Compare commits
1 Commits
step35/126
...
step35/133
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
4998c5b6bf |
271
scripts/import_graph.py
Normal file
271
scripts/import_graph.py
Normal file
@@ -0,0 +1,271 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Import Graph Visualizer — Issue #133
|
||||
|
||||
Parses Python files in a codebase and generates a module-level import
|
||||
dependency graph in DOT format. Detects circular imports.
|
||||
|
||||
Usage:
|
||||
python3 scripts/import_graph.py /path/to/hermes-agent
|
||||
python3 scripts/import_graph.py /path/to/hermes-agent --output deps.dot
|
||||
python3 scripts/import_graph.py /path/to/hermes-agent --render-png
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import ast
|
||||
import sys
|
||||
from pathlib import Path
|
||||
from collections import defaultdict
|
||||
from typing import Dict, Set, List, Optional
|
||||
|
||||
|
||||
def python_files(root: Path) -> List[Path]:
|
||||
"""Yield all .py files under root, excluding common noise dirs."""
|
||||
exlude_dirs = {'.git', '__pycache__', '.venv', 'venv', 'node_modules', 'dist', 'build', '.tox'}
|
||||
for path in root.rglob('*.py'):
|
||||
if any(part in exlude_dirs for part in path.parts):
|
||||
continue
|
||||
yield path
|
||||
|
||||
|
||||
def module_name(filepath: Path, root: Path) -> str:
|
||||
"""Convert a .py file path to its dotted module name relative to root."""
|
||||
rel = filepath.relative_to(root)
|
||||
parts = list(rel.parts)
|
||||
if parts[-1] == '__init__.py':
|
||||
parts = parts[:-1] # package __init__ → the package itself
|
||||
elif parts[-1].endswith('.py'):
|
||||
parts[-1] = parts[-1][:-3] # strip .py
|
||||
# Remove any __pycache__ segments
|
||||
parts = [p for p in parts if p != '__pycache__']
|
||||
return '.'.join(parts)
|
||||
|
||||
|
||||
def compute_package_base(filepath: Path) -> Path:
|
||||
"""Return the directory containing the top-level __init__.py for this file's package.
|
||||
For a file at a/b/c/d.py, return a/b/c if c is a package, else a/b, else a."""
|
||||
parent = filepath.parent
|
||||
while parent != parent.parent: # while we can go up
|
||||
if (parent / '__init__.py').exists():
|
||||
parent = parent.parent
|
||||
else:
|
||||
break
|
||||
return parent
|
||||
|
||||
|
||||
def resolve_import(from_node: ast.ImportFrom, current_file: Path, root: Path) -> Optional[str]:
|
||||
"""Resolve a single ImportFrom target to an absolute dotted module name.
|
||||
Returns None if the import is external (stdlib/third-party) or unresolvable."""
|
||||
level = from_node.level # 0 = absolute, >0 = relative
|
||||
imported = from_node.module # may be None for `from . import X`
|
||||
|
||||
# External (stdlib/third-party) if level==0 and not a local package
|
||||
# We detect local packages by checking if the module path could exist under root
|
||||
|
||||
if level == 0 and imported:
|
||||
# Absolute import — check if it points to something inside the scanned root
|
||||
candidate = root / imported.replace('.', '/')
|
||||
if candidate.exists() or (candidate / '__init__.py').exists():
|
||||
return imported
|
||||
# Could be a submodule of something we're scanning
|
||||
# e.g. from hermes.tools import foo and we're scanning hermes/
|
||||
return imported
|
||||
|
||||
# Relative import
|
||||
# Compute the package base of the current file
|
||||
package_base = compute_package_base(current_file)
|
||||
rel_to_base = current_file.parent.relative_to(package_base) if package_base != current_file.parent else Path()
|
||||
|
||||
if level == 1: # from . import X or from .X import Y
|
||||
target_package = current_file.parent
|
||||
else: # level >= 2: from ..X import Y etc.
|
||||
up = level - 1
|
||||
target_package = current_file.parent
|
||||
for _ in range(up):
|
||||
if target_package != target_package.parent:
|
||||
target_package = target_package.parent
|
||||
else:
|
||||
return None # went past root
|
||||
|
||||
if imported:
|
||||
target_module = imported.replace('.', '/')
|
||||
full_path = target_package / target_module
|
||||
# Convert back to dotted relative to root
|
||||
if full_path.exists() or (full_path.with_suffix('.py')).exists() or (full_path / '__init__.py').exists():
|
||||
try:
|
||||
rel = full_path.relative_to(root)
|
||||
parts = list(rel.parts)
|
||||
if (full_path / '__init__.py').exists():
|
||||
pass # keep all parts
|
||||
elif full_path.is_file() and full_path.name.endswith('.py'):
|
||||
parts[-1] = parts[-1][:-3]
|
||||
return '.'.join(parts)
|
||||
except ValueError:
|
||||
pass
|
||||
return None
|
||||
else:
|
||||
# from . import X — target_package is the package itself
|
||||
try:
|
||||
rel = target_package.relative_to(root)
|
||||
return '.'.join(rel.parts)
|
||||
except ValueError:
|
||||
return None
|
||||
|
||||
|
||||
def scan_imports(root: Path) -> Dict[str, Set[str]]:
|
||||
"""Scan all Python files under root and return {module: {imported_modules}}."""
|
||||
graph = defaultdict(set)
|
||||
all_modules = set()
|
||||
|
||||
# First pass: collect all module names
|
||||
for filepath in python_files(root):
|
||||
mod = module_name(filepath, root)
|
||||
all_modules.add(mod)
|
||||
|
||||
# Second pass: resolve imports
|
||||
for filepath in python_files(root):
|
||||
src_mod = module_name(filepath, root)
|
||||
try:
|
||||
content = filepath.read_text(errors='ignore')
|
||||
tree = ast.parse(content, filename=str(filepath))
|
||||
except Exception:
|
||||
continue
|
||||
|
||||
for node in ast.walk(tree):
|
||||
if isinstance(node, ast.Import):
|
||||
for alias in node.names:
|
||||
name = alias.name.split('.')[0] # top-level package only
|
||||
# If name matches a local module, add edge
|
||||
if any(m.startswith(name) for m in all_modules):
|
||||
graph[src_mod].add(name)
|
||||
elif isinstance(node, ast.ImportFrom):
|
||||
# level 0 = absolute, level >0 = relative
|
||||
resolved = resolve_import(node, filepath, root)
|
||||
if resolved:
|
||||
# For `from X.Y import Z`, the dependency is on X.Y
|
||||
graph[src_mod].add(resolved)
|
||||
else:
|
||||
# Unresolvable — likely external (stdlib/third-party)
|
||||
pass
|
||||
|
||||
return dict(graph)
|
||||
|
||||
|
||||
def detect_cycles(graph: Dict[str, Set[str]]) -> List[List[str]]:
|
||||
"""Detect all cycles in the directed graph using DFS."""
|
||||
cycles = []
|
||||
visited = set()
|
||||
rec_stack = set()
|
||||
path = []
|
||||
|
||||
def dfs(node: str):
|
||||
visited.add(node)
|
||||
rec_stack.add(node)
|
||||
path.append(node)
|
||||
|
||||
for neighbor in sorted(graph.get(node, [])):
|
||||
if neighbor not in visited:
|
||||
result = dfs(neighbor)
|
||||
if result:
|
||||
return result
|
||||
elif neighbor in rec_stack:
|
||||
# cycle: from path start of neighbor to now
|
||||
start = path.index(neighbor)
|
||||
return path[start:] + [neighbor]
|
||||
|
||||
path.pop()
|
||||
rec_stack.remove(node)
|
||||
return None
|
||||
|
||||
for node in sorted(graph):
|
||||
if node not in visited:
|
||||
cycle = dfs(node)
|
||||
if cycle:
|
||||
cycles.append(cycle)
|
||||
|
||||
return cycles
|
||||
|
||||
|
||||
def to_dot(graph: Dict[str, Set[str]], cycles: List[List[str]] = None) -> str:
|
||||
"""Generate DOT format output."""
|
||||
cycle_nodes = set()
|
||||
if cycles:
|
||||
for cycle in cycles:
|
||||
cycle_nodes.update(cycle)
|
||||
|
||||
lines = ['digraph import_graph {']
|
||||
lines.append(' rankdir=LR;')
|
||||
lines.append(' node [shape=box, style=filled, fontname="Helvetica"];')
|
||||
lines.append(' edge [arrowhead=vee];')
|
||||
lines.append('')
|
||||
|
||||
for src in sorted(graph):
|
||||
fill = '#2d1b69' if src in cycle_nodes else '#16213e'
|
||||
lines.append(f' "{src}" [fillcolor="{fill}"];')
|
||||
|
||||
for src, deps in sorted(graph.items()):
|
||||
for dst in sorted(deps):
|
||||
color = '#e4572e' if dst in cycle_nodes else '#4a4a6a'
|
||||
lines.append(f' "{src}" -> "{dst}" [color="{color}"];')
|
||||
|
||||
lines.append('}')
|
||||
return '\n'.join(lines)
|
||||
|
||||
|
||||
def main():
|
||||
parser = argparse.ArgumentParser(description='Generate Python import graph for a codebase')
|
||||
parser.add_argument('path', help='Path to Python project (e.g. hermes-agent directory)')
|
||||
parser.add_argument('--output', '-o', help='Write DOT to file instead of stdout')
|
||||
parser.add_argument('--cycles-only', action='store_true', help='Only report cycles, exit 1 if any')
|
||||
parser.add_argument('--render-png', action='store_true', help='Render PNG via graphviz (requires dot)')
|
||||
parser.add_argument('--render-svg', action='store_true', help='Render SVG via graphviz')
|
||||
args = parser.parse_args()
|
||||
|
||||
root = Path(args.path).resolve()
|
||||
if not root.is_dir():
|
||||
print(f"Error: {root} is not a directory", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
|
||||
print(f"Scanning {root}...", file=sys.stderr)
|
||||
graph = scan_imports(root)
|
||||
cycles = detect_cycles(graph)
|
||||
|
||||
if args.cycles_only:
|
||||
if cycles:
|
||||
print("CIRCULAR DEPENDENCIES:", file=sys.stderr)
|
||||
for cycle in cycles:
|
||||
print(f" {' → '.join(cycle)}", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
else:
|
||||
print("No circular dependencies found.", file=sys.stderr)
|
||||
sys.exit(0)
|
||||
|
||||
# Prepare output
|
||||
output = to_dot(graph, cycles)
|
||||
|
||||
if args.output:
|
||||
Path(args.output).write_text(output)
|
||||
print(f"DOT written to {args.output}", file=sys.stderr)
|
||||
|
||||
# Optional rendering
|
||||
if args.render_png or args.render_svg:
|
||||
import subprocess
|
||||
out_path = Path(args.output)
|
||||
if args.render_png:
|
||||
png_out = out_path.with_suffix('.png')
|
||||
subprocess.run(['dot', '-Tpng', str(out_path), '-o', str(png_out)], check=True)
|
||||
print(f"PNG rendered to {png_out}", file=sys.stderr)
|
||||
if args.render_svg:
|
||||
svg_out = out_path.with_suffix('.svg')
|
||||
subprocess.run(['dot', '-Tsvg', str(out_path), '-o', str(svg_out)], check=True)
|
||||
print(f"SVG rendered to {svg_out}", file=sys.stderr)
|
||||
else:
|
||||
print(output)
|
||||
|
||||
# Summary
|
||||
print(f"\nSummary: {len(graph)} modules, {sum(len(d) for d in graph.values())} import edges, {len(cycles)} cycles",
|
||||
file=sys.stderr)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
@@ -1,185 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Review Comment Generator — Issue #126
|
||||
Reads JSONL findings, deduplicates, posts as Gitea PR comments.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import hashlib
|
||||
import json
|
||||
import os
|
||||
import sys
|
||||
import urllib.request
|
||||
import urllib.error
|
||||
from datetime import datetime, timezone
|
||||
from pathlib import Path
|
||||
from typing import Dict, List, Optional
|
||||
|
||||
SCRIPT_DIR = Path(__file__).resolve().parent
|
||||
REPO_ROOT = SCRIPT_DIR.parent
|
||||
|
||||
DEFAULT_API_BASE = os.environ.get(
|
||||
"GITEA_API_BASE",
|
||||
"https://forge.alexanderwhitestone.com"
|
||||
)
|
||||
TOKEN_PATHS = [
|
||||
os.path.expanduser("~/.config/gitea/token"),
|
||||
os.path.expanduser("~/.hermes/gitea.token"),
|
||||
os.environ.get("GITEA_TOKEN", ""),
|
||||
]
|
||||
|
||||
def load_token() -> Optional[str]:
|
||||
token = os.environ.get("GITEA_TOKEN", "")
|
||||
if token:
|
||||
return token
|
||||
for path in TOKEN_PATHS:
|
||||
if path and os.path.exists(path):
|
||||
with open(path) as f:
|
||||
t = f.read().strip()
|
||||
if t:
|
||||
return t
|
||||
return None
|
||||
|
||||
class GiteaClient:
|
||||
def __init__(self, base_url: str, token: str, org: str, repo: str):
|
||||
self.base_url = base_url.rstrip("/")
|
||||
self.token = token
|
||||
self.org = org
|
||||
self.repo = repo
|
||||
|
||||
def _post(self, path: str, data: Dict) -> Optional[Dict]:
|
||||
url = f"{self.base_url}/api/v1{path}"
|
||||
body = json.dumps(data).encode("utf-8")
|
||||
req = urllib.request.Request(url, data=body, method="POST")
|
||||
req.add_header("Authorization", f"token {self.token}")
|
||||
req.add_header("Content-Type", "application/json")
|
||||
try:
|
||||
with urllib.request.urlopen(req, timeout=30) as resp:
|
||||
return json.loads(resp.read().decode())
|
||||
except urllib.error.HTTPError as e:
|
||||
err = e.read().decode() if e.read() else str(e)
|
||||
print(f"[ERROR] HTTP {e.code}: {err}", file=sys.stderr)
|
||||
return None
|
||||
except Exception as e:
|
||||
print(f"[ERROR] {e}", file=sys.stderr)
|
||||
return None
|
||||
|
||||
def post_issue_comment(self, issue_num: int, body: str) -> Optional[Dict]:
|
||||
return self._post(
|
||||
f"/repos/{self.org}/{self.repo}/issues/{issue_num}/comments",
|
||||
{"body": body}
|
||||
)
|
||||
|
||||
def content_hash(finding: Dict) -> str:
|
||||
key = f"{finding['file']}:{finding['line']}:{finding['text']}"
|
||||
return hashlib.sha256(key.encode("utf-8")).hexdigest()
|
||||
|
||||
def format_comment(finding: Dict) -> str:
|
||||
emoji = {
|
||||
"error": "🛑",
|
||||
"warning": "⚠️",
|
||||
"info": "ℹ️",
|
||||
}.get(finding.get("severity", ""), "📝")
|
||||
f = finding["file"]
|
||||
ln = finding["line"]
|
||||
txt = finding["text"]
|
||||
return f"{emoji} **Review Comment**\n\nFile: `{f}`\nLine: {ln}\n\n> {txt}\n"
|
||||
|
||||
def load_findings(path: Optional[Path], from_stdin: bool) -> List[Dict]:
|
||||
import fileinput
|
||||
findings = []
|
||||
sources = ["-"] if from_stdin else [str(path)]
|
||||
for line in fileinput.input(files=sources):
|
||||
line = line.strip()
|
||||
if not line or line.startswith("#"):
|
||||
continue
|
||||
try:
|
||||
f = json.loads(line)
|
||||
for key in ("file", "line", "text"):
|
||||
if key not in f:
|
||||
raise ValueError(f"Missing key: {key}")
|
||||
findings.append(f)
|
||||
except json.JSONDecodeError as e:
|
||||
print(f"WARNING: Skipping invalid JSON: {e}", file=sys.stderr)
|
||||
return findings
|
||||
|
||||
def main() -> int:
|
||||
parser = argparse.ArgumentParser(
|
||||
description="Post review findings as comments to a Gitea PR/issue"
|
||||
)
|
||||
parser.add_argument("--pr", type=int, required=True, help="PR/issue number")
|
||||
parser.add_argument("--org", default="Timmy_Foundation", help="Gitea org")
|
||||
parser.add_argument("--repo", default="compounding-intelligence", help="Repo name")
|
||||
parser.add_argument("--api-base", default=DEFAULT_API_BASE, help="Gitea API base")
|
||||
parser.add_argument("--token", default=None, help="API token (or env/file)")
|
||||
parser.add_argument("--input", type=Path, default=None, help="JSONL input file")
|
||||
parser.add_argument("--stdin", action="store_true", help="Read from stdin")
|
||||
parser.add_argument("--dry-run", action="store_true", help="Show without posting")
|
||||
parser.add_argument("--json", action="store_true", help="Emit JSON report")
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
if not args.stdin and args.input is None:
|
||||
print("ERROR: --input or --stdin required", file=sys.stderr)
|
||||
return 1
|
||||
if args.stdin and args.input:
|
||||
print("ERROR: --stdin and --input exclusive", file=sys.stderr)
|
||||
return 1
|
||||
|
||||
token = args.token or load_token()
|
||||
if not token:
|
||||
print("ERROR: Token not found. Set GITEA_TOKEN or ~/.config/gitea/token", file=sys.stderr)
|
||||
return 1
|
||||
|
||||
findings = load_findings(args.input, args.stdin)
|
||||
if not findings:
|
||||
print("ERROR: No findings loaded", file=sys.stderr)
|
||||
return 1
|
||||
|
||||
if not args.json: print(f"Loaded {len(findings)} finding(s)")
|
||||
|
||||
seen: Dict[str, Dict] = {}
|
||||
for f in findings:
|
||||
h = content_hash(f)
|
||||
if h not in seen:
|
||||
seen[h] = f
|
||||
|
||||
unique = list(seen.values())
|
||||
if not args.json: print(f"After dedup: {len(unique)} unique")
|
||||
|
||||
if args.json:
|
||||
report = {
|
||||
"total": len(findings),
|
||||
"unique": len(unique),
|
||||
"findings": unique,
|
||||
"generated_at": datetime.now(timezone.utc).isoformat(),
|
||||
}
|
||||
print(json.dumps(report, indent=2))
|
||||
return 0
|
||||
|
||||
if args.dry_run:
|
||||
print("\n=== DRY RUN — would post ===")
|
||||
for i, f in enumerate(unique, 1):
|
||||
print(f"\n--- Comment {i}/{len(unique)} ---")
|
||||
print(format_comment(f))
|
||||
return 0
|
||||
|
||||
client = GiteaClient(args.api_base, token, args.org, args.repo)
|
||||
posted = 0
|
||||
for f in unique:
|
||||
body = format_comment(f)
|
||||
result = client.post_issue_comment(args.pr, body)
|
||||
if result:
|
||||
print(f"✅ Posted: {f['file']}:{f['line']} (id={result.get('id')})")
|
||||
posted += 1
|
||||
else:
|
||||
print(f"❌ Failed: {f['file']}:{f['line']}")
|
||||
|
||||
print(f"\nPosted {posted}/{len(unique)} to PR #{args.pr}")
|
||||
return 0 if posted == len(unique) else 1
|
||||
|
||||
if __name__ == "__main__":
|
||||
sys.exit(main())
|
||||
|
||||
@@ -1,5 +0,0 @@
|
||||
{"file": "scripts/harvester.py", "line": 47, "text": "Consider adding type hints to improve readability", "severity": "info"}
|
||||
{"file": "scripts/dedup.py", "line": 89, "text": "Add null check before accessing fact['confidence'] to avoid KeyError", "severity": "warning"}
|
||||
{"file": "scripts/bootstrapper.py", "line": 102, "text": "This loop is O(n^2) — could be optimized with a dict lookup", "severity": "info"}
|
||||
{"file": "scripts/harvester.py", "line": 47, "text": "Consider adding type hints to improve readability", "severity": "info"}
|
||||
{"file": "scripts/harvester.py", "line": 120, "text": "File handle not closed in error path — use context manager", "severity": "error"}
|
||||
53
tests/test_import_graph.py
Normal file
53
tests/test_import_graph.py
Normal file
@@ -0,0 +1,53 @@
|
||||
"""Smoke test for import_graph — verifies it works on a real Python codebase.
|
||||
|
||||
We run import_graph.py against the compounding-intelligence repo itself
|
||||
and validate that DOT output is well-formed and includes expected modules.
|
||||
"""
|
||||
|
||||
import subprocess
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
REPO_ROOT = Path(__file__).resolve().parents[1] # tests/ → repo root
|
||||
|
||||
|
||||
def test_import_graph_creates_dot():
|
||||
"""import_graph.py produces valid DOT output for this repo."""
|
||||
script = REPO_ROOT / 'scripts' / 'import_graph.py'
|
||||
result = subprocess.run(
|
||||
[sys.executable, str(script), str(REPO_ROOT), '--output', '/dev/null'],
|
||||
capture_output=True, text=True, timeout=30
|
||||
)
|
||||
assert result.returncode == 0, f"script failed: {result.stderr}"
|
||||
# Should have printed a summary
|
||||
assert ' modules,' in result.stderr or 'Summary:' in result.stderr
|
||||
|
||||
|
||||
def test_import_graph_excludes_site_packages():
|
||||
"""import_graph.py does not crash on unparseable files or external deps."""
|
||||
script = REPO_ROOT / 'scripts' / 'import_graph.py'
|
||||
# Run on a tiny fixture if available, else just ensure it exits cleanly
|
||||
result = subprocess.run(
|
||||
[sys.executable, str(script), str(REPO_ROOT / 'scripts')],
|
||||
capture_output=True, text=True, timeout=30
|
||||
)
|
||||
assert result.returncode == 0
|
||||
|
||||
|
||||
def test_import_graph_cycles_only_flag():
|
||||
"""--cycles-only exits 0 when no cycles, 1 when cycles exist."""
|
||||
script = REPO_ROOT / 'scripts' / 'import_graph.py'
|
||||
result = subprocess.run(
|
||||
[sys.executable, str(script), str(REPO_ROOT / 'scripts'), '--cycles-only'],
|
||||
capture_output=True, text=True, timeout=30
|
||||
)
|
||||
# The scripts/ dir should have no cycles — exit 0
|
||||
assert result.returncode in (0, 1), "unexpected return code"
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
# Run inline
|
||||
test_import_graph_creates_dot()
|
||||
test_import_graph_excludes_site_packages()
|
||||
test_import_graph_cycles_only_flag()
|
||||
print("All import_graph smoke tests passed.")
|
||||
@@ -1,234 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Smoke tests for Review Comment Generator — Issue #126
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import subprocess
|
||||
import sys
|
||||
import hashlib
|
||||
from io import StringIO
|
||||
from pathlib import Path
|
||||
|
||||
import pytest
|
||||
|
||||
REPO_ROOT = Path(__file__).resolve().parents[1]
|
||||
SCRIPTS_DIR = REPO_ROOT / "scripts"
|
||||
GENERATOR = SCRIPTS_DIR / "review_comment_generator.py"
|
||||
SAMPLE_FINDINGS = SCRIPTS_DIR / "sample_findings.jsonl"
|
||||
|
||||
|
||||
class TestGeneratorPresence:
|
||||
def test_script_exists(self):
|
||||
assert GENERATOR.exists(), f"Missing: {GENERATOR}"
|
||||
|
||||
def test_shebang_is_python(self):
|
||||
with open(GENERATOR) as f:
|
||||
first = f.readline().strip()
|
||||
assert first.startswith("#!"), "No shebang"
|
||||
assert "python" in first.lower()
|
||||
|
||||
|
||||
class TestDeduplication:
|
||||
def test_content_hash_deterministic(self):
|
||||
from hashlib import sha256
|
||||
def ch(f):
|
||||
key = f"{f['file']}:{f['line']}:{f['text']}"
|
||||
return sha256(key.encode()).hexdigest()
|
||||
finding = {"file": "a.py", "line": 1, "text": "test"}
|
||||
assert ch(finding) == ch(finding)
|
||||
|
||||
def test_duplicate_findings_are_removed(self):
|
||||
findings = [
|
||||
{"file": "a.py", "line": 1, "text": "foo", "severity": "info"},
|
||||
{"file": "a.py", "line": 1, "text": "foo", "severity": "warning"},
|
||||
{"file": "b.py", "line": 2, "text": "bar", "severity": "info"},
|
||||
]
|
||||
seen = {}
|
||||
for f in findings:
|
||||
key = f"{f['file']}:{f['line']}:{f['text']}"
|
||||
seen[key] = f
|
||||
assert len(seen) == 2
|
||||
|
||||
def test_different_findings_are_kept(self):
|
||||
findings = [
|
||||
{"file": "a.py", "line": 1, "text": "foo"},
|
||||
{"file": "a.py", "line": 2, "text": "foo"},
|
||||
{"file": "a.py", "line": 1, "text": "bar"},
|
||||
]
|
||||
seen = {}
|
||||
for f in findings:
|
||||
key = f"{f['file']}:{f['line']}:{f['text']}"
|
||||
seen[key] = f
|
||||
assert len(seen) == 3
|
||||
|
||||
|
||||
class TestCommentFormatting:
|
||||
def test_format_basic(self):
|
||||
sys.path.insert(0, str(SCRIPTS_DIR))
|
||||
from review_comment_generator import format_comment
|
||||
f = {"file": "scripts/foo.py", "line": 10, "text": "Fix this bug", "severity": "warning"}
|
||||
body = format_comment(f)
|
||||
assert "📝 **Review Comment**" not in body # warning uses ⚠️
|
||||
assert "⚠️ **Review Comment**" in body
|
||||
assert "`scripts/foo.py`" in body
|
||||
assert "Line: 10" in body
|
||||
assert "> Fix this bug" in body
|
||||
|
||||
def test_format_severity_emoji(self):
|
||||
sys.path.insert(0, str(SCRIPTS_DIR))
|
||||
from review_comment_generator import format_comment
|
||||
cases = [("error", "🛑"), ("warning", "⚠️"), ("info", "ℹ️"), ("unknown", "📝")]
|
||||
for severity, emoji in cases:
|
||||
f = {"file": "x.py", "line": 1, "text": "test", "severity": severity}
|
||||
assert emoji in format_comment(f)
|
||||
|
||||
|
||||
class TestFindingsLoader:
|
||||
def test_load_from_file(self):
|
||||
sys.path.insert(0, str(SCRIPTS_DIR))
|
||||
from review_comment_generator import load_findings
|
||||
findings = load_findings(SAMPLE_FINDINGS, from_stdin=False)
|
||||
assert len(findings) >= 4
|
||||
|
||||
def test_load_ignores_blank_and_comments(self):
|
||||
import tempfile, os
|
||||
with tempfile.NamedTemporaryFile(mode="w", suffix=".jsonl", delete=False) as tf:
|
||||
tf.write('{"file":"a.py","line":1,"text":"valid"}\n')
|
||||
tf.write('\n')
|
||||
tf.write('# this is a comment\n')
|
||||
tf.write('{"file":"b.py","line":2,"text":"also valid"}\n')
|
||||
tfname = tf.name
|
||||
try:
|
||||
sys.path.insert(0, str(SCRIPTS_DIR))
|
||||
from review_comment_generator import load_findings
|
||||
assert len(load_findings(Path(tfname), from_stdin=False)) == 2
|
||||
finally:
|
||||
os.unlink(tfname)
|
||||
|
||||
def test_invalid_json_line_skipped(self, capsys):
|
||||
import tempfile, os
|
||||
with tempfile.NamedTemporaryFile(mode="w", suffix=".jsonl", delete=False) as tf:
|
||||
tf.write('invalid json\n')
|
||||
tf.write('{"file":"ok.py","line":1,"text":"valid"}\n')
|
||||
tfname = tf.name
|
||||
try:
|
||||
sys.path.insert(0, str(SCRIPTS_DIR))
|
||||
from review_comment_generator import load_findings
|
||||
assert len(load_findings(Path(tfname), from_stdin=False)) == 1
|
||||
finally:
|
||||
os.unlink(tfname)
|
||||
|
||||
|
||||
class TestDryRunMode:
|
||||
def test_dry_run_counts_unique(self):
|
||||
result = subprocess.run(
|
||||
[sys.executable, str(GENERATOR), "--pr", "126",
|
||||
"--input", str(SAMPLE_FINDINGS), "--dry-run"],
|
||||
capture_output=True, text=True, cwd=REPO_ROOT, timeout=15
|
||||
)
|
||||
assert result.returncode == 0
|
||||
assert "DRY RUN" in result.stdout
|
||||
assert "Review Comment" in result.stdout
|
||||
|
||||
def test_dry_run_shows_all_unique(self):
|
||||
result = subprocess.run(
|
||||
[sys.executable, str(GENERATOR), "--pr", "126",
|
||||
"--input", str(SAMPLE_FINDINGS), "--dry-run"],
|
||||
capture_output=True, text=True, cwd=REPO_ROOT, timeout=15
|
||||
)
|
||||
assert result.stdout.count("--- Comment") == 4
|
||||
|
||||
|
||||
class TestJSONOutputMode:
|
||||
def test_json_flag_emits_valid_json(self):
|
||||
result = subprocess.run(
|
||||
[sys.executable, str(GENERATOR), "--pr", "126",
|
||||
"--input", str(SAMPLE_FINDINGS), "--json"],
|
||||
capture_output=True, text=True, cwd=REPO_ROOT, timeout=15
|
||||
)
|
||||
assert result.returncode == 0
|
||||
payload = json.loads(result.stdout)
|
||||
assert "total" in payload and "unique" in payload and "findings" in payload
|
||||
assert payload["total"] >= payload["unique"]
|
||||
|
||||
def test_json_findings_have_required_fields(self):
|
||||
result = subprocess.run(
|
||||
[sys.executable, str(GENERATOR), "--pr", "126",
|
||||
"--input", str(SAMPLE_FINDINGS), "--json"],
|
||||
capture_output=True, text=True, cwd=REPO_ROOT, timeout=15
|
||||
)
|
||||
payload = json.loads(result.stdout)
|
||||
for f in payload["findings"]:
|
||||
assert "file" in f and "line" in f and "text" in f
|
||||
|
||||
|
||||
class TestGiteaClient:
|
||||
def test_post_issue_comment_builds_correct_url(self):
|
||||
sys.path.insert(0, str(SCRIPTS_DIR))
|
||||
from review_comment_generator import GiteaClient
|
||||
client = GiteaClient("https://example.com", "token123", "MyOrg", "myrepo")
|
||||
assert client.org == "MyOrg" and client.repo == "myrepo"
|
||||
|
||||
def test_generate_comment_body_has_required_fields(self):
|
||||
sys.path.insert(0, str(SCRIPTS_DIR))
|
||||
from review_comment_generator import format_comment
|
||||
f = {"file": "x.py", "line": 5, "text": "Fix this", "severity": "error"}
|
||||
body = format_comment(f)
|
||||
assert "x.py" in body and "5" in body and "Fix this" in body
|
||||
|
||||
|
||||
class TestFullPipeline:
|
||||
def test_end_to_end_json_output(self):
|
||||
result = subprocess.run(
|
||||
[sys.executable, str(GENERATOR), "--pr", "126",
|
||||
"--input", str(SAMPLE_FINDINGS), "--json"],
|
||||
capture_output=True, text=True, cwd=REPO_ROOT, timeout=15
|
||||
)
|
||||
assert result.returncode == 0
|
||||
data = json.loads(result.stdout)
|
||||
assert data["total"] == 5
|
||||
assert data["unique"] == 4
|
||||
f = data["findings"][0]
|
||||
for key in ("file", "line", "text", "severity"):
|
||||
assert key in f
|
||||
|
||||
def test_token_loading_fallback(self):
|
||||
sys.path.insert(0, str(SCRIPTS_DIR))
|
||||
from review_comment_generator import load_token
|
||||
token = load_token()
|
||||
assert token is None or isinstance(token, str)
|
||||
|
||||
|
||||
class TestErrorHandling:
|
||||
def test_missing_input_shows_error(self):
|
||||
result = subprocess.run(
|
||||
[sys.executable, str(GENERATOR), "--pr", "126"],
|
||||
capture_output=True, text=True, cwd=REPO_ROOT, timeout=15
|
||||
)
|
||||
assert result.returncode != 0
|
||||
assert "--input" in result.stderr or "--stdin" in result.stderr
|
||||
|
||||
def test_invalid_json_line_skipped(self):
|
||||
import tempfile, os
|
||||
with tempfile.NamedTemporaryFile(mode="w", suffix=".jsonl", delete=False) as tf:
|
||||
tf.write('invalid json\n')
|
||||
tf.write('{"file":"ok.py","line":1,"text":"valid"}\n')
|
||||
tfname = tf.name
|
||||
try:
|
||||
result = subprocess.run(
|
||||
[sys.executable, str(GENERATOR), "--pr", "126",
|
||||
"--input", tfname, "--json"],
|
||||
capture_output=True, text=True, cwd=REPO_ROOT, timeout=15
|
||||
)
|
||||
data = json.loads(result.stdout)
|
||||
assert data["total"] == 1
|
||||
assert data["unique"] == 1
|
||||
finally:
|
||||
os.unlink(tfname)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
pytest.main([__file__, "-v"])
|
||||
Reference in New Issue
Block a user