Great, this works now

Cargo.lock

@@ -140,6 +140,7 @@ dependencies = [
  "memmap2",
  "regex",
  "serde",
+ "serde_json",
  "walkdir",
 ]
 
@@ -168,6 +169,7 @@ dependencies = [
  "iana-time-zone",
  "js-sys",
  "num-traits",
+ "serde",
  "wasm-bindgen",
  "windows-link",
 ]
@@ -305,6 +307,12 @@ version = "1.70.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "7943c866cc5cd64cbc25b2e01621d07fa8eb2a1a23160ee81ce38704e97b8ecf"
 
+[[package]]
+name = "itoa"
+version = "1.0.15"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4a5f13b858c8d314ee3e8f639011f7ccefe71f97f96e50151fb991f267928e2c"
+
 [[package]]
 name = "js-sys"
 version = "0.3.77"
@@ -457,6 +465,12 @@ version = "1.0.21"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "8a0d197bd2c9dc6e53b84da9556a69ba4cdfab8619eb41a8bd1cc2027a0f6b1d"
 
+[[package]]
+name = "ryu"
+version = "1.0.20"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "28d3b2b1366ec20994f1fd18c3c594f05c5dd4bc44d8bb0c1c632c8d6829481f"
+
 [[package]]
 name = "same-file"
 version = "1.0.6"
@@ -486,6 +500,18 @@ dependencies = [
  "syn",
 ]
 
+[[package]]
+name = "serde_json"
+version = "1.0.141"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "30b9eff21ebe718216c6ec64e1d9ac57087aad11efc64e32002bce4a0d4c03d3"
+dependencies = [
+ "itoa",
+ "memchr",
+ "ryu",
+ "serde",
+]
+
 [[package]]
 name = "shlex"
 version = "1.3.0"

Cargo.toml

@@ -8,6 +8,7 @@ clap = { version = "4.0", features = ["derive"] }
 memmap2 = "0.9"
 inotify = "0.10"
 serde = { version = "1.0", features = ["derive"] }
+serde_json = "1.0"
 walkdir = "2.0"
 regex = "1.0"
-chrono = "0.4"
+chrono = { version = "0.4", features = ["serde"] }

readme.md

@@ -1,6 +1,6 @@
 # CARTO - Universal System File and Package Mapper
 
-A command-line tool that provides comprehensive observability into your Linux system's package installations and file ownership. Built in Rust for performance and reliability.
+A command-line tool that provides comprehensive observability into your Linux system's package installations and file ownership. Providing a clear, tracable providence for every executable, and configuration file on your system.
 
 ## Installation
 
@@ -13,22 +13,27 @@ just install
 ## Usage
 
 # Show package file tree
-carto tree --package bash
+`carto tree --package bash`
-carto tree --package "Signal Desktop (org.signal.Signal)"
+
+`carto tree --package "Signal Desktop (org.signal.Signal)"`
 
 # Package information
-carto package bash
+`carto package bash`
 
 # File ownership
-carto file /usr/bin/bash
+
+`carto file /usr/bin/bash`
 
 # List packages
-carto packages
+`carto packages`
-carto packages --source dnf
+
-carto packages --source flatpak
+`carto packages --source dnf`
+
+`carto packages --source flatpak`
 
 # Find files in package
-carto find --package bash
+
+`carto find --package bash`
 
 ## Example Output
 

src/cli/mod.rs

@@ -1,4 +1,5 @@
 pub mod tree;
+pub mod scan;
 
 use clap::{Parser, Subcommand};
 
@@ -9,11 +10,39 @@ pub struct Cli {
     pub command: Commands,
 }
 
+#[derive(clap::ValueEnum, Clone, Debug)]
+pub enum OutputFormat {
+    Simple,
+    Detailed,
+    Summary,
+    Json,
+    Tree,
+}
+
 #[derive(Subcommand)]
 pub enum Commands {
-    /// Scan system and build/update database
     Scan {
-        #[arg(short, long, help = "Force full rescan")]
+        /// Directories to scan (defaults to /)
+        paths: Vec<String>,
+        
+        /// Output format
+        #[arg(short, long, value_enum, default_value = "summary")]
+        format: OutputFormat,
+        
+        /// Show detailed file information
+        #[arg(long)]
+        detailed: bool,
+        
+        /// Show file sizes
+        #[arg(long)]
+        sizes: bool,
+        
+        /// Include expected orphans (/tmp, /var/log)
+        #[arg(long)]
+        include_expected: bool,
+        
+        /// Force full rescan
+        #[arg(short = 'F', long)]
         force: bool,
     },
 

src/cli/scan.rs

@@ -0,0 +1,442 @@
+use crate::{CartoError, PackageManager};
+use crate::database::format::{OrphanCategory, ScanSummary};
+use crate::cli::OutputFormat;
+use crate::package_managers::find_file_owner;
+use std::path::{Path, PathBuf};
+use std::collections::HashMap;
+use walkdir::WalkDir;
+use serde::{Serialize, Deserialize};
+use chrono::{DateTime, Utc};
+
+#[derive(Debug, Clone, Serialize)]
+pub struct OrphanFile {
+    pub path: PathBuf,
+    pub category: OrphanCategory,
+    pub size: u64,
+    pub modified: u64,
+    pub created: u64,
+}
+
+#[derive(Debug, Serialize)]
+pub struct ScanResults {
+    pub scan_time: DateTime<Utc>,
+    pub scanned_paths: Vec<String>,
+    pub total_files_scanned: u64,
+    pub total_orphans: usize,
+    pub orphans_by_category: HashMap<String, Vec<OrphanFile>>,
+    pub total_orphan_size: u64,
+    pub scan_duration_seconds: f64,
+}
+
+impl ScanResults {
+    pub fn new(scanned_paths: Vec<String>) -> Self {
+        Self {
+            scan_time: Utc::now(),
+            scanned_paths,
+            total_files_scanned: 0,
+            total_orphans: 0,
+            orphans_by_category: HashMap::new(),
+            total_orphan_size: 0,
+            scan_duration_seconds: 0.0,
+        }
+    }
+}
+
+pub struct Scanner<'a> {
+    managers: &'a [Box<dyn PackageManager>],
+    exclude_paths: Vec<PathBuf>,
+}
+impl<'a> Scanner<'a> {
+    pub fn new(managers: &'a [Box<dyn PackageManager>]) -> Self {
+    let exclude_paths = vec![
+        // Existing exclusions
+        PathBuf::from("/proc"),
+        PathBuf::from("/sys"),
+        PathBuf::from("/dev"),
+        PathBuf::from("/run"),
+        PathBuf::from("/var/run"),
+        PathBuf::from("/tmp/.X11-unix"),
+        PathBuf::from("/tmp/.ICE-unix"),
+
+        PathBuf::from("/var/lib/containers"),
+        PathBuf::from("/var/lib/docker"),
+        PathBuf::from("/home/.local/share/containers"),  // Your specific issue
+        PathBuf::from("/var/lib/flatpak"),
+        PathBuf::from("/var/cache"),
+        PathBuf::from("/var/tmp"),
+        PathBuf::from("/tmp"),
+        PathBuf::from("/var/log"),
+        PathBuf::from("/var/spool"),
+        PathBuf::from("/boot"),
+        PathBuf::from("/usr/src"),  // Kernel sources
+        PathBuf::from("/home"),     // User data isn't "orphaned"
+        PathBuf::from("/root"),
+    ];
+
+        Self {
+            managers,
+            exclude_paths,
+        }
+    }
+
+    pub fn scan_paths(
+        &self,
+        paths: &[String],
+        include_expected: bool,
+    ) -> Result<ScanResults, CartoError> {
+        let start_time = std::time::Instant::now();
+        let scan_paths = if paths.is_empty() {
+            vec![
+                "/usr".to_string(),
+                "/etc".to_string(), 
+                "/opt".to_string(),
+                "/lib".to_string(),
+                "/lib64".to_string(),
+            ]
+        } else {
+            paths.to_vec()
+        };
+        
+        let mut results = ScanResults::new(scan_paths.clone());
+        let mut orphans: Vec<OrphanFile> = Vec::new();
+
+        for path_str in &scan_paths {
+            let path = Path::new(path_str);
+            if !path.exists() {
+                eprintln!("Warning: Path {} does not exist, skipping", path_str);
+                continue;
+            }
+
+            println!("Scanning: {}", path_str);
+            self.scan_directory(path, &mut orphans, &mut results)?;
+        }
+
+        // Categorize orphans
+        self.categorize_orphans(&mut orphans, include_expected, &mut results);
+
+        results.total_orphans = orphans.len();
+        results.total_orphan_size = orphans.iter().map(|o| o.size).sum();
+        results.scan_duration_seconds = start_time.elapsed().as_secs_f64();
+
+        Ok(results)
+    }
+
+    fn scan_directory(
+        &self,
+        root: &Path,
+        orphans: &mut Vec<OrphanFile>,
+        results: &mut ScanResults,
+    ) -> Result<(), CartoError> {
+        let walker = WalkDir::new(root)
+            .follow_links(false)
+            .into_iter()
+            .filter_entry(|e| !self.should_exclude_path(e.path()));
+
+        for entry in walker {
+            let entry = match entry {
+                Ok(entry) => entry,
+                Err(e) => {
+                    eprintln!("Warning: Error accessing {}: {}", e.path().unwrap_or(Path::new("unknown")).display(), e);
+                    continue;
+                }
+            };
+
+            if !entry.file_type().is_file() {
+                continue;
+            }
+
+            results.total_files_scanned += 1;
+
+            // Check if file is owned by any package manager
+            let path = entry.path();
+            let is_owned = self.is_file_owned(path)?;
+
+            if !is_owned {
+                if let Ok(metadata) = entry.metadata() {
+                    let orphan = OrphanFile {
+                        path: path.to_path_buf(),
+                        category: OrphanCategory::Unknown, // Will be categorized later
+                        size: metadata.len(),
+                        modified: metadata.modified()
+                            .unwrap_or(std::time::UNIX_EPOCH)
+                            .duration_since(std::time::UNIX_EPOCH)
+                            .unwrap_or_default()
+                            .as_secs(),
+                        created: metadata.created()
+                            .unwrap_or(std::time::UNIX_EPOCH)
+                            .duration_since(std::time::UNIX_EPOCH)
+                            .unwrap_or_default()
+                            .as_secs(),
+                    };
+                    orphans.push(orphan);
+                }
+            }
+
+            // Progress indicator for large scans
+            if results.total_files_scanned % 10000 == 0 {
+                println!("Scanned {} files, found {} orphans", 
+                         results.total_files_scanned, orphans.len());
+            }
+        }
+
+        Ok(())
+    }
+
+    fn should_exclude_path(&self, path: &Path) -> bool {
+        for exclude in &self.exclude_paths {
+            if path.starts_with(exclude) {
+                return true;
+            }
+        }
+
+        let path_str = path.to_string_lossy();
+        
+        // Container storage patterns
+        if path_str.contains("/containers/storage/") ||
+        path_str.contains("/overlay/") ||
+        path_str.contains("/docker/") ||
+        
+        // Build and cache directories
+        path_str.contains("/.git/") ||
+        path_str.contains("/.cache/") ||
+        path_str.contains("/cache/") ||
+        path_str.contains("/.local/share/Trash/") ||
+        
+        // Mount points and removable media
+        path_str.starts_with("/media/") ||
+        path_str.starts_with("/mnt/") ||
+        
+        // Snap and flatpak user data
+        path_str.contains("/snap/") ||
+        path_str.contains("/.var/app/") {
+            return true;
+        }
+
+        false
+    }
+
+    fn is_file_owned(&self, path: &Path) -> Result<bool, CartoError> {
+        // Check all package managers to see if any owns this file
+        match find_file_owner(path) {
+            Ok(Some(_)) => Ok(true),
+            Ok(None) => Ok(false),
+            Err(e) => {
+                // Don't fail the entire scan for individual file errors
+                eprintln!("Warning: Error checking ownership of {}: {}", path.display(), e);
+                Ok(false)
+            }
+        }
+    }
+
+    fn categorize_orphans(
+        &self,
+        orphans: &mut [OrphanFile],
+        include_expected: bool,
+        results: &mut ScanResults,
+    ) {
+        for orphan in orphans.iter_mut() {
+            orphan.category = self.categorize_file(&orphan.path);
+        }
+
+        // Group by category
+        for orphan in orphans.iter() {
+            if !include_expected && orphan.category == OrphanCategory::Expected {
+                continue;
+            }
+
+            let category_name = orphan.category.name().to_string();
+            results.orphans_by_category
+                .entry(category_name)
+                .or_insert_with(Vec::new)
+                .push(orphan.clone());
+        }
+    }
+
+    fn categorize_file(&self, path: &Path) -> OrphanCategory {
+        let path_str = path.to_string_lossy();
+
+        // Expected orphans in common temporary/log locations
+        if path_str.starts_with("/tmp/") ||
+           path_str.starts_with("/var/tmp/") ||
+           path_str.starts_with("/var/log/") ||
+           path_str.starts_with("/var/cache/") ||
+           path_str.starts_with("/var/spool/") {
+            return OrphanCategory::Expected;
+        }
+
+        // User data in home directories
+        if path_str.starts_with("/home/") ||
+           path_str.starts_with("/root/") {
+            return OrphanCategory::UserData;
+        }
+
+        // System generated files
+        if path_str.starts_with("/var/lib/") ||
+           path_str.starts_with("/var/run/") ||
+           path_str.contains("/.cache/") ||
+           path_str.contains("/cache/") {
+            return OrphanCategory::SystemGenerated;
+        }
+
+        // Configuration backups
+        if let Some(extension) = path.extension() {
+            let ext = extension.to_string_lossy().to_lowercase();
+            if ext == "bak" || ext == "orig" || ext == "old" || ext == "backup" {
+                return OrphanCategory::ConfigBackup;
+            }
+        }
+
+        // Temporary files in unusual locations
+        if let Some(filename) = path.file_name() {
+            let name = filename.to_string_lossy().to_lowercase();
+            if name.starts_with("tmp") || 
+               name.starts_with(".tmp") ||
+               name.ends_with(".tmp") ||
+               name.ends_with("~") {
+                return OrphanCategory::Temporary;
+            }
+        }
+
+        OrphanCategory::Unknown
+    }
+}
+
+pub fn print_scan_results(
+    results: &ScanResults,
+    format: &OutputFormat,
+    detailed: bool,
+    show_sizes: bool,
+) -> Result<(), CartoError> {
+    match format {
+        OutputFormat::Json => print_json_results(results),
+        OutputFormat::Summary => print_summary_results(results, show_sizes),
+        OutputFormat::Detailed => print_detailed_results(results, show_sizes),
+        OutputFormat::Simple => print_simple_results(results),
+        OutputFormat::Tree => print_tree_results(results, show_sizes),
+    }
+}
+
+fn print_json_results(results: &ScanResults) -> Result<(), CartoError> {
+    match serde_json::to_string_pretty(results) {
+        Ok(json) => {
+            println!("{}", json);
+            Ok(())
+        }
+        Err(e) => Err(CartoError::CommandFailed(format!("JSON serialization failed: {}", e))),
+    }
+}
+
+fn print_summary_results(results: &ScanResults, show_sizes: bool) -> Result<(), CartoError> {
+    println!("Scan Summary");
+    println!("============");
+    println!("Scan completed: {}", results.scan_time.format("%Y-%m-%d %H:%M:%S UTC"));
+    println!("Duration: {:.2} seconds", results.scan_duration_seconds);
+    println!("Scanned paths: {}", results.scanned_paths.join(", "));
+    println!("Total files scanned: {}", results.total_files_scanned);
+    println!("Total orphan files: {}", results.total_orphans);
+    
+    if show_sizes {
+        println!("Total orphan size: {}", format_size(results.total_orphan_size));
+    }
+    
+    println!("\nOrphans by Category:");
+    for (category, orphans) in &results.orphans_by_category {
+        let category_size: u64 = orphans.iter().map(|o| o.size).sum();
+        if show_sizes {
+            println!("  {}: {} files ({})", category, orphans.len(), format_size(category_size));
+        } else {
+            println!("  {}: {} files", category, orphans.len());
+        }
+    }
+
+    Ok(())
+}
+
+fn print_detailed_results(results: &ScanResults, show_sizes: bool) -> Result<(), CartoError> {
+    print_summary_results(results, show_sizes)?;
+    
+    println!("\nDetailed File Listings:");
+    for (category, orphans) in &results.orphans_by_category {
+        println!("\n{} ({} files):", category.to_uppercase(), orphans.len());
+        println!("{}", "=".repeat(50));
+        
+        for orphan in orphans.iter().take(20) { // Limit to first 20 per category
+            if show_sizes {
+                println!("  {} ({})", orphan.path.display(), format_size(orphan.size));
+            } else {
+                println!("  {}", orphan.path.display());
+            }
+        }
+        
+        if orphans.len() > 20 {
+            println!("  ... and {} more files", orphans.len() - 20);
+        }
+    }
+
+    Ok(())
+}
+
+fn print_simple_results(results: &ScanResults) -> Result<(), CartoError> {
+    println!("Found {} orphan files in {:.1}s", results.total_orphans, results.scan_duration_seconds);
+    for (category, orphans) in &results.orphans_by_category {
+        println!("{}: {}", category, orphans.len());
+    }
+    Ok(())
+}
+
+fn print_tree_results(results: &ScanResults, show_sizes: bool) -> Result<(), CartoError> {
+    use std::collections::BTreeMap;
+    
+    println!("Orphan Files by Directory Tree");
+    println!("==============================");
+    
+    for (category, orphans) in &results.orphans_by_category {
+        println!("\n{} ({} files):", category.to_uppercase(), orphans.len());
+        
+        // Group files by their parent directory
+        let mut dir_map: BTreeMap<PathBuf, Vec<&OrphanFile>> = BTreeMap::new();
+        for orphan in orphans {
+            if let Some(parent) = orphan.path.parent() {
+                dir_map.entry(parent.to_path_buf()).or_insert_with(Vec::new).push(orphan);
+            }
+        }
+        
+        for (dir, files) in dir_map.iter().take(10) { // Limit directories shown
+            println!("  {}/", dir.display());
+            for file in files.iter().take(5) { // Limit files per directory
+                let filename = file.path.file_name().unwrap_or_default().to_string_lossy();
+                if show_sizes {
+                    println!("    ├── {} ({})", filename, format_size(file.size));
+                } else {
+                    println!("    ├── {}", filename);
+                }
+            }
+            if files.len() > 5 {
+                println!("    └── ... and {} more files", files.len() - 5);
+            }
+        }
+        
+        if dir_map.len() > 10 {
+            println!("  ... and {} more directories", dir_map.len() - 10);
+        }
+    }
+    
+    Ok(())
+}
+
+fn format_size(bytes: u64) -> String {
+    const UNITS: &[&str] = &["B", "KB", "MB", "GB", "TB"];
+    let mut size = bytes as f64;
+    let mut unit_idx = 0;
+    
+    while size >= 1024.0 && unit_idx < UNITS.len() - 1 {
+        size /= 1024.0;
+        unit_idx += 1;
+    }
+    
+    if unit_idx == 0 {
+        format!("{} {}", bytes, UNITS[unit_idx])
+    } else {
+        format!("{:.1} {}", size, UNITS[unit_idx])
+    }
+}

src/database/format.rs

@@ -1,15 +1,22 @@
 use memmap2::Mmap;
 use std::fs::File;
+use std::path::Path;
+use crate::{CartoError, PackageSource};
+use serde::Serialize;
 
 #[repr(C, packed)]
 pub struct DatabaseHeader {
-    magic: [u8; 8],        // "WHEREDB\0"
+    magic: [u8; 8],        // "CARTODB\0"
     version: u32,
     created: u64,          // Unix timestamp
     file_count: u64,
     package_count: u32,
+    orphan_count: u64,     // Count of orphaned files
+    scan_count: u32,       // Number of scans performed
     files_offset: u64,
     packages_offset: u64,
+    orphans_offset: u64,   // Offset to orphan records
+    scans_offset: u64,     // Offset to scan metadata
     strings_offset: u64,
     index_offset: u64,
 }
@@ -36,14 +43,99 @@ pub struct PackageRecord {
     first_file_idx: u32,
 }
 
-pub struct WhereDatabase {
+#[repr(C, packed)]
+pub struct OrphanRecord {
+    path_hash: u64,        // FNV-1a hash for quick lookups
+    category: u8,          // OrphanCategory as u8
+    permissions: u16,
+    size: u64,
+    mtime: u64,
+    ctime: u64,            // Creation time for cleanup planning
+    path_offset: u32,      // offset into string pool
+    scan_id: u32,          // Which scan discovered this orphan
+}
+
+#[repr(C, packed)]
+pub struct ScanRecord {
+    id: u32,
+    scan_time: u64,        // Unix timestamp when scan was performed
+    scanned_paths_offset: u32,  // Comma-separated list of scanned paths
+    orphans_found: u32,    // Number of orphans found in this scan
+    total_files_scanned: u64,
+    scan_duration: u32,    // Duration in seconds
+}
+
+#[derive(Debug, Clone, PartialEq, Eq, Hash, Serialize)] 
+pub enum OrphanCategory {
+    Unknown = 0,           // Files with no clear ownership
+    Expected = 1,          // Files in /tmp, /var/tmp, /var/log, etc.
+    UserData = 2,          // Files in /home directories
+    SystemGenerated = 3,   // Runtime files, caches
+    ConfigBackup = 4,      // .bak, .orig config files
+    Temporary = 5,         // Temp files in unusual locations
+}
+
+impl OrphanCategory {
+    pub fn from_u8(value: u8) -> Self {
+        match value {
+            0 => OrphanCategory::Unknown,
+            1 => OrphanCategory::Expected,
+            2 => OrphanCategory::UserData,
+            3 => OrphanCategory::SystemGenerated,
+            4 => OrphanCategory::ConfigBackup,
+            5 => OrphanCategory::Temporary,
+            _ => OrphanCategory::Unknown,
+        }
+    }
+    
+    pub fn name(&self) -> &'static str {
+        match self {
+            OrphanCategory::Unknown => "unknown",
+            OrphanCategory::Expected => "expected",
+            OrphanCategory::UserData => "user-data",
+            OrphanCategory::SystemGenerated => "system-generated",
+            OrphanCategory::ConfigBackup => "config-backup",
+            OrphanCategory::Temporary => "temporary",
+        }
+    }
+    
+    pub fn description(&self) -> &'static str {
+        match self {
+            OrphanCategory::Unknown => "Files with no clear package ownership",
+            OrphanCategory::Expected => "Files in temporary/log directories",
+            OrphanCategory::UserData => "Files in user home directories",
+            OrphanCategory::SystemGenerated => "Runtime and cache files",
+            OrphanCategory::ConfigBackup => "Configuration backup files",
+            OrphanCategory::Temporary => "Temporary files in unusual locations",
+        }
+    }
+}
+
+pub struct FileInfo {
+    pub path: String,
+    pub package: Option<String>,
+    pub source: Option<PackageSource>,
+    pub size: u64,
+    pub modified: u64,
+}
+
+pub struct OrphanInfo {
+    pub path: String,
+    pub category: OrphanCategory,
+    pub size: u64,
+    pub modified: u64,
+    pub created: u64,
+    pub scan_id: u32,
+}
+
+pub struct CartoDatabase {
     _file: File,
     mmap: Mmap,
     header: &'static DatabaseHeader,
 }
 
-impl WhereDatabase {
+impl CartoDatabase {
-    pub fn open<P: AsRef<Path>>(path: P) -> Result<Self, WhereError> {
+    pub fn open<P: AsRef<Path>>(path: P) -> Result<Self, CartoError> {
         let file = File::open(path)?;
         let mmap = unsafe { memmap2::MmapOptions::new().map(&file)? };
         
@@ -52,11 +144,11 @@ impl WhereDatabase {
         };
         
         // Validate magic number
-        if &header.magic != b"WHEREDB\0" {
+        if &header.magic != b"CARTODB\0" {
-            return Err(WhereError::InvalidDatabase);
+            return Err(CartoError::InvalidDatabase);
         }
         
-        Ok(WhereDatabase {
+        Ok(CartoDatabase {
             _file: file,
             mmap,
             header,
@@ -64,17 +156,60 @@ impl WhereDatabase {
     }
     
     pub fn find_file(&self, path: &str) -> Option<FileInfo> {
-        let hash = fnv1a_hash(path.as_bytes());
+        let hash = self.fnv1a_hash(path.as_bytes());
         
-        // Binary search through sorted file records
+        // First check package-owned files
+        if let Some(file_info) = self.find_package_file(hash, path) {
+            return Some(file_info);
+        }
+        
+        // Then check orphaned files
+        self.find_orphan_file(hash, path)
+    }
+    
+    pub fn find_orphans_by_category(&self, category: OrphanCategory) -> Vec<OrphanInfo> {
+        let orphans = self.get_orphan_records();
+        orphans.iter()
+            .filter(|record| OrphanCategory::from_u8(record.category) == category)
+            .map(|record| OrphanInfo {
+                path: self.get_string(record.path_offset),
+                category: OrphanCategory::from_u8(record.category),
+                size: record.size,
+                modified: record.mtime,
+                created: record.ctime,
+                scan_id: record.scan_id,
+            })
+            .collect()
+    }
+    
+    pub fn get_scan_summary(&self) -> ScanSummary {
+        let orphans = self.get_orphan_records();
+        let mut category_counts = std::collections::HashMap::new();
+        let mut total_size = 0u64;
+        
+        for record in orphans {
+            let category = OrphanCategory::from_u8(record.category);
+            *category_counts.entry(category).or_insert(0) += 1;
+            total_size += record.size;
+        }
+        
+        ScanSummary {
+            total_orphans: orphans.len(),
+            category_counts,
+            total_size,
+            last_scan: self.get_last_scan_time(),
+        }
+    }
+    
+    fn find_package_file(&self, hash: u64, path: &str) -> Option<FileInfo> {
         let files = self.get_file_records();
         match files.binary_search_by_key(&hash, |record| record.path_hash) {
             Ok(idx) => {
                 let record = &files[idx];
                 Some(FileInfo {
                     path: self.get_string(record.path_offset),
-                    package: self.get_package_name(record.package_id),
+                    package: Some(self.get_package_name(record.package_id)),
-                    source: PackageSource::from_u8(record.source),
+                    source: Some(PackageSource::from_u8(record.source)),
                     size: record.size,
                     modified: record.mtime,
                 })
@@ -82,4 +217,85 @@ impl WhereDatabase {
             Err(_) => None,
         }
     }
+    
+    fn find_orphan_file(&self, hash: u64, path: &str) -> Option<FileInfo> {
+        let orphans = self.get_orphan_records();
+        match orphans.binary_search_by_key(&hash, |record| record.path_hash) {
+            Ok(idx) => {
+                let record = &orphans[idx];
+                Some(FileInfo {
+                    path: self.get_string(record.path_offset),
+                    package: None,
+                    source: None,
+                    size: record.size,
+                    modified: record.mtime,
+                })
+            }
+            Err(_) => None,
+        }
+    }
+    
+    fn get_file_records(&self) -> &[FileRecord] {
+        unsafe {
+            std::slice::from_raw_parts(
+                self.mmap.as_ptr().add(self.header.files_offset as usize) as *const FileRecord,
+                self.header.file_count as usize
+            )
+        }
+    }
+    
+    fn get_orphan_records(&self) -> &[OrphanRecord] {
+        unsafe {
+            std::slice::from_raw_parts(
+                self.mmap.as_ptr().add(self.header.orphans_offset as usize) as *const OrphanRecord,
+                self.header.orphan_count as usize
+            )
+        }
+    }
+    
+    fn get_string(&self, offset: u32) -> String {
+        // Implementation for reading from string pool
+        // This is a placeholder - actual implementation depends on string storage format
+        String::new()
+    }
+    
+    fn get_package_name(&self, package_id: u32) -> String {
+        // Implementation for getting package name by ID
+        // This is a placeholder - actual implementation depends on package storage
+        String::new()
+    }
+    
+    fn get_last_scan_time(&self) -> Option<u64> {
+        if self.header.scan_count == 0 {
+            return None;
+        }
+        
+        let scans = unsafe {
+            std::slice::from_raw_parts(
+                self.mmap.as_ptr().add(self.header.scans_offset as usize) as *const ScanRecord,
+                self.header.scan_count as usize
+            )
+        };
+        
+        scans.last().map(|scan| scan.scan_time)
+    }
+    
+    fn fnv1a_hash(&self, bytes: &[u8]) -> u64 {
+        const FNV_OFFSET_BASIS: u64 = 14695981039346656037;
+        const FNV_PRIME: u64 = 1099511628211;
+        
+        let mut hash = FNV_OFFSET_BASIS;
+        for byte in bytes {
+            hash ^= *byte as u64;
+            hash = hash.wrapping_mul(FNV_PRIME);
+        }
+        hash
+    }
+}
+
+pub struct ScanSummary {
+    pub total_orphans: usize,
+    pub category_counts: std::collections::HashMap<OrphanCategory, usize>,
+    pub total_size: u64,
+    pub last_scan: Option<u64>,
 }

src/database/mod.rs

@@ -0,0 +1 @@
+pub mod format;

src/main.rs

@@ -3,12 +3,15 @@
 
 pub mod package_managers;
 pub mod cli;
+pub mod database;
 
-use std::path::PathBuf;
+use std::path::{self, PathBuf};
 use package_managers::{detect_available_managers, PackageManager, PackageSource};
 use cli::{Cli, Commands};
 use clap::Parser;
 
+use crate::cli::OutputFormat;
+
 // Define the types that your modules need
 #[derive(Debug, Clone)]
 pub struct PackageInfo {
@@ -61,6 +64,10 @@ fn main() -> Result<(), Box<dyn std::error::Error>> {
     let cli = Cli::parse();
     let managers = detect_available_managers();
     
+    if managers.is_empty() {
+        eprintln!("Warning: No package managers detected");
+    }
+    
     match cli.command {
         Commands::Tree { depth, package, source } => {
             handle_tree_command(&managers, depth, package, source)?;
@@ -77,8 +84,8 @@ fn main() -> Result<(), Box<dyn std::error::Error>> {
         Commands::Find { name, package, size } => {
             handle_find_command(&managers, name, package, size)?;
         }
-        Commands::Scan { force } => {
+        Commands::Scan { force, paths, format, detailed, sizes, include_expected } => {
-            handle_scan_command(&managers, force)?;
+            handle_scan_command(&managers, paths, format, force, detailed, sizes, include_expected)?;
         }
     }
     
@@ -89,23 +96,54 @@ fn handle_tree_command(
     managers: &[Box<dyn PackageManager>], 
     _depth: Option<usize>, 
     package_filter: Option<String>,
-    _source_filter: Option<String>
+    source_filter: Option<String>
 ) -> Result<(), Box<dyn std::error::Error>> {
-    if let Some(dnf) = managers.iter().find(|m| m.name() == "dnf") {
+    let target_managers: Vec<&Box<dyn PackageManager>> = if let Some(source_name) = source_filter {
+        // Filter to specific manager
+        managers.iter().filter(|m| m.name().to_lowercase() == source_name.to_lowercase()).collect()
+    } else {
+        // Use all managers
+        managers.iter().collect()
+    };
+
+    if target_managers.is_empty() {
+        println!("No suitable package managers found");
+        return Ok(());
+    }
+
     if let Some(package_name) = package_filter {
-            // Show tree for specific package
+        // Show tree for specific package across all managers
-            cli::tree::print_package_tree(dnf.as_ref(), &package_name)?;
+        let mut found = false;
-        } else {
+        for manager in &target_managers {
-            // Show tree for first few packages as demo
+            match manager.get_package_info(&package_name) {
-            println!("Package file trees (first 5 packages):");
+                Ok(Some(_)) => {
-            let packages = dnf.get_installed_packages()?;
+                    println!("Package '{}' from {}:", package_name, manager.name());
-            for package in packages.iter().take(5) {
+                    cli::tree::print_package_tree(manager.as_ref(), &package_name)?;
-                cli::tree::print_package_tree(dnf.as_ref(), &package.name)?;
+                    found = true;
-                println!(); // Empty line between packages
+                    println!();
+                }
+                Ok(None) => continue,
+                Err(e) => eprintln!("Error checking {} in {}: {}", package_name, manager.name(), e),
             }
         }
+        if !found {
+            println!("Package '{}' not found in any package manager", package_name);
+        }
     } else {
-        println!("No DNF package manager found");
+        // Show tree for first few packages from each manager as demo
+        for manager in &target_managers {
+            match manager.get_installed_packages() {
+                Ok(packages) => {
+                    println!("{} package file trees (first 3 packages):", manager.name());
+                    for package in packages.iter().take(3) {
+                        println!("  Package: {}", package.name);
+                        cli::tree::print_package_tree(manager.as_ref(), &package.name)?;
+                        println!();
+                    }
+                }
+                Err(e) => eprintln!("Error getting packages from {}: {}", manager.name(), e),
+            }
+        }
     }
     Ok(())
 }
@@ -114,10 +152,13 @@ fn handle_package_command(
     managers: &[Box<dyn PackageManager>], 
     name: &str
 ) -> Result<(), Box<dyn std::error::Error>> {
-    if let Some(dnf) = managers.iter().find(|m| m.name() == "dnf") {
+    let mut found = false;
-        match dnf.get_package_info(name) {
+    
+    // Search all managers for the package
+    for manager in managers {
+        match manager.get_package_info(name) {
             Ok(Some(info)) => {
-                println!("Package: {}", info.name);
+                println!("Package: {} (from {})", info.name, manager.name());
                 println!("Version: {}", info.version);
                 println!("Source: {}", info.source.name());
                 println!("Install time: {}", info.install_time);
@@ -125,18 +166,25 @@ fn handle_package_command(
                 
                 // Show file tree for this package
                 println!("\nFiles:");
-                cli::tree::print_package_tree(dnf.as_ref(), name)?;
+                cli::tree::print_package_tree(manager.as_ref(), name)?;
+                found = true;
+                println!();
             }
-            Ok(None) => println!("Package '{}' not found", name),
+            Ok(None) => continue,
-            Err(e) => println!("Error: {}", e),
+            Err(e) => eprintln!("Error checking {} in {}: {}", name, manager.name(), e),
         }
     }
+    
+    if !found {
+        println!("Package '{}' not found in any package manager", name);
+    }
+    
     Ok(())
 }
 
 fn handle_packages_command(
     managers: &[Box<dyn PackageManager>], 
-    source_filter: Option<String>  // Removed the underscore!
+    source_filter: Option<String>
 ) -> Result<(), Box<dyn std::error::Error>> {
     if let Some(source_name) = source_filter {
         // Filter by specific source
@@ -184,13 +232,32 @@ fn handle_file_command(
     managers: &[Box<dyn PackageManager>], 
     path: &str
 ) -> Result<(), Box<dyn std::error::Error>> {
-    if let Some(dnf) = managers.iter().find(|m| m.name() == "dnf") {
+    let path_obj = std::path::Path::new(path);
-        match dnf.get_file_owner(std::path::Path::new(path)) {
+    let mut owners = Vec::new();
-            Ok(Some(owner)) => println!("{} is owned by package: {}", path, owner),
+    
-            Ok(None) => println!("{} is not owned by any package", path),
+    // Check all managers for file ownership
-            Err(e) => println!("Error checking {}: {}", path, e),
+    for manager in managers {
+        match manager.get_file_owner(path_obj) {
+            Ok(Some(owner)) => {
+                owners.push((manager.name(), owner));
+            }
+            Ok(None) => continue,
+            Err(e) => eprintln!("Warning: Error checking {} in {}: {}", path, manager.name(), e),
         }
     }
+    
+    if owners.is_empty() {
+        println!("{} is not owned by any package", path);
+    } else if owners.len() == 1 {
+        let (manager, owner) = &owners[0];
+        println!("{} is owned by package: {} ({})", path, owner, manager);
+    } else {
+        println!("{} is owned by multiple packages:", path);
+        for (manager, owner) in owners {
+            println!("  {} ({} package manager)", owner, manager);
+        }
+    }
+    
     Ok(())
 }
 
@@ -201,16 +268,27 @@ fn handle_find_command(
     _size: Option<String>
 ) -> Result<(), Box<dyn std::error::Error>> {
     if let Some(package_name) = package {
-        if let Some(dnf) = managers.iter().find(|m| m.name() == "dnf") {
+        let mut found = false;
-            match dnf.get_package_files(&package_name) {
+        
+        // Search all managers for the package
+        for manager in managers {
+            match manager.get_package_files(&package_name) {
                 Ok(files) => {
-                    println!("Files in package '{}':", package_name);
+                    if !files.is_empty() {
+                        println!("Files in package '{}' from {}:", package_name, manager.name());
                         for file in files {
                             println!("  {}", file.display());
                         }
+                        found = true;
+                        println!();
                     }
-                Err(e) => println!("Error: {}", e),
                 }
+                Err(e) => eprintln!("Error checking {} in {}: {}", package_name, manager.name(), e),
+            }
+        }
+        
+        if !found {
+            println!("Package '{}' not found in any package manager", package_name);
         }
     } else {
         println!("Find command needs more specific criteria");
@@ -219,9 +297,16 @@ fn handle_find_command(
 }
 
 fn handle_scan_command(
-    _managers: &[Box<dyn PackageManager>], 
+    managers: &[Box<dyn PackageManager>],
-    _force: bool
+    paths: Vec<String>,
+    format: OutputFormat,
+    _force: bool,
+    detailed: bool,
+    sizes: bool,
+    include_expected: bool,
 ) -> Result<(), Box<dyn std::error::Error>> {
-    println!("Scan functionality not yet implemented");
+    let scanner = cli::scan::Scanner::new(managers);
+    let results = scanner.scan_paths(&paths, include_expected)?;
+    cli::scan::print_scan_results(&results, &format, detailed, sizes)?;
     Ok(())
 }