Files
xiaobai-review/tools/build_architecture_inventory.py

340 lines
15 KiB
Python

from __future__ import annotations
import argparse
import ast
import json
import re
from pathlib import Path
from typing import Any
ROOT = Path(__file__).resolve().parents[1]
OUTPUT = ROOT / "config" / "architecture-inventory.json"
def relative(path: Path) -> str:
return path.relative_to(ROOT).as_posix()
def source(path: str) -> str:
return (ROOT / path).read_text(encoding="utf-8")
def page_inventory(html: str) -> list[dict[str, str]]:
items: list[dict[str, str]] = []
seen: set[str] = set()
pattern = re.compile(
r'<button[^>]+data-view="(?P<id>[^"]+)"[^>]+title="(?P<title>[^"]+)"',
re.IGNORECASE,
)
for match in pattern.finditer(html):
page_id = match.group("id")
if page_id in seen:
continue
seen.add(page_id)
items.append({"id": page_id, "title": match.group("title")})
return items
def api_inventory(server: str) -> dict[str, list[str]]:
routes = json.loads(source("config/api.config.json"))["routes"]
exact = sorted(
{item["path"] for item in routes if item["match"] == "exact"}
)
prefixes = sorted(
set(re.findall(r'parsed\.path\.startswith\(\s*"(/api/[^"]+)"', server))
)
patterns = sorted(
{item["path"] for item in routes if item["match"] == "regex"}
)
return {"exact": exact, "prefixes": prefixes, "patterns": patterns}
def database_inventory(sources: list[str]) -> list[str]:
tables: list[str] = []
for database in sources:
tables.extend(
re.findall(
r"CREATE TABLE IF NOT EXISTS\s+([a-zA-Z0-9_]+)", database
)
)
return list(dict.fromkeys(tables))
def python_functions(path: str, prefixes: tuple[str, ...]) -> list[str]:
tree = ast.parse(source(path), filename=path)
result: list[str] = []
for node in ast.walk(tree):
if isinstance(node, (ast.FunctionDef, ast.AsyncFunctionDef)) and node.name.startswith(prefixes):
result.append(node.name)
return sorted(set(result))
def css_layers(html: str) -> list[str]:
return re.findall(r'<link[^>]+rel="stylesheet"[^>]+href="([^"]+)"', html)
def frontend_fragments(registry: str) -> list[str]:
return re.findall(
r'^\s*\["[^"]+", "(/pages/[^"]+/page\.html(?:\?[^"]*)?)", \[',
registry,
re.MULTILINE,
)
def source_metrics(path: Path) -> dict[str, int]:
text = path.read_text(encoding="utf-8")
return {
"bytes": len(text.encode("utf-8")),
"lines": len(text.splitlines()),
}
def code_hotspots() -> list[dict[str, Any]]:
candidates = [
"backend/application.py",
"backend/http/dispatch.py",
"backend/features/system/service.py",
"backend/features/accounts/application.py",
"backend/jobs/service.py",
"database.py",
"backend/features/screener/engine.py",
"backend/features/screener/catalog.py",
"backend/features/screener/data_sync.py",
"backend/features/screener/indicators.py",
"backend/features/screener/factors.py",
"backend/features/screener/formula.py",
"backend/features/screener/regime.py",
"backend/features/screener/selection.py",
"backend/features/screener/backtest.py",
"backend/features/market/insights.py",
"backend/features/market/insights_context.py",
"backend/features/market/insights_auction_scoring.py",
"backend/features/market/insights_auction_data.py",
"backend/features/market/insights_auction.py",
"backend/features/market/insights_themes.py",
"backend/features/market/insights_popularity.py",
"backend/data/providers/tushare_client.py",
"backend/data/providers/tushare_transport.py",
"backend/data/providers/tushare_helpers.py",
"backend/data/providers/tushare_dashboard.py",
"backend/data/providers/tushare_indices.py",
"backend/data/providers/tushare_industries.py",
"backend/data/providers/tushare_sectors.py",
"backend/data/providers/tushare_dragon_tiger.py",
"backend/data/providers/tushare_stocks.py",
"backend/data/providers/tushare_daily.py",
"backend/features/heaven/service.py",
"backend/features/heaven/manual.py",
"backend/features/heaven/trend.py",
"backend/features/heaven/market_context.py",
"backend/features/heaven/readings.py",
"backend/features/heaven/engine.py",
"frontend/index.html",
"frontend/bootstrap.js",
"frontend/pages.config.js",
"frontend/app.js",
"frontend/shared/context.js",
"frontend/shared/application.js",
"frontend/shared/feedback.js",
"frontend/shared/dashboard.js",
"frontend/shared/session.js",
"frontend/shared/admin.js",
"frontend/shared/theme.js",
"frontend/shared/table.js",
"frontend/pages/heaven/foundation.css",
"frontend/pages/screener/foundation.css",
"frontend/pages/auction/foundation.css",
"frontend/shared/shell.css",
"frontend/pages/heaven/page.js",
]
candidates.extend(
relative(path)
for path in sorted((ROOT / "frontend" / "pages" / "market").glob("*.js"))
)
candidates.extend(
relative(path)
for path in sorted((ROOT / "backend" / "features").glob("*/routes.py"))
)
candidates.extend(
relative(path)
for path in sorted((ROOT / "frontend" / "pages").glob("*/page.html"))
)
rows = []
for name in candidates:
path = ROOT / name
if not path.is_file():
continue
rows.append({"path": name, **source_metrics(path)})
return sorted(rows, key=lambda item: item["bytes"], reverse=True)
def build() -> dict[str, Any]:
html = source("frontend/index.html")
page_registry = source("frontend/pages.config.js")
fragments = frontend_fragments(page_registry)
http_sources = [source("backend/http/dispatch.py")]
http_sources.extend(
path.read_text(encoding="utf-8")
for path in sorted((ROOT / "backend" / "features").glob("*/routes.py"))
)
server = "\n".join(http_sources)
database_sources = [source("database.py")]
database_sources.extend(
path.read_text(encoding="utf-8")
for path in sorted((ROOT / "backend" / "database" / "migrations").glob("m*.py"))
)
database_sources.append(
source("backend/database/migrations/runner.py")
)
pages = page_inventory(html)
api = api_inventory(server)
tables = database_inventory(database_sources)
return {
"schema_version": 1,
"captured_from": "app accepted modular runtime",
"runtime": {
"http_server": "http.server.ThreadingHTTPServer",
"application_processes": 1,
"database": "SQLite WAL",
"frontend": "build-free HTML/CSS/JavaScript",
"container_port": 8765,
},
"counts": {
"primary_pages": len(pages),
"api_exact_paths": len(api["exact"]),
"api_prefixes": len(api["prefixes"]),
"api_patterns": len(api["patterns"]),
"database_tables": len(tables),
"frontend_page_fragments": len(fragments),
},
"pages": pages,
"api": api,
"database_tables": tables,
"background_job_methods": python_functions(
"backend/jobs/service.py",
("_background", "_run_background", "_schedule_", "run_automatic"),
),
"external_data_adapters": [
{"provider": "tushare", "path": "backend/data/providers/tushare_client.py", "runtime_role": "stable client facade for primary deterministic market data"},
{"provider": "ifind", "path": "backend/data/providers/ifind_client.py", "runtime_role": "realtime, charts, snapshots, enrichment"},
{"provider": "eastmoney", "path": "backend/features/market/charts.py", "runtime_role": "display chart fallback"},
{"provider": "eastmoney", "path": "backend/data/realtime.py", "runtime_role": "isolated realtime observation"},
{"provider": "tencent", "path": "backend/data/realtime.py", "runtime_role": "index observation fallback"},
],
"provider_domains": [
{"provider": "tushare", "path": "backend/data/providers/tushare_transport.py", "responsibility": "HTTP transport and provider errors"},
{"provider": "tushare", "path": "backend/data/providers/tushare_dashboard.py", "responsibility": "market overview and realtime breadth"},
{"provider": "tushare", "path": "backend/data/providers/tushare_indices.py", "responsibility": "market indices"},
{"provider": "tushare", "path": "backend/data/providers/tushare_industries.py", "responsibility": "Shenwan membership and industry snapshots"},
{"provider": "tushare", "path": "backend/data/providers/tushare_sectors.py", "responsibility": "generic sector snapshots"},
{"provider": "tushare", "path": "backend/data/providers/tushare_dragon_tiger.py", "responsibility": "hot-money directory and dragon-tiger activity"},
{"provider": "tushare", "path": "backend/data/providers/tushare_stocks.py", "responsibility": "stock detail and intraday bars"},
{"provider": "tushare", "path": "backend/data/providers/tushare_daily.py", "responsibility": "trading calendar, daily bars, and limit lists"},
{"provider": "tushare", "path": "backend/data/providers/tushare_helpers.py", "responsibility": "shared deterministic normalization helpers"},
],
"provider_construction": [
{"client": "TushareClient", "owner": "backend/data/providers/tushare.py", "compatibility_fallback": "backend/features/market/service.py"},
{"client": "IfindHttpClient", "owner": "backend/data/gateway.py"},
{"client": "MarketChartClient", "owner": "backend/data/gateway.py"},
{"client": "WebRealtimeAggregator", "owner": "backend/data/gateway.py"},
],
"heaven_service_owners": {
"facade": "backend/features/heaven/service.py",
"manual_validation_and_safety": "backend/features/heaven/manual.py",
"trend_orchestration_and_quality": "backend/features/heaven/trend.py",
"market_context": "backend/features/heaven/market_context.py",
"readings_and_interpretation": "backend/features/heaven/readings.py",
},
"market_insight_owners": {
"facade": "backend/features/market/insights.py",
"shared_context": "backend/features/market/insights_context.py",
"auction_scoring": "backend/features/market/insights_auction_scoring.py",
"auction_data": "backend/features/market/insights_auction_data.py",
"auction_orchestration": "backend/features/market/insights_auction.py",
"themes": "backend/features/market/insights_themes.py",
"popularity": "backend/features/market/insights_popularity.py",
},
"application_owners": {
"composition_root": "backend/application.py",
"http_dispatch": "backend/http/dispatch.py",
"system_service": "backend/features/system/service.py",
"account_bridge": "backend/features/accounts/application.py",
"job_lifecycle": "backend/jobs/service.py",
"feature_routes": "backend/features/*/routes.py",
},
"numeric_normalization": [
{"function": "finite_number", "path": "backend/data/numbers.py"},
{"function": "non_nan_number", "path": "backend/data/numbers.py"},
],
"date_formatting": [
{"function": "display_compact_date", "path": "backend/bootstrap/config.py"},
],
"llm_entrypoints": [
{"function": "stream_with_mentor", "path": "backend/features/mentor/agent.py"},
{"function": "interpret_heaven", "path": "backend/features/heaven/agent.py"},
{"function": "stream_review_assistant", "path": "backend/features/review/agent.py"},
{"function": "compile_strategy_with_llm", "path": "backend/features/screener/compiler.py"},
{"function": "test_llm_connection", "path": "backend/features/screener/compiler.py"},
],
"llm_transport": [
{"function": "chat_completion", "path": "backend/llm/transport.py"},
{"function": "stream_chat_completion", "path": "backend/llm/transport.py"},
],
"http_transport": [
{"function": "send_json", "path": "backend/http/handler.py"},
{"function": "send_ndjson_stream", "path": "backend/http/handler.py"},
],
"css_layers": css_layers(html),
"frontend_composition": {
"shell": "frontend/index.html",
"bootstrap": "frontend/bootstrap.js",
"registry": "frontend/pages.config.js",
"startup": "frontend/app.js",
"runtime_owners": {
"context": "frontend/shared/context.js",
"application": "frontend/shared/application.js",
"feedback": "frontend/shared/feedback.js",
"dashboard": "frontend/shared/dashboard.js",
"session": "frontend/shared/session.js",
"admin": "frontend/shared/admin.js",
"theme": "frontend/shared/theme.js",
"table": "frontend/shared/table.js",
},
"market_runtime_owners": {
"breadth": "frontend/pages/market/breadth.js",
"charts": "frontend/pages/market/charts.js",
"entity_detail": "frontend/pages/market/entity-detail.js",
"stock_detail": "frontend/pages/market/stock-detail.js",
"preview": "frontend/pages/market/preview.js",
"search": "frontend/pages/market/search.js",
"bindings": "frontend/pages/market/bindings.js",
},
"fragments": [path.split("?", 1)[0] for path in fragments],
},
"code_hotspots": code_hotspots(),
}
def main() -> int:
parser = argparse.ArgumentParser(description="Build the current architecture inventory")
parser.add_argument("--check", action="store_true", help="fail when the committed inventory is stale")
args = parser.parse_args()
rendered = json.dumps(build(), ensure_ascii=False, indent=2) + "\n"
if args.check:
if not OUTPUT.exists() or OUTPUT.read_text(encoding="utf-8") != rendered:
raise SystemExit(
"architecture inventory is stale; run "
"tools/build_architecture_inventory.py"
)
print("Architecture inventory is current.")
return 0
OUTPUT.parent.mkdir(parents=True, exist_ok=True)
OUTPUT.write_text(rendered, encoding="utf-8")
print(relative(OUTPUT))
return 0
if __name__ == "__main__":
raise SystemExit(main())