fix(format): resolve each hard link once

A hard link's target may go through other hard links, and each was resolved again every time a path went through it. With each link's target naming the previous link twice (g/s{i} -> /g/s{i-1}/s{i-1}) the work doubled per link: finish() took 46 s for 26 links in a debug build, and 60 would never finish. Resolved links are now remembered, so the work is linear in the links, and a hard link met again while it is being resolved is reported as a cycle by name. The depth limit (64) still bounds the recursion through links not yet resolved. Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>
2026-09-26 09:01:13 -05:00
parent bd1d8f1a59
commit 400e3a9fec
2 changed files with 104 additions and 7 deletions
@@ -827,3 +827,52 @@ fn a_link_too_big_for_dense_storage_is_an_error() {
    assert_eq!(out, "[11, 65001]");
    h5dump_ok(&path);
 }
+
+#[test]
+fn chained_hard_links_resolve_in_linear_time() {
+    skip_if_no_python!();
+    // Each link's target goes through the previous link twice. Resolving
+    // them without remembering resolved links doubled the work per link:
+    // 26 links took 46 s in a debug build, so 60 would never finish.
+    fn chain(reverse: bool) -> FileBuilder {
+        let mut b = FileBuilder::new();
+        let mut g = b.create_group("g");
+        g.create_dataset("v").with_i32_data(&[5]);
+        b.add_group(g.finish());
+        let mut order: Vec<usize> = (0..60).collect();
+        if reverse {
+            order.reverse();
+        }
+        for i in order {
+            if i == 0 {
+                b.add_hard_link("g/s0", "/g");
+            } else {
+                b.add_hard_link(&format!("g/s{i}"), &format!("/g/s{}/s{}", i - 1, i - 1));
+            }
+        }
+        b
+    }
+    let (tx, rx) = std::sync::mpsc::channel();
+    std::thread::spawn(move || {
+        let bytes = [false, true].map(|r| chain(r).finish().unwrap());
+        tx.send(bytes).unwrap();
+    });
+    let [forward, reverse] = rx
+        .recv_timeout(std::time::Duration::from_secs(60))
+        .expect("resolving 60 chained hard links took over a minute");
+
+    let dir = tempfile::tempdir().unwrap();
+    for (name, bytes) in [("forward.h5", forward), ("reverse.h5", reverse)] {
+        let path = dir.path().join(name).display().to_string();
+        std::fs::write(&path, bytes).unwrap();
+        let out = h5py(
+            &path,
+            "with h5py.File(path, 'r') as f:\n\
+             \x20   print(json.dumps([h5py.h5o.get_info(f['g'].id).rc, len(f['g']),\n\
+             \x20       int(f['g/s59/s30/s0/v'][0]), f['g/s59'] == f['g']]))",
+        );
+        assert_eq!(out, "[61, 61, 5, true]", "{name}");
+        let f = File::open(&path).unwrap();
+        assert_eq!(f.dataset("g/s59/s0/v").unwrap().read_i32().unwrap(), [5]);
+    }
+}