chore: development v0.2.16 - comprehensive testing complete [auto-commit]

Author: githubrobbi

Cargo.lock

@@ -32,7 +32,7 @@ members = [
 # Workspace Package Metadata (inherited by all crates)
 # ─────────────────────────────────────────────────────────────────────────────
 [workspace.package]
-version = "0.2.15"
+version = "0.2.16"
 edition = "2024"
 rust-version = "1.85"
 license = "MPL-2.0 OR LicenseRef-UFFS-Commercial"

Cargo.toml

@@ -21,7 +21,7 @@ Traditional file search tools (including `os.walk`, `FindFirstFile`, etc.) work
 
 **UFFS reads the MFT directly** - once - and queries it in memory using Polars DataFrames. This is like reading the entire phonebook once instead of looking up each name individually.
 
-### Benchmark Results (v0.2.15)
+### Benchmark Results (v0.2.16)
 
 | Drive Type | Records | Time | Throughput |
 |------------|---------|------|------------|
@@ -33,7 +33,7 @@ Traditional file search tools (including `os.walk`, `FindFirstFile`, etc.) work
 
 | Comparison | Records | Time | Notes |
 |------------|---------|------|-------|
-| **UFFS v0.2.15** | **18.7 Million** | **~142 seconds** | All disks, fast mode |
+| **UFFS v0.2.16** | **18.7 Million** | **~142 seconds** | All disks, fast mode |
 | UFFS v0.1.30 | 18.7 Million | ~315 seconds | Baseline |
 | Everything | 19 Million | 178 seconds | All disks |
 | WizFile | 6.5 Million | 299 seconds | Single HDD |

README.md

@@ -304,14 +304,19 @@ use uffs_mft::{MftProgress, MftReader};
 /// - Extension filtering: `--ext pictures,mp4,pdf`
 /// - Output customization: `--out`, `--columns`, `--sep`, `--quotes`,
 ///   `--header`, `--pos`, `--neg`
-#[allow(clippy::too_many_arguments, clippy::fn_params_excessive_bools)]
+#[allow(
+    clippy::too_many_arguments,
+    clippy::fn_params_excessive_bools,
+    clippy::print_stderr
+)]
 pub async fn search(
     pattern: &str,
     single_drive: Option<char>,
     multi_drives: Option<Vec<char>>,
     index: Option<PathBuf>,
     files_only: bool,
     dirs_only: bool,
+    hide_system: bool,
     min_size: Option<u64>,
     max_size: Option<u64>,
     limit: u32,
@@ -326,6 +331,9 @@ pub async fn search(
     pos: &str,
     neg: &str,
 ) -> Result<()> {
+    // Start timing for "Finished in X s" output (C++ compatibility)
+    let start_time = std::time::Instant::now();
+
     // Parse the pattern to extract drive prefix and pattern type
     let parsed = ParsedPattern::parse(pattern)
         .with_context(|| format!("Invalid pattern: {pattern}"))?
@@ -337,6 +345,7 @@ pub async fn search(
         ext_filter,
         files_only,
         dirs_only,
+        hide_system,
         min_size,
         max_size,
         limit,
@@ -360,7 +369,7 @@ pub async fn search(
 
         if needs_streaming {
             // Streaming mode: output results as each drive completes
-            return search_streaming(
+            let result = search_streaming(
                 multi_drives,
                 single_drive,
                 &filters,
@@ -369,6 +378,10 @@ pub async fn search(
                 &output_config,
             )
             .await;
+            // Print timing after streaming completes
+            let elapsed = start_time.elapsed();
+            eprintln!("Finished in {} s", elapsed.as_secs());
+            return result;
         }
     }
 
@@ -390,6 +403,10 @@ pub async fn search(
     // Output results
     write_results(&results, format, out, &output_config)?;
 
+    // Print timing (C++ compatibility: "Finished in X s")
+    let elapsed = start_time.elapsed();
+    eprintln!("Finished in {} s", elapsed.as_secs());
+
     info!(count = results.height(), "Search complete");
     Ok(())
 }
@@ -511,6 +528,9 @@ async fn load_and_filter_data(
             filtered = resolver
                 .add_path_column_auto(&filtered)
                 .context("Failed to add path column")?;
+            // Add path_only column (directory portion of path)
+            filtered = uffs_core::add_path_only_column(&filtered)
+                .context("Failed to add path_only column")?;
         }
 
         return Ok(filtered);
@@ -553,6 +573,8 @@ struct QueryFilters<'a> {
     files_only: bool,
     /// Only return directories (not files).
     dirs_only: bool,
+    /// Hide system files (files starting with $).
+    hide_system: bool,
     /// Minimum file size filter.
     min_size: Option<u64>,
     /// Maximum file size filter.
@@ -586,6 +608,11 @@ fn execute_query(
         query = query.directories_only();
     }
 
+    // Apply hide_system filter (exclude files starting with $)
+    if filters.hide_system {
+        query = query.hide_system_files();
+    }
+
     // Apply size filters
     if let Some(min) = filters.min_size {
         query = query.min_size(min);
@@ -893,7 +920,25 @@ async fn search_multi_drive_filtered(
             // DataFrames)
             let with_paths = if let Some(ref mut resolver) = path_resolver {
                 match resolver.add_path_column_auto(&filtered) {
-                    Ok(df) => df,
+                    Ok(df) => {
+                        // Add path_only column (directory portion of path)
+                        match uffs_core::add_path_only_column(&df) {
+                            Ok(df_with_path_only) => df_with_path_only,
+                            Err(e) => {
+                                let _ = tx
+                                    .send(DriveResult {
+                                        drive: drive_char,
+                                        df: None,
+                                        records_read,
+                                        matches,
+                                        error: Some(format!("Failed to add path_only: {e}")),
+                                        paths_resolved: false,
+                                    })
+                                    .await;
+                                return;
+                            }
+                        }
+                    }
                     Err(e) => {
                         let _ = tx
                             .send(DriveResult {

crates/uffs-cli/src/commands.rs

@@ -121,6 +121,10 @@ struct Cli {
     #[arg(long)]
     dirs_only: bool,
 
+    /// Hide system files (files starting with $)
+    #[arg(long)]
+    hide_system: bool,
+
     /// Minimum file size in bytes
     #[arg(long)]
     min_size: Option<u64>,
@@ -150,20 +154,21 @@ struct Cli {
     out: String,
 
     /// Columns to output (comma-separated or "all")
-    /// Default: path only (CPP compatible)
-    #[arg(long, default_value = "path")]
+    /// Default: all columns (CPP compatible)
+    #[arg(long, default_value = "all")]
     columns: String,
 
     /// Column separator (default: comma)
     #[arg(long, default_value = ",")]
     sep: String,
 
-    /// Quote character for string values (empty = no quotes)
-    #[arg(long, default_value = "")]
+    /// Quote character for string values (default: double-quote for CPP
+    /// compatibility)
+    #[arg(long, default_value = "\"")]
     quotes: String,
 
-    /// Include header row in output
-    #[arg(long, default_value = "false")]
+    /// Include header row in output (default: true for CPP compatibility)
+    #[arg(long, default_value = "true")]
     header: bool,
 
     /// Representation for active/true boolean attributes
@@ -217,6 +222,10 @@ enum Commands {
         #[arg(long)]
         dirs_only: bool,
 
+        /// Hide system files (files starting with $)
+        #[arg(long)]
+        hide_system: bool,
+
         /// Minimum file size in bytes
         #[arg(long)]
         min_size: Option<u64>,
@@ -261,8 +270,8 @@ enum Commands {
         /// hidden, system, archive, readonly, compressed, encrypted,
         /// sparse, reparse, offline, notindexed, temporary, virtual,
         /// pinned, unpinned, descendants
-        /// Default: path only (CPP compatible)
-        #[arg(long, default_value = "path")]
+        /// Default: all columns (CPP compatible)
+        #[arg(long, default_value = "all")]
         columns: String,
 
         /// Column separator (default: comma)
@@ -271,12 +280,13 @@ enum Commands {
         #[arg(long, default_value = ",")]
         sep: String,
 
-        /// Quote character for string values (empty = no quotes)
-        #[arg(long, default_value = "")]
+        /// Quote character for string values (default: double-quote for CPP
+        /// compatibility)
+        #[arg(long, default_value = "\"")]
         quotes: String,
 
-        /// Include header row in output
-        #[arg(long, default_value = "false")]
+        /// Include header row in output (default: true for CPP compatibility)
+        #[arg(long, default_value = "true")]
         header: bool,
 
         /// Representation for active/true boolean attributes
@@ -444,6 +454,7 @@ async fn run() -> Result<()> {
             index,
             files_only,
             dirs_only,
+            hide_system,
             min_size,
             max_size,
             limit,
@@ -465,6 +476,7 @@ async fn run() -> Result<()> {
                 index,
                 files_only,
                 dirs_only,
+                hide_system,
                 min_size,
                 max_size,
                 limit,
@@ -504,6 +516,7 @@ async fn run() -> Result<()> {
                     cli.index,
                     cli.files_only,
                     cli.dirs_only,
+                    cli.hide_system,
                     cli.min_size,
                     cli.max_size,
                     cli.limit,

crates/uffs-cli/src/main.rs

@@ -158,7 +158,9 @@ impl CompiledPattern {
                     col_expr.str().starts_with(lit(prefix.clone()))
                 } else {
                     let escaped = regex_escape(prefix);
-                    col_expr.str().contains(lit(format!("(?i)^{escaped}")), true)
+                    col_expr
+                        .str()
+                        .contains(lit(format!("(?i)^{escaped}")), true)
                 }
             }
 
@@ -168,7 +170,9 @@ impl CompiledPattern {
                     col_expr.str().ends_with(lit(suffix.clone()))
                 } else {
                     let escaped = regex_escape(suffix);
-                    col_expr.str().contains(lit(format!("(?i){escaped}$")), true)
+                    col_expr
+                        .str()
+                        .contains(lit(format!("(?i){escaped}$")), true)
                 }
             }
 
@@ -873,8 +877,10 @@ mod tests {
             "$I07QSZ8.TXT",
             "test.TXT",
         ];
-        let df =
-            DataFrame::new(input_names.len(), vec![Column::new("name".into(), &input_names)])?;
+        let df = DataFrame::new(
+            input_names.len(),
+            vec![Column::new("name".into(), &input_names)],
+        )?;
 
         // Test case-sensitive suffix matching
         let pattern = CompiledPattern::Suffix(".txt".to_owned());
@@ -903,8 +909,10 @@ mod tests {
             "normal.txt",
             "$BITMAP",
         ];
-        let df =
-            DataFrame::new(input_names.len(), vec![Column::new("name".into(), &input_names)])?;
+        let df = DataFrame::new(
+            input_names.len(),
+            vec![Column::new("name".into(), &input_names)],
+        )?;
 
         // Test that files starting with $ are matched by *.txt pattern
         let pattern = CompiledPattern::Suffix(".txt".to_owned());
@@ -920,7 +928,12 @@ mod tests {
         );
 
         // Verify $I07QSZ8.txt is in the results
-        let matched_names: Vec<&str> = result.column("name")?.str()?.into_iter().flatten().collect();
+        let matched_names: Vec<&str> = result
+            .column("name")?
+            .str()?
+            .into_iter()
+            .flatten()
+            .collect();
         assert!(
             matched_names.contains(&"$I07QSZ8.txt") || matched_names.contains(&"$i07qsz8.txt"),
             "Should include $I07QSZ8.txt: {matched_names:?}"

crates/uffs-core/src/compiled_pattern.rs

@@ -77,7 +77,7 @@ pub use extensions::{
 pub use path_resolver::add_path_column_multi_drive;
 pub use path_resolver::{
     FastPathResolver, FastPathResolverMultiDrive, FastPathResolverStats, NameArena, PathResolver,
-    add_paths_from_full_data,
+    add_path_only_column, add_paths_from_full_data,
 };
 pub use query::MftQuery;
 // Re-export commonly used types