firefrost-gaming/skill-seekers-reference
3
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

style: Run ruff format on 15 files (CI fix)

Browse Source 
CI uses 'ruff format' not 'black' - applied proper formatting:

Files reformatted by ruff:
- config_extractor.py
- doc_scraper.py
- how_to_guide_builder.py
- llms_txt_parser.py
- pattern_recognizer.py
- test_example_extractor.py
- unified_codebase_analyzer.py
- test_architecture_scenarios.py
- test_async_scraping.py
- test_github_scraper.py
- test_guide_enhancer.py
- test_install_agent.py
- test_issue_219_e2e.py
- test_llms_txt_downloader.py
- test_skip_llms_txt.py

Fixes CI formatting check failure.

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
This commit is contained in:
yusyus
2026-01-18 00:01:30 +03:00
parent 9d43956b1d
commit 85c8d9d385
15 changed files with 179 additions and 510 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
src/skill_seekers/cli/config_extractor.py
View File

@@ -89,9 +89,7 @@ class ConfigExtractionResult:
config_files: list[ConfigFile] = field(default_factory=list)
total_files: int = 0
total_settings: int = 0
detected_patterns: dict[str, list[str]] = field(
default_factory=dict
) # pattern -> files
detected_patterns: dict[str, list[str]] = field(default_factory=dict) # pattern -> files
errors: list[str] = field(default_factory=list)
def to_dict(self) -> dict:
@@ -241,9 +239,7 @@ class ConfigFileDetector:
"*.egg-info",
}
def find_config_files(
self, directory: Path, max_files: int = 100
) -> list[ConfigFile]:
def find_config_files(self, directory: Path, max_files: int = 100) -> list[ConfigFile]:
"""
Find all configuration files in directory.
@@ -314,10 +310,7 @@ class ConfigFileDetector:
filename = file_path.name.lower()
# Database configs
if any(
word in path_lower
for word in ["database", "db", "postgres", "mysql", "mongo"]
):
if any(word in path_lower for word in ["database", "db", "postgres", "mysql", "mongo"]):
return "database_configuration"
# API configs
@@ -333,9 +326,7 @@ class ConfigFileDetector:
return "docker_configuration"
# CI/CD configs
if any(
word in path_lower for word in [".travis", ".gitlab", ".github", "ci", "cd"]
):
if any(word in path_lower for word in [".travis", ".gitlab", ".github", "ci", "cd"]):
return "ci_cd_configuration"
# Package configs
@@ -347,11 +338,7 @@ class ConfigFileDetector:
return "typescript_configuration"
# Framework configs
if (
"next.config" in filename
or "vue.config" in filename
or "webpack.config" in filename
):
if "next.config" in filename or "vue.config" in filename or "webpack.config" in filename:
return "framework_configuration"
# Environment configs
@@ -531,9 +518,7 @@ class ConfigParser:
for match in re.finditer(pattern, config_file.raw_content):
if len(match.groups()) >= 2:
key = match.group(1)
value = (
match.group(3) if len(match.groups()) > 2 else match.group(2)
)
value = match.group(3) if len(match.groups()) > 2 else match.group(2)
setting = ConfigSetting(
key=key, value=value, value_type=self._infer_type(value)
@@ -579,9 +564,7 @@ class ConfigParser:
for key, value in data.items():
if isinstance(value, dict):
# Recurse into nested dicts
self._extract_settings_from_dict(
value, config_file, parent_path + [key]
)
self._extract_settings_from_dict(value, config_file, parent_path + [key])
else:
setting = ConfigSetting(
key=".".join(parent_path + [key]) if parent_path else key,
@@ -872,9 +855,7 @@ def main():
print("\n📊 Summary:")
print(f" Config files found: {result.total_files}")
print(f" Total settings: {result.total_settings}")
print(
f" Detected patterns: {', '.join(result.detected_patterns.keys()) or 'None'}"
)
print(f" Detected patterns: {', '.join(result.detected_patterns.keys()) or 'None'}")
if "ai_enhancements" in output_dict:
print(f" ✨ AI enhancements: Yes ({enhance_mode} mode)")

165
src/skill_seekers/cli/doc_scraper.py
View File

@@ -148,9 +148,7 @@ def infer_description_from_docs(
class DocToSkillConverter:
def __init__(
self, config: dict[str, Any], dry_run: bool = False, resume: bool = False
) -> None:
def __init__(self, config: dict[str, Any], dry_run: bool = False, resume: bool = False) -> None:
self.config = config
self.name = config["name"]
self.base_url = config["base_url"]
@@ -165,9 +163,7 @@ class DocToSkillConverter:
# Checkpoint config
checkpoint_config = config.get("checkpoint", {})
self.checkpoint_enabled = checkpoint_config.get("enabled", False)
self.checkpoint_interval = checkpoint_config.get(
"interval", DEFAULT_CHECKPOINT_INTERVAL
)
self.checkpoint_interval = checkpoint_config.get("interval", DEFAULT_CHECKPOINT_INTERVAL)
# llms.txt detection state
skip_llms_txt_value = config.get("skip_llms_txt", False)
@@ -322,9 +318,7 @@ class DocToSkillConverter:
for h in main.find_all(["h1", "h2", "h3", "h4", "h5", "h6"]):
text = self.clean_text(h.get_text())
if text:
page["headings"].append(
{"level": h.name, "text": text, "id": h.get("id", "")}
)
page["headings"].append({"level": h.name, "text": text, "id": h.get("id", "")})
# Extract code with language detection
code_selector = selectors.get("code_blocks", "pre code")
@@ -391,9 +385,7 @@ class DocToSkillConverter:
import re
# Detect if content is actually HTML (some .md URLs return HTML)
if content.strip().startswith("<!DOCTYPE") or content.strip().startswith(
"<html"
):
if content.strip().startswith("<!DOCTYPE") or content.strip().startswith("<html"):
return self._extract_html_as_markdown(content, url)
page = {
@@ -432,9 +424,7 @@ class DocToSkillConverter:
code_blocks = re.findall(r"```(\w+)?\n(.*?)```", content, re.DOTALL)
for lang, code in code_blocks:
if len(code.strip()) > 10:
page["code_samples"].append(
{"code": code.strip(), "language": lang or "unknown"}
)
page["code_samples"].append({"code": code.strip(), "language": lang or "unknown"})
# Extract content (paragraphs)
content_no_code = re.sub(r"```.*?```", "", content, flags=re.DOTALL)
@@ -458,11 +448,7 @@ class DocToSkillConverter:
# Strip anchor fragments
full_url = full_url.split("#")[0]
# Only include .md URLs to avoid client-side rendered HTML pages
if (
".md" in full_url
and self.is_valid_url(full_url)
and full_url not in page["links"]
):
if ".md" in full_url and self.is_valid_url(full_url) and full_url not in page["links"]:
page["links"].append(full_url)
return page
@@ -526,18 +512,14 @@ class DocToSkillConverter:
for h in main.find_all(["h1", "h2", "h3", "h4", "h5", "h6"]):
text = self.clean_text(h.get_text())
if text:
page["headings"].append(
{"level": h.name, "text": text, "id": h.get("id", "")}
)
page["headings"].append({"level": h.name, "text": text, "id": h.get("id", "")})
# Extract code blocks
for code_elem in main.select("pre code, pre"):
code = code_elem.get_text()
if len(code.strip()) > 10:
lang = self.detect_language(code_elem, code)
page["code_samples"].append(
{"code": code.strip(), "language": lang}
)
page["code_samples"].append({"code": code.strip(), "language": lang})
# Extract paragraphs
paragraphs = []
@@ -558,9 +540,7 @@ class DocToSkillConverter:
# Log low-confidence detections for debugging
if confidence < 0.5:
logger.debug(
f"Low confidence language detection: {lang} ({confidence:.2f})"
)
logger.debug(f"Low confidence language detection: {lang} ({confidence:.2f})")
return lang # Return string for backward compatibility
@@ -573,10 +553,7 @@ class DocToSkillConverter:
# Look for "Example:" or "Pattern:" sections
for elem in main.find_all(["p", "div"]):
text = elem.get_text().lower()
if any(
word in text
for word in ["example:", "pattern:", "usage:", "typical use"]
):
if any(word in text for word in ["example:", "pattern:", "usage:", "typical use"]):
# Get the code that follows
next_code = elem.find_next(["pre", "code"])
if next_code:
@@ -598,9 +575,7 @@ class DocToSkillConverter:
"""Save page data (skip pages with empty content)"""
# Skip pages with empty or very short content
if not page.get("content") or len(page.get("content", "")) < 50:
logger.debug(
"Skipping page with empty/short content: %s", page.get("url", "unknown")
)
logger.debug("Skipping page with empty/short content: %s", page.get("url", "unknown"))
return
url_hash = hashlib.md5(page["url"].encode()).hexdigest()[:10]
@@ -648,10 +623,7 @@ class DocToSkillConverter:
# Add new URLs
for link in page["links"]:
if (
link not in self.visited_urls
and link not in self.pending_urls
):
if link not in self.visited_urls and link not in self.pending_urls:
self.pending_urls.append(link)
else:
# Single-threaded mode (no lock needed)
@@ -672,9 +644,7 @@ class DocToSkillConverter:
except Exception as e:
if self.workers > 1:
with self.lock:
logger.error(
" ✗ Error scraping %s: %s: %s", url, type(e).__name__, e
)
logger.error(" ✗ Error scraping %s: %s: %s", url, type(e).__name__, e)
else:
logger.error(" ✗ Error scraping page: %s: %s", type(e).__name__, e)
logger.error(" URL: %s", url)
@@ -792,9 +762,7 @@ class DocToSkillConverter:
# Check for explicit config URL first
explicit_url = self.config.get("llms_txt_url")
if explicit_url:
logger.info(
"\n📌 Using explicit llms_txt_url from config: %s", explicit_url
)
logger.info("\n📌 Using explicit llms_txt_url from config: %s", explicit_url)
# Download explicit file first
downloader = LlmsTxtDownloader(explicit_url)
@@ -915,9 +883,7 @@ class DocToSkillConverter:
logger.info(" ✓ %s (%d chars)", filename, len(content))
if not downloaded:
logger.warning(
"⚠️ Failed to download any variants, falling back to HTML scraping"
)
logger.warning("⚠️ Failed to download any variants, falling back to HTML scraping")
return False
# Save ALL variants to references/
@@ -1032,9 +998,7 @@ class DocToSkillConverter:
# Single-threaded mode (original sequential logic)
if self.workers <= 1:
while self.pending_urls and (
unlimited or len(self.visited_urls) < preview_limit
):
while self.pending_urls and (unlimited or len(self.visited_urls) < preview_limit):
url = self.pending_urls.popleft()
if url in self.visited_urls:
@@ -1046,9 +1010,7 @@ class DocToSkillConverter:
# Just show what would be scraped
logger.info(" [Preview] %s", url)
try:
headers = {
"User-Agent": "Mozilla/5.0 (Documentation Scraper - Dry Run)"
}
headers = {"User-Agent": "Mozilla/5.0 (Documentation Scraper - Dry Run)"}
response = requests.get(url, headers=headers, timeout=10)
soup = BeautifulSoup(response.content, "html.parser")
@@ -1060,16 +1022,11 @@ class DocToSkillConverter:
if main:
for link in main.find_all("a", href=True):
href = urljoin(url, link["href"])
if (
self.is_valid_url(href)
and href not in self.visited_urls
):
if self.is_valid_url(href) and href not in self.visited_urls:
self.pending_urls.append(href)
except Exception as e:
# Failed to extract links in fast mode, continue anyway
logger.warning(
"⚠️ Warning: Could not extract links from %s: %s", url, e
)
logger.warning("⚠️ Warning: Could not extract links from %s: %s", url, e)
else:
self.scrape_page(url)
self.pages_scraped += 1
@@ -1092,9 +1049,7 @@ class DocToSkillConverter:
with ThreadPoolExecutor(max_workers=self.workers) as executor:
futures = []
while self.pending_urls and (
unlimited or len(self.visited_urls) < preview_limit
):
while self.pending_urls and (unlimited or len(self.visited_urls) < preview_limit):
# Get next batch of URLs (thread-safe)
batch = []
batch_size = min(self.workers * 2, len(self.pending_urls))
@@ -1152,9 +1107,7 @@ class DocToSkillConverter:
self.pages_scraped += 1
if self.dry_run:
logger.info(
"\n✅ Dry run complete: would scrape ~%d pages", len(self.visited_urls)
)
logger.info("\n✅ Dry run complete: would scrape ~%d pages", len(self.visited_urls))
if len(self.visited_urls) >= preview_limit:
logger.info(
" (showing first %d, actual scraping may find more)",
@@ -1221,9 +1174,7 @@ class DocToSkillConverter:
) as client:
tasks = []
while self.pending_urls and (
unlimited or len(self.visited_urls) < preview_limit
):
while self.pending_urls and (unlimited or len(self.visited_urls) < preview_limit):
# Get next batch of URLs
batch = []
batch_size = min(self.workers * 2, len(self.pending_urls))
@@ -1271,9 +1222,7 @@ class DocToSkillConverter:
await asyncio.gather(*tasks, return_exceptions=True)
if self.dry_run:
logger.info(
"\n✅ Dry run complete: would scrape ~%d pages", len(self.visited_urls)
)
logger.info("\n✅ Dry run complete: would scrape ~%d pages", len(self.visited_urls))
if len(self.visited_urls) >= preview_limit:
logger.info(
" (showing first %d, actual scraping may find more)",
@@ -1323,9 +1272,7 @@ class DocToSkillConverter:
return pages
def smart_categorize(
self, pages: list[dict[str, Any]]
) -> dict[str, list[dict[str, Any]]]:
def smart_categorize(self, pages: list[dict[str, Any]]) -> dict[str, list[dict[str, Any]]]:
"""Improved categorization with better pattern matching"""
category_defs = self.config.get("categories", {})
@@ -1377,18 +1324,14 @@ class DocToSkillConverter:
for page in pages:
path = urlparse(page["url"]).path
segments = [
s
for s in path.split("/")
if s and s not in ["en", "stable", "latest", "docs"]
s for s in path.split("/") if s and s not in ["en", "stable", "latest", "docs"]
]
for seg in segments:
url_segments[seg] += 1
# Top segments become categories
top_segments = sorted(url_segments.items(), key=lambda x: x[1], reverse=True)[
:8
]
top_segments = sorted(url_segments.items(), key=lambda x: x[1], reverse=True)[:8]
categories = {}
for seg, count in top_segments:
@@ -1408,9 +1351,7 @@ class DocToSkillConverter:
return categories
def generate_quick_reference(
self, pages: list[dict[str, Any]]
) -> list[dict[str, str]]:
def generate_quick_reference(self, pages: list[dict[str, Any]]) -> list[dict[str, str]]:
"""Generate quick reference from common patterns (NEW FEATURE)"""
quick_ref = []
@@ -1492,9 +1433,7 @@ class DocToSkillConverter:
if pages:
first_page_html = pages[0].get("raw_html", "")
break
description = infer_description_from_docs(
self.base_url, first_page_html, self.name
)
description = infer_description_from_docs(self.base_url, first_page_html, self.name)
else:
description = self.config["description"]
@@ -1502,9 +1441,7 @@ class DocToSkillConverter:
example_codes = []
for pages in categories.values():
for page in pages[:3]: # First 3 pages per category
for sample in page.get("code_samples", [])[
:2
]: # First 2 samples per page
for sample in page.get("code_samples", [])[:2]: # First 2 samples per page
code = sample.get("code", sample if isinstance(sample, str) else "")
lang = sample.get("language", "unknown")
if len(code) < 200 and lang != "unknown":
@@ -1554,9 +1491,7 @@ This skill should be triggered when:
content += pattern.get("code", "")[:300]
content += "\n```\n\n"
else:
content += (
"*Quick reference patterns will be added as you use the skill.*\n\n"
)
content += "*Quick reference patterns will be added as you use the skill.*\n\n"
# Add example codes from docs
if example_codes:
@@ -1571,9 +1506,7 @@ This skill includes comprehensive documentation in `references/`:
"""
for cat in sorted(categories.keys()):
content += (
f"- **{cat}.md** - {cat.replace('_', ' ').title()} documentation\n"
)
content += f"- **{cat}.md** - {cat.replace('_', ' ').title()} documentation\n"
content += """
Use `view` to read specific reference files when detailed information is needed.
@@ -1721,9 +1654,7 @@ def validate_config(config: dict[str, Any]) -> tuple[list[str], list[str]]:
)
# Validate base_url
if "base_url" in config and not config["base_url"].startswith(
("http://", "https://")
):
if "base_url" in config and not config["base_url"].startswith(("http://", "https://")):
errors.append(
f"Invalid base_url: '{config['base_url']}' (must start with http:// or https://)"
)
@@ -1840,18 +1771,12 @@ def load_config(config_path: str) -> dict[str, Any]:
except json.JSONDecodeError as e:
logger.error("❌ Error: Invalid JSON in config file: %s", config_path)
logger.error(" Details: %s", e)
logger.error(
" Suggestion: Check syntax at line %d, column %d", e.lineno, e.colno
)
logger.error(" Suggestion: Check syntax at line %d, column %d", e.lineno, e.colno)
sys.exit(1)
except FileNotFoundError:
logger.error("❌ Error: Config file not found: %s", config_path)
logger.error(
" Suggestion: Create a config file or use an existing one from configs/"
)
logger.error(
" Available configs: react.json, vue.json, django.json, godot.json"
)
logger.error(" Suggestion: Create a config file or use an existing one from configs/")
logger.error(" Available configs: react.json, vue.json, django.json, godot.json")
sys.exit(1)
# Validate config
@@ -1869,9 +1794,7 @@ def load_config(config_path: str) -> dict[str, Any]:
logger.error("❌ Configuration validation errors in %s:", config_path)
for error in errors:
logger.error(" - %s", error)
logger.error(
"\n Suggestion: Fix the above errors or check configs/ for working examples"
)
logger.error("\n Suggestion: Fix the above errors or check configs/ for working examples")
sys.exit(1)
return config
@@ -2025,9 +1948,7 @@ def setup_argument_parser() -> argparse.ArgumentParser:
action="store_true",
help="Resume from last checkpoint (for interrupted scrapes)",
)
parser.add_argument(
"--fresh", action="store_true", help="Clear checkpoint and start fresh"
)
parser.add_argument("--fresh", action="store_true", help="Clear checkpoint and start fresh")
parser.add_argument(
"--rate-limit",
"-r",
@@ -2126,15 +2047,11 @@ def get_configuration(args: argparse.Namespace) -> dict[str, Any]:
if args.workers:
# Validate workers count
if args.workers < 1:
logger.error(
"❌ Error: --workers must be at least 1 (got %d)", args.workers
)
logger.error("❌ Error: --workers must be at least 1 (got %d)", args.workers)
logger.error(" Suggestion: Use --workers 1 (default) or omit the flag")
sys.exit(1)
if args.workers > 10:
logger.warning(
"⚠️ Warning: --workers capped at 10 (requested %d)", args.workers
)
logger.warning("⚠️ Warning: --workers capped at 10 (requested %d)", args.workers)
args.workers = 10
config["workers"] = args.workers
if args.workers > 1:
@@ -2336,9 +2253,7 @@ def execute_enhancement(config: dict[str, Any], args: argparse.Namespace) -> Non
# Suggest enhancement if not done
if not args.enhance and not args.enhance_local:
logger.info("\n💡 Optional: Enhance SKILL.md with Claude:")
logger.info(
" Local (recommended): skill-seekers-enhance output/%s/", config["name"]
)
logger.info(" Local (recommended): skill-seekers-enhance output/%s/", config["name"])
logger.info(" or re-run with: --enhance-local")
logger.info(
" API-based: skill-seekers-enhance-api output/%s/",

53
src/skill_seekers/cli/how_to_guide_builder.py
View File

@@ -79,9 +79,7 @@ class WorkflowStep:
setup_required: str | None = None
explanation: str | None = None # Why this step matters
common_pitfall: str | None = None # Warning for this step
common_variations: list[str] = field(
default_factory=list
) # AI: Alternative approaches
common_variations: list[str] = field(default_factory=list) # AI: Alternative approaches
@dataclass
@@ -223,9 +221,7 @@ class WorkflowAnalyzer:
# Check if next statement is assertion (verification)
idx = statements.index(stmt)
verification = None
if idx + 1 < len(statements) and isinstance(
statements[idx + 1], ast.Assert
):
if idx + 1 < len(statements) and isinstance(statements[idx + 1], ast.Assert):
verification = ast.get_source_segment(code, statements[idx + 1])
steps.append(
@@ -244,9 +240,7 @@ class WorkflowAnalyzer:
return steps
def _extract_steps_heuristic(
self, code: str, _workflow: dict
) -> list[WorkflowStep]:
def _extract_steps_heuristic(self, code: str, _workflow: dict) -> list[WorkflowStep]:
"""Extract steps using heuristics (for non-Python or invalid syntax)"""
steps = []
lines = code.split("\n")
@@ -282,9 +276,7 @@ class WorkflowAnalyzer:
step_code = "\n".join(current_step)
description = self._infer_description_from_code(step_code)
steps.append(
WorkflowStep(
step_number=step_num, code=step_code, description=description
)
WorkflowStep(step_number=step_num, code=step_code, description=description)
)
return steps
@@ -454,9 +446,7 @@ class WorkflowGrouper:
groups = self._group_by_file_path(workflows)
return groups
def _group_by_ai_tutorial_group(
self, workflows: list[dict]
) -> dict[str, list[dict]]:
def _group_by_ai_tutorial_group(self, workflows: list[dict]) -> dict[str, list[dict]]:
"""Group by AI-generated tutorial_group (from C3.6 enhancement)"""
groups = defaultdict(list)
ungrouped = []
@@ -914,9 +904,7 @@ class HowToGuideBuilder:
"""Filter to workflow category only"""
return [ex for ex in examples if ex.get("category") == "workflow"]
def _create_guide(
self, title: str, workflows: list[dict], enhancer=None
) -> HowToGuide:
def _create_guide(self, title: str, workflows: list[dict], enhancer=None) -> HowToGuide:
"""
Generate single guide from workflow(s).
@@ -974,18 +962,14 @@ class HowToGuideBuilder:
# Add AI enhancements if enhancer is available
if enhancer:
self._enhance_guide_with_ai(
guide, primary_workflow.get("ai_analysis", {}), enhancer
)
self._enhance_guide_with_ai(guide, primary_workflow.get("ai_analysis", {}), enhancer)
elif self.enhance_with_ai and primary_workflow.get("ai_analysis"):
# Fallback to old enhancement method (basic)
self._enhance_guide_with_ai_basic(guide, primary_workflow["ai_analysis"])
return guide
def _generate_overview(
self, primary_workflow: dict, _all_workflows: list[dict]
) -> str:
def _generate_overview(self, primary_workflow: dict, _all_workflows: list[dict]) -> str:
"""Generate guide overview"""
# Try to get explanation from AI analysis
if primary_workflow.get("ai_analysis"):
@@ -1019,10 +1003,7 @@ class HowToGuideBuilder:
# Prepare guide data for enhancer
guide_data = {
"title": guide.title,
"steps": [
{"description": step.description, "code": step.code}
for step in guide.steps
],
"steps": [{"description": step.description, "code": step.code} for step in guide.steps],
"language": "python", # TODO: Detect from code
"prerequisites": guide.prerequisites,
"description": guide.overview,
@@ -1055,9 +1036,7 @@ class HowToGuideBuilder:
if "use_cases" in enhanced_data:
guide.use_cases = enhanced_data["use_cases"]
logger.info(
f"✨ Enhanced guide '{guide.title}' with comprehensive AI improvements"
)
logger.info(f"✨ Enhanced guide '{guide.title}' with comprehensive AI improvements")
def _enhance_guide_with_ai_basic(self, guide: HowToGuide, ai_analysis: dict):
"""
@@ -1122,9 +1101,7 @@ class HowToGuideBuilder:
for guide in guides:
# Generate filename from title
filename = (
guide.title.lower().replace(" ", "-").replace(":", "") + ".md"
)
filename = guide.title.lower().replace(" ", "-").replace(":", "") + ".md"
file_path = use_case_dir / filename
# Generate and save markdown
@@ -1135,9 +1112,7 @@ class HowToGuideBuilder:
index_markdown = self.generator.generate_index(collection.guides)
(output_dir / "index.md").write_text(index_markdown, encoding="utf-8")
logger.info(
f"✅ Saved {collection.total_guides} guides + index to {output_dir}"
)
logger.info(f"✅ Saved {collection.total_guides} guides + index to {output_dir}")
# ============================================================================
@@ -1244,9 +1219,7 @@ Grouping Strategies:
# Extract from directory using test example extractor
print("⚠️ Directory input requires test example extractor")
print(" Please use test_examples.json output from C3.2")
print(
f" Or run: skill-seekers extract-test-examples {input_path} --json > examples.json"
)
print(f" Or run: skill-seekers extract-test-examples {input_path} --json > examples.json")
sys.exit(1)
else:

8
src/skill_seekers/cli/llms_txt_parser.py
View File

@@ -127,9 +127,7 @@ class LlmsTxtParser:
# Extract code blocks
code_blocks = re.findall(r"```(\w+)?\n(.*?)```", content, re.DOTALL)
for lang, code in code_blocks:
page["code_samples"].append(
{"code": code.strip(), "language": lang or "unknown"}
)
page["code_samples"].append({"code": code.strip(), "language": lang or "unknown"})
# Extract h2/h3 headings
headings = re.findall(r"^(#{2,3})\s+(.+)$", content, re.MULTILINE)
@@ -146,9 +144,7 @@ class LlmsTxtParser:
content_no_code = re.sub(r"```.*?```", "", content, flags=re.DOTALL)
# Extract paragraphs
paragraphs = [
p.strip() for p in content_no_code.split("\n\n") if len(p.strip()) > 20
]
paragraphs = [p.strip() for p in content_no_code.split("\n\n") if len(p.strip()) > 20]
page["content"] = "\n\n".join(paragraphs)
return page

62
src/skill_seekers/cli/pattern_recognizer.py
View File

@@ -237,9 +237,7 @@ class PatternRecognizer:
self.detectors.append(TemplateMethodDetector(self.depth))
self.detectors.append(ChainOfResponsibilityDetector(self.depth))
def analyze_file(
self, file_path: str, content: str, language: str
) -> PatternReport:
def analyze_file(self, file_path: str, content: str, language: str) -> PatternReport:
"""
Analyze a single file for design patterns.
@@ -581,9 +579,7 @@ class FactoryDetector(BasePatternDetector):
# Check if multiple factory methods exist (Abstract Factory pattern)
if len(factory_methods) >= 2:
evidence.append(
f"Multiple factory methods: {', '.join(factory_methods[:3])}"
)
evidence.append(f"Multiple factory methods: {', '.join(factory_methods[:3])}")
confidence += 0.2
# Check for inheritance (factory hierarchy)
@@ -800,35 +796,25 @@ class StrategyDetector(BasePatternDetector):
]
if siblings:
evidence.append(
f"Part of strategy family with: {', '.join(siblings[:3])}"
)
evidence.append(f"Part of strategy family with: {', '.join(siblings[:3])}")
confidence += 0.5
if base_class and (
"strategy" in base_class.lower() or "policy" in base_class.lower()
):
if base_class and ("strategy" in base_class.lower() or "policy" in base_class.lower()):
evidence.append(f"Inherits from strategy base: {base_class}")
confidence += 0.3
# Check if this is a strategy base class
# (has subclasses in same file)
subclasses = [
cls.name for cls in all_classes if class_sig.name in cls.base_classes
]
subclasses = [cls.name for cls in all_classes if class_sig.name in cls.base_classes]
if len(subclasses) >= 2:
evidence.append(
f"Strategy base with implementations: {', '.join(subclasses[:3])}"
)
evidence.append(f"Strategy base with implementations: {', '.join(subclasses[:3])}")
confidence += 0.6
# Check for single dominant method (strategy interface)
if len(class_sig.methods) == 1 or len(class_sig.methods) == 2:
# Single method or method + __init__
main_method = [
m for m in class_sig.methods if m.name not in ["__init__", "__new__"]
]
main_method = [m for m in class_sig.methods if m.name not in ["__init__", "__new__"]]
if main_method:
evidence.append(f"Strategy interface method: {main_method[0].name}")
confidence += 0.2
@@ -939,8 +925,7 @@ class DecoratorDetector(BasePatternDetector):
if init_method and len(init_method.parameters) > 1: # More than just 'self'
param_names = [p.name for p in init_method.parameters if p.name != "self"]
if any(
name in ["wrapped", "component", "inner", "obj", "target"]
for name in param_names
name in ["wrapped", "component", "inner", "obj", "target"] for name in param_names
):
evidence.append(f"Takes wrapped object in constructor: {param_names}")
confidence += 0.4
@@ -1298,9 +1283,7 @@ class TemplateMethodDetector(BasePatternDetector):
class_lower = class_sig.name.lower()
if any(keyword in class_lower for keyword in template_keywords):
# Check if has subclasses
subclasses = [
cls.name for cls in all_classes if class_sig.name in cls.base_classes
]
subclasses = [cls.name for cls in all_classes if class_sig.name in cls.base_classes]
if subclasses:
return PatternInstance(
@@ -1310,9 +1293,7 @@ class TemplateMethodDetector(BasePatternDetector):
location="",
class_name=class_sig.name,
line_number=class_sig.line_number,
evidence=[
f"Abstract base with subclasses: {', '.join(subclasses[:2])}"
],
evidence=[f"Abstract base with subclasses: {', '.join(subclasses[:2])}"],
related_classes=subclasses,
)
@@ -1329,9 +1310,7 @@ class TemplateMethodDetector(BasePatternDetector):
# 3. Has template method that orchestrates
# Check for subclasses
subclasses = [
cls.name for cls in all_classes if class_sig.name in cls.base_classes
]
subclasses = [cls.name for cls in all_classes if class_sig.name in cls.base_classes]
if len(subclasses) >= 1:
evidence.append(f"Base class with {len(subclasses)} implementations")
@@ -1467,8 +1446,7 @@ class ChainOfResponsibilityDetector(BasePatternDetector):
# Check for set_next() method
has_set_next = any(
"next" in m.name.lower()
and ("set" in m.name.lower() or "add" in m.name.lower())
"next" in m.name.lower() and ("set" in m.name.lower() or "add" in m.name.lower())
for m in class_sig.methods
)
@@ -1489,9 +1467,7 @@ class ChainOfResponsibilityDetector(BasePatternDetector):
]
if siblings and has_next_ref:
evidence.append(
f"Part of handler chain with: {', '.join(siblings[:2])}"
)
evidence.append(f"Part of handler chain with: {', '.join(siblings[:2])}")
confidence += 0.2
if confidence >= 0.5:
@@ -1590,9 +1566,7 @@ class LanguageAdapter:
pattern.evidence.append("Abstract Factory pattern")
# Template Method: Abstract classes common
elif (
pattern.pattern_type == "TemplateMethod" and "abstract" in evidence_str
):
elif pattern.pattern_type == "TemplateMethod" and "abstract" in evidence_str:
pattern.confidence = min(pattern.confidence + 0.1, 1.0)
# Go adaptations
@@ -1645,9 +1619,7 @@ class LanguageAdapter:
pattern.evidence.append("Ruby Singleton module")
# Builder: Method chaining is idiomatic
elif (
pattern.pattern_type == "Builder" and "method chaining" in evidence_str
):
elif pattern.pattern_type == "Builder" and "method chaining" in evidence_str:
pattern.confidence = min(pattern.confidence + 0.05, 1.0)
# PHP adaptations
@@ -1702,9 +1674,7 @@ Supported Languages:
action="append",
help="Source file to analyze (can be specified multiple times)",
)
parser.add_argument(
"--directory", help="Directory to analyze (analyzes all source files)"
)
parser.add_argument("--directory", help="Directory to analyze (analyzes all source files)")
parser.add_argument(
"--output", help="Output directory for results (default: current directory)"
)

61
src/skill_seekers/cli/test_example_extractor.py
View File

@@ -194,15 +194,11 @@ class PythonTestAnalyzer:
for node in ast.walk(tree):
if isinstance(node, ast.ClassDef):
if self._is_test_class(node):
examples.extend(
self._extract_from_test_class(node, file_path, imports)
)
examples.extend(self._extract_from_test_class(node, file_path, imports))
# Find test functions (pytest)
elif isinstance(node, ast.FunctionDef) and self._is_test_function(node):
examples.extend(
self._extract_from_test_function(node, file_path, imports)
)
examples.extend(self._extract_from_test_function(node, file_path, imports))
return examples
@@ -236,9 +232,7 @@ class PythonTestAnalyzer:
return True
# Has @pytest.mark decorator
for decorator in node.decorator_list:
if isinstance(decorator, ast.Attribute) and "pytest" in ast.unparse(
decorator
):
if isinstance(decorator, ast.Attribute) and "pytest" in ast.unparse(decorator):
return True
return False
@@ -255,9 +249,7 @@ class PythonTestAnalyzer:
for node in class_node.body:
if isinstance(node, ast.FunctionDef) and node.name.startswith("test_"):
examples.extend(
self._analyze_test_body(
node, file_path, imports, setup_code=setup_code
)
self._analyze_test_body(node, file_path, imports, setup_code=setup_code)
)
return examples
@@ -269,9 +261,7 @@ class PythonTestAnalyzer:
# Check for fixture parameters
fixture_setup = self._extract_fixtures(func_node)
return self._analyze_test_body(
func_node, file_path, imports, setup_code=fixture_setup
)
return self._analyze_test_body(func_node, file_path, imports, setup_code=fixture_setup)
def _extract_setup_method(self, class_node: ast.ClassDef) -> str | None:
"""Extract setUp method code"""
@@ -328,9 +318,7 @@ class PythonTestAnalyzer:
examples.extend(configs)
# 4. Multi-step workflows (integration tests)
workflows = self._find_workflows(
func_node, file_path, docstring, setup_code, tags, imports
)
workflows = self._find_workflows(func_node, file_path, docstring, setup_code, tags, imports)
examples.extend(workflows)
return examples
@@ -491,9 +479,7 @@ class PythonTestAnalyzer:
code=code,
language="Python",
description=f"Configuration example: {description}",
expected_behavior=self._extract_assertion_after(
func_node, node
),
expected_behavior=self._extract_assertion_after(func_node, node),
setup_code=setup_code,
file_path=file_path,
line_start=node.lineno,
@@ -594,9 +580,7 @@ class PythonTestAnalyzer:
integration_keywords = ["workflow", "integration", "end_to_end", "e2e", "full"]
return any(keyword in test_name for keyword in integration_keywords)
def _extract_assertion_after(
self, func_node: ast.FunctionDef, target_node: ast.AST
) -> str:
def _extract_assertion_after(self, func_node: ast.FunctionDef, target_node: ast.AST) -> str:
"""Find assertion that follows the target node"""
found_target = False
for stmt in func_node.body:
@@ -727,8 +711,7 @@ class GenericTestAnalyzer:
code=config_match.group(0),
language=language,
file_path=file_path,
line_number=code[: start_pos + config_match.start()].count("\n")
+ 1,
line_number=code[: start_pos + config_match.start()].count("\n") + 1,
)
examples.append(example)
@@ -871,9 +854,7 @@ class TestExampleExtractor:
logger.warning(f"⚠️ Failed to initialize AI enhancer: {e}")
self.enhance_with_ai = False
def extract_from_directory(
self, directory: Path, recursive: bool = True
) -> ExampleReport:
def extract_from_directory(self, directory: Path, recursive: bool = True) -> ExampleReport:
"""Extract examples from all test files in directory"""
directory = Path(directory)
@@ -927,13 +908,11 @@ class TestExampleExtractor:
# Limit per file
if len(filtered_examples) > self.max_per_file:
# Sort by confidence and take top N
filtered_examples = sorted(
filtered_examples, key=lambda x: x.confidence, reverse=True
)[: self.max_per_file]
filtered_examples = sorted(filtered_examples, key=lambda x: x.confidence, reverse=True)[
: self.max_per_file
]
logger.info(
f"Extracted {len(filtered_examples)} examples from {file_path.name}"
)
logger.info(f"Extracted {len(filtered_examples)} examples from {file_path.name}")
return filtered_examples
@@ -988,9 +967,7 @@ class TestExampleExtractor:
# Calculate averages
avg_complexity = (
sum(ex.complexity_score for ex in examples) / len(examples)
if examples
else 0.0
sum(ex.complexity_score for ex in examples) / len(examples) if examples else 0.0
)
high_value_count = sum(1 for ex in examples if ex.confidence > 0.7)
@@ -1050,9 +1027,7 @@ Examples:
help="Maximum examples per file (default: 10)",
)
parser.add_argument("--json", action="store_true", help="Output JSON format")
parser.add_argument(
"--markdown", action="store_true", help="Output Markdown format"
)
parser.add_argument("--markdown", action="store_true", help="Output Markdown format")
parser.add_argument(
"--recursive",
action="store_true",
@@ -1079,9 +1054,7 @@ Examples:
examples = extractor.extract_from_file(Path(args.file))
report = extractor._create_report(examples, file_path=args.file)
else:
report = extractor.extract_from_directory(
Path(args.directory), recursive=args.recursive
)
report = extractor.extract_from_directory(Path(args.directory), recursive=args.recursive)
# Output results
if args.json:

28
src/skill_seekers/cli/unified_codebase_analyzer.py
View File

@@ -124,9 +124,7 @@ class UnifiedCodebaseAnalyzer:
AnalysisResult with all 3 streams
"""
# Use three-stream fetcher
fetcher = GitHubThreeStreamFetcher(
repo_url, self.github_token, interactive=interactive
)
fetcher = GitHubThreeStreamFetcher(repo_url, self.github_token, interactive=interactive)
three_streams = fetcher.fetch(output_dir)
# Analyze code with specified depth
@@ -245,9 +243,7 @@ class UnifiedCodebaseAnalyzer:
basic = self.basic_analysis(directory)
# Run full C3.x analysis using existing codebase_scraper
print(
"🔍 Running C3.x components (patterns, examples, guides, configs, architecture)..."
)
print("🔍 Running C3.x components (patterns, examples, guides, configs, architecture)...")
try:
# Import codebase analyzer
@@ -282,19 +278,11 @@ class UnifiedCodebaseAnalyzer:
c3x = {**basic, "analysis_type": "c3x", **c3x_data}
print("✅ C3.x analysis complete!")
print(
f" - {len(c3x_data.get('c3_1_patterns', []))} design patterns detected"
)
print(
f" - {c3x_data.get('c3_2_examples_count', 0)} test examples extracted"
)
print(
f" - {len(c3x_data.get('c3_3_guides', []))} how-to guides generated"
)
print(f" - {len(c3x_data.get('c3_1_patterns', []))} design patterns detected")
print(f" - {c3x_data.get('c3_2_examples_count', 0)} test examples extracted")
print(f" - {len(c3x_data.get('c3_3_guides', []))} how-to guides generated")
print(f" - {len(c3x_data.get('c3_4_configs', []))} config files analyzed")
print(
f" - {len(c3x_data.get('c3_7_architecture', []))} architectural patterns found"
)
print(f" - {len(c3x_data.get('c3_7_architecture', []))} architectural patterns found")
return c3x
@@ -451,9 +439,7 @@ class UnifiedCodebaseAnalyzer:
if item.is_dir():
# Only include immediate subdirectories
structure["children"].append(
{"name": item.name, "type": "directory"}
)
structure["children"].append({"name": item.name, "type": "directory"})
elif item.is_file():
structure["children"].append(
{"name": item.name, "type": "file", "extension": item.suffix}