fix: restore main runtime sources and cache consistency
This commit is contained in:
User
46
data/__init__.py
Normal file
46
data/__init__.py
Normal file
@@ -0,0 +1,46 @@
|
||||
"""
|
||||
数据目录
|
||||
|
||||
统一数据库结构（按业务域和运行环境划分）：
|
||||
- data/prod/feedback.db: 反馈、FAQ 与质量报告
|
||||
- data/prod/knowledge.db: 同步、纲要与文档版本
|
||||
- data/dev/session.db: 本地开发会话与审计日志
|
||||
- data/dev/exam.db: 本地出题、试卷与批阅数据
|
||||
|
||||
使用方式：
|
||||
from data.db import get_connection, init_databases
|
||||
|
||||
# 首次运行时初始化
|
||||
init_databases()
|
||||
|
||||
# 使用连接
|
||||
with get_connection("session") as conn:
|
||||
cursor = conn.cursor()
|
||||
cursor.execute("SELECT * FROM sessions")
|
||||
"""
|
||||
|
||||
from data.db import (
|
||||
get_connection,
|
||||
get_raw_connection,
|
||||
init_databases,
|
||||
get_db_stats,
|
||||
row_to_dict,
|
||||
rows_to_list,
|
||||
json_parse,
|
||||
json_stringify,
|
||||
DB_PATHS,
|
||||
DATA_DIR,
|
||||
)
|
||||
|
||||
__all__ = [
|
||||
"get_connection",
|
||||
"get_raw_connection",
|
||||
"init_databases",
|
||||
"get_db_stats",
|
||||
"row_to_dict",
|
||||
"rows_to_list",
|
||||
"json_parse",
|
||||
"json_stringify",
|
||||
"DB_PATHS",
|
||||
"DATA_DIR",
|
||||
]
|
||||
821
data/db.py
Normal file
821
data/db.py
Normal file
@@ -0,0 +1,821 @@
|
||||
"""
|
||||
统一数据访问层 - 集中管理所有数据库连接
|
||||
|
||||
功能：
|
||||
1. 统一数据库路径配置（按环境分离：prod/dev）
|
||||
2. 连接池管理（上下文管理器）
|
||||
3. WAL 模式 + 外键约束
|
||||
4. 自动事务管理（commit/rollback）
|
||||
5. 初始化所有表结构
|
||||
|
||||
数据库分离：
|
||||
- feedback.db: 反馈系统（生产模式也使用）
|
||||
- knowledge.db: 知识管理（生产模式也使用）
|
||||
- session.db: 会话管理（仅开发模式）
|
||||
- exam.db: 出题系统（仅开发模式）
|
||||
|
||||
使用方式：
|
||||
from data.db import get_connection, init_databases
|
||||
|
||||
# 初始化数据库（首次运行时调用）
|
||||
init_databases()
|
||||
|
||||
# 使用连接
|
||||
with get_connection("feedback") as conn:
|
||||
cursor = conn.cursor()
|
||||
cursor.execute("SELECT * FROM feedbacks WHERE user_id = ?", (user_id,))
|
||||
rows = cursor.fetchall()
|
||||
"""
|
||||
|
||||
import sqlite3
|
||||
import os
|
||||
import json
|
||||
import logging
|
||||
import threading
|
||||
from contextlib import contextmanager
|
||||
from typing import Generator, Dict, List, Optional
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
# ==================== 路径配置 ====================
|
||||
|
||||
DATA_DIR = os.path.dirname(os.path.abspath(__file__))
|
||||
|
||||
DB_PATHS = {
|
||||
# 生产模式数据库（开发模式也使用）
|
||||
"feedback": os.path.join(DATA_DIR, "prod", "feedback.db"),
|
||||
"knowledge": os.path.join(DATA_DIR, "prod", "knowledge.db"),
|
||||
|
||||
# 仅开发模式数据库
|
||||
"session": os.path.join(DATA_DIR, "dev", "session.db"),
|
||||
"exam": os.path.join(DATA_DIR, "dev", "exam.db"),
|
||||
}
|
||||
|
||||
# 数据库名称映射（用于日志）
|
||||
DB_NAMES = {
|
||||
"feedback": "反馈系统数据库（反馈、FAQ、质量报告）",
|
||||
"knowledge": "知识管理数据库（同步、大纲、版本）",
|
||||
"session": "会话管理数据库（会话、消息、审计日志）",
|
||||
"exam": "出题系统数据库（题库、试卷、批卷）",
|
||||
}
|
||||
|
||||
_init_lock = threading.Lock()
|
||||
_initialized = False
|
||||
|
||||
|
||||
# ==================== 连接管理 ====================
|
||||
|
||||
@contextmanager
|
||||
def get_connection(db_name: str, row_factory: bool = True) -> Generator[sqlite3.Connection, None, None]:
|
||||
"""
|
||||
获取数据库连接（上下文管理器）
|
||||
|
||||
Args:
|
||||
db_name: 数据库名称 ("feedback", "knowledge", "session", "exam")
|
||||
row_factory: 是否启用行工厂（返回字典格式）
|
||||
|
||||
Yields:
|
||||
sqlite3.Connection: 数据库连接
|
||||
|
||||
Example:
|
||||
with get_connection("feedback") as conn:
|
||||
cursor = conn.cursor()
|
||||
cursor.execute("SELECT * FROM feedbacks")
|
||||
rows = cursor.fetchall()
|
||||
"""
|
||||
if db_name not in DB_PATHS:
|
||||
raise ValueError(f"未知的数据库: {db_name}，可用: {list(DB_PATHS.keys())}")
|
||||
|
||||
db_path = DB_PATHS[db_name]
|
||||
|
||||
# fresh clone 中 prod/dev 目录尚不存在；连接前统一创建父目录。
|
||||
os.makedirs(os.path.dirname(db_path), exist_ok=True)
|
||||
|
||||
# 关键：check_same_thread=False 支持多worker
|
||||
conn = sqlite3.connect(db_path, timeout=30, check_same_thread=False)
|
||||
|
||||
# 启用 WAL 模式（提升并发性能）
|
||||
conn.execute("PRAGMA journal_mode=WAL")
|
||||
|
||||
# 设置繁忙超时（5秒）
|
||||
conn.execute("PRAGMA busy_timeout=5000")
|
||||
|
||||
# 启用外键约束
|
||||
conn.execute("PRAGMA foreign_keys=ON")
|
||||
|
||||
# 设置行工厂（返回字典格式）
|
||||
if row_factory:
|
||||
conn.row_factory = sqlite3.Row
|
||||
|
||||
try:
|
||||
yield conn
|
||||
conn.commit()
|
||||
except Exception:
|
||||
conn.rollback()
|
||||
raise
|
||||
finally:
|
||||
conn.close()
|
||||
|
||||
|
||||
def get_raw_connection(db_name: str) -> sqlite3.Connection:
|
||||
"""
|
||||
获取原始数据库连接（不使用上下文管理器）
|
||||
|
||||
注意：调用者需要手动关闭连接
|
||||
|
||||
Args:
|
||||
db_name: 数据库名称
|
||||
|
||||
Returns:
|
||||
sqlite3.Connection: 数据库连接
|
||||
"""
|
||||
if db_name not in DB_PATHS:
|
||||
raise ValueError(f"未知的数据库: {db_name}")
|
||||
|
||||
db_path = DB_PATHS[db_name]
|
||||
os.makedirs(os.path.dirname(db_path), exist_ok=True)
|
||||
conn = sqlite3.connect(db_path, timeout=30, check_same_thread=False)
|
||||
conn.execute("PRAGMA journal_mode=WAL")
|
||||
conn.execute("PRAGMA busy_timeout=5000")
|
||||
conn.execute("PRAGMA foreign_keys=ON")
|
||||
conn.row_factory = sqlite3.Row
|
||||
return conn
|
||||
|
||||
|
||||
# ==================== 数据库初始化 ====================
|
||||
|
||||
def init_databases():
|
||||
"""
|
||||
初始化所有数据库表结构
|
||||
|
||||
按环境分离为：
|
||||
- 生产模式数据库（开发模式也使用）：feedback.db, knowledge.db
|
||||
- 仅开发模式数据库：session.db, exam.db
|
||||
"""
|
||||
global _initialized
|
||||
if _initialized:
|
||||
return
|
||||
|
||||
from config import IS_DEV
|
||||
|
||||
with _init_lock:
|
||||
if _initialized:
|
||||
return
|
||||
|
||||
# 始终初始化生产模式数据库
|
||||
_init_feedback_db()
|
||||
_init_knowledge_db()
|
||||
|
||||
# 仅开发模式初始化会话和出题数据库
|
||||
if IS_DEV:
|
||||
_init_session_db()
|
||||
_init_exam_db()
|
||||
logger.info("所有数据库初始化完成（开发模式）")
|
||||
else:
|
||||
logger.info("生产模式数据库初始化完成")
|
||||
|
||||
_initialized = True
|
||||
|
||||
|
||||
def _init_feedback_db():
|
||||
"""初始化 feedback.db（反馈系统数据库 - 生产模式也使用）"""
|
||||
with get_connection("feedback", row_factory=False) as conn:
|
||||
cursor = conn.cursor()
|
||||
|
||||
# ========== 反馈表 ==========
|
||||
cursor.execute('''
|
||||
CREATE TABLE IF NOT EXISTS feedbacks (
|
||||
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
||||
session_id TEXT NOT NULL,
|
||||
query TEXT NOT NULL,
|
||||
answer TEXT,
|
||||
sources TEXT,
|
||||
rating INTEGER NOT NULL,
|
||||
reason TEXT,
|
||||
user_id TEXT,
|
||||
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
|
||||
)
|
||||
''')
|
||||
|
||||
cursor.execute('''
|
||||
CREATE INDEX IF NOT EXISTS idx_feedback_session
|
||||
ON feedbacks(session_id)
|
||||
''')
|
||||
|
||||
cursor.execute('''
|
||||
CREATE INDEX IF NOT EXISTS idx_feedback_rating
|
||||
ON feedbacks(rating)
|
||||
''')
|
||||
|
||||
cursor.execute('''
|
||||
CREATE INDEX IF NOT EXISTS idx_feedback_created
|
||||
ON feedbacks(created_at)
|
||||
''')
|
||||
|
||||
# ========== FAQ 表 ==========
|
||||
cursor.execute('''
|
||||
CREATE TABLE IF NOT EXISTS faqs (
|
||||
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
||||
question TEXT NOT NULL,
|
||||
answer TEXT NOT NULL,
|
||||
source_documents TEXT,
|
||||
frequency INTEGER DEFAULT 1,
|
||||
avg_rating REAL DEFAULT 0,
|
||||
status TEXT DEFAULT 'draft',
|
||||
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
|
||||
updated_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
|
||||
)
|
||||
''')
|
||||
|
||||
cursor.execute('''
|
||||
CREATE INDEX IF NOT EXISTS idx_faq_status
|
||||
ON faqs(status)
|
||||
''')
|
||||
|
||||
# ========== FAQ 问题变体表（Multi-Query Indexing）==========
|
||||
cursor.execute('''
|
||||
CREATE TABLE IF NOT EXISTS faq_variants (
|
||||
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
||||
faq_id INTEGER NOT NULL,
|
||||
variant_question TEXT NOT NULL,
|
||||
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
|
||||
FOREIGN KEY (faq_id) REFERENCES faqs(id) ON DELETE CASCADE
|
||||
)
|
||||
''')
|
||||
|
||||
cursor.execute('''
|
||||
CREATE INDEX IF NOT EXISTS idx_faq_variant_faq
|
||||
ON faq_variants(faq_id)
|
||||
''')
|
||||
|
||||
# ========== 质量报告表 ==========
|
||||
cursor.execute('''
|
||||
CREATE TABLE IF NOT EXISTS quality_reports (
|
||||
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
||||
report_type TEXT NOT NULL,
|
||||
start_date DATE NOT NULL,
|
||||
end_date DATE NOT NULL,
|
||||
total_queries INTEGER DEFAULT 0,
|
||||
total_feedback INTEGER DEFAULT 0,
|
||||
positive_count INTEGER DEFAULT 0,
|
||||
negative_count INTEGER DEFAULT 0,
|
||||
avg_rating REAL DEFAULT 0,
|
||||
satisfaction_rate REAL DEFAULT 0,
|
||||
high_freq_queries TEXT,
|
||||
low_rating_queries TEXT,
|
||||
improvement_suggestions TEXT,
|
||||
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
|
||||
)
|
||||
''')
|
||||
|
||||
# ========== FAQ 建议表 ==========
|
||||
cursor.execute('''
|
||||
CREATE TABLE IF NOT EXISTS faq_suggestions (
|
||||
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
||||
query TEXT NOT NULL,
|
||||
answer TEXT,
|
||||
frequency INTEGER DEFAULT 1,
|
||||
avg_rating REAL DEFAULT 0,
|
||||
status TEXT DEFAULT 'pending',
|
||||
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
|
||||
)
|
||||
''')
|
||||
|
||||
cursor.execute('''
|
||||
CREATE INDEX IF NOT EXISTS idx_faq_suggestion_status
|
||||
ON faq_suggestions(status)
|
||||
''')
|
||||
|
||||
logger.info(f"初始化数据库: {DB_PATHS['feedback']} (feedback.db)")
|
||||
|
||||
|
||||
def _init_session_db():
|
||||
"""初始化 session.db（会话管理数据库 - 仅开发模式使用）"""
|
||||
with get_connection("session", row_factory=False) as conn:
|
||||
cursor = conn.cursor()
|
||||
|
||||
# ========== 会话表 ==========
|
||||
cursor.execute('''
|
||||
CREATE TABLE IF NOT EXISTS sessions (
|
||||
session_id TEXT PRIMARY KEY,
|
||||
user_id TEXT NOT NULL,
|
||||
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
|
||||
last_active TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
|
||||
metadata TEXT
|
||||
)
|
||||
''')
|
||||
|
||||
cursor.execute('''
|
||||
CREATE INDEX IF NOT EXISTS idx_sessions_user
|
||||
ON sessions(user_id)
|
||||
''')
|
||||
|
||||
# ========== 消息表 ==========
|
||||
cursor.execute('''
|
||||
CREATE TABLE IF NOT EXISTS messages (
|
||||
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
||||
session_id TEXT NOT NULL,
|
||||
role TEXT NOT NULL,
|
||||
content TEXT NOT NULL,
|
||||
metadata TEXT,
|
||||
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
|
||||
FOREIGN KEY (session_id) REFERENCES sessions(session_id) ON DELETE CASCADE
|
||||
)
|
||||
''')
|
||||
|
||||
cursor.execute('''
|
||||
CREATE INDEX IF NOT EXISTS idx_messages_session
|
||||
ON messages(session_id, created_at)
|
||||
''')
|
||||
|
||||
# ========== 审计日志表 ==========
|
||||
cursor.execute('''
|
||||
CREATE TABLE IF NOT EXISTS audit_logs (
|
||||
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
||||
user_id TEXT NOT NULL,
|
||||
username TEXT DEFAULT '',
|
||||
action TEXT NOT NULL,
|
||||
query TEXT,
|
||||
result_summary TEXT,
|
||||
sources TEXT,
|
||||
role TEXT,
|
||||
department TEXT,
|
||||
ip_address TEXT,
|
||||
duration_ms INTEGER,
|
||||
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
|
||||
)
|
||||
''')
|
||||
|
||||
cursor.execute('''
|
||||
CREATE INDEX IF NOT EXISTS idx_audit_user
|
||||
ON audit_logs(user_id, created_at)
|
||||
''')
|
||||
|
||||
cursor.execute('''
|
||||
CREATE INDEX IF NOT EXISTS idx_audit_action
|
||||
ON audit_logs(action, created_at)
|
||||
''')
|
||||
|
||||
cursor.execute('''
|
||||
CREATE INDEX IF NOT EXISTS idx_audit_created
|
||||
ON audit_logs(created_at)
|
||||
''')
|
||||
|
||||
logger.info(f"初始化数据库: {DB_PATHS['session']} (session.db)")
|
||||
|
||||
|
||||
def _init_knowledge_db():
|
||||
"""初始化 knowledge.db（知识管理数据库）"""
|
||||
with get_connection("knowledge", row_factory=False) as conn:
|
||||
cursor = conn.cursor()
|
||||
|
||||
# ========== 文档哈希表 ==========
|
||||
cursor.execute('''
|
||||
CREATE TABLE IF NOT EXISTS document_hashes (
|
||||
document_id TEXT PRIMARY KEY,
|
||||
document_name TEXT,
|
||||
content_hash TEXT,
|
||||
file_size INTEGER,
|
||||
last_modified TIMESTAMP,
|
||||
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
|
||||
updated_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
|
||||
)
|
||||
''')
|
||||
|
||||
# ========== 变更日志表 ==========
|
||||
cursor.execute('''
|
||||
CREATE TABLE IF NOT EXISTS change_logs (
|
||||
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
||||
document_id TEXT,
|
||||
document_name TEXT,
|
||||
change_type TEXT,
|
||||
old_hash TEXT,
|
||||
new_hash TEXT,
|
||||
change_time TIMESTAMP,
|
||||
processed INTEGER DEFAULT 0,
|
||||
error_message TEXT,
|
||||
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
|
||||
)
|
||||
''')
|
||||
|
||||
cursor.execute('''
|
||||
CREATE INDEX IF NOT EXISTS idx_change_logs_time
|
||||
ON change_logs(change_time)
|
||||
''')
|
||||
|
||||
cursor.execute('''
|
||||
CREATE INDEX IF NOT EXISTS idx_change_logs_processed
|
||||
ON change_logs(processed)
|
||||
''')
|
||||
|
||||
# ========== 同步状态表 ==========
|
||||
cursor.execute('''
|
||||
CREATE TABLE IF NOT EXISTS sync_status (
|
||||
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
||||
sync_type TEXT,
|
||||
status TEXT,
|
||||
start_time TIMESTAMP,
|
||||
end_time TIMESTAMP,
|
||||
documents_processed INTEGER,
|
||||
documents_added INTEGER,
|
||||
documents_modified INTEGER,
|
||||
documents_deleted INTEGER,
|
||||
error_message TEXT,
|
||||
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
|
||||
)
|
||||
''')
|
||||
|
||||
# ========== 纲要缓存表 ==========
|
||||
cursor.execute('''
|
||||
CREATE TABLE IF NOT EXISTS outline_cache (
|
||||
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
||||
document_id TEXT NOT NULL UNIQUE,
|
||||
document_name TEXT,
|
||||
total_pages INTEGER DEFAULT 0,
|
||||
content_hash TEXT NOT NULL,
|
||||
outline_json TEXT NOT NULL,
|
||||
generated_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
|
||||
)
|
||||
''')
|
||||
|
||||
cursor.execute('''
|
||||
CREATE INDEX IF NOT EXISTS idx_outline_doc
|
||||
ON outline_cache(document_id)
|
||||
''')
|
||||
|
||||
# ========== 文档向量缓存表 ==========
|
||||
cursor.execute('''
|
||||
CREATE TABLE IF NOT EXISTS document_vectors (
|
||||
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
||||
document_id TEXT NOT NULL UNIQUE,
|
||||
document_name TEXT,
|
||||
vector_hash TEXT,
|
||||
vector_json TEXT NOT NULL,
|
||||
tags_json TEXT,
|
||||
updated_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
|
||||
)
|
||||
''')
|
||||
|
||||
cursor.execute('''
|
||||
CREATE INDEX IF NOT EXISTS idx_vector_doc
|
||||
ON document_vectors(document_id)
|
||||
''')
|
||||
|
||||
# ========== 推荐缓存表 ==========
|
||||
cursor.execute('''
|
||||
CREATE TABLE IF NOT EXISTS recommendation_cache (
|
||||
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
||||
document_id TEXT NOT NULL,
|
||||
recommendations_json TEXT NOT NULL,
|
||||
generated_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
|
||||
)
|
||||
''')
|
||||
|
||||
# ========== 文档版本表（统一结构） ==========
|
||||
cursor.execute('''
|
||||
CREATE TABLE IF NOT EXISTS document_versions (
|
||||
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
||||
document_id TEXT NOT NULL,
|
||||
collection TEXT,
|
||||
version TEXT NOT NULL DEFAULT 'v1',
|
||||
content_hash TEXT,
|
||||
status TEXT NOT NULL DEFAULT 'active',
|
||||
effective_date DATE,
|
||||
expiry_date DATE,
|
||||
deprecated_date DATETIME,
|
||||
deprecated_reason TEXT,
|
||||
deprecated_by TEXT,
|
||||
change_summary TEXT,
|
||||
changed_sections TEXT,
|
||||
supersedes TEXT,
|
||||
chunk_count INTEGER DEFAULT 0,
|
||||
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
|
||||
created_by TEXT,
|
||||
UNIQUE(document_id, collection, version)
|
||||
)
|
||||
''')
|
||||
|
||||
# ========== 版本变更日志表 ==========
|
||||
cursor.execute('''
|
||||
CREATE TABLE IF NOT EXISTS version_change_logs (
|
||||
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
||||
document_id TEXT NOT NULL,
|
||||
collection TEXT,
|
||||
old_version TEXT,
|
||||
new_version TEXT,
|
||||
old_status TEXT,
|
||||
new_status TEXT,
|
||||
change_type TEXT NOT NULL,
|
||||
reason TEXT,
|
||||
changed_by TEXT,
|
||||
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
|
||||
)
|
||||
''')
|
||||
|
||||
# 添加性能优化索引
|
||||
cursor.execute('''
|
||||
CREATE INDEX IF NOT EXISTS idx_document_versions_status
|
||||
ON document_versions(document_id, collection, status)
|
||||
''')
|
||||
|
||||
cursor.execute('''
|
||||
CREATE INDEX IF NOT EXISTS idx_version_change_logs_document
|
||||
ON version_change_logs(document_id, collection, created_at DESC)
|
||||
''')
|
||||
|
||||
logger.info(f"初始化数据库: {DB_PATHS['knowledge']} (knowledge.db)")
|
||||
|
||||
|
||||
def _init_exam_db():
|
||||
"""初始化 exam.db（出题系统数据库）"""
|
||||
with get_connection("exam", row_factory=False) as conn:
|
||||
cursor = conn.cursor()
|
||||
|
||||
# ========== 题目表 ==========
|
||||
cursor.execute('''
|
||||
CREATE TABLE IF NOT EXISTS questions (
|
||||
id TEXT PRIMARY KEY,
|
||||
question_type TEXT NOT NULL,
|
||||
content TEXT NOT NULL,
|
||||
options TEXT,
|
||||
correct_answer TEXT NOT NULL,
|
||||
analysis TEXT,
|
||||
knowledge_points TEXT,
|
||||
difficulty INTEGER DEFAULT 3,
|
||||
score INTEGER NOT NULL,
|
||||
source_file TEXT NOT NULL,
|
||||
source_collection TEXT NOT NULL,
|
||||
source_snippet TEXT,
|
||||
source_hash TEXT,
|
||||
status TEXT DEFAULT 'approved',
|
||||
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
|
||||
created_by TEXT,
|
||||
updated_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
|
||||
)
|
||||
''')
|
||||
|
||||
cursor.execute('''
|
||||
CREATE INDEX IF NOT EXISTS idx_questions_source
|
||||
ON questions(source_file)
|
||||
''')
|
||||
|
||||
# ========== 试卷表 ==========
|
||||
cursor.execute('''
|
||||
CREATE TABLE IF NOT EXISTS exams (
|
||||
id TEXT PRIMARY KEY,
|
||||
name TEXT NOT NULL,
|
||||
description TEXT,
|
||||
total_score INTEGER NOT NULL,
|
||||
total_count INTEGER NOT NULL,
|
||||
duration INTEGER DEFAULT 60,
|
||||
status TEXT DEFAULT 'published',
|
||||
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
|
||||
created_by TEXT
|
||||
)
|
||||
''')
|
||||
|
||||
# ========== 试卷题目关联表 ==========
|
||||
cursor.execute('''
|
||||
CREATE TABLE IF NOT EXISTS exam_questions (
|
||||
exam_id TEXT NOT NULL,
|
||||
question_id TEXT NOT NULL,
|
||||
question_order INTEGER NOT NULL,
|
||||
PRIMARY KEY (exam_id, question_id),
|
||||
FOREIGN KEY (exam_id) REFERENCES exams(id) ON DELETE CASCADE,
|
||||
FOREIGN KEY (question_id) REFERENCES questions(id) ON DELETE CASCADE
|
||||
)
|
||||
''')
|
||||
|
||||
# ========== 学生答卷表（只存 student_id） ==========
|
||||
cursor.execute('''
|
||||
CREATE TABLE IF NOT EXISTS student_answers (
|
||||
id TEXT PRIMARY KEY,
|
||||
exam_id TEXT NOT NULL,
|
||||
student_id TEXT NOT NULL,
|
||||
question_id TEXT NOT NULL,
|
||||
question_type TEXT NOT NULL,
|
||||
student_answer TEXT NOT NULL,
|
||||
score REAL DEFAULT 0,
|
||||
max_score INTEGER NOT NULL,
|
||||
feedback TEXT,
|
||||
score_details TEXT,
|
||||
submitted_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
|
||||
graded_at TIMESTAMP,
|
||||
FOREIGN KEY (exam_id) REFERENCES exams(id) ON DELETE CASCADE,
|
||||
FOREIGN KEY (question_id) REFERENCES questions(id) ON DELETE CASCADE
|
||||
)
|
||||
''')
|
||||
|
||||
cursor.execute('''
|
||||
CREATE INDEX IF NOT EXISTS idx_student_answers_exam
|
||||
ON student_answers(exam_id, student_id)
|
||||
''')
|
||||
|
||||
# ========== 批阅报告表（只存 student_id） ==========
|
||||
cursor.execute('''
|
||||
CREATE TABLE IF NOT EXISTS grade_reports (
|
||||
id TEXT PRIMARY KEY,
|
||||
exam_id TEXT NOT NULL,
|
||||
student_id TEXT NOT NULL,
|
||||
total_score REAL NOT NULL,
|
||||
max_score REAL NOT NULL,
|
||||
score_rate REAL,
|
||||
analysis TEXT,
|
||||
graded_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
|
||||
FOREIGN KEY (exam_id) REFERENCES exams(id) ON DELETE CASCADE
|
||||
)
|
||||
''')
|
||||
|
||||
# ========== 题目-制度关联表 ==========
|
||||
cursor.execute('''
|
||||
CREATE TABLE IF NOT EXISTS question_document_links (
|
||||
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
||||
question_id TEXT NOT NULL,
|
||||
question_type TEXT NOT NULL,
|
||||
exam_id TEXT NOT NULL,
|
||||
document_id TEXT NOT NULL,
|
||||
document_name TEXT,
|
||||
chapter TEXT,
|
||||
key_points TEXT,
|
||||
relevance_score REAL DEFAULT 0,
|
||||
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
|
||||
)
|
||||
''')
|
||||
|
||||
cursor.execute('''
|
||||
CREATE INDEX IF NOT EXISTS idx_qdl_question
|
||||
ON question_document_links(question_id)
|
||||
''')
|
||||
|
||||
cursor.execute('''
|
||||
CREATE INDEX IF NOT EXISTS idx_qdl_document
|
||||
ON question_document_links(document_id)
|
||||
''')
|
||||
|
||||
# ========== 知识点表 ==========
|
||||
cursor.execute('''
|
||||
CREATE TABLE IF NOT EXISTS knowledge_points (
|
||||
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
||||
name TEXT NOT NULL UNIQUE,
|
||||
category TEXT,
|
||||
description TEXT,
|
||||
parent_id INTEGER,
|
||||
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
|
||||
FOREIGN KEY (parent_id) REFERENCES knowledge_points(id)
|
||||
)
|
||||
''')
|
||||
|
||||
# ========== 题目-知识点关联表 ==========
|
||||
cursor.execute('''
|
||||
CREATE TABLE IF NOT EXISTS question_knowledge_links (
|
||||
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
||||
question_id TEXT NOT NULL,
|
||||
question_type TEXT NOT NULL,
|
||||
exam_id TEXT NOT NULL,
|
||||
knowledge_point_id INTEGER NOT NULL,
|
||||
knowledge_point_name TEXT,
|
||||
weight REAL DEFAULT 1.0,
|
||||
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
|
||||
FOREIGN KEY (knowledge_point_id) REFERENCES knowledge_points(id)
|
||||
)
|
||||
''')
|
||||
|
||||
cursor.execute('''
|
||||
CREATE INDEX IF NOT EXISTS idx_qkl_question
|
||||
ON question_knowledge_links(question_id)
|
||||
''')
|
||||
|
||||
cursor.execute('''
|
||||
CREATE INDEX IF NOT EXISTS idx_qkl_knowledge
|
||||
ON question_knowledge_links(knowledge_point_id)
|
||||
''')
|
||||
|
||||
# ========== 题目状态表 ==========
|
||||
cursor.execute('''
|
||||
CREATE TABLE IF NOT EXISTS question_status (
|
||||
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
||||
question_id TEXT NOT NULL UNIQUE,
|
||||
question_type TEXT NOT NULL,
|
||||
exam_id TEXT NOT NULL,
|
||||
status TEXT DEFAULT 'approved',
|
||||
affected_by TEXT,
|
||||
affect_reason TEXT,
|
||||
updated_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
|
||||
)
|
||||
''')
|
||||
|
||||
cursor.execute('''
|
||||
CREATE INDEX IF NOT EXISTS idx_qs_status
|
||||
ON question_status(status)
|
||||
''')
|
||||
|
||||
# ========== 整卷分析报告表 ==========
|
||||
cursor.execute('''
|
||||
CREATE TABLE IF NOT EXISTS exam_analysis_reports (
|
||||
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
||||
report_id TEXT NOT NULL UNIQUE,
|
||||
exam_id TEXT,
|
||||
exam_name TEXT,
|
||||
student_id TEXT,
|
||||
total_score REAL,
|
||||
max_score REAL,
|
||||
score_rate REAL,
|
||||
type_scores TEXT,
|
||||
knowledge_analysis TEXT,
|
||||
weak_points TEXT,
|
||||
strong_points TEXT,
|
||||
ai_comment TEXT,
|
||||
study_suggestions TEXT,
|
||||
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
|
||||
)
|
||||
''')
|
||||
|
||||
# ========== 新题建议表 ==========
|
||||
cursor.execute('''
|
||||
CREATE TABLE IF NOT EXISTS question_suggestions (
|
||||
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
||||
document_id TEXT NOT NULL,
|
||||
suggestion TEXT,
|
||||
status TEXT DEFAULT 'pending',
|
||||
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
|
||||
)
|
||||
''')
|
||||
|
||||
logger.info(f"初始化数据库: {DB_PATHS['exam']} (exam.db)")
|
||||
|
||||
|
||||
# ==================== 工具函数 ====================
|
||||
|
||||
def row_to_dict(row: sqlite3.Row) -> Dict:
|
||||
"""将 sqlite3.Row 转换为字典"""
|
||||
if row is None:
|
||||
return {}
|
||||
return dict(row)
|
||||
|
||||
|
||||
def rows_to_list(rows: List[sqlite3.Row]) -> List[Dict]:
|
||||
"""将 sqlite3.Row 列表转换为字典列表"""
|
||||
return [row_to_dict(row) for row in rows]
|
||||
|
||||
|
||||
def json_parse(value: str, default=None):
|
||||
"""安全解析 JSON 字符串"""
|
||||
if not value:
|
||||
return default
|
||||
try:
|
||||
return json.loads(value)
|
||||
except (json.JSONDecodeError, TypeError):
|
||||
return default
|
||||
|
||||
|
||||
def json_stringify(value, ensure_ascii: bool = False) -> str:
|
||||
"""将对象转换为 JSON 字符串"""
|
||||
if value is None:
|
||||
return None
|
||||
return json.dumps(value, ensure_ascii=ensure_ascii)
|
||||
|
||||
|
||||
def get_db_stats() -> Dict:
|
||||
"""获取所有数据库的统计信息"""
|
||||
stats = {}
|
||||
|
||||
for db_name, db_path in DB_PATHS.items():
|
||||
if os.path.exists(db_path):
|
||||
file_size = os.path.getsize(db_path)
|
||||
|
||||
with get_connection(db_name, row_factory=False) as conn:
|
||||
cursor = conn.cursor()
|
||||
|
||||
# 获取所有表名
|
||||
cursor.execute(
|
||||
"SELECT name FROM sqlite_master WHERE type='table' ORDER BY name"
|
||||
)
|
||||
tables = [row[0] for row in cursor.fetchall()]
|
||||
|
||||
# 统计每个表的行数
|
||||
table_counts = {}
|
||||
for table in tables:
|
||||
cursor.execute(f"SELECT COUNT(*) FROM {table}")
|
||||
table_counts[table] = cursor.fetchone()[0]
|
||||
|
||||
stats[db_name] = {
|
||||
"path": db_path,
|
||||
"name": DB_NAMES.get(db_name, db_name),
|
||||
"file_size": file_size,
|
||||
"tables": table_counts,
|
||||
"total_rows": sum(table_counts.values())
|
||||
}
|
||||
else:
|
||||
stats[db_name] = {
|
||||
"path": db_path,
|
||||
"name": DB_NAMES.get(db_name, db_name),
|
||||
"exists": False
|
||||
}
|
||||
|
||||
return stats
|
||||
|
||||
|
||||
# ==================== 自动初始化 ====================
|
||||
|
||||
# 模块加载时不自动初始化，由调用方决定何时初始化
|
||||
# 这样可以避免在 import 时创建数据库文件
|
||||
Reference in New Issue
Block a user