feat(conformance): in-repo, reproducible conformance sweep

conformance/run.sh fetches eight public HDF5 corpora pinned by commit (conformance/corpus.txt) into a gitignored cache, reads every file with clawhdf5 (conformance/probe, a crate outside the workspace) and with h5py/libhdf5 (ref.py), and the CVE files with h5dump, each under a timeout and an address-space limit; compare.py classifies the files, report.py writes CONFORMANCE.md and check.py gates on panics/hangs/crashes/OOM and on regressions against conformance/baseline.json. ~25 s once cached. Changes from the ad-hoc audit harness: - the probe compares non-IEEE-layout floats (N-Bit) and integers with a bit offset or reduced precision as the values libhdf5 converts them to, not raw file bytes: 8 files that showed as mismatches now read identically; - ref.py exits without tearing down h5py objects: libhdf5 2.0 aborts while freeing them for two files about half the time, which flipped them between ok and h5py-cannot-read from run to run; - the file list is defined (list_files.py): netCDF classic files are left out, 11 HDF5 files the ad-hoc sweep missed are in. Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>
2026-09-25 22:06:00 -05:00
parent 42b81d9f1c
commit 9179aa356e
15 changed files with 2577 additions and 0 deletions
@@ -0,0 +1,88 @@
+#!/usr/bin/env python3
+"""check.py <results_dir> <baseline.json> [--update]
+
+The conformance gate. Fails (exit 1) when
+  * clawhdf5 panicked, hung, crashed or ran out of memory on any file, or
+  * the ok count fell below the baseline's, or
+  * a file the baseline lists as ok is no longer ok (even if another file
+    became ok and the total held).
+New ok files are reported so the baseline can be raised (--update rewrites it
+from the results).
+"""
+import json
+import os
+import sys
+
+FATAL = ("panic", "hang", "crash", "oom")
+
+
+def main():
+    args = [a for a in sys.argv[1:] if not a.startswith("--")]
+    update = "--update" in sys.argv
+    res_dir, base_path = args
+    res = json.load(open(os.path.join(res_dir, "results.json")))
+    rows = res["rows"]
+    counts = {}
+    per_corpus = {}
+    for r in rows:
+        counts[r["class"]] = counts.get(r["class"], 0) + 1
+        pc = per_corpus.setdefault(r["corpus"], {})
+        pc[r["class"]] = pc.get(r["class"], 0) + 1
+    ok_files = sorted(r["file"] for r in rows if r["class"] == "ok")
+
+    if update:
+        meta = {}
+        mp = os.path.join(res_dir, "report-meta.json")
+        if os.path.exists(mp):
+            meta = json.load(open(mp))
+        base = {
+            "comment": "conformance/run.sh fails if the ok count drops below `ok` or a file in `ok_files` stops being ok. "
+                       "Regenerate with `conformance/run.sh --update-baseline` after an intended change.",
+            "commit": meta.get("commit", ""),
+            "date": meta.get("date", ""),
+            "reference": meta.get("reference", ""),
+            "files": len(rows),
+            "ok": len(ok_files),
+            "counts": dict(sorted(counts.items())),
+            "per_corpus": {k: dict(sorted(v.items())) for k, v in sorted(per_corpus.items())},
+            "ok_files": ok_files,
+        }
+        with open(base_path, "w") as fh:
+            json.dump(base, fh, indent=1)
+            fh.write("\n")
+        print(f"baseline updated: {len(ok_files)} ok of {len(rows)} files -> {base_path}")
+        return 0
+
+    base = json.load(open(base_path))
+    failures = []
+    fatal = [r for r in rows if r["class"] in FATAL]
+    for r in fatal:
+        failures.append(f"{r['class']}: {r['file']}: {r['ours_detail'][:200]}")
+    if len(ok_files) < base["ok"]:
+        failures.append(f"ok count dropped: {len(ok_files)} < baseline {base['ok']}")
+    now_ok = set(ok_files)
+    by_file = {r["file"]: r for r in rows}
+    for f in base["ok_files"]:
+        if f not in now_ok:
+            r = by_file.get(f)
+            why = f"now {r['class']}: {(r['ours_detail'] or r['first_issue'])[:200]}" if r else "no longer in the corpus"
+            failures.append(f"regressed: {f}: {why}")
+    gained = sorted(now_ok - set(base["ok_files"]))
+
+    print(f"conformance: {len(ok_files)} ok of {len(rows)} files (baseline {base['ok']} of {base['files']}); "
+          + ", ".join(f"{k} {v}" for k, v in sorted(counts.items())))
+    if gained:
+        print(f"{len(gained)} file(s) newly ok — raise the baseline with `conformance/run.sh --update-baseline`:")
+        for f in gained:
+            print(f"  + {f}")
+    if failures:
+        print(f"CONFORMANCE GATE FAILED ({len(failures)}):")
+        for f in failures:
+            print(f"  - {f}")
+        return 1
+    print("conformance gate passed")
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())