Merge pull request #77 from PR0M3TH3AN/beta

Beta
2025-09-07 06:38:44 +00:00 · 2025-05-24 21:54:52 -04:00
parent 0a5682805b 06d96fd3f1
commit 0e4d777b62
11 changed files with 788 additions and 405 deletions
--- a/.gitignore
+++ b/.gitignore
@@ -1,7 +1,6 @@
 # === Rust build artifacts ===

 /target/
-/Cargo.lock

 # === IDE & Editor settings ===

--- a/Cargo.lock
+++ b/Cargo.lock
@@ -79,12 +79,12 @@ dependencies = [

 [[package]]
 name = "anstyle-wincon"
-version = "3.0.7"
+version = "3.0.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ca3534e77181a9cc07539ad51f2141fe32f6c3ffd4df76db8ad92346b003ae4e"
+checksum = "6680de5231bd6ee4c6191b8a1325daa282b415391ec9d3a37bd34f2060dc73fa"
 dependencies = [
 "anstyle",
- "once_cell",
+ "once_cell_polyfill",
 "windows-sys 0.59.0",
 ]

@@ -156,9 +156,9 @@ checksum = "1628fb46dfa0b37568d12e5edd512553eccf6a22a78e8bde00bb4aed84d5bdbf"

 [[package]]
 name = "cc"
-version = "1.2.23"
+version = "1.2.24"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5f4ac86a9e5bc1e2b3449ab9d7d3a6a405e3d1bb28d7b9be8614f55846ae3766"
+checksum = "16595d3be041c03b09d08d0858631facccee9221e579704070e6e9e4915d3bc7"
 dependencies = [
 "shlex",
 ]
@@ -470,12 +470,6 @@ version = "0.3.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a8d1add55171497b4705a648c6b583acafb01d58050a51727785f0b2c8e0a2b2"

-[[package]]
-name = "hashbrown"
-version = "0.12.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8a9ee70c43aaf417c914396645a0fa852624801b24ebb7ae78fe8272889ac888"
-
 [[package]]
 name = "hashbrown"
 version = "0.14.5"
@@ -530,16 +524,6 @@ dependencies = [
 "cc",
 ]

-[[package]]
-name = "indexmap"
-version = "1.9.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bd070e393353796e801d209ad339e89596eb4c8d430d18ede6a1cced8fafbd99"
-dependencies = [
- "autocfg",
- "hashbrown 0.12.3",
-]
-
 [[package]]
 name = "indexmap"
 version = "2.9.0"
@@ -635,8 +619,8 @@ dependencies = [
 "glob",
 "lazy_static",
 "notify",
- "priority-queue",
 "rusqlite",
+ "same-file",
 "serde_json",
 "sha2",
 "shellexpand",
@@ -820,6 +804,12 @@ version = "1.21.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "42f5e15c9953c5e4ccceeb2e7382a716482c34515315f7b03532b8b4e8393d2d"

+[[package]]
+name = "once_cell_polyfill"
+version = "1.70.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a4895175b425cb1f87721b59f0f286c2092bd4af812243672510e1ac53e2e0ad"
+
 [[package]]
 name = "option-ext"
 version = "0.2.0"
@@ -874,16 +864,6 @@ dependencies = [
 "termtree",
 ]

-[[package]]
-name = "priority-queue"
-version = "1.4.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a0bda9164fe05bc9225752d54aae413343c36f684380005398a6a8fde95fe785"
-dependencies = [
- "autocfg",
- "indexmap 1.9.3",
-]
-
 [[package]]
 name = "proc-macro2"
 version = "1.0.95"
@@ -1012,9 +992,9 @@ dependencies = [

 [[package]]
 name = "rustversion"
-version = "1.0.20"
+version = "1.0.21"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "eded382c5f5f786b989652c49544c4877d9f015cc22e145a5ea8ea66c2921cd2"
+checksum = "8a0d197bd2c9dc6e53b84da9556a69ba4cdfab8619eb41a8bd1cc2027a0f6b1d"

 [[package]]
 name = "ryu"
@@ -1069,7 +1049,7 @@ version = "0.9.34+deprecated"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "6a8b1a1a2ebf674015cc02edccce75287f1a0130d394307b36743c2f5d504b47"
 dependencies = [
- "indexmap 2.9.0",
+ "indexmap",
 "itoa",
 "ryu",
 "serde",
--- a/cli-bin/docs/cli_cheatsheet.md
+++ b/cli-bin/docs/cli_cheatsheet.md
@@ -22,3 +22,6 @@
 | `event add` | — |
 | `event timeline` | — |
 | `backup run` | --dir, --prune, --verify, --file |
+| `watch start` | --debounce-ms |
+| `watch status` | — |
+| `watch stop` | — |
--- a/docs/adr/DP-001_schema_v1.1.md
+++ b/docs/adr/DP-001_schema_v1.1.md
@@ -8,14 +8,14 @@

 We’ve landed a basic SQLite-backed `files` table and a contentless FTS5 index. Before we build out higher-level features, we need to lock down our **v1.1** metadata schema for:

- **Hierarchical tags** (`tags` + `file_tags`) – optional `canonical_id` for aliases
+- **Hierarchical tags** (`tags` + `file_tags`) – alias resolution handled at query time
 - **Custom attributes** (`attributes`)
 - **File-to-file relationships** (`links`)
 - **Named collections** (`collections` + `collection_files`)
 - **Views** (`views`)

-Locking this schema now lets downstream CLI & GUI work against a stable model and ensures our migrations stay easy to reason about.  
-Tags optionally reference a canonical tag via the `canonical_id` column.
+Locking this schema now lets downstream CLI & GUI work against a stable model and ensures our migrations stay easy to reason about.
+Alias relationships are resolved outside the table itself; there is no `canonical_id` column.

 ## 2. Decision

@@ -58,7 +58,6 @@ entity tags {
  --
    name      : TEXT
    parent_id : INTEGER <<FK>>
-    canonical_id : INTEGER <<FK>>
 }

 entity file_tags {
@@ -151,6 +150,7 @@ Or in plain-ASCII:
 | **0003\_create\_links\_collections\_views.sql** | Add `links`, `collections`, `collection_files`, `views` |
 | **0004\_fix\_hierarchical\_tags\_fts.sql**             | Recursive CTE for full tag-path indexing in FTS triggers      |
 | **0005_add_dirty_table.sql**                           | Track modified files needing reindexing |
+| **0006_drop_tags_canonical_id.sql**                   | Remove legacy `canonical_id` column from `tags` |

 ### Performance-Critical Indexes

--- a/docs/roadmap.md
+++ b/docs/roadmap.md
@@ -46,7 +46,7 @@
 | Tarpaulin coverage gate    | S0             | —                    | –         |
 | Watch mode (FS events)     | Epic 1         | `marlin watch .`     | DP‑002    |
 | Backup auto‑prune          | Epic 1         | `backup --prune N`   | –         |
-| Rename/move tracking     | Epic 2         | automatic path update | Spec‑RMH |
+| ~~Rename/move tracking~~     | Epic 2         | automatic path update | Spec‑RMH |
 | Dirty‑scan                 | Epic 2         | `scan --dirty`       | DP‑002    |
 | Grep snippets              | Phase 3        | `search -C3 …`       | DP‑004    |
 | Hash / dedupe              | Phase 4        | `scan --rehash`      | DP‑005    |
@@ -75,7 +75,7 @@ Before a milestone is declared “shipped”:
 | - | ------------------------------ | ------ | ------------- |
 | ~~1~~ | ~~Crate split + CI baseline~~      | @alice | ~~26 May 25~~ |
 | ~~2~~ | ~~Tarpaulin + Hyperfine jobs~~     | @bob   | ~~26 May 25~~ |
-| 3 | **DP‑001 Schema v1.1** draft   | @carol | **30 May 25** |
+| ~~3~~ | ~~DP‑001 Schema v1.1 draft~~   | @carol | ~~30 May 25~~ |
 | ~~4~~ | ~~backup prune CLI + nightly job~~ | @dave  | ~~05 Jun 25~~ |

 > *This roadmap now contains both product-level “what” and engineering-level “how/when/prove it”.  It should allow a new contributor to jump in, pick the matching DP, and know exactly the bar they must clear for their code to merge.*  
--- a/docs/vision.md
+++ b/docs/vision.md
@@ -8,7 +8,7 @@

 | Feature Area                        | Capabilities                                                                                                                                                                                                                                                                                                                             |
 | ----------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| **Tagging System**                  | • Unlimited, hierarchical or flat tags.<br>• Alias/synonym support with precedence rules (admin‑defined canonical name).<br>• **Bulk tag editing** via multi‑select context menu.<br>• Folder‑to‑Tag import with optional *watch & sync* mode so new sub‑folders inherit tags automatically.                                             |
+| **Tagging System**                  | • Unlimited, hierarchical or flat tags.<br>• Alias/synonym support via admin‑defined mappings (canonical names resolved at query time).<br>• **Bulk tag editing** via multi‑select context menu.<br>• Folder‑to‑Tag import with optional *watch & sync* mode so new sub‑folders inherit tags automatically.                                             |
 | **Custom Metadata Attributes**      | • User‑defined fields (text, number, date, enum, boolean).<br>• Per‑template **Custom Metadata Schemas** (e.g. *Photo* → *Date, Location*).                                                                                                                                                                                              |
 | **File Relationships**              | • Typed, directional or bidirectional links (*related to*, *duplicate of*, *cites*…).<br>• Plugin API can register new relationship sets.                                                                                                                                                                                                |
 | **Version Control for Metadata**    | • Every change logged; unlimited roll‑back.<br>• Side‑by‑side diff viewer and *blame* panel showing *who/when/what*.<br>• Offline edits stored locally and merged (Git‑style optimistic merge with conflict prompts).                                                                                                                    |
@@ -36,7 +36,7 @@

 ```text
 files(id PK, path, inode, size, mtime, ctime, hash)
-tags(id PK, name, parent_id, canonical_id)
+tags(id PK, name, parent_id)
 file_tags(file_id FK, tag_id FK)
 attributes(id PK, file_id FK, key, value, value_type)
 relationships(id PK, src_file_id FK, dst_file_id FK, rel_type, direction)
--- a/libmarlin/Cargo.toml
+++ b/libmarlin/Cargo.toml
@@ -11,13 +11,13 @@ crossbeam-channel  = "0.5"
 directories        = "5"
 glob               = "0.3"
 notify             = "6.0"
-priority-queue     = "1.3"
 rusqlite           = { version = "0.31", features = ["bundled", "backup"] }
 sha2               = "0.10"
 tracing            = "0.1"
 tracing-subscriber = { version = "0.3", features = ["fmt", "env-filter"] }
 walkdir            = "2.5"
 shlex              = "1.3"
+same-file         = "1"
 shellexpand        = "3.1"
 serde_json         = { version = "1", optional = true }

--- a/libmarlin/src/db/migrations/0007_fix_rename_trigger.sql
+++ b/libmarlin/src/db/migrations/0007_fix_rename_trigger.sql
@@ -0,0 +1,20 @@
+-- src/db/migrations/0007_fix_rename_trigger.sql
+PRAGMA foreign_keys = ON;
+PRAGMA journal_mode = WAL;
+
+-- Recreate files_fts_au_file trigger using INSERT OR REPLACE
+DROP TRIGGER IF EXISTS files_fts_au_file;
+CREATE TRIGGER files_fts_au_file
+AFTER UPDATE OF path ON files
+BEGIN
+    INSERT OR REPLACE INTO files_fts(rowid, path, tags_text, attrs_text)
+        SELECT NEW.id,
+               NEW.path,
+               (SELECT IFNULL(GROUP_CONCAT(t.name, ' '), '')
+                  FROM file_tags ft
+                  JOIN tags t ON ft.tag_id = t.id
+                 WHERE ft.file_id = NEW.id),
+               (SELECT IFNULL(GROUP_CONCAT(a.key || '=' || a.value, ' '), '')
+                  FROM attributes a
+                 WHERE a.file_id = NEW.id);
+END;
--- a/libmarlin/src/db/mod.rs
+++ b/libmarlin/src/db/mod.rs
@@ -50,6 +50,10 @@ const MIGRATIONS: &[(&str, &str)] = &[
        "0006_drop_tags_canonical_id.sql",
        include_str!("migrations/0006_drop_tags_canonical_id.sql"),
    ),
+    (
+        "0007_fix_rename_trigger.sql",
+        include_str!("migrations/0007_fix_rename_trigger.sql"),
+    ),
 ];

 /* ─── schema helpers ─────────────────────────────────────────────── */
@@ -387,6 +391,39 @@ pub fn take_dirty(conn: &Connection) -> Result<Vec<i64>> {
    Ok(ids)
 }

+/* ─── rename helpers ────────────────────────────────────────────── */
+
+pub fn update_file_path(conn: &Connection, old_path: &str, new_path: &str) -> Result<()> {
+    let file_id: i64 = conn.query_row("SELECT id FROM files WHERE path = ?1", [old_path], |r| {
+        r.get(0)
+    })?;
+    conn.execute(
+        "UPDATE files SET path = ?1 WHERE id = ?2",
+        params![new_path, file_id],
+    )?;
+    mark_dirty(conn, file_id)?;
+    Ok(())
+}
+
+pub fn rename_directory(conn: &mut Connection, old_dir: &str, new_dir: &str) -> Result<()> {
+    let like_pattern = format!("{}/%", old_dir.trim_end_matches('/'));
+    let ids = {
+        let mut stmt = conn.prepare("SELECT id FROM files WHERE path LIKE ?1")?;
+        let rows = stmt.query_map([&like_pattern], |r| r.get::<_, i64>(0))?;
+        rows.collect::<StdResult<Vec<_>, _>>()?
+    };
+    let tx = conn.transaction()?;
+    tx.execute(
+        "UPDATE files SET path = REPLACE(path, ?1, ?2) WHERE path LIKE ?3",
+        params![old_dir, new_dir, like_pattern],
+    )?;
+    for fid in ids {
+        mark_dirty(&tx, fid)?;
+    }
+    tx.commit()?;
+    Ok(())
+}
+
 /* ─── backup / restore helpers ────────────────────────────────────── */

 pub fn backup<P: AsRef<Path>>(db_path: P) -> Result<PathBuf> {
--- a/libmarlin/src/watcher.rs
+++ b/libmarlin/src/watcher.rs
--- a/libmarlin/src/watcher_tests.rs
+++ b/libmarlin/src/watcher_tests.rs
@@ -7,14 +7,46 @@ mod tests {
    // These are still from the watcher module
    use crate::db::open as open_marlin_db;
    use crate::watcher::{FileWatcher, WatcherConfig, WatcherState}; // Use your project's DB open function
+    use crate::Marlin;

    use std::fs::{self, File};
    use std::io::Write;
    // No longer need: use std::path::PathBuf;
    use std::thread;
-    use std::time::Duration;
+    use std::time::{Duration, Instant};
    use tempfile::tempdir;

+    /// Polls the DB until `query` returns `expected` or the timeout elapses.
+    fn wait_for_row_count(
+        marlin: &Marlin,
+        path: &std::path::Path,
+        expected: i64,
+        timeout: Duration,
+    ) {
+        let start = Instant::now();
+        loop {
+            let count: i64 = marlin
+                .conn()
+                .query_row(
+                    "SELECT COUNT(*) FROM files WHERE path = ?1",
+                    [path.to_string_lossy()],
+                    |r| r.get(0),
+                )
+                .unwrap();
+            if count == expected {
+                break;
+            }
+            if start.elapsed() > timeout {
+                panic!(
+                    "Timed out waiting for {} rows for {}",
+                    expected,
+                    path.display()
+                );
+            }
+            thread::sleep(Duration::from_millis(50));
+        }
+    }
+
    #[test]
    fn test_watcher_lifecycle() {
        // Create a temp directory for testing
@@ -60,7 +92,7 @@ mod tests {
        thread::sleep(Duration::from_millis(200));
        fs::remove_file(&new_file_path).expect("Failed to remove file");

-        thread::sleep(Duration::from_millis(500));
+        thread::sleep(Duration::from_millis(1500));
        watcher.stop().expect("Failed to stop watcher");

        assert_eq!(watcher.status().unwrap().state, WatcherState::Stopped);
@@ -144,4 +176,97 @@ mod tests {
            );
        }
    }
+
+    #[test]
+    fn rename_file_updates_db() {
+        let tmp = tempdir().unwrap();
+        let dir = tmp.path();
+        let file = dir.join("a.txt");
+        fs::write(&file, b"hi").unwrap();
+        let db_path = dir.join("test.db");
+        let mut marlin = Marlin::open_at(&db_path).unwrap();
+        marlin.scan(&[dir]).unwrap();
+
+        let mut watcher = marlin
+            .watch(
+                dir,
+                Some(WatcherConfig {
+                    debounce_ms: 50,
+                    ..Default::default()
+                }),
+            )
+            .unwrap();
+
+        thread::sleep(Duration::from_millis(100));
+        let new_file = dir.join("b.txt");
+        fs::rename(&file, &new_file).unwrap();
+        wait_for_row_count(&marlin, &new_file, 1, Duration::from_secs(10));
+        watcher.stop().unwrap();
+        assert!(
+            watcher.status().unwrap().events_processed > 0,
+            "rename event should be processed"
+        );
+
+        let count: i64 = marlin
+            .conn()
+            .query_row(
+                "SELECT COUNT(*) FROM files WHERE path = ?1",
+                [new_file.to_string_lossy()],
+                |r| r.get(0),
+            )
+            .unwrap();
+        assert_eq!(count, 1);
+    }
+
+    #[test]
+    fn rename_directory_updates_children() {
+        let tmp = tempdir().unwrap();
+        let dir = tmp.path();
+        let sub = dir.join("old");
+        fs::create_dir(&sub).unwrap();
+        let f1 = sub.join("one.txt");
+        fs::write(&f1, b"1").unwrap();
+        let f2 = sub.join("two.txt");
+        fs::write(&f2, b"2").unwrap();
+
+        let db_path = dir.join("test2.db");
+        let mut marlin = Marlin::open_at(&db_path).unwrap();
+        marlin.scan(&[dir]).unwrap();
+
+        let mut watcher = marlin
+            .watch(
+                dir,
+                Some(WatcherConfig {
+                    debounce_ms: 50,
+                    ..Default::default()
+                }),
+            )
+            .unwrap();
+
+        thread::sleep(Duration::from_millis(100));
+        let new = dir.join("newdir");
+        fs::rename(&sub, &new).unwrap();
+        for fname in ["one.txt", "two.txt"] {
+            let p = new.join(fname);
+            wait_for_row_count(&marlin, &p, 1, Duration::from_secs(10));
+        }
+        watcher.stop().unwrap();
+        assert!(
+            watcher.status().unwrap().events_processed > 0,
+            "rename event should be processed"
+        );
+
+        for fname in ["one.txt", "two.txt"] {
+            let p = new.join(fname);
+            let cnt: i64 = marlin
+                .conn()
+                .query_row(
+                    "SELECT COUNT(*) FROM files WHERE path = ?1",
+                    [p.to_string_lossy()],
+                    |r| r.get(0),
+                )
+                .unwrap();
+            assert_eq!(cnt, 1, "{} missing", p.display());
+        }
+    }
 }