Files
codex-app-server/cloud/migrations.py
T
host dc3f572b2b Postgres real backend: psycopg adapter, schema, migration
Replace the PostgresDatabase skeleton with a real implementation:
psycopg (v3) first, psycopg2 second, lazy load, missing driver
still raises PostgresDriverMissingError with no silent SQLite
fallback. A sqlite3-style adapter (PgConnection/PgCursor/PgRow)
translates ? placeholders to %s outside string literals, maps
UNIQUE/FK violations, lock errors and connection failures to
explicit Postgres error types, and handles INSERT OR REPLACE,
PRAGMA table_info, AUTOINCREMENT and FTS5 refusal. POSTGRES_SCHEMA
covers all business tables with tasks result columns; server
init_db uses it under CLOUD_DB_BACKEND=postgres, SQLite path
unchanged. migrate_sqlite_to_postgres.py copies rows with
ON CONFLICT DO NOTHING and reseeds identity sequences.
Tests: cloud 239 (235 pass, 4 skipped without a real server),
host 27 pass; real-server tests skip unless CLOUD_TEST_PG_DSN
is set.
2026-10-26 03:23:06 +08:00

121 lines
4.4 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
"""SQLite -> Postgres 迁移(控制面状态库)。
只做一件事:把一个 SQLite 库文件里的行原样插进 Postgres,
表名与列名不改。幂等:Postgres 侧用 ``ON CONFLICT DO NOTHING``,
跑两次不重复插(第二次各表 inserted 为 0)。
- schema 来自 cloud.db.POSTGRES_SCHEMA / init_postgres_schema,
本模块不另发明表结构;迁移前先建表(若目标库已有表,
CREATE TABLE IF NOT EXISTS 是 no-op)。
- kb_fts(SQLite FTS5 虚拟表)不迁移:Postgres 没有 FTS5,
KBStore 在 PG 上走 LIKE 分支,kb_docs 的 content 已足够。
- sqlite_sequence(AUTOINCREMENT 内部表)不迁移。
- 不打印、不返回任何密码或密钥:函数只返回 {表: inserted},
CLI 只打印表名与行数。
- Postgres 连接参数只走 CLOUD_DB_* 环境变量(见 cloud.db),
本模块不读、不拼连接串、不接受命令行密码参数。
"""
import os
import sqlite3
from cloud.db import (
POSTGRES_SCHEMA,
PostgresDatabase,
init_postgres_schema,
)
# 迁移顺序:无外键约束,顺序只影响日志可读性;用户表在前,
# 审计/成本等追加表在后。kb_fts 与 sqlite_sequence 明确排除。
MIGRATION_TABLES = (
"users",
"projects",
"project_members",
"tasks",
"audit_log",
"summaries",
"kb_docs",
"cost_records",
"oauth_states",
"slack_users",
"push_subscriptions",
)
_SKIP_TABLES = frozenset({"kb_fts", "sqlite_sequence"})
def migrate_sqlite_to_postgres(sqlite_path, pg_conn=None, tables=None):
"""迁移并返回 {表名: 本次插入行数}。
pg_conn 为 None 时用 PostgresDatabase().connect() 新建连接
(驱动缺失时抛 PostgresDriverMissingError,绝不回落);
传入连接时调用方负责关闭,本函数不关闭它。tables 为 None
时迁 MIGRATION_TABLES 全量;显式传表名时只迁其中在
SQLite 里存在的表,不存在的表在结果里记 0(不报错,
因为老库可能还没建出某张表,例如未用过的 push 表)。
"""
wanted = tuple(tables) if tables is not None else MIGRATION_TABLES
src = sqlite3.connect(str(sqlite_path))
src.row_factory = sqlite3.Row
own_conn = pg_conn is None
if own_conn:
pg_conn = PostgresDatabase().connect()
try:
init_postgres_schema(pg_conn)
result = {}
for table in wanted:
if table in _SKIP_TABLES:
result[table] = 0
continue
try:
rows = src.execute(
'SELECT * FROM "%s"' % table).fetchall()
except sqlite3.OperationalError:
# 老库里没有这张表:记 0,不中断其余表。
result[table] = 0
continue
if not rows:
result[table] = 0
continue
columns = [d[0] for d in src.execute(
'SELECT * FROM "%s" LIMIT 0' % table).description]
placeholders = ", ".join("?" for _ in columns)
col_list = ", ".join('"%s"' % c for c in columns)
inserted = 0
for row in rows:
cur = pg_conn.execute(
'INSERT INTO "%s" (%s) VALUES (%s)'
" ON CONFLICT DO NOTHING"
% (table, col_list, placeholders),
tuple(row[c] for c in columns))
if cur.rowcount:
inserted += cur.rowcount
# 身份列的序列不会因显式插 id 自动前进:迁完把序列
# 拨到当前最大 id,否则后续省略 id 的 INSERT 会撞主键。
if table in ("audit_log", "summaries", "kb_docs",
"cost_records") and "id" in columns:
try:
pg_conn.execute(
"SELECT setval(pg_get_serial_sequence(?, ?),"
" COALESCE((SELECT MAX(id) FROM \"%s\"), 1), true)"
% table,
(table, "id"))
except Exception:
pass
pg_conn.commit()
result[table] = inserted
return result
finally:
src.close()
if own_conn:
try:
pg_conn.close()
except Exception:
pass
__all__ = [
"MIGRATION_TABLES",
"migrate_sqlite_to_postgres",
]