migration: preserve market insights slice

This commit is contained in:
leefer
2026-07-31 02:41:56 +08:00
parent 814e75730a
commit cf2aad28ec
30 changed files with 2487 additions and 1759 deletions
+111
View File
@@ -0,0 +1,111 @@
from __future__ import annotations
import argparse
import hashlib
import http.cookiejar
import json
import urllib.error
import urllib.request
from pathlib import Path
from typing import Any
def request_json(
opener: urllib.request.OpenerDirector,
url: str,
payload: dict[str, Any] | None = None,
) -> tuple[int, Any]:
data = None
headers = {"Accept": "application/json"}
if payload is not None:
data = json.dumps(payload, ensure_ascii=False).encode("utf-8")
headers["Content-Type"] = "application/json"
request = urllib.request.Request(url, data=data, headers=headers)
try:
with opener.open(request, timeout=90) as response:
return response.status, json.loads(response.read().decode("utf-8"))
except urllib.error.HTTPError as exc:
return exc.code, json.loads(exc.read().decode("utf-8"))
def session(base_url: str, username: str, password: str) -> urllib.request.OpenerDirector:
opener = urllib.request.build_opener(
urllib.request.HTTPCookieProcessor(http.cookiejar.CookieJar())
)
status, body = request_json(
opener,
f"{base_url.rstrip('/')}/api/auth/login",
{"username": username, "password": password},
)
if status != 200 or not body.get("ok"):
raise RuntimeError(f"Login failed for {base_url}: HTTP {status} {body}")
return opener
def digest(value: Any) -> str:
content = json.dumps(
value, ensure_ascii=False, sort_keys=True, separators=(",", ":")
).encode("utf-8")
return hashlib.sha256(content).hexdigest()
def comparable(value: Any) -> Any:
if isinstance(value, dict):
return {
key: comparable(item)
for key, item in value.items()
if key != "request_id"
}
if isinstance(value, list):
return [comparable(item) for item in value]
return value
def main() -> None:
parser = argparse.ArgumentParser(description="Compare authenticated preservation APIs")
parser.add_argument("--original", required=True)
parser.add_argument("--migrated", required=True)
parser.add_argument("--username", required=True)
parser.add_argument("--password", required=True)
parser.add_argument("--output", type=Path, required=True)
parser.add_argument("endpoints", nargs="+")
args = parser.parse_args()
original = session(args.original, args.username, args.password)
migrated = session(args.migrated, args.username, args.password)
rows = []
all_equal = True
for endpoint in args.endpoints:
original_status, original_body = request_json(
original, f"{args.original.rstrip('/')}{endpoint}"
)
migrated_status, migrated_body = request_json(
migrated, f"{args.migrated.rstrip('/')}{endpoint}"
)
original_comparable = comparable(original_body)
migrated_comparable = comparable(migrated_body)
equal = original_status == migrated_status and original_comparable == migrated_comparable
all_equal = all_equal and equal
rows.append(
{
"endpoint": endpoint,
"original_status": original_status,
"migrated_status": migrated_status,
"original_sha256": digest(original_comparable),
"migrated_sha256": digest(migrated_comparable),
"equal": equal,
}
)
result = {"all_equal": all_equal, "endpoints": rows}
args.output.parent.mkdir(parents=True, exist_ok=True)
args.output.write_text(
json.dumps(result, ensure_ascii=False, indent=2) + "\n", encoding="utf-8"
)
print(json.dumps(result, ensure_ascii=False, indent=2))
if not all_equal:
raise SystemExit(1)
if __name__ == "__main__":
main()
@@ -0,0 +1,92 @@
from __future__ import annotations
import argparse
import hashlib
import json
import sqlite3
from pathlib import Path
from typing import Any
def digest(value: Any) -> str:
content = json.dumps(
value, ensure_ascii=False, sort_keys=True, separators=(",", ":"), default=str
).encode("utf-8")
return hashlib.sha256(content).hexdigest()
def schema(connection: sqlite3.Connection) -> list[dict[str, Any]]:
rows = connection.execute(
"""
SELECT type, name, tbl_name, sql
FROM sqlite_master
WHERE name NOT LIKE 'sqlite_%'
ORDER BY type, name
"""
).fetchall()
return [dict(row) for row in rows]
def table_rows(connection: sqlite3.Connection, table: str) -> list[dict[str, Any]]:
quoted = '"' + table.replace('"', '""') + '"'
rows = [dict(row) for row in connection.execute(f"SELECT * FROM {quoted}").fetchall()]
return sorted(rows, key=lambda row: json.dumps(row, ensure_ascii=False, sort_keys=True, default=str))
def main() -> None:
parser = argparse.ArgumentParser(description="Compare preservation SQLite databases")
parser.add_argument("--original", type=Path, required=True)
parser.add_argument("--migrated", type=Path, required=True)
parser.add_argument("--output", type=Path, required=True)
parser.add_argument("tables", nargs="+")
args = parser.parse_args()
original = sqlite3.connect(args.original)
migrated = sqlite3.connect(args.migrated)
original.row_factory = sqlite3.Row
migrated.row_factory = sqlite3.Row
try:
original_schema = schema(original)
migrated_schema = schema(migrated)
tables = []
all_equal = original_schema == migrated_schema
for table in args.tables:
original_rows = table_rows(original, table)
migrated_rows = table_rows(migrated, table)
equal = original_rows == migrated_rows
all_equal = all_equal and equal
tables.append(
{
"table": table,
"original_count": len(original_rows),
"migrated_count": len(migrated_rows),
"original_sha256": digest(original_rows),
"migrated_sha256": digest(migrated_rows),
"equal": equal,
}
)
result = {
"all_equal": all_equal,
"schema": {
"object_count": len(original_schema),
"original_sha256": digest(original_schema),
"migrated_sha256": digest(migrated_schema),
"equal": original_schema == migrated_schema,
},
"tables": tables,
}
finally:
original.close()
migrated.close()
args.output.parent.mkdir(parents=True, exist_ok=True)
args.output.write_text(
json.dumps(result, ensure_ascii=False, indent=2) + "\n", encoding="utf-8"
)
print(json.dumps(result, ensure_ascii=False, indent=2))
if not all_equal:
raise SystemExit(1)
if __name__ == "__main__":
main()
+46
View File
@@ -0,0 +1,46 @@
from __future__ import annotations
import argparse
import sys
from http.server import ThreadingHTTPServer
from pathlib import Path
def main() -> None:
parser = argparse.ArgumentParser(description="Run an isolated preservation runtime")
parser.add_argument("--runtime-root", type=Path, required=True)
parser.add_argument("--data-dir", type=Path, required=True)
parser.add_argument("--port", type=int, required=True)
args = parser.parse_args()
runtime_root = args.runtime_root.resolve()
data_dir = args.data_dir.resolve()
data_dir.mkdir(parents=True, exist_ok=True)
sys.path.insert(0, str(runtime_root))
if (runtime_root / "backend" / "bootstrap" / "config.py").is_file():
from backend.bootstrap import config
config.DATA_DIR = data_dir
config.PRIVATE_MENTOR_SKILLS_DIR = data_dir / "private-mentor-skills"
else:
import app_config as config
config.DATA_DIR = data_dir
config.PRIVATE_MENTOR_SKILLS_DIR = data_dir / "private-mentor-skills"
from server import RequestHandler, SERVICE
server = ThreadingHTTPServer(("127.0.0.1", args.port), RequestHandler)
print(f"Preservation runtime is running at http://127.0.0.1:{args.port}", flush=True)
try:
server.serve_forever()
except KeyboardInterrupt:
pass
finally:
SERVICE._background_stop.set()
server.server_close()
if __name__ == "__main__":
main()