Merge pull request #7 from PR0M3TH3AN/beta

Beta
2025-09-08 07:08:44 +00:00 · 2025-05-19 00:00:22 -04:00
parent 035bff40b3 7b596ab17a
commit aca60ef47c
13 changed files with 284 additions and 50 deletions
--- a/.gitignore
+++ b/.gitignore
@@ -38,6 +38,10 @@ test.db
 .env.*


-# === Other ===
+# === Other Files ===
 repo-context.txt
-saved_config.yaml
+saved_config.yaml
+
+# === Other Dirs ===
+/bench/corpus
+/bench/backups
--- a/bench/dirty-vs-full.md
+++ b/bench/dirty-vs-full.md
@@ -0,0 +1,4 @@
+| Command | Mean [ms] | Min [ms] | Max [ms] | Relative |
+|:---|---:|---:|---:|---:|
+| `full-scan` | 427.0 ± 30.5 | 402.2 | 467.4 | 6.36 ± 0.49 |
+| `dirty-scan` | 67.2 ± 2.1 | 64.7 | 71.6 | 1.00 |
--- a/bench/dirty-vs-full.sh
+++ b/bench/dirty-vs-full.sh
@@ -0,0 +1,91 @@
+#!/usr/bin/env bash
+#
+# bench/dirty-vs-full.sh
+#
+# Compare full-scan vs dirty-scan performance on a large corpus,
+# simulating a random set of file modifications before each dirty scan,
+# and reporting corpus size, number of dirty files, and speedup.
+#
+
+set -euo pipefail
+IFS=$'\n\t'
+
+# Path to the marlin binary (adjust if you build elsewhere)
+MARLIN_BIN=${MARLIN_BIN:-target/release/marlin}
+
+# Directory containing your test corpus (100k+ files)
+CORPUS_DIR=${CORPUS_DIR:-bench/corpus}
+
+# Where to put the ephemeral DB
+DB_PATH=${DB_PATH:-bench/index.db}
+
+# How many files to mark dirty before each dirty‐scan run
+DIRTY_COUNT=${DIRTY_COUNT:-100}
+
+# Number of warm‐up runs
+WARMUPS=${WARMUPS:-3}
+
+# Tell Marlin where to write its DB
+export MARLIN_DB_PATH="$DB_PATH"
+
+# Ensure hyperfine is installed
+if ! command -v hyperfine &>/dev/null; then
+  echo "Error: hyperfine not found. Please install it and try again." >&2
+  exit 1
+fi
+
+# Ensure our corpus exists
+if [ ! -d "$CORPUS_DIR" ]; then
+  echo "Error: corpus directory '$CORPUS_DIR' not found." >&2
+  exit 1
+fi
+
+# Count corpus size
+CORPUS_SIZE=$(find "$CORPUS_DIR" -type f | wc -l | tr -d ' ')
+echo "→ Corpus size: $CORPUS_SIZE files"
+echo "→ Will mark $DIRTY_COUNT files dirty per dirty‐scan run"
+echo
+
+# Clean up any old database
+rm -f "$DB_PATH"
+
+# First, populate the DB once so that dirty-scan has something to do
+echo "→ Initial full scan to populate DB"
+"$MARLIN_BIN" scan "$CORPUS_DIR" >/dev/null 2>&1
+
+echo
+echo "→ Benchmarking full vs dirty scan with hyperfine"
+hyperfine \
+  --warmup "$WARMUPS" \
+  --prepare "
+    # wipe and re-populate
+    rm -f '$DB_PATH'
+    mkdir -p bench
+    export MARLIN_DB_PATH='$DB_PATH'
+    $MARLIN_BIN scan '$CORPUS_DIR' >/dev/null 2>&1
+
+    # seed $DIRTY_COUNT random files as 'dirty' in the DB
+    sqlite3 '$DB_PATH' \"INSERT OR IGNORE INTO file_changes(file_id, marked_at)
+      SELECT id, strftime('%s','now') FROM files
+      ORDER BY RANDOM()
+      LIMIT $DIRTY_COUNT;\"
+  " \
+  --command-name "full-scan"  "MARLIN_DB_PATH='$DB_PATH' $MARLIN_BIN scan       '$CORPUS_DIR' >/dev/null 2>&1" \
+  --command-name "dirty-scan" "MARLIN_DB_PATH='$DB_PATH' $MARLIN_BIN scan --dirty '$CORPUS_DIR' >/dev/null 2>&1" \
+  --export-markdown bench/dirty-vs-full.md
+
+echo
+echo "Results written to bench/dirty-vs-full.md"
+
+# Extract the speedup factor from the markdown table:
+#   the "Relative" column on the full-scan row tells us how many times
+#   slower full-scan is relative to dirty-scan (baseline = 1.00).
+SPEEDUP=$(grep '\`full-scan\`' bench/dirty-vs-full.md \
+         | awk -F'|' '{print $5}' \
+         | xargs)
+
+echo
+echo "→ Summary:"
+echo "   Corpus size:        $CORPUS_SIZE files"
+echo "   Dirty files seeded: $DIRTY_COUNT"
+echo "   Dirty‐scan speedup: dirty-scan ran $SPEEDUP times faster than full-scan"
--- a/bench/gen-corpus.sh
+++ b/bench/gen-corpus.sh
@@ -0,0 +1,30 @@
+#!/usr/bin/env bash
+#
+# bench/gen-corpus.sh
+#
+# Generate a synthetic corpus of N files in nested directories.
+# Defaults to 1 000 files so it stays laptop-friendly.
+#
+
+set -euo pipefail
+IFS=$'\n\t'
+
+# How many files? (default: 1 000)
+COUNT=${COUNT:-100000}
+# Where to put them
+TARGET=${TARGET:-bench/corpus}
+
+# Wipe any old corpus
+rm -rf "$TARGET"
+mkdir -p "$TARGET"
+
+echo "🚀 Generating $COUNT files under $TARGET…"
+for i in $(seq 1 "$COUNT"); do
+  # bucket into 100 sub-dirs so walkdir has some structure
+  dir_index=$(( (i - 1) / (COUNT / 100 + 1) ))
+  subdir="$TARGET/dir$(printf "%03d" "$dir_index")"
+  mkdir -p "$subdir"
+  echo "This is file #$i" > "$subdir/file_$i.txt"
+done
+
+echo "✅ Done: $(find "$TARGET" -type f | wc -l) files created."
--- a/cli-bin/src/cli.rs
+++ b/cli-bin/src/cli.rs
@@ -1,4 +1,5 @@
 // src/cli.rs
+
 pub mod link;
 pub mod coll;
 pub mod view;
@@ -42,6 +43,10 @@ pub enum Commands {

    /// Scan one or more directories and populate the file index
    Scan {
+        /// Only re-index files marked dirty by `marlin watch`
+        #[arg(long)]
+        dirty: bool,
+
        /// Directories to scan (defaults to cwd)
        paths: Vec<std::path::PathBuf>,
    },
--- a/cli-bin/src/main.rs
+++ b/cli-bin/src/main.rs
@@ -16,6 +16,7 @@ use libmarlin::{
    scan,
    utils::determine_scan_root,
 };
+use libmarlin::db::take_dirty;

 use anyhow::{Context, Result};
 use clap::{CommandFactory, Parser};
@@ -83,13 +84,31 @@ fn main() -> Result<()> {
        }

        /* ---- scan ------------------------------------------------ */
-        Commands::Scan { paths } => {
-            let scan_paths = if paths.is_empty() {
+        Commands::Scan { dirty, paths } => {
+            // Determine full-scan roots
+            let scan_paths: Vec<std::path::PathBuf> = if paths.is_empty() {
                vec![env::current_dir()?]
-            } else { paths };
+            } else {
+                paths.into_iter().collect()
+            };

-            for p in scan_paths {
-                scan::scan_directory(&mut conn, &p)?;
+            if dirty {
+                // Incremental: only re-index the files marked dirty
+                let dirty_ids = take_dirty(&conn)?;
+                for id in dirty_ids {
+                    // look up each path by its file_id
+                    let path: String = conn.query_row(
+                        "SELECT path FROM files WHERE id = ?1",
+                        [id],
+                        |r| r.get(0),
+                    )?;
+                    scan::scan_directory(&mut conn, Path::new(&path))?;
+                }
+            } else {
+                // Full rescan of the given directories
+                for p in scan_paths {
+                    scan::scan_directory(&mut conn, &p)?;
+                }
            }
        }

--- a/docs/adr/DP-001_schema_v1.1.md
+++ b/docs/adr/DP-001_schema_v1.1.md
@@ -12,23 +12,34 @@ We’ve landed a basic SQLite-backed `files` table and a contentless FTS5 index.
 - **Custom attributes** (`attributes`)
 - **File-to-file relationships** (`links`)
 - **Named collections** (`collections` + `collection_files`)
- **Saved views** (`views`)
+- **Saved views** (`saved_views`)

-Locking this schema now lets downstream CLI & GUI work against a stable model and ensures our migrations stay easy to reason about.
+Locking this schema now lets downstream CLI & GUI work against a stable model and ensures our migrations stay easy to reason about.  
+*Note: Tag aliases and their `canonical_id` support are deferred to DP-006 (v1.5).*

 ## 2. Decision

-1. **Bump to schema version 1.1** in our migration table.
+Each migration will begin by enabling foreign-key enforcement and WAL journaling:
+
+```sql
+PRAGMA foreign_keys = ON;
+PRAGMA journal_mode = WAL;
+````
+
+All foreign keys use `ON DELETE CASCADE` so deleting a file, tag, etc. automatically cleans up dependents.
+
+1. **Bump to schema version 1.1** in our `schema_version` table.
 2. Provide four migration scripts, applied in order:
-   1. `0001_initial_schema.sql`   – create `files`, `tags`, `file_tags`, `attributes`, `files_fts`, core FTS triggers.
-   2. `0002_update_fts_and_triggers.sql`  – replace old tag/attr FTS triggers with `INSERT OR REPLACE` semantics for full-row refresh.
-   3. `0003_create_links_collections_views.sql`  – introduce `links`, `collections`, `collection_files`, `views` tables.
-   4. `0004_fix_hierarchical_tags_fts.sql`  – refine FTS triggers to index full hierarchical tag-paths via a recursive CTE.
+
+   1. **0001\_initial\_schema.sql** – create core tables (`files`, `tags`, `file_tags`, `attributes`), a contentless FTS5 table (`files_fts`), core FTS triggers, and performance-critical indexes.
+   2. **0002\_update\_fts\_and\_triggers.sql** – replace old tag/attr FTS triggers with `INSERT OR REPLACE` semantics for full-row refresh.
+   3. **0003\_create\_links\_collections\_saved\_views.sql** – introduce `links`, `collections`, `collection_files`, and `saved_views` tables.
+   4. **0004\_fix\_hierarchical\_tags\_fts.sql** – refine FTS triggers to index full hierarchical tag-paths via a recursive CTE.
 3. Expose this schema through our library (`libmarlin::db::open`) so any client sees a v1.1 store.

 ## 3. ER Diagram

-Below is the updated entity-relationship diagram, expressed in PlantUML for clarity. It shows all of the core metadata domains and their relationships:
+Below is the updated entity-relationship diagram (PlantUML):

 ```plantuml
@startuml
@@ -42,11 +53,10 @@ entity files {
 }

 entity tags {
-  * id           : INTEGER <<PK>>
+  * id        : INTEGER <<PK>>
  --
-    name         : TEXT
-    parent_id    : INTEGER <<FK>>
-    canonical_id : INTEGER <<FK>>
+    name      : TEXT
+    parent_id : INTEGER <<FK>>
 }

 entity file_tags {
@@ -63,7 +73,7 @@ entity attributes {
 }

 entity links {
-  * id           : INTEGER <<PK>>
+  * id            : INTEGER <<PK>>
  --
    src_file_id : INTEGER <<FK>>
    dst_file_id : INTEGER <<FK>>
@@ -81,7 +91,7 @@ entity collection_files {
  * file_id       : INTEGER <<FK>>
 }

-entity views {
+entity saved_views {
  * id    : INTEGER <<PK>>
  --
    name  : TEXT
@@ -99,11 +109,11 @@ files          ||--o{ links : "dst_file_id"
 collections    ||--o{ collection_files
 files          ||--o{ collection_files

-views           ||..|| files  : "smart queries (via FTS)"
+saved_views    ||..|| files : "exec via FTS"
@enduml
-````
+```

-*(If you prefer a plain‐ASCII sketch, you can replace the above PlantUML block with:)*
+Or in plain-ASCII:

 ```ascii
 ┌────────┐        ┌────────────┐        ┌───────┐
@@ -124,19 +134,28 @@ views           ||..|| files  : "smart queries (via FTS)"
 │ collections │1──*─│ collection_files │*──1─│ files  │
 └─────────────┘     └──────────────────┘     └────────┘

-┌───────┐
-│ views │
-└───────┘
+┌─────────────┐
+│ saved_views │
+│ (exec FTS)  │
+└─────────────┘
 ```

 ## 4. Migration Summary

-| File                                            | Purpose                                                 |
-| ----------------------------------------------- | ------------------------------------------------------- |
-| **0001\_initial\_schema.sql**                   | Core tables + contentless FTS + path/triggers           |
-| **0002\_update\_fts\_and\_triggers.sql**        | Full-row FTS refresh on tag/attr changes                |
-| **0003\_create\_links\_collections\_views.sql** | Add `links`, `collections`, `collection_files`, `views` |
-| **0004\_fix\_hierarchical\_tags\_fts.sql**      | Recursive CTE for full path tag indexing                |
+| File                                                   | Purpose                                                       |
+| ------------------------------------------------------ | ------------------------------------------------------------- |
+| **0001\_initial\_schema.sql**                          | Core tables + contentless FTS + core triggers + indexes       |
+| **0002\_update\_fts\_and\_triggers.sql**               | Full-row FTS refresh on tag/attr changes                      |
+| **0003\_create\_links\_collections\_saved\_views.sql** | Add `links`, `collections`, `collection_files`, `saved_views` |
+| **0004\_fix\_hierarchical\_tags\_fts.sql**             | Recursive CTE for full tag-path indexing in FTS triggers      |
+
+### Performance-Critical Indexes
+
+* `idx_files_path`       on `files(path)`
+* `idx_files_hash`       on `files(hash)`
+* `idx_tags_name_parent` on `tags(name, parent_id)`
+* `idx_file_tags_tag_id` on `file_tags(tag_id)`
+* `idx_attr_file_key`    on `attributes(file_id, key)`

 ## 5. Example CLI Session

@@ -156,6 +175,10 @@ Saved view 'tasks' = tag:project AND TODO

 $ marlin view list
 tasks: tag:project AND TODO
+
+$ marlin view exec tasks
+~/Projects/Alpha/draft1.md
+~/Projects/Beta/final.md
 ```

 ## 6. Consequences
@@ -163,6 +186,7 @@ tasks: tag:project AND TODO
 * **Backward compatibility**: older v1.0 stores will be migrated on first open.
 * **Stability**: downstream features (TUI, VS Code, web UI) can depend on a stable v1.1 schema.
 * **Simplicity**: by consolidating metadata domains now, future migrations remain small and focused.
+* **Performance**: v1.1 schema meets our cold-start P95 ≤ 3 s on a 100 k-file corpus (with CI-enforced benchmarks and the indexes above).

 ---

--- a/libmarlin/src/db/migrations/0005_add_dirty_table.sql
+++ b/libmarlin/src/db/migrations/0005_add_dirty_table.sql
@@ -0,0 +1,8 @@
+PRAGMA foreign_keys = ON;
+PRAGMA journal_mode = WAL;
+
+-- Track which files need re-indexing
+CREATE TABLE IF NOT EXISTS file_changes (
+  file_id   INTEGER PRIMARY KEY REFERENCES files(id) ON DELETE CASCADE,
+  marked_at INTEGER NOT NULL             -- UNIX timestamp
+);
--- a/libmarlin/src/db/mod.rs
+++ b/libmarlin/src/db/mod.rs
@@ -15,7 +15,7 @@ use rusqlite::{
    Connection,
    OpenFlags,
    OptionalExtension,
-    TransactionBehavior,  
+    TransactionBehavior,
 };
 use tracing::{debug, info, warn};

@@ -26,6 +26,7 @@ const MIGRATIONS: &[(&str, &str)] = &[
    ("0002_update_fts_and_triggers.sql", include_str!("migrations/0002_update_fts_and_triggers.sql")),
    ("0003_create_links_collections_views.sql", include_str!("migrations/0003_create_links_collections_views.sql")),
    ("0004_fix_hierarchical_tags_fts.sql", include_str!("migrations/0004_fix_hierarchical_tags_fts.sql")),
+    ("0005_add_dirty_table.sql", include_str!("migrations/0005_add_dirty_table.sql")),
 ];

 /* ─── connection bootstrap ────────────────────────────────────────── */
@@ -39,13 +40,12 @@ pub fn open<P: AsRef<Path>>(db_path: P) -> Result<Connection> {
    conn.pragma_update(None, "foreign_keys", "ON")?;

    // Wait up to 30 s for a competing writer before giving up
-    conn.busy_timeout(std::time::Duration::from_secs(30))?;   // ← tweaked
+    conn.busy_timeout(std::time::Duration::from_secs(30))?;

    apply_migrations(&mut conn)?;
    Ok(conn)
 }

-
 /* ─── migration runner ────────────────────────────────────────────── */

 pub(crate) fn apply_migrations(conn: &mut Connection) -> Result<()> {
@@ -85,7 +85,7 @@ pub(crate) fn apply_migrations(conn: &mut Connection) -> Result<()> {

        info!("applying migration {}", fname);
        tx.execute_batch(sql)
-            .with_context(|| format!("could not apply migration {fname}"))?;
+            .with_context(|| format!("could not apply migration {}", fname))?;

        tx.execute(
            "INSERT INTO schema_version (version, applied_on) VALUES (?1, ?2)",
@@ -158,7 +158,12 @@ pub fn upsert_attr(conn: &Connection, file_id: i64, key: &str, value: &str) -> R

 /* ─── links ───────────────────────────────────────────────────────── */

-pub fn add_link(conn: &Connection, src_file_id: i64, dst_file_id: i64, link_type: Option<&str>) -> Result<()> {
+pub fn add_link(
+    conn: &Connection,
+    src_file_id: i64,
+    dst_file_id: i64,
+    link_type: Option<&str>,
+) -> Result<()> {
    conn.execute(
        "INSERT INTO links(src_file_id, dst_file_id, type)
         VALUES (?1, ?2, ?3)
@@ -168,7 +173,12 @@ pub fn add_link(conn: &Connection, src_file_id: i64, dst_file_id: i64, link_type
    Ok(())
 }

-pub fn remove_link(conn: &Connection, src_file_id: i64, dst_file_id: i64, link_type: Option<&str>) -> Result<()> {
+pub fn remove_link(
+    conn: &Connection,
+    src_file_id: i64,
+    dst_file_id: i64,
+    link_type: Option<&str>,
+) -> Result<()> {
    conn.execute(
        "DELETE FROM links
         WHERE src_file_id = ?1
@@ -190,8 +200,10 @@ pub fn list_links(
    // Files matching pattern
    let mut stmt = conn.prepare("SELECT id, path FROM files WHERE path LIKE ?1")?;
    let rows = stmt
-        .query_map(params![like_pattern], |r| Ok((r.get::<_, i64>(0)?, r.get::<_, String>(1)?)))?
-        .collect::<Result<Vec<_>, _>>()?;
+        .query_map(params![like_pattern], |r| {
+            Ok((r.get::<_, i64>(0)?, r.get::<_, String>(1)?))
+        })?
+        .collect::<StdResult<Vec<_>, _>>()?;

    let mut out = Vec::new();
    for (fid, fpath) in rows {
@@ -210,8 +222,10 @@ pub fn list_links(

        let mut stmt2 = conn.prepare(&sql)?;
        let links = stmt2
-            .query_map(params![fid, link_type], |r| Ok((r.get::<_, String>(0)?, r.get::<_, Option<String>>(1)?)))?
-            .collect::<Result<Vec<_>, _>>()?;
+            .query_map(params![fid, link_type], |r| {
+                Ok((r.get::<_, String>(0)?, r.get::<_, Option<String>>(1)?))
+            })?
+            .collect::<StdResult<Vec<_>, _>>()?;

        for (other, typ) in links {
            out.push((fpath.clone(), other, typ));
@@ -238,11 +252,11 @@ pub fn find_backlinks(
        Ok((r.get::<_, String>(0)?, r.get::<_, Option<String>>(1)?))
    })?;

-    let out = rows.collect::<StdResult<Vec<_>, _>>()?;   // rusqlite → anyhow via `?`
+    let out = rows.collect::<StdResult<Vec<_>, _>>()?;
    Ok(out)
 }

-/* ─── NEW: collections helpers ────────────────────────────────────── */
+/* ─── collections helpers ────────────────────────────────────────── */

 pub fn ensure_collection(conn: &Connection, name: &str) -> Result<i64> {
    conn.execute(
@@ -281,7 +295,7 @@ pub fn list_collection(conn: &Connection, name: &str) -> Result<Vec<String>> {
    Ok(list)
 }

-/* ─── NEW: saved views (smart folders) ────────────────────────────── */
+/* ─── saved views (smart folders) ───────────────────────────────── */

 pub fn save_view(conn: &Connection, name: &str, query: &str) -> Result<()> {
    conn.execute(
@@ -295,7 +309,6 @@ pub fn save_view(conn: &Connection, name: &str, query: &str) -> Result<()> {

 pub fn list_views(conn: &Connection) -> Result<Vec<(String, String)>> {
    let mut stmt = conn.prepare("SELECT name, query FROM views ORDER BY name")?;
-
    let rows = stmt.query_map([], |r| Ok((r.get::<_, String>(0)?, r.get::<_, String>(1)?)))?;
    let list = rows.collect::<StdResult<Vec<_>, _>>()?;
    Ok(list)
@@ -307,7 +320,32 @@ pub fn view_query(conn: &Connection, name: &str) -> Result<String> {
        [name],
        |r| r.get::<_, String>(0),
    )
-    .context(format!("no view called '{name}'"))
+    .context(format!("no view called '{}'", name))
+}
+
+/* ─── dirty‐scan helpers ─────────────────────────────────────────── */
+
+/// Mark a file as “dirty” so it’ll be picked up by `scan_dirty`.
+pub fn mark_dirty(conn: &Connection, file_id: i64) -> Result<()> {
+    conn.execute(
+        "INSERT OR IGNORE INTO file_changes(file_id, marked_at)
+         VALUES (?1, strftime('%s','now'))",
+        params![file_id],
+    )?;
+    Ok(())
+}
+
+/// Take and clear all dirty file IDs for incremental re-scan.
+pub fn take_dirty(conn: &Connection) -> Result<Vec<i64>> {
+    let mut ids = Vec::new();
+    {
+        let mut stmt = conn.prepare("SELECT file_id FROM file_changes")?;
+        for row in stmt.query_map([], |r| r.get(0))? {
+            ids.push(row?);
+        }
+    }
+    conn.execute("DELETE FROM file_changes", [])?;
+    Ok(ids)
 }

 /* ─── backup / restore helpers ────────────────────────────────────── */
--- a/libmarlin/src/scan.rs
+++ b/libmarlin/src/scan.rs
@@ -11,7 +11,10 @@ use walkdir::WalkDir;
 /// Recursively walk `root` and upsert file metadata.
 /// Triggers keep the FTS table in sync.
 pub fn scan_directory(conn: &mut Connection, root: &Path) -> Result<usize> {
+    // Begin a transaction so we batch many inserts/updates together
    let tx = conn.transaction()?;
+
+    // Prepare the upsert statement once
    let mut stmt = tx.prepare(
        r#"
        INSERT INTO files(path, size, mtime)
@@ -23,12 +26,15 @@ pub fn scan_directory(conn: &mut Connection, root: &Path) -> Result<usize> {
    )?;

    let mut count = 0usize;
+
+    // Walk the directory recursively
    for entry in WalkDir::new(root)
        .into_iter()
        .filter_map(Result::ok)
        .filter(|e| e.file_type().is_file())
    {
        let path = entry.path();
+
        // Skip the database file and its WAL/SHM siblings
        if let Some(name) = path.file_name().and_then(|n| n.to_str()) {
            if name.ends_with(".db") || name.ends_with("-wal") || name.ends_with("-shm") {
@@ -36,6 +42,7 @@ pub fn scan_directory(conn: &mut Connection, root: &Path) -> Result<usize> {
            }
        }

+        // Gather file metadata
        let meta = fs::metadata(path)?;
        let size = meta.len() as i64;
        let mtime = meta
@@ -43,14 +50,18 @@ pub fn scan_directory(conn: &mut Connection, root: &Path) -> Result<usize> {
            .duration_since(std::time::UNIX_EPOCH)?
            .as_secs() as i64;

+        // Execute the upsert
        let path_str = path.to_string_lossy();
        stmt.execute(params![path_str, size, mtime])?;
        count += 1;
+
        debug!(file = %path_str, "indexed");
    }

+    // Finalize and commit
    drop(stmt);
    tx.commit()?;
+
    info!(indexed = count, "scan complete");
    Ok(count)
 }
--- a/target/.rustc_info.json
+++ b/target/.rustc_info.json
@@ -1 +1 @@
-{"rustc_fingerprint":17558195974417946175,"outputs":{"7971740275564407648":{"success":true,"status":"","code":0,"stdout":"___\nlib___.rlib\nlib___.so\nlib___.so\nlib___.a\nlib___.so\n/home/user/.rustup/toolchains/nightly-x86_64-unknown-linux-gnu\noff\npacked\nunpacked\n___\ndebug_assertions\nfmt_debug=\"full\"\noverflow_checks\npanic=\"unwind\"\nproc_macro\nrelocation_model=\"pic\"\ntarget_abi=\"\"\ntarget_arch=\"x86_64\"\ntarget_endian=\"little\"\ntarget_env=\"gnu\"\ntarget_family=\"unix\"\ntarget_feature=\"fxsr\"\ntarget_feature=\"sse\"\ntarget_feature=\"sse2\"\ntarget_feature=\"x87\"\ntarget_has_atomic\ntarget_has_atomic=\"16\"\ntarget_has_atomic=\"32\"\ntarget_has_atomic=\"64\"\ntarget_has_atomic=\"8\"\ntarget_has_atomic=\"ptr\"\ntarget_has_atomic_equal_alignment=\"16\"\ntarget_has_atomic_equal_alignment=\"32\"\ntarget_has_atomic_equal_alignment=\"64\"\ntarget_has_atomic_equal_alignment=\"8\"\ntarget_has_atomic_equal_alignment=\"ptr\"\ntarget_has_atomic_load_store\ntarget_has_atomic_load_store=\"16\"\ntarget_has_atomic_load_store=\"32\"\ntarget_has_atomic_load_store=\"64\"\ntarget_has_atomic_load_store=\"8\"\ntarget_has_atomic_load_store=\"ptr\"\ntarget_has_reliable_f128\ntarget_has_reliable_f16\ntarget_has_reliable_f16_math\ntarget_os=\"linux\"\ntarget_pointer_width=\"64\"\ntarget_thread_local\ntarget_vendor=\"unknown\"\nub_checks\nunix\n","stderr":""},"10431901537437931773":{"success":true,"status":"","code":0,"stdout":"___\nlib___.rlib\nlib___.so\nlib___.so\nlib___.a\nlib___.so\n/home/user/.rustup/toolchains/nightly-x86_64-unknown-linux-gnu\noff\npacked\nunpacked\n___\ndebug_assertions\nfmt_debug=\"full\"\noverflow_checks\npanic=\"unwind\"\nproc_macro\nrelocation_model=\"pic\"\ntarget_abi=\"\"\ntarget_arch=\"x86_64\"\ntarget_endian=\"little\"\ntarget_env=\"gnu\"\ntarget_family=\"unix\"\ntarget_feature=\"fxsr\"\ntarget_feature=\"sse\"\ntarget_feature=\"sse2\"\ntarget_feature=\"x87\"\ntarget_has_atomic\ntarget_has_atomic=\"16\"\ntarget_has_atomic=\"32\"\ntarget_has_atomic=\"64\"\ntarget_has_atomic=\"8\"\ntarget_has_atomic=\"ptr\"\ntarget_has_atomic_equal_alignment=\"16\"\ntarget_has_atomic_equal_alignment=\"32\"\ntarget_has_atomic_equal_alignment=\"64\"\ntarget_has_atomic_equal_alignment=\"8\"\ntarget_has_atomic_equal_alignment=\"ptr\"\ntarget_has_atomic_load_store\ntarget_has_atomic_load_store=\"16\"\ntarget_has_atomic_load_store=\"32\"\ntarget_has_atomic_load_store=\"64\"\ntarget_has_atomic_load_store=\"8\"\ntarget_has_atomic_load_store=\"ptr\"\ntarget_has_reliable_f128\ntarget_has_reliable_f16\ntarget_has_reliable_f16_math\ntarget_os=\"linux\"\ntarget_pointer_width=\"64\"\ntarget_thread_local\ntarget_vendor=\"unknown\"\ntarpaulin\nub_checks\nunix\n","stderr":""},"17747080675513052775":{"success":true,"status":"","code":0,"stdout":"rustc 1.89.0-nightly (777d37277 2025-05-17)\nbinary: rustc\ncommit-hash: 777d372772aa3b39ba7273fcb8208a89f2ab0afd\ncommit-date: 2025-05-17\nhost: x86_64-unknown-linux-gnu\nrelease: 1.89.0-nightly\nLLVM version: 20.1.4\n","stderr":""}},"successes":{}}
+{"rustc_fingerprint":10768506583288887294,"outputs":{"7971740275564407648":{"success":true,"status":"","code":0,"stdout":"___\nlib___.rlib\nlib___.so\nlib___.so\nlib___.a\nlib___.so\n/home/user/.rustup/toolchains/stable-x86_64-unknown-linux-gnu\noff\npacked\nunpacked\n___\ndebug_assertions\npanic=\"unwind\"\nproc_macro\ntarget_abi=\"\"\ntarget_arch=\"x86_64\"\ntarget_endian=\"little\"\ntarget_env=\"gnu\"\ntarget_family=\"unix\"\ntarget_feature=\"fxsr\"\ntarget_feature=\"sse\"\ntarget_feature=\"sse2\"\ntarget_has_atomic=\"16\"\ntarget_has_atomic=\"32\"\ntarget_has_atomic=\"64\"\ntarget_has_atomic=\"8\"\ntarget_has_atomic=\"ptr\"\ntarget_os=\"linux\"\ntarget_pointer_width=\"64\"\ntarget_vendor=\"unknown\"\nunix\n","stderr":""},"17747080675513052775":{"success":true,"status":"","code":0,"stdout":"rustc 1.86.0 (05f9846f8 2025-03-31)\nbinary: rustc\ncommit-hash: 05f9846f893b09a1be1fc8560e33fc3c815cfecb\ncommit-date: 2025-03-31\nhost: x86_64-unknown-linux-gnu\nrelease: 1.86.0\nLLVM version: 19.1.7\n","stderr":""}},"successes":{}}
--- a/target/release/marlin
+++ b/target/release/marlin
--- a/target/release/marlin.d
+++ b/target/release/marlin.d
@@ -1 +1 @@
-/home/user/Documents/GitHub/Marlin/target/release/marlin: /home/user/Documents/GitHub/Marlin/cli-bin/build.rs /home/user/Documents/GitHub/Marlin/cli-bin/src/cli/annotate.rs /home/user/Documents/GitHub/Marlin/cli-bin/src/cli/coll.rs /home/user/Documents/GitHub/Marlin/cli-bin/src/cli/event.rs /home/user/Documents/GitHub/Marlin/cli-bin/src/cli/link.rs /home/user/Documents/GitHub/Marlin/cli-bin/src/cli/remind.rs /home/user/Documents/GitHub/Marlin/cli-bin/src/cli/state.rs /home/user/Documents/GitHub/Marlin/cli-bin/src/cli/task.rs /home/user/Documents/GitHub/Marlin/cli-bin/src/cli/version.rs /home/user/Documents/GitHub/Marlin/cli-bin/src/cli/view.rs /home/user/Documents/GitHub/Marlin/cli-bin/src/cli.rs /home/user/Documents/GitHub/Marlin/cli-bin/src/main.rs /home/user/Documents/GitHub/Marlin/libmarlin/src/config.rs /home/user/Documents/GitHub/Marlin/libmarlin/src/db/migrations/0001_initial_schema.sql /home/user/Documents/GitHub/Marlin/libmarlin/src/db/migrations/0002_update_fts_and_triggers.sql /home/user/Documents/GitHub/Marlin/libmarlin/src/db/migrations/0003_create_links_collections_views.sql /home/user/Documents/GitHub/Marlin/libmarlin/src/db/migrations/0004_fix_hierarchical_tags_fts.sql /home/user/Documents/GitHub/Marlin/libmarlin/src/db/mod.rs /home/user/Documents/GitHub/Marlin/libmarlin/src/lib.rs /home/user/Documents/GitHub/Marlin/libmarlin/src/logging.rs /home/user/Documents/GitHub/Marlin/libmarlin/src/scan.rs /home/user/Documents/GitHub/Marlin/libmarlin/src/utils.rs
+/home/user/Documents/GitHub/Marlin/target/release/marlin: /home/user/Documents/GitHub/Marlin/cli-bin/build.rs /home/user/Documents/GitHub/Marlin/cli-bin/src/cli/annotate.rs /home/user/Documents/GitHub/Marlin/cli-bin/src/cli/coll.rs /home/user/Documents/GitHub/Marlin/cli-bin/src/cli/event.rs /home/user/Documents/GitHub/Marlin/cli-bin/src/cli/link.rs /home/user/Documents/GitHub/Marlin/cli-bin/src/cli/remind.rs /home/user/Documents/GitHub/Marlin/cli-bin/src/cli/state.rs /home/user/Documents/GitHub/Marlin/cli-bin/src/cli/task.rs /home/user/Documents/GitHub/Marlin/cli-bin/src/cli/version.rs /home/user/Documents/GitHub/Marlin/cli-bin/src/cli/view.rs /home/user/Documents/GitHub/Marlin/cli-bin/src/cli.rs /home/user/Documents/GitHub/Marlin/cli-bin/src/main.rs /home/user/Documents/GitHub/Marlin/libmarlin/src/config.rs /home/user/Documents/GitHub/Marlin/libmarlin/src/db/migrations/0001_initial_schema.sql /home/user/Documents/GitHub/Marlin/libmarlin/src/db/migrations/0002_update_fts_and_triggers.sql /home/user/Documents/GitHub/Marlin/libmarlin/src/db/migrations/0003_create_links_collections_views.sql /home/user/Documents/GitHub/Marlin/libmarlin/src/db/migrations/0004_fix_hierarchical_tags_fts.sql /home/user/Documents/GitHub/Marlin/libmarlin/src/db/migrations/0005_add_dirty_table.sql /home/user/Documents/GitHub/Marlin/libmarlin/src/db/mod.rs /home/user/Documents/GitHub/Marlin/libmarlin/src/lib.rs /home/user/Documents/GitHub/Marlin/libmarlin/src/logging.rs /home/user/Documents/GitHub/Marlin/libmarlin/src/scan.rs /home/user/Documents/GitHub/Marlin/libmarlin/src/utils.rs