fix: hash only same-size files in dedup scan

Equal files have equal sizes, and the scan only uses the sha1. Files alone at their size are no longer read and the rest get one digest instead of five. Same 278 groups (645 paths), same dry-run output, 36.7 s to 1.9 s.

tests/test_dedup.py

@@ -309,5 +309,37 @@ class TheNoDedupListIsPinned(unittest.TestCase):
         self.assertEqual(expected - set(NODEDUP_DIRS), set())
 
 
+class OnlyFilesSharingASizeAreHashed(_Bios):
+    """Equal files have equal sizes. Hashing all 9 442 files with five
+    digests took 33 s for 278 groups that a sha1 of the 4 543 files sharing
+    a size finds the same."""
+
+    def test_a_file_alone_at_its_size_is_not_read(self):
+        from unittest import mock
+
+        self.write("A/one.bin")
+        self.write("B/one.bin")
+        self.write("C/other.bin", b"a payload of its own length")
+        self.write("D/same_size.bin", b"IDENTICAL PAYLOAX")
+        calls: list[tuple[str, frozenset | None]] = []
+        real = dedup.compute_hashes
+
+        def spy(path, algorithms=None, cache=True):
+            calls.append((os.path.relpath(path, self.bios), algorithms))
+            return real(path, algorithms, cache)
+
+        with mock.patch.object(dedup, "compute_hashes", spy):
+            groups = dedup.scan_duplicates(str(self.bios))
+        self.assertEqual(
+            sorted(path for path, _algos in calls),
+            sorted(os.path.join(*p.split("/")) for p in ("A/one.bin", "B/one.bin", "D/same_size.bin")),
+        )
+        self.assertTrue(all(algos == frozenset({"sha1"}) for _path, algos in calls))
+        multi = [paths for paths in groups.values() if len(paths) > 1]
+        self.assertEqual(len(multi), 1)
+        self.assertEqual(sorted(os.path.relpath(p, self.bios) for p in multi[0]),
+                         sorted(os.path.join(*p.split("/")) for p in ("A/one.bin", "B/one.bin")))
+
+
 if __name__ == "__main__":
     unittest.main()