ARCHIVE/rippled
1
0
Fork 0
mirror of https://github.com/XRPLF/rippled.git synced 2026-06-03 08:46:46 +00:00
Code Issues Packages Projects Releases Wiki Activity

github workflows

Browse Source
This commit is contained in:
Denis Angell
2026-05-13 18:21:39 +02:00
parent a761b0d43c
commit 536f87b952
9 changed files with 1358 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

277
.github/scripts/doc-coverage-check.py vendored Normal file
View File

@@ -0,0 +1,277 @@
#!/usr/bin/env python3
"""
Documentation coverage checker for xrpld.
Parses coverxygen LCOV output, compares against per-module thresholds
defined in .github/doc-coverage-thresholds.json, and generates a
markdown report suitable for posting as a PR comment.
Usage:
python3 doc-coverage-check.py \
--lcov-file doc-coverage.info \
--threshold-file .github/doc-coverage-thresholds.json \
--output doc-coverage-report.md \
[--base-lcov-file base-doc-coverage.info]
"""
import argparse
import json
import re
import sys
from collections import defaultdict
from pathlib import Path
def parse_lcov(lcov_path: str) -> dict[str, dict[str, int]]:
"""Parse LCOV-format file into per-file coverage data.
Returns a dict mapping file paths to {"documented": N, "total": N}.
"""
coverage = {}
current_file = None
documented = 0
total = 0
with open(lcov_path) as f:
for line in f:
line = line.strip()
if line.startswith("SF:"):
current_file = line[3:]
documented = 0
total = 0
elif line.startswith("DA:"):
parts = line[3:].split(",")
if len(parts) >= 2:
total += 1
if int(parts[1]) > 0:
documented += 1
elif line == "end_of_record":
if current_file:
coverage[current_file] = {
"documented": documented,
"total": total,
}
current_file = None
return coverage
def compute_module_coverage(
coverage: dict[str, dict[str, int]],
module_prefixes: list[str],
) -> dict[str, dict[str, int | float]]:
"""Aggregate file-level coverage into module-level stats."""
modules = {}
for prefix in module_prefixes:
doc = 0
tot = 0
for filepath, stats in coverage.items():
if filepath.startswith(prefix) or f"/{prefix}" in filepath:
doc += stats["documented"]
tot += stats["total"]
pct = (doc / tot * 100) if tot > 0 else 0.0
modules[prefix] = {"documented": doc, "total": tot, "percent": round(pct, 1)}
return modules
def compute_global_coverage(
coverage: dict[str, dict[str, int]],
) -> dict[str, int | float]:
"""Compute overall coverage across all files."""
doc = sum(s["documented"] for s in coverage.values())
tot = sum(s["total"] for s in coverage.values())
pct = (doc / tot * 100) if tot > 0 else 0.0
return {"documented": doc, "total": tot, "percent": round(pct, 1)}
def check_ratchet(
current: dict[str, dict[str, int | float]],
base: dict[str, dict[str, int | float]] | None,
current_global: dict[str, int | float],
base_global: dict[str, int | float] | None,
) -> list[str]:
"""Check that no module or global coverage decreased vs base branch."""
violations = []
if base_global and current_global["percent"] < base_global["percent"]:
violations.append(
f"Global coverage decreased: {base_global['percent']}% -> "
f"{current_global['percent']}%"
)
if base:
for module, stats in current.items():
if module in base and stats["percent"] < base[module]["percent"]:
violations.append(
f"`{module}` coverage decreased: "
f"{base[module]['percent']}% -> {stats['percent']}%"
)
return violations
def check_new_files(
coverage: dict[str, dict[str, int]],
new_files: list[str],
min_coverage: int,
) -> list[str]:
"""Check that new files meet minimum documentation coverage."""
violations = []
for filepath in new_files:
for covered_path, stats in coverage.items():
if filepath in covered_path or covered_path.endswith(filepath):
if stats["total"] > 0:
pct = stats["documented"] / stats["total"] * 100
if pct < min_coverage:
violations.append(
f"`{filepath}` has {pct:.0f}% doc coverage "
f"(minimum {min_coverage}%)"
)
break
return violations
def coverage_emoji(pct: float) -> str:
if pct >= 80:
return "+"
if pct >= 50:
return "~"
return "-"
def generate_report(
global_stats: dict[str, int | float],
module_stats: dict[str, dict[str, int | float]],
thresholds: dict,
violations: list[str],
new_file_violations: list[str],
) -> str:
"""Generate a markdown report for the PR comment."""
lines = []
lines.append("## Documentation Coverage Report")
lines.append("")
passed = not violations and not new_file_violations
status = "PASSED" if passed else "FAILED"
lines.append(f"**Status:** {status}")
lines.append(
f"**Global Coverage:** {global_stats['percent']}% "
f"({global_stats['documented']}/{global_stats['total']} entities documented)"
)
lines.append(
f"**Minimum Threshold:** {thresholds.get('global_minimum', 0)}%"
)
lines.append("")
if violations or new_file_violations:
lines.append("### Violations")
lines.append("")
for v in violations + new_file_violations:
lines.append(f"- {v}")
lines.append("")
lines.append("### Module Coverage")
lines.append("")
lines.append("| Module | Coverage | Documented | Total | Threshold |")
lines.append("|--------|----------|------------|-------|-----------|")
module_thresholds = thresholds.get("module_thresholds", {})
for module in sorted(module_stats.keys()):
stats = module_stats[module]
threshold = module_thresholds.get(module, 0)
emoji = coverage_emoji(stats["percent"])
lines.append(
f"| `{module}` | {stats['percent']}% | "
f"{stats['documented']} | {stats['total']} | {threshold}% |"
)
lines.append("")
lines.append(
"*Coverage measured by [coverxygen](https://github.com/psycofdj/coverxygen). "
"See [docs/DOCUMENTATION_STANDARDS.md](../docs/DOCUMENTATION_STANDARDS.md) "
"for documentation guidelines.*"
)
return "\n".join(lines)
def main():
parser = argparse.ArgumentParser(description="Check documentation coverage")
parser.add_argument("--lcov-file", required=True, help="Path to LCOV coverage file")
parser.add_argument(
"--threshold-file", required=True, help="Path to thresholds JSON"
)
parser.add_argument("--output", required=True, help="Path to write markdown report")
parser.add_argument(
"--base-lcov-file", default=None, help="Path to base branch LCOV file"
)
parser.add_argument(
"--new-files",
default="",
help="Comma-separated list of new C++ files in this PR",
)
args = parser.parse_args()
with open(args.threshold_file) as f:
thresholds = json.load(f)
coverage = parse_lcov(args.lcov_file)
module_prefixes = list(thresholds.get("module_thresholds", {}).keys())
module_stats = compute_module_coverage(coverage, module_prefixes)
global_stats = compute_global_coverage(coverage)
base_coverage = None
base_module_stats = None
base_global_stats = None
if args.base_lcov_file and Path(args.base_lcov_file).exists():
base_coverage = parse_lcov(args.base_lcov_file)
base_module_stats = compute_module_coverage(base_coverage, module_prefixes)
base_global_stats = compute_global_coverage(base_coverage)
violations = []
if global_stats["percent"] < thresholds.get("global_minimum", 0):
violations.append(
f"Global coverage {global_stats['percent']}% is below minimum "
f"{thresholds['global_minimum']}%"
)
for module, threshold in thresholds.get("module_thresholds", {}).items():
if module in module_stats and module_stats[module]["percent"] < threshold:
violations.append(
f"`{module}` coverage {module_stats[module]['percent']}% is below "
f"threshold {threshold}%"
)
if thresholds.get("ratchet_mode") == "no_decrease":
violations.extend(
check_ratchet(
module_stats, base_module_stats, global_stats, base_global_stats
)
)
new_file_violations = []
if args.new_files:
new_files = [f.strip() for f in args.new_files.split(",") if f.strip()]
new_file_min = thresholds.get("new_file_minimum", 80)
new_file_violations = check_new_files(coverage, new_files, new_file_min)
report = generate_report(
global_stats, module_stats, thresholds, violations, new_file_violations
)
with open(args.output, "w") as f:
f.write(report)
print(report)
if violations or new_file_violations:
print(f"\nFAILED: {len(violations) + len(new_file_violations)} violation(s)")
sys.exit(1)
else:
print("\nPASSED: All coverage thresholds met")
sys.exit(0)
if __name__ == "__main__":
main()

279
.github/scripts/doc-review.py vendored Normal file
View File

@@ -0,0 +1,279 @@
#!/usr/bin/env python3
"""
Diff-aware documentation review for xrpld PRs.
For each changed C++ file, extracts the diff hunks and existing doc
comments, then asks the Anthropic API whether documentation needs
updating. Produces:
- doc-review-report.md: summary comment for the PR
- doc-review-comments.json: inline review comments with file/line info
"""
import json
import os
import re
import subprocess
import sys
from dataclasses import dataclass
from pathlib import Path
try:
import anthropic
except ImportError:
print("ERROR: anthropic package not installed. Run: pip install anthropic")
sys.exit(1)
MODEL = "claude-sonnet-4-6"
MAX_TOKENS = 2048
SYSTEM_PROMPT = """You are a documentation reviewer for the xrpld (XRP Ledger daemon) C++ codebase.
Your job is to review code changes and determine whether existing documentation
comments need updating, or whether new documentation is needed.
Documentation style: Javadoc-style Doxygen comments (/** ... */).
See the project's docs/DOCUMENTATION_STANDARDS.md for full guidelines.
Rules:
- Only flag REAL semantic drift: changed behavior, new parameters, removed
functionality, changed return values, new error conditions.
- Do NOT flag cosmetic changes (whitespace, formatting, variable renames that
don't change semantics).
- Do NOT suggest docs for private implementation details unless the logic is
genuinely non-obvious.
- Do NOT paraphrase function signatures. Good docs explain WHY and WHAT
BEHAVIOR, not WHAT THE CODE LITERALLY DOES.
- Be terse. Each finding should be 1-3 sentences.
For each issue found, respond with a JSON array of objects:
{
"issues": [
{
"file": "path/to/file.h",
"line": 42,
"severity": "warning" | "suggestion",
"message": "Brief description of the doc issue",
"suggested_doc": "Optional: suggested doc comment text"
}
],
"summary": "One-paragraph summary of documentation state for this file"
}
If no issues are found, return: {"issues": [], "summary": "Documentation is up to date."}
Respond ONLY with valid JSON. No markdown fences, no explanation outside JSON."""
@dataclass
class FileAnalysis:
path: str
diff: str
existing_docs: str
file_content: str
def get_diff(base_sha: str, head_sha: str, filepath: str) -> str:
"""Get the unified diff for a specific file between two commits."""
try:
result = subprocess.run(
["git", "diff", f"{base_sha}...{head_sha}", "--", filepath],
capture_output=True,
text=True,
check=True,
)
return result.stdout
except subprocess.CalledProcessError:
return ""
def extract_doc_comments(content: str) -> str:
"""Extract all /** ... */ doc comments from file content."""
pattern = r'/\*\*[\s\S]*?\*/'
matches = re.findall(pattern, content)
return "\n\n".join(matches) if matches else "(no documentation comments found)"
def read_file_safe(filepath: str) -> str:
"""Read a file, returning empty string if it doesn't exist."""
try:
return Path(filepath).read_text(encoding="utf-8", errors="replace")
except (FileNotFoundError, PermissionError):
return ""
def analyze_file(client: anthropic.Anthropic, analysis: FileAnalysis) -> dict:
"""Send a file's diff and docs to the API for review."""
user_prompt = f"""Review the following code change for documentation accuracy.
## File: {analysis.path}
## Git Diff:
```
{analysis.diff[:8000]}
```
## Existing Documentation Comments:
```
{analysis.existing_docs[:4000]}
```
## Current File Content (first 200 lines for context):
```cpp
{chr(10).join(analysis.file_content.split(chr(10))[:200])}
```
Analyze whether the diff introduces changes that make existing docs inaccurate,
or adds new public API surface that lacks documentation."""
try:
response = client.messages.create(
model=MODEL,
max_tokens=MAX_TOKENS,
system=SYSTEM_PROMPT,
messages=[{"role": "user", "content": user_prompt}],
)
text = response.content[0].text.strip()
if text.startswith("```"):
text = re.sub(r'^```\w*\n?', '', text)
text = re.sub(r'\n?```$', '', text)
return json.loads(text)
except (json.JSONDecodeError, Exception) as e:
return {
"issues": [],
"summary": f"Analysis failed: {str(e)[:200]}",
}
def generate_report(
results: dict[str, dict],
changed_files: list[str],
) -> str:
"""Generate the markdown summary report."""
lines = ["## Documentation Review Report", ""]
total_issues = sum(len(r.get("issues", [])) for r in results.values())
warnings = sum(
1
for r in results.values()
for i in r.get("issues", [])
if i.get("severity") == "warning"
)
suggestions = total_issues - warnings
if total_issues == 0:
lines.append("No documentation issues found.")
else:
lines.append(
f"Found **{total_issues}** documentation issue(s) "
f"across **{len(changed_files)}** changed file(s): "
f"{warnings} warning(s), {suggestions} suggestion(s)."
)
lines.append("")
lines.append(f"Files reviewed: {len(changed_files)}")
lines.append("")
for filepath, result in sorted(results.items()):
issues = result.get("issues", [])
summary = result.get("summary", "")
if issues:
lines.append(f"### `{filepath}`")
lines.append("")
lines.append(summary)
lines.append("")
for issue in issues:
severity = issue.get("severity", "suggestion")
icon = "**Warning:**" if severity == "warning" else "**Suggestion:**"
line_num = issue.get("line", "?")
msg = issue.get("message", "")
lines.append(f"- {icon} Line {line_num}: {msg}")
lines.append("")
lines.append("---")
lines.append(
"*Automated documentation review. "
"See [docs/DOCUMENTATION_STANDARDS.md](../docs/DOCUMENTATION_STANDARDS.md) "
"for guidelines.*"
)
return "\n".join(lines)
def generate_inline_comments(results: dict[str, dict]) -> list[dict]:
"""Generate inline PR review comments from analysis results."""
comments = []
for filepath, result in results.items():
for issue in result.get("issues", []):
line = issue.get("line")
if not line or not isinstance(line, int):
continue
body = issue.get("message", "")
suggested = issue.get("suggested_doc")
if suggested:
body += f"\n\n**Suggested documentation:**\n```cpp\n{suggested}\n```"
severity = issue.get("severity", "suggestion")
prefix = "Doc Warning" if severity == "warning" else "Doc Suggestion"
body = f"**{prefix}:** {body}"
comments.append({"path": filepath, "line": line, "body": body})
return comments
def main():
api_key = os.environ.get("ANTHROPIC_API_KEY")
if not api_key:
print("ERROR: ANTHROPIC_API_KEY not set")
sys.exit(1)
changed_files_str = os.environ.get("CHANGED_FILES", "")
if not changed_files_str:
print("No changed files to review")
sys.exit(0)
base_sha = os.environ.get("BASE_SHA", "HEAD~1")
head_sha = os.environ.get("HEAD_SHA", "HEAD")
changed_files = [f.strip() for f in changed_files_str.split() if f.strip()]
cpp_files = [
f for f in changed_files if f.endswith((".h", ".hpp", ".cpp"))
]
if not cpp_files:
print("No C++ files changed")
sys.exit(0)
print(f"Reviewing {len(cpp_files)} file(s) for documentation accuracy...")
client = anthropic.Anthropic(api_key=api_key)
results = {}
for filepath in cpp_files:
print(f" Analyzing: {filepath}")
diff = get_diff(base_sha, head_sha, filepath)
if not diff:
continue
content = read_file_safe(filepath)
existing_docs = extract_doc_comments(content)
analysis = FileAnalysis(
path=filepath,
diff=diff,
existing_docs=existing_docs,
file_content=content,
)
results[filepath] = analyze_file(client, analysis)
report = generate_report(results, cpp_files)
Path("doc-review-report.md").write_text(report)
print("\nReport written to doc-review-report.md")
comments = generate_inline_comments(results)
Path("doc-review-comments.json").write_text(json.dumps(comments, indent=2))
print(f"Generated {len(comments)} inline comment(s)")
if __name__ == "__main__":
main()