feat: frequency threshold sweep — 0.01-0.20 across 4 codebases

Sweet spot: 0.01-0.05. At 0.01 RAGSAK gets 61 SOREs (26.1% cov) with
real conventions like warn.status.body.ErrorResponse. At 0.05 coverage
jumps to 45.4% but that pattern disappears. Flask dies at 0.15+.

Current default min_coverage=0.2 is too aggressive for most codebases.
This commit is contained in:
tobjend 2026-07-12 01:26:45 +02:00
parent 1b98b1d24e
commit 8028570ceb
6 changed files with 1386 additions and 0 deletions

View file

@ -210,6 +210,37 @@ structural tokens (response/client patterns) are highly repetitive.
--- ---
## Round 8: Frequency Threshold Sweep
**Hypothesis:** The fixed `min_coverage=0.2` is too aggressive. Lower thresholds
reveal more patterns while still filtering noise.
**Method:** Test thresholds 0.000.20 on all 4 codebases. Measure symbol count,
surviving sequences, SORE success, coverage.
**Results:**
| Codebase | Thresh | Syms | Seqs | SOREs | Coverage |
|----------|--------|------|------|-------|----------|
| RAGSAK | 0.01 | 130 | 1270 | 61 | 26.1% |
| RAGSAK | 0.05 | 16 | 919 | 40 | 45.4% |
| RAGSAK | 0.10 | 5 | 657 | 19 | 69.1% |
| Flask | 0.01 | 47 | 784 | 28 | 35.2% |
| Flask | 0.05 | 5 | 414 | 7 | 44.4% |
| Flask | 0.10 | 2 | 237 | 5 | 100.0% |
| Coroutines | 0.01 | 76 | 4802 | 175 | 40.4% |
| FastAPI | 0.01 | 23 | 2678 | 14 | 17.0% |
Key findings:
- Coverage increases with threshold (trivial: 1 symbol = 100% coverage)
- Sweet spot: 0.010.05. Enough symbols for meaningful patterns, enough
filtering to remove noise.
- At 0.01: RAGSAK gets `warn.status.body.ErrorResponse` (real convention)
- At 0.05: that pattern disappears (too aggressive)
- Flask dies at 0.15+ (0 symbols survive)
---
## What We Learned (Summary) ## What We Learned (Summary)
1. **Per-package grouping is too sparse.** 1-3 sequences per package isn't 1. **Per-package grouping is too sparse.** 1-3 sequences per package isn't

167
experiments/freq_eval.py Normal file
View file

@ -0,0 +1,167 @@
"""Frequency Threshold Experiment — Test different min_coverage values.
The current pipeline uses min_coverage=0.2 fixed. This tests what happens
at 0.01, 0.05, 0.10, 0.15, 0.20 on all 4 codebases.
"""
import json
import time
from collections import Counter, defaultdict
from pathlib import Path
from bex.tag_preprocessor.analyze import (
_preprocess_files, _file_to_package, scan_directory, frequency_filter
)
from bex.tag_preprocessor.code import _extract_call_tokens, _extract_coarsened_tokens
from bex.twotinf import build_soa
from bex.rwr0 import rwr0
RESULTS_DIR = Path(__file__).parent / "results"
CODEBASES = {
"ragsak": {"name": "RAGSAK", "path": "/home/tobi/Desktop/kesai/RAGSAK", "ext": ".kt"},
"flask": {"name": "Flask", "path": "/home/tobi/Desktop/dervish/external_refs/flask", "ext": ".py"},
"coroutines": {"name": "Kotlin Coroutines", "path": "/home/tobi/Desktop/dervish/projects/grammar-inference-engine/external_refs/kotlinx.coroutines", "ext": ".kt"},
"fastapi": {"name": "FastAPI", "path": "/home/tobi/Desktop/dervish/projects/grammar-inference-engine/external_refs/fastapi", "ext": ".py"},
}
THRESHOLDS = [0.0, 0.01, 0.02, 0.05, 0.10, 0.15, 0.20]
def load_data(base, ext):
groups = scan_directory(base)
files = groups.get(ext, [])
sequences, seq_files = _preprocess_files(files)
raw_seqs = [_extract_call_tokens(seq) for seq in sequences]
packages = [_file_to_package(fp, base) for fp in seq_files]
return raw_seqs, packages, seq_files
def measure_at_threshold(raw_seqs, packages, threshold):
"""Measure what happens at a given frequency threshold."""
# Count symbol frequency
sym_file = Counter()
for seq in raw_seqs:
for sym in set(seq):
sym_file[sym] += 1
total = len(raw_seqs)
n_keep = sum(1 for c in sym_file.values() if c >= max(1, int(total * threshold)))
keep_syms = {s for s, c in sym_file.items() if c >= max(1, int(total * threshold))}
surviving = sum(1 for seq in raw_seqs if any(s in keep_syms for s in seq))
# Filter sequences
wrapped = [[(j, s, 0) for j, s in enumerate(seq)] for seq in raw_seqs]
filtered = frequency_filter(wrapped, min_coverage=threshold)
clean = [[text for _, text, _ in r] for r in filtered]
clean = [s for s in clean if s]
# Group by first 3 symbols for inference
contexts = defaultdict(list)
for i, seq in enumerate(clean):
if not seq:
contexts[("_eps",)].append(seq)
else:
ctx = tuple(seq[:3])
contexts[ctx].append(seq)
sore_successes = 0
methods_in_good = 0
total_methods = 0
top_patterns = []
for ctx, seqs in sorted(contexts.items(), key=lambda x: -len(x[1])):
n = len(seqs)
total_methods += n
if n < 3:
continue
unique = len(set(tuple(s) for s in seqs))
if unique / n > 0.9:
continue
alphabet = set()
for s in seqs:
alphabet.update(s)
if len(alphabet) > 20:
continue
try:
soa = build_soa(seqs)
sore = rwr0(soa)
if sore != "":
sore_successes += 1
methods_in_good += n
top_patterns.append({
"context": str(ctx),
"methods": n,
"unique": unique,
"sore": sore[:150],
})
except Exception:
pass
return {
"threshold": threshold,
"symbols_total": len(sym_file),
"symbols_kept": n_keep,
"seqs_total": total,
"seqs_surviving": surviving,
"contexts": len(contexts),
"sore_successes": sore_successes,
"total_methods": total_methods,
"methods_in_good": methods_in_good,
"coverage": round(methods_in_good / total_methods * 100, 1) if total_methods else 0,
"top_patterns": top_patterns[:5],
}
def run_codebase(key):
cfg = CODEBASES[key]
print(f"\n{'=' * 60}")
print(f" {cfg['name']}")
print(f"{'=' * 60}")
raw_seqs, packages, seq_files = load_data(cfg["path"], cfg["ext"])
print(f" {len(raw_seqs)} methods from {len(set(packages))} packages")
results = []
for thresh in THRESHOLDS:
t0 = time.time()
r = measure_at_threshold(raw_seqs, packages, thresh)
elapsed = time.time() - t0
r["elapsed"] = round(elapsed, 2)
results.append(r)
print(f" thresh={thresh:.2f} syms={r['symbols_kept']:4d} seqs={r['seqs_surviving']:5d} "
f"ctxs={r['contexts']:4d} SOREs={r['sore_successes']:3d} cov={r['coverage']:5.1f}% "
f"({elapsed:.1f}s)")
out_path = RESULTS_DIR / f"freq_{key}.json"
with open(out_path, "w") as f:
json.dump({"codebase": cfg["name"], "results": results}, f, indent=2)
print(f" Saved to {out_path}")
return results
def main():
all_results = {}
for key in CODEBASES:
all_results[key] = run_codebase(key)
# Summary table
print(f"\n{'=' * 80}")
print(" SUMMARY")
print(f"{'=' * 80}")
print(f" {'Codebase':20s} {'Thresh':7s} {'Syms':5s} {'Seqs':6s} {'SOREs':6s} {'Cov':7s}")
print(f" {'-'*55}")
for key, results in all_results.items():
name = CODEBASES[key]["name"]
for r in results:
print(f" {name:20s} {r['threshold']:7.2f} {r['symbols_kept']:5d} "
f"{r['seqs_surviving']:6d} {r['sore_successes']:6d} {r['coverage']:6.1f}%")
return all_results
if __name__ == "__main__":
main()

View file

@ -0,0 +1,302 @@
{
"codebase": "Kotlin Coroutines",
"results": [
{
"threshold": 0.0,
"symbols_total": 2962,
"symbols_kept": 2962,
"seqs_total": 6720,
"seqs_surviving": 6559,
"contexts": 3433,
"sore_successes": 207,
"total_methods": 6559,
"methods_in_good": 1384,
"coverage": 21.1,
"top_patterns": [
{
"context": "('expectUnreached',)",
"methods": 76,
"unique": 1,
"sore": "expectUnreached"
},
{
"context": "('test', 'main', 'verifyLines')",
"methods": 56,
"unique": 1,
"sore": "test.main.verifyLines"
},
{
"context": "('expect',)",
"methods": 42,
"unique": 1,
"sore": "expect"
},
{
"context": "('close',)",
"methods": 40,
"unique": 1,
"sore": "close"
},
{
"context": "('noImpl',)",
"methods": 34,
"unique": 1,
"sore": "noImpl"
}
],
"elapsed": 0.82
},
{
"threshold": 0.01,
"symbols_total": 2962,
"symbols_kept": 76,
"seqs_total": 6720,
"seqs_surviving": 4802,
"contexts": 1297,
"sore_successes": 175,
"total_methods": 4802,
"methods_in_good": 1939,
"coverage": 40.4,
"top_patterns": [
{
"context": "('test', 'main')",
"methods": 85,
"unique": 1,
"sore": "test.main"
},
{
"context": "('expectUnreached',)",
"methods": 81,
"unique": 1,
"sore": "expectUnreached"
},
{
"context": "('expect',)",
"methods": 73,
"unique": 1,
"sore": "expect"
},
{
"context": "('block',)",
"methods": 59,
"unique": 1,
"sore": "block"
},
{
"context": "('compareAndSet',)",
"methods": 55,
"unique": 1,
"sore": "compareAndSet"
}
],
"elapsed": 0.85
},
{
"threshold": 0.02,
"symbols_total": 2962,
"symbols_kept": 38,
"seqs_total": 6720,
"seqs_surviving": 3954,
"contexts": 826,
"sore_successes": 148,
"total_methods": 3954,
"methods_in_good": 1635,
"coverage": 41.4,
"top_patterns": [
{
"context": "('expectUnreached',)",
"methods": 92,
"unique": 1,
"sore": "expectUnreached"
},
{
"context": "('runTest',)",
"methods": 82,
"unique": 1,
"sore": "runTest"
},
{
"context": "('error', 'error')",
"methods": 80,
"unique": 1,
"sore": "(error)+"
},
{
"context": "('expect',)",
"methods": 75,
"unique": 1,
"sore": "expect"
},
{
"context": "('assertEquals',)",
"methods": 73,
"unique": 1,
"sore": "assertEquals"
}
],
"elapsed": 0.72
},
{
"threshold": 0.05,
"symbols_total": 2962,
"symbols_kept": 17,
"seqs_total": 6720,
"seqs_surviving": 3511,
"contexts": 430,
"sore_successes": 104,
"total_methods": 3511,
"methods_in_good": 1674,
"coverage": 47.7,
"top_patterns": [
{
"context": "('runTest',)",
"methods": 220,
"unique": 1,
"sore": "runTest"
},
{
"context": "('expectUnreached',)",
"methods": 99,
"unique": 1,
"sore": "expectUnreached"
},
{
"context": "('assertEquals',)",
"methods": 91,
"unique": 1,
"sore": "assertEquals"
},
{
"context": "('runTest', 'assertEquals')",
"methods": 88,
"unique": 1,
"sore": "runTest.assertEquals"
},
{
"context": "('expect',)",
"methods": 81,
"unique": 1,
"sore": "expect"
}
],
"elapsed": 0.36
},
{
"threshold": 0.1,
"symbols_total": 2962,
"symbols_kept": 5,
"seqs_total": 6720,
"seqs_surviving": 2675,
"contexts": 61,
"sore_successes": 28,
"total_methods": 2675,
"methods_in_good": 1633,
"coverage": 61.0,
"top_patterns": [
{
"context": "('runTest',)",
"methods": 428,
"unique": 1,
"sore": "runTest"
},
{
"context": "('assertEquals',)",
"methods": 236,
"unique": 1,
"sore": "assertEquals"
},
{
"context": "('runTest', 'assertEquals')",
"methods": 197,
"unique": 1,
"sore": "runTest.assertEquals"
},
{
"context": "('runTest', 'expect', 'launch')",
"methods": 197,
"unique": 72,
"sore": "runTest.((expect)+|((assertEquals)+|(finish|(launch)+))+)+"
},
{
"context": "('launch',)",
"methods": 145,
"unique": 1,
"sore": "launch"
}
],
"elapsed": 0.09
},
{
"threshold": 0.15,
"symbols_total": 2962,
"symbols_kept": 4,
"seqs_total": 6720,
"seqs_surviving": 2499,
"contexts": 34,
"sore_successes": 19,
"total_methods": 2499,
"methods_in_good": 1309,
"coverage": 52.4,
"top_patterns": [
{
"context": "('runTest',)",
"methods": 549,
"unique": 1,
"sore": "runTest"
},
{
"context": "('assertEquals',)",
"methods": 253,
"unique": 1,
"sore": "assertEquals"
},
{
"context": "('runTest', 'assertEquals')",
"methods": 233,
"unique": 1,
"sore": "runTest.assertEquals"
},
{
"context": "('expect',)",
"methods": 102,
"unique": 1,
"sore": "expect"
},
{
"context": "('assertEquals', 'assertEquals')",
"methods": 55,
"unique": 1,
"sore": "(assertEquals)+"
}
],
"elapsed": 0.05
},
{
"threshold": 0.2,
"symbols_total": 2962,
"symbols_kept": 1,
"seqs_total": 6720,
"seqs_surviving": 1736,
"contexts": 3,
"sore_successes": 2,
"total_methods": 1736,
"methods_in_good": 1734,
"coverage": 99.9,
"top_patterns": [
{
"context": "('runTest',)",
"methods": 1728,
"unique": 1,
"sore": "runTest"
},
{
"context": "('runTest', 'runTest')",
"methods": 6,
"unique": 1,
"sore": "(runTest)+"
}
],
"elapsed": 0.03
}
]
}

View file

@ -0,0 +1,320 @@
{
"codebase": "FastAPI",
"results": [
{
"threshold": 0.0,
"symbols_total": 1503,
"symbols_kept": 1503,
"seqs_total": 4811,
"seqs_surviving": 3657,
"contexts": 795,
"sore_successes": 53,
"total_methods": 3657,
"methods_in_good": 518,
"coverage": 14.2,
"top_patterns": [
{
"context": "('get', 'get')",
"methods": 89,
"unique": 1,
"sore": "(get)+"
},
{
"context": "('HTTPException', 'HTTPException')",
"methods": 38,
"unique": 1,
"sore": "(HTTPException)+"
},
{
"context": "('update', 'update')",
"methods": 33,
"unique": 1,
"sore": "(update)+"
},
{
"context": "('post', 'post')",
"methods": 30,
"unique": 1,
"sore": "(post)+"
},
{
"context": "('User', 'User')",
"methods": 23,
"unique": 1,
"sore": "(User)+"
}
],
"elapsed": 0.52
},
{
"threshold": 0.01,
"symbols_total": 1503,
"symbols_kept": 23,
"seqs_total": 4811,
"seqs_surviving": 2678,
"contexts": 78,
"sore_successes": 14,
"total_methods": 2678,
"methods_in_good": 456,
"coverage": 17.0,
"top_patterns": [
{
"context": "('get', 'get')",
"methods": 123,
"unique": 1,
"sore": "(get)+"
},
{
"context": "('put', 'put', 'json')",
"methods": 67,
"unique": 2,
"sore": "((put)+|(json)+)+"
},
{
"context": "('HTTPException', 'HTTPException')",
"methods": 53,
"unique": 1,
"sore": "(HTTPException)+"
},
{
"context": "('update', 'update')",
"methods": 41,
"unique": 1,
"sore": "(update)+"
},
{
"context": "('post', 'post')",
"methods": 32,
"unique": 1,
"sore": "(post)+"
}
],
"elapsed": 0.16
},
{
"threshold": 0.02,
"symbols_total": 1503,
"symbols_kept": 8,
"seqs_total": 4811,
"seqs_surviving": 2331,
"contexts": 32,
"sore_successes": 9,
"total_methods": 2331,
"methods_in_good": 430,
"coverage": 18.4,
"top_patterns": [
{
"context": "('get', 'get')",
"methods": 173,
"unique": 1,
"sore": "(get)+"
},
{
"context": "('json', 'json')",
"methods": 73,
"unique": 1,
"sore": "(json)+"
},
{
"context": "('snapshot', 'snapshot')",
"methods": 42,
"unique": 1,
"sore": "(snapshot)+"
},
{
"context": "('post', 'post')",
"methods": 33,
"unique": 1,
"sore": "(post)+"
},
{
"context": "('raises', 'raises', 'get')",
"methods": 33,
"unique": 2,
"sore": "((raises)+|(get)+)+"
}
],
"elapsed": 0.09
},
{
"threshold": 0.05,
"symbols_total": 1503,
"symbols_kept": 5,
"seqs_total": 4811,
"seqs_surviving": 2277,
"contexts": 17,
"sore_successes": 5,
"total_methods": 2277,
"methods_in_good": 574,
"coverage": 25.2,
"top_patterns": [
{
"context": "('get', 'get')",
"methods": 234,
"unique": 1,
"sore": "(get)+"
},
{
"context": "('TestClient', 'TestClient')",
"methods": 176,
"unique": 1,
"sore": "(TestClient)+"
},
{
"context": "('json', 'json')",
"methods": 73,
"unique": 1,
"sore": "(json)+"
},
{
"context": "('post', 'post')",
"methods": 48,
"unique": 1,
"sore": "(post)+"
},
{
"context": "('snapshot', 'snapshot')",
"methods": 43,
"unique": 1,
"sore": "(snapshot)+"
}
],
"elapsed": 0.08
},
{
"threshold": 0.1,
"symbols_total": 1503,
"symbols_kept": 3,
"seqs_total": 4811,
"seqs_surviving": 2182,
"contexts": 10,
"sore_successes": 8,
"total_methods": 2182,
"methods_in_good": 1997,
"coverage": 91.5,
"top_patterns": [
{
"context": "('get', 'get', 'json')",
"methods": 951,
"unique": 6,
"sore": "((get)+|(json)+)+"
},
{
"context": "('TestClient', 'TestClient', 'get')",
"methods": 274,
"unique": 11,
"sore": "((TestClient)+|((get)+|(json)+)+)+"
},
{
"context": "('json', 'json')",
"methods": 248,
"unique": 1,
"sore": "(json)+"
},
{
"context": "('get', 'get')",
"methods": 235,
"unique": 1,
"sore": "(get)+"
},
{
"context": "('TestClient', 'TestClient')",
"methods": 184,
"unique": 1,
"sore": "(TestClient)+"
}
],
"elapsed": 0.05
},
{
"threshold": 0.15,
"symbols_total": 1503,
"symbols_kept": 2,
"seqs_total": 4811,
"seqs_surviving": 1998,
"contexts": 6,
"sore_successes": 5,
"total_methods": 1998,
"methods_in_good": 1987,
"coverage": 99.4,
"top_patterns": [
{
"context": "('get', 'get', 'json')",
"methods": 1161,
"unique": 7,
"sore": "((get)+|(json)+)+"
},
{
"context": "('json', 'json')",
"methods": 425,
"unique": 1,
"sore": "(json)+"
},
{
"context": "('get', 'get')",
"methods": 302,
"unique": 1,
"sore": "(get)+"
},
{
"context": "('get', 'get', 'get')",
"methods": 96,
"unique": 20,
"sore": "((get)+|(json)+)+"
},
{
"context": "('json', 'json', 'get')",
"methods": 3,
"unique": 2,
"sore": "((json)+|(get)+)+"
}
],
"elapsed": 0.04
},
{
"threshold": 0.2,
"symbols_total": 1503,
"symbols_kept": 2,
"seqs_total": 4811,
"seqs_surviving": 1998,
"contexts": 6,
"sore_successes": 5,
"total_methods": 1998,
"methods_in_good": 1987,
"coverage": 99.4,
"top_patterns": [
{
"context": "('get', 'get', 'json')",
"methods": 1161,
"unique": 7,
"sore": "((get)+|(json)+)+"
},
{
"context": "('json', 'json')",
"methods": 425,
"unique": 1,
"sore": "(json)+"
},
{
"context": "('get', 'get')",
"methods": 302,
"unique": 1,
"sore": "(get)+"
},
{
"context": "('get', 'get', 'get')",
"methods": 96,
"unique": 20,
"sore": "((get)+|(json)+)+"
},
{
"context": "('json', 'json', 'get')",
"methods": 3,
"unique": 2,
"sore": "((json)+|(get)+)+"
}
],
"elapsed": 0.04
}
]
}

View file

@ -0,0 +1,258 @@
{
"codebase": "Flask",
"results": [
{
"threshold": 0.0,
"symbols_total": 1055,
"symbols_kept": 1055,
"seqs_total": 1424,
"seqs_surviving": 1109,
"contexts": 598,
"sore_successes": 25,
"total_methods": 1109,
"methods_in_good": 207,
"coverage": 18.7,
"top_patterns": [
{
"context": "('append', 'append')",
"methods": 51,
"unique": 1,
"sore": "(append)+"
},
{
"context": "('render_template', 'render_template')",
"methods": 31,
"unique": 1,
"sore": "(render_template)+"
},
{
"context": "('abort', 'abort')",
"methods": 16,
"unique": 1,
"sore": "(abort)+"
},
{
"context": "('get', 'get')",
"methods": 10,
"unique": 1,
"sore": "(get)+"
},
{
"context": "('pop', 'pop')",
"methods": 10,
"unique": 1,
"sore": "(pop)+"
}
],
"elapsed": 0.05
},
{
"threshold": 0.01,
"symbols_total": 1055,
"symbols_kept": 47,
"seqs_total": 1424,
"seqs_surviving": 784,
"contexts": 173,
"sore_successes": 28,
"total_methods": 784,
"methods_in_good": 276,
"coverage": 35.2,
"top_patterns": [
{
"context": "('append', 'append')",
"methods": 54,
"unique": 1,
"sore": "(append)+"
},
{
"context": "('render_template', 'render_template')",
"methods": 33,
"unique": 1,
"sore": "(render_template)+"
},
{
"context": "('get', 'get')",
"methods": 19,
"unique": 1,
"sore": "(get)+"
},
{
"context": "('abort', 'abort')",
"methods": 16,
"unique": 1,
"sore": "(abort)+"
},
{
"context": "('pop', 'pop')",
"methods": 15,
"unique": 1,
"sore": "(pop)+"
}
],
"elapsed": 0.13
},
{
"threshold": 0.02,
"symbols_total": 1055,
"symbols_kept": 20,
"seqs_total": 1424,
"seqs_surviving": 621,
"contexts": 86,
"sore_successes": 11,
"total_methods": 621,
"methods_in_good": 213,
"coverage": 34.3,
"top_patterns": [
{
"context": "('append', 'append')",
"methods": 64,
"unique": 1,
"sore": "(append)+"
},
{
"context": "('render_template', 'render_template')",
"methods": 35,
"unique": 1,
"sore": "(render_template)+"
},
{
"context": "('get', 'get')",
"methods": 34,
"unique": 1,
"sore": "(get)+"
},
{
"context": "('pop', 'pop')",
"methods": 17,
"unique": 1,
"sore": "(pop)+"
},
{
"context": "('abort', 'abort')",
"methods": 16,
"unique": 1,
"sore": "(abort)+"
}
],
"elapsed": 0.07
},
{
"threshold": 0.05,
"symbols_total": 1055,
"symbols_kept": 5,
"seqs_total": 1424,
"seqs_surviving": 414,
"contexts": 16,
"sore_successes": 7,
"total_methods": 414,
"methods_in_good": 184,
"coverage": 44.4,
"top_patterns": [
{
"context": "('append', 'append')",
"methods": 83,
"unique": 1,
"sore": "(append)+"
},
{
"context": "('get', 'get')",
"methods": 53,
"unique": 1,
"sore": "(get)+"
},
{
"context": "('get', 'get', 'get')",
"methods": 23,
"unique": 4,
"sore": "(get)+"
},
{
"context": "('route', 'route')",
"methods": 11,
"unique": 1,
"sore": "(route)+"
},
{
"context": "('route', 'route', 'get')",
"methods": 8,
"unique": 3,
"sore": "((route)+|(get)+)+"
}
],
"elapsed": 0.02
},
{
"threshold": 0.1,
"symbols_total": 1055,
"symbols_kept": 2,
"seqs_total": 1424,
"seqs_surviving": 237,
"contexts": 5,
"sore_successes": 5,
"total_methods": 237,
"methods_in_good": 237,
"coverage": 100.0,
"top_patterns": [
{
"context": "('route', 'route', 'get')",
"methods": 83,
"unique": 5,
"sore": "((route)+|(get)+)+"
},
{
"context": "('get', 'get')",
"methods": 60,
"unique": 1,
"sore": "(get)+"
},
{
"context": "('route', 'route', 'route')",
"methods": 38,
"unique": 14,
"sore": "((route)+|(get)+)+"
},
{
"context": "('get', 'get', 'get')",
"methods": 33,
"unique": 6,
"sore": "(get)+"
},
{
"context": "('route', 'route')",
"methods": 23,
"unique": 1,
"sore": "(route)+"
}
],
"elapsed": 0.01
},
{
"threshold": 0.15,
"symbols_total": 1055,
"symbols_kept": 0,
"seqs_total": 1424,
"seqs_surviving": 0,
"contexts": 0,
"sore_successes": 0,
"total_methods": 0,
"methods_in_good": 0,
"coverage": 0,
"top_patterns": [],
"elapsed": 0.01
},
{
"threshold": 0.2,
"symbols_total": 1055,
"symbols_kept": 0,
"seqs_total": 1424,
"seqs_surviving": 0,
"contexts": 0,
"sore_successes": 0,
"total_methods": 0,
"methods_in_good": 0,
"coverage": 0,
"top_patterns": [],
"elapsed": 0.01
}
]
}

View file

@ -0,0 +1,308 @@
{
"codebase": "RAGSAK",
"results": [
{
"threshold": 0.0,
"symbols_total": 1724,
"symbols_kept": 1724,
"seqs_total": 1609,
"seqs_surviving": 1578,
"contexts": 1065,
"sore_successes": 49,
"total_methods": 1578,
"methods_in_good": 217,
"coverage": 13.8,
"top_patterns": [
{
"context": "('warn', 'status', 'body')",
"methods": 22,
"unique": 1,
"sore": "warn.status.body.ErrorResponse"
},
{
"context": "('ery {', 'stKnowledgeBases()', 'gRequest(m')",
"methods": 12,
"unique": 4,
"sore": "ery {.stKnowledgeBases().gRequest(m.(ckKnowledgeBase(re.ertEquals(Kn.\"k|eckKnowledgeBase(r.(sertEquals(K.(\"|(sertEquals(t|sertNull(o)))"
},
{
"context": "('mockk',)",
"methods": 11,
"unique": 1,
"sore": "mockk"
},
{
"context": "('filesIn', 'assertTrue', 'hasImport')",
"methods": 7,
"unique": 2,
"sore": "filesIn.assertTrue.(hasImport)+"
},
{
"context": "('of',)",
"methods": 7,
"unique": 1,
"sore": "of"
}
],
"elapsed": 0.09
},
{
"threshold": 0.01,
"symbols_total": 1724,
"symbols_kept": 130,
"seqs_total": 1609,
"seqs_surviving": 1270,
"contexts": 633,
"sore_successes": 61,
"total_methods": 1270,
"methods_in_good": 331,
"coverage": 26.1,
"top_patterns": [
{
"context": "('assertEquals', 'assertEquals')",
"methods": 23,
"unique": 1,
"sore": "(assertEquals)+"
},
{
"context": "('warn', 'status', 'body')",
"methods": 22,
"unique": 1,
"sore": "warn.status.body.ErrorResponse"
},
{
"context": "('map',)",
"methods": 16,
"unique": 1,
"sore": "map"
},
{
"context": "('mockk',)",
"methods": 12,
"unique": 1,
"sore": "mockk"
},
{
"context": "('build',)",
"methods": 11,
"unique": 1,
"sore": "build"
}
],
"elapsed": 0.08
},
{
"threshold": 0.02,
"symbols_total": 1724,
"symbols_kept": 54,
"seqs_total": 1609,
"seqs_surviving": 1185,
"contexts": 456,
"sore_successes": 56,
"total_methods": 1185,
"methods_in_good": 405,
"coverage": 34.2,
"top_patterns": [
{
"context": "('assertEquals', 'assertEquals')",
"methods": 28,
"unique": 1,
"sore": "(assertEquals)+"
},
{
"context": "('warn', 'status', 'body')",
"methods": 25,
"unique": 1,
"sore": "warn.status.body"
},
{
"context": "('assertTrue',)",
"methods": 18,
"unique": 1,
"sore": "assertTrue"
},
{
"context": "('map',)",
"methods": 17,
"unique": 1,
"sore": "map"
},
{
"context": "('of',)",
"methods": 17,
"unique": 1,
"sore": "of"
}
],
"elapsed": 0.21
},
{
"threshold": 0.05,
"symbols_total": 1724,
"symbols_kept": 16,
"seqs_total": 1609,
"seqs_surviving": 919,
"contexts": 182,
"sore_successes": 40,
"total_methods": 919,
"methods_in_good": 417,
"coverage": 45.4,
"top_patterns": [
{
"context": "('build',)",
"methods": 40,
"unique": 1,
"sore": "build"
},
{
"context": "('assertEquals', 'assertEquals')",
"methods": 34,
"unique": 1,
"sore": "(assertEquals)+"
},
{
"context": "('of',)",
"methods": 34,
"unique": 1,
"sore": "of"
},
{
"context": "('map',)",
"methods": 33,
"unique": 1,
"sore": "map"
},
{
"context": "('assertTrue',)",
"methods": 29,
"unique": 1,
"sore": "assertTrue"
}
],
"elapsed": 0.16
},
{
"threshold": 0.1,
"symbols_total": 1724,
"symbols_kept": 5,
"seqs_total": 1609,
"seqs_surviving": 657,
"contexts": 44,
"sore_successes": 19,
"total_methods": 657,
"methods_in_good": 454,
"coverage": 69.1,
"top_patterns": [
{
"context": "('assertTrue',)",
"methods": 68,
"unique": 1,
"sore": "assertTrue"
},
{
"context": "('every',)",
"methods": 57,
"unique": 1,
"sore": "every"
},
{
"context": "('assertEquals',)",
"methods": 44,
"unique": 1,
"sore": "assertEquals"
},
{
"context": "('assertEquals', 'assertEquals')",
"methods": 43,
"unique": 1,
"sore": "(assertEquals)+"
},
{
"context": "('every', 'listOf', 'listOf')",
"methods": 41,
"unique": 30,
"sore": "(((assertEquals)+|(assertTrue)+)+|((every)+|((listOf)+|(any)+)+)+)+"
}
],
"elapsed": 0.1
},
{
"threshold": 0.15,
"symbols_total": 1724,
"symbols_kept": 2,
"seqs_total": 1609,
"seqs_surviving": 473,
"contexts": 9,
"sore_successes": 8,
"total_methods": 473,
"methods_in_good": 431,
"coverage": 91.1,
"top_patterns": [
{
"context": "('every',)",
"methods": 95,
"unique": 1,
"sore": "every"
},
{
"context": "('assertEquals',)",
"methods": 72,
"unique": 1,
"sore": "assertEquals"
},
{
"context": "('every', 'every', 'every')",
"methods": 59,
"unique": 20,
"sore": "((every)+|(assertEquals)+)+"
},
{
"context": "('assertEquals', 'assertEquals')",
"methods": 56,
"unique": 1,
"sore": "(assertEquals)+"
},
{
"context": "('every', 'assertEquals')",
"methods": 47,
"unique": 1,
"sore": "every.assertEquals"
}
],
"elapsed": 0.02
},
{
"threshold": 0.2,
"symbols_total": 1724,
"symbols_kept": 1,
"seqs_total": 1609,
"seqs_surviving": 326,
"contexts": 3,
"sore_successes": 3,
"total_methods": 326,
"methods_in_good": 326,
"coverage": 100.0,
"top_patterns": [
{
"context": "('assertEquals',)",
"methods": 162,
"unique": 1,
"sore": "assertEquals"
},
{
"context": "('assertEquals', 'assertEquals')",
"methods": 87,
"unique": 1,
"sore": "(assertEquals)+"
},
{
"context": "('assertEquals', 'assertEquals', 'assertEquals')",
"methods": 77,
"unique": 10,
"sore": "(assertEquals)+"
}
],
"elapsed": 0.01
}
]
}