Add official multihash spec vector tests

.github/workflows/tox.yml

@@ -23,6 +23,8 @@ jobs:
       fail-fast: false
     steps:
       - uses: actions/checkout@v4
+        with:
+          submodules: recursive
       - uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
@@ -50,6 +52,8 @@ jobs:
       fail-fast: false
     steps:
       - uses: actions/checkout@v4
+        with:
+          submodules: recursive
       - name: Set up Python ${{ matrix.python-version }}
         uses: actions/setup-python@v5
         with:

.gitmodules

@@ -0,0 +1,3 @@
+[submodule "spec/multihash"]
+	path = spec/multihash
+	url = https://github.com/multiformats/multihash.git

MANIFEST.in

@@ -9,3 +9,4 @@ recursive-exclude * __pycache__
 recursive-exclude * *.py[co]
 
 recursive-include docs *.rst conf.py Makefile make.bat *.jpg *.png *.gif
+graft spec

newsfragments/53.misc.rst

@@ -0,0 +1 @@
+Add official multihash spec vector tests validating :func:`~multihash.sum` against ``spec/multihash`` test cases.

tests/test_spec_vectors.py

@@ -0,0 +1,49 @@
+"""Official multihash spec vector tests."""
+
+import csv
+from binascii import hexlify
+from pathlib import Path
+
+import pytest
+
+from multihash import FuncReg, HashComputationError, sum
+
+SPEC_VECTORS = Path(__file__).resolve().parents[1] / "spec" / "multihash" / "tests" / "values" / "test_cases.csv"
+
+# Spec CSV uses "sha3" as an alias for sha3-512 (same as go-multihash).
+_ALGORITHM_ALIASES = {
+    "sha3": "sha3-512",
+}
+
+
+def _load_cases():
+    if not SPEC_VECTORS.is_file():
+        pytest.skip(f"spec vectors not found at {SPEC_VECTORS} (init git submodules?)")
+    with SPEC_VECTORS.open(newline="") as f:
+        reader = csv.reader(f)
+        next(reader)  # header
+        return list(reader)
+
+
+@pytest.mark.parametrize("algorithm,bits_str,input_hex,expected_hex", _load_cases())
+def test_spec_vectors(algorithm, bits_str, input_hex, expected_hex):
+    """Validate sum() against official multihash test vectors.
+
+    The CSV ``input`` column is hashed as UTF-8/ASCII of the hex string itself
+    (not as decoded binary), matching go-multihash ``TestSpecVectors``.
+    """
+    algorithm = _ALGORITHM_ALIASES.get(algorithm, algorithm)
+    length_bytes = int(bits_str) // 8
+    data = input_hex.encode()
+
+    try:
+        FuncReg.get(algorithm)
+    except KeyError:
+        pytest.skip(f"hash {algorithm} not registered")
+
+    try:
+        actual = sum(data, algorithm, length=length_bytes)
+    except (HashComputationError, KeyError, ValueError) as exc:
+        pytest.skip(f"hash {algorithm} unavailable: {exc}")
+
+    assert hexlify(actual.encode()).decode() == expected_hex