82 lines
2.9 KiB
Python
82 lines
2.9 KiB
Python
|
import sys
|
||
|
|
import os
|
||
|
|
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||
|
|
|
||
|
|
from sqlalchemy import create_engine, text
|
||
|
|
from backend.core.config import settings
|
||
|
|
|
||
|
|
def update_database_schema():
|
||
|
|
"""
|
||
|
|
数据库无损升级脚本
|
||
|
|
"""
|
||
|
|
print(f"🔌 连接数据库: {settings.DB_NAME}...")
|
||
|
|
engine = create_engine(settings.DATABASE_URL)
|
||
|
|
|
||
|
|
commands = [
|
||
|
|
# 1. 安全添加 meta_info 列 (旧数据会自动填充为 {})
|
||
|
|
"""
|
||
|
|
DO $$
|
||
|
|
BEGIN
|
||
|
|
IF NOT EXISTS (SELECT 1 FROM information_schema.columns WHERE table_name='knowledge_chunks' AND column_name='meta_info') THEN
|
||
|
|
ALTER TABLE knowledge_chunks ADD COLUMN meta_info JSONB DEFAULT '{}';
|
||
|
|
RAISE NOTICE '已添加 meta_info 列';
|
||
|
|
END IF;
|
||
|
|
END $$;
|
||
|
|
""",
|
||
|
|
|
||
|
|
# 2. 安全添加 content_tsvector 列
|
||
|
|
"""
|
||
|
|
DO $$
|
||
|
|
BEGIN
|
||
|
|
IF NOT EXISTS (SELECT 1 FROM information_schema.columns WHERE table_name='knowledge_chunks' AND column_name='content_tsvector') THEN
|
||
|
|
ALTER TABLE knowledge_chunks ADD COLUMN content_tsvector TSVECTOR;
|
||
|
|
RAISE NOTICE '已添加 content_tsvector 列';
|
||
|
|
END IF;
|
||
|
|
END $$;
|
||
|
|
""",
|
||
|
|
|
||
|
|
# 3. 创建索引 (不影响现有数据)
|
||
|
|
"CREATE INDEX IF NOT EXISTS idx_chunks_meta ON knowledge_chunks USING GIN (meta_info);",
|
||
|
|
"CREATE INDEX IF NOT EXISTS idx_chunks_tsvector ON knowledge_chunks USING GIN (content_tsvector);",
|
||
|
|
|
||
|
|
# 4. 创建触发器函数 (用于新插入的数据)
|
||
|
|
"""
|
||
|
|
CREATE OR REPLACE FUNCTION chunks_tsvector_trigger() RETURNS trigger AS $$
|
||
|
|
BEGIN
|
||
|
|
new.content_tsvector := to_tsvector('english', coalesce(new.title, '') || ' ' || new.content);
|
||
|
|
return new;
|
||
|
|
END
|
||
|
|
$$ LANGUAGE plpgsql;
|
||
|
|
""",
|
||
|
|
|
||
|
|
# 5. 绑定触发器
|
||
|
|
"""
|
||
|
|
DO $$
|
||
|
|
BEGIN
|
||
|
|
IF NOT EXISTS (SELECT 1 FROM pg_trigger WHERE tgname = 'tsvectorupdate') THEN
|
||
|
|
CREATE TRIGGER tsvectorupdate BEFORE INSERT OR UPDATE
|
||
|
|
ON knowledge_chunks FOR EACH ROW EXECUTE PROCEDURE chunks_tsvector_trigger();
|
||
|
|
END IF;
|
||
|
|
END $$;
|
||
|
|
""",
|
||
|
|
|
||
|
|
# 6. 【新增】回填旧数据
|
||
|
|
# 让以前存的 task_id=6 的数据也能生成关键词索引
|
||
|
|
"""
|
||
|
|
UPDATE knowledge_chunks
|
||
|
|
SET content_tsvector = to_tsvector('english', coalesce(title, '') || ' ' || content)
|
||
|
|
WHERE content_tsvector IS NULL;
|
||
|
|
"""
|
||
|
|
]
|
||
|
|
|
||
|
|
with engine.begin() as conn:
|
||
|
|
for cmd in commands:
|
||
|
|
try:
|
||
|
|
conn.execute(text(cmd))
|
||
|
|
except Exception as e:
|
||
|
|
print(f"⚠️ 执行警告 (通常可忽略): {e}")
|
||
|
|
|
||
|
|
print("✅ 数据库结构升级完成！旧数据已保留并兼容。")
|
||
|
|
|
||
|
|
if __name__ == "__main__":
|
||
|
|
update_database_schema()
|