a specific folder
+    async fn estimate_folder(&self, folder_path: &str) -> Result<WebDAVFolderInfo> {
+        debug!("Estimating folder: {}", folder_path);
+        
+        // Sample a few subdirectories to estimate the total
+        let sample_files = self.discover_files_single_directory(folder_path).await?;
+        
+        // Get subdirectories for deeper estimation
+        let subdirs = self.get_subdirectories(folder_path).await?;
+        
+        let mut total_files = sample_files.len() as i64;
+        let mut total_size: i64 = sample_files.iter().map(|f| f.size).sum();
+        
+        // Sample a few subdirectories to extrapolate
+        let sample_size = std::cmp::min(5, subdirs.len());
+        if sample_size > 0 {
+            let mut sample_total = 0i64;
+            
+            for subdir in subdirs.iter().take(sample_size) {
+                if let Ok(subdir_files) = self.discover_files_single_directory(subdir).await {
+                    sample_total += subdir_files.len() as i64;
+                }
+            }
+            
+            // Extrapolate based on sample
+            if sample_total > 0 {
+                let avg_files_per_subdir = sample_total as f64 / sample_size as f64;
+                total_files += (avg_files_per_subdir * subdirs.len() as f64) as i64;
+            }
+        }
+
+        // Filter for supported files
+        let supported_files = (total_files as f64 * self.calculate_support_ratio(&sample_files)) as i64;
+        
+        let total_size_mb = total_size as f64 / (1024.0 * 1024.0);
+        let estimated_time_hours = (supported_files as f32 * 2.0) / 3600.0; // 2 seconds per file
+
+        Ok(WebDAVFolderInfo {
+            path: folder_path.to_string(),
+            total_files,
+            supported_files,
+            estimated_time_hours,
+            total_size_mb,
+        })
+    }
+
+    /// Gets subdirectories for a given path
+    async fn get_subdirectories(&self, directory_path: &str) -> Result<Vec<String>> {
+        let url = self.connection.get_url_for_path(directory_path);
+        
+        let propfind_body = r#"<?xml version="1.0" encoding="utf-8"?>
+            <D:propfind xmlns:D="DAV:">
+                <D:prop>
+                    <D:resourcetype/>
+                </D:prop>
+            </D:propfind>"#;
+
+        let response = self.connection
+            .authenticated_request(
+                Method::from_bytes(b"PROPFIND")?,
+                &url,
+                Some(propfind_body.to_string()),
+                Some(vec![
+                    ("Depth", "1"),
+                    ("Content-Type", "application/xml"),
+                ]),
+            )
+            .await?;
+
+        let body = response.text().await?;
+        let (_, directories) = parse_propfind_response_with_directories(&body)?;
+        
+        Ok(directories)
+    }
+
+    /// Calculates the ratio of supported files in a sample
+    fn calculate_support_ratio(&self, sample_files: &[FileInfo]) -> f64 {
+        if sample_files.is_empty() {
+            return 1.0; // Assume all files are supported if no sample
+        }
+
+        let supported_count = sample_files
+            .iter()
+            .filter(|file| self.config.is_supported_extension(&file.name))
+            .count();
+
+        supported_count as f64 / sample_files.len() as f64
+    }
+
+    /// Filters files by last modified date (for incremental syncs)
+    pub fn filter_files_by_date(&self, files: Vec<FileInfo>, since: chrono::DateTime<chrono::Utc>) -> Vec<FileInfo> {
+        files
+            .into_iter()
+            .filter(|file| {
+                file.last_modified
+                    .map(|modified| modified > since)
+                    .unwrap_or(true) // Include files without modification date
+            })
+            .collect()
+    }
+
+    /// Deduplicates files by ETag or path
+    pub fn deduplicate_files(&self, files: Vec<FileInfo>) -> Vec<FileInfo> {
+        let mut seen_etags = HashSet::new();
+        let mut seen_paths = HashSet::new();
+        let mut deduplicated = Vec::new();
+
+        for file in files {
+            let is_duplicate = if !file.etag.is_empty() {
+                !seen_etags.insert(file.etag.clone())
+            } else {
+                !seen_paths.insert(file.path.clone())
+            };
+
+            if !is_duplicate {
+                deduplicated.push(file);
+            }
+        }
+
+        debug!("Deduplicated {} files", deduplicated.len());
+        deduplicated
+    }
+}

src/services/webdav/mod.rs

@@ -0,0 +1,17 @@
+// WebDAV service modules organized by functionality
+
+pub mod config;
+pub mod connection;
+pub mod discovery;
+pub mod validation;
+pub mod service;
+
+// Re-export main types for convenience
+pub use config::{WebDAVConfig, RetryConfig, ConcurrencyConfig};
+pub use connection::WebDAVConnection;
+pub use discovery::WebDAVDiscovery;
+pub use validation::{
+    WebDAVValidator, ValidationReport, ValidationIssue, ValidationIssueType, 
+    ValidationSeverity, ValidationRecommendation, ValidationAction, ValidationSummary
+};
+pub use service::{WebDAVService, ServerCapabilities, HealthStatus, test_webdav_connection};

src/services/webdav/service.rs

@@ -0,0 +1,391 @@
+use anyhow::{anyhow, Result};
+use std::sync::Arc;
+use tokio::sync::Semaphore;
+use tracing::{debug, error, info, warn};
+
+use crate::models::{
+    FileInfo, WebDAVConnectionResult, WebDAVCrawlEstimate, WebDAVTestConnection,
+};
+
+use super::config::{WebDAVConfig, RetryConfig, ConcurrencyConfig};
+use super::connection::WebDAVConnection;
+use super::discovery::WebDAVDiscovery;
+use super::validation::{WebDAVValidator, ValidationReport};
+
+/// Main WebDAV service that coordinates all WebDAV operations
+pub struct WebDAVService {
+    connection: Arc<WebDAVConnection>,
+    discovery: Arc<WebDAVDiscovery>,
+    validator: Arc<WebDAVValidator>,
+    config: WebDAVConfig,
+    retry_config: RetryConfig,
+    concurrency_config: ConcurrencyConfig,
+    scan_semaphore: Arc<Semaphore>,
+    download_semaphore: Arc<Semaphore>,
+}
+
+impl WebDAVService {
+    /// Creates a new WebDAV service with default configurations
+    pub fn new(config: WebDAVConfig) -> Result<Self> {
+        Self::new_with_configs(config, RetryConfig::default(), ConcurrencyConfig::default())
+    }
+
+    /// Creates a new WebDAV service with custom retry configuration
+    pub fn new_with_retry(config: WebDAVConfig, retry_config: RetryConfig) -> Result<Self> {
+        Self::new_with_configs(config, retry_config, ConcurrencyConfig::default())
+    }
+
+    /// Creates a new WebDAV service with all custom configurations
+    pub fn new_with_configs(
+        config: WebDAVConfig, 
+        retry_config: RetryConfig, 
+        concurrency_config: ConcurrencyConfig
+    ) -> Result<Self> {
+        // Validate configuration
+        config.validate()?;
+
+        // Create connection handler
+        let connection = Arc::new(WebDAVConnection::new(config.clone(), retry_config.clone())?);
+        
+        // Create discovery handler
+        let discovery = Arc::new(WebDAVDiscovery::new(
+            connection.as_ref().clone(),
+            config.clone(),
+            concurrency_config.clone(),
+        ));
+
+        // Create validator
+        let validator = Arc::new(WebDAVValidator::new(
+            connection.as_ref().clone(),
+            config.clone(),
+        ));
+
+        // Create semaphores for concurrency control
+        let scan_semaphore = Arc::new(Semaphore::new(concurrency_config.max_concurrent_scans));
+        let download_semaphore = Arc::new(Semaphore::new(concurrency_config.max_concurrent_downloads));
+
+        Ok(Self {
+            connection,
+            discovery,
+            validator,
+            config,
+            retry_config,
+            concurrency_config,
+            scan_semaphore,
+            download_semaphore,
+        })
+    }
+
+    /// Tests the WebDAV connection
+    pub async fn test_connection(&self) -> Result<WebDAVConnectionResult> {
+        info!("🔍 Testing WebDAV connection for service");
+        self.connection.test_connection().await
+    }
+
+    /// Tests WebDAV connection with provided configuration (static method)
+    pub async fn test_connection_with_config(test_config: &WebDAVTestConnection) -> Result<WebDAVConnectionResult> {
+        WebDAVConnection::test_connection_with_config(test_config).await
+    }
+}
+
+/// Tests WebDAV connection with provided configuration (standalone function for backward compatibility)
+pub async fn test_webdav_connection(test_config: &WebDAVTestConnection) -> Result<WebDAVConnectionResult> {
+    WebDAVConnection::test_connection_with_config(test_config).await
+}
+
+impl WebDAVService {
+    /// Performs a comprehensive system validation
+    pub async fn validate_system(&self) -> Result<ValidationReport> {
+        info!("🔍 Performing comprehensive WebDAV system validation");
+        self.validator.validate_system().await
+    }
+
+    /// Estimates crawl time and resource requirements
+    pub async fn estimate_crawl(&self) -> Result<WebDAVCrawlEstimate> {
+        info!("📊 Estimating WebDAV crawl requirements");
+        self.discovery.estimate_crawl().await
+    }
+
+    /// Discovers all files in watch folders
+    pub async fn discover_all_files(&self) -> Result<Vec<FileInfo>> {
+        info!("🔍 Discovering all files in watch folders");
+        let mut all_files = Vec::new();
+
+        for watch_folder in &self.config.watch_folders {
+            info!("📁 Scanning watch folder: {}", watch_folder);
+            
+            match self.discovery.discover_files(watch_folder, true).await {
+                Ok(files) => {
+                    info!("✅ Found {} files in {}", files.len(), watch_folder);
+                    all_files.extend(files);
+                }
+                Err(e) => {
+                    error!("❌ Failed to scan watch folder '{}': {}", watch_folder, e);
+                    return Err(anyhow!("Failed to scan watch folder '{}': {}", watch_folder, e));
+                }
+            }
+        }
+
+        // Deduplicate files across folders
+        let deduplicated_files = self.discovery.deduplicate_files(all_files);
+        
+        info!("🎯 Total unique files discovered: {}", deduplicated_files.len());
+        Ok(deduplicated_files)
+    }
+
+    /// Discovers files changed since a specific date (for incremental syncs)
+    pub async fn discover_changed_files(&self, since: chrono::DateTime<chrono::Utc>) -> Result<Vec<FileInfo>> {
+        info!("🔍 Discovering files changed since: {}", since);
+        
+        let all_files = self.discover_all_files().await?;
+        let changed_files = self.discovery.filter_files_by_date(all_files, since);
+        
+        info!("📈 Found {} files changed since {}", changed_files.len(), since);
+        Ok(changed_files)
+    }
+
+    /// Discovers files in a specific directory
+    pub async fn discover_files_in_directory(&self, directory_path: &str, recursive: bool) -> Result<Vec<FileInfo>> {
+        info!("🔍 Discovering files in directory: {} (recursive: {})", directory_path, recursive);
+        self.discovery.discover_files(directory_path, recursive).await
+    }
+
+    /// Downloads a file from WebDAV server
+    pub async fn download_file(&self, file_info: &FileInfo) -> Result<Vec<u8>> {
+        let _permit = self.download_semaphore.acquire().await?;
+        
+        debug!("⬇️ Downloading file: {}", file_info.path);
+        
+        let url = self.connection.get_url_for_path(&file_info.path);
+        
+        let response = self.connection
+            .authenticated_request(
+                reqwest::Method::GET,
+                &url,
+                None,
+                None,
+            )
+            .await?;
+
+        if !response.status().is_success() {
+            return Err(anyhow!(
+                "Failed to download file '{}': HTTP {}",
+                file_info.path,
+                response.status()
+            ));
+        }
+
+        let content = response.bytes().await?;
+        debug!("✅ Downloaded {} bytes for file: {}", content.len(), file_info.path);
+        
+        Ok(content.to_vec())
+    }
+
+    /// Downloads multiple files concurrently
+    pub async fn download_files(&self, files: &[FileInfo]) -> Result<Vec<(FileInfo, Result<Vec<u8>>)>> {
+        info!("⬇️ Downloading {} files concurrently", files.len());
+        
+        let tasks = files.iter().map(|file| {
+            let file_clone = file.clone();
+            let service_clone = self.clone();
+            
+            async move {
+                let result = service_clone.download_file(&file_clone).await;
+                (file_clone, result)
+            }
+        });
+
+        let results = futures_util::future::join_all(tasks).await;
+        
+        let success_count = results.iter().filter(|(_, result)| result.is_ok()).count();
+        let failure_count = results.len() - success_count;
+        
+        info!("📊 Download completed: {} successful, {} failed", success_count, failure_count);
+        
+        Ok(results)
+    }
+
+    /// Gets file metadata without downloading content
+    pub async fn get_file_metadata(&self, file_path: &str) -> Result<FileInfo> {
+        debug!("📋 Getting metadata for file: {}", file_path);
+        
+        let url = self.connection.get_url_for_path(file_path);
+        
+        let propfind_body = r#"<?xml version="1.0" encoding="utf-8"?>
+            <D:propfind xmlns:D="DAV:">
+                <D:prop>
+                    <D:displayname/>
+                    <D:getcontentlength/>
+                    <D:getlastmodified/>
+                    <D:getetag/>
+                    <D:resourcetype/>
+                    <D:creationdate/>
+                </D:prop>
+            </D:propfind>"#;
+
+        let response = self.connection
+            .authenticated_request(
+                reqwest::Method::from_bytes(b"PROPFIND")?,
+                &url,
+                Some(propfind_body.to_string()),
+                Some(vec![
+                    ("Depth", "0"),
+                    ("Content-Type", "application/xml"),
+                ]),
+            )
+            .await?;
+
+        let body = response.text().await?;
+        let files = crate::webdav_xml_parser::parse_propfind_response(&body)?;
+        
+        files.into_iter()
+            .find(|f| f.path == file_path)
+            .ok_or_else(|| anyhow!("File metadata not found: {}", file_path))
+    }
+
+    /// Checks if a file exists on the WebDAV server
+    pub async fn file_exists(&self, file_path: &str) -> Result<bool> {
+        match self.get_file_metadata(file_path).await {
+            Ok(_) => Ok(true),
+            Err(_) => Ok(false),
+        }
+    }
+
+    /// Gets the server capabilities and features
+    pub async fn get_server_capabilities(&self) -> Result<ServerCapabilities> {
+        debug!("🔍 Checking server capabilities");
+        
+        let options_response = self.connection
+            .authenticated_request(
+                reqwest::Method::OPTIONS,
+                &self.config.webdav_url(),
+                None,
+                None,
+            )
+            .await?;
+
+        let dav_header = options_response
+            .headers()
+            .get("dav")
+            .and_then(|v| v.to_str().ok())
+            .unwrap_or("")
+            .to_string();
+
+        let allow_header = options_response
+            .headers()
+            .get("allow")
+            .and_then(|v| v.to_str().ok())
+            .unwrap_or("")
+            .to_string();
+
+        let server_header = options_response
+            .headers()
+            .get("server")
+            .and_then(|v| v.to_str().ok())
+            .map(|s| s.to_string());
+
+        Ok(ServerCapabilities {
+            dav_compliance: dav_header,
+            allowed_methods: allow_header,
+            server_software: server_header,
+            supports_etag: dav_header.contains("1") || dav_header.contains("2"),
+            supports_depth_infinity: dav_header.contains("1"),
+        })
+    }
+
+    /// Performs a health check on the WebDAV service
+    pub async fn health_check(&self) -> Result<HealthStatus> {
+        info!("🏥 Performing WebDAV service health check");
+        
+        let start_time = std::time::Instant::now();
+        
+        // Test basic connectivity
+        let connection_result = self.test_connection().await?;
+        if !connection_result.success {
+            return Ok(HealthStatus {
+                healthy: false,
+                message: format!("Connection failed: {}", connection_result.message),
+                response_time_ms: start_time.elapsed().as_millis() as u64,
+                details: None,
+            });
+        }
+
+        // Test each watch folder
+        for folder in &self.config.watch_folders {
+            if let Err(e) = self.connection.test_propfind(folder).await {
+                return Ok(HealthStatus {
+                    healthy: false,
+                    message: format!("Watch folder '{}' is inaccessible: {}", folder, e),
+                    response_time_ms: start_time.elapsed().as_millis() as u64,
+                    details: Some(serde_json::json!({
+                        "failed_folder": folder,
+                        "error": e.to_string()
+                    })),
+                });
+            }
+        }
+
+        let response_time = start_time.elapsed().as_millis() as u64;
+        
+        Ok(HealthStatus {
+            healthy: true,
+            message: "All systems operational".to_string(),
+            response_time_ms: response_time,
+            details: Some(serde_json::json!({
+                "tested_folders": self.config.watch_folders,
+                "server_type": connection_result.server_type,
+                "server_version": connection_result.server_version
+            })),
+        })
+    }
+
+    /// Gets configuration information
+    pub fn get_config(&self) -> &WebDAVConfig {
+        &self.config
+    }
+
+    /// Gets retry configuration
+    pub fn get_retry_config(&self) -> &RetryConfig {
+        &self.retry_config
+    }
+
+    /// Gets concurrency configuration
+    pub fn get_concurrency_config(&self) -> &ConcurrencyConfig {
+        &self.concurrency_config
+    }
+}
+
+// Implement Clone to allow sharing the service
+impl Clone for WebDAVService {
+    fn clone(&self) -> Self {
+        Self {
+            connection: Arc::clone(&self.connection),
+            discovery: Arc::clone(&self.discovery),
+            validator: Arc::clone(&self.validator),
+            config: self.config.clone(),
+            retry_config: self.retry_config.clone(),
+            concurrency_config: self.concurrency_config.clone(),
+            scan_semaphore: Arc::clone(&self.scan_semaphore),
+            download_semaphore: Arc::clone(&self.download_semaphore),
+        }
+    }
+}
+
+/// Server capabilities information
+#[derive(Debug, Clone)]
+pub struct ServerCapabilities {
+    pub dav_compliance: String,
+    pub allowed_methods: String,
+    pub server_software: Option<String>,
+    pub supports_etag: bool,
+    pub supports_depth_infinity: bool,
+}
+
+/// Health status information
+#[derive(Debug, Clone)]
+pub struct HealthStatus {
+    pub healthy: bool,
+    pub message: String,
+    pub response_time_ms: u64,
+    pub details: Option<serde_json::Value>,
+}

src/services/webdav/validation.rs

@@ -0,0 +1,352 @@
+use anyhow::{anyhow, Result};
+use serde::{Deserialize, Serialize};
+use std::collections::HashMap;
+use tracing::{debug, error, info, warn};
+
+use super::config::WebDAVConfig;
+use super::connection::WebDAVConnection;
+
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct ValidationReport {
+    pub overall_health_score: i32, // 0-100
+    pub issues: Vec<ValidationIssue>,
+    pub recommendations: Vec<ValidationRecommendation>,
+    pub summary: ValidationSummary,
+}
+
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct ValidationIssue {
+    pub issue_type: ValidationIssueType,
+    pub severity: ValidationSeverity,
+    pub directory_path: String,
+    pub description: String,
+    pub details: Option<serde_json::Value>,
+    pub detected_at: chrono::DateTime<chrono::Utc>,
+}
+
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub enum ValidationIssueType {
+    /// Directory exists on server but not in our tracking
+    Untracked,
+    /// Directory in our tracking but missing on server  
+    Missing,
+    /// ETag mismatch between server and our cache
+    ETagMismatch,
+    /// Directory hasn't been scanned in a very long time
+    Stale,
+    /// Server errors when accessing directory
+    Inaccessible,
+    /// ETag support seems unreliable for this directory
+    ETagUnreliable,
+}
+
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub enum ValidationSeverity {
+    Info,    // No action needed, just FYI
+    Warning, // Should investigate but not urgent
+    Error,   // Needs immediate attention
+    Critical, // System integrity at risk
+}
+
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct ValidationRecommendation {
+    pub action: ValidationAction,
+    pub reason: String,
+    pub affected_directories: Vec<String>,
+    pub priority: ValidationSeverity,
+}
+
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub enum ValidationAction {
+    /// Run a deep scan of specific directories
+    DeepScanRequired,
+    /// Clear and rebuild directory tracking
+    RebuildTracking,
+    /// ETag support is unreliable, switch to periodic scans
+    DisableETagOptimization,
+    /// Clean up orphaned database entries
+    CleanupDatabase,
+    /// Server configuration issue needs attention
+    CheckServerConfiguration,
+    /// No action needed, system is healthy
+    NoActionRequired,
+}
+
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct ValidationSummary {
+    pub total_directories_checked: usize,
+    pub healthy_directories: usize,
+    pub directories_with_issues: usize,
+    pub critical_issues: usize,
+    pub warning_issues: usize,
+    pub info_issues: usize,
+    pub validation_duration_ms: u64,
+}
+
+pub struct WebDAVValidator {
+    connection: WebDAVConnection,
+    config: WebDAVConfig,
+}
+
+impl WebDAVValidator {
+    pub fn new(connection: WebDAVConnection, config: WebDAVConfig) -> Self {
+        Self { connection, config }
+    }
+
+    /// Performs comprehensive validation of WebDAV setup and directory tracking
+    pub async fn validate_system(&self) -> Result<ValidationReport> {
+        let start_time = std::time::Instant::now();
+        info!("🔍 Starting WebDAV system validation");
+
+        let mut issues = Vec::new();
+        let mut total_checked = 0;
+
+        // Test basic connectivity
+        match self.connection.test_connection().await {
+            Ok(result) if !result.success => {
+                issues.push(ValidationIssue {
+                    issue_type: ValidationIssueType::Inaccessible,
+                    severity: ValidationSeverity::Critical,
+                    directory_path: "/".to_string(),
+                    description: format!("WebDAV server connection failed: {}", result.message),
+                    details: None,
+                    detected_at: chrono::Utc::now(),
+                });
+            }
+            Err(e) => {
+                issues.push(ValidationIssue {
+                    issue_type: ValidationIssueType::Inaccessible,
+                    severity: ValidationSeverity::Critical,
+                    directory_path: "/".to_string(),
+                    description: format!("WebDAV server connectivity test failed: {}", e),
+                    details: None,
+                    detected_at: chrono::Utc::now(),
+                });
+            }
+            _ => {
+                debug!("✅ Basic connectivity test passed");
+            }
+        }
+
+        // Validate each watch folder
+        for folder in &self.config.watch_folders {
+            total_checked += 1;
+            if let Err(e) = self.validate_watch_folder(folder, &mut issues).await {
+                warn!("Failed to validate watch folder '{}': {}", folder, e);
+            }
+        }
+
+        // Test ETag reliability
+        self.validate_etag_support(&mut issues).await?;
+
+        // Generate recommendations based on issues
+        let recommendations = self.generate_recommendations(&issues);
+
+        let validation_duration = start_time.elapsed().as_millis() as u64;
+        let health_score = self.calculate_health_score(&issues);
+
+        let summary = ValidationSummary {
+            total_directories_checked: total_checked,
+            healthy_directories: total_checked - issues.len(),
+            directories_with_issues: issues.len(),
+            critical_issues: issues.iter().filter(|i| matches!(i.severity, ValidationSeverity::Critical)).count(),
+            warning_issues: issues.iter().filter(|i| matches!(i.severity, ValidationSeverity::Warning)).count(),
+            info_issues: issues.iter().filter(|i| matches!(i.severity, ValidationSeverity::Info)).count(),
+            validation_duration_ms: validation_duration,
+        };
+
+        info!("✅ WebDAV validation completed in {}ms. Health score: {}/100", 
+            validation_duration, health_score);
+
+        Ok(ValidationReport {
+            overall_health_score: health_score,
+            issues,
+            recommendations,
+            summary,
+        })
+    }
+
+    /// Validates a specific watch folder
+    async fn validate_watch_folder(&self, folder: &str, issues: &mut Vec<ValidationIssue>) -> Result<()> {
+        debug!("Validating watch folder: {}", folder);
+
+        // Test PROPFIND access
+        match self.connection.test_propfind(folder).await {
+            Ok(_) => {
+                debug!("✅ Watch folder '{}' is accessible", folder);
+            }
+            Err(e) => {
+                issues.push(ValidationIssue {
+                    issue_type: ValidationIssueType::Inaccessible,
+                    severity: ValidationSeverity::Error,
+                    directory_path: folder.to_string(),
+                    description: format!("Cannot access watch folder: {}", e),
+                    details: Some(serde_json::json!({
+                        "error": e.to_string(),
+                        "folder": folder
+                    })),
+                    detected_at: chrono::Utc::now(),
+                });
+            }
+        }
+
+        Ok(())
+    }
+
+    /// Tests ETag support reliability
+    async fn validate_etag_support(&self, issues: &mut Vec<ValidationIssue>) -> Result<()> {
+        debug!("Testing ETag support reliability");
+
+        // Test ETag consistency across multiple requests
+        for folder in &self.config.watch_folders {
+            if let Err(e) = self.test_etag_consistency(folder, issues).await {
+                warn!("ETag consistency test failed for '{}': {}", folder, e);
+            }
+        }
+
+        Ok(())
+    }
+
+    /// Tests ETag consistency for a specific folder
+    async fn test_etag_consistency(&self, folder: &str, issues: &mut Vec<ValidationIssue>) -> Result<()> {
+        // Make two consecutive PROPFIND requests and compare ETags
+        let etag1 = self.get_folder_etag(folder).await?;
+        tokio::time::sleep(std::time::Duration::from_millis(100)).await;
+        let etag2 = self.get_folder_etag(folder).await?;
+
+        if etag1 != etag2 && etag1.is_some() && etag2.is_some() {
+            issues.push(ValidationIssue {
+                issue_type: ValidationIssueType::ETagUnreliable,
+                severity: ValidationSeverity::Warning,
+                directory_path: folder.to_string(),
+                description: "ETag values are inconsistent across requests".to_string(),
+                details: Some(serde_json::json!({
+                    "etag1": etag1,
+                    "etag2": etag2,
+                    "folder": folder
+                })),
+                detected_at: chrono::Utc::now(),
+            });
+        }
+
+        Ok(())
+    }
+
+    /// Gets the ETag for a folder
+    async fn get_folder_etag(&self, folder: &str) -> Result<Option<String>> {
+        let url = self.connection.get_url_for_path(folder);
+        
+        let propfind_body = r#"<?xml version="1.0" encoding="utf-8"?>
+            <D:propfind xmlns:D="DAV:">
+                <D:prop>
+                    <D:getetag/>
+                </D:prop>
+            </D:propfind>"#;
+
+        let response = self.connection
+            .authenticated_request(
+                reqwest::Method::from_bytes(b"PROPFIND")?,
+                &url,
+                Some(propfind_body.to_string()),
+                Some(vec![
+                    ("Depth", "0"),
+                    ("Content-Type", "application/xml"),
+                ]),
+            )
+            .await?;
+
+        let body = response.text().await?;
+        
+        // Parse ETag from XML response (simplified)
+        if let Some(start) = body.find("<D:getetag>") {
+            if let Some(end) = body[start..].find("</D:getetag>") {
+                let etag = &body[start + 11..start + end];
+                return Ok(Some(etag.trim_matches('"').to_string()));
+            }
+        }
+
+        Ok(None)
+    }
+
+    /// Generates recommendations based on detected issues
+    fn generate_recommendations(&self, issues: &Vec<ValidationIssue>) -> Vec<ValidationRecommendation> {
+        let mut recommendations = Vec::new();
+        let mut directories_by_issue: HashMap<ValidationIssueType, Vec<String>> = HashMap::new();
+
+        // Group directories by issue type
+        for issue in issues {
+            directories_by_issue
+                .entry(issue.issue_type.clone())
+                .or_insert_with(Vec::new)
+                .push(issue.directory_path.clone());
+        }
+
+        // Generate recommendations for each issue type
+        for (issue_type, directories) in directories_by_issue {
+            let recommendation = match issue_type {
+                ValidationIssueType::Inaccessible => ValidationRecommendation {
+                    action: ValidationAction::CheckServerConfiguration,
+                    reason: "Some directories are inaccessible. Check server configuration and permissions.".to_string(),
+                    affected_directories: directories,
+                    priority: ValidationSeverity::Critical,
+                },
+                ValidationIssueType::ETagUnreliable => ValidationRecommendation {
+                    action: ValidationAction::DisableETagOptimization,
+                    reason: "ETag support appears unreliable. Consider disabling ETag optimization.".to_string(),
+                    affected_directories: directories,
+                    priority: ValidationSeverity::Warning,
+                },
+                ValidationIssueType::Missing => ValidationRecommendation {
+                    action: ValidationAction::CleanupDatabase,
+                    reason: "Some tracked directories no longer exist on the server.".to_string(),
+                    affected_directories: directories,
+                    priority: ValidationSeverity::Warning,
+                },
+                ValidationIssueType::Stale => ValidationRecommendation {
+                    action: ValidationAction::DeepScanRequired,
+                    reason: "Some directories haven't been scanned recently.".to_string(),
+                    affected_directories: directories,
+                    priority: ValidationSeverity::Info,
+                },
+                _ => ValidationRecommendation {
+                    action: ValidationAction::DeepScanRequired,
+                    reason: "General validation issues detected.".to_string(),
+                    affected_directories: directories,
+                    priority: ValidationSeverity::Warning,
+                },
+            };
+            recommendations.push(recommendation);
+        }
+
+        if recommendations.is_empty() {
+            recommendations.push(ValidationRecommendation {
+                action: ValidationAction::NoActionRequired,
+                reason: "System validation passed successfully.".to_string(),
+                affected_directories: Vec::new(),
+                priority: ValidationSeverity::Info,
+            });
+        }
+
+        recommendations
+    }
+
+    /// Calculates overall health score based on issues
+    fn calculate_health_score(&self, issues: &Vec<ValidationIssue>) -> i32 {
+        if issues.is_empty() {
+            return 100;
+        }
+
+        let mut penalty = 0;
+        for issue in issues {
+            let issue_penalty = match issue.severity {
+                ValidationSeverity::Critical => 30,
+                ValidationSeverity::Error => 20,
+                ValidationSeverity::Warning => 10,
+                ValidationSeverity::Info => 5,
+            };
+            penalty += issue_penalty;
+        }
+
+        std::cmp::max(0, 100 - penalty)
+    }
+}

src/tests/unit_webdav_smart_scanning_tests.rs

@@ -1,4 +1,4 @@
-use crate::services::webdav_service::{WebDAVConfig, WebDAVService};
+use crate::services::webdav::{WebDAVConfig, WebDAVService};
 
 fn create_test_config() -> WebDAVConfig {
     WebDAVConfig {