marius/Open_Ultra_SAST
1
0
Fork 0
mirror of https://github.com/norandom/OpenUltraSAST.git synced 2026-10-18 12:39:28 +00:00
Code Issues Packages Projects Releases Wiki Activity

chore: format the whole tree and lint the scratch measurement scripts; CI has been red since 25ae4b4

Browse Source 
CI runs ruff format --check and ruff check over the whole repository; 29 files had drifted from the formatter and
four measurement scripts carried lint findings, so every push since 25ae4b4 failed before pytest ran.

Co-Authored-By: Claude Fable 5.1 <[email protected]>
This commit is contained in:
Marius Ciepluch
2026-10-14 02:49:44 +02:00
co-authored by Claude Fable 5.1
parent fbbc03f3ea
commit 0d7d3f0dc9
29 changed files with 281 additions and 133 deletions
Download Patch File Download Diff File Expand all files Collapse all files
benchmarks/measurements/2026-10-13-source-module-label-diff/compare_labels.py
+30 -8
View File
@@ -1,23 +1,45 @@
"""Compare the baseline labels (old modules) with the labels built on source.py, sentinel-normalised."""
import glob, json, collections, sys
import collections
import glob
import json
import sys
def load(pattern):
files = glob.glob(pattern)
if not files:
sys.exit(f"no labels file for {pattern}")
rows = [json.loads(l) for l in open(files[0]) if l.strip()]
with open(files[0]) as stream:
rows = [json.loads(line) for line in stream if line.strip()]
return files[0], rows
bfile, before = load("/home/mc/ousast-results/fossil/p1-baseline/out/labels-*.jsonl")
afile, after = load("/home/mc/ousast-results/fossil/p1-after/out/labels-*.jsonl")
def key(r):
s = json.dumps(r, sort_keys=True).replace("<global>", "<module>")
return s
B = collections.Counter(key(r) for r in before); A = collections.Counter(key(r) for r in after)
only_b = B - A; only_a = A - B
print("baseline:", bfile, len(before), "rows"); print("after: ", afile, len(after), "rows")
B = collections.Counter(key(r) for r in before)
A = collections.Counter(key(r) for r in after)
only_b = B - A
only_a = A - B
print("baseline:", bfile, len(before), "rows")
print("after: ", afile, len(after), "rows")
print("identical after sentinel normalisation:", len(only_b) == 0 and len(only_a) == 0)
print("rows only in baseline:", sum(only_b.values()), " rows only in after:", sum(only_a.values()))
def summarize(c, title):
print(f"--- {title} (first 8)")
for s, n in list(c.items())[:8]:
r = json.loads(s); print(" ", {k: r.get(k) for k in ("candidate", "family", "label", "source", "unit", "pin_role") if k in r})
summarize(only_b, "only baseline"); summarize(only_a, "only after")
for s in list(c)[:8]:
r = json.loads(s)
print(" ", {k: r.get(k) for k in ("candidate", "family", "label", "source", "unit", "pin_role") if k in r})
summarize(only_b, "only baseline")
summarize(only_a, "only after")