bench backfill: close 36 orphan-project dirs + fix rubocop MOAD misclass

Previously 52 registered defects had no project dir locally because their
patches live under a sibling project (e.g. ans-* under defects/ansible/,
geth-0001 under defects/go-ethereum/, cfe-* under defects/cfengine/).

Created defects/{stem}/bench/ for each orphan stem (ans, argo, cel, cfe,
element, geth, go-stdlib, hv, igraph, nats, nx, openscad, otel, pre, r,
rmq, simplex, sm, solargraph, tf, tf-aws) and wrote the standard list-vs-set
benches against each defect. Patches stay where they are; bench_status
looks up by defect-id prefix, not patch location.

Also added defects/rubocop/ with benches for rubocop-0001 and rubocop-0002
(Array -> Set with compare_by_identity). Both were misclassified as
MOAD-0011 ReDoS in generate_undf.py; the tickets show they're CWE-407
Sedimentary (O(N*S) -> O(N+S) via identity Set).

Coverage: 1243 -> 1281 (96.0% -> 98.9%). The 14 remaining are truly
missing — no patch anywhere in the tree: dragonflybsd-0001..0005,
jami-daemon, jitsi-videobridge, netbsd-0001..0004, regamedll-cs-0001,
supertuxkart-0002, hadoop-rpc-0001.
This commit is contained in:
russell@unturf.com 2026-04-23 12:37:51 -04:00
parent b5b9cce0a1
commit 99be1fbed9
125 changed files with 3950 additions and 0 deletions

6
defects/rubocop/Makefile Normal file
View file

@ -0,0 +1,6 @@
.PHONY: all bench clean
all: bench
bench:
python3 bench/run_all.py
clean:
rm -rf bench/__pycache__ __pycache__

View file

@ -0,0 +1,76 @@
#!/usr/bin/env python3
# bench-rubocop-0001.py
# IgnoredNode @ignored_nodes Array: `ignored_node?(node)` runs
# `ignored_nodes.any? { |n| n.equal?(node) }` — O(S) per call.
# `part_of_ignored_node?` maps over the full array each call — O(S).
# For R regexp_literal + S string_literal nodes per file, the StringHelp
# path costs O(R × S). Fix: `Set.new.compare_by_identity` — O(1) via
# object hash/identity.
import sys
import time
class _Node:
"""Ruby node object — identity used for membership (RuboCop Parser::AST::Node)."""
__slots__ = ("id",)
def __init__(self, i):
self.id = i
def bench_defective(r, s):
"""Array membership via identity scan — O(R*S)."""
ignored = [_Node(i) for i in range(r)] # R regexp nodes ignored
strs = [ignored[i % r] if i % 3 == 0 else _Node(1000 + i) for i in range(s)]
t0 = time.perf_counter()
hits = 0
for node in strs:
# Array#any? { |n| n.equal?(node) } — O(R) per call
found = False
for ig in ignored:
if ig is node:
found = True
break
if found:
hits += 1
return time.perf_counter() - t0
def bench_fixed(r, s):
"""Set.compare_by_identity — O(1) membership via object id."""
ignored_set = set()
ignored_list = []
for i in range(r):
n = _Node(i)
ignored_set.add(id(n)) # identity hash
ignored_list.append(n)
strs = [ignored_list[i % r] if i % 3 == 0 else _Node(1000 + i) for i in range(s)]
t0 = time.perf_counter()
hits = 0
for node in strs:
if id(node) in ignored_set: # O(1)
hits += 1
return time.perf_counter() - t0
TRIALS = 3
CASES = [(50, 500), (100, 1000), (200, 2000), (500, 5000)]
def run():
lines = []
header = "=== rubocop-0001: IgnoredNode Array#any?(equal?) vs Set.compare_by_identity ==="
print(header); lines.append(header)
for r, s in CASES:
df = min(bench_defective(r, s) for _ in range(TRIALS))
fx = min(bench_fixed(r, s) for _ in range(TRIALS))
speedup = (df / fx) if fx > 0 else float("inf")
line = f"R={r:<4} S={s:<5}: defective={df*1000:.3f}ms fixed={fx*1000:.3f}ms speedup={speedup:.1f}x"
print(line); lines.append(line); sys.stdout.flush()
return lines
if __name__ == "__main__":
run()

View file

@ -0,0 +1,54 @@
#!/usr/bin/env python3
# bench-rubocop-0002.py
# Style::RedundantSelf @allowed_send_nodes Array: `allowed_send_node?`
# calls `.include?(node)` — O(S) per send_node check. With N send_node
# checks and S allowed entries accumulated during one file, total cost is
# O(N*S). Fix: swap Array for Set for O(1) include?.
import sys
import time
def bench_defective(n_checks, s_allowed):
allowed = list(range(s_allowed)) # Ruby Array @allowed_send_nodes
queries = [i % (s_allowed + 100) for i in range(n_checks)]
t0 = time.perf_counter()
hits = 0
for q in queries:
if q in allowed: # list __contains__ = O(S)
hits += 1
return time.perf_counter() - t0
def bench_fixed(n_checks, s_allowed):
allowed = set(range(s_allowed)) # Ruby Set @allowed_send_nodes
queries = [i % (s_allowed + 100) for i in range(n_checks)]
t0 = time.perf_counter()
hits = 0
for q in queries:
if q in allowed: # O(1)
hits += 1
return time.perf_counter() - t0
TRIALS = 3
CASES = [(500, 50), (1000, 100), (2000, 200), (5000, 500)]
def run():
lines = []
header = "=== rubocop-0002: RedundantSelf Array#include? vs Set#include? ==="
print(header); lines.append(header)
for n, s in CASES:
df = min(bench_defective(n, s) for _ in range(TRIALS))
fx = min(bench_fixed(n, s) for _ in range(TRIALS))
speedup = (df / fx) if fx > 0 else float("inf")
line = f"N={n:<5} S={s:<4}: defective={df*1000:.3f}ms fixed={fx*1000:.3f}ms speedup={speedup:.1f}x"
print(line); lines.append(line); sys.stdout.flush()
return lines
if __name__ == "__main__":
run()

View file

@ -0,0 +1,12 @@
=== rubocop-0001: IgnoredNode Array#any?(equal?) vs Set.compare_by_identity ===
R=50 S=500 : defective=0.534ms fixed=0.075ms speedup=7.1x
R=100 S=1000 : defective=2.005ms fixed=0.150ms speedup=13.4x
R=200 S=2000 : defective=7.898ms fixed=0.288ms speedup=27.4x
R=500 S=5000 : defective=47.680ms fixed=0.731ms speedup=65.2x
=== rubocop-0002: RedundantSelf Array#include? vs Set#include? ===
N=500 S=50 : defective=0.380ms fixed=0.023ms speedup=16.8x
N=1000 S=100 : defective=1.422ms fixed=0.048ms speedup=29.7x
N=2000 S=200 : defective=5.185ms fixed=0.132ms speedup=39.3x
N=5000 S=500 : defective=33.127ms fixed=0.423ms speedup=78.4x

View file

@ -0,0 +1,22 @@
#!/usr/bin/env python3
import importlib.util, os, sys
BENCH_DIR = os.path.dirname(os.path.abspath(__file__))
def load_module(filename):
path = os.path.join(BENCH_DIR, filename)
spec = importlib.util.spec_from_file_location("mod", path)
mod = importlib.util.module_from_spec(spec)
spec.loader.exec_module(mod)
return mod
all_lines = []
for fname in ["bench-rubocop-0001.py", "bench-rubocop-0002.py"]:
mod = load_module(fname)
lines = mod.run()
all_lines.extend(lines); all_lines.append("")
print(); sys.stdout.flush()
out_path = os.path.join(BENCH_DIR, "results.txt")
with open(out_path, "w") as f:
f.write("\n".join(all_lines) + "\n")
print(f"results written to {out_path}"); sys.stdout.flush()