Critical fixes: 1. Compute column: Add Chinese comma support in formula validation - Problem: Formula with Chinese comma failed validation - Fix: Add Chinese comma character to allowed_chars regex - Example: Support formulas like 'col1(kg)+ col2,col3' 2. Binning operation: Fix NaN serialization error - Problem: 'Out of range float values are not JSON compliant: nan' - Fix: Enhanced NaN/inf handling in binning endpoint - Added np.inf/-np.inf replacement before JSON serialization - Added manual JSON serialization with NaN->null conversion 3. Enhanced all operation endpoints for consistency - Updated conditional, dropna endpoints with same NaN/inf handling - Ensures all operations return JSON-compliant data Modified files: - extraction_service/operations/compute.py: Add Chinese comma to regex - extraction_service/main.py: Enhanced NaN handling in binning/conditional/dropna Status: Hotfix complete, ready for testing
39 lines
1.3 KiB
SQL
39 lines
1.3 KiB
SQL
-- 创建 Tool C Session 表
|
||
-- 日期: 2025-12-06
|
||
-- 用途: 科研数据编辑器会话管理
|
||
|
||
CREATE TABLE IF NOT EXISTS dc_schema.dc_tool_c_sessions (
|
||
id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
|
||
user_id VARCHAR(255) NOT NULL,
|
||
file_name VARCHAR(500) NOT NULL,
|
||
file_key VARCHAR(500) NOT NULL,
|
||
|
||
-- 数据元信息
|
||
total_rows INTEGER NOT NULL,
|
||
total_cols INTEGER NOT NULL,
|
||
columns JSONB NOT NULL,
|
||
encoding VARCHAR(50),
|
||
file_size INTEGER NOT NULL,
|
||
|
||
-- 时间戳
|
||
created_at TIMESTAMP NOT NULL DEFAULT CURRENT_TIMESTAMP,
|
||
updated_at TIMESTAMP NOT NULL DEFAULT CURRENT_TIMESTAMP,
|
||
expires_at TIMESTAMP NOT NULL
|
||
);
|
||
|
||
-- 创建索引
|
||
CREATE INDEX IF NOT EXISTS idx_dc_tool_c_sessions_user_id ON dc_schema.dc_tool_c_sessions(user_id);
|
||
CREATE INDEX IF NOT EXISTS idx_dc_tool_c_sessions_expires_at ON dc_schema.dc_tool_c_sessions(expires_at);
|
||
|
||
-- 添加注释
|
||
COMMENT ON TABLE dc_schema.dc_tool_c_sessions IS 'Tool C (科研数据编辑器) Session会话表';
|
||
COMMENT ON COLUMN dc_schema.dc_tool_c_sessions.file_key IS 'OSS存储路径: dc/tool-c/sessions/{timestamp}-{fileName}';
|
||
COMMENT ON COLUMN dc_schema.dc_tool_c_sessions.columns IS '列名数组 ["age", "gender", "diagnosis"]';
|
||
COMMENT ON COLUMN dc_schema.dc_tool_c_sessions.expires_at IS '过期时间(创建后10分钟)';
|
||
|
||
|
||
|
||
|
||
|
||
|