conformance/report.py

@@ -98,13 +98,40 @@ def is_h5py_be_vlen(i):
             and ">" in (i.get("ours_dtype") or ""))
 
 
+# Objects the reference (h5py 3.16 / HDF5 2.0) reads only because of an
+# HDF5 2.0 bug, and that clawhdf5 refuses: each one reads past a buffer or
+# returns bytes the file does not hold, and libhdf5's develop branch refuses the
+# first three. (file, object) -> why. Checked 2026-09-26 against HDF5 2.0.0
+# and HDFGroup/hdf5 develop sources; see docs/known-issues.md.
+LIBHDF5_BUGS = {
+    ("cve_hdf5/cvefiles/cve-2025-2308.h5", "/Scale_offset_long_long_data_le"):
+        "scale-offset codes run past the end of the chunk: HDF5 2.0 reads past its buffer; "
+        "libhdf5's develop branch refuses the chunk (\"Buffer too short\")",
+    ("cve_hdf5/cvefiles/cve-2025-44904.h5", "/Scale_offset_float_data_le"):
+        "unfiltered chunks of 38 and 37 bytes for 48-byte chunks: HDF5 2.0 fills the rest with "
+        "whatever its buffer held; libhdf5's develop branch refuses them (\"incorrect chunk size returned "
+        "from index for unfiltered chunk\")",
+    ("hdf5/test/testfiles/bad_nbit_parms_walk.h5", "/Nbit_int_data_le"):
+        "an N-Bit parameter list one value short: HDF5 2.0 reads past the list; libhdf5's own "
+        "test (`test_filter_bad_params`, test/dsets.c) now requires the read to fail",
+    ("cve_hdf5/cvefiles/cve-2025-44905.h5", "/Shuffle_float_data_le"):
+        "a chunk B-tree key with element offset 4096: libhdf5's lookup misses the chunk and "
+        "returns fill values for data the file holds; clawhdf5 refuses the key",
+}
+
+
+def is_libhdf5_bug(rel, i):
+    return i["kind"] == "our-error" and any(
+        f == rel and i["detail"].startswith(obj + ":") for (f, obj) in LIBHDF5_BUGS)
+
+
 known = collections.defaultdict(list)
 for r in rows:
-    if r["class"] != "mismatch":
-        continue
     iss = issues.get(r["file"], [])
-    if iss and all(is_h5py_be_vlen(i) for i in iss):
+    if r["class"] == "mismatch" and iss and all(is_h5py_be_vlen(i) for i in iss):
         known["h5py-be-vlen"].append(r["file"])
+    if r["class"] == "our-error" and iss and all(is_libhdf5_bug(r["file"], i) for i in iss):
+        known["libhdf5-2.0"].append(r["file"])
 
 
 # --- the CVE corpus: clawhdf5 vs h5dump vs h5py ------------------------------
@@ -230,9 +257,13 @@ for c in sorted(by_corpus):
     w(f"| {c} | {sum(cnt.values())} | " + " | ".join(str(cnt.get(k, 0)) for k in CLASSES) + " |")
 w(f"| **all** | **{len(rows)}** | " + " | ".join(f"**{total.get(k, 0)}**" for k in CLASSES) + " |")
 w("")
-n_known = sum(len(v) for v in known.values())
-if n_known:
-    w(f"{n_known} of the {total.get('mismatch', 0)} mismatches are a known h5py bug, not ours (see *Known not-our-bug*).")
+if known["h5py-be-vlen"]:
+    w(f"{len(known['h5py-be-vlen'])} of the {total.get('mismatch', 0)} mismatches are a known h5py bug, "
+      "not ours (see *Known not-our-bug*).")
+    w("")
+if known["libhdf5-2.0"]:
+    w(f"{len(known['libhdf5-2.0'])} of the {total.get('our-error', 0)} our-errors are corrupt data that "
+      "HDF5 2.0 reads only through a bug and clawhdf5 refuses (see *Known not-our-bug*).")
     w("")
 w("Corpora (fetched by `conformance/fetch-corpus.sh` into the gitignored `conformance/.cache/`):")
 w("")
@@ -311,6 +342,11 @@ if res["incomparable"]:
     w("  (FP8 -> float16, bfloat16 -> float32, x87 long double -> float128) the values are not")
     w("  compared (shape and presence still are): "
       + ", ".join(f"{k} ({n}x)" for k, n in res["incomparable"]) + ".")
+w("- **Corrupt data HDF5 2.0 reads through a bug.** clawhdf5 refuses these objects; h5py 3.16 /")
+w("  HDF5 2.0 returns values for them that the file does not hold:")
+for (f, obj), why in sorted(LIBHDF5_BUGS.items()):
+    here = "" if f in known["libhdf5-2.0"] else " (not an our-error in this run)"
+    w(f"  - `{f}` `{obj}`: {why}{here}.")
 w("- **References** are compared by presence only (`R`), not by target.")
 w("")
 if res.get("ref_only_errors"):