CHANGELOG.md

@@ -128,15 +128,17 @@
   - `h5rs stat FILE` reports h5stat's object, link, rank, layout, filter,
     attribute, raw-data and file-size figures (equal to h5stat's on the test
     files); metadata space is one figure, not broken down.
-  - `h5rs diff [-r] [-q] [-d D] [-p R] A B [OBJ1 [OBJ2]]` compares objects,
-    kinds, datatypes, shapes, attributes, values and link targets; exit
-    status 0/1/2 as h5diff's. Every path is compared, including every name
-    of a hard-linked object and the members of a hard-linked group; with a
-    `-d`/`-p` tolerance, integers are compared exactly in integer
-    arithmetic (no loss above 2^53), and a `-p` below the f64 epsilon
-    compares exactly, as h5diff's. Objects
-    that cannot be compared count as a difference (h5diff exits 0 for them),
-    and NaN equals NaN.
+  - `h5rs diff [-r] [-q] [-d D] [-p R] [--follow-symlinks] A B [OBJ1 [OBJ2]]`
+    compares objects, kinds, datatypes, shapes, attributes, values and link
+    targets; exit status 0/1/2 as h5diff's. Soft links are compared by
+    target path, as h5diff's default, or with `--follow-symlinks` by the
+    objects they lead to (external links are never followed). Every path is
+    compared, including every name of a hard-linked object and the members
+    of a hard-linked group; with a `-d`/`-p` tolerance, integers are
+    compared exactly in integer arithmetic (no loss above 2^53), and a `-p`
+    below the f64 epsilon compares exactly, as h5diff's. Objects that cannot
+    be compared count as a difference (h5diff exits 0 for them), and NaN
+    equals NaN.
   - `h5rs check [--data] FILE` is a structural validator: it walks every
     object, parses every header message, verifies the checksums of every
     version 2+ structure it meets (superblock, object headers and

crates/clawhdf5-tools/README.md

@@ -140,6 +140,7 @@ $ h5rs diff a.h5 b.h5 /x /y          # different paths in each
 $ h5rs diff -r a.h5 b.h5 /d          # list every differing element
 $ h5rs diff -d 0.001 a.h5 b.h5       # |a - b| > 0.001 is a difference
 $ h5rs diff -p 0.01 a.h5 b.h5        # |a - b| / |a| > 1% is a difference
+$ h5rs diff --follow-symlinks a.h5 b.h5 /lnk   # what the soft link /lnk leads to
 ```
 
 Integers are compared in integer arithmetic, with or without a tolerance, so
@@ -150,7 +151,14 @@ exactly, as h5diff's does.
 Exit status: 0 no differences, 1 differences, 2 error — the same as h5diff's
 on the cases `diff_exit_codes_match_h5diff` runs. Compared: which objects
 exist, their kinds, datatypes and shapes, attribute sets and values, dataset
-values, and soft/external link targets. Every path is compared: an object
+values, and soft/external link targets. A soft link — including an OBJ
+that is itself a soft link — is compared as a link, by its target path, as
+h5diff does; `--follow-symlinks` compares the objects soft links lead to
+instead (and walks into soft-linked groups), and two dangling links are then
+the same, as in h5diff. External links are always compared by target (file
+and path): `--follow-symlinks` does not open other files, where h5diff's
+does. Two dangling soft links with different targets are a difference
+(h5diff reports them with `-r`/`-v` but exits 0 without). Every path is compared: an object
 hard-linked under two names is compared under both, with everything below
 it, so a file that shares one object between two names equals a file that
 stores two identical copies. Differences from h5diff, on purpose: objects

crates/clawhdf5-tools/src/diff.rs

@@ -18,10 +18,14 @@ usage: h5rs diff [options] FILE1 FILE2 [OBJ1 [OBJ2]]
 
 Compare FILE1 and FILE2 (or OBJ1 in FILE1 with OBJ2 in FILE2, and everything
 below them): the objects present, their kinds, datatypes, shapes, attribute
-sets and values, and soft/external link targets.
+sets and values, and soft/external link targets (an OBJ that is itself a
+soft link is compared as a link, as h5diff does, unless --follow-symlinks).
 
   -r, --report       list every differing element (position, values, difference)
   -q, --quiet        print nothing; only the exit status
+  --follow-symlinks  compare the objects soft links lead to (and walk into
+                     soft-linked groups) instead of the links' target paths;
+                     two dangling links are the same
   -d, --delta D      numbers differ only when |a - b| > D
   -p, --relative R   numbers differ only when |a - b| / |a| > R (an R below
                      the f64 epsilon, 2.2e-16, compares exactly, as h5diff)
@@ -46,6 +50,8 @@ struct Opts {
     quiet: bool,
     tol: Tol,
     count: usize,
+    /// Compare the objects soft links lead to, not the links' targets.
+    follow: bool,
 }
 
 /// What a relative path names in one file.
@@ -108,6 +114,7 @@ pub fn run(args: &mut Args, out: &mut Out) -> std::io::Result<i32> {
         quiet: false,
         tol: Tol::Exact,
         count: usize::MAX,
+        follow: false,
     };
     let mut max_bytes = None;
     let mut pos = Vec::new();
@@ -115,6 +122,7 @@ pub fn run(args: &mut Args, out: &mut Out) -> std::io::Result<i32> {
         match a.as_str() {
             "-r" | "--report" => opts.report = true,
             "-q" | "--quiet" => opts.quiet = true,
+            "--follow-symlinks" => opts.follow = true,
             "-d" | "--delta" => match args.number::<f64>() {
                 Some(d) if d >= 0.0 => opts.tol = Tol::Delta(d),
                 _ => return args.usage_error(out, "--delta needs a number >= 0", USAGE),
@@ -171,8 +179,8 @@ pub fn run(args: &mut Args, out: &mut Out) -> std::io::Result<i32> {
     let obj2 = pos.get(3).cloned().unwrap_or_else(|| obj1.clone());
     let mut sides = Vec::new();
     for (h5, (obj, f)) in files.iter().zip([(&obj1, &pos[0]), (&obj2, &pos[1])]) {
-        let addr = match h5.resolve(obj) {
-            Ok(a) => a,
+        let start = match start(h5, obj, opts.follow) {
+            Ok(x) => x,
             Err(_) => {
                 writeln!(
                     out.e,
@@ -187,7 +195,11 @@ pub fn run(args: &mut Args, out: &mut Out) -> std::io::Result<i32> {
         } else {
             format!("/{base}")
         };
-        let entries = match collect(h5, addr) {
+        let collected = match start {
+            Start::Obj(addr) => collect(h5, addr, &base, opts.follow),
+            Start::Link(e) => Ok(BTreeMap::from([(String::new(), e)])),
+        };
+        let entries = match collected {
             Ok(e) => e,
             Err(e) => {
                 writeln!(out.e, "h5rs diff: {f}: {e}")?;
@@ -246,6 +258,51 @@ pub fn run(args: &mut Args, out: &mut Out) -> std::io::Result<i32> {
     })
 }
 
+/// What OBJ1/OBJ2 names.
+enum Start {
+    Obj(u64),
+    /// A soft (not followed, or dangling), external or user-defined link.
+    Link(Entry),
+}
+
+/// Resolve OBJ1/OBJ2. Soft links on the way to it are followed, as in any
+/// HDF5 path; a soft link that *is* the named object is compared as a link
+/// (its target path), as h5diff does, unless `follow`.
+fn start(h5: &H5, obj: &str, follow: bool) -> crate::h5::Result<Start> {
+    let p = obj.trim_matches('/');
+    if !p.is_empty() {
+        let (parent, name) = p.rsplit_once('/').unwrap_or(("", p));
+        let link = h5
+            .resolve(parent)
+            .and_then(|a| h5.header(a))
+            .and_then(|h| h5.links(&h))
+            .ok()
+            .and_then(|ls| ls.into_iter().find(|l| l.name == name));
+        if let Some(l) = link {
+            return Ok(match l.kind {
+                LinkKind::Hard(a) => Start::Obj(a),
+                LinkKind::Soft(t) if follow => match soft_target(h5, &format!("/{parent}"), &t) {
+                    Ok(a) => Start::Obj(a),
+                    Err(_) => Start::Link(Entry::Soft(t)),
+                },
+                LinkKind::Soft(t) => Start::Link(Entry::Soft(t)),
+                LinkKind::External { file, path } => Start::Link(Entry::External(file, path)),
+                LinkKind::UserDefined(t) => Start::Link(Entry::UserDefined(t)),
+            });
+        }
+    }
+    h5.resolve(obj).map(Start::Obj)
+}
+
+/// The object a soft link in group `parent` (an absolute path) leads to.
+fn soft_target(h5: &H5, parent: &str, target: &str) -> crate::h5::Result<u64> {
+    if target.starts_with('/') {
+        h5.resolve(target)
+    } else {
+        h5.resolve(&format!("{}/{target}", parent.trim_end_matches('/')))
+    }
+}
+
 /// One object as the path walk sees it: what its paths compare as, and
 /// (for a group) its links.
 struct Node {
@@ -258,8 +315,15 @@ struct Node {
 /// names is compared under both, with everything below it: two files that
 /// hold the same values are equal whether one shares an object between
 /// names and the other stores copies. A hard link back to an ancestor (a
-/// cycle) is recorded, not descended into.
-fn collect(h5: &H5, start: u64) -> crate::h5::Result<BTreeMap<String, Entry>> {
+/// cycle) is recorded, not descended into. With `follow`, a soft link is
+/// walked like a hard link to its target (a dangling one stays a link);
+/// `base` is the absolute path of `start`, for relative link targets.
+fn collect(
+    h5: &H5,
+    start: u64,
+    base: &str,
+    follow: bool,
+) -> crate::h5::Result<BTreeMap<String, Entry>> {
     let mut cache: HashMap<u64, Rc<Node>> = HashMap::new();
     let mut node = |addr: u64| -> Rc<Node> {
         cache
@@ -313,6 +377,12 @@ fn collect(h5: &H5, start: u64) -> crate::h5::Result<BTreeMap<String, Entry>> {
             let child = format!("{path}/{}", l.name);
             match &l.kind {
                 LinkKind::Hard(a) => stack.push((*a, child, chain.clone())),
+                LinkKind::Soft(t) if follow => match soft_target(h5, &format!("{base}{path}"), t) {
+                    Ok(a) => stack.push((a, child, chain.clone())),
+                    Err(_) => {
+                        entries.insert(child, Entry::Soft(t.clone()));
+                    }
+                },
                 LinkKind::Soft(t) => {
                     entries.insert(child, Entry::Soft(t.clone()));
                 }
@@ -365,7 +435,9 @@ impl Diff {
             (Entry::Broken(e), _) => self.error(out, &format!("<{pa}> in <{}>: {e}", a.label)),
             (_, Entry::Broken(e)) => self.error(out, &format!("<{pb}> in <{}>: {e}", b.label)),
             (Entry::Soft(x), Entry::Soft(y)) => {
-                if x != y {
+                // Followed links that are left are dangling on both sides,
+                // which h5diff counts as the same.
+                if x != y && !self.opts.follow {
                     self.diffs += 1;
                     self.say(out, &format!("soft link: <{pa}> -> {x} and <{pb}> -> {y}"))?;
                 }

crates/clawhdf5-tools/tests/gen_files.py

@@ -132,6 +132,23 @@ for name, d in (("big1.h5", 0), ("big2.h5", 1)):
         f["i"] = np.array([2**60 + d, -(2**62) - d], dtype="i8")
         f["u"] = np.array([2**64 - 1 - d], dtype="u8")
 
+# Soft links: the same link targets, whose target objects differ.
+for name, v in (("soft1.h5", 0), ("soft2.h5", 1)):
+    with h5py.File(os.path.join(out, name), "w") as f:
+        f["z"] = np.arange(4) + v
+        f.create_group("g")["s"] = h5py.SoftLink("/z")
+        grp = f.create_group("grp")
+        grp["d"] = np.arange(3) + v
+        f["lnk"] = h5py.SoftLink("/grp")
+        f["dang"] = h5py.SoftLink("/nowhere")
+# Soft links: different link targets, whose target objects are equal.
+for name, t in (("target1.h5", "/a"), ("target2.h5", "/b")):
+    with h5py.File(os.path.join(out, name), "w") as f:
+        f["a"] = np.arange(4)
+        f["b"] = np.arange(4)
+        f["s"] = h5py.SoftLink(t)
+        f["rel"] = h5py.SoftLink("a")
+
 with h5py.File(os.path.join(out, "userblock.h5"), "w", userblock_size=1024) as f:
     f["d"] = np.arange(10)
 

crates/clawhdf5-tools/tests/h5rs_interop.rs

@@ -412,6 +412,45 @@ fn diff_tolerances_compare_large_integers_exactly() {
     );
 }
 
+/// A soft link is compared as a link (its target path), as h5diff does,
+/// unless `--follow-symlinks`, which compares (and walks into) what it
+/// leads to; two dangling links are then the same.
+#[test]
+fn diff_soft_links_like_h5diff() {
+    let Some(f) = generate() else { return };
+    let (s1, s2, t1, t2) = (
+        f.p("soft1.h5"),
+        f.p("soft2.h5"),
+        f.p("target1.h5"),
+        f.p("target2.h5"),
+    );
+    let fl = "--follow-symlinks";
+    let cases: Vec<(Vec<&str>, i32)> = vec![
+        (vec![&s1, &s2, "/g/s"], 0),
+        (vec![&s1, &s2, "/g"], 0),
+        (vec![&s1, &s2, "/lnk"], 0),
+        (vec![&s1, &s2, "/dang"], 0),
+        (vec![&s1, &s2, "/lnk/d"], 1),
+        (vec![&t1, &t2, "/s"], 1),
+        (vec![&t1, &t2, "/s", "/rel"], 1),
+        (vec![fl, &s1, &s2, "/g/s"], 1),
+        (vec![fl, &s1, &s2, "/g"], 1),
+        (vec![fl, &s1, &s2, "/lnk"], 1),
+        (vec![fl, &s1, &s2, "/dang"], 0),
+        (vec![fl, &s1, &s1], 0),
+        (vec![fl, &t1, &t2, "/s"], 0),
+        (vec![fl, &t1, &t2, "/s", "/rel"], 0),
+    ];
+    let have_h5diff = tool_available("h5diff");
+    for (args, want) in cases {
+        if have_h5diff {
+            assert_eq!(code(&run("h5diff", &args)), want, "h5diff {args:?}");
+        }
+        let o = h5rs(&[&["diff"], args.as_slice()].concat());
+        assert_eq!(code(&o), want, "h5rs diff {args:?}: {}", stdout(&o));
+    }
+}
+
 /// An object hard-linked under two names is compared under both, with
 /// everything below it, so a file that shares one object between two names
 /// equals a file that stores two identical copies.